Merge branch 'main' into fix-httpx-example

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/configuration-options.md

@@ -373,7 +373,7 @@ Les options de configuration de l'agent sont définies dans les sections `[agent
   - Description : Si l'éditeur LLM est activé dans l'espace d'action (fonctionne uniquement avec l'appel de fonction)
 
 **Utilisation du micro-agent**
-- `use_microagents`
+- `enable_prompt_extensions`
   - Type : `bool`
   - Valeur par défaut : `true`
   - Description : Indique si l'utilisation des micro-agents est activée ou non

evaluation/benchmarks/miniwob/README.md

@@ -8,6 +8,9 @@ Please follow instruction [here](../../README.md#setup) to setup your local deve
 
 ## Test if your environment works
 
+Follow the instructions here https://miniwob.farama.org/content/getting_started/ & https://miniwob.farama.org/content/viewing/
+to set up MiniWoB server in your local environment at http://localhost:8080/miniwob/
+
 Access with browser the above MiniWoB URLs and see if they load correctly.
 
 ## Run Evaluation

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -71,7 +71,7 @@ def process_git_patch(patch):
     return patch
 
 
-def get_config(instance: pd.Series) -> AppConfig:
+def get_config(metadata: EvalMetadata, instance: pd.Series) -> AppConfig:
     # We use a different instance image for the each instance of swe-bench eval
     base_container_image = get_instance_docker_image(instance['instance_id'])
     logger.info(
@@ -132,7 +132,7 @@ def process_instance(
     else:
         logger.info(f'Starting evaluation for instance {instance.instance_id}.')
 
-    config = get_config(instance)
+    config = get_config(metadata, instance)
     instance_id = instance.instance_id
     model_patch = instance['model_patch']
     test_spec: TestSpec = instance['test_spec']

evaluation/benchmarks/swe_bench/run_infer.py

@@ -158,6 +158,7 @@ def get_config(
         codeact_enable_browsing=RUN_WITH_BROWSING,
         codeact_enable_llm_editor=False,
         condenser=metadata.condenser_config,
+        enable_prompt_extensions=False,
     )
     config.set_agent_config(agent_config)
     return config

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

@@ -156,7 +156,7 @@ describe("Sidebar", () => {
       await user.click(advancedOptionsSwitch);
 
       const apiKeyInput = within(settingsModal).getByLabelText(/API\$KEY/i);
-      await user.type(apiKeyInput, "SET");
+      await user.type(apiKeyInput, "**********");
 
       const saveButton = within(settingsModal).getByTestId(
         "save-settings-button",

frontend/package.json

@@ -79,7 +79,7 @@
     "@playwright/test": "^1.49.1",
     "@react-router/dev": "^7.1.2",
     "@tailwindcss/typography": "^0.5.16",
-    "@tanstack/eslint-plugin-query": "^5.62.16",
+    "@tanstack/eslint-plugin-query": "^5.64.2",
     "@testing-library/jest-dom": "^6.6.1",
     "@testing-library/react": "^16.2.0",
     "@testing-library/user-event": "^14.6.0",
@@ -100,7 +100,7 @@
     "eslint-config-prettier": "^10.0.1",
     "eslint-plugin-import": "^2.29.1",
     "eslint-plugin-jsx-a11y": "^6.10.2",
-    "eslint-plugin-prettier": "^5.2.2",
+    "eslint-plugin-prettier": "^5.2.3",
     "eslint-plugin-react": "^7.37.4",
     "eslint-plugin-react-hooks": "^4.6.2",
     "husky": "^9.1.6",

frontend/src/api/open-hands.ts

@@ -10,6 +10,7 @@ import {
   AuthenticateResponse,
   Conversation,
   ResultSet,
+  GetTrajectoryResponse,
 } from "./open-hands.types";
 import { openHands } from "./open-hands-axios";
 import { ApiSettings } from "#/services/settings";
@@ -354,6 +355,15 @@ class OpenHands {
 
     return response.data.items;
   }
+
+  static async getTrajectory(
+    conversationId: string,
+  ): Promise<GetTrajectoryResponse> {
+    const { data } = await openHands.get<GetTrajectoryResponse>(
+      `/api/conversations/${conversationId}/trajectory`,
+    );
+    return data;
+  }
 }
 
 export default OpenHands;

frontend/src/api/open-hands.types.ts

@@ -55,6 +55,11 @@ export interface GetVSCodeUrlResponse {
   error?: string;
 }
 
+export interface GetTrajectoryResponse {
+  trajectory: unknown[] | null;
+  error?: string;
+}
+
 export interface AuthenticateResponse {
   message?: string;
   error?: string;

frontend/src/components/features/chat/chat-interface.tsx

@@ -1,8 +1,11 @@
 import { useDispatch, useSelector } from "react-redux";
+import toast from "react-hot-toast";
 import React from "react";
 import posthog from "posthog-js";
+import { useParams } from "react-router";
 import { convertImageToBase64 } from "#/utils/convert-image-to-base-64";
 import { FeedbackActions } from "../feedback/feedback-actions";
+import { ExportActions } from "../export/export-actions";
 import { createChatMessage } from "#/services/chat-service";
 import { InteractiveChatBox } from "./interactive-chat-box";
 import { addUserMessage } from "#/state/chat-slice";
@@ -19,6 +22,8 @@ import { ActionSuggestions } from "./action-suggestions";
 import { ContinueButton } from "#/components/shared/buttons/continue-button";
 import { ScrollToBottomButton } from "#/components/shared/buttons/scroll-to-bottom-button";
 import { LoadingSpinner } from "#/components/shared/loading-spinner";
+import { useGetTrajectory } from "#/hooks/mutation/use-get-trajectory";
+import { downloadTrajectory } from "#/utils/download-files";
 
 function getEntryPoint(
   hasRepository: boolean | null,
@@ -47,6 +52,8 @@ export function ChatInterface() {
   const { selectedRepository, importedProjectZip } = useSelector(
     (state: RootState) => state.initialQuery,
   );
+  const params = useParams();
+  const { mutate: getTrajectory } = useGetTrajectory();
 
   const handleSendMessage = async (content: string, files: File[]) => {
     if (messages.length === 0) {
@@ -90,6 +97,25 @@ export function ChatInterface() {
     setFeedbackPolarity(polarity);
   };
 
+  const onClickExportTrajectoryButton = () => {
+    if (!params.conversationId) {
+      toast.error("ConversationId unknown, cannot download trajectory");
+      return;
+    }
+
+    getTrajectory(params.conversationId, {
+      onSuccess: async (data) => {
+        await downloadTrajectory(
+          params.conversationId ?? "unknown",
+          data.trajectory,
+        );
+      },
+      onError: (error) => {
+        toast.error(error.message);
+      },
+    });
+  };
+
   const isWaitingForUserInput =
     curAgentState === AgentState.AWAITING_USER_INPUT ||
     curAgentState === AgentState.FINISHED;
@@ -137,6 +163,9 @@ export function ChatInterface() {
               onClickShareFeedbackActionButton("negative")
             }
           />
+          <ExportActions
+            onExportTrajectory={() => onClickExportTrajectoryButton()}
+          />
 
           <div className="absolute left-1/2 transform -translate-x-1/2 bottom-0">
             {messages.length > 2 &&

frontend/src/components/features/export/export-actions.tsx

@@ -0,0 +1,17 @@
+import ExportIcon from "#/icons/export.svg?react";
+import { ExportActionButton } from "#/components/shared/buttons/export-action-button";
+
+interface ExportActionsProps {
+  onExportTrajectory: () => void;
+}
+
+export function ExportActions({ onExportTrajectory }: ExportActionsProps) {
+  return (
+    <div data-testid="export-actions" className="flex gap-1">
+      <ExportActionButton
+        onClick={onExportTrajectory}
+        icon={<ExportIcon width={15} height={15} />}
+      />
+    </div>
+  );
+}

frontend/src/components/shared/buttons/export-action-button.tsx

@@ -0,0 +1,17 @@
+interface ExportActionButtonProps {
+  onClick: () => void;
+  icon: React.ReactNode;
+}
+
+export function ExportActionButton({ onClick, icon }: ExportActionButtonProps) {
+  return (
+    <button
+      type="button"
+      onClick={onClick}
+      className="button-base p-1 hover:bg-neutral-500"
+      title="Export trajectory"
+    >
+      {icon}
+    </button>
+  );
+}

frontend/src/components/shared/modals/settings/settings-form.tsx

@@ -171,7 +171,7 @@ export function SettingsForm({
 
           <APIKeyInput
             isDisabled={!!disabled}
-            isSet={settings.LLM_API_KEY === "SET"}
+            isSet={settings.LLM_API_KEY === "**********"}
           />
 
           {showAdvancedOptions && (

frontend/src/context/settings-context.tsx

@@ -34,7 +34,7 @@ export function SettingsProvider({ children }: SettingsProviderProps) {
       ...newSettings,
     };
 
-    if (updatedSettings.LLM_API_KEY === "SET") {
+    if (updatedSettings.LLM_API_KEY === "**********") {
       delete updatedSettings.LLM_API_KEY;
     }
 

frontend/src/hooks/mutation/use-get-trajectory.ts

@@ -0,0 +1,7 @@
+import { useMutation } from "@tanstack/react-query";
+import OpenHands from "#/api/open-hands";
+
+export const useGetTrajectory = () =>
+  useMutation({
+    mutationFn: (cid: string) => OpenHands.getTrajectory(cid),
+  });

frontend/src/types/file-system.d.ts

@@ -26,6 +26,18 @@ interface FileSystemDirectoryHandle {
   ): Promise<FileSystemFileHandle>;
 }
 
+interface SaveFilePickerOptions {
+  suggestedName?: string;
+  types?: Array<{
+    description?: string;
+    accept: Record<string, string[]>;
+  }>;
+  excludeAcceptAllOption?: boolean;
+}
+
 interface Window {
   showDirectoryPicker(): Promise<FileSystemDirectoryHandle>;
+  showSaveFilePicker(
+    options?: SaveFilePickerOptions,
+  ): Promise<FileSystemFileHandle>;
 }

frontend/src/utils/download-files.ts

@@ -22,6 +22,13 @@ function isFileSystemAccessSupported(): boolean {
   return "showDirectoryPicker" in window;
 }
 
+/**
+ * Checks if the Save File Picker API is supported
+ */
+function isSaveFilePickerSupported(): boolean {
+  return "showSaveFilePicker" in window;
+}
+
 /**
  * Creates subdirectories and returns the final directory handle
  */
@@ -162,6 +169,39 @@ async function processBatch(
   };
 }
 
+export async function downloadTrajectory(
+  conversationId: string,
+  data: unknown[] | null,
+): Promise<void> {
+  try {
+    if (!isSaveFilePickerSupported()) {
+      throw new Error(
+        "Your browser doesn't support downloading folders. Please use Chrome, Edge, or another browser that supports the File System Access API.",
+      );
+    }
+    const options = {
+      suggestedName: `trajectory-${conversationId}.json`,
+      types: [
+        {
+          description: "JSON File",
+          accept: {
+            "application/json": [".json"],
+          },
+        },
+      ],
+    };
+
+    const handle = await window.showSaveFilePicker(options);
+    const writable = await handle.createWritable();
+    await writable.write(JSON.stringify(data, null, 2));
+    await writable.close();
+  } catch (error) {
+    throw new Error(
+      `Failed to download file: ${error instanceof Error ? error.message : String(error)}`,
+    );
+  }
+}
+
 /**
  * Downloads files from the workspace one by one
  * @param initialPath Initial path to start downloading from. If not provided, downloads from root

openhands/agenthub/codeact_agent/codeact_agent.py

@@ -277,16 +277,11 @@ def get_observation_message(
             # if it doesn't have tool call metadata, it was triggered by a user action
             if obs.tool_call_metadata is None:
                 text = truncate_content(
-                    f'\nObserved result of command executed by user:\n{obs.content}',
+                    f'\nObserved result of command executed by user:\n{obs.to_agent_observation()}',
                     max_message_chars,
                 )
             else:
-                text = truncate_content(
-                    obs.content
-                    + f'\n[Python Interpreter: {obs.metadata.py_interpreter_path}]',
-                    max_message_chars,
-                )
-            text += f'\n[Command finished with exit code {obs.exit_code}]'
+                text = truncate_content(obs.to_agent_observation(), max_message_chars)
             message = Message(role='user', content=[TextContent(text=text)])
         elif isinstance(obs, IPythonRunCellObservation):
             text = obs.content

openhands/agenthub/codeact_agent/function_calling.py

@@ -80,7 +80,7 @@
     ),
 )
 
-_FILE_EDIT_DESCRIPTION = """Edit a file.
+_FILE_EDIT_DESCRIPTION = """Edit a file in plain-text format.
 * The assistant can edit files by specifying the file path and providing a draft of the new file content.
 * The draft content doesn't need to be exactly the same as the existing file; the assistant may skip unchanged lines using comments like `# unchanged` to indicate unchanged sections.
 * IMPORTANT: For large files (e.g., > 300 lines), specify the range of lines to edit using `start` and `end` (1-indexed, inclusive). The range should be smaller than 300 lines.
@@ -216,7 +216,7 @@ def __init__(self):
     ),
 )
 
-_STR_REPLACE_EDITOR_DESCRIPTION = """Custom editing tool for viewing, creating and editing files
+_STR_REPLACE_EDITOR_DESCRIPTION = """Custom editing tool for viewing, creating and editing files in plain-text format
 * State is persistent across command calls and discussions with the user
 * If `path` is a file, `view` displays the result of applying `cat -n`. If `path` is a directory, `view` lists non-hidden files and directories up to 2 levels deep
 * The `create` command cannot be used if the specified `path` already exists as a file