Merge branch 'main' into feature/strict-mypy-checks

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -30,6 +30,7 @@ body:
       description: How are you running OpenHands?
       options:
         - Docker command in README
+        - GitHub resolver
         - Development workflow
         - app.all-hands.dev
         - Other

.github/workflows/dummy-agent-test.yml

@@ -19,20 +19,6 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3

.github/workflows/ghcr-build.yml

@@ -41,20 +41,6 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@v4
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
       - name: Set up QEMU
         uses: docker/[email protected]
         with:
@@ -104,20 +90,6 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@v4
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
       - name: Set up QEMU
         uses: docker/[email protected]
         with:
@@ -219,7 +191,7 @@ jobs:
             exit 1
           fi
 
-  # Run unit tests with the EventStream runtime Docker images as root
+  # Run unit tests with the Docker runtime Docker images as root
   test_runtime_root:
     name: RT Unit Tests (Root)
     needs: [ghcr_build_runtime]
@@ -230,20 +202,6 @@ jobs:
         base_image: ['nikolaik']
     steps:
       - uses: actions/checkout@v4
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
@@ -275,7 +233,7 @@ jobs:
         run: pipx install poetry
       - name: Install Python dependencies using Poetry
         run: make install-python-dependencies
-      - name: Run runtime tests
+      - name: Run docker runtime tests
         run: |
           # We install pytest-xdist in order to run tests across CPUs
           poetry run pip install pytest-xdist
@@ -286,7 +244,7 @@ jobs:
           image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
           image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
 
-          TEST_RUNTIME=eventstream \
+          TEST_RUNTIME=docker \
           SANDBOX_USER_ID=$(id -u) \
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
           TEST_IN_CI=true \
@@ -297,7 +255,7 @@ jobs:
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
 
-  # Run unit tests with the EventStream runtime Docker images as openhands user
+  # Run unit tests with the Docker runtime Docker images as openhands user
   test_runtime_oh:
     name: RT Unit Tests (openhands)
     runs-on: ubuntu-latest
@@ -307,20 +265,6 @@ jobs:
         base_image: ['nikolaik']
     steps:
       - uses: actions/checkout@v4
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
@@ -363,7 +307,7 @@ jobs:
           image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
           image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
 
-          TEST_RUNTIME=eventstream \
+          TEST_RUNTIME=docker \
           SANDBOX_USER_ID=$(id -u) \
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
           TEST_IN_CI=true \

.github/workflows/integration-runner.yml

@@ -160,7 +160,6 @@ jobs:
           echo "api_key = \"$LLM_API_KEY\"" >> config.toml
           echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
           echo "temperature = 0.0" >> config.toml
-
       - name: Run integration test evaluation for DelegatorAgent (DeepSeek)
         env:
           SANDBOX_FORCE_REBUILD_RUNTIME: True
@@ -174,12 +173,42 @@ jobs:
           cat $REPORT_FILE_DELEGATOR_DEEPSEEK >> $GITHUB_ENV
           echo >> $GITHUB_ENV
           echo "EOF" >> $GITHUB_ENV
+      # -------------------------------------------------------------
+      # Run VisualBrowsingAgent tests for DeepSeek, limited to t05 and t06
+      - name: Wait a little bit (again)
+        run: sleep 5
+
+      - name: Configure config.toml for testing VisualBrowsingAgent (DeepSeek)
+        env:
+          LLM_MODEL: "litellm_proxy/deepseek-chat"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 15
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+      - name: Run integration test evaluation for VisualBrowsingAgent (DeepSeek)
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD VisualBrowsingAgent '' 15 $N_PROCESSES "t05_simple_browsing,t06_github_pr_browsing.py" 'visualbrowsing_deepseek_run'
+
+          # Find and export the visual browsing agent test results
+          REPORT_FILE_VISUALBROWSING_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/VisualBrowsingAgent/deepseek*_maxiter_15_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE_VISUALBROWSING_DEEPSEEK: $REPORT_FILE_VISUALBROWSING_DEEPSEEK"
+          echo "INTEGRATION_TEST_REPORT_VISUALBROWSING_DEEPSEEK<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_VISUALBROWSING_DEEPSEEK >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
 
       - name: Create archive of evaluation outputs
         run: |
           TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
           cd evaluation/evaluation_outputs/outputs  # Change to the outputs directory
-          tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/* integration_tests/DelegatorAgent/*  # Only include the actual result directories
+          tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/* integration_tests/DelegatorAgent/* integration_tests/VisualBrowsingAgent/* # Only include the actual result directories
 
       - name: Upload evaluation results as artifact
         uses: actions/upload-artifact@v4
@@ -227,4 +256,7 @@ jobs:
               **Integration Tests Report Delegator (DeepSeek)**
               ${{ env.INTEGRATION_TEST_REPORT_DELEGATOR_DEEPSEEK }}
               ---
+              **Integration Tests Report VisualBrowsing (DeepSeek)**
+              ${{ env.INTEGRATION_TEST_REPORT_VISUALBROWSING_DEEPSEEK }}
+              ---
               Download testing outputs (includes both Haiku and DeepSeek results): [Download](${{ steps.upload_results_artifact.outputs.artifact-url }})

.github/workflows/openhands-resolver.yml

@@ -20,6 +20,10 @@ on:
         required: false
         type: string
         default: "anthropic/claude-3-5-sonnet-20241022"
+      LLM_API_VERSION:
+        required: false
+        type: string
+        default: ""
       base_container_image:
         required: false
         type: string
@@ -84,6 +88,10 @@ jobs:
         run: |
           python -m pip index versions openhands-ai > openhands_versions.txt
           OPENHANDS_VERSION=$(head -n 1 openhands_versions.txt | awk '{print $2}' | tr -d '()')
+          # Ensure requirements.txt ends with newline before appending
+          if [ -f requirements.txt ] && [ -s requirements.txt ]; then
+            sed -i -e '$a\' requirements.txt
+          fi
           echo "openhands-ai==${OPENHANDS_VERSION}" >> requirements.txt
           cat requirements.txt
 
@@ -112,6 +120,7 @@ jobs:
           LLM_MODEL: ${{ secrets.LLM_MODEL || inputs.LLM_MODEL }}
           LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
           LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          LLM_API_VERSION: ${{ inputs.LLM_API_VERSION }}
           PAT_TOKEN: ${{ secrets.PAT_TOKEN }}
           PAT_USERNAME: ${{ secrets.PAT_USERNAME }}
           GITHUB_TOKEN: ${{ github.token }}
@@ -168,7 +177,7 @@ jobs:
           echo "SANDBOX_ENV_BASE_CONTAINER_IMAGE=${{ inputs.base_container_image }}" >> $GITHUB_ENV
 
           # Set branch variables
-          echo "TARGET_BRANCH=${{ inputs.target_branch }}" >> $GITHUB_ENV
+          echo "TARGET_BRANCH=${{ inputs.target_branch || 'main' }}" >> $GITHUB_ENV
 
       - name: Comment on issue with start message
         uses: actions/github-script@v7
@@ -226,6 +235,7 @@ jobs:
           LLM_MODEL: ${{ secrets.LLM_MODEL || inputs.LLM_MODEL }}
           LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
           LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          LLM_API_VERSION: ${{ inputs.LLM_API_VERSION }}
           PYTHONPATH: ""
         run: |
           cd /tmp && python -m openhands.resolver.resolve_issue \
@@ -261,11 +271,13 @@ jobs:
           LLM_MODEL: ${{ secrets.LLM_MODEL || inputs.LLM_MODEL }}
           LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
           LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          LLM_API_VERSION: ${{ inputs.LLM_API_VERSION }}
           PYTHONPATH: ""
         run: |
           if [ "${{ steps.check_result.outputs.RESOLUTION_SUCCESS }}" == "true" ]; then
             cd /tmp && python -m openhands.resolver.send_pull_request \
               --issue-number ${{ env.ISSUE_NUMBER }} \
+              --target-branch ${{ env.TARGET_BRANCH }} \
               --pr-type draft \
               --reviewer ${{ github.actor }} | tee pr_result.txt && \
               grep "draft created" pr_result.txt | sed 's/.*\///g' > pr_number.txt

.github/workflows/stale.yml

@@ -19,3 +19,4 @@ jobs:
           close-issue-message: 'This issue was closed because it has been stalled for over 30 days with no activity.'
           close-pr-message: 'This PR was closed because it has been stalled for over 30 days with no activity.'
           days-before-close: 7
+          operations-per-run: 150