Merge branch 'main' into enyst/delegation

.github/workflows/openhands-resolver.yml

@@ -184,6 +184,7 @@ jobs:
             });
 
       - name: Install OpenHands
+        id: install_openhands
         uses: actions/github-script@v7
         env:
           COMMENT_BODY: ${{ github.event.comment.body || '' }}
@@ -196,7 +197,6 @@ jobs:
             const reviewBody = process.env.REVIEW_BODY.trim();
             const labelName = process.env.LABEL_NAME.trim();
             const eventName = process.env.EVENT_NAME.trim();
-
             // Check conditions
             const isExperimentalLabel = labelName === "fix-me-experimental";
             const isIssueCommentExperimental =
@@ -205,6 +205,9 @@ jobs:
             const isReviewCommentExperimental =
               eventName === "pull_request_review" && reviewBody.includes("@openhands-agent-exp");
 
+            // Set output variable
+            core.setOutput('isExperimental', isExperimentalLabel || isIssueCommentExperimental || isReviewCommentExperimental);
+
             // Perform package installation
             if (isExperimentalLabel || isIssueCommentExperimental || isReviewCommentExperimental) {
               console.log("Installing experimental OpenHands...");
@@ -230,7 +233,8 @@ jobs:
             --issue-number ${{ env.ISSUE_NUMBER }} \
             --issue-type ${{ env.ISSUE_TYPE }} \
             --max-iterations ${{ env.MAX_ITERATIONS }} \
-            --comment-id ${{ env.COMMENT_ID }}
+            --comment-id ${{ env.COMMENT_ID }} \
+            --is-experimental ${{ steps.install_openhands.outputs.isExperimental }}
 
       - name: Check resolution result
         id: check_result

compose.yml → docker-compose.yml

@@ -1,4 +1,4 @@
-#
+
 services:
   openhands:
     build:
@@ -7,15 +7,16 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.19-nikolaik}
-      - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik}
+      #- SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234} # enable this only if you want a specific non-root sandbox user but you will have to manually adjust permissions of openhands-state for this user
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:
       - "3000:3000"
     extra_hosts:
       - "host.docker.internal:host-gateway"
     volumes:
       - /var/run/docker.sock:/var/run/docker.sock
+      - ~/.openhands-state:/.openhands-state
       - ${WORKSPACE_BASE:-$PWD/workspace}:/opt/workspace_base
     pull_policy: build
     stdin_open: true

evaluation/benchmarks/the_agent_company/run_infer.py

@@ -80,7 +80,7 @@ def load_dependencies(runtime: Runtime) -> List[str]:
 def init_task_env(runtime: Runtime, hostname: str, env_llm_config: LLMConfig):
     command = (
         f'SERVER_HOSTNAME={hostname} '
-        f'LITELLM_API_KEY={env_llm_config.api_key} '
+        f'LITELLM_API_KEY={env_llm_config.api_key.get_secret_value() if env_llm_config.api_key else None} '
         f'LITELLM_BASE_URL={env_llm_config.base_url} '
         f'LITELLM_MODEL={env_llm_config.model} '
         'bash /utils/init.sh'
@@ -165,7 +165,7 @@ def run_evaluator(
     runtime: Runtime, env_llm_config: LLMConfig, trajectory_path: str, result_path: str
 ):
     command = (
-        f'LITELLM_API_KEY={env_llm_config.api_key} '
+        f'LITELLM_API_KEY={env_llm_config.api_key.get_secret_value() if env_llm_config.api_key else None} '
         f'LITELLM_BASE_URL={env_llm_config.base_url} '
         f'LITELLM_MODEL={env_llm_config.model} '
         f"DECRYPTION_KEY='theagentcompany is all you need' "  # Hardcoded Key

evaluation/utils/shared.py

@@ -52,30 +52,6 @@ class EvalMetadata(BaseModel):
     details: dict[str, Any] | None = None
     condenser_config: CondenserConfig | None = None
 
-    def model_dump(self, *args, **kwargs):
-        dumped_dict = super().model_dump(*args, **kwargs)
-        # avoid leaking sensitive information
-        dumped_dict['llm_config'] = self.llm_config.to_safe_dict()
-        if hasattr(self.condenser_config, 'llm_config'):
-            dumped_dict['condenser_config']['llm_config'] = (
-                self.condenser_config.llm_config.to_safe_dict()
-            )
-
-        return dumped_dict
-
-    def model_dump_json(self, *args, **kwargs):
-        dumped = super().model_dump_json(*args, **kwargs)
-        dumped_dict = json.loads(dumped)
-        # avoid leaking sensitive information
-        dumped_dict['llm_config'] = self.llm_config.to_safe_dict()
-        if hasattr(self.condenser_config, 'llm_config'):
-            dumped_dict['condenser_config']['llm_config'] = (
-                self.condenser_config.llm_config.to_safe_dict()
-            )
-
-        logger.debug(f'Dumped metadata: {dumped_dict}')
-        return json.dumps(dumped_dict)
-
 
 class EvalOutput(BaseModel):
     # NOTE: User-specified
@@ -98,23 +74,6 @@ class EvalOutput(BaseModel):
     # Optionally save the input test instance
     instance: dict[str, Any] | None = None
 
-    def model_dump(self, *args, **kwargs):
-        dumped_dict = super().model_dump(*args, **kwargs)
-        # Remove None values
-        dumped_dict = {k: v for k, v in dumped_dict.items() if v is not None}
-        # Apply custom serialization for metadata (to avoid leaking sensitive information)
-        if self.metadata is not None:
-            dumped_dict['metadata'] = self.metadata.model_dump()
-        return dumped_dict
-
-    def model_dump_json(self, *args, **kwargs):
-        dumped = super().model_dump_json(*args, **kwargs)
-        dumped_dict = json.loads(dumped)
-        # Apply custom serialization for metadata (to avoid leaking sensitive information)
-        if 'metadata' in dumped_dict:
-            dumped_dict['metadata'] = json.loads(self.metadata.model_dump_json())
-        return json.dumps(dumped_dict)
-
 
 class EvalException(Exception):
     pass
@@ -314,7 +273,7 @@ def update_progress(
     logger.info(
         f'Finished evaluation for instance {result.instance_id}: {str(result.test_result)[:300]}...\n'
     )
-    output_fp.write(json.dumps(result.model_dump()) + '\n')
+    output_fp.write(result.model_dump_json() + '\n')
     output_fp.flush()
 
 

frontend/__tests__/components/features/sidebar/sidebar.test.tsx

@@ -1,10 +1,12 @@
-import { screen } from "@testing-library/react";
+import { screen, within } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
-import { describe, expect, it } from "vitest";
+import { afterEach, describe, expect, it, vi } from "vitest";
 import { renderWithProviders } from "test-utils";
 import { createRoutesStub } from "react-router";
 import { Sidebar } from "#/components/features/sidebar/sidebar";
 import { MULTI_CONVERSATION_UI } from "#/utils/feature-flags";
+import OpenHands from "#/api/open-hands";
+import { MOCK_USER_PREFERENCES } from "#/mocks/handlers";
 
 const renderSidebar = () => {
   const RouterStub = createRoutesStub([
@@ -43,4 +45,101 @@ describe("Sidebar", () => {
       ).not.toBeInTheDocument();
     },
   );
+
+  describe("Settings", () => {
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+
+    afterEach(() => {
+      vi.clearAllMocks();
+    });
+
+    it("should fetch settings data on mount", () => {
+      renderSidebar();
+      expect(getSettingsSpy).toHaveBeenCalledOnce();
+    });
+
+    it("should send all settings data when saving AI configuration", async () => {
+      const user = userEvent.setup();
+      renderSidebar();
+
+      const settingsButton = screen.getByTestId("settings-button");
+      await user.click(settingsButton);
+
+      const settingsModal = screen.getByTestId("ai-config-modal");
+      const saveButton = within(settingsModal).getByTestId(
+        "save-settings-button",
+      );
+      await user.click(saveButton);
+
+      expect(saveSettingsSpy).toHaveBeenCalledWith({
+        ...MOCK_USER_PREFERENCES.settings,
+        // the actual values are falsey (null or "") but we're checking for undefined
+        llm_api_key: undefined,
+        llm_base_url: undefined,
+        security_analyzer: undefined,
+      });
+    });
+
+    it("should send all settings data when saving account settings", async () => {
+      const user = userEvent.setup();
+      renderSidebar();
+
+      const userAvatar = screen.getByTestId("user-avatar");
+      await user.click(userAvatar);
+
+      const menu = screen.getByTestId("account-settings-context-menu");
+      const accountSettingsButton = within(menu).getByTestId(
+        "account-settings-button",
+      );
+      await user.click(accountSettingsButton);
+
+      const accountSettingsModal = screen.getByTestId("account-settings-form");
+      const saveButton =
+        within(accountSettingsModal).getByTestId("save-settings");
+      await user.click(saveButton);
+
+      expect(saveSettingsSpy).toHaveBeenCalledWith({
+        ...MOCK_USER_PREFERENCES.settings,
+        llm_api_key: undefined, // null or undefined
+      });
+    });
+
+    it("should not reset AI configuration when saving account settings", async () => {
+      const user = userEvent.setup();
+      renderSidebar();
+
+      const userAvatar = screen.getByTestId("user-avatar");
+      await user.click(userAvatar);
+
+      const menu = screen.getByTestId("account-settings-context-menu");
+      const accountSettingsButton = within(menu).getByTestId(
+        "account-settings-button",
+      );
+      await user.click(accountSettingsButton);
+
+      const accountSettingsModal = screen.getByTestId("account-settings-form");
+
+      const languageInput =
+        within(accountSettingsModal).getByLabelText(/language/i);
+      await user.click(languageInput);
+
+      const norskOption = screen.getByText(/norsk/i);
+      await user.click(norskOption);
+
+      const tokenInput =
+        within(accountSettingsModal).getByLabelText(/github token/i);
+      await user.type(tokenInput, "new-token");
+
+      const saveButton =
+        within(accountSettingsModal).getByTestId("save-settings");
+      await user.click(saveButton);
+
+      expect(saveSettingsSpy).toHaveBeenCalledWith({
+        ...MOCK_USER_PREFERENCES.settings,
+        language: "no",
+        llm_api_key: undefined, // null or undefined
+      });
+    });
+  });
 });