From e41c87e9e917ca2fb05f286cde3b1ae2f4ce0aaa Mon Sep 17 00:00:00 2001 From: openhands Date: Wed, 13 Nov 2024 14:01:33 +0000 Subject: [PATCH 01/27] Integrate OpenHands resolver into main repository 1. Move resolver code from openhands-resolver repo into openhands/resolver/ 2. Move tests into tests/unit/resolver/ 3. Update GitHub workflow to use integrated resolver 4. Update imports to reflect new package structure --- .github/workflows/openhands-resolver.yml | 243 +++- openhands/resolver/README.md | 182 +++ openhands/resolver/__init__.py | 1 + openhands/resolver/github_issue.py | 21 + openhands/resolver/io_utils.py | 16 + openhands/resolver/issue_definitions.py | 604 ++++++++++ openhands/resolver/patching/README.md | 4 + openhands/resolver/patching/__init__.py | 6 + openhands/resolver/patching/apply.py | 120 ++ openhands/resolver/patching/exceptions.py | 31 + openhands/resolver/patching/patch.py | 1007 ++++++++++++++++ openhands/resolver/patching/snippets.py | 60 + .../guess_success/issue-success-check.jinja | 18 + .../guess_success/pr-feedback-check.jinja | 24 + .../guess_success/pr-review-check.jinja | 21 + .../guess_success/pr-thread-check.jinja | 21 + .../all-hands-ai___openhands-resolver.txt | 4 + .../all-hands-ai___openhands.txt | 7 + .../repo_instructions/rbren___rss-parser.txt | 4 + .../prompts/resolve/basic-followup.jinja | 24 + .../prompts/resolve/basic-with-tests.jinja | 17 + .../resolver/prompts/resolve/basic.jinja | 13 + .../prompts/resolve/pr-changes-summary.jinja | 3 + openhands/resolver/resolve_all_issues.py | 383 ++++++ openhands/resolver/resolve_issue.py | 609 ++++++++++ openhands/resolver/resolver_output.py | 18 + openhands/resolver/send_pull_request.py | 623 ++++++++++ openhands/resolver/utils.py | 141 +++ .../resolver/visualize_resolver_output.py | 42 + tests/unit/resolver/mock_output/output.jsonl | 2 + .../resolver/mock_output/repo/src/App.css | 42 + .../resolver/mock_output/repo/src/App.tsx | 14 + .../repo/src/PullRequestViewer.test.tsx | 19 + .../repo/src/PullRequestViewer.tsx | 112 ++ tests/unit/resolver/test_guess_success.py | 66 ++ tests/unit/resolver/test_issue_handler.py | 644 ++++++++++ .../resolver/test_pr_handler_guess_success.py | 393 ++++++ tests/unit/resolver/test_pr_title_escaping.py | 148 +++ tests/unit/resolver/test_resolve_issues.py | 786 ++++++++++++ tests/unit/resolver/test_send_pull_request.py | 1056 +++++++++++++++++ tests/unit/resolver/test_version.py | 20 + 41 files changed, 7562 insertions(+), 7 deletions(-) create mode 100644 openhands/resolver/README.md create mode 100644 openhands/resolver/__init__.py create mode 100644 openhands/resolver/github_issue.py create mode 100644 openhands/resolver/io_utils.py create mode 100644 openhands/resolver/issue_definitions.py create mode 100644 openhands/resolver/patching/README.md create mode 100644 openhands/resolver/patching/__init__.py create mode 100644 openhands/resolver/patching/apply.py create mode 100644 openhands/resolver/patching/exceptions.py create mode 100644 openhands/resolver/patching/patch.py create mode 100644 openhands/resolver/patching/snippets.py create mode 100644 openhands/resolver/prompts/guess_success/issue-success-check.jinja create mode 100644 openhands/resolver/prompts/guess_success/pr-feedback-check.jinja create mode 100644 openhands/resolver/prompts/guess_success/pr-review-check.jinja create mode 100644 openhands/resolver/prompts/guess_success/pr-thread-check.jinja create mode 100644 openhands/resolver/prompts/repo_instructions/all-hands-ai___openhands-resolver.txt create mode 100644 openhands/resolver/prompts/repo_instructions/all-hands-ai___openhands.txt create mode 100644 openhands/resolver/prompts/repo_instructions/rbren___rss-parser.txt create mode 100644 openhands/resolver/prompts/resolve/basic-followup.jinja create mode 100644 openhands/resolver/prompts/resolve/basic-with-tests.jinja create mode 100644 openhands/resolver/prompts/resolve/basic.jinja create mode 100644 openhands/resolver/prompts/resolve/pr-changes-summary.jinja create mode 100644 openhands/resolver/resolve_all_issues.py create mode 100644 openhands/resolver/resolve_issue.py create mode 100644 openhands/resolver/resolver_output.py create mode 100644 openhands/resolver/send_pull_request.py create mode 100644 openhands/resolver/utils.py create mode 100644 openhands/resolver/visualize_resolver_output.py create mode 100644 tests/unit/resolver/mock_output/output.jsonl create mode 100644 tests/unit/resolver/mock_output/repo/src/App.css create mode 100644 tests/unit/resolver/mock_output/repo/src/App.tsx create mode 100644 tests/unit/resolver/mock_output/repo/src/PullRequestViewer.test.tsx create mode 100644 tests/unit/resolver/mock_output/repo/src/PullRequestViewer.tsx create mode 100644 tests/unit/resolver/test_guess_success.py create mode 100644 tests/unit/resolver/test_issue_handler.py create mode 100644 tests/unit/resolver/test_pr_handler_guess_success.py create mode 100644 tests/unit/resolver/test_pr_title_escaping.py create mode 100644 tests/unit/resolver/test_resolve_issues.py create mode 100644 tests/unit/resolver/test_send_pull_request.py create mode 100644 tests/unit/resolver/test_version.py diff --git a/.github/workflows/openhands-resolver.yml b/.github/workflows/openhands-resolver.yml index 3adf543cc2b5..117d0325d862 100644 --- a/.github/workflows/openhands-resolver.yml +++ b/.github/workflows/openhands-resolver.yml @@ -1,15 +1,244 @@ -name: Resolve Issues with OpenHands +name: Auto-Fix Tagged Issue with OpenHands on: + workflow_call: + inputs: + max_iterations: + required: false + type: number + default: 50 + macro: + required: false + type: string + default: "@openhands-agent" + secrets: + LLM_MODEL: + required: true + LLM_API_KEY: + required: true + LLM_BASE_URL: + required: false + PAT_TOKEN: + required: true + PAT_USERNAME: + required: true + issues: types: [labeled] pull_request: types: [labeled] + issue_comment: + types: [created] + pull_request_review_comment: + types: [created] + pull_request_review: + types: [submitted] + +permissions: + contents: write + pull-requests: write + issues: write jobs: - call-openhands-resolver: - uses: All-Hands-AI/openhands-resolver/.github/workflows/openhands-resolver.yml@main - if: github.event.label.name == 'fix-me' - with: - max_iterations: 50 - secrets: inherit + auto-fix: + if: | + github.event_name == 'workflow_call' || + github.event.label.name == 'fix-me' || + github.event.label.name == 'fix-me-experimental' || + + ( + ((github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment') && + startsWith(github.event.comment.body, inputs.macro || '@openhands-agent') && + (github.event.comment.author_association == 'OWNER' || github.event.comment.author_association == 'COLLABORATOR' || github.event.comment.author_association == 'MEMBER') + ) || + + (github.event_name == 'pull_request_review' && + startsWith(github.event.review.body, inputs.macro || '@openhands-agent') && + (github.event.review.author_association == 'OWNER' || github.event.review.author_association == 'COLLABORATOR' || github.event.review.author_association == 'MEMBER') + ) + ) + runs-on: ubuntu-latest + steps: + - name: Checkout repository + uses: actions/checkout@v4 + + - name: Set up Python + uses: actions/setup-python@v5 + with: + python-version: "3.12" + + - name: Check required environment variables + env: + LLM_MODEL: ${{ secrets.LLM_MODEL }} + LLM_API_KEY: ${{ secrets.LLM_API_KEY }} + LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }} + PAT_TOKEN: ${{ secrets.PAT_TOKEN }} + PAT_USERNAME: ${{ secrets.PAT_USERNAME }} + run: | + required_vars=("LLM_MODEL" "LLM_API_KEY" "PAT_TOKEN" "PAT_USERNAME") + for var in "${required_vars[@]}"; do + if [ -z "${!var}" ]; then + echo "Error: Required environment variable $var is not set." + exit 1 + fi + done + + - name: Set environment variables + run: | + if [ -n "${{ github.event.review.body }}" ]; then + echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV + echo "ISSUE_TYPE=pr" >> $GITHUB_ENV + elif [ -n "${{ github.event.issue.pull_request }}" ]; then + echo "ISSUE_NUMBER=${{ github.event.issue.number }}" >> $GITHUB_ENV + echo "ISSUE_TYPE=pr" >> $GITHUB_ENV + elif [ -n "${{ github.event.pull_request.number }}" ]; then + echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV + echo "ISSUE_TYPE=pr" >> $GITHUB_ENV + else + echo "ISSUE_NUMBER=${{ github.event.issue.number }}" >> $GITHUB_ENV + echo "ISSUE_TYPE=issue" >> $GITHUB_ENV + fi + + if [ -n "${{ github.event.review.body }}" ]; then + echo "COMMENT_ID=${{ github.event.review.id || 'None' }}" >> $GITHUB_ENV + else + echo "COMMENT_ID=${{ github.event.comment.id || 'None' }}" >> $GITHUB_ENV + fi + + echo "MAX_ITERATIONS=${{ inputs.max_iterations || 50 }}" >> $GITHUB_ENV + echo "SANDBOX_ENV_GITHUB_TOKEN=${{ secrets.GITHUB_TOKEN }}" >> $GITHUB_ENV + + - name: Comment on issue with start message + uses: actions/github-script@v7 + with: + github-token: ${{secrets.GITHUB_TOKEN}} + script: | + const issueType = process.env.ISSUE_TYPE; + github.rest.issues.createComment({ + issue_number: ${{ env.ISSUE_NUMBER }}, + owner: context.repo.owner, + repo: context.repo.repo, + body: `OpenHands started fixing the ${issueType}! You can monitor the progress [here](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}).` + }); + + - name: Install OpenHands + run: | + python -m pip install --upgrade pip + pip install -e . + + - name: Attempt to resolve issue + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + LLM_MODEL: ${{ secrets.LLM_MODEL }} + LLM_API_KEY: ${{ secrets.LLM_API_KEY }} + LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }} + PYTHONPATH: "" + run: | + cd /tmp && python -m openhands.resolver.resolve_issue \ + --repo ${{ github.repository }} \ + --issue-number ${{ env.ISSUE_NUMBER }} \ + --issue-type ${{ env.ISSUE_TYPE }} \ + --max-iterations ${{ env.MAX_ITERATIONS }} \ + --comment-id ${{ env.COMMENT_ID }} + + - name: Check resolution result + id: check_result + run: | + if cd /tmp && grep -q '"success":true' output/output.jsonl; then + echo "RESOLUTION_SUCCESS=true" >> $GITHUB_OUTPUT + else + echo "RESOLUTION_SUCCESS=false" >> $GITHUB_OUTPUT + fi + + - name: Upload output.jsonl as artifact + uses: actions/upload-artifact@v4 + if: always() # Upload even if the previous steps fail + with: + name: resolver-output + path: /tmp/output/output.jsonl + retention-days: 30 # Keep the artifact for 30 days + + - name: Create draft PR or push branch + env: + GITHUB_TOKEN: ${{ secrets.PAT_TOKEN }} + LLM_MODEL: ${{ secrets.LLM_MODEL }} + LLM_API_KEY: ${{ secrets.LLM_API_KEY }} + LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }} + PYTHONPATH: "" + run: | + if [ "${{ steps.check_result.outputs.RESOLUTION_SUCCESS }}" == "true" ]; then + cd /tmp && python -m openhands.resolver.send_pull_request \ + --issue-number ${{ env.ISSUE_NUMBER }} \ + --pr-type draft | tee pr_result.txt && \ + grep "draft created" pr_result.txt | sed 's/.*\///g' > pr_number.txt + else + cd /tmp && python -m openhands.resolver.send_pull_request \ + --issue-number ${{ env.ISSUE_NUMBER }} \ + --pr-type branch \ + --send-on-failure | tee branch_result.txt && \ + grep "branch created" branch_result.txt | sed 's/.*\///g; s/.expand=1//g' > branch_name.txt + fi + + - name: Comment on issue + uses: actions/github-script@v7 + with: + github-token: ${{secrets.GITHUB_TOKEN}} + script: | + const fs = require('fs'); + const issueNumber = ${{ env.ISSUE_NUMBER }}; + const success = ${{ steps.check_result.outputs.RESOLUTION_SUCCESS }}; + + let prNumber = ''; + let branchName = ''; + let logContent = ''; + const noChangesMessage = `No changes to commit for issue #${issueNumber}. Skipping commit.`; + + try { + if (success){ + logContent = fs.readFileSync('/tmp/pr_result.txt', 'utf8').trim(); + } else { + logContent = fs.readFileSync('/tmp/branch_result.txt', 'utf8').trim(); + } + } catch (error) { + console.error('Error reading results file:', error); + } + + try { + if (success) { + prNumber = fs.readFileSync('/tmp/pr_number.txt', 'utf8').trim(); + } else { + branchName = fs.readFileSync('/tmp/branch_name.txt', 'utf8').trim(); + } + } catch (error) { + console.error('Error reading file:', error); + } + + if (logContent.includes(noChangesMessage)) { + github.rest.issues.createComment({ + issue_number: issueNumber, + owner: context.repo.owner, + repo: context.repo.repo, + body: `The workflow to fix this issue encountered an error. Openhands failed to create any code changes.` + }); + } else if (success && prNumber) { + github.rest.issues.createComment({ + issue_number: issueNumber, + owner: context.repo.owner, + repo: context.repo.repo, + body: `A potential fix has been generated and a draft PR #${prNumber} has been created. Please review the changes.` + }); + } else if (!success && branchName) { + github.rest.issues.createComment({ + issue_number: issueNumber, + owner: context.repo.owner, + repo: context.repo.repo, + body: `An attempt was made to automatically fix this issue, but it was unsuccessful. A branch named '${branchName}' has been created with the attempted changes. You can view the branch [here](https://github.com/${context.repo.owner}/${context.repo.repo}/tree/${branchName}). Manual intervention may be required.` + }); + } else { + github.rest.issues.createComment({ + issue_number: issueNumber, + owner: context.repo.owner, + repo: context.repo.repo, + body: `The workflow to fix this issue encountered an error. Please check the workflow logs for more information.` + }); + } diff --git a/openhands/resolver/README.md b/openhands/resolver/README.md new file mode 100644 index 000000000000..30984acc0e85 --- /dev/null +++ b/openhands/resolver/README.md @@ -0,0 +1,182 @@ +# OpenHands Github Issue Resolver 🙌 + +Need help resolving a GitHub issue but don't have the time to do it yourself? Let an AI agent help you out! + +This tool allows you to use open-source AI agents based on [OpenHands](https://github.com/all-hands-ai/openhands) +to attempt to resolve GitHub issues automatically. While it can handle multiple issues, it's primarily designed +to help you resolve one issue at a time with high quality. + +Getting started is simple - just follow the instructions below. + +## Using the GitHub Actions Workflow + +This repository includes a GitHub Actions workflow that can automatically attempt to fix individual issues labeled with 'fix-me'. +Follow these steps to use this workflow in your own repository: + +1. [Create a personal access token](https://github.com/settings/tokens?type=beta) with read/write scope for "contents", "issues", "pull requests", and "workflows" + +2. Create an API key for the [Claude API](https://www.anthropic.com/api) (recommended) or another supported LLM service + +3. Copy `examples/openhands-resolver.yml` to your repository's `.github/workflows/` directory + +4. Configure repository permissions: + - Go to `Settings -> Actions -> General -> Workflow permissions` + - Select "Read and write permissions" + - Enable "Allow Github Actions to create and approve pull requests" + + Note: If the "Read and write permissions" option is greyed out: + - First check if permissions need to be set at the organization level + - If still greyed out at the organization level, permissions need to be set in the [Enterprise policy settings](https://docs.github.com/en/enterprise-cloud@latest/admin/enforcing-policies/enforcing-policies-for-your-enterprise/enforcing-policies-for-github-actions-in-your-enterprise#enforcing-a-policy-for-workflow-permissions-in-your-enterprise) + +5. Set up [GitHub secrets](https://docs.github.com/en/actions/security-for-github-actions/security-guides/using-secrets-in-github-actions): + - Required: + - `PAT_USERNAME`: GitHub username for the personal access token + - `PAT_TOKEN`: The personal access token + - `LLM_MODEL`: LLM model to use (e.g., "anthropic/claude-3-5-sonnet-20241022") + - `LLM_API_KEY`: Your LLM API key + - Optional: + - `LLM_BASE_URL`: Base URL for LLM API (only if using a proxy) + + Note: You can set these secrets at the organization level to use across multiple repositories. + +6. Usage: + There are two ways to trigger the OpenHands agent: + + a. Using the 'fix-me' label: + - Add the 'fix-me' label to any issue you want the AI to resolve + - The agent will consider all comments in the issue thread when resolving + - The workflow will: + 1. Attempt to resolve the issue using OpenHands + 2. Create a draft PR if successful, or push a branch if unsuccessful + 3. Comment on the issue with the results + 4. Remove the 'fix-me' label once processed + + b. Using `@openhands-agent` mention: + - Create a new comment containing `@openhands-agent` in any issue + - The agent will only consider the comment where it's mentioned + - The workflow will: + 1. Attempt to resolve the issue based on the specific comment + 2. Create a draft PR if successful, or push a branch if unsuccessful + 3. Comment on the issue with the results + +Need help? Feel free to [open an issue](https://github.com/all-hands-ai/openhands-resolver/issues) or email us at [contact@all-hands.dev](mailto:contact@all-hands.dev). + +## Manual Installation + +If you prefer to run the resolver programmatically instead of using GitHub Actions, follow these steps: + +1. Install the package: + +```bash +pip install openhands-resolver +``` + +2. Create a GitHub access token: + - Visit [GitHub's token settings](https://github.com/settings/personal-access-tokens/new) + - Create a fine-grained token with these scopes: + - "Content" + - "Pull requests" + - "Issues" + - "Workflows" + - If you don't have push access to the target repo, you can fork it first + +3. Set up environment variables: + +```bash +# GitHub credentials +export GITHUB_TOKEN="your-github-token" +export GITHUB_USERNAME="your-github-username" # Optional, defaults to token owner + +# LLM configuration +export LLM_MODEL="anthropic/claude-3-5-sonnet-20241022" # Recommended +export LLM_API_KEY="your-llm-api-key" +export LLM_BASE_URL="your-api-url" # Optional, for API proxies +``` + +Note: OpenHands works best with powerful models like Anthropic's Claude or OpenAI's GPT-4. While other models are supported, they may not perform as well for complex issue resolution. + +## Resolving Issues + +The resolver can automatically attempt to fix a single issue in your repository using the following command: + +```bash +python -m openhands_resolver.resolve_issue --repo [OWNER]/[REPO] --issue-number [NUMBER] +``` + +For instance, if you want to resolve issue #100 in this repo, you would run: + +```bash +python -m openhands_resolver.resolve_issue --repo all-hands-ai/openhands-resolver --issue-number 100 +``` + +The output will be written to the `output/` directory. + +If you've installed the package from source using poetry, you can use: + +```bash +poetry run python openhands_resolver/resolve_issue.py --repo all-hands-ai/openhands-resolver --issue-number 100 +``` + +For resolving multiple issues at once (e.g., in a batch process), you can use the `resolve_all_issues` command: + +```bash +python -m openhands_resolver.resolve_all_issues --repo [OWNER]/[REPO] --issue-numbers [NUMBERS] +``` + +For example: + +```bash +python -m openhands_resolver.resolve_all_issues --repo all-hands-ai/openhands-resolver --issue-numbers 100,101,102 +``` + +## Responding to PR Comments + +The resolver can also respond to comments on pull requests using: + +```bash +python -m openhands_resolver.send_pull_request --issue-number PR_NUMBER --issue-type pr +``` + +This functionality is available both through the GitHub Actions workflow and when running the resolver locally. + +## Visualizing successful PRs + +To find successful PRs, you can run the following command: + +```bash +grep '"success":true' output/output.jsonl | sed 's/.*\("number":[0-9]*\).*/\1/g' +``` + +Then you can go through and visualize the ones you'd like. + +```bash +python -m openhands_resolver.visualize_resolver_output --issue-number ISSUE_NUMBER --vis-method json +``` + +## Uploading PRs + +If you find any PRs that were successful, you can upload them. +There are three ways you can upload: + +1. `branch` - upload a branch without creating a PR +2. `draft` - create a draft PR +3. `ready` - create a non-draft PR that's ready for review + +```bash +python -m openhands_resolver.send_pull_request --issue-number ISSUE_NUMBER --github-username YOUR_GITHUB_USERNAME --pr-type draft +``` + +If you want to upload to a fork, you can do so by specifying the `fork-owner`: + +```bash +python -m openhands_resolver.send_pull_request --issue-number ISSUE_NUMBER --github-username YOUR_GITHUB_USERNAME --pr-type draft --fork-owner YOUR_GITHUB_USERNAME +``` + +## Providing Custom Instructions + +You can customize how the AI agent approaches issue resolution by adding a `.openhands_instructions` file to the root of your repository. If present, this file's contents will be injected into the prompt for openhands edits. + +## Troubleshooting + +If you have any issues, please open an issue on this github repo, we're happy to help! +Alternatively, you can [email us](mailto:contact@all-hands.dev) or join the [OpenHands Slack workspace](https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA) and ask there. diff --git a/openhands/resolver/__init__.py b/openhands/resolver/__init__.py new file mode 100644 index 000000000000..260c070a890d --- /dev/null +++ b/openhands/resolver/__init__.py @@ -0,0 +1 @@ +__version__ = "0.3.1" diff --git a/openhands/resolver/github_issue.py b/openhands/resolver/github_issue.py new file mode 100644 index 000000000000..1eefb947a95f --- /dev/null +++ b/openhands/resolver/github_issue.py @@ -0,0 +1,21 @@ +from pydantic import BaseModel + + +class ReviewThread(BaseModel): + comment: str + files: list[str] + + +class GithubIssue(BaseModel): + owner: str + repo: str + number: int + title: str + body: str + thread_comments: list[str] | None = None # Added field for issue thread comments + closing_issues: list[str] | None = None + review_comments: list[str] | None = None + review_threads: list[ReviewThread] | None = None + thread_ids: list[str] | None = None + head_branch: str | None = None + diff --git a/openhands/resolver/io_utils.py b/openhands/resolver/io_utils.py new file mode 100644 index 000000000000..41c4ba6c9cfa --- /dev/null +++ b/openhands/resolver/io_utils.py @@ -0,0 +1,16 @@ +import json +from typing import Iterable +from openhands.resolver.resolver_output import ResolverOutput + + +def load_all_resolver_outputs(output_jsonl: str) -> Iterable[ResolverOutput]: + with open(output_jsonl, "r") as f: + for line in f: + yield ResolverOutput.model_validate(json.loads(line)) + + +def load_single_resolver_output(output_jsonl: str, issue_number: int) -> ResolverOutput: + for resolver_output in load_all_resolver_outputs(output_jsonl): + if resolver_output.issue.number == issue_number: + return resolver_output + raise ValueError(f"Issue number {issue_number} not found in {output_jsonl}") diff --git a/openhands/resolver/issue_definitions.py b/openhands/resolver/issue_definitions.py new file mode 100644 index 000000000000..b001ba840d22 --- /dev/null +++ b/openhands/resolver/issue_definitions.py @@ -0,0 +1,604 @@ +import re +import os +from abc import ABC, abstractmethod +from typing import ClassVar, Any +import requests +import litellm +import jinja2 +import json + +from openhands.events.event import Event +from openhands.resolver.github_issue import GithubIssue, ReviewThread +from openhands.core.config import LLMConfig +from openhands.core.logger import openhands_logger as logger + + + +class IssueHandlerInterface(ABC): + issue_type: ClassVar[str] + + @abstractmethod + def get_converted_issues(self, comment_id: int | None = None) -> list[GithubIssue]: + """Download issues from GitHub.""" + pass + + @abstractmethod + def get_instruction(self, issue: GithubIssue, prompt_template: str, repo_instruction: str | None = None) -> tuple[str, list[str]]: + """Generate instruction and image urls for the agent.""" + pass + + @abstractmethod + def guess_success(self, issue: GithubIssue, history: list[Event], llm_config: LLMConfig) -> tuple[bool, list[bool] | None, str]: + """Guess if the issue has been resolved based on the agent's output.""" + pass + + + + +class IssueHandler(IssueHandlerInterface): + issue_type: ClassVar[str] = "issue" + + def __init__(self, owner: str, repo: str, token: str): + self.download_url = "https://api.github.com/repos/{}/{}/issues" + self.owner = owner + self.repo = repo + self.token = token + + def _download_issues_from_github(self) -> list[Any]: + url = self.download_url.format(self.owner, self.repo) + headers = { + "Authorization": f"token {self.token}", + "Accept": "application/vnd.github.v3+json", + } + params: dict[str, int | str] = {"state": "open", "per_page": 100, "page": 1} + all_issues = [] + + while True: + response = requests.get(url, headers=headers, params=params) + response.raise_for_status() + issues = response.json() + + if not issues: + break + + if not isinstance(issues, list) or any( + [not isinstance(issue, dict) for issue in issues] + ): + raise ValueError("Expected list of dictionaries from Github API.") + + all_issues.extend(issues) + assert isinstance(params["page"], int) + params["page"] += 1 + + return all_issues + def _extract_image_urls(self, issue_body: str) -> list[str]: + # Regular expression to match Markdown image syntax ![alt text](image_url) + image_pattern = r'!\[.*?\]\((https?://[^\s)]+)\)' + return re.findall(image_pattern, issue_body) + + def _extract_issue_references(self, body: str) -> list[int]: + pattern = r"#(\d+)" + return [int(match) for match in re.findall(pattern, body)] + + + def _get_issue_comments(self, issue_number: int, comment_id: int | None = None) -> list[str] | None: + """Download comments for a specific issue from Github.""" + url = f"https://api.github.com/repos/{self.owner}/{self.repo}/issues/{issue_number}/comments" + headers = { + "Authorization": f"token {self.token}", + "Accept": "application/vnd.github.v3+json", + } + params = {"per_page": 100, "page": 1} + all_comments = [] + + while True: + response = requests.get(url, headers=headers, params=params) + response.raise_for_status() + comments = response.json() + + if not comments: + break + + if comment_id: + matching_comment = next((comment["body"] for comment in comments if comment["id"] == comment_id), None) + if matching_comment: + return [matching_comment] + else: + all_comments.extend([comment["body"] for comment in comments]) + + params["page"] += 1 + + return all_comments if all_comments else None + + def get_converted_issues(self, comment_id: int | None = None) -> list[GithubIssue]: + """Download issues from Github. + + Returns: + List of Github issues. + """ + all_issues = self._download_issues_from_github() + converted_issues = [] + for issue in all_issues: + if any([issue.get(key) is None for key in ["number", "title", "body"]]): + logger.warning( + f"Skipping issue {issue} as it is missing number, title, or body." + ) + continue + + if "pull_request" in issue: + continue + + # Get issue thread comments + thread_comments = self._get_issue_comments(issue["number"], comment_id=comment_id) + # Convert empty lists to None for optional fields + issue_details = GithubIssue( + owner=self.owner, + repo=self.repo, + number=issue["number"], + title=issue["title"], + body=issue["body"], + thread_comments=thread_comments, + review_comments=None, # Initialize review comments as None for regular issues + ) + + converted_issues.append(issue_details) + + return converted_issues + + def get_instruction(self, issue: GithubIssue, prompt_template: str, repo_instruction: str | None = None) -> tuple[str, list[str]]: + """Generate instruction for the agent""" + # Format thread comments if they exist + thread_context = "" + if issue.thread_comments: + thread_context = "\n\nIssue Thread Comments:\n" + "\n---\n".join(issue.thread_comments) + + images = [] + images.extend(self._extract_image_urls(issue.body)) + images.extend(self._extract_image_urls(thread_context)) + + template = jinja2.Template(prompt_template) + return template.render(body=issue.title + "\n\n" + issue.body + thread_context, repo_instruction=repo_instruction), images + + + + + def guess_success(self, issue: GithubIssue, history: list[Event], llm_config: LLMConfig) -> tuple[bool, None | list[bool], str]: + """Guess if the issue is fixed based on the history and the issue description.""" + + last_message = history[-1].message + # Include thread comments in the prompt if they exist + issue_context = issue.body + if issue.thread_comments: + issue_context += "\n\nIssue Thread Comments:\n" + "\n---\n".join(issue.thread_comments) + + with open(os.path.join(os.path.dirname(__file__), "prompts/guess_success/issue-success-check.jinja"), 'r') as f: + template = jinja2.Template(f.read()) + prompt = template.render(issue_context=issue_context, last_message=last_message) + + response = litellm.completion( + + model=llm_config.model, + messages=[{"role": "user", "content": prompt}], + api_key=llm_config.api_key, + base_url=llm_config.base_url, + ) + + answer = response.choices[0].message.content.strip() + pattern = r'--- success\n*(true|false)\n*--- explanation*\n((?:.|\n)*)' + match = re.search(pattern, answer) + if match: + return match.group(1).lower() == 'true', None, match.group(2) + + return False, None, f"Failed to decode answer from LLM response: {answer}" + + + +class PRHandler(IssueHandler): + issue_type: ClassVar[str] = "pr" + + def __init__(self, owner: str, repo: str, token: str): + super().__init__(owner, repo, token) + self.download_url = "https://api.github.com/repos/{}/{}/pulls" + + + + def __download_pr_metadata(self, pull_number: int, comment_id: int | None = None) -> tuple[list[str], list[int], list[str], list[ReviewThread], list[str]]: + + """ + Run a GraphQL query against the GitHub API for information on + 1. unresolved review comments + 2. referenced issues the pull request would close + + Args: + query: The GraphQL query as a string. + variables: A dictionary of variables for the query. + token: Your GitHub personal access token. + + Returns: + The JSON response from the GitHub API. + """ + # Using graphql as REST API doesn't indicate resolved status for review comments + # TODO: grabbing the first 10 issues, 100 review threads, and 100 coments; add pagination to retrieve all + query = """ + query($owner: String!, $repo: String!, $pr: Int!) { + repository(owner: $owner, name: $repo) { + pullRequest(number: $pr) { + closingIssuesReferences(first: 10) { + edges { + node { + body + number + } + } + } + url + reviews(first: 100) { + nodes { + body + state + fullDatabaseId + } + } + reviewThreads(first: 100) { + edges{ + node{ + id + isResolved + comments(first: 100) { + totalCount + nodes { + body + path + fullDatabaseId + } + } + } + } + } + } + } + } + """ + + + + variables = { + "owner": self.owner, + "repo": self.repo, + "pr": pull_number + } + + url = "https://api.github.com/graphql" + headers = { + "Authorization": f"Bearer {self.token}", + "Content-Type": "application/json" + } + + response = requests.post(url, json={"query": query, "variables": variables}, headers=headers) + response.raise_for_status() + response_json = response.json() + + # Parse the response to get closing issue references and unresolved review comments + pr_data = response_json.get("data", {}).get("repository", {}).get("pullRequest", {}) + + # Get closing issues + closing_issues = pr_data.get("closingIssuesReferences", {}).get("edges", []) + closing_issues_bodies = [issue["node"]["body"] for issue in closing_issues] + closing_issue_numbers = [issue["node"]["number"] for issue in closing_issues] # Extract issue numbers + + # Get review comments + reviews = pr_data.get("reviews", {}).get("nodes", []) + if comment_id is not None: + reviews = [review for review in reviews if int(review["fullDatabaseId"]) == comment_id] + review_bodies = [review["body"] for review in reviews] + + # Get unresolved review threads + review_threads = [] + thread_ids = [] # Store thread IDs; agent replies to the thread + raw_review_threads = pr_data.get("reviewThreads", {}).get("edges", []) + for thread in raw_review_threads: + node = thread.get("node", {}) + if not node.get("isResolved", True): # Check if the review thread is unresolved + id = node.get("id") + thread_contains_comment_id = False + my_review_threads = node.get("comments", {}).get("nodes", []) + message = "" + files = [] + for i, review_thread in enumerate(my_review_threads): + if comment_id is not None and int(review_thread["fullDatabaseId"]) == comment_id: + thread_contains_comment_id = True + + if i == len(my_review_threads) - 1: # Check if it's the last thread in the thread + if len(my_review_threads) > 1: + message += "---\n" # Add "---" before the last message if there's more than one thread + message += "latest feedback:\n" + review_thread["body"] + "\n" + else: + message += review_thread["body"] + "\n" # Add each thread in a new line + + file = review_thread.get("path") + if file and file not in files: + files.append(file) + + if comment_id is None or thread_contains_comment_id: + unresolved_thread = ReviewThread( + comment=message, + files=files + ) + review_threads.append(unresolved_thread) + thread_ids.append(id) + + return closing_issues_bodies, closing_issue_numbers, review_bodies, review_threads, thread_ids + + + # Override processing of downloaded issues + def _get_pr_comments(self, pr_number: int, comment_id: int | None = None) -> list[str] | None: + """Download comments for a specific pull request from Github.""" + url = f"https://api.github.com/repos/{self.owner}/{self.repo}/issues/{pr_number}/comments" + headers = { + "Authorization": f"token {self.token}", + "Accept": "application/vnd.github.v3+json", + } + params = {"per_page": 100, "page": 1} + all_comments = [] + + while True: + response = requests.get(url, headers=headers, params=params) + response.raise_for_status() + comments = response.json() + + if not comments: + break + + if comment_id is not None: + matching_comment = next((comment["body"] for comment in comments if comment["id"] == comment_id), None) + if matching_comment: + return [matching_comment] + else: + all_comments.extend([comment["body"] for comment in comments]) + + params["page"] += 1 + + return all_comments if all_comments else None + + def __get_context_from_external_issues_references( + self, + closing_issues: list[str], + closing_issue_numbers: list[int], + issue_body: str, + review_comments: list[str], + review_threads: list[ReviewThread], + thread_comments: list[str] | None + ): + new_issue_references = [] + + if issue_body: + new_issue_references.extend(self._extract_issue_references(issue_body)) + + if review_comments: + for comment in review_comments: + new_issue_references.extend(self._extract_issue_references(comment)) + + if review_threads: + for review_thread in review_threads: + new_issue_references.extend(self._extract_issue_references(review_thread.comment)) + + if thread_comments: + for thread_comment in thread_comments: + new_issue_references.extend(self._extract_issue_references(thread_comment)) + + non_duplicate_references = set(new_issue_references) + unique_issue_references = non_duplicate_references.difference(closing_issue_numbers) + + for issue_number in unique_issue_references: + url = f"https://api.github.com/repos/{self.owner}/{self.repo}/issues/{issue_number}" + headers = { + "Authorization": f"Bearer {self.token}", + "Accept": "application/vnd.github.v3+json", + } + response = requests.get(url, headers=headers) + response.raise_for_status() + issue_data = response.json() + issue_body = issue_data.get("body", "") + if issue_body: + closing_issues.append(issue_body) + + + return closing_issues + + def get_converted_issues(self, comment_id: int | None = None) -> list[GithubIssue]: + all_issues = self._download_issues_from_github() + converted_issues = [] + for issue in all_issues: + # For PRs, body can be None + if any([issue.get(key) is None for key in ["number", "title"]]): + logger.warning( + f"Skipping #{issue} as it is missing number or title." + ) + continue + + # Handle None body for PRs + body = issue.get("body") if issue.get("body") is not None else "" + closing_issues, closing_issues_numbers, review_comments, review_threads, thread_ids = self.__download_pr_metadata(issue["number"], comment_id=comment_id) + head_branch = issue["head"]["ref"] + + # Get PR thread comments + thread_comments = self._get_pr_comments(issue["number"], comment_id=comment_id) + + + closing_issues = self.__get_context_from_external_issues_references(closing_issues, + closing_issues_numbers, + body, + review_comments, + review_threads, + thread_comments) + + issue_details = GithubIssue( + owner=self.owner, + repo=self.repo, + number=issue["number"], + title=issue["title"], + body=body, + closing_issues=closing_issues, + review_comments=review_comments, + review_threads=review_threads, + thread_ids=thread_ids, + head_branch=head_branch, + thread_comments=thread_comments + ) + + converted_issues.append(issue_details) + + return converted_issues + + + def get_instruction(self, issue: GithubIssue, prompt_template: str, repo_instruction: str | None = None) -> tuple[str, list[str]]: + """Generate instruction for the agent""" + template = jinja2.Template(prompt_template) + images = [] + + issues_str = None + if issue.closing_issues: + issues_str = json.dumps(issue.closing_issues, indent=4) + images.extend(self._extract_image_urls(issues_str)) + + # Handle PRs with review comments + review_comments_str = None + if issue.review_comments: + review_comments_str = json.dumps(issue.review_comments, indent=4) + images.extend(self._extract_image_urls(review_comments_str)) + + # Handle PRs with file-specific review comments + review_thread_str = None + review_thread_file_str = None + if issue.review_threads: + review_threads = [review_thread.comment for review_thread in issue.review_threads] + review_thread_files = [] + for review_thread in issue.review_threads: + review_thread_files.extend(review_thread.files) + review_thread_str = json.dumps(review_threads, indent=4) + review_thread_file_str = json.dumps(review_thread_files, indent=4) + images.extend(self._extract_image_urls(review_thread_str)) + + # Format thread comments if they exist + thread_context = "" + if issue.thread_comments: + thread_context = "\n\nPR Thread Comments:\n" + "\n---\n".join(issue.thread_comments) + images.extend(self._extract_image_urls(thread_context)) + + instruction = template.render( + issues=issues_str, + review_comments=review_comments_str, + review_threads=review_thread_str, + files=review_thread_file_str, + thread_context=thread_context, + repo_instruction=repo_instruction + ) + return instruction, images + + + def _check_feedback_with_llm(self, prompt: str, llm_config: LLMConfig) -> tuple[bool, str]: + """Helper function to check feedback with LLM and parse response""" + response = litellm.completion( + model=llm_config.model, + messages=[{"role": "user", "content": prompt}], + api_key=llm_config.api_key, + base_url=llm_config.base_url, + ) + + answer = response.choices[0].message.content.strip() + pattern = r'--- success\n*(true|false)\n*--- explanation*\n((?:.|\n)*)' + match = re.search(pattern, answer) + if match: + return match.group(1).lower() == 'true', match.group(2).strip() + return False, f"Failed to decode answer from LLM response: {answer}" + + def _check_review_thread(self, review_thread: ReviewThread, issues_context: str, last_message: str, llm_config: LLMConfig) -> tuple[bool, str]: + """Check if a review thread's feedback has been addressed""" + files_context = json.dumps(review_thread.files, indent=4) + + with open(os.path.join(os.path.dirname(__file__), "prompts/guess_success/pr-feedback-check.jinja"), 'r') as f: + template = jinja2.Template(f.read()) + + prompt = template.render( + issue_context=issues_context, + feedback=review_thread.comment, + files_context=files_context, + last_message=last_message, + ) + + return self._check_feedback_with_llm(prompt, llm_config) + + def _check_thread_comments(self, thread_comments: list[str], issues_context: str, last_message: str, llm_config: LLMConfig) -> tuple[bool, str]: + """Check if thread comments feedback has been addressed""" + thread_context = "\n---\n".join(thread_comments) + + with open(os.path.join(os.path.dirname(__file__), "prompts/guess_success/pr-thread-check.jinja"), 'r') as f: + template = jinja2.Template(f.read()) + + prompt = template.render( + issue_context=issues_context, + thread_context=thread_context, + last_message=last_message, + ) + + return self._check_feedback_with_llm(prompt, llm_config) + + def _check_review_comments(self, review_comments: list[str], issues_context: str, last_message: str, llm_config: LLMConfig) -> tuple[bool, str]: + """Check if review comments feedback has been addressed""" + review_context = "\n---\n".join(review_comments) + + with open(os.path.join(os.path.dirname(__file__), "prompts/guess_success/pr-review-check.jinja"), 'r') as f: + template = jinja2.Template(f.read()) + + prompt = template.render( + issue_context=issues_context, + review_context=review_context, + last_message=last_message, + ) + + return self._check_feedback_with_llm(prompt, llm_config) + + def guess_success(self, issue: GithubIssue, history: list[Event], llm_config: LLMConfig) -> tuple[bool, None | list[bool], str]: + """Guess if the issue is fixed based on the history and the issue description.""" + + last_message = history[-1].message + issues_context = json.dumps(issue.closing_issues, indent=4) + success_list = [] + explanation_list = [] + + # Handle PRs with file-specific review comments + if issue.review_threads: + for review_thread in issue.review_threads: + success, explanation = self._check_review_thread(review_thread, issues_context, last_message, llm_config) + success_list.append(success) + explanation_list.append(explanation) + # Handle PRs with only thread comments (no file-specific review comments) + elif issue.thread_comments: + success, explanation = self._check_thread_comments(issue.thread_comments, issues_context, last_message, llm_config) + success_list.append(success) + explanation_list.append(explanation) + elif issue.review_comments: + # Handle PRs with only review comments (no file-specific review comments or thread comments) + success, explanation = self._check_review_comments(issue.review_comments, issues_context, last_message, llm_config) + success_list.append(success) + explanation_list.append(explanation) + else: + # No review comments, thread comments, or file-level review comments found + return False, None, "No feedback was found to process" + + # Return overall success (all must be true) and explanations + if not success_list: + return False, None, "No feedback was processed" + return all(success_list), success_list, "\n".join(explanation_list) + + + + + + + + + + + + diff --git a/openhands/resolver/patching/README.md b/openhands/resolver/patching/README.md new file mode 100644 index 000000000000..e0c7b98eac78 --- /dev/null +++ b/openhands/resolver/patching/README.md @@ -0,0 +1,4 @@ +# Patching code + +Originally from [whatthepatch](https://github.com/cscorley/whatthepatch) +(MIT license) diff --git a/openhands/resolver/patching/__init__.py b/openhands/resolver/patching/__init__.py new file mode 100644 index 000000000000..5c31f160a0a0 --- /dev/null +++ b/openhands/resolver/patching/__init__.py @@ -0,0 +1,6 @@ +# -*- coding: utf-8 -*- + +from .patch import parse_patch +from .apply import apply_diff + +__all__ = ["parse_patch", "apply_diff"] diff --git a/openhands/resolver/patching/apply.py b/openhands/resolver/patching/apply.py new file mode 100644 index 000000000000..f13e814292cb --- /dev/null +++ b/openhands/resolver/patching/apply.py @@ -0,0 +1,120 @@ +# -*- coding: utf-8 -*- + +import os.path +import subprocess +import tempfile + +from .exceptions import HunkApplyException, SubprocessException +from .snippets import remove, which + + +def _apply_diff_with_subprocess(diff, lines, reverse=False): + # call out to patch program + patchexec = which("patch") + if not patchexec: + raise SubprocessException("cannot find patch program", code=-1) + + tempdir = tempfile.gettempdir() + + filepath = os.path.join(tempdir, "wtp-" + str(hash(diff.header))) + oldfilepath = filepath + ".old" + newfilepath = filepath + ".new" + rejfilepath = filepath + ".rej" + patchfilepath = filepath + ".patch" + with open(oldfilepath, "w") as f: + f.write("\n".join(lines) + "\n") + + with open(patchfilepath, "w") as f: + f.write(diff.text) + + args = [ + patchexec, + "--reverse" if reverse else "--forward", + "--quiet", + "--no-backup-if-mismatch", + "-o", + newfilepath, + "-i", + patchfilepath, + "-r", + rejfilepath, + oldfilepath, + ] + ret = subprocess.call(args) + + with open(newfilepath) as f: + lines = f.read().splitlines() + + try: + with open(rejfilepath) as f: + rejlines = f.read().splitlines() + except IOError: + rejlines = None + + remove(oldfilepath) + remove(newfilepath) + remove(rejfilepath) + remove(patchfilepath) + + # do this last to ensure files get cleaned up + if ret != 0: + raise SubprocessException("patch program failed", code=ret) + + return lines, rejlines + + +def _reverse(changes): + def _reverse_change(c): + return c._replace(old=c.new, new=c.old) + + return [_reverse_change(c) for c in changes] + + +def apply_diff(diff, text, reverse=False, use_patch=False): + try: + lines = text.splitlines() + except AttributeError: + lines = list(text) + + if use_patch: + return _apply_diff_with_subprocess(diff, lines, reverse) + + n_lines = len(lines) + + changes = _reverse(diff.changes) if reverse else diff.changes + # check that the source text matches the context of the diff + for old, new, line, hunk in changes: + # might have to check for line is None here for ed scripts + if old is not None and line is not None: + if old > n_lines: + raise HunkApplyException( + 'context line {n}, "{line}" does not exist in source'.format( + n=old, line=line + ), + hunk=hunk, + ) + if lines[old - 1] != line: + raise HunkApplyException( + 'context line {n}, "{line}" does not match "{sl}"'.format( + n=old, line=line, sl=lines[old - 1] + ), + hunk=hunk, + ) + + # for calculating the old line + r = 0 + i = 0 + + for old, new, line, hunk in changes: + if old is not None and new is None: + del lines[old - 1 - r + i] + r += 1 + elif old is None and new is not None: + lines.insert(new - 1, line) + i += 1 + elif old is not None and new is not None: + # Sometimes, people remove hunks from patches, making these + # numbers completely unreliable. Because they're jerks. + pass + + return lines diff --git a/openhands/resolver/patching/exceptions.py b/openhands/resolver/patching/exceptions.py new file mode 100644 index 000000000000..594b079e8365 --- /dev/null +++ b/openhands/resolver/patching/exceptions.py @@ -0,0 +1,31 @@ +class PatchingException(Exception): + pass + + +class HunkException(PatchingException): + def __init__(self, msg, hunk=None): + self.hunk = hunk + if hunk is not None: + super(HunkException, self).__init__( + "{msg}, in hunk #{n}".format(msg=msg, n=hunk) + ) + else: + super(HunkException, self).__init__(msg) + + +class ApplyException(PatchingException): + pass + + +class SubprocessException(ApplyException): + def __init__(self, msg, code): + super(SubprocessException, self).__init__(msg) + self.code = code + + +class HunkApplyException(HunkException, ApplyException, ValueError): + pass + + +class ParseException(HunkException, ValueError): + pass diff --git a/openhands/resolver/patching/patch.py b/openhands/resolver/patching/patch.py new file mode 100644 index 000000000000..317aec42e805 --- /dev/null +++ b/openhands/resolver/patching/patch.py @@ -0,0 +1,1007 @@ +# -*- coding: utf-8 -*- +import base64 +import re +import zlib +from collections import namedtuple + +from . import exceptions +from .snippets import findall_regex, split_by_regex + +header = namedtuple( + "header", + "index_path old_path old_version new_path new_version", +) + +diffobj = namedtuple("diffobj", "header changes text") +Change = namedtuple("Change", "old new line hunk") + +file_timestamp_str = "(.+?)(?:\t|:| +)(.*)" +# .+? was previously [^:\t\n\r\f\v]+ + +# general diff regex +diffcmd_header = re.compile("^diff.* (.+) (.+)$") +unified_header_index = re.compile("^Index: (.+)$") +unified_header_old_line = re.compile(r"^--- " + file_timestamp_str + "$") +unified_header_new_line = re.compile(r"^\+\+\+ " + file_timestamp_str + "$") +unified_hunk_start = re.compile(r"^@@ -(\d+),?(\d*) \+(\d+),?(\d*) @@(.*)$") +unified_change = re.compile("^([-+ ])(.*)$") + +context_header_old_line = re.compile(r"^\*\*\* " + file_timestamp_str + "$") +context_header_new_line = re.compile("^--- " + file_timestamp_str + "$") +context_hunk_start = re.compile(r"^\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*$") +context_hunk_old = re.compile(r"^\*\*\* (\d+),?(\d*) \*\*\*\*$") +context_hunk_new = re.compile(r"^--- (\d+),?(\d*) ----$") +context_change = re.compile("^([-+ !]) (.*)$") + +ed_hunk_start = re.compile(r"^(\d+),?(\d*)([acd])$") +ed_hunk_end = re.compile("^.$") +# much like forward ed, but no 'c' type +rcs_ed_hunk_start = re.compile(r"^([ad])(\d+) ?(\d*)$") + +default_hunk_start = re.compile(r"^(\d+),?(\d*)([acd])(\d+),?(\d*)$") +default_hunk_mid = re.compile("^---$") +default_change = re.compile("^([><]) (.*)$") + +# Headers + +# git has a special index header and no end part +git_diffcmd_header = re.compile("^diff --git a/(.+) b/(.+)$") +git_header_index = re.compile(r"^index ([a-f0-9]+)..([a-f0-9]+) ?(\d*)$") +git_header_old_line = re.compile("^--- (.+)$") +git_header_new_line = re.compile(r"^\+\+\+ (.+)$") +git_header_file_mode = re.compile(r"^(new|deleted) file mode \d{6}$") +git_header_binary_file = re.compile("^Binary files (.+) and (.+) differ") +git_binary_patch_start = re.compile(r"^GIT binary patch$") +git_binary_literal_start = re.compile(r"^literal (\d+)$") +git_binary_delta_start = re.compile(r"^delta (\d+)$") +base85string = re.compile(r"^[0-9A-Za-z!#$%&()*+;<=>?@^_`{|}~-]+$") + +bzr_header_index = re.compile("=== (.+)") +bzr_header_old_line = unified_header_old_line +bzr_header_new_line = unified_header_new_line + +svn_header_index = unified_header_index +svn_header_timestamp_version = re.compile(r"\((?:working copy|revision (\d+))\)") +svn_header_timestamp = re.compile(r".*(\(.*\))$") + +cvs_header_index = unified_header_index +cvs_header_rcs = re.compile(r"^RCS file: (.+)(?:,\w{1}$|$)") +cvs_header_timestamp = re.compile(r"(.+)\t([\d.]+)") +cvs_header_timestamp_colon = re.compile(r":([\d.]+)\t(.+)") +old_cvs_diffcmd_header = re.compile("^diff.* (.+):(.*) (.+):(.*)$") + + +def parse_patch(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + # maybe use this to nuke all of those line endings? + # lines = [x.splitlines()[0] for x in lines] + lines = [x if len(x) == 0 else x.splitlines()[0] for x in lines] + + check = [ + unified_header_index, + diffcmd_header, + cvs_header_rcs, + git_header_index, + context_header_old_line, + unified_header_old_line, + ] + + diffs = [] + for c in check: + diffs = split_by_regex(lines, c) + if len(diffs) > 1: + break + + for diff in diffs: + difftext = "\n".join(diff) + "\n" + h = parse_header(diff) + d = parse_diff(diff) + if h or d: + yield diffobj(header=h, changes=d, text=difftext) + + +def parse_header(text): + h = parse_scm_header(text) + if h is None: + h = parse_diff_header(text) + return h + + +def parse_scm_header(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + check = [ + (git_header_index, parse_git_header), + (old_cvs_diffcmd_header, parse_cvs_header), + (cvs_header_rcs, parse_cvs_header), + (svn_header_index, parse_svn_header), + ] + + for regex, parser in check: + diffs = findall_regex(lines, regex) + if len(diffs) > 0: + git_opt = findall_regex(lines, git_diffcmd_header) + if len(git_opt) > 0: + res = parser(lines) + if res: + old_path = res.old_path + new_path = res.new_path + if old_path.startswith("a/"): + old_path = old_path[2:] + + if new_path.startswith("b/"): + new_path = new_path[2:] + + return header( + index_path=res.index_path, + old_path=old_path, + old_version=res.old_version, + new_path=new_path, + new_version=res.new_version, + ) + else: + res = parser(lines) + + return res + + return None + + +def parse_diff_header(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + check = [ + (unified_header_new_line, parse_unified_header), + (context_header_old_line, parse_context_header), + (diffcmd_header, parse_diffcmd_header), + # TODO: + # git_header can handle version-less unified headers, but + # will trim a/ and b/ in the paths if they exist... + (git_header_new_line, parse_git_header), + ] + + for regex, parser in check: + diffs = findall_regex(lines, regex) + if len(diffs) > 0: + return parser(lines) + + return None # no header? + + +def parse_diff(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + check = [ + (unified_hunk_start, parse_unified_diff), + (context_hunk_start, parse_context_diff), + (default_hunk_start, parse_default_diff), + (ed_hunk_start, parse_ed_diff), + (rcs_ed_hunk_start, parse_rcs_ed_diff), + (git_binary_patch_start, parse_git_binary_diff), + ] + + for hunk, parser in check: + diffs = findall_regex(lines, hunk) + if len(diffs) > 0: + return parser(lines) + return None + + +def parse_git_header(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + old_version = None + new_version = None + old_path = None + new_path = None + cmd_old_path = None + cmd_new_path = None + for line in lines: + hm = git_diffcmd_header.match(line) + if hm: + cmd_old_path = hm.group(1) + cmd_new_path = hm.group(2) + continue + + g = git_header_index.match(line) + if g: + old_version = g.group(1) + new_version = g.group(2) + continue + + # git always has it's own special headers + o = git_header_old_line.match(line) + if o: + old_path = o.group(1) + + n = git_header_new_line.match(line) + if n: + new_path = n.group(1) + + binary = git_header_binary_file.match(line) + if binary: + old_path = binary.group(1) + new_path = binary.group(2) + + if old_path and new_path: + if old_path.startswith("a/"): + old_path = old_path[2:] + + if new_path.startswith("b/"): + new_path = new_path[2:] + return header( + index_path=None, + old_path=old_path, + old_version=old_version, + new_path=new_path, + new_version=new_version, + ) + + # if we go through all of the text without finding our normal info, + # use the cmd if available + if cmd_old_path and cmd_new_path and old_version and new_version: + if cmd_old_path.startswith("a/"): + cmd_old_path = cmd_old_path[2:] + + if cmd_new_path.startswith("b/"): + cmd_new_path = cmd_new_path[2:] + + return header( + index_path=None, + # wow, I kind of hate this: + # assume /dev/null if the versions are zeroed out + old_path="/dev/null" if old_version == "0000000" else cmd_old_path, + old_version=old_version, + new_path="/dev/null" if new_version == "0000000" else cmd_new_path, + new_version=new_version, + ) + + return None + + +def parse_svn_header(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + headers = findall_regex(lines, svn_header_index) + if len(headers) == 0: + return None + + while len(lines) > 0: + i = svn_header_index.match(lines[0]) + del lines[0] + if not i: + continue + + diff_header = parse_diff_header(lines) + if not diff_header: + return header( + index_path=i.group(1), + old_path=i.group(1), + old_version=None, + new_path=i.group(1), + new_version=None, + ) + + opath = diff_header.old_path + over = diff_header.old_version + if over: + oend = svn_header_timestamp_version.match(over) + if oend and oend.group(1): + over = int(oend.group(1)) + elif opath: + ts = svn_header_timestamp.match(opath) + if ts: + opath = opath[: -len(ts.group(1))] + oend = svn_header_timestamp_version.match(ts.group(1)) + if oend and oend.group(1): + over = int(oend.group(1)) + + npath = diff_header.new_path + nver = diff_header.new_version + if nver: + nend = svn_header_timestamp_version.match(diff_header.new_version) + if nend and nend.group(1): + nver = int(nend.group(1)) + elif npath: + ts = svn_header_timestamp.match(npath) + if ts: + npath = npath[: -len(ts.group(1))] + nend = svn_header_timestamp_version.match(ts.group(1)) + if nend and nend.group(1): + nver = int(nend.group(1)) + + if not isinstance(over, int): + over = None + + if not isinstance(nver, int): + nver = None + + return header( + index_path=i.group(1), + old_path=opath, + old_version=over, + new_path=npath, + new_version=nver, + ) + + return None + + +def parse_cvs_header(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + headers = findall_regex(lines, cvs_header_rcs) + headers_old = findall_regex(lines, old_cvs_diffcmd_header) + + if headers: + # parse rcs style headers + while len(lines) > 0: + i = cvs_header_index.match(lines[0]) + del lines[0] + if not i: + continue + + diff_header = parse_diff_header(lines) + if diff_header: + over = diff_header.old_version + if over: + oend = cvs_header_timestamp.match(over) + oend_c = cvs_header_timestamp_colon.match(over) + if oend: + over = oend.group(2) + elif oend_c: + over = oend_c.group(1) + + nver = diff_header.new_version + if nver: + nend = cvs_header_timestamp.match(nver) + nend_c = cvs_header_timestamp_colon.match(nver) + if nend: + nver = nend.group(2) + elif nend_c: + nver = nend_c.group(1) + + return header( + index_path=i.group(1), + old_path=diff_header.old_path, + old_version=over, + new_path=diff_header.new_path, + new_version=nver, + ) + return header( + index_path=i.group(1), + old_path=i.group(1), + old_version=None, + new_path=i.group(1), + new_version=None, + ) + elif headers_old: + # parse old style headers + while len(lines) > 0: + i = cvs_header_index.match(lines[0]) + del lines[0] + if not i: + continue + + d = old_cvs_diffcmd_header.match(lines[0]) + if not d: + return header( + index_path=i.group(1), + old_path=i.group(1), + old_version=None, + new_path=i.group(1), + new_version=None, + ) + + # will get rid of the useless stuff for us + parse_diff_header(lines) + over = d.group(2) if d.group(2) else None + nver = d.group(4) if d.group(4) else None + return header( + index_path=i.group(1), + old_path=d.group(1), + old_version=over, + new_path=d.group(3), + new_version=nver, + ) + + return None + + +def parse_diffcmd_header(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + headers = findall_regex(lines, diffcmd_header) + if len(headers) == 0: + return None + + while len(lines) > 0: + d = diffcmd_header.match(lines[0]) + del lines[0] + if d: + return header( + index_path=None, + old_path=d.group(1), + old_version=None, + new_path=d.group(2), + new_version=None, + ) + return None + + +def parse_unified_header(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + headers = findall_regex(lines, unified_header_new_line) + if len(headers) == 0: + return None + + while len(lines) > 1: + o = unified_header_old_line.match(lines[0]) + del lines[0] + if o: + n = unified_header_new_line.match(lines[0]) + del lines[0] + if n: + over = o.group(2) + if len(over) == 0: + over = None + + nver = n.group(2) + if len(nver) == 0: + nver = None + + return header( + index_path=None, + old_path=o.group(1), + old_version=over, + new_path=n.group(1), + new_version=nver, + ) + + return None + + +def parse_context_header(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + headers = findall_regex(lines, context_header_old_line) + if len(headers) == 0: + return None + + while len(lines) > 1: + o = context_header_old_line.match(lines[0]) + del lines[0] + if o: + n = context_header_new_line.match(lines[0]) + del lines[0] + if n: + over = o.group(2) + if len(over) == 0: + over = None + + nver = n.group(2) + if len(nver) == 0: + nver = None + + return header( + index_path=None, + old_path=o.group(1), + old_version=over, + new_path=n.group(1), + new_version=nver, + ) + + return None + + +def parse_default_diff(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + old = 0 + new = 0 + old_len = 0 + new_len = 0 + r = 0 + i = 0 + + changes = list() + + hunks = split_by_regex(lines, default_hunk_start) + for hunk_n, hunk in enumerate(hunks): + if not len(hunk): + continue + + r = 0 + i = 0 + while len(hunk) > 0: + h = default_hunk_start.match(hunk[0]) + c = default_change.match(hunk[0]) + del hunk[0] + if h: + old = int(h.group(1)) + if len(h.group(2)) > 0: + old_len = int(h.group(2)) - old + 1 + else: + old_len = 0 + + new = int(h.group(4)) + if len(h.group(5)) > 0: + new_len = int(h.group(5)) - new + 1 + else: + new_len = 0 + + elif c: + kind = c.group(1) + line = c.group(2) + + if kind == "<" and (r != old_len or r == 0): + changes.append(Change(old + r, None, line, hunk_n)) + r += 1 + elif kind == ">" and (i != new_len or i == 0): + changes.append(Change(None, new + i, line, hunk_n)) + i += 1 + + if len(changes) > 0: + return changes + + return None + + +def parse_unified_diff(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + old = 0 + new = 0 + r = 0 + i = 0 + old_len = 0 + new_len = 0 + + changes = list() + + hunks = split_by_regex(lines, unified_hunk_start) + for hunk_n, hunk in enumerate(hunks): + # reset counters + r = 0 + i = 0 + while len(hunk) > 0: + h = unified_hunk_start.match(hunk[0]) + del hunk[0] + if h: + old = int(h.group(1)) + if len(h.group(2)) > 0: + old_len = int(h.group(2)) + else: + old_len = 0 + + new = int(h.group(3)) + if len(h.group(4)) > 0: + new_len = int(h.group(4)) + else: + new_len = 0 + + h = None + break + + for n in hunk: + c = unified_change.match(n) + if c: + kind = c.group(1) + line = c.group(2) + + if kind == "-" and (r != old_len or r == 0): + changes.append(Change(old + r, None, line, hunk_n)) + r += 1 + elif kind == "+" and (i != new_len or i == 0): + changes.append(Change(None, new + i, line, hunk_n)) + i += 1 + elif kind == " ": + if r != old_len and i != new_len: + changes.append(Change(old + r, new + i, line, hunk_n)) + r += 1 + i += 1 + + if len(changes) > 0: + return changes + + return None + + +def parse_context_diff(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + old = 0 + new = 0 + j = 0 + k = 0 + + changes = list() + + hunks = split_by_regex(lines, context_hunk_start) + for hunk_n, hunk in enumerate(hunks): + if not len(hunk): + continue + + j = 0 + k = 0 + parts = split_by_regex(hunk, context_hunk_new) + if len(parts) != 2: + raise exceptions.ParseException("Context diff invalid", hunk_n) + + old_hunk = parts[0] + new_hunk = parts[1] + + while len(old_hunk) > 0: + o = context_hunk_old.match(old_hunk[0]) + del old_hunk[0] + + if not o: + continue + + old = int(o.group(1)) + old_len = int(o.group(2)) + 1 - old + while len(new_hunk) > 0: + n = context_hunk_new.match(new_hunk[0]) + del new_hunk[0] + + if not n: + continue + + new = int(n.group(1)) + new_len = int(n.group(2)) + 1 - new + break + break + + # now have old and new set, can start processing? + if len(old_hunk) > 0 and len(new_hunk) == 0: + msg = "Got unexpected change in removal hunk: " + # only removes left? + while len(old_hunk) > 0: + c = context_change.match(old_hunk[0]) + del old_hunk[0] + + if not c: + continue + + kind = c.group(1) + line = c.group(2) + + if kind == "-" and (j != old_len or j == 0): + changes.append(Change(old + j, None, line, hunk_n)) + j += 1 + elif kind == " " and ( + (j != old_len and k != new_len) or (j == 0 or k == 0) + ): + changes.append(Change(old + j, new + k, line, hunk_n)) + j += 1 + k += 1 + elif kind == "+" or kind == "!": + raise exceptions.ParseException(msg + kind, hunk_n) + + continue + + if len(old_hunk) == 0 and len(new_hunk) > 0: + msg = "Got unexpected change in removal hunk: " + # only insertions left? + while len(new_hunk) > 0: + c = context_change.match(new_hunk[0]) + del new_hunk[0] + + if not c: + continue + + kind = c.group(1) + line = c.group(2) + + if kind == "+" and (k != new_len or k == 0): + changes.append(Change(None, new + k, line, hunk_n)) + k += 1 + elif kind == " " and ( + (j != old_len and k != new_len) or (j == 0 or k == 0) + ): + changes.append(Change(old + j, new + k, line, hunk_n)) + j += 1 + k += 1 + elif kind == "-" or kind == "!": + raise exceptions.ParseException(msg + kind, hunk_n) + continue + + # both + while len(old_hunk) > 0 and len(new_hunk) > 0: + oc = context_change.match(old_hunk[0]) + nc = context_change.match(new_hunk[0]) + okind = None + nkind = None + + if oc: + okind = oc.group(1) + oline = oc.group(2) + + if nc: + nkind = nc.group(1) + nline = nc.group(2) + + if not (oc or nc): + del old_hunk[0] + del new_hunk[0] + elif okind == " " and nkind == " " and oline == nline: + changes.append(Change(old + j, new + k, oline, hunk_n)) + j += 1 + k += 1 + del old_hunk[0] + del new_hunk[0] + elif okind == "-" or okind == "!" and (j != old_len or j == 0): + changes.append(Change(old + j, None, oline, hunk_n)) + j += 1 + del old_hunk[0] + elif nkind == "+" or nkind == "!" and (k != new_len or k == 0): + changes.append(Change(None, new + k, nline, hunk_n)) + k += 1 + del new_hunk[0] + else: + return None + + if len(changes) > 0: + return changes + + return None + + +def parse_ed_diff(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + old = 0 + j = 0 + k = 0 + + r = 0 + i = 0 + + changes = list() + + hunks = split_by_regex(lines, ed_hunk_start) + hunks.reverse() + for hunk_n, hunk in enumerate(hunks): + if not len(hunk): + continue + j = 0 + k = 0 + while len(hunk) > 0: + o = ed_hunk_start.match(hunk[0]) + del hunk[0] + + if not o: + continue + + old = int(o.group(1)) + old_end = int(o.group(2)) if len(o.group(2)) else old + + hunk_kind = o.group(3) + if hunk_kind == "d": + k = 0 + while old_end >= old: + changes.append(Change(old + k, None, None, hunk_n)) + r += 1 + k += 1 + old_end -= 1 + continue + + while len(hunk) > 0: + e = ed_hunk_end.match(hunk[0]) + if not e and hunk_kind == "c": + k = 0 + while old_end >= old: + changes.append(Change(old + k, None, None, hunk_n)) + r += 1 + k += 1 + old_end -= 1 + + # I basically have no idea why this works + # for these tests. + changes.append( + Change( + None, + old - r + i + k + j, + hunk[0], + hunk_n, + ) + ) + i += 1 + j += 1 + if not e and hunk_kind == "a": + changes.append( + Change( + None, + old - r + i + 1, + hunk[0], + hunk_n, + ) + ) + i += 1 + + del hunk[0] + + if len(changes) > 0: + return changes + + return None + + +def parse_rcs_ed_diff(text): + # much like forward ed, but no 'c' type + try: + lines = text.splitlines() + except AttributeError: + lines = text + + old = 0 + j = 0 + size = 0 + total_change_size = 0 + + changes = list() + + hunks = split_by_regex(lines, rcs_ed_hunk_start) + for hunk_n, hunk in enumerate(hunks): + if len(hunk): + j = 0 + while len(hunk) > 0: + o = rcs_ed_hunk_start.match(hunk[0]) + del hunk[0] + + if not o: + continue + + hunk_kind = o.group(1) + old = int(o.group(2)) + size = int(o.group(3)) + + if hunk_kind == "a": + old += total_change_size + 1 + total_change_size += size + while size > 0 and len(hunk) > 0: + changes.append(Change(None, old + j, hunk[0], hunk_n)) + j += 1 + size -= 1 + + del hunk[0] + + elif hunk_kind == "d": + total_change_size -= size + while size > 0: + changes.append(Change(old + j, None, None, hunk_n)) + j += 1 + size -= 1 + + if len(changes) > 0: + return changes + + return None + + +def parse_git_binary_diff(text): + try: + lines = text.splitlines() + except AttributeError: + lines = text + + changes = list() + + old_version = None + new_version = None + cmd_old_path = None + cmd_new_path = None + # the sizes are used as latch-up + old_size = None + new_size = None + old_encoded = "" + new_encoded = "" + for line in lines: + if cmd_old_path is None and cmd_new_path is None: + hm = git_diffcmd_header.match(line) + if hm: + cmd_old_path = hm.group(1) + cmd_new_path = hm.group(2) + continue + + if old_version is None and new_version is None: + g = git_header_index.match(line) + if g: + old_version = g.group(1) + new_version = g.group(2) + continue + + # the first is added file + if new_size is None: + literal = git_binary_literal_start.match(line) + if literal: + new_size = int(literal.group(1)) + continue + delta = git_binary_delta_start.match(line) + if delta: + # not supported + new_size = 0 + continue + elif new_size > 0: + if base85string.match(line): + assert len(line) >= 6 and ((len(line) - 1) % 5) == 0 + new_encoded += line[1:] + elif 0 == len(line): + decoded = base64.b85decode(new_encoded) + added_data = zlib.decompress(decoded) + assert new_size == len(added_data) + change = Change(None, 0, added_data, None) + changes.append(change) + new_size = 0 + else: + break + + # the second is removed file + if old_size is None: + literal = git_binary_literal_start.match(line) + if literal: + old_size = int(literal.group(1)) + delta = git_binary_delta_start.match(line) + if delta: + # not supported + old_size = 0 + continue + elif old_size > 0: + if base85string.match(line): + assert len(line) >= 6 and ((len(line) - 1) % 5) == 0 + old_encoded += line[1:] + elif 0 == len(line): + decoded = base64.b85decode(old_encoded) + removed_data = zlib.decompress(decoded) + assert old_size == len(removed_data) + change = Change(0, None, None, removed_data) + changes.append(change) + old_size = 0 + else: + break + + return changes diff --git a/openhands/resolver/patching/snippets.py b/openhands/resolver/patching/snippets.py new file mode 100644 index 000000000000..d0e57f163320 --- /dev/null +++ b/openhands/resolver/patching/snippets.py @@ -0,0 +1,60 @@ +# -*- coding: utf-8 -*- + +import os +from shutil import rmtree + + +def remove(path): + if os.path.exists(path): + if os.path.isdir(path): + rmtree(path) + else: + os.remove(path) + + +# find all indices of a list of strings that match a regex +def findall_regex(items, regex): + found = list() + for i in range(0, len(items)): + k = regex.match(items[i]) + if k: + found.append(i) + k = None + + return found + + +def split_by_regex(items, regex): + splits = list() + indices = findall_regex(items, regex) + k = None + for i in indices: + if k is None: + splits.append(items[0:i]) + k = i + else: + splits.append(items[k:i]) + k = i + + splits.append(items[k:]) + + return splits + + +# http://stackoverflow.com/questions/377017/test-if-executable-exists-in-python +def which(program): + def is_exe(fpath): + return os.path.isfile(fpath) and os.access(fpath, os.X_OK) + + fpath, fname = os.path.split(program) + if fpath: + if is_exe(program): + return program + else: + for path in os.environ["PATH"].split(os.pathsep): + path = path.strip('"') + exe_file = os.path.join(path, program) + if is_exe(exe_file): + return exe_file + + return None diff --git a/openhands/resolver/prompts/guess_success/issue-success-check.jinja b/openhands/resolver/prompts/guess_success/issue-success-check.jinja new file mode 100644 index 000000000000..5e882cb731a5 --- /dev/null +++ b/openhands/resolver/prompts/guess_success/issue-success-check.jinja @@ -0,0 +1,18 @@ +Given the following issue description and the last message from an AI agent attempting to fix it, determine if the issue has been successfully resolved. + +Issue description: +{{ issue_context }} + +Last message from AI agent: +{{ last_message }} + +(1) has the issue been successfully resolved? +(2) If the issue has been resolved, please provide an explanation of what was done in the PR that can be sent to a human reviewer on github. If the issue has not been resolved, please provide an explanation of why. + +Answer in exactly the format below, with only true or false for success, and an explanation of the result. + +--- success +true/false + +--- explanation +... diff --git a/openhands/resolver/prompts/guess_success/pr-feedback-check.jinja b/openhands/resolver/prompts/guess_success/pr-feedback-check.jinja new file mode 100644 index 000000000000..19e57d48ca10 --- /dev/null +++ b/openhands/resolver/prompts/guess_success/pr-feedback-check.jinja @@ -0,0 +1,24 @@ +You are given one or more issue descriptions, a piece of feedback to resolve the issues, and the last message from an AI agent attempting to incorporate the feedback. If the feedback is addressed to a specific code file, then the file locations will be provided as well. Determine if the feedback has been successfully resolved. + +Issue descriptions: +{{ issue_context }} + +Feedback: +{{ feedback }} + +Files locations: +{{ files_context }} + +Last message from AI agent: +{{ last_message }} + +(1) has the feedback been successfully incorporated? +(2) If the feedback has been incorporated, please provide an explanation of what was done that can be sent to a human reviewer on github. If the feedback has not been resolved, please provide an explanation of why. + +Answer in exactly the format below, with only true or false for success, and an explanation of the result. + +--- success +true/false + +--- explanation +... diff --git a/openhands/resolver/prompts/guess_success/pr-review-check.jinja b/openhands/resolver/prompts/guess_success/pr-review-check.jinja new file mode 100644 index 000000000000..49a7ef39afc8 --- /dev/null +++ b/openhands/resolver/prompts/guess_success/pr-review-check.jinja @@ -0,0 +1,21 @@ +You are given one or more issue descriptions, the PR review comments, and the last message from an AI agent attempting to address the feedback. Determine if the feedback has been successfully resolved. + +Issue descriptions: +{{ issue_context }} + +PR Review Comments: +{{ review_context }} + +Last message from AI agent: +{{ last_message }} + +(1) has the feedback been successfully incorporated? +(2) If the feedback has been incorporated, please provide an explanation of what was done that can be sent to a human reviewer on github. If the feedback has not been resolved, please provide an explanation of why. + +Answer in exactly the format below, with only true or false for success, and an explanation of the result. + +--- success +true/false + +--- explanation +... diff --git a/openhands/resolver/prompts/guess_success/pr-thread-check.jinja b/openhands/resolver/prompts/guess_success/pr-thread-check.jinja new file mode 100644 index 000000000000..ebe9c242c551 --- /dev/null +++ b/openhands/resolver/prompts/guess_success/pr-thread-check.jinja @@ -0,0 +1,21 @@ +You are given one or more issue descriptions, the PR thread comments, and the last message from an AI agent attempting to address the feedback. Determine if the feedback has been successfully resolved. + +Issue descriptions: +{{ issue_context }} + +PR Thread Comments: +{{ thread_context }} + +Last message from AI agent: +{{ last_message }} + +(1) has the feedback been successfully incorporated? +(2) If the feedback has been incorporated, please provide an explanation of what was done that can be sent to a human reviewer on github. If the feedback has not been resolved, please provide an explanation of why. + +Answer in exactly the format below, with only true or false for success, and an explanation of the result. + +--- success +true/false + +--- explanation +... diff --git a/openhands/resolver/prompts/repo_instructions/all-hands-ai___openhands-resolver.txt b/openhands/resolver/prompts/repo_instructions/all-hands-ai___openhands-resolver.txt new file mode 100644 index 000000000000..ca040d591683 --- /dev/null +++ b/openhands/resolver/prompts/repo_instructions/all-hands-ai___openhands-resolver.txt @@ -0,0 +1,4 @@ +This is a Python repo for openhands-resolver, a library that attempts to resolve github issues with the AI agent OpenHands. + +- Setup: `poetry install --with test --with dev` +- Testing: `poetry run pytest tests/test_*.py` \ No newline at end of file diff --git a/openhands/resolver/prompts/repo_instructions/all-hands-ai___openhands.txt b/openhands/resolver/prompts/repo_instructions/all-hands-ai___openhands.txt new file mode 100644 index 000000000000..015ea101a075 --- /dev/null +++ b/openhands/resolver/prompts/repo_instructions/all-hands-ai___openhands.txt @@ -0,0 +1,7 @@ +OpenHands is an automated AI software engineer. It is a repo with a Python backend +(in the `openhands` directory) and typescript frontend (in the `frontend` directory). + +- Setup: To set up the repo, including frontend/backend you can `make build` +- Backend Testing: All tests are in `tests/unit/test_*.py`. To test new code, you + can do `poetry run pytest tests/unit/test_xxx.py` where `xxx` is the appropriate + file for the current functionality. Write all tests with pytest. diff --git a/openhands/resolver/prompts/repo_instructions/rbren___rss-parser.txt b/openhands/resolver/prompts/repo_instructions/rbren___rss-parser.txt new file mode 100644 index 000000000000..b6e8fba1a200 --- /dev/null +++ b/openhands/resolver/prompts/repo_instructions/rbren___rss-parser.txt @@ -0,0 +1,4 @@ +This is a node repo for an RSS parser. +- Setup: `yes | npm install` +- Testing: `SKIP_BROWSER_TESTS=1 npm test` +- Writing Tests: Add to the `test` directory. \ No newline at end of file diff --git a/openhands/resolver/prompts/resolve/basic-followup.jinja b/openhands/resolver/prompts/resolve/basic-followup.jinja new file mode 100644 index 000000000000..cf26d80b3bdd --- /dev/null +++ b/openhands/resolver/prompts/resolve/basic-followup.jinja @@ -0,0 +1,24 @@ +The current code is an attempt at fixing one or more issues. The code is not satisfactory and follow up feedback have been provided to address this. +The feedback may be addressed to specific code files. In this case the file locations will be provided. +Please update the code based on the feedback for the repository in /workspace. +An environment has been set up for you to start working. You may assume all necessary tools are installed. + +# Issues addressed +{{ issues }} + +# Review comments +{{ review_comments }} + +# Review threads +{{ review_threads }} + +# Review thread files +{{ files }} + +IMPORTANT: You should ONLY interact with the environment provided to you AND NEVER ASK FOR HUMAN HELP. +You SHOULD INCLUDE PROPER INDENTATION in your edit commands.{% if repo_instruction %} + +Some basic information about this repository: +{{ repo_instruction }}{% endif %} + +When you think you have fixed the issue through code changes, please finish the interaction. \ No newline at end of file diff --git a/openhands/resolver/prompts/resolve/basic-with-tests.jinja b/openhands/resolver/prompts/resolve/basic-with-tests.jinja new file mode 100644 index 000000000000..54c35910ec62 --- /dev/null +++ b/openhands/resolver/prompts/resolve/basic-with-tests.jinja @@ -0,0 +1,17 @@ +Please fix the following issue for the repository in /workspace. +An environment has been set up for you to start working. You may assume all necessary tools are installed. + +# Problem Statement +{{ body }} + +IMPORTANT: You should ONLY interact with the environment provided to you AND NEVER ASK FOR HUMAN HELP. +You SHOULD INCLUDE PROPER INDENTATION in your edit commands.{% if repo_instruction %} + +Some basic information about this repository: +{{ repo_instruction }}{% endif %} + +For all changes to actual application code (e.g. in Python or Javascript), add an appropriate test to the testing directory to make sure that the issue has been fixed. +Run the tests, and if they pass you are done! +You do NOT need to write new tests if there are only changes to documentation or configuration files. + +When you think you have fixed the issue through code changes, please call the finish action to end the interaction. \ No newline at end of file diff --git a/openhands/resolver/prompts/resolve/basic.jinja b/openhands/resolver/prompts/resolve/basic.jinja new file mode 100644 index 000000000000..b3bec7ef7f53 --- /dev/null +++ b/openhands/resolver/prompts/resolve/basic.jinja @@ -0,0 +1,13 @@ +Please fix the following issue for the repository in /workspace. +An environment has been set up for you to start working. You may assume all necessary tools are installed. + +# Problem Statement +{{ body }} + +IMPORTANT: You should ONLY interact with the environment provided to you AND NEVER ASK FOR HUMAN HELP. +You SHOULD INCLUDE PROPER INDENTATION in your edit commands.{% if repo_instruction %} + +Some basic information about this repository: +{{ repo_instruction }}{% endif %} + +When you think you have fixed the issue through code changes, please finish the interaction. \ No newline at end of file diff --git a/openhands/resolver/prompts/resolve/pr-changes-summary.jinja b/openhands/resolver/prompts/resolve/pr-changes-summary.jinja new file mode 100644 index 000000000000..ba9b1bcab4b0 --- /dev/null +++ b/openhands/resolver/prompts/resolve/pr-changes-summary.jinja @@ -0,0 +1,3 @@ +Please create a concise overview of the following changes, commenting on whether all issues have been successfully resolved or if there are still issues remaining: + +{{ comment_message }} diff --git a/openhands/resolver/resolve_all_issues.py b/openhands/resolver/resolve_all_issues.py new file mode 100644 index 000000000000..86b4708ea6d3 --- /dev/null +++ b/openhands/resolver/resolve_all_issues.py @@ -0,0 +1,383 @@ +# flake8: noqa: E501 + +import asyncio +import argparse +import multiprocessing as mp +import os +import pathlib +import subprocess +from typing import Awaitable, TextIO +from tqdm import tqdm + +from openhands.resolver.github_issue import GithubIssue +from openhands.resolver.resolver_output import ResolverOutput +import openhands +from openhands.core.logger import openhands_logger as logger +from openhands.core.config import LLMConfig +from openhands.resolver.resolve_issue import ( + process_issue, + issue_handler_factory, +) + + +def cleanup(): + print("Cleaning up child processes...") + for process in mp.active_children(): + print(f"Terminating child process: {process.name}") + process.terminate() + process.join() + + +# This function tracks the progress AND write the output to a JSONL file +async def update_progress(output: Awaitable[ResolverOutput], output_fp: TextIO, pbar: tqdm) -> None: + resolved_output = await output + pbar.update(1) + pbar.set_description(f'issue {resolved_output.issue.number}') + pbar.set_postfix_str( + f'Test Result: {resolved_output.metrics.get("test_result", "N/A") if resolved_output.metrics else "N/A"}' + ) + logger.info( + f'Finished issue {resolved_output.issue.number}: {resolved_output.metrics.get("test_result", "N/A") if resolved_output.metrics else "N/A"}' + ) + output_fp.write(resolved_output.model_dump_json() + "\n") + output_fp.flush() + +async def resolve_issues( + owner: str, + repo: str, + token: str, + username: str, + max_iterations: int, + limit_issues: int | None, + num_workers: int, + output_dir: str, + llm_config: LLMConfig, + runtime_container_image: str, + prompt_template: str, + issue_type: str, + repo_instruction: str | None, + issue_numbers: list[int] | None, +) -> None: + """Resolve multiple github issues. + + Args: + owner: Github owner of the repo. + repo: Github repository to resolve issues in form of `owner/repo`. + token: Github token to access the repository. + username: Github username to access the repository. + max_iterations: Maximum number of iterations to run + limit_issues: Limit the number of issues to resolve. + num_workers: Number of workers to use for parallel processing. + output_dir: Output directory to write the results. + runtime_container_image: Container image to use. + prompt_template: Prompt template to use. + repo_instruction: Repository instruction to use. + issue_numbers: List of issue numbers to resolve. + """ + + issue_handler = issue_handler_factory(issue_type, owner, repo, token) + + # Load dataset + issues: list[GithubIssue] = issue_handler.get_converted_issues() + + if issue_numbers is not None: + issues = [issue for issue in issues if issue.number in issue_numbers] + logger.info(f"Limiting resolving to issues {issue_numbers}.") + if limit_issues is not None: + issues = issues[:limit_issues] + logger.info(f"Limiting resolving to first {limit_issues} issues.") + + # TEST METADATA + model_name = llm_config.model.split("/")[-1] + + pathlib.Path(output_dir).mkdir(parents=True, exist_ok=True) + pathlib.Path(os.path.join(output_dir, "infer_logs")).mkdir( + parents=True, exist_ok=True + ) + logger.info(f"Using output directory: {output_dir}") + + # checkout the repo + repo_dir = os.path.join(output_dir, "repo") + if not os.path.exists(repo_dir): + checkout_output = subprocess.check_output( + [ + "git", + "clone", + f"https://{username}:{token}@github.com/{owner}/{repo}", + f"{output_dir}/repo", + ] + ).decode("utf-8") + if "fatal" in checkout_output: + raise RuntimeError(f"Failed to clone repository: {checkout_output}") + + # get the commit id of current repo for reproducibility + base_commit = ( + subprocess.check_output( + ["git", "rev-parse", "HEAD"], cwd=repo_dir + ) + .decode("utf-8") + .strip() + ) + logger.info(f"Base commit: {base_commit}") + + if repo_instruction is None: + # Check for .openhands_instructions file in the workspace directory + openhands_instructions_path = os.path.join(repo_dir, '.openhands_instructions') + if os.path.exists(openhands_instructions_path): + with open(openhands_instructions_path, 'r') as f: + repo_instruction = f.read() + + # OUTPUT FILE + output_file = os.path.join(output_dir, "output.jsonl") + logger.info(f"Writing output to {output_file}") + finished_numbers = set() + if os.path.exists(output_file): + with open(output_file, "r") as f: + for line in f: + data = ResolverOutput.model_validate_json(line) + finished_numbers.add(data.issue.number) + logger.warning( + f"Output file {output_file} already exists. Loaded {len(finished_numbers)} finished issues." + ) + output_fp = open(output_file, "a") + + logger.info( + f"Resolving issues with model {model_name}, max iterations {max_iterations}." + ) + + # ============================================= + # filter out finished issues + new_issues = [] + for issue in issues: + if issue.number in finished_numbers: + logger.info(f"Skipping issue {issue.number} as it is already finished.") + continue + new_issues.append(issue) + logger.info( + f"Finished issues: {len(finished_numbers)}, Remaining issues: {len(issues)}" + ) + # ============================================= + + pbar = tqdm(total=len(issues)) + + # This sets the multi-processing + logger.info(f"Using {num_workers} workers.") + + try: + tasks = [] + for issue in issues: + + # checkout to pr branch + if issue_type == "pr": + logger.info(f"Checking out to PR branch {issue.head_branch} for issue {issue.number}") + + subprocess.check_output( + ["git", "checkout", f"{issue.head_branch}"], + cwd=repo_dir, + ) + + base_commit = ( + subprocess.check_output( + ["git", "rev-parse", "HEAD"], cwd=repo_dir + ) + .decode("utf-8") + .strip() + ) + + task = update_progress( + process_issue( + issue, + base_commit, + max_iterations, + llm_config, + output_dir, + runtime_container_image, + prompt_template, + issue_handler, + repo_instruction, + bool(num_workers > 1), + ), + output_fp, + pbar, + ) + tasks.append(task) + + # Use asyncio.gather with a semaphore to limit concurrency + sem = asyncio.Semaphore(num_workers) + + async def run_with_semaphore(task): + async with sem: + return await task + + await asyncio.gather(*[run_with_semaphore(task) for task in tasks]) + + except KeyboardInterrupt: + print("KeyboardInterrupt received. Cleaning up...") + cleanup() + + output_fp.close() + logger.info("Finished.") + + +def main(): + parser = argparse.ArgumentParser(description="Resolve multiple issues from Github.") + parser.add_argument( + "--repo", + type=str, + required=True, + help="Github repository to resolve issues in form of `owner/repo`.", + ) + parser.add_argument( + "--token", + type=str, + default=None, + help="Github token to access the repository.", + ) + parser.add_argument( + "--username", + type=str, + default=None, + help="Github username to access the repository.", + ) + parser.add_argument( + "--runtime-container-image", + type=str, + default=None, + help="Container image to use.", + ) + parser.add_argument( + "--max-iterations", + type=int, + default=50, + help="Maximum number of iterations to run.", + ) + parser.add_argument( + "--limit-issues", + type=int, + default=None, + help="Limit the number of issues to resolve.", + ) + parser.add_argument( + "--issue-numbers", + type=str, + default=None, + help="Comma separated list of issue numbers to resolve.", + ) + parser.add_argument( + "--num-workers", + type=int, + default=1, + help="Number of workers to use for parallel processing.", + ) + parser.add_argument( + "--output-dir", + type=str, + default="output", + help="Output directory to write the results.", + ) + parser.add_argument( + "--llm-model", + type=str, + default=None, + help="LLM model to use.", + ) + parser.add_argument( + "--llm-api-key", + type=str, + default=None, + help="LLM API key to use.", + ) + parser.add_argument( + "--llm-base-url", + type=str, + default=None, + help="LLM base URL to use.", + ) + parser.add_argument( + "--prompt-file", + type=str, + default=None, + help="Path to the prompt template file in Jinja format.", + ) + parser.add_argument( + "--repo-instruction-file", + type=str, + default=None, + help="Path to the repository instruction file in text format.", + ) + parser.add_argument( + "--issue-type", + type=str, + default="issue", + choices=["issue", "pr"], + help="Type of issue to resolve, either open issue or pr comments.", + ) + + my_args = parser.parse_args() + + runtime_container_image = my_args.runtime_container_image + if runtime_container_image is None: + runtime_container_image = f"ghcr.io/all-hands-ai/runtime:{openhands.__version__}-nikolaik" + + owner, repo = my_args.repo.split("/") + token = ( + my_args.token if my_args.token else os.getenv("GITHUB_TOKEN") + ) + username = ( + my_args.username + if my_args.username + else os.getenv("GITHUB_USERNAME") + ) + + if not token: + raise ValueError("Github token is required.") + + llm_config = LLMConfig( + model=my_args.llm_model or os.environ["LLM_MODEL"], + api_key=my_args.llm_api_key or os.environ["LLM_API_KEY"], + base_url=my_args.llm_base_url or os.environ.get("LLM_BASE_URL", None), + ) + + repo_instruction = None + if my_args.repo_instruction_file: + with open(my_args.repo_instruction_file, 'r') as f: + repo_instruction = f.read() + + issue_numbers = None + if my_args.issue_numbers: + issue_numbers = [int(number) for number in my_args.issue_numbers.split(",")] + + issue_type = my_args.issue_type + + # Read the prompt template + prompt_file = my_args.prompt_file + if prompt_file is None: + if issue_type == "issue": + prompt_file = os.path.join(os.path.dirname(__file__), "prompts/resolve/basic-with-tests.jinja") + else: + prompt_file = os.path.join(os.path.dirname(__file__), "prompts/resolve/basic-followup.jinja") + with open(prompt_file, 'r') as f: + prompt_template = f.read() + + asyncio.run( + resolve_issues( + owner=owner, + repo=repo, + token=token, + username=username, + runtime_container_image=runtime_container_image, + max_iterations=my_args.max_iterations, + limit_issues=my_args.limit_issues, + num_workers=my_args.num_workers, + output_dir=my_args.output_dir, + llm_config=llm_config, + prompt_template=prompt_template, + issue_type=issue_type, + repo_instruction=repo_instruction, + issue_numbers=issue_numbers, + ) + ) + + +if __name__ == "__main__": + main() \ No newline at end of file diff --git a/openhands/resolver/resolve_issue.py b/openhands/resolver/resolve_issue.py new file mode 100644 index 000000000000..7ed8a39fb0e6 --- /dev/null +++ b/openhands/resolver/resolve_issue.py @@ -0,0 +1,609 @@ +# flake8: noqa: E501 + +import asyncio +import dataclasses +import os +import pathlib +import shutil +import subprocess +import json +from typing import Any +from uuid import uuid4 +from termcolor import colored + +from openhands.resolver.github_issue import GithubIssue +from openhands.resolver.issue_definitions import ( + IssueHandler, + IssueHandlerInterface, + PRHandler +) +from openhands.resolver.resolver_output import ResolverOutput +import openhands +from openhands.core.main import create_runtime, run_controller +from openhands.controller.state.state import State +from openhands.core.logger import openhands_logger as logger +from openhands.events.action import CmdRunAction, MessageAction +from openhands.events.stream import EventStreamSubscriber +from openhands.events.observation import ( + CmdOutputObservation, + ErrorObservation, + Observation, +) +from openhands.core.config import ( + AppConfig, + SandboxConfig, + AgentConfig, +) +from openhands.core.config import LLMConfig +from openhands.runtime.base import Runtime +from openhands.resolver.utils import ( + codeact_user_response, + reset_logger_for_multiprocessing, +) + + +# Don't make this confgurable for now, unless we have other competitive agents +AGENT_CLASS = "CodeActAgent" + + +def initialize_runtime( + runtime: Runtime, +): + """Initialize the runtime for the agent. + + This function is called before the runtime is used to run the agent. + Currently it does nothing. + """ + logger.info('-' * 30) + logger.info('BEGIN Runtime Completion Fn') + logger.info('-' * 30) + obs: Observation + + action = CmdRunAction(command='cd /workspace') + logger.info(action, extra={'msg_type': 'ACTION'}) + obs = runtime.run_action(action) + logger.info(obs, extra={'msg_type': 'OBSERVATION'}) + if not isinstance(obs, CmdOutputObservation) or obs.exit_code != 0: + raise RuntimeError( + f"Failed to change directory to /workspace.\n{obs}" + ) + + action = CmdRunAction(command='git config --global core.pager ""') + logger.info(action, extra={'msg_type': 'ACTION'}) + obs = runtime.run_action(action) + logger.info(obs, extra={'msg_type': 'OBSERVATION'}) + if not isinstance(obs, CmdOutputObservation) or obs.exit_code != 0: + raise RuntimeError(f"Failed to set git config.\n{obs}") + + +async def complete_runtime( + runtime: Runtime, + base_commit: str, +) -> dict[str, Any]: + """Complete the runtime for the agent. + + This function is called before the runtime is used to run the agent. + If you need to do something in the sandbox to get the correctness metric after + the agent has run, modify this function. + """ + logger.info('-' * 30) + logger.info('BEGIN Runtime Completion Fn') + logger.info('-' * 30) + obs: Observation + + action = CmdRunAction(command='cd /workspace') + logger.info(action, extra={'msg_type': 'ACTION'}) + obs = runtime.run_action(action) + logger.info(obs, extra={'msg_type': 'OBSERVATION'}) + if not isinstance(obs, CmdOutputObservation) or obs.exit_code != 0: + raise RuntimeError( + f"Failed to change directory to /workspace. Observation: {obs}" + ) + + action = CmdRunAction(command='git config --global core.pager ""') + logger.info(action, extra={'msg_type': 'ACTION'}) + obs = runtime.run_action(action) + logger.info(obs, extra={'msg_type': 'OBSERVATION'}) + if not isinstance(obs, CmdOutputObservation) or obs.exit_code != 0: + raise RuntimeError(f"Failed to set git config. Observation: {obs}") + + action = CmdRunAction(command='git config --global --add safe.directory /workspace') + logger.info(action, extra={'msg_type': 'ACTION'}) + obs = runtime.run_action(action) + logger.info(obs, extra={'msg_type': 'OBSERVATION'}) + if not isinstance(obs, CmdOutputObservation) or obs.exit_code != 0: + raise RuntimeError(f"Failed to set git config. Observation: {obs}") + + action = CmdRunAction(command='git add -A') + logger.info(action, extra={'msg_type': 'ACTION'}) + obs = runtime.run_action(action) + logger.info(obs, extra={'msg_type': 'OBSERVATION'}) + if not isinstance(obs, CmdOutputObservation) or obs.exit_code != 0: + raise RuntimeError(f"Failed to git add. Observation: {obs}") + + n_retries = 0 + git_patch = None + while n_retries < 5: + action = CmdRunAction( + command=f'git diff --no-color --cached {base_commit}', + keep_prompt=False, + ) + action.timeout = 600 + 100 * n_retries + logger.info(action, extra={'msg_type': 'ACTION'}) + obs = runtime.run_action(action) + logger.info(obs, extra={'msg_type': 'OBSERVATION'}) + n_retries += 1 + if isinstance(obs, CmdOutputObservation): + if obs.exit_code == 0: + git_patch = obs.content.strip() + break + else: + logger.info('Failed to get git diff, retrying...') + await asyncio.sleep(10) + elif isinstance(obs, ErrorObservation): + logger.error(f'Error occurred: {obs.content}. Retrying...') + await asyncio.sleep(10) + else: + raise ValueError(f'Unexpected observation type: {type(obs)}') + + logger.info('-' * 30) + logger.info('END Runtime Completion Fn') + logger.info('-' * 30) + return {'git_patch': git_patch} + + +async def process_issue( + issue: GithubIssue, + base_commit: str, + max_iterations: int, + llm_config: LLMConfig, + output_dir: str, + runtime_container_image: str, + prompt_template: str, + issue_handler: IssueHandlerInterface, + repo_instruction: str | None = None, + reset_logger: bool = False, +) -> ResolverOutput: + + # Setup the logger properly, so you can run multi-processing to parallelize processing + if reset_logger: + log_dir = os.path.join(output_dir, 'infer_logs') + reset_logger_for_multiprocessing(logger, str(issue.number), log_dir) + else: + logger.info(f'Starting fixing issue {issue.number}.') + + workspace_base = os.path.join(output_dir, "workspace", f"{issue_handler.issue_type}_{issue.number}") + + # Get the absolute path of the workspace base + workspace_base = os.path.abspath(workspace_base) + # write the repo to the workspace + if os.path.exists(workspace_base): + shutil.rmtree(workspace_base) + shutil.copytree(os.path.join(output_dir, "repo"), workspace_base) + + config = AppConfig( + default_agent="CodeActAgent", + runtime='eventstream', + max_budget_per_task=4, + max_iterations=max_iterations, + sandbox=SandboxConfig( + runtime_container_image=runtime_container_image, + enable_auto_lint=False, + use_host_network=False, + # large enough timeout, since some testcases take very long to run + timeout=300, + ), + # do not mount workspace + workspace_base=workspace_base, + workspace_mount_path=workspace_base, + agents={ + "CodeActAgent": AgentConfig( + disabled_microagents=["github"] + ) + }, + ) + config.set_llm_config(llm_config) + + runtime = create_runtime(config, sid=f"{issue.number}") + await runtime.connect() + async def on_event(evt): + logger.info(evt) + runtime.event_stream.subscribe(EventStreamSubscriber.MAIN, on_event, str(uuid4())) + + initialize_runtime(runtime) + + instruction, images_urls = issue_handler.get_instruction(issue, prompt_template, repo_instruction) + # Here's how you can run the agent (similar to the `main` function) and get the final task state + action = MessageAction( + content=instruction, + image_urls=images_urls + ) + try: + state: State | None = await run_controller( + config=config, + initial_user_action=action, + runtime=runtime, + fake_user_response_fn=codeact_user_response, + ) + if state is None: + raise RuntimeError("Failed to run the agent.") + except (ValueError, RuntimeError) as e: + error_msg = f"Agent failed with error: {str(e)}" + logger.error(error_msg) + state = None + last_error: str | None = error_msg + + # Get git patch + return_val = await complete_runtime(runtime, base_commit) + git_patch = return_val['git_patch'] + logger.info( + f'Got git diff for instance {issue.number}:\n--------\n{git_patch}\n--------' + ) + + # Serialize histories and set defaults for failed state + if state is None: + histories = [] + metrics = None + success = False + comment_success = None + success_explanation = "Agent failed to run" + last_error = "Agent failed to run or crashed" + else: + histories = [dataclasses.asdict(event) for event in state.history] + metrics = state.metrics.get() if state.metrics else None + # determine success based on the history and the issue description + success, comment_success, success_explanation = issue_handler.guess_success(issue, state.history, llm_config) + + if issue_handler.issue_type == "pr" and comment_success: + success_log = "I have updated the PR and resolved some of the issues that were cited in the pull request review. Specifically, I identified the following revision requests, and all the ones that I think I successfully resolved are checked off. All the unchecked ones I was not able to resolve, so manual intervention may be required:\n" + try: + explanations = json.loads(success_explanation) + except json.JSONDecodeError: + logger.error(f"Failed to parse success_explanation as JSON: {success_explanation}") + explanations = [str(success_explanation)] # Use raw string as fallback + + for success_indicator, explanation in zip(comment_success, explanations): + status = colored("[X]", "red") if success_indicator else colored("[ ]", "red") + bullet_point = colored("-", "yellow") + success_log += f"\n{bullet_point} {status}: {explanation}" + logger.info(success_log) + last_error = state.last_error if state.last_error else None + + # Save the output + output = ResolverOutput( + issue=issue, + issue_type=issue_handler.issue_type, + instruction=instruction, + base_commit=base_commit, + git_patch=git_patch, + history=histories, + metrics=metrics, + success=success, + comment_success=comment_success, + success_explanation=success_explanation, + error=last_error, + ) + return output + + +def issue_handler_factory(issue_type: str, owner: str, repo: str, token: str) -> IssueHandlerInterface: + if issue_type == "issue": + return IssueHandler(owner, repo, token) + elif issue_type == "pr": + return PRHandler(owner, repo, token) + else: + raise ValueError(f"Invalid issue type: {issue_type}") + + +async def resolve_issue( + owner: str, + repo: str, + token: str, + username: str, + max_iterations: int, + output_dir: str, + llm_config: LLMConfig, + runtime_container_image: str, + prompt_template: str, + issue_type: str, + repo_instruction: str | None, + issue_number: int, + comment_id: int | None, + reset_logger: bool = False, +) -> None: + """Resolve a single github issue. + + Args: + owner: Github owner of the repo. + repo: Github repository to resolve issues in form of `owner/repo`. + token: Github token to access the repository. + username: Github username to access the repository. + max_iterations: Maximum number of iterations to run + output_dir: Output directory to write the results. + runtime_container_image: Container image to use. + prompt_template: Prompt template to use. + repo_instruction: Repository instruction to use. + issue_number: Issue number to resolve. + """ + + issue_handler = issue_handler_factory(issue_type, owner, repo, token) + + # Load dataset + issues: list[GithubIssue] = issue_handler.get_converted_issues(comment_id=comment_id) + + # Find the specific issue + issue = next((i for i in issues if i.number == issue_number), None) + if not issue: + raise ValueError(f"Issue {issue_number} not found") + + if comment_id is not None: + if (issue_type == 'pr' + and not issue.review_comments + and not issue.review_threads + and not issue.thread_comments): + raise ValueError(f"Comment ID {comment_id} did not have a match for issue {issue.number}") + + if (issue_type == 'issue' + and not issue.thread_comments): + raise ValueError(f"Comment ID {comment_id} did not have a match for issue {issue.number}") + + + + # TEST METADATA + model_name = llm_config.model.split("/")[-1] + + pathlib.Path(output_dir).mkdir(parents=True, exist_ok=True) + pathlib.Path(os.path.join(output_dir, "infer_logs")).mkdir( + parents=True, exist_ok=True + ) + logger.info(f"Using output directory: {output_dir}") + + # checkout the repo + repo_dir = os.path.join(output_dir, "repo") + if not os.path.exists(repo_dir): + checkout_output = subprocess.check_output( + [ + "git", + "clone", + f"https://{username}:{token}@github.com/{owner}/{repo}", + f"{output_dir}/repo", + ] + ).decode("utf-8") + if "fatal" in checkout_output: + raise RuntimeError(f"Failed to clone repository: {checkout_output}") + + # get the commit id of current repo for reproducibility + base_commit = ( + subprocess.check_output( + ["git", "rev-parse", "HEAD"], cwd=repo_dir + ) + .decode("utf-8") + .strip() + ) + logger.info(f"Base commit: {base_commit}") + + if repo_instruction is None: + # Check for .openhands_instructions file in the workspace directory + openhands_instructions_path = os.path.join(repo_dir, '.openhands_instructions') + if os.path.exists(openhands_instructions_path): + with open(openhands_instructions_path, 'r') as f: + repo_instruction = f.read() + + # OUTPUT FILE + output_file = os.path.join(output_dir, "output.jsonl") + logger.info(f"Writing output to {output_file}") + + # Check if this issue was already processed + if os.path.exists(output_file): + with open(output_file, "r") as f: + for line in f: + data = ResolverOutput.model_validate_json(line) + if data.issue.number == issue_number: + logger.warning(f"Issue {issue_number} was already processed. Skipping.") + return + + output_fp = open(output_file, "a") + + logger.info( + f"Resolving issue {issue_number} with Agent {AGENT_CLASS}, model {model_name}, max iterations {max_iterations}." + ) + + try: + # checkout to pr branch if needed + if issue_type == "pr": + logger.info(f"Checking out to PR branch {issue.head_branch} for issue {issue.number}") + + subprocess.check_output( + ["git", "checkout", f"{issue.head_branch}"], + cwd=repo_dir, + ) + + base_commit = ( + subprocess.check_output( + ["git", "rev-parse", "HEAD"], cwd=repo_dir + ) + .decode("utf-8") + .strip() + ) + + output = await process_issue( + issue, + base_commit, + max_iterations, + llm_config, + output_dir, + runtime_container_image, + prompt_template, + issue_handler, + repo_instruction, + reset_logger, + ) + output_fp.write(output.model_dump_json() + "\n") + output_fp.flush() + + finally: + output_fp.close() + logger.info("Finished.") + + +def main(): + import argparse + + def int_or_none(value): + if value.lower() == 'none': + return None + else: + return int(value) + + + parser = argparse.ArgumentParser(description="Resolve a single issue from Github.") + parser.add_argument( + "--repo", + type=str, + required=True, + help="Github repository to resolve issues in form of `owner/repo`.", + ) + parser.add_argument( + "--token", + type=str, + default=None, + help="Github token to access the repository.", + ) + parser.add_argument( + "--username", + type=str, + default=None, + help="Github username to access the repository.", + ) + parser.add_argument( + "--runtime-container-image", + type=str, + default=None, + help="Container image to use.", + ) + parser.add_argument( + "--max-iterations", + type=int, + default=50, + help="Maximum number of iterations to run.", + ) + parser.add_argument( + "--issue-number", + type=int, + required=True, + help="Issue number to resolve.", + ) + parser.add_argument( + "--comment-id", + type=int_or_none, + required=False, + default=None, + help="Resolve a specific comment" + ) + parser.add_argument( + "--output-dir", + type=str, + default="output", + help="Output directory to write the results.", + ) + parser.add_argument( + "--llm-model", + type=str, + default=None, + help="LLM model to use.", + ) + parser.add_argument( + "--llm-api-key", + type=str, + default=None, + help="LLM API key to use.", + ) + parser.add_argument( + "--llm-base-url", + type=str, + default=None, + help="LLM base URL to use.", + ) + parser.add_argument( + "--prompt-file", + type=str, + default=None, + help="Path to the prompt template file in Jinja format.", + ) + parser.add_argument( + "--repo-instruction-file", + type=str, + default=None, + help="Path to the repository instruction file in text format.", + ) + parser.add_argument( + "--issue-type", + type=str, + default="issue", + choices=["issue", "pr"], + help="Type of issue to resolve, either open issue or pr comments.", + ) + + my_args = parser.parse_args() + + runtime_container_image = my_args.runtime_container_image + if runtime_container_image is None: + runtime_container_image = f"ghcr.io/all-hands-ai/runtime:{openhands.__version__}-nikolaik" + + owner, repo = my_args.repo.split("/") + token = ( + my_args.token if my_args.token else os.getenv("GITHUB_TOKEN") + ) + username = ( + my_args.username + if my_args.username + else os.getenv("GITHUB_USERNAME") + ) + + if not token: + raise ValueError("Github token is required.") + + llm_config = LLMConfig( + model=my_args.llm_model or os.environ["LLM_MODEL"], + api_key=my_args.llm_api_key or os.environ["LLM_API_KEY"], + base_url=my_args.llm_base_url or os.environ.get("LLM_BASE_URL", None), + ) + + repo_instruction = None + if my_args.repo_instruction_file: + with open(my_args.repo_instruction_file, 'r') as f: + repo_instruction = f.read() + + issue_type = my_args.issue_type + + # Read the prompt template + prompt_file = my_args.prompt_file + if prompt_file is None: + if issue_type == "issue": + prompt_file = os.path.join(os.path.dirname(__file__), "prompts/resolve/basic-with-tests.jinja") + else: + prompt_file = os.path.join(os.path.dirname(__file__), "prompts/resolve/basic-followup.jinja") + with open(prompt_file, 'r') as f: + prompt_template = f.read() + + asyncio.run( + resolve_issue( + owner=owner, + repo=repo, + token=token, + username=username, + runtime_container_image=runtime_container_image, + max_iterations=my_args.max_iterations, + output_dir=my_args.output_dir, + llm_config=llm_config, + prompt_template=prompt_template, + issue_type=issue_type, + repo_instruction=repo_instruction, + issue_number=my_args.issue_number, + comment_id=my_args.comment_id, + ) + ) + + +if __name__ == "__main__": + main() diff --git a/openhands/resolver/resolver_output.py b/openhands/resolver/resolver_output.py new file mode 100644 index 000000000000..33ebbf6ed1ce --- /dev/null +++ b/openhands/resolver/resolver_output.py @@ -0,0 +1,18 @@ +from typing import Any +from litellm import BaseModel +from openhands.resolver.github_issue import GithubIssue + + +class ResolverOutput(BaseModel): + # NOTE: User-specified + issue: GithubIssue + issue_type: str + instruction: str + base_commit: str + git_patch: str + history: list[dict[str, Any]] + metrics: dict[str, Any] | None + success: bool + comment_success: list[bool] | None + success_explanation: str + error: str | None diff --git a/openhands/resolver/send_pull_request.py b/openhands/resolver/send_pull_request.py new file mode 100644 index 000000000000..1dd466c6812a --- /dev/null +++ b/openhands/resolver/send_pull_request.py @@ -0,0 +1,623 @@ +import argparse +import os +import shutil + +import litellm +import jinja2 +from openhands.resolver.github_issue import GithubIssue +from openhands.resolver.io_utils import ( + load_all_resolver_outputs, + load_single_resolver_output, +) +from openhands.resolver.patching import parse_patch, apply_diff +import requests +import subprocess +import json + +from openhands.core.config import LLMConfig +from openhands.core.logger import openhands_logger as logger +from openhands.resolver.resolver_output import ResolverOutput + + +def apply_patch(repo_dir: str, patch: str) -> None: + diffs = parse_patch(patch) + for diff in diffs: + if not diff.header.new_path: + print("Warning: Could not determine file to patch") + continue + + # Remove both "a/" and "b/" prefixes from paths + old_path = ( + os.path.join(repo_dir, diff.header.old_path.removeprefix("a/").removeprefix("b/")) + if diff.header.old_path and diff.header.old_path != "/dev/null" + else None + ) + new_path = os.path.join(repo_dir, diff.header.new_path.removeprefix("a/").removeprefix("b/")) + + # Check if the file is being deleted + if diff.header.new_path == "/dev/null": + assert old_path is not None + if os.path.exists(old_path): + os.remove(old_path) + print(f"Deleted file: {old_path}") + continue + + # Handle file rename + if old_path and new_path and "rename from" in patch: + # Create parent directory of new path + os.makedirs(os.path.dirname(new_path), exist_ok=True) + try: + # Try to move the file directly + shutil.move(old_path, new_path) + except shutil.SameFileError: + # If it's the same file (can happen with directory renames), copy first then remove + shutil.copy2(old_path, new_path) + os.remove(old_path) + + # Try to remove empty parent directories + old_dir = os.path.dirname(old_path) + while old_dir and old_dir.startswith(repo_dir): + try: + os.rmdir(old_dir) + old_dir = os.path.dirname(old_dir) + except OSError: + # Directory not empty or other error, stop trying to remove parents + break + continue + + if old_path: + # Open the file in binary mode to detect line endings + with open(old_path, "rb") as f: + original_content = f.read() + + # Detect line endings + if b"\r\n" in original_content: + newline = "\r\n" + elif b"\n" in original_content: + newline = "\n" + else: + newline = None # Let Python decide + + try: + with open(old_path, "r", newline=newline) as f: + split_content = [x.strip(newline) for x in f.readlines()] + except UnicodeDecodeError as e: + logger.error(f"Error reading file {old_path}: {e}") + split_content = [] + else: + newline = "\n" + split_content = [] + + if diff.changes is None: + print(f"Warning: No changes to apply for {old_path}") + continue + + new_content = apply_diff(diff, split_content) + + # Ensure the directory exists before writing the file + os.makedirs(os.path.dirname(new_path), exist_ok=True) + + # Write the new content using the detected line endings + with open(new_path, "w", newline=newline) as f: + for line in new_content: + print(line, file=f) + + print("Patch applied successfully") + + +def initialize_repo( + output_dir: str, issue_number: int, issue_type: str, base_commit: str | None = None +) -> str: + src_dir = os.path.join(output_dir, "repo") + dest_dir = os.path.join(output_dir, "patches", f"{issue_type}_{issue_number}") + + if not os.path.exists(src_dir): + raise ValueError(f"Source directory {src_dir} does not exist.") + + if os.path.exists(dest_dir): + shutil.rmtree(dest_dir) + + shutil.copytree(src_dir, dest_dir) + print(f"Copied repository to {dest_dir}") + + if base_commit: + result = subprocess.run( + f"git -C {dest_dir} checkout {base_commit}", + shell=True, + capture_output=True, + text=True, + ) + if result.returncode != 0: + print(f"Error checking out commit: {result.stderr}") + raise RuntimeError("Failed to check out commit") + + return dest_dir + + +def make_commit(repo_dir: str, issue: GithubIssue, issue_type: str) -> None: + # Check if git username is set + result = subprocess.run( + f"git -C {repo_dir} config user.name", + shell=True, + capture_output=True, + text=True, + ) + + if not result.stdout.strip(): + # If username is not set, configure git + subprocess.run( + f'git -C {repo_dir} config user.name "openhands" && ' + f'git -C {repo_dir} config user.email "openhands@all-hands.dev" && ' + f'git -C {repo_dir} config alias.git "git --no-pager"', + shell=True, + check=True, + ) + print("Git user configured as openhands") + + result = subprocess.run( + f"git -C {repo_dir} add .", shell=True, capture_output=True, text=True + ) + if result.returncode != 0: + print(f"Error adding files: {result.stderr}") + raise RuntimeError("Failed to add files to git") + + status_result = subprocess.run( + f"git -C {repo_dir} status --porcelain", + shell=True, + capture_output=True, + text=True, + ) + + if not status_result.stdout.strip(): + print(f"No changes to commit for issue #{issue.number}. Skipping commit.") + raise RuntimeError("ERROR: Openhands failed to make code changes.") + + + commit_message = f"Fix {issue_type} #{issue.number}: {issue.title}" + result = subprocess.run( + ["git", "-C", repo_dir, "commit", "-m", commit_message], + capture_output=True, + text=True, + ) + if result.returncode != 0: + raise RuntimeError(f"Failed to commit changes: {result}") + + + + +def branch_exists(base_url: str, branch_name: str, headers: dict) -> bool: + print(f"Checking if branch {branch_name} exists...") + response = requests.get(f"{base_url}/branches/{branch_name}", headers=headers) + exists = response.status_code == 200 + print(f"Branch {branch_name} exists: {exists}") + return exists + +def send_pull_request( + github_issue: GithubIssue, + github_token: str, + github_username: str | None, + patch_dir: str, + llm_config: LLMConfig, + pr_type: str, + fork_owner: str | None = None, + additional_message: str | None = None, +) -> str: + if pr_type not in ["branch", "draft", "ready"]: + raise ValueError(f"Invalid pr_type: {pr_type}") + + # Set up headers and base URL for GitHub API + headers = { + "Authorization": f"token {github_token}", + "Accept": "application/vnd.github.v3+json", + } + base_url = f"https://api.github.com/repos/{github_issue.owner}/{github_issue.repo}" + + # Create a new branch with a unique name + base_branch_name = f"openhands-fix-issue-{github_issue.number}" + branch_name = base_branch_name + attempt = 1 + + print("Checking if branch exists...") + while branch_exists(base_url, branch_name, headers): + attempt += 1 + branch_name = f"{base_branch_name}-try{attempt}" + + # Get the default branch + print("Getting default branch...") + response = requests.get(f"{base_url}", headers=headers) + response.raise_for_status() + default_branch = response.json()["default_branch"] + print(f"Default branch: {default_branch}") + + # Create and checkout the new branch + print("Creating new branch...") + result = subprocess.run( + ["git", "-C", patch_dir, "checkout", "-b", branch_name], + capture_output=True, + text=True, + ) + if result.returncode != 0: + print(f"Error creating new branch: {result.stderr}") + raise RuntimeError( + f"Failed to create a new branch {branch_name} in {patch_dir}:" + ) + + # Determine the repository to push to (original or fork) + push_owner = fork_owner if fork_owner else github_issue.owner + push_repo = github_issue.repo + + print("Pushing changes...") + username_and_token = f"{github_username}:{github_token}" if github_username else f"x-auth-token:{github_token}" + push_url = f"https://{username_and_token}@github.com/{push_owner}/{push_repo}.git" + result = subprocess.run( + ["git", "-C", patch_dir, "push", push_url, branch_name], + capture_output=True, + text=True, + ) + if result.returncode != 0: + print(f"Error pushing changes: {result.stderr}") + raise RuntimeError("Failed to push changes to the remote repository") + + pr_title = f"Fix issue #{github_issue.number}: {github_issue.title}" + pr_body = f"This pull request fixes #{github_issue.number}." + if additional_message: + pr_body += f"\n\n{additional_message}" + pr_body += "\n\nAutomatic fix generated by [OpenHands](https://github.com/All-Hands-AI/OpenHands/) 🙌" + + + # If we are not sending a PR, we can finish early and return the + # URL for the user to open a PR manually + if pr_type == "branch": + url = f"https://github.com/{push_owner}/{github_issue.repo}/compare/{branch_name}?expand=1" + else: + data = { + "title": pr_title, # No need to escape title for GitHub API + "body": pr_body, + "head": branch_name, + "base": default_branch, + "draft": pr_type == "draft", + } + response = requests.post(f"{base_url}/pulls", headers=headers, json=data) + if response.status_code == 403: + raise RuntimeError( + "Failed to create pull request due to missing permissions. " + "Make sure that the provided token has push permissions for the repository." + ) + response.raise_for_status() + pr_data = response.json() + + url = pr_data["html_url"] + + print(f"{pr_type} created: {url}\n\n--- Title: {pr_title}\n\n--- Body:\n{pr_body}") + + return url + +def reply_to_comment(github_token: str, comment_id: str, reply: str): + # Opting for graphql as REST API doesn't allow reply to replies in comment threads + query = """ + mutation($body: String!, $pullRequestReviewThreadId: ID!) { + addPullRequestReviewThreadReply(input: { body: $body, pullRequestReviewThreadId: $pullRequestReviewThreadId }) { + comment { + id + body + createdAt + } + } + } + """ + + comment_reply = f"Openhands fix success summary\n\n\n{reply}" + variables = { + "body": comment_reply, + "pullRequestReviewThreadId": comment_id + } + url = "https://api.github.com/graphql" + headers = { + "Authorization": f"Bearer {github_token}", + "Content-Type": "application/json" + } + + response = requests.post(url, json={"query": query, "variables": variables}, headers=headers) + response.raise_for_status() + + +def update_existing_pull_request( + github_issue: GithubIssue, + github_token: str, + github_username: str | None, + patch_dir: str, + llm_config: LLMConfig, + comment_message: str | None = None, + additional_message: str | None = None, +) -> str: + """Update an existing pull request with the new patches. + + Args: + github_issue: The issue to update. + github_token: The GitHub token to use for authentication. + github_username: The GitHub username to use for authentication. + patch_dir: The directory containing the patches to apply. + llm_config: The LLM configuration to use for summarizing changes. + comment_message: The main message to post as a comment on the PR. + additional_message: The additional messages to post as a comment on the PR in json list format. + """ + + # Set up headers and base URL for GitHub API + headers = { + "Authorization": f"token {github_token}", + "Accept": "application/vnd.github.v3+json", + } + base_url = f"https://api.github.com/repos/{github_issue.owner}/{github_issue.repo}" + branch_name = github_issue.head_branch + + # Push the changes to the existing branch + push_command = ( + f"git -C {patch_dir} push " + f"https://{github_username}:{github_token}@github.com/" + f"{github_issue.owner}/{github_issue.repo}.git {branch_name}" + ) + + result = subprocess.run(push_command, shell=True, capture_output=True, text=True) + if result.returncode != 0: + print(f"Error pushing changes: {result.stderr}") + raise RuntimeError("Failed to push changes to the remote repository") + + pr_url = f"https://github.com/{github_issue.owner}/{github_issue.repo}/pull/{github_issue.number}" + print(f"Updated pull request {pr_url} with new patches.") + + # Generate a summary of all comment success indicators for PR message + if not comment_message and additional_message: + try: + explanations = json.loads(additional_message) + if explanations: + comment_message = "OpenHands made the following changes to resolve the issues:\n\n" + for explanation in explanations: + comment_message += f"- {explanation}\n" + + # Summarize with LLM if provided + if llm_config is not None: + with open(os.path.join(os.path.dirname(__file__), "prompts/resolve/pr-changes-summary.jinja"), 'r') as f: + template = jinja2.Template(f.read()) + prompt = template.render(comment_message=comment_message) + response = litellm.completion( + model=llm_config.model, + messages=[{"role": "user", "content": prompt}], + api_key=llm_config.api_key, + base_url=llm_config.base_url, + ) + comment_message = response.choices[0].message.content.strip() + + except (json.JSONDecodeError, TypeError): + comment_message = "New OpenHands update" + + # Post a comment on the PR + if comment_message: + comment_url = f"{base_url}/issues/{github_issue.number}/comments" + comment_data = { + "body": comment_message + } + comment_response = requests.post(comment_url, headers=headers, json=comment_data) + if comment_response.status_code != 201: + print(f"Failed to post comment: {comment_response.status_code} {comment_response.text}") + else: + print(f"Comment added to the PR: {comment_message}") + + # Reply to each unresolved comment thread + if additional_message and github_issue.thread_ids: + explanations = json.loads(additional_message) + for count, reply_comment in enumerate(explanations): + comment_id = github_issue.thread_ids[count] + reply_to_comment(github_token, comment_id, reply_comment) + + return pr_url + + +def process_single_issue( + output_dir: str, + resolver_output: ResolverOutput, + github_token: str, + github_username: str, + pr_type: str, + llm_config: LLMConfig, + fork_owner: str | None, + send_on_failure: bool, +) -> None: + if not resolver_output.success and not send_on_failure: + print( + f"Issue {resolver_output.issue.number} was not successfully resolved. Skipping PR creation." + ) + return + + issue_type = resolver_output.issue_type + + if issue_type == "issue": + patched_repo_dir = initialize_repo( + output_dir, + resolver_output.issue.number, + issue_type, + resolver_output.base_commit + ) + elif issue_type == "pr": + patched_repo_dir = initialize_repo( + output_dir, + resolver_output.issue.number, + issue_type, + resolver_output.issue.head_branch + ) + else: + raise ValueError(f"Invalid issue type: {issue_type}") + + + + + apply_patch(patched_repo_dir, resolver_output.git_patch) + + make_commit(patched_repo_dir, resolver_output.issue, issue_type) + + if issue_type == "pr": + update_existing_pull_request( + github_issue=resolver_output.issue, + github_token=github_token, + github_username=github_username, + patch_dir=patched_repo_dir, + additional_message=resolver_output.success_explanation, + llm_config=llm_config, + ) + else: + send_pull_request( + github_issue=resolver_output.issue, + github_token=github_token, + github_username=github_username, + patch_dir=patched_repo_dir, + pr_type=pr_type, + llm_config=llm_config, + fork_owner=fork_owner, + additional_message=resolver_output.success_explanation, + ) + + +def process_all_successful_issues( + output_dir: str, + github_token: str, + github_username: str, + pr_type: str, + llm_config: LLMConfig, + fork_owner: str | None, +) -> None: + output_path = os.path.join(output_dir, "output.jsonl") + for resolver_output in load_all_resolver_outputs(output_path): + if resolver_output.success: + print(f"Processing issue {resolver_output.issue.number}") + process_single_issue( + output_dir, + resolver_output, + github_token, + github_username, + pr_type, + llm_config, + fork_owner, + False, + ) + + +def main(): + parser = argparse.ArgumentParser(description="Send a pull request to Github.") + parser.add_argument( + "--github-token", + type=str, + default=None, + help="Github token to access the repository.", + ) + parser.add_argument( + "--github-username", + type=str, + default=None, + help="Github username to access the repository.", + ) + parser.add_argument( + "--output-dir", + type=str, + default="output", + help="Output directory to write the results.", + ) + parser.add_argument( + "--pr-type", + type=str, + default="draft", + choices=["branch", "draft", "ready"], + help="Type of the pull request to send [branch, draft, ready]", + ) + parser.add_argument( + "--issue-number", + type=str, + required=True, + help="Issue number to send the pull request for, or 'all_successful' to process all successful issues.", + ) + parser.add_argument( + "--fork-owner", + type=str, + default=None, + help="Owner of the fork to push changes to (if different from the original repo owner).", + ) + parser.add_argument( + "--send-on-failure", + action="store_true", + help="Send a pull request even if the issue was not successfully resolved.", + ) + parser.add_argument( + "--llm-model", + type=str, + default=None, + help="LLM model to use for summarizing changes.", + ) + parser.add_argument( + "--llm-api-key", + type=str, + default=None, + help="API key for the LLM model.", + ) + parser.add_argument( + "--llm-base-url", + type=str, + default=None, + help="Base URL for the LLM model.", + ) + my_args = parser.parse_args() + + github_token = ( + my_args.github_token if my_args.github_token else os.getenv("GITHUB_TOKEN") + ) + if not github_token: + raise ValueError( + "Github token is not set, set via --github-token or GITHUB_TOKEN environment variable." + ) + github_username = ( + my_args.github_username + if my_args.github_username + else os.getenv("GITHUB_USERNAME") + ) + + llm_config = LLMConfig( + model=my_args.llm_model or os.environ["LLM_MODEL"], + api_key=my_args.llm_api_key or os.environ["LLM_API_KEY"], + base_url=my_args.llm_base_url or os.environ.get("LLM_BASE_URL", None), + ) + + if not os.path.exists(my_args.output_dir): + raise ValueError(f"Output directory {my_args.output_dir} does not exist.") + + if my_args.issue_number == "all_successful": + process_all_successful_issues( + my_args.output_dir, + github_token, + github_username, + my_args.pr_type, + llm_config, + my_args.fork_owner, + ) + else: + if not my_args.issue_number.isdigit(): + raise ValueError(f"Issue number {my_args.issue_number} is not a number.") + issue_number = int(my_args.issue_number) + output_path = os.path.join(my_args.output_dir, "output.jsonl") + resolver_output = load_single_resolver_output(output_path, issue_number) + process_single_issue( + my_args.output_dir, + resolver_output, + github_token, + github_username, + my_args.pr_type, + llm_config, + my_args.fork_owner, + my_args.send_on_failure, + ) + +if __name__ == "__main__": + main() + + + + + + + diff --git a/openhands/resolver/utils.py b/openhands/resolver/utils.py new file mode 100644 index 000000000000..826c7b95dc3f --- /dev/null +++ b/openhands/resolver/utils.py @@ -0,0 +1,141 @@ +import json +import logging +import multiprocessing as mp +import os +from typing import Callable + +import pandas as pd + +from openhands.controller.state.state import State +from openhands.core.logger import get_console_handler +from openhands.core.logger import openhands_logger as logger +from openhands.events.action import Action +from openhands.events.action.message import MessageAction + + +def codeact_user_response( + state: State, + encapsulate_solution: bool = False, + try_parse: Callable[[Action | None], str] | None = None, +) -> str: + encaps_str = ( + ( + 'Please encapsulate your final answer (answer ONLY) within and .\n' + 'For example: The answer to the question is 42 .\n' + ) + if encapsulate_solution + else '' + ) + msg = ( + 'Please continue working on the task on whatever approach you think is suitable.\n' + 'If you think you have solved the task, please first send your answer to user through message and then finish the interaction.\n' + f'{encaps_str}' + 'IMPORTANT: YOU SHOULD NEVER ASK FOR HUMAN HELP.\n' + ) + + if state.history: + # check if the last action has an answer, if so, early exit + if try_parse is not None: + last_action = next( + ( + event + for event in reversed(state.history) + if isinstance(event, Action) + ), + None, + ) + ans = try_parse(last_action) + if ans is not None: + return '/exit' + + # check if the agent has tried to talk to the user 3 times, if so, let the agent know it can give up + user_msgs = [ + event + for event in state.history + if isinstance(event, MessageAction) and event.source == 'user' + ] + if len(user_msgs) >= 2: + # let the agent know that it can give up when it has tried 3 times + return ( + msg + + 'If you want to give up, run: exit .\n' + ) + return msg + + +def cleanup(): + print("Cleaning up child processes...") + for process in mp.active_children(): + print(f"Terminating child process: {process.name}") + process.terminate() + process.join() + + +def prepare_dataset(dataset: pd.DataFrame, output_file: str, eval_n_limit: int): + assert ( + "instance_id" in dataset.columns + ), ( + "Expected 'instance_id' column in the dataset. You should define your own " + "unique identifier for each instance and use it as the 'instance_id' column." + ) + id_column = "instance_id" + logger.info(f"Writing evaluation output to {output_file}") + finished_ids = set() + if os.path.exists(output_file): + with open(output_file, "r") as f: + for line in f: + data = json.loads(line) + finished_ids.add(data[id_column]) + logger.warning( + f"Output file {output_file} already exists. Loaded " + f"{len(finished_ids)} finished instances." + ) + + if eval_n_limit: + dataset = dataset.head(eval_n_limit) + logger.info(f"Limiting evaluation to first {eval_n_limit} instances.") + + new_dataset = [ + instance + for _, instance in dataset.iterrows() + if instance[id_column] not in finished_ids + ] + logger.info( + f"Finished instances: {len(finished_ids)}, " + f"Remaining instances: {len(new_dataset)}" + ) + + return pd.DataFrame(new_dataset) + + +def reset_logger_for_multiprocessing( + logger: logging.Logger, instance_id: str, log_dir: str +): + """Reset the logger for multiprocessing. + + Save logs to a separate file for each process, instead of trying to write to the + same file/console from multiple processes. + """ + # Set up logger + log_file = os.path.join( + log_dir, + f"instance_{instance_id}.log", + ) + # Remove all existing handlers from logger + for handler in logger.handlers[:]: + logger.removeHandler(handler) + # add back the console handler to print ONE line + logger.addHandler(get_console_handler()) + logger.info( + f"Starting resolver for instance {instance_id}.\n" + f'Hint: run "tail -f {log_file}" to see live logs in a separate shell' + ) + # Remove all existing handlers from logger + for handler in logger.handlers[:]: + logger.removeHandler(handler) + os.makedirs(os.path.dirname(log_file), exist_ok=True) + file_handler = logging.FileHandler(log_file) + file_handler.setFormatter( + logging.Formatter("%(asctime)s - %(levelname)s - %(message)s") + ) + logger.addHandler(file_handler) diff --git a/openhands/resolver/visualize_resolver_output.py b/openhands/resolver/visualize_resolver_output.py new file mode 100644 index 000000000000..c338ae5c0d00 --- /dev/null +++ b/openhands/resolver/visualize_resolver_output.py @@ -0,0 +1,42 @@ +import argparse +import os +from openhands.resolver.io_utils import load_single_resolver_output + + +def visualize_resolver_output(issue_number: int, output_dir: str, vis_method: str): + output_jsonl = os.path.join(output_dir, "output.jsonl") + resolver_output = load_single_resolver_output(output_jsonl, issue_number) + if vis_method == "json": + print(resolver_output.model_dump_json(indent=4)) + else: + raise ValueError(f"Invalid visualization method: {vis_method}") + + +if __name__ == "__main__": + parser = argparse.ArgumentParser(description="Visualize a patch.") + parser.add_argument( + "--issue-number", + type=int, + required=True, + help="Issue number to send the pull request for.", + ) + parser.add_argument( + "--output-dir", + type=str, + default="output", + help="Output directory to write the results.", + ) + parser.add_argument( + "--vis-method", + type=str, + default="json", + choices=["json"], + help="Method to visualize the patch [json].", + ) + my_args = parser.parse_args() + + visualize_resolver_output( + issue_number=my_args.issue_number, + output_dir=my_args.output_dir, + vis_method=my_args.vis_method, + ) diff --git a/tests/unit/resolver/mock_output/output.jsonl b/tests/unit/resolver/mock_output/output.jsonl new file mode 100644 index 000000000000..ef8285956a59 --- /dev/null +++ b/tests/unit/resolver/mock_output/output.jsonl @@ -0,0 +1,2 @@ +{"issue":{"owner":"neubig","repo":"pr-viewer","number":5,"title":"Add MIT license","body":"We can license this repo under the MIT license."},"issue_type":"issue","instruction":"Please fix the following issue for the repository in /workspace.\nEnvironment has been set up for you to start working. You may assume all necessary tools are installed.\n\n# Problem Statement\nWe can license this repo under the MIT license.\n\nIMPORTANT: You should ONLY interact with the environment provided to you AND NEVER ASK FOR HUMAN HELP.\nYou should NOT modify any existing test case files. If needed, you can add new test cases in a NEW file to reproduce the issue.\nYou SHOULD INCLUDE PROPER INDENTATION in your edit commands.\nWhen you think you have fixed the issue through code changes, please run the following command: exit .","base_commit":"","git_patch":"diff --git a/LICENSE b/LICENSE\r\nnew file mode 100644\r\nindex 0000000..dbf96a3\r\n--- /dev/null\r\n+++ b/LICENSE\r\n@@ -0,0 +1,21 @@\r\n+MIT License\r\n+\r\n+Copyright (c) 2024 [Your Name or Organization Name]\r\n+\r\n+Permission is hereby granted, free of charge, to any person obtaining a copy\r\n+of this software and associated documentation files (the \"Software\"), to deal\r\n+in the Software without restriction, including without limitation the rights\r\n+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell\r\n+copies of the Software, and to permit persons to whom the Software is\r\n+furnished to do so, subject to the following conditions:\r\n+\r\n+The above copyright notice and this permission notice shall be included in all\r\n+copies or substantial portions of the Software.\r\n+\r\n+THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\r\n+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\r\n+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\r\n+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\r\n+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\r\n+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\r\n+SOFTWARE.\r\n\\ No newline at end of file","history":[{"content":"Please fix the following issue for the repository in /workspace.\nEnvironment has been set up for you to start working. You may assume all necessary tools are installed.\n\n# Problem Statement\nWe can license this repo under the MIT license.\n\nIMPORTANT: You should ONLY interact with the environment provided to you AND NEVER ASK FOR HUMAN HELP.\nYou should NOT modify any existing test case files. If needed, you can add new test cases in a NEW file to reproduce the issue.\nYou SHOULD INCLUDE PROPER INDENTATION in your edit commands.\nWhen you think you have fixed the issue through code changes, please run the following command: exit .","images_urls":null,"wait_for_response":false,"action":"message","security_risk":null},{"command":"touch LICENSE","thought":"Certainly! I'll add the MIT license to the repository in /workspace. Let's start by creating the license file.","keep_prompt":true,"action":"run","is_confirmed":"confirmed","security_risk":null},{"content":"\r\nroot@bcd3959393a1:/workspace # ","command_id":-1,"command":"touch LICENSE","exit_code":0,"observation":"run"},{"code":"mit_license = \"\"\"MIT License\n\nCopyright (c) 2024 [Your Name or Organization Name]\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE.\"\"\"\n\nwith open('LICENSE', 'w') as license_file:\n license_file.write(mit_license)\n\nprint(\"MIT License has been added to the LICENSE file.\")","thought":"Thank you for the reminder. Let's proceed with adding the MIT license content to the LICENSE file.","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"MIT License has been added to the LICENSE file.\n[Jupyter current working directory: /workspace]","code":"mit_license = \"\"\"MIT License\n\nCopyright (c) 2024 [Your Name or Organization Name]\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE.\"\"\"\n\nwith open('LICENSE', 'w') as license_file:\n license_file.write(mit_license)\n\nprint(\"MIT License has been added to the LICENSE file.\")","observation":"run_ipython"},{"command":"cat LICENSE","thought":"Great! We've successfully added the MIT License to the repository. Now, let's verify the contents of the LICENSE file to ensure everything is correct.","keep_prompt":true,"action":"run","is_confirmed":"confirmed","security_risk":null},{"content":"MIT License\r\n\r\nCopyright (c) 2024 [Your Name or Organization Name]\r\n\r\nPermission is hereby granted, free of charge, to any person obtaining a copy\r\nof this software and associated documentation files (the \"Software\"), to deal\r\nin the Software without restriction, including without limitation the rights\r\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\r\ncopies of the Software, and to permit persons to whom the Software is\r\nfurnished to do so, subject to the following conditions:\r\n\r\nThe above copyright notice and this permission notice shall be included in all\r\ncopies or substantial portions of the Software.\r\n\r\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\r\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\r\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\r\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\r\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\r\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\r\nSOFTWARE.\r\nroot@bcd3959393a1:/workspace # ","command_id":-1,"command":"cat LICENSE","exit_code":0,"observation":"run"},{"outputs":{},"thought":"The MIT License has been successfully added to the repository. The content of the LICENSE file is correct and follows the standard MIT License format. \n\nTo complete the task, we should update the copyright line with the appropriate name or organization. Since we don't have specific information about the repository owner, we'll leave it as is for now. If needed, the repository owner can update this line later.\n\nNow that we have added the MIT License to the repository, the task is complete. We have successfully licensed the repo under the MIT license.","action":"finish"}],"metrics":{"accumulated_cost":0.070713,"costs":[0.015396,0.019719,0.016742999999999997,0.018855]},"success":true,"comment_success":null,"success_explanation":"The AI agent has successfully added the MIT License to the repository. The LICENSE file has been created with the correct content following the standard MIT License format. While the copyright line could be updated with specific owner information, this is not strictly necessary for the license to be valid and can be done later if needed. The core requirement of licensing the repo under the MIT license has been fulfilled, thus resolving the issue.","error":null} +{"issue":{"owner":"neubig","repo":"pr-viewer","number":1,"title":"Add a toggle for dark mode","body":"It'd be nice if this app could also support dark mode, we can add a toggle that can turn on dark mode.\r\n\r\nThis would require adding a toggle that switches between the different modes to JS, and modifying the css file."},"issue_type": "issue","instruction":"Please fix the following issue for the repository in /workspace.\nEnvironment has been set up for you to start working. You may assume all necessary tools are installed.\n\n# Problem Statement\nIt'd be nice if this app could also support dark mode, we can add a toggle that can turn on dark mode.\r\n\r\nThis would require adding a toggle that switches between the different modes to JS, and modifying the css file.\n\nIMPORTANT: You should ONLY interact with the environment provided to you AND NEVER ASK FOR HUMAN HELP.\nYou should NOT modify any existing test case files. If needed, you can add new test cases in a NEW file to reproduce the issue.\nYou SHOULD INCLUDE PROPER INDENTATION in your edit commands.\nWhen you think you have fixed the issue through code changes, please run the following command: exit .","base_commit":"","git_patch":"diff --git a/src/App.css b/src/App.css\r\nindex b9d355d..b3c4c63 100644\r\n--- a/src/App.css\r\n+++ b/src/App.css\r\n@@ -5,6 +5,17 @@\r\n text-align: center;\r\n }\r\n \r\n+body {\r\n+ background-color: #ffffff;\r\n+ color: #213547;\r\n+ transition: background-color 0.3s, color 0.3s;\r\n+}\r\n+\r\n+body.dark-mode {\r\n+ background-color: #242424;\r\n+ color: #ffffff;\r\n+}\r\n+\r\n .logo {\r\n height: 6em;\r\n padding: 1.5em;\r\n@@ -40,3 +51,29 @@\r\n .read-the-docs {\r\n color: #888;\r\n }\r\n+\r\n+.dark-mode-toggle {\r\n+ position: fixed;\r\n+ top: 20px;\r\n+ right: 20px;\r\n+ background-color: #646cff;\r\n+ color: white;\r\n+ border: none;\r\n+ padding: 10px 20px;\r\n+ border-radius: 5px;\r\n+ cursor: pointer;\r\n+ transition: background-color 0.3s;\r\n+}\r\n+\r\n+.dark-mode-toggle:hover {\r\n+ background-color: #535bf2;\r\n+}\r\n+\r\n+.dark-mode .dark-mode-toggle {\r\n+ background-color: #ffffff;\r\n+ color: #242424;\r\n+}\r\n+\r\n+.dark-mode .dark-mode-toggle:hover {\r\n+ background-color: #e6e6e6;\r\n+}\r\ndiff --git a/src/PullRequestViewer.tsx b/src/PullRequestViewer.tsx\r\nindex 6a8281f..a7598b3 100644\r\n--- a/src/PullRequestViewer.tsx\r\n+++ b/src/PullRequestViewer.tsx\r\n@@ -24,7 +24,8 @@ interface Repo {\r\n const PullRequestViewer: React.FC = () => {\r\n const [repos, setRepos] = useState([]);\r\n const [selectedRepo, setSelectedRepo] = useState(null);\r\n- const [pullRequests, setPullRequests] = useState([]);\r\n+const [pullRequests, setPullRequests] = useState([]);\r\n+ const [darkMode, setDarkMode] = useState(false);\r\n \r\n useEffect(() => {\r\n const fetchRepos = async () => {\r\n@@ -80,9 +81,17 @@ const PullRequestViewer: React.FC = () => {\r\n fetchPullRequests();\r\n }, [selectedRepo]);\r\n \r\n+ const toggleDarkMode = () => {\r\n+ setDarkMode(!darkMode);\r\n+ document.body.classList.toggle('dark-mode');\r\n+ };\r\n+\r\n return (\r\n-
\r\n+
\r\n

Pull Request Viewer

\r\n+ \r\n exit .","images_urls":null,"wait_for_response":false,"action":"message","security_risk":null},{"command":"ls -R /workspace","thought":"Certainly! I'll add dark mode support to the application by modifying the necessary files. Let's start by examining the current structure of the project.","keep_prompt":true,"action":"run","is_confirmed":"confirmed","security_risk":null},{"content":"/workspace:\r\nREADME.md\t package-lock.json src\t\ttsconfig.node.json\r\neslint.config.js package.json\t tsconfig.app.json\tvite.config.ts\r\nindex.html\t public\t tsconfig.json\r\n\r\n/workspace/public:\r\nvite.svg\r\n\r\n/workspace/src:\r\nApp.css PullRequestViewer.test.tsx assets\tmain.tsx vite-env.d.ts\r\nApp.tsx PullRequestViewer.tsx\t index.css\tsetupTests.ts\r\n\r\n/workspace/src/assets:\r\nreact.svg\r\n\r\nroot@b365937733b2:/workspace # ","command_id":-1,"command":"ls -R /workspace","exit_code":0,"observation":"run"},{"code":"open_file('/workspace/src/App.css')","thought":"Thank you for providing the project structure. Let's start by modifying the necessary files to add dark mode support.\n\nFirst, let's update the CSS file to include dark mode styles:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[File: /workspace/src/App.css (42 lines total)]\n(this is the beginning of the file)\n1|#root {\n2| max-width: 1280px;\n3| margin: 0 auto;\n4| padding: 2rem;\n5| text-align: center;\n6|}\n7|\n8|.logo {\n9| height: 6em;\n10| padding: 1.5em;\n11| will-change: filter;\n12| transition: filter 300ms;\n13|}\n14|.logo:hover {\n15| filter: drop-shadow(0 0 2em #646cffaa);\n16|}\n17|.logo.react:hover {\n18| filter: drop-shadow(0 0 2em #61dafbaa);\n19|}\n20|\n21|@keyframes logo-spin {\n22| from {\n23| transform: rotate(0deg);\n24| }\n25| to {\n26| transform: rotate(360deg);\n27| }\n28|}\n29|\n30|@media (prefers-reduced-motion: no-preference) {\n31| a:nth-of-type(2) .logo {\n32| animation: logo-spin infinite 20s linear;\n33| }\n34|}\n35|\n36|.card {\n37| padding: 2em;\n38|}\n39|\n40|.read-the-docs {\n41| color: #888;\n42|}\n(this is the end of the file)\n[Jupyter current working directory: /workspace]","code":"open_file('/workspace/src/App.css')","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/App.css',\nto_replace=\"\"\"#root {\n max-width: 1280px;\n margin: 0 auto;\n padding: 2rem;\n text-align: center;\n}\n\n.logo {\n height: 6em;\n padding: 1.5em;\n will-change: filter;\n transition: filter 300ms;\n}\n.logo:hover {\n filter: drop-shadow(0 0 2em #646cffaa);\n}\n.logo.react:hover {\n filter: drop-shadow(0 0 2em #61dafbaa);\n}\n\n@keyframes logo-spin {\n from {\n transform: rotate(0deg);\n }\n to {\n transform: rotate(360deg);\n }\n}\n\n@media (prefers-reduced-motion: no-preference) {\n a:nth-of-type(2) .logo {\n animation: logo-spin infinite 20s linear;\n }\n}\n\n.card {\n padding: 2em;\n}\n\n.read-the-docs {\n color: #888;\n}\"\"\",\nnew_content=\"\"\"#root {\n max-width: 1280px;\n margin: 0 auto;\n padding: 2rem;\n text-align: center;\n}\n\nbody {\n background-color: #ffffff;\n color: #213547;\n transition: background-color 0.3s, color 0.3s;\n}\n\nbody.dark-mode {\n background-color: #242424;\n color: #ffffff;\n}\n\n.logo {\n height: 6em;\n padding: 1.5em;\n will-change: filter;\n transition: filter 300ms;\n}\n.logo:hover {\n filter: drop-shadow(0 0 2em #646cffaa);\n}\n.logo.react:hover {\n filter: drop-shadow(0 0 2em #61dafbaa);\n}\n\n@keyframes logo-spin {\n from {\n transform: rotate(0deg);\n }\n to {\n transform: rotate(360deg);\n }\n}\n\n@media (prefers-reduced-motion: no-preference) {\n a:nth-of-type(2) .logo {\n animation: logo-spin infinite 20s linear;\n }\n}\n\n.card {\n padding: 2em;\n}\n\n.read-the-docs {\n color: #888;\n}\n\n.dark-mode-toggle {\n position: fixed;\n top: 20px;\n right: 20px;\n background-color: #646cff;\n color: white;\n border: none;\n padding: 10px 20px;\n border-radius: 5px;\n cursor: pointer;\n transition: background-color 0.3s;\n}\n\n.dark-mode-toggle:hover {\n background-color: #535bf2;\n}\n\n.dark-mode .dark-mode-toggle {\n background-color: #ffffff;\n color: #242424;\n}\n\n.dark-mode .dark-mode-toggle:hover {\n background-color: #e6e6e6;\n}\"\"\"\n)","thought":"Let's update the CSS file to include dark mode styles. We'll add a new class for dark mode and modify existing styles:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[File: /workspace/src/App.css (79 lines total after edit)]\n(this is the beginning of the file)\n1|#root {\n2| max-width: 1280px;\n3| margin: 0 auto;\n4| padding: 2rem;\n5| text-align: center;\n6|}\n7|\n8|body {\n9| background-color: #ffffff;\n10| color: #213547;\n11| transition: background-color 0.3s, color 0.3s;\n12|}\n13|\n14|body.dark-mode {\n15| background-color: #242424;\n16| color: #ffffff;\n17|}\n18|\n19|.logo {\n20| height: 6em;\n21| padding: 1.5em;\n22| will-change: filter;\n23| transition: filter 300ms;\n24|}\n25|.logo:hover {\n26| filter: drop-shadow(0 0 2em #646cffaa);\n27|}\n28|.logo.react:hover {\n29| filter: drop-shadow(0 0 2em #61dafbaa);\n30|}\n31|\n32|@keyframes logo-spin {\n33| from {\n34| transform: rotate(0deg);\n35| }\n36| to {\n37| transform: rotate(360deg);\n38| }\n39|}\n40|\n41|@media (prefers-reduced-motion: no-preference) {\n42| a:nth-of-type(2) .logo {\n43| animation: logo-spin infinite 20s linear;\n44| }\n45|}\n46|\n47|.card {\n48| padding: 2em;\n49|}\n50|\n51|.read-the-docs {\n52| color: #888;\n53|}\n54|\n55|.dark-mode-toggle {\n56| position: fixed;\n57| top: 20px;\n58| right: 20px;\n59| background-color: #646cff;\n60| color: white;\n61| border: none;\n62| padding: 10px 20px;\n63| border-radius: 5px;\n64| cursor: pointer;\n65| transition: background-color 0.3s;\n66|}\n67|\n68|.dark-mode-toggle:hover {\n69| background-color: #535bf2;\n70|}\n71|\n72|.dark-mode .dark-mode-toggle {\n73| background-color: #ffffff;\n74| color: #242424;\n75|}\n76|\n77|.dark-mode .dark-mode-toggle:hover {\n78| background-color: #e6e6e6;\n79|}\n(this is the end of the file)\n[File updated (edited at line 1). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/App.css',\nto_replace=\"\"\"#root {\n max-width: 1280px;\n margin: 0 auto;\n padding: 2rem;\n text-align: center;\n}\n\n.logo {\n height: 6em;\n padding: 1.5em;\n will-change: filter;\n transition: filter 300ms;\n}\n.logo:hover {\n filter: drop-shadow(0 0 2em #646cffaa);\n}\n.logo.react:hover {\n filter: drop-shadow(0 0 2em #61dafbaa);\n}\n\n@keyframes logo-spin {\n from {\n transform: rotate(0deg);\n }\n to {\n transform: rotate(360deg);\n }\n}\n\n@media (prefers-reduced-motion: no-preference) {\n a:nth-of-type(2) .logo {\n animation: logo-spin infinite 20s linear;\n }\n}\n\n.card {\n padding: 2em;\n}\n\n.read-the-docs {\n color: #888;\n}\"\"\",\nnew_content=\"\"\"#root {\n max-width: 1280px;\n margin: 0 auto;\n padding: 2rem;\n text-align: center;\n}\n\nbody {\n background-color: #ffffff;\n color: #213547;\n transition: background-color 0.3s, color 0.3s;\n}\n\nbody.dark-mode {\n background-color: #242424;\n color: #ffffff;\n}\n\n.logo {\n height: 6em;\n padding: 1.5em;\n will-change: filter;\n transition: filter 300ms;\n}\n.logo:hover {\n filter: drop-shadow(0 0 2em #646cffaa);\n}\n.logo.react:hover {\n filter: drop-shadow(0 0 2em #61dafbaa);\n}\n\n@keyframes logo-spin {\n from {\n transform: rotate(0deg);\n }\n to {\n transform: rotate(360deg);\n }\n}\n\n@media (prefers-reduced-motion: no-preference) {\n a:nth-of-type(2) .logo {\n animation: logo-spin infinite 20s linear;\n }\n}\n\n.card {\n padding: 2em;\n}\n\n.read-the-docs {\n color: #888;\n}\n\n.dark-mode-toggle {\n position: fixed;\n top: 20px;\n right: 20px;\n background-color: #646cff;\n color: white;\n border: none;\n padding: 10px 20px;\n border-radius: 5px;\n cursor: pointer;\n transition: background-color 0.3s;\n}\n\n.dark-mode-toggle:hover {\n background-color: #535bf2;\n}\n\n.dark-mode .dark-mode-toggle {\n background-color: #ffffff;\n color: #242424;\n}\n\n.dark-mode .dark-mode-toggle:hover {\n background-color: #e6e6e6;\n}\"\"\"\n)","observation":"run_ipython"},{"code":"open_file('/workspace/src/App.tsx')","thought":"The CSS file has been updated successfully. Now, let's modify the App.tsx file to add the dark mode toggle functionality:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[File: /workspace/src/App.tsx (14 lines total)]\n(this is the beginning of the file)\n1|\n2|import React from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| return (\n8|
\n9| \n10|
\n11| )\n12|}\n13|\n14|export default App\n(this is the end of the file)\n[Jupyter current working directory: /workspace]","code":"open_file('/workspace/src/App.tsx')","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React, { useState, useEffect } from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n const [darkMode, setDarkMode] = useState(false);\n\n useEffect(() => {\n if (darkMode) {\n document.body.classList.add('dark-mode');\n } else {\n document.body.classList.remove('dark-mode');\n }\n }, [darkMode]);\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode);\n };\n\n return (\n
\n \n \n
\n )\n}\n\nexport default App\"\"\"\n)","thought":"Thank you for showing me the App.tsx file. Let's modify it to add the dark mode toggle functionality:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[Your proposed edit has introduced new syntax error(s). Please understand the errors and retry your edit command.]\n/workspace/src/App.tsx:22\n[This is how your edit would have looked if applied]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React, { useState, useEffect } from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| const [darkMode, setDarkMode] = useState(false);\n8|\n9| useEffect(() => {\n10| if (darkMode) {\n11| document.body.classList.add('dark-mode');\n12| } else {\n13| document.body.classList.remove('dark-mode');\n14| }\n15| }, [darkMode]);\n16|\n17| const toggleDarkMode = () => {\n18| setDarkMode(!darkMode);\n19| };\n20|\n21| return (\n22|
\n23| \n26| \n27|
\n28| )\n29|}\n30|\n31|export default App\n(this is the end of the file)\n-------------------------------------------------\n\n[This is the original code before your edit]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| return (\n8|
\n9| \n10|
\n11| )\n12|}\n13|\n14|export default App\n(this is the end of the file)\n-------------------------------------------------\nYour changes have NOT been applied. Please fix your edit command and try again.\nYou either need to 1) Specify the correct start/end line arguments or 2) Correct your edit code.\nDO NOT re-run the same failed edit command. Running it again will lead to the same error.\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React, { useState, useEffect } from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n const [darkMode, setDarkMode] = useState(false);\n\n useEffect(() => {\n if (darkMode) {\n document.body.classList.add('dark-mode');\n } else {\n document.body.classList.remove('dark-mode');\n }\n }, [darkMode]);\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode);\n };\n\n return (\n
\n \n \n
\n )\n}\n\nexport default App\"\"\"\n)","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React, { useState, useEffect } from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n const [darkMode, setDarkMode] = useState(false);\n\n useEffect(() => {\n if (darkMode) {\n document.body.classList.add('dark-mode');\n } else {\n document.body.classList.remove('dark-mode');\n }\n }, [darkMode]);\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode);\n };\n\n return (\n
\n \n \n
\n );\n}\n\nexport default App\"\"\"\n)","thought":"I apologize for the confusion. It seems the edit was not applied due to a syntax error. Let's try to modify the App.tsx file again with the correct syntax:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[Your proposed edit has introduced new syntax error(s). Please understand the errors and retry your edit command.]\n/workspace/src/App.tsx:22\n[This is how your edit would have looked if applied]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React, { useState, useEffect } from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| const [darkMode, setDarkMode] = useState(false);\n8|\n9| useEffect(() => {\n10| if (darkMode) {\n11| document.body.classList.add('dark-mode');\n12| } else {\n13| document.body.classList.remove('dark-mode');\n14| }\n15| }, [darkMode]);\n16|\n17| const toggleDarkMode = () => {\n18| setDarkMode(!darkMode);\n19| };\n20|\n21| return (\n22|
\n23| \n26| \n27|
\n28| );\n29|}\n30|\n31|export default App\n(this is the end of the file)\n-------------------------------------------------\n\n[This is the original code before your edit]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| return (\n8|
\n9| \n10|
\n11| )\n12|}\n13|\n14|export default App\n(this is the end of the file)\n-------------------------------------------------\nYour changes have NOT been applied. Please fix your edit command and try again.\nYou either need to 1) Specify the correct start/end line arguments or 2) Correct your edit code.\nDO NOT re-run the same failed edit command. Running it again will lead to the same error.\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React, { useState, useEffect } from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n const [darkMode, setDarkMode] = useState(false);\n\n useEffect(() => {\n if (darkMode) {\n document.body.classList.add('dark-mode');\n } else {\n document.body.classList.remove('dark-mode');\n }\n }, [darkMode]);\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode);\n };\n\n return (\n
\n \n \n
\n );\n}\n\nexport default App\"\"\"\n)","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React, { useState, useEffect } from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n const [darkMode, setDarkMode] = useState(false)\n\n useEffect(() => {\n if (darkMode) {\n document.body.classList.add('dark-mode')\n } else {\n document.body.classList.remove('dark-mode')\n }\n }, [darkMode])\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode)\n }\n\n return (\n
\n \n \n
\n )\n}\n\nexport default App\"\"\"\n)","thought":"I apologize for the confusion. It seems that the file is using a different syntax or formatting. Let's try to modify the App.tsx file again, keeping the original formatting and only adding the necessary changes:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[Your proposed edit has introduced new syntax error(s). Please understand the errors and retry your edit command.]\n/workspace/src/App.tsx:22\n[This is how your edit would have looked if applied]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React, { useState, useEffect } from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| const [darkMode, setDarkMode] = useState(false)\n8|\n9| useEffect(() => {\n10| if (darkMode) {\n11| document.body.classList.add('dark-mode')\n12| } else {\n13| document.body.classList.remove('dark-mode')\n14| }\n15| }, [darkMode])\n16|\n17| const toggleDarkMode = () => {\n18| setDarkMode(!darkMode)\n19| }\n20|\n21| return (\n22|
\n23| \n26| \n27|
\n28| )\n29|}\n30|\n31|export default App\n(this is the end of the file)\n-------------------------------------------------\n\n[This is the original code before your edit]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| return (\n8|
\n9| \n10|
\n11| )\n12|}\n13|\n14|export default App\n(this is the end of the file)\n-------------------------------------------------\nYour changes have NOT been applied. Please fix your edit command and try again.\nYou either need to 1) Specify the correct start/end line arguments or 2) Correct your edit code.\nDO NOT re-run the same failed edit command. Running it again will lead to the same error.\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React, { useState, useEffect } from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n const [darkMode, setDarkMode] = useState(false)\n\n useEffect(() => {\n if (darkMode) {\n document.body.classList.add('dark-mode')\n } else {\n document.body.classList.remove('dark-mode')\n }\n }, [darkMode])\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode)\n }\n\n return (\n
\n \n \n
\n )\n}\n\nexport default App\"\"\"\n)","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React, { useState, useEffect } from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App(): JSX.Element {\n const [darkMode, setDarkMode] = useState(false)\n\n useEffect(() => {\n if (darkMode) {\n document.body.classList.add('dark-mode')\n } else {\n document.body.classList.remove('dark-mode')\n }\n }, [darkMode])\n\n const toggleDarkMode = (): void => {\n setDarkMode(!darkMode)\n }\n\n return (\n
\n \n \n
\n )\n}\n\nexport default App\"\"\"\n)","thought":"I apologize for the confusion. It seems that the file is using TypeScript, which requires type annotations. Let's modify the App.tsx file with the correct TypeScript syntax:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[Your proposed edit has introduced new syntax error(s). Please understand the errors and retry your edit command.]\n/workspace/src/App.tsx:22\n[This is how your edit would have looked if applied]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React, { useState, useEffect } from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App(): JSX.Element {\n7| const [darkMode, setDarkMode] = useState(false)\n8|\n9| useEffect(() => {\n10| if (darkMode) {\n11| document.body.classList.add('dark-mode')\n12| } else {\n13| document.body.classList.remove('dark-mode')\n14| }\n15| }, [darkMode])\n16|\n17| const toggleDarkMode = (): void => {\n18| setDarkMode(!darkMode)\n19| }\n20|\n21| return (\n22|
\n23| \n26| \n27|
\n28| )\n29|}\n30|\n31|export default App\n(this is the end of the file)\n-------------------------------------------------\n\n[This is the original code before your edit]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| return (\n8|
\n9| \n10|
\n11| )\n12|}\n13|\n14|export default App\n(this is the end of the file)\n-------------------------------------------------\nYour changes have NOT been applied. Please fix your edit command and try again.\nYou either need to 1) Specify the correct start/end line arguments or 2) Correct your edit code.\nDO NOT re-run the same failed edit command. Running it again will lead to the same error.\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React, { useState, useEffect } from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App(): JSX.Element {\n const [darkMode, setDarkMode] = useState(false)\n\n useEffect(() => {\n if (darkMode) {\n document.body.classList.add('dark-mode')\n } else {\n document.body.classList.remove('dark-mode')\n }\n }, [darkMode])\n\n const toggleDarkMode = (): void => {\n setDarkMode(!darkMode)\n }\n\n return (\n
\n \n \n
\n )\n}\n\nexport default App\"\"\"\n)","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React, { useState, useEffect } from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n const [darkMode, setDarkMode] = useState(false)\n\n useEffect(() => {\n if (darkMode) {\n document.body.classList.add('dark-mode')\n } else {\n document.body.classList.remove('dark-mode')\n }\n }, [darkMode])\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode)\n }\n\n return (\n
\n \n \n
\n )\n}\n\nexport default App\"\"\"\n)","thought":"I apologize for the persistent errors. It seems that the TypeScript configuration might be stricter than expected. Let's try a simpler approach without type annotations:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[Your proposed edit has introduced new syntax error(s). Please understand the errors and retry your edit command.]\n/workspace/src/App.tsx:22\n[This is how your edit would have looked if applied]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React, { useState, useEffect } from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| const [darkMode, setDarkMode] = useState(false)\n8|\n9| useEffect(() => {\n10| if (darkMode) {\n11| document.body.classList.add('dark-mode')\n12| } else {\n13| document.body.classList.remove('dark-mode')\n14| }\n15| }, [darkMode])\n16|\n17| const toggleDarkMode = () => {\n18| setDarkMode(!darkMode)\n19| }\n20|\n21| return (\n22|
\n23| \n26| \n27|
\n28| )\n29|}\n30|\n31|export default App\n(this is the end of the file)\n-------------------------------------------------\n\n[This is the original code before your edit]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| return (\n8|
\n9| \n10|
\n11| )\n12|}\n13|\n14|export default App\n(this is the end of the file)\n-------------------------------------------------\nYour changes have NOT been applied. Please fix your edit command and try again.\nYou either need to 1) Specify the correct start/end line arguments or 2) Correct your edit code.\nDO NOT re-run the same failed edit command. Running it again will lead to the same error.\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React, { useState, useEffect } from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n const [darkMode, setDarkMode] = useState(false)\n\n useEffect(() => {\n if (darkMode) {\n document.body.classList.add('dark-mode')\n } else {\n document.body.classList.remove('dark-mode')\n }\n }, [darkMode])\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode)\n }\n\n return (\n
\n \n \n
\n )\n}\n\nexport default App\"\"\"\n)","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React, { useState } from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n const [darkMode, setDarkMode] = useState(false)\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode)\n document.body.classList.toggle('dark-mode')\n }\n\n return (\n
\n \n \n
\n )\n}\n\nexport default App\"\"\"\n)","thought":"I apologize for the continued errors. It seems that there might be some configuration issues or restrictions in place. Let's try a minimal change to add the dark mode toggle without modifying the existing structure too much:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[Your proposed edit has introduced new syntax error(s). Please understand the errors and retry your edit command.]\n/workspace/src/App.tsx:15\n[This is how your edit would have looked if applied]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React, { useState } from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| const [darkMode, setDarkMode] = useState(false)\n8|\n9| const toggleDarkMode = () => {\n10| setDarkMode(!darkMode)\n11| document.body.classList.toggle('dark-mode')\n12| }\n13|\n14| return (\n15|
\n16| \n19| \n20|
\n21| )\n22|}\n23|\n24|export default App\n(this is the end of the file)\n-------------------------------------------------\n\n[This is the original code before your edit]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| return (\n8|
\n9| \n10|
\n11| )\n12|}\n13|\n14|export default App\n(this is the end of the file)\n-------------------------------------------------\nYour changes have NOT been applied. Please fix your edit command and try again.\nYou either need to 1) Specify the correct start/end line arguments or 2) Correct your edit code.\nDO NOT re-run the same failed edit command. Running it again will lead to the same error.\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React, { useState } from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n const [darkMode, setDarkMode] = useState(false)\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode)\n document.body.classList.toggle('dark-mode')\n }\n\n return (\n
\n \n \n
\n )\n}\n\nexport default App\"\"\"\n)","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React, { useState } from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n const [darkMode, setDarkMode] = useState(false)\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode)\n document.body.classList.toggle('dark-mode')\n }\n\n return (\n
\n \n \n
\n )\n}\n\nexport default App\"\"\"\n)","thought":"I apologize for the persistent errors. It seems that there might be some strict TypeScript configurations or linting rules in place. Let's try a minimal change that should work with most configurations:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[Your proposed edit has introduced new syntax error(s). Please understand the errors and retry your edit command.]\n/workspace/src/App.tsx:14\n[This is how your edit would have looked if applied]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React, { useState } from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| const [darkMode, setDarkMode] = useState(false)\n8|\n9| const toggleDarkMode = () => {\n10| setDarkMode(!darkMode)\n11| document.body.classList.toggle('dark-mode')\n12| }\n13|\n14| return (\n15|
\n16| \n19| \n20|
\n21| )\n22|}\n23|\n24|export default App\n(this is the end of the file)\n-------------------------------------------------\n\n[This is the original code before your edit]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| return (\n8|
\n9| \n10|
\n11| )\n12|}\n13|\n14|export default App\n(this is the end of the file)\n-------------------------------------------------\nYour changes have NOT been applied. Please fix your edit command and try again.\nYou either need to 1) Specify the correct start/end line arguments or 2) Correct your edit code.\nDO NOT re-run the same failed edit command. Running it again will lead to the same error.\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React, { useState } from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n const [darkMode, setDarkMode] = useState(false)\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode)\n document.body.classList.toggle('dark-mode')\n }\n\n return (\n
\n \n \n
\n )\n}\n\nexport default App\"\"\"\n)","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n const toggleDarkMode = () => {\n document.body.classList.toggle('dark-mode')\n }\n\n return (\n
\n \n \n
\n )\n}\n\nexport default App\"\"\"\n)","thought":"I apologize for the continued errors. It seems that the project might have strict TypeScript or linting configurations that are preventing our changes. Let's try a minimal change that should work with most configurations and avoid potential syntax errors:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[Your proposed edit has introduced new syntax error(s). Please understand the errors and retry your edit command.]\n/workspace/src/App.tsx:12\n[This is how your edit would have looked if applied]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| const toggleDarkMode = () => {\n8| document.body.classList.toggle('dark-mode')\n9| }\n10|\n11| return (\n12|
\n13| \n14| \n15|
\n16| )\n17|}\n18|\n19|export default App\n(this is the end of the file)\n-------------------------------------------------\n\n[This is the original code before your edit]\n-------------------------------------------------\n(this is the beginning of the file)\n1|\n2|import React from 'react'\n3|import './App.css'\n4|import PullRequestViewer from './PullRequestViewer'\n5|\n6|function App() {\n7| return (\n8|
\n9| \n10|
\n11| )\n12|}\n13|\n14|export default App\n(this is the end of the file)\n-------------------------------------------------\nYour changes have NOT been applied. Please fix your edit command and try again.\nYou either need to 1) Specify the correct start/end line arguments or 2) Correct your edit code.\nDO NOT re-run the same failed edit command. Running it again will lead to the same error.\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/App.tsx',\nto_replace=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n return (\n
\n \n
\n )\n}\n\nexport default App\"\"\",\nnew_content=\"\"\"\nimport React from 'react'\nimport './App.css'\nimport PullRequestViewer from './PullRequestViewer'\n\nfunction App() {\n const toggleDarkMode = () => {\n document.body.classList.toggle('dark-mode')\n }\n\n return (\n
\n \n \n
\n )\n}\n\nexport default App\"\"\"\n)","observation":"run_ipython"},{"code":"open_file('/workspace/src/PullRequestViewer.tsx')","thought":"I apologize for the continued errors. It seems that the project has very strict configurations that are preventing even minimal changes. Let's try a different approach by adding the dark mode toggle functionality to the existing PullRequestViewer component instead of modifying the App component.\n\nFirst, let's check the contents of the PullRequestViewer.tsx file:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[File: /workspace/src/PullRequestViewer.tsx (112 lines total)]\n(this is the beginning of the file)\n1|\n2|\n3|\n4|import React, { useState, useEffect } from 'react';\n5|import axios from 'axios';\n6|import { Octokit } from '@octokit/rest';\n7|import Select from 'react-select';\n8|\n9|const octokit = new Octokit({ auth: import.meta.env.VITE_GITHUB_TOKEN });\n10|\n11|interface PullRequest {\n12| title: string;\n13| html_url: string;\n14| user: {\n15| login: string;\n16| };\n17|}\n18|\n19|interface Repo {\n20| value: string;\n21| label: string;\n22|}\n23|\n24|const PullRequestViewer: React.FC = () => {\n25| const [repos, setRepos] = useState([]);\n26| const [selectedRepo, setSelectedRepo] = useState(null);\n27| const [pullRequests, setPullRequests] = useState([]);\n28|\n29| useEffect(() => {\n30| const fetchRepos = async () => {\n31| try {\n32| const response = await octokit.repos.listForOrg({\n33| org: 'OpenDevin',\n34| type: 'all',\n35| });\n36| const repoOptions = response.data.map(repo => ({\n37| value: repo.name,\n38| label: repo.name,\n39| }));\n40| setRepos(repoOptions);\n41| } catch (error) {\n42| console.error('Error fetching repos:', error);\n43| }\n44| };\n45| fetchRepos();\n46| }, []);\n47|\n48| useEffect(() => {\n49| const fetchPullRequests = async () => {\n50| if (selectedRepo) {\n51| try {\n52| let allPullRequests: PullRequest[] = [];\n53| let page = 1;\n54| let hasNextPage = true;\n55|\n56| while (hasNextPage) {\n57| const response = await octokit.pulls.list({\n58| owner: 'OpenDevin',\n59| repo: selectedRepo.value,\n60| state: 'open',\n61| per_page: 100,\n62| page: page,\n63| });\n64|\n65| allPullRequests = [...allPullRequests, ...response.data];\n66|\n67| if (response.data.length < 100) {\n68| hasNextPage = false;\n69| } else {\n70| page++;\n71| }\n72| }\n73|\n74| setPullRequests(allPullRequests);\n75| } catch (error) {\n76| console.error('Error fetching pull requests:', error);\n77| }\n78| }\n79| };\n80| fetchPullRequests();\n81| }, [selectedRepo]);\n82|\n83| return (\n84|
\n85|

Pull Request Viewer

\n86| setSelectedRepo(option as Repo)}\n90| placeholder=\"Select a repository\"\n91| aria-label=\"Select a repository\"\n92| />\n93| {pullRequests.length > 0 ? (\n94|
    \n95| {pullRequests.map((pr) => (\n96|
  • \n97| \n98| {pr.title}\n99| \n100| {' by '}\n(12 more lines below)\n[Jupyter current working directory: /workspace]","code":"open_file('/workspace/src/PullRequestViewer.tsx')","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/PullRequestViewer.tsx',\nto_replace=\"\"\"\nimport React, { useState, useEffect } from 'react';\nimport axios from 'axios';\nimport { Octokit } from '@octokit/rest';\nimport Select from 'react-select';\n\nconst octokit = new Octokit({ auth: import.meta.env.VITE_GITHUB_TOKEN });\n\ninterface PullRequest {\n title: string;\n html_url: string;\n user: {\n login: string;\n };\n}\n\ninterface Repo {\n value: string;\n label: string;\n}\n\nconst PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n return (\n
    \n

    Pull Request Viewer

    \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
      \n {pullRequests.map((pr) => (\n
    • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
      • \n ))}\n
    \n ) : (\n

    No pull requests found.

    \n )}\n
    \n );\n};\n\nexport default PullRequestViewer;\"\"\",\nnew_content=\"\"\"\nimport React, { useState, useEffect } from 'react';\nimport axios from 'axios';\nimport { Octokit } from '@octokit/rest';\nimport Select from 'react-select';\n\nconst octokit = new Octokit({ auth: import.meta.env.VITE_GITHUB_TOKEN });\n\ninterface PullRequest {\n title: string;\n html_url: string;\n user: {\n login: string;\n };\n}\n\ninterface Repo {\n value: string;\n label: string;\n}\n\nconst PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n const [darkMode, setDarkMode] = useState(false);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode);\n document.body.classList.toggle('dark-mode');\n };\n\n return (\n
    \n

    Pull Request Viewer

    \n \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
      \n {pullRequests.map((pr) => (\n
    • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
      • \n ))}\n
    \n ) : (\n

    No pull requests found.

    \n )}\n
    \n );\n};\n\nexport default PullRequestViewer;\"\"\"\n)","thought":"Thank you for showing me the PullRequestViewer.tsx file. Let's modify this file to add the dark mode toggle functionality. We'll add a dark mode toggle button and update the component's styling based on the dark mode state.","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[No exact match found in /workspace/src/PullRequestViewer.tsx for\n```\n\nimport React, { useState, useEffect } from 'react';\nimport axios from 'axios';\nimport { Octokit } from '@octokit/rest';\nimport Select from 'react-select';\n\nconst octokit = new Octokit({ auth: import.meta.env.VITE_GITHUB_TOKEN });\n\ninterface PullRequest {\n title: string;\n html_url: string;\n user: {\n login: string;\n };\n}\n\ninterface Repo {\n value: string;\n label: string;\n}\n\nconst PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n return (\n
    \n

    Pull Request Viewer

    \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
      \n {pullRequests.map((pr) => (\n
    • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
      • \n ))}\n
    \n ) : (\n

    No pull requests found.

    \n )}\n
    \n );\n};\n\nexport default PullRequestViewer;\n```\n]\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/PullRequestViewer.tsx',\nto_replace=\"\"\"\nimport React, { useState, useEffect } from 'react';\nimport axios from 'axios';\nimport { Octokit } from '@octokit/rest';\nimport Select from 'react-select';\n\nconst octokit = new Octokit({ auth: import.meta.env.VITE_GITHUB_TOKEN });\n\ninterface PullRequest {\n title: string;\n html_url: string;\n user: {\n login: string;\n };\n}\n\ninterface Repo {\n value: string;\n label: string;\n}\n\nconst PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n return (\n
    \n

    Pull Request Viewer

    \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
      \n {pullRequests.map((pr) => (\n
    • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
      • \n ))}\n
    \n ) : (\n

    No pull requests found.

    \n )}\n
    \n );\n};\n\nexport default PullRequestViewer;\"\"\",\nnew_content=\"\"\"\nimport React, { useState, useEffect } from 'react';\nimport axios from 'axios';\nimport { Octokit } from '@octokit/rest';\nimport Select from 'react-select';\n\nconst octokit = new Octokit({ auth: import.meta.env.VITE_GITHUB_TOKEN });\n\ninterface PullRequest {\n title: string;\n html_url: string;\n user: {\n login: string;\n };\n}\n\ninterface Repo {\n value: string;\n label: string;\n}\n\nconst PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n const [darkMode, setDarkMode] = useState(false);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode);\n document.body.classList.toggle('dark-mode');\n };\n\n return (\n
    \n

    Pull Request Viewer

    \n \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
      \n {pullRequests.map((pr) => (\n
    • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
      • \n ))}\n
    \n ) : (\n

    No pull requests found.

    \n )}\n
    \n );\n};\n\nexport default PullRequestViewer;\"\"\"\n)","observation":"run_ipython"},{"code":"open_file('/workspace/src/PullRequestViewer.tsx')","thought":"I apologize for the confusion. It seems that the content of the PullRequestViewer.tsx file has changed since we last viewed it. Let's try to add the dark mode toggle functionality to the existing file content. First, let's view the current content of the file:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[File: /workspace/src/PullRequestViewer.tsx (112 lines total)]\n(this is the beginning of the file)\n1|\n2|\n3|\n4|import React, { useState, useEffect } from 'react';\n5|import axios from 'axios';\n6|import { Octokit } from '@octokit/rest';\n7|import Select from 'react-select';\n8|\n9|const octokit = new Octokit({ auth: import.meta.env.VITE_GITHUB_TOKEN });\n10|\n11|interface PullRequest {\n12| title: string;\n13| html_url: string;\n14| user: {\n15| login: string;\n16| };\n17|}\n18|\n19|interface Repo {\n20| value: string;\n21| label: string;\n22|}\n23|\n24|const PullRequestViewer: React.FC = () => {\n25| const [repos, setRepos] = useState([]);\n26| const [selectedRepo, setSelectedRepo] = useState(null);\n27| const [pullRequests, setPullRequests] = useState([]);\n28|\n29| useEffect(() => {\n30| const fetchRepos = async () => {\n31| try {\n32| const response = await octokit.repos.listForOrg({\n33| org: 'OpenDevin',\n34| type: 'all',\n35| });\n36| const repoOptions = response.data.map(repo => ({\n37| value: repo.name,\n38| label: repo.name,\n39| }));\n40| setRepos(repoOptions);\n41| } catch (error) {\n42| console.error('Error fetching repos:', error);\n43| }\n44| };\n45| fetchRepos();\n46| }, []);\n47|\n48| useEffect(() => {\n49| const fetchPullRequests = async () => {\n50| if (selectedRepo) {\n51| try {\n52| let allPullRequests: PullRequest[] = [];\n53| let page = 1;\n54| let hasNextPage = true;\n55|\n56| while (hasNextPage) {\n57| const response = await octokit.pulls.list({\n58| owner: 'OpenDevin',\n59| repo: selectedRepo.value,\n60| state: 'open',\n61| per_page: 100,\n62| page: page,\n63| });\n64|\n65| allPullRequests = [...allPullRequests, ...response.data];\n66|\n67| if (response.data.length < 100) {\n68| hasNextPage = false;\n69| } else {\n70| page++;\n71| }\n72| }\n73|\n74| setPullRequests(allPullRequests);\n75| } catch (error) {\n76| console.error('Error fetching pull requests:', error);\n77| }\n78| }\n79| };\n80| fetchPullRequests();\n81| }, [selectedRepo]);\n82|\n83| return (\n84|
    \n85|

    Pull Request Viewer

    \n86| setSelectedRepo(option as Repo)}\n90| placeholder=\"Select a repository\"\n91| aria-label=\"Select a repository\"\n92| />\n93| {pullRequests.length > 0 ? (\n94|
      \n95| {pullRequests.map((pr) => (\n96|
    • \n97| \n98| {pr.title}\n99| \n100| {' by '}\n(12 more lines below)\n[Jupyter current working directory: /workspace]","code":"open_file('/workspace/src/PullRequestViewer.tsx')","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/PullRequestViewer.tsx',\nto_replace=\"\"\"const PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n return (\n
      \n

      Pull Request Viewer

      \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
        \n {pullRequests.map((pr) => (\n
      • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
        • \n ))}\n
      \n ) : (\n

      No pull requests found.

      \n )}\n
      \n );\n};\"\"\",\nnew_content=\"\"\"const PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n const [darkMode, setDarkMode] = useState(false);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode);\n document.body.classList.toggle('dark-mode');\n };\n\n return (\n
      \n

      Pull Request Viewer

      \n \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
        \n {pullRequests.map((pr) => (\n
      • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
        • \n ))}\n
      \n ) : (\n

      No pull requests found.

      \n )}\n
      \n );\n};\"\"\"\n)","thought":"Thank you for showing me the current content of the file. Now, let's add the dark mode toggle functionality to the PullRequestViewer component. We'll make the following changes:\n\n1. Add a new state variable for dark mode\n2. Create a function to toggle dark mode\n3. Add a button to toggle dark mode\n4. Update the component's className based on the dark mode state\n\nHere's the updated code:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[No exact match found in /workspace/src/PullRequestViewer.tsx for\n```\nconst PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n return (\n
      \n

      Pull Request Viewer

      \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
        \n {pullRequests.map((pr) => (\n
      • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
        • \n ))}\n
      \n ) : (\n

      No pull requests found.

      \n )}\n
      \n );\n};\n```\n]\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/PullRequestViewer.tsx',\nto_replace=\"\"\"const PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n return (\n
      \n

      Pull Request Viewer

      \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
        \n {pullRequests.map((pr) => (\n
      • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
        • \n ))}\n
      \n ) : (\n

      No pull requests found.

      \n )}\n
      \n );\n};\"\"\",\nnew_content=\"\"\"const PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n const [darkMode, setDarkMode] = useState(false);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode);\n document.body.classList.toggle('dark-mode');\n };\n\n return (\n
      \n

      Pull Request Viewer

      \n \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
        \n {pullRequests.map((pr) => (\n
      • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
        • \n ))}\n
      \n ) : (\n

      No pull requests found.

      \n )}\n
      \n );\n};\"\"\"\n)","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/PullRequestViewer.tsx',\nto_replace=\"\"\"const PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n return (\n
      \n

      Pull Request Viewer

      \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
        \n {pullRequests.map((pr) => (\n
      • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
        • \n ))}\n
      \n ) : (\n

      No pull requests found.

      \n )}\n
      \n );\n};\"\"\",\nnew_content=\"\"\"const PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n const [darkMode, setDarkMode] = useState(false);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode);\n document.body.classList.toggle('dark-mode');\n };\n\n return (\n
      \n

      Pull Request Viewer

      \n \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
        \n {pullRequests.map((pr) => (\n
      • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
        • \n ))}\n
      \n ) : (\n

      No pull requests found.

      \n )}\n
      \n );\n};\"\"\"\n)","thought":"I apologize for the confusion. It seems that the content of the file has changed since we last viewed it. Let's try to add the dark mode toggle functionality by modifying the existing content. We'll add the dark mode state and toggle function, and update the component's return statement.","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[No exact match found in /workspace/src/PullRequestViewer.tsx for\n```\nconst PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n return (\n
      \n

      Pull Request Viewer

      \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
        \n {pullRequests.map((pr) => (\n
      • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
        • \n ))}\n
      \n ) : (\n

      No pull requests found.

      \n )}\n
      \n );\n};\n```\n]\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/PullRequestViewer.tsx',\nto_replace=\"\"\"const PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n return (\n
      \n

      Pull Request Viewer

      \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
        \n {pullRequests.map((pr) => (\n
      • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
        • \n ))}\n
      \n ) : (\n

      No pull requests found.

      \n )}\n
      \n );\n};\"\"\",\nnew_content=\"\"\"const PullRequestViewer: React.FC = () => {\n const [repos, setRepos] = useState([]);\n const [selectedRepo, setSelectedRepo] = useState(null);\n const [pullRequests, setPullRequests] = useState([]);\n const [darkMode, setDarkMode] = useState(false);\n\n useEffect(() => {\n const fetchRepos = async () => {\n try {\n const response = await octokit.repos.listForOrg({\n org: 'OpenDevin',\n type: 'all',\n });\n const repoOptions = response.data.map(repo => ({\n value: repo.name,\n label: repo.name,\n }));\n setRepos(repoOptions);\n } catch (error) {\n console.error('Error fetching repos:', error);\n }\n };\n fetchRepos();\n }, []);\n\n useEffect(() => {\n const fetchPullRequests = async () => {\n if (selectedRepo) {\n try {\n let allPullRequests: PullRequest[] = [];\n let page = 1;\n let hasNextPage = true;\n\n while (hasNextPage) {\n const response = await octokit.pulls.list({\n owner: 'OpenDevin',\n repo: selectedRepo.value,\n state: 'open',\n per_page: 100,\n page: page,\n });\n\n allPullRequests = [...allPullRequests, ...response.data];\n\n if (response.data.length < 100) {\n hasNextPage = false;\n } else {\n page++;\n }\n }\n\n setPullRequests(allPullRequests);\n } catch (error) {\n console.error('Error fetching pull requests:', error);\n }\n }\n };\n fetchPullRequests();\n }, [selectedRepo]);\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode);\n document.body.classList.toggle('dark-mode');\n };\n\n return (\n
      \n

      Pull Request Viewer

      \n \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\n {pullRequests.length > 0 ? (\n
        \n {pullRequests.map((pr) => (\n
      • \n \n {pr.title}\n \n {' by '}\n {pr.user.login}\n
        • \n ))}\n
      \n ) : (\n

      No pull requests found.

      \n )}\n
      \n );\n};\"\"\"\n)","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/PullRequestViewer.tsx',\nto_replace=\"const [pullRequests, setPullRequests] = useState([]);\",\nnew_content=\"\"\"const [pullRequests, setPullRequests] = useState([]);\n const [darkMode, setDarkMode] = useState(false);\"\"\"\n)","thought":"I apologize for the confusion. It seems that the content of the file has changed significantly since we last viewed it. Let's try a different approach by adding the dark mode functionality to the existing code without replacing large portions of it. We'll modify the file incrementally:\n\n1. First, let's add the dark mode state:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[File: /workspace/src/PullRequestViewer.tsx (113 lines total after edit)]\n(this is the beginning of the file)\n1|\n2|\n3|\n4|import React, { useState, useEffect } from 'react';\n5|import axios from 'axios';\n6|import { Octokit } from '@octokit/rest';\n7|import Select from 'react-select';\n8|\n9|const octokit = new Octokit({ auth: import.meta.env.VITE_GITHUB_TOKEN });\n10|\n11|interface PullRequest {\n12| title: string;\n13| html_url: string;\n14| user: {\n15| login: string;\n16| };\n17|}\n18|\n19|interface Repo {\n20| value: string;\n21| label: string;\n22|}\n23|\n24|const PullRequestViewer: React.FC = () => {\n25| const [repos, setRepos] = useState([]);\n26| const [selectedRepo, setSelectedRepo] = useState(null);\n27|const [pullRequests, setPullRequests] = useState([]);\n28| const [darkMode, setDarkMode] = useState(false);\n29|\n30| useEffect(() => {\n31| const fetchRepos = async () => {\n32| try {\n33| const response = await octokit.repos.listForOrg({\n34| org: 'OpenDevin',\n35| type: 'all',\n36| });\n37| const repoOptions = response.data.map(repo => ({\n38| value: repo.name,\n39| label: repo.name,\n40| }));\n41| setRepos(repoOptions);\n42| } catch (error) {\n43| console.error('Error fetching repos:', error);\n44| }\n45| };\n46| fetchRepos();\n47| }, []);\n48|\n49| useEffect(() => {\n50| const fetchPullRequests = async () => {\n51| if (selectedRepo) {\n52| try {\n53| let allPullRequests: PullRequest[] = [];\n54| let page = 1;\n55| let hasNextPage = true;\n56|\n57| while (hasNextPage) {\n58| const response = await octokit.pulls.list({\n59| owner: 'OpenDevin',\n60| repo: selectedRepo.value,\n61| state: 'open',\n62| per_page: 100,\n63| page: page,\n64| });\n65|\n66| allPullRequests = [...allPullRequests, ...response.data];\n67|\n68| if (response.data.length < 100) {\n69| hasNextPage = false;\n70| } else {\n71| page++;\n72| }\n73| }\n74|\n75| setPullRequests(allPullRequests);\n76| } catch (error) {\n77| console.error('Error fetching pull requests:', error);\n78| }\n79| }\n80| };\n81| fetchPullRequests();\n82| }, [selectedRepo]);\n83|\n84| return (\n85|
      \n86|

      Pull Request Viewer

      \n87| setSelectedRepo(option as Repo)}\n91| placeholder=\"Select a repository\"\n92| aria-label=\"Select a repository\"\n93| />\n94| {pullRequests.length > 0 ? (\n95|
        \n96| {pullRequests.map((pr) => (\n97|
      • \n98| \n99| {pr.title}\n100| \n(13 more lines below)\n[File updated (edited at line 27). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/PullRequestViewer.tsx',\nto_replace=\"const [pullRequests, setPullRequests] = useState([]);\",\nnew_content=\"\"\"const [pullRequests, setPullRequests] = useState([]);\n const [darkMode, setDarkMode] = useState(false);\"\"\"\n)","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/PullRequestViewer.tsx',\nto_replace=\" }, [selectedRepo]);\",\nnew_content=\"\"\" }, [selectedRepo]);\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode);\n document.body.classList.toggle('dark-mode');\n };\"\"\"\n)","thought":"Thank you for the update. Now let's add the toggle function for dark mode:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[File: /workspace/src/PullRequestViewer.tsx (118 lines total after edit)]\n(18 more lines above)\n19|interface Repo {\n20| value: string;\n21| label: string;\n22|}\n23|\n24|const PullRequestViewer: React.FC = () => {\n25| const [repos, setRepos] = useState([]);\n26| const [selectedRepo, setSelectedRepo] = useState(null);\n27|const [pullRequests, setPullRequests] = useState([]);\n28| const [darkMode, setDarkMode] = useState(false);\n29|\n30| useEffect(() => {\n31| const fetchRepos = async () => {\n32| try {\n33| const response = await octokit.repos.listForOrg({\n34| org: 'OpenDevin',\n35| type: 'all',\n36| });\n37| const repoOptions = response.data.map(repo => ({\n38| value: repo.name,\n39| label: repo.name,\n40| }));\n41| setRepos(repoOptions);\n42| } catch (error) {\n43| console.error('Error fetching repos:', error);\n44| }\n45| };\n46| fetchRepos();\n47| }, []);\n48|\n49| useEffect(() => {\n50| const fetchPullRequests = async () => {\n51| if (selectedRepo) {\n52| try {\n53| let allPullRequests: PullRequest[] = [];\n54| let page = 1;\n55| let hasNextPage = true;\n56|\n57| while (hasNextPage) {\n58| const response = await octokit.pulls.list({\n59| owner: 'OpenDevin',\n60| repo: selectedRepo.value,\n61| state: 'open',\n62| per_page: 100,\n63| page: page,\n64| });\n65|\n66| allPullRequests = [...allPullRequests, ...response.data];\n67|\n68| if (response.data.length < 100) {\n69| hasNextPage = false;\n70| } else {\n71| page++;\n72| }\n73| }\n74|\n75| setPullRequests(allPullRequests);\n76| } catch (error) {\n77| console.error('Error fetching pull requests:', error);\n78| }\n79| }\n80| };\n81| fetchPullRequests();\n82| }, [selectedRepo]);\n83|\n84| const toggleDarkMode = () => {\n85| setDarkMode(!darkMode);\n86| document.body.classList.toggle('dark-mode');\n87| };\n88|\n89| return (\n90|
        \n91|

        Pull Request Viewer

        \n92| setSelectedRepo(option as Repo)}\n96| placeholder=\"Select a repository\"\n97| aria-label=\"Select a repository\"\n98| />\n99| {pullRequests.length > 0 ? (\n100|
          \n101| {pullRequests.map((pr) => (\n102|
        • \n103| \n104| {pr.title}\n105| \n106| {' by '}\n107| {pr.user.login}\n108|
          • \n109| ))}\n110|
        \n111| ) : (\n112|

        No open pull requests found.

        \n113| )}\n114|
        \n115| );\n116|};\n117|\n118|export default PullRequestViewer;\n(this is the end of the file)\n[File updated (edited at line 82). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/PullRequestViewer.tsx',\nto_replace=\" }, [selectedRepo]);\",\nnew_content=\"\"\" }, [selectedRepo]);\n\n const toggleDarkMode = () => {\n setDarkMode(!darkMode);\n document.body.classList.toggle('dark-mode');\n };\"\"\"\n)","observation":"run_ipython"},{"code":"edit_file_by_replace(\n'/workspace/src/PullRequestViewer.tsx',\nto_replace=\"\"\" return (\n
        \n

        Pull Request Viewer

        \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\"\"\",\nnew_content=\"\"\" return (\n
        \n

        Pull Request Viewer

        \n \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\"\"\"\n)","thought":"Thank you for the update. Now let's add the dark mode toggle button and update the main div to include the dark mode class:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[File: /workspace/src/PullRequestViewer.tsx (121 lines total after edit)]\n(21 more lines above)\n22|}\n23|\n24|const PullRequestViewer: React.FC = () => {\n25| const [repos, setRepos] = useState([]);\n26| const [selectedRepo, setSelectedRepo] = useState(null);\n27|const [pullRequests, setPullRequests] = useState([]);\n28| const [darkMode, setDarkMode] = useState(false);\n29|\n30| useEffect(() => {\n31| const fetchRepos = async () => {\n32| try {\n33| const response = await octokit.repos.listForOrg({\n34| org: 'OpenDevin',\n35| type: 'all',\n36| });\n37| const repoOptions = response.data.map(repo => ({\n38| value: repo.name,\n39| label: repo.name,\n40| }));\n41| setRepos(repoOptions);\n42| } catch (error) {\n43| console.error('Error fetching repos:', error);\n44| }\n45| };\n46| fetchRepos();\n47| }, []);\n48|\n49| useEffect(() => {\n50| const fetchPullRequests = async () => {\n51| if (selectedRepo) {\n52| try {\n53| let allPullRequests: PullRequest[] = [];\n54| let page = 1;\n55| let hasNextPage = true;\n56|\n57| while (hasNextPage) {\n58| const response = await octokit.pulls.list({\n59| owner: 'OpenDevin',\n60| repo: selectedRepo.value,\n61| state: 'open',\n62| per_page: 100,\n63| page: page,\n64| });\n65|\n66| allPullRequests = [...allPullRequests, ...response.data];\n67|\n68| if (response.data.length < 100) {\n69| hasNextPage = false;\n70| } else {\n71| page++;\n72| }\n73| }\n74|\n75| setPullRequests(allPullRequests);\n76| } catch (error) {\n77| console.error('Error fetching pull requests:', error);\n78| }\n79| }\n80| };\n81| fetchPullRequests();\n82| }, [selectedRepo]);\n83|\n84| const toggleDarkMode = () => {\n85| setDarkMode(!darkMode);\n86| document.body.classList.toggle('dark-mode');\n87| };\n88|\n89| return (\n90|
        \n91|

        Pull Request Viewer

        \n92| \n95| setSelectedRepo(option as Repo)}\n99| placeholder=\"Select a repository\"\n100| aria-label=\"Select a repository\"\n101| />\n102| {pullRequests.length > 0 ? (\n103|
          \n104| {pullRequests.map((pr) => (\n105|
        • \n106| \n107| {pr.title}\n108| \n109| {' by '}\n110| {pr.user.login}\n111|
          • \n112| ))}\n113|
        \n114| ) : (\n115|

        No open pull requests found.

        \n116| )}\n117|
        \n118| );\n119|};\n120|\n121|export default PullRequestViewer;\n(this is the end of the file)\n[File updated (edited at line 89). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]\n[Jupyter current working directory: /workspace]","code":"edit_file_by_replace(\n'/workspace/src/PullRequestViewer.tsx',\nto_replace=\"\"\" return (\n
        \n

        Pull Request Viewer

        \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\"\"\",\nnew_content=\"\"\" return (\n
        \n

        Pull Request Viewer

        \n \n setSelectedRepo(option as Repo)}\n placeholder=\"Select a repository\"\n aria-label=\"Select a repository\"\n />\"\"\"\n)","observation":"run_ipython"},{"code":"open_file('/workspace/src/App.css')","thought":"The changes have been successfully applied to the PullRequestViewer.tsx file. We have added the dark mode functionality as requested. Now, let's update the App.css file to include the dark mode styles:","action":"run_ipython","is_confirmed":"confirmed","security_risk":null,"kernel_init_code":"from agentskills import *"},{"content":"[File: /workspace/src/App.css (79 lines total)]\n(this is the beginning of the file)\n1|#root {\n2| max-width: 1280px;\n3| margin: 0 auto;\n4| padding: 2rem;\n5| text-align: center;\n6|}\n7|\n8|body {\n9| background-color: #ffffff;\n10| color: #213547;\n11| transition: background-color 0.3s, color 0.3s;\n12|}\n13|\n14|body.dark-mode {\n15| background-color: #242424;\n16| color: #ffffff;\n17|}\n18|\n19|.logo {\n20| height: 6em;\n21| padding: 1.5em;\n22| will-change: filter;\n23| transition: filter 300ms;\n24|}\n25|.logo:hover {\n26| filter: drop-shadow(0 0 2em #646cffaa);\n27|}\n28|.logo.react:hover {\n29| filter: drop-shadow(0 0 2em #61dafbaa);\n30|}\n31|\n32|@keyframes logo-spin {\n33| from {\n34| transform: rotate(0deg);\n35| }\n36| to {\n37| transform: rotate(360deg);\n38| }\n39|}\n40|\n41|@media (prefers-reduced-motion: no-preference) {\n42| a:nth-of-type(2) .logo {\n43| animation: logo-spin infinite 20s linear;\n44| }\n45|}\n46|\n47|.card {\n48| padding: 2em;\n49|}\n50|\n51|.read-the-docs {\n52| color: #888;\n53|}\n54|\n55|.dark-mode-toggle {\n56| position: fixed;\n57| top: 20px;\n58| right: 20px;\n59| background-color: #646cff;\n60| color: white;\n61| border: none;\n62| padding: 10px 20px;\n63| border-radius: 5px;\n64| cursor: pointer;\n65| transition: background-color 0.3s;\n66|}\n67|\n68|.dark-mode-toggle:hover {\n69| background-color: #535bf2;\n70|}\n71|\n72|.dark-mode .dark-mode-toggle {\n73| background-color: #ffffff;\n74| color: #242424;\n75|}\n76|\n77|.dark-mode .dark-mode-toggle:hover {\n78| background-color: #e6e6e6;\n79|}\n(this is the end of the file)\n[Jupyter current working directory: /workspace]","code":"open_file('/workspace/src/App.css')","observation":"run_ipython"},{"outputs":{},"thought":"The App.css file already contains the necessary styles for dark mode. We don't need to make any changes to this file. The dark mode functionality has been successfully implemented in the PullRequestViewer component.\n\nTo summarize the changes we've made:\n\n1. We added a dark mode state to the PullRequestViewer component.\n2. We implemented a toggleDarkMode function to switch between light and dark modes.\n3. We added a button to toggle dark mode in the component's render method.\n4. We updated the main div to include the dark-mode class when dark mode is active.\n\nThe existing CSS styles in App.css will handle the appearance changes for dark mode.\n\nThe task of adding dark mode support to the application has been completed. The toggle can now turn on and off dark mode as requested.","action":"finish"}],"metrics":{"accumulated_cost":1.152933,"costs":[0.015645,0.016581,0.029745,0.022647,0.027885,0.0309,0.033864000000000005,0.036774,0.039504,0.041799,0.044382000000000005,0.046148999999999996,0.045693,0.07552500000000001,0.057120000000000004,0.083457,0.09005099999999999,0.075882,0.078789,0.084789,0.085836,0.089916]},"success":true,"comment_success":null,"success_explanation":"The AI agent has successfully implemented the dark mode functionality as requested. They added a toggle to switch between light and dark modes in the PullRequestViewer component, created the necessary state and function to handle the mode switching, and ensured that the existing CSS in App.css will apply the appropriate styles. The agent confirms that the dark mode can be turned on and off using the newly added toggle, which directly addresses the requirements specified in the issue description.","error":null} diff --git a/tests/unit/resolver/mock_output/repo/src/App.css b/tests/unit/resolver/mock_output/repo/src/App.css new file mode 100644 index 000000000000..b9d355df2a59 --- /dev/null +++ b/tests/unit/resolver/mock_output/repo/src/App.css @@ -0,0 +1,42 @@ +#root { + max-width: 1280px; + margin: 0 auto; + padding: 2rem; + text-align: center; +} + +.logo { + height: 6em; + padding: 1.5em; + will-change: filter; + transition: filter 300ms; +} +.logo:hover { + filter: drop-shadow(0 0 2em #646cffaa); +} +.logo.react:hover { + filter: drop-shadow(0 0 2em #61dafbaa); +} + +@keyframes logo-spin { + from { + transform: rotate(0deg); + } + to { + transform: rotate(360deg); + } +} + +@media (prefers-reduced-motion: no-preference) { + a:nth-of-type(2) .logo { + animation: logo-spin infinite 20s linear; + } +} + +.card { + padding: 2em; +} + +.read-the-docs { + color: #888; +} diff --git a/tests/unit/resolver/mock_output/repo/src/App.tsx b/tests/unit/resolver/mock_output/repo/src/App.tsx new file mode 100644 index 000000000000..c3dd99ca1b44 --- /dev/null +++ b/tests/unit/resolver/mock_output/repo/src/App.tsx @@ -0,0 +1,14 @@ + +import React from 'react' +import './App.css' +import PullRequestViewer from './PullRequestViewer' + +function App() { + return ( +
        + +
        + ) +} + +export default App diff --git a/tests/unit/resolver/mock_output/repo/src/PullRequestViewer.test.tsx b/tests/unit/resolver/mock_output/repo/src/PullRequestViewer.test.tsx new file mode 100644 index 000000000000..10f29598b56f --- /dev/null +++ b/tests/unit/resolver/mock_output/repo/src/PullRequestViewer.test.tsx @@ -0,0 +1,19 @@ + + +import React from 'react'; +import { render, screen } from '@testing-library/react'; +import PullRequestViewer from './PullRequestViewer'; + +describe('PullRequestViewer', () => { + it('renders the component title', () => { + render(); + const titleElement = screen.getByText(/Pull Request Viewer/i); + expect(titleElement).toBeInTheDocument(); + }); + + it('renders the repository select dropdown', () => { + render(); + const selectElement = screen.getByRole('combobox', { name: /select a repository/i }); + expect(selectElement).toBeInTheDocument(); + }); +}); diff --git a/tests/unit/resolver/mock_output/repo/src/PullRequestViewer.tsx b/tests/unit/resolver/mock_output/repo/src/PullRequestViewer.tsx new file mode 100644 index 000000000000..6a8281f7af49 --- /dev/null +++ b/tests/unit/resolver/mock_output/repo/src/PullRequestViewer.tsx @@ -0,0 +1,112 @@ + + + +import React, { useState, useEffect } from 'react'; +import axios from 'axios'; +import { Octokit } from '@octokit/rest'; +import Select from 'react-select'; + +const octokit = new Octokit({ auth: import.meta.env.VITE_GITHUB_TOKEN }); + +interface PullRequest { + title: string; + html_url: string; + user: { + login: string; + }; +} + +interface Repo { + value: string; + label: string; +} + +const PullRequestViewer: React.FC = () => { + const [repos, setRepos] = useState([]); + const [selectedRepo, setSelectedRepo] = useState(null); + const [pullRequests, setPullRequests] = useState([]); + + useEffect(() => { + const fetchRepos = async () => { + try { + const response = await octokit.repos.listForOrg({ + org: 'OpenDevin', + type: 'all', + }); + const repoOptions = response.data.map(repo => ({ + value: repo.name, + label: repo.name, + })); + setRepos(repoOptions); + } catch (error) { + console.error('Error fetching repos:', error); + } + }; + fetchRepos(); + }, []); + + useEffect(() => { + const fetchPullRequests = async () => { + if (selectedRepo) { + try { + let allPullRequests: PullRequest[] = []; + let page = 1; + let hasNextPage = true; + + while (hasNextPage) { + const response = await octokit.pulls.list({ + owner: 'OpenDevin', + repo: selectedRepo.value, + state: 'open', + per_page: 100, + page: page, + }); + + allPullRequests = [...allPullRequests, ...response.data]; + + if (response.data.length < 100) { + hasNextPage = false; + } else { + page++; + } + } + + setPullRequests(allPullRequests); + } catch (error) { + console.error('Error fetching pull requests:', error); + } + } + }; + fetchPullRequests(); + }, [selectedRepo]); + + return ( +
        +

        Pull Request Viewer

        + { - const toastId = idMap.get(id); - if (toastId === undefined) return; - if (toastId) { - toast.success(msg, { - id: toastId, - duration: 4000, - style: { - background: "#333", - color: "#fff", - lineBreak: "anywhere", - }, - iconTheme: { - primary: "#333", - secondary: "#fff", - }, - }); - } - idMap.delete(id); + success: (id: string, msg: string, duration: number = 4000) => { + if (idMap.has(id)) return; // prevent duplicate toast + const toastId = toast.success(msg, { + duration, + style: { + background: "#333", + color: "#fff", + }, + iconTheme: { + primary: "#333", + secondary: "#fff", + }, + }); + idMap.set(id, toastId); }, settingsChanged: (msg: string) => { toast(msg, { @@ -48,7 +42,6 @@ export default { style: { background: "#333", color: "#fff", - lineBreak: "anywhere", }, }); }, diff --git a/openhands/agenthub/browsing_agent/__init__.py b/openhands/agenthub/browsing_agent/__init__.py index fe90dc828226..436d69d135f9 100644 --- a/openhands/agenthub/browsing_agent/__init__.py +++ b/openhands/agenthub/browsing_agent/__init__.py @@ -1,4 +1,4 @@ from openhands.agenthub.browsing_agent.browsing_agent import BrowsingAgent from openhands.controller.agent import Agent -Agent.register("BrowsingAgent", BrowsingAgent) +Agent.register('BrowsingAgent', BrowsingAgent) diff --git a/openhands/agenthub/browsing_agent/browsing_agent.py b/openhands/agenthub/browsing_agent/browsing_agent.py index dec7753d1519..822677bab526 100644 --- a/openhands/agenthub/browsing_agent/browsing_agent.py +++ b/openhands/agenthub/browsing_agent/browsing_agent.py @@ -24,10 +24,10 @@ ) USE_NAV = ( - os.environ.get("USE_NAV", "true") == "true" + os.environ.get('USE_NAV', 'true') == 'true' ) # only disable NAV actions when running webarena and miniwob benchmarks USE_CONCISE_ANSWER = ( - os.environ.get("USE_CONCISE_ANSWER", "false") == "true" + os.environ.get('USE_CONCISE_ANSWER', 'false') == 'true' ) # only return concise answer when running webarena and miniwob benchmarks if not USE_NAV and USE_CONCISE_ANSWER: @@ -37,7 +37,7 @@ def get_error_prefix(last_browser_action: str) -> str: - return f"IMPORTANT! Last action is incorrect:\n{last_browser_action}\nThink again with the current observation of the page.\n" + return f'IMPORTANT! Last action is incorrect:\n{last_browser_action}\nThink again with the current observation of the page.\n' def get_system_message(goal: str, action_space: str) -> str: @@ -92,7 +92,7 @@ def get_prompt( class BrowsingAgent(Agent): - VERSION = "1.0" + VERSION = '1.0' """ An agent that interacts with the browser. """ @@ -113,9 +113,9 @@ def __init__( super().__init__(llm, config) # define a configurable action space, with chat functionality, web navigation, and webpage grounding using accessibility tree and HTML. # see https://github.com/ServiceNow/BrowserGym/blob/main/core/src/browsergym/core/action/highlevel.py for more details - action_subsets = ["chat", "bid"] + action_subsets = ['chat', 'bid'] if USE_NAV: - action_subsets.append("nav") + action_subsets.append('nav') self.action_space = HighLevelActionSet( subsets=action_subsets, strict=False, # less strict on the parsing of the actions @@ -144,9 +144,9 @@ def step(self, state: State) -> Action: """ messages: list[Message] = [] prev_actions = [] - cur_url = "" - cur_axtree_txt = "" - error_prefix = "" + cur_url = '' + cur_axtree_txt = '' + error_prefix = '' last_obs = None last_action = None @@ -154,7 +154,7 @@ def step(self, state: State) -> Action: # for webarena and miniwob++ eval, we need to retrieve the initial observation already in browser env # initialize and retrieve the first observation by issuing an noop OP # For non-benchmark browsing, the browser env starts with a blank page, and the agent is expected to first navigate to desired websites - return BrowseInteractiveAction(browser_actions="noop()") + return BrowseInteractiveAction(browser_actions='noop()') for event in state.history: if isinstance(event, BrowseInteractiveAction): @@ -162,14 +162,14 @@ def step(self, state: State) -> Action: last_action = event elif isinstance(event, MessageAction) and event.source == EventSource.AGENT: # agent has responded, task finished. - return AgentFinishAction(outputs={"content": event.content}) + return AgentFinishAction(outputs={'content': event.content}) elif isinstance(event, Observation): last_obs = event if EVAL_MODE: prev_actions = prev_actions[1:] # remove the first noop action - prev_action_str = "\n".join(prev_actions) + prev_action_str = '\n'.join(prev_actions) # if the final BrowserInteractiveAction exec BrowserGym's send_msg_to_user, # we should also send a message back to the user in OpenHands and call it a day if ( @@ -184,7 +184,7 @@ def step(self, state: State) -> Action: error_prefix = get_error_prefix(last_obs.last_browser_action) self.error_accumulator += 1 if self.error_accumulator > 5: - return MessageAction("Too many errors encountered. Task failed.") + return MessageAction('Too many errors encountered. Task failed.') cur_url = last_obs.url @@ -197,27 +197,27 @@ def step(self, state: State) -> Action: ) except Exception as e: logger.error( - "Error when trying to process the accessibility tree: %s", e + 'Error when trying to process the accessibility tree: %s', e ) - return MessageAction("Error encountered when browsing.") + return MessageAction('Error encountered when browsing.') goal, _ = state.get_current_user_intent() if goal is None: - goal = state.inputs["task"] + goal = state.inputs['task'] system_msg = get_system_message( goal, self.action_space.describe(with_long_description=False, with_examples=True), ) - messages.append(Message(role="system", content=[TextContent(text=system_msg)])) + messages.append(Message(role='system', content=[TextContent(text=system_msg)])) prompt = get_prompt(error_prefix, cur_url, cur_axtree_txt, prev_action_str) - messages.append(Message(role="user", content=[TextContent(text=prompt)])) + messages.append(Message(role='user', content=[TextContent(text=prompt)])) response = self.llm.completion( messages=self.llm.format_messages_for_llm(messages), - stop=[")```", ")\n```"], + stop=[')```', ')\n```'], ) return self.response_parser.parse(response) diff --git a/openhands/agenthub/browsing_agent/prompt.py b/openhands/agenthub/browsing_agent/prompt.py index 0bd6883bf873..354156841912 100644 --- a/openhands/agenthub/browsing_agent/prompt.py +++ b/openhands/agenthub/browsing_agent/prompt.py @@ -31,22 +31,22 @@ class Flags: use_action_history: bool = False use_memory: bool = False use_diff: bool = False - html_type: str = "pruned_html" + html_type: str = 'pruned_html' use_concrete_example: bool = True use_abstract_example: bool = False multi_actions: bool = False action_space: Literal[ - "python", "bid", "coord", "bid+coord", "bid+nav", "coord+nav", "bid+coord+nav" - ] = "bid" + 'python', 'bid', 'coord', 'bid+coord', 'bid+nav', 'coord+nav', 'bid+coord+nav' + ] = 'bid' is_strict: bool = False # This flag will be automatically disabled `if not chat_model_args.has_vision()` use_screenshot: bool = True enable_chat: bool = False max_prompt_tokens: int = 100_000 extract_visible_tag: bool = False - extract_coords: Literal["False", "center", "box"] = "False" + extract_coords: Literal['False', 'center', 'box'] = 'False' extract_visible_elements_only: bool = False - demo_mode: Literal["off", "default", "only_visible_elements"] = "off" + demo_mode: Literal['off', 'default', 'only_visible_elements'] = 'off' def copy(self): return deepcopy(self) @@ -63,7 +63,7 @@ def from_dict(self, flags_dict): if not isinstance(flags_dict, dict): raise ValueError( - f"Unregcognized type for flags_dict of type {type(flags_dict)}." + f'Unregcognized type for flags_dict of type {type(flags_dict)}.' ) return Flags(**flags_dict) @@ -77,9 +77,9 @@ class PromptElement: attributes or @property decorator. """ - _prompt = "" - _abstract_ex = "" - _concrete_ex = "" + _prompt = '' + _abstract_ex = '' + _concrete_ex = '' def __init__(self, visible: bool = True) -> None: """Prompt element that can be hidden. @@ -131,7 +131,7 @@ def _hide(self, value): if self.is_visible: return value else: - return "" + return '' def _parse_answer(self, text_answer) -> dict: if self.is_visible: @@ -174,9 +174,9 @@ def shrink(self) -> None: lines = self._prompt.splitlines() new_line_count = int(len(lines) * (1 - self.shrink_speed)) self.deleted_lines += len(lines) - new_line_count - self._prompt = "\n".join(lines[:new_line_count]) + self._prompt = '\n'.join(lines[:new_line_count]) self._prompt += ( - f"\n... Deleted {self.deleted_lines} lines to reduce prompt size." + f'\n... Deleted {self.deleted_lines} lines to reduce prompt size.' ) self.shrink_calls += 1 @@ -212,9 +212,9 @@ def fit_tokens( if isinstance(prompt, str): prompt_str = prompt elif isinstance(prompt, list): - prompt_str = "\n".join([p["text"] for p in prompt if p["type"] == "text"]) + prompt_str = '\n'.join([p['text'] for p in prompt if p['type'] == 'text']) else: - raise ValueError(f"Unrecognized type for prompt: {type(prompt)}") + raise ValueError(f'Unrecognized type for prompt: {type(prompt)}') n_chars = len(prompt_str) if n_chars <= max_prompt_chars: return prompt @@ -231,33 +231,33 @@ def fit_tokens( class HTML(Truncater): - def __init__(self, html, visible: bool = True, prefix="") -> None: + def __init__(self, html, visible: bool = True, prefix='') -> None: super().__init__(visible=visible, start_truncate_iteration=5) - self._prompt = f"\n{prefix}HTML:\n{html}\n" + self._prompt = f'\n{prefix}HTML:\n{html}\n' class AXTree(Truncater): def __init__( - self, ax_tree, visible: bool = True, coord_type=None, prefix="" + self, ax_tree, visible: bool = True, coord_type=None, prefix='' ) -> None: super().__init__(visible=visible, start_truncate_iteration=10) - if coord_type == "center": + if coord_type == 'center': coord_note = """\ Note: center coordinates are provided in parenthesis and are relative to the top left corner of the page.\n\n""" - elif coord_type == "box": + elif coord_type == 'box': coord_note = """\ Note: bounding box of each object are provided in parenthesis and are relative to the top left corner of the page.\n\n""" else: - coord_note = "" - self._prompt = f"\n{prefix}AXTree:\n{coord_note}{ax_tree}\n" + coord_note = '' + self._prompt = f'\n{prefix}AXTree:\n{coord_note}{ax_tree}\n' class Error(PromptElement): - def __init__(self, error, visible: bool = True, prefix="") -> None: + def __init__(self, error, visible: bool = True, prefix='') -> None: super().__init__(visible=visible) - self._prompt = f"\n{prefix}Error from previous action:\n{error}\n" + self._prompt = f'\n{prefix}Error from previous action:\n{error}\n' class Observation(Shrinkable): @@ -270,17 +270,17 @@ def __init__(self, obs, flags: Flags) -> None: super().__init__() self.flags = flags self.obs = obs - self.html = HTML(obs[flags.html_type], visible=flags.use_html, prefix="## ") + self.html = HTML(obs[flags.html_type], visible=flags.use_html, prefix='## ') self.ax_tree = AXTree( - obs["axtree_txt"], + obs['axtree_txt'], visible=flags.use_ax_tree, coord_type=flags.extract_coords, - prefix="## ", + prefix='## ', ) self.error = Error( - obs["last_action_error"], - visible=flags.use_error_logs and obs["last_action_error"], - prefix="## ", + obs['last_action_error'], + visible=flags.use_error_logs and obs['last_action_error'], + prefix='## ', ) def shrink(self): @@ -289,24 +289,24 @@ def shrink(self): @property def _prompt(self) -> str: # type: ignore - return f"\n# Observation of current step:\n{self.html.prompt}{self.ax_tree.prompt}{self.error.prompt}\n\n" + return f'\n# Observation of current step:\n{self.html.prompt}{self.ax_tree.prompt}{self.error.prompt}\n\n' def add_screenshot(self, prompt): if self.flags.use_screenshot: if isinstance(prompt, str): - prompt = [{"type": "text", "text": prompt}] + prompt = [{'type': 'text', 'text': prompt}] img_url = BrowserEnv.image_to_jpg_base64_url( - self.obs["screenshot"], add_data_prefix=True + self.obs['screenshot'], add_data_prefix=True ) - prompt.append({"type": "image_url", "image_url": img_url}) + prompt.append({'type': 'image_url', 'image_url': img_url}) return prompt class MacNote(PromptElement): def __init__(self) -> None: - super().__init__(visible=platform.system() == "Darwin") - self._prompt = "\nNote: you are on mac so you should use Meta instead of Control for Control+C etc.\n" + super().__init__(visible=platform.system() == 'Darwin') + self._prompt = '\nNote: you are on mac so you should use Meta instead of Control for Control+C etc.\n' class BeCautious(PromptElement): @@ -351,7 +351,7 @@ def __init__(self, chat_messages, visible: bool = True) -> None: ## Chat messages: """ - self._prompt += "\n".join( + self._prompt += '\n'.join( [ f"""\ - [{msg['role']}], {msg['message']}""" @@ -381,20 +381,20 @@ def __init__( self.history = History(obs_history, actions, memories, thoughts, flags) if self.flags.enable_chat: self.instructions: Union[ChatInstructions, GoalInstructions] = ( - ChatInstructions(obs_history[-1]["chat_messages"]) + ChatInstructions(obs_history[-1]['chat_messages']) ) else: if ( - "chat_messages" in obs_history[-1] + 'chat_messages' in obs_history[-1] and sum( - [msg["role"] == "user" for msg in obs_history[-1]["chat_messages"]] + [msg['role'] == 'user' for msg in obs_history[-1]['chat_messages']] ) > 1 ): logging.warning( - "Agent is in goal mode, but multiple user messages are present in the chat. Consider switching to `enable_chat=True`." + 'Agent is in goal mode, but multiple user messages are present in the chat. Consider switching to `enable_chat=True`.' ) - self.instructions = GoalInstructions(obs_history[-1]["goal"]) + self.instructions = GoalInstructions(obs_history[-1]['goal']) self.obs = Observation(obs_history[-1], self.flags) self.action_space = ActionSpace(self.flags) @@ -456,7 +456,7 @@ def __init__(self, flags: Flags) -> None: self.action_space = _get_action_space(flags) self._prompt = ( - f"# Action space:\n{self.action_space.describe()}{MacNote().prompt}\n" + f'# Action space:\n{self.action_space.describe()}{MacNote().prompt}\n' ) self._abstract_ex = f""" @@ -471,17 +471,17 @@ def __init__(self, flags: Flags) -> None: def _parse_answer(self, text_answer): ans_dict = parse_html_tags_raise( - text_answer, keys=["action"], merge_multiple=True + text_answer, keys=['action'], merge_multiple=True ) try: # just check if action can be mapped to python code but keep action as is # the environment will be responsible for mapping it to python - self.action_space.to_python_code(ans_dict["action"]) + self.action_space.to_python_code(ans_dict['action']) except Exception as e: raise ParseError( - f"Error while parsing action\n: {e}\n" - "Make sure your answer is restricted to the allowed actions." + f'Error while parsing action\n: {e}\n' + 'Make sure your answer is restricted to the allowed actions.' ) return ans_dict @@ -489,34 +489,34 @@ def _parse_answer(self, text_answer): def _get_action_space(flags: Flags) -> AbstractActionSet: match flags.action_space: - case "python": + case 'python': action_space = PythonActionSet(strict=flags.is_strict) if flags.multi_actions: warn( - f"Flag action_space={repr(flags.action_space)} incompatible with multi_actions={repr(flags.multi_actions)}.", + f'Flag action_space={repr(flags.action_space)} incompatible with multi_actions={repr(flags.multi_actions)}.', stacklevel=2, ) - if flags.demo_mode != "off": + if flags.demo_mode != 'off': warn( - f"Flag action_space={repr(flags.action_space)} incompatible with demo_mode={repr(flags.demo_mode)}.", + f'Flag action_space={repr(flags.action_space)} incompatible with demo_mode={repr(flags.demo_mode)}.', stacklevel=2, ) return action_space - case "bid": - action_subsets = ["chat", "bid"] - case "coord": - action_subsets = ["chat", "coord"] - case "bid+coord": - action_subsets = ["chat", "bid", "coord"] - case "bid+nav": - action_subsets = ["chat", "bid", "nav"] - case "coord+nav": - action_subsets = ["chat", "coord", "nav"] - case "bid+coord+nav": - action_subsets = ["chat", "bid", "coord", "nav"] + case 'bid': + action_subsets = ['chat', 'bid'] + case 'coord': + action_subsets = ['chat', 'coord'] + case 'bid+coord': + action_subsets = ['chat', 'bid', 'coord'] + case 'bid+nav': + action_subsets = ['chat', 'bid', 'nav'] + case 'coord+nav': + action_subsets = ['chat', 'coord', 'nav'] + case 'bid+coord+nav': + action_subsets = ['chat', 'bid', 'coord', 'nav'] case _: raise NotImplementedError( - f"Unknown action_space {repr(flags.action_space)}" + f'Unknown action_space {repr(flags.action_space)}' ) action_space = HighLevelActionSet( @@ -530,7 +530,7 @@ def _get_action_space(flags: Flags) -> AbstractActionSet: class Memory(PromptElement): - _prompt = "" # provided in the abstract and concrete examples + _prompt = '' # provided in the abstract and concrete examples _abstract_ex = """ @@ -548,12 +548,12 @@ class Memory(PromptElement): def _parse_answer(self, text_answer): return parse_html_tags_raise( - text_answer, optional_keys=["memory"], merge_multiple=True + text_answer, optional_keys=['memory'], merge_multiple=True ) class Think(PromptElement): - _prompt = "" + _prompt = '' _abstract_ex = """ @@ -571,7 +571,7 @@ class Think(PromptElement): def _parse_answer(self, text_answer): return parse_html_tags_raise( - text_answer, optional_keys=["think"], merge_multiple=True + text_answer, optional_keys=['think'], merge_multiple=True ) @@ -581,10 +581,10 @@ def diff(previous, new): If the difference is above diff_threshold, return the diff string. """ if previous == new: - return "Identical", [] + return 'Identical', [] if len(previous) == 0 or previous is None: - return "previous is empty", [] + return 'previous is empty', [] diff_gen = difflib.ndiff(previous.splitlines(), new.splitlines()) @@ -592,23 +592,23 @@ def diff(previous, new): plus_count = 0 minus_count = 0 for line in diff_gen: - if line.strip().startswith("+"): + if line.strip().startswith('+'): diff_lines.append(line) plus_count += 1 - elif line.strip().startswith("-"): + elif line.strip().startswith('-'): diff_lines.append(line) minus_count += 1 else: continue - header = f"{plus_count} lines added and {minus_count} lines removed:" + header = f'{plus_count} lines added and {minus_count} lines removed:' return header, diff_lines class Diff(Shrinkable): def __init__( - self, previous, new, prefix="", max_line_diff=20, shrink_speed=2, visible=True + self, previous, new, prefix='', max_line_diff=20, shrink_speed=2, visible=True ) -> None: super().__init__(visible=visible) self.max_line_diff = max_line_diff @@ -622,11 +622,11 @@ def shrink(self): @property def _prompt(self) -> str: # type: ignore - diff_str = "\n".join(self.diff_lines[: self.max_line_diff]) + diff_str = '\n'.join(self.diff_lines[: self.max_line_diff]) if len(self.diff_lines) > self.max_line_diff: original_count = len(self.diff_lines) - diff_str = f"{diff_str}\nDiff truncated, {original_count - self.max_line_diff} changes now shown." - return f"{self.prefix}{self.header}\n{diff_str}\n" + diff_str = f'{diff_str}\nDiff truncated, {original_count - self.max_line_diff} changes now shown.' + return f'{self.prefix}{self.header}\n{diff_str}\n' class HistoryStep(Shrinkable): @@ -637,25 +637,25 @@ def __init__( self.html_diff = Diff( previous_obs[flags.html_type], current_obs[flags.html_type], - prefix="\n### HTML diff:\n", + prefix='\n### HTML diff:\n', shrink_speed=shrink_speed, visible=lambda: flags.use_html and flags.use_diff, ) self.ax_tree_diff = Diff( - previous_obs["axtree_txt"], - current_obs["axtree_txt"], - prefix="\n### Accessibility tree diff:\n", + previous_obs['axtree_txt'], + current_obs['axtree_txt'], + prefix='\n### Accessibility tree diff:\n', shrink_speed=shrink_speed, visible=lambda: flags.use_ax_tree and flags.use_diff, ) self.error = Error( - current_obs["last_action_error"], + current_obs['last_action_error'], visible=( flags.use_error_logs - and current_obs["last_action_error"] + and current_obs['last_action_error'] and flags.use_past_error_logs ), - prefix="### ", + prefix='### ', ) self.shrink_speed = shrink_speed self.action = action @@ -669,17 +669,17 @@ def shrink(self): @property def _prompt(self) -> str: # type: ignore - prompt = "" + prompt = '' if self.flags.use_action_history: - prompt += f"\n### Action:\n{self.action}\n" + prompt += f'\n### Action:\n{self.action}\n' prompt += ( - f"{self.error.prompt}{self.html_diff.prompt}{self.ax_tree_diff.prompt}" + f'{self.error.prompt}{self.html_diff.prompt}{self.ax_tree_diff.prompt}' ) if self.flags.use_memory and self.memory is not None: - prompt += f"\n### Memory:\n{self.memory}\n" + prompt += f'\n### Memory:\n{self.memory}\n' return prompt @@ -715,14 +715,14 @@ def shrink(self): @property def _prompt(self): - prompts = ["# History of interaction with the task:\n"] + prompts = ['# History of interaction with the task:\n'] for i, step in enumerate(self.history_steps): - prompts.append(f"## step {i}") + prompts.append(f'## step {i}') prompts.append(step.prompt) - return "\n".join(prompts) + "\n" + return '\n'.join(prompts) + '\n' -if __name__ == "__main__": +if __name__ == '__main__': html_template = """ @@ -736,27 +736,27 @@ def _prompt(self): OBS_HISTORY = [ { - "goal": "do this and that", - "pruned_html": html_template.format(1), - "axtree_txt": "[1] Click me", - "last_action_error": "", + 'goal': 'do this and that', + 'pruned_html': html_template.format(1), + 'axtree_txt': '[1] Click me', + 'last_action_error': '', }, { - "goal": "do this and that", - "pruned_html": html_template.format(2), - "axtree_txt": "[1] Click me", - "last_action_error": "", + 'goal': 'do this and that', + 'pruned_html': html_template.format(2), + 'axtree_txt': '[1] Click me', + 'last_action_error': '', }, { - "goal": "do this and that", - "pruned_html": html_template.format(3), - "axtree_txt": "[1] Click me", - "last_action_error": "Hey, there is an error now", + 'goal': 'do this and that', + 'pruned_html': html_template.format(3), + 'axtree_txt': '[1] Click me', + 'last_action_error': 'Hey, there is an error now', }, ] ACTIONS = ["click('41')", "click('42')"] - MEMORIES = ["memory A", "memory B"] - THOUGHTS = ["thought A", "thought B"] + MEMORIES = ['memory A', 'memory B'] + THOUGHTS = ['thought A', 'thought B'] flags = Flags( use_html=True, @@ -768,7 +768,7 @@ def _prompt(self): use_action_history=True, use_memory=True, use_diff=True, - html_type="pruned_html", + html_type='pruned_html', use_concrete_example=True, use_abstract_example=True, use_screenshot=False, diff --git a/openhands/agenthub/browsing_agent/response_parser.py b/openhands/agenthub/browsing_agent/response_parser.py index a04378fa31b0..8687016c6ad7 100644 --- a/openhands/agenthub/browsing_agent/response_parser.py +++ b/openhands/agenthub/browsing_agent/response_parser.py @@ -21,17 +21,17 @@ def parse(self, response: str) -> Action: return self.parse_action(action_str) def parse_response(self, response) -> str: - action_str = response["choices"][0]["message"]["content"] + action_str = response['choices'][0]['message']['content'] if action_str is None: - return "" + return '' action_str = action_str.strip() # Ensure action_str ends with ')```' if action_str: - if not action_str.endswith("```"): - if action_str.endswith(")"): - action_str += "```" # prevent duplicate ending paranthesis, e.g. send_msg_to_user('Done')) + if not action_str.endswith('```'): + if action_str.endswith(')'): + action_str += '```' # prevent duplicate ending paranthesis, e.g. send_msg_to_user('Done')) else: - action_str += ")```" # expected format + action_str += ')```' # expected format logger.debug(action_str) return action_str @@ -53,7 +53,7 @@ def __init__( pass def check_condition(self, action_str: str) -> bool: - return "```" not in action_str + return '```' not in action_str def parse(self, action_str: str) -> Action: msg = f'send_msg_to_user("""{action_str}""")' @@ -92,29 +92,29 @@ def parse(self, action_str: str) -> Action: # when the LLM returns only one string, it looks like this: ### goto('https://www.whitehouse.gov/about-the-white-house/presidents/') # and parse_response added )``` to the end of the string - parts = action_str.split("```") + parts = action_str.split('```') browser_actions = ( - parts[1].strip() if parts[1].strip() != "" else parts[0].strip() + parts[1].strip() if parts[1].strip() != '' else parts[0].strip() ) - thought = parts[0].strip() if parts[1].strip() != "" else "" + thought = parts[0].strip() if parts[1].strip() != '' else '' # if the LLM wants to talk to the user, we extract the message - msg_content = "" - for sub_action in browser_actions.split("\n"): - if "send_msg_to_user(" in sub_action: + msg_content = '' + for sub_action in browser_actions.split('\n'): + if 'send_msg_to_user(' in sub_action: try: tree = ast.parse(sub_action) args = tree.body[0].value.args # type: ignore msg_content = args[0].value except SyntaxError: - logger.error(f"Error parsing action: {sub_action}") + logger.error(f'Error parsing action: {sub_action}') # the syntax was not correct, but we can still try to get the message # e.g. send_msg_to_user("Hello, world!") or send_msg_to_user('Hello, world!' match = re.search(r'send_msg_to_user\((["\'])(.*?)\1\)', sub_action) if match: msg_content = match.group(2) else: - msg_content = "" + msg_content = '' return BrowseInteractiveAction( browser_actions=browser_actions, diff --git a/openhands/agenthub/browsing_agent/utils.py b/openhands/agenthub/browsing_agent/utils.py index d57deb37255f..8e67679966ae 100644 --- a/openhands/agenthub/browsing_agent/utils.py +++ b/openhands/agenthub/browsing_agent/utils.py @@ -8,12 +8,12 @@ def yaml_parser(message): """Parse a yaml message for the retry function.""" # saves gpt-3.5 from some yaml parsing errors - message = re.sub(r":\s*\n(?=\S|\n)", ": ", message) + message = re.sub(r':\s*\n(?=\S|\n)', ': ', message) try: value = yaml.safe_load(message) valid = True - retry_message = "" + retry_message = '' except yaml.YAMLError as e: warn(str(e), stacklevel=2) value = {} @@ -22,7 +22,7 @@ def yaml_parser(message): return value, valid, retry_message -def _compress_chunks(text, identifier, skip_list, split_regex="\n\n+"): +def _compress_chunks(text, identifier, skip_list, split_regex='\n\n+'): """Compress a string by replacing redundant chunks by identifiers. Chunks are defined by the split_regex.""" text_list = re.split(split_regex, text) text_list = [chunk.strip() for chunk in text_list] @@ -33,11 +33,11 @@ def _compress_chunks(text, identifier, skip_list, split_regex="\n\n+"): # Store items that occur more than once in a dictionary for item, count in counter.items(): if count > 1 and item not in skip_list and len(item) > 10: - def_dict[f"{identifier}-{id}"] = item + def_dict[f'{identifier}-{id}'] = item id += 1 # Replace redundant items with their identifiers in the text - compressed_text = "\n".join(text_list) + compressed_text = '\n'.join(text_list) for key, value in def_dict.items(): compressed_text = compressed_text.replace(value, key) @@ -48,23 +48,23 @@ def compress_string(text): """Compress a string by replacing redundant paragraphs and lines with identifiers.""" # Perform paragraph-level compression def_dict, compressed_text = _compress_chunks( - text, identifier="§", skip_list=[], split_regex="\n\n+" + text, identifier='§', skip_list=[], split_regex='\n\n+' ) # Perform line-level compression, skipping any paragraph identifiers line_dict, compressed_text = _compress_chunks( - compressed_text, "¶", list(def_dict.keys()), split_regex="\n+" + compressed_text, '¶', list(def_dict.keys()), split_regex='\n+' ) def_dict.update(line_dict) # Create a definitions section - def_lines = [""] + def_lines = [''] for key, value in def_dict.items(): - def_lines.append(f"{key}:\n{value}") - def_lines.append("") - definitions = "\n".join(def_lines) + def_lines.append(f'{key}:\n{value}') + def_lines.append('') + definitions = '\n'.join(def_lines) - return definitions + "\n" + compressed_text + return definitions + '\n' + compressed_text def extract_html_tags(text, keys): @@ -91,7 +91,7 @@ def extract_html_tags(text, keys): # text = text.lower() # keys = set([k.lower() for k in keys]) for key in keys: - pattern = f"<{key}>(.*?)" + pattern = f'<{key}>(.*?)' matches = re.findall(pattern, text, re.DOTALL) if matches: content_dict[key] = [match.strip() for match in matches] @@ -140,19 +140,19 @@ def parse_html_tags(text, keys=(), optional_keys=(), merge_multiple=False): for key in all_keys: if key not in content_dict: if key not in optional_keys: - retry_messages.append(f"Missing the key <{key}> in the answer.") + retry_messages.append(f'Missing the key <{key}> in the answer.') else: val = content_dict[key] content_dict[key] = val[0] if len(val) > 1: if not merge_multiple: retry_messages.append( - f"Found multiple instances of the key {key}. You should have only one of them." + f'Found multiple instances of the key {key}. You should have only one of them.' ) else: # merge the multiple instances - content_dict[key] = "\n".join(val) + content_dict[key] = '\n'.join(val) valid = len(retry_messages) == 0 - retry_message = "\n".join(retry_messages) + retry_message = '\n'.join(retry_messages) return content_dict, valid, retry_message diff --git a/openhands/agenthub/codeact_agent/__init__.py b/openhands/agenthub/codeact_agent/__init__.py index 9edd9eb08ef6..63f1fdb820b4 100644 --- a/openhands/agenthub/codeact_agent/__init__.py +++ b/openhands/agenthub/codeact_agent/__init__.py @@ -1,4 +1,4 @@ from openhands.agenthub.codeact_agent.codeact_agent import CodeActAgent from openhands.controller.agent import Agent -Agent.register("CodeActAgent", CodeActAgent) +Agent.register('CodeActAgent', CodeActAgent) diff --git a/openhands/agenthub/codeact_agent/action_parser.py b/openhands/agenthub/codeact_agent/action_parser.py index 3e76fed5e898..75fab1156f8c 100644 --- a/openhands/agenthub/codeact_agent/action_parser.py +++ b/openhands/agenthub/codeact_agent/action_parser.py @@ -46,21 +46,21 @@ def parse(self, response) -> Action: def parse_response(self, response) -> str: action = response.choices[0].message.content if action is None: - return "" - for lang in ["bash", "ipython", "browse"]: + return '' + for lang in ['bash', 'ipython', 'browse']: # special handling for DeepSeek: it has stop-word bug and returns - if f"" not in action: - action = action.replace(f"") + if f'' not in action: + action = action.replace(f'') - if f"" in action and f"" not in action: - action += f"" + if f'' in action and f'' not in action: + action += f'' # special handling for DeepSeek: it has stop-word bug and returns - if "" not in action: - action = action.replace("") + if '' not in action: + action = action.replace('') - if "" not in action: - action += "" + if '' not in action: + action += '' return action def parse_action(self, action_str: str) -> Action: @@ -72,19 +72,19 @@ def parse_action(self, action_str: str) -> Action: def action_to_str(self, action: Action) -> str: if isinstance(action, CmdRunAction): return ( - f"{action.thought}\n\n{action.command}\n" + f'{action.thought}\n\n{action.command}\n' ) elif isinstance(action, IPythonRunCellAction): - return f"{action.thought}\n\n{action.code}\n" + return f'{action.thought}\n\n{action.code}\n' elif isinstance(action, AgentDelegateAction): return f'{action.thought}\n\n{action.inputs["task"]}\n' elif isinstance(action, FileEditAction): - return f"{action.thought}\n\n{action.content}\n" + return f'{action.thought}\n\n{action.content}\n' elif isinstance(action, MessageAction): return action.content - elif isinstance(action, AgentFinishAction) and action.source == "agent": + elif isinstance(action, AgentFinishAction) and action.source == 'agent': return action.thought - return "" + return '' class CodeActActionParserFinish(ActionParser): @@ -98,14 +98,14 @@ def __init__( self.finish_command = None def check_condition(self, action_str: str) -> bool: - self.finish_command = re.search(r".*", action_str, re.DOTALL) + self.finish_command = re.search(r'.*', action_str, re.DOTALL) return self.finish_command is not None def parse(self, action_str: str) -> Action: assert ( self.finish_command is not None - ), "self.finish_command should not be None when parse is called" - thought = action_str.replace(self.finish_command.group(0), "").strip() + ), 'self.finish_command should not be None when parse is called' + thought = action_str.replace(self.finish_command.group(0), '').strip() return AgentFinishAction(thought=thought) @@ -122,18 +122,18 @@ def __init__( def check_condition(self, action_str: str) -> bool: self.bash_command = re.search( - r"(.*?)", action_str, re.DOTALL + r'(.*?)', action_str, re.DOTALL ) return self.bash_command is not None def parse(self, action_str: str) -> Action: assert ( self.bash_command is not None - ), "self.bash_command should not be None when parse is called" - thought = action_str.replace(self.bash_command.group(0), "").strip() + ), 'self.bash_command should not be None when parse is called' + thought = action_str.replace(self.bash_command.group(0), '').strip() # a command was found command_group = self.bash_command.group(1).strip() - if command_group.strip() == "exit": + if command_group.strip() == 'exit': return AgentFinishAction(thought=thought) return CmdRunAction(command=command_group, thought=thought) @@ -147,20 +147,20 @@ def __init__( self, ): self.python_code = None - self.jupyter_kernel_init_code: str = "from agentskills import *" + self.jupyter_kernel_init_code: str = 'from agentskills import *' def check_condition(self, action_str: str) -> bool: self.python_code = re.search( - r"(.*?)", action_str, re.DOTALL + r'(.*?)', action_str, re.DOTALL ) return self.python_code is not None def parse(self, action_str: str) -> Action: assert ( self.python_code is not None - ), "self.python_code should not be None when parse is called" + ), 'self.python_code should not be None when parse is called' code_group = self.python_code.group(1).strip() - thought = action_str.replace(self.python_code.group(0), "").strip() + thought = action_str.replace(self.python_code.group(0), '').strip() return IPythonRunCellAction( code=code_group, thought=thought, @@ -180,24 +180,24 @@ def __init__( def check_condition(self, action_str: str) -> bool: self.agent_delegate = re.search( - r"(.*)", action_str, re.DOTALL + r'(.*)', action_str, re.DOTALL ) return self.agent_delegate is not None def parse(self, action_str: str) -> Action: assert ( self.agent_delegate is not None - ), "self.agent_delegate should not be None when parse is called" - thought = action_str.replace(self.agent_delegate.group(0), "").strip() + ), 'self.agent_delegate should not be None when parse is called' + thought = action_str.replace(self.agent_delegate.group(0), '').strip() browse_actions = self.agent_delegate.group(1).strip() thought = ( - f"{thought}\nI should start with: {browse_actions}" + f'{thought}\nI should start with: {browse_actions}' if thought - else f"I should start with: {browse_actions}" + else f'I should start with: {browse_actions}' ) return AgentDelegateAction( - agent="BrowsingAgent", thought=thought, inputs={"task": browse_actions} + agent='BrowsingAgent', thought=thought, inputs={'task': browse_actions} ) @@ -229,7 +229,7 @@ def __init__(self): self.file_edit_match: re.Match | None = None def check_condition(self, action_str: str) -> bool: - if " bool: f'FileEditAction detected but the format is incorrect. Unable to match for in:\n{"-" * 80}\n{action_str}\n{"-" * 80}' ) raise LLMMalformedActionError( - "FileEditAction detected but the format is incorrect. Usage:\n" + 'FileEditAction detected but the format is incorrect. Usage:\n' '\n' - "[content_to_edit]\n" - "\n" + '[content_to_edit]\n' + '\n' ) path = self.file_edit_match.group(2) @@ -256,7 +256,7 @@ def check_condition(self, action_str: str) -> bool: if not path: raise LLMMalformedActionError( - "FileEditAction detected but no `path` specified. You should specify the path of the file to edit." + 'FileEditAction detected but no `path` specified. You should specify the path of the file to edit.' ) if start: @@ -264,7 +264,7 @@ def check_condition(self, action_str: str) -> bool: int(start) except ValueError: raise LLMMalformedActionError( - f"FileEditAction detected but `start` is not a valid integer: {start}" + f'FileEditAction detected but `start` is not a valid integer: {start}' ) if end: @@ -272,7 +272,7 @@ def check_condition(self, action_str: str) -> bool: int(end) except ValueError: raise LLMMalformedActionError( - f"FileEditAction detected but `end` is not a valid integer: {end}" + f'FileEditAction detected but `end` is not a valid integer: {end}' ) return True @@ -280,7 +280,7 @@ def check_condition(self, action_str: str) -> bool: def parse(self, action_str: str) -> Action: assert ( self.file_edit_match is not None - ), "self.file_edit_match should not be None when parse is called" + ), 'self.file_edit_match should not be None when parse is called' file_path = self.file_edit_match.group(2).strip() start_line = ( @@ -294,7 +294,7 @@ def parse(self, action_str: str) -> Action: else None ) content = self.file_edit_match.group(7) - thought = action_str.replace(self.file_edit_match.group(0), "").strip() + thought = action_str.replace(self.file_edit_match.group(0), '').strip() action = FileEditAction(path=file_path, content=content, thought=thought) if start_line is not None: diff --git a/openhands/agenthub/codeact_agent/codeact_agent.py b/openhands/agenthub/codeact_agent/codeact_agent.py index c7f6b8525539..629c6edfb18b 100644 --- a/openhands/agenthub/codeact_agent/codeact_agent.py +++ b/openhands/agenthub/codeact_agent/codeact_agent.py @@ -43,7 +43,7 @@ class CodeActAgent(Agent): - VERSION = "2.2" + VERSION = '2.2' """ The Code Act Agent is a minimalist agent. The agent works by passing the model a list of action-observation pairs and prompting the model to take the next step. @@ -70,7 +70,7 @@ class CodeActAgent(Agent): AgentSkillsRequirement(), JupyterRequirement(), ] - obs_prefix = "OBSERVATION:\n" + obs_prefix = 'OBSERVATION:\n' def __init__( self, @@ -88,8 +88,8 @@ def __init__( self.function_calling_active = self.config.function_calling if self.function_calling_active and not self.llm.is_function_calling_active(): logger.warning( - f"Function calling not supported for model {self.llm.config.model}. " - "Disabling function calling." + f'Function calling not supported for model {self.llm.config.model}. ' + 'Disabling function calling.' ) self.function_calling_active = False @@ -100,24 +100,18 @@ def __init__( codeact_enable_llm_editor=self.config.codeact_enable_llm_editor, ) logger.debug( - f"TOOLS loaded for CodeActAgent: {json.dumps(self.tools, indent=2)}" + f'TOOLS loaded for CodeActAgent: {json.dumps(self.tools, indent=2)}' ) self.prompt_manager = PromptManager( - microagent_dir=os.path.join(os.path.dirname(__file__), "micro") - if self.config.use_microagents - else None, - prompt_dir=os.path.join(os.path.dirname(__file__), "prompts", "tools"), + microagent_dir=os.path.join(os.path.dirname(__file__), 'micro') if self.config.use_microagents else None, + prompt_dir=os.path.join(os.path.dirname(__file__), 'prompts', 'tools'), disabled_microagents=self.config.disabled_microagents, ) else: self.action_parser = CodeActResponseParser() self.prompt_manager = PromptManager( - microagent_dir=os.path.join(os.path.dirname(__file__), "micro") - if self.config.use_microagents - else None, - prompt_dir=os.path.join( - os.path.dirname(__file__), "prompts", "default" - ), + microagent_dir=os.path.join(os.path.dirname(__file__), 'micro') if self.config.use_microagents else None, + prompt_dir=os.path.join(os.path.dirname(__file__), 'prompts', 'default'), agent_skills_docs=AgentSkillsRequirement.documentation, disabled_microagents=self.config.disabled_microagents, ) @@ -168,11 +162,11 @@ def get_action_message( FileEditAction, BrowseInteractiveAction, ), - ) or (isinstance(action, AgentFinishAction) and action.source == "agent"): + ) or (isinstance(action, AgentFinishAction) and action.source == 'agent'): if self.function_calling_active: tool_metadata = action.tool_call_metadata assert tool_metadata is not None, ( - "Tool call metadata should NOT be None when function calling is enabled. Action: " + 'Tool call metadata should NOT be None when function calling is enabled. Action: ' + str(action) ) @@ -183,7 +177,7 @@ def get_action_message( pending_tool_call_action_messages[llm_response.id] = Message( role=assistant_msg.role, # tool call content SHOULD BE a string - content=[TextContent(text=assistant_msg.content or "")] + content=[TextContent(text=assistant_msg.content or '')] if assistant_msg.content is not None else [], tool_calls=assistant_msg.tool_calls, @@ -191,19 +185,19 @@ def get_action_message( return [] else: assert not isinstance(action, BrowseInteractiveAction), ( - "BrowseInteractiveAction is not supported in non-function calling mode. Action: " + 'BrowseInteractiveAction is not supported in non-function calling mode. Action: ' + str(action) ) content = [TextContent(text=self.action_parser.action_to_str(action))] return [ Message( - role="user" if action.source == "user" else "assistant", + role='user' if action.source == 'user' else 'assistant', content=content, ) ] elif isinstance(action, MessageAction): - role = "user" if action.source == "user" else "assistant" - content = [TextContent(text=action.content or "")] + role = 'user' if action.source == 'user' else 'assistant' + content = [TextContent(text=action.content or '')] if self.llm.vision_is_active() and action.image_urls: content.append(ImageContent(image_urls=action.image_urls)) return [ @@ -246,58 +240,58 @@ def get_observation_message( """ message: Message max_message_chars = self.llm.config.max_message_chars - obs_prefix = "OBSERVATION:\n" + obs_prefix = 'OBSERVATION:\n' if isinstance(obs, CmdOutputObservation): text = obs_prefix + truncate_content( obs.content + obs.interpreter_details, max_message_chars ) - text += f"\n[Command finished with exit code {obs.exit_code}]" - message = Message(role="user", content=[TextContent(text=text)]) + text += f'\n[Command finished with exit code {obs.exit_code}]' + message = Message(role='user', content=[TextContent(text=text)]) elif isinstance(obs, IPythonRunCellObservation): text = obs_prefix + obs.content # replace base64 images with a placeholder - splitted = text.split("\n") + splitted = text.split('\n') for i, line in enumerate(splitted): - if "![image](data:image/png;base64," in line: + if '![image](data:image/png;base64,' in line: splitted[i] = ( - "![image](data:image/png;base64, ...) already displayed to user" + '![image](data:image/png;base64, ...) already displayed to user' ) - text = "\n".join(splitted) + text = '\n'.join(splitted) text = truncate_content(text, max_message_chars) - message = Message(role="user", content=[TextContent(text=text)]) + message = Message(role='user', content=[TextContent(text=text)]) elif isinstance(obs, FileEditObservation): text = obs_prefix + truncate_content(str(obs), max_message_chars) - message = Message(role="user", content=[TextContent(text=text)]) + message = Message(role='user', content=[TextContent(text=text)]) elif isinstance(obs, BrowserOutputObservation): text = obs.get_agent_obs_text() message = Message( - role="user", + role='user', content=[TextContent(text=obs_prefix + text)], ) elif isinstance(obs, AgentDelegateObservation): text = obs_prefix + truncate_content( - obs.outputs["content"] if "content" in obs.outputs else "", + obs.outputs['content'] if 'content' in obs.outputs else '', max_message_chars, ) - message = Message(role="user", content=[TextContent(text=text)]) + message = Message(role='user', content=[TextContent(text=text)]) elif isinstance(obs, ErrorObservation): text = obs_prefix + truncate_content(obs.content, max_message_chars) - text += "\n[Error occurred in processing last action]" - message = Message(role="user", content=[TextContent(text=text)]) + text += '\n[Error occurred in processing last action]' + message = Message(role='user', content=[TextContent(text=text)]) elif isinstance(obs, UserRejectObservation): - text = "OBSERVATION:\n" + truncate_content(obs.content, max_message_chars) - text += "\n[Last action has been rejected by the user]" - message = Message(role="user", content=[TextContent(text=text)]) + text = 'OBSERVATION:\n' + truncate_content(obs.content, max_message_chars) + text += '\n[Last action has been rejected by the user]' + message = Message(role='user', content=[TextContent(text=text)]) else: # If an observation message is not returned, it will cause an error # when the LLM tries to return the next message - raise ValueError(f"Unknown observation type: {type(obs)}") + raise ValueError(f'Unknown observation type: {type(obs)}') if self.function_calling_active: # Update the message as tool response properly if (tool_call_metadata := obs.tool_call_metadata) is not None: tool_call_id_to_message[tool_call_metadata.tool_call_id] = Message( - role="tool", + role='tool', content=message.content, tool_call_id=tool_call_metadata.tool_call_id, name=tool_call_metadata.function_name, @@ -333,23 +327,23 @@ def step(self, state: State) -> Action: # if we're done, go back latest_user_message = state.get_last_user_message() - if latest_user_message and latest_user_message.content.strip() == "/exit": + if latest_user_message and latest_user_message.content.strip() == '/exit': return AgentFinishAction() # prepare what we want to send to the LLM messages = self._get_messages(state) params: dict = { - "messages": self.llm.format_messages_for_llm(messages), + 'messages': self.llm.format_messages_for_llm(messages), } if self.function_calling_active: - params["tools"] = self.tools - params["parallel_tool_calls"] = False + params['tools'] = self.tools + params['parallel_tool_calls'] = False else: - params["stop"] = [ - "", - "", - "", - "", + params['stop'] = [ + '', + '', + '', + '', ] response = self.llm.completion(**params) @@ -395,7 +389,7 @@ def _get_messages(self, state: State) -> list[Message]: """ messages: list[Message] = [ Message( - role="system", + role='system', content=[ TextContent( text=self.prompt_manager.get_system_message(), @@ -408,7 +402,7 @@ def _get_messages(self, state: State) -> list[Message]: if example_message: messages.append( Message( - role="user", + role='user', content=[TextContent(text=example_message)], cache_prompt=self.llm.is_caching_prompt_active(), ) @@ -430,7 +424,7 @@ def _get_messages(self, state: State) -> list[Message]: tool_call_id_to_message=tool_call_id_to_message, ) else: - raise ValueError(f"Unknown event type: {type(event)}") + raise ValueError(f'Unknown event type: {type(event)}') # Check pending tool call action messages and see if they are complete _response_ids_to_remove = [] @@ -439,8 +433,8 @@ def _get_messages(self, state: State) -> list[Message]: pending_message, ) in pending_tool_call_action_messages.items(): assert pending_message.tool_calls is not None, ( - "Tool calls should NOT be None when function calling is enabled & the message is considered pending tool call. " - f"Pending message: {pending_message}" + 'Tool calls should NOT be None when function calling is enabled & the message is considered pending tool call. ' + f'Pending message: {pending_message}' ) if all( tool_call.id in tool_call_id_to_message @@ -460,7 +454,7 @@ def _get_messages(self, state: State) -> list[Message]: for message in messages_to_add: if message: - if message.role == "user": + if message.role == 'user': self.prompt_manager.enhance_message(message) # handle error if the message is the SAME role as the previous message # litellm.exceptions.BadRequestError: litellm.BadRequestError: OpenAIException - Error code: 400 - {'detail': 'Only supports u/a/u/a/u...'} @@ -469,7 +463,7 @@ def _get_messages(self, state: State) -> list[Message]: if ( messages and messages[-1].role == message.role - and message.role != "tool" + and message.role != 'tool' ): messages[-1].content.extend(message.content) else: @@ -481,7 +475,7 @@ def _get_messages(self, state: State) -> list[Message]: # https://github.com/anthropics/anthropic-quickstarts/blob/8f734fd08c425c6ec91ddd613af04ff87d70c5a0/computer-use-demo/computer_use_demo/loop.py#L241-L262 breakpoints_remaining = 3 # remaining 1 for system/tool for message in reversed(messages): - if message.role == "user" or message.role == "tool": + if message.role == 'user' or message.role == 'tool': if breakpoints_remaining > 0: message.content[ -1 diff --git a/openhands/agenthub/codeact_agent/function_calling.py b/openhands/agenthub/codeact_agent/function_calling.py index e230dbb0150f..177e7b7ff171 100644 --- a/openhands/agenthub/codeact_agent/function_calling.py +++ b/openhands/agenthub/codeact_agent/function_calling.py @@ -32,19 +32,19 @@ """ CmdRunTool = ChatCompletionToolParam( - type="function", + type='function', function=ChatCompletionToolParamFunctionChunk( - name="execute_bash", + name='execute_bash', description=_BASH_DESCRIPTION, parameters={ - "type": "object", - "properties": { - "command": { - "type": "string", - "description": "The bash command to execute. Can be empty to view additional logs when previous exit code is `-1`. Can be `ctrl+c` to interrupt the currently running process.", + 'type': 'object', + 'properties': { + 'command': { + 'type': 'string', + 'description': 'The bash command to execute. Can be empty to view additional logs when previous exit code is `-1`. Can be `ctrl+c` to interrupt the currently running process.', }, }, - "required": ["command"], + 'required': ['command'], }, ), ) @@ -58,19 +58,19 @@ # {AgentSkillsRequirement.documentation}""" IPythonTool = ChatCompletionToolParam( - type="function", + type='function', function=ChatCompletionToolParamFunctionChunk( - name="execute_ipython_cell", + name='execute_ipython_cell', description=_IPYTHON_DESCRIPTION, parameters={ - "type": "object", - "properties": { - "code": { - "type": "string", - "description": "The Python code to execute. Supports magic commands like %pip.", + 'type': 'object', + 'properties': { + 'code': { + 'type': 'string', + 'description': 'The Python code to execute. Supports magic commands like %pip.', }, }, - "required": ["code"], + 'required': ['code'], }, ), ) @@ -182,31 +182,31 @@ def __init__(self): """ LLMBasedFileEditTool = ChatCompletionToolParam( - type="function", + type='function', function=ChatCompletionToolParamFunctionChunk( - name="edit_file", + name='edit_file', description=_FILE_EDIT_DESCRIPTION, parameters={ - "type": "object", - "properties": { - "path": { - "type": "string", - "description": "The absolute path to the file to be edited.", + 'type': 'object', + 'properties': { + 'path': { + 'type': 'string', + 'description': 'The absolute path to the file to be edited.', }, - "new_content_draft": { - "type": "string", - "description": "A draft of the new content for the file being edited. Note that the assistant may skip unchanged lines.", + 'new_content_draft': { + 'type': 'string', + 'description': 'A draft of the new content for the file being edited. Note that the assistant may skip unchanged lines.', }, - "start": { - "type": "integer", - "description": "The starting line number for the edit (1-indexed, inclusive). Default is 1.", + 'start': { + 'type': 'integer', + 'description': 'The starting line number for the edit (1-indexed, inclusive). Default is 1.', }, - "end": { - "type": "integer", - "description": "The ending line number for the edit (1-indexed, inclusive). Default is -1 (end of file).", + 'end': { + 'type': 'integer', + 'description': 'The ending line number for the edit (1-indexed, inclusive). Default is -1 (end of file).', }, }, - "required": ["path", "content"], + 'required': ['path', 'content'], }, ), ) @@ -225,52 +225,52 @@ def __init__(self): """ StrReplaceEditorTool = ChatCompletionToolParam( - type="function", + type='function', function=ChatCompletionToolParamFunctionChunk( - name="str_replace_editor", + name='str_replace_editor', description=_STR_REPLACE_EDITOR_DESCRIPTION, parameters={ - "type": "object", - "properties": { - "command": { - "description": "The commands to run. Allowed options are: `view`, `create`, `str_replace`, `insert`, `undo_edit`.", - "enum": ["view", "create", "str_replace", "insert", "undo_edit"], - "type": "string", + 'type': 'object', + 'properties': { + 'command': { + 'description': 'The commands to run. Allowed options are: `view`, `create`, `str_replace`, `insert`, `undo_edit`.', + 'enum': ['view', 'create', 'str_replace', 'insert', 'undo_edit'], + 'type': 'string', }, - "path": { - "description": "Absolute path to file or directory, e.g. `/workspace/file.py` or `/workspace`.", - "type": "string", + 'path': { + 'description': 'Absolute path to file or directory, e.g. `/workspace/file.py` or `/workspace`.', + 'type': 'string', }, - "file_text": { - "description": "Required parameter of `create` command, with the content of the file to be created.", - "type": "string", + 'file_text': { + 'description': 'Required parameter of `create` command, with the content of the file to be created.', + 'type': 'string', }, - "old_str": { - "description": "Required parameter of `str_replace` command containing the string in `path` to replace.", - "type": "string", + 'old_str': { + 'description': 'Required parameter of `str_replace` command containing the string in `path` to replace.', + 'type': 'string', }, - "new_str": { - "description": "Optional parameter of `str_replace` command containing the new string (if not given, no string will be added). Required parameter of `insert` command containing the string to insert.", - "type": "string", + 'new_str': { + 'description': 'Optional parameter of `str_replace` command containing the new string (if not given, no string will be added). Required parameter of `insert` command containing the string to insert.', + 'type': 'string', }, - "insert_line": { - "description": "Required parameter of `insert` command. The `new_str` will be inserted AFTER the line `insert_line` of `path`.", - "type": "integer", + 'insert_line': { + 'description': 'Required parameter of `insert` command. The `new_str` will be inserted AFTER the line `insert_line` of `path`.', + 'type': 'integer', }, - "view_range": { - "description": "Optional parameter of `view` command when `path` points to a file. If none is given, the full file is shown. If provided, the file will be shown in the indicated line number range, e.g. [11, 12] will show lines 11 and 12. Indexing at 1 to start. Setting `[start_line, -1]` shows all lines from `start_line` to the end of the file.", - "items": {"type": "integer"}, - "type": "array", + 'view_range': { + 'description': 'Optional parameter of `view` command when `path` points to a file. If none is given, the full file is shown. If provided, the file will be shown in the indicated line number range, e.g. [11, 12] will show lines 11 and 12. Indexing at 1 to start. Setting `[start_line, -1]` shows all lines from `start_line` to the end of the file.', + 'items': {'type': 'integer'}, + 'type': 'array', }, }, - "required": ["command", "path"], + 'required': ['command', 'path'], }, ), ) # from browsergym/core/action/highlevel.py _browser_action_space = HighLevelActionSet( - subsets=["bid", "nav"], + subsets=['bid', 'nav'], strict=False, # less strict on the parsing of the actions multiaction=True, # enable to agent to take multiple actions at once ) @@ -395,28 +395,28 @@ def __init__(self): for _, action in _browser_action_space.action_set.items(): assert ( action.signature in _BROWSER_TOOL_DESCRIPTION - ), f"Browser description mismatch. Please double check if the BrowserGym updated their action space.\n\nAction: {action.signature}" + ), f'Browser description mismatch. Please double check if the BrowserGym updated their action space.\n\nAction: {action.signature}' assert ( action.description in _BROWSER_TOOL_DESCRIPTION - ), f"Browser description mismatch. Please double check if the BrowserGym updated their action space.\n\nAction: {action.description}" + ), f'Browser description mismatch. Please double check if the BrowserGym updated their action space.\n\nAction: {action.description}' BrowserTool = ChatCompletionToolParam( - type="function", + type='function', function=ChatCompletionToolParamFunctionChunk( - name="browser", + name='browser', description=_BROWSER_DESCRIPTION, parameters={ - "type": "object", - "properties": { - "code": { - "type": "string", - "description": ( - "The Python code that interacts with the browser.\n" + 'type': 'object', + 'properties': { + 'code': { + 'type': 'string', + 'description': ( + 'The Python code that interacts with the browser.\n' + _BROWSER_TOOL_DESCRIPTION ), } }, - "required": ["code"], + 'required': ['code'], }, ), ) @@ -424,16 +424,16 @@ def __init__(self): _FINISH_DESCRIPTION = """Finish the interaction when the task is complete OR if the assistant cannot proceed further with the task.""" FinishTool = ChatCompletionToolParam( - type="function", + type='function', function=ChatCompletionToolParamFunctionChunk( - name="finish", + name='finish', description=_FINISH_DESCRIPTION, ), ) def combine_thought(action: Action, thought: str) -> Action: - if not hasattr(action, "thought"): + if not hasattr(action, 'thought'): return action if thought: action.thought = thought @@ -442,17 +442,17 @@ def combine_thought(action: Action, thought: str) -> Action: def response_to_actions(response: ModelResponse) -> list[Action]: actions: list[Action] = [] - assert len(response.choices) == 1, "Only one choice is supported for now" + assert len(response.choices) == 1, 'Only one choice is supported for now' assistant_msg = response.choices[0].message if assistant_msg.tool_calls: # Check if there's assistant_msg.content. If so, add it to the thought - thought = "" + thought = '' if isinstance(assistant_msg.content, str): thought = assistant_msg.content elif isinstance(assistant_msg.content, list): for msg in assistant_msg.content: - if msg["type"] == "text": - thought += msg["text"] + if msg['type'] == 'text': + thought += msg['text'] # Process each tool call to OpenHands action for i, tool_call in enumerate(assistant_msg.tool_calls): @@ -461,33 +461,33 @@ def response_to_actions(response: ModelResponse) -> list[Action]: arguments = json.loads(tool_call.function.arguments) except json.decoder.JSONDecodeError as e: raise RuntimeError( - f"Failed to parse tool call arguments: {tool_call.function.arguments}" + f'Failed to parse tool call arguments: {tool_call.function.arguments}' ) from e - if tool_call.function.name == "execute_bash": + if tool_call.function.name == 'execute_bash': action = CmdRunAction(**arguments) - elif tool_call.function.name == "execute_ipython_cell": + elif tool_call.function.name == 'execute_ipython_cell': action = IPythonRunCellAction(**arguments) - elif tool_call.function.name == "delegate_to_browsing_agent": + elif tool_call.function.name == 'delegate_to_browsing_agent': action = AgentDelegateAction( - agent="BrowsingAgent", + agent='BrowsingAgent', inputs=arguments, ) - elif tool_call.function.name == "finish": + elif tool_call.function.name == 'finish': action = AgentFinishAction() - elif tool_call.function.name == "edit_file": + elif tool_call.function.name == 'edit_file': action = FileEditAction(**arguments) - elif tool_call.function.name == "str_replace_editor": + elif tool_call.function.name == 'str_replace_editor': # We implement this in agent_skills, which can be used via Jupyter # convert tool_call.function.arguments to kwargs that can be passed to file_editor - code = f"print(file_editor(**{arguments}))" + code = f'print(file_editor(**{arguments}))' logger.debug( - f"TOOL CALL: str_replace_editor -> file_editor with code: {code}" + f'TOOL CALL: str_replace_editor -> file_editor with code: {code}' ) action = IPythonRunCellAction(code=code, include_extra=False) - elif tool_call.function.name == "browser": - action = BrowseInteractiveAction(browser_actions=arguments["code"]) + elif tool_call.function.name == 'browser': + action = BrowseInteractiveAction(browser_actions=arguments['code']) else: - raise RuntimeError(f"Unknown tool call: {tool_call.function.name}") + raise RuntimeError(f'Unknown tool call: {tool_call.function.name}') # We only add thought to the first action if i == 0: diff --git a/openhands/agenthub/codeact_swe_agent/__init__.py b/openhands/agenthub/codeact_swe_agent/__init__.py index d7e826febae6..ef5233786194 100644 --- a/openhands/agenthub/codeact_swe_agent/__init__.py +++ b/openhands/agenthub/codeact_swe_agent/__init__.py @@ -1,4 +1,4 @@ from openhands.agenthub.codeact_swe_agent.codeact_swe_agent import CodeActSWEAgent from openhands.controller.agent import Agent -Agent.register("CodeActSWEAgent", CodeActSWEAgent) +Agent.register('CodeActSWEAgent', CodeActSWEAgent) diff --git a/openhands/agenthub/codeact_swe_agent/action_parser.py b/openhands/agenthub/codeact_swe_agent/action_parser.py index ffa16463b7b8..c77c1404a6e6 100644 --- a/openhands/agenthub/codeact_swe_agent/action_parser.py +++ b/openhands/agenthub/codeact_swe_agent/action_parser.py @@ -21,14 +21,14 @@ def __init__( self.finish_command = None def check_condition(self, action_str: str) -> bool: - self.finish_command = re.search(r".*", action_str, re.DOTALL) + self.finish_command = re.search(r'.*', action_str, re.DOTALL) return self.finish_command is not None def parse(self, action_str: str) -> Action: assert ( self.finish_command is not None - ), "self.finish_command should not be None when parse is called" - thought = action_str.replace(self.finish_command.group(0), "").strip() + ), 'self.finish_command should not be None when parse is called' + thought = action_str.replace(self.finish_command.group(0), '').strip() return AgentFinishAction(thought=thought) @@ -45,18 +45,18 @@ def __init__( def check_condition(self, action_str: str) -> bool: self.bash_command = re.search( - r"(.*?)", action_str, re.DOTALL + r'(.*?)', action_str, re.DOTALL ) return self.bash_command is not None def parse(self, action_str: str) -> Action: assert ( self.bash_command is not None - ), "self.bash_command should not be None when parse is called" - thought = action_str.replace(self.bash_command.group(0), "").strip() + ), 'self.bash_command should not be None when parse is called' + thought = action_str.replace(self.bash_command.group(0), '').strip() # a command was found command_group = self.bash_command.group(1).strip() - if command_group.strip() == "exit": + if command_group.strip() == 'exit': return AgentFinishAction() return CmdRunAction(command=command_group, thought=thought) @@ -70,20 +70,20 @@ def __init__( self, ): self.python_code = None - self.jupyter_kernel_init_code: str = "from agentskills import *" + self.jupyter_kernel_init_code: str = 'from agentskills import *' def check_condition(self, action_str: str) -> bool: self.python_code = re.search( - r"(.*?)", action_str, re.DOTALL + r'(.*?)', action_str, re.DOTALL ) return self.python_code is not None def parse(self, action_str: str) -> Action: assert ( self.python_code is not None - ), "self.python_code should not be None when parse is called" + ), 'self.python_code should not be None when parse is called' code_group = self.python_code.group(1).strip() - thought = action_str.replace(self.python_code.group(0), "").strip() + thought = action_str.replace(self.python_code.group(0), '').strip() return IPythonRunCellAction( code=code_group, thought=thought, diff --git a/openhands/agenthub/codeact_swe_agent/codeact_swe_agent.py b/openhands/agenthub/codeact_swe_agent/codeact_swe_agent.py index ba7834b1ca98..8d403d357e03 100644 --- a/openhands/agenthub/codeact_swe_agent/codeact_swe_agent.py +++ b/openhands/agenthub/codeact_swe_agent/codeact_swe_agent.py @@ -34,7 +34,7 @@ def get_system_message() -> str: - return f"{SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}" + return f'{SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}' def get_in_context_example() -> str: @@ -42,7 +42,7 @@ def get_in_context_example() -> str: class CodeActSWEAgent(Agent): - VERSION = "1.6" + VERSION = '1.6' """ This agent is an adaptation of the original [SWE Agent](https://swe-agent.com/) based on CodeAct 1.5 using the `agentskills` library of OpenHands. @@ -80,13 +80,13 @@ def __init__( def action_to_str(self, action: Action) -> str: if isinstance(action, CmdRunAction): return ( - f"{action.thought}\n\n{action.command}\n" + f'{action.thought}\n\n{action.command}\n' ) elif isinstance(action, IPythonRunCellAction): - return f"{action.thought}\n\n{action.code}\n" + return f'{action.thought}\n\n{action.code}\n' elif isinstance(action, MessageAction): return action.content - return "" + return '' def get_action_message(self, action: Action) -> Message | None: if isinstance(action, (CmdRunAction, IPythonRunCellAction, MessageAction)): @@ -100,7 +100,7 @@ def get_action_message(self, action: Action) -> Message | None: content.append(ImageContent(image_urls=action.image_urls)) return Message( - role="user" if action.source == "user" else "assistant", content=content + role='user' if action.source == 'user' else 'assistant', content=content ) return None @@ -108,33 +108,33 @@ def get_action_message(self, action: Action) -> Message | None: def get_observation_message(self, obs: Observation) -> Message | None: max_message_chars = self.llm.config.max_message_chars if isinstance(obs, CmdOutputObservation): - text = "OBSERVATION:\n" + truncate_content( + text = 'OBSERVATION:\n' + truncate_content( obs.content + obs.interpreter_details, max_message_chars ) text += ( - f"\n[Command {obs.command_id} finished with exit code {obs.exit_code}]" + f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]' ) - return Message(role="user", content=[TextContent(text=text)]) + return Message(role='user', content=[TextContent(text=text)]) elif isinstance(obs, IPythonRunCellObservation): - text = "OBSERVATION:\n" + obs.content + text = 'OBSERVATION:\n' + obs.content # replace base64 images with a placeholder - splitted = text.split("\n") + splitted = text.split('\n') for i, line in enumerate(splitted): - if "![image](data:image/png;base64," in line: + if '![image](data:image/png;base64,' in line: splitted[i] = ( - "![image](data:image/png;base64, ...) already displayed to user" + '![image](data:image/png;base64, ...) already displayed to user' ) - text = "\n".join(splitted) + text = '\n'.join(splitted) text = truncate_content(text, max_message_chars) - return Message(role="user", content=[TextContent(text=text)]) + return Message(role='user', content=[TextContent(text=text)]) elif isinstance(obs, ErrorObservation): - text = "OBSERVATION:\n" + truncate_content(obs.content, max_message_chars) - text += "\n[Error occurred in processing last action]" - return Message(role="user", content=[TextContent(text=text)]) + text = 'OBSERVATION:\n' + truncate_content(obs.content, max_message_chars) + text += '\n[Error occurred in processing last action]' + return Message(role='user', content=[TextContent(text=text)]) else: # If an observation message is not returned, it will cause an error # when the LLM tries to return the next message - raise ValueError(f"Unknown observation type: {type(obs)}") + raise ValueError(f'Unknown observation type: {type(obs)}') def reset(self) -> None: """Resets the CodeAct Agent.""" @@ -155,7 +155,7 @@ def step(self, state: State) -> Action: """ # if we're done, go back last_user_message = state.get_last_user_message() - if last_user_message and last_user_message.content.strip() == "/exit": + if last_user_message and last_user_message.content.strip() == '/exit': return AgentFinishAction() # prepare what we want to send to the LLM @@ -163,8 +163,8 @@ def step(self, state: State) -> Action: response = self.llm.completion( messages=self.llm.format_messages_for_llm(messages), stop=[ - "", - "", + '', + '', ], ) @@ -172,8 +172,8 @@ def step(self, state: State) -> Action: def _get_messages(self, state: State) -> list[Message]: messages: list[Message] = [ - Message(role="system", content=[TextContent(text=self.system_message)]), - Message(role="user", content=[TextContent(text=self.in_context_example)]), + Message(role='system', content=[TextContent(text=self.system_message)]), + Message(role='user', content=[TextContent(text=self.in_context_example)]), ] for event in state.history: @@ -183,7 +183,7 @@ def _get_messages(self, state: State) -> list[Message]: elif isinstance(event, Observation): message = self.get_observation_message(event) else: - raise ValueError(f"Unknown event type: {type(event)}") + raise ValueError(f'Unknown event type: {type(event)}') # add regular message if message: @@ -198,7 +198,7 @@ def _get_messages(self, state: State) -> list[Message]: # the latest user message is important: # we want to remind the agent of the environment constraints latest_user_message = next( - (m for m in reversed(messages) if m.role == "user"), None + (m for m in reversed(messages) if m.role == 'user'), None ) # Get the last user text inside content @@ -211,7 +211,7 @@ def _get_messages(self, state: State) -> list[Message]: ) ) # add a reminder to the prompt - reminder_text = f"\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task. When finished reply with ." + reminder_text = f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task. When finished reply with .' if latest_user_message_text: latest_user_message_text.text = ( diff --git a/openhands/agenthub/codeact_swe_agent/prompt.py b/openhands/agenthub/codeact_swe_agent/prompt.py index ddb39ebdaa71..1a2ffabad95f 100644 --- a/openhands/agenthub/codeact_swe_agent/prompt.py +++ b/openhands/agenthub/codeact_swe_agent/prompt.py @@ -3,8 +3,8 @@ _AGENT_SKILLS_DOCS = AgentSkillsRequirement.documentation COMMAND_DOCS = ( - "\nApart from the standard Python library, the assistant can also use the following functions (already imported) in environment:\n" - f"{_AGENT_SKILLS_DOCS}" + '\nApart from the standard Python library, the assistant can also use the following functions (already imported) in environment:\n' + f'{_AGENT_SKILLS_DOCS}' "Please note that THE `edit_file` FUNCTION REQUIRES PROPER INDENTATION. If the assistant would like to add the line ' print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run." ) diff --git a/openhands/agenthub/codeact_swe_agent/response_parser.py b/openhands/agenthub/codeact_swe_agent/response_parser.py index 3375b2c2c291..147b8655f8f8 100644 --- a/openhands/agenthub/codeact_swe_agent/response_parser.py +++ b/openhands/agenthub/codeact_swe_agent/response_parser.py @@ -33,10 +33,10 @@ def parse(self, response: str) -> Action: def parse_response(self, response) -> str: action = response.choices[0].message.content if action is None: - return "" - for lang in ["bash", "ipython"]: - if f"" in action and f"" not in action: - action += f"" + return '' + for lang in ['bash', 'ipython']: + if f'' in action and f'' not in action: + action += f'' return action def parse_action(self, action_str: str) -> Action: diff --git a/openhands/agenthub/delegator_agent/__init__.py b/openhands/agenthub/delegator_agent/__init__.py index 21a3fa14cca8..68e20efa3092 100644 --- a/openhands/agenthub/delegator_agent/__init__.py +++ b/openhands/agenthub/delegator_agent/__init__.py @@ -1,4 +1,4 @@ from openhands.agenthub.delegator_agent.agent import DelegatorAgent from openhands.controller.agent import Agent -Agent.register("DelegatorAgent", DelegatorAgent) +Agent.register('DelegatorAgent', DelegatorAgent) diff --git a/openhands/agenthub/delegator_agent/agent.py b/openhands/agenthub/delegator_agent/agent.py index f86335923ae9..7cb987c8c3f7 100644 --- a/openhands/agenthub/delegator_agent/agent.py +++ b/openhands/agenthub/delegator_agent/agent.py @@ -7,12 +7,12 @@ class DelegatorAgent(Agent): - VERSION = "1.0" + VERSION = '1.0' """ The Delegator Agent is responsible for delegating tasks to other agents based on the current task. """ - current_delegate: str = "" + current_delegate: str = '' def __init__(self, llm: LLM, config: AgentConfig): """Initialize the Delegator Agent with an LLM @@ -33,11 +33,11 @@ def step(self, state: State) -> Action: - AgentFinishAction: If the last state was 'completed', 'verified', or 'abandoned' - AgentDelegateAction: The next agent to delegate the task to """ - if self.current_delegate == "": - self.current_delegate = "study" + if self.current_delegate == '': + self.current_delegate = 'study' task, _ = state.get_current_user_intent() return AgentDelegateAction( - agent="StudyRepoForTaskAgent", inputs={"task": task} + agent='StudyRepoForTaskAgent', inputs={'task': task} ) # last observation in history should be from the delegate @@ -48,40 +48,40 @@ def step(self, state: State) -> Action: break if not isinstance(last_observation, AgentDelegateObservation): - raise Exception("Last observation is not an AgentDelegateObservation") + raise Exception('Last observation is not an AgentDelegateObservation') goal, _ = state.get_current_user_intent() - if self.current_delegate == "study": - self.current_delegate = "coder" + if self.current_delegate == 'study': + self.current_delegate = 'coder' return AgentDelegateAction( - agent="CoderAgent", + agent='CoderAgent', inputs={ - "task": goal, - "summary": last_observation.outputs["summary"], + 'task': goal, + 'summary': last_observation.outputs['summary'], }, ) - elif self.current_delegate == "coder": - self.current_delegate = "verifier" + elif self.current_delegate == 'coder': + self.current_delegate = 'verifier' return AgentDelegateAction( - agent="VerifierAgent", + agent='VerifierAgent', inputs={ - "task": goal, + 'task': goal, }, ) - elif self.current_delegate == "verifier": + elif self.current_delegate == 'verifier': if ( - "completed" in last_observation.outputs - and last_observation.outputs["completed"] + 'completed' in last_observation.outputs + and last_observation.outputs['completed'] ): return AgentFinishAction() else: - self.current_delegate = "coder" + self.current_delegate = 'coder' return AgentDelegateAction( - agent="CoderAgent", + agent='CoderAgent', inputs={ - "task": goal, - "summary": last_observation.outputs["summary"], + 'task': goal, + 'summary': last_observation.outputs['summary'], }, ) else: - raise Exception("Invalid delegate state") + raise Exception('Invalid delegate state') diff --git a/openhands/agenthub/dummy_agent/__init__.py b/openhands/agenthub/dummy_agent/__init__.py index 0873b1d525d3..d0db8e26c9cd 100644 --- a/openhands/agenthub/dummy_agent/__init__.py +++ b/openhands/agenthub/dummy_agent/__init__.py @@ -1,4 +1,4 @@ from openhands.agenthub.dummy_agent.agent import DummyAgent from openhands.controller.agent import Agent -Agent.register("DummyAgent", DummyAgent) +Agent.register('DummyAgent', DummyAgent) diff --git a/openhands/agenthub/dummy_agent/agent.py b/openhands/agenthub/dummy_agent/agent.py index 5d7bc9c545e4..272e6c935f2e 100644 --- a/openhands/agenthub/dummy_agent/agent.py +++ b/openhands/agenthub/dummy_agent/agent.py @@ -35,7 +35,7 @@ """ ActionObs = TypedDict( - "ActionObs", {"action": Action, "observations": list[Observation]} + 'ActionObs', {'action': Action, 'observations': list[Observation]} ) @@ -50,81 +50,81 @@ def __init__(self, llm: LLM, config: AgentConfig): super().__init__(llm, config) self.steps: list[ActionObs] = [ { - "action": AddTaskAction( - parent="None", goal="check the current directory" + 'action': AddTaskAction( + parent='None', goal='check the current directory' ), - "observations": [], + 'observations': [], }, { - "action": AddTaskAction(parent="0", goal="run ls"), - "observations": [], + 'action': AddTaskAction(parent='0', goal='run ls'), + 'observations': [], }, { - "action": ModifyTaskAction(task_id="0", state="in_progress"), - "observations": [], + 'action': ModifyTaskAction(task_id='0', state='in_progress'), + 'observations': [], }, { - "action": MessageAction("Time to get started!"), - "observations": [], + 'action': MessageAction('Time to get started!'), + 'observations': [], }, { - "action": CmdRunAction(command='echo "foo"'), - "observations": [ + 'action': CmdRunAction(command='echo "foo"'), + 'observations': [ CmdOutputObservation( - "foo", command_id=-1, command='echo "foo"', exit_code=0 + 'foo', command_id=-1, command='echo "foo"', exit_code=0 ) ], }, { - "action": FileWriteAction( - content='echo "Hello, World!"', path="hello.sh" + 'action': FileWriteAction( + content='echo "Hello, World!"', path='hello.sh' ), - "observations": [ + 'observations': [ FileWriteObservation( - content='echo "Hello, World!"', path="hello.sh" + content='echo "Hello, World!"', path='hello.sh' ) ], }, { - "action": FileReadAction(path="hello.sh"), - "observations": [ - FileReadObservation('echo "Hello, World!"\n', path="hello.sh") + 'action': FileReadAction(path='hello.sh'), + 'observations': [ + FileReadObservation('echo "Hello, World!"\n', path='hello.sh') ], }, { - "action": CmdRunAction(command="bash hello.sh"), - "observations": [ + 'action': CmdRunAction(command='bash hello.sh'), + 'observations': [ CmdOutputObservation( - "bash: hello.sh: No such file or directory", + 'bash: hello.sh: No such file or directory', command_id=-1, - command="bash workspace/hello.sh", + command='bash workspace/hello.sh', exit_code=127, ) ], }, { - "action": BrowseURLAction(url="https://google.com"), - "observations": [ + 'action': BrowseURLAction(url='https://google.com'), + 'observations': [ # BrowserOutputObservation('Simulated Google page',url='https://google.com',screenshot=''), ], }, { - "action": BrowseInteractiveAction( + 'action': BrowseInteractiveAction( browser_actions='goto("https://google.com")' ), - "observations": [ + 'observations': [ # BrowserOutputObservation('Simulated Google page after interaction',url='https://google.com',screenshot=''), ], }, { - "action": AgentRejectAction(), - "observations": [NullObservation("")], + 'action': AgentRejectAction(), + 'observations': [NullObservation('')], }, { - "action": AgentFinishAction( - outputs={}, thought="Task completed", action="finish" + 'action': AgentFinishAction( + outputs={}, thought='Task completed', action='finish' ), - "observations": [AgentStateChangedObservation("", AgentState.FINISHED)], + 'observations': [AgentStateChangedObservation('', AgentState.FINISHED)], }, ] @@ -133,23 +133,23 @@ def step(self, state: State) -> Action: return AgentFinishAction() current_step = self.steps[state.iteration] - action = current_step["action"] + action = current_step['action'] # If the action is AddTaskAction or ModifyTaskAction, update the parent ID or task_id if isinstance(action, AddTaskAction): - if action.parent == "None": - action.parent = "" # Root task has no parent - elif action.parent == "0": + if action.parent == 'None': + action.parent = '' # Root task has no parent + elif action.parent == '0': action.parent = state.root_task.id - elif action.parent.startswith("0."): - action.parent = f"{state.root_task.id}{action.parent[1:]}" + elif action.parent.startswith('0.'): + action.parent = f'{state.root_task.id}{action.parent[1:]}' elif isinstance(action, ModifyTaskAction): - if action.task_id == "0": + if action.task_id == '0': action.task_id = state.root_task.id - elif action.task_id.startswith("0."): - action.task_id = f"{state.root_task.id}{action.task_id[1:]}" + elif action.task_id.startswith('0.'): + action.task_id = f'{state.root_task.id}{action.task_id[1:]}' # Ensure the task_id doesn't start with a dot - if action.task_id.startswith("."): + if action.task_id.startswith('.'): action.task_id = action.task_id[1:] elif isinstance(action, (BrowseURLAction, BrowseInteractiveAction)): try: @@ -162,13 +162,13 @@ def step(self, state: State) -> Action: if state.iteration > 0: prev_step = self.steps[state.iteration - 1] - if "observations" in prev_step and prev_step["observations"]: - expected_observations = prev_step["observations"] + if 'observations' in prev_step and prev_step['observations']: + expected_observations = prev_step['observations'] hist_events = state.history[-len(expected_observations) :] if len(hist_events) < len(expected_observations): print( - f"Warning: Expected {len(expected_observations)} observations, but got {len(hist_events)}" + f'Warning: Expected {len(expected_observations)} observations, but got {len(hist_events)}' ) for i in range(min(len(expected_observations), len(hist_events))): @@ -177,16 +177,16 @@ def step(self, state: State) -> Action: # Remove dynamic fields for comparison for obs in [hist_obs, expected_obs]: - obs.pop("id", None) - obs.pop("timestamp", None) - obs.pop("cause", None) - obs.pop("source", None) - if "extras" in obs: - obs["extras"].pop("command_id", None) + obs.pop('id', None) + obs.pop('timestamp', None) + obs.pop('cause', None) + obs.pop('source', None) + if 'extras' in obs: + obs['extras'].pop('command_id', None) if hist_obs != expected_obs: print( - f"Warning: Observation mismatch. Expected {expected_obs}, got {hist_obs}" + f'Warning: Observation mismatch. Expected {expected_obs}, got {hist_obs}' ) return action @@ -201,11 +201,11 @@ def handle_browser_unavailable( self, action: Union[BrowseURLAction, BrowseInteractiveAction] ) -> Action: # Create a message action to inform that browsing is not available - message = "Browser actions are not available in the DummyAgent environment." + message = 'Browser actions are not available in the DummyAgent environment.' if isinstance(action, BrowseURLAction): - message += f" Unable to browse URL: {action.url}" + message += f' Unable to browse URL: {action.url}' elif isinstance(action, BrowseInteractiveAction): message += ( - f" Unable to perform interactive browsing: {action.browser_actions}" + f' Unable to perform interactive browsing: {action.browser_actions}' ) return MessageAction(content=message) diff --git a/openhands/agenthub/micro/agent.py b/openhands/agenthub/micro/agent.py index f5fbc05b181c..a9b0825afd9d 100644 --- a/openhands/agenthub/micro/agent.py +++ b/openhands/agenthub/micro/agent.py @@ -28,12 +28,14 @@ def to_json(obj, **kwargs): class MicroAgent(Agent): - VERSION = "1.0" - prompt = "" + VERSION = '1.0' + prompt = '' agent_definition: dict = {} def history_to_json(self, history: list[Event], max_events: int = 20, **kwargs): - """Serialize and simplify history to str format""" + """ + Serialize and simplify history to str format + """ processed_history = [] event_count = 0 @@ -52,11 +54,11 @@ def history_to_json(self, history: list[Event], max_events: int = 20, **kwargs): def __init__(self, llm: LLM, config: AgentConfig): super().__init__(llm, config) - if "name" not in self.agent_definition: - raise ValueError("Agent definition must contain a name") + if 'name' not in self.agent_definition: + raise ValueError('Agent definition must contain a name') self.prompt_template = Environment(loader=BaseLoader).from_string(self.prompt) self.delegates = all_microagents.copy() - del self.delegates[self.agent_definition["name"]] + del self.delegates[self.agent_definition['name']] def step(self, state: State) -> Action: last_user_message, last_image_urls = state.get_current_user_intent() @@ -71,10 +73,10 @@ def step(self, state: State) -> Action: content = [TextContent(text=prompt)] if self.llm.vision_is_active() and last_image_urls: content.append(ImageContent(image_urls=last_image_urls)) - message = Message(role="user", content=content) + message = Message(role='user', content=content) resp = self.llm.completion( messages=self.llm.format_messages_for_llm(message), ) - action_resp = resp["choices"][0]["message"]["content"] + action_resp = resp['choices'][0]['message']['content'] action = parse_response(action_resp) return action diff --git a/openhands/agenthub/micro/instructions.py b/openhands/agenthub/micro/instructions.py index e932961257df..73e72eb2b3c9 100644 --- a/openhands/agenthub/micro/instructions.py +++ b/openhands/agenthub/micro/instructions.py @@ -2,7 +2,7 @@ instructions: dict = {} -base_dir = os.path.dirname(os.path.abspath(__file__)) + "/_instructions" +base_dir = os.path.dirname(os.path.abspath(__file__)) + '/_instructions' for root, dirs, files in os.walk(base_dir): if len(files) == 0: continue @@ -10,7 +10,7 @@ obj = instructions else: rel_base = os.path.relpath(root, base_dir) - keys = rel_base.split("/") + keys = rel_base.split('/') obj = instructions for key in keys: if key not in obj: @@ -18,5 +18,5 @@ obj = obj[key] for file in files: without_ext = os.path.splitext(file)[0] - with open(os.path.join(root, file), "r") as f: + with open(os.path.join(root, file), 'r') as f: obj[without_ext] = f.read() diff --git a/openhands/agenthub/micro/registry.py b/openhands/agenthub/micro/registry.py index c10698415489..cc16e4d26d9b 100644 --- a/openhands/agenthub/micro/registry.py +++ b/openhands/agenthub/micro/registry.py @@ -8,20 +8,20 @@ dirs = sorted(os.listdir(os.path.dirname(__file__))) for dir in dirs: - base = os.path.dirname(__file__) + "/" + dir + base = os.path.dirname(__file__) + '/' + dir if os.path.isfile(base): continue - if dir.startswith("_"): + if dir.startswith('_'): continue - promptFile = base + "/prompt.md" - agentFile = base + "/agent.yaml" + promptFile = base + '/prompt.md' + agentFile = base + '/agent.yaml' if not os.path.isfile(promptFile) or not os.path.isfile(agentFile): - raise Exception(f"Missing prompt or agent file in {base}. Please create them.") - with open(promptFile, "r") as f: + raise Exception(f'Missing prompt or agent file in {base}. Please create them.') + with open(promptFile, 'r') as f: prompt = f.read() - with open(agentFile, "r") as f: + with open(agentFile, 'r') as f: agent = yaml.safe_load(f) - if "name" not in agent: - raise Exception(f"Missing name in {agentFile}") - agent["prompt"] = prompt - all_microagents[agent["name"]] = agent + if 'name' not in agent: + raise Exception(f'Missing name in {agentFile}') + agent['prompt'] = prompt + all_microagents[agent['name']] = agent diff --git a/openhands/agenthub/planner_agent/__init__.py b/openhands/agenthub/planner_agent/__init__.py index b09a79dcdc76..e8c030e84c09 100644 --- a/openhands/agenthub/planner_agent/__init__.py +++ b/openhands/agenthub/planner_agent/__init__.py @@ -1,4 +1,4 @@ from openhands.agenthub.planner_agent.agent import PlannerAgent from openhands.controller.agent import Agent -Agent.register("PlannerAgent", PlannerAgent) +Agent.register('PlannerAgent', PlannerAgent) diff --git a/openhands/agenthub/planner_agent/agent.py b/openhands/agenthub/planner_agent/agent.py index 659d0efe4007..f5aef523d9b9 100644 --- a/openhands/agenthub/planner_agent/agent.py +++ b/openhands/agenthub/planner_agent/agent.py @@ -9,7 +9,7 @@ class PlannerAgent(Agent): - VERSION = "1.0" + VERSION = '1.0' """ The planner agent utilizes a special prompting strategy to create long term plans for solving problems. The agent is given its previous action-observation pairs, current task, and hint based on last action taken at every step. @@ -36,9 +36,9 @@ def step(self, state: State) -> Action: - Action: The next action to take based on llm response """ if state.root_task.state in [ - "completed", - "verified", - "abandoned", + 'completed', + 'verified', + 'abandoned', ]: return AgentFinishAction() @@ -48,6 +48,6 @@ def step(self, state: State) -> Action: content = [TextContent(text=prompt)] if self.llm.vision_is_active() and image_urls: content.append(ImageContent(image_urls=image_urls)) - message = Message(role="user", content=content) + message = Message(role='user', content=content) resp = self.llm.completion(messages=self.llm.format_messages_for_llm(message)) return self.response_parser.parse(resp) diff --git a/openhands/agenthub/planner_agent/prompt.py b/openhands/agenthub/planner_agent/prompt.py index 8ab0e6e58d17..7b73f4353131 100644 --- a/openhands/agenthub/planner_agent/prompt.py +++ b/openhands/agenthub/planner_agent/prompt.py @@ -101,18 +101,18 @@ def get_hint(latest_action_id: str) -> str: """Returns action type hint based on given action_id""" hints = { - "": "You haven't taken any actions yet. Start by using `ls` to check out what files you're working with.", - ActionType.RUN: "You should think about the command you just ran, what output it gave, and how that affects your plan.", - ActionType.READ: "You should think about the file you just read, what you learned from it, and how that affects your plan.", - ActionType.WRITE: "You just changed a file. You should think about how it affects your plan.", - ActionType.BROWSE: "You should think about the page you just visited, and what you learned from it.", + '': "You haven't taken any actions yet. Start by using `ls` to check out what files you're working with.", + ActionType.RUN: 'You should think about the command you just ran, what output it gave, and how that affects your plan.', + ActionType.READ: 'You should think about the file you just read, what you learned from it, and how that affects your plan.', + ActionType.WRITE: 'You just changed a file. You should think about how it affects your plan.', + ActionType.BROWSE: 'You should think about the page you just visited, and what you learned from it.', ActionType.MESSAGE: "Look at your last thought in the history above. What does it suggest? Don't think anymore--take action.", - ActionType.ADD_TASK: "You should think about the next action to take.", - ActionType.MODIFY_TASK: "You should think about the next action to take.", - ActionType.SUMMARIZE: "", - ActionType.FINISH: "", + ActionType.ADD_TASK: 'You should think about the next action to take.', + ActionType.MODIFY_TASK: 'You should think about the next action to take.', + ActionType.SUMMARIZE: '', + ActionType.FINISH: '', } - return hints.get(latest_action_id, "") + return hints.get(latest_action_id, '') def get_prompt_and_images( @@ -159,19 +159,19 @@ def get_prompt_and_images( plan_status = "You're not currently working on any tasks. Your next action MUST be to mark a task as in_progress." # the hint, based on the last action - hint = get_hint(event_to_memory(latest_action, max_message_chars).get("action", "")) - logger.debug("HINT:\n" + hint, extra={"msg_type": "DETAIL"}) + hint = get_hint(event_to_memory(latest_action, max_message_chars).get('action', '')) + logger.debug('HINT:\n' + hint, extra={'msg_type': 'DETAIL'}) # the last relevant user message (the task) message, image_urls = state.get_current_user_intent() # finally, fill in the prompt return prompt % { - "task": message, - "plan": plan_str, - "history": history_str, - "hint": hint, - "plan_status": plan_status, + 'task': message, + 'plan': plan_str, + 'history': history_str, + 'hint': hint, + 'plan_status': plan_status, }, image_urls @@ -184,8 +184,8 @@ def parse_response(response: str) -> Action: - Action: A valid next action to perform from model output """ action_dict = json.loads(response) - if "contents" in action_dict: + if 'contents' in action_dict: # The LLM gets confused here. Might as well be robust - action_dict["content"] = action_dict.pop("contents") + action_dict['content'] = action_dict.pop('contents') action = action_from_dict(action_dict) return action diff --git a/openhands/agenthub/planner_agent/response_parser.py b/openhands/agenthub/planner_agent/response_parser.py index d0f93e8a7879..12068cd5b769 100644 --- a/openhands/agenthub/planner_agent/response_parser.py +++ b/openhands/agenthub/planner_agent/response_parser.py @@ -16,7 +16,7 @@ def parse(self, response: str) -> Action: def parse_response(self, response) -> str: # get the next action from the response - return response["choices"][0]["message"]["content"] + return response['choices'][0]['message']['content'] def parse_action(self, action_str: str) -> Action: """Parses a string to find an action within it @@ -30,8 +30,8 @@ def parse_action(self, action_str: str) -> Action: # attempt to load the JSON dict from the response action_dict = json.loads(action_str) - if "content" in action_dict: + if 'content' in action_dict: # The LLM gets confused here. Might as well be robust - action_dict["contents"] = action_dict.pop("content") + action_dict['contents'] = action_dict.pop('content') return action_from_dict(action_dict) diff --git a/openhands/controller/agent_controller.py b/openhands/controller/agent_controller.py index 09da4d9f300d..78b27c89ff7f 100644 --- a/openhands/controller/agent_controller.py +++ b/openhands/controller/agent_controller.py @@ -42,7 +42,7 @@ ) from openhands.events.serialization.event import truncate_content from openhands.llm.llm import LLM -from openhands.runtime.utils.shutdown_listener import should_continue +from openhands.utils.shutdown_listener import should_continue # note: RESUME is only available on web GUI TRAFFIC_CONTROL_REMINDER = ( @@ -131,8 +131,7 @@ def __init__( async def close(self): """Closes the agent controller, canceling any ongoing tasks and unsubscribing from the event stream. - Note that it's fairly important that this closes properly, otherwise the state is incomplete. - """ + Note that it's fairly important that this closes properly, otherwise the state is incomplete.""" await self.set_agent_state_to(AgentState.STOPPED) # we made history, now is the time to rewrite it! @@ -190,6 +189,7 @@ async def _react_to_exception( async def start_step_loop(self): """The main loop for the agent's step-by-step execution.""" + self.log('info', 'Starting step loop...') while should_continue(): try: @@ -303,6 +303,7 @@ async def _handle_message_action(self, action: MessageAction): def reset_task(self): """Resets the agent's task.""" + self.almost_stuck = 0 self.agent.reset() @@ -659,6 +660,7 @@ def _init_history(self): - Excludes all events between the action and observation - Includes the delegate action and observation themselves """ + # define range of events to fetch # delegates start with a start_id and initially won't find any events # otherwise we're restoring a previous session diff --git a/openhands/controller/state/state.py b/openhands/controller/state/state.py index f9438c0f8c2b..d52844d418b4 100644 --- a/openhands/controller/state/state.py +++ b/openhands/controller/state/state.py @@ -18,13 +18,13 @@ class TrafficControlState(str, Enum): # default state, no rate limiting - NORMAL = "normal" + NORMAL = 'normal' # task paused due to traffic control - THROTTLING = "throttling" + THROTTLING = 'throttling' # traffic control is temporarily paused - PAUSED = "paused" + PAUSED = 'paused' RESUMABLE_STATES = [ @@ -37,7 +37,8 @@ class TrafficControlState(str, Enum): @dataclass class State: - """Represents the running state of an agent in the OpenHands system, saving data of its operation and memory. + """ + Represents the running state of an agent in the OpenHands system, saving data of its operation and memory. - Multi-agent/delegate state: - store the task (conversation between the agent and the user) @@ -96,26 +97,26 @@ class State: # NOTE: This will never be used by the controller, but it can be used by different # evaluation tasks to store extra data needed to track the progress/state of the task. extra_data: dict[str, Any] = field(default_factory=dict) - last_error: str = "" + last_error: str = '' def save_to_session(self, sid: str, file_store: FileStore): pickled = pickle.dumps(self) - logger.debug(f"Saving state to session {sid}:{self.agent_state}") - encoded = base64.b64encode(pickled).decode("utf-8") + logger.debug(f'Saving state to session {sid}:{self.agent_state}') + encoded = base64.b64encode(pickled).decode('utf-8') try: - file_store.write(f"sessions/{sid}/agent_state.pkl", encoded) + file_store.write(f'sessions/{sid}/agent_state.pkl', encoded) except Exception as e: - logger.error(f"Failed to save state to session: {e}") + logger.error(f'Failed to save state to session: {e}') raise e @staticmethod - def restore_from_session(sid: str, file_store: FileStore) -> "State": + def restore_from_session(sid: str, file_store: FileStore) -> 'State': try: - encoded = file_store.read(f"sessions/{sid}/agent_state.pkl") + encoded = file_store.read(f'sessions/{sid}/agent_state.pkl') pickled = base64.b64decode(encoded) state = pickle.loads(pickled) except Exception as e: - logger.warning(f"Could not restore state from session: {e}") + logger.warning(f'Could not restore state from session: {e}') raise e # update state @@ -131,14 +132,14 @@ def restore_from_session(sid: str, file_store: FileStore) -> "State": def __getstate__(self): # don't pickle history, it will be restored from the event stream state = self.__dict__.copy() - state["history"] = [] + state['history'] = [] return state def __setstate__(self, state): self.__dict__.update(state) # make sure we always have the attribute history - if not hasattr(self, "history"): + if not hasattr(self, 'history'): self.history = [] def get_current_user_intent(self) -> tuple[str | None, list[str] | None]: @@ -146,7 +147,7 @@ def get_current_user_intent(self) -> tuple[str | None, list[str] | None]: last_user_message = None last_user_message_image_urls: list[str] | None = [] for event in reversed(self.history): - if isinstance(event, MessageAction) and event.source == "user": + if isinstance(event, MessageAction) and event.source == 'user': last_user_message = event.content last_user_message_image_urls = event.image_urls elif isinstance(event, AgentFinishAction): diff --git a/openhands/controller/state/task.py b/openhands/controller/state/task.py index ffd3adaa14db..456ae0f0a27d 100644 --- a/openhands/controller/state/task.py +++ b/openhands/controller/state/task.py @@ -4,11 +4,11 @@ ) from openhands.core.logger import openhands_logger as logger -OPEN_STATE = "open" -COMPLETED_STATE = "completed" -ABANDONED_STATE = "abandoned" -IN_PROGRESS_STATE = "in_progress" -VERIFIED_STATE = "verified" +OPEN_STATE = 'open' +COMPLETED_STATE = 'completed' +ABANDONED_STATE = 'abandoned' +IN_PROGRESS_STATE = 'in_progress' +VERIFIED_STATE = 'verified' STATES = [ OPEN_STATE, COMPLETED_STATE, @@ -21,12 +21,12 @@ class Task: id: str goal: str - parent: "Task | None" - subtasks: list["Task"] + parent: 'Task | None' + subtasks: list['Task'] def __init__( self, - parent: "Task", + parent: 'Task', goal: str, state: str = OPEN_STATE, subtasks=None, # noqa: B006 @@ -42,26 +42,26 @@ def __init__( if subtasks is None: subtasks = [] if parent.id: - self.id = parent.id + "." + str(len(parent.subtasks)) + self.id = parent.id + '.' + str(len(parent.subtasks)) else: self.id = str(len(parent.subtasks)) self.parent = parent self.goal = goal - logger.debug(f"Creating task {self.id} with parent={parent.id}, goal={goal}") + logger.debug(f'Creating task {self.id} with parent={parent.id}, goal={goal}') self.subtasks = [] for subtask in subtasks or []: if isinstance(subtask, Task): self.subtasks.append(subtask) else: - goal = subtask.get("goal") - state = subtask.get("state") - subtasks = subtask.get("subtasks") - logger.debug(f"Reading: {goal}, {state}, {subtasks}") + goal = subtask.get('goal') + state = subtask.get('state') + subtasks = subtask.get('subtasks') + logger.debug(f'Reading: {goal}, {state}, {subtasks}') self.subtasks.append(Task(self, goal, state, subtasks)) self.state = OPEN_STATE - def to_string(self, indent=""): + def to_string(self, indent=''): """Returns a string representation of the task and its subtasks. Args: @@ -70,20 +70,20 @@ def to_string(self, indent=""): Returns: A string representation of the task and its subtasks. """ - emoji = "" + emoji = '' if self.state == VERIFIED_STATE: - emoji = "✅" + emoji = '✅' elif self.state == COMPLETED_STATE: - emoji = "🟢" + emoji = '🟢' elif self.state == ABANDONED_STATE: - emoji = "❌" + emoji = '❌' elif self.state == IN_PROGRESS_STATE: - emoji = "💪" + emoji = '💪' elif self.state == OPEN_STATE: - emoji = "🔵" - result = indent + emoji + " " + self.id + " " + self.goal + "\n" + emoji = '🔵' + result = indent + emoji + ' ' + self.id + ' ' + self.goal + '\n' for subtask in self.subtasks: - result += subtask.to_string(indent + " ") + result += subtask.to_string(indent + ' ') return result def to_dict(self): @@ -93,10 +93,10 @@ def to_dict(self): A dictionary containing the task's attributes. """ return { - "id": self.id, - "goal": self.goal, - "state": self.state, - "subtasks": [t.to_dict() for t in self.subtasks], + 'id': self.id, + 'goal': self.goal, + 'state': self.state, + 'subtasks': [t.to_dict() for t in self.subtasks], } def set_state(self, state): @@ -108,7 +108,7 @@ def set_state(self, state): TaskInvalidStateError: If the provided state is invalid. """ if state not in STATES: - logger.error("Invalid state: %s", state) + logger.error('Invalid state: %s', state) raise TaskInvalidStateError(state) self.state = state if ( @@ -123,7 +123,7 @@ def set_state(self, state): if self.parent is not None: self.parent.set_state(state) - def get_current_task(self) -> "Task | None": + def get_current_task(self) -> 'Task | None': """Retrieves the current task in progress. Returns: @@ -151,8 +151,8 @@ class RootTask(Task): state: The state of the root_task. """ - id: str = "" - goal: str = "" + id: str = '' + goal: str = '' parent: None = None def __init__(self): @@ -179,18 +179,18 @@ def get_task_by_id(self, id: str) -> Task: Raises: AgentMalformedActionError: If the provided task ID is invalid or does not exist. """ - if id == "": + if id == '': return self if len(self.subtasks) == 0: - raise LLMMalformedActionError("Task does not exist:" + id) + raise LLMMalformedActionError('Task does not exist:' + id) try: - parts = [int(p) for p in id.split(".")] + parts = [int(p) for p in id.split('.')] except ValueError: - raise LLMMalformedActionError("Invalid task id:" + id) + raise LLMMalformedActionError('Invalid task id:' + id) task: Task = self for part in parts: if part >= len(task.subtasks): - raise LLMMalformedActionError("Task does not exist:" + id) + raise LLMMalformedActionError('Task does not exist:' + id) task = task.subtasks[part] return task @@ -215,7 +215,7 @@ def set_subtask_state(self, id: str, state: str): state: The new state of the subtask. """ task = self.get_task_by_id(id) - logger.debug("Setting task {task.id} from state {task.state} to {state}") + logger.debug('Setting task {task.id} from state {task.state} to {state}') task.set_state(state) unfinished_tasks = [ t diff --git a/openhands/core/cli.py b/openhands/core/cli.py index b870e1e4fe14..53db5ca27747 100644 --- a/openhands/core/cli.py +++ b/openhands/core/cli.py @@ -78,6 +78,7 @@ def display_event(event: Event): async def main(): """Runs the agent in CLI mode""" + parser = get_parser() # Add the version argument parser.add_argument( @@ -115,6 +116,7 @@ async def main(): event_stream=event_stream, sid=sid, plugins=agent_cls.sandbox_plugins, + headless_mode=True, ) controller = AgentController( diff --git a/openhands/core/config/__init__.py b/openhands/core/config/__init__.py index 8cc2cd082e76..b8fefb715cf3 100644 --- a/openhands/core/config/__init__.py +++ b/openhands/core/config/__init__.py @@ -19,19 +19,19 @@ ) __all__ = [ - "OH_DEFAULT_AGENT", - "OH_MAX_ITERATIONS", - "AgentConfig", - "AppConfig", - "LLMConfig", - "SandboxConfig", - "SecurityConfig", - "load_app_config", - "load_from_env", - "load_from_toml", - "finalize_config", - "get_llm_config_arg", - "get_field_info", - "get_parser", - "parse_arguments", + 'OH_DEFAULT_AGENT', + 'OH_MAX_ITERATIONS', + 'AgentConfig', + 'AppConfig', + 'LLMConfig', + 'SandboxConfig', + 'SecurityConfig', + 'load_app_config', + 'load_from_env', + 'load_from_toml', + 'finalize_config', + 'get_llm_config_arg', + 'get_field_info', + 'get_parser', + 'parse_arguments', ] diff --git a/openhands/core/config/app_config.py b/openhands/core/config/app_config.py index 3b1951532072..d11072a9c92d 100644 --- a/openhands/core/config/app_config.py +++ b/openhands/core/config/app_config.py @@ -48,62 +48,62 @@ class AppConfig: default_agent: str = OH_DEFAULT_AGENT sandbox: SandboxConfig = field(default_factory=SandboxConfig) security: SecurityConfig = field(default_factory=SecurityConfig) - runtime: str = "eventstream" - file_store: str = "memory" - file_store_path: str = "/tmp/file_store" + runtime: str = 'eventstream' + file_store: str = 'memory' + file_store_path: str = '/tmp/file_store' trajectories_path: str | None = None workspace_base: str | None = None workspace_mount_path: str | None = None - workspace_mount_path_in_sandbox: str = "/workspace" + workspace_mount_path_in_sandbox: str = '/workspace' workspace_mount_rewrite: str | None = None - cache_dir: str = "/tmp/cache" + cache_dir: str = '/tmp/cache' run_as_openhands: bool = True max_iterations: int = OH_MAX_ITERATIONS max_budget_per_task: float | None = None - e2b_api_key: str = "" - modal_api_token_id: str = "" - modal_api_token_secret: str = "" + e2b_api_key: str = '' + modal_api_token_id: str = '' + modal_api_token_secret: str = '' disable_color: bool = False jwt_secret: str = uuid.uuid4().hex debug: bool = False file_uploads_max_file_size_mb: int = 0 file_uploads_restrict_file_types: bool = False - file_uploads_allowed_extensions: list[str] = field(default_factory=lambda: [".*"]) + file_uploads_allowed_extensions: list[str] = field(default_factory=lambda: ['.*']) runloop_api_key: str | None = None defaults_dict: ClassVar[dict] = {} - def get_llm_config(self, name="llm") -> LLMConfig: + def get_llm_config(self, name='llm') -> LLMConfig: """Llm is the name for default config (for backward compatibility prior to 0.8)""" if name in self.llms: return self.llms[name] - if name is not None and name != "llm": + if name is not None and name != 'llm': logger.openhands_logger.warning( - f"llm config group {name} not found, using default config" + f'llm config group {name} not found, using default config' ) - if "llm" not in self.llms: - self.llms["llm"] = LLMConfig() - return self.llms["llm"] + if 'llm' not in self.llms: + self.llms['llm'] = LLMConfig() + return self.llms['llm'] - def set_llm_config(self, value: LLMConfig, name="llm"): + def set_llm_config(self, value: LLMConfig, name='llm'): self.llms[name] = value - def get_agent_config(self, name="agent") -> AgentConfig: + def get_agent_config(self, name='agent') -> AgentConfig: """Agent is the name for default config (for backward compability prior to 0.8)""" if name in self.agents: return self.agents[name] - if "agent" not in self.agents: - self.agents["agent"] = AgentConfig() - return self.agents["agent"] + if 'agent' not in self.agents: + self.agents['agent'] = AgentConfig() + return self.agents['agent'] - def set_agent_config(self, value: AgentConfig, name="agent"): + def set_agent_config(self, value: AgentConfig, name='agent'): self.agents[name] = value def get_agent_to_llm_config_map(self) -> dict[str, LLMConfig]: """Get a map of agent names to llm configs.""" return {name: self.get_llm_config_from_agent(name) for name in self.agents} - def get_llm_config_from_agent(self, name="agent") -> LLMConfig: + def get_llm_config_from_agent(self, name='agent') -> LLMConfig: agent_config: AgentConfig = self.get_agent_config(name) llm_config_name = agent_config.llm_config return self.get_llm_config(llm_config_name) @@ -135,16 +135,16 @@ def __str__(self): attr_value = getattr(self, f.name) if attr_name in [ - "e2b_api_key", - "github_token", - "jwt_secret", - "modal_api_token_id", - "modal_api_token_secret", - "runloop_api_key", + 'e2b_api_key', + 'github_token', + 'jwt_secret', + 'modal_api_token_id', + 'modal_api_token_secret', + 'runloop_api_key', ]: - attr_value = "******" if attr_value else None + attr_value = '******' if attr_value else None - attr_str.append(f"{attr_name}={repr(attr_value)}") + attr_str.append(f'{attr_name}={repr(attr_value)}') return f"AppConfig({', '.join(attr_str)}" diff --git a/openhands/core/config/config_utils.py b/openhands/core/config/config_utils.py index 1b324ef8172c..6e7ddebac611 100644 --- a/openhands/core/config/config_utils.py +++ b/openhands/core/config/config_utils.py @@ -1,7 +1,7 @@ from types import UnionType from typing import get_args, get_origin -OH_DEFAULT_AGENT = "CodeActAgent" +OH_DEFAULT_AGENT = 'CodeActAgent' OH_MAX_ITERATIONS = 100 @@ -29,11 +29,11 @@ def get_field_info(f): # type name in a pretty format type_name = ( - field_type.__name__ if hasattr(field_type, "__name__") else str(field_type) + field_type.__name__ if hasattr(field_type, '__name__') else str(field_type) ) # default is always present default = f.default # return a schema with the useful info for frontend - return {"type": type_name.lower(), "optional": optional, "default": default} + return {'type': type_name.lower(), 'optional': optional, 'default': default} diff --git a/openhands/core/config/llm_config.py b/openhands/core/config/llm_config.py index 6eac2372fc98..477b47ccdbe1 100644 --- a/openhands/core/config/llm_config.py +++ b/openhands/core/config/llm_config.py @@ -5,7 +5,7 @@ from openhands.core.config.config_utils import get_field_info from openhands.core.logger import LOG_DIR -LLM_SENSITIVE_FIELDS = ["api_key", "aws_access_key_id", "aws_secret_access_key"] +LLM_SENSITIVE_FIELDS = ['api_key', 'aws_access_key_id', 'aws_secret_access_key'] @dataclass @@ -45,18 +45,18 @@ class LLMConfig: draft_editor: A more efficient LLM to use for file editing. Introduced in [PR 3985](https://github.com/All-Hands-AI/OpenHands/pull/3985). """ - model: str = "claude-3-5-sonnet-20241022" + model: str = 'claude-3-5-sonnet-20241022' api_key: str | None = None base_url: str | None = None api_version: str | None = None - embedding_model: str = "local" + embedding_model: str = 'local' embedding_base_url: str | None = None embedding_deployment_name: str | None = None aws_access_key_id: str | None = None aws_secret_access_key: str | None = None aws_region_name: str | None = None - openrouter_site_url: str = "https://docs.all-hands.dev/" - openrouter_app_name: str = "OpenHands" + openrouter_site_url: str = 'https://docs.all-hands.dev/' + openrouter_app_name: str = 'OpenHands' num_retries: int = 8 retry_multiplier: float = 2 retry_min_wait: int = 15 @@ -75,8 +75,8 @@ class LLMConfig: disable_vision: bool | None = None caching_prompt: bool = True log_completions: bool = False - log_completions_folder: str = os.path.join(LOG_DIR, "completions") - draft_editor: Optional["LLMConfig"] = None + log_completions_folder: str = os.path.join(LOG_DIR, 'completions') + draft_editor: Optional['LLMConfig'] = None def defaults_to_dict(self) -> dict: """Serialize fields to a dict for the frontend, including type hints, defaults, and whether it's optional.""" @@ -86,14 +86,16 @@ def defaults_to_dict(self) -> dict: return result def __post_init__(self): - """Post-initialization hook to assign OpenRouter-related variables to environment variables. + """ + Post-initialization hook to assign OpenRouter-related variables to environment variables. This ensures that these values are accessible to litellm at runtime. """ + # Assign OpenRouter-specific variables to environment variables if self.openrouter_site_url: - os.environ["OR_SITE_URL"] = self.openrouter_site_url + os.environ['OR_SITE_URL'] = self.openrouter_site_url if self.openrouter_app_name: - os.environ["OR_APP_NAME"] = self.openrouter_app_name + os.environ['OR_APP_NAME'] = self.openrouter_app_name def __str__(self): attr_str = [] @@ -102,9 +104,9 @@ def __str__(self): attr_value = getattr(self, f.name) if attr_name in LLM_SENSITIVE_FIELDS: - attr_value = "******" if attr_value else None + attr_value = '******' if attr_value else None - attr_str.append(f"{attr_name}={repr(attr_value)}") + attr_str.append(f'{attr_name}={repr(attr_value)}') return f"LLMConfig({', '.join(attr_str)})" @@ -116,20 +118,20 @@ def to_safe_dict(self): ret = self.__dict__.copy() for k, v in ret.items(): if k in LLM_SENSITIVE_FIELDS: - ret[k] = "******" if v else None + ret[k] = '******' if v else None elif isinstance(v, LLMConfig): ret[k] = v.to_safe_dict() return ret @classmethod - def from_dict(cls, llm_config_dict: dict) -> "LLMConfig": + def from_dict(cls, llm_config_dict: dict) -> 'LLMConfig': """Create an LLMConfig object from a dictionary. This function is used to create an LLMConfig object from a dictionary, with the exception of the 'draft_editor' key, which is a nested LLMConfig object. """ args = {k: v for k, v in llm_config_dict.items() if not isinstance(v, dict)} - if "draft_editor" in llm_config_dict: - draft_editor_config = LLMConfig(**llm_config_dict["draft_editor"]) - args["draft_editor"] = draft_editor_config + if 'draft_editor' in llm_config_dict: + draft_editor_config = LLMConfig(**llm_config_dict['draft_editor']) + args['draft_editor'] = draft_editor_config return cls(**args) diff --git a/openhands/core/config/sandbox_config.py b/openhands/core/config/sandbox_config.py index 21ba2b01b896..57f4b189b182 100644 --- a/openhands/core/config/sandbox_config.py +++ b/openhands/core/config/sandbox_config.py @@ -34,13 +34,13 @@ class SandboxConfig: platform: The platform on which the image should be built. Default is None. """ - remote_runtime_api_url: str = "http://localhost:8000" - local_runtime_url: str = "http://localhost" + remote_runtime_api_url: str = 'http://localhost:8000' + local_runtime_url: str = 'http://localhost' keep_runtime_alive: bool = True api_key: str | None = None - base_container_image: str = "nikolaik/python-nodejs:python3.12-nodejs22" # default to nikolaik/python-nodejs:python3.12-nodejs22 for eventstream runtime + base_container_image: str = 'nikolaik/python-nodejs:python3.12-nodejs22' # default to nikolaik/python-nodejs:python3.12-nodejs22 for eventstream runtime runtime_container_image: str | None = None - user_id: int = os.getuid() if hasattr(os, "getuid") else 1000 + user_id: int = os.getuid() if hasattr(os, 'getuid') else 1000 timeout: int = 120 remote_runtime_init_timeout: int = 180 enable_auto_lint: bool = ( @@ -67,7 +67,7 @@ def __str__(self): attr_name = f.name attr_value = getattr(self, f.name) - attr_str.append(f"{attr_name}={repr(attr_value)}") + attr_str.append(f'{attr_name}={repr(attr_value)}') return f"SandboxConfig({', '.join(attr_str)})" diff --git a/openhands/core/config/security_config.py b/openhands/core/config/security_config.py index 3b143f927524..a4c49c2b0cda 100644 --- a/openhands/core/config/security_config.py +++ b/openhands/core/config/security_config.py @@ -28,7 +28,7 @@ def __str__(self): attr_name = f.name attr_value = getattr(self, f.name) - attr_str.append(f"{attr_name}={repr(attr_value)}") + attr_str.append(f'{attr_name}={repr(attr_value)}') return f"SecurityConfig({', '.join(attr_str)})" diff --git a/openhands/core/config/utils.py b/openhands/core/config/utils.py index 0e52b9ee5651..86794e8aac2f 100644 --- a/openhands/core/config/utils.py +++ b/openhands/core/config/utils.py @@ -37,7 +37,7 @@ def get_optional_type(union_type: UnionType) -> Any: return next((t for t in types if t is not type(None)), None) # helper function to set attributes based on env vars - def set_attr_from_env(sub_config: Any, prefix=""): + def set_attr_from_env(sub_config: Any, prefix=''): """Set attributes of a config dataclass based on environment variables.""" for field_name, field_type in sub_config.__annotations__.items(): # compute the expected env var name from the prefix and field name @@ -47,7 +47,7 @@ def set_attr_from_env(sub_config: Any, prefix=""): if is_dataclass(field_type): # nested dataclass nested_sub_config = getattr(sub_config, field_name) - set_attr_from_env(nested_sub_config, prefix=field_name + "_") + set_attr_from_env(nested_sub_config, prefix=field_name + '_') elif env_var_name in env_or_toml_dict: # convert the env var to the correct type and set it value = env_or_toml_dict[env_var_name] @@ -63,13 +63,13 @@ def set_attr_from_env(sub_config: Any, prefix=""): # Attempt to cast the env var to type hinted in the dataclass if field_type is bool: - cast_value = str(value).lower() in ["true", "1"] + cast_value = str(value).lower() in ['true', '1'] else: cast_value = field_type(value) setattr(sub_config, field_name, cast_value) except (ValueError, TypeError): logger.openhands_logger.error( - f"Error setting env var {env_var_name}={value}: check that the value is of the right type" + f'Error setting env var {env_var_name}={value}: check that the value is of the right type' ) # Start processing from the root of the config object @@ -77,13 +77,13 @@ def set_attr_from_env(sub_config: Any, prefix=""): # load default LLM config from env default_llm_config = cfg.get_llm_config() - set_attr_from_env(default_llm_config, "LLM_") + set_attr_from_env(default_llm_config, 'LLM_') # load default agent config from env default_agent_config = cfg.get_agent_config() - set_attr_from_env(default_agent_config, "AGENT_") + set_attr_from_env(default_agent_config, 'AGENT_') -def load_from_toml(cfg: AppConfig, toml_file: str = "config.toml"): +def load_from_toml(cfg: AppConfig, toml_file: str = 'config.toml'): """Load the config from the toml file. Supports both styles of config vars. Args: @@ -92,65 +92,65 @@ def load_from_toml(cfg: AppConfig, toml_file: str = "config.toml"): """ # try to read the config.toml file into the config object try: - with open(toml_file, "r", encoding="utf-8") as toml_contents: + with open(toml_file, 'r', encoding='utf-8') as toml_contents: toml_config = toml.load(toml_contents) except FileNotFoundError: return except toml.TomlDecodeError as e: logger.openhands_logger.warning( - f"Cannot parse config from toml, toml values have not been applied.\nError: {e}", + f'Cannot parse config from toml, toml values have not been applied.\nError: {e}', exc_info=False, ) return # if there was an exception or core is not in the toml, try to use the old-style toml - if "core" not in toml_config: + if 'core' not in toml_config: # re-use the env loader to set the config from env-style vars load_from_env(cfg, toml_config) return - core_config = toml_config["core"] + core_config = toml_config['core'] # load llm configs and agent configs for key, value in toml_config.items(): if isinstance(value, dict): try: - if key is not None and key.lower() == "agent": + if key is not None and key.lower() == 'agent': logger.openhands_logger.debug( - "Attempt to load default agent config from config toml" + 'Attempt to load default agent config from config toml' ) non_dict_fields = { k: v for k, v in value.items() if not isinstance(v, dict) } agent_config = AgentConfig(**non_dict_fields) - cfg.set_agent_config(agent_config, "agent") + cfg.set_agent_config(agent_config, 'agent') for nested_key, nested_value in value.items(): if isinstance(nested_value, dict): logger.openhands_logger.debug( - f"Attempt to load group {nested_key} from config toml as agent config" + f'Attempt to load group {nested_key} from config toml as agent config' ) agent_config = AgentConfig(**nested_value) cfg.set_agent_config(agent_config, nested_key) - elif key is not None and key.lower() == "llm": + elif key is not None and key.lower() == 'llm': logger.openhands_logger.debug( - "Attempt to load default LLM config from config toml" + 'Attempt to load default LLM config from config toml' ) llm_config = LLMConfig.from_dict(value) - cfg.set_llm_config(llm_config, "llm") + cfg.set_llm_config(llm_config, 'llm') for nested_key, nested_value in value.items(): if isinstance(nested_value, dict): logger.openhands_logger.debug( - f"Attempt to load group {nested_key} from config toml as llm config" + f'Attempt to load group {nested_key} from config toml as llm config' ) llm_config = LLMConfig.from_dict(nested_value) cfg.set_llm_config(llm_config, nested_key) - elif not key.startswith("sandbox") and key.lower() != "core": + elif not key.startswith('sandbox') and key.lower() != 'core': logger.openhands_logger.warning( f'Unknown key in {toml_file}: "{key}"' ) except (TypeError, KeyError) as e: logger.openhands_logger.warning( - f"Cannot parse config from toml, toml values have not been applied.\n Error: {e}", + f'Cannot parse config from toml, toml values have not been applied.\n Error: {e}', exc_info=False, ) else: @@ -161,18 +161,18 @@ def load_from_toml(cfg: AppConfig, toml_file: str = "config.toml"): sandbox_config = cfg.sandbox # migrate old sandbox configs from [core] section to sandbox config - keys_to_migrate = [key for key in core_config if key.startswith("sandbox_")] + keys_to_migrate = [key for key in core_config if key.startswith('sandbox_')] for key in keys_to_migrate: - new_key = key.replace("sandbox_", "") + new_key = key.replace('sandbox_', '') if new_key in sandbox_config.__annotations__: # read the key in sandbox and remove it from core setattr(sandbox_config, new_key, core_config.pop(key)) else: - logger.openhands_logger.warning(f"Unknown sandbox config: {key}") + logger.openhands_logger.warning(f'Unknown sandbox config: {key}') # the new style values override the old style values - if "sandbox" in toml_config: - sandbox_config = SandboxConfig(**toml_config["sandbox"]) + if 'sandbox' in toml_config: + sandbox_config = SandboxConfig(**toml_config['sandbox']) # update the config object with the new values cfg.sandbox = sandbox_config @@ -180,10 +180,10 @@ def load_from_toml(cfg: AppConfig, toml_file: str = "config.toml"): if hasattr(cfg, key): setattr(cfg, key, value) else: - logger.openhands_logger.warning(f"Unknown core config key: {key}") + logger.openhands_logger.warning(f'Unknown core config key: {key}') except (TypeError, KeyError) as e: logger.openhands_logger.warning( - f"Cannot parse config from toml, toml values have not been applied.\nError: {e}", + f'Cannot parse config from toml, toml values have not been applied.\nError: {e}', exc_info=False, ) @@ -197,7 +197,7 @@ def finalize_config(cfg: AppConfig): if cfg.workspace_mount_rewrite: base = cfg.workspace_base or os.getcwd() - parts = cfg.workspace_mount_rewrite.split(":") + parts = cfg.workspace_mount_rewrite.split(':') cfg.workspace_mount_path = base.replace(parts[0], parts[1]) # make sure log_completions_folder is an absolute path @@ -206,10 +206,10 @@ def finalize_config(cfg: AppConfig): if llm.embedding_base_url is None: llm.embedding_base_url = llm.base_url - if cfg.sandbox.use_host_network and platform.system() == "Darwin": + if cfg.sandbox.use_host_network and platform.system() == 'Darwin': logger.openhands_logger.warning( - "Please upgrade to Docker Desktop 4.29.0 or later to use host network mode on macOS. " - "See https://github.com/docker/roadmap/issues/238#issuecomment-2044688144 for more information." + 'Please upgrade to Docker Desktop 4.29.0 or later to use host network mode on macOS. ' + 'See https://github.com/docker/roadmap/issues/238#issuecomment-2044688144 for more information.' ) # make sure cache dir exists @@ -219,7 +219,7 @@ def finalize_config(cfg: AppConfig): # Utility function for command line --group argument def get_llm_config_arg( - llm_config_arg: str, toml_file: str = "config.toml" + llm_config_arg: str, toml_file: str = 'config.toml' ) -> LLMConfig | None: """Get a group of llm settings from the config file. @@ -246,127 +246,127 @@ def get_llm_config_arg( LLMConfig: The LLMConfig object with the settings from the config file. """ # keep only the name, just in case - llm_config_arg = llm_config_arg.strip("[]") + llm_config_arg = llm_config_arg.strip('[]') # truncate the prefix, just in case - if llm_config_arg.startswith("llm."): + if llm_config_arg.startswith('llm.'): llm_config_arg = llm_config_arg[4:] - logger.openhands_logger.debug(f"Loading llm config from {llm_config_arg}") + logger.openhands_logger.debug(f'Loading llm config from {llm_config_arg}') # load the toml file try: - with open(toml_file, "r", encoding="utf-8") as toml_contents: + with open(toml_file, 'r', encoding='utf-8') as toml_contents: toml_config = toml.load(toml_contents) except FileNotFoundError as e: - logger.openhands_logger.error(f"Config file not found: {e}") + logger.openhands_logger.error(f'Config file not found: {e}') return None except toml.TomlDecodeError as e: logger.openhands_logger.error( - f"Cannot parse llm group from {llm_config_arg}. Exception: {e}" + f'Cannot parse llm group from {llm_config_arg}. Exception: {e}' ) return None # update the llm config with the specified section - if "llm" in toml_config and llm_config_arg in toml_config["llm"]: - return LLMConfig.from_dict(toml_config["llm"][llm_config_arg]) - logger.openhands_logger.debug(f"Loading from toml failed for {llm_config_arg}") + if 'llm' in toml_config and llm_config_arg in toml_config['llm']: + return LLMConfig.from_dict(toml_config['llm'][llm_config_arg]) + logger.openhands_logger.debug(f'Loading from toml failed for {llm_config_arg}') return None # Command line arguments def get_parser() -> argparse.ArgumentParser: """Get the parser for the command line arguments.""" - parser = argparse.ArgumentParser(description="Run an agent with a specific task") + parser = argparse.ArgumentParser(description='Run an agent with a specific task') parser.add_argument( - "--config-file", + '--config-file', type=str, - default="config.toml", - help="Path to the config file (default: config.toml in the current directory)", + default='config.toml', + help='Path to the config file (default: config.toml in the current directory)', ) parser.add_argument( - "-d", - "--directory", + '-d', + '--directory', type=str, - help="The working directory for the agent", + help='The working directory for the agent', ) parser.add_argument( - "-t", - "--task", + '-t', + '--task', type=str, - default="", - help="The task for the agent to perform", + default='', + help='The task for the agent to perform', ) parser.add_argument( - "-f", - "--file", + '-f', + '--file', type=str, - help="Path to a file containing the task. Overrides -t if both are provided.", + help='Path to a file containing the task. Overrides -t if both are provided.', ) parser.add_argument( - "-c", - "--agent-cls", + '-c', + '--agent-cls', default=OH_DEFAULT_AGENT, type=str, - help="Name of the default agent to use", + help='Name of the default agent to use', ) parser.add_argument( - "-i", - "--max-iterations", + '-i', + '--max-iterations', default=OH_MAX_ITERATIONS, type=int, - help="The maximum number of iterations to run the agent", + help='The maximum number of iterations to run the agent', ) parser.add_argument( - "-b", - "--max-budget-per-task", + '-b', + '--max-budget-per-task', type=float, - help="The maximum budget allowed per task, beyond which the agent will stop.", + help='The maximum budget allowed per task, beyond which the agent will stop.', ) # --eval configs are for evaluations only parser.add_argument( - "--eval-output-dir", - default="evaluation/evaluation_outputs/outputs", + '--eval-output-dir', + default='evaluation/evaluation_outputs/outputs', type=str, - help="The directory to save evaluation output", + help='The directory to save evaluation output', ) parser.add_argument( - "--eval-n-limit", + '--eval-n-limit', default=None, type=int, - help="The number of instances to evaluate", + help='The number of instances to evaluate', ) parser.add_argument( - "--eval-num-workers", + '--eval-num-workers', default=4, type=int, - help="The number of workers to use for evaluation", + help='The number of workers to use for evaluation', ) parser.add_argument( - "--eval-note", + '--eval-note', default=None, type=str, - help="The note to add to the evaluation directory", + help='The note to add to the evaluation directory', ) parser.add_argument( - "-l", - "--llm-config", + '-l', + '--llm-config', default=None, type=str, help='Replace default LLM ([llm] section in config.toml) config with the specified LLM config, e.g. "llama3" for [llm.llama3] section in config.toml', ) parser.add_argument( - "-n", - "--name", - default="default", + '-n', + '--name', + default='default', type=str, - help="Name for the session", + help='Name for the session', ) parser.add_argument( - "--eval-ids", + '--eval-ids', default=None, type=str, - help="The comma-separated list (in quotes) of IDs of the instances to evaluate", + help='The comma-separated list (in quotes) of IDs of the instances to evaluate', ) return parser @@ -379,7 +379,7 @@ def parse_arguments() -> argparse.Namespace: def load_app_config( - set_logging_levels: bool = True, config_file: str = "config.toml" + set_logging_levels: bool = True, config_file: str = 'config.toml' ) -> AppConfig: """Load the configuration from the specified config file and environment variables. diff --git a/openhands/core/const/guide_url.py b/openhands/core/const/guide_url.py index 031fa92dc48e..c401de8bb6a1 100644 --- a/openhands/core/const/guide_url.py +++ b/openhands/core/const/guide_url.py @@ -1 +1 @@ -TROUBLESHOOTING_URL = "https://docs.all-hands.dev/modules/usage/troubleshooting" +TROUBLESHOOTING_URL = 'https://docs.all-hands.dev/modules/usage/troubleshooting' diff --git a/openhands/core/logger.py b/openhands/core/logger.py index b6968688a459..20a4a4d6581a 100644 --- a/openhands/core/logger.py +++ b/openhands/core/logger.py @@ -114,14 +114,18 @@ def print_lines(self): self.replace_current_line(line) def move_back(self, amount=-1): - """'\033[F' moves the cursor up one line.""" + """ + '\033[F' moves the cursor up one line. + """ if amount == -1: amount = self.max_lines self._write('\033[F' * (self.max_lines)) self._flush() def replace_current_line(self, line=''): - """'\033[2K\r' clears the line and moves the cursor to the beginning of the line.""" + """ + '\033[2K\r' clears the line and moves the cursor to the beginning of the line. + """ self._write('\033[2K' + line + '\n') self._flush() diff --git a/openhands/core/loop.py b/openhands/core/loop.py index 26fda9d0e3f8..2a2808dd0980 100644 --- a/openhands/core/loop.py +++ b/openhands/core/loop.py @@ -11,7 +11,8 @@ async def run_agent_until_done( runtime: Runtime, end_states: list[AgentState], ): - """run_agent_until_done takes a controller and a runtime, and will run + """ + run_agent_until_done takes a controller and a runtime, and will run the agent until it reaches a terminal state. Note that runtime must be connected before being passed in here. """ diff --git a/openhands/core/main.py b/openhands/core/main.py index 4b3bce90ce62..94ee0cf3b20c 100644 --- a/openhands/core/main.py +++ b/openhands/core/main.py @@ -54,11 +54,14 @@ def read_task_from_stdin() -> str: def create_runtime( config: AppConfig, sid: str | None = None, + headless_mode: bool = True, ) -> Runtime: """Create a runtime for the agent to run on. config: The app config. sid: The session id. + headless_mode: Whether the agent is run in headless mode. `create_runtime` is typically called within evaluation scripts, + where we don't want to have the VSCode UI open, so it defaults to True. """ # if sid is provided on the command line, use it as the name of the event stream # otherwise generate it on the basis of the configured jwt_secret @@ -80,6 +83,7 @@ def create_runtime( event_stream=event_stream, sid=session_id, plugins=agent_cls.sandbox_plugins, + headless_mode=headless_mode, ) return runtime @@ -122,7 +126,7 @@ async def run_controller( sid = sid or generate_sid(config) if runtime is None: - runtime = create_runtime(config, sid=sid) + runtime = create_runtime(config, sid=sid, headless_mode=headless_mode) await runtime.connect() event_stream = runtime.event_stream diff --git a/openhands/core/schema/__init__.py b/openhands/core/schema/__init__.py index 47c1eb93e008..370bf022f8ff 100644 --- a/openhands/core/schema/__init__.py +++ b/openhands/core/schema/__init__.py @@ -4,8 +4,8 @@ from openhands.core.schema.observation import ObservationType __all__ = [ - "ActionType", - "ObservationType", - "ConfigType", - "AgentState", + 'ActionType', + 'ObservationType', + 'ConfigType', + 'AgentState', ] diff --git a/openhands/core/schema/action.py b/openhands/core/schema/action.py index 646d29cac4e4..dc4cfe542e0a 100644 --- a/openhands/core/schema/action.py +++ b/openhands/core/schema/action.py @@ -1,89 +1,89 @@ from pydantic import BaseModel, Field -__all__ = ["ActionType"] +__all__ = ['ActionType'] class ActionTypeSchema(BaseModel): - INIT: str = Field(default="initialize") + INIT: str = Field(default='initialize') """Initializes the agent. Only sent by client. """ - MESSAGE: str = Field(default="message") + MESSAGE: str = Field(default='message') """Represents a message. """ - START: str = Field(default="start") + START: str = Field(default='start') """Starts a new development task OR send chat from the user. Only sent by the client. """ - READ: str = Field(default="read") + READ: str = Field(default='read') """Reads the content of a file. """ - WRITE: str = Field(default="write") + WRITE: str = Field(default='write') """Writes the content to a file. """ - EDIT: str = Field(default="edit") + EDIT: str = Field(default='edit') """Edits a file by providing a draft. """ - RUN: str = Field(default="run") + RUN: str = Field(default='run') """Runs a command. """ - RUN_IPYTHON: str = Field(default="run_ipython") + RUN_IPYTHON: str = Field(default='run_ipython') """Runs a IPython cell. """ - BROWSE: str = Field(default="browse") + BROWSE: str = Field(default='browse') """Opens a web page. """ - BROWSE_INTERACTIVE: str = Field(default="browse_interactive") + BROWSE_INTERACTIVE: str = Field(default='browse_interactive') """Interact with the browser instance. """ - DELEGATE: str = Field(default="delegate") + DELEGATE: str = Field(default='delegate') """Delegates a task to another agent. """ - FINISH: str = Field(default="finish") + FINISH: str = Field(default='finish') """If you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working. """ - REJECT: str = Field(default="reject") + REJECT: str = Field(default='reject') """If you're absolutely certain that you cannot complete the task with given requirements, use the reject action to stop working. """ - NULL: str = Field(default="null") + NULL: str = Field(default='null') - SUMMARIZE: str = Field(default="summarize") + SUMMARIZE: str = Field(default='summarize') - ADD_TASK: str = Field(default="add_task") + ADD_TASK: str = Field(default='add_task') - MODIFY_TASK: str = Field(default="modify_task") + MODIFY_TASK: str = Field(default='modify_task') - PAUSE: str = Field(default="pause") + PAUSE: str = Field(default='pause') """Pauses the task. """ - RESUME: str = Field(default="resume") + RESUME: str = Field(default='resume') """Resumes the task. """ - STOP: str = Field(default="stop") + STOP: str = Field(default='stop') """Stops the task. Must send a start action to restart a new task. """ - CHANGE_AGENT_STATE: str = Field(default="change_agent_state") + CHANGE_AGENT_STATE: str = Field(default='change_agent_state') - PUSH: str = Field(default="push") + PUSH: str = Field(default='push') """Push a branch to github.""" - SEND_PR: str = Field(default="send_pr") + SEND_PR: str = Field(default='send_pr') """Send a PR to github.""" diff --git a/openhands/core/schema/agent.py b/openhands/core/schema/agent.py index 19eb6975403a..4ea09d7afc2a 100644 --- a/openhands/core/schema/agent.py +++ b/openhands/core/schema/agent.py @@ -2,50 +2,50 @@ class AgentState(str, Enum): - LOADING = "loading" + LOADING = 'loading' """The agent is loading. """ - INIT = "init" + INIT = 'init' """The agent is initialized. """ - RUNNING = "running" + RUNNING = 'running' """The agent is running. """ - AWAITING_USER_INPUT = "awaiting_user_input" + AWAITING_USER_INPUT = 'awaiting_user_input' """The agent is awaiting user input. """ - PAUSED = "paused" + PAUSED = 'paused' """The agent is paused. """ - STOPPED = "stopped" + STOPPED = 'stopped' """The agent is stopped. """ - FINISHED = "finished" + FINISHED = 'finished' """The agent is finished with the current task. """ - REJECTED = "rejected" + REJECTED = 'rejected' """The agent rejects the task. """ - ERROR = "error" + ERROR = 'error' """An error occurred during the task. """ - AWAITING_USER_CONFIRMATION = "awaiting_user_confirmation" + AWAITING_USER_CONFIRMATION = 'awaiting_user_confirmation' """The agent is awaiting user confirmation. """ - USER_CONFIRMED = "user_confirmed" + USER_CONFIRMED = 'user_confirmed' """The user confirmed the agent's action. """ - USER_REJECTED = "user_rejected" + USER_REJECTED = 'user_rejected' """The user rejected the agent's action. """ diff --git a/openhands/core/schema/config.py b/openhands/core/schema/config.py index c58f315b35f6..1272ebe655a5 100644 --- a/openhands/core/schema/config.py +++ b/openhands/core/schema/config.py @@ -3,47 +3,47 @@ class ConfigType(str, Enum): # For frontend - AGENT = "AGENT" - AGENT_MEMORY_ENABLED = "AGENT_MEMORY_ENABLED" - AGENT_MEMORY_MAX_THREADS = "AGENT_MEMORY_MAX_THREADS" - AWS_ACCESS_KEY_ID = "AWS_ACCESS_KEY_ID" - AWS_REGION_NAME = "AWS_REGION_NAME" - AWS_SECRET_ACCESS_KEY = "AWS_SECRET_ACCESS_KEY" - BASE_CONTAINER_IMAGE = "BASE_CONTAINER_IMAGE" - CACHE_DIR = "CACHE_DIR" - CONFIRMATION_MODE = "CONFIRMATION_MODE" - DEBUG = "DEBUG" - DISABLE_COLOR = "DISABLE_COLOR" - E2B_API_KEY = "E2B_API_KEY" - FILE_UPLOADS_ALLOWED_EXTENSIONS = "FILE_UPLOADS_ALLOWED_EXTENSIONS" - FILE_UPLOADS_MAX_FILE_SIZE_MB = "FILE_UPLOADS_MAX_FILE_SIZE_MB" - FILE_UPLOADS_RESTRICT_FILE_TYPES = "FILE_UPLOADS_RESTRICT_FILE_TYPES" - LLM_API_KEY = "LLM_API_KEY" - LLM_API_VERSION = "LLM_API_VERSION" - LLM_BASE_URL = "LLM_BASE_URL" - LLM_CACHING_PROMPT = "LLM_CACHING_PROMPT" - LLM_CUSTOM_LLM_PROVIDER = "LLM_CUSTOM_LLM_PROVIDER" - LLM_DROP_PARAMS = "LLM_DROP_PARAMS" - LLM_EMBEDDING_BASE_URL = "LLM_EMBEDDING_BASE_URL" - LLM_EMBEDDING_DEPLOYMENT_NAME = "LLM_EMBEDDING_DEPLOYMENT_NAME" - LLM_EMBEDDING_MODEL = "LLM_EMBEDDING_MODEL" - LLM_MAX_INPUT_TOKENS = "LLM_MAX_INPUT_TOKENS" - LLM_MAX_OUTPUT_TOKENS = "LLM_MAX_OUTPUT_TOKENS" - LLM_MODEL = "LLM_MODEL" - LLM_NUM_RETRIES = "LLM_NUM_RETRIES" - LLM_RETRY_MAX_WAIT = "LLM_RETRY_MAX_WAIT" - LLM_RETRY_MIN_WAIT = "LLM_RETRY_MIN_WAIT" - LLM_TEMPERATURE = "LLM_TEMPERATURE" - LLM_TIMEOUT = "LLM_TIMEOUT" - LLM_TOP_P = "LLM_TOP_P" - LLM_DISABLE_VISION = "LLM_DISABLE_VISION" - MAX_ITERATIONS = "MAX_ITERATIONS" - RUN_AS_OPENHANDS = "RUN_AS_OPENHANDS" - SANDBOX_TIMEOUT = "SANDBOX_TIMEOUT" - SANDBOX_USER_ID = "SANDBOX_USER_ID" - SECURITY_ANALYZER = "SECURITY_ANALYZER" - USE_HOST_NETWORK = "USE_HOST_NETWORK" - WORKSPACE_BASE = "WORKSPACE_BASE" - WORKSPACE_MOUNT_PATH = "WORKSPACE_MOUNT_PATH" - WORKSPACE_MOUNT_PATH_IN_SANDBOX = "WORKSPACE_MOUNT_PATH_IN_SANDBOX" - WORKSPACE_MOUNT_REWRITE = "WORKSPACE_MOUNT_REWRITE" + AGENT = 'AGENT' + AGENT_MEMORY_ENABLED = 'AGENT_MEMORY_ENABLED' + AGENT_MEMORY_MAX_THREADS = 'AGENT_MEMORY_MAX_THREADS' + AWS_ACCESS_KEY_ID = 'AWS_ACCESS_KEY_ID' + AWS_REGION_NAME = 'AWS_REGION_NAME' + AWS_SECRET_ACCESS_KEY = 'AWS_SECRET_ACCESS_KEY' + BASE_CONTAINER_IMAGE = 'BASE_CONTAINER_IMAGE' + CACHE_DIR = 'CACHE_DIR' + CONFIRMATION_MODE = 'CONFIRMATION_MODE' + DEBUG = 'DEBUG' + DISABLE_COLOR = 'DISABLE_COLOR' + E2B_API_KEY = 'E2B_API_KEY' + FILE_UPLOADS_ALLOWED_EXTENSIONS = 'FILE_UPLOADS_ALLOWED_EXTENSIONS' + FILE_UPLOADS_MAX_FILE_SIZE_MB = 'FILE_UPLOADS_MAX_FILE_SIZE_MB' + FILE_UPLOADS_RESTRICT_FILE_TYPES = 'FILE_UPLOADS_RESTRICT_FILE_TYPES' + LLM_API_KEY = 'LLM_API_KEY' + LLM_API_VERSION = 'LLM_API_VERSION' + LLM_BASE_URL = 'LLM_BASE_URL' + LLM_CACHING_PROMPT = 'LLM_CACHING_PROMPT' + LLM_CUSTOM_LLM_PROVIDER = 'LLM_CUSTOM_LLM_PROVIDER' + LLM_DROP_PARAMS = 'LLM_DROP_PARAMS' + LLM_EMBEDDING_BASE_URL = 'LLM_EMBEDDING_BASE_URL' + LLM_EMBEDDING_DEPLOYMENT_NAME = 'LLM_EMBEDDING_DEPLOYMENT_NAME' + LLM_EMBEDDING_MODEL = 'LLM_EMBEDDING_MODEL' + LLM_MAX_INPUT_TOKENS = 'LLM_MAX_INPUT_TOKENS' + LLM_MAX_OUTPUT_TOKENS = 'LLM_MAX_OUTPUT_TOKENS' + LLM_MODEL = 'LLM_MODEL' + LLM_NUM_RETRIES = 'LLM_NUM_RETRIES' + LLM_RETRY_MAX_WAIT = 'LLM_RETRY_MAX_WAIT' + LLM_RETRY_MIN_WAIT = 'LLM_RETRY_MIN_WAIT' + LLM_TEMPERATURE = 'LLM_TEMPERATURE' + LLM_TIMEOUT = 'LLM_TIMEOUT' + LLM_TOP_P = 'LLM_TOP_P' + LLM_DISABLE_VISION = 'LLM_DISABLE_VISION' + MAX_ITERATIONS = 'MAX_ITERATIONS' + RUN_AS_OPENHANDS = 'RUN_AS_OPENHANDS' + SANDBOX_TIMEOUT = 'SANDBOX_TIMEOUT' + SANDBOX_USER_ID = 'SANDBOX_USER_ID' + SECURITY_ANALYZER = 'SECURITY_ANALYZER' + USE_HOST_NETWORK = 'USE_HOST_NETWORK' + WORKSPACE_BASE = 'WORKSPACE_BASE' + WORKSPACE_MOUNT_PATH = 'WORKSPACE_MOUNT_PATH' + WORKSPACE_MOUNT_PATH_IN_SANDBOX = 'WORKSPACE_MOUNT_PATH_IN_SANDBOX' + WORKSPACE_MOUNT_REWRITE = 'WORKSPACE_MOUNT_REWRITE' diff --git a/openhands/core/schema/observation.py b/openhands/core/schema/observation.py index 232d8b7ee090..622f2680f785 100644 --- a/openhands/core/schema/observation.py +++ b/openhands/core/schema/observation.py @@ -1,48 +1,48 @@ from pydantic import BaseModel, Field -__all__ = ["ObservationType"] +__all__ = ['ObservationType'] class ObservationTypeSchema(BaseModel): - READ: str = Field(default="read") + READ: str = Field(default='read') """The content of a file """ - WRITE: str = Field(default="write") + WRITE: str = Field(default='write') - EDIT: str = Field(default="edit") + EDIT: str = Field(default='edit') - BROWSE: str = Field(default="browse") + BROWSE: str = Field(default='browse') """The HTML content of a URL """ - RUN: str = Field(default="run") + RUN: str = Field(default='run') """The output of a command """ - RUN_IPYTHON: str = Field(default="run_ipython") + RUN_IPYTHON: str = Field(default='run_ipython') """Runs a IPython cell. """ - CHAT: str = Field(default="chat") + CHAT: str = Field(default='chat') """A message from the user """ - DELEGATE: str = Field(default="delegate") + DELEGATE: str = Field(default='delegate') """The result of a task delegated to another agent """ - MESSAGE: str = Field(default="message") + MESSAGE: str = Field(default='message') - ERROR: str = Field(default="error") + ERROR: str = Field(default='error') - SUCCESS: str = Field(default="success") + SUCCESS: str = Field(default='success') - NULL: str = Field(default="null") + NULL: str = Field(default='null') - AGENT_STATE_CHANGED: str = Field(default="agent_state_changed") + AGENT_STATE_CHANGED: str = Field(default='agent_state_changed') - USER_REJECTED: str = Field(default="user_rejected") + USER_REJECTED: str = Field(default='user_rejected') ObservationType = ObservationTypeSchema() diff --git a/openhands/core/utils/json.py b/openhands/core/utils/json.py index ad78bf977f8c..c0b22740bec4 100644 --- a/openhands/core/utils/json.py +++ b/openhands/core/utils/json.py @@ -37,11 +37,11 @@ def loads(json_str, **kwargs): depth = 0 start = -1 for i, char in enumerate(json_str): - if char == "{": + if char == '{': if depth == 0: start = i depth += 1 - elif char == "}": + elif char == '}': depth -= 1 if depth == 0 and start != -1: response = json_str[start : i + 1] @@ -50,6 +50,6 @@ def loads(json_str, **kwargs): return json.loads(json_str, **kwargs) except (json.JSONDecodeError, ValueError, TypeError) as e: raise LLMResponseError( - "Invalid JSON in response. Please make sure the response is a valid JSON object." + 'Invalid JSON in response. Please make sure the response is a valid JSON object.' ) from e - raise LLMResponseError("No valid JSON object found in response.") + raise LLMResponseError('No valid JSON object found in response.') diff --git a/openhands/events/action/__init__.py b/openhands/events/action/__init__.py index e78b15600c31..129cb3073982 100644 --- a/openhands/events/action/__init__.py +++ b/openhands/events/action/__init__.py @@ -18,22 +18,22 @@ from openhands.events.action.tasks import AddTaskAction, ModifyTaskAction __all__ = [ - "Action", - "NullAction", - "CmdRunAction", - "BrowseURLAction", - "BrowseInteractiveAction", - "FileReadAction", - "FileWriteAction", - "FileEditAction", - "AgentFinishAction", - "AgentRejectAction", - "AgentDelegateAction", - "AgentSummarizeAction", - "AddTaskAction", - "ModifyTaskAction", - "ChangeAgentStateAction", - "IPythonRunCellAction", - "MessageAction", - "ActionConfirmationStatus", + 'Action', + 'NullAction', + 'CmdRunAction', + 'BrowseURLAction', + 'BrowseInteractiveAction', + 'FileReadAction', + 'FileWriteAction', + 'FileEditAction', + 'AgentFinishAction', + 'AgentRejectAction', + 'AgentDelegateAction', + 'AgentSummarizeAction', + 'AddTaskAction', + 'ModifyTaskAction', + 'ChangeAgentStateAction', + 'IPythonRunCellAction', + 'MessageAction', + 'ActionConfirmationStatus', ] diff --git a/openhands/events/action/action.py b/openhands/events/action/action.py index e70cf037ce3f..0605af7ed53e 100644 --- a/openhands/events/action/action.py +++ b/openhands/events/action/action.py @@ -6,9 +6,9 @@ class ActionConfirmationStatus(str, Enum): - CONFIRMED = "confirmed" - REJECTED = "rejected" - AWAITING_CONFIRMATION = "awaiting_confirmation" + CONFIRMED = 'confirmed' + REJECTED = 'rejected' + AWAITING_CONFIRMATION = 'awaiting_confirmation' class ActionSecurityRisk(int, Enum): diff --git a/openhands/events/action/agent.py b/openhands/events/action/agent.py index 1e11ec5c67a4..f49f573ed698 100644 --- a/openhands/events/action/agent.py +++ b/openhands/events/action/agent.py @@ -10,12 +10,12 @@ class ChangeAgentStateAction(Action): """Fake action, just to notify the client that a task state has changed.""" agent_state: str - thought: str = "" + thought: str = '' action: str = ActionType.CHANGE_AGENT_STATE @property def message(self) -> str: - return f"Agent state changed to {self.agent_state}" + return f'Agent state changed to {self.agent_state}' @dataclass @@ -28,8 +28,8 @@ def message(self) -> str: return self.summary def __str__(self) -> str: - ret = "**AgentSummarizeAction**\n" - ret += f"SUMMARY: {self.summary}" + ret = '**AgentSummarizeAction**\n' + ret += f'SUMMARY: {self.summary}' return ret @@ -44,12 +44,12 @@ class AgentFinishAction(Action): """ outputs: dict[str, Any] = field(default_factory=dict) - thought: str = "" + thought: str = '' action: str = ActionType.FINISH @property def message(self) -> str: - if self.thought != "": + if self.thought != '': return self.thought return "All done! What's next on the agenda?" @@ -57,14 +57,14 @@ def message(self) -> str: @dataclass class AgentRejectAction(Action): outputs: dict = field(default_factory=dict) - thought: str = "" + thought: str = '' action: str = ActionType.REJECT @property def message(self) -> str: - msg: str = "Task is rejected by the agent." - if "reason" in self.outputs: - msg += " Reason: " + self.outputs["reason"] + msg: str = 'Task is rejected by the agent.' + if 'reason' in self.outputs: + msg += ' Reason: ' + self.outputs['reason'] return msg @@ -72,7 +72,7 @@ def message(self) -> str: class AgentDelegateAction(Action): agent: str inputs: dict - thought: str = "" + thought: str = '' action: str = ActionType.DELEGATE @property diff --git a/openhands/events/action/browse.py b/openhands/events/action/browse.py index d2a9dab7f6ab..41816216d6d5 100644 --- a/openhands/events/action/browse.py +++ b/openhands/events/action/browse.py @@ -8,28 +8,28 @@ @dataclass class BrowseURLAction(Action): url: str - thought: str = "" + thought: str = '' action: str = ActionType.BROWSE runnable: ClassVar[bool] = True security_risk: ActionSecurityRisk | None = None @property def message(self) -> str: - return f"Browsing URL: {self.url}" + return f'Browsing URL: {self.url}' def __str__(self) -> str: - ret = "**BrowseURLAction**\n" + ret = '**BrowseURLAction**\n' if self.thought: - ret += f"THOUGHT: {self.thought}\n" - ret += f"URL: {self.url}" + ret += f'THOUGHT: {self.thought}\n' + ret += f'URL: {self.url}' return ret @dataclass class BrowseInteractiveAction(Action): browser_actions: str - thought: str = "" - browsergym_send_msg_to_user: str = "" + thought: str = '' + browsergym_send_msg_to_user: str = '' action: str = ActionType.BROWSE_INTERACTIVE runnable: ClassVar[bool] = True security_risk: ActionSecurityRisk | None = None @@ -37,12 +37,12 @@ class BrowseInteractiveAction(Action): @property def message(self) -> str: return ( - f"I am interacting with the browser:\n" f"```\n{self.browser_actions}\n```" + f'I am interacting with the browser:\n' f'```\n{self.browser_actions}\n```' ) def __str__(self) -> str: - ret = "**BrowseInteractiveAction**\n" + ret = '**BrowseInteractiveAction**\n' if self.thought: - ret += f"THOUGHT: {self.thought}\n" - ret += f"BROWSER_ACTIONS: {self.browser_actions}" + ret += f'THOUGHT: {self.thought}\n' + ret += f'BROWSER_ACTIONS: {self.browser_actions}' return ret diff --git a/openhands/events/action/commands.py b/openhands/events/action/commands.py index 1989081ebe61..83dd19f9d161 100644 --- a/openhands/events/action/commands.py +++ b/openhands/events/action/commands.py @@ -12,7 +12,7 @@ @dataclass class CmdRunAction(Action): command: str - thought: str = "" + thought: str = '' blocking: bool = False # If False, the command will be run in a non-blocking / interactive way # The partial command outputs will be returned as output observation. @@ -33,20 +33,20 @@ class CmdRunAction(Action): @property def message(self) -> str: - return f"Running command: {self.command}" + return f'Running command: {self.command}' def __str__(self) -> str: - ret = f"**CmdRunAction (source={self.source})**\n" + ret = f'**CmdRunAction (source={self.source})**\n' if self.thought: - ret += f"THOUGHT: {self.thought}\n" - ret += f"COMMAND:\n{self.command}" + ret += f'THOUGHT: {self.thought}\n' + ret += f'COMMAND:\n{self.command}' return ret @dataclass class IPythonRunCellAction(Action): code: str - thought: str = "" + thought: str = '' include_extra: bool = ( True # whether to include CWD & Python interpreter in the output ) @@ -54,15 +54,15 @@ class IPythonRunCellAction(Action): runnable: ClassVar[bool] = True confirmation_state: ActionConfirmationStatus = ActionConfirmationStatus.CONFIRMED security_risk: ActionSecurityRisk | None = None - kernel_init_code: str = "" # code to run in the kernel (if the kernel is restarted) + kernel_init_code: str = '' # code to run in the kernel (if the kernel is restarted) def __str__(self) -> str: - ret = "**IPythonRunCellAction**\n" + ret = '**IPythonRunCellAction**\n' if self.thought: - ret += f"THOUGHT: {self.thought}\n" - ret += f"CODE:\n{self.code}" + ret += f'THOUGHT: {self.thought}\n' + ret += f'CODE:\n{self.code}' return ret @property def message(self) -> str: - return f"Running Python code interactively: {self.code}" + return f'Running Python code interactively: {self.code}' diff --git a/openhands/events/action/empty.py b/openhands/events/action/empty.py index a1b496cd725c..32e034600102 100644 --- a/openhands/events/action/empty.py +++ b/openhands/events/action/empty.py @@ -12,4 +12,4 @@ class NullAction(Action): @property def message(self) -> str: - return "No action" + return 'No action' diff --git a/openhands/events/action/files.py b/openhands/events/action/files.py index d4b3c848e17b..3e2131228b6b 100644 --- a/openhands/events/action/files.py +++ b/openhands/events/action/files.py @@ -15,14 +15,14 @@ class FileReadAction(Action): path: str start: int = 0 end: int = -1 - thought: str = "" + thought: str = '' action: str = ActionType.READ runnable: ClassVar[bool] = True security_risk: ActionSecurityRisk | None = None @property def message(self) -> str: - return f"Reading file: {self.path}" + return f'Reading file: {self.path}' @dataclass @@ -36,14 +36,14 @@ class FileWriteAction(Action): content: str start: int = 0 end: int = -1 - thought: str = "" + thought: str = '' action: str = ActionType.WRITE runnable: ClassVar[bool] = True security_risk: ActionSecurityRisk | None = None @property def message(self) -> str: - return f"Writing file: {self.path}" + return f'Writing file: {self.path}' @dataclass @@ -60,15 +60,15 @@ class FileEditAction(Action): content: str start: int = 1 end: int = -1 - thought: str = "" + thought: str = '' action: str = ActionType.EDIT runnable: ClassVar[bool] = True security_risk: ActionSecurityRisk | None = None def __repr__(self) -> str: - ret = "**FileEditAction**\n" - ret += f"Thought: {self.thought}\n" - ret += f"Range: [L{self.start}:L{self.end}]\n" - ret += f"Path: [{self.path}]\n" - ret += f"Content:\n```\n{self.content}\n```\n" + ret = '**FileEditAction**\n' + ret += f'Thought: {self.thought}\n' + ret += f'Range: [L{self.start}:L{self.end}]\n' + ret += f'Path: [{self.path}]\n' + ret += f'Content:\n```\n{self.content}\n```\n' return ret diff --git a/openhands/events/action/message.py b/openhands/events/action/message.py index c9500004971f..86d7c439e936 100644 --- a/openhands/events/action/message.py +++ b/openhands/events/action/message.py @@ -24,11 +24,10 @@ def images_urls(self): @images_urls.setter def images_urls(self, value): self.image_urls = value - def __str__(self) -> str: - ret = f"**MessageAction** (source={self.source})\n" - ret += f"CONTENT: {self.content}" + ret = f'**MessageAction** (source={self.source})\n' + ret += f'CONTENT: {self.content}' if self.image_urls: for url in self.image_urls: - ret += f"\nIMAGE_URL: {url}" + ret += f'\nIMAGE_URL: {url}' return ret diff --git a/openhands/events/action/tasks.py b/openhands/events/action/tasks.py index 429c24a959d6..b1f1c215f74d 100644 --- a/openhands/events/action/tasks.py +++ b/openhands/events/action/tasks.py @@ -9,21 +9,21 @@ class AddTaskAction(Action): parent: str goal: str subtasks: list = field(default_factory=list) - thought: str = "" + thought: str = '' action: str = ActionType.ADD_TASK @property def message(self) -> str: - return f"Added task: {self.goal}" + return f'Added task: {self.goal}' @dataclass class ModifyTaskAction(Action): task_id: str state: str - thought: str = "" + thought: str = '' action: str = ActionType.MODIFY_TASK @property def message(self) -> str: - return f"Set task {self.task_id} to {self.state}" + return f'Set task {self.task_id} to {self.state}' diff --git a/openhands/events/observation/__init__.py b/openhands/events/observation/__init__.py index 7cd08f5449ee..28525b09aabb 100644 --- a/openhands/events/observation/__init__.py +++ b/openhands/events/observation/__init__.py @@ -17,17 +17,17 @@ from openhands.events.observation.success import SuccessObservation __all__ = [ - "Observation", - "NullObservation", - "CmdOutputObservation", - "IPythonRunCellObservation", - "BrowserOutputObservation", - "FileReadObservation", - "FileWriteObservation", - "FileEditObservation", - "ErrorObservation", - "AgentStateChangedObservation", - "AgentDelegateObservation", - "SuccessObservation", - "UserRejectObservation", + 'Observation', + 'NullObservation', + 'CmdOutputObservation', + 'IPythonRunCellObservation', + 'BrowserOutputObservation', + 'FileReadObservation', + 'FileWriteObservation', + 'FileEditObservation', + 'ErrorObservation', + 'AgentStateChangedObservation', + 'AgentDelegateObservation', + 'SuccessObservation', + 'UserRejectObservation', ] diff --git a/openhands/events/observation/agent.py b/openhands/events/observation/agent.py index 2ad71a4773ca..802c23c3786d 100644 --- a/openhands/events/observation/agent.py +++ b/openhands/events/observation/agent.py @@ -13,4 +13,4 @@ class AgentStateChangedObservation(Observation): @property def message(self) -> str: - return "" + return '' diff --git a/openhands/events/observation/browse.py b/openhands/events/observation/browse.py index b7aa3d1936a2..9632fac57d54 100644 --- a/openhands/events/observation/browse.py +++ b/openhands/events/observation/browse.py @@ -22,43 +22,43 @@ class BrowserOutputObservation(Observation): extra_element_properties: dict = field( default_factory=dict, repr=False ) # don't show in repr - last_browser_action: str = "" - last_browser_action_error: str = "" - focused_element_bid: str = "" + last_browser_action: str = '' + last_browser_action_error: str = '' + focused_element_bid: str = '' @property def message(self) -> str: - return "Visited " + self.url + return 'Visited ' + self.url def __str__(self) -> str: ret = ( - "**BrowserOutputObservation**\n" - f"URL: {self.url}\n" - f"Error: {self.error}\n" - f"Open pages: {self.open_pages_urls}\n" - f"Active page index: {self.active_page_index}\n" - f"Last browser action: {self.last_browser_action}\n" - f"Last browser action error: {self.last_browser_action_error}\n" - f"Focused element bid: {self.focused_element_bid}\n" - f"Content: {self.content}\n" + '**BrowserOutputObservation**\n' + f'URL: {self.url}\n' + f'Error: {self.error}\n' + f'Open pages: {self.open_pages_urls}\n' + f'Active page index: {self.active_page_index}\n' + f'Last browser action: {self.last_browser_action}\n' + f'Last browser action error: {self.last_browser_action_error}\n' + f'Focused element bid: {self.focused_element_bid}\n' + f'Content: {self.content}\n' ) - ret += "--- Agent Observation ---\n" + ret += '--- Agent Observation ---\n' ret += self.get_agent_obs_text() return ret def get_agent_obs_text(self) -> str: """Get a concise text that will be shown to the agent.""" - text = f"[Current URL: {self.url}]\n" - text += f"[Focused element bid: {self.focused_element_bid}]\n\n" + text = f'[Current URL: {self.url}]\n' + text += f'[Focused element bid: {self.focused_element_bid}]\n\n' if self.error: text += ( - "================ BEGIN error message ===============\n" - "The following error occurred when executing the last action:\n" - f"{self.last_browser_action_error}\n" - "================ END error message ===============\n" + '================ BEGIN error message ===============\n' + 'The following error occurred when executing the last action:\n' + f'{self.last_browser_action_error}\n' + '================ END error message ===============\n' ) else: - text += "[Action executed successfully.]\n" + text += '[Action executed successfully.]\n' try: # We do not filter visible only here because we want to show the full content @@ -66,12 +66,12 @@ def get_agent_obs_text(self) -> str: # FIXME: handle the case when the web page is too large cur_axtree_txt = self.get_axtree_str(filter_visible_only=False) text += ( - f"============== BEGIN accessibility tree ==============\n" - f"{cur_axtree_txt}\n" - f"============== END accessibility tree ==============\n" + f'============== BEGIN accessibility tree ==============\n' + f'{cur_axtree_txt}\n' + f'============== END accessibility tree ==============\n' ) except Exception as e: - text += f"\n[Error encountered when processing the accessibility tree: {e}]" + text += f'\n[Error encountered when processing the accessibility tree: {e}]' return text def get_axtree_str(self, filter_visible_only: bool = False) -> str: diff --git a/openhands/events/observation/commands.py b/openhands/events/observation/commands.py index c1b76b247cfa..a182168e694a 100644 --- a/openhands/events/observation/commands.py +++ b/openhands/events/observation/commands.py @@ -13,7 +13,7 @@ class CmdOutputObservation(Observation): exit_code: int = 0 hidden: bool = False observation: str = ObservationType.RUN - interpreter_details: str = "" + interpreter_details: str = '' @property def error(self) -> bool: @@ -21,10 +21,10 @@ def error(self) -> bool: @property def message(self) -> str: - return f"Command `{self.command}` executed with exit code {self.exit_code}." + return f'Command `{self.command}` executed with exit code {self.exit_code}.' def __str__(self) -> str: - return f"**CmdOutputObservation (source={self.source}, exit code={self.exit_code})**\n{self.content}" + return f'**CmdOutputObservation (source={self.source}, exit code={self.exit_code})**\n{self.content}' @dataclass @@ -40,7 +40,7 @@ def error(self) -> bool: @property def message(self) -> str: - return "Code executed in IPython cell." + return 'Code executed in IPython cell.' def __str__(self) -> str: - return f"**IPythonRunCellObservation**\n{self.content}" + return f'**IPythonRunCellObservation**\n{self.content}' diff --git a/openhands/events/observation/delegate.py b/openhands/events/observation/delegate.py index 95e05b5ff3ff..9e98c6b5982a 100644 --- a/openhands/events/observation/delegate.py +++ b/openhands/events/observation/delegate.py @@ -19,4 +19,4 @@ class AgentDelegateObservation(Observation): @property def message(self) -> str: - return "" + return '' diff --git a/openhands/events/observation/empty.py b/openhands/events/observation/empty.py index 5cc802804d22..9d7d0f18a792 100644 --- a/openhands/events/observation/empty.py +++ b/openhands/events/observation/empty.py @@ -14,4 +14,4 @@ class NullObservation(Observation): @property def message(self) -> str: - return "No observation" + return 'No observation' diff --git a/openhands/events/observation/error.py b/openhands/events/observation/error.py index d91ac1bf2a1e..4ed05b89ac78 100644 --- a/openhands/events/observation/error.py +++ b/openhands/events/observation/error.py @@ -13,11 +13,11 @@ class ErrorObservation(Observation): """ observation: str = ObservationType.ERROR - error_id: str = "" + error_id: str = '' @property def message(self) -> str: return self.content def __str__(self) -> str: - return f"**ErrorObservation**\n{self.content}" + return f'**ErrorObservation**\n{self.content}' diff --git a/openhands/events/observation/files.py b/openhands/events/observation/files.py index 563c601579cd..bfc45264ccae 100644 --- a/openhands/events/observation/files.py +++ b/openhands/events/observation/files.py @@ -14,7 +14,7 @@ class FileReadObservation(Observation): @property def message(self) -> str: - return f"I read the file {self.path}." + return f'I read the file {self.path}.' @dataclass @@ -26,7 +26,7 @@ class FileWriteObservation(Observation): @property def message(self) -> str: - return f"I wrote to the file {self.path}." + return f'I wrote to the file {self.path}.' @dataclass @@ -42,12 +42,12 @@ class FileEditObservation(Observation): @property def message(self) -> str: - return f"I edited the file {self.path}." + return f'I edited the file {self.path}.' def get_edit_groups(self, n_context_lines: int = 2) -> list[dict[str, list[str]]]: """Get the edit groups of the file edit.""" - old_lines = self.old_content.split("\n") - new_lines = self.new_content.split("\n") + old_lines = self.old_content.split('\n') + new_lines = self.new_content.split('\n') # Borrowed from difflib.unified_diff to directly parse into structured format. edit_groups: list[dict] = [] for group in SequenceMatcher(None, old_lines, new_lines).get_grouped_opcodes( @@ -56,29 +56,29 @@ def get_edit_groups(self, n_context_lines: int = 2) -> list[dict[str, list[str]] # take the max line number in the group _indent_pad_size = len(str(group[-1][3])) + 1 # +1 for the "*" prefix cur_group: dict[str, list[str]] = { - "before_edits": [], - "after_edits": [], + 'before_edits': [], + 'after_edits': [], } for tag, i1, i2, j1, j2 in group: - if tag == "equal": + if tag == 'equal': for idx, line in enumerate(old_lines[i1:i2]): - cur_group["before_edits"].append( - f"{i1+idx+1:>{_indent_pad_size}}|{line}" + cur_group['before_edits'].append( + f'{i1+idx+1:>{_indent_pad_size}}|{line}' ) for idx, line in enumerate(new_lines[j1:j2]): - cur_group["after_edits"].append( - f"{j1+idx+1:>{_indent_pad_size}}|{line}" + cur_group['after_edits'].append( + f'{j1+idx+1:>{_indent_pad_size}}|{line}' ) continue - if tag in {"replace", "delete"}: + if tag in {'replace', 'delete'}: for idx, line in enumerate(old_lines[i1:i2]): - cur_group["before_edits"].append( - f"-{i1+idx+1:>{_indent_pad_size-1}}|{line}" + cur_group['before_edits'].append( + f'-{i1+idx+1:>{_indent_pad_size-1}}|{line}' ) - if tag in {"replace", "insert"}: + if tag in {'replace', 'insert'}: for idx, line in enumerate(new_lines[j1:j2]): - cur_group["after_edits"].append( - f"+{j1+idx+1:>{_indent_pad_size-1}}|{line}" + cur_group['after_edits'].append( + f'+{j1+idx+1:>{_indent_pad_size-1}}|{line}' ) edit_groups.append(cur_group) return edit_groups @@ -97,37 +97,37 @@ def visualize_diff( n_context_lines: The number of lines of context to show before and after the changes. change_applied: Whether the changes are applied to the file. If true, the file have been modified. If not, the file is not modified (due to linting errors). """ - if change_applied and self.content.strip() == "": + if change_applied and self.content.strip() == '': # diff patch is empty - return "(no changes detected. Please make sure your edits changes the content of the existing file.)\n" + return '(no changes detected. Please make sure your edits changes the content of the existing file.)\n' edit_groups = self.get_edit_groups(n_context_lines=n_context_lines) result = [ - f"[Existing file {self.path} is edited with {len(edit_groups)} changes.]" + f'[Existing file {self.path} is edited with {len(edit_groups)} changes.]' if change_applied else f"[Changes are NOT applied to {self.path} - Here's how the file looks like if changes are applied.]" ] - op_type = "edit" if change_applied else "ATTEMPTED edit" + op_type = 'edit' if change_applied else 'ATTEMPTED edit' for i, cur_edit_group in enumerate(edit_groups): if i != 0: - result.append("-------------------------") - result.append(f"[begin of {op_type} {i+1} / {len(edit_groups)}]") - result.append(f"(content before {op_type})") - result.extend(cur_edit_group["before_edits"]) - result.append(f"(content after {op_type})") - result.extend(cur_edit_group["after_edits"]) - result.append(f"[end of {op_type} {i+1} / {len(edit_groups)}]") - return "\n".join(result) + result.append('-------------------------') + result.append(f'[begin of {op_type} {i+1} / {len(edit_groups)}]') + result.append(f'(content before {op_type})') + result.extend(cur_edit_group['before_edits']) + result.append(f'(content after {op_type})') + result.extend(cur_edit_group['after_edits']) + result.append(f'[end of {op_type} {i+1} / {len(edit_groups)}]') + return '\n'.join(result) def __str__(self) -> str: - ret = "" + ret = '' if not self.prev_exist: assert ( - self.old_content == "" - ), "old_content should be empty if the file is new (prev_exist=False)." - ret += f"[New file {self.path} is created with the provided content.]\n" - return ret.rstrip() + "\n" + self.old_content == '' + ), 'old_content should be empty if the file is new (prev_exist=False).' + ret += f'[New file {self.path} is created with the provided content.]\n' + return ret.rstrip() + '\n' ret += self.visualize_diff() - return ret.rstrip() + "\n" + return ret.rstrip() + '\n' diff --git a/openhands/events/serialization/__init__.py b/openhands/events/serialization/__init__.py index 1e70dbe8f6c1..f36d08d86cf0 100644 --- a/openhands/events/serialization/__init__.py +++ b/openhands/events/serialization/__init__.py @@ -12,10 +12,10 @@ ) __all__ = [ - "action_from_dict", - "event_from_dict", - "event_to_dict", - "event_to_memory", - "event_to_trajectory", - "observation_from_dict", + 'action_from_dict', + 'event_from_dict', + 'event_to_dict', + 'event_to_memory', + 'event_to_trajectory', + 'observation_from_dict', ] diff --git a/openhands/events/serialization/action.py b/openhands/events/serialization/action.py index 4fc92f9d7d4e..defac3b5dda6 100644 --- a/openhands/events/serialization/action.py +++ b/openhands/events/serialization/action.py @@ -43,37 +43,37 @@ def action_from_dict(action: dict) -> Action: if not isinstance(action, dict): - raise LLMMalformedActionError("action must be a dictionary") + raise LLMMalformedActionError('action must be a dictionary') action = action.copy() - if "action" not in action: + if 'action' not in action: raise LLMMalformedActionError(f"'action' key is not found in {action=}") - if not isinstance(action["action"], str): + if not isinstance(action['action'], str): raise LLMMalformedActionError( f"'{action['action']=}' is not defined. Available actions: {ACTION_TYPE_TO_CLASS.keys()}" ) - action_class = ACTION_TYPE_TO_CLASS.get(action["action"]) + action_class = ACTION_TYPE_TO_CLASS.get(action['action']) if action_class is None: raise LLMMalformedActionError( f"'{action['action']=}' is not defined. Available actions: {ACTION_TYPE_TO_CLASS.keys()}" ) - args = action.get("args", {}) + args = action.get('args', {}) # Remove timestamp from args if present - timestamp = args.pop("timestamp", None) + timestamp = args.pop('timestamp', None) # compatibility for older event streams # is_confirmed has been renamed to confirmation_state - is_confirmed = args.pop("is_confirmed", None) + is_confirmed = args.pop('is_confirmed', None) if is_confirmed is not None: - args["confirmation_state"] = is_confirmed + args['confirmation_state'] = is_confirmed # images_urls has been renamed to image_urls - if "images_urls" in args: - args["image_urls"] = args.pop("images_urls") - + if 'images_urls' in args: + args['image_urls'] = args.pop('images_urls') + try: decoded_action = action_class(**args) - if "timeout" in action: - decoded_action.timeout = action["timeout"] + if 'timeout' in action: + decoded_action.timeout = action['timeout'] # Set timestamp if it was provided if timestamp: @@ -81,6 +81,6 @@ def action_from_dict(action: dict) -> Action: except TypeError as e: raise LLMMalformedActionError( - f"action={action} has the wrong arguments: {str(e)}" + f'action={action} has the wrong arguments: {str(e)}' ) return decoded_action diff --git a/openhands/events/serialization/event.py b/openhands/events/serialization/event.py index f381eda8aef2..78f7940626d4 100644 --- a/openhands/events/serialization/event.py +++ b/openhands/events/serialization/event.py @@ -10,109 +10,109 @@ # TODO: move `content` into `extras` TOP_KEYS = [ - "id", - "timestamp", - "source", - "message", - "cause", - "action", - "observation", - "tool_call_metadata", + 'id', + 'timestamp', + 'source', + 'message', + 'cause', + 'action', + 'observation', + 'tool_call_metadata', ] -UNDERSCORE_KEYS = ["id", "timestamp", "source", "cause", "tool_call_metadata"] +UNDERSCORE_KEYS = ['id', 'timestamp', 'source', 'cause', 'tool_call_metadata'] DELETE_FROM_TRAJECTORY_EXTRAS = { - "screenshot", - "dom_object", - "axtree_object", - "active_page_index", - "last_browser_action", - "last_browser_action_error", - "focused_element_bid", - "extra_element_properties", + 'screenshot', + 'dom_object', + 'axtree_object', + 'active_page_index', + 'last_browser_action', + 'last_browser_action_error', + 'focused_element_bid', + 'extra_element_properties', } -DELETE_FROM_MEMORY_EXTRAS = DELETE_FROM_TRAJECTORY_EXTRAS | {"open_pages_urls"} +DELETE_FROM_MEMORY_EXTRAS = DELETE_FROM_TRAJECTORY_EXTRAS | {'open_pages_urls'} -def event_from_dict(data) -> "Event": +def event_from_dict(data) -> 'Event': evt: Event - if "action" in data: + if 'action' in data: evt = action_from_dict(data) - elif "observation" in data: + elif 'observation' in data: evt = observation_from_dict(data) else: - raise ValueError("Unknown event type: " + data) + raise ValueError('Unknown event type: ' + data) for key in UNDERSCORE_KEYS: if key in data: value = data[key] - if key == "timestamp" and isinstance(value, datetime): + if key == 'timestamp' and isinstance(value, datetime): value = value.isoformat() - if key == "source": + if key == 'source': value = EventSource(value) - if key == "tool_call_metadata": + if key == 'tool_call_metadata': value = ToolCallMetadata(**value) - setattr(evt, "_" + key, value) + setattr(evt, '_' + key, value) return evt -def event_to_dict(event: "Event") -> dict: +def event_to_dict(event: 'Event') -> dict: props = asdict(event) d = {} for key in TOP_KEYS: if hasattr(event, key) and getattr(event, key) is not None: d[key] = getattr(event, key) - elif hasattr(event, f"_{key}") and getattr(event, f"_{key}") is not None: - d[key] = getattr(event, f"_{key}") - if key == "id" and d.get("id") == -1: - d.pop("id", None) - if key == "timestamp" and "timestamp" in d: - if isinstance(d["timestamp"], datetime): - d["timestamp"] = d["timestamp"].isoformat() - if key == "source" and "source" in d: - d["source"] = d["source"].value - if key == "tool_call_metadata" and "tool_call_metadata" in d: - d["tool_call_metadata"] = d["tool_call_metadata"].model_dump() + elif hasattr(event, f'_{key}') and getattr(event, f'_{key}') is not None: + d[key] = getattr(event, f'_{key}') + if key == 'id' and d.get('id') == -1: + d.pop('id', None) + if key == 'timestamp' and 'timestamp' in d: + if isinstance(d['timestamp'], datetime): + d['timestamp'] = d['timestamp'].isoformat() + if key == 'source' and 'source' in d: + d['source'] = d['source'].value + if key == 'tool_call_metadata' and 'tool_call_metadata' in d: + d['tool_call_metadata'] = d['tool_call_metadata'].model_dump() props.pop(key, None) - if "security_risk" in props and props["security_risk"] is None: - props.pop("security_risk") - if "action" in d: - d["args"] = props + if 'security_risk' in props and props['security_risk'] is None: + props.pop('security_risk') + if 'action' in d: + d['args'] = props if event.timeout is not None: - d["timeout"] = event.timeout - elif "observation" in d: - d["content"] = props.pop("content", "") - d["extras"] = props + d['timeout'] = event.timeout + elif 'observation' in d: + d['content'] = props.pop('content', '') + d['extras'] = props else: - raise ValueError("Event must be either action or observation") + raise ValueError('Event must be either action or observation') return d -def event_to_trajectory(event: "Event") -> dict: +def event_to_trajectory(event: 'Event') -> dict: d = event_to_dict(event) - if "extras" in d: - remove_fields(d["extras"], DELETE_FROM_TRAJECTORY_EXTRAS) + if 'extras' in d: + remove_fields(d['extras'], DELETE_FROM_TRAJECTORY_EXTRAS) return d -def event_to_memory(event: "Event", max_message_chars: int) -> dict: +def event_to_memory(event: 'Event', max_message_chars: int) -> dict: d = event_to_dict(event) - d.pop("id", None) - d.pop("cause", None) - d.pop("timestamp", None) - d.pop("message", None) - d.pop("image_urls", None) + d.pop('id', None) + d.pop('cause', None) + d.pop('timestamp', None) + d.pop('message', None) + d.pop('image_urls', None) # runnable actions have some extra fields used in the BE/FE, which should not be sent to the LLM - if "args" in d: - d["args"].pop("blocking", None) - d["args"].pop("keep_prompt", None) - d["args"].pop("confirmation_state", None) - - if "extras" in d: - remove_fields(d["extras"], DELETE_FROM_MEMORY_EXTRAS) - if isinstance(event, Observation) and "content" in d: - d["content"] = truncate_content(d["content"], max_message_chars) + if 'args' in d: + d['args'].pop('blocking', None) + d['args'].pop('keep_prompt', None) + d['args'].pop('confirmation_state', None) + + if 'extras' in d: + remove_fields(d['extras'], DELETE_FROM_MEMORY_EXTRAS) + if isinstance(event, Observation) and 'content' in d: + d['content'] = truncate_content(d['content'], max_message_chars) return d @@ -125,6 +125,6 @@ def truncate_content(content: str, max_chars: int) -> str: half = max_chars // 2 return ( content[:half] - + "\n[... Observation truncated due to length ...]\n" + + '\n[... Observation truncated due to length ...]\n' + content[-half:] ) diff --git a/openhands/events/serialization/observation.py b/openhands/events/serialization/observation.py index 18e9ecdba81b..9030ccb1e1dd 100644 --- a/openhands/events/serialization/observation.py +++ b/openhands/events/serialization/observation.py @@ -39,15 +39,15 @@ def observation_from_dict(observation: dict) -> Observation: observation = observation.copy() - if "observation" not in observation: + if 'observation' not in observation: raise KeyError(f"'observation' key is not found in {observation=}") - observation_class = OBSERVATION_TYPE_TO_CLASS.get(observation["observation"]) + observation_class = OBSERVATION_TYPE_TO_CLASS.get(observation['observation']) if observation_class is None: raise KeyError( f"'{observation['observation']=}' is not defined. Available observations: {OBSERVATION_TYPE_TO_CLASS.keys()}" ) - observation.pop("observation") - observation.pop("message", None) - content = observation.pop("content", "") - extras = observation.pop("extras", {}) + observation.pop('observation') + observation.pop('message', None) + content = observation.pop('content', '') + extras = observation.pop('extras', {}) return observation_class(content=content, **extras) diff --git a/openhands/events/serialization/utils.py b/openhands/events/serialization/utils.py index fb0f1303ddf1..de448e01429b 100644 --- a/openhands/events/serialization/utils.py +++ b/openhands/events/serialization/utils.py @@ -14,7 +14,7 @@ def remove_fields(obj, fields: set[str]): elif isinstance(obj, (list, tuple)): for item in obj: remove_fields(item, fields) - elif hasattr(obj, "__dataclass_fields__"): + elif hasattr(obj, '__dataclass_fields__'): raise ValueError( - "Object must not contain dataclass, consider converting to dict first" + 'Object must not contain dataclass, consider converting to dict first' ) diff --git a/openhands/events/stream.py b/openhands/events/stream.py index 465f27405a58..24e95bf98147 100644 --- a/openhands/events/stream.py +++ b/openhands/events/stream.py @@ -9,9 +9,9 @@ from openhands.core.utils import json from openhands.events.event import Event, EventSource from openhands.events.serialization.event import event_from_dict, event_to_dict -from openhands.runtime.utils.shutdown_listener import should_continue from openhands.storage import FileStore from openhands.utils.async_utils import call_sync_from_async +from openhands.utils.shutdown_listener import should_continue class EventStreamSubscriber(str, Enum): @@ -90,7 +90,8 @@ def get_events( filter_out_type: tuple[type[Event], ...] | None = None, filter_hidden=False, ) -> Iterable[Event]: - """Retrieve events from the event stream, optionally filtering out events of a given type + """ + Retrieve events from the event stream, optionally filtering out events of a given type and events marked as hidden. Args: diff --git a/openhands/linter/languages/python.py b/openhands/linter/languages/python.py index fc302146aaa4..9b7e944a2868 100644 --- a/openhands/linter/languages/python.py +++ b/openhands/linter/languages/python.py @@ -7,13 +7,13 @@ def python_compile_lint(fname: str) -> list[LintResult]: try: - with open(fname, "r") as f: + with open(fname, 'r') as f: code = f.read() - compile(code, fname, "exec") # USE TRACEBACK BELOW HERE + compile(code, fname, 'exec') # USE TRACEBACK BELOW HERE return [] except SyntaxError as err: - err_lineno = getattr(err, "end_lineno", err.lineno) - err_offset = getattr(err, "end_offset", err.offset) + err_lineno = getattr(err, 'end_lineno', err.lineno) + err_offset = getattr(err, 'end_offset', err.offset) if err_offset and err_offset < 0: err_offset = err.offset return [ @@ -24,8 +24,8 @@ def python_compile_lint(fname: str) -> list[LintResult]: def flake_lint(filepath: str) -> list[LintResult]: - fatal = "F821,F822,F831,E112,E113,E999,E902" - flake8_cmd = f"flake8 --select={fatal} --isolated {filepath}" + fatal = 'F821,F822,F831,E112,E113,E999,E902' + flake8_cmd = f'flake8 --select={fatal} --isolated {filepath}' try: cmd_outputs = run_cmd(flake8_cmd) @@ -35,17 +35,17 @@ def flake_lint(filepath: str) -> list[LintResult]: if not cmd_outputs: return results for line in cmd_outputs.splitlines(): - parts = line.split(":") + parts = line.split(':') if len(parts) >= 4: _msg = parts[3].strip() if len(parts) > 4: - _msg += ": " + parts[4].strip() + _msg += ': ' + parts[4].strip() try: line_num = int(parts[1]) except ValueError as e: logger.warning( - f"Error parsing flake8 output for line: {e}. Parsed parts: {parts}. Skipping..." + f'Error parsing flake8 output for line: {e}. Parsed parts: {parts}. Skipping...' ) continue @@ -54,10 +54,10 @@ def flake_lint(filepath: str) -> list[LintResult]: except ValueError as e: column_num = 1 _msg = ( - parts[2].strip() + " " + _msg + parts[2].strip() + ' ' + _msg ) # add the unparsed message to the original message logger.warning( - f"Error parsing flake8 output for column: {e}. Parsed parts: {parts}. Using default column 1." + f'Error parsing flake8 output for column: {e}. Parsed parts: {parts}. Using default column 1.' ) results.append( @@ -74,7 +74,7 @@ def flake_lint(filepath: str) -> list[LintResult]: class PythonLinter(BaseLinter): @property def supported_extensions(self) -> List[str]: - return [".py"] + return ['.py'] def lint(self, file_path: str) -> list[LintResult]: error = flake_lint(file_path) @@ -84,7 +84,7 @@ def lint(self, file_path: str) -> list[LintResult]: def compile_lint(self, file_path: str, code: str) -> List[LintResult]: try: - compile(code, file_path, "exec") + compile(code, file_path, 'exec') return [] except SyntaxError as e: return [ @@ -93,6 +93,6 @@ def compile_lint(self, file_path: str, code: str) -> List[LintResult]: line=e.lineno, column=e.offset, message=str(e), - rule="SyntaxError", + rule='SyntaxError', ) ] diff --git a/openhands/linter/languages/treesitter.py b/openhands/linter/languages/treesitter.py index e85c381e886d..83b5d466aecc 100644 --- a/openhands/linter/languages/treesitter.py +++ b/openhands/linter/languages/treesitter.py @@ -7,7 +7,7 @@ from openhands.linter.base import BaseLinter, LintResult # tree_sitter is throwing a FutureWarning -warnings.simplefilter("ignore", category=FutureWarning) +warnings.simplefilter('ignore', category=FutureWarning) def tree_context(fname, code, line_nums): @@ -34,10 +34,10 @@ def tree_context(fname, code, line_nums): def traverse_tree(node): """Traverses the tree to find errors.""" errors = [] - if node.type == "ERROR" or node.is_missing: + if node.type == 'ERROR' or node.is_missing: line_no = node.start_point[0] + 1 col_no = node.start_point[1] + 1 - error_type = "Missing node" if node.is_missing else "Syntax error" + error_type = 'Missing node' if node.is_missing else 'Syntax error' errors.append((line_no, col_no, error_type)) for child in node.children: @@ -57,9 +57,9 @@ def lint(self, file_path: str) -> list[LintResult]: if not lang: return [] parser = get_parser(lang) - with open(file_path, "r") as f: + with open(file_path, 'r') as f: code = f.read() - tree = parser.parse(bytes(code, "utf-8")) + tree = parser.parse(bytes(code, 'utf-8')) errors = traverse_tree(tree.root_node) if not errors: return [] diff --git a/openhands/linter/utils/__init__.py b/openhands/linter/utils/__init__.py index c346a8f561a4..e48f26f076b5 100644 --- a/openhands/linter/utils/__init__.py +++ b/openhands/linter/utils/__init__.py @@ -1,3 +1,3 @@ from .cmd import check_tool_installed, run_cmd -__all__ = ["run_cmd", "check_tool_installed"] +__all__ = ['run_cmd', 'check_tool_installed'] diff --git a/openhands/linter/utils/cmd.py b/openhands/linter/utils/cmd.py index 13989d645bab..f5c2803c3d77 100644 --- a/openhands/linter/utils/cmd.py +++ b/openhands/linter/utils/cmd.py @@ -7,13 +7,14 @@ def run_cmd(cmd: str, cwd: str | None = None) -> str | None: If the command succeeds, return None. If the command fails, return the stdout. """ + process = subprocess.Popen( cmd.split(), cwd=cwd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, - encoding="utf-8", - errors="replace", + encoding='utf-8', + errors='replace', ) stdout, _ = process.communicate() if process.returncode == 0: @@ -25,7 +26,7 @@ def check_tool_installed(tool_name: str) -> bool: """Check if a tool is installed.""" try: subprocess.run( - [tool_name, "--version"], + [tool_name, '--version'], check=True, cwd=os.getcwd(), stdout=subprocess.PIPE, diff --git a/openhands/llm/async_llm.py b/openhands/llm/async_llm.py index f2226dcd167a..ed84273c737b 100644 --- a/openhands/llm/async_llm.py +++ b/openhands/llm/async_llm.py @@ -7,7 +7,7 @@ from openhands.core.exceptions import UserCancelledError from openhands.core.logger import openhands_logger as logger from openhands.llm.llm import LLM, LLM_RETRY_EXCEPTIONS -from openhands.runtime.utils.shutdown_listener import should_continue +from openhands.utils.shutdown_listener import should_continue class AsyncLLM(LLM): diff --git a/openhands/llm/retry_mixin.py b/openhands/llm/retry_mixin.py index a1705f0d30ca..1005677320e1 100644 --- a/openhands/llm/retry_mixin.py +++ b/openhands/llm/retry_mixin.py @@ -13,7 +13,8 @@ class RetryMixin: """Mixin class for retry logic.""" def retry_decorator(self, **kwargs): - """Create a LLM retry decorator with customizable parameters. This is used for 429 errors, and a few other exceptions in LLM classes. + """ + Create a LLM retry decorator with customizable parameters. This is used for 429 errors, and a few other exceptions in LLM classes. Args: **kwargs: Keyword arguments to override default retry behavior. diff --git a/openhands/memory/memory.py b/openhands/memory/memory.py index 509bb8b2ffbe..9d83cc9cdc8c 100644 --- a/openhands/memory/memory.py +++ b/openhands/memory/memory.py @@ -35,6 +35,7 @@ def __init__( event_stream: EventStream, ): """Initialize the chromadb and set up ChromaVectorStore for later use.""" + check_llama_index() # initialize the chromadb client diff --git a/openhands/runtime/__init__.py b/openhands/runtime/__init__.py index 66c89dadca15..16534daf6b56 100644 --- a/openhands/runtime/__init__.py +++ b/openhands/runtime/__init__.py @@ -1,31 +1,25 @@ from openhands.core.logger import openhands_logger as logger from openhands.runtime.impl.e2b.sandbox import E2BBox +from openhands.runtime.impl.eventstream.eventstream_runtime import ( + EventStreamRuntime, +) +from openhands.runtime.impl.modal.modal_runtime import ModalRuntime +from openhands.runtime.impl.remote.remote_runtime import RemoteRuntime +from openhands.runtime.impl.runloop.runloop_runtime import RunloopRuntime def get_runtime_cls(name: str): # Local imports to avoid circular imports if name == 'eventstream': - from openhands.runtime.impl.eventstream.eventstream_runtime import ( - EventStreamRuntime, - ) - return EventStreamRuntime elif name == 'e2b': - from openhands.runtime.impl.e2b.e2b_runtime import E2BRuntime - - return E2BRuntime + return E2BBox elif name == 'remote': - from openhands.runtime.impl.remote.remote_runtime import RemoteRuntime - return RemoteRuntime elif name == 'modal': logger.debug('Using ModalRuntime') - from openhands.runtime.impl.modal.modal_runtime import ModalRuntime - return ModalRuntime elif name == 'runloop': - from openhands.runtime.impl.runloop.runloop_runtime import RunloopRuntime - return RunloopRuntime else: raise ValueError(f'Runtime {name} not supported') @@ -33,5 +27,9 @@ def get_runtime_cls(name: str): __all__ = [ 'E2BBox', + 'RemoteRuntime', + 'ModalRuntime', + 'RunloopRuntime', + 'EventStreamRuntime', 'get_runtime_cls', ] diff --git a/openhands/runtime/action_execution_server.py b/openhands/runtime/action_execution_server.py index 3afba6b6f5bb..aeb0d4c7a407 100644 --- a/openhands/runtime/action_execution_server.py +++ b/openhands/runtime/action_execution_server.py @@ -1,4 +1,5 @@ -"""This is the main file for the runtime client. +""" +This is the main file for the runtime client. It is responsible for executing actions received from OpenHands backend and producing observations. NOTE: this will be executed inside the docker sandbox. @@ -46,14 +47,11 @@ from openhands.events.serialization import event_from_dict, event_to_dict from openhands.runtime.browser import browse from openhands.runtime.browser.browser_env import BrowserEnv -from openhands.runtime.plugins import ( - ALL_PLUGINS, - JupyterPlugin, - Plugin, -) +from openhands.runtime.plugins import ALL_PLUGINS, JupyterPlugin, Plugin, VSCodePlugin from openhands.runtime.utils.bash import BashSession from openhands.runtime.utils.files import insert_lines, read_lines from openhands.runtime.utils.runtime_init import init_user_and_working_directory +from openhands.runtime.utils.system import check_port_available from openhands.utils.async_utils import wait_all @@ -115,7 +113,10 @@ def initial_pwd(self): return self._initial_pwd async def ainit(self): - await wait_all(self._init_plugin(plugin) for plugin in self.plugins_to_load) + await wait_all( + (self._init_plugin(plugin) for plugin in self.plugins_to_load), + timeout=30, + ) # This is a temporary workaround # TODO: refactor AgentSkills to be part of JupyterPlugin @@ -344,6 +345,8 @@ def close(self): ) # example: python client.py 8000 --working-dir /workspace --plugins JupyterRequirement args = parser.parse_args() + os.environ['VSCODE_PORT'] = str(int(args.port) + 1) + assert check_port_available(int(os.environ['VSCODE_PORT'])) plugins_to_load: list[Plugin] = [] if args.plugins: @@ -526,6 +529,19 @@ async def download_file(path: str): async def alive(): return {'status': 'ok'} + # ================================ + # VSCode-specific operations + # ================================ + + @app.get('/vscode/connection_token') + async def get_vscode_connection_token(): + assert client is not None + if 'vscode' in client.plugins: + plugin: VSCodePlugin = client.plugins['vscode'] # type: ignore + return {'token': plugin.vscode_connection_token} + else: + return {'token': None} + # ================================ # File-specific operations for UI # ================================ diff --git a/openhands/runtime/base.py b/openhands/runtime/base.py index 076732a4636c..b12c501c19f3 100644 --- a/openhands/runtime/base.py +++ b/openhands/runtime/base.py @@ -30,7 +30,11 @@ UserRejectObservation, ) from openhands.events.serialization.action import ACTION_TYPE_TO_CLASS -from openhands.runtime.plugins import JupyterRequirement, PluginRequirement +from openhands.runtime.plugins import ( + JupyterRequirement, + PluginRequirement, + VSCodeRequirement, +) from openhands.runtime.utils.edit import FileEditRuntimeMixin from openhands.utils.async_utils import call_sync_from_async @@ -84,13 +88,20 @@ def __init__( env_vars: dict[str, str] | None = None, status_callback: Callable | None = None, attach_to_existing: bool = False, + headless_mode: bool = False, ): self.sid = sid self.event_stream = event_stream self.event_stream.subscribe( EventStreamSubscriber.RUNTIME, self.on_event, self.sid ) - self.plugins = plugins if plugins is not None and len(plugins) > 0 else [] + self.plugins = ( + copy.deepcopy(plugins) if plugins is not None and len(plugins) > 0 else [] + ) + # add VSCode plugin if not in headless mode + if not headless_mode: + self.plugins.append(VSCodeRequirement()) + self.status_callback = status_callback self.attach_to_existing = attach_to_existing @@ -101,6 +112,10 @@ def __init__( if env_vars is not None: self.initial_env_vars.update(env_vars) + self._vscode_enabled = any( + isinstance(plugin, VSCodeRequirement) for plugin in self.plugins + ) + # Load mixins FileEditRuntimeMixin.__init__(self) @@ -278,3 +293,15 @@ def list_files(self, path: str | None = None) -> list[str]: def copy_from(self, path: str) -> Path: """Zip all files in the sandbox and return a path in the local filesystem.""" raise NotImplementedError('This method is not implemented in the base class.') + + # ==================================================================== + # VSCode + # ==================================================================== + + @property + def vscode_enabled(self) -> bool: + return self._vscode_enabled + + @property + def vscode_url(self) -> str | None: + raise NotImplementedError('This method is not implemented in the base class.') diff --git a/openhands/runtime/browser/__init__.py b/openhands/runtime/browser/__init__.py index db13465101ce..2687e03c684f 100644 --- a/openhands/runtime/browser/__init__.py +++ b/openhands/runtime/browser/__init__.py @@ -1,3 +1,3 @@ from openhands.runtime.browser.utils import browse -__all__ = ["browse"] +__all__ = ['browse'] diff --git a/openhands/runtime/browser/browser_env.py b/openhands/runtime/browser/browser_env.py index 8f9b06e14321..d9a7fd752956 100644 --- a/openhands/runtime/browser/browser_env.py +++ b/openhands/runtime/browser/browser_env.py @@ -16,25 +16,25 @@ from openhands.core.exceptions import BrowserInitException from openhands.core.logger import openhands_logger as logger -from openhands.runtime.utils.shutdown_listener import should_continue, should_exit +from openhands.utils.shutdown_listener import should_continue, should_exit from openhands.utils.tenacity_stop import stop_if_should_exit -BROWSER_EVAL_GET_GOAL_ACTION = "GET_EVAL_GOAL" -BROWSER_EVAL_GET_REWARDS_ACTION = "GET_EVAL_REWARDS" +BROWSER_EVAL_GET_GOAL_ACTION = 'GET_EVAL_GOAL' +BROWSER_EVAL_GET_REWARDS_ACTION = 'GET_EVAL_REWARDS' class BrowserEnv: def __init__(self, browsergym_eval_env: str | None = None): self.html_text_converter = self.get_html_text_converter() self.eval_mode = False - self.eval_dir = "" + self.eval_dir = '' # EVAL only: browsergym_eval_env must be provided for evaluation self.browsergym_eval_env = browsergym_eval_env self.eval_mode = bool(browsergym_eval_env) # Initialize browser environment process - multiprocessing.set_start_method("spawn", force=True) + multiprocessing.set_start_method('spawn', force=True) self.browser_side, self.agent_side = multiprocessing.Pipe() self.init_browser() @@ -57,42 +57,42 @@ def get_html_text_converter(self): retry=tenacity.retry_if_exception_type(BrowserInitException), ) def init_browser(self): - logger.debug("Starting browser env...") + logger.debug('Starting browser env...') try: self.process = multiprocessing.Process(target=self.browser_process) self.process.start() except Exception as e: - logger.error(f"Failed to start browser process: {e}") + logger.error(f'Failed to start browser process: {e}') raise if not self.check_alive(): self.close() - raise BrowserInitException("Failed to start browser environment.") + raise BrowserInitException('Failed to start browser environment.') def browser_process(self): if self.eval_mode: assert self.browsergym_eval_env is not None - logger.debug("Initializing browser env for web browsing evaluation.") - if "webarena" in self.browsergym_eval_env: + logger.debug('Initializing browser env for web browsing evaluation.') + if 'webarena' in self.browsergym_eval_env: import browsergym.webarena # noqa F401 register webarena tasks as gym environments - elif "miniwob" in self.browsergym_eval_env: + elif 'miniwob' in self.browsergym_eval_env: import browsergym.miniwob # noqa F401 register miniwob tasks as gym environments else: raise ValueError( - f"Unsupported browsergym eval env: {self.browsergym_eval_env}" + f'Unsupported browsergym eval env: {self.browsergym_eval_env}' ) env = gym.make( self.browsergym_eval_env, - tags_to_mark="all", + tags_to_mark='all', ) else: env = gym.make( - "browsergym/openended", - task_kwargs={"start_url": "about:blank", "goal": "PLACEHOLDER_GOAL"}, + 'browsergym/openended', + task_kwargs={'start_url': 'about:blank', 'goal': 'PLACEHOLDER_GOAL'}, wait_for_user_message=False, headless=True, disable_env_checker=True, - tags_to_mark="all", + tags_to_mark='all', ) obs, info = env.reset() @@ -102,39 +102,39 @@ def browser_process(self): self.eval_rewards: list[float] = [] if self.eval_mode: logger.debug(f"Browsing goal: {obs['goal']}") - self.eval_goal = obs["goal"] + self.eval_goal = obs['goal'] - logger.debug("Browser env started.") + logger.debug('Browser env started.') while should_continue(): try: if self.browser_side.poll(timeout=0.01): unique_request_id, action_data = self.browser_side.recv() # shutdown the browser environment - if unique_request_id == "SHUTDOWN": - logger.debug("SHUTDOWN recv, shutting down browser env...") + if unique_request_id == 'SHUTDOWN': + logger.debug('SHUTDOWN recv, shutting down browser env...') env.close() return - elif unique_request_id == "IS_ALIVE": - self.browser_side.send(("ALIVE", None)) + elif unique_request_id == 'IS_ALIVE': + self.browser_side.send(('ALIVE', None)) continue # EVAL ONLY: Get evaluation info - if action_data["action"] == BROWSER_EVAL_GET_GOAL_ACTION: + if action_data['action'] == BROWSER_EVAL_GET_GOAL_ACTION: self.browser_side.send( - (unique_request_id, {"text_content": self.eval_goal}) + (unique_request_id, {'text_content': self.eval_goal}) ) continue - elif action_data["action"] == BROWSER_EVAL_GET_REWARDS_ACTION: + elif action_data['action'] == BROWSER_EVAL_GET_REWARDS_ACTION: self.browser_side.send( ( unique_request_id, - {"text_content": json.dumps(self.eval_rewards)}, + {'text_content': json.dumps(self.eval_rewards)}, ) ) continue - action = action_data["action"] + action = action_data['action'] obs, reward, terminated, truncated, info = env.step(action) # EVAL ONLY: Save the rewards into file for evaluation @@ -142,15 +142,15 @@ def browser_process(self): self.eval_rewards.append(reward) # add text content of the page - html_str = flatten_dom_to_str(obs["dom_object"]) - obs["text_content"] = self.html_text_converter.handle(html_str) + html_str = flatten_dom_to_str(obs['dom_object']) + obs['text_content'] = self.html_text_converter.handle(html_str) # make observation serializable - obs["screenshot"] = self.image_to_png_base64_url(obs["screenshot"]) - obs["active_page_index"] = obs["active_page_index"].item() - obs["elapsed_time"] = obs["elapsed_time"].item() + obs['screenshot'] = self.image_to_png_base64_url(obs['screenshot']) + obs['active_page_index'] = obs['active_page_index'].item() + obs['elapsed_time'] = obs['elapsed_time'].item() self.browser_side.send((unique_request_id, obs)) except KeyboardInterrupt: - logger.debug("Browser env process interrupted by user.") + logger.debug('Browser env process interrupted by user.') try: env.close() except Exception: @@ -160,33 +160,33 @@ def browser_process(self): def step(self, action_str: str, timeout: float = 30) -> dict: """Execute an action in the browser environment and return the observation.""" unique_request_id = str(uuid.uuid4()) - self.agent_side.send((unique_request_id, {"action": action_str})) + self.agent_side.send((unique_request_id, {'action': action_str})) start_time = time.time() while True: if should_exit() or time.time() - start_time > timeout: - raise TimeoutError("Browser environment took too long to respond.") + raise TimeoutError('Browser environment took too long to respond.') if self.agent_side.poll(timeout=0.01): response_id, obs = self.agent_side.recv() if response_id == unique_request_id: return obs def check_alive(self, timeout: float = 60): - self.agent_side.send(("IS_ALIVE", None)) + self.agent_side.send(('IS_ALIVE', None)) if self.agent_side.poll(timeout=timeout): response_id, _ = self.agent_side.recv() - if response_id == "ALIVE": + if response_id == 'ALIVE': return True - logger.debug(f"Browser env is not alive. Response ID: {response_id}") + logger.debug(f'Browser env is not alive. Response ID: {response_id}') def close(self): if not self.process.is_alive(): return try: - self.agent_side.send(("SHUTDOWN", None)) + self.agent_side.send(('SHUTDOWN', None)) self.process.join(5) # Wait for the process to terminate if self.process.is_alive(): logger.error( - "Browser process did not terminate, forcefully terminating..." + 'Browser process did not terminate, forcefully terminating...' ) self.process.terminate() self.process.join(5) # Wait for the process to terminate @@ -196,7 +196,7 @@ def close(self): self.agent_side.close() self.browser_side.close() except Exception: - logger.error("Encountered an error when closing browser env", exc_info=True) + logger.error('Encountered an error when closing browser env', exc_info=True) @staticmethod def image_to_png_base64_url( @@ -205,16 +205,16 @@ def image_to_png_base64_url( """Convert a numpy array to a base64 encoded png image url.""" if isinstance(image, np.ndarray): image = Image.fromarray(image) - if image.mode in ("RGBA", "LA"): - image = image.convert("RGB") + if image.mode in ('RGBA', 'LA'): + image = image.convert('RGB') buffered = io.BytesIO() - image.save(buffered, format="PNG") + image.save(buffered, format='PNG') image_base64 = base64.b64encode(buffered.getvalue()).decode() return ( - f"data:image/png;base64,{image_base64}" + f'data:image/png;base64,{image_base64}' if add_data_prefix - else f"{image_base64}" + else f'{image_base64}' ) @staticmethod @@ -224,14 +224,14 @@ def image_to_jpg_base64_url( """Convert a numpy array to a base64 encoded jpeg image url.""" if isinstance(image, np.ndarray): image = Image.fromarray(image) - if image.mode in ("RGBA", "LA"): - image = image.convert("RGB") + if image.mode in ('RGBA', 'LA'): + image = image.convert('RGB') buffered = io.BytesIO() - image.save(buffered, format="JPEG") + image.save(buffered, format='JPEG') image_base64 = base64.b64encode(buffered.getvalue()).decode() return ( - f"data:image/jpeg;base64,{image_base64}" + f'data:image/jpeg;base64,{image_base64}' if add_data_prefix - else f"{image_base64}" + else f'{image_base64}' ) diff --git a/openhands/runtime/browser/utils.py b/openhands/runtime/browser/utils.py index 517954f78a1b..336b3801e3e2 100644 --- a/openhands/runtime/browser/utils.py +++ b/openhands/runtime/browser/utils.py @@ -16,7 +16,7 @@ async def browse( if isinstance(action, BrowseURLAction): # legacy BrowseURLAction asked_url = action.url - if not asked_url.startswith("http"): + if not asked_url.startswith('http'): asked_url = os.path.abspath(os.curdir) + action.url action_str = f'goto("{asked_url}")' @@ -25,36 +25,36 @@ async def browse( # action in BrowserGym: see https://github.com/ServiceNow/BrowserGym/blob/main/core/src/browsergym/core/action/functions.py action_str = action.browser_actions else: - raise ValueError(f"Invalid action type: {action.action}") + raise ValueError(f'Invalid action type: {action.action}') try: # obs provided by BrowserGym: see https://github.com/ServiceNow/BrowserGym/blob/main/core/src/browsergym/core/env.py#L396 obs = browser.step(action_str) return BrowserOutputObservation( - content=obs["text_content"], # text content of the page - url=obs.get("url", ""), # URL of the page - screenshot=obs.get("screenshot", None), # base64-encoded screenshot, png - open_pages_urls=obs.get("open_pages_urls", []), # list of open pages + content=obs['text_content'], # text content of the page + url=obs.get('url', ''), # URL of the page + screenshot=obs.get('screenshot', None), # base64-encoded screenshot, png + open_pages_urls=obs.get('open_pages_urls', []), # list of open pages active_page_index=obs.get( - "active_page_index", -1 + 'active_page_index', -1 ), # index of the active page - dom_object=obs.get("dom_object", {}), # DOM object - axtree_object=obs.get("axtree_object", {}), # accessibility tree object - extra_element_properties=obs.get("extra_element_properties", {}), + dom_object=obs.get('dom_object', {}), # DOM object + axtree_object=obs.get('axtree_object', {}), # accessibility tree object + extra_element_properties=obs.get('extra_element_properties', {}), focused_element_bid=obs.get( - "focused_element_bid", None + 'focused_element_bid', None ), # focused element bid last_browser_action=obs.get( - "last_action", "" + 'last_action', '' ), # last browser env action performed - last_browser_action_error=obs.get("last_action_error", ""), - error=True if obs.get("last_action_error", "") else False, # error flag + last_browser_action_error=obs.get('last_action_error', ''), + error=True if obs.get('last_action_error', '') else False, # error flag ) except Exception as e: return BrowserOutputObservation( content=str(e), - screenshot="", + screenshot='', error=True, last_browser_action_error=str(e), - url=asked_url if action.action == ActionType.BROWSE else "", + url=asked_url if action.action == ActionType.BROWSE else '', ) diff --git a/openhands/runtime/builder/__init__.py b/openhands/runtime/builder/__init__.py index 2d0767f6ef58..fcebb8a24056 100644 --- a/openhands/runtime/builder/__init__.py +++ b/openhands/runtime/builder/__init__.py @@ -1,4 +1,4 @@ from openhands.runtime.builder.base import RuntimeBuilder from openhands.runtime.builder.docker import DockerRuntimeBuilder -__all__ = ["RuntimeBuilder", "DockerRuntimeBuilder"] +__all__ = ['RuntimeBuilder', 'DockerRuntimeBuilder'] diff --git a/openhands/runtime/builder/base.py b/openhands/runtime/builder/base.py index df2ee99035c9..4930b13d7ffd 100644 --- a/openhands/runtime/builder/base.py +++ b/openhands/runtime/builder/base.py @@ -9,13 +9,13 @@ def build( tags: list[str], platform: str | None = None, ) -> str: - """Build the runtime image. + """ + Build the runtime image. Args: path (str): The path to the runtime image's build directory. tags (list[str]): The tags to apply to the runtime image (e.g., ["repo:my-repo", "sha:my-sha"]). platform (str, optional): The target platform for the build. Defaults to None. - Returns: str: The name:tag of the runtime image after build (e.g., "repo:sha"). This can be different from the tags input if the builder chooses to mutate the tags (e.g., adding a @@ -28,7 +28,8 @@ def build( @abc.abstractmethod def image_exists(self, image_name: str, pull_from_repo: bool = True) -> bool: - """Check if the runtime image exists. + """ + Check if the runtime image exists. Args: image_name (str): The name of the runtime image (e.g., "repo:sha"). diff --git a/openhands/runtime/builder/docker.py b/openhands/runtime/builder/docker.py index c304b1ebaa83..a3cb5af39f3d 100644 --- a/openhands/runtime/builder/docker.py +++ b/openhands/runtime/builder/docker.py @@ -16,9 +16,9 @@ def __init__(self, docker_client: docker.DockerClient): self.docker_client = docker_client version_info = self.docker_client.version() - server_version = version_info.get("Version", "").replace("-", ".") - if tuple(map(int, server_version.split(".")[:2])) < (18, 9): - raise RuntimeError("Docker server version must be >= 18.09 to use BuildKit") + server_version = version_info.get('Version', '').replace('-', '.') + if tuple(map(int, server_version.split('.')[:2])) < (18, 9): + raise RuntimeError('Docker server version must be >= 18.09 to use BuildKit') self.rolling_logger = RollingLogger(max_lines=10) @@ -52,35 +52,35 @@ def build( """ self.docker_client = docker.from_env() version_info = self.docker_client.version() - server_version = version_info.get("Version", "").replace("-", ".") - if tuple(map(int, server_version.split("."))) < (18, 9): - raise RuntimeError("Docker server version must be >= 18.09 to use BuildKit") + server_version = version_info.get('Version', '').replace('-', '.') + if tuple(map(int, server_version.split('.'))) < (18, 9): + raise RuntimeError('Docker server version must be >= 18.09 to use BuildKit') target_image_hash_name = tags[0] - target_image_repo, target_image_source_tag = target_image_hash_name.split(":") - target_image_tag = tags[1].split(":")[1] if len(tags) > 1 else None + target_image_repo, target_image_source_tag = target_image_hash_name.split(':') + target_image_tag = tags[1].split(':')[1] if len(tags) > 1 else None buildx_cmd = [ - "docker", - "buildx", - "build", - "--progress=plain", - f"--build-arg=OPENHANDS_RUNTIME_VERSION={oh_version}", - f"--build-arg=OPENHANDS_RUNTIME_BUILD_TIME={datetime.datetime.now().isoformat()}", - f"--tag={target_image_hash_name}", - "--load", + 'docker', + 'buildx', + 'build', + '--progress=plain', + f'--build-arg=OPENHANDS_RUNTIME_VERSION={oh_version}', + f'--build-arg=OPENHANDS_RUNTIME_BUILD_TIME={datetime.datetime.now().isoformat()}', + f'--tag={target_image_hash_name}', + '--load', ] # Include the platform argument only if platform is specified if platform: - buildx_cmd.append(f"--platform={platform}") + buildx_cmd.append(f'--platform={platform}') - cache_dir = "/tmp/.buildx-cache" + cache_dir = '/tmp/.buildx-cache' if use_local_cache and self._is_cache_usable(cache_dir): buildx_cmd.extend( [ - f"--cache-from=type=local,src={cache_dir}", - f"--cache-to=type=local,dest={cache_dir},mode=max", + f'--cache-from=type=local,src={cache_dir}', + f'--cache-to=type=local,dest={cache_dir},mode=max', ] ) @@ -90,7 +90,7 @@ def build( buildx_cmd.append(path) # must be last! self.rolling_logger.start( - "================ DOCKER BUILD STARTED ================" + '================ DOCKER BUILD STARTED ================' ) try: @@ -103,7 +103,7 @@ def build( ) if process.stdout: - for line in iter(process.stdout.readline, ""): + for line in iter(process.stdout.readline, ''): line = line.strip() if line: self._output_logs(line) @@ -119,51 +119,51 @@ def build( ) except subprocess.CalledProcessError as e: - logger.error(f"Image build failed:\n{e}") - logger.error(f"Command output:\n{e.output}") + logger.error(f'Image build failed:\n{e}') + logger.error(f'Command output:\n{e.output}') raise except subprocess.TimeoutExpired: - logger.error("Image build timed out") + logger.error('Image build timed out') raise except FileNotFoundError as e: - logger.error(f"Python executable not found: {e}") + logger.error(f'Python executable not found: {e}') raise except PermissionError as e: logger.error( - f"Permission denied when trying to execute the build command:\n{e}" + f'Permission denied when trying to execute the build command:\n{e}' ) raise except Exception as e: - logger.error(f"An unexpected error occurred during the build process: {e}") + logger.error(f'An unexpected error occurred during the build process: {e}') raise - logger.info(f"Image [{target_image_hash_name}] build finished.") + logger.info(f'Image [{target_image_hash_name}] build finished.') if target_image_tag: image = self.docker_client.images.get(target_image_hash_name) image.tag(target_image_repo, target_image_tag) logger.info( - f"Re-tagged image [{target_image_hash_name}] with more generic tag [{target_image_tag}]" + f'Re-tagged image [{target_image_hash_name}] with more generic tag [{target_image_tag}]' ) # Check if the image is built successfully image = self.docker_client.images.get(target_image_hash_name) if image is None: raise RuntimeError( - f"Build failed: Image {target_image_hash_name} not found" + f'Build failed: Image {target_image_hash_name} not found' ) tags_str = ( - f"{target_image_source_tag}, {target_image_tag}" + f'{target_image_source_tag}, {target_image_tag}' if target_image_tag else target_image_source_tag ) logger.info( - f"Image {target_image_repo} with tags [{tags_str}] built successfully" + f'Image {target_image_repo} with tags [{tags_str}] built successfully' ) return target_image_hash_name @@ -177,28 +177,28 @@ def image_exists(self, image_name: str, pull_from_repo: bool = True) -> bool: bool: Whether the Docker image exists in the registry or in the local store """ if not image_name: - logger.error(f"Invalid image name: `{image_name}`") + logger.error(f'Invalid image name: `{image_name}`') return False try: - logger.debug(f"Checking, if image exists locally:\n{image_name}") + logger.debug(f'Checking, if image exists locally:\n{image_name}') self.docker_client.images.get(image_name) - logger.debug("Image found locally.") + logger.debug('Image found locally.') return True except docker.errors.ImageNotFound: if not pull_from_repo: - logger.debug(f"Image {image_name} not found locally") + logger.debug(f'Image {image_name} not found locally') return False try: logger.debug( - "Image not found locally. Trying to pull it, please wait..." + 'Image not found locally. Trying to pull it, please wait...' ) layers: dict[str, dict[str, str]] = {} previous_layer_count = 0 - if ":" in image_name: - image_repo, image_tag = image_name.split(":", 1) + if ':' in image_name: + image_repo, image_tag = image_name.split(':', 1) else: image_repo = image_name image_tag = None @@ -208,18 +208,18 @@ def image_exists(self, image_name: str, pull_from_repo: bool = True) -> bool: ): self._output_build_progress(line, layers, previous_layer_count) previous_layer_count = len(layers) - logger.debug("Image pulled") + logger.debug('Image pulled') return True except docker.errors.ImageNotFound: - logger.debug("Could not find image locally or in registry.") + logger.debug('Could not find image locally or in registry.') return False except Exception as e: - msg = "Image could not be pulled: " + msg = 'Image could not be pulled: ' ex_msg = str(e) - if "Not Found" in ex_msg: - msg += "image not found in registry." + if 'Not Found' in ex_msg: + msg += 'image not found in registry.' else: - msg += f"{ex_msg}" + msg += f'{ex_msg}' logger.debug(msg) return False @@ -232,61 +232,62 @@ def _output_logs(self, new_line: str) -> None: def _output_build_progress( self, current_line: dict, layers: dict, previous_layer_count: int ) -> None: - if "id" in current_line and "progressDetail" in current_line: - layer_id = current_line["id"] + if 'id' in current_line and 'progressDetail' in current_line: + layer_id = current_line['id'] if layer_id not in layers: - layers[layer_id] = {"status": "", "progress": "", "last_logged": 0} + layers[layer_id] = {'status': '', 'progress': '', 'last_logged': 0} - if "status" in current_line: - layers[layer_id]["status"] = current_line["status"] + if 'status' in current_line: + layers[layer_id]['status'] = current_line['status'] - if "progress" in current_line: - layers[layer_id]["progress"] = current_line["progress"] + if 'progress' in current_line: + layers[layer_id]['progress'] = current_line['progress'] - if "progressDetail" in current_line: - progress_detail = current_line["progressDetail"] - if "total" in progress_detail and "current" in progress_detail: - total = progress_detail["total"] - current = progress_detail["current"] + if 'progressDetail' in current_line: + progress_detail = current_line['progressDetail'] + if 'total' in progress_detail and 'current' in progress_detail: + total = progress_detail['total'] + current = progress_detail['current'] percentage = min( (current / total) * 100, 100 ) # Ensure it doesn't exceed 100% else: percentage = ( - 100 if layers[layer_id]["status"] == "Download complete" else 0 + 100 if layers[layer_id]['status'] == 'Download complete' else 0 ) if self.rolling_logger.is_enabled(): self.rolling_logger.move_back(previous_layer_count) for lid, layer_data in sorted(layers.items()): self.rolling_logger.replace_current_line() - status = layer_data["status"] - progress = layer_data["progress"] - if status == "Download complete": + status = layer_data['status'] + progress = layer_data['progress'] + if status == 'Download complete': self.rolling_logger.write_immediately( - f"Layer {lid}: Download complete" + f'Layer {lid}: Download complete' ) - elif status == "Already exists": + elif status == 'Already exists': self.rolling_logger.write_immediately( - f"Layer {lid}: Already exists" + f'Layer {lid}: Already exists' ) else: self.rolling_logger.write_immediately( - f"Layer {lid}: {progress} {status}" + f'Layer {lid}: {progress} {status}' ) elif percentage != 0 and ( - percentage - layers[layer_id]["last_logged"] >= 10 or percentage == 100 + percentage - layers[layer_id]['last_logged'] >= 10 or percentage == 100 ): logger.debug( f'Layer {layer_id}: {layers[layer_id]["progress"]} {layers[layer_id]["status"]}' ) - layers[layer_id]["last_logged"] = percentage - elif "status" in current_line: - logger.debug(current_line["status"]) + layers[layer_id]['last_logged'] = percentage + elif 'status' in current_line: + logger.debug(current_line['status']) def _prune_old_cache_files(self, cache_dir: str, max_age_days: int = 7) -> None: - """Prune cache files older than the specified number of days. + """ + Prune cache files older than the specified number of days. Args: cache_dir (str): The path to the cache directory. @@ -303,14 +304,15 @@ def _prune_old_cache_files(self, cache_dir: str, max_age_days: int = 7) -> None: file_age = current_time - os.path.getmtime(file_path) if file_age > max_age_seconds: os.remove(file_path) - logger.debug(f"Removed old cache file: {file_path}") + logger.debug(f'Removed old cache file: {file_path}') except Exception as e: - logger.warning(f"Error processing cache file {file_path}: {e}") + logger.warning(f'Error processing cache file {file_path}: {e}') except Exception as e: - logger.warning(f"Error during build cache pruning: {e}") + logger.warning(f'Error during build cache pruning: {e}') def _is_cache_usable(self, cache_dir: str) -> bool: - """Check if the cache directory is usable (exists and is writable). + """ + Check if the cache directory is usable (exists and is writable). Args: cache_dir (str): The path to the cache directory. @@ -321,18 +323,18 @@ def _is_cache_usable(self, cache_dir: str) -> bool: if not os.path.exists(cache_dir): try: os.makedirs(cache_dir, exist_ok=True) - logger.debug(f"Created cache directory: {cache_dir}") + logger.debug(f'Created cache directory: {cache_dir}') except OSError as e: - logger.debug(f"Failed to create cache directory {cache_dir}: {e}") + logger.debug(f'Failed to create cache directory {cache_dir}: {e}') return False if not os.access(cache_dir, os.W_OK): logger.warning( - f"Cache directory {cache_dir} is not writable. Caches will not be used for Docker builds." + f'Cache directory {cache_dir} is not writable. Caches will not be used for Docker builds.' ) return False self._prune_old_cache_files(cache_dir) - logger.debug(f"Cache directory {cache_dir} is usable") + logger.debug(f'Cache directory {cache_dir} is usable') return True diff --git a/openhands/runtime/builder/remote.py b/openhands/runtime/builder/remote.py index 8969d07c5792..c9d3228a70af 100644 --- a/openhands/runtime/builder/remote.py +++ b/openhands/runtime/builder/remote.py @@ -8,7 +8,7 @@ from openhands.core.logger import openhands_logger as logger from openhands.runtime.builder import RuntimeBuilder from openhands.runtime.utils.request import send_request -from openhands.runtime.utils.shutdown_listener import ( +from openhands.utils.shutdown_listener import ( should_continue, sleep_if_should_continue, ) @@ -21,87 +21,87 @@ def __init__(self, api_url: str, api_key: str): self.api_url = api_url self.api_key = api_key self.session = requests.Session() - self.session.headers.update({"X-API-Key": self.api_key}) + self.session.headers.update({'X-API-Key': self.api_key}) def build(self, path: str, tags: list[str], platform: str | None = None) -> str: """Builds a Docker image using the Runtime API's /build endpoint.""" # Create a tar archive of the build context tar_buffer = io.BytesIO() - with tarfile.open(fileobj=tar_buffer, mode="w:gz") as tar: - tar.add(path, arcname=".") + with tarfile.open(fileobj=tar_buffer, mode='w:gz') as tar: + tar.add(path, arcname='.') tar_buffer.seek(0) # Encode the tar file as base64 - base64_encoded_tar = base64.b64encode(tar_buffer.getvalue()).decode("utf-8") + base64_encoded_tar = base64.b64encode(tar_buffer.getvalue()).decode('utf-8') # Prepare the multipart form data files = [ - ("context", ("context.tar.gz", base64_encoded_tar)), - ("target_image", (None, tags[0])), + ('context', ('context.tar.gz', base64_encoded_tar)), + ('target_image', (None, tags[0])), ] # Add additional tags if present for tag in tags[1:]: - files.append(("tags", (None, tag))) + files.append(('tags', (None, tag))) # Send the POST request to /build (Begins the build process) try: response = send_request( self.session, - "POST", - f"{self.api_url}/build", + 'POST', + f'{self.api_url}/build', files=files, timeout=30, ) except requests.exceptions.HTTPError as e: if e.response.status_code == 429: - logger.warning("Build was rate limited. Retrying in 30 seconds.") + logger.warning('Build was rate limited. Retrying in 30 seconds.') time.sleep(30) return self.build(path, tags, platform) else: raise e build_data = response.json() - build_id = build_data["build_id"] - logger.info(f"Build initiated with ID: {build_id}") + build_id = build_data['build_id'] + logger.info(f'Build initiated with ID: {build_id}') # Poll /build_status until the build is complete start_time = time.time() timeout = 30 * 60 # 20 minutes in seconds while should_continue(): if time.time() - start_time > timeout: - logger.error("Build timed out after 30 minutes") - raise RuntimeError("Build timed out after 30 minutes") + logger.error('Build timed out after 30 minutes') + raise RuntimeError('Build timed out after 30 minutes') status_response = send_request( self.session, - "GET", - f"{self.api_url}/build_status", - params={"build_id": build_id}, + 'GET', + f'{self.api_url}/build_status', + params={'build_id': build_id}, ) if status_response.status_code != 200: - logger.error(f"Failed to get build status: {status_response.text}") + logger.error(f'Failed to get build status: {status_response.text}') raise RuntimeError( - f"Failed to get build status: {status_response.text}" + f'Failed to get build status: {status_response.text}' ) status_data = status_response.json() - status = status_data["status"] - logger.info(f"Build status: {status}") + status = status_data['status'] + logger.info(f'Build status: {status}') - if status == "SUCCESS": + if status == 'SUCCESS': logger.debug(f"Successfully built {status_data['image']}") - return status_data["image"] + return status_data['image'] elif status in [ - "FAILURE", - "INTERNAL_ERROR", - "TIMEOUT", - "CANCELLED", - "EXPIRED", + 'FAILURE', + 'INTERNAL_ERROR', + 'TIMEOUT', + 'CANCELLED', + 'EXPIRED', ]: error_message = status_data.get( - "error", f"Build failed with status: {status}. Build ID: {build_id}" + 'error', f'Build failed with status: {status}. Build ID: {build_id}' ) logger.error(error_message) raise RuntimeError(error_message) @@ -109,31 +109,31 @@ def build(self, path: str, tags: list[str], platform: str | None = None) -> str: # Wait before polling again sleep_if_should_continue(30) - raise RuntimeError("Build interrupted (likely received SIGTERM or SIGINT).") + raise RuntimeError('Build interrupted (likely received SIGTERM or SIGINT).') def image_exists(self, image_name: str, pull_from_repo: bool = True) -> bool: """Checks if an image exists in the remote registry using the /image_exists endpoint.""" - params = {"image": image_name} + params = {'image': image_name} response = send_request( self.session, - "GET", - f"{self.api_url}/image_exists", + 'GET', + f'{self.api_url}/image_exists', params=params, ) if response.status_code != 200: - logger.error(f"Failed to check image existence: {response.text}") - raise RuntimeError(f"Failed to check image existence: {response.text}") + logger.error(f'Failed to check image existence: {response.text}') + raise RuntimeError(f'Failed to check image existence: {response.text}') result = response.json() - if result["exists"]: + if result['exists']: logger.debug( f"Image {image_name} exists. " f"Uploaded at: {result['image']['upload_time']}, " f"Size: {result['image']['image_size_bytes'] / 1024 / 1024:.2f} MB" ) else: - logger.debug(f"Image {image_name} does not exist.") + logger.debug(f'Image {image_name} does not exist.') - return result["exists"] + return result['exists'] diff --git a/openhands/runtime/impl/e2b/e2b_runtime.py b/openhands/runtime/impl/e2b/e2b_runtime.py index 8c084daab3a8..7c9c297f424c 100644 --- a/openhands/runtime/impl/e2b/e2b_runtime.py +++ b/openhands/runtime/impl/e2b/e2b_runtime.py @@ -24,7 +24,7 @@ def __init__( self, config: AppConfig, event_stream: EventStream, - sid: str = "default", + sid: str = 'default', plugins: list[PluginRequirement] | None = None, sandbox: E2BSandbox | None = None, status_callback: Optional[Callable] = None, @@ -39,27 +39,27 @@ def __init__( if sandbox is None: self.sandbox = E2BSandbox() if not isinstance(self.sandbox, E2BSandbox): - raise ValueError("E2BRuntime requires an E2BSandbox") + raise ValueError('E2BRuntime requires an E2BSandbox') self.file_store = E2BFileStore(self.sandbox.filesystem) def read(self, action: FileReadAction) -> Observation: content = self.file_store.read(action.path) - lines = read_lines(content.split("\n"), action.start, action.end) - code_view = "".join(lines) + lines = read_lines(content.split('\n'), action.start, action.end) + code_view = ''.join(lines) return FileReadObservation(code_view, path=action.path) def write(self, action: FileWriteAction) -> Observation: if action.start == 0 and action.end == -1: self.file_store.write(action.path, action.content) - return FileWriteObservation(content="", path=action.path) + return FileWriteObservation(content='', path=action.path) files = self.file_store.list(action.path) if action.path in files: - all_lines = self.file_store.read(action.path).split("\n") + all_lines = self.file_store.read(action.path).split('\n') new_file = insert_lines( - action.content.split("\n"), all_lines, action.start, action.end + action.content.split('\n'), all_lines, action.start, action.end ) - self.file_store.write(action.path, "".join(new_file)) - return FileWriteObservation("", path=action.path) + self.file_store.write(action.path, ''.join(new_file)) + return FileWriteObservation('', path=action.path) else: # FIXME: we should create a new file here - return ErrorObservation(f"File not found: {action.path}") + return ErrorObservation(f'File not found: {action.path}') diff --git a/openhands/runtime/impl/e2b/sandbox.py b/openhands/runtime/impl/e2b/sandbox.py index fd4858d278bf..d145dac35115 100644 --- a/openhands/runtime/impl/e2b/sandbox.py +++ b/openhands/runtime/impl/e2b/sandbox.py @@ -12,7 +12,7 @@ class E2BBox: closed = False - _cwd: str = "/home/user" + _cwd: str = '/home/user' _env: dict[str, str] = {} is_initial_session: bool = True @@ -20,7 +20,7 @@ def __init__( self, config: SandboxConfig, e2b_api_key: str, - template: str = "openhands", + template: str = 'openhands', ): self.config = copy.deepcopy(config) self.initialize_plugins: bool = config.initialize_plugins @@ -28,8 +28,8 @@ def __init__( api_key=e2b_api_key, template=template, # It's possible to stream stdout and stderr from sandbox and from each process - on_stderr=lambda x: logger.debug(f"E2B sandbox stderr: {x}"), - on_stdout=lambda x: logger.debug(f"E2B sandbox stdout: {x}"), + on_stderr=lambda x: logger.debug(f'E2B sandbox stderr: {x}'), + on_stdout=lambda x: logger.debug(f'E2B sandbox stdout: {x}'), cwd=self._cwd, # Default workdir inside sandbox ) logger.debug(f'Started E2B sandbox with ID "{self.sandbox.id}"') @@ -42,11 +42,11 @@ def _archive(self, host_src: str, recursive: bool = False): if recursive: assert os.path.isdir( host_src - ), "Source must be a directory when recursive is True" - files = glob(host_src + "/**/*", recursive=True) + ), 'Source must be a directory when recursive is True' + files = glob(host_src + '/**/*', recursive=True) srcname = os.path.basename(host_src) - tar_filename = os.path.join(os.path.dirname(host_src), srcname + ".tar") - with tarfile.open(tar_filename, mode="w") as tar: + tar_filename = os.path.join(os.path.dirname(host_src), srcname + '.tar') + with tarfile.open(tar_filename, mode='w') as tar: for file in files: tar.add( file, arcname=os.path.relpath(file, os.path.dirname(host_src)) @@ -54,10 +54,10 @@ def _archive(self, host_src: str, recursive: bool = False): else: assert os.path.isfile( host_src - ), "Source must be a file when recursive is False" + ), 'Source must be a file when recursive is False' srcname = os.path.basename(host_src) - tar_filename = os.path.join(os.path.dirname(host_src), srcname + ".tar") - with tarfile.open(tar_filename, mode="w") as tar: + tar_filename = os.path.join(os.path.dirname(host_src), srcname + '.tar') + with tarfile.open(tar_filename, mode='w') as tar: tar.add(host_src, arcname=srcname) return tar_filename @@ -67,12 +67,12 @@ def execute(self, cmd: str, timeout: int | None = None) -> tuple[int, str]: try: process_output = process.wait(timeout=timeout) except TimeoutException: - logger.debug("Command timed out, killing process...") + logger.debug('Command timed out, killing process...') process.kill() return -1, f'Command: "{cmd}" timed out' logs = [m.line for m in process_output.messages] - logs_str = "\n".join(logs) + logs_str = '\n'.join(logs) if process.exit_code is None: return -1, logs_str @@ -84,24 +84,24 @@ def copy_to(self, host_src: str, sandbox_dest: str, recursive: bool = False): tar_filename = self._archive(host_src, recursive) # Prepend the sandbox destination with our sandbox cwd - sandbox_dest = os.path.join(self._cwd, sandbox_dest.removeprefix("/")) + sandbox_dest = os.path.join(self._cwd, sandbox_dest.removeprefix('/')) - with open(tar_filename, "rb") as tar_file: + with open(tar_filename, 'rb') as tar_file: # Upload the archive to /home/user (default destination that always exists) uploaded_path = self.sandbox.upload_file(tar_file) # Check if sandbox_dest exists. If not, create it. - process = self.sandbox.process.start_and_wait(f"test -d {sandbox_dest}") + process = self.sandbox.process.start_and_wait(f'test -d {sandbox_dest}') if process.exit_code != 0: self.sandbox.filesystem.make_dir(sandbox_dest) # Extract the archive into the destination and delete the archive process = self.sandbox.process.start_and_wait( - f"sudo tar -xf {uploaded_path} -C {sandbox_dest} && sudo rm {uploaded_path}" + f'sudo tar -xf {uploaded_path} -C {sandbox_dest} && sudo rm {uploaded_path}' ) if process.exit_code != 0: raise Exception( - f"Failed to extract {uploaded_path} to {sandbox_dest}: {process.stderr}" + f'Failed to extract {uploaded_path} to {sandbox_dest}: {process.stderr}' ) # Delete the local archive diff --git a/openhands/runtime/impl/eventstream/eventstream_runtime.py b/openhands/runtime/impl/eventstream/eventstream_runtime.py index 5ecf665f0c6b..77cbaf338281 100644 --- a/openhands/runtime/impl/eventstream/eventstream_runtime.py +++ b/openhands/runtime/impl/eventstream/eventstream_runtime.py @@ -44,7 +44,7 @@ from openhands.utils.async_utils import call_sync_from_async from openhands.utils.tenacity_stop import stop_if_should_exit -CONTAINER_NAME_PREFIX = "openhands-runtime-" +CONTAINER_NAME_PREFIX = 'openhands-runtime-' def remove_all_runtime_containers(): @@ -63,7 +63,7 @@ class LogBuffer: """ def __init__(self, container: docker.models.containers.Container, logFn: Callable): - self.init_msg = "Runtime client initialized." + self.init_msg = 'Runtime client initialized.' self.buffer: list[str] = [] self.lock = threading.Lock() @@ -95,15 +95,15 @@ def stream_logs(self): if self._stop_event.is_set(): break if log_line: - decoded_line = log_line.decode("utf-8").rstrip() + decoded_line = log_line.decode('utf-8').rstrip() self.append(decoded_line) except Exception as e: - self.log("error", f"Error streaming docker logs: {e}") + self.log('error', f'Error streaming docker logs: {e}') def __del__(self): if self.log_stream_thread.is_alive(): self.log( - "warn", + 'warn', "LogBuffer was not properly closed. Use 'log_buffer.close()' for clean shutdown.", ) self.close(timeout=5) @@ -131,11 +131,12 @@ def init_base_runtime( self, config: AppConfig, event_stream: EventStream, - sid: str = "default", + sid: str = 'default', plugins: list[PluginRequirement] | None = None, env_vars: dict[str, str] | None = None, status_callback: Callable | None = None, attach_to_existing: bool = False, + headless_mode: bool = True, ): super().__init__( config, @@ -145,22 +146,26 @@ def init_base_runtime( env_vars, status_callback, attach_to_existing, + headless_mode, ) def __init__( self, config: AppConfig, event_stream: EventStream, - sid: str = "default", + sid: str = 'default', plugins: list[PluginRequirement] | None = None, env_vars: dict[str, str] | None = None, status_callback: Callable | None = None, attach_to_existing: bool = False, + headless_mode: bool = True, ): self.config = config self._host_port = 30000 # initial dummy value self._container_port = 30001 # initial dummy value - self.api_url = f"{self.config.sandbox.local_runtime_url}:{self._container_port}" + self._vscode_url: str | None = None # initial dummy value + self._runtime_initialized: bool = False + self.api_url = f'{self.config.sandbox.local_runtime_url}:{self._container_port}' self.session = requests.Session() self.status_callback = status_callback @@ -178,8 +183,8 @@ def __init__( if self.config.sandbox.runtime_extra_deps: self.log( - "debug", - f"Installing extra user-provided dependencies in the runtime image: {self.config.sandbox.runtime_extra_deps}", + 'debug', + f'Installing extra user-provided dependencies in the runtime image: {self.config.sandbox.runtime_extra_deps}', ) self.init_base_runtime( @@ -190,25 +195,26 @@ def __init__( env_vars, status_callback, attach_to_existing, + headless_mode, ) async def connect(self): - self.send_status_message("STATUS$STARTING_RUNTIME") + self.send_status_message('STATUS$STARTING_RUNTIME') try: await call_sync_from_async(self._attach_to_container) except docker.errors.NotFound as e: if self.attach_to_existing: self.log( - "error", - f"Container {self.container_name} not found.", + 'error', + f'Container {self.container_name} not found.', ) raise e if self.runtime_container_image is None: if self.base_container_image is None: raise ValueError( - "Neither runtime container image nor base container image is set" + 'Neither runtime container image nor base container image is set' ) - self.send_status_message("STATUS$STARTING_CONTAINER") + self.send_status_message('STATUS$STARTING_CONTAINER') self.runtime_container_image = build_runtime_image( self.base_container_image, self.runtime_builder, @@ -218,29 +224,33 @@ async def connect(self): ) self.log( - "info", f"Starting runtime with image: {self.runtime_container_image}" + 'info', f'Starting runtime with image: {self.runtime_container_image}' ) await call_sync_from_async(self._init_container) - self.log("info", f"Container started: {self.container_name}") + self.log( + 'info', + f'Container started: {self.container_name}. VSCode URL: {self.vscode_url}', + ) if not self.attach_to_existing: - self.log("info", f"Waiting for client to become ready at {self.api_url}...") - self.send_status_message("STATUS$WAITING_FOR_CLIENT") + self.log('info', f'Waiting for client to become ready at {self.api_url}...') + self.send_status_message('STATUS$WAITING_FOR_CLIENT') await call_sync_from_async(self._wait_until_alive) if not self.attach_to_existing: - self.log("info", "Runtime is ready.") + self.log('info', 'Runtime is ready.') if not self.attach_to_existing: await call_sync_from_async(self.setup_initial_env) self.log( - "debug", - f"Container initialized with plugins: {[plugin.name for plugin in self.plugins]}", + 'debug', + f'Container initialized with plugins: {[plugin.name for plugin in self.plugins]}. VSCode URL: {self.vscode_url}', ) if not self.attach_to_existing: - self.send_status_message(" ") + self.send_status_message(' ') + self._runtime_initialized = True @staticmethod @lru_cache(maxsize=1) @@ -249,48 +259,55 @@ def _init_docker_client() -> docker.DockerClient: return docker.from_env() except Exception as ex: logger.error( - "Launch docker client failed. Please make sure you have installed docker and started docker desktop/daemon.", + 'Launch docker client failed. Please make sure you have installed docker and started docker desktop/daemon.', ) raise ex def _init_container(self): - self.log("debug", "Preparing to start container...") - self.send_status_message("STATUS$PREPARING_CONTAINER") - plugin_arg = "" + self.log('debug', 'Preparing to start container...') + self.send_status_message('STATUS$PREPARING_CONTAINER') + plugin_arg = '' if self.plugins is not None and len(self.plugins) > 0: plugin_arg = ( f'--plugins {" ".join([plugin.name for plugin in self.plugins])} ' ) - self._host_port = self._find_available_port() self._container_port = ( self._host_port ) # in future this might differ from host port - self.api_url = f"{self.config.sandbox.local_runtime_url}:{self._container_port}" + self.api_url = f'{self.config.sandbox.local_runtime_url}:{self._container_port}' use_host_network = self.config.sandbox.use_host_network - network_mode: str | None = "host" if use_host_network else None + network_mode: str | None = 'host' if use_host_network else None + port_mapping: dict[str, list[dict[str, str]]] | None = ( None if use_host_network - else {f"{self._container_port}/tcp": [{"HostPort": str(self._host_port)}]} + else {f'{self._container_port}/tcp': [{'HostPort': str(self._host_port)}]} ) if use_host_network: self.log( - "warn", - "Using host network mode. If you are using MacOS, please make sure you have the latest version of Docker Desktop and enabled host network feature: https://docs.docker.com/network/drivers/host/#docker-desktop", + 'warn', + 'Using host network mode. If you are using MacOS, please make sure you have the latest version of Docker Desktop and enabled host network feature: https://docs.docker.com/network/drivers/host/#docker-desktop', ) # Combine environment variables environment = { - "port": str(self._container_port), - "PYTHONUNBUFFERED": 1, + 'port': str(self._container_port), + 'PYTHONUNBUFFERED': 1, } if self.config.debug or DEBUG: - environment["DEBUG"] = "true" + environment['DEBUG'] = 'true' - self.log("debug", f"Workspace Base: {self.config.workspace_base}") + if self.vscode_enabled: + # vscode is on port +1 from container port + if isinstance(port_mapping, dict): + port_mapping[f'{self._container_port + 1}/tcp'] = [ + {'HostPort': str(self._host_port + 1)} + ] + + self.log('debug', f'Workspace Base: {self.config.workspace_base}') if ( self.config.workspace_mount_path is not None and self.config.workspace_mount_path_in_sandbox is not None @@ -298,27 +315,27 @@ def _init_container(self): # e.g. result would be: {"/home/user/openhands/workspace": {'bind': "/workspace", 'mode': 'rw'}} volumes = { self.config.workspace_mount_path: { - "bind": self.config.workspace_mount_path_in_sandbox, - "mode": "rw", + 'bind': self.config.workspace_mount_path_in_sandbox, + 'mode': 'rw', } } - logger.debug(f"Mount dir: {self.config.workspace_mount_path}") + logger.debug(f'Mount dir: {self.config.workspace_mount_path}') else: logger.debug( - "Mount dir is not set, will not mount the workspace directory to the container" + 'Mount dir is not set, will not mount the workspace directory to the container' ) volumes = None self.log( - "debug", - f"Sandbox workspace: {self.config.workspace_mount_path_in_sandbox}", + 'debug', + f'Sandbox workspace: {self.config.workspace_mount_path_in_sandbox}', ) if self.config.sandbox.browsergym_eval_env is not None: browsergym_arg = ( - f"--browsergym-eval-env {self.config.sandbox.browsergym_eval_env}" + f'--browsergym-eval-env {self.config.sandbox.browsergym_eval_env}' ) else: - browsergym_arg = "" + browsergym_arg = '' try: self.container = self.docker_client.containers.run( @@ -335,35 +352,35 @@ def _init_container(self): ), network_mode=network_mode, ports=port_mapping, - working_dir="/openhands/code/", # do not change this! + working_dir='/openhands/code/', # do not change this! name=self.container_name, detach=True, environment=environment, volumes=volumes, ) self.log_buffer = LogBuffer(self.container, self.log) - self.log("debug", f"Container started. Server url: {self.api_url}") - self.send_status_message("STATUS$CONTAINER_STARTED") + self.log('debug', f'Container started. Server url: {self.api_url}') + self.send_status_message('STATUS$CONTAINER_STARTED') except docker.errors.APIError as e: - if "409" in str(e): + if '409' in str(e): self.log( - "warning", - f"Container {self.container_name} already exists. Removing...", + 'warning', + f'Container {self.container_name} already exists. Removing...', ) remove_all_containers(self.container_name) return self._init_container() else: self.log( - "error", - f"Error: Instance {self.container_name} FAILED to start container!\n", + 'error', + f'Error: Instance {self.container_name} FAILED to start container!\n', ) except Exception as e: self.log( - "error", - f"Error: Instance {self.container_name} FAILED to start container!\n", + 'error', + f'Error: Instance {self.container_name} FAILED to start container!\n', ) - self.log("error", str(e)) + self.log('error', str(e)) self.close() raise e @@ -372,35 +389,35 @@ def _attach_to_container(self): self.log_buffer = LogBuffer(container, self.log) self.container = container self._container_port = 0 - for port in container.attrs["NetworkSettings"]["Ports"]: - self._container_port = int(port.split("/")[0]) + for port in container.attrs['NetworkSettings']['Ports']: + self._container_port = int(port.split('/')[0]) break self._host_port = self._container_port - self.api_url = f"{self.config.sandbox.local_runtime_url}:{self._container_port}" + self.api_url = f'{self.config.sandbox.local_runtime_url}:{self._container_port}' self.log( - "debug", - f"attached to container: {self.container_name} {self._container_port} {self.api_url}", + 'debug', + f'attached to container: {self.container_name} {self._container_port} {self.api_url}', ) def _refresh_logs(self): - self.log("debug", "Getting container logs...") + self.log('debug', 'Getting container logs...') assert ( self.log_buffer is not None - ), "Log buffer is expected to be initialized when container is started" + ), 'Log buffer is expected to be initialized when container is started' logs = self.log_buffer.get_and_clear() if logs: - formatted_logs = "\n".join([f" |{log}" for log in logs]) + formatted_logs = '\n'.join([f' |{log}' for log in logs]) self.log( - "debug", - "\n" - + "-" * 35 - + "Container logs:" - + "-" * 35 - + f"\n{formatted_logs}" - + "\n" - + "-" * 80, + 'debug', + '\n' + + '-' * 35 + + 'Container logs:' + + '-' * 35 + + f'\n{formatted_logs}' + + '\n' + + '-' * 80, ) @tenacity.retry( @@ -411,12 +428,12 @@ def _refresh_logs(self): def _wait_until_alive(self): self._refresh_logs() if not self.log_buffer: - raise RuntimeError("Runtime client is not ready.") + raise RuntimeError('Runtime client is not ready.') send_request( self.session, - "GET", - f"{self.api_url}/alive", + 'GET', + f'{self.api_url}/alive', timeout=5, ) @@ -449,27 +466,27 @@ def run_action(self, action: Action) -> Observation: with self.action_semaphore: if not action.runnable: - return NullObservation("") + return NullObservation('') if ( - hasattr(action, "confirmation_state") + hasattr(action, 'confirmation_state') and action.confirmation_state == ActionConfirmationStatus.AWAITING_CONFIRMATION ): - return NullObservation("") + return NullObservation('') action_type = action.action # type: ignore[attr-defined] if action_type not in ACTION_TYPE_TO_CLASS: - raise ValueError(f"Action {action_type} does not exist.") + raise ValueError(f'Action {action_type} does not exist.') if not hasattr(self, action_type): return ErrorObservation( - f"Action {action_type} is not supported in the current runtime.", - error_id="AGENT_ERROR$BAD_ACTION", + f'Action {action_type} is not supported in the current runtime.', + error_id='AGENT_ERROR$BAD_ACTION', ) if ( - getattr(action, "confirmation_state", None) + getattr(action, 'confirmation_state', None) == ActionConfirmationStatus.REJECTED ): return UserRejectObservation( - "Action has been rejected by the user! Waiting for further user input." + 'Action has been rejected by the user! Waiting for further user input.' ) self._refresh_logs() @@ -479,9 +496,9 @@ def run_action(self, action: Action) -> Observation: try: response = send_request( self.session, - "POST", - f"{self.api_url}/execute_action", - json={"action": event_to_dict(action)}, + 'POST', + f'{self.api_url}/execute_action', + json={'action': event_to_dict(action)}, # wait a few more seconds to get the timeout error from client side timeout=action.timeout + 5, ) @@ -490,7 +507,7 @@ def run_action(self, action: Action) -> Observation: obs._cause = action.id # type: ignore[attr-defined] except requests.Timeout: raise RuntimeError( - f"Runtime failed to return execute_action before the requested timeout of {action.timeout}s" + f'Runtime failed to return execute_action before the requested timeout of {action.timeout}s' ) self._refresh_logs() return obs @@ -521,18 +538,18 @@ def copy_to( self, host_src: str, sandbox_dest: str, recursive: bool = False ) -> None: if not os.path.exists(host_src): - raise FileNotFoundError(f"Source file {host_src} does not exist") + raise FileNotFoundError(f'Source file {host_src} does not exist') self._refresh_logs() try: if recursive: # For recursive copy, create a zip file with tempfile.NamedTemporaryFile( - suffix=".zip", delete=False + suffix='.zip', delete=False ) as temp_zip: temp_zip_path = temp_zip.name - with ZipFile(temp_zip_path, "w") as zipf: + with ZipFile(temp_zip_path, 'w') as zipf: for root, _, files in os.walk(host_src): for file in files: file_path = os.path.join(root, file) @@ -541,31 +558,31 @@ def copy_to( ) zipf.write(file_path, arcname) - upload_data = {"file": open(temp_zip_path, "rb")} + upload_data = {'file': open(temp_zip_path, 'rb')} else: # For single file copy - upload_data = {"file": open(host_src, "rb")} + upload_data = {'file': open(host_src, 'rb')} - params = {"destination": sandbox_dest, "recursive": str(recursive).lower()} + params = {'destination': sandbox_dest, 'recursive': str(recursive).lower()} send_request( self.session, - "POST", - f"{self.api_url}/upload_file", + 'POST', + f'{self.api_url}/upload_file', files=upload_data, params=params, timeout=300, ) except requests.Timeout: - raise TimeoutError("Copy operation timed out") + raise TimeoutError('Copy operation timed out') except Exception as e: - raise RuntimeError(f"Copy operation failed: {str(e)}") + raise RuntimeError(f'Copy operation failed: {str(e)}') finally: if recursive: os.unlink(temp_zip_path) self.log( - "debug", f"Copy completed: host:{host_src} -> runtime:{sandbox_dest}" + 'debug', f'Copy completed: host:{host_src} -> runtime:{sandbox_dest}' ) self._refresh_logs() @@ -578,12 +595,12 @@ def list_files(self, path: str | None = None) -> list[str]: try: data = {} if path is not None: - data["path"] = path + data['path'] = path response = send_request( self.session, - "POST", - f"{self.api_url}/list_files", + 'POST', + f'{self.api_url}/list_files', json=data, timeout=10, ) @@ -591,17 +608,17 @@ def list_files(self, path: str | None = None) -> list[str]: assert isinstance(response_json, list) return response_json except requests.Timeout: - raise TimeoutError("List files operation timed out") + raise TimeoutError('List files operation timed out') def copy_from(self, path: str) -> Path: """Zip all files in the sandbox and return as a stream of bytes.""" self._refresh_logs() try: - params = {"path": path} + params = {'path': path} response = send_request( self.session, - "GET", - f"{self.api_url}/download_files", + 'GET', + f'{self.api_url}/download_files', params=params, stream=True, timeout=30, @@ -612,7 +629,7 @@ def copy_from(self, path: str) -> Path: temp_file.write(chunk) return Path(temp_file.name) except requests.Timeout: - raise TimeoutError("Copy operation timed out") + raise TimeoutError('Copy operation timed out') def _is_port_in_use_docker(self, port): containers = self.docker_client.containers.list() @@ -630,3 +647,30 @@ def _find_available_port(self, max_attempts=5): return port # If no port is found after max_attempts, return the last tried port return port + + @property + def vscode_url(self) -> str | None: + if self.vscode_enabled and self._runtime_initialized: + if ( + hasattr(self, '_vscode_url') and self._vscode_url is not None + ): # cached value + return self._vscode_url + + response = send_request( + self.session, + 'GET', + f'{self.api_url}/vscode/connection_token', + timeout=10, + ) + response_json = response.json() + assert isinstance(response_json, dict) + if response_json['token'] is None: + return None + self._vscode_url = f'http://localhost:{self._host_port + 1}/?tkn={response_json["token"]}&folder={self.config.workspace_mount_path_in_sandbox}' + self.log( + 'debug', + f'VSCode URL: {self._vscode_url}', + ) + return self._vscode_url + else: + return None diff --git a/openhands/runtime/impl/modal/modal_runtime.py b/openhands/runtime/impl/modal/modal_runtime.py index a71021de8e9d..40014f8aa3c1 100644 --- a/openhands/runtime/impl/modal/modal_runtime.py +++ b/openhands/runtime/impl/modal/modal_runtime.py @@ -29,7 +29,7 @@ # Modal's log generator returns strings, but the upstream LogBuffer expects bytes. def bytes_shim(string_generator) -> Generator[bytes, None, None]: for line in string_generator: - yield line.encode("utf-8") + yield line.encode('utf-8') class ModalLogBuffer(LogBuffer): @@ -41,7 +41,7 @@ class ModalLogBuffer(LogBuffer): """ def __init__(self, sandbox: modal.Sandbox): - self.init_msg = "Runtime client initialized." + self.init_msg = 'Runtime client initialized.' self.buffer: list[str] = [] self.lock = threading.Lock() @@ -65,21 +65,22 @@ class ModalRuntime(EventStreamRuntime): env_vars (dict[str, str] | None, optional): Environment variables to set. Defaults to None. """ - container_name_prefix = "openhands-sandbox-" + container_name_prefix = 'openhands-sandbox-' sandbox: modal.Sandbox | None def __init__( self, config: AppConfig, event_stream: EventStream, - sid: str = "default", + sid: str = 'default', plugins: list[PluginRequirement] | None = None, env_vars: dict[str, str] | None = None, status_callback: Callable | None = None, attach_to_existing: bool = False, + headless_mode: bool = True, ): - assert config.modal_api_token_id, "Modal API token id is required" - assert config.modal_api_token_secret, "Modal API token secret is required" + assert config.modal_api_token_id, 'Modal API token id is required' + assert config.modal_api_token_secret, 'Modal API token secret is required' self.config = config self.sandbox = None @@ -88,14 +89,14 @@ def __init__( config.modal_api_token_id, config.modal_api_token_secret ) self.app = modal.App.lookup( - "openhands", create_if_missing=True, client=self.modal_client + 'openhands', create_if_missing=True, client=self.modal_client ) # workspace_base cannot be used because we can't bind mount into a sandbox. if self.config.workspace_base is not None: self.log( - "warning", - "Setting workspace_base is not supported in the modal runtime.", + 'warning', + 'Setting workspace_base is not supported in the modal runtime.', ) # This value is arbitrary as it's private to the container @@ -112,8 +113,8 @@ def __init__( if self.config.sandbox.runtime_extra_deps: self.log( - "debug", - f"Installing extra user-provided dependencies in the runtime image: {self.config.sandbox.runtime_extra_deps}", + 'debug', + f'Installing extra user-provided dependencies in the runtime image: {self.config.sandbox.runtime_extra_deps}', ) self.init_base_runtime( @@ -124,12 +125,13 @@ def __init__( env_vars, status_callback, attach_to_existing, + headless_mode, ) async def connect(self): - self.send_status_message("STATUS$STARTING_RUNTIME") + self.send_status_message('STATUS$STARTING_RUNTIME') - self.log("debug", f"ModalRuntime `{self.sid}`") + self.log('debug', f'ModalRuntime `{self.sid}`') self.image = self._get_image_definition( self.base_container_image_id, @@ -140,36 +142,36 @@ async def connect(self): if self.attach_to_existing: if self.sid in MODAL_RUNTIME_IDS: sandbox_id = MODAL_RUNTIME_IDS[self.sid] - self.log("debug", f"Attaching to existing Modal sandbox: {sandbox_id}") + self.log('debug', f'Attaching to existing Modal sandbox: {sandbox_id}') self.sandbox = modal.Sandbox.from_id( sandbox_id, client=self.modal_client ) else: - self.send_status_message("STATUS$PREPARING_CONTAINER") + self.send_status_message('STATUS$PREPARING_CONTAINER') await call_sync_from_async( self._init_sandbox, sandbox_workspace_dir=self.config.workspace_mount_path_in_sandbox, plugins=self.plugins, ) - self.send_status_message("STATUS$CONTAINER_STARTED") + self.send_status_message('STATUS$CONTAINER_STARTED') self.log_buffer = ModalLogBuffer(self.sandbox) if self.sandbox is None: - raise Exception("Sandbox not initialized") + raise Exception('Sandbox not initialized') tunnel = self.sandbox.tunnels()[self.container_port] self.api_url = tunnel.url - self.log("debug", f"Container started. Server url: {self.api_url}") + self.log('debug', f'Container started. Server url: {self.api_url}') if not self.attach_to_existing: - self.log("debug", "Waiting for client to become ready...") - self.send_status_message("STATUS$WAITING_FOR_CLIENT") + self.log('debug', 'Waiting for client to become ready...') + self.send_status_message('STATUS$WAITING_FOR_CLIENT') self._wait_until_alive() self.setup_initial_env() if not self.attach_to_existing: - self.send_status_message(" ") + self.send_status_message(' ') def _get_image_definition( self, @@ -189,15 +191,15 @@ def _get_image_definition( ) base_runtime_image = modal.Image.from_dockerfile( - path=os.path.join(build_folder, "Dockerfile"), + path=os.path.join(build_folder, 'Dockerfile'), context_mount=modal.Mount.from_local_dir( local_path=build_folder, - remote_path=".", # to current WORKDIR + remote_path='.', # to current WORKDIR ), ) else: raise ValueError( - "Neither runtime container image nor base container image is set" + 'Neither runtime container image nor base container image is set' ) return base_runtime_image.run_commands( @@ -219,43 +221,43 @@ def _init_sandbox( plugins: list[PluginRequirement] | None = None, ): try: - self.log("debug", "Preparing to start container...") + self.log('debug', 'Preparing to start container...') plugin_args = [] if plugins is not None and len(plugins) > 0: - plugin_args.append("--plugins") + plugin_args.append('--plugins') plugin_args.extend([plugin.name for plugin in plugins]) # Combine environment variables environment: dict[str, str | None] = { - "port": str(self.container_port), - "PYTHONUNBUFFERED": "1", + 'port': str(self.container_port), + 'PYTHONUNBUFFERED': '1', } if self.config.debug: - environment["DEBUG"] = "true" + environment['DEBUG'] = 'true' browsergym_args = [] if self.config.sandbox.browsergym_eval_env is not None: browsergym_args = [ - "-browsergym-eval-env", + '-browsergym-eval-env', self.config.sandbox.browsergym_eval_env, ] env_secret = modal.Secret.from_dict(environment) - self.log("debug", f"Sandbox workspace: {sandbox_workspace_dir}") + self.log('debug', f'Sandbox workspace: {sandbox_workspace_dir}') sandbox_start_cmd = get_remote_startup_command( self.container_port, sandbox_workspace_dir, - "openhands" if self.config.run_as_openhands else "root", + 'openhands' if self.config.run_as_openhands else 'root', self.config.sandbox.user_id, plugin_args, browsergym_args, ) - self.log("debug", f"Starting container with command: {sandbox_start_cmd}") + self.log('debug', f'Starting container with command: {sandbox_start_cmd}') self.sandbox = modal.Sandbox.create( *sandbox_start_cmd, secrets=[env_secret], - workdir="/openhands/code", + workdir='/openhands/code', encrypted_ports=[self.container_port], image=self.image, app=self.app, @@ -263,13 +265,13 @@ def _init_sandbox( timeout=60 * 60, ) MODAL_RUNTIME_IDS[self.sid] = self.sandbox.object_id - self.log("debug", "Container started") + self.log('debug', 'Container started') except Exception as e: self.log( - "error", f"Error: Instance {self.sid} FAILED to start container!\n" + 'error', f'Error: Instance {self.sid} FAILED to start container!\n' ) - self.log("error", str(e)) + self.log('error', str(e)) self.close() raise e diff --git a/openhands/runtime/impl/remote/remote_runtime.py b/openhands/runtime/impl/remote/remote_runtime.py index 3a26fc65f7df..8c9843de98b4 100644 --- a/openhands/runtime/impl/remote/remote_runtime.py +++ b/openhands/runtime/impl/remote/remote_runtime.py @@ -3,6 +3,7 @@ import threading from pathlib import Path from typing import Callable, Optional +from urllib.parse import urlparse from zipfile import ZipFile import requests @@ -52,11 +53,12 @@ def __init__( self, config: AppConfig, event_stream: EventStream, - sid: str = "default", + sid: str = 'default', plugins: list[PluginRequirement] | None = None, env_vars: dict[str, str] | None = None, status_callback: Optional[Callable] = None, attach_to_existing: bool = False, + headless_mode: bool = True, ): # We need to set session and action_semaphore before the __init__ below, or we get odd errors self.session = requests.Session() @@ -70,18 +72,19 @@ def __init__( env_vars, status_callback, attach_to_existing, + headless_mode, ) if self.config.sandbox.api_key is None: raise ValueError( - "API key is required to use the remote runtime. " - "Please set the API key in the config (config.toml) or as an environment variable (SANDBOX_API_KEY)." + 'API key is required to use the remote runtime. ' + 'Please set the API key in the config (config.toml) or as an environment variable (SANDBOX_API_KEY).' ) - self.session.headers.update({"X-API-Key": self.config.sandbox.api_key}) + self.session.headers.update({'X-API-Key': self.config.sandbox.api_key}) if self.config.workspace_base is not None: self.log( - "debug", - "Setting workspace_base is not supported in the remote runtime.", + 'debug', + 'Setting workspace_base is not supported in the remote runtime.', ) self.runtime_builder = RemoteRuntimeBuilder( @@ -89,103 +92,106 @@ def __init__( ) self.runtime_id: str | None = None self.runtime_url: str | None = None + self._runtime_initialized: bool = False + self._vscode_url: str | None = None # initial dummy value async def connect(self): try: await call_sync_from_async(self._start_or_attach_to_runtime) except RuntimeNotReadyError: - self.log("error", "Runtime failed to start, timed out before ready") + self.log('error', 'Runtime failed to start, timed out before ready') raise await call_sync_from_async(self.setup_initial_env) + self._runtime_initialized = True def _start_or_attach_to_runtime(self): existing_runtime = self._check_existing_runtime() if existing_runtime: - self.log("debug", f"Using existing runtime with ID: {self.runtime_id}") + self.log('debug', f'Using existing runtime with ID: {self.runtime_id}') elif self.attach_to_existing: - raise RuntimeError("Could not find existing runtime to attach to.") + raise RuntimeError('Could not find existing runtime to attach to.') else: - self.send_status_message("STATUS$STARTING_CONTAINER") + self.send_status_message('STATUS$STARTING_CONTAINER') if self.config.sandbox.runtime_container_image is None: self.log( - "info", - f"Building remote runtime with base image: {self.config.sandbox.base_container_image}", + 'info', + f'Building remote runtime with base image: {self.config.sandbox.base_container_image}', ) self._build_runtime() else: self.log( - "info", - f"Starting remote runtime with image: {self.config.sandbox.runtime_container_image}", + 'info', + f'Starting remote runtime with image: {self.config.sandbox.runtime_container_image}', ) self.container_image = self.config.sandbox.runtime_container_image self._start_runtime() assert ( self.runtime_id is not None - ), "Runtime ID is not set. This should never happen." + ), 'Runtime ID is not set. This should never happen.' assert ( self.runtime_url is not None - ), "Runtime URL is not set. This should never happen." - self.send_status_message("STATUS$WAITING_FOR_CLIENT") + ), 'Runtime URL is not set. This should never happen.' + self.send_status_message('STATUS$WAITING_FOR_CLIENT') if not self.attach_to_existing: - self.log("info", "Waiting for runtime to be alive...") + self.log('info', 'Waiting for runtime to be alive...') self._wait_until_alive() if not self.attach_to_existing: - self.log("info", "Runtime is ready.") - self.send_status_message(" ") + self.log('info', 'Runtime is ready.') + self.send_status_message(' ') def _check_existing_runtime(self) -> bool: try: response = self._send_request( - "GET", - f"{self.config.sandbox.remote_runtime_api_url}/sessions/{self.sid}", + 'GET', + f'{self.config.sandbox.remote_runtime_api_url}/sessions/{self.sid}', is_retry=False, timeout=5, ) except requests.HTTPError as e: if e.response.status_code == 404: return False - self.log("debug", f"Error while looking for remote runtime: {e}") + self.log('debug', f'Error while looking for remote runtime: {e}') raise data = response.json() - status = data.get("status") - if status == "running": + status = data.get('status') + if status == 'running': self._parse_runtime_response(response) return True - elif status == "stopped": - self.log("debug", "Found existing remote runtime, but it is stopped") + elif status == 'stopped': + self.log('debug', 'Found existing remote runtime, but it is stopped') return False - elif status == "paused": - self.log("debug", "Found existing remote runtime, but it is paused") + elif status == 'paused': + self.log('debug', 'Found existing remote runtime, but it is paused') self._parse_runtime_response(response) self._resume_runtime() return True else: - self.log("error", f"Invalid response from runtime API: {data}") + self.log('error', f'Invalid response from runtime API: {data}') return False def _build_runtime(self): - self.log("debug", f"Building RemoteRuntime config:\n{self.config}") + self.log('debug', f'Building RemoteRuntime config:\n{self.config}') response = self._send_request( - "GET", - f"{self.config.sandbox.remote_runtime_api_url}/registry_prefix", + 'GET', + f'{self.config.sandbox.remote_runtime_api_url}/registry_prefix', is_retry=False, timeout=10, ) response_json = response.json() - registry_prefix = response_json["registry_prefix"] - os.environ["OH_RUNTIME_RUNTIME_IMAGE_REPO"] = ( - registry_prefix.rstrip("/") + "/runtime" + registry_prefix = response_json['registry_prefix'] + os.environ['OH_RUNTIME_RUNTIME_IMAGE_REPO'] = ( + registry_prefix.rstrip('/') + '/runtime' ) self.log( - "debug", + 'debug', f'Runtime image repo: {os.environ["OH_RUNTIME_RUNTIME_IMAGE_REPO"]}', ) if self.config.sandbox.runtime_extra_deps: self.log( - "debug", - f"Installing extra user-provided dependencies in the runtime image: {self.config.sandbox.runtime_extra_deps}", + 'debug', + f'Installing extra user-provided dependencies in the runtime image: {self.config.sandbox.runtime_extra_deps}', ) # Build the container image @@ -198,73 +204,110 @@ def _build_runtime(self): ) response = self._send_request( - "GET", - f"{self.config.sandbox.remote_runtime_api_url}/image_exists", + 'GET', + f'{self.config.sandbox.remote_runtime_api_url}/image_exists', is_retry=False, - params={"image": self.container_image}, + params={'image': self.container_image}, timeout=10, ) - if not response.json()["exists"]: - raise RuntimeError(f"Container image {self.container_image} does not exist") + if not response.json()['exists']: + raise RuntimeError(f'Container image {self.container_image} does not exist') def _start_runtime(self): # Prepare the request body for the /start endpoint plugin_args = [] if self.plugins is not None and len(self.plugins) > 0: - plugin_args = ["--plugins"] + [plugin.name for plugin in self.plugins] + plugin_args = ['--plugins'] + [plugin.name for plugin in self.plugins] browsergym_args = [] if self.config.sandbox.browsergym_eval_env is not None: browsergym_args = [ - "--browsergym-eval-env" - ] + self.config.sandbox.browsergym_eval_env.split(" ") + '--browsergym-eval-env' + ] + self.config.sandbox.browsergym_eval_env.split(' ') command = get_remote_startup_command( self.port, self.config.workspace_mount_path_in_sandbox, - "openhands" if self.config.run_as_openhands else "root", + 'openhands' if self.config.run_as_openhands else 'root', self.config.sandbox.user_id, plugin_args, browsergym_args, ) start_request = { - "image": self.container_image, - "command": command, - "working_dir": "/openhands/code/", - "environment": {"DEBUG": "true"} if self.config.debug else {}, - "session_id": self.sid, + 'image': self.container_image, + 'command': command, + 'working_dir': '/openhands/code/', + 'environment': {'DEBUG': 'true'} if self.config.debug else {}, + 'session_id': self.sid, } # Start the sandbox using the /start endpoint response = self._send_request( - "POST", - f"{self.config.sandbox.remote_runtime_api_url}/start", + 'POST', + f'{self.config.sandbox.remote_runtime_api_url}/start', is_retry=False, json=start_request, ) self._parse_runtime_response(response) self.log( - "debug", - f"Runtime started. URL: {self.runtime_url}", + 'debug', + f'Runtime started. URL: {self.runtime_url}', ) def _resume_runtime(self): self._send_request( - "POST", - f"{self.config.sandbox.remote_runtime_api_url}/resume", + 'POST', + f'{self.config.sandbox.remote_runtime_api_url}/resume', is_retry=False, - json={"runtime_id": self.runtime_id}, + json={'runtime_id': self.runtime_id}, timeout=30, ) - self.log("debug", "Runtime resumed.") + self.log('debug', 'Runtime resumed.') def _parse_runtime_response(self, response: requests.Response): start_response = response.json() - self.runtime_id = start_response["runtime_id"] - self.runtime_url = start_response["url"] - if "session_api_key" in start_response: + self.runtime_id = start_response['runtime_id'] + self.runtime_url = start_response['url'] + if 'session_api_key' in start_response: self.session.headers.update( - {"X-Session-API-Key": start_response["session_api_key"]} + {'X-Session-API-Key': start_response['session_api_key']} ) + @property + def vscode_url(self) -> str | None: + if self.vscode_enabled and self._runtime_initialized: + if ( + hasattr(self, '_vscode_url') and self._vscode_url is not None + ): # cached value + return self._vscode_url + + response = self._send_request( + 'GET', + f'{self.runtime_url}/vscode/connection_token', + timeout=10, + ) + response_json = response.json() + assert isinstance(response_json, dict) + if response_json['token'] is None: + return None + # parse runtime_url to get vscode_url + _parsed_url = urlparse(self.runtime_url) + assert isinstance(_parsed_url.scheme, str) and isinstance( + _parsed_url.netloc, str + ) + self._vscode_url = f'{_parsed_url.scheme}://vscode-{_parsed_url.netloc}/?tkn={response_json["token"]}&folder={self.config.workspace_mount_path_in_sandbox}' + self.log( + 'debug', + f'VSCode URL: {self._vscode_url}', + ) + return self._vscode_url + else: + return None + + @tenacity.retry( + stop=tenacity.stop_after_delay(180) | stop_if_should_exit(), + reraise=True, + retry=tenacity.retry_if_exception_type(RuntimeNotReadyError), + wait=tenacity.wait_fixed(2), + ) def _wait_until_alive(self): retry_decorator = tenacity.retry( stop=tenacity.stop_after_delay( @@ -278,56 +321,56 @@ def _wait_until_alive(self): return retry_decorator(self._wait_until_alive_impl)() def _wait_until_alive_impl(self): - self.log("debug", f"Waiting for runtime to be alive at url: {self.runtime_url}") + self.log('debug', f'Waiting for runtime to be alive at url: {self.runtime_url}') runtime_info_response = self._send_request( - "GET", - f"{self.config.sandbox.remote_runtime_api_url}/sessions/{self.sid}", + 'GET', + f'{self.config.sandbox.remote_runtime_api_url}/sessions/{self.sid}', ) runtime_data = runtime_info_response.json() - assert "runtime_id" in runtime_data - assert runtime_data["runtime_id"] == self.runtime_id - assert "pod_status" in runtime_data - pod_status = runtime_data["pod_status"] - self.log("debug", f"Pod status: {pod_status}") + assert 'runtime_id' in runtime_data + assert runtime_data['runtime_id'] == self.runtime_id + assert 'pod_status' in runtime_data + pod_status = runtime_data['pod_status'] + self.log('debug', f'Pod status: {pod_status}') # FIXME: We should fix it at the backend of /start endpoint, make sure # the pod is created before returning the response. # Retry a period of time to give the cluster time to start the pod - if pod_status == "Ready": + if pod_status == 'Ready': try: self._send_request( - "GET", - f"{self.runtime_url}/alive", + 'GET', + f'{self.runtime_url}/alive', ) # will raise exception if we don't get 200 back. except requests.HTTPError as e: self.log( - "warning", f"Runtime /alive failed, but pod says it's ready: {e}" + 'warning', f"Runtime /alive failed, but pod says it's ready: {e}" ) raise RuntimeNotReadyError( - f"Runtime /alive failed to respond with 200: {e}" + f'Runtime /alive failed to respond with 200: {e}' ) return elif ( - pod_status == "Not Found" - or pod_status == "Pending" - or pod_status == "Running" + pod_status == 'Not Found' + or pod_status == 'Pending' + or pod_status == 'Running' ): # nb: Running is not yet Ready raise RuntimeNotReadyError( - f"Runtime (ID={self.runtime_id}) is not yet ready. Status: {pod_status}" + f'Runtime (ID={self.runtime_id}) is not yet ready. Status: {pod_status}' ) - elif pod_status in ("Failed", "Unknown"): + elif pod_status in ('Failed', 'Unknown'): # clean up the runtime self.close() raise RuntimeError( - f"Runtime (ID={self.runtime_id}) failed to start. Current status: {pod_status}" + f'Runtime (ID={self.runtime_id}) failed to start. Current status: {pod_status}' ) else: # Maybe this should be a hard failure, but passing through in case the API changes - self.log("warning", f"Unknown pod status: {pod_status}") + self.log('warning', f'Unknown pod status: {pod_status}') self.log( - "debug", - f"Waiting for runtime pod to be active. Current status: {pod_status}", + 'debug', + f'Waiting for runtime pod to be active. Current status: {pod_status}', ) raise RuntimeNotReadyError() @@ -338,19 +381,19 @@ def close(self, timeout: int = 10): if self.runtime_id and self.session: try: response = self._send_request( - "POST", - f"{self.config.sandbox.remote_runtime_api_url}/stop", + 'POST', + f'{self.config.sandbox.remote_runtime_api_url}/stop', is_retry=False, - json={"runtime_id": self.runtime_id}, + json={'runtime_id': self.runtime_id}, timeout=timeout, ) if response.status_code != 200: self.log( - "error", - f"Failed to stop runtime: {response.text}", + 'error', + f'Failed to stop runtime: {response.text}', ) else: - self.log("debug", "Runtime stopped.") + self.log('debug', 'Runtime stopped.') except Exception as e: raise e finally: @@ -363,24 +406,24 @@ def run_action(self, action: Action, is_retry: bool = False) -> Observation: return self.edit(action) with self.action_semaphore: if not action.runnable: - return NullObservation("") + return NullObservation('') action_type = action.action # type: ignore[attr-defined] if action_type not in ACTION_TYPE_TO_CLASS: - raise ValueError(f"Action {action_type} does not exist.") + raise ValueError(f'Action {action_type} does not exist.') if not hasattr(self, action_type): return ErrorObservation( - f"[Runtime (ID={self.runtime_id})] Action {action_type} is not supported in the current runtime.", - error_id="AGENT_ERROR$BAD_ACTION", + f'[Runtime (ID={self.runtime_id})] Action {action_type} is not supported in the current runtime.', + error_id='AGENT_ERROR$BAD_ACTION', ) assert action.timeout is not None try: - request_body = {"action": event_to_dict(action)} - self.log("debug", f"Request body: {request_body}") + request_body = {'action': event_to_dict(action)} + self.log('debug', f'Request body: {request_body}') response = self._send_request( - "POST", - f"{self.runtime_url}/execute_action", + 'POST', + f'{self.runtime_url}/execute_action', is_retry=False, json=request_body, # wait a few more seconds to get the timeout error from client side @@ -391,7 +434,7 @@ def run_action(self, action: Action, is_retry: bool = False) -> Observation: obs._cause = action.id # type: ignore[attr-defined] except requests.Timeout: raise RuntimeError( - f"Runtime failed to return execute_action before the requested timeout of {action.timeout}s" + f'Runtime failed to return execute_action before the requested timeout of {action.timeout}s' ) return obs @@ -400,16 +443,16 @@ def _send_request(self, method, url, is_retry=False, **kwargs): try: return send_request(self.session, method, url, **kwargs) except requests.Timeout: - self.log("error", "No response received within the timeout period.") + self.log('error', 'No response received within the timeout period.') raise except requests.HTTPError as e: if is_runtime_request and e.response.status_code == 404: raise RuntimeDisconnectedError( - f"404 error while connecting to {self.runtime_url}" + f'404 error while connecting to {self.runtime_url}' ) elif is_runtime_request and e.response.status_code == 503: if not is_retry: - self.log("warning", "Runtime appears to be paused. Resuming...") + self.log('warning', 'Runtime appears to be paused. Resuming...') self._resume_runtime() self._wait_until_alive() return self._send_request(method, url, True, **kwargs) @@ -441,16 +484,16 @@ def copy_to( self, host_src: str, sandbox_dest: str, recursive: bool = False ) -> None: if not os.path.exists(host_src): - raise FileNotFoundError(f"Source file {host_src} does not exist") + raise FileNotFoundError(f'Source file {host_src} does not exist') try: if recursive: with tempfile.NamedTemporaryFile( - suffix=".zip", delete=False + suffix='.zip', delete=False ) as temp_zip: temp_zip_path = temp_zip.name - with ZipFile(temp_zip_path, "w") as zipf: + with ZipFile(temp_zip_path, 'w') as zipf: for root, _, files in os.walk(host_src): for file in files: file_path = os.path.join(root, file) @@ -459,39 +502,39 @@ def copy_to( ) zipf.write(file_path, arcname) - upload_data = {"file": open(temp_zip_path, "rb")} + upload_data = {'file': open(temp_zip_path, 'rb')} else: - upload_data = {"file": open(host_src, "rb")} + upload_data = {'file': open(host_src, 'rb')} - params = {"destination": sandbox_dest, "recursive": str(recursive).lower()} + params = {'destination': sandbox_dest, 'recursive': str(recursive).lower()} response = self._send_request( - "POST", - f"{self.runtime_url}/upload_file", + 'POST', + f'{self.runtime_url}/upload_file', is_retry=False, files=upload_data, params=params, timeout=300, ) self.log( - "debug", - f"Copy completed: host:{host_src} -> runtime:{sandbox_dest}. Response: {response.text}", + 'debug', + f'Copy completed: host:{host_src} -> runtime:{sandbox_dest}. Response: {response.text}', ) finally: if recursive: os.unlink(temp_zip_path) self.log( - "debug", f"Copy completed: host:{host_src} -> runtime:{sandbox_dest}" + 'debug', f'Copy completed: host:{host_src} -> runtime:{sandbox_dest}' ) def list_files(self, path: str | None = None) -> list[str]: data = {} if path is not None: - data["path"] = path + data['path'] = path response = self._send_request( - "POST", - f"{self.runtime_url}/list_files", + 'POST', + f'{self.runtime_url}/list_files', is_retry=False, json=data, timeout=30, @@ -502,10 +545,10 @@ def list_files(self, path: str | None = None) -> list[str]: def copy_from(self, path: str) -> Path: """Zip all files in the sandbox and return as a stream of bytes.""" - params = {"path": path} + params = {'path': path} response = self._send_request( - "GET", - f"{self.runtime_url}/download_files", + 'GET', + f'{self.runtime_url}/download_files', is_retry=False, params=params, stream=True, diff --git a/openhands/runtime/impl/runloop/runloop_runtime.py b/openhands/runtime/impl/runloop/runloop_runtime.py index 7e052f2e73b6..36ad4590b7a5 100644 --- a/openhands/runtime/impl/runloop/runloop_runtime.py +++ b/openhands/runtime/impl/runloop/runloop_runtime.py @@ -21,7 +21,7 @@ from openhands.runtime.utils.request import send_request from openhands.utils.tenacity_stop import stop_if_should_exit -CONTAINER_NAME_PREFIX = "openhands-runtime-" +CONTAINER_NAME_PREFIX = 'openhands-runtime-' class RunloopLogBuffer(LogBuffer): @@ -34,7 +34,7 @@ class RunloopLogBuffer(LogBuffer): def __init__(self, runloop_api_client: Runloop, devbox_id: str): self.client_ready = False - self.init_msg = "Runtime client initialized." + self.init_msg = 'Runtime client initialized.' self.buffer: list[str] = [] self.lock = threading.Lock() @@ -52,6 +52,7 @@ def stream_logs(self): This method runs in its own thread to handle the blocking operation of reading log lines from the Docker SDK's synchronous generator. """ + try: # TODO(Runloop) Replace with stream while True: @@ -75,7 +76,7 @@ def stream_logs(self): time.sleep(1) except Exception as e: - logger.error(f"Error streaming runloop logs: {e}") + logger.error(f'Error streaming runloop logs: {e}') # NB: Match LogBuffer behavior on below methods @@ -103,13 +104,13 @@ def __init__( self, config: AppConfig, event_stream: EventStream, - sid: str = "default", + sid: str = 'default', plugins: list[PluginRequirement] | None = None, env_vars: dict[str, str] | None = None, status_callback: Callable | None = None, attach_to_existing: bool = False, ): - assert config.runloop_api_key is not None, "Runloop API key is required" + assert config.runloop_api_key is not None, 'Runloop API key is required' self.devbox: DevboxView | None = None self.config = config self.runloop_api_client = Runloop( @@ -136,15 +137,15 @@ def __init__( ) def _wait_for_devbox(self, devbox: DevboxView) -> DevboxView: """Pull devbox status until it is running""" - if devbox == "running": + if devbox == 'running': return devbox devbox = self.runloop_api_client.devboxes.retrieve(id=devbox.id) - if devbox.status != "running": - raise ConnectionRefusedError("Devbox is not running") + if devbox.status != 'running': + raise ConnectionRefusedError('Devbox is not running') # Devbox is connected and running - logging.debug(f"devbox.id={devbox.id} is running") + logging.debug(f'devbox.id={devbox.id} is running') return devbox def _create_new_devbox(self) -> DevboxView: @@ -152,13 +153,13 @@ def _create_new_devbox(self) -> DevboxView: sandbox_workspace_dir = self.config.workspace_mount_path_in_sandbox plugin_args = [] if self.plugins is not None and len(self.plugins) > 0: - plugin_args.append("--plugins") + plugin_args.append('--plugins') plugin_args.extend([plugin.name for plugin in self.plugins]) browsergym_args = [] if self.config.sandbox.browsergym_eval_env is not None: browsergym_args = [ - "-browsergym-eval-env", + '-browsergym-eval-env', self.config.sandbox.browsergym_eval_env, ] @@ -166,7 +167,7 @@ def _create_new_devbox(self) -> DevboxView: start_command = get_remote_startup_command( self._sandbox_port, sandbox_workspace_dir, - "openhands" if self.config.run_as_openhands else "root", + 'openhands' if self.config.run_as_openhands else 'root', self.config.sandbox.user_id, plugin_args, browsergym_args, @@ -176,33 +177,33 @@ def _create_new_devbox(self) -> DevboxView: # NB: start off as root, action_execution_server will ultimately choose user but expects all context # (ie browser) to be installed as root start_command = ( - "export MAMBA_ROOT_PREFIX=/openhands/micromamba && " - "cd /openhands/code && " - + "/openhands/micromamba/bin/micromamba run -n openhands poetry config virtualenvs.path /openhands/poetry && " - + " ".join(start_command) + 'export MAMBA_ROOT_PREFIX=/openhands/micromamba && ' + 'cd /openhands/code && ' + + '/openhands/micromamba/bin/micromamba run -n openhands poetry config virtualenvs.path /openhands/poetry && ' + + ' '.join(start_command) ) entrypoint = f"sudo bash -c '{start_command}'" devbox = self.runloop_api_client.devboxes.create( entrypoint=entrypoint, - setup_commands=[f"mkdir -p {self.config.workspace_mount_path_in_sandbox}"], + setup_commands=[f'mkdir -p {self.config.workspace_mount_path_in_sandbox}'], name=self.sid, - environment_variables={"DEBUG": "true"} if self.config.debug else {}, - prebuilt="openhands", + environment_variables={'DEBUG': 'true'} if self.config.debug else {}, + prebuilt='openhands', launch_parameters=LaunchParameters( available_ports=[self._sandbox_port], - resource_size_request="LARGE", + resource_size_request='LARGE', ), - metadata={"container-name": self.container_name}, + metadata={'container-name': self.container_name}, ) return self._wait_for_devbox(devbox) async def connect(self): - self.send_status_message("STATUS$STARTING_RUNTIME") + self.send_status_message('STATUS$STARTING_RUNTIME') if self.attach_to_existing: active_devboxes = self.runloop_api_client.devboxes.list( - status="running" + status='running' ).devboxes self.devbox = next( (devbox for devbox in active_devboxes if devbox.name == self.sid), None @@ -219,22 +220,22 @@ async def connect(self): # Hook up logs self.log_buffer = RunloopLogBuffer(self.runloop_api_client, self.devbox.id) - self.api_url = f"https://{tunnel.url}" - logger.info(f"Container started. Server url: {self.api_url}") + self.api_url = f'https://{tunnel.url}' + logger.info(f'Container started. Server url: {self.api_url}') # End Runloop connect # NOTE: Copied from EventStreamRuntime - logger.info("Waiting for client to become ready...") - self.send_status_message("STATUS$WAITING_FOR_CLIENT") + logger.info('Waiting for client to become ready...') + self.send_status_message('STATUS$WAITING_FOR_CLIENT') self._wait_until_alive() if not self.attach_to_existing: self.setup_initial_env() logger.info( - f"Container initialized with plugins: {[plugin.name for plugin in self.plugins]}" + f'Container initialized with plugins: {[plugin.name for plugin in self.plugins]}' ) - self.send_status_message(" ") + self.send_status_message(' ') @tenacity.retry( stop=tenacity.stop_after_delay(120) | stop_if_should_exit(), @@ -245,17 +246,17 @@ def _wait_until_alive(self): # NB(Runloop): Remote logs are not guaranteed realtime, removing client_ready check from logs self._refresh_logs() if not self.log_buffer: - raise RuntimeError("Runtime client is not ready.") + raise RuntimeError('Runtime client is not ready.') response = send_request( self.session, - "GET", - f"{self.api_url}/alive", + 'GET', + f'{self.api_url}/alive', timeout=5, ) if response.status_code == 200: return else: - msg = f"Action execution API is not alive. Response: {response}" + msg = f'Action execution API is not alive. Response: {response}' logger.error(msg) raise RuntimeError(msg) diff --git a/openhands/runtime/plugins/__init__.py b/openhands/runtime/plugins/__init__.py index 25bc9cf4cc97..e8a30ef04acc 100644 --- a/openhands/runtime/plugins/__init__.py +++ b/openhands/runtime/plugins/__init__.py @@ -5,17 +5,21 @@ ) from openhands.runtime.plugins.jupyter import JupyterPlugin, JupyterRequirement from openhands.runtime.plugins.requirement import Plugin, PluginRequirement +from openhands.runtime.plugins.vscode import VSCodePlugin, VSCodeRequirement __all__ = [ - "Plugin", - "PluginRequirement", - "AgentSkillsRequirement", - "AgentSkillsPlugin", - "JupyterRequirement", - "JupyterPlugin", + 'Plugin', + 'PluginRequirement', + 'AgentSkillsRequirement', + 'AgentSkillsPlugin', + 'JupyterRequirement', + 'JupyterPlugin', + 'VSCodeRequirement', + 'VSCodePlugin', ] ALL_PLUGINS = { - "jupyter": JupyterPlugin, - "agent_skills": AgentSkillsPlugin, + 'jupyter': JupyterPlugin, + 'agent_skills': AgentSkillsPlugin, + 'vscode': VSCodePlugin, } diff --git a/openhands/runtime/plugins/agent_skills/__init__.py b/openhands/runtime/plugins/agent_skills/__init__.py index afaa0e3b74f1..01f9d7e028ee 100644 --- a/openhands/runtime/plugins/agent_skills/__init__.py +++ b/openhands/runtime/plugins/agent_skills/__init__.py @@ -6,9 +6,9 @@ @dataclass class AgentSkillsRequirement(PluginRequirement): - name: str = "agent_skills" + name: str = 'agent_skills' documentation: str = agentskills.DOCUMENTATION class AgentSkillsPlugin(Plugin): - name: str = "agent_skills" + name: str = 'agent_skills' diff --git a/openhands/runtime/plugins/agent_skills/agentskills.py b/openhands/runtime/plugins/agent_skills/agentskills.py index b1d88cb470ee..046f8af20c61 100644 --- a/openhands/runtime/plugins/agent_skills/agentskills.py +++ b/openhands/runtime/plugins/agent_skills/agentskills.py @@ -11,21 +11,21 @@ ) __all__ = file_ops.__all__ + file_reader.__all__ -DOCUMENTATION = "" +DOCUMENTATION = '' for func_name in __all__: func = globals()[func_name] cur_doc = func.__doc__ # remove indentation from docstring and extra empty lines - cur_doc = "\n".join(filter(None, map(lambda x: x.strip(), cur_doc.split("\n")))) + cur_doc = '\n'.join(filter(None, map(lambda x: x.strip(), cur_doc.split('\n')))) # now add a consistent 4 indentation - cur_doc = "\n".join(map(lambda x: " " * 4 + x, cur_doc.split("\n"))) + cur_doc = '\n'.join(map(lambda x: ' ' * 4 + x, cur_doc.split('\n'))) - fn_signature = f"{func.__name__}" + str(signature(func)) - DOCUMENTATION += f"{fn_signature}:\n{cur_doc}\n\n" + fn_signature = f'{func.__name__}' + str(signature(func)) + DOCUMENTATION += f'{fn_signature}:\n{cur_doc}\n\n' # Add file_editor (a function) from openhands.runtime.plugins.agent_skills.file_editor import file_editor # noqa: E402 -__all__ += ["file_editor"] +__all__ += ['file_editor'] diff --git a/openhands/runtime/plugins/agent_skills/file_editor/__init__.py b/openhands/runtime/plugins/agent_skills/file_editor/__init__.py index 8fdfd6761be6..06d5bcca6325 100644 --- a/openhands/runtime/plugins/agent_skills/file_editor/__init__.py +++ b/openhands/runtime/plugins/agent_skills/file_editor/__init__.py @@ -5,4 +5,4 @@ from openhands_aci.editor import file_editor -__all__ = ["file_editor"] +__all__ = ['file_editor'] diff --git a/openhands/runtime/plugins/agent_skills/file_ops/file_ops.py b/openhands/runtime/plugins/agent_skills/file_ops/file_ops.py index ada615f4ec13..b2e1b4c8aa4c 100644 --- a/openhands/runtime/plugins/agent_skills/file_ops/file_ops.py +++ b/openhands/runtime/plugins/agent_skills/file_ops/file_ops.py @@ -21,15 +21,15 @@ WINDOW = 100 # This is also used in unit tests! -MSG_FILE_UPDATED = "[File updated (edited at line {line_number}). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]" -LINTER_ERROR_MSG = "[Your proposed edit has introduced new syntax error(s). Please understand the errors and retry your edit command.]\n" +MSG_FILE_UPDATED = '[File updated (edited at line {line_number}). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]' +LINTER_ERROR_MSG = '[Your proposed edit has introduced new syntax error(s). Please understand the errors and retry your edit command.]\n' # ================================================================================================== def _output_error(error_msg: str) -> bool: - print(f"ERROR: {error_msg}") + print(f'ERROR: {error_msg}') return False @@ -37,10 +37,10 @@ def _is_valid_filename(file_name) -> bool: if not file_name or not isinstance(file_name, str) or not file_name.strip(): return False invalid_chars = '<>:"/\\|?*' - if os.name == "nt": # Windows + if os.name == 'nt': # Windows invalid_chars = '<>:"/\\|?*' - elif os.name == "posix": # Unix-like systems - invalid_chars = "\0" + elif os.name == 'posix': # Unix-like systems + invalid_chars = '\0' for char in invalid_chars: if char in file_name: @@ -72,7 +72,7 @@ def _check_current_file(file_path: str | None = None) -> bool: if not file_path: file_path = CURRENT_FILE if not file_path or not os.path.isfile(file_path): - return _output_error("No file open. Use the open_file function first.") + return _output_error('No file open. Use the open_file function first.') return True @@ -93,8 +93,8 @@ def _lint_file(file_path: str) -> tuple[str | None, int | None]: # Linting successful. No issues found. return None, None first_error_line = lint_error[0].line if len(lint_error) > 0 else None - error_text = "ERRORS:\n" + "\n".join( - [f"{file_path}:{err.line}:{err.column}: {err.message}" for err in lint_error] + error_text = 'ERRORS:\n' + '\n'.join( + [f'{file_path}:{err.line}:{err.column}: {err.message}' for err in lint_error] ) return error_text, first_error_line @@ -108,8 +108,8 @@ def _print_window( content = file.read() # Ensure the content ends with a newline character - if not content.endswith("\n"): - content += "\n" + if not content.endswith('\n'): + content += '\n' lines = content.splitlines(True) # Keep all line ending characters total_lines = len(lines) @@ -132,22 +132,22 @@ def _print_window( if end == total_lines: start = max(1, end - window + 1) - output = "" + output = '' # only display this when there's at least one line above if start > 1: - output += f"({start - 1} more lines above)\n" + output += f'({start - 1} more lines above)\n' else: - output += "(this is the beginning of the file)\n" + output += '(this is the beginning of the file)\n' for i in range(start, end + 1): - _new_line = f"{i}|{lines[i-1]}" - if not _new_line.endswith("\n"): - _new_line += "\n" + _new_line = f'{i}|{lines[i-1]}' + if not _new_line.endswith('\n'): + _new_line += '\n' output += _new_line if end < total_lines: - output += f"({total_lines - end} more lines below)\n" + output += f'({total_lines - end} more lines below)\n' else: - output += "(this is the end of the file)\n" + output += '(this is the end of the file)\n' output = output.rstrip() if return_str: @@ -158,8 +158,8 @@ def _print_window( def _cur_file_header(current_file, total_lines) -> str: if not current_file: - return "" - return f"[File: {os.path.abspath(current_file)} ({total_lines} lines total)]\n" + return '' + return f'[File: {os.path.abspath(current_file)} ({total_lines} lines total)]\n' def open_file( @@ -177,7 +177,7 @@ def open_file( global CURRENT_FILE, CURRENT_LINE, WINDOW if not os.path.isfile(path): - _output_error(f"File {path} not found.") + _output_error(f'File {path} not found.') return CURRENT_FILE = os.path.abspath(path) @@ -185,7 +185,7 @@ def open_file( total_lines = max(1, sum(1 for _ in file)) if not isinstance(line_number, int) or line_number < 1 or line_number > total_lines: - _output_error(f"Line number must be between 1 and {total_lines}") + _output_error(f'Line number must be between 1 and {total_lines}') return CURRENT_LINE = line_number @@ -201,8 +201,8 @@ def open_file( return_str=True, ignore_window=False, ) - if output.strip().endswith("more lines below)"): - output += "\n[Use `scroll_down` to view the next 100 lines of the file!]" + if output.strip().endswith('more lines below)'): + output += '\n[Use `scroll_down` to view the next 100 lines of the file!]' print(output) @@ -218,7 +218,7 @@ def goto_line(line_number: int) -> None: with open(str(CURRENT_FILE)) as file: total_lines = max(1, sum(1 for _ in file)) if not isinstance(line_number, int) or line_number < 1 or line_number > total_lines: - _output_error(f"Line number must be between 1 and {total_lines}.") + _output_error(f'Line number must be between 1 and {total_lines}.') return CURRENT_LINE = _clamp(line_number, 1, total_lines) @@ -272,7 +272,7 @@ class LineNumberError(Exception): pass -def search_dir(search_term: str, dir_path: str = "./") -> None: +def search_dir(search_term: str, dir_path: str = './') -> None: """Searches for search_term in all files in dir. If dir is not provided, searches in the current directory. Args: @@ -280,15 +280,15 @@ def search_dir(search_term: str, dir_path: str = "./") -> None: dir_path: str: The path to the directory to search. """ if not os.path.isdir(dir_path): - _output_error(f"Directory {dir_path} not found") + _output_error(f'Directory {dir_path} not found') return matches = [] for root, _, files in os.walk(dir_path): for file in files: - if file.startswith("."): + if file.startswith('.'): continue file_path = os.path.join(root, file) - with open(file_path, "r", errors="ignore") as f: + with open(file_path, 'r', errors='ignore') as f: for line_num, line in enumerate(f, 1): if search_term in line: matches.append((file_path, line_num, line.strip())) @@ -308,7 +308,7 @@ def search_dir(search_term: str, dir_path: str = "./") -> None: print(f'[Found {num_matches} matches for "{search_term}" in {dir_path}]') for file_path, line_num, line in matches: - print(f"{file_path} (Line {line_num}): {line}") + print(f'{file_path} (Line {line_num}): {line}') print(f'[End of matches for "{search_term}" in {dir_path}]') @@ -323,10 +323,10 @@ def search_file(search_term: str, file_path: str | None = None) -> None: if file_path is None: file_path = CURRENT_FILE if file_path is None: - _output_error("No file specified or open. Use the open_file function first.") + _output_error('No file specified or open. Use the open_file function first.') return if not os.path.isfile(file_path): - _output_error(f"File {file_path} not found.") + _output_error(f'File {file_path} not found.') return matches = [] @@ -338,13 +338,13 @@ def search_file(search_term: str, file_path: str | None = None) -> None: if matches: print(f'[Found {len(matches)} matches for "{search_term}" in {file_path}]') for match in matches: - print(f"Line {match[0]}: {match[1]}") + print(f'Line {match[0]}: {match[1]}') print(f'[End of matches for "{search_term}" in {file_path}]') else: print(f'[No matches found for "{search_term}" in {file_path}]') -def find_file(file_name: str, dir_path: str = "./") -> None: +def find_file(file_name: str, dir_path: str = './') -> None: """Finds all files with the given name in the specified directory. Args: @@ -352,7 +352,7 @@ def find_file(file_name: str, dir_path: str = "./") -> None: dir_path: str: The path to the directory to search. """ if not os.path.isdir(dir_path): - _output_error(f"Directory {dir_path} not found") + _output_error(f'Directory {dir_path} not found') return matches = [] @@ -364,18 +364,18 @@ def find_file(file_name: str, dir_path: str = "./") -> None: if matches: print(f'[Found {len(matches)} matches for "{file_name}" in {dir_path}]') for match in matches: - print(f"{match}") + print(f'{match}') print(f'[End of matches for "{file_name}" in {dir_path}]') else: print(f'[No matches found for "{file_name}" in {dir_path}]') __all__ = [ - "open_file", - "goto_line", - "scroll_down", - "scroll_up", - "search_dir", - "search_file", - "find_file", + 'open_file', + 'goto_line', + 'scroll_down', + 'scroll_up', + 'search_dir', + 'search_file', + 'find_file', ] diff --git a/openhands/runtime/plugins/agent_skills/file_reader/file_readers.py b/openhands/runtime/plugins/agent_skills/file_reader/file_readers.py index 7f61ac910e9c..ee41eab0e4bb 100644 --- a/openhands/runtime/plugins/agent_skills/file_reader/file_readers.py +++ b/openhands/runtime/plugins/agent_skills/file_reader/file_readers.py @@ -40,14 +40,14 @@ def parse_pdf(file_path: str) -> None: Args: file_path: str: The path to the file to open. """ - print(f"[Reading PDF file from {file_path}]") + print(f'[Reading PDF file from {file_path}]') content = PyPDF2.PdfReader(file_path) - text = "" + text = '' for page_idx in range(len(content.pages)): text += ( - f"@@ Page {page_idx + 1} @@\n" + f'@@ Page {page_idx + 1} @@\n' + content.pages[page_idx].extract_text() - + "\n\n" + + '\n\n' ) print(text.strip()) @@ -58,11 +58,11 @@ def parse_docx(file_path: str) -> None: Args: file_path: str: The path to the file to open. """ - print(f"[Reading DOCX file from {file_path}]") + print(f'[Reading DOCX file from {file_path}]') content = docx.Document(file_path) - text = "" + text = '' for i, para in enumerate(content.paragraphs): - text += f"@@ Page {i + 1} @@\n" + para.text + "\n\n" + text += f'@@ Page {i + 1} @@\n' + para.text + '\n\n' print(text) @@ -72,7 +72,7 @@ def parse_latex(file_path: str) -> None: Args: file_path: str: The path to the file to open. """ - print(f"[Reading LaTex file from {file_path}]") + print(f'[Reading LaTex file from {file_path}]') with open(file_path) as f: data = f.read() text = LatexNodes2Text().latex_to_text(data) @@ -80,8 +80,8 @@ def parse_latex(file_path: str) -> None: def _base64_img(file_path: str) -> str: - with open(file_path, "rb") as image_file: - encoded_image = base64.b64encode(image_file.read()).decode("utf-8") + with open(file_path, 'rb') as image_file: + encoded_image = base64.b64encode(image_file.read()).decode('utf-8') return encoded_image @@ -96,8 +96,8 @@ def _base64_video(file_path: str, frame_interval: int = 10) -> list[str]: if not success: break if frame_count % frame_interval == 0: - _, buffer = cv2.imencode(".jpg", frame) - base64_frames.append(base64.b64encode(buffer).decode("utf-8")) + _, buffer = cv2.imencode('.jpg', frame) + base64_frames.append(base64.b64encode(buffer).decode('utf-8')) frame_count += 1 video.release() return base64_frames @@ -106,40 +106,40 @@ def _base64_video(file_path: str, frame_interval: int = 10) -> list[str]: def _prepare_image_messages(task: str, base64_image: str): return [ { - "role": "user", - "content": [ - {"type": "text", "text": task}, + 'role': 'user', + 'content': [ + {'type': 'text', 'text': task}, { - "type": "image_url", - "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"}, + 'type': 'image_url', + 'image_url': {'url': f'data:image/jpeg;base64,{base64_image}'}, }, ], } ] -def parse_audio(file_path: str, model: str = "whisper-1") -> None: +def parse_audio(file_path: str, model: str = 'whisper-1') -> None: """Parses the content of an audio file and prints it. Args: file_path: str: The path to the audio file to transcribe. model: str: The audio model to use for transcription. Defaults to 'whisper-1'. """ - print(f"[Transcribing audio file from {file_path}]") + print(f'[Transcribing audio file from {file_path}]') try: # TODO: record the COST of the API call - with open(file_path, "rb") as audio_file: + with open(file_path, 'rb') as audio_file: transcript = _get_openai_client().audio.translations.create( model=model, file=audio_file ) print(transcript.text) except Exception as e: - print(f"Error transcribing audio file: {e}") + print(f'Error transcribing audio file: {e}') def parse_image( - file_path: str, task: str = "Describe this image as detail as possible." + file_path: str, task: str = 'Describe this image as detail as possible.' ) -> None: """Parses the content of an image file and prints the description. @@ -147,7 +147,7 @@ def parse_image( file_path: str: The path to the file to open. task: str: The task description for the API call. Defaults to 'Describe this image as detail as possible.'. """ - print(f"[Reading image file from {file_path}]") + print(f'[Reading image file from {file_path}]') # TODO: record the COST of the API call try: base64_image = _base64_img(file_path) @@ -160,12 +160,12 @@ def parse_image( print(content) except Exception as error: - print(f"Error with the request: {error}") + print(f'Error with the request: {error}') def parse_video( file_path: str, - task: str = "Describe this image as detail as possible.", + task: str = 'Describe this image as detail as possible.', frame_interval: int = 30, ) -> None: """Parses the content of an image file and prints the description. @@ -177,10 +177,10 @@ def parse_video( """ print( - f"[Processing video file from {file_path} with frame interval {frame_interval}]" + f'[Processing video file from {file_path} with frame interval {frame_interval}]' ) - task = task or "This is one frame from a video, please summarize this frame." + task = task or 'This is one frame from a video, please summarize this frame.' base64_frames = _base64_video(file_path) selected_frames = base64_frames[::frame_interval] @@ -188,12 +188,12 @@ def parse_video( new_interval = len(base64_frames) // 30 selected_frames = base64_frames[::new_interval] - print(f"Totally {len(selected_frames)} would be analyze...\n") + print(f'Totally {len(selected_frames)} would be analyze...\n') idx = 0 for base64_frame in selected_frames: idx += 1 - print(f"Process the {file_path}, current No. {idx * frame_interval} frame...") + print(f'Process the {file_path}, current No. {idx * frame_interval} frame...') # TODO: record the COST of the API call try: response = _get_openai_client().chat.completions.create( @@ -207,7 +207,7 @@ def parse_video( print(current_frame_content) except Exception as error: - print(f"Error with the request: {error}") + print(f'Error with the request: {error}') def parse_pptx(file_path: str) -> None: @@ -216,29 +216,29 @@ def parse_pptx(file_path: str) -> None: Args: file_path: str: The path to the file to open. """ - print(f"[Reading PowerPoint file from {file_path}]") + print(f'[Reading PowerPoint file from {file_path}]') try: pres = Presentation(str(file_path)) text = [] for slide_idx, slide in enumerate(pres.slides): - text.append(f"@@ Slide {slide_idx + 1} @@") + text.append(f'@@ Slide {slide_idx + 1} @@') for shape in slide.shapes: - if hasattr(shape, "text"): + if hasattr(shape, 'text'): text.append(shape.text) - print("\n".join(text)) + print('\n'.join(text)) except Exception as e: - print(f"Error reading PowerPoint file: {e}") + print(f'Error reading PowerPoint file: {e}') __all__ = [ - "parse_pdf", - "parse_docx", - "parse_latex", - "parse_pptx", + 'parse_pdf', + 'parse_docx', + 'parse_latex', + 'parse_pptx', ] # This is called from OpenHands's side # If SANDBOX_ENV_OPENAI_API_KEY is set, we will be able to use these tools in the sandbox environment if _get_openai_api_key() and _get_openai_base_url(): - __all__ += ["parse_audio", "parse_video", "parse_image"] + __all__ += ['parse_audio', 'parse_video', 'parse_image'] diff --git a/openhands/runtime/plugins/agent_skills/utils/config.py b/openhands/runtime/plugins/agent_skills/utils/config.py index a0a9bc45895e..f0084c540393 100644 --- a/openhands/runtime/plugins/agent_skills/utils/config.py +++ b/openhands/runtime/plugins/agent_skills/utils/config.py @@ -10,19 +10,19 @@ # AFTER the agentskills is imported (the case for EventStreamRuntime) # ================================================================================================== def _get_openai_api_key(): - return os.getenv("OPENAI_API_KEY", os.getenv("SANDBOX_ENV_OPENAI_API_KEY", "")) + return os.getenv('OPENAI_API_KEY', os.getenv('SANDBOX_ENV_OPENAI_API_KEY', '')) def _get_openai_base_url(): - return os.getenv("OPENAI_BASE_URL", "https://api.openai.com/v1") + return os.getenv('OPENAI_BASE_URL', 'https://api.openai.com/v1') def _get_openai_model(): - return os.getenv("OPENAI_MODEL", "gpt-4o") + return os.getenv('OPENAI_MODEL', 'gpt-4o') def _get_max_token(): - return os.getenv("MAX_TOKEN", 500) + return os.getenv('MAX_TOKEN', 500) def _get_openai_client(): diff --git a/openhands/runtime/plugins/agent_skills/utils/dependency.py b/openhands/runtime/plugins/agent_skills/utils/dependency.py index e0c2f52cee51..1ff1636fb545 100644 --- a/openhands/runtime/plugins/agent_skills/utils/dependency.py +++ b/openhands/runtime/plugins/agent_skills/utils/dependency.py @@ -8,4 +8,4 @@ def import_functions( if hasattr(module, name): target_globals[name] = getattr(module, name) else: - raise ValueError(f"Function {name} not found in {module.__name__}") + raise ValueError(f'Function {name} not found in {module.__name__}') diff --git a/openhands/runtime/plugins/jupyter/__init__.py b/openhands/runtime/plugins/jupyter/__init__.py index 422115e947b2..23128b60a8f9 100644 --- a/openhands/runtime/plugins/jupyter/__init__.py +++ b/openhands/runtime/plugins/jupyter/__init__.py @@ -8,51 +8,51 @@ from openhands.runtime.plugins.jupyter.execute_server import JupyterKernel from openhands.runtime.plugins.requirement import Plugin, PluginRequirement from openhands.runtime.utils import find_available_tcp_port -from openhands.runtime.utils.shutdown_listener import should_continue +from openhands.utils.shutdown_listener import should_continue @dataclass class JupyterRequirement(PluginRequirement): - name: str = "jupyter" + name: str = 'jupyter' class JupyterPlugin(Plugin): - name: str = "jupyter" + name: str = 'jupyter' - async def initialize(self, username: str, kernel_id: str = "openhands-default"): + async def initialize(self, username: str, kernel_id: str = 'openhands-default'): self.kernel_gateway_port = find_available_tcp_port(40000, 49999) self.kernel_id = kernel_id self.gateway_process = subprocess.Popen( ( f"su - {username} -s /bin/bash << 'EOF'\n" - "cd /openhands/code\n" - "export POETRY_VIRTUALENVS_PATH=/openhands/poetry;\n" - "export PYTHONPATH=/openhands/code:$PYTHONPATH;\n" - "export MAMBA_ROOT_PREFIX=/openhands/micromamba;\n" - "/openhands/micromamba/bin/micromamba run -n openhands " - "poetry run jupyter kernelgateway " - "--KernelGatewayApp.ip=0.0.0.0 " - f"--KernelGatewayApp.port={self.kernel_gateway_port}\n" - "EOF" + 'cd /openhands/code\n' + 'export POETRY_VIRTUALENVS_PATH=/openhands/poetry;\n' + 'export PYTHONPATH=/openhands/code:$PYTHONPATH;\n' + 'export MAMBA_ROOT_PREFIX=/openhands/micromamba;\n' + '/openhands/micromamba/bin/micromamba run -n openhands ' + 'poetry run jupyter kernelgateway ' + '--KernelGatewayApp.ip=0.0.0.0 ' + f'--KernelGatewayApp.port={self.kernel_gateway_port}\n' + 'EOF' ), stderr=subprocess.STDOUT, shell=True, ) # read stdout until the kernel gateway is ready - output = "" + output = '' while should_continue() and self.gateway_process.stdout is not None: - line = self.gateway_process.stdout.readline().decode("utf-8") + line = self.gateway_process.stdout.readline().decode('utf-8') output += line - if "at" in line: + if 'at' in line: break time.sleep(1) - logger.debug("Waiting for jupyter kernel gateway to start...") + logger.debug('Waiting for jupyter kernel gateway to start...') logger.debug( - f"Jupyter kernel gateway started at port {self.kernel_gateway_port}. Output: {output}" + f'Jupyter kernel gateway started at port {self.kernel_gateway_port}. Output: {output}' ) _obs = await self.run( - IPythonRunCellAction(code="import sys; print(sys.executable)") + IPythonRunCellAction(code='import sys; print(sys.executable)') ) self.python_interpreter_path = _obs.content.strip() @@ -60,12 +60,12 @@ async def _run(self, action: Action) -> IPythonRunCellObservation: """Internal method to run a code cell in the jupyter kernel.""" if not isinstance(action, IPythonRunCellAction): raise ValueError( - f"Jupyter plugin only supports IPythonRunCellAction, but got {action}" + f'Jupyter plugin only supports IPythonRunCellAction, but got {action}' ) - if not hasattr(self, "kernel"): + if not hasattr(self, 'kernel'): self.kernel = JupyterKernel( - f"localhost:{self.kernel_gateway_port}", self.kernel_id + f'localhost:{self.kernel_gateway_port}', self.kernel_id ) if not self.kernel.initialized: diff --git a/openhands/runtime/plugins/jupyter/execute_server.py b/openhands/runtime/plugins/jupyter/execute_server.py index 54bef75fc59a..da038d526686 100644 --- a/openhands/runtime/plugins/jupyter/execute_server.py +++ b/openhands/runtime/plugins/jupyter/execute_server.py @@ -44,21 +44,21 @@ def strip_ansi(o: str) -> str: 'Lorem dolor sit ipsum' """ # pattern = re.compile(r'/(\x9B|\x1B\[)[0-?]*[ -\/]*[@-~]/') - pattern = re.compile(r"\x1B\[\d+(;\d+){0,2}m") - stripped = pattern.sub("", o) + pattern = re.compile(r'\x1B\[\d+(;\d+){0,2}m') + stripped = pattern.sub('', o) return stripped class JupyterKernel: - def __init__(self, url_suffix, convid, lang="python"): - self.base_url = f"http://{url_suffix}" - self.base_ws_url = f"ws://{url_suffix}" + def __init__(self, url_suffix, convid, lang='python'): + self.base_url = f'http://{url_suffix}' + self.base_ws_url = f'ws://{url_suffix}' self.lang = lang self.kernel_id = None self.ws = None self.convid = convid logging.info( - f"Jupyter kernel created for conversation {convid} at {url_suffix}" + f'Jupyter kernel created for conversation {convid} at {url_suffix}' ) self.heartbeat_interval = 10000 # 10 seconds @@ -66,14 +66,14 @@ def __init__(self, url_suffix, convid, lang="python"): self.initialized = False async def initialize(self): - await self.execute(r"%colors nocolor") + await self.execute(r'%colors nocolor') # pre-defined tools self.tools_to_run: list[str] = [ # TODO: You can add code for your pre-defined tools here ] for tool in self.tools_to_run: res = await self.execute(tool) - logging.info(f"Tool [{tool}] initialized:\n{res}") + logging.info(f'Tool [{tool}] initialized:\n{res}') self.initialized = True async def _send_heartbeat(self): @@ -88,7 +88,7 @@ async def _send_heartbeat(self): await self._connect() except ConnectionRefusedError: logging.info( - "ConnectionRefusedError: Failed to reconnect to kernel websocket - Is the kernel still running?" + 'ConnectionRefusedError: Failed to reconnect to kernel websocket - Is the kernel still running?' ) async def _connect(self): @@ -102,12 +102,12 @@ async def _connect(self): while n_tries > 0: try: response = await client.fetch( - "{}/api/kernels".format(self.base_url), - method="POST", - body=json_encode({"name": self.lang}), + '{}/api/kernels'.format(self.base_url), + method='POST', + body=json_encode({'name': self.lang}), ) kernel = json_decode(response.body) - self.kernel_id = kernel["id"] + self.kernel_id = kernel['id'] break except Exception: # kernels are not ready yet @@ -115,15 +115,15 @@ async def _connect(self): await asyncio.sleep(1) if n_tries == 0: - raise ConnectionRefusedError("Failed to connect to kernel") + raise ConnectionRefusedError('Failed to connect to kernel') ws_req = HTTPRequest( - url="{}/api/kernels/{}/channels".format( + url='{}/api/kernels/{}/channels'.format( self.base_ws_url, url_escape(self.kernel_id) ) ) self.ws = await websocket_connect(ws_req) - logging.info("Connected to kernel websocket") + logging.info('Connected to kernel websocket') # Setup heartbeat if self.heartbeat_callback: @@ -147,28 +147,28 @@ async def execute(self, code, timeout=120): res = await self.ws.write_message( json_encode( { - "header": { - "username": "", - "version": "5.0", - "session": "", - "msg_id": msg_id, - "msg_type": "execute_request", + 'header': { + 'username': '', + 'version': '5.0', + 'session': '', + 'msg_id': msg_id, + 'msg_type': 'execute_request', }, - "parent_header": {}, - "channel": "shell", - "content": { - "code": code, - "silent": False, - "store_history": False, - "user_expressions": {}, - "allow_stdin": False, + 'parent_header': {}, + 'channel': 'shell', + 'content': { + 'code': code, + 'silent': False, + 'store_history': False, + 'user_expressions': {}, + 'allow_stdin': False, }, - "metadata": {}, - "buffers": {}, + 'metadata': {}, + 'buffers': {}, } ) ) - logging.info(f"Executed code in jupyter kernel:\n{res}") + logging.info(f'Executed code in jupyter kernel:\n{res}') outputs = [] @@ -178,68 +178,68 @@ async def wait_for_messages(): assert self.ws is not None msg = await self.ws.read_message() msg = json_decode(msg) - msg_type = msg["msg_type"] - parent_msg_id = msg["parent_header"].get("msg_id", None) + msg_type = msg['msg_type'] + parent_msg_id = msg['parent_header'].get('msg_id', None) if parent_msg_id != msg_id: continue - if os.environ.get("DEBUG"): + if os.environ.get('DEBUG'): logging.info( f"MSG TYPE: {msg_type.upper()} DONE:{execution_done}\nCONTENT: {msg['content']}" ) - if msg_type == "error": - traceback = "\n".join(msg["content"]["traceback"]) + if msg_type == 'error': + traceback = '\n'.join(msg['content']['traceback']) outputs.append(traceback) execution_done = True - elif msg_type == "stream": - outputs.append(msg["content"]["text"]) - elif msg_type in ["execute_result", "display_data"]: - outputs.append(msg["content"]["data"]["text/plain"]) - if "image/png" in msg["content"]["data"]: + elif msg_type == 'stream': + outputs.append(msg['content']['text']) + elif msg_type in ['execute_result', 'display_data']: + outputs.append(msg['content']['data']['text/plain']) + if 'image/png' in msg['content']['data']: # use markdone to display image (in case of large image) outputs.append( f"\n![image](data:image/png;base64,{msg['content']['data']['image/png']})\n" ) - elif msg_type == "execute_reply": + elif msg_type == 'execute_reply': execution_done = True return execution_done async def interrupt_kernel(): client = AsyncHTTPClient() interrupt_response = await client.fetch( - f"{self.base_url}/api/kernels/{self.kernel_id}/interrupt", - method="POST", - body=json_encode({"kernel_id": self.kernel_id}), + f'{self.base_url}/api/kernels/{self.kernel_id}/interrupt', + method='POST', + body=json_encode({'kernel_id': self.kernel_id}), ) - logging.info(f"Kernel interrupted: {interrupt_response}") + logging.info(f'Kernel interrupted: {interrupt_response}') try: execution_done = await asyncio.wait_for(wait_for_messages(), timeout) except asyncio.TimeoutError: await interrupt_kernel() - return f"[Execution timed out ({timeout} seconds).]" + return f'[Execution timed out ({timeout} seconds).]' if not outputs and execution_done: - ret = "[Code executed successfully with no output]" + ret = '[Code executed successfully with no output]' else: - ret = "".join(outputs) + ret = ''.join(outputs) # Remove ANSI ret = strip_ansi(ret) - if os.environ.get("DEBUG"): - logging.info(f"OUTPUT:\n{ret}") + if os.environ.get('DEBUG'): + logging.info(f'OUTPUT:\n{ret}') return ret async def shutdown_async(self): if self.kernel_id: client = AsyncHTTPClient() await client.fetch( - "{}/api/kernels/{}".format(self.base_url, self.kernel_id), - method="DELETE", + '{}/api/kernels/{}'.format(self.base_url, self.kernel_id), + method='DELETE', ) self.kernel_id = None if self.ws: @@ -253,11 +253,11 @@ def initialize(self, jupyter_kernel): async def post(self): data = json_decode(self.request.body) - code = data.get("code") + code = data.get('code') if not code: self.set_status(400) - self.write("Missing code") + self.write('Missing code') return output = await self.jupyter_kernel.execute(code) @@ -268,18 +268,18 @@ async def post(self): def make_app(): jupyter_kernel = JupyterKernel( f"localhost:{os.environ.get('JUPYTER_GATEWAY_PORT')}", - os.environ.get("JUPYTER_GATEWAY_KERNEL_ID"), + os.environ.get('JUPYTER_GATEWAY_KERNEL_ID'), ) asyncio.get_event_loop().run_until_complete(jupyter_kernel.initialize()) return tornado.web.Application( [ - (r"/execute", ExecuteHandler, {"jupyter_kernel": jupyter_kernel}), + (r'/execute', ExecuteHandler, {'jupyter_kernel': jupyter_kernel}), ] ) -if __name__ == "__main__": +if __name__ == '__main__': app = make_app() - app.listen(os.environ.get("JUPYTER_EXEC_SERVER_PORT")) + app.listen(os.environ.get('JUPYTER_EXEC_SERVER_PORT')) tornado.ioloop.IOLoop.current().start() diff --git a/openhands/runtime/plugins/vscode/__init__.py b/openhands/runtime/plugins/vscode/__init__.py new file mode 100644 index 000000000000..881ad7502aae --- /dev/null +++ b/openhands/runtime/plugins/vscode/__init__.py @@ -0,0 +1,51 @@ +import os +import subprocess +import time +import uuid +from dataclasses import dataclass + +from openhands.core.logger import openhands_logger as logger +from openhands.runtime.plugins.requirement import Plugin, PluginRequirement +from openhands.runtime.utils.shutdown_listener import should_continue +from openhands.runtime.utils.system import check_port_available + + +@dataclass +class VSCodeRequirement(PluginRequirement): + name: str = 'vscode' + + +class VSCodePlugin(Plugin): + name: str = 'vscode' + + async def initialize(self, username: str): + self.vscode_port = int(os.environ['VSCODE_PORT']) + self.vscode_connection_token = str(uuid.uuid4()) + assert check_port_available(self.vscode_port) + cmd = ( + f"su - {username} -s /bin/bash << 'EOF'\n" + f'sudo chown -R {username}:{username} /openhands/.openvscode-server\n' + 'cd /workspace\n' + f'exec /openhands/.openvscode-server/bin/openvscode-server --host 0.0.0.0 --connection-token {self.vscode_connection_token} --port {self.vscode_port}\n' + 'EOF' + ) + print(cmd) + self.gateway_process = subprocess.Popen( + cmd, + stderr=subprocess.STDOUT, + shell=True, + ) + # read stdout until the kernel gateway is ready + output = '' + while should_continue() and self.gateway_process.stdout is not None: + line = self.gateway_process.stdout.readline().decode('utf-8') + print(line) + output += line + if 'at' in line: + break + time.sleep(1) + logger.debug('Waiting for VSCode server to start...') + + logger.debug( + f'VSCode server started at port {self.vscode_port}. Output: {output}' + ) diff --git a/openhands/runtime/utils/__init__.py b/openhands/runtime/utils/__init__.py index fdb4411a530c..622a0b609573 100644 --- a/openhands/runtime/utils/__init__.py +++ b/openhands/runtime/utils/__init__.py @@ -3,4 +3,4 @@ find_available_tcp_port, ) -__all__ = ["display_number_matrix", "find_available_tcp_port"] +__all__ = ['display_number_matrix', 'find_available_tcp_port'] diff --git a/openhands/runtime/utils/bash.py b/openhands/runtime/utils/bash.py index c08aa4fe25db..a5019315a038 100644 --- a/openhands/runtime/utils/bash.py +++ b/openhands/runtime/utils/bash.py @@ -17,15 +17,15 @@ def split_bash_commands(commands): if not commands.strip(): - return [""] + return [''] try: parsed = bashlex.parse(commands) except bashlex.errors.ParsingError as e: logger.debug( - f"Failed to parse bash commands\n" - f"[input]: {commands}\n" - f"[warning]: {e}\n" - f"The original command will be returned as is." + f'Failed to parse bash commands\n' + f'[input]: {commands}\n' + f'[warning]: {e}\n' + f'The original command will be returned as is.' ) # If parsing fails, return the original commands return [commands] @@ -39,7 +39,7 @@ def split_bash_commands(commands): # Include any text between the last command and this one if start > last_end: between = commands[last_end:start] - logger.debug(f"BASH PARSING between: {between}") + logger.debug(f'BASH PARSING between: {between}') if result: result[-1] += between.rstrip() elif between.strip(): @@ -48,21 +48,21 @@ def split_bash_commands(commands): # Extract the command, preserving original formatting command = commands[start:end].rstrip() - logger.debug(f"BASH PARSING command: {command}") + logger.debug(f'BASH PARSING command: {command}') result.append(command) last_end = end # Add any remaining text after the last command to the last command remaining = commands[last_end:].rstrip() - logger.debug(f"BASH PARSING remaining: {remaining}") + logger.debug(f'BASH PARSING remaining: {remaining}') if last_end < len(commands) and result: result[-1] += remaining - logger.debug(f"BASH PARSING result[-1] += remaining: {result[-1]}") + logger.debug(f'BASH PARSING result[-1] += remaining: {result[-1]}') elif last_end < len(commands): if remaining: result.append(remaining) - logger.debug(f"BASH PARSING result.append(remaining): {result[-1]}") + logger.debug(f'BASH PARSING result.append(remaining): {result[-1]}') return result @@ -73,9 +73,9 @@ def __init__(self, work_dir: str, username: str): self._pwd = work_dir self.shell = pexpect.spawn( - f"su {username}", - encoding="utf-8", - codec_errors="replace", + f'su {username}', + encoding='utf-8', + codec_errors='replace', echo=False, ) self._init_bash_shell(work_dir) @@ -93,23 +93,23 @@ def workdir(self): def _get_working_directory(self): # NOTE: this is part of initialization, so we hard code the timeout - result, exit_code = self._execute_bash("pwd", timeout=60, keep_prompt=False) + result, exit_code = self._execute_bash('pwd', timeout=60, keep_prompt=False) if exit_code != 0: raise RuntimeError( - f"Failed to get working directory (exit code: {exit_code}): {result}" + f'Failed to get working directory (exit code: {exit_code}): {result}' ) return result.strip() def _init_bash_shell(self, work_dir: str): self.__bash_PS1 = ( - r"[PEXPECT_BEGIN]\n" + r'[PEXPECT_BEGIN]\n' r'$(which python >/dev/null 2>&1 && echo "[Python Interpreter: $(which python)]\n")' - r"\u@\h:\w\n" - r"[PEXPECT_END]" + r'\u@\h:\w\n' + r'[PEXPECT_END]' ) # This should NOT match "PS1=\u@\h:\w [PEXPECT]$" when `env` is executed - self.__bash_expect_regex = r"\[PEXPECT_BEGIN\]\s*(.*?)\s*([a-z0-9_-]*)@([a-zA-Z0-9.-]*):(.+)\s*\[PEXPECT_END\]" + self.__bash_expect_regex = r'\[PEXPECT_BEGIN\]\s*(.*?)\s*([a-z0-9_-]*)@([a-zA-Z0-9.-]*):(.+)\s*\[PEXPECT_END\]' # Set umask to allow group write permissions self.shell.sendline(f'umask 002; export PS1="{self.__bash_PS1}"; export PS2=""') self.shell.expect(self.__bash_expect_regex) @@ -119,7 +119,7 @@ def _init_bash_shell(self, work_dir: str): ) self.shell.expect(self.__bash_expect_regex) logger.debug( - f"Bash initialized. Working directory: {work_dir}. Output: [{self.shell.before}]" + f'Bash initialized. Working directory: {work_dir}. Output: [{self.shell.before}]' ) # Ensure the group has write permissions on the working directory self.shell.sendline(f'chmod g+rw "{work_dir}"') @@ -128,17 +128,17 @@ def _init_bash_shell(self, work_dir: str): def _get_bash_prompt_and_update_pwd(self): ps1 = self.shell.after if ps1 == pexpect.EOF: - logger.error(f"Bash shell EOF! {self.shell.after=}, {self.shell.before=}") - raise RuntimeError("Bash shell EOF") + logger.error(f'Bash shell EOF! {self.shell.after=}, {self.shell.before=}') + raise RuntimeError('Bash shell EOF') if ps1 == pexpect.TIMEOUT: - logger.warning("Bash shell timeout") - return "" + logger.warning('Bash shell timeout') + return '' # begin at the last occurrence of '[PEXPECT_BEGIN]'. # In multi-line bash commands, the prompt will be repeated # and the matched regex captures all of them # - we only want the last one (newest prompt) - _begin_pos = ps1.rfind("[PEXPECT_BEGIN]") + _begin_pos = ps1.rfind('[PEXPECT_BEGIN]') if _begin_pos != -1: ps1 = ps1[_begin_pos:] @@ -146,19 +146,19 @@ def _get_bash_prompt_and_update_pwd(self): matched = re.match(self.__bash_expect_regex, ps1) assert ( matched is not None - ), f"Failed to parse bash prompt: {ps1}. This should not happen." + ), f'Failed to parse bash prompt: {ps1}. This should not happen.' other_info, username, hostname, working_dir = matched.groups() working_dir = working_dir.rstrip() self._pwd = os.path.expanduser(working_dir) # re-assemble the prompt # ignore the hostname AND use 'openhands-workspace' - prompt = f"{other_info.strip()}\n{username}@openhands-workspace:{working_dir} " - if username == "root": - prompt += "#" + prompt = f'{other_info.strip()}\n{username}@openhands-workspace:{working_dir} ' + if username == 'root': + prompt += '#' else: - prompt += "$" - return prompt + " " + prompt += '$' + return prompt + ' ' def _execute_bash( self, @@ -167,7 +167,7 @@ def _execute_bash( keep_prompt: bool = True, kill_on_timeout: bool = True, ) -> tuple[str, int]: - logger.debug(f"Executing command: {command}") + logger.debug(f'Executing command: {command}') self.shell.sendline(command) return self._continue_bash( timeout=timeout, keep_prompt=keep_prompt, kill_on_timeout=kill_on_timeout @@ -183,51 +183,51 @@ def _interrupt_bash( # try to interrupt the bash shell use SIGINT while max_retries > 0: self.shell.sendintr() # send SIGINT to the shell - logger.debug("Sent SIGINT to bash. Waiting for output...") + logger.debug('Sent SIGINT to bash. Waiting for output...') try: self.shell.expect(self.__bash_expect_regex, timeout=interrupt_timeout) output = self.shell.before - logger.debug(f"Received output after SIGINT: {output}") + logger.debug(f'Received output after SIGINT: {output}') exit_code = 130 # SIGINT - _additional_msg = "" + _additional_msg = '' if action_timeout is not None: _additional_msg = ( - f"Command timed out after {action_timeout} seconds. " + f'Command timed out after {action_timeout} seconds. ' ) output += ( - "\r\n\r\n" - + f"[{_additional_msg}SIGINT was sent to interrupt the command.]" + '\r\n\r\n' + + f'[{_additional_msg}SIGINT was sent to interrupt the command.]' ) return output, exit_code except pexpect.TIMEOUT as e: - logger.warning(f"Bash pexpect.TIMEOUT while waiting for SIGINT: {e}") + logger.warning(f'Bash pexpect.TIMEOUT while waiting for SIGINT: {e}') max_retries -= 1 # fall back to send control-z logger.error( - "Failed to get output after SIGINT. Max retries reached. Sending control-z..." + 'Failed to get output after SIGINT. Max retries reached. Sending control-z...' ) - self.shell.sendcontrol("z") + self.shell.sendcontrol('z') self.shell.expect(self.__bash_expect_regex) output = self.shell.before - logger.debug(f"Received output after control-z: {output}") + logger.debug(f'Received output after control-z: {output}') # Try to kill the job - self.shell.sendline("kill -9 %1") + self.shell.sendline('kill -9 %1') self.shell.expect(self.__bash_expect_regex) - logger.debug(f"Received output after killing job %1: {self.shell.before}") + logger.debug(f'Received output after killing job %1: {self.shell.before}') output += self.shell.before - _additional_msg = "" + _additional_msg = '' if action_timeout is not None: - _additional_msg = f"Command timed out after {action_timeout} seconds. " + _additional_msg = f'Command timed out after {action_timeout} seconds. ' output += ( - "\r\n\r\n" - + f"[{_additional_msg}SIGINT was sent to interrupt the command, but failed. The command was killed.]" + '\r\n\r\n' + + f'[{_additional_msg}SIGINT was sent to interrupt the command, but failed. The command was killed.]' ) # Try to get the exit code again - self.shell.sendline("echo $?") + self.shell.sendline('echo $?') self.shell.expect(self.__bash_expect_regex) _exit_code_output = self.shell.before exit_code = self._parse_exit_code(_exit_code_output) @@ -238,7 +238,7 @@ def _parse_exit_code(self, output: str) -> int: try: exit_code = int(output.strip().split()[0]) except Exception: - logger.error("Error getting exit code from bash script") + logger.error('Error getting exit code from bash script') # If we try to run an invalid shell script the output sometimes includes error text # rather than the error code - we assume this is an error exit_code = 2 @@ -250,47 +250,47 @@ def _continue_bash( keep_prompt: bool = True, kill_on_timeout: bool = True, ) -> tuple[str, int]: - logger.debug(f"Continuing bash with timeout={timeout}") + logger.debug(f'Continuing bash with timeout={timeout}') try: self.shell.expect(self.__bash_expect_regex, timeout=timeout) output = self.shell.before # Get exit code - self.shell.sendline("echo $?") - logger.debug("Requesting exit code...") + self.shell.sendline('echo $?') + logger.debug('Requesting exit code...') self.shell.expect(self.__bash_expect_regex, timeout=timeout) _exit_code_output = self.shell.before exit_code = self._parse_exit_code(_exit_code_output) except pexpect.TIMEOUT as e: - logger.warning(f"Bash pexpect.TIMEOUT while executing bash command: {e}") + logger.warning(f'Bash pexpect.TIMEOUT while executing bash command: {e}') if kill_on_timeout: output, exit_code = self._interrupt_bash(action_timeout=timeout) else: - output = self.shell.before or "" + output = self.shell.before or '' exit_code = -1 finally: bash_prompt = self._get_bash_prompt_and_update_pwd() if keep_prompt: - output += "\r\n" + bash_prompt + output += '\r\n' + bash_prompt return output, exit_code def run(self, action: CmdRunAction) -> CmdOutputObservation | ErrorObservation: try: assert ( action.timeout is not None - ), f"Timeout argument is required for CmdRunAction: {action}" + ), f'Timeout argument is required for CmdRunAction: {action}' commands = split_bash_commands(action.command) - all_output = "" - python_interpreter = "" + all_output = '' + python_interpreter = '' for command in commands: - if command == "": + if command == '': output, exit_code = self._continue_bash( timeout=SOFT_TIMEOUT_SECONDS, keep_prompt=action.keep_prompt, kill_on_timeout=False, ) - elif command.lower() == "ctrl+c": + elif command.lower() == 'ctrl+c': output, exit_code = self._interrupt_bash( action_timeout=None, # intentionally None ) @@ -305,24 +305,24 @@ def run(self, action: CmdRunAction) -> CmdOutputObservation | ErrorObservation: ) # Get rid of the python interpreter string from each line of the output. # We need it only once at the end. - parts = output.rsplit("[Python Interpreter: ", 1) + parts = output.rsplit('[Python Interpreter: ', 1) output = parts[0] if len(parts) == 2: - python_interpreter = "[Python Interpreter: " + parts[1] + python_interpreter = '[Python Interpreter: ' + parts[1] if all_output: # previous output already exists so we add a newline - all_output += "\r\n" + all_output += '\r\n' # If the command originated with the agent, append the command that was run... if action.source == EventSource.AGENT: - all_output += command + "\r\n" + all_output += command + '\r\n' all_output += str(output) if exit_code != 0: break return CmdOutputObservation( command_id=-1, - content=all_output.rstrip("\r\n"), + content=all_output.rstrip('\r\n'), command=action.command, hidden=action.hidden, exit_code=exit_code, @@ -330,5 +330,5 @@ def run(self, action: CmdRunAction) -> CmdOutputObservation | ErrorObservation: ) except UnicodeDecodeError as e: return ErrorObservation( - f"Runtime bash execution failed: Command output could not be decoded as utf-8. {str(e)}", + f'Runtime bash execution failed: Command output could not be decoded as utf-8. {str(e)}', ) diff --git a/openhands/runtime/utils/command.py b/openhands/runtime/utils/command.py index b46486de5c60..1617ec20f36f 100644 --- a/openhands/runtime/utils/command.py +++ b/openhands/runtime/utils/command.py @@ -7,23 +7,23 @@ def get_remote_startup_command( browsergym_args: list[str], ): return [ - "/openhands/micromamba/bin/micromamba", - "run", - "-n", - "openhands", - "poetry", - "run", - "python", - "-u", - "-m", - "openhands.runtime.action_execution_server", + '/openhands/micromamba/bin/micromamba', + 'run', + '-n', + 'openhands', + 'poetry', + 'run', + 'python', + '-u', + '-m', + 'openhands.runtime.action_execution_server', str(port), - "--working-dir", + '--working-dir', sandbox_workspace_dir, *plugin_args, - "--username", + '--username', username, - "--user-id", + '--user-id', str(user_id), *browsergym_args, ] diff --git a/openhands/runtime/utils/edit.py b/openhands/runtime/utils/edit.py index 1e46c571dfe0..cd3ffd0b71ce 100644 --- a/openhands/runtime/utils/edit.py +++ b/openhands/runtime/utils/edit.py @@ -52,7 +52,7 @@ def _extract_code(string): - pattern = r"```(?:\w*\n)?(.*?)```" + pattern = r'```(?:\w*\n)?(.*?)```' matches = re.findall(pattern, string, re.DOTALL) if not matches: return None @@ -64,16 +64,16 @@ def get_new_file_contents( ) -> str | None: while num_retries > 0: messages = [ - {"role": "system", "content": SYS_MSG}, + {'role': 'system', 'content': SYS_MSG}, { - "role": "user", - "content": USER_MSG.format( + 'role': 'user', + 'content': USER_MSG.format( old_contents=old_contents, draft_changes=draft_changes ), }, ] resp = llm.completion(messages=messages) - new_contents = _extract_code(resp["choices"][0]["message"]["content"]) + new_contents = _extract_code(resp['choices'][0]['message']['content']) if new_contents is not None: return new_contents num_retries -= 1 @@ -107,18 +107,18 @@ def __init__(self, *args, **kwargs): # manually set the model name for the draft editor LLM to distinguish token costs llm_metrics = Metrics( - model_name="draft_editor:" + llm_config.draft_editor.model + model_name='draft_editor:' + llm_config.draft_editor.model ) if llm_config.draft_editor.caching_prompt: logger.debug( - "It is not recommended to cache draft editor LLM prompts as it may incur high costs for the same prompt. " - "Automatically setting caching_prompt=false." + 'It is not recommended to cache draft editor LLM prompts as it may incur high costs for the same prompt. ' + 'Automatically setting caching_prompt=false.' ) llm_config.draft_editor.caching_prompt = False self.draft_editor_llm = LLM(llm_config.draft_editor, metrics=llm_metrics) logger.debug( - f"[Draft edit functionality] enabled with LLM: {self.draft_editor_llm}" + f'[Draft edit functionality] enabled with LLM: {self.draft_editor_llm}' ) def _validate_range( @@ -131,7 +131,7 @@ def _validate_range( or (start > end and end != -1 and start != -1) ): return ErrorObservation( - f"Invalid range for editing: start={start}, end={end}, total lines={total_lines}. start must be >= 1 and <={total_lines} (total lines of the edited file), start <= end, or start == -1 (append to the end of the file)." + f'Invalid range for editing: start={start}, end={end}, total lines={total_lines}. start must be >= 1 and <={total_lines} (total lines of the edited file), start <= end, or start == -1 (append to the end of the file).' ) if ( (end < 1 and end != -1) @@ -139,7 +139,7 @@ def _validate_range( or (end < start and start != -1 and end != -1) ): return ErrorObservation( - f"Invalid range for editing: start={start}, end={end}, total lines={total_lines}. end must be >= 1 and <= {total_lines} (total lines of the edited file), end >= start, or end == -1 (to edit till the end of the file)." + f'Invalid range for editing: start={start}, end={end}, total lines={total_lines}. end must be >= 1 and <= {total_lines} (total lines of the edited file), end >= start, or end == -1 (to edit till the end of the file).' ) return None @@ -154,9 +154,9 @@ def _get_lint_error( linter = DefaultLinter() # Copy the original file to a temporary file (with the same ext) and lint it with tempfile.NamedTemporaryFile( - suffix=suffix, mode="w+", encoding="utf-8" + suffix=suffix, mode='w+', encoding='utf-8' ) as original_file_copy, tempfile.NamedTemporaryFile( - suffix=suffix, mode="w+", encoding="utf-8" + suffix=suffix, mode='w+', encoding='utf-8' ) as updated_file_copy: # Lint the original file original_file_copy.write(old_content) @@ -180,20 +180,20 @@ def _get_lint_error( ) error_message = ( ( - f"\n[Linting failed for edited file {filepath}. {len(updated_lint_error)} lint errors found.]\n" - "[begin attempted changes]\n" - f"{_obs.visualize_diff(change_applied=False)}\n" - "[end attempted changes]\n" + f'\n[Linting failed for edited file {filepath}. {len(updated_lint_error)} lint errors found.]\n' + '[begin attempted changes]\n' + f'{_obs.visualize_diff(change_applied=False)}\n' + '[end attempted changes]\n' ) - + "-" * 40 - + "\n" + + '-' * 40 + + '\n' ) - error_message += "-" * 20 + "First 5 lint errors" + "-" * 20 + "\n" + error_message += '-' * 20 + 'First 5 lint errors' + '-' * 20 + '\n' for i, lint_error in enumerate(updated_lint_error[:5]): - error_message += f"[begin lint error {i}]\n" - error_message += lint_error.visualize().strip() + "\n" - error_message += f"[end lint error {i}]\n" - error_message += "-" * 40 + "\n" + error_message += f'[begin lint error {i}]\n' + error_message += lint_error.visualize().strip() + '\n' + error_message += f'[end lint error {i}]\n' + error_message += '-' * 40 + '\n' return ErrorObservation(error_message) return None @@ -201,10 +201,10 @@ def edit(self, action: FileEditAction) -> Observation: obs = self.read(FileReadAction(path=action.path)) if ( isinstance(obs, ErrorObservation) - and "File not found".lower() in obs.content.lower() + and 'File not found'.lower() in obs.content.lower() ): logger.debug( - f"Agent attempted to edit a file that does not exist. Creating the file. Error msg: {obs.content}" + f'Agent attempted to edit a file that does not exist. Creating the file. Error msg: {obs.content}' ) # directly write the new content obs = self.write( @@ -214,22 +214,22 @@ def edit(self, action: FileEditAction) -> Observation: return obs if not isinstance(obs, FileWriteObservation): raise ValueError( - f"Expected FileWriteObservation, got {type(obs)}: {str(obs)}" + f'Expected FileWriteObservation, got {type(obs)}: {str(obs)}' ) return FileEditObservation( - content=get_diff("", action.content, action.path), + content=get_diff('', action.content, action.path), path=action.path, prev_exist=False, - old_content="", + old_content='', new_content=action.content, ) if not isinstance(obs, FileReadObservation): raise ValueError( - f"Expected FileReadObservation, got {type(obs)}: {str(obs)}" + f'Expected FileReadObservation, got {type(obs)}: {str(obs)}' ) original_file_content = obs.content - old_file_lines = original_file_content.split("\n") + old_file_lines = original_file_content.split('\n') # NOTE: start and end are 1-indexed start = action.start end = action.end @@ -240,7 +240,7 @@ def edit(self, action: FileEditAction) -> Observation: # append to the end of the file if start == -1: - updated_content = "\n".join(old_file_lines + action.content.split("\n")) + updated_content = '\n'.join(old_file_lines + action.content.split('\n')) diff = get_diff(original_file_content, updated_content, action.path) # Lint the updated content if self.config.sandbox.enable_auto_lint: @@ -279,9 +279,9 @@ def edit(self, action: FileEditAction) -> Observation: length_of_range = end_idx - start_idx if length_of_range > self.MAX_LINES_TO_EDIT + 1: error_msg = ( - f"[Edit error: The range of lines to edit is too long.]\n" - f"[The maximum number of lines allowed to edit at once is {self.MAX_LINES_TO_EDIT}. " - f"Got (L{start_idx + 1}-L{end_idx}) {length_of_range} lines.]\n" # [start_idx, end_idx), so no need to + 1 + f'[Edit error: The range of lines to edit is too long.]\n' + f'[The maximum number of lines allowed to edit at once is {self.MAX_LINES_TO_EDIT}. ' + f'Got (L{start_idx + 1}-L{end_idx}) {length_of_range} lines.]\n' # [start_idx, end_idx), so no need to + 1 ) # search for relevant ranges to hint the agent topk_chunks: list[Chunk] = get_top_k_chunk_matches( @@ -291,29 +291,29 @@ def edit(self, action: FileEditAction) -> Observation: max_chunk_size=20, # lines ) error_msg += ( - "Here are some snippets that maybe relevant to the provided edit.\n" + 'Here are some snippets that maybe relevant to the provided edit.\n' ) for i, chunk in enumerate(topk_chunks): - error_msg += f"[begin relevant snippet {i+1}. Line range: L{chunk.line_range[0]}-L{chunk.line_range[1]}. Similarity: {chunk.normalized_lcs}]\n" + error_msg += f'[begin relevant snippet {i+1}. Line range: L{chunk.line_range[0]}-L{chunk.line_range[1]}. Similarity: {chunk.normalized_lcs}]\n' error_msg += f'[Browse around it via `open_file("{action.path}", {(chunk.line_range[0] + chunk.line_range[1]) // 2})`]\n' - error_msg += chunk.visualize() + "\n" - error_msg += f"[end relevant snippet {i+1}]\n" - error_msg += "-" * 40 + "\n" + error_msg += chunk.visualize() + '\n' + error_msg += f'[end relevant snippet {i+1}]\n' + error_msg += '-' * 40 + '\n' - error_msg += "Consider using `open_file` to explore around the relevant snippets if needed.\n" + error_msg += 'Consider using `open_file` to explore around the relevant snippets if needed.\n' error_msg += f'**IMPORTANT**: Please REDUCE the range of edits to less than {self.MAX_LINES_TO_EDIT} lines by setting `start` and `end` in the edit action (e.g. ``). ' return ErrorObservation(error_msg) - content_to_edit = "\n".join(old_file_lines[start_idx:end_idx]) + content_to_edit = '\n'.join(old_file_lines[start_idx:end_idx]) self.draft_editor_llm.reset() _edited_content = get_new_file_contents( self.draft_editor_llm, content_to_edit, action.content ) if _edited_content is None: ret_err = ErrorObservation( - "Failed to get new file contents. " - "Please try to reduce the number of edits and try again." + 'Failed to get new file contents. ' + 'Please try to reduce the number of edits and try again.' ) ret_err.llm_metrics = self.draft_editor_llm.metrics return ret_err @@ -321,10 +321,10 @@ def edit(self, action: FileEditAction) -> Observation: # piece the updated content with the unchanged content updated_lines = ( old_file_lines[:start_idx] - + _edited_content.split("\n") + + _edited_content.split('\n') + old_file_lines[end_idx:] ) - updated_content = "\n".join(updated_lines) + updated_content = '\n'.join(updated_lines) diff = get_diff(original_file_content, updated_content, action.path) # Lint the updated content diff --git a/openhands/runtime/utils/files.py b/openhands/runtime/utils/files.py index 54145fc990ed..b9664cafc45f 100644 --- a/openhands/runtime/utils/files.py +++ b/openhands/runtime/utils/files.py @@ -38,7 +38,7 @@ def resolve_path( # If the path is outside the workspace, deny it if not abs_path_in_sandbox.is_relative_to(workspace_mount_path_in_sandbox): - raise PermissionError(f"File access not permitted: {file_path}") + raise PermissionError(f'File access not permitted: {file_path}') # Get path relative to the root of the workspace inside the sandbox path_in_workspace = abs_path_in_sandbox.relative_to( @@ -81,15 +81,15 @@ async def read_file( ) try: - with open(whole_path, "r", encoding="utf-8") as file: + with open(whole_path, 'r', encoding='utf-8') as file: lines = read_lines(file.readlines(), start, end) except FileNotFoundError: - return ErrorObservation(f"File not found: {path}") + return ErrorObservation(f'File not found: {path}') except UnicodeDecodeError: - return ErrorObservation(f"File could not be decoded as utf-8: {path}") + return ErrorObservation(f'File could not be decoded as utf-8: {path}') except IsADirectoryError: - return ErrorObservation(f"Path is a directory: {path}. You can only read files") - code_view = "".join(lines) + return ErrorObservation(f'Path is a directory: {path}. You can only read files') + code_view = ''.join(lines) return FileReadObservation(path=path, content=code_view) @@ -97,9 +97,9 @@ def insert_lines( to_insert: list[str], original: list[str], start: int = 0, end: int = -1 ): """Insert the new content to the original content based on start and end""" - new_lines = [""] if start == 0 else original[:start] - new_lines += [i + "\n" for i in to_insert] - new_lines += [""] if end == -1 else original[end:] + new_lines = [''] if start == 0 else original[:start] + new_lines += [i + '\n' for i in to_insert] + new_lines += [''] if end == -1 else original[end:] return new_lines @@ -112,7 +112,7 @@ async def write_file( start=0, end=-1, ) -> Observation: - insert = content.split("\n") + insert = content.split('\n') try: whole_path = resolve_path( @@ -120,26 +120,26 @@ async def write_file( ) if not os.path.exists(os.path.dirname(whole_path)): os.makedirs(os.path.dirname(whole_path)) - mode = "w" if not os.path.exists(whole_path) else "r+" + mode = 'w' if not os.path.exists(whole_path) else 'r+' try: - with open(whole_path, mode, encoding="utf-8") as file: - if mode != "w": + with open(whole_path, mode, encoding='utf-8') as file: + if mode != 'w': all_lines = file.readlines() new_file = insert_lines(insert, all_lines, start, end) else: - new_file = [i + "\n" for i in insert] + new_file = [i + '\n' for i in insert] file.seek(0) file.writelines(new_file) file.truncate() except FileNotFoundError: - return ErrorObservation(f"File not found: {path}") + return ErrorObservation(f'File not found: {path}') except IsADirectoryError: return ErrorObservation( - f"Path is a directory: {path}. You can only write to files" + f'Path is a directory: {path}. You can only write to files' ) except UnicodeDecodeError: - return ErrorObservation(f"File could not be decoded as utf-8: {path}") + return ErrorObservation(f'File could not be decoded as utf-8: {path}') except PermissionError: - return ErrorObservation(f"Malformed paths not permitted: {path}") - return FileWriteObservation(content="", path=path) + return ErrorObservation(f'Malformed paths not permitted: {path}') + return FileWriteObservation(content='', path=path) diff --git a/openhands/runtime/utils/runtime_build.py b/openhands/runtime/utils/runtime_build.py index 2dc55e45a81d..eab98befe538 100644 --- a/openhands/runtime/utils/runtime_build.py +++ b/openhands/runtime/utils/runtime_build.py @@ -19,13 +19,13 @@ class BuildFromImageType(Enum): - SCRATCH = "scratch" # Slowest: Build from base image (no dependencies are reused) - VERSIONED = "versioned" # Medium speed: Reuse the most recent image with the same base image & OH version (a lot of dependencies are already installed) - LOCK = "lock" # Fastest: Reuse the most recent image with the exact SAME dependencies (lock files) + SCRATCH = 'scratch' # Slowest: Build from base image (no dependencies are reused) + VERSIONED = 'versioned' # Medium speed: Reuse the most recent image with the same base image & OH version (a lot of dependencies are already installed) + LOCK = 'lock' # Fastest: Reuse the most recent image with the exact SAME dependencies (lock files) def get_runtime_image_repo(): - return os.getenv("OH_RUNTIME_RUNTIME_IMAGE_REPO", "ghcr.io/all-hands-ai/runtime") + return os.getenv('OH_RUNTIME_RUNTIME_IMAGE_REPO', 'ghcr.io/all-hands-ai/runtime') def _generate_dockerfile( @@ -45,16 +45,16 @@ def _generate_dockerfile( """ env = Environment( loader=FileSystemLoader( - searchpath=os.path.join(os.path.dirname(__file__), "runtime_templates") + searchpath=os.path.join(os.path.dirname(__file__), 'runtime_templates') ) ) - template = env.get_template("Dockerfile.j2") + template = env.get_template('Dockerfile.j2') dockerfile_content = template.render( base_image=base_image, build_from_scratch=build_from == BuildFromImageType.SCRATCH, build_from_versioned=build_from == BuildFromImageType.VERSIONED, - extra_deps=extra_deps if extra_deps is not None else "", + extra_deps=extra_deps if extra_deps is not None else '', ) return dockerfile_content @@ -68,35 +68,36 @@ def get_runtime_image_repo_and_tag(base_image: str) -> tuple[str, str]: Returns: - tuple[str, str]: The Docker repo and tag of the Docker image """ + if get_runtime_image_repo() in base_image: logger.debug( - f"The provided image [{base_image}] is already a valid runtime image.\n" - f"Will try to reuse it as is." + f'The provided image [{base_image}] is already a valid runtime image.\n' + f'Will try to reuse it as is.' ) - if ":" not in base_image: - base_image = base_image + ":latest" - repo, tag = base_image.split(":") + if ':' not in base_image: + base_image = base_image + ':latest' + repo, tag = base_image.split(':') return repo, tag else: - if ":" not in base_image: - base_image = base_image + ":latest" - [repo, tag] = base_image.split(":") + if ':' not in base_image: + base_image = base_image + ':latest' + [repo, tag] = base_image.split(':') # Hash the repo if it's too long if len(repo) > 32: repo_hash = hashlib.md5(repo[:-24].encode()).hexdigest()[:8] - repo = f"{repo_hash}_{repo[-24:]}" # Use 8 char hash + last 24 chars + repo = f'{repo_hash}_{repo[-24:]}' # Use 8 char hash + last 24 chars else: - repo = repo.replace("/", "_s_") + repo = repo.replace('/', '_s_') - new_tag = f"oh_v{oh_version}_image_{repo}_tag_{tag}" + new_tag = f'oh_v{oh_version}_image_{repo}_tag_{tag}' # if it's still too long, hash the entire image name if len(new_tag) > 128: - new_tag = f"oh_v{oh_version}_image_{hashlib.md5(new_tag.encode()).hexdigest()[:64]}" + new_tag = f'oh_v{oh_version}_image_{hashlib.md5(new_tag.encode()).hexdigest()[:64]}' logger.warning( - f"The new tag [{new_tag}] is still too long, so we use an hash of the entire image name: {new_tag}" + f'The new tag [{new_tag}] is still too long, so we use an hash of the entire image name: {new_tag}' ) return get_runtime_image_repo(), new_tag @@ -163,19 +164,19 @@ def build_runtime_image_in_folder( platform: str | None = None, ) -> str: runtime_image_repo, _ = get_runtime_image_repo_and_tag(base_image) - lock_tag = f"oh_v{oh_version}_{get_hash_for_lock_files(base_image)}" + lock_tag = f'oh_v{oh_version}_{get_hash_for_lock_files(base_image)}' versioned_tag = ( # truncate the base image to 96 characters to fit in the tag max length (128 characters) - f"oh_v{oh_version}_{get_tag_for_versioned_image(base_image)}" + f'oh_v{oh_version}_{get_tag_for_versioned_image(base_image)}' ) - versioned_image_name = f"{runtime_image_repo}:{versioned_tag}" - source_tag = f"{lock_tag}_{get_hash_for_source_files()}" - hash_image_name = f"{runtime_image_repo}:{source_tag}" + versioned_image_name = f'{runtime_image_repo}:{versioned_tag}' + source_tag = f'{lock_tag}_{get_hash_for_source_files()}' + hash_image_name = f'{runtime_image_repo}:{source_tag}' - logger.info(f"Building image: {hash_image_name}") + logger.info(f'Building image: {hash_image_name}') if force_rebuild: logger.debug( - f"Force rebuild: [{runtime_image_repo}:{source_tag}] from scratch." + f'Force rebuild: [{runtime_image_repo}:{source_tag}] from scratch.' ) prep_build_folder( build_folder, @@ -195,29 +196,29 @@ def build_runtime_image_in_folder( ) return hash_image_name - lock_image_name = f"{runtime_image_repo}:{lock_tag}" + lock_image_name = f'{runtime_image_repo}:{lock_tag}' build_from = BuildFromImageType.SCRATCH # If the exact image already exists, we do not need to build it if runtime_builder.image_exists(hash_image_name, False): - logger.debug(f"Reusing Image [{hash_image_name}]") + logger.debug(f'Reusing Image [{hash_image_name}]') return hash_image_name # We look for an existing image that shares the same lock_tag. If such an image exists, we # can use it as the base image for the build and just copy source files. This makes the build # much faster. if runtime_builder.image_exists(lock_image_name): - logger.debug(f"Build [{hash_image_name}] from lock image [{lock_image_name}]") + logger.debug(f'Build [{hash_image_name}] from lock image [{lock_image_name}]') build_from = BuildFromImageType.LOCK base_image = lock_image_name elif runtime_builder.image_exists(versioned_image_name): logger.info( - f"Build [{hash_image_name}] from versioned image [{versioned_image_name}]" + f'Build [{hash_image_name}] from versioned image [{versioned_image_name}]' ) build_from = BuildFromImageType.VERSIONED base_image = versioned_image_name else: - logger.debug(f"Build [{hash_image_name}] from scratch") + logger.debug(f'Build [{hash_image_name}] from scratch') prep_build_folder(build_folder, base_image, build_from, extra_deps) if not dry_run: @@ -248,26 +249,26 @@ def prep_build_folder( # If package is not found, build from source code openhands_source_dir = Path(openhands.__file__).parent project_root = openhands_source_dir.parent - logger.debug(f"Building source distribution using project root: {project_root}") + logger.debug(f'Building source distribution using project root: {project_root}') # Copy the 'openhands' directory (Source code) shutil.copytree( openhands_source_dir, - Path(build_folder, "code", "openhands"), + Path(build_folder, 'code', 'openhands'), ignore=shutil.ignore_patterns( - ".*/", - "__pycache__/", - "*.pyc", - "*.md", + '.*/', + '__pycache__/', + '*.pyc', + '*.md', ), ) # Copy pyproject.toml and poetry.lock files - for file in ["pyproject.toml", "poetry.lock"]: + for file in ['pyproject.toml', 'poetry.lock']: src = Path(openhands_source_dir, file) if not src.exists(): src = Path(project_root, file) - shutil.copy2(src, Path(build_folder, "code", file)) + shutil.copy2(src, Path(build_folder, 'code', file)) # Create a Dockerfile and write it to build_folder dockerfile_content = _generate_dockerfile( @@ -275,7 +276,7 @@ def prep_build_folder( build_from=build_from, extra_deps=extra_deps, ) - with open(Path(build_folder, "Dockerfile"), "w") as file: # type: ignore + with open(Path(build_folder, 'Dockerfile'), 'w') as file: # type: ignore file.write(dockerfile_content) # type: ignore @@ -289,19 +290,19 @@ def truncate_hash(hash: str) -> str: while value > 0 and len(result) < 16: value, remainder = divmod(value, len(_ALPHABET)) result.append(_ALPHABET[remainder]) - return "".join(result) + return ''.join(result) def get_hash_for_lock_files(base_image: str): openhands_source_dir = Path(openhands.__file__).parent md5 = hashlib.md5() md5.update(base_image.encode()) - for file in ["pyproject.toml", "poetry.lock"]: + for file in ['pyproject.toml', 'poetry.lock']: src = Path(openhands_source_dir, file) if not src.exists(): src = Path(openhands_source_dir.parent, file) - with open(src, "rb") as f: - for chunk in iter(lambda: f.read(4096), b""): + with open(src, 'rb') as f: + for chunk in iter(lambda: f.read(4096), b''): md5.update(chunk) # We get away with truncation because we want something that is unique # rather than something that is cryptographically secure @@ -310,18 +311,18 @@ def get_hash_for_lock_files(base_image: str): def get_tag_for_versioned_image(base_image: str): - return base_image.replace("/", "_s_").replace(":", "_t_").lower()[-96:] + return base_image.replace('/', '_s_').replace(':', '_t_').lower()[-96:] def get_hash_for_source_files(): openhands_source_dir = Path(openhands.__file__).parent dir_hash = dirhash( openhands_source_dir, - "md5", + 'md5', ignore=[ - ".*/", # hidden directories - "__pycache__/", - "*.pyc", + '.*/', # hidden directories + '__pycache__/', + '*.pyc', ], ) # We get away with truncation because we want something that is unique @@ -341,30 +342,30 @@ def _build_sandbox_image( ): """Build and tag the sandbox image. The image will be tagged with all tags that do not yet exist""" names = [ - f"{runtime_image_repo}:{source_tag}", - f"{runtime_image_repo}:{lock_tag}", + f'{runtime_image_repo}:{source_tag}', + f'{runtime_image_repo}:{lock_tag}', ] if versioned_tag is not None: - names.append(f"{runtime_image_repo}:{versioned_tag}") + names.append(f'{runtime_image_repo}:{versioned_tag}') names = [name for name in names if not runtime_builder.image_exists(name, False)] image_name = runtime_builder.build( path=str(build_folder), tags=names, platform=platform ) if not image_name: - raise RuntimeError(f"Build failed for image {names}") + raise RuntimeError(f'Build failed for image {names}') return image_name -if __name__ == "__main__": +if __name__ == '__main__': parser = argparse.ArgumentParser() parser.add_argument( - "--base_image", type=str, default="nikolaik/python-nodejs:python3.12-nodejs22" + '--base_image', type=str, default='nikolaik/python-nodejs:python3.12-nodejs22' ) - parser.add_argument("--build_folder", type=str, default=None) - parser.add_argument("--force_rebuild", action="store_true", default=False) - parser.add_argument("--platform", type=str, default=None) + parser.add_argument('--build_folder', type=str, default=None) + parser.add_argument('--force_rebuild', action='store_true', default=False) + parser.add_argument('--platform', type=str, default=None) args = parser.parse_args() if args.build_folder is not None: @@ -374,16 +375,16 @@ def _build_sandbox_image( build_folder = args.build_folder assert os.path.exists( build_folder - ), f"Build folder {build_folder} does not exist" + ), f'Build folder {build_folder} does not exist' logger.debug( - f"Copying the source code and generating the Dockerfile in the build folder: {build_folder}" + f'Copying the source code and generating the Dockerfile in the build folder: {build_folder}' ) runtime_image_repo, runtime_image_tag = get_runtime_image_repo_and_tag( args.base_image ) logger.debug( - f"Runtime image repo: {runtime_image_repo} and runtime image tag: {runtime_image_tag}" + f'Runtime image repo: {runtime_image_repo} and runtime image tag: {runtime_image_tag}' ) with tempfile.TemporaryDirectory() as temp_dir: @@ -399,38 +400,38 @@ def _build_sandbox_image( ) _runtime_image_repo, runtime_image_source_tag = ( - runtime_image_hash_name.split(":") + runtime_image_hash_name.split(':') ) # Move contents of temp_dir to build_folder shutil.copytree(temp_dir, build_folder, dirs_exist_ok=True) logger.debug( - f"Build folder [{build_folder}] is ready: {os.listdir(build_folder)}" + f'Build folder [{build_folder}] is ready: {os.listdir(build_folder)}' ) # We now update the config.sh in the build_folder to contain the required values. This is used in the # containers/build.sh script which is called to actually build the Docker image - with open(os.path.join(build_folder, "config.sh"), "a") as file: + with open(os.path.join(build_folder, 'config.sh'), 'a') as file: file.write( ( - f"\n" - f"DOCKER_IMAGE_TAG={runtime_image_tag}\n" - f"DOCKER_IMAGE_SOURCE_TAG={runtime_image_source_tag}\n" + f'\n' + f'DOCKER_IMAGE_TAG={runtime_image_tag}\n' + f'DOCKER_IMAGE_SOURCE_TAG={runtime_image_source_tag}\n' ) ) logger.debug( - f"`config.sh` is updated with the image repo[{runtime_image_repo}] and tags [{runtime_image_tag}, {runtime_image_source_tag}]" + f'`config.sh` is updated with the image repo[{runtime_image_repo}] and tags [{runtime_image_tag}, {runtime_image_source_tag}]' ) logger.debug( - f"Dockerfile, source code and config.sh are ready in {build_folder}" + f'Dockerfile, source code and config.sh are ready in {build_folder}' ) else: # If a build_folder is not provided, after copying the required source code and dynamically creating the # Dockerfile, we actually build the Docker image - logger.debug("Building image in a temporary folder") + logger.debug('Building image in a temporary folder') docker_builder = DockerRuntimeBuilder(docker.from_env()) image_name = build_runtime_image( args.base_image, docker_builder, platform=args.platform ) - logger.debug(f"\nBuilt image: {image_name}\n") + logger.debug(f'\nBuilt image: {image_name}\n') diff --git a/openhands/runtime/utils/runtime_init.py b/openhands/runtime/utils/runtime_init.py index 6615db359a19..9ebba67fcd31 100644 --- a/openhands/runtime/utils/runtime_init.py +++ b/openhands/runtime/utils/runtime_init.py @@ -31,41 +31,42 @@ def init_user_and_working_directory( Returns: int | None: The user ID if it was updated, None otherwise. """ + # First create the working directory, independent of the user - logger.debug(f"Client working directory: {initial_pwd}") - command = f"umask 002; mkdir -p {initial_pwd}" + logger.debug(f'Client working directory: {initial_pwd}') + command = f'umask 002; mkdir -p {initial_pwd}' output = subprocess.run(command, shell=True, capture_output=True) out_str = output.stdout.decode() - command = f"chown -R {username}:root {initial_pwd}" + command = f'chown -R {username}:root {initial_pwd}' output = subprocess.run(command, shell=True, capture_output=True) out_str += output.stdout.decode() - command = f"chmod g+rw {initial_pwd}" + command = f'chmod g+rw {initial_pwd}' output = subprocess.run(command, shell=True, capture_output=True) out_str += output.stdout.decode() - logger.debug(f"Created working directory. Output: [{out_str}]") + logger.debug(f'Created working directory. Output: [{out_str}]') # Skip root since it is already created - if username == "root": + if username == 'root': return None # Check if the username already exists existing_user_id = -1 try: result = subprocess.run( - f"id -u {username}", shell=True, check=True, capture_output=True + f'id -u {username}', shell=True, check=True, capture_output=True ) existing_user_id = int(result.stdout.decode().strip()) # The user ID already exists, skip setup if existing_user_id == user_id: logger.debug( - f"User `{username}` already has the provided UID {user_id}. Skipping user setup." + f'User `{username}` already has the provided UID {user_id}. Skipping user setup.' ) else: logger.warning( - f"User `{username}` already exists with UID {existing_user_id}. Skipping user setup." + f'User `{username}` already exists with UID {existing_user_id}. Skipping user setup.' ) return existing_user_id return None @@ -73,30 +74,30 @@ def init_user_and_working_directory( # Returncode 1 indicates, that the user does not exist yet if e.returncode == 1: logger.debug( - f"User `{username}` does not exist. Proceeding with user creation." + f'User `{username}` does not exist. Proceeding with user creation.' ) else: - logger.error(f"Error checking user `{username}`, skipping setup:\n{e}\n") + logger.error(f'Error checking user `{username}`, skipping setup:\n{e}\n') raise # Add sudoer sudoer_line = r"echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers" output = subprocess.run(sudoer_line, shell=True, capture_output=True) if output.returncode != 0: - raise RuntimeError(f"Failed to add sudoer: {output.stderr.decode()}") - logger.debug(f"Added sudoer successfully. Output: [{output.stdout.decode()}]") + raise RuntimeError(f'Failed to add sudoer: {output.stderr.decode()}') + logger.debug(f'Added sudoer successfully. Output: [{output.stdout.decode()}]') command = ( - f"useradd -rm -d /home/{username} -s /bin/bash " - f"-g root -G sudo -u {user_id} {username}" + f'useradd -rm -d /home/{username} -s /bin/bash ' + f'-g root -G sudo -u {user_id} {username}' ) output = subprocess.run(command, shell=True, capture_output=True) if output.returncode == 0: logger.debug( - f"Added user `{username}` successfully with UID {user_id}. Output: [{output.stdout.decode()}]" + f'Added user `{username}` successfully with UID {user_id}. Output: [{output.stdout.decode()}]' ) else: raise RuntimeError( - f"Failed to create user `{username}` with UID {user_id}. Output: [{output.stderr.decode()}]" + f'Failed to create user `{username}` with UID {user_id}. Output: [{output.stderr.decode()}]' ) return None diff --git a/openhands/runtime/utils/runtime_templates/Dockerfile.j2 b/openhands/runtime/utils/runtime_templates/Dockerfile.j2 index f9fb596d3414..cb27bf22795c 100644 --- a/openhands/runtime/utils/runtime_templates/Dockerfile.j2 +++ b/openhands/runtime/utils/runtime_templates/Dockerfile.j2 @@ -1,8 +1,71 @@ FROM {{ base_image }} -# Shared environment variables (regardless of init or not) -ENV POETRY_VIRTUALENVS_PATH=/openhands/poetry -ENV MAMBA_ROOT_PREFIX=/openhands/micromamba +# Shared environment variables +ENV POETRY_VIRTUALENVS_PATH=/openhands/poetry \ + MAMBA_ROOT_PREFIX=/openhands/micromamba \ + LANG=C.UTF-8 \ + LC_ALL=C.UTF-8 \ + EDITOR=code \ + VISUAL=code \ + GIT_EDITOR="code --wait" \ + OPENVSCODE_SERVER_ROOT=/openhands/.openvscode-server + +{% macro setup_base_system() %} + +# Install base system dependencies +RUN apt-get update && \ + apt-get install -y --no-install-recommends \ + wget curl sudo apt-utils git \ + {% if 'ubuntu' in base_image and (base_image.endswith(':latest') or base_image.endswith(':24.04')) %} + libgl1 \ + {% else %} + libgl1-mesa-glx \ + {% endif %} + libasound2-plugins libatomic1 curl && \ + apt-get clean && \ + rm -rf /var/lib/apt/lists/* + +# Remove UID 1000 if it's called pn--this fixes the nikolaik image for ubuntu users +RUN if getent passwd 1000 | grep -q pn; then userdel pn; fi + +# Create necessary directories +RUN mkdir -p /openhands && \ + mkdir -p /openhands/logs && \ + mkdir -p /openhands/poetry + +{% endmacro %} + +{% macro setup_vscode_server() %} +# Reference: +# 1. https://github.com/gitpod-io/openvscode-server +# 2. https://github.com/gitpod-io/openvscode-releases + +# Setup VSCode Server +ARG RELEASE_TAG="openvscode-server-v1.94.2" +ARG RELEASE_ORG="gitpod-io" +# ARG USERNAME=openvscode-server +# ARG USER_UID=1000 +# ARG USER_GID=1000 + +RUN if [ -z "${RELEASE_TAG}" ]; then \ + echo "The RELEASE_TAG build arg must be set." >&2 && \ + exit 1; \ + fi && \ + arch=$(uname -m) && \ + if [ "${arch}" = "x86_64" ]; then \ + arch="x64"; \ + elif [ "${arch}" = "aarch64" ]; then \ + arch="arm64"; \ + elif [ "${arch}" = "armv7l" ]; then \ + arch="armhf"; \ + fi && \ + wget https://github.com/${RELEASE_ORG}/openvscode-server/releases/download/${RELEASE_TAG}/${RELEASE_TAG}-linux-${arch}.tar.gz && \ + tar -xzf ${RELEASE_TAG}-linux-${arch}.tar.gz && \ + mv -f ${RELEASE_TAG}-linux-${arch} ${OPENVSCODE_SERVER_ROOT} && \ + cp ${OPENVSCODE_SERVER_ROOT}/bin/remote-cli/openvscode-server ${OPENVSCODE_SERVER_ROOT}/bin/remote-cli/code && \ + rm -f ${RELEASE_TAG}-linux-${arch}.tar.gz + +{% endmacro %} {% macro install_dependencies() %} # Install all dependencies @@ -28,6 +91,7 @@ RUN \ # Clean up apt-get clean && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \ /openhands/micromamba/bin/micromamba clean --all + {% endmacro %} {% if build_from_scratch %} @@ -37,25 +101,8 @@ RUN \ # This is used in cases where the base image is something more generic like nikolaik/python-nodejs # rather than the current OpenHands release -{% if 'ubuntu' in base_image and (base_image.endswith(':latest') or base_image.endswith(':24.04')) %} -{% set LIBGL_MESA = 'libgl1' %} -{% else %} -{% set LIBGL_MESA = 'libgl1-mesa-glx' %} -{% endif %} - -# Install necessary packages and clean up in one layer -RUN apt-get update && \ - apt-get install -y wget curl sudo apt-utils {{ LIBGL_MESA }} libasound2-plugins git && \ - apt-get clean && \ - rm -rf /var/lib/apt/lists/* - -# Remove UID 1000 if it's called pn--this fixes the nikolaik image for ubuntu users -RUN if getent passwd 1000 | grep -q pn; then userdel pn; fi - -# Create necessary directories -RUN mkdir -p /openhands && \ - mkdir -p /openhands/logs && \ - mkdir -p /openhands/poetry +{{ setup_base_system() }} +{{ setup_vscode_server() }} # Install micromamba RUN mkdir -p /openhands/micromamba/bin && \ @@ -72,6 +119,7 @@ RUN \ if [ -d /openhands/code ]; then rm -rf /openhands/code; fi && \ mkdir -p /openhands/code/openhands && \ touch /openhands/code/openhands/__init__.py + COPY ./code/pyproject.toml ./code/poetry.lock /openhands/code/ {{ install_dependencies() }} diff --git a/openhands/runtime/utils/system.py b/openhands/runtime/utils/system.py index 9d5bfb3173ae..8055b9b56915 100644 --- a/openhands/runtime/utils/system.py +++ b/openhands/runtime/utils/system.py @@ -3,6 +3,18 @@ import time +def check_port_available(port: int) -> bool: + sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) + try: + sock.bind(('localhost', port)) + return True + except OSError: + time.sleep(0.1) # Short delay to further reduce chance of collisions + return False + finally: + sock.close() + + def find_available_tcp_port(min_port=30000, max_port=39999, max_attempts=10) -> int: """Find an available TCP port in a specified range. @@ -19,15 +31,8 @@ def find_available_tcp_port(min_port=30000, max_port=39999, max_attempts=10) -> rng.shuffle(ports) for port in ports[:max_attempts]: - sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) - try: - sock.bind(("localhost", port)) + if check_port_available(port): return port - except OSError: - time.sleep(0.1) # Short delay to further reduce chance of collisions - continue - finally: - sock.close() return -1 @@ -37,16 +42,16 @@ def display_number_matrix(number: int) -> str | None: # Define the matrix representation for each digit digits = { - "0": ["###", "# #", "# #", "# #", "###"], - "1": [" #", " #", " #", " #", " #"], - "2": ["###", " #", "###", "# ", "###"], - "3": ["###", " #", "###", " #", "###"], - "4": ["# #", "# #", "###", " #", " #"], - "5": ["###", "# ", "###", " #", "###"], - "6": ["###", "# ", "###", "# #", "###"], - "7": ["###", " #", " #", " #", " #"], - "8": ["###", "# #", "###", "# #", "###"], - "9": ["###", "# #", "###", " #", "###"], + '0': ['###', '# #', '# #', '# #', '###'], + '1': [' #', ' #', ' #', ' #', ' #'], + '2': ['###', ' #', '###', '# ', '###'], + '3': ['###', ' #', '###', ' #', '###'], + '4': ['# #', '# #', '###', ' #', ' #'], + '5': ['###', '# ', '###', ' #', '###'], + '6': ['###', '# ', '###', '# #', '###'], + '7': ['###', ' #', ' #', ' #', ' #'], + '8': ['###', '# #', '###', '# #', '###'], + '9': ['###', '# #', '###', ' #', '###'], } # alternatively, with leading zeros: num_str = f"{number:03d}" @@ -54,8 +59,8 @@ def display_number_matrix(number: int) -> str | None: result = [] for row in range(5): - line = " ".join(digits[digit][row] for digit in num_str) + line = ' '.join(digits[digit][row] for digit in num_str) result.append(line) - matrix_display = "\n".join(result) - return f"\n{matrix_display}\n" + matrix_display = '\n'.join(result) + return f'\n{matrix_display}\n' diff --git a/openhands/runtime/utils/tenacity_stop.py b/openhands/runtime/utils/tenacity_stop.py index e6dc01db4606..d9aa83a6130d 100644 --- a/openhands/runtime/utils/tenacity_stop.py +++ b/openhands/runtime/utils/tenacity_stop.py @@ -1,11 +1,11 @@ from tenacity import RetryCallState from tenacity.stop import stop_base -from openhands.runtime.utils.shutdown_listener import should_exit +from openhands.utils.shutdown_listener import should_exit class stop_if_should_exit(stop_base): """Stop if the should_exit flag is set.""" - def __call__(self, retry_state: "RetryCallState") -> bool: + def __call__(self, retry_state: 'RetryCallState') -> bool: return should_exit() diff --git a/openhands/security/invariant/__init__.py b/openhands/security/invariant/__init__.py index 24c7709e3118..9445ef804a01 100644 --- a/openhands/security/invariant/__init__.py +++ b/openhands/security/invariant/__init__.py @@ -1,5 +1,5 @@ from openhands.security.invariant.analyzer import InvariantAnalyzer __all__ = [ - "InvariantAnalyzer", + 'InvariantAnalyzer', ] diff --git a/openhands/security/invariant/analyzer.py b/openhands/security/invariant/analyzer.py index 2275ddd0f1f3..0ba13b4ecddf 100644 --- a/openhands/security/invariant/analyzer.py +++ b/openhands/security/invariant/analyzer.py @@ -28,9 +28,9 @@ class InvariantAnalyzer(SecurityAnalyzer): trace: list[TraceElement] input: list[dict] - container_name: str = "openhands-invariant-server" - image_name: str = "ghcr.io/invariantlabs-ai/server:openhands" - api_host: str = "http://localhost" + container_name: str = 'openhands-invariant-server' + image_name: str = 'ghcr.io/invariantlabs-ai/server:openhands' + api_host: str = 'http://localhost' timeout: int = 180 settings: dict = {} @@ -52,16 +52,16 @@ def __init__( self.docker_client = docker.from_env() except Exception as ex: logger.exception( - "Error creating Invariant Security Analyzer container. Please check that Docker is running or disable the Security Analyzer in settings.", + 'Error creating Invariant Security Analyzer container. Please check that Docker is running or disable the Security Analyzer in settings.', exc_info=False, ) raise ex running_containers = self.docker_client.containers.list( - filters={"name": self.container_name} + filters={'name': self.container_name} ) if not running_containers: all_containers = self.docker_client.containers.list( - all=True, filters={"name": self.container_name} + all=True, filters={'name': self.container_name} ) if all_containers: self.container = all_containers[0] @@ -71,33 +71,33 @@ def __init__( self.container = self.docker_client.containers.run( self.image_name, name=self.container_name, - platform="linux/amd64", - ports={"8000/tcp": self.api_port}, + platform='linux/amd64', + ports={'8000/tcp': self.api_port}, detach=True, ) else: self.container = running_containers[0] elapsed = 0 - while self.container.status != "running": + while self.container.status != 'running': self.container = self.docker_client.containers.get(self.container_name) elapsed += 1 logger.debug( - f"waiting for container to start: {elapsed}, container status: {self.container.status}" + f'waiting for container to start: {elapsed}, container status: {self.container.status}' ) if elapsed > self.timeout: break self.api_port = int( - self.container.attrs["NetworkSettings"]["Ports"]["8000/tcp"][0]["HostPort"] + self.container.attrs['NetworkSettings']['Ports']['8000/tcp'][0]['HostPort'] ) - self.api_server = f"{self.api_host}:{self.api_port}" + self.api_server = f'{self.api_host}:{self.api_port}' self.client = InvariantClient(self.api_server, self.sid) if policy is None: policy, _ = self.client.Policy.get_template() if policy is None: - policy = "" + policy = '' self.monitor = self.client.Monitor.from_string(policy) async def close(self): @@ -109,15 +109,15 @@ async def log_event(self, event: Event) -> None: self.trace.extend(element) self.input.extend([e.model_dump(exclude_none=True) for e in element]) # type: ignore [call-overload] else: - logger.debug("Invariant skipping element: event") + logger.debug('Invariant skipping element: event') def get_risk(self, results: list[str]) -> ActionSecurityRisk: mapping = { - "high": ActionSecurityRisk.HIGH, - "medium": ActionSecurityRisk.MEDIUM, - "low": ActionSecurityRisk.LOW, + 'high': ActionSecurityRisk.HIGH, + 'medium': ActionSecurityRisk.MEDIUM, + 'low': ActionSecurityRisk.LOW, } - regex = r"(?<=risk=)\w+" + regex = r'(?<=risk=)\w+' risks = [] for result in results: m = re.search(regex, result) @@ -137,22 +137,22 @@ async def should_confirm(self, event: Event) -> bool: risk = event.security_risk # type: ignore [attr-defined] return ( risk is not None - and risk < self.settings.get("RISK_SEVERITY", ActionSecurityRisk.MEDIUM) - and hasattr(event, "confirmation_state") + and risk < self.settings.get('RISK_SEVERITY', ActionSecurityRisk.MEDIUM) + and hasattr(event, 'confirmation_state') and event.confirmation_state == ActionConfirmationStatus.AWAITING_CONFIRMATION ) async def confirm(self, event: Event) -> None: new_event = action_from_dict( - {"action": "change_agent_state", "args": {"agent_state": "user_confirmed"}} + {'action': 'change_agent_state', 'args': {'agent_state': 'user_confirmed'}} ) # we should confirm only on agent actions event_source = event.source if event.source else EventSource.AGENT await call_sync_from_async(self.event_stream.add_event, new_event, event_source) async def security_risk(self, event: Action) -> ActionSecurityRisk: - logger.debug("Calling security_risk on InvariantAnalyzer") + logger.debug('Calling security_risk on InvariantAnalyzer') new_elements = parse_element(self.trace, event) input = [e.model_dump(exclude_none=True) for e in new_elements] # type: ignore [call-overload] self.trace.extend(new_elements) @@ -160,7 +160,7 @@ async def security_risk(self, event: Action) -> ActionSecurityRisk: self.input.extend(input) risk = ActionSecurityRisk.UNKNOWN if err: - logger.warning(f"Error checking policy: {err}") + logger.warning(f'Error checking policy: {err}') return risk risk = self.get_risk(result) @@ -169,35 +169,35 @@ async def security_risk(self, event: Action) -> ActionSecurityRisk: ### Handle API requests async def handle_api_request(self, request: Request) -> Any: - path_parts = request.url.path.strip("/").split("/") + path_parts = request.url.path.strip('/').split('/') endpoint = path_parts[-1] # Get the last part of the path - if request.method == "GET": - if endpoint == "export-trace": + if request.method == 'GET': + if endpoint == 'export-trace': return await self.export_trace(request) - elif endpoint == "policy": + elif endpoint == 'policy': return await self.get_policy(request) - elif endpoint == "settings": + elif endpoint == 'settings': return await self.get_settings(request) - elif request.method == "POST": - if endpoint == "policy": + elif request.method == 'POST': + if endpoint == 'policy': return await self.update_policy(request) - elif endpoint == "settings": + elif endpoint == 'settings': return await self.update_settings(request) - raise HTTPException(status_code=405, detail="Method Not Allowed") + raise HTTPException(status_code=405, detail='Method Not Allowed') async def export_trace(self, request: Request) -> Any: return JSONResponse(content=self.input) async def get_policy(self, request: Request) -> Any: - return JSONResponse(content={"policy": self.monitor.policy}) + return JSONResponse(content={'policy': self.monitor.policy}) async def update_policy(self, request: Request) -> Any: data = await request.json() - policy = data.get("policy") + policy = data.get('policy') new_monitor = self.client.Monitor.from_string(policy) self.monitor = new_monitor - return JSONResponse(content={"policy": policy}) + return JSONResponse(content={'policy': policy}) async def get_settings(self, request: Request) -> Any: return JSONResponse(content=self.settings) diff --git a/openhands/security/invariant/client.py b/openhands/security/invariant/client.py index a9228f268f83..c41828745658 100644 --- a/openhands/security/invariant/client.py +++ b/openhands/security/invariant/client.py @@ -12,7 +12,7 @@ def __init__(self, server_url: str, session_id: str | None = None): self.server = server_url self.session_id, err = self._create_session(session_id) if err: - raise RuntimeError(f"Failed to create session: {err}") + raise RuntimeError(f'Failed to create session: {err}') self.Policy = self._Policy(self) self.Monitor = self._Monitor(self) @@ -24,12 +24,12 @@ def _create_session( try: if session_id: response = requests.get( - f"{self.server}/session/new?session_id={session_id}", timeout=60 + f'{self.server}/session/new?session_id={session_id}', timeout=60 ) else: - response = requests.get(f"{self.server}/session/new", timeout=60) + response = requests.get(f'{self.server}/session/new', timeout=60) response.raise_for_status() - return response.json().get("id"), None + return response.json().get('id'), None except (ConnectionError, Timeout): elapsed += 1 time.sleep(1) @@ -37,12 +37,12 @@ def _create_session( return None, http_err except Exception as err: return None, err - return None, ConnectionError("Connection timed out") + return None, ConnectionError('Connection timed out') def close_session(self) -> Union[None, Exception]: try: response = requests.delete( - f"{self.server}/session/?session_id={self.session_id}", timeout=60 + f'{self.server}/session/?session_id={self.session_id}', timeout=60 ) response.raise_for_status() except (ConnectionError, Timeout, HTTPError) as err: @@ -57,19 +57,19 @@ def __init__(self, invariant): def _create_policy(self, rule: str) -> tuple[str | None, Exception | None]: try: response = requests.post( - f"{self.server}/policy/new?session_id={self.session_id}", - json={"rule": rule}, + f'{self.server}/policy/new?session_id={self.session_id}', + json={'rule': rule}, timeout=60, ) response.raise_for_status() - return response.json().get("policy_id"), None + return response.json().get('policy_id'), None except (ConnectionError, Timeout, HTTPError) as err: return None, err def get_template(self) -> tuple[str | None, Exception | None]: try: response = requests.get( - f"{self.server}/policy/template", + f'{self.server}/policy/template', timeout=60, ) response.raise_for_status() @@ -87,8 +87,8 @@ def from_string(self, rule: str): def analyze(self, trace: list[dict]) -> Union[Any, Exception]: try: response = requests.post( - f"{self.server}/policy/{self.policy_id}/analyze?session_id={self.session_id}", - json={"trace": trace}, + f'{self.server}/policy/{self.policy_id}/analyze?session_id={self.session_id}', + json={'trace': trace}, timeout=60, ) response.raise_for_status() @@ -100,17 +100,17 @@ class _Monitor: def __init__(self, invariant): self.server = invariant.server self.session_id = invariant.session_id - self.policy = "" + self.policy = '' def _create_monitor(self, rule: str) -> tuple[str | None, Exception | None]: try: response = requests.post( - f"{self.server}/monitor/new?session_id={self.session_id}", - json={"rule": rule}, + f'{self.server}/monitor/new?session_id={self.session_id}', + json={'rule': rule}, timeout=60, ) response.raise_for_status() - return response.json().get("monitor_id"), None + return response.json().get('monitor_id'), None except (ConnectionError, Timeout, HTTPError) as err: return None, err @@ -127,8 +127,8 @@ def check( ) -> Union[Any, Exception]: try: response = requests.post( - f"{self.server}/monitor/{self.monitor_id}/check?session_id={self.session_id}", - json={"past_events": past_events, "pending_events": pending_events}, + f'{self.server}/monitor/{self.monitor_id}/check?session_id={self.session_id}', + json={'past_events': past_events, 'pending_events': pending_events}, timeout=60, ) response.raise_for_status() diff --git a/openhands/security/invariant/nodes.py b/openhands/security/invariant/nodes.py index 42d7b6a6011f..47410264743b 100644 --- a/openhands/security/invariant/nodes.py +++ b/openhands/security/invariant/nodes.py @@ -10,7 +10,7 @@ class LLM: class Event(BaseModel): metadata: dict | None = Field( - default_factory=dict, description="Metadata associated with the event" + default_factory=dict, description='Metadata associated with the event' ) @@ -32,9 +32,9 @@ class Message(Event): def __rich_repr__(self): # Print on separate line - yield "role", self.role - yield "content", self.content - yield "tool_calls", self.tool_calls + yield 'role', self.role + yield 'content', self.content + yield 'tool_calls', self.tool_calls class ToolOutput(Event): diff --git a/openhands/security/invariant/parser.py b/openhands/security/invariant/parser.py index b3d6e06ed167..dea128692442 100644 --- a/openhands/security/invariant/parser.py +++ b/openhands/security/invariant/parser.py @@ -26,7 +26,7 @@ def get_next_id(trace: list[TraceElement]) -> str: for i in range(1, len(used_ids) + 2): if str(i) not in used_ids: return str(i) - return "1" + return '1' def get_last_id( @@ -43,21 +43,21 @@ def parse_action(trace: list[TraceElement], action: Action) -> list[TraceElement inv_trace = [] # type: list[TraceElement] if type(action) == MessageAction: if action.source == EventSource.USER: - inv_trace.append(Message(role="user", content=action.content)) + inv_trace.append(Message(role='user', content=action.content)) else: - inv_trace.append(Message(role="assistant", content=action.content)) + inv_trace.append(Message(role='assistant', content=action.content)) elif type(action) in [NullAction, ChangeAgentStateAction]: pass - elif hasattr(action, "action") and action.action is not None: + elif hasattr(action, 'action') and action.action is not None: event_dict = event_to_dict(action) - args = event_dict.get("args", {}) - thought = args.pop("thought", None) + args = event_dict.get('args', {}) + thought = args.pop('thought', None) function = Function(name=action.action, arguments=args) if thought is not None: - inv_trace.append(Message(role="assistant", content=thought)) - inv_trace.append(ToolCall(id=next_id, type="function", function=function)) + inv_trace.append(Message(role='assistant', content=thought)) + inv_trace.append(ToolCall(id=next_id, type='function', function=function)) else: - logger.error(f"Unknown action type: {type(action)}") + logger.error(f'Unknown action type: {type(action)}') return inv_trace @@ -67,10 +67,10 @@ def parse_observation( last_id = get_last_id(trace) if type(obs) in [NullObservation, AgentStateChangedObservation]: return [] - elif hasattr(obs, "content") and obs.content is not None: - return [ToolOutput(role="tool", content=obs.content, tool_call_id=last_id)] + elif hasattr(obs, 'content') and obs.content is not None: + return [ToolOutput(role='tool', content=obs.content, tool_call_id=last_id)] else: - logger.error(f"Unknown observation type: {type(obs)}") + logger.error(f'Unknown observation type: {type(obs)}') return [] @@ -99,5 +99,5 @@ def add_action(self, action: Action): def add_observation(self, obs: Observation): self.trace.extend(parse_observation(self.trace, obs)) - def concatenate(self, other: "InvariantState"): + def concatenate(self, other: 'InvariantState'): self.trace.extend(other.trace) diff --git a/openhands/server/auth/__init__.py b/openhands/server/auth/__init__.py index ed33d8d618c7..0fe3ddd8cc0c 100644 --- a/openhands/server/auth/__init__.py +++ b/openhands/server/auth/__init__.py @@ -1,3 +1,3 @@ from openhands.server.auth.auth import get_sid_from_token, sign_token -__all__ = ["get_sid_from_token", "sign_token"] +__all__ = ['get_sid_from_token', 'sign_token'] diff --git a/openhands/server/auth/auth.py b/openhands/server/auth/auth.py index 3547361ea369..d668650f5834 100644 --- a/openhands/server/auth/auth.py +++ b/openhands/server/auth/auth.py @@ -15,19 +15,19 @@ def get_sid_from_token(token: str, jwt_secret: str) -> str: """ try: # Decode the JWT using the specified secret and algorithm - payload = jwt.decode(token, jwt_secret, algorithms=["HS256"]) + payload = jwt.decode(token, jwt_secret, algorithms=['HS256']) # Ensure the payload contains 'sid' - if "sid" in payload: - return payload["sid"] + if 'sid' in payload: + return payload['sid'] else: - logger.error("SID not found in token") - return "" + logger.error('SID not found in token') + return '' except InvalidTokenError: - logger.error("Invalid token") + logger.error('Invalid token') except Exception as e: - logger.exception("Unexpected error decoding token: %s", e) - return "" + logger.exception('Unexpected error decoding token: %s', e) + return '' def sign_token(payload: dict[str, object], jwt_secret: str) -> str: @@ -36,4 +36,4 @@ def sign_token(payload: dict[str, object], jwt_secret: str) -> str: # "sid": sid, # # "exp": datetime.now(timezone.utc) + timedelta(minutes=15), # } - return jwt.encode(payload, jwt_secret, algorithm="HS256") + return jwt.encode(payload, jwt_secret, algorithm='HS256') diff --git a/openhands/server/data_models/feedback.py b/openhands/server/data_models/feedback.py index 54463e24169f..59f32008b520 100644 --- a/openhands/server/data_models/feedback.py +++ b/openhands/server/data_models/feedback.py @@ -10,36 +10,36 @@ class FeedbackDataModel(BaseModel): version: str email: str - polarity: Literal["positive", "negative"] + polarity: Literal['positive', 'negative'] feedback: Literal[ - "positive", "negative" + 'positive', 'negative' ] # TODO: remove this, its here for backward compatibility - permissions: Literal["public", "private"] + permissions: Literal['public', 'private'] trajectory: Optional[list[dict[str, Any]]] -FEEDBACK_URL = "https://share-od-trajectory-3u9bw9tx.uc.gateway.dev/share_od_trajectory" +FEEDBACK_URL = 'https://share-od-trajectory-3u9bw9tx.uc.gateway.dev/share_od_trajectory' def store_feedback(feedback: FeedbackDataModel) -> dict[str, str]: # Start logging feedback.feedback = feedback.polarity display_feedback = feedback.model_dump() - if "trajectory" in display_feedback: - display_feedback["trajectory"] = ( + if 'trajectory' in display_feedback: + display_feedback['trajectory'] = ( f"elided [length: {len(display_feedback['trajectory'])}" ) - if "token" in display_feedback: - display_feedback["token"] = "elided" - logger.debug(f"Got feedback: {display_feedback}") + if 'token' in display_feedback: + display_feedback['token'] = 'elided' + logger.debug(f'Got feedback: {display_feedback}') # Start actual request response = requests.post( FEEDBACK_URL, - headers={"Content-Type": "application/json"}, + headers={'Content-Type': 'application/json'}, json=feedback.model_dump(), ) if response.status_code != 200: - raise ValueError(f"Failed to store feedback: {response.text}") + raise ValueError(f'Failed to store feedback: {response.text}') response_data = json.loads(response.text) - logger.debug(f"Stored feedback: {response.text}") + logger.debug(f'Stored feedback: {response.text}') return response_data diff --git a/openhands/server/listen.py b/openhands/server/listen.py index 94c956a1459b..d18bea277404 100644 --- a/openhands/server/listen.py +++ b/openhands/server/listen.py @@ -368,7 +368,8 @@ async def websocket_endpoint(websocket: WebSocket): @app.get('/api/options/models') async def get_litellm_models() -> list[str]: - """Get all models supported by LiteLLM. + """ + Get all models supported by LiteLLM. This function combines models from litellm and Bedrock, removing any error-prone Bedrock models. @@ -891,6 +892,34 @@ async def authenticate(request: Request): return response +@app.get('/api/vscode-url') +async def get_vscode_url(request: Request): + """Get the VSCode URL. + + This endpoint allows getting the VSCode URL. + + Args: + request (Request): The incoming FastAPI request object. + + Returns: + JSONResponse: A JSON response indicating the success of the operation. + """ + try: + runtime: Runtime = request.state.conversation.runtime + logger.debug(f'Runtime type: {type(runtime)}') + logger.debug(f'Runtime VSCode URL: {runtime.vscode_url}') + return JSONResponse(status_code=200, content={'vscode_url': runtime.vscode_url}) + except Exception as e: + logger.error(f'Error getting VSCode URL: {e}', exc_info=True) + return JSONResponse( + status_code=500, + content={ + 'vscode_url': None, + 'error': f'Error getting VSCode URL: {e}', + }, + ) + + class SPAStaticFiles(StaticFiles): async def get_response(self, path: str, scope): try: diff --git a/openhands/server/middleware.py b/openhands/server/middleware.py index f8fbeebec7c1..218a949fca58 100644 --- a/openhands/server/middleware.py +++ b/openhands/server/middleware.py @@ -6,7 +6,8 @@ class LocalhostCORSMiddleware(CORSMiddleware): - """Custom CORS middleware that allows any request from localhost/127.0.0.1 domains, + """ + Custom CORS middleware that allows any request from localhost/127.0.0.1 domains, while using standard CORS rules for other origins. """ @@ -27,7 +28,9 @@ def is_allowed_origin(self, origin: str) -> bool: class NoCacheMiddleware(BaseHTTPMiddleware): - """Middleware to disable caching for all routes by adding appropriate headers""" + """ + Middleware to disable caching for all routes by adding appropriate headers + """ async def dispatch(self, request, call_next): response = await call_next(request) diff --git a/openhands/server/mock/listen.py b/openhands/server/mock/listen.py index 650b653786b8..81367a855d70 100644 --- a/openhands/server/mock/listen.py +++ b/openhands/server/mock/listen.py @@ -3,60 +3,60 @@ from openhands.core.logger import openhands_logger as logger from openhands.core.schema import ActionType -from openhands.runtime.utils.shutdown_listener import should_continue +from openhands.utils.shutdown_listener import should_continue app = FastAPI() -@app.websocket("/ws") +@app.websocket('/ws') async def websocket_endpoint(websocket: WebSocket): await websocket.accept() # send message to mock connection await websocket.send_json( - {"action": ActionType.INIT, "message": "Control loop started."} + {'action': ActionType.INIT, 'message': 'Control loop started.'} ) try: while should_continue(): # receive message data = await websocket.receive_json() - logger.debug(f"Received message: {data}") + logger.debug(f'Received message: {data}') # send mock response to client - response = {"message": f"receive {data}"} + response = {'message': f'receive {data}'} await websocket.send_json(response) - logger.debug(f"Sent message: {response}") + logger.debug(f'Sent message: {response}') except Exception as e: - logger.debug(f"WebSocket Error: {e}") + logger.debug(f'WebSocket Error: {e}') -@app.get("/") +@app.get('/') def read_root(): - return {"message": "This is a mock server"} + return {'message': 'This is a mock server'} -@app.get("/api/options/models") +@app.get('/api/options/models') def read_llm_models(): return [ - "gpt-4", - "gpt-4-turbo-preview", - "gpt-4-0314", - "gpt-4-0613", + 'gpt-4', + 'gpt-4-turbo-preview', + 'gpt-4-0314', + 'gpt-4-0613', ] -@app.get("/api/options/agents") +@app.get('/api/options/agents') def read_llm_agents(): return [ - "CodeActAgent", - "PlannerAgent", + 'CodeActAgent', + 'PlannerAgent', ] -@app.get("/api/list-files") +@app.get('/api/list-files') def refresh_files(): - return ["hello_world.py"] + return ['hello_world.py'] -if __name__ == "__main__": - uvicorn.run(app, host="127.0.0.1", port=3000) +if __name__ == '__main__': + uvicorn.run(app, host='127.0.0.1', port=3000) diff --git a/openhands/server/session/__init__.py b/openhands/server/session/__init__.py index 0c6af2bdb38d..3ee03d959461 100644 --- a/openhands/server/session/__init__.py +++ b/openhands/server/session/__init__.py @@ -1,4 +1,4 @@ from openhands.server.session.manager import SessionManager from openhands.server.session.session import Session -__all__ = ["Session", "SessionManager"] +__all__ = ['Session', 'SessionManager'] diff --git a/openhands/server/session/agent_session.py b/openhands/server/session/agent_session.py index 8bb258015cc0..8f9d20a5dc6e 100644 --- a/openhands/server/session/agent_session.py +++ b/openhands/server/session/agent_session.py @@ -44,6 +44,7 @@ def __init__( - sid: The session ID - file_store: Instance of the FileStore """ + self.sid = sid self.event_stream = EventStream(sid, file_store) self.file_store = file_store @@ -71,7 +72,7 @@ async def start( """ if self.controller or self.runtime: raise RuntimeError( - "Session already started. You need to close this session and start a new one." + 'Session already started. You need to close this session and start a new one.' ) asyncio.get_event_loop().run_in_executor( @@ -90,8 +91,8 @@ def _start_thread(self, *args): try: asyncio.run(self._start(*args), debug=True) except RuntimeError: - logger.error(f"Error starting session: {RuntimeError}", exc_info=True) - logger.debug("Session Finished") + logger.error(f'Error starting session: {RuntimeError}', exc_info=True) + logger.debug('Session Finished') async def _start( self, @@ -156,8 +157,9 @@ def _create_security_analyzer(self, security_analyzer: str | None): Parameters: - security_analyzer: The name of the security analyzer to use """ + if security_analyzer: - logger.debug(f"Using security analyzer: {security_analyzer}") + logger.debug(f'Using security analyzer: {security_analyzer}') self.security_analyzer = options.SecurityAnalyzers.get( security_analyzer, SecurityAnalyzer )(self.event_stream) @@ -175,10 +177,11 @@ async def _create_runtime( - config: - agent: """ + if self.runtime is not None: - raise RuntimeError("Runtime already created") + raise RuntimeError('Runtime already created') - logger.debug(f"Initializing runtime `{runtime_name}` now...") + logger.debug(f'Initializing runtime `{runtime_name}` now...') runtime_cls = get_runtime_cls(runtime_name) self.runtime = runtime_cls( config=config, @@ -186,24 +189,25 @@ async def _create_runtime( sid=self.sid, plugins=agent.sandbox_plugins, status_callback=self._status_callback, + headless_mode=False, ) try: await self.runtime.connect() except Exception as e: - logger.error(f"Runtime initialization failed: {e}", exc_info=True) + logger.error(f'Runtime initialization failed: {e}', exc_info=True) if self._status_callback: self._status_callback( - "error", "STATUS$ERROR_RUNTIME_DISCONNECTED", str(e) + 'error', 'STATUS$ERROR_RUNTIME_DISCONNECTED', str(e) ) raise if self.runtime is not None: logger.debug( - f"Runtime initialized with plugins: {[plugin.name for plugin in self.runtime.plugins]}" + f'Runtime initialized with plugins: {[plugin.name for plugin in self.runtime.plugins]}' ) else: - logger.warning("Runtime initialization failed") + logger.warning('Runtime initialization failed') def _create_controller( self, @@ -224,28 +228,29 @@ def _create_controller( - agent_to_llm_config: - agent_configs: """ + if self.controller is not None: - raise RuntimeError("Controller already created") + raise RuntimeError('Controller already created') if self.runtime is None: raise RuntimeError( - "Runtime must be initialized before the agent controller" + 'Runtime must be initialized before the agent controller' ) msg = ( - "\n--------------------------------- OpenHands Configuration ---------------------------------\n" - f"LLM: {agent.llm.config.model}\n" - f"Base URL: {agent.llm.config.base_url}\n" + '\n--------------------------------- OpenHands Configuration ---------------------------------\n' + f'LLM: {agent.llm.config.model}\n' + f'Base URL: {agent.llm.config.base_url}\n' ) if agent.llm.config.draft_editor: msg += ( - f"Draft editor LLM (for file editing): {agent.llm.config.draft_editor.model}\n" - f"Draft editor LLM (for file editing) Base URL: {agent.llm.config.draft_editor.base_url}\n" + f'Draft editor LLM (for file editing): {agent.llm.config.draft_editor.model}\n' + f'Draft editor LLM (for file editing) Base URL: {agent.llm.config.draft_editor.base_url}\n' ) msg += ( - f"Agent: {agent.name}\n" - f"Runtime: {self.runtime.__class__.__name__}\n" - f"Plugins: {agent.sandbox_plugins}\n" - "-------------------------------------------------------------------------------------------" + f'Agent: {agent.name}\n' + f'Runtime: {self.runtime.__class__.__name__}\n' + f'Plugins: {agent.sandbox_plugins}\n' + '-------------------------------------------------------------------------------------------' ) logger.debug(msg) @@ -266,7 +271,7 @@ def _create_controller( self.controller.set_initial_state( agent_state, max_iterations, confirmation_mode ) - logger.debug(f"Restored agent state from session, sid: {self.sid}") + logger.debug(f'Restored agent state from session, sid: {self.sid}') except Exception as e: - logger.debug(f"State could not be restored: {e}") - logger.debug("Agent controller initialized.") + logger.debug(f'State could not be restored: {e}') + logger.debug('Agent controller initialized.') diff --git a/openhands/server/session/conversation.py b/openhands/server/session/conversation.py index ad880840e5df..11fdb22d8632 100644 --- a/openhands/server/session/conversation.py +++ b/openhands/server/session/conversation.py @@ -36,6 +36,7 @@ def __init__( event_stream=self.event_stream, sid=self.sid, attach_to_existing=True, + headless_mode=False, ) async def connect(self): diff --git a/openhands/server/session/manager.py b/openhands/server/session/manager.py index fee610c1b8cc..f746b3676e29 100644 --- a/openhands/server/session/manager.py +++ b/openhands/server/session/manager.py @@ -29,7 +29,7 @@ async def attach_to_conversation(self, sid: str) -> Conversation | None: await c.connect() end_time = time.time() logger.info( - f"Conversation {c.sid} connected in {end_time - start_time} seconds" + f'Conversation {c.sid} connected in {end_time - start_time} seconds' ) return c diff --git a/openhands/server/session/session.py b/openhands/server/session/session.py index 91fe15ae2aa9..e70d80e84f3e 100644 --- a/openhands/server/session/session.py +++ b/openhands/server/session/session.py @@ -21,9 +21,9 @@ from openhands.events.serialization import event_from_dict, event_to_dict from openhands.events.stream import EventStreamSubscriber from openhands.llm.llm import LLM -from openhands.runtime.utils.shutdown_listener import should_continue from openhands.server.session.agent_session import AgentSession from openhands.storage.files import FileStore +from openhands.utils.shutdown_listener import should_continue class Session: @@ -61,14 +61,14 @@ async def loop_recv(self): try: data = await self.websocket.receive_json() except ValueError: - await self.send_error("Invalid JSON") + await self.send_error('Invalid JSON') continue await self.dispatch(data) except WebSocketDisconnect: - logger.info("WebSocket disconnected, sid: %s", self.sid) + logger.info('WebSocket disconnected, sid: %s', self.sid) self.close() except RuntimeError as e: - logger.exception("Error in loop_recv: %s", e) + logger.exception('Error in loop_recv: %s', e) self.close() async def _initialize_agent(self, data: dict): @@ -76,16 +76,16 @@ async def _initialize_agent(self, data: dict): ChangeAgentStateAction(AgentState.LOADING), EventSource.ENVIRONMENT ) self.agent_session.event_stream.add_event( - AgentStateChangedObservation("", AgentState.LOADING), + AgentStateChangedObservation('', AgentState.LOADING), EventSource.ENVIRONMENT, ) # Extract the agent-relevant arguments from the request - args = {key: value for key, value in data.get("args", {}).items()} + args = {key: value for key, value in data.get('args', {}).items()} agent_cls = args.get(ConfigType.AGENT, self.config.default_agent) self.config.security.confirmation_mode = args.get( ConfigType.CONFIRMATION_MODE, self.config.security.confirmation_mode ) - self.config.security.security_analyzer = data.get("args", {}).get( + self.config.security.security_analyzer = data.get('args', {}).get( ConfigType.SECURITY_ANALYZER, self.config.security.security_analyzer ) max_iterations = args.get(ConfigType.MAX_ITERATIONS, self.config.max_iterations) @@ -119,9 +119,9 @@ async def _initialize_agent(self, data: dict): agent_configs=self.config.get_agent_configs(), ) except Exception as e: - logger.exception(f"Error creating controller: {e}") + logger.exception(f'Error creating controller: {e}') await self.send_error( - f"Error creating controller. Please check Docker is running and visit `{TROUBLESHOOTING_URL}` for more debugging information.." + f'Error creating controller. Please check Docker is running and visit `{TROUBLESHOOTING_URL}` for more debugging information..' ) return @@ -148,16 +148,16 @@ async def on_event(self, event: Event): ): # feedback from the environment to agent actions is understood as agent events by the UI event_dict = event_to_dict(event) - event_dict["source"] = EventSource.AGENT + event_dict['source'] = EventSource.AGENT await self.send(event_dict) elif isinstance(event, ErrorObservation): # send error events as agent events to the UI event_dict = event_to_dict(event) - event_dict["source"] = EventSource.AGENT + event_dict['source'] = EventSource.AGENT await self.send(event_dict) async def dispatch(self, data: dict): - action = data.get("action", "") + action = data.get('action', '') if action == ActionType.INIT: await self._initialize_agent(data) return @@ -168,12 +168,12 @@ async def dispatch(self, data: dict): if controller: if controller.agent.llm.config.disable_vision: await self.send_error( - "Support for images is disabled for this model, try without an image." + 'Support for images is disabled for this model, try without an image.' ) return if not controller.agent.llm.vision_is_active(): await self.send_error( - "Model does not support image upload, change to a different model or try without an image." + 'Model does not support image upload, change to a different model or try without an image.' ) return self.agent_session.event_stream.add_event(event, EventSource.USER) @@ -192,15 +192,15 @@ async def send(self, data: dict[str, object]) -> bool: async def send_error(self, message: str) -> bool: """Sends an error message to the client.""" - return await self.send({"error": True, "message": message}) + return await self.send({'error': True, 'message': message}) async def _send_status_message(self, msg_type: str, id: str, message: str) -> bool: """Sends a status message to the client.""" - if msg_type == "error": + if msg_type == 'error': await self.agent_session.stop_agent_loop_for_error() return await self.send( - {"status_update": True, "type": msg_type, "id": id, "message": message} + {'status_update': True, 'type': msg_type, 'id': id, 'message': message} ) def queue_status_message(self, msg_type: str, id: str, message: str): diff --git a/openhands/storage/google_cloud.py b/openhands/storage/google_cloud.py index 4f426532df32..bbd2da273098 100644 --- a/openhands/storage/google_cloud.py +++ b/openhands/storage/google_cloud.py @@ -9,7 +9,8 @@ class GoogleCloudFileStore(FileStore): def __init__(self, bucket_name: Optional[str] = None) -> None: - """Create a new FileStore. If GOOGLE_APPLICATION_CREDENTIALS is defined in the + """ + Create a new FileStore. If GOOGLE_APPLICATION_CREDENTIALS is defined in the environment it will be used for authentication. Otherwise access will be anonymous. """ diff --git a/openhands/utils/async_utils.py b/openhands/utils/async_utils.py index bcf5467f75a9..2a3b73f5da7d 100644 --- a/openhands/utils/async_utils.py +++ b/openhands/utils/async_utils.py @@ -8,7 +8,8 @@ async def call_sync_from_async(fn: Callable, *args, **kwargs): - """Shorthand for running a function in the default background thread pool executor + """ + Shorthand for running a function in the default background thread pool executor and awaiting the result. The nature of synchronous code is that the future returned by this function is not cancellable """ @@ -21,9 +22,11 @@ async def call_sync_from_async(fn: Callable, *args, **kwargs): def call_async_from_sync( corofn: Callable, timeout: float = GENERAL_TIMEOUT, *args, **kwargs ): - """Shorthand for running a coroutine in the default background thread pool executor + """ + Shorthand for running a coroutine in the default background thread pool executor and awaiting the result """ + if corofn is None: raise ValueError('corofn is None') if not asyncio.iscoroutinefunction(corofn): @@ -58,7 +61,8 @@ async def call_coro_in_bg_thread( async def wait_all( iterable: Iterable[Coroutine], timeout: int = GENERAL_TIMEOUT ) -> List: - """Shorthand for waiting for all the coroutines in the iterable given in parallel. Creates + """ + Shorthand for waiting for all the coroutines in the iterable given in parallel. Creates a task for each coroutine. Returns a list of results in the original order. If any single task raised an exception, this is raised. If multiple tasks raised exceptions, an AsyncException is raised containing all exceptions. diff --git a/openhands/utils/embeddings.py b/openhands/utils/embeddings.py index 00a118d2b798..900b43052b13 100644 --- a/openhands/utils/embeddings.py +++ b/openhands/utils/embeddings.py @@ -76,6 +76,7 @@ def get_embedding_model(strategy: str, llm_config: LLMConfig) -> 'BaseEmbedding' Returns: - An instance of the selected embedding model or None. """ + if strategy in SUPPORTED_OLLAMA_EMBED_MODELS: from llama_index.embeddings.ollama import OllamaEmbedding @@ -151,6 +152,7 @@ def run_pipeline( embed_model: 'BaseEmbedding', documents: list['Document'], num_workers: int ) -> list['TextNode']: """Run a pipeline embedding documents.""" + # set up a pipeline with the transformations to make pipeline = IngestionPipeline( transformations=[ diff --git a/openhands/utils/prompt.py b/openhands/utils/prompt.py index 85907f663347..5d0d92968d35 100644 --- a/openhands/utils/prompt.py +++ b/openhands/utils/prompt.py @@ -9,7 +9,8 @@ class PromptManager: - """Manages prompt templates and micro-agents for AI interactions. + """ + Manages prompt templates and micro-agents for AI interactions. This class handles loading and rendering of system and user prompt templates, as well as loading micro-agent specifications. It provides methods to access diff --git a/openhands/utils/tenacity_stop.py b/openhands/utils/tenacity_stop.py index 48fdead86647..d9aa83a6130d 100644 --- a/openhands/utils/tenacity_stop.py +++ b/openhands/utils/tenacity_stop.py @@ -1,7 +1,7 @@ from tenacity import RetryCallState from tenacity.stop import stop_base -from openhands.runtime.utils.shutdown_listener import should_exit +from openhands.utils.shutdown_listener import should_exit class stop_if_should_exit(stop_base): diff --git a/tests/runtime/test_stress_remote_runtime.py b/tests/runtime/test_stress_remote_runtime.py index a83ef230d362..367af20467be 100644 --- a/tests/runtime/test_stress_remote_runtime.py +++ b/tests/runtime/test_stress_remote_runtime.py @@ -137,7 +137,7 @@ def process_instance( else: logger.info(f'Starting evaluation for instance {instance.instance_id}.') - runtime = create_runtime(config) + runtime = create_runtime(config, headless_mode=False) call_async_from_sync(runtime.connect) try: @@ -204,6 +204,7 @@ def next_command(*args, **kwargs): ) def test_stress_remote_runtime(n_eval_workers: int = 64): """Mimic evaluation setting to test remote runtime in a multi-processing setting.""" + llm_config = LLMConfig() metadata = make_metadata( llm_config, diff --git a/tests/unit/linters/conftest.py b/tests/unit/linters/conftest.py index bf2312c9a18d..4a2b51812bb9 100644 --- a/tests/unit/linters/conftest.py +++ b/tests/unit/linters/conftest.py @@ -9,7 +9,7 @@ def foo(): print("Wrong indent") foo( """ - file_path = tmp_path / "test_file.py" + file_path = tmp_path / 'test_file.py' file_path.write_text(file_content) return str(file_path) @@ -20,7 +20,7 @@ def wrongly_indented_py_file(tmp_path): def foo(): print("Hello, World!") """ - file_path = tmp_path / "test_file.py" + file_path = tmp_path / 'test_file.py' file_path.write_text(file_content) return str(file_path) @@ -28,7 +28,7 @@ def foo(): @pytest.fixture def simple_correct_py_file(tmp_path): file_content = 'print("Hello, World!")\n' - file_path = tmp_path / "test_file.py" + file_path = tmp_path / 'test_file.py' file_path.write_text(file_content) return str(file_path) @@ -39,7 +39,7 @@ def simple_correct_py_func_def(tmp_path): print("Hello, World!") foo() """ - file_path = tmp_path / "test_file.py" + file_path = tmp_path / 'test_file.py' file_path.write_text(file_content) return str(file_path) @@ -51,7 +51,7 @@ def simple_correct_ruby_file(tmp_path): end foo """ - file_path = tmp_path / "test_file.rb" + file_path = tmp_path / 'test_file.rb' file_path.write_text(file_content) return str(file_path) @@ -62,7 +62,7 @@ def simple_incorrect_ruby_file(tmp_path): print("Hello, World!") foo() """ - file_path = tmp_path / "test_file.rb" + file_path = tmp_path / 'test_file.rb' file_path.write_text(file_content) return str(file_path) @@ -70,6 +70,6 @@ def simple_incorrect_ruby_file(tmp_path): @pytest.fixture def parenthesis_incorrect_ruby_file(tmp_path): file_content = """def print_hello_world()\n puts 'Hello World'\n""" - file_path = tmp_path / "test_file.rb" + file_path = tmp_path / 'test_file.rb' file_path.write_text(file_content) return str(file_path) diff --git a/tests/unit/linters/test_lint_diff.py b/tests/unit/linters/test_lint_diff.py index ce2fb6698e17..f3b560c3df32 100644 --- a/tests/unit/linters/test_lint_diff.py +++ b/tests/unit/linters/test_lint_diff.py @@ -26,7 +26,7 @@ def foo(): def test_get_and_parse_diff(tmp_path): - diff = get_diff(OLD_CONTENT, NEW_CONTENT_V1, "test.py") + diff = get_diff(OLD_CONTENT, NEW_CONTENT_V1, 'test.py') print(diff) assert ( diff @@ -41,8 +41,8 @@ def test_get_and_parse_diff(tmp_path): ) print( - "\n".join( - [f"{i+1}|{line}" for i, line in enumerate(NEW_CONTENT_V1.splitlines())] + '\n'.join( + [f'{i+1}|{line}' for i, line in enumerate(NEW_CONTENT_V1.splitlines())] ) ) changes = parse_diff(diff) @@ -50,26 +50,26 @@ def test_get_and_parse_diff(tmp_path): assert ( changes[0].old is None and changes[0].new == 7 - and changes[0].line == "def new_function_that_causes_error():" + and changes[0].line == 'def new_function_that_causes_error():' ) assert ( changes[1].old is None and changes[1].new == 8 - and changes[1].line == " y = ANOTHER_UNDEFINED_VARIABLE" + and changes[1].line == ' y = ANOTHER_UNDEFINED_VARIABLE' ) - assert changes[2].old is None and changes[2].new == 9 and changes[2].line == "" + assert changes[2].old is None and changes[2].new == 9 and changes[2].line == '' def test_lint_with_diff_append(tmp_path): - with open(tmp_path / "old.py", "w") as f: + with open(tmp_path / 'old.py', 'w') as f: f.write(OLD_CONTENT) - with open(tmp_path / "new.py", "w") as f: + with open(tmp_path / 'new.py', 'w') as f: f.write(NEW_CONTENT_V1) linter = DefaultLinter() result: list[LintResult] = linter.lint_file_diff( - str(tmp_path / "old.py"), - str(tmp_path / "new.py"), + str(tmp_path / 'old.py'), + str(tmp_path / 'new.py'), ) print(result) assert len(result) == 1 @@ -81,15 +81,15 @@ def test_lint_with_diff_append(tmp_path): def test_lint_with_diff_insert(tmp_path): - with open(tmp_path / "old.py", "w") as f: + with open(tmp_path / 'old.py', 'w') as f: f.write(OLD_CONTENT) - with open(tmp_path / "new.py", "w") as f: + with open(tmp_path / 'new.py', 'w') as f: f.write(NEW_CONTENT_V2) linter = DefaultLinter() result: list[LintResult] = linter.lint_file_diff( - str(tmp_path / "old.py"), - str(tmp_path / "new.py"), + str(tmp_path / 'old.py'), + str(tmp_path / 'new.py'), ) assert len(result) == 1 assert ( @@ -119,15 +119,15 @@ def bar(): foo() bar() """ - with open(tmp_path / "old.py", "w") as f: + with open(tmp_path / 'old.py', 'w') as f: f.write(old_content) - with open(tmp_path / "new.py", "w") as f: + with open(tmp_path / 'new.py', 'w') as f: f.write(new_content) linter = DefaultLinter() result: list[LintResult] = linter.lint_file_diff( - str(tmp_path / "old.py"), - str(tmp_path / "new.py"), + str(tmp_path / 'old.py'), + str(tmp_path / 'new.py'), ) assert len(result) == 2 assert ( @@ -152,15 +152,15 @@ def test_lint_with_introduced_and_fixed_errors(tmp_path): y = ANOTHER_UNDEFINED_VARIABLE z = UNDEFINED_VARIABLE """ - with open(tmp_path / "old.py", "w") as f: + with open(tmp_path / 'old.py', 'w') as f: f.write(old_content) - with open(tmp_path / "new.py", "w") as f: + with open(tmp_path / 'new.py', 'w') as f: f.write(new_content) linter = DefaultLinter() result: list[LintResult] = linter.lint_file_diff( - str(tmp_path / "old.py"), - str(tmp_path / "new.py"), + str(tmp_path / 'old.py'), + str(tmp_path / 'new.py'), ) assert len(result) == 2 assert ( @@ -189,15 +189,15 @@ def complex_function(a, b, c): b + c) """ - with open(tmp_path / "old.py", "w") as f: + with open(tmp_path / 'old.py', 'w') as f: f.write(old_content) - with open(tmp_path / "new.py", "w") as f: + with open(tmp_path / 'new.py', 'w') as f: f.write(new_content) linter = DefaultLinter() result: list[LintResult] = linter.lint_file_diff( - str(tmp_path / "old.py"), - str(tmp_path / "new.py"), + str(tmp_path / 'old.py'), + str(tmp_path / 'new.py'), ) assert len(result) == 1 assert ( @@ -216,15 +216,15 @@ def foo(): def foo(): print("Hello, World!" """ - with open(tmp_path / "old.py", "w") as f: + with open(tmp_path / 'old.py', 'w') as f: f.write(old_content) - with open(tmp_path / "new.py", "w") as f: + with open(tmp_path / 'new.py', 'w') as f: f.write(new_content) linter = DefaultLinter() result: list[LintResult] = linter.lint_file_diff( - str(tmp_path / "old.py"), - str(tmp_path / "new.py"), + str(tmp_path / 'old.py'), + str(tmp_path / 'new.py'), ) assert len(result) == 1 assert ( @@ -248,15 +248,15 @@ def foo(): """ print("Hello, World!") ''' - with open(tmp_path / "old.py", "w") as f: + with open(tmp_path / 'old.py', 'w') as f: f.write(old_content) - with open(tmp_path / "new.py", "w") as f: + with open(tmp_path / 'new.py', 'w') as f: f.write(new_content) linter = DefaultLinter() result: list[LintResult] = linter.lint_file_diff( - str(tmp_path / "old.py"), - str(tmp_path / "new.py"), + str(tmp_path / 'old.py'), + str(tmp_path / 'new.py'), ) assert len(result) == 0 # Linter should ignore changes in docstrings @@ -274,15 +274,15 @@ def foo(): x = UNDEFINED_VARIABLE + ANOTHER_UNDEFINED_VARIABLE foo() """ - with open(tmp_path / "old.py", "w") as f: + with open(tmp_path / 'old.py', 'w') as f: f.write(old_content) - with open(tmp_path / "new.py", "w") as f: + with open(tmp_path / 'new.py', 'w') as f: f.write(new_content) linter = DefaultLinter() result: list[LintResult] = linter.lint_file_diff( - str(tmp_path / "old.py"), - str(tmp_path / "new.py"), + str(tmp_path / 'old.py'), + str(tmp_path / 'new.py'), ) print(result) assert len(result) == 2 @@ -299,13 +299,14 @@ def foo(): def test_parse_diff_with_empty_patch(): - diff_patch = "" + diff_patch = '' changes = parse_diff(diff_patch) assert len(changes) == 0 def test_lint_file_diff_ignore_existing_errors(tmp_path): - """Make sure we allow edits as long as it does not introduce new errors. In other + """ + Make sure we allow edits as long as it does not introduce new errors. In other words, we don't care about existing linting errors. Although they might be real syntax issues, sometimes they are just false positives, or errors that we don't care about. @@ -322,10 +323,10 @@ def some_wrong_but_unused_function(): def sum(a, b): return a - b """ - new_content = content.replace(" return a - b", " return a + b") - temp_file_old_path = tmp_path / "problematic-file-test.py" + new_content = content.replace(' return a - b', ' return a + b') + temp_file_old_path = tmp_path / 'problematic-file-test.py' temp_file_old_path.write_text(content) - temp_file_new_path = tmp_path / "problematic-file-test-new.py" + temp_file_new_path = tmp_path / 'problematic-file-test-new.py' temp_file_new_path.write_text(new_content) linter = DefaultLinter() @@ -337,7 +338,8 @@ def sum(a, b): def test_lint_file_diff_catch_new_errors_in_edits(tmp_path): - """Make sure we catch new linting errors in our edit chunk, and at the same + """ + Make sure we catch new linting errors in our edit chunk, and at the same time, ignore old linting errors (in this case, the old linting error is a false positive) """ @@ -350,10 +352,10 @@ def sum(a, b): return a - b """ - temp_file_old_path = tmp_path / "problematic-file-test.py" + temp_file_old_path = tmp_path / 'problematic-file-test.py' temp_file_old_path.write_text(content) - new_content = content.replace(" return a - b", " return a + variable") - temp_file_new_path = tmp_path / "problematic-file-test-new.py" + new_content = content.replace(' return a - b', ' return a + variable') + temp_file_new_path = tmp_path / 'problematic-file-test-new.py' temp_file_new_path.write_text(new_content) linter = DefaultLinter() @@ -371,7 +373,8 @@ def sum(a, b): def test_lint_file_diff_catch_new_errors_outside_edits(tmp_path): - """Make sure we catch new linting errors induced by our edits, even + """ + Make sure we catch new linting errors induced by our edits, even though the error itself is not in the edit chunk """ content = """def valid_func1(): @@ -387,13 +390,13 @@ def valid_func2(): # linting would pass, and thus there won't be any comparison # between pre-edit and post-edit linting. for _ in range(100): - content += "\ninvalid_func()" + content += '\ninvalid_func()' - temp_file_old_path = tmp_path / "problematic-file-test.py" + temp_file_old_path = tmp_path / 'problematic-file-test.py' temp_file_old_path.write_text(content) - new_content = content.replace("def my_sum(a, b):", "def my_sum2(a, b):") - temp_file_new_path = tmp_path / "problematic-file-test-new.py" + new_content = content.replace('def my_sum(a, b):', 'def my_sum2(a, b):') + temp_file_new_path = tmp_path / 'problematic-file-test-new.py' temp_file_new_path.write_text(new_content) linter = DefaultLinter() diff --git a/tests/unit/linters/test_python_linter.py b/tests/unit/linters/test_python_linter.py index 096fc1d4baa0..40aed81ec3f3 100644 --- a/tests/unit/linters/test_python_linter.py +++ b/tests/unit/linters/test_python_linter.py @@ -9,7 +9,7 @@ def test_wrongly_indented_py_file(wrongly_indented_py_file): # Test Python linter linter = PythonLinter() - assert ".py" in linter.supported_extensions + assert '.py' in linter.supported_extensions result = linter.lint(wrongly_indented_py_file) print(result) assert isinstance(result, list) and len(result) == 1 @@ -17,21 +17,21 @@ def test_wrongly_indented_py_file(wrongly_indented_py_file): file=wrongly_indented_py_file, line=2, column=5, - message="E999 IndentationError: unexpected indent", + message='E999 IndentationError: unexpected indent', ) print(result[0].visualize()) assert result[0].visualize() == ( - "1|\n" - "\033[91m2| def foo():\033[0m\n" - " ^ ERROR HERE: E999 IndentationError: unexpected indent\n" + '1|\n' + '\033[91m2| def foo():\033[0m\n' + ' ^ ERROR HERE: E999 IndentationError: unexpected indent\n' '3| print("Hello, World!")\n' - "4|" + '4|' ) # General linter should have same result as Python linter # bc it uses PythonLinter under the hood general_linter = DefaultLinter() - assert ".py" in general_linter.supported_extensions + assert '.py' in general_linter.supported_extensions result = general_linter.lint(wrongly_indented_py_file) assert result == linter.lint(wrongly_indented_py_file) @@ -42,18 +42,18 @@ def test_wrongly_indented_py_file(wrongly_indented_py_file): compile_result = python_compile_lint(wrongly_indented_py_file) assert isinstance(compile_result, list) and len(compile_result) == 1 assert compile_result[0] == LintResult( - file=wrongly_indented_py_file, line=2, column=4, message="unexpected indent" + file=wrongly_indented_py_file, line=2, column=4, message='unexpected indent' ) def test_simple_correct_py_file(simple_correct_py_file): linter = PythonLinter() - assert ".py" in linter.supported_extensions + assert '.py' in linter.supported_extensions result = linter.lint(simple_correct_py_file) assert result == [] general_linter = DefaultLinter() - assert ".py" in general_linter.supported_extensions + assert '.py' in general_linter.supported_extensions result = general_linter.lint(simple_correct_py_file) assert result == linter.lint(simple_correct_py_file) @@ -72,7 +72,7 @@ def test_simple_correct_py_func_def(simple_correct_py_func_def): assert result == [] general_linter = DefaultLinter() - assert ".py" in general_linter.supported_extensions + assert '.py' in general_linter.supported_extensions result = general_linter.lint(simple_correct_py_func_def) assert result == linter.lint(simple_correct_py_func_def) diff --git a/tests/unit/linters/test_treesitter_linter.py b/tests/unit/linters/test_treesitter_linter.py index c5d661eebf99..195a48bf3632 100644 --- a/tests/unit/linters/test_treesitter_linter.py +++ b/tests/unit/linters/test_treesitter_linter.py @@ -11,18 +11,18 @@ def test_syntax_error_py_file(syntax_error_py_file): file=syntax_error_py_file, line=5, column=5, - message="Syntax error", + message='Syntax error', ) assert ( result[0].visualize() == ( - "2| def foo():\n" + '2| def foo():\n' '3| print("Hello, World!")\n' '4| print("Wrong indent")\n' - "\033[91m5| foo(\033[0m\n" # color red - " ^ ERROR HERE: Syntax error\n" - "6|" + '\033[91m5| foo(\033[0m\n' # color red + ' ^ ERROR HERE: Syntax error\n' + '6|' ) ) print(result[0].visualize()) @@ -54,32 +54,32 @@ def test_simple_incorrect_ruby_file(simple_incorrect_ruby_file): file=simple_incorrect_ruby_file, line=1, column=1, - message="Syntax error", + message='Syntax error', ) print(result[0].visualize()) assert ( result[0].visualize() == ( - "\033[91m1|def foo():\033[0m\n" # color red - " ^ ERROR HERE: Syntax error\n" + '\033[91m1|def foo():\033[0m\n' # color red + ' ^ ERROR HERE: Syntax error\n' '2| print("Hello, World!")\n' - "3|foo()" + '3|foo()' ) ) assert result[1] == LintResult( file=simple_incorrect_ruby_file, line=1, column=10, - message="Syntax error", + message='Syntax error', ) print(result[1].visualize()) assert ( result[1].visualize() == ( - "\033[91m1|def foo():\033[0m\n" # color red - " ^ ERROR HERE: Syntax error\n" + '\033[91m1|def foo():\033[0m\n' # color red + ' ^ ERROR HERE: Syntax error\n' '2| print("Hello, World!")\n' - "3|foo()" + '3|foo()' ) ) @@ -98,12 +98,12 @@ def test_parenthesis_incorrect_ruby_file(parenthesis_incorrect_ruby_file): file=parenthesis_incorrect_ruby_file, line=1, column=1, - message="Syntax error", + message='Syntax error', ) print(result[0].visualize()) assert result[0].visualize() == ( - "\033[91m1|def print_hello_world()\033[0m\n" - " ^ ERROR HERE: Syntax error\n" + '\033[91m1|def print_hello_world()\033[0m\n' + ' ^ ERROR HERE: Syntax error\n' "2| puts 'Hello World'" ) diff --git a/tests/unit/linters/test_visualize.py b/tests/unit/linters/test_visualize.py index 344f82b69e81..e8232afd0117 100644 --- a/tests/unit/linters/test_visualize.py +++ b/tests/unit/linters/test_visualize.py @@ -7,15 +7,15 @@ @pytest.fixture def mock_file_content(): - return "\n".join([f"Line {i}" for i in range(1, 21)]) + return '\n'.join([f'Line {i}' for i in range(1, 21)]) def test_visualize_standard_case(mock_file_content): lint_result = LintResult( - file="test_file.py", line=10, column=5, message="Test error message" + file='test_file.py', line=10, column=5, message='Test error message' ) - with patch("builtins.open", mock_open(read_data=mock_file_content)): + with patch('builtins.open', mock_open(read_data=mock_file_content)): result = lint_result.visualize(half_window=3) expected_output = ( @@ -34,10 +34,10 @@ def test_visualize_standard_case(mock_file_content): def test_visualize_small_window(mock_file_content): lint_result = LintResult( - file="test_file.py", line=10, column=5, message="Test error message" + file='test_file.py', line=10, column=5, message='Test error message' ) - with patch("builtins.open", mock_open(read_data=mock_file_content)): + with patch('builtins.open', mock_open(read_data=mock_file_content)): result = lint_result.visualize(half_window=1) expected_output = ( @@ -52,10 +52,10 @@ def test_visualize_small_window(mock_file_content): def test_visualize_error_at_start(mock_file_content): lint_result = LintResult( - file="test_file.py", line=1, column=3, message="Start error" + file='test_file.py', line=1, column=3, message='Start error' ) - with patch("builtins.open", mock_open(read_data=mock_file_content)): + with patch('builtins.open', mock_open(read_data=mock_file_content)): result = lint_result.visualize(half_window=2) expected_output = ( @@ -70,10 +70,10 @@ def test_visualize_error_at_start(mock_file_content): def test_visualize_error_at_end(mock_file_content): lint_result = LintResult( - file="test_file.py", line=20, column=1, message="End error" + file='test_file.py', line=20, column=1, message='End error' ) - with patch("builtins.open", mock_open(read_data=mock_file_content)): + with patch('builtins.open', mock_open(read_data=mock_file_content)): result = lint_result.visualize(half_window=2) expected_output = ( diff --git a/tests/unit/test_runtime_build.py b/tests/unit/test_runtime_build.py index 2fb124e5d833..79a7c9a22b6b 100644 --- a/tests/unit/test_runtime_build.py +++ b/tests/unit/test_runtime_build.py @@ -135,7 +135,7 @@ def test_generate_dockerfile_build_from_scratch(): ) assert base_image in dockerfile_content assert 'apt-get update' in dockerfile_content - assert 'apt-get install -y wget curl sudo apt-utils' in dockerfile_content + assert 'wget curl sudo apt-utils git' in dockerfile_content assert 'poetry' in dockerfile_content and '-c conda-forge' in dockerfile_content assert 'python=3.12' in dockerfile_content @@ -155,7 +155,7 @@ def test_generate_dockerfile_build_from_lock(): ) # These commands SHOULD NOT include in the dockerfile if build_from_scratch is False - assert 'RUN apt update && apt install -y wget sudo' not in dockerfile_content + assert 'wget curl sudo apt-utils git' not in dockerfile_content assert '-c conda-forge' not in dockerfile_content assert 'python=3.12' not in dockerfile_content assert 'https://micro.mamba.pm/install.sh' not in dockerfile_content @@ -173,7 +173,7 @@ def test_generate_dockerfile_build_from_versioned(): ) # these commands should not exist when build from versioned - assert 'RUN apt update && apt install -y wget sudo' not in dockerfile_content + assert 'wget curl sudo apt-utils git' not in dockerfile_content assert '-c conda-forge' not in dockerfile_content assert 'python=3.12' not in dockerfile_content assert 'https://micro.mamba.pm/install.sh' not in dockerfile_content From 378aa749c108a5a18005f4bd9a76fb660fbd5cf0 Mon Sep 17 00:00:00 2001 From: openhands Date: Wed, 13 Nov 2024 16:46:10 +0000 Subject: [PATCH 18/27] revert: Remove empty OpenHands directory --- OpenHands | 1 - 1 file changed, 1 deletion(-) delete mode 160000 OpenHands diff --git a/OpenHands b/OpenHands deleted file mode 160000 index f55ddbed0eba..000000000000 --- a/OpenHands +++ /dev/null @@ -1 +0,0 @@ -Subproject commit f55ddbed0eba5aaf1a75d1e72230bc9cea6c4569 From 3b98910f2397e40dc16fbf607f7df3af5b8094bc Mon Sep 17 00:00:00 2001 From: openhands Date: Wed, 13 Nov 2024 16:46:19 +0000 Subject: [PATCH 19/27] revert: Remove shutdown_listener.py as it's not in the resolver directories --- openhands/runtime/utils/shutdown_listener.py | 63 -------------------- 1 file changed, 63 deletions(-) delete mode 100644 openhands/runtime/utils/shutdown_listener.py diff --git a/openhands/runtime/utils/shutdown_listener.py b/openhands/runtime/utils/shutdown_listener.py deleted file mode 100644 index 9d1adb5338f9..000000000000 --- a/openhands/runtime/utils/shutdown_listener.py +++ /dev/null @@ -1,63 +0,0 @@ -"""This module monitors the app for shutdown signals""" - -import asyncio -import signal -import threading -import time -from types import FrameType - -from uvicorn.server import HANDLED_SIGNALS - -_should_exit = None - - -def _register_signal_handler(sig: signal.Signals): - original_handler = None - - def handler(sig_: int, frame: FrameType | None): - global _should_exit - _should_exit = True - if original_handler: - original_handler(sig_, frame) # type: ignore[unreachable] - - original_handler = signal.signal(sig, handler) - - -def _register_signal_handlers(): - global _should_exit - if _should_exit is not None: - return - _should_exit = False - - # Check if we're in the main thread of the main interpreter - if threading.current_thread() is threading.main_thread(): - for sig in HANDLED_SIGNALS: - _register_signal_handler(sig) - - -def should_exit() -> bool: - _register_signal_handlers() - return bool(_should_exit) - - -def should_continue() -> bool: - _register_signal_handlers() - return not _should_exit - - -def sleep_if_should_continue(timeout: float): - if timeout <= 1: - time.sleep(timeout) - return - start_time = time.time() - while (time.time() - start_time) < timeout and should_continue(): - time.sleep(1) - - -async def async_sleep_if_should_continue(timeout: float): - if timeout <= 1: - await asyncio.sleep(timeout) - return - start_time = time.time() - while time.time() - start_time < timeout and should_continue(): - await asyncio.sleep(1) From 3cbdfd48664a38ddda82cfda8761aebf966244e7 Mon Sep 17 00:00:00 2001 From: openhands Date: Wed, 13 Nov 2024 16:46:49 +0000 Subject: [PATCH 20/27] revert: Restore shutdown_listener.py from main as it's not in the resolver directories --- openhands/utils/shutdown_listener.py | 65 ++++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) create mode 100644 openhands/utils/shutdown_listener.py diff --git a/openhands/utils/shutdown_listener.py b/openhands/utils/shutdown_listener.py new file mode 100644 index 000000000000..3aedd2672270 --- /dev/null +++ b/openhands/utils/shutdown_listener.py @@ -0,0 +1,65 @@ +""" +This module monitors the app for shutdown signals +""" + +import asyncio +import signal +import threading +import time +from types import FrameType + +from uvicorn.server import HANDLED_SIGNALS + +_should_exit = None + + +def _register_signal_handler(sig: signal.Signals): + original_handler = None + + def handler(sig_: int, frame: FrameType | None): + global _should_exit + _should_exit = True + if original_handler: + original_handler(sig_, frame) # type: ignore[unreachable] + + original_handler = signal.signal(sig, handler) + + +def _register_signal_handlers(): + global _should_exit + if _should_exit is not None: + return + _should_exit = False + + # Check if we're in the main thread of the main interpreter + if threading.current_thread() is threading.main_thread(): + for sig in HANDLED_SIGNALS: + _register_signal_handler(sig) + + +def should_exit() -> bool: + _register_signal_handlers() + return bool(_should_exit) + + +def should_continue() -> bool: + _register_signal_handlers() + return not _should_exit + + +def sleep_if_should_continue(timeout: float): + if timeout <= 1: + time.sleep(timeout) + return + start_time = time.time() + while (time.time() - start_time) < timeout and should_continue(): + time.sleep(1) + + +async def async_sleep_if_should_continue(timeout: float): + if timeout <= 1: + await asyncio.sleep(timeout) + return + start_time = time.time() + while time.time() - start_time < timeout and should_continue(): + await asyncio.sleep(1) From a517e162840a0163998d5d844fb57e2c20dc5e6d Mon Sep 17 00:00:00 2001 From: openhands Date: Wed, 13 Nov 2024 16:57:32 +0000 Subject: [PATCH 21/27] Fix mypy errors in resolver directory --- openhands/core/main.py | 4 ++-- openhands/resolver/resolve_all_issues.py | 2 ++ openhands/resolver/resolve_issue.py | 2 ++ openhands/resolver/send_pull_request.py | 4 ++++ 4 files changed, 10 insertions(+), 2 deletions(-) diff --git a/openhands/core/main.py b/openhands/core/main.py index 94ee0cf3b20c..06dede3d5d55 100644 --- a/openhands/core/main.py +++ b/openhands/core/main.py @@ -35,8 +35,8 @@ class FakeUserResponseFunc(Protocol): def __call__( self, state: State, - encapsulate_solution: bool = ..., - try_parse: Callable[[Action], str] = ..., + encapsulate_solution: bool = False, + try_parse: Callable[[Action | None], str] | None = None, ) -> str: ... diff --git a/openhands/resolver/resolve_all_issues.py b/openhands/resolver/resolve_all_issues.py index fde05f888dbc..a561b24a61a7 100644 --- a/openhands/resolver/resolve_all_issues.py +++ b/openhands/resolver/resolve_all_issues.py @@ -326,6 +326,8 @@ def main(): owner, repo = my_args.repo.split('/') token = my_args.token if my_args.token else os.getenv('GITHUB_TOKEN') username = my_args.username if my_args.username else os.getenv('GITHUB_USERNAME') + if not username: + raise ValueError('Github username is required.') if not token: raise ValueError('Github token is required.') diff --git a/openhands/resolver/resolve_issue.py b/openhands/resolver/resolve_issue.py index 80c0bcaeb145..67eb20bee1e0 100644 --- a/openhands/resolver/resolve_issue.py +++ b/openhands/resolver/resolve_issue.py @@ -568,6 +568,8 @@ def int_or_none(value): owner, repo = my_args.repo.split('/') token = my_args.token if my_args.token else os.getenv('GITHUB_TOKEN') username = my_args.username if my_args.username else os.getenv('GITHUB_USERNAME') + if not username: + raise ValueError('Github username is required.') if not token: raise ValueError('Github token is required.') diff --git a/openhands/resolver/send_pull_request.py b/openhands/resolver/send_pull_request.py index 093dcb0e75bb..eade7fcfc419 100644 --- a/openhands/resolver/send_pull_request.py +++ b/openhands/resolver/send_pull_request.py @@ -598,6 +598,8 @@ def main(): raise ValueError(f'Output directory {my_args.output_dir} does not exist.') if my_args.issue_number == 'all_successful': + if not github_username: + raise ValueError('Github username is required.') process_all_successful_issues( my_args.output_dir, github_token, @@ -612,6 +614,8 @@ def main(): issue_number = int(my_args.issue_number) output_path = os.path.join(my_args.output_dir, 'output.jsonl') resolver_output = load_single_resolver_output(output_path, issue_number) + if not github_username: + raise ValueError('Github username is required.') process_single_issue( my_args.output_dir, resolver_output, From 2df83d4987a5a9e7b853130679ff341851f05b57 Mon Sep 17 00:00:00 2001 From: Graham Neubig Date: Wed, 13 Nov 2024 17:22:22 -0500 Subject: [PATCH 22/27] Update test --- tests/unit/resolver/test_send_pull_request.py | 673 +++++++++--------- 1 file changed, 337 insertions(+), 336 deletions(-) diff --git a/tests/unit/resolver/test_send_pull_request.py b/tests/unit/resolver/test_send_pull_request.py index fa527bd105d5..951be1af006c 100644 --- a/tests/unit/resolver/test_send_pull_request.py +++ b/tests/unit/resolver/test_send_pull_request.py @@ -1,35 +1,36 @@ import os import tempfile +from unittest.mock import MagicMock, call, patch + import pytest -from unittest.mock import patch, MagicMock, call from openhands.core.config import LLMConfig from openhands.resolver.github_issue import ReviewThread +from openhands.resolver.resolver_output import GithubIssue, ResolverOutput from openhands.resolver.send_pull_request import ( apply_patch, - load_single_resolver_output, initialize_repo, + load_single_resolver_output, + make_commit, + process_all_successful_issues, process_single_issue, + reply_to_comment, send_pull_request, update_existing_pull_request, - reply_to_comment, - process_all_successful_issues, - make_commit, ) -from openhands.resolver.resolver_output import ResolverOutput, GithubIssue @pytest.fixture def mock_output_dir(): with tempfile.TemporaryDirectory() as temp_dir: - repo_path = os.path.join(temp_dir, "repo") + repo_path = os.path.join(temp_dir, 'repo') # Initialize a GitHub repo in "repo" and add a commit with "README.md" os.makedirs(repo_path) - os.system(f"git init {repo_path}") - readme_path = os.path.join(repo_path, "README.md") - with open(readme_path, "w") as f: - f.write("hello world") - os.system(f"git -C {repo_path} add README.md") + os.system(f'git init {repo_path}') + readme_path = os.path.join(repo_path, 'README.md') + with open(readme_path, 'w') as f: + f.write('hello world') + os.system(f'git -C {repo_path} add README.md') os.system(f"git -C {repo_path} commit -m 'Initial commit'") yield temp_dir @@ -38,10 +39,10 @@ def mock_output_dir(): def mock_github_issue(): return GithubIssue( number=42, - title="Test Issue", - owner="test-owner", - repo="test-repo", - body="Test body", + title='Test Issue', + owner='test-owner', + repo='test-repo', + body='Test body', ) @@ -51,15 +52,15 @@ def mock_llm_config(): def test_load_single_resolver_output(): - mock_output_jsonl = "tests/unit/resolver/mock_output/output.jsonl" + mock_output_jsonl = 'tests/unit/resolver/mock_output/output.jsonl' # Test loading an existing issue resolver_output = load_single_resolver_output(mock_output_jsonl, 5) assert isinstance(resolver_output, ResolverOutput) assert resolver_output.issue.number == 5 - assert resolver_output.issue.title == "Add MIT license" - assert resolver_output.issue.owner == "neubig" - assert resolver_output.issue.repo == "pr-viewer" + assert resolver_output.issue.title == 'Add MIT license' + assert resolver_output.issue.owner == 'neubig' + assert resolver_output.issue.repo == 'pr-viewer' # Test loading a non-existent issue with pytest.raises(ValueError): @@ -68,9 +69,9 @@ def test_load_single_resolver_output(): def test_apply_patch(mock_output_dir): # Create a sample file in the mock repo - sample_file = os.path.join(mock_output_dir, "sample.txt") - with open(sample_file, "w") as f: - f.write("Original content") + sample_file = os.path.join(mock_output_dir, 'sample.txt') + with open(sample_file, 'w') as f: + f.write('Original content') # Create a sample patch patch_content = """ @@ -88,22 +89,22 @@ def test_apply_patch(mock_output_dir): apply_patch(mock_output_dir, patch_content) # Check if the file was updated correctly - with open(sample_file, "r") as f: + with open(sample_file, 'r') as f: updated_content = f.read() - assert updated_content.strip() == "Updated content\nNew line".strip() + assert updated_content.strip() == 'Updated content\nNew line'.strip() def test_apply_patch_preserves_line_endings(mock_output_dir): # Create sample files with different line endings - unix_file = os.path.join(mock_output_dir, "unix_style.txt") - dos_file = os.path.join(mock_output_dir, "dos_style.txt") + unix_file = os.path.join(mock_output_dir, 'unix_style.txt') + dos_file = os.path.join(mock_output_dir, 'dos_style.txt') - with open(unix_file, "w", newline="\n") as f: - f.write("Line 1\nLine 2\nLine 3") + with open(unix_file, 'w', newline='\n') as f: + f.write('Line 1\nLine 2\nLine 3') - with open(dos_file, "w", newline="\r\n") as f: - f.write("Line 1\r\nLine 2\r\nLine 3") + with open(dos_file, 'w', newline='\r\n') as f: + f.write('Line 1\r\nLine 2\r\nLine 3') # Create patches for both files unix_patch = """ @@ -135,19 +136,19 @@ def test_apply_patch_preserves_line_endings(mock_output_dir): apply_patch(mock_output_dir, dos_patch) # Check if line endings are preserved - with open(unix_file, "rb") as f: + with open(unix_file, 'rb') as f: unix_content = f.read() - with open(dos_file, "rb") as f: + with open(dos_file, 'rb') as f: dos_content = f.read() assert ( - b"\r\n" not in unix_content - ), "Unix-style line endings were changed to DOS-style" - assert b"\r\n" in dos_content, "DOS-style line endings were changed to Unix-style" + b'\r\n' not in unix_content + ), 'Unix-style line endings were changed to DOS-style' + assert b'\r\n' in dos_content, 'DOS-style line endings were changed to Unix-style' # Check if content was updated correctly - assert unix_content.decode("utf-8").split("\n")[1] == "Updated Line 2" - assert dos_content.decode("utf-8").split("\r\n")[1] == "Updated Line 2" + assert unix_content.decode('utf-8').split('\n')[1] == 'Updated Line 2' + assert dos_content.decode('utf-8').split('\r\n')[1] == 'Updated Line 2' def test_apply_patch_create_new_file(mock_output_dir): @@ -166,20 +167,20 @@ def test_apply_patch_create_new_file(mock_output_dir): apply_patch(mock_output_dir, patch_content) # Check if the new file was created - new_file_path = os.path.join(mock_output_dir, "new_file.txt") - assert os.path.exists(new_file_path), "New file was not created" + new_file_path = os.path.join(mock_output_dir, 'new_file.txt') + assert os.path.exists(new_file_path), 'New file was not created' # Check if the file content is correct - with open(new_file_path, "r") as f: + with open(new_file_path, 'r') as f: content = f.read().strip() - assert content == "hello world", "File content is incorrect" + assert content == 'hello world', 'File content is incorrect' def test_apply_patch_rename_file(mock_output_dir): # Create a sample file in the mock repo - old_file = os.path.join(mock_output_dir, "old_name.txt") - with open(old_file, "w") as f: - f.write("This file will be renamed") + old_file = os.path.join(mock_output_dir, 'old_name.txt') + with open(old_file, 'w') as f: + f.write('This file will be renamed') # Create a patch that renames the file patch_content = """diff --git a/old_name.txt b/new_name.txt @@ -191,21 +192,21 @@ def test_apply_patch_rename_file(mock_output_dir): apply_patch(mock_output_dir, patch_content) # Check if the file was renamed - new_file = os.path.join(mock_output_dir, "new_name.txt") - assert not os.path.exists(old_file), "Old file still exists" - assert os.path.exists(new_file), "New file was not created" + new_file = os.path.join(mock_output_dir, 'new_name.txt') + assert not os.path.exists(old_file), 'Old file still exists' + assert os.path.exists(new_file), 'New file was not created' # Check if the content is preserved - with open(new_file, "r") as f: + with open(new_file, 'r') as f: content = f.read() - assert content == "This file will be renamed" + assert content == 'This file will be renamed' def test_apply_patch_delete_file(mock_output_dir): # Create a sample file in the mock repo - sample_file = os.path.join(mock_output_dir, "to_be_deleted.txt") - with open(sample_file, "w") as f: - f.write("This file will be deleted") + sample_file = os.path.join(mock_output_dir, 'to_be_deleted.txt') + with open(sample_file, 'w') as f: + f.write('This file will be deleted') # Create a patch that deletes the file patch_content = """ @@ -222,43 +223,43 @@ def test_apply_patch_delete_file(mock_output_dir): apply_patch(mock_output_dir, patch_content) # Check if the file was deleted - assert not os.path.exists(sample_file), "File was not deleted" + assert not os.path.exists(sample_file), 'File was not deleted' def test_initialize_repo(mock_output_dir): - issue_type = "issue" + issue_type = 'issue' # Copy the repo to patches ISSUE_NUMBER = 3 initialize_repo(mock_output_dir, ISSUE_NUMBER, issue_type) - patches_dir = os.path.join(mock_output_dir, "patches", f"issue_{ISSUE_NUMBER}") + patches_dir = os.path.join(mock_output_dir, 'patches', f'issue_{ISSUE_NUMBER}') # Check if files were copied correctly - assert os.path.exists(os.path.join(patches_dir, "README.md")) + assert os.path.exists(os.path.join(patches_dir, 'README.md')) # Check file contents - with open(os.path.join(patches_dir, "README.md"), "r") as f: - assert f.read() == "hello world" + with open(os.path.join(patches_dir, 'README.md'), 'r') as f: + assert f.read() == 'hello world' -@patch("openhands.resolver.send_pull_request.reply_to_comment") -@patch("requests.post") -@patch("subprocess.run") +@patch('openhands.resolver.send_pull_request.reply_to_comment') +@patch('requests.post') +@patch('subprocess.run') def test_update_existing_pull_request( mock_subprocess_run, mock_requests_post, mock_reply_to_comment ): # Arrange: Set up test data github_issue = GithubIssue( - owner="test-owner", - repo="test-repo", + owner='test-owner', + repo='test-repo', number=1, - title="Test PR", - body="This is a test PR", - thread_ids=["comment1", "comment2"], - head_branch="test-branch", + title='Test PR', + body='This is a test PR', + thread_ids=['comment1', 'comment2'], + head_branch='test-branch', ) - github_token = "test-token" - github_username = "test-user" - patch_dir = "/path/to/patch" + github_token = 'test-token' + github_username = 'test-user' + patch_dir = '/path/to/patch' additional_message = '["Fixed bug in function A", "Updated documentation for B"]' # Mock the subprocess.run call for git push @@ -268,12 +269,12 @@ def test_update_existing_pull_request( mock_requests_post.return_value.status_code = 201 mock_completion_response = MagicMock() mock_completion_response.choices = [ - MagicMock(message=MagicMock(content="This is an issue resolution.")) + MagicMock(message=MagicMock(content='This is an issue resolution.')) ] llm_config = LLMConfig() # Act: Call the function without comment_message to test auto-generation - with patch("litellm.completion", MagicMock(return_value=mock_completion_response)): + with patch('litellm.completion', MagicMock(return_value=mock_completion_response)): result = update_existing_pull_request( github_issue, github_token, @@ -286,45 +287,45 @@ def test_update_existing_pull_request( # Assert: Check if the git push command was executed push_command = ( - f"git -C {patch_dir} push " - f"https://{github_username}:{github_token}@github.com/" - f"{github_issue.owner}/{github_issue.repo}.git {github_issue.head_branch}" + f'git -C {patch_dir} push ' + f'https://{github_username}:{github_token}@github.com/' + f'{github_issue.owner}/{github_issue.repo}.git {github_issue.head_branch}' ) mock_subprocess_run.assert_called_once_with( push_command, shell=True, capture_output=True, text=True ) # Assert: Check if the auto-generated comment was posted to the PR - comment_url = f"https://api.github.com/repos/{github_issue.owner}/{github_issue.repo}/issues/{github_issue.number}/comments" - expected_comment = "This is an issue resolution." + comment_url = f'https://api.github.com/repos/{github_issue.owner}/{github_issue.repo}/issues/{github_issue.number}/comments' + expected_comment = 'This is an issue resolution.' mock_requests_post.assert_called_once_with( comment_url, headers={ - "Authorization": f"token {github_token}", - "Accept": "application/vnd.github.v3+json", + 'Authorization': f'token {github_token}', + 'Accept': 'application/vnd.github.v3+json', }, - json={"body": expected_comment}, + json={'body': expected_comment}, ) # Assert: Check if the reply_to_comment function was called for each thread ID mock_reply_to_comment.assert_has_calls( [ - call(github_token, "comment1", "Fixed bug in function A"), - call(github_token, "comment2", "Updated documentation for B"), + call(github_token, 'comment1', 'Fixed bug in function A'), + call(github_token, 'comment2', 'Updated documentation for B'), ] ) # Assert: Check the returned PR URL assert ( result - == f"https://github.com/{github_issue.owner}/{github_issue.repo}/pull/{github_issue.number}" + == f'https://github.com/{github_issue.owner}/{github_issue.repo}/pull/{github_issue.number}' ) -@pytest.mark.parametrize("pr_type", ["branch", "draft", "ready"]) -@patch("subprocess.run") -@patch("requests.post") -@patch("requests.get") +@pytest.mark.parametrize('pr_type', ['branch', 'draft', 'ready']) +@patch('subprocess.run') +@patch('requests.post') +@patch('requests.get') def test_send_pull_request( mock_get, mock_post, @@ -334,15 +335,15 @@ def test_send_pull_request( mock_llm_config, pr_type, ): - repo_path = os.path.join(mock_output_dir, "repo") + repo_path = os.path.join(mock_output_dir, 'repo') # Mock API responses mock_get.side_effect = [ MagicMock(status_code=404), # Branch doesn't exist - MagicMock(json=lambda: {"default_branch": "main"}), + MagicMock(json=lambda: {'default_branch': 'main'}), ] mock_post.return_value.json.return_value = { - "html_url": "https://github.com/test-owner/test-repo/pull/1" + 'html_url': 'https://github.com/test-owner/test-repo/pull/1' } # Mock subprocess.run calls @@ -354,8 +355,8 @@ def test_send_pull_request( # Call the function result = send_pull_request( github_issue=mock_github_issue, - github_token="test-token", - github_username="test-user", + github_token='test-token', + github_username='test-user', patch_dir=repo_path, pr_type=pr_type, llm_config=mock_llm_config, @@ -369,68 +370,68 @@ def test_send_pull_request( checkout_call, push_call = mock_run.call_args_list assert checkout_call == call( - ["git", "-C", repo_path, "checkout", "-b", "openhands-fix-issue-42"], + ['git', '-C', repo_path, 'checkout', '-b', 'openhands-fix-issue-42'], capture_output=True, text=True, ) assert push_call == call( [ - "git", - "-C", + 'git', + '-C', repo_path, - "push", - "https://test-user:test-token@github.com/test-owner/test-repo.git", - "openhands-fix-issue-42", + 'push', + 'https://test-user:test-token@github.com/test-owner/test-repo.git', + 'openhands-fix-issue-42', ], capture_output=True, text=True, ) # Check PR creation based on pr_type - if pr_type == "branch": + if pr_type == 'branch': assert ( result - == "https://github.com/test-owner/test-repo/compare/openhands-fix-issue-42?expand=1" + == 'https://github.com/test-owner/test-repo/compare/openhands-fix-issue-42?expand=1' ) mock_post.assert_not_called() else: - assert result == "https://github.com/test-owner/test-repo/pull/1" + assert result == 'https://github.com/test-owner/test-repo/pull/1' mock_post.assert_called_once() - post_data = mock_post.call_args[1]["json"] - assert post_data["title"] == "Fix issue #42: Test Issue" - assert post_data["body"].startswith("This pull request fixes #42.") - assert post_data["head"] == "openhands-fix-issue-42" - assert post_data["base"] == "main" - assert post_data["draft"] == (pr_type == "draft") + post_data = mock_post.call_args[1]['json'] + assert post_data['title'] == 'Fix issue #42: Test Issue' + assert post_data['body'].startswith('This pull request fixes #42.') + assert post_data['head'] == 'openhands-fix-issue-42' + assert post_data['base'] == 'main' + assert post_data['draft'] == (pr_type == 'draft') -@patch("subprocess.run") -@patch("requests.post") -@patch("requests.get") +@patch('subprocess.run') +@patch('requests.post') +@patch('requests.get') def test_send_pull_request_git_push_failure( mock_get, mock_post, mock_run, mock_github_issue, mock_output_dir, mock_llm_config ): - repo_path = os.path.join(mock_output_dir, "repo") + repo_path = os.path.join(mock_output_dir, 'repo') # Mock API responses - mock_get.return_value = MagicMock(json=lambda: {"default_branch": "main"}) + mock_get.return_value = MagicMock(json=lambda: {'default_branch': 'main'}) # Mock the subprocess.run calls mock_run.side_effect = [ MagicMock(returncode=0), # git checkout -b - MagicMock(returncode=1, stderr="Error: failed to push some refs"), # git push + MagicMock(returncode=1, stderr='Error: failed to push some refs'), # git push ] # Test that RuntimeError is raised when git push fails with pytest.raises( - RuntimeError, match="Failed to push changes to the remote repository" + RuntimeError, match='Failed to push changes to the remote repository' ): send_pull_request( github_issue=mock_github_issue, - github_token="test-token", - github_username="test-user", + github_token='test-token', + github_username='test-user', patch_dir=repo_path, - pr_type="ready", + pr_type='ready', llm_config=mock_llm_config, ) @@ -440,39 +441,39 @@ def test_send_pull_request_git_push_failure( # Check the git checkout -b command checkout_call = mock_run.call_args_list[0] assert checkout_call[0][0] == [ - "git", - "-C", + 'git', + '-C', repo_path, - "checkout", - "-b", - "openhands-fix-issue-42", + 'checkout', + '-b', + 'openhands-fix-issue-42', ] # Check the git push command push_call = mock_run.call_args_list[1] assert push_call[0][0] == [ - "git", - "-C", + 'git', + '-C', repo_path, - "push", - "https://test-user:test-token@github.com/test-owner/test-repo.git", - "openhands-fix-issue-42", + 'push', + 'https://test-user:test-token@github.com/test-owner/test-repo.git', + 'openhands-fix-issue-42', ] # Assert that no pull request was created mock_post.assert_not_called() -@patch("subprocess.run") -@patch("requests.post") -@patch("requests.get") +@patch('subprocess.run') +@patch('requests.post') +@patch('requests.get') def test_send_pull_request_permission_error( mock_get, mock_post, mock_run, mock_github_issue, mock_output_dir, mock_llm_config ): - repo_path = os.path.join(mock_output_dir, "repo") + repo_path = os.path.join(mock_output_dir, 'repo') # Mock API responses - mock_get.return_value = MagicMock(json=lambda: {"default_branch": "main"}) + mock_get.return_value = MagicMock(json=lambda: {'default_branch': 'main'}) mock_post.return_value.status_code = 403 # Mock subprocess.run calls @@ -483,14 +484,14 @@ def test_send_pull_request_permission_error( # Test that RuntimeError is raised when PR creation fails due to permissions with pytest.raises( - RuntimeError, match="Failed to create pull request due to missing permissions." + RuntimeError, match='Failed to create pull request due to missing permissions.' ): send_pull_request( github_issue=mock_github_issue, - github_token="test-token", - github_username="test-user", + github_token='test-token', + github_username='test-user', patch_dir=repo_path, - pr_type="ready", + pr_type='ready', llm_config=mock_llm_config, ) @@ -499,23 +500,23 @@ def test_send_pull_request_permission_error( mock_post.assert_called_once() -@patch("requests.post") +@patch('requests.post') def test_reply_to_comment(mock_post): # Arrange: set up the test data - github_token = "test_token" - comment_id = "test_comment_id" - reply = "This is a test reply." + github_token = 'test_token' + comment_id = 'test_comment_id' + reply = 'This is a test reply.' # Mock the response from the GraphQL API mock_response = MagicMock() mock_response.status_code = 200 mock_response.json.return_value = { - "data": { - "addPullRequestReviewThreadReply": { - "comment": { - "id": "test_reply_id", - "body": "Openhands fix success summary\n\n\nThis is a test reply.", - "createdAt": "2024-10-01T12:34:56Z", + 'data': { + 'addPullRequestReviewThreadReply': { + 'comment': { + 'id': 'test_reply_id', + 'body': 'Openhands fix success summary\n\n\nThis is a test reply.', + 'createdAt': '2024-10-01T12:34:56Z', } } } @@ -540,17 +541,17 @@ def test_reply_to_comment(mock_post): """ expected_variables = { - "body": "Openhands fix success summary\n\n\nThis is a test reply.", - "pullRequestReviewThreadId": comment_id, + 'body': 'Openhands fix success summary\n\n\nThis is a test reply.', + 'pullRequestReviewThreadId': comment_id, } # Check that the correct request was made to the API mock_post.assert_called_once_with( - "https://api.github.com/graphql", - json={"query": query, "variables": expected_variables}, + 'https://api.github.com/graphql', + json={'query': query, 'variables': expected_variables}, headers={ - "Authorization": f"Bearer {github_token}", - "Content-Type": "application/json", + 'Authorization': f'Bearer {github_token}', + 'Content-Type': 'application/json', }, ) @@ -558,10 +559,10 @@ def test_reply_to_comment(mock_post): mock_response.raise_for_status.assert_called_once() -@patch("openhands.resolver.send_pull_request.initialize_repo") -@patch("openhands.resolver.send_pull_request.apply_patch") -@patch("openhands.resolver.send_pull_request.update_existing_pull_request") -@patch("openhands.resolver.send_pull_request.make_commit") +@patch('openhands.resolver.send_pull_request.initialize_repo') +@patch('openhands.resolver.send_pull_request.apply_patch') +@patch('openhands.resolver.send_pull_request.update_existing_pull_request') +@patch('openhands.resolver.send_pull_request.make_commit') def test_process_single_pr_update( mock_make_commit, mock_update_existing_pull_request, @@ -571,40 +572,40 @@ def test_process_single_pr_update( mock_llm_config, ): # Initialize test data - github_token = "test_token" - github_username = "test_user" - pr_type = "draft" + github_token = 'test_token' + github_username = 'test_user' + pr_type = 'draft' resolver_output = ResolverOutput( issue=GithubIssue( - owner="test-owner", - repo="test-repo", + owner='test-owner', + repo='test-repo', number=1, - title="Issue 1", - body="Body 1", + title='Issue 1', + body='Body 1', closing_issues=[], review_threads=[ - ReviewThread(comment="review comment for feedback", files=[]) + ReviewThread(comment='review comment for feedback', files=[]) ], - thread_ids=["1"], - head_branch="branch 1", + thread_ids=['1'], + head_branch='branch 1', ), - issue_type="pr", - instruction="Test instruction 1", - base_commit="def456", - git_patch="Test patch 1", + issue_type='pr', + instruction='Test instruction 1', + base_commit='def456', + git_patch='Test patch 1', history=[], metrics={}, success=True, comment_success=None, - success_explanation="[Test success 1]", + success_explanation='[Test success 1]', error=None, ) mock_update_existing_pull_request.return_value = ( - "https://github.com/test-owner/test-repo/pull/1" + 'https://github.com/test-owner/test-repo/pull/1' ) - mock_initialize_repo.return_value = f"{mock_output_dir}/patches/pr_1" + mock_initialize_repo.return_value = f'{mock_output_dir}/patches/pr_1' process_single_issue( mock_output_dir, @@ -617,27 +618,27 @@ def test_process_single_pr_update( False, ) - mock_initialize_repo.assert_called_once_with(mock_output_dir, 1, "pr", "branch 1") + mock_initialize_repo.assert_called_once_with(mock_output_dir, 1, 'pr', 'branch 1') mock_apply_patch.assert_called_once_with( - f"{mock_output_dir}/patches/pr_1", resolver_output.git_patch + f'{mock_output_dir}/patches/pr_1', resolver_output.git_patch ) mock_make_commit.assert_called_once_with( - f"{mock_output_dir}/patches/pr_1", resolver_output.issue, "pr" + f'{mock_output_dir}/patches/pr_1', resolver_output.issue, 'pr' ) mock_update_existing_pull_request.assert_called_once_with( github_issue=resolver_output.issue, github_token=github_token, github_username=github_username, - patch_dir=f"{mock_output_dir}/patches/pr_1", - additional_message="[Test success 1]", + patch_dir=f'{mock_output_dir}/patches/pr_1', + additional_message='[Test success 1]', llm_config=mock_llm_config, ) -@patch("openhands.resolver.send_pull_request.initialize_repo") -@patch("openhands.resolver.send_pull_request.apply_patch") -@patch("openhands.resolver.send_pull_request.send_pull_request") -@patch("openhands.resolver.send_pull_request.make_commit") +@patch('openhands.resolver.send_pull_request.initialize_repo') +@patch('openhands.resolver.send_pull_request.apply_patch') +@patch('openhands.resolver.send_pull_request.send_pull_request') +@patch('openhands.resolver.send_pull_request.make_commit') def test_process_single_issue( mock_make_commit, mock_send_pull_request, @@ -647,35 +648,35 @@ def test_process_single_issue( mock_llm_config, ): # Initialize test data - github_token = "test_token" - github_username = "test_user" - pr_type = "draft" + github_token = 'test_token' + github_username = 'test_user' + pr_type = 'draft' resolver_output = ResolverOutput( issue=GithubIssue( - owner="test-owner", - repo="test-repo", + owner='test-owner', + repo='test-repo', number=1, - title="Issue 1", - body="Body 1", + title='Issue 1', + body='Body 1', ), - issue_type="issue", - instruction="Test instruction 1", - base_commit="def456", - git_patch="Test patch 1", + issue_type='issue', + instruction='Test instruction 1', + base_commit='def456', + git_patch='Test patch 1', history=[], metrics={}, success=True, comment_success=None, - success_explanation="Test success 1", + success_explanation='Test success 1', error=None, ) # Mock return value mock_send_pull_request.return_value = ( - "https://github.com/test-owner/test-repo/pull/1" + 'https://github.com/test-owner/test-repo/pull/1' ) - mock_initialize_repo.return_value = f"{mock_output_dir}/patches/issue_1" + mock_initialize_repo.return_value = f'{mock_output_dir}/patches/issue_1' # Call the function process_single_issue( @@ -690,18 +691,18 @@ def test_process_single_issue( ) # Assert that the mocked functions were called with correct arguments - mock_initialize_repo.assert_called_once_with(mock_output_dir, 1, "issue", "def456") + mock_initialize_repo.assert_called_once_with(mock_output_dir, 1, 'issue', 'def456') mock_apply_patch.assert_called_once_with( - f"{mock_output_dir}/patches/issue_1", resolver_output.git_patch + f'{mock_output_dir}/patches/issue_1', resolver_output.git_patch ) mock_make_commit.assert_called_once_with( - f"{mock_output_dir}/patches/issue_1", resolver_output.issue, "issue" + f'{mock_output_dir}/patches/issue_1', resolver_output.issue, 'issue' ) mock_send_pull_request.assert_called_once_with( github_issue=resolver_output.issue, github_token=github_token, github_username=github_username, - patch_dir=f"{mock_output_dir}/patches/issue_1", + patch_dir=f'{mock_output_dir}/patches/issue_1', pr_type=pr_type, fork_owner=None, additional_message=resolver_output.success_explanation, @@ -709,10 +710,10 @@ def test_process_single_issue( ) -@patch("openhands.resolver.send_pull_request.initialize_repo") -@patch("openhands.resolver.send_pull_request.apply_patch") -@patch("openhands.resolver.send_pull_request.send_pull_request") -@patch("openhands.resolver.send_pull_request.make_commit") +@patch('openhands.resolver.send_pull_request.initialize_repo') +@patch('openhands.resolver.send_pull_request.apply_patch') +@patch('openhands.resolver.send_pull_request.send_pull_request') +@patch('openhands.resolver.send_pull_request.make_commit') def test_process_single_issue_unsuccessful( mock_make_commit, mock_send_pull_request, @@ -722,28 +723,28 @@ def test_process_single_issue_unsuccessful( mock_llm_config, ): # Initialize test data - github_token = "test_token" - github_username = "test_user" - pr_type = "draft" + github_token = 'test_token' + github_username = 'test_user' + pr_type = 'draft' resolver_output = ResolverOutput( issue=GithubIssue( - owner="test-owner", - repo="test-repo", + owner='test-owner', + repo='test-repo', number=1, - title="Issue 1", - body="Body 1", + title='Issue 1', + body='Body 1', ), - issue_type="issue", - instruction="Test instruction 1", - base_commit="def456", - git_patch="Test patch 1", + issue_type='issue', + instruction='Test instruction 1', + base_commit='def456', + git_patch='Test patch 1', history=[], metrics={}, success=False, comment_success=None, - success_explanation="", - error="Test error", + success_explanation='', + error='Test error', ) # Call the function @@ -765,69 +766,69 @@ def test_process_single_issue_unsuccessful( mock_send_pull_request.assert_not_called() -@patch("openhands.resolver.send_pull_request.load_all_resolver_outputs") -@patch("openhands.resolver.send_pull_request.process_single_issue") +@patch('openhands.resolver.send_pull_request.load_all_resolver_outputs') +@patch('openhands.resolver.send_pull_request.process_single_issue') def test_process_all_successful_issues( mock_process_single_issue, mock_load_all_resolver_outputs, mock_llm_config ): # Create ResolverOutput objects with properly initialized GithubIssue instances resolver_output_1 = ResolverOutput( issue=GithubIssue( - owner="test-owner", - repo="test-repo", + owner='test-owner', + repo='test-repo', number=1, - title="Issue 1", - body="Body 1", + title='Issue 1', + body='Body 1', ), - issue_type="issue", - instruction="Test instruction 1", - base_commit="def456", - git_patch="Test patch 1", + issue_type='issue', + instruction='Test instruction 1', + base_commit='def456', + git_patch='Test patch 1', history=[], metrics={}, success=True, comment_success=None, - success_explanation="Test success 1", + success_explanation='Test success 1', error=None, ) resolver_output_2 = ResolverOutput( issue=GithubIssue( - owner="test-owner", - repo="test-repo", + owner='test-owner', + repo='test-repo', number=2, - title="Issue 2", - body="Body 2", + title='Issue 2', + body='Body 2', ), - issue_type="issue", - instruction="Test instruction 2", - base_commit="ghi789", - git_patch="Test patch 2", + issue_type='issue', + instruction='Test instruction 2', + base_commit='ghi789', + git_patch='Test patch 2', history=[], metrics={}, success=False, comment_success=None, - success_explanation="", - error="Test error 2", + success_explanation='', + error='Test error 2', ) resolver_output_3 = ResolverOutput( issue=GithubIssue( - owner="test-owner", - repo="test-repo", + owner='test-owner', + repo='test-repo', number=3, - title="Issue 3", - body="Body 3", + title='Issue 3', + body='Body 3', ), - issue_type="issue", - instruction="Test instruction 3", - base_commit="jkl012", - git_patch="Test patch 3", + issue_type='issue', + instruction='Test instruction 3', + base_commit='jkl012', + git_patch='Test patch 3', history=[], metrics={}, success=True, comment_success=None, - success_explanation="Test success 3", + success_explanation='Test success 3', error=None, ) @@ -839,10 +840,10 @@ def test_process_all_successful_issues( # Call the function process_all_successful_issues( - "output_dir", - "github_token", - "github_username", - "draft", + 'output_dir', + 'github_token', + 'github_username', + 'draft', mock_llm_config, # llm_config None, # fork_owner ) @@ -854,21 +855,21 @@ def test_process_all_successful_issues( mock_process_single_issue.assert_has_calls( [ call( - "output_dir", + 'output_dir', resolver_output_1, - "github_token", - "github_username", - "draft", + 'github_token', + 'github_username', + 'draft', mock_llm_config, None, False, ), call( - "output_dir", + 'output_dir', resolver_output_3, - "github_token", - "github_username", - "draft", + 'github_token', + 'github_username', + 'draft', mock_llm_config, None, False, @@ -879,19 +880,19 @@ def test_process_all_successful_issues( # Add more assertions as needed to verify the behavior of the function -@patch("requests.get") -@patch("subprocess.run") +@patch('requests.get') +@patch('subprocess.run') def test_send_pull_request_branch_naming( mock_run, mock_get, mock_github_issue, mock_output_dir, mock_llm_config ): - repo_path = os.path.join(mock_output_dir, "repo") + repo_path = os.path.join(mock_output_dir, 'repo') # Mock API responses mock_get.side_effect = [ MagicMock(status_code=200), # First branch exists MagicMock(status_code=200), # Second branch exists MagicMock(status_code=404), # Third branch doesn't exist - MagicMock(json=lambda: {"default_branch": "main"}), # Get default branch + MagicMock(json=lambda: {'default_branch': 'main'}), # Get default branch ] # Mock subprocess.run calls @@ -903,10 +904,10 @@ def test_send_pull_request_branch_naming( # Call the function result = send_pull_request( github_issue=mock_github_issue, - github_token="test-token", - github_username="test-user", + github_token='test-token', + github_username='test-user', patch_dir=repo_path, - pr_type="branch", + pr_type='branch', llm_config=mock_llm_config, ) @@ -918,18 +919,18 @@ def test_send_pull_request_branch_naming( checkout_call, push_call = mock_run.call_args_list assert checkout_call == call( - ["git", "-C", repo_path, "checkout", "-b", "openhands-fix-issue-42-try3"], + ['git', '-C', repo_path, 'checkout', '-b', 'openhands-fix-issue-42-try3'], capture_output=True, text=True, ) assert push_call == call( [ - "git", - "-C", + 'git', + '-C', repo_path, - "push", - "https://test-user:test-token@github.com/test-owner/test-repo.git", - "openhands-fix-issue-42-try3", + 'push', + 'https://test-user:test-token@github.com/test-owner/test-repo.git', + 'openhands-fix-issue-42-try3', ], capture_output=True, text=True, @@ -938,16 +939,16 @@ def test_send_pull_request_branch_naming( # Check the result assert ( result - == "https://github.com/test-owner/test-repo/compare/openhands-fix-issue-42-try3?expand=1" + == 'https://github.com/test-owner/test-repo/compare/openhands-fix-issue-42-try3?expand=1' ) -@patch("openhands.resolver.send_pull_request.argparse.ArgumentParser") -@patch("openhands.resolver.send_pull_request.process_all_successful_issues") -@patch("openhands.resolver.send_pull_request.process_single_issue") -@patch("openhands.resolver.send_pull_request.load_single_resolver_output") -@patch("os.path.exists") -@patch("os.getenv") +@patch('openhands.resolver.send_pull_request.argparse.ArgumentParser') +@patch('openhands.resolver.send_pull_request.process_all_successful_issues') +@patch('openhands.resolver.send_pull_request.process_single_issue') +@patch('openhands.resolver.send_pull_request.load_single_resolver_output') +@patch('os.path.exists') +@patch('os.getenv') def test_main( mock_getenv, mock_path_exists, @@ -961,20 +962,20 @@ def test_main( # Setup mock parser mock_args = MagicMock() mock_args.github_token = None - mock_args.github_username = None - mock_args.output_dir = "/mock/output" - mock_args.pr_type = "draft" - mock_args.issue_number = "42" + mock_args.github_username = 'mock_username' + mock_args.output_dir = '/mock/output' + mock_args.pr_type = 'draft' + mock_args.issue_number = '42' mock_args.fork_owner = None mock_args.send_on_failure = False - mock_args.llm_model = "mock_model" - mock_args.llm_base_url = "mock_url" - mock_args.llm_api_key = "mock_key" + mock_args.llm_model = 'mock_model' + mock_args.llm_base_url = 'mock_url' + mock_args.llm_api_key = 'mock_key' mock_parser.return_value.parse_args.return_value = mock_args # Setup environment variables mock_getenv.side_effect = ( - lambda key, default=None: "mock_token" if key == "GITHUB_TOKEN" else default + lambda key, default=None: 'mock_token' if key == 'GITHUB_TOKEN' else default ) # Setup path exists @@ -995,57 +996,57 @@ def test_main( # Assert function calls mock_parser.assert_called_once() - mock_getenv.assert_any_call("GITHUB_TOKEN") - mock_path_exists.assert_called_with("/mock/output") - mock_load_single_resolver_output.assert_called_with("/mock/output/output.jsonl", 42) + mock_getenv.assert_any_call('GITHUB_TOKEN') + mock_path_exists.assert_called_with('/mock/output') + mock_load_single_resolver_output.assert_called_with('/mock/output/output.jsonl', 42) mock_process_single_issue.assert_called_with( - "/mock/output", + '/mock/output', mock_resolver_output, - "mock_token", - None, - "draft", + 'mock_token', + 'mock_username', + 'draft', llm_config, None, False, ) # Test for 'all_successful' issue number - mock_args.issue_number = "all_successful" + mock_args.issue_number = 'all_successful' main() mock_process_all_successful_issues.assert_called_with( - "/mock/output", - "mock_token", - None, - "draft", + '/mock/output', + 'mock_token', + 'mock_username', + 'draft', llm_config, None, ) # Test for invalid issue number - mock_args.issue_number = "invalid" + mock_args.issue_number = 'invalid' with pytest.raises(ValueError): main() -@patch("subprocess.run") +@patch('subprocess.run') def test_make_commit_escapes_issue_title(mock_subprocess_run): # Setup - repo_dir = "/path/to/repo" + repo_dir = '/path/to/repo' issue = GithubIssue( - owner="test-owner", - repo="test-repo", + owner='test-owner', + repo='test-repo', number=42, title='Issue with "quotes" and $pecial characters', - body="Test body", + body='Test body', ) # Mock subprocess.run to return success for all calls mock_subprocess_run.return_value = MagicMock( - returncode=0, stdout="sample output", stderr="" + returncode=0, stdout='sample output', stderr='' ) # Call the function - issue_type = "issue" + issue_type = 'issue' make_commit(repo_dir, issue, issue_type) # Assert that subprocess.run was called with the correct arguments @@ -1058,60 +1059,60 @@ def test_make_commit_escapes_issue_title(mock_subprocess_run): 'Fix issue #42: Issue with "quotes" and $pecial characters' ) assert [ - "git", - "-C", - "/path/to/repo", - "commit", - "-m", + 'git', + '-C', + '/path/to/repo', + 'commit', + '-m', expected_commit_message, ] == git_commit_call -@patch("subprocess.run") +@patch('subprocess.run') def test_make_commit_no_changes(mock_subprocess_run): # Setup - repo_dir = "/path/to/repo" + repo_dir = '/path/to/repo' issue = GithubIssue( - owner="test-owner", - repo="test-repo", + owner='test-owner', + repo='test-repo', number=42, - title="Issue with no changes", - body="Test body", + title='Issue with no changes', + body='Test body', ) # Mock subprocess.run to simulate no changes in the repo mock_subprocess_run.side_effect = [ MagicMock(returncode=0), MagicMock(returncode=0), - MagicMock(returncode=1, stdout=""), # git status --porcelain (no changes) + MagicMock(returncode=1, stdout=''), # git status --porcelain (no changes) ] with pytest.raises( - RuntimeError, match="ERROR: Openhands failed to make code changes." + RuntimeError, match='ERROR: Openhands failed to make code changes.' ): - make_commit(repo_dir, issue, "issue") + make_commit(repo_dir, issue, 'issue') # Check that subprocess.run was called for checking git status and add, but not commit assert mock_subprocess_run.call_count == 3 git_status_call = mock_subprocess_run.call_args_list[2][0][0] - assert f"git -C {repo_dir} status --porcelain" in git_status_call + assert f'git -C {repo_dir} status --porcelain' in git_status_call def test_apply_patch_rename_directory(mock_output_dir): # Create a sample directory structure - old_dir = os.path.join(mock_output_dir, "prompts", "resolve") + old_dir = os.path.join(mock_output_dir, 'prompts', 'resolve') os.makedirs(old_dir) # Create test files test_files = [ - "issue-success-check.jinja", - "pr-feedback-check.jinja", - "pr-thread-check.jinja", + 'issue-success-check.jinja', + 'pr-feedback-check.jinja', + 'pr-thread-check.jinja', ] for filename in test_files: file_path = os.path.join(old_dir, filename) - with open(file_path, "w") as f: - f.write(f"Content of {filename}") + with open(file_path, 'w') as f: + f.write(f'Content of {filename}') # Create a patch that renames the directory patch_content = """diff --git a/prompts/resolve/issue-success-check.jinja b/prompts/guess_success/issue-success-check.jinja @@ -1131,16 +1132,16 @@ def test_apply_patch_rename_directory(mock_output_dir): apply_patch(mock_output_dir, patch_content) # Check if files were moved correctly - new_dir = os.path.join(mock_output_dir, "prompts", "guess_success") - assert not os.path.exists(old_dir), "Old directory still exists" - assert os.path.exists(new_dir), "New directory was not created" + new_dir = os.path.join(mock_output_dir, 'prompts', 'guess_success') + assert not os.path.exists(old_dir), 'Old directory still exists' + assert os.path.exists(new_dir), 'New directory was not created' # Check if all files were moved and content preserved for filename in test_files: old_path = os.path.join(old_dir, filename) new_path = os.path.join(new_dir, filename) - assert not os.path.exists(old_path), f"Old file {filename} still exists" - assert os.path.exists(new_path), f"New file {filename} was not created" - with open(new_path, "r") as f: + assert not os.path.exists(old_path), f'Old file {filename} still exists' + assert os.path.exists(new_path), f'New file {filename} was not created' + with open(new_path, 'r') as f: content = f.read() - assert content == f"Content of {filename}", f"Content mismatch for {filename}" + assert content == f'Content of {filename}', f'Content mismatch for {filename}' From aa78d7256037199a4f1437c37c9b0532f657c742 Mon Sep 17 00:00:00 2001 From: Graham Neubig Date: Wed, 13 Nov 2024 17:58:58 -0500 Subject: [PATCH 23/27] Update action --- .github/workflows/openhands-resolver.yml | 31 ++++++++++++++++++++---- 1 file changed, 26 insertions(+), 5 deletions(-) diff --git a/.github/workflows/openhands-resolver.yml b/.github/workflows/openhands-resolver.yml index 117d0325d862..9bb11c3c482e 100644 --- a/.github/workflows/openhands-resolver.yml +++ b/.github/workflows/openhands-resolver.yml @@ -40,6 +40,7 @@ permissions: issues: write jobs: + auto-fix: if: | github.event_name == 'workflow_call' || @@ -47,12 +48,12 @@ jobs: github.event.label.name == 'fix-me-experimental' || ( - ((github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment') && + ((github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment') && startsWith(github.event.comment.body, inputs.macro || '@openhands-agent') && (github.event.comment.author_association == 'OWNER' || github.event.comment.author_association == 'COLLABORATOR' || github.event.comment.author_association == 'MEMBER') ) || - - (github.event_name == 'pull_request_review' && + + (github.event_name == 'pull_request_review' && startsWith(github.event.review.body, inputs.macro || '@openhands-agent') && (github.event.review.author_association == 'OWNER' || github.event.review.author_association == 'COLLABORATOR' || github.event.review.author_association == 'MEMBER') ) @@ -67,6 +68,22 @@ jobs: with: python-version: "3.12" + - name: Get latest versions and create requirements.txt + run: | + python -m pip index versions openhands-ai > openhands_versions.txt + OPENHANDS_VERSION=$(head -n 1 openhands_versions.txt | awk '{print $2}' | tr -d '()') + echo "openhands-resolver==${OPENHANDS_VERSION}" >> requirements.txt + cat requirements.txt + + - name: Cache pip dependencies + if: github.event.label.name != 'fix-me-experimental' + uses: actions/cache@v3 + with: + path: ${{ env.pythonLocation }}/lib/python3.12/site-packages/* + key: ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }} + restore-keys: | + ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }} + - name: Check required environment variables env: LLM_MODEL: ${{ secrets.LLM_MODEL }} @@ -123,8 +140,12 @@ jobs: - name: Install OpenHands run: | - python -m pip install --upgrade pip - pip install -e . + if [ "${{ github.event.label.name }}" == "fix-me-experimental" ]; then + python -m pip install --upgrade pip + pip install git+https://github.com/all-hands-ai/openhands.git + else + python -m pip install --upgrade -r requirements.txt + fi - name: Attempt to resolve issue env: From 1ddb332529bfcb03b433119ddfa4057d7d6e3c1c Mon Sep 17 00:00:00 2001 From: Graham Neubig Date: Wed, 13 Nov 2024 20:26:40 -0500 Subject: [PATCH 24/27] Apply suggestions from code review Co-authored-by: Rohit Malhotra --- openhands/resolver/README.md | 4 ++-- openhands/resolver/examples/openhands-resolver.yml | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/openhands/resolver/README.md b/openhands/resolver/README.md index 30984acc0e85..94e3c09fcac9 100644 --- a/openhands/resolver/README.md +++ b/openhands/resolver/README.md @@ -68,7 +68,7 @@ If you prefer to run the resolver programmatically instead of using GitHub Actio 1. Install the package: ```bash -pip install openhands-resolver +pip install openhands-ai ``` 2. Create a GitHub access token: @@ -100,7 +100,7 @@ Note: OpenHands works best with powerful models like Anthropic's Claude or OpenA The resolver can automatically attempt to fix a single issue in your repository using the following command: ```bash -python -m openhands_resolver.resolve_issue --repo [OWNER]/[REPO] --issue-number [NUMBER] +python -m openhands.resolver.resolve_issue --repo [OWNER]/[REPO] --issue-number [NUMBER] ``` For instance, if you want to resolve issue #100 in this repo, you would run: diff --git a/openhands/resolver/examples/openhands-resolver.yml b/openhands/resolver/examples/openhands-resolver.yml index 3204c5fb0b04..6555e15057c7 100644 --- a/openhands/resolver/examples/openhands-resolver.yml +++ b/openhands/resolver/examples/openhands-resolver.yml @@ -22,7 +22,7 @@ jobs: startsWith(github.event.comment.body, vars.OPENHANDS_MACRO || '@openhands-agent') && (github.event.comment.author_association == 'OWNER' || github.event.comment.author_association == 'COLLABORATOR' || github.event.comment.author_association == 'MEMBER')) }} - uses: All-Hands-AI/OpenHands/openhands/resolver/.github/workflows/openhands-resolver.yml@main + uses: All-Hands-AI/OpenHands/.github/workflows/openhands-resolver.yml@main with: macro: ${{ vars.OPENHANDS_MACRO || '@openhands-agent' }} max_iterations: 50 From 5f774ac0c85221a9dcc68c884f16bb80b4c53770 Mon Sep 17 00:00:00 2001 From: Graham Neubig Date: Wed, 13 Nov 2024 20:32:33 -0500 Subject: [PATCH 25/27] Update resolver --- openhands/resolver/README.md | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/openhands/resolver/README.md b/openhands/resolver/README.md index 94e3c09fcac9..fab0071b737f 100644 --- a/openhands/resolver/README.md +++ b/openhands/resolver/README.md @@ -106,7 +106,7 @@ python -m openhands.resolver.resolve_issue --repo [OWNER]/[REPO] --issue-number For instance, if you want to resolve issue #100 in this repo, you would run: ```bash -python -m openhands_resolver.resolve_issue --repo all-hands-ai/openhands-resolver --issue-number 100 +python -m openhands.resolver.resolve_issue --repo all-hands-ai/openhands-resolver --issue-number 100 ``` The output will be written to the `output/` directory. @@ -114,19 +114,19 @@ The output will be written to the `output/` directory. If you've installed the package from source using poetry, you can use: ```bash -poetry run python openhands_resolver/resolve_issue.py --repo all-hands-ai/openhands-resolver --issue-number 100 +poetry run python openhands.resolver/resolve_issue.py --repo all-hands-ai/openhands-resolver --issue-number 100 ``` For resolving multiple issues at once (e.g., in a batch process), you can use the `resolve_all_issues` command: ```bash -python -m openhands_resolver.resolve_all_issues --repo [OWNER]/[REPO] --issue-numbers [NUMBERS] +python -m openhands.resolver.resolve_all_issues --repo [OWNER]/[REPO] --issue-numbers [NUMBERS] ``` For example: ```bash -python -m openhands_resolver.resolve_all_issues --repo all-hands-ai/openhands-resolver --issue-numbers 100,101,102 +python -m openhands.resolver.resolve_all_issues --repo all-hands-ai/openhands-resolver --issue-numbers 100,101,102 ``` ## Responding to PR Comments @@ -134,7 +134,7 @@ python -m openhands_resolver.resolve_all_issues --repo all-hands-ai/openhands-re The resolver can also respond to comments on pull requests using: ```bash -python -m openhands_resolver.send_pull_request --issue-number PR_NUMBER --issue-type pr +python -m openhands.resolver.send_pull_request --issue-number PR_NUMBER --issue-type pr ``` This functionality is available both through the GitHub Actions workflow and when running the resolver locally. @@ -150,7 +150,7 @@ grep '"success":true' output/output.jsonl | sed 's/.*\("number":[0-9]*\).*/\1/g' Then you can go through and visualize the ones you'd like. ```bash -python -m openhands_resolver.visualize_resolver_output --issue-number ISSUE_NUMBER --vis-method json +python -m openhands.resolver.visualize_resolver_output --issue-number ISSUE_NUMBER --vis-method json ``` ## Uploading PRs @@ -163,13 +163,13 @@ There are three ways you can upload: 3. `ready` - create a non-draft PR that's ready for review ```bash -python -m openhands_resolver.send_pull_request --issue-number ISSUE_NUMBER --github-username YOUR_GITHUB_USERNAME --pr-type draft +python -m openhands.resolver.send_pull_request --issue-number ISSUE_NUMBER --github-username YOUR_GITHUB_USERNAME --pr-type draft ``` If you want to upload to a fork, you can do so by specifying the `fork-owner`: ```bash -python -m openhands_resolver.send_pull_request --issue-number ISSUE_NUMBER --github-username YOUR_GITHUB_USERNAME --pr-type draft --fork-owner YOUR_GITHUB_USERNAME +python -m openhands.resolver.send_pull_request --issue-number ISSUE_NUMBER --github-username YOUR_GITHUB_USERNAME --pr-type draft --fork-owner YOUR_GITHUB_USERNAME ``` ## Providing Custom Instructions From 28f8f6b6ae8d0ecd417070bf71762576d901e3d1 Mon Sep 17 00:00:00 2001 From: Graham Neubig Date: Wed, 13 Nov 2024 20:34:22 -0500 Subject: [PATCH 26/27] Update gitignore --- .gitignore | 3 +++ 1 file changed, 3 insertions(+) diff --git a/.gitignore b/.gitignore index 0cc7d149d781..6d3108331456 100644 --- a/.gitignore +++ b/.gitignore @@ -176,6 +176,9 @@ evaluation/gorilla/data evaluation/toolqa/data evaluation/scienceagentbench/benchmark +# openhands resolver +output/ + # frontend # dependencies From 1f2f2c9c6cc65404a34e4e49eebcdabd64c059aa Mon Sep 17 00:00:00 2001 From: Graham Neubig Date: Wed, 13 Nov 2024 20:41:23 -0500 Subject: [PATCH 27/27] Update openhands/resolver/README.md --- openhands/resolver/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/openhands/resolver/README.md b/openhands/resolver/README.md index fab0071b737f..d91699fe0c20 100644 --- a/openhands/resolver/README.md +++ b/openhands/resolver/README.md @@ -114,7 +114,7 @@ The output will be written to the `output/` directory. If you've installed the package from source using poetry, you can use: ```bash -poetry run python openhands.resolver/resolve_issue.py --repo all-hands-ai/openhands-resolver --issue-number 100 +poetry run python openhands/resolver/resolve_issue.py --repo all-hands-ai/openhands-resolver --issue-number 100 ``` For resolving multiple issues at once (e.g., in a batch process), you can use the `resolve_all_issues` command: