Try

.devcontainer/devcontainer.json

@@ -12,5 +12,4 @@
 		"ghcr.io/devcontainers/features/node:1": {},
 	},
 	"postCreateCommand": ".devcontainer/setup.sh",
-	"runArgs": ["--network=host"],
 }

.github/CODEOWNERS

@@ -5,7 +5,7 @@
 /frontend/ @rbren @amanape
 
 # Evaluation code owners
-/evaluation/ @xingyaoww @neubig
+/evaluation/ @xingyaoww @neubig 
 
 # Documentation code owners
 /docs/ @mamoodi

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -33,7 +33,6 @@ body:
         - Docker command in README
         - GitHub resolver
         - Development workflow
-        - CLI
         - app.all-hands.dev
         - Other
       default: 0

.github/dependabot.yml

@@ -16,6 +16,7 @@ updates:
       mcp-packages:
         patterns:
           - "mcp"
+          - "mcpm"
       security-all:
         applies-to: "security-updates"
         patterns:

.github/workflows/ghcr-build.yml

@@ -313,8 +313,6 @@ jobs:
           TEST_IN_CI=true \
           RUN_AS_OPENHANDS=false \
           poetry run pytest -n 7 -raRs --reruns 2 --reruns-delay 5 -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py --durations=10
-        env:
-          DEBUG: "1"
 
   # Run unit tests with the Docker runtime Docker images as openhands user
   test_runtime_oh:
@@ -380,8 +378,6 @@ jobs:
           TEST_IN_CI=true \
           RUN_AS_OPENHANDS=true \
           poetry run pytest -n 7 -raRs --reruns 2 --reruns-delay 5 -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py --durations=10
-        env:
-          DEBUG: "1"
 
   # The two following jobs (named identically) are to check whether all the runtime tests have passed as the
   # "All Runtime Tests Passed" is a required job for PRs to merge

.github/workflows/py-unit-tests.yml

@@ -74,11 +74,5 @@ jobs:
         run: poetry install --with dev,test,runtime
       - name: Run Windows unit tests
         run: poetry run pytest -svv tests/unit/test_windows_bash.py
-        env:
-          DEBUG: "1"
       - name: Run Windows runtime tests with LocalRuntime
         run: $env:TEST_RUNTIME="local"; poetry run pytest -svv tests/runtime/test_bash.py
-        env:
-          TEST_RUNTIME: local
-          DEBUG: "1"
-

docs/docs.json

@@ -38,11 +38,12 @@
                 ]
               },
               "usage/cloud/cloud-ui",
+              "usage/cloud/cloud-issue-resolver",
               "usage/cloud/cloud-api"
             ]
           },
           {
-            "group": "Running OpenHands on Your Own",
+            "group": "Running OpenHands Locally",
             "pages": [
               "usage/local-setup",
               "usage/how-to/gui-mode",

docs/usage/cloud/cloud-issue-resolver.mdx

@@ -0,0 +1,33 @@
+---
+title: Cloud Issue Resolver
+description: The Cloud Issue Resolver automates code fixes and provides intelligent assistance for your repositories on GitHub.
+---
+
+## Setup
+
+The Cloud Issue Resolver is available automatically when you grant OpenHands Cloud repository access:
+- [GitHub repository access](./github-installation#adding-repository-access)
+
+## Usage
+
+After granting OpenHands Cloud repository access, you can use the Cloud Issue Resolver on issues and pull requests in your repositories.
+
+### Working with Issues
+
+On your repository, label an issue with `openhands` or add a message starting with
+`@openhands`. OpenHands will:
+1. Comment on the issue to let you know it is working on it
+   - You can click on the link to track the progress on OpenHands Cloud
+2. Open a pull request if it determines that the issue has been successfully resolved
+3. Comment on the issue with a summary of the performed tasks and a link to the PR
+
+### Working with Pull Requests
+
+To get OpenHands to work on pull requests, mention `@openhands` in comments to:
+- Ask questions
+- Request updates
+- Get code explanations
+
+OpenHands will:
+1. Comment to let you know it is working on it
+2. Perform the requested task

docs/usage/cloud/cloud-ui.mdx

@@ -1,36 +1,28 @@
 ---
 title: Cloud UI
-description: The Cloud UI provides a web interface for interacting with OpenHands. This page explains how to use the
- OpenHands Cloud UI.
+description: The Cloud UI provides a web interface for interacting with OpenHands AI. This page explains how to access and use the OpenHands Cloud UI.
 ---
 
-## Landing Page
 
-The landing page is where you can:
+## Accessing the UI
 
-- [Add GitHub repository access](/usage/cloud/github-installation#adding-github-repository-access) to OpenHands.
-- [Select a GitHub repo](/usage/cloud/github-installation#working-with-github-repos-in-openhands-cloud) or
-  [a GitLab repo](/usage/cloud/gitlab-installation#working-with-gitlab-repos-in-openhands-cloud) to start working on.
-- See `Suggested Tasks` for repositories that OpenHands has access to.
-- Launch an empty conversation using `Launch from Scratch`.
+The OpenHands Cloud UI can be accessed at [app.all-hands.dev](https://app.all-hands.dev). You'll need to sign in with your GitHub or GitLab account to access the interface.
 
-## Settings
-
-The Settings page allows you to:
-
-- [Configure GitHub repository access](/usage/cloud/github-installation#modifying-repository-access) for OpenHands.
-- Set application settings like your preferred language, notifications and other preferences.
-- Add credits to your account.
-- Generate custom secrets.
-- Create API keys to work with OpenHands programmatically.
 
 ## Key Features
 
-For an overview of the key features available inside a conversation, please refer to the [Key Features](../key-features)
-section of the documentation.
+For detailed information about the features available in the OpenHands Cloud UI, please refer to the [Key Features](../key-features) section of the documentation.
+
+## Settings
+
+The settings page allows you to:
+
+- Configure your account preferences.
+- Manage repository access.
+- Generate API keys for programmatic access.
+- Generate custom secrets for the agent.
 
 ## Next Steps
 
-- [Install GitHub Integration](/usage/cloud/github-installation) to use OpenHands with your GitHub repositories.
-- [Install GitLab Integration](/usage/cloud/gitlab-installation) to use OpenHands with your GitLab repositories.
-- [Use the Cloud API](/usage/cloud/cloud-api) to programmatically interact with OpenHands.
+- [Use the Cloud Issue Resolver](./cloud-issue-resolver) to automate code fixes and get assistance.
+- [Learn about the Cloud API](./cloud-api) for programmatic access.

docs/usage/cloud/github-installation.mdx

@@ -1,7 +1,7 @@
 ---
 title: GitHub Integration
 description: This guide walks you through the process of installing OpenHands Cloud for your GitHub repositories. Once
-  set up, it will allow OpenHands to work with your GitHub repository through the Cloud UI or straight from GitHub!
+  set up, it will allow OpenHands to work with your GitHub repository through the Cloud UI or straight from GitHub issues!
 ---
 
 ## Prerequisites
@@ -37,11 +37,11 @@ You can modify GitHub repository access at any time by:
 - Selecting `Add GitHub repos` on the landing page or
 - Visiting the Settings page and selecting `Configure GitHub Repositories` under the `Git` tab
 
-## Working With GitHub Repos in Openhands Cloud
+## Working With Github Repos in Openhands Cloud
 
 Once you've granted GitHub repository access, you can start working with your GitHub repository. Use the `select a repo`
 and `select a branch` dropdowns to select the appropriate repository and branch you'd like OpenHands to work on. Then
-click on `Launch` to start the conversation!
+click on `Launch` to start the session!
 
 ![Connect Repo](/static/img/connect-repo.png)
 
@@ -67,5 +67,5 @@ To get OpenHands to work on pull requests, mention `@openhands` in the comments
 
 ## Next Steps
 
-- [Learn about the Cloud UI](/usage/cloud/cloud-ui).
-- [Use the Cloud API](/usage/cloud/cloud-api) to programmatically interact with OpenHands.
+- [Access the Cloud UI](./cloud-ui) to interact with the web interface
+- [Use the Cloud API](./cloud-api) to programmatically interact with OpenHands

docs/usage/cloud/gitlab-installation.mdx

@@ -1,25 +1,23 @@
 ---
 title: GitLab Integration
-description: This guide walks you through the process of installing OpenHands Cloud for your GitLab repositories. Once
-  set up, it will allow OpenHands to work with your GitLab repository.
+description: This guide walks you through the process of installing and configuring OpenHands Cloud for your GitLab repositories.
 ---
 
 ## Prerequisites
 
-- Signed in to [OpenHands Cloud](https://app.all-hands.dev) with [a GitLab account](/usage/cloud/openhands-cloud).
+- A GitLab account
+- Access to OpenHands Cloud
 
-## Adding GitLab Repository Access
+## Installation Steps
 
-Upon signing into OpenHands Cloud with a GitLab account, OpenHands will have access to your repositories.
+1. Log in to [OpenHands Cloud](https://app.all-hands.dev)
+2. If you haven't connected your GitLab account yet:
+   - Click on `Log in with GitLab`
+   - Authorize the OpenHands application
 
-## Working With GitLab Repos in Openhands Cloud
 
-After signing in with a Gitlab account, use the `select a repo` and `select a branch` dropdowns to select the
-appropriate repository and branch you'd like OpenHands to work on. Then click on `Launch` to start the conversation!
-
-![Connect Repo](/static/img/connect-repo.png)
 
 ## Next Steps
 
-- [Learn about the Cloud UI](/usage/cloud/cloud-ui).
-- [Use the Cloud API](/usage/cloud/cloud-api) to programmatically interact with OpenHands.
+- [Access the Cloud UI](./cloud-ui) to interact with the web interface
+- [Use the Cloud API](./cloud-api) to programmatically interact with OpenHands

docs/usage/cloud/openhands-cloud.mdx

@@ -14,13 +14,13 @@ You'll be prompted to connect with your GitHub or GitLab account:
 2. Review the permissions requested by OpenHands and authorize the application.
    - OpenHands will require certain permissions from your account. To read more about these permissions,
      you can click the `Learn more` link on the authorization page.
-3. Review and accept the `terms of service` and select `Continue`.
 
 ## Next Steps
 
 Once you've connected your account, you can:
 
-- [Install GitHub Integration](/usage/cloud/github-installation) to use OpenHands with your GitHub repositories.
-- [Install GitLab Integration](/usage/cloud/gitlab-installation) to use OpenHands with your GitLab repositories.
-- [Learn about the Cloud UI](/usage/cloud/cloud-ui).
-- [Use the Cloud API](/usage/cloud/cloud-api) to programmatically interact with OpenHands.
+- [Install GitHub Integration](./github-installation) to use OpenHands with your GitHub repositories
+- [Install GitLab Integration](./gitlab-installation) to use OpenHands with your GitLab repositories
+- [Access the Cloud UI](./cloud-ui) to interact with the web interface
+- [Use the Cloud API](./cloud-api) to programmatically interact with OpenHands
+- [Set up the Cloud Issue Resolver](./cloud-issue-resolver) to automate code fixes and provide intelligent assistance

docs/usage/how-to/cli-mode.mdx

@@ -9,29 +9,16 @@ This mode is different from the [headless mode](./headless-mode), which is non-i
 
 ### Running with Python
 
-1. Install OpenHands using pip:
-
-```bash
-pip install openhands-ai
-```
-
+1. Ensure you have followed the [Development setup instructions](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
 2. Set your model, API key, and other preferences using environment variables or with the [`config.toml`](https://github.com/All-Hands-AI/OpenHands/blob/main/config.template.toml) file.
 3. Launch an interactive OpenHands conversation from the command line:
 
 ```bash
-openhands
+poetry run python -m openhands.cli.main
 ```
 
 This command opens an interactive prompt where you can type tasks or commands and get responses from OpenHands.
 
-#### For Developers
-
-If you have cloned the repository, you can run the CLI directly using Poetry:
-
-```bash
-poetry run python -m openhands.cli.main
-```
-
 ### Running with Docker
 
 1. Set the following environment variables in your terminal:

docs/usage/how-to/custom-sandbox-guide.mdx

@@ -46,7 +46,7 @@ This will produce a new image called `custom-image`, which will be available in
 
 ## Using the Docker Command
 
-When running OpenHands using [the docker command](/usage/local-setup#start-the-app), replace
+When running OpenHands using [the docker command](/usage/installation#start-the-app), replace
 `-e SANDBOX_RUNTIME_CONTAINER_IMAGE=...` with `-e SANDBOX_BASE_CONTAINER_IMAGE=<custom image name>`:
 
 ```commandline

docs/usage/how-to/github-action.mdx

@@ -48,6 +48,6 @@ The customization options you can set are:
 | `LLM_MODEL`                      | Variable | Set the LLM to use with OpenHands                                                                   | `LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"` |
 | `OPENHANDS_MAX_ITER`             | Variable | Set max limit for agent iterations                                                                  | `OPENHANDS_MAX_ITER=10`                            |
 | `OPENHANDS_MACRO`                | Variable | Customize default macro for invoking the resolver                                                   | `OPENHANDS_MACRO=@resolveit`                       |
-| `OPENHANDS_BASE_CONTAINER_IMAGE` | Variable | Custom Sandbox ([learn more](/usage/how-to/custom-sandbox-guide))                                   | `OPENHANDS_BASE_CONTAINER_IMAGE="custom_image"`    |
+| `OPENHANDS_BASE_CONTAINER_IMAGE` | Variable | Custom Sandbox ([learn more](https://docs.all-hands.dev/modules/usage/how-to/custom-sandbox-guide)) | `OPENHANDS_BASE_CONTAINER_IMAGE="custom_image"`    |
 | `TARGET_BRANCH`                  | Variable | Merge to branch other than `main`                                                                   | `TARGET_BRANCH="dev"`                              |
 | `TARGET_RUNNER`                  | Variable | Target runner to execute the agent workflow (default ubuntu-latest)                                 | `TARGET_RUNNER="custom-runner"`                    |

docs/usage/installation.mdx

@@ -16,4 +16,4 @@ For more information see [getting started with OpenHands Cloud.](/usage/cloud/op
 
 Run OpenHands on your local system and bring your own LLM and API key.
 
-For more information see [running OpenHands on your own.](/usage/local-setup)
+For more information see [running OpenHands locally.](/usage/local-setup)

docs/usage/llms/local-llms.mdx

@@ -48,7 +48,7 @@ We recommend using [LMStudio](https://lmstudio.ai/) for serving these models loc
 
 ### Start OpenHands with locally served model
 
-Check [the installation guide](/usage/local-setup) to make sure you have all the prerequisites for running OpenHands.
+Check [the installation guide](https://docs.all-hands.dev/modules/usage/installation) to make sure you have all the prerequisites for running OpenHands.
 
 ```bash
 export LMSTUDIO_MODEL_NAME="imported-models/uncategorized/devstralq4_k_m.gguf" # <- Replace this with the model name you copied from LMStudio

docs/usage/local-setup.mdx

@@ -109,14 +109,6 @@ OpenHands requires an API key to access most language models. Here's how to get
 
 </Accordion>
 
-<Accordion title="Google (Gemini)">
-
-1. Create a Google account if you don't already have one.
-2. [Generate an API key](https://aistudio.google.com/apikey).
-3. [Set up billing](https://aistudio.google.com/usage?tab=billing).
-
-</Accordion>
-
 </AccordionGroup>
 
 Consider setting usage limits to control costs.

docs/usage/prompting/microagents-overview.mdx

@@ -11,7 +11,7 @@ Currently OpenHands supports the following types of microagents:
 - [Keyword-Triggered Microagents](./microagents-keyword): Guidelines activated by specific keywords in prompts.
 
 To customize OpenHands' behavior, create a .openhands/microagents/ directory in the root of your repository and
-add `<microagent_name>.md` files inside. For repository-specific guidelines, you can ask OpenHands to analyze your repository and create a comprehensive `repo.md` file (see [General Microagents](./microagents-repo) for details).
+add `<microagent_name>.md` files inside.
 
 <Note>
 Loaded microagents take up space in the context window.

docs/usage/prompting/microagents-repo.mdx

@@ -17,45 +17,13 @@ Frontmatter should be enclosed in triple dashes (---) and may include the follow
 |-----------|-----------------------------------------|----------|----------------|
 | `agent`   | The agent this microagent applies to    | No       | 'CodeActAgent' |
 
-## Creating a Comprehensive Repository Agent
-
-To create an effective repository agent, you can ask OpenHands to analyze your repository with a prompt like:
+## Example
 
+General microagent file example located at `.openhands/microagents/repo.md`:
 ```
-Please browse the repository, look at the documentation and relevant code, and understand the purpose of this repository.
-
-Specifically, I want you to create a `.openhands/microagents/repo.md` file. This file should contain succinct information that summarizes:
-1. The purpose of this repository
-2. The general setup of this repo
-3. A brief description of the structure of this repo
-
-Read all the GitHub workflows under .github/ of the repository (if this folder exists) to understand the CI checks (e.g., linter, pre-commit), and include those in the repo.md file.
-```
-
-This approach helps OpenHands capture repository context efficiently, reducing the need for repeated searches during conversations and ensuring more accurate solutions.
-
-## Example Content
-
-A comprehensive repository agent file (`.openhands/microagents/repo.md`) should include:
-
-```
-# Repository Purpose
 This project is a TODO application that allows users to track TODO items.
 
-# Setup Instructions
 To set it up, you can run `npm run build`.
-
-# Repository Structure
-- `/src`: Core application code
-- `/tests`: Test suite
-- `/docs`: Documentation
-- `/.github`: CI/CD workflows
-
-# CI/CD Workflows
-- `lint.yml`: Runs ESLint on all JavaScript files
-- `test.yml`: Runs the test suite on pull requests
-
-# Development Guidelines
 Always make sure the tests are passing before committing changes. You can run the tests by running `npm run test`.
 ```
 

evaluation/README.md

@@ -71,6 +71,7 @@ EVAL_CONDENSER=summarizer_for_eval \
 The name is up to you, but should match a name defined in your `config.toml` file. The last argument in the command specifies the condenser configuration to use. In this case, `summarizer_for_eval` is used, which refers to the LLM-based summarizing condenser as defined above.
 
 If no condenser configuration is specified, the 'noop' condenser will be used by default, which keeps the full conversation history.
+```
 
 For other configurations specific to evaluation, such as `save_trajectory_path`, these are typically set in the `get_config` function of the respective `run_infer.py` file for each benchmark.
 

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

@@ -1,60 +1,5 @@
-import axios, { AxiosError, AxiosResponse } from "axios";
+import axios from "axios";
 
 export const openHands = axios.create({
   baseURL: `${window.location.protocol}//${import.meta.env.VITE_BACKEND_BASE_URL || window?.location.host}`,
 });
-
-// Helper function to check if a response contains an email verification error
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-const checkForEmailVerificationError = (data: any): boolean => {
-  const EMAIL_NOT_VERIFIED = "EmailNotVerifiedError";
-
-  if (typeof data === "string") {
-    return data.includes(EMAIL_NOT_VERIFIED);
-  }
-
-  if (typeof data === "object" && data !== null) {
-    if ("message" in data) {
-      const { message } = data;
-      if (typeof message === "string") {
-        return message.includes(EMAIL_NOT_VERIFIED);
-      }
-      if (Array.isArray(message)) {
-        return message.some(
-          (msg) => typeof msg === "string" && msg.includes(EMAIL_NOT_VERIFIED),
-        );
-      }
-    }
-
-    // Search any values in object in case message key is different
-    return Object.values(data).some(
-      (value) =>
-        (typeof value === "string" && value.includes(EMAIL_NOT_VERIFIED)) ||
-        (Array.isArray(value) &&
-          value.some(
-            (v) => typeof v === "string" && v.includes(EMAIL_NOT_VERIFIED),
-          )),
-    );
-  }
-
-  return false;
-};
-
-// Set up the global interceptor
-openHands.interceptors.response.use(
-  (response: AxiosResponse) => response,
-  (error: AxiosError) => {
-    // Check if it's a 403 error with the email verification message
-    if (
-      error.response?.status === 403 &&
-      checkForEmailVerificationError(error.response?.data)
-    ) {
-      if (window.location.pathname !== "/settings/user") {
-        window.location.reload();
-      }
-    }
-
-    // Continue with the error for other error handlers
-    return Promise.reject(error);
-  },
-);

frontend/src/api/open-hands.ts

@@ -236,26 +236,6 @@ class OpenHands {
     return data;
   }
 
-  static async startConversation(
-    conversationId: string,
-  ): Promise<Conversation | null> {
-    const { data } = await openHands.post<Conversation | null>(
-      `/api/conversations/${conversationId}/start`,
-    );
-
-    return data;
-  }
-
-  static async stopConversation(
-    conversationId: string,
-  ): Promise<Conversation | null> {
-    const { data } = await openHands.post<Conversation | null>(
-      `/api/conversations/${conversationId}/stop`,
-    );
-
-    return data;
-  }
-
   /**
    * Get the settings from the server or use the default settings if not found
    */

frontend/src/components/features/controls/agent-status-bar.tsx

@@ -84,7 +84,7 @@ export function AgentStatusBar() {
       setStatusMessage(t(I18nKey.STATUS$STARTING_RUNTIME));
       setIndicatorColor(IndicatorColor.RED);
     } else if (status === WsClientProviderStatus.DISCONNECTED) {
-      setStatusMessage(t(I18nKey.STATUS$WEBSOCKET_CLOSED));
+      setStatusMessage(t(I18nKey.STATUS$CONNECTED)); // Using STATUS$CONNECTED instead of STATUS$CONNECTING
       setIndicatorColor(IndicatorColor.RED);
     } else {
       setStatusMessage(AGENT_STATUS_MAP[curAgentState].message);

frontend/src/components/features/diff-viewer/file-diff-viewer.tsx

@@ -122,7 +122,7 @@ export function FileDiffViewer({ path, type }: FileDiffViewerProps) {
     modifiedEditor.onDidContentSizeChange(updateEditorHeight);
   };
 
-  const status = (type === "U" ? STATUS_MAP.A : STATUS_MAP[type]) || "?";
+  const status = type === "U" ? STATUS_MAP.A : STATUS_MAP[type];
 
   let statusIcon: React.ReactNode;
   if (typeof status === "string") {

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

@@ -96,7 +96,7 @@ export function SettingsForm({ settings, models, onClose }: SettingsFormProps) {
             testId="llm-api-key-help-anchor"
             text={t(I18nKey.SETTINGS$DONT_KNOW_API_KEY)}
             linkText={t(I18nKey.SETTINGS$CLICK_FOR_INSTRUCTIONS)}
-            href="https://docs.all-hands.dev/usage/local-setup#getting-an-api-key"
+            href="https://docs.all-hands.dev/usage/installation#getting-an-api-key"
           />
         </div>
 

frontend/src/context/ws-client-provider.tsx

@@ -150,8 +150,7 @@ export function WsClientProvider({
   const { providers } = useUserProviders();
 
   const messageRateHandler = useRate({ threshold: 250 });
-  const { data: conversation, refetch: refetchConversation } =
-    useActiveConversation();
+  const { data: conversation } = useActiveConversation();
 
   function send(event: Record<string, unknown>) {
     if (!sioRef.current) {
@@ -270,11 +269,14 @@ export function WsClientProvider({
     sio.io.opts.query.latest_event_id = lastEventRef.current?.id;
     updateStatusWhenErrorMessagePresent(data);
 
-    setErrorMessage(hasValidMessageProperty(data) ? data.message : "");
+    setErrorMessage(
+      hasValidMessageProperty(data)
+        ? data.message
+        : "The WebSocket connection was closed.",
+    );
   }
 
   function handleError(data: unknown) {
-    // set status
     setStatus(WsClientProviderStatus.DISCONNECTED);
     updateStatusWhenErrorMessagePresent(data);
 
@@ -283,9 +285,6 @@ export function WsClientProvider({
         ? data.message
         : "An unknown error occurred on the WebSocket connection.",
     );
-
-    // check if something went wrong with the conversation.
-    refetchConversation();
   }
 
   React.useEffect(() => {
@@ -301,19 +300,12 @@ export function WsClientProvider({
     if (!conversationId) {
       throw new Error("No conversation ID provided");
     }
-    if (
-      !conversation ||
-      ["STOPPED", "STARTING"].includes(conversation.status)
-    ) {
+    if (!conversation || conversation.status === "STARTING") {
       return () => undefined; // conversation not yet loaded
     }
 
     let sio = sioRef.current;
 
-    if (sio?.connected) {
-      sio.disconnect();
-    }
-
     const lastEvent = lastEventRef.current;
     const query = {
       latest_event_id: lastEvent?.id ?? -1,

frontend/src/hooks/query/use-active-conversation.ts

@@ -9,7 +9,7 @@ export const useActiveConversation = () => {
   const { conversationId } = useConversationId();
   const userConversation = useUserConversation(conversationId, (query) => {
     if (query.state.data?.status === "STARTING") {
-      return 3000; // 3 seconds
+      return 2000; // 2 seconds
     }
     return FIVE_MINUTES;
   });
@@ -17,10 +17,6 @@ export const useActiveConversation = () => {
   useEffect(() => {
     const conversation = userConversation.data;
     OpenHands.setCurrentConversation(conversation || null);
-  }, [
-    conversationId,
-    userConversation.isFetched,
-    userConversation?.data?.status,
-  ]);
+  }, [conversationId, userConversation.isFetched]);
   return userConversation;
 };

frontend/src/hooks/query/use-settings.ts

@@ -45,7 +45,6 @@ export const useSettings = () => {
     // would want to show the modal immediately if the
     // settings are not found
     retry: (_, error) => error.status !== 404,
-    refetchOnWindowFocus: false,
     staleTime: 1000 * 60 * 5, // 5 minutes
     gcTime: 1000 * 60 * 15, // 15 minutes
     enabled: !isOnTosPage && !!userIsAuthenticated,

frontend/src/hooks/use-handle-email-verification.ts

@@ -0,0 +1,116 @@
+import { useEffect } from "react";
+import { useQueryClient } from "@tanstack/react-query";
+import { useNavigate } from "react-router";
+import { AxiosError } from "axios";
+import { openHands } from "#/api/open-hands-axios";
+import { Settings } from "#/types/settings";
+import { useConfig } from "#/hooks/query/use-config";
+
+/**
+ * Hook to handle email verification errors (403 with "Email has not been verified" message)
+ * This hook sets up an axios interceptor that will reload settings and navigate to the user settings page
+ * when a 403 error with the specific message is encountered.
+ */
+export const useHandleEmailVerification = () => {
+  const queryClient = useQueryClient();
+  const navigate = useNavigate();
+  const { data: config } = useConfig();
+  const appMode = config?.APP_MODE;
+  console.log(`config: ${config}`);
+  console.log(`AppMode: ${appMode}`);
+
+  useEffect(() => {
+    // Add response interceptor
+    const interceptorId = openHands.interceptors.response.use(
+      (response) => response,
+      (error: AxiosError) => {
+        console.log(
+          `Received error ${error.response?.status} with message ${error.response?.data}`,
+        );
+
+        const EMAIL_NOT_VERIFIED = "EmailNotVerifiedError";
+        // check for email verification error message no matter how it is returned.
+        const isEmailNotVerified = (() => {
+          const data = error.response?.data;
+
+          if (typeof data === "string") {
+            return data.includes(EMAIL_NOT_VERIFIED);
+          }
+
+          if (typeof data === "object" && data !== null) {
+            if ("message" in data) {
+              const { message } = data;
+              if (typeof message === "string") {
+                return message.includes(EMAIL_NOT_VERIFIED);
+              }
+              if (Array.isArray(message)) {
+                return message.some(
+                  (msg) =>
+                    typeof msg === "string" && msg.includes(EMAIL_NOT_VERIFIED),
+                );
+              }
+            }
+
+            // Search any values in object in case message key is different
+            return Object.values(data).some(
+              (value) =>
+                (typeof value === "string" &&
+                  value.includes(EMAIL_NOT_VERIFIED)) ||
+                (Array.isArray(value) &&
+                  value.some(
+                    (v) =>
+                      typeof v === "string" && v.includes(EMAIL_NOT_VERIFIED),
+                  )),
+            );
+          }
+
+          return false;
+        })();
+
+        // Check if it's a 403 error with the specific message
+        if (error.response?.status === 403 && isEmailNotVerified) {
+          console.log("EMAIL VERIFICATION ERROR");
+          // Only handle this in SAAS mode
+          console.log(`config1: ${config}`);
+          console.log(`AppMode1: ${appMode}`);
+          if (appMode === "saas") {
+            // Update settings to mark email as unverified
+            queryClient.setQueryData(
+              ["settings"],
+              (oldData: Settings | undefined) => {
+                if (oldData) {
+                  console.log("ADDING EMAIL_VERIFIED is FALSE");
+                  return {
+                    ...oldData,
+                    EMAIL_VERIFIED: false,
+                  };
+                }
+                console.log("NO CHANGES TO SETTINGS");
+                return oldData;
+              },
+            );
+
+            // Invalidate settings to reload them
+            queryClient.invalidateQueries({ queryKey: ["settings"] });
+
+            // Navigate to settings/user page
+            // The EmailVerificationGuard will handle the redirect
+            console.log("NAVIGATING to /settings/user");
+            navigate("/settings/user");
+          }
+        } else {
+          console.log("NOT EMAIL VERIFICATION ERROR");
+          console.log(typeof error.response?.data);
+        }
+
+        // Continue with the error for other error handlers
+        return Promise.reject(error);
+      },
+    );
+
+    // Clean up interceptor when component unmounts
+    return () => {
+      openHands.interceptors.response.eject(interceptorId);
+    };
+  }, [queryClient, navigate]);
+};

frontend/src/i18n/declaration.ts

@@ -1,6 +1,5 @@
 // this file generate by script, don't modify it manually!!!
 export enum I18nKey {
-  STATUS$WEBSOCKET_CLOSED = "STATUS$WEBSOCKET_CLOSED",
   HOME$LAUNCH_FROM_SCRATCH = "HOME$LAUNCH_FROM_SCRATCH",
   HOME$READ_THIS = "HOME$READ_THIS",
   AUTH$LOGGING_BACK_IN = "AUTH$LOGGING_BACK_IN",
@@ -567,7 +566,6 @@ export enum I18nKey {
   SETTINGS$SENDING = "SETTINGS$SENDING",
   SETTINGS$VERIFICATION_EMAIL_SENT = "SETTINGS$VERIFICATION_EMAIL_SENT",
   SETTINGS$EMAIL_VERIFICATION_REQUIRED = "SETTINGS$EMAIL_VERIFICATION_REQUIRED",
-  SETTINGS$INVALID_EMAIL_FORMAT = "SETTINGS$INVALID_EMAIL_FORMAT",
   SETTINGS$EMAIL_VERIFICATION_RESTRICTION_MESSAGE = "SETTINGS$EMAIL_VERIFICATION_RESTRICTION_MESSAGE",
   SETTINGS$RESEND_VERIFICATION = "SETTINGS$RESEND_VERIFICATION",
   SETTINGS$FAILED_TO_RESEND_VERIFICATION = "SETTINGS$FAILED_TO_RESEND_VERIFICATION",

frontend/src/i18n/translation.json

@@ -1,20 +1,4 @@
 {
-    "STATUS$WEBSOCKET_CLOSED": {
-        "en": "The WebSocket connection was closed.",
-        "ja": "WebSocket接続が閉じられました。",
-        "zh-CN": "WebSocket连接已关闭。",
-        "zh-TW": "WebSocket連接已關閉。",
-        "ko-KR": "WebSocket 연결이 닫혔습니다.",
-        "no": "WebSocket-tilkoblingen ble lukket.",
-        "it": "La connessione WebSocket è stata chiusa.",
-        "pt": "A conexão WebSocket foi fechada.",
-        "es": "La conexión WebSocket se ha cerrado.",
-        "ar": "تم إغلاق اتصال WebSocket.",
-        "fr": "La connexion WebSocket a été fermée.",
-        "tr": "WebSocket bağlantısı kapatıldı.",
-        "de": "Die WebSocket-Verbindung wurde geschlossen.",
-        "uk": "З'єднання WebSocket було закрито."
-    },
     "HOME$LAUNCH_FROM_SCRATCH": {
         "en": "Launch from Scratch",
         "ja": "ゼロから始める",
@@ -9071,22 +9055,6 @@
         "de": "Sie müssen Ihre E-Mail-Adresse bestätigen, bevor Sie All Hands verwenden können",
         "uk": "Ви повинні підтвердити свою електронну адресу перед використанням All Hands"
     },
-    "SETTINGS$INVALID_EMAIL_FORMAT": {
-        "en": "Please enter a valid email address",
-        "ja": "有効なメールアドレスを入力してください",
-        "zh-CN": "请输入有效的电子邮件地址",
-        "zh-TW": "請輸入有效的電子郵件地址",
-        "ko-KR": "유효한 이메일 주소를 입력하세요",
-        "no": "Vennligst skriv inn en gyldig e-postadresse",
-        "it": "Inserisci un indirizzo email valido",
-        "pt": "Por favor, insira um endereço de e-mail válido",
-        "es": "Por favor, introduzca una dirección de correo electrónico válida",
-        "ar": "الرجاء إدخال عنوان بريد إلكتروني صالح",
-        "fr": "Veuillez entrer une adresse e-mail valide",
-        "tr": "Lütfen geçerli bir e-posta adresi girin",
-        "de": "Bitte geben Sie eine gültige E-Mail-Adresse ein",
-        "uk": "Будь ласка, введіть дійсну електронну адресу"
-    },
     "SETTINGS$EMAIL_VERIFICATION_RESTRICTION_MESSAGE": {
         "en": "Your access is limited until your email is verified. You can only access this settings page.",
         "ja": "メールが確認されるまでアクセスが制限されています。この設定ページにのみアクセスできます。",

frontend/src/routes/conversation.tsx

@@ -43,7 +43,7 @@ function AppContent() {
   const { t } = useTranslation();
   const { data: settings } = useSettings();
   const { conversationId } = useConversationId();
-  const { data: conversation, isFetched, refetch } = useActiveConversation();
+  const { data: conversation, isFetched } = useActiveConversation();
   const { data: isAuthed } = useIsAuthed();
 
   const { curAgentState } = useSelector((state: RootState) => state.agent);
@@ -61,13 +61,8 @@ function AppContent() {
         "This conversation does not exist, or you do not have permission to access it.",
       );
       navigate("/");
-    } else if (conversation?.status === "STOPPED") {
-      // start the conversation if the state is stopped on initial load
-      OpenHands.startConversation(conversation.conversation_id).then(() =>
-        refetch(),
-      );
     }
-  }, [conversation?.conversation_id, isFetched, isAuthed]);
+  }, [conversation, isFetched, isAuthed]);
 
   React.useEffect(() => {
     dispatch(clearTerminal());

frontend/src/routes/llm-settings.tsx

@@ -304,7 +304,7 @@ function LlmSettingsScreen() {
                 testId="llm-api-key-help-anchor"
                 text={t(I18nKey.SETTINGS$DONT_KNOW_API_KEY)}
                 linkText={t(I18nKey.SETTINGS$CLICK_FOR_INSTRUCTIONS)}
-                href="https://docs.all-hands.dev/usage/local-setup#getting-an-api-key"
+                href="https://docs.all-hands.dev/usage/installation#getting-an-api-key"
               />
 
               <SettingsInput
@@ -379,7 +379,7 @@ function LlmSettingsScreen() {
                 testId="llm-api-key-help-anchor-advanced"
                 text={t(I18nKey.SETTINGS$DONT_KNOW_API_KEY)}
                 linkText={t(I18nKey.SETTINGS$CLICK_FOR_INSTRUCTIONS)}
-                href="https://docs.all-hands.dev/usage/local-setup#getting-an-api-key"
+                href="https://docs.all-hands.dev/usage/installation#getting-an-api-key"
               />
 
               <SettingsInput

frontend/src/routes/root-layout.tsx

@@ -24,6 +24,7 @@ import { displaySuccessToast } from "#/utils/custom-toast-handlers";
 import { useIsOnTosPage } from "#/hooks/use-is-on-tos-page";
 import { useAutoLogin } from "#/hooks/use-auto-login";
 import { useAuthCallback } from "#/hooks/use-auth-callback";
+import { useHandleEmailVerification } from "#/hooks/use-handle-email-verification";
 import { LOCAL_STORAGE_KEYS } from "#/utils/local-storage";
 import { EmailVerificationGuard } from "#/components/features/guards/email-verification-guard";
 
@@ -93,6 +94,9 @@ export default function MainApp() {
   // Handle authentication callback and set login method after successful authentication
   useAuthCallback();
 
+  // Set up interceptor for email verification errors
+  useHandleEmailVerification();
+
   React.useEffect(() => {
     // Don't change language when on TOS page
     if (!isOnTosPage && settings?.LANGUAGE) {

frontend/src/routes/user-settings.tsx

@@ -5,9 +5,6 @@ import { useSettings } from "#/hooks/query/use-settings";
 import { openHands } from "#/api/open-hands-axios";
 import { displaySuccessToast } from "#/utils/custom-toast-handlers";
 
-// Email validation regex pattern
-const EMAIL_REGEX = /^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$/;
-
 function EmailInputSection({
   email,
   onEmailChange,
@@ -17,7 +14,6 @@ function EmailInputSection({
   isResendingVerification,
   isEmailChanged,
   emailVerified,
-  isEmailValid,
   children,
 }: {
   email: string;
@@ -28,7 +24,6 @@ function EmailInputSection({
   isResendingVerification: boolean;
   isEmailChanged: boolean;
   emailVerified?: boolean;
-  isEmailValid: boolean;
   children: React.ReactNode;
 }) {
   const { t } = useTranslation();
@@ -41,30 +36,17 @@ function EmailInputSection({
             type="email"
             value={email}
             onChange={onEmailChange}
-            className={`text-base text-white p-2 bg-base-tertiary rounded border ${
-              isEmailChanged && !isEmailValid
-                ? "border-red-500"
-                : "border-tertiary"
-            } flex-grow focus:outline-none focus:border-transparent focus:ring-0`}
+            className="text-base text-white p-2 bg-base-tertiary rounded border border-tertiary flex-grow focus:outline-none focus:border-transparent focus:ring-0"
             placeholder={t("SETTINGS$USER_EMAIL_LOADING")}
             data-testid="email-input"
           />
         </div>
 
-        {isEmailChanged && !isEmailValid && (
-          <div
-            className="text-red-500 text-sm mt-1"
-            data-testid="email-validation-error"
-          >
-            {t("SETTINGS$INVALID_EMAIL_FORMAT")}
-          </div>
-        )}
-
         <div className="flex items-center gap-3 mt-2">
           <button
             type="button"
             onClick={onSaveEmail}
-            disabled={!isEmailChanged || isSaving || !isEmailValid}
+            disabled={!isEmailChanged || isSaving}
             className="px-4 py-2 rounded bg-primary text-white hover:opacity-80 disabled:opacity-30 disabled:cursor-not-allowed disabled:text-[#0D0F11]"
             data-testid="save-email-button"
           >
@@ -116,7 +98,6 @@ function UserSettingsScreen() {
   const [originalEmail, setOriginalEmail] = useState("");
   const [isSaving, setIsSaving] = useState(false);
   const [isResendingVerification, setIsResendingVerification] = useState(false);
-  const [isEmailValid, setIsEmailValid] = useState(true);
   const queryClient = useQueryClient();
   const pollingIntervalRef = useRef<number | null>(null);
   const prevVerificationStatusRef = useRef<boolean | undefined>(undefined);
@@ -125,7 +106,6 @@ function UserSettingsScreen() {
     if (settings?.EMAIL) {
       setEmail(settings.EMAIL);
       setOriginalEmail(settings.EMAIL);
-      setIsEmailValid(EMAIL_REGEX.test(settings.EMAIL));
     }
   }, [settings?.EMAIL]);
 
@@ -163,13 +143,11 @@ function UserSettingsScreen() {
   }, [settings?.EMAIL_VERIFIED, refetch, queryClient, t]);
 
   const handleEmailChange = (e: React.ChangeEvent<HTMLInputElement>) => {
-    const newEmail = e.target.value;
-    setEmail(newEmail);
-    setIsEmailValid(EMAIL_REGEX.test(newEmail));
+    setEmail(e.target.value);
   };
 
   const handleSaveEmail = async () => {
-    if (email === originalEmail || !isEmailValid) return;
+    if (email === originalEmail) return;
     try {
       setIsSaving(true);
       await openHands.post("/api/email", { email }, { withCredentials: true });
@@ -216,7 +194,6 @@ function UserSettingsScreen() {
             isResendingVerification={isResendingVerification}
             isEmailChanged={isEmailChanged}
             emailVerified={settings?.EMAIL_VERIFIED}
-            isEmailValid={isEmailValid}
           >
             {settings?.EMAIL_VERIFIED === false && <VerificationAlert />}
           </EmailInputSection>

frontend/src/utils/tips.ts

@@ -12,7 +12,7 @@ export const TIPS: Tip[] = [
   },
   {
     key: I18nKey.TIPS$SETUP_SCRIPT,
-    link: "https://docs.all-hands.dev/usage/prompting/repository#setup-script",
+    link: "https://docs.all-hands.dev/usage/customization/repository",
   },
   { key: I18nKey.TIPS$VSCODE_INSTANCE },
   { key: I18nKey.TIPS$SAVE_WORK },
@@ -30,7 +30,7 @@ export const TIPS: Tip[] = [
   },
   {
     key: I18nKey.TIPS$GITHUB_HOOK,
-    link: "https://docs.all-hands.dev/usage/cloud/github-installation#working-on-github-issues-and-pull-requests-using-openhands",
+    link: "https://docs.all-hands.dev/usage/cloud/cloud-issue-resolver",
   },
   {
     key: I18nKey.TIPS$BLOG_SIGNUP,
@@ -38,7 +38,7 @@ export const TIPS: Tip[] = [
   },
   {
     key: I18nKey.TIPS$API_USAGE,
-    link: "https://docs.all-hands.dev/api-reference/health-check",
+    link: "https://docs.all-hands.dev/swagger-ui/",
   },
 ];
 

microagents/README.md

@@ -117,10 +117,7 @@ You can see an example of a repo agent in [the agent for the OpenHands repo itse
    - Include repository structure details
    - Specify testing and build procedures
    - List environment requirements
-   - Document CI workflows and checks
-   - Include information about code quality standards
    - Maintain up-to-date team practices
-   - Consider using OpenHands to generate a comprehensive repo.md (see [Creating a Repository Agent](#creating-a-repository-agent))
    - YAML frontmatter is optional - files without frontmatter will be loaded with default settings
 
 ### Submission Process

microagents/add_agent.md

@@ -37,4 +37,5 @@ When creating a new microagent:
 For detailed information, see:
 
 - [Microagents Overview](https://docs.all-hands.dev/usage/prompting/microagents-overview)
+- [Microagents Syntax](https://docs.all-hands.dev/usage/prompting/microagents-syntax)
 - [Example GitHub Microagent](https://github.com/All-Hands-AI/OpenHands/blob/main/microagents/github.md)

microagents/add_repo_inst.md

@@ -1,65 +0,0 @@
----
-name: add_repo_inst
-version: 1.0.0
-author: openhands
-agent: CodeActAgent
-triggers:
-- /add_repo_inst
-inputs:
-  - name: REPO_FOLDER_NAME
-    description: "Branch for the agent to work on"
----
-
-Please browse the current repository under /workspace/{{ REPO_FOLDER_NAME }}, look at the documentation and relevant code, and understand the purpose of this repository.
-
-Specifically, I want you to create a `.openhands/microagents/repo.md`  file. This file should contain succinct information that summarizes (1) the purpose of this repository, (2) the general setup of this repo, and (3) a brief description of the structure of this repo.
-
-Here's an example:
-```markdown
----
-name: repo
-type: repo
-agent: CodeActAgent
----
-
-This repository contains the code for OpenHands, an automated AI software engineer. It has a Python backend
-(in the `openhands` directory) and React frontend (in the `frontend` directory).
-
-## General Setup:
-To set up the entire repo, including frontend and backend, run `make build`.
-You don't need to do this unless the user asks you to, or if you're trying to run the entire application.
-
-Before pushing any changes, you should ensure that any lint errors or simple test errors have been fixed.
-
-* If you've made changes to the backend, you should run `pre-commit run --all-files --config ./dev_config/python/.pre-commit-config.yaml`
-* If you've made changes to the frontend, you should run `cd frontend && npm run lint:fix && npm run build ; cd ..`
-
-If either command fails, it may have automatically fixed some issues. You should fix any issues that weren't automatically fixed,
-then re-run the command to ensure it passes.
-
-## Repository Structure
-Backend:
-- Located in the `openhands` directory
-- Testing:
-  - All tests are in `tests/unit/test_*.py`
-  - To test new code, run `poetry run pytest tests/unit/test_xxx.py` where `xxx` is the appropriate file for the current functionality
-  - Write all tests with pytest
-
-Frontend:
-- Located in the `frontend` directory
-- Prerequisites: A recent version of NodeJS / NPM
-- Setup: Run `npm install` in the frontend directory
-- Testing:
-  - Run tests: `npm run test`
-  - To run specific tests: `npm run test -- -t "TestName"`
-- Building:
-  - Build for production: `npm run build`
-- Environment Variables:
-  - Set in `frontend/.env` or as environment variables
-  - Available variables: VITE_BACKEND_HOST, VITE_USE_TLS, VITE_INSECURE_SKIP_VERIFY, VITE_FRONTEND_PORT
-- Internationalization:
-  - Generate i18n declaration file: `npm run make-i18n`
-```
-
-Now, please write a similar markdown for the current repository.
-Read all the GitHub workflows under .github/ of the repository (if this folder exists) to understand the CI checks (e.g., linter, pre-commit), and include those in the repo.md file.

microagents/address_pr_comments.md

@@ -1,19 +0,0 @@
----
-name: address_pr_comments
-version: 1.0.0
-author: openhands
-agent: CodeActAgent
-triggers:
-- /address_pr_comments
-inputs:
-  - name: PR_URL
-    description: "URL of the pull request"
-  - name: BRANCH_NAME
-    description: "Branch name corresponds to the pull request"
----
-
-First, check the branch {{ BRANCH_NAME }} and read the diff against the main branch to understand the purpose.
-
-This branch corresponds to this PR {{ PR_URL }}
-
-Next, you should use the GitHub API to read the reviews and comments on this PR and address them.

microagents/fix_test.md

@@ -1,23 +0,0 @@
----
-name: fix_test
-version: 1.0.0
-author: openhands
-agent: CodeActAgent
-triggers:
-- /fix_test
-inputs:
-  - name: BRANCH_NAME
-    description: "Branch for the agent to work on"
-  - name: TEST_COMMAND_TO_RUN
-    description: "The test command you want the agent to work on. For example, `pytest tests/unit/test_bash_parsing.py`"
-  - name: FUNCTION_TO_FIX
-    description: "The name of function to fix"
-  - name: FILE_FOR_FUNCTION
-    description: "The path of the file that contains the function"
----
-
-Can you check out branch "{{ BRANCH_NAME }}", and run {{ TEST_COMMAND_TO_RUN }}.
-
-Help me fix these tests to pass by fixing the {{ FUNCTION_TO_FIX }} function in file {{ FILE_FOR_FUNCTION }}.
-
-PLEASE DO NOT modify the tests by yourself -- Let me know if you think some of the tests are incorrect.

microagents/update_pr_description.md

@@ -1,21 +0,0 @@
----
-name: update_pr_description
-version: 1.0.0
-author: openhands
-agent: CodeActAgent
-triggers:
-- /update_pr_description
-inputs:
-  - name: PR_URL
-    description: "URL of the pull request"
-    type: string
-    validation:
-      pattern: "^https://github.com/.+/.+/pull/[0-9]+$"
-  - name: BRANCH_NAME
-    description: "Branch name corresponds to the pull request"
-    type: string
----
-
-Please check the branch "{{ BRANCH_NAME }}" and look at the diff against the main branch. This branch belongs to this PR "{{ PR_URL }}".
-
-Once you understand the purpose of the diff, please use Github API to read the existing PR description, and update it to be more reflective of the changes we've made when necessary.

microagents/update_test.md

@@ -1,19 +0,0 @@
----
-name: update_test
-version: 1.0.0
-author: openhands
-agent: CodeActAgent
-triggers:
-- /update_test
-inputs:
-  - name: BRANCH_NAME
-    description: "Branch for the agent to work on"
-  - name: TEST_COMMAND_TO_RUN
-    description: "The test command you want the agent to work on. For example, `pytest tests/unit/test_bash_parsing.py`"
----
-
-Can you check out branch "{{ BRANCH_NAME }}", and run {{ TEST_COMMAND_TO_RUN }}.
-
-The current implementation of the code is correct BUT the test functions {{ FUNCTION_TO_FIX }} in file {{ FILE_FOR_FUNCTION }} are failing.
-
-Please update the test file so that they pass with the current version of the implementation.

openhands/cli/tui.py

@@ -12,7 +12,7 @@ from prompt_toolkit import PromptSession, print_formatted_text
 from prompt_toolkit.application import Application
 from prompt_toolkit.completion import CompleteEvent, Completer, Completion
 from prompt_toolkit.document import Document
-from prompt_toolkit.formatted_text import HTML, StyleAndTextTuples
+from prompt_toolkit.formatted_text import HTML, FormattedText, StyleAndTextTuples
 from prompt_toolkit.input import create_input
 from prompt_toolkit.key_binding import KeyBindings
 from prompt_toolkit.key_binding.key_processor import KeyPressEvent
@@ -132,113 +132,51 @@ def display_initialization_animation(text: str, is_loaded: asyncio.Event) -> Non
 
 
 def display_banner(session_id: str) -> None:
-    banner_text = r"""<gold>
+    print_formatted_text(
+        HTML(r"""<gold>
      ___                    _   _                 _
     /  _ \ _ __   ___ _ __ | | | | __ _ _ __   __| |___
     | | | | '_ \ / _ \ '_ \| |_| |/ _` | '_ \ / _` / __|
     | |_| | |_) |  __/ | | |  _  | (_| | | | | (_| \__ \
     \___ /| .__/ \___|_| |_|_| |_|\__,_|_| |_|\__,_|___/
           |_|
-    </gold>"""
-
-    # Use TextArea with focusable=True to allow text selection
-    banner_container = Frame(
-        TextArea(
-            text=banner_text.replace('<gold>', '').replace('</gold>', ''),
-            read_only=True,
-            style=COLOR_GOLD,
-            wrap_lines=True,
-            focusable=True,  # Allow focusing to enable text selection
-        ),
-        style=f'fg:{COLOR_GOLD}',
+    </gold>"""),
+        style=DEFAULT_STYLE,
     )
-    print_container(banner_container)
 
-    # Call print_formatted_text to maintain compatibility with tests
+    print_formatted_text(HTML(f'<grey>OpenHands CLI v{__version__}</grey>'))
+
     print_formatted_text('')
-
-    version_container = Frame(
-        TextArea(
-            text=f'OpenHands CLI v{__version__}',
-            read_only=True,
-            style=COLOR_GREY,
-            wrap_lines=True,
-            focusable=True,  # Allow focusing to enable text selection
-        ),
-        style=f'fg:{COLOR_GREY}',
-    )
-    print_container(version_container)
-
-    # Call print_formatted_text to maintain compatibility with tests
-    print_formatted_text('')
-
-    session_container = Frame(
-        TextArea(
-            text=f'Initialized conversation {session_id}',
-            read_only=True,
-            style=COLOR_GREY,
-            wrap_lines=True,
-            focusable=True,  # Allow focusing to enable text selection
-        ),
-        style=f'fg:{COLOR_GREY}',
-    )
-    print_formatted_text('')
-    print_container(session_container)
+    print_formatted_text(HTML(f'<grey>Initialized conversation {session_id}</grey>'))
     print_formatted_text('')
 
 
 def display_welcome_message(message: str = '') -> None:
-    # Use TextArea with focusable=True to allow text selection
-    welcome_container = Frame(
-        TextArea(
-            text="Let's start building!",
-            read_only=True,
-            style=COLOR_GOLD,
-            wrap_lines=True,
-            focusable=True,  # Allow focusing to enable text selection
-        ),
-        style=f'fg:{COLOR_GOLD}',
+    print_formatted_text(
+        HTML("<gold>Let's start building!</gold>\n"), style=DEFAULT_STYLE
     )
-    print_container(welcome_container)
-
-    # Call print_formatted_text to maintain compatibility with tests
-    print_formatted_text('')
-
     if message:
-        message_text = f'{message} Type /help for help'
+        print_formatted_text(
+            HTML(f'{message} <grey>Type /help for help</grey>'),
+            style=DEFAULT_STYLE,
+        )
     else:
-        message_text = 'What do you want to build? Type /help for help'
-
-    message_container = Frame(
-        TextArea(
-            text=message_text,
-            read_only=True,
-            style=COLOR_GREY,
-            wrap_lines=True,
-            focusable=True,  # Allow focusing to enable text selection
-        ),
-        style=f'fg:{COLOR_GREY}',
-    )
-    print_container(message_container)
-
-    # Call print_formatted_text to maintain compatibility with tests
-    print_formatted_text('')
+        print_formatted_text(
+            HTML('What do you want to build? <grey>Type /help for help</grey>'),
+            style=DEFAULT_STYLE,
+        )
 
 
 def display_initial_user_prompt(prompt: str) -> None:
-    # Use TextArea with focusable=True to allow text selection
-    prompt_container = Frame(
-        TextArea(
-            text=f'> {prompt}',
-            read_only=True,
-            style=COLOR_GOLD,
-            wrap_lines=True,
-            focusable=True,  # Allow focusing to enable text selection
-        ),
-        style=f'fg:{COLOR_GOLD}',
+    print_formatted_text(
+        FormattedText(
+            [
+                ('', '\n'),
+                (COLOR_GOLD, '> '),
+                ('', prompt),
+            ]
+        )
     )
-    print_formatted_text('')
-    print_container(prompt_container)
 
 
 # Prompt output display functions
@@ -286,7 +224,6 @@ def display_error(error: str) -> None:
                 read_only=True,
                 style='ansired',
                 wrap_lines=True,
-                focusable=True,  # Allow focusing to enable text selection
             ),
             title='Error',
             style='ansired',
@@ -302,7 +239,6 @@ def display_command(event: CmdRunAction) -> None:
             read_only=True,
             style=COLOR_GREY,
             wrap_lines=True,
-            focusable=True,  # Allow focusing to enable text selection
         ),
         title='Command',
         style='ansiblue',
@@ -331,7 +267,6 @@ def display_command_output(output: str) -> None:
             read_only=True,
             style=COLOR_GREY,
             wrap_lines=True,
-            focusable=True,  # Allow focusing to enable text selection
         ),
         title='Command Output',
         style=f'fg:{COLOR_GREY}',
@@ -347,7 +282,6 @@ def display_file_edit(event: FileEditObservation) -> None:
             read_only=True,
             wrap_lines=True,
             lexer=CustomDiffLexer(),
-            focusable=True,  # Allow focusing to enable text selection
         ),
         title='File Edit',
         style=f'fg:{COLOR_GREY}',
@@ -364,7 +298,6 @@ def display_file_read(event: FileReadObservation) -> None:
             read_only=True,
             style=COLOR_GREY,
             wrap_lines=True,
-            focusable=True,  # Allow focusing to enable text selection
         ),
         title='File Read',
         style=f'fg:{COLOR_GREY}',
@@ -383,7 +316,6 @@ def initialize_streaming_output():
         read_only=True,
         style=COLOR_GREY,
         wrap_lines=True,
-        focusable=True,  # Allow focusing to enable text selection
     )
     container = Frame(
         streaming_output_text_area,
@@ -493,7 +425,6 @@ def display_usage_metrics(usage_metrics: UsageMetrics) -> None:
             read_only=True,
             style=COLOR_GREY,
             wrap_lines=True,
-            focusable=True,  # Allow focusing to enable text selection
         ),
         title='Usage Metrics',
         style=f'fg:{COLOR_GREY}',

openhands/events/nested_event_store.py

@@ -3,7 +3,6 @@ from typing import Iterable
 from urllib.parse import urlencode
 
 import httpx  # type: ignore
-from fastapi import status
 
 from openhands.events.event import Event
 from openhands.events.event_filter import EventFilter
@@ -43,9 +42,6 @@ class NestedEventStore(EventStoreABC):
             if self.session_api_key:
                 headers['X-Session-API-Key'] = self.session_api_key
             response = httpx.get(url, headers=headers)
-            if response.status_code == status.HTTP_404_NOT_FOUND:
-                # Follow pattern of event store not throwing errors on not found
-                return
             result_set = response.json()
             for result in result_set['events']:
                 event = event_from_dict(result)

openhands/integrations/github/github_service.py

@@ -505,7 +505,10 @@ class GitHubService(BaseGitService, GitService):
         )
 
         # Return the HTML URL of the created PR
-        return response['html_url']
+        if 'html_url' in response:
+            return response['html_url']
+        else:
+            return f'PR created but URL not found in response: {response}'
 
 
 

openhands/integrations/gitlab/gitlab_service.py

@@ -500,8 +500,12 @@ class GitLabService(BaseGitService, GitService):
             url=url, params=payload, method=RequestMethod.POST
         )
 
+        # Return the web URL of the created MR
+        if 'web_url' in response:
+            return response['web_url']
+        else:
+            return f'MR created but URL not found in response: {response}'
 
-        return response['web_url']
 
 
 

openhands/integrations/templates/resolver/github/issue_comment_conversation_instructions.j2

@@ -15,3 +15,4 @@ When you're done, make sure to
 2. Use the `create_pr` tool to open a new PR
 3. Name the branch using `openhands/` as a prefix (e.g `openhands/update-readme`)
 4. The PR description should mention that it "fixes" or "closes" the issue number
+5. Make sure to leave the following sentence at the end of the PR description: `@{{ username }} can click here to [continue refining the PR]({{ conversation_url }})`

openhands/integrations/templates/resolver/github/issue_labeled_conversation_instructions.j2

@@ -9,3 +9,4 @@ When you're done, make sure to
 
 1. Use the `create_pr` tool to open a new PR
 2. The PR description should mention that it "fixes" or "closes" the issue number
+3. Make sure to leave the following sentence at the end of the PR description: `@{{ username }} can click here to [continue refining the PR]({{ conversation_url }})`

openhands/integrations/templates/resolver/gitlab/issue_comment_conversation_instructions.j2

@@ -15,3 +15,4 @@ When you're done, make sure to
 2. Use the `create_mr` tool to open a new MR
 3. Name the branch using `openhands/` as a prefix (e.g `openhands/update-readme`)
 4. The MR description should mention that it "fixes" or "closes" the issue number
+5. Make sure to leave the following sentence at the end of the MR description: `@{{ username }} can click here to [continue refining the MR]({{ conversation_url }})`

openhands/integrations/templates/resolver/gitlab/issue_labeled_conversation_instructions.j2

@@ -9,3 +9,4 @@ When you're done, make sure to
 
 1. Use the `create_mr` tool to open a new MR
 2. The MR description should mention that it "fixes" or "closes" the issue number
+3. Make sure to leave the following sentence at the end of the MR description: `@{{ username }} can click here to [continue refining the MR]({{ conversation_url }})`

openhands/integrations/templates/resolver/slack/user_message_conversation_instructions.j2

@@ -5,3 +5,7 @@ These are a list of text messages attached in order of most recent.
 {{ message }}
 {% if not loop.last %}\n\n{% endif %}
 {% endfor %}
+
+
+If you opened a pull request, please leave the following comment at the end your summary and pull request description
+`{{ username }} can click here to [continue refining the PR]({{ conversation_url }})`

openhands/integrations/templates/resolver/summary_prompt.j2

@@ -1,8 +1,5 @@
-Please send a final message summarizing your work.
+Please summarize your work.
 
-If you simply answered a question, this final message should re-state the answer to the question.
-
-If you made changes, please first double-check the git diff, think carefully about the user's request(s), and check:
-1. whether the request has been completely addressed and all of the instructions have been followed faithfully (in checklist format if appropriate).
-2. whether the changes are concise (if there are any extraneous changes not important to addressing the user's request they should be reverted).
-If the request has been addressed and the changes are concise, then push your changes to the remote branch and send a final message summarizing the changes.
+If you answered a question, please re-state the answer to the question
+If you made changes, please create a concise overview on whether the request has been addressed successfully or if there are were issues with the attempt.
+If successful, make sure your changes are pushed to the remote branch.

openhands/mcp/client.py

@@ -1,12 +1,13 @@
+import asyncio
+import datetime
+from contextlib import AsyncExitStack
 from typing import Optional
 
-from fastmcp import Client
-from fastmcp.client.transports import SSETransport, StreamableHttpTransport
-from mcp import McpError
-from mcp.types import CallToolResult
+from mcp import ClientSession
+from mcp.client.sse import sse_client
+from mcp.client.streamable_http import streamablehttp_client
 from pydantic import BaseModel, Field
 
-from openhands.core.config.mcp_config import MCPSHTTPServerConfig, MCPSSEServerConfig
 from openhands.core.logger import openhands_logger as logger
 from openhands.mcp.tool import MCPClientTool
 
@@ -16,7 +17,8 @@ class MCPClient(BaseModel):
     A collection of tools that connects to an MCP server and manages available tools through the Model Context Protocol.
     """
 
-    client: Optional[Client] = None
+    session: Optional[ClientSession] = None
+    exit_stack: AsyncExitStack = AsyncExitStack()
     description: str = 'MCP client tools for server interaction'
     tools: list[MCPClientTool] = Field(default_factory=list)
     tool_map: dict[str, MCPClientTool] = Field(default_factory=dict)
@@ -24,87 +26,189 @@ class MCPClient(BaseModel):
     class Config:
         arbitrary_types_allowed = True
 
+    async def connect_sse(
+        self,
+        server_url: str,
+        api_key: str | None = None,
+        conversation_id: str | None = None,
+        timeout: float = 30.0,
+    ) -> None:
+        """Connect to an MCP server using SSE transport.
+
+        Args:
+            server_url: The URL of the SSE server to connect to.
+            timeout: Connection timeout in seconds. Default is 30 seconds.
+        """
+        if not server_url:
+            raise ValueError('Server URL is required.')
+        if self.session:
+            await self.disconnect()
+
+        try:
+            # Use asyncio.wait_for to enforce the timeout
+            async def connect_with_timeout():
+                headers = (
+                    {
+                        'Authorization': f'Bearer {api_key}',
+                        's': api_key,  # We need this for action execution server's MCP Router
+                        'X-Session-API-Key': api_key,  # We need this for Remote Runtime
+                    }
+                    if api_key
+                    else {}
+                )
+
+                if conversation_id:
+                    headers['X-OpenHands-Conversation-ID'] = conversation_id
+
+                # Convert float timeout to datetime.timedelta for consistency
+                timeout_delta = datetime.timedelta(seconds=timeout)
+
+                streams_context = sse_client(
+                    url=server_url,
+                    headers=headers if headers else None,
+                    timeout=timeout,
+                )
+                streams = await self.exit_stack.enter_async_context(streams_context)
+                # For SSE client, we only get read_stream and write_stream (2 values)
+                read_stream, write_stream = streams
+                self.session = await self.exit_stack.enter_async_context(
+                    ClientSession(
+                        read_stream, write_stream, read_timeout_seconds=timeout_delta
+                    )
+                )
+                await self._initialize_and_list_tools()
+
+            # Apply timeout to the entire connection process
+            await asyncio.wait_for(connect_with_timeout(), timeout=timeout)
+        except asyncio.TimeoutError:
+            logger.error(
+                f'Connection to {server_url} timed out after {timeout} seconds'
+            )
+            await self.disconnect()  # Clean up resources
+            raise  # Re-raise the TimeoutError
+        except Exception as e:
+            logger.error(f'Error connecting to {server_url}: {str(e)}')
+            await self.disconnect()  # Clean up resources
+            raise
+
     async def _initialize_and_list_tools(self) -> None:
         """Initialize session and populate tool map."""
-        if not self.client:
+        if not self.session:
             raise RuntimeError('Session not initialized.')
 
-        async with self.client:
-            tools = await self.client.list_tools()
+        await self.session.initialize()
+        response = await self.session.list_tools()
 
         # Clear existing tools
         self.tools = []
 
         # Create proper tool objects for each server tool
-        for tool in tools:
+        for tool in response.tools:
             server_tool = MCPClientTool(
                 name=tool.name,
                 description=tool.description,
                 inputSchema=tool.inputSchema,
-                session=self.client,
+                session=self.session,
             )
             self.tool_map[tool.name] = server_tool
             self.tools.append(server_tool)
 
-        logger.info(f'Connected to server with tools: {[tool.name for tool in tools]}')
+        logger.info(
+            f'Connected to server with tools: {[tool.name for tool in response.tools]}'
+        )
 
-    async def connect_http(
-        self,
-        server: MCPSSEServerConfig | MCPSHTTPServerConfig,
-        conversation_id: str | None = None,
-        timeout: float = 30.0,
-    ):
-        """Connect to MCP server using SHTTP or SSE transport"""
-        server_url = server.url
-        api_key = server.api_key
-
-        if not server_url:
-            raise ValueError('Server URL is required.')
-
-        try:
-            headers = (
-                {
-                    'Authorization': f'Bearer {api_key}',
-                    's': api_key,  # We need this for action execution server's MCP Router
-                    'X-Session-API-Key': api_key,  # We need this for Remote Runtime
-                }
-                if api_key
-                else {}
-            )
-
-            if conversation_id:
-                headers['X-OpenHands-ServerConversation-ID'] = conversation_id
-
-            # Instantiate custom transports due to custom headers
-            if isinstance(server, MCPSHTTPServerConfig):
-                transport = StreamableHttpTransport(
-                    url=server_url,
-                    headers=headers if headers else None,
-                )
-            else:
-                transport = SSETransport(
-                    url=server_url,
-                    headers=headers if headers else None,
-                )
-
-            self.client = Client(transport, timeout=timeout)
-
-            await self._initialize_and_list_tools()
-        except McpError as e:
-            logger.error(f'McpError connecting to {server_url}: {e}')
-            raise  # Re-raise the error
-
-        except Exception as e:
-            logger.error(f'Error connecting to {server_url}: {e}')
-            raise
-
-    async def call_tool(self, tool_name: str, args: dict) -> CallToolResult:
+    async def call_tool(self, tool_name: str, args: dict):
         """Call a tool on the MCP server."""
         if tool_name not in self.tool_map:
             raise ValueError(f'Tool {tool_name} not found.')
         # The MCPClientTool is primarily for metadata; use the session to call the actual tool.
-        if not self.client:
+        if not self.session:
             raise RuntimeError('Client session is not available.')
+        return await self.session.call_tool(name=tool_name, arguments=args)
 
-        async with self.client:
-            return await self.client.call_tool_mcp(name=tool_name, arguments=args)
+    async def connect_shttp(
+        self,
+        server_url: str,
+        api_key: str | None = None,
+        conversation_id: str | None = None,
+        timeout: float = 30.0,
+    ) -> None:
+        """Connect to an MCP server using StreamableHTTP transport.
+
+        Args:
+            server_url: The URL of the StreamableHTTP server to connect to.
+            api_key: Optional API key for authentication.
+            conversation_id: Optional conversation ID for session tracking.
+            timeout: Connection timeout in seconds. Default is 30 seconds.
+        """
+        if not server_url:
+            raise ValueError('Server URL is required.')
+        if self.session:
+            await self.disconnect()
+
+        try:
+            # Use asyncio.wait_for to enforce the timeout
+            async def connect_with_timeout():
+                headers = (
+                    {
+                        'Authorization': f'Bearer {api_key}',
+                        's': api_key,  # We need this for action execution server's MCP Router
+                        'X-Session-API-Key': api_key,  # We need this for Remote Runtime
+                    }
+                    if api_key
+                    else {}
+                )
+
+                if conversation_id:
+                    headers['X-OpenHands-Conversation-ID'] = conversation_id
+
+                # Convert float timeout to datetime.timedelta
+                timeout_delta = datetime.timedelta(seconds=timeout)
+                sse_read_timeout_delta = datetime.timedelta(
+                    seconds=timeout * 10
+                )  # 10x longer for read timeout
+
+                streams_context = streamablehttp_client(
+                    url=server_url,
+                    headers=headers if headers else None,
+                    timeout=timeout_delta,
+                    sse_read_timeout=sse_read_timeout_delta,
+                )
+                streams = await self.exit_stack.enter_async_context(streams_context)
+                # For StreamableHTTP client, we get read_stream, write_stream, and get_session_id (3 values)
+                read_stream, write_stream, _ = streams
+                self.session = await self.exit_stack.enter_async_context(
+                    ClientSession(
+                        read_stream, write_stream, read_timeout_seconds=timeout_delta
+                    )
+                )
+                await self._initialize_and_list_tools()
+
+            # Apply timeout to the entire connection process
+            await asyncio.wait_for(connect_with_timeout(), timeout=timeout)
+        except asyncio.TimeoutError:
+            logger.error(
+                f'Connection to {server_url} timed out after {timeout} seconds'
+            )
+            await self.disconnect()  # Clean up resources
+            raise  # Re-raise the TimeoutError
+        except Exception as e:
+            logger.error(f'Error connecting to {server_url}: {str(e)}')
+            await self.disconnect()  # Clean up resources
+            raise
+
+    async def disconnect(self) -> None:
+        """Disconnect from the MCP server and clean up resources."""
+        if self.session:
+            try:
+                # Close the session first
+                if hasattr(self.session, 'close'):
+                    await self.session.close()
+                # Then close the exit stack
+                await self.exit_stack.aclose()
+            except Exception as e:
+                logger.error(f'Error during disconnect: {str(e)}')
+            finally:
+                self.session = None
+                self.tools = []
+                logger.info('Disconnected from MCP server')

openhands/mcp/utils.py

@@ -72,22 +72,38 @@ async def create_mcp_clients(
     mcp_clients = []
 
     for server in servers:
-        is_shttp = isinstance(server, MCPSHTTPServerConfig)
-        connection_type = 'SHTTP' if is_shttp else 'SSE'
+        is_sse = isinstance(server, MCPSSEServerConfig)
+        connection_type = 'SSE' if is_sse else 'SHTTP'
         logger.info(
             f'Initializing MCP agent for {server} with {connection_type} connection...'
         )
         client = MCPClient()
 
         try:
-            await client.connect_http(server, conversation_id=conversation_id)
+            if is_sse:
+                await client.connect_sse(
+                    server.url,
+                    api_key=server.api_key,
+                    conversation_id=conversation_id,
+                )
+            else:
+                await client.connect_shttp(
+                    server.url,
+                    api_key=server.api_key,
+                    conversation_id=conversation_id,
+                )
 
             # Only add the client to the list after a successful connection
             mcp_clients.append(client)
 
         except Exception as e:
             logger.error(f'Failed to connect to {server}: {str(e)}', exc_info=True)
-
+            try:
+                await client.disconnect()
+            except Exception as disconnect_error:
+                logger.error(
+                    f'Error during disconnect after failed connection: {str(disconnect_error)}'
+                )
     return mcp_clients
 
 
@@ -127,6 +143,13 @@ async def fetch_mcp_tools_from_config(
         # Convert tools to the format expected by the agent
         mcp_tools = convert_mcp_clients_to_tools(mcp_clients)
 
+        # Always disconnect clients to clean up resources
+        for mcp_client in mcp_clients:
+            try:
+                await mcp_client.disconnect()
+            except Exception as disconnect_error:
+                logger.error(f'Error disconnecting MCP client: {str(disconnect_error)}')
+
     except Exception as e:
         logger.error(f'Error fetching MCP tools: {str(e)}')
         return []

openhands/microagent/microagent.py

@@ -1,5 +1,4 @@
 import io
-import re
 from pathlib import Path
 from typing import Union
 
@@ -10,7 +9,7 @@ from openhands.core.exceptions import (
     MicroagentValidationError,
 )
 from openhands.core.logger import openhands_logger as logger
-from openhands.microagent.types import InputMetadata, MicroagentMetadata, MicroagentType
+from openhands.microagent.types import MicroagentMetadata, MicroagentType
 
 
 class BaseMicroagent(BaseModel):
@@ -92,24 +91,13 @@ class BaseMicroagent(BaseModel):
         subclass_map = {
             MicroagentType.KNOWLEDGE: KnowledgeMicroagent,
             MicroagentType.REPO_KNOWLEDGE: RepoMicroagent,
-            MicroagentType.TASK: TaskMicroagent,
         }
 
         # Infer the agent type:
-        # 1. If inputs exist -> TASK
-        # 2. If triggers exist -> KNOWLEDGE
-        # 3. Else (no triggers) -> REPO (always active)
+        # 1. If triggers exist -> KNOWLEDGE (optional)
+        # 2. Else (no triggers) -> REPO (always active)
         inferred_type: MicroagentType
-        if metadata.inputs:
-            inferred_type = MicroagentType.TASK
-            # Add a trigger for the agent name if not already present
-            trigger = f'/{metadata.name}'
-            if not metadata.triggers or trigger not in metadata.triggers:
-                if not metadata.triggers:
-                    metadata.triggers = [trigger]
-                else:
-                    metadata.triggers.append(trigger)
-        elif metadata.triggers:
+        if metadata.triggers:
             inferred_type = MicroagentType.KNOWLEDGE
         else:
             # No triggers, default to REPO
@@ -134,9 +122,7 @@ class BaseMicroagent(BaseModel):
 
 
 class KnowledgeMicroagent(BaseMicroagent):
-    """Knowledge micro-agents provide specialized expertise that's triggered by keywords in conversations.
-
-    They help with:
+    """Knowledge micro-agents provide specialized expertise that's triggered by keywords in conversations. They help with:
     - Language best practices
     - Framework guidelines
     - Common patterns
@@ -145,8 +131,8 @@ class KnowledgeMicroagent(BaseMicroagent):
 
     def __init__(self, **data):
         super().__init__(**data)
-        if self.type not in [MicroagentType.KNOWLEDGE, MicroagentType.TASK]:
-            raise ValueError('KnowledgeMicroagent must have type KNOWLEDGE or TASK')
+        if self.type != MicroagentType.KNOWLEDGE:
+            raise ValueError('KnowledgeMicroagent must have type KNOWLEDGE')
 
     def match_trigger(self, message: str) -> str | None:
         """Match a trigger in the message.
@@ -185,57 +171,6 @@ class RepoMicroagent(BaseMicroagent):
             )
 
 
-class TaskMicroagent(KnowledgeMicroagent):
-    """TaskMicroagent is a special type of KnowledgeMicroagent that requires user input.
-
-    These microagents are triggered by a special format: "/{agent_name}"
-    and will prompt the user for any required inputs before proceeding.
-    """
-
-    def __init__(self, **data):
-        super().__init__(**data)
-        if self.type != MicroagentType.TASK:
-            raise ValueError(
-                f'TaskMicroagent initialized with incorrect type: {self.type}'
-            )
-
-        # Append a prompt to ask for missing variables
-        self._append_missing_variables_prompt()
-
-    def _append_missing_variables_prompt(self) -> None:
-        """Append a prompt to ask for missing variables."""
-        # Check if the content contains any variables or has inputs defined
-        if not self.requires_user_input() and not self.metadata.inputs:
-            return
-
-        prompt = "\n\nIf the user didn't provide any of these variables, ask the user to provide them first before the agent can proceed with the task."
-        self.content += prompt
-
-    def extract_variables(self, content: str) -> list[str]:
-        """Extract variables from the content.
-
-        Variables are in the format ${variable_name}.
-        """
-        pattern = r'\$\{([a-zA-Z_][a-zA-Z0-9_]*)\}'
-        matches = re.findall(pattern, content)
-        return matches
-
-    def requires_user_input(self) -> bool:
-        """Check if this microagent requires user input.
-
-        Returns True if the content contains variables in the format ${variable_name}.
-        """
-        # Check if the content contains any variables
-        variables = self.extract_variables(self.content)
-        logger.debug(f'This microagent requires user input: {variables}')
-        return len(variables) > 0
-
-    @property
-    def inputs(self) -> list[InputMetadata]:
-        """Get the inputs for this microagent."""
-        return self.metadata.inputs
-
-
 def load_microagents_from_dir(
     microagent_dir: Union[str, Path],
 ) -> tuple[dict[str, RepoMicroagent], dict[str, KnowledgeMicroagent]]:
@@ -247,7 +182,7 @@ def load_microagents_from_dir(
         microagent_dir: Path to the microagents directory (e.g. .openhands/microagents)
 
     Returns:
-        Tuple of (repo_agents, knowledge_agents) dictionaries
+        Tuple of (repo_agents, knowledge_agents, task_agents) dictionaries
     """
     if isinstance(microagent_dir, str):
         microagent_dir = Path(microagent_dir)
@@ -267,7 +202,6 @@ def load_microagents_from_dir(
                 if isinstance(agent, RepoMicroagent):
                     repo_agents[agent.name] = agent
                 elif isinstance(agent, KnowledgeMicroagent):
-                    # Both KnowledgeMicroagent and TaskMicroagent go into knowledge_agents
                     knowledge_agents[agent.name] = agent
             except MicroagentValidationError as e:
                 # For validation errors, include the original exception

openhands/microagent/types.py

@@ -12,14 +12,6 @@ class MicroagentType(str, Enum):
 
     KNOWLEDGE = 'knowledge'  # Optional microagent, triggered by keywords
     REPO_KNOWLEDGE = 'repo'  # Always active microagent
-    TASK = 'task'  # Special type for task microagents that require user input
-
-
-class InputMetadata(BaseModel):
-    """Metadata for task microagent inputs."""
-
-    name: str
-    description: str
 
 
 class MicroagentMetadata(BaseModel):
@@ -30,7 +22,6 @@ class MicroagentMetadata(BaseModel):
     version: str = Field(default='1.0.0')
     agent: str = Field(default='CodeActAgent')
     triggers: list[str] = []  # optional, only exists for knowledge microagents
-    inputs: list[InputMetadata] = []  # optional, only exists for task microagents
     mcp_tools: MCPConfig | None = (
         None  # optional, for microagents that provide additional MCP tools
     )

openhands/runtime/action_execution_server.py

@@ -9,6 +9,7 @@ import argparse
 import asyncio
 import base64
 import json
+import logging
 import mimetypes
 import os
 import shutil
@@ -25,6 +26,8 @@ from fastapi import Depends, FastAPI, HTTPException, Request, UploadFile
 from fastapi.exceptions import RequestValidationError
 from fastapi.responses import FileResponse, JSONResponse
 from fastapi.security import APIKeyHeader
+from mcpm import MCPRouter, RouterConfig
+from mcpm.router.router import logger as mcp_router_logger
 from openhands_aci.editor.editor import OHEditor
 from openhands_aci.editor.exceptions import ToolError
 from openhands_aci.editor.results import ToolResult
@@ -34,7 +37,6 @@ from starlette.background import BackgroundTask
 from starlette.exceptions import HTTPException as StarletteHTTPException
 from uvicorn import run
 
-from openhands.core.config.mcp_config import MCPStdioServerConfig
 from openhands.core.exceptions import BrowserUnavailableException
 from openhands.core.logger import openhands_logger as logger
 from openhands.events.action import (
@@ -61,18 +63,21 @@ 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.file_viewer_server import start_file_viewer_server
-
-# Import our custom MCP Proxy Manager
-from openhands.runtime.mcp.proxy import MCPProxyManager
 from openhands.runtime.plugins import ALL_PLUGINS, JupyterPlugin, Plugin, VSCodePlugin
 from openhands.runtime.utils import find_available_tcp_port
+from openhands.runtime.utils.async_bash import AsyncBashSession
 from openhands.runtime.utils.bash import BashSession
 from openhands.runtime.utils.files import insert_lines, read_lines
+from openhands.runtime.utils.log_capture import capture_logs
 from openhands.runtime.utils.memory_monitor import MemoryMonitor
 from openhands.runtime.utils.runtime_init import init_user_and_working_directory
 from openhands.runtime.utils.system_stats import get_system_stats
 from openhands.utils.async_utils import call_sync_from_async, wait_all
 
+# Set MCP router logger to the same level as the main logger
+mcp_router_logger.setLevel(logger.getEffectiveLevel())
+
+
 if sys.platform == 'win32':
     from openhands.runtime.utils.windows_bash import WindowsPowershellSession
 
@@ -249,10 +254,12 @@ class ActionExecutor:
         # If we get here, the browser is ready
         logger.debug('Browser is ready')
 
-    def _create_bash_session(self, cwd: str | None = None):
+    async def ainit(self):
+        # bash needs to be initialized first
+        logger.debug('Initializing bash session')
         if sys.platform == 'win32':
-            return WindowsPowershellSession(  # type: ignore[name-defined]
-                work_dir=cwd or self._initial_cwd,
+            self.bash_session = WindowsPowershellSession(  # type: ignore[name-defined]
+                work_dir=self._initial_cwd,
                 username=self.username,
                 no_change_timeout_seconds=int(
                     os.environ.get('NO_CHANGE_TIMEOUT_SECONDS', 10)
@@ -260,21 +267,15 @@ class ActionExecutor:
                 max_memory_mb=self.max_memory_gb * 1024 if self.max_memory_gb else None,
             )
         else:
-            bash_session = BashSession(
-                work_dir=cwd or self._initial_cwd,
+            self.bash_session = BashSession(
+                work_dir=self._initial_cwd,
                 username=self.username,
                 no_change_timeout_seconds=int(
                     os.environ.get('NO_CHANGE_TIMEOUT_SECONDS', 10)
                 ),
                 max_memory_mb=self.max_memory_gb * 1024 if self.max_memory_gb else None,
             )
-            bash_session.initialize()
-            return bash_session
-
-    async def ainit(self):
-        # bash needs to be initialized first
-        logger.debug('Initializing bash session')
-        self.bash_session = self._create_bash_session()
+            self.bash_session.initialize()
         logger.debug('Bash session initialized')
 
         # Start browser initialization in the background
@@ -387,11 +388,18 @@ class ActionExecutor:
         self, action: CmdRunAction
     ) -> CmdOutputObservation | ErrorObservation:
         try:
-            bash_session = self.bash_session
             if action.is_static:
-                bash_session = self._create_bash_session(action.cwd)
-            assert bash_session is not None
-            obs = await call_sync_from_async(bash_session.execute, action)
+                path = action.cwd or self._initial_cwd
+                result = await AsyncBashSession.execute(action.command, path)
+                obs = CmdOutputObservation(
+                    content=result.content,
+                    exit_code=result.exit_code,
+                    command=action.command,
+                )
+                return obs
+
+            assert self.bash_session is not None
+            obs = await call_sync_from_async(self.bash_session.execute, action)
             return obs
         except Exception as e:
             logger.error(f'Error running command: {e}')
@@ -467,7 +475,7 @@ class ActionExecutor:
         filepath = self._resolve_path(action.path, working_dir)
         try:
             if filepath.lower().endswith(('.png', '.jpg', '.jpeg', '.bmp', '.gif')):
-                with open(filepath, 'rb') as file:
+                with open(filepath, 'rb') as file:  # noqa: ASYNC101
                     image_data = file.read()
                     encoded_image = base64.b64encode(image_data).decode('utf-8')
                     mime_type, _ = mimetypes.guess_type(filepath)
@@ -477,13 +485,13 @@ class ActionExecutor:
 
                 return FileReadObservation(path=filepath, content=encoded_image)
             elif filepath.lower().endswith('.pdf'):
-                with open(filepath, 'rb') as file:
+                with open(filepath, 'rb') as file:  # noqa: ASYNC101
                     pdf_data = file.read()
                     encoded_pdf = base64.b64encode(pdf_data).decode('utf-8')
                     encoded_pdf = f'data:application/pdf;base64,{encoded_pdf}'
                 return FileReadObservation(path=filepath, content=encoded_pdf)
             elif filepath.lower().endswith(('.mp4', '.webm', '.ogg')):
-                with open(filepath, 'rb') as file:
+                with open(filepath, 'rb') as file:  # noqa: ASYNC101
                     video_data = file.read()
                     encoded_video = base64.b64encode(video_data).decode('utf-8')
                     mime_type, _ = mimetypes.guess_type(filepath)
@@ -493,7 +501,7 @@ class ActionExecutor:
 
                 return FileReadObservation(path=filepath, content=encoded_video)
 
-            with open(filepath, 'r', encoding='utf-8') as file:
+            with open(filepath, 'r', encoding='utf-8') as file:  # noqa: ASYNC101
                 lines = read_lines(file.readlines(), action.start, action.end)
         except FileNotFoundError:
             return ErrorObservation(
@@ -526,7 +534,7 @@ class ActionExecutor:
 
         mode = 'w' if not file_exists else 'r+'
         try:
-            with open(filepath, mode, encoding='utf-8') as file:
+            with open(filepath, mode, encoding='utf-8') as file:  # noqa: ASYNC101
                 if mode != 'w':
                     all_lines = file.readlines()
                     new_file = insert_lines(insert, all_lines, action.start, action.end)
@@ -650,11 +658,14 @@ if __name__ == '__main__':
             plugins_to_load.append(ALL_PLUGINS[plugin]())  # type: ignore
 
     client: ActionExecutor | None = None
-    mcp_proxy_manager: MCPProxyManager | None = None
+    mcp_router: MCPRouter | None = None
+    MCP_ROUTER_PROFILE_PATH = os.path.join(
+        os.path.dirname(__file__), 'mcp', 'config.json'
+    )
 
     @asynccontextmanager
     async def lifespan(app: FastAPI):
-        global client, mcp_proxy_manager
+        global client, mcp_router
         logger.info('Initializing ActionExecutor...')
         client = ActionExecutor(
             plugins_to_load,
@@ -669,36 +680,63 @@ if __name__ == '__main__':
         # Check if we're on Windows
         is_windows = sys.platform == 'win32'
 
-        # Initialize and mount MCP Proxy Manager (skip on Windows)
+        # Initialize and mount MCP Router (skip on Windows)
         if is_windows:
-            logger.info('Skipping MCP Proxy initialization on Windows')
-            mcp_proxy_manager = None
+            logger.info('Skipping MCP Router initialization on Windows')
+            mcp_router = None
         else:
-            logger.info('Initializing MCP Proxy Manager...')
-            # Create a MCP Proxy Manager
-            mcp_proxy_manager = MCPProxyManager(
-                auth_enabled=bool(SESSION_API_KEY),
-                api_key=SESSION_API_KEY,
-                logger_level=logger.getEffectiveLevel(),
+            logger.info('Initializing MCP Router...')
+            mcp_router = MCPRouter(
+                profile_path=MCP_ROUTER_PROFILE_PATH,
+                router_config=RouterConfig(
+                    api_key=SESSION_API_KEY,
+                    auth_enabled=bool(SESSION_API_KEY),
+                ),
             )
-            mcp_proxy_manager.initialize()
-            # Mount the proxy to the app
             allowed_origins = ['*']
-            try:
-                await mcp_proxy_manager.mount_to_app(app, allowed_origins)
-            except Exception as e:
-                logger.error(f'Error mounting MCP Proxy: {e}', exc_info=True)
-                raise RuntimeError(f'Cannot mount MCP Proxy: {e}')
+            sse_app = await mcp_router.get_sse_server_app(
+                allow_origins=allowed_origins, include_lifespan=False
+            )
+
+        # Only mount SSE app if MCP Router is initialized (not on Windows)
+        if mcp_router is not None:
+            # Check for route conflicts before mounting
+            main_app_routes = {route.path for route in app.routes}
+            sse_app_routes = {route.path for route in sse_app.routes}
+            conflicting_routes = main_app_routes.intersection(sse_app_routes)
+
+            if conflicting_routes:
+                logger.error(f'Route conflicts detected: {conflicting_routes}')
+                raise RuntimeError(
+                    f'Cannot mount SSE app - conflicting routes found: {conflicting_routes}'
+                )
+
+            app.mount('/', sse_app)
+            logger.info(
+                f'Mounted MCP Router SSE app at root path with allowed origins: {allowed_origins}'
+            )
+
+            # Additional debug logging
+            if logger.isEnabledFor(logging.DEBUG):
+                logger.debug('Main app routes:')
+                for route in main_app_routes:
+                    logger.debug(f'  {route}')
+                logger.debug('MCP SSE server app routes:')
+                for route in sse_app_routes:
+                    logger.debug(f'  {route}')
 
         yield
 
         # Clean up & release the resources
-        logger.info('Shutting down MCP Proxy Manager...')
-        if mcp_proxy_manager:
-            del mcp_proxy_manager
-            mcp_proxy_manager = None
+        logger.info('Shutting down MCP Router...')
+        if mcp_router:
+            try:
+                await mcp_router.shutdown()
+                logger.info('MCP Router shutdown successfully.')
+            except Exception as e:
+                logger.error(f'Error shutting down MCP Router: {e}', exc_info=True)
         else:
-            logger.info('MCP Proxy Manager instance not found for shutdown.')
+            logger.info('MCP Router instance not found for shutdown.')
 
         logger.info('Closing ActionExecutor...')
         if client:
@@ -790,9 +828,6 @@ if __name__ == '__main__':
         # Check if we're on Windows
         is_windows = sys.platform == 'win32'
 
-        # Access the global mcp_proxy_manager variable
-        global mcp_proxy_manager
-
         if is_windows:
             # On Windows, just return a success response without doing anything
             logger.info(
@@ -807,10 +842,17 @@ if __name__ == '__main__':
             )
 
         # Non-Windows implementation
-        if mcp_proxy_manager is None:
-            raise HTTPException(
-                status_code=500, detail='MCP Proxy Manager is not initialized'
-            )
+        assert mcp_router is not None
+        assert os.path.exists(MCP_ROUTER_PROFILE_PATH)
+
+        # Use synchronous file operations outside of async function
+        def read_profile():
+            with open(MCP_ROUTER_PROFILE_PATH, 'r') as f:
+                return json.load(f)
+
+        current_profile = read_profile()
+        assert 'default' in current_profile
+        assert isinstance(current_profile['default'], list)
 
         # Get the request body
         mcp_tools_to_sync = await request.json()
@@ -818,17 +860,31 @@ if __name__ == '__main__':
             raise HTTPException(
                 status_code=400, detail='Request must be a list of MCP tools to sync'
             )
+
         logger.info(
-            f'Updating MCP server with tools: {json.dumps(mcp_tools_to_sync, indent=2)}'
+            f'Updating MCP server to: {json.dumps(mcp_tools_to_sync, indent=2)}.\nPrevious profile: {json.dumps(current_profile, indent=2)}'
         )
-        mcp_tools_to_sync = [MCPStdioServerConfig(**tool) for tool in mcp_tools_to_sync]
-        try:
-            await mcp_proxy_manager.update_and_remount(app, mcp_tools_to_sync, ['*'])
-            logger.info('MCP Proxy Manager updated and remounted successfully')
-            router_error_log = ''
-        except Exception as e:
-            logger.error(f'Error updating MCP Proxy Manager: {e}', exc_info=True)
-            router_error_log = str(e)
+        current_profile['default'] = mcp_tools_to_sync
+
+        # Use synchronous file operations outside of async function
+        def write_profile(profile):
+            with open(MCP_ROUTER_PROFILE_PATH, 'w') as f:
+                json.dump(profile, f)
+
+        write_profile(current_profile)
+
+        # Manually reload the profile and update the servers
+        mcp_router.profile_manager.reload()
+        servers_wait_for_update = mcp_router.get_unique_servers()
+        async with capture_logs('mcpm.router.router') as log_capture:
+            await mcp_router.update_servers(servers_wait_for_update)
+        router_error_log = log_capture.getvalue()
+
+        logger.info(
+            f'MCP router updated successfully with unique servers: {servers_wait_for_update}'
+        )
+        if router_error_log:
+            logger.warning(f'Some MCP servers failed to be added: {router_error_log}')
 
         return JSONResponse(
             status_code=200,
@@ -863,7 +919,7 @@ if __name__ == '__main__':
                     )
 
                 zip_path = os.path.join(full_dest_path, file.filename)
-                with open(zip_path, 'wb') as buffer:
+                with open(zip_path, 'wb') as buffer:  # noqa: ASYNC101
                     shutil.copyfileobj(file.file, buffer)
 
                 # Extract the zip file
@@ -876,7 +932,7 @@ if __name__ == '__main__':
             else:
                 # For single file uploads
                 file_path = os.path.join(full_dest_path, file.filename)
-                with open(file_path, 'wb') as buffer:
+                with open(file_path, 'wb') as buffer:  # noqa: ASYNC101
                     shutil.copyfileobj(file.file, buffer)
                 logger.debug(f'Uploaded file {file.filename} to {destination}')
 

openhands/runtime/base.py

@@ -400,7 +400,7 @@ class Runtime(FileEditRuntimeMixin):
                     'No repository selected. Initializing a new git repository in the workspace.'
                 )
                 action = CmdRunAction(
-                    command=f'git init && git config --global --add safe.directory {self.workspace_root}'
+                    command='git init',
                 )
                 self.run_action(action)
             else:
@@ -952,9 +952,6 @@ fi
         exit_code = 0
         content = ''
 
-        if isinstance(obs, ErrorObservation):
-            exit_code = -1
-
         if hasattr(obs, 'exit_code'):
             exit_code = obs.exit_code
         if hasattr(obs, 'content'):

openhands/runtime/impl/action_execution/action_execution_client.py

@@ -406,7 +406,7 @@ class ActionExecutionClient(Runtime):
                 'POST',
                 f'{self.action_execution_server_url}/update_mcp_server',
                 json=stdio_tools,
-                timeout=60,
+                timeout=10,
             )
             result = response.json()
             if response.status_code != 200:
@@ -435,7 +435,7 @@ class ActionExecutionClient(Runtime):
             # We should always include the runtime as an MCP server whenever there's > 0 stdio servers
             updated_mcp_config.sse_servers.append(
                 MCPSSEServerConfig(
-                    url=self.action_execution_server_url.rstrip('/') + '/mcp/sse',
+                    url=self.action_execution_server_url.rstrip('/') + '/sse',
                     api_key=self.session_api_key,
                 )
             )
@@ -464,13 +464,16 @@ class ActionExecutionClient(Runtime):
         )
 
         # Create clients for this specific operation
-        mcp_clients = await create_mcp_clients(
-            updated_mcp_config.sse_servers, updated_mcp_config.shttp_servers, self.sid
-        )
+        mcp_clients = await create_mcp_clients(updated_mcp_config.sse_servers, updated_mcp_config.shttp_servers, self.sid)
 
         # Call the tool and return the result
         # No need for try/finally since disconnect() is now just resetting state
         result = await call_tool_mcp_handler(mcp_clients, action)
+
+        # Reset client state (no active connections to worry about)
+        for client in mcp_clients:
+            await client.disconnect()
+
         return result
 
     def close(self) -> None:

openhands/runtime/mcp/config.json

@@ -1,6 +1,3 @@
 {
-    "mcpServers": {
-        "default": {}
-    },
-    "tools": []
+    "default": []
 }

openhands/runtime/mcp/proxy/README.md

@@ -1,71 +0,0 @@
-# MCP Proxy Manager
-
-This module provides a manager class for handling FastMCP proxy instances in OpenHands, including initialization, configuration, and mounting to FastAPI applications.
-
-## Overview
-
-The `MCPProxyManager` class encapsulates all the functionality related to creating, configuring, and managing FastMCP proxy instances. It simplifies the process of:
-
-1. Initializing a FastMCP proxy
-2. Configuring the proxy with tools
-3. Mounting the proxy to a FastAPI application
-4. Updating the proxy configuration
-5. Shutting down the proxy
-
-## Usage
-
-### Basic Usage
-
-```python
-from openhands.runtime.mcp.proxy import MCPProxyManager
-from fastapi import FastAPI
-
-# Create a FastAPI app
-app = FastAPI()
-
-# Create a proxy manager
-proxy_manager = MCPProxyManager(
-    name="MyProxyServer",
-    auth_enabled=True,
-    api_key="my-api-key"
-)
-
-# Initialize the proxy
-proxy_manager.initialize()
-
-# Mount the proxy to the app
-await proxy_manager.mount_to_app(app, allow_origins=["*"])
-
-# Update the tools configuration
-tools = [
-    {
-        "name": "my_tool",
-        "description": "My tool description",
-        "parameters": {...}
-    }
-]
-proxy_manager.update_tools(tools)
-
-# Update and remount the proxy
-await proxy_manager.update_and_remount(app, tools, allow_origins=["*"])
-
-# Shutdown the proxy
-await proxy_manager.shutdown()
-```
-
-### In-Memory Configuration
-
-The `MCPProxyManager` maintains the configuration in-memory, eliminating the need for file-based configuration. This makes it easier to update the configuration and reduces the complexity of the code.
-
-## Benefits
-
-1. **Simplified API**: The `MCPProxyManager` provides a simple and intuitive API for managing FastMCP proxies.
-2. **In-Memory Configuration**: Configuration is maintained in-memory, eliminating the need for file I/O operations.
-3. **Improved Error Handling**: The manager provides better error handling and logging for proxy operations.
-4. **Cleaner Code**: By encapsulating proxy-related functionality in a dedicated class, the code is more maintainable and easier to understand.
-
-## Implementation Details
-
-The `MCPProxyManager` uses the `FastMCP.as_proxy()` method to create a proxy server. It manages the lifecycle of the proxy, including initialization, configuration updates, and shutdown.
-
-When updating the tools configuration, the manager creates a new proxy with the updated configuration and remounts it to the FastAPI application, ensuring that the proxy is always up-to-date with the latest configuration.

openhands/runtime/mcp/proxy/__init__.py

@@ -1,7 +0,0 @@
-"""
-MCP Proxy module for OpenHands.
-"""
-
-from openhands.runtime.mcp.proxy.manager import MCPProxyManager
-
-__all__ = ['MCPProxyManager']

openhands/runtime/mcp/proxy/manager.py

@@ -1,138 +0,0 @@
-"""
-MCP Proxy Manager for OpenHands.
-
-This module provides a manager class for handling FastMCP proxy instances,
-including initialization, configuration, and mounting to FastAPI applications.
-"""
-
-import logging
-from typing import Any, Optional
-
-from fastapi import FastAPI
-from fastmcp import FastMCP
-from fastmcp.utilities.logging import get_logger as fastmcp_get_logger
-
-from openhands.core.config.mcp_config import MCPStdioServerConfig
-
-logger = logging.getLogger(__name__)
-fastmcp_logger = fastmcp_get_logger('fastmcp')
-
-
-class MCPProxyManager:
-    """
-    Manager for FastMCP proxy instances.
-
-    This class encapsulates all the functionality related to creating, configuring,
-    and managing FastMCP proxy instances, including mounting them to FastAPI applications.
-    """
-
-    def __init__(
-        self,
-        auth_enabled: bool = False,
-        api_key: Optional[str] = None,
-        logger_level: Optional[int] = None,
-    ):
-        """
-        Initialize the MCP Proxy Manager.
-
-        Args:
-            name: Name of the proxy server
-            auth_enabled: Whether authentication is enabled
-            api_key: API key for authentication (required if auth_enabled is True)
-            logger_level: Logging level for the FastMCP logger
-        """
-        self.auth_enabled = auth_enabled
-        self.api_key = api_key
-        self.proxy: Optional[FastMCP] = None
-        # Initialize with a valid configuration format for FastMCP
-        self.config: dict[str, Any] = {
-            'mcpServers': {},
-        }
-
-        # Configure FastMCP logger
-        if logger_level is not None:
-            fastmcp_logger.setLevel(logger_level)
-
-    def initialize(self) -> None:
-        """
-        Initialize the FastMCP proxy with the current configuration.
-        """
-        if len(self.config['mcpServers']) == 0:
-            logger.info(
-                f"No MCP servers configured for FastMCP Proxy, skipping initialization."
-            )
-            return None
-
-        # Create a new proxy with the current configuration
-        self.proxy = FastMCP.as_proxy(
-            self.config,
-            auth_enabled=self.auth_enabled,
-            api_key=self.api_key,
-        )
-
-        logger.info(f"FastMCP Proxy initialized successfully")
-
-    async def mount_to_app(
-        self, app: FastAPI, allow_origins: Optional[list[str]] = None
-    ) -> None:
-        """
-        Mount the SSE server app to a FastAPI application.
-
-        Args:
-            app: FastAPI application to mount to
-            allow_origins: List of allowed origins for CORS
-        """
-        if len(self.config['mcpServers']) == 0:
-            logger.info(
-                f"No MCP servers configured for FastMCP Proxy, skipping mount."
-            )
-            return
-
-        if not self.proxy:
-            raise ValueError('FastMCP Proxy is not initialized')
-
-        # Get the SSE app
-        # mcp_app = self.proxy.http_app(path='/shttp')
-        mcp_app = self.proxy.http_app(path='/sse', transport='sse')
-        app.mount('/mcp', mcp_app)
-
-        # Remove any existing mounts at root path
-        if '/mcp' in app.routes:
-            app.routes.remove('/mcp')
-
-        app.mount('/', mcp_app)
-        logger.info(f"Mounted FastMCP Proxy app at /mcp")
-
-
-    async def update_and_remount(
-        self,
-        app: FastAPI,
-        stdio_servers: list[MCPStdioServerConfig],
-        allow_origins: Optional[list[str]] = None,
-    ) -> None:
-        """
-        Update the tools configuration and remount the proxy to the app.
-
-        This is a convenience method that combines updating the tools,
-        shutting down the existing proxy, initializing a new one, and
-        mounting it to the app.
-
-        Args:
-            app: FastAPI application to mount to
-            tools: List of tool configurations
-            allow_origins: List of allowed origins for CORS
-        """
-        tools = {
-            t.name: t.model_dump()
-            for t in stdio_servers
-        }
-        self.config['mcpServers'] = tools
-
-        del self.proxy
-        self.proxy = None
-
-        # Initialize a new proxy
-        self.initialize()
-
-        # Mount the new proxy to the app
-        await self.mount_to_app(app, allow_origins)

openhands/runtime/utils/async_bash.py

@@ -0,0 +1,54 @@
+import asyncio
+import os
+
+from openhands.runtime.base import CommandResult
+
+
+class AsyncBashSession:
+    @staticmethod
+    async def execute(command: str, work_dir: str) -> CommandResult:
+        """Execute a command in the bash session asynchronously."""
+        work_dir = os.path.abspath(work_dir)
+
+        if not os.path.exists(work_dir):
+            raise ValueError(f'Work directory {work_dir} does not exist.')
+
+        command = command.strip()
+        if not command:
+            return CommandResult(content='', exit_code=0)
+
+        try:
+            process = await asyncio.subprocess.create_subprocess_shell(
+                command,
+                stdout=asyncio.subprocess.PIPE,
+                stderr=asyncio.subprocess.PIPE,
+                cwd=work_dir,
+            )
+
+            try:
+                stdout, stderr = await asyncio.wait_for(
+                    process.communicate(), timeout=30
+                )
+                output = stdout.decode('utf-8')
+
+                if stderr:
+                    output = stderr.decode('utf-8')
+                    print(f'!##! Error running command: {stderr.decode("utf-8")}')
+
+                return CommandResult(content=output, exit_code=process.returncode or 0)
+
+            except asyncio.TimeoutError:
+                process.terminate()
+
+                # Allow a brief moment for cleanup
+                try:
+                    await asyncio.wait_for(process.wait(), timeout=1.0)
+                except asyncio.TimeoutError:
+                    process.kill()  # Force kill if it doesn't terminate cleanly
+
+                return CommandResult(content='Command timed out.', exit_code=-1)
+
+        except Exception as e:
+            return CommandResult(
+                content=f'Error running command: {str(e)}', exit_code=-1
+            )

openhands/runtime/utils/bash.py

@@ -17,7 +17,6 @@ from openhands.events.observation.commands import (
     CmdOutputMetadata,
     CmdOutputObservation,
 )
-from openhands.runtime.utils.bash_constants import TIMEOUT_MESSAGE_TEMPLATE
 from openhands.utils.shutdown_listener import should_continue
 
 
@@ -380,7 +379,9 @@ class BashSession:
         metadata = CmdOutputMetadata()  # No metadata available
         metadata.suffix = (
             f'\n[The command has no new output after {self.NO_CHANGE_TIMEOUT_SECONDS} seconds. '
-            f'{TIMEOUT_MESSAGE_TEMPLATE}]'
+            "You may wait longer to see additional output by sending empty command '', "
+            'send other commands to interact with the current process, '
+            'or send keys to interrupt/kill the command.]'
         )
         command_output = self._get_command_output(
             command,
@@ -413,7 +414,9 @@ class BashSession:
         metadata = CmdOutputMetadata()  # No metadata available
         metadata.suffix = (
             f'\n[The command timed out after {timeout} seconds. '
-            f'{TIMEOUT_MESSAGE_TEMPLATE}]'
+            "You may wait longer to see additional output by sending empty command '', "
+            'send other commands to interact with the current process, '
+            'or send keys to interrupt/kill the command.]'
         )
         command_output = self._get_command_output(
             command,

openhands/runtime/utils/bash_constants.py

@@ -1,7 +0,0 @@
-# Common timeout message that can be used across different timeout scenarios
-TIMEOUT_MESSAGE_TEMPLATE = (
-    "You may wait longer to see additional output by sending empty command '', "
-    'send other commands to interact with the current process, '
-    'send keys to interrupt/kill the command, '
-    'or use the timeout parameter in execute_bash for future commands.'
-)

openhands/runtime/utils/git_handler.py

@@ -44,7 +44,7 @@ class GitHandler:
         Returns:
             bool: True if inside a Git repository, otherwise False.
         """
-        cmd = 'git --no-pager rev-parse --is-inside-work-tree'
+        cmd = 'git rev-parse --is-inside-work-tree'
         output = self.execute(cmd, self.cwd)
         return output.content.strip() == 'true'
 
@@ -71,7 +71,7 @@ class GitHandler:
         Returns:
             bool: True if the reference exists, otherwise False.
         """
-        cmd = f'git --no-pager rev-parse --verify {ref}'
+        cmd = f'git rev-parse --verify {ref}'
         output = self.execute(cmd, self.cwd)
         return output.exit_code == 0
 
@@ -86,9 +86,9 @@ class GitHandler:
         default_branch = self._get_default_branch()
 
         ref_current_branch = f'origin/{current_branch}'
-        ref_non_default_branch = f'$(git --no-pager merge-base HEAD "$(git --no-pager rev-parse --abbrev-ref origin/{default_branch})")'
+        ref_non_default_branch = f'$(git merge-base HEAD "$(git rev-parse --abbrev-ref origin/{default_branch})")'
         ref_default_branch = 'origin/' + default_branch
-        ref_new_repo = '$(git --no-pager rev-parse --verify 4b825dc642cb6eb9a060e54bf8d69288fbee4904)'  # compares with empty tree
+        ref_new_repo = '$(git rev-parse --verify 4b825dc642cb6eb9a060e54bf8d69288fbee4904)'  # compares with empty tree
 
         refs = [
             ref_current_branch,
@@ -116,7 +116,7 @@ class GitHandler:
         if not ref:
             return ''
 
-        cmd = f'git --no-pager show {ref}:{file_path}'
+        cmd = f'git show {ref}:{file_path}'
         output = self.execute(cmd, self.cwd)
         return output.content if output.exit_code == 0 else ''
 
@@ -127,7 +127,7 @@ class GitHandler:
         Returns:
             str: The name of the primary branch.
         """
-        cmd = 'git --no-pager remote show origin | grep "HEAD branch"'
+        cmd = 'git remote show origin | grep "HEAD branch"'
         output = self.execute(cmd, self.cwd)
         return output.content.split()[-1].strip()
 
@@ -138,7 +138,7 @@ class GitHandler:
         Returns:
             str: The name of the current branch.
         """
-        cmd = 'git --no-pager rev-parse --abbrev-ref HEAD'
+        cmd = 'git rev-parse --abbrev-ref HEAD'
         output = self.execute(cmd, self.cwd)
         return output.content.strip()
 
@@ -153,12 +153,8 @@ class GitHandler:
         if not ref:
             return []
 
-        diff_cmd = f'git --no-pager diff --name-status {ref}'
+        diff_cmd = f'git diff --name-status {ref}'
         output = self.execute(diff_cmd, self.cwd)
-        if output.exit_code != 0:
-            raise RuntimeError(
-                f'Failed to get diff for ref {ref} in {self.cwd}. Command output: {output.content}'
-            )
         return output.content.splitlines()
 
     def _get_untracked_files(self) -> list[dict[str, str]]:
@@ -168,7 +164,7 @@ class GitHandler:
         Returns:
             list[dict[str, str]]: A list of dictionaries containing file paths and statuses.
         """
-        cmd = 'git --no-pager ls-files --others --exclude-standard'
+        cmd = 'git ls-files --others --exclude-standard'
         output = self.execute(cmd, self.cwd)
         obs_list = output.content.splitlines()
         return (

openhands/runtime/utils/windows_bash.py

@@ -20,7 +20,6 @@ from openhands.events.observation.commands import (
     CmdOutputMetadata,
     CmdOutputObservation,
 )
-from openhands.runtime.utils.bash_constants import TIMEOUT_MESSAGE_TEMPLATE
 from openhands.utils.shutdown_listener import should_continue
 
 pythonnet.load('coreclr')
@@ -560,7 +559,9 @@ class WindowsPowershellSession:
             else:
                 metadata.suffix = (
                     f'\n[The command timed out after {timeout_seconds} seconds. '
-                    f'{TIMEOUT_MESSAGE_TEMPLATE}]'
+                    "You may wait longer to see additional output by sending empty command '', "
+                    'send other commands to interact with the current process, '
+                    'or send keys to interrupt/kill the command.]'
                 )
 
             return CmdOutputObservation(
@@ -1330,7 +1331,9 @@ class WindowsPowershellSession:
             # Align suffix with bash.py timeout message
             suffix = (
                 f'\n[The command timed out after {timeout_seconds} seconds. '
-                f'{TIMEOUT_MESSAGE_TEMPLATE}]'
+                "You may wait longer to see additional output by sending empty command '', "
+                'send other commands to interact with the current process, '
+                'or send keys to interrupt/kill the command.]'
             )
         elif shutdown_requested:
             # Align suffix with bash.py equivalent (though bash.py might not have specific shutdown message)

openhands/server/conversation_manager/docker_nested_conversation_manager.py

@@ -281,31 +281,7 @@ class DockerNestedConversationManager(ConversationManager):
         raise ValueError('unsupported_operation')
 
     async def close_session(self, sid: str):
-        # First try to graceful stop server.
-        try:
-            container = self.docker_client.containers.get(f'openhands-runtime-{sid}')
-        except docker.errors.NotFound as e:
-            return
-        try:
-            nested_url = self.get_nested_url_for_container(container)
-            async with httpx.AsyncClient(
-                headers={
-                    'X-Session-API-Key': self._get_session_api_key_for_conversation(sid)
-                }
-            ) as client:
-                response = await client.post(f'{nested_url}/api/conversations/{sid}/stop')
-                response.raise_for_status()
-
-                # Check up to 3 times that client has closed
-                for _ in range(3):
-                    response = await client.get(f'{nested_url}/api/conversations/{sid}')
-                    if response.status_code == status.HTTP_200_OK and response.json().get('status') == "STOPPED":
-                        break
-                    await asyncio.sleep(1)
-
-        except Exception:
-            logger.exception("error_stopping_container")
-        container.stop()
+        stop_all_containers(f'openhands-runtime-{sid}')
 
     async def get_agent_loop_info(self, user_id: str | None = None, filter_to_sids: set[str] | None = None) -> list[AgentLoopInfo]:
         results = []

openhands/server/conversation_manager/standalone_conversation_manager.py

@@ -369,9 +369,7 @@ class StandaloneConversationManager(ConversationManager):
             f'removing connections: {connection_ids_to_remove}',
             extra={'session_id': sid},
         )
-        # Perform a graceful shutdown of each connection
         for connection_id in connection_ids_to_remove:
-            await self.sio.disconnect(connection_id)
             self._local_connection_id_to_session_id.pop(connection_id, None)
 
         session = self._local_agent_loops_by_sid.pop(sid, None)

openhands/server/listen_socket.py

@@ -12,7 +12,6 @@ from openhands.events.action import (
 )
 from openhands.events.action.agent import RecallAction
 from openhands.events.async_event_store_wrapper import AsyncEventStoreWrapper
-from openhands.events.event_store import EventStore
 from openhands.events.observation import (
     NullObservation,
 )
@@ -125,48 +124,6 @@ async def connect(connection_id: str, environ: dict) -> None:
             f'User {user_id} is allowed to connect to conversation {conversation_id}'
         )
 
-        try:
-            event_store = EventStore(
-                conversation_id, conversation_manager.file_store, user_id
-            )
-        except FileNotFoundError as e:
-            logger.error(
-                f'Failed to create EventStore for conversation {conversation_id}: {e}'
-            )
-            raise ConnectionRefusedError(f'Failed to access conversation events: {e}')
-
-        logger.info(
-            f'Replaying event stream for conversation {conversation_id} with connection_id {connection_id}...'
-        )
-        agent_state_changed = None
-
-        # Create an async store to replay events
-        async_store = AsyncEventStoreWrapper(event_store, latest_event_id + 1)
-
-        # Process all available events
-        async for event in async_store:
-            logger.debug(f'oh_event: {event.__class__.__name__}')
-
-            if isinstance(
-                event,
-                (NullAction, NullObservation, RecallAction),
-            ):
-                continue
-            elif isinstance(event, AgentStateChangedObservation):
-                agent_state_changed = event
-            else:
-                await sio.emit('oh_event', event_to_dict(event), to=connection_id)
-
-        # Send the agent state changed event last if we have one
-        if agent_state_changed:
-            await sio.emit(
-                'oh_event', event_to_dict(agent_state_changed), to=connection_id
-            )
-
-        logger.info(
-            f'Finished replaying event stream for conversation {conversation_id}'
-        )
-
         conversation_init_data = await setup_init_convo_settings(
             user_id, conversation_id, providers_set
         )
@@ -176,12 +133,32 @@ async def connect(connection_id: str, environ: dict) -> None:
             conversation_init_data,
             user_id,
         )
-
+        logger.info(
+            f'Connected to conversation {conversation_id} with connection_id {connection_id}. Replaying event stream...'
+        )
+        agent_state_changed = None
         if agent_loop_info is None:
             raise ConnectionRefusedError('Failed to join conversation')
-
+        async_store = AsyncEventStoreWrapper(
+            agent_loop_info.event_store, latest_event_id + 1
+        )
+        async for event in async_store:
+            logger.debug(f'oh_event: {event.__class__.__name__}')
+            if isinstance(
+                event,
+                (NullAction, NullObservation, RecallAction),
+            ):
+                continue
+            elif isinstance(event, AgentStateChangedObservation):
+                agent_state_changed = event
+            else:
+                await sio.emit('oh_event', event_to_dict(event), to=connection_id)
+        if agent_state_changed:
+            await sio.emit(
+                'oh_event', event_to_dict(agent_state_changed), to=connection_id
+            )
         logger.info(
-            f'Successfully joined conversation {conversation_id} with connection_id {connection_id}'
+            f'Finished replaying event stream for conversation {conversation_id}'
         )
     except ConnectionRefusedError:
         # Close the broken connection after sending an error message

openhands/server/routes/mcp.py

@@ -1,4 +1,3 @@
-import os
 import re
 from typing import Annotated
 
@@ -11,10 +10,9 @@ from openhands.core.logger import openhands_logger as logger
 from openhands.integrations.github.github_service import GithubServiceImpl
 from openhands.integrations.gitlab.gitlab_service import GitLabServiceImpl
 from openhands.integrations.provider import ProviderToken
-from openhands.integrations.service_types import GitService, ProviderType
+from openhands.integrations.service_types import ProviderType
 from openhands.server.dependencies import get_dependencies
-from openhands.server.shared import ConversationStoreImpl, config, server_config
-from openhands.server.types import AppMode
+from openhands.server.shared import ConversationStoreImpl, config
 from openhands.server.user_auth import (
     get_access_token,
     get_provider_tokens,
@@ -22,34 +20,10 @@ from openhands.server.user_auth import (
 )
 from openhands.storage.data_models.conversation_metadata import ConversationMetadata
 
-mcp_server = FastMCP(
-    'mcp', stateless_http=True, dependencies=get_dependencies(), mask_error_details=True
-)
-
-HOST = f'https://{os.getenv("WEB_HOST", "app.all-hands.dev").strip()}'
-CONVO_URL = HOST + '/{}'
-
-
-async def get_convo_link(service: GitService, conversation_id: str, body: str) -> str:
-    """
-    Appends a followup link, in the PR body, to the OpenHands conversation that opened the PR
-    """
-
-    if server_config.app_mode != AppMode.SAAS:
-        return body
-
-    user = await service.get_user()
-    username = user.login
-    convo_url = CONVO_URL.format(conversation_id)
-    convo_link = (
-        f'@{username} can click here to [continue refining the PR]({convo_url})'
-    )
-    body += f'\n\n{convo_link}'
-    return body
-
+mcp_server = FastMCP('mcp', stateless_http=True, dependencies=get_dependencies(), mask_error_details=True)
 
 async def save_pr_metadata(
-    user_id: str | None, conversation_id: str, tool_result: str
+    user_id: str, conversation_id: str, tool_result: str
 ) -> None:
     conversation_store = await ConversationStoreImpl.get_instance(config, user_id)
     conversation: ConversationMetadata = await conversation_store.get_metadata(
@@ -70,11 +44,7 @@ async def save_pr_metadata(
         pr_number = int(match_merge_request.group(1))
 
     if pr_number:
-        logger.info(f'Saving PR number: {pr_number} for convo {conversation_id}')
         conversation.pr_number.append(pr_number)
-    else:
-        logger.warning(f'Failed to extract PR number for convo {conversation_id}')
-
     await conversation_store.save_metadata(conversation)
 
 
@@ -114,11 +84,6 @@ async def create_pr(
         base_domain=github_token.host,
     )
 
-    try:
-        body = await get_convo_link(github_service, conversation_id, body or '')
-    except Exception as e:
-        logger.warning(f'Failed to append convo link: {e}')
-
     try:
         response = await github_service.create_pr(
             repo_name=repo_name,
@@ -128,11 +93,11 @@ async def create_pr(
             body=body,
         )
 
-        if conversation_id:
+        if conversation_id and user_id:
             await save_pr_metadata(user_id, conversation_id, response)
 
     except Exception as e:
-        error = f'Error creating pull request: {e}'
+        error = f"Error creating pull request: {e}"
         raise ToolError(str(error))
 
     return response
@@ -167,7 +132,7 @@ async def create_mr(
         else ProviderToken()
     )
 
-    gitlab_service = GitLabServiceImpl(
+    github_service = GitLabServiceImpl(
         user_id=github_token.user_id,
         external_auth_id=user_id,
         external_auth_token=access_token,
@@ -176,14 +141,7 @@ async def create_mr(
     )
 
     try:
-        description = await get_convo_link(
-            gitlab_service, conversation_id, description or ''
-        )
-    except Exception as e:
-        logger.warning(f'Failed to append convo link: {e}')
-
-    try:
-        response = await gitlab_service.create_mr(
+        response = await github_service.create_mr(
             id=id,
             source_branch=source_branch,
             target_branch=target_branch,
@@ -195,7 +153,7 @@ async def create_mr(
             await save_pr_metadata(user_id, conversation_id, response)
 
     except Exception as e:
-        error = f'Error creating merge request: {e}'
+        error = f"Error creating merge request: {e}"
         raise ToolError(str(error))
 
     return response

openhands/server/services/conversation_service.py

@@ -124,8 +124,8 @@ async def create_new_conversation(
             image_urls=image_urls or [],
         )
 
-    if attach_convo_id:
-        logger.warning('Attaching convo ID is deprecated, skipping process')
+    if attach_convo_id and conversation_instructions:
+        conversation_instructions = conversation_instructions.format(conversation_id)
 
     agent_loop_info = await conversation_manager.maybe_start_agent_loop(
         conversation_id,

openhands/server/utils.py

@@ -12,7 +12,7 @@ async def get_conversation_store(request: Request) -> ConversationStore | None:
     )
     if conversation_store:
         return conversation_store
-    user_id = await get_user_id(request)
+    user_id = get_user_id(request)
     conversation_store = await ConversationStoreImpl.get_instance(config, user_id)
     request.state.conversation_store = conversation_store
     return conversation_store

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.1.3 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
 
 [[package]]
 name = "aiohappyeyeballs"
@@ -373,7 +373,7 @@ description = "LTS Port of Python audioop"
 optional = false
 python-versions = ">=3.13"
 groups = ["main"]
-markers = "python_version == \"3.13\""
+markers = "python_version >= \"3.13\""
 files = [
     {file = "audioop_lts-0.2.1-cp313-abi3-macosx_10_13_universal2.whl", hash = "sha256:fd1345ae99e17e6910f47ce7d52673c6a1a70820d78b67de1b7abb3af29c426a"},
     {file = "audioop_lts-0.2.1-cp313-abi3-macosx_10_13_x86_64.whl", hash = "sha256:e175350da05d2087e12cea8e72a70a1a8b14a17e92ed2022952a4419689ede5e"},
@@ -2116,6 +2116,52 @@ files = [
     {file = "docstring_parser-0.16.tar.gz", hash = "sha256:538beabd0af1e2db0146b6bd3caa526c35a34d61af9fd2887f3a8a27a739aa6e"},
 ]
 
+[[package]]
+name = "duckdb"
+version = "1.3.0"
+description = "DuckDB in-process database"
+optional = false
+python-versions = ">=3.7.0"
+groups = ["main"]
+files = [
+    {file = "duckdb-1.3.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:fc65c1e97aa010359c43c0342ea423e6efa3cb8c8e3f133b0765451ce674e3db"},
+    {file = "duckdb-1.3.0-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:8fc91b629646679e33806342510335ccbbeaf2b823186f0ae829fd48e7a63c66"},
+    {file = "duckdb-1.3.0-cp310-cp310-macosx_12_0_x86_64.whl", hash = "sha256:1a69b970553fd015c557238d427ef00be3c8ed58c3bc3641aef987e33f8bf614"},
+    {file = "duckdb-1.3.0-cp310-cp310-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1003e84c07b84680cee6d06e4795b6e861892474704f7972058594a52c7473cf"},
+    {file = "duckdb-1.3.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:992239b54ca6f015ad0ed0d80f3492c065313c4641df0a226183b8860cb7f5b0"},
+    {file = "duckdb-1.3.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:0ba1c5af59e8147216149b814b1970b8f7e3c240494a9688171390db3c504b29"},
+    {file = "duckdb-1.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:57b794ca28e22b23bd170506cb1d4704a3608e67f0fe33273db9777b69bdf26a"},
+    {file = "duckdb-1.3.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:60a58b85929754abb21db1e739d2f53eaef63e6015e62ba58eae3425030e7935"},
+    {file = "duckdb-1.3.0-cp311-cp311-macosx_12_0_universal2.whl", hash = "sha256:1d46b5a20f078b1b2284243e02a1fde7e12cbb8d205fce62e4700bcfe6a09881"},
+    {file = "duckdb-1.3.0-cp311-cp311-macosx_12_0_x86_64.whl", hash = "sha256:0044e5ffb2d46308099640a92f99980a44e12bb68642aa9e6b08acbf300d64a1"},
+    {file = "duckdb-1.3.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5cb813de2ca2f5e7c77392a67bdcaa174bfd69ebbfdfc983024af270c77a0447"},
+    {file = "duckdb-1.3.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7a0c993eb6df2b30b189ad747f3aea1b0b87b78ab7f80c6e7c57117b6e8dbfb0"},
+    {file = "duckdb-1.3.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:6728e209570d36ece66dd7249e5d6055326321137cd807f26300733283930cd4"},
+    {file = "duckdb-1.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:7e652b7c8dbdb91a94fd7d543d3e115d24a25aa0791a373a852e20cb7bb21154"},
+    {file = "duckdb-1.3.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:f24038fe9b83dcbaeafb1ed76ec3b3f38943c1c8d27ab464ad384db8a6658b61"},
+    {file = "duckdb-1.3.0-cp312-cp312-macosx_12_0_universal2.whl", hash = "sha256:956c85842841bef68f4a5388c6b225b933151a7c06d568390fc895fc44607913"},
+    {file = "duckdb-1.3.0-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:efe883d822ed56fcfbb6a7b397c13f6a0d2eaeb3bc4ef4510f84fadb3dfe416d"},
+    {file = "duckdb-1.3.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:3872a3a1b80ffba5264ea236a3754d0c41d3c7b01bdf8cdcb1c180fc1b8dc8e2"},
+    {file = "duckdb-1.3.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:30bf45ad78a5a997f378863e036e917b481d18d685e5c977cd0a3faf2e31fbaf"},
+    {file = "duckdb-1.3.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:85cbd8e1d65df8a0780023baf5045d3033fabd154799bc9ea6d9ab5728f41eb3"},
+    {file = "duckdb-1.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:8754c40dac0f26d9fb0363bbb5df02f7a61ce6a6728d5efc02c3bc925d7c89c3"},
+    {file = "duckdb-1.3.0-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:176b9818d940c52ac7f31c64a98cf172d7c19d2a006017c9c4e9c06c246e36bf"},
+    {file = "duckdb-1.3.0-cp313-cp313-macosx_12_0_universal2.whl", hash = "sha256:03981f7e8793f07a4a9a2ba387640e71d0a99ebcaf8693ab09f96d59e628b713"},
+    {file = "duckdb-1.3.0-cp313-cp313-macosx_12_0_x86_64.whl", hash = "sha256:a177d55a38a62fdf79b59a0eaa32531a1dbb443265f6d67f64992cc1e82b755c"},
+    {file = "duckdb-1.3.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b1c30e3749823147d5578bc3f01f35d1a0433a1c768908d946056ec8d6e1757e"},
+    {file = "duckdb-1.3.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5855f3a564baf22eeeab70c120b51f5a11914f1f1634f03382daeb6b1dea4c62"},
+    {file = "duckdb-1.3.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:9b1fac15a48056f7c2739cf8800873063ba2f691e91a9b2fc167658a401ca76a"},
+    {file = "duckdb-1.3.0-cp313-cp313-win_amd64.whl", hash = "sha256:fbdfc1c0b83b90f780ae74038187ee696bb56ab727a289752372d7ec42dda65b"},
+    {file = "duckdb-1.3.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:5f6b5d725546ad30abc125a6813734b493fea694bc3123e991c480744573c2f1"},
+    {file = "duckdb-1.3.0-cp39-cp39-macosx_12_0_universal2.whl", hash = "sha256:fcbcc9b956b06cf5ee94629438ecab88de89b08b5620fcda93665c222ab18cd4"},
+    {file = "duckdb-1.3.0-cp39-cp39-macosx_12_0_x86_64.whl", hash = "sha256:2d32f2d44105e1705d8a0fb6d6d246fd69aff82c80ad23293266244b66b69012"},
+    {file = "duckdb-1.3.0-cp39-cp39-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0aa7a5c0dcb780850e6da1227fb1d552af8e1a5091e02667ab6ace61ab49ce6c"},
+    {file = "duckdb-1.3.0-cp39-cp39-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7cb254fd5405f3edbd7d962ba39c72e4ab90b37cb4d0e34846089796c8078419"},
+    {file = "duckdb-1.3.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:a7d337b58c59fd2cd9faae531b05d940f8d92bdc2e14cb6e9a5a37675ad2742d"},
+    {file = "duckdb-1.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:b3cea3a345755c7dbcb58403dbab8befd499c82f0d27f893a4c1d4b8cf56ec54"},
+    {file = "duckdb-1.3.0.tar.gz", hash = "sha256:09aaa4b1dca24f4d1f231e7ae66b6413e317b7e04e2753541d42df6c8113fac7"},
+]
+
 [[package]]
 name = "dulwich"
 version = "0.22.8"
@@ -3166,7 +3212,7 @@ google-auth = ">=2.14.1,<2.24.0 || >2.24.0,<2.25.0 || >2.25.0,<3.0.0"
 grpc-google-iam-v1 = ">=0.14.0,<1.0.0"
 proto-plus = [
     {version = ">=1.25.0,<2.0.0", markers = "python_version >= \"3.13\""},
-    {version = ">=1.22.3,<2.0.0"},
+    {version = ">=1.22.3,<2.0.0", markers = "python_version < \"3.13\""},
 ]
 protobuf = ">=3.20.2,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<7.0.0"
 
@@ -5352,6 +5398,30 @@ cli = ["python-dotenv (>=1.0.0)", "typer (>=0.12.4)"]
 rich = ["rich (>=13.9.4)"]
 ws = ["websockets (>=15.0.1)"]
 
+[[package]]
+name = "mcpm"
+version = "1.12.0"
+description = "MCPM - Model Context Protocol Manager"
+optional = false
+python-versions = ">=3.10"
+groups = ["main"]
+files = [
+    {file = "mcpm-1.12.0-py3-none-any.whl", hash = "sha256:ed3a87300420bcdb9cd12ef290179fda5bd51eb2f4cd3e793084d83eed91b249"},
+    {file = "mcpm-1.12.0.tar.gz", hash = "sha256:e9d2b852b90d7fd62dede584f035dd6b2b3d068d233e96b82aead835f81a911a"},
+]
+
+[package.dependencies]
+click = ">=8.1.3"
+duckdb = ">=1.2.2"
+mcp = ">=1.8.0"
+prompt-toolkit = ">=3.0.0"
+psutil = ">=7.0.0"
+pydantic = ">=2.5.1"
+requests = ">=2.28.0"
+rich = ">=12.0.0"
+ruamel-yaml = ">=0.18.10"
+watchfiles = ">=1.0.4"
+
 [[package]]
 name = "mdurl"
 version = "0.1.2"
@@ -6386,106 +6456,102 @@ et-xmlfile = "*"
 
 [[package]]
 name = "opentelemetry-api"
-version = "1.34.0"
+version = "1.25.0"
 description = "OpenTelemetry Python API"
 optional = false
-python-versions = ">=3.9"
+python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "opentelemetry_api-1.34.0-py3-none-any.whl", hash = "sha256:390b81984affe4453180820ca518de55e3be051111e70cc241bb3b0071ca3a2c"},
-    {file = "opentelemetry_api-1.34.0.tar.gz", hash = "sha256:48d167589134799093005b7f7f347c69cc67859c693b17787f334fbe8871279f"},
+    {file = "opentelemetry_api-1.25.0-py3-none-any.whl", hash = "sha256:757fa1aa020a0f8fa139f8959e53dec2051cc26b832e76fa839a6d76ecefd737"},
+    {file = "opentelemetry_api-1.25.0.tar.gz", hash = "sha256:77c4985f62f2614e42ce77ee4c9da5fa5f0bc1e1821085e9a47533a9323ae869"},
 ]
 
 [package.dependencies]
-importlib-metadata = ">=6.0,<8.8.0"
-typing-extensions = ">=4.5.0"
+deprecated = ">=1.2.6"
+importlib-metadata = ">=6.0,<=7.1"
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-common"
-version = "1.34.0"
+version = "1.25.0"
 description = "OpenTelemetry Protobuf encoding"
 optional = false
-python-versions = ">=3.9"
+python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "opentelemetry_exporter_otlp_proto_common-1.34.0-py3-none-any.whl", hash = "sha256:a5ab7a9b7c3c7ba957c8ddcb08c0c93b1d732e066f544682a250ecf4d7a9ceef"},
-    {file = "opentelemetry_exporter_otlp_proto_common-1.34.0.tar.gz", hash = "sha256:5916d9ceda8c733adbec5e9cecf654fbf359e9f619ff43214277076fba888557"},
+    {file = "opentelemetry_exporter_otlp_proto_common-1.25.0-py3-none-any.whl", hash = "sha256:15637b7d580c2675f70246563363775b4e6de947871e01d0f4e3881d1848d693"},
+    {file = "opentelemetry_exporter_otlp_proto_common-1.25.0.tar.gz", hash = "sha256:c93f4e30da4eee02bacd1e004eb82ce4da143a2f8e15b987a9f603e0a85407d3"},
 ]
 
 [package.dependencies]
-opentelemetry-proto = "1.34.0"
+opentelemetry-proto = "1.25.0"
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-grpc"
-version = "1.34.0"
+version = "1.25.0"
 description = "OpenTelemetry Collector Protobuf over gRPC Exporter"
 optional = false
-python-versions = ">=3.9"
+python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "opentelemetry_exporter_otlp_proto_grpc-1.34.0-py3-none-any.whl", hash = "sha256:31c41017af85833242d49beb07bde7341b0a145f0b898ee383f3e3019037afb1"},
-    {file = "opentelemetry_exporter_otlp_proto_grpc-1.34.0.tar.gz", hash = "sha256:a634425340f506d5ebf641c92d88eb873754d4c5259b5b816afb234c6f87b37d"},
+    {file = "opentelemetry_exporter_otlp_proto_grpc-1.25.0-py3-none-any.whl", hash = "sha256:3131028f0c0a155a64c430ca600fd658e8e37043cb13209f0109db5c1a3e4eb4"},
+    {file = "opentelemetry_exporter_otlp_proto_grpc-1.25.0.tar.gz", hash = "sha256:c0b1661415acec5af87625587efa1ccab68b873745ca0ee96b69bb1042087eac"},
 ]
 
 [package.dependencies]
+deprecated = ">=1.2.6"
 googleapis-common-protos = ">=1.52,<2.0"
-grpcio = [
-    {version = ">=1.66.2,<2.0.0", markers = "python_version >= \"3.13\""},
-    {version = ">=1.63.2,<2.0.0", markers = "python_version < \"3.13\""},
-]
+grpcio = ">=1.0.0,<2.0.0"
 opentelemetry-api = ">=1.15,<2.0"
-opentelemetry-exporter-otlp-proto-common = "1.34.0"
-opentelemetry-proto = "1.34.0"
-opentelemetry-sdk = ">=1.34.0,<1.35.0"
-typing-extensions = ">=4.5.0"
+opentelemetry-exporter-otlp-proto-common = "1.25.0"
+opentelemetry-proto = "1.25.0"
+opentelemetry-sdk = ">=1.25.0,<1.26.0"
 
 [[package]]
 name = "opentelemetry-proto"
-version = "1.34.0"
+version = "1.25.0"
 description = "OpenTelemetry Python Proto"
 optional = false
-python-versions = ">=3.9"
+python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "opentelemetry_proto-1.34.0-py3-none-any.whl", hash = "sha256:ffb1f1b27552fda5a1cd581e34243cc0b6f134fb14c1c2a33cc3b4b208c9bf97"},
-    {file = "opentelemetry_proto-1.34.0.tar.gz", hash = "sha256:73e40509b692630a47192888424f7e0b8fb19d9ecf2f04e6f708170cd3346dfe"},
+    {file = "opentelemetry_proto-1.25.0-py3-none-any.whl", hash = "sha256:f07e3341c78d835d9b86665903b199893befa5e98866f63d22b00d0b7ca4972f"},
+    {file = "opentelemetry_proto-1.25.0.tar.gz", hash = "sha256:35b6ef9dc4a9f7853ecc5006738ad40443701e52c26099e197895cbda8b815a3"},
 ]
 
 [package.dependencies]
-protobuf = ">=5.0,<6.0"
+protobuf = ">=3.19,<5.0"
 
 [[package]]
 name = "opentelemetry-sdk"
-version = "1.34.0"
+version = "1.25.0"
 description = "OpenTelemetry Python SDK"
 optional = false
-python-versions = ">=3.9"
+python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "opentelemetry_sdk-1.34.0-py3-none-any.whl", hash = "sha256:7850bcd5b5c95f9aae48603d6592bdad5c7bdef50c03e06393f8f457d891fe32"},
-    {file = "opentelemetry_sdk-1.34.0.tar.gz", hash = "sha256:719559622afcd515c2aec462ccb749ba2e70075a01df45837623643814d33716"},
+    {file = "opentelemetry_sdk-1.25.0-py3-none-any.whl", hash = "sha256:d97ff7ec4b351692e9d5a15af570c693b8715ad78b8aafbec5c7100fe966b4c9"},
+    {file = "opentelemetry_sdk-1.25.0.tar.gz", hash = "sha256:ce7fc319c57707ef5bf8b74fb9f8ebdb8bfafbe11898410e0d2a761d08a98ec7"},
 ]
 
 [package.dependencies]
-opentelemetry-api = "1.34.0"
-opentelemetry-semantic-conventions = "0.55b0"
-typing-extensions = ">=4.5.0"
+opentelemetry-api = "1.25.0"
+opentelemetry-semantic-conventions = "0.46b0"
+typing-extensions = ">=3.7.4"
 
 [[package]]
 name = "opentelemetry-semantic-conventions"
-version = "0.55b0"
+version = "0.46b0"
 description = "OpenTelemetry Semantic Conventions"
 optional = false
-python-versions = ">=3.9"
+python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "opentelemetry_semantic_conventions-0.55b0-py3-none-any.whl", hash = "sha256:63bb15b67377700e51c422d0d24092ca6ce9f3a4cb6f032375aa8af1fc2aab65"},
-    {file = "opentelemetry_semantic_conventions-0.55b0.tar.gz", hash = "sha256:933d2e20c2dbc0f9b2f4f52138282875b4b14c66c491f5273bcdef1781368e9c"},
+    {file = "opentelemetry_semantic_conventions-0.46b0-py3-none-any.whl", hash = "sha256:6daef4ef9fa51d51855d9f8e0ccd3a1bd59e0e545abe99ac6203804e36ab3e07"},
+    {file = "opentelemetry_semantic_conventions-0.46b0.tar.gz", hash = "sha256:fbc982ecbb6a6e90869b15c1673be90bd18c8a56ff1cffc0864e38e2edffaefa"},
 ]
 
 [package.dependencies]
-opentelemetry-api = "1.34.0"
-typing-extensions = ">=4.5.0"
+opentelemetry-api = "1.25.0"
 
 [[package]]
 name = "overrides"
@@ -7105,23 +7171,23 @@ testing = ["google-api-core (>=1.31.5)"]
 
 [[package]]
 name = "protobuf"
-version = "5.29.5"
+version = "4.25.8"
 description = ""
 optional = false
 python-versions = ">=3.8"
 groups = ["main", "evaluation"]
 files = [
-    {file = "protobuf-5.29.5-cp310-abi3-win32.whl", hash = "sha256:3f1c6468a2cfd102ff4703976138844f78ebd1fb45f49011afc5139e9e283079"},
-    {file = "protobuf-5.29.5-cp310-abi3-win_amd64.whl", hash = "sha256:3f76e3a3675b4a4d867b52e4a5f5b78a2ef9565549d4037e06cf7b0942b1d3fc"},
-    {file = "protobuf-5.29.5-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:e38c5add5a311f2a6eb0340716ef9b039c1dfa428b28f25a7838ac329204a671"},
-    {file = "protobuf-5.29.5-cp38-abi3-manylinux2014_aarch64.whl", hash = "sha256:fa18533a299d7ab6c55a238bf8629311439995f2e7eca5caaff08663606e9015"},
-    {file = "protobuf-5.29.5-cp38-abi3-manylinux2014_x86_64.whl", hash = "sha256:63848923da3325e1bf7e9003d680ce6e14b07e55d0473253a690c3a8b8fd6e61"},
-    {file = "protobuf-5.29.5-cp38-cp38-win32.whl", hash = "sha256:ef91363ad4faba7b25d844ef1ada59ff1604184c0bcd8b39b8a6bef15e1af238"},
-    {file = "protobuf-5.29.5-cp38-cp38-win_amd64.whl", hash = "sha256:7318608d56b6402d2ea7704ff1e1e4597bee46d760e7e4dd42a3d45e24b87f2e"},
-    {file = "protobuf-5.29.5-cp39-cp39-win32.whl", hash = "sha256:6f642dc9a61782fa72b90878af134c5afe1917c89a568cd3476d758d3c3a0736"},
-    {file = "protobuf-5.29.5-cp39-cp39-win_amd64.whl", hash = "sha256:470f3af547ef17847a28e1f47200a1cbf0ba3ff57b7de50d22776607cd2ea353"},
-    {file = "protobuf-5.29.5-py3-none-any.whl", hash = "sha256:6cf42630262c59b2d8de33954443d94b746c952b01434fc58a417fdbd2e84bd5"},
-    {file = "protobuf-5.29.5.tar.gz", hash = "sha256:bc1463bafd4b0929216c35f437a8e28731a2b7fe3d98bb77a600efced5a15c84"},
+    {file = "protobuf-4.25.8-cp310-abi3-win32.whl", hash = "sha256:504435d831565f7cfac9f0714440028907f1975e4bed228e58e72ecfff58a1e0"},
+    {file = "protobuf-4.25.8-cp310-abi3-win_amd64.whl", hash = "sha256:bd551eb1fe1d7e92c1af1d75bdfa572eff1ab0e5bf1736716814cdccdb2360f9"},
+    {file = "protobuf-4.25.8-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:ca809b42f4444f144f2115c4c1a747b9a404d590f18f37e9402422033e464e0f"},
+    {file = "protobuf-4.25.8-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:9ad7ef62d92baf5a8654fbb88dac7fa5594cfa70fd3440488a5ca3bfc6d795a7"},
+    {file = "protobuf-4.25.8-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:83e6e54e93d2b696a92cad6e6efc924f3850f82b52e1563778dfab8b355101b0"},
+    {file = "protobuf-4.25.8-cp38-cp38-win32.whl", hash = "sha256:27d498ffd1f21fb81d987a041c32d07857d1d107909f5134ba3350e1ce80a4af"},
+    {file = "protobuf-4.25.8-cp38-cp38-win_amd64.whl", hash = "sha256:d552c53d0415449c8d17ced5c341caba0d89dbf433698e1436c8fa0aae7808a3"},
+    {file = "protobuf-4.25.8-cp39-cp39-win32.whl", hash = "sha256:077ff8badf2acf8bc474406706ad890466274191a48d0abd3bd6987107c9cde5"},
+    {file = "protobuf-4.25.8-cp39-cp39-win_amd64.whl", hash = "sha256:f4510b93a3bec6eba8fd8f1093e9d7fb0d4a24d1a81377c10c0e5bbfe9e4ed24"},
+    {file = "protobuf-4.25.8-py3-none-any.whl", hash = "sha256:15a0af558aa3b13efef102ae6e4f3efac06f1eea11afb3a57db2901447d9fb59"},
+    {file = "protobuf-4.25.8.tar.gz", hash = "sha256:6135cf8affe1fc6f76cced2641e4ea8d3e59518d1f24ae41ba97bcad82d397cd"},
 ]
 
 [[package]]
@@ -8867,6 +8933,82 @@ files = [
 [package.dependencies]
 pyasn1 = ">=0.1.3"
 
+[[package]]
+name = "ruamel-yaml"
+version = "0.18.12"
+description = "ruamel.yaml is a YAML parser/emitter that supports roundtrip preservation of comments, seq/map flow style, and map key order"
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "ruamel.yaml-0.18.12-py3-none-any.whl", hash = "sha256:790ba4c48b6a6e6b12b532a7308779eb12d2aaab3a80fdb8389216f28ea2b287"},
+    {file = "ruamel.yaml-0.18.12.tar.gz", hash = "sha256:5a38fd5ce39d223bebb9e3a6779e86b9427a03fb0bf9f270060f8b149cffe5e2"},
+]
+
+[package.dependencies]
+"ruamel.yaml.clib" = {version = ">=0.2.7", markers = "platform_python_implementation == \"CPython\" and python_version < \"3.14\""}
+
+[package.extras]
+docs = ["mercurial (>5.7)", "ryd"]
+jinja2 = ["ruamel.yaml.jinja2 (>=0.2)"]
+
+[[package]]
+name = "ruamel-yaml-clib"
+version = "0.2.12"
+description = "C version of reader, parser and emitter for ruamel.yaml derived from libyaml"
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+markers = "platform_python_implementation == \"CPython\""
+files = [
+    {file = "ruamel.yaml.clib-0.2.12-cp310-cp310-macosx_13_0_arm64.whl", hash = "sha256:11f891336688faf5156a36293a9c362bdc7c88f03a8a027c2c1d8e0bcde998e5"},
+    {file = "ruamel.yaml.clib-0.2.12-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:a606ef75a60ecf3d924613892cc603b154178ee25abb3055db5062da811fd969"},
+    {file = "ruamel.yaml.clib-0.2.12-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fd5415dded15c3822597455bc02bcd66e81ef8b7a48cb71a33628fc9fdde39df"},
+    {file = "ruamel.yaml.clib-0.2.12-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f66efbc1caa63c088dead1c4170d148eabc9b80d95fb75b6c92ac0aad2437d76"},
+    {file = "ruamel.yaml.clib-0.2.12-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:22353049ba4181685023b25b5b51a574bce33e7f51c759371a7422dcae5402a6"},
+    {file = "ruamel.yaml.clib-0.2.12-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:932205970b9f9991b34f55136be327501903f7c66830e9760a8ffb15b07f05cd"},
+    {file = "ruamel.yaml.clib-0.2.12-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:a52d48f4e7bf9005e8f0a89209bf9a73f7190ddf0489eee5eb51377385f59f2a"},
+    {file = "ruamel.yaml.clib-0.2.12-cp310-cp310-win32.whl", hash = "sha256:3eac5a91891ceb88138c113f9db04f3cebdae277f5d44eaa3651a4f573e6a5da"},
+    {file = "ruamel.yaml.clib-0.2.12-cp310-cp310-win_amd64.whl", hash = "sha256:ab007f2f5a87bd08ab1499bdf96f3d5c6ad4dcfa364884cb4549aa0154b13a28"},
+    {file = "ruamel.yaml.clib-0.2.12-cp311-cp311-macosx_13_0_arm64.whl", hash = "sha256:4a6679521a58256a90b0d89e03992c15144c5f3858f40d7c18886023d7943db6"},
+    {file = "ruamel.yaml.clib-0.2.12-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:d84318609196d6bd6da0edfa25cedfbabd8dbde5140a0a23af29ad4b8f91fb1e"},
+    {file = "ruamel.yaml.clib-0.2.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bb43a269eb827806502c7c8efb7ae7e9e9d0573257a46e8e952f4d4caba4f31e"},
+    {file = "ruamel.yaml.clib-0.2.12-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:811ea1594b8a0fb466172c384267a4e5e367298af6b228931f273b111f17ef52"},
+    {file = "ruamel.yaml.clib-0.2.12-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:cf12567a7b565cbf65d438dec6cfbe2917d3c1bdddfce84a9930b7d35ea59642"},
+    {file = "ruamel.yaml.clib-0.2.12-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:7dd5adc8b930b12c8fc5b99e2d535a09889941aa0d0bd06f4749e9a9397c71d2"},
+    {file = "ruamel.yaml.clib-0.2.12-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:1492a6051dab8d912fc2adeef0e8c72216b24d57bd896ea607cb90bb0c4981d3"},
+    {file = "ruamel.yaml.clib-0.2.12-cp311-cp311-win32.whl", hash = "sha256:bd0a08f0bab19093c54e18a14a10b4322e1eacc5217056f3c063bd2f59853ce4"},
+    {file = "ruamel.yaml.clib-0.2.12-cp311-cp311-win_amd64.whl", hash = "sha256:a274fb2cb086c7a3dea4322ec27f4cb5cc4b6298adb583ab0e211a4682f241eb"},
+    {file = "ruamel.yaml.clib-0.2.12-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:20b0f8dc160ba83b6dcc0e256846e1a02d044e13f7ea74a3d1d56ede4e48c632"},
+    {file = "ruamel.yaml.clib-0.2.12-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:943f32bc9dedb3abff9879edc134901df92cfce2c3d5c9348f172f62eb2d771d"},
+    {file = "ruamel.yaml.clib-0.2.12-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95c3829bb364fdb8e0332c9931ecf57d9be3519241323c5274bd82f709cebc0c"},
+    {file = "ruamel.yaml.clib-0.2.12-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:749c16fcc4a2b09f28843cda5a193e0283e47454b63ec4b81eaa2242f50e4ccd"},
+    {file = "ruamel.yaml.clib-0.2.12-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:bf165fef1f223beae7333275156ab2022cffe255dcc51c27f066b4370da81e31"},
+    {file = "ruamel.yaml.clib-0.2.12-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:32621c177bbf782ca5a18ba4d7af0f1082a3f6e517ac2a18b3974d4edf349680"},
+    {file = "ruamel.yaml.clib-0.2.12-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:b82a7c94a498853aa0b272fd5bc67f29008da798d4f93a2f9f289feb8426a58d"},
+    {file = "ruamel.yaml.clib-0.2.12-cp312-cp312-win32.whl", hash = "sha256:e8c4ebfcfd57177b572e2040777b8abc537cdef58a2120e830124946aa9b42c5"},
+    {file = "ruamel.yaml.clib-0.2.12-cp312-cp312-win_amd64.whl", hash = "sha256:0467c5965282c62203273b838ae77c0d29d7638c8a4e3a1c8bdd3602c10904e4"},
+    {file = "ruamel.yaml.clib-0.2.12-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:4c8c5d82f50bb53986a5e02d1b3092b03622c02c2eb78e29bec33fd9593bae1a"},
+    {file = "ruamel.yaml.clib-0.2.12-cp313-cp313-manylinux2014_aarch64.whl", hash = "sha256:e7e3736715fbf53e9be2a79eb4db68e4ed857017344d697e8b9749444ae57475"},
+    {file = "ruamel.yaml.clib-0.2.12-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b7e75b4965e1d4690e93021adfcecccbca7d61c7bddd8e22406ef2ff20d74ef"},
+    {file = "ruamel.yaml.clib-0.2.12-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:96777d473c05ee3e5e3c3e999f5d23c6f4ec5b0c38c098b3a5229085f74236c6"},
+    {file = "ruamel.yaml.clib-0.2.12-cp313-cp313-musllinux_1_1_i686.whl", hash = "sha256:3bc2a80e6420ca8b7d3590791e2dfc709c88ab9152c00eeb511c9875ce5778bf"},
+    {file = "ruamel.yaml.clib-0.2.12-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:e188d2699864c11c36cdfdada94d781fd5d6b0071cd9c427bceb08ad3d7c70e1"},
+    {file = "ruamel.yaml.clib-0.2.12-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:4f6f3eac23941b32afccc23081e1f50612bdbe4e982012ef4f5797986828cd01"},
+    {file = "ruamel.yaml.clib-0.2.12-cp313-cp313-win32.whl", hash = "sha256:6442cb36270b3afb1b4951f060eccca1ce49f3d087ca1ca4563a6eb479cb3de6"},
+    {file = "ruamel.yaml.clib-0.2.12-cp313-cp313-win_amd64.whl", hash = "sha256:e5b8daf27af0b90da7bb903a876477a9e6d7270be6146906b276605997c7e9a3"},
+    {file = "ruamel.yaml.clib-0.2.12-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:fc4b630cd3fa2cf7fce38afa91d7cfe844a9f75d7f0f36393fa98815e911d987"},
+    {file = "ruamel.yaml.clib-0.2.12-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:bc5f1e1c28e966d61d2519f2a3d451ba989f9ea0f2307de7bc45baa526de9e45"},
+    {file = "ruamel.yaml.clib-0.2.12-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5a0e060aace4c24dcaf71023bbd7d42674e3b230f7e7b97317baf1e953e5b519"},
+    {file = "ruamel.yaml.clib-0.2.12-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e2f1c3765db32be59d18ab3953f43ab62a761327aafc1594a2a1fbe038b8b8a7"},
+    {file = "ruamel.yaml.clib-0.2.12-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:d85252669dc32f98ebcd5d36768f5d4faeaeaa2d655ac0473be490ecdae3c285"},
+    {file = "ruamel.yaml.clib-0.2.12-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:e143ada795c341b56de9418c58d028989093ee611aa27ffb9b7f609c00d813ed"},
+    {file = "ruamel.yaml.clib-0.2.12-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:2c59aa6170b990d8d2719323e628aaf36f3bfbc1c26279c0eeeb24d05d2d11c7"},
+    {file = "ruamel.yaml.clib-0.2.12-cp39-cp39-win32.whl", hash = "sha256:beffaed67936fbbeffd10966a4eb53c402fafd3d6833770516bf7314bc6ffa12"},
+    {file = "ruamel.yaml.clib-0.2.12-cp39-cp39-win_amd64.whl", hash = "sha256:040ae85536960525ea62868b642bdb0c2cc6021c9f9d507810c0c604e66f5a7b"},
+    {file = "ruamel.yaml.clib-0.2.12.tar.gz", hash = "sha256:6c8fbb13ec503f99a91901ab46e0b07ae7941cd527393187039aec586fdfd36f"},
+]
+
 [[package]]
 name = "ruff"
 version = "0.11.11"
@@ -9193,6 +9335,7 @@ files = [
     {file = "setuptools-80.9.0-py3-none-any.whl", hash = "sha256:062d34222ad13e0cc312a4c02d73f059e86a4acbfbdea8f8f76b28c99f306922"},
     {file = "setuptools-80.9.0.tar.gz", hash = "sha256:f36b47402ecde768dbfafc46e8e4207b4360c654f1f3bb84475f0a28628fb19c"},
 ]
+markers = {evaluation = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
 
 [package.extras]
 check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\"", "ruff (>=0.8.0) ; sys_platform != \"cygwin\""]
@@ -9435,7 +9578,7 @@ description = "Standard library aifc redistribution. \"dead battery\"."
 optional = false
 python-versions = "*"
 groups = ["main"]
-markers = "python_version == \"3.13\""
+markers = "python_version >= \"3.13\""
 files = [
     {file = "standard_aifc-3.13.0-py3-none-any.whl", hash = "sha256:f7ae09cc57de1224a0dd8e3eb8f73830be7c3d0bc485de4c1f82b4a7f645ac66"},
     {file = "standard_aifc-3.13.0.tar.gz", hash = "sha256:64e249c7cb4b3daf2fdba4e95721f811bde8bdfc43ad9f936589b7bb2fae2e43"},
@@ -9452,7 +9595,7 @@ description = "Standard library chunk redistribution. \"dead battery\"."
 optional = false
 python-versions = "*"
 groups = ["main"]
-markers = "python_version == \"3.13\""
+markers = "python_version >= \"3.13\""
 files = [
     {file = "standard_chunk-3.13.0-py3-none-any.whl", hash = "sha256:17880a26c285189c644bd5bd8f8ed2bdb795d216e3293e6dbe55bbd848e2982c"},
     {file = "standard_chunk-3.13.0.tar.gz", hash = "sha256:4ac345d37d7e686d2755e01836b8d98eda0d1a3ee90375e597ae43aaf064d654"},
@@ -11614,4 +11757,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.12,<3.14"
-content-hash = "8c960ca43a540bfd96dc029d45fa4e0a4a3f75c2996feecaa8b989c348655f70"
+content-hash = "eaa84e30dbafb061a75b4b173a8ba16542c4a03ab74583c55ab282cd6119e430"

pyproject.toml

@@ -20,12 +20,12 @@ packages = [
 
 [tool.poetry.dependencies]
 python = "^3.12,<3.14"
-litellm = "^1.60.0, !=1.64.4, !=1.67.*"            # avoid 1.64.4 (known bug) & 1.67.* (known bug #10272)
-aiohttp = ">=3.9.0,!=3.11.13"                      # Pin to avoid yanked version 3.11.13
-google-generativeai = "*"                          # To use litellm with Gemini Pro API
-google-api-python-client = "^2.164.0"              # For Google Sheets API
-google-auth-httplib2 = "*"                         # For Google Sheets authentication
-google-auth-oauthlib = "*"                         # For Google Sheets OAuth
+litellm = "^1.60.0, !=1.64.4, !=1.67.*"           # avoid 1.64.4 (known bug) & 1.67.* (known bug #10272)
+aiohttp = ">=3.9.0,!=3.11.13"                     # Pin to avoid yanked version 3.11.13
+google-generativeai = "*"                         # To use litellm with Gemini Pro API
+google-api-python-client = "^2.164.0"             # For Google Sheets API
+google-auth-httplib2 = "*"                        # For Google Sheets authentication
+google-auth-oauthlib = "*"                        # For Google Sheets OAuth
 termcolor = "*"
 docker = "*"
 fastapi = "*"
@@ -34,7 +34,7 @@ types-toml = "*"
 uvicorn = "*"
 numpy = "*"
 json-repair = "*"
-browsergym-core = "0.13.3"                         # integrate browsergym-core as the browsing interface
+browsergym-core = "0.13.3"                        # integrate browsergym-core as the browsing interface
 html2text = "*"
 e2b = ">=1.0.5,<1.4.0"
 pexpect = "*"
@@ -49,9 +49,9 @@ tornado = "*"
 python-dotenv = "*"
 rapidfuzz = "^3.9.0"
 whatthepatch = "^1.0.6"
-protobuf = "^5.0.0,<6.0.0"                         # Updated to support newer opentelemetry
-opentelemetry-api = "^1.33.1"
-opentelemetry-exporter-otlp-proto-grpc = "^1.33.1"
+protobuf = "^4.21.6,<5.0.0"                       # chromadb currently fails on 5.0+
+opentelemetry-api = "1.25.0"
+opentelemetry-exporter-otlp-proto-grpc = "1.25.0"
 modal = ">=0.66.26,<0.78.0"
 runloop-api-client = "0.33.0"
 libtmux = ">=0.37,<0.40"
@@ -67,6 +67,7 @@ poetry = "^2.1.2"
 anyio = "4.9.0"
 pythonnet = "*"
 fastmcp = "^2.5.2"
+mcpm = "1.12.0"
 python-frontmatter = "^1.1.0"
 # TODO: Should these go into the runtime group?
 ipywidgets = "^8.1.5"

tests/runtime/test_bash.py

@@ -16,16 +16,6 @@ from openhands.events.action import CmdRunAction
 from openhands.events.observation import CmdOutputObservation, ErrorObservation
 from openhands.runtime.impl.cli.cli_runtime import CLIRuntime
 from openhands.runtime.impl.local.local_runtime import LocalRuntime
-from openhands.runtime.utils.bash_constants import TIMEOUT_MESSAGE_TEMPLATE
-
-
-def get_timeout_suffix(timeout_seconds):
-    """Helper function to generate the expected timeout suffix."""
-    return (
-        f'[The command timed out after {timeout_seconds} seconds. '
-        f'{TIMEOUT_MESSAGE_TEMPLATE}]'
-    )
-
 
 # ============================================================================================================================
 # Bash-specific tests
@@ -66,7 +56,10 @@ def test_bash_server(temp_dir, runtime_cls, run_as_openhands):
         if runtime_cls == CLIRuntime:
             assert '[The command timed out after 1.0 seconds.]' in obs.metadata.suffix
         else:
-            assert get_timeout_suffix(1.0) in obs.metadata.suffix
+            assert (
+                "[The command timed out after 1.0 seconds. You may wait longer to see additional output by sending empty command '', send other commands to interact with the current process, or send keys to interrupt/kill the command.]"
+                in obs.metadata.suffix
+            )
 
         action = CmdRunAction(command='C-c', is_input=True)
         action.set_hard_timeout(30)

tests/runtime/test_mcp_action.py

@@ -114,11 +114,9 @@ def test_default_activated_tools():
     )
     with open(mcp_config_path, 'r') as f:
         mcp_config = json.load(f)
-    assert 'mcpServers' in mcp_config
-    assert 'default' in mcp_config['mcpServers']
-    assert 'tools' in mcp_config
+    assert 'default' in mcp_config
     # no tools are always activated yet
-    assert len(mcp_config['tools']) == 0
+    assert len(mcp_config['default']) == 0
 
 
 @pytest.mark.asyncio
@@ -251,11 +249,7 @@ async def test_both_stdio_and_sse_mcp(
         assert obs_cat.exit_code == 0
 
         mcp_action_fetch = MCPAction(
-            # NOTE: the tool name is `fetch_fetch` because the tool name is `fetch`
-            # And FastMCP Proxy will pre-pend the server name (in this case, `fetch`)
-            # to the tool name, so the full tool name becomes `fetch_fetch`
-            name='fetch',
-            arguments={'url': 'http://localhost:8000'},
+            name='fetch', arguments={'url': 'http://localhost:8000'}
         )
         obs_fetch = await runtime.call_tool_mcp(mcp_action_fetch)
         logger.info(obs_fetch, extra={'msg_type': 'OBSERVATION'})
@@ -310,9 +304,7 @@ async def test_microagent_and_one_stdio_mcp_in_config(
         logger.info(f'updated_config: {updated_config}')
 
         # ======= Test the stdio server in the config =======
-        mcp_action_sse = MCPAction(
-            name='filesystem_list_directory', arguments={'path': '/'}
-        )
+        mcp_action_sse = MCPAction(name='list_directory', arguments={'path': '/'})
         obs_sse = await runtime.call_tool_mcp(mcp_action_sse)
         logger.info(obs_sse, extra={'msg_type': 'OBSERVATION'})
         assert isinstance(obs_sse, MCPObservation), (
@@ -340,7 +332,7 @@ async def test_microagent_and_one_stdio_mcp_in_config(
         assert obs_cat.exit_code == 0
 
         mcp_action_fetch = MCPAction(
-            name='fetch_fetch', arguments={'url': 'http://localhost:8000'}
+            name='fetch', arguments={'url': 'http://localhost:8000'}
         )
         obs_fetch = await runtime.call_tool_mcp(mcp_action_fetch)
         logger.info(obs_fetch, extra={'msg_type': 'OBSERVATION'})

tests/runtime/test_microagent.py

@@ -1,7 +1,6 @@
 """Tests for microagent loading in runtime."""
 
 import os
-import tempfile
 from pathlib import Path
 from unittest.mock import AsyncMock, MagicMock, patch
 
@@ -14,13 +13,7 @@ from conftest import (
 from openhands.core.config import MCPConfig
 from openhands.core.config.mcp_config import MCPStdioServerConfig
 from openhands.mcp.utils import add_mcp_tools_to_agent
-from openhands.microagent.microagent import (
-    BaseMicroagent,
-    KnowledgeMicroagent,
-    RepoMicroagent,
-    TaskMicroagent,
-)
-from openhands.microagent.types import MicroagentType
+from openhands.microagent import KnowledgeMicroagent, RepoMicroagent
 
 
 def _create_test_microagents(test_dir: str):
@@ -180,176 +173,6 @@ Repository-specific test instructions.
         _close_test_runtime(runtime)
 
 
-def test_task_microagent_creation():
-    """Test that a TaskMicroagent is created correctly."""
-    content = """---
-name: test_task
-version: 1.0.0
-author: openhands
-agent: CodeActAgent
-triggers:
-- /test_task
-inputs:
-  - name: TEST_VAR
-    description: "Test variable"
----
-
-This is a test task microagent with a variable: ${test_var}.
-"""
-
-    with tempfile.NamedTemporaryFile(suffix='.md') as f:
-        f.write(content.encode())
-        f.flush()
-
-        agent = BaseMicroagent.load(f.name)
-
-        assert isinstance(agent, TaskMicroagent)
-        assert agent.type == MicroagentType.TASK
-        assert agent.name == 'test_task'
-        assert '/test_task' in agent.triggers
-        assert "If the user didn't provide any of these variables" in agent.content
-
-
-def test_task_microagent_variable_extraction():
-    """Test that variables are correctly extracted from the content."""
-    content = """---
-name: test_task
-version: 1.0.0
-author: openhands
-agent: CodeActAgent
-triggers:
-- /test_task
-inputs:
-  - name: var1
-    description: "Variable 1"
----
-
-This is a test with variables: ${var1}, ${var2}, and ${var3}.
-"""
-
-    with tempfile.NamedTemporaryFile(suffix='.md') as f:
-        f.write(content.encode())
-        f.flush()
-
-        agent = BaseMicroagent.load(f.name)
-
-        assert isinstance(agent, TaskMicroagent)
-        variables = agent.extract_variables(agent.content)
-        assert set(variables) == {'var1', 'var2', 'var3'}
-        assert agent.requires_user_input()
-
-
-def test_knowledge_microagent_no_prompt():
-    """Test that a regular KnowledgeMicroagent doesn't get the prompt."""
-    content = """---
-name: test_knowledge
-version: 1.0.0
-author: openhands
-agent: CodeActAgent
-triggers:
-- test_knowledge
----
-
-This is a test knowledge microagent.
-"""
-
-    with tempfile.NamedTemporaryFile(suffix='.md') as f:
-        f.write(content.encode())
-        f.flush()
-
-        agent = BaseMicroagent.load(f.name)
-
-        assert isinstance(agent, KnowledgeMicroagent)
-        assert agent.type == MicroagentType.KNOWLEDGE
-        assert "If the user didn't provide any of these variables" not in agent.content
-
-
-def test_task_microagent_trigger_addition():
-    """Test that a trigger is added if not present."""
-    content = """---
-name: test_task
-version: 1.0.0
-author: openhands
-agent: CodeActAgent
-inputs:
-  - name: TEST_VAR
-    description: "Test variable"
----
-
-This is a test task microagent.
-"""
-
-    with tempfile.NamedTemporaryFile(suffix='.md') as f:
-        f.write(content.encode())
-        f.flush()
-
-        agent = BaseMicroagent.load(f.name)
-
-        assert isinstance(agent, TaskMicroagent)
-        assert '/test_task' in agent.triggers
-
-
-def test_task_microagent_no_duplicate_trigger():
-    """Test that a trigger is not duplicated if already present."""
-    content = """---
-name: test_task
-version: 1.0.0
-author: openhands
-agent: CodeActAgent
-triggers:
-- /test_task
-- another_trigger
-inputs:
-  - name: TEST_VAR
-    description: "Test variable"
----
-
-This is a test task microagent.
-"""
-
-    with tempfile.NamedTemporaryFile(suffix='.md') as f:
-        f.write(content.encode())
-        f.flush()
-
-        agent = BaseMicroagent.load(f.name)
-
-        assert isinstance(agent, TaskMicroagent)
-        assert agent.triggers.count('/test_task') == 1  # No duplicates
-        assert len(agent.triggers) == 2
-        assert 'another_trigger' in agent.triggers
-        assert '/test_task' in agent.triggers
-
-
-def test_task_microagent_match_trigger():
-    """Test that a task microagent matches its trigger correctly."""
-    content = """---
-name: test_task
-version: 1.0.0
-author: openhands
-agent: CodeActAgent
-triggers:
-- /test_task
-inputs:
-  - name: TEST_VAR
-    description: "Test variable"
----
-
-This is a test task microagent.
-"""
-
-    with tempfile.NamedTemporaryFile(suffix='.md') as f:
-        f.write(content.encode())
-        f.flush()
-
-        agent = BaseMicroagent.load(f.name)
-
-        assert isinstance(agent, TaskMicroagent)
-        assert agent.match_trigger('/test_task') == '/test_task'
-        assert agent.match_trigger('  /test_task  ') == '/test_task'
-        assert agent.match_trigger('This contains /test_task') == '/test_task'
-        assert agent.match_trigger('/other_task') is None
-
-
 def test_default_tools_microagent_exists():
     """Test that the default-tools microagent exists in the global microagents directory."""
     # Get the path to the global microagents directory

tests/runtime/trajs/basic_gui_mode.json

@@ -589,7 +589,7 @@
         "working_dir": null,
         "py_interpreter_path": null,
         "prefix": "",
-        "suffix": "\n[The command has no new output after 30 seconds. You may wait longer to see additional output by sending empty command '', send other commands to interact with the current process, send keys to interrupt/kill the command, or use the timeout parameter in execute_bash for future commands.]"
+        "suffix": "\n[The command has no new output after 30 seconds. You may wait longer to see additional output by sending empty command '', send other commands to interact with the current process, or send keys to interrupt/kill the command.]"
       },
       "hidden": false
     },

tests/unit/test_bash_session.py

@@ -5,15 +5,6 @@ import time
 from openhands.core.logger import openhands_logger as logger
 from openhands.events.action import CmdRunAction
 from openhands.runtime.utils.bash import BashCommandStatus, BashSession
-from openhands.runtime.utils.bash_constants import TIMEOUT_MESSAGE_TEMPLATE
-
-
-def get_no_change_timeout_suffix(timeout_seconds):
-    """Helper function to generate the expected no-change timeout suffix."""
-    return (
-        f'\n[The command has no new output after {timeout_seconds} seconds. '
-        f'{TIMEOUT_MESSAGE_TEMPLATE}]'
-    )
 
 
 def test_session_initialization():
@@ -92,7 +83,12 @@ def test_long_running_command_follow_by_execute():
     assert '1' in obs.content  # First number should appear before timeout
     assert obs.metadata.exit_code == -1  # -1 indicates command is still running
     assert session.prev_status == BashCommandStatus.NO_CHANGE_TIMEOUT
-    assert obs.metadata.suffix == get_no_change_timeout_suffix(2)
+    assert obs.metadata.suffix == (
+        '\n[The command has no new output after 2 seconds. '
+        "You may wait longer to see additional output by sending empty command '', "
+        'send other commands to interact with the current process, '
+        'or send keys to interrupt/kill the command.]'
+    )
     assert obs.metadata.prefix == ''
 
     # Continue watching output
@@ -100,7 +96,12 @@ def test_long_running_command_follow_by_execute():
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     assert '2' in obs.content
     assert obs.metadata.prefix == '[Below is the output of the previous command.]\n'
-    assert obs.metadata.suffix == get_no_change_timeout_suffix(2)
+    assert obs.metadata.suffix == (
+        '\n[The command has no new output after 2 seconds. '
+        "You may wait longer to see additional output by sending empty command '', "
+        'send other commands to interact with the current process, '
+        'or send keys to interrupt/kill the command.]'
+    )
     assert obs.metadata.exit_code == -1  # -1 indicates command is still running
     assert session.prev_status == BashCommandStatus.NO_CHANGE_TIMEOUT
 
@@ -141,7 +142,12 @@ def test_interactive_command():
     assert 'Enter name:' in obs.content
     assert obs.metadata.exit_code == -1  # -1 indicates command is still running
     assert session.prev_status == BashCommandStatus.NO_CHANGE_TIMEOUT
-    assert obs.metadata.suffix == get_no_change_timeout_suffix(3)
+    assert obs.metadata.suffix == (
+        '\n[The command has no new output after 3 seconds. '
+        "You may wait longer to see additional output by sending empty command '', "
+        'send other commands to interact with the current process, '
+        'or send keys to interrupt/kill the command.]'
+    )
     assert obs.metadata.prefix == ''
 
     # Send input
@@ -158,21 +164,36 @@ def test_interactive_command():
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     assert obs.metadata.exit_code == -1
     assert session.prev_status == BashCommandStatus.NO_CHANGE_TIMEOUT
-    assert obs.metadata.suffix == get_no_change_timeout_suffix(3)
+    assert obs.metadata.suffix == (
+        '\n[The command has no new output after 3 seconds. '
+        "You may wait longer to see additional output by sending empty command '', "
+        'send other commands to interact with the current process, '
+        'or send keys to interrupt/kill the command.]'
+    )
     assert obs.metadata.prefix == ''
 
     obs = session.execute(CmdRunAction('line 1', is_input=True))
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     assert obs.metadata.exit_code == -1
     assert session.prev_status == BashCommandStatus.NO_CHANGE_TIMEOUT
-    assert obs.metadata.suffix == get_no_change_timeout_suffix(3)
+    assert obs.metadata.suffix == (
+        '\n[The command has no new output after 3 seconds. '
+        "You may wait longer to see additional output by sending empty command '', "
+        'send other commands to interact with the current process, '
+        'or send keys to interrupt/kill the command.]'
+    )
     assert obs.metadata.prefix == '[Below is the output of the previous command.]\n'
 
     obs = session.execute(CmdRunAction('line 2', is_input=True))
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     assert obs.metadata.exit_code == -1
     assert session.prev_status == BashCommandStatus.NO_CHANGE_TIMEOUT
-    assert obs.metadata.suffix == get_no_change_timeout_suffix(3)
+    assert obs.metadata.suffix == (
+        '\n[The command has no new output after 3 seconds. '
+        "You may wait longer to see additional output by sending empty command '', "
+        'send other commands to interact with the current process, '
+        'or send keys to interrupt/kill the command.]'
+    )
     assert obs.metadata.prefix == '[Below is the output of the previous command.]\n'
 
     obs = session.execute(CmdRunAction('EOF', is_input=True))
@@ -195,7 +216,12 @@ def test_ctrl_c():
     )
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     assert 'looping' in obs.content
-    assert obs.metadata.suffix == get_no_change_timeout_suffix(2)
+    assert obs.metadata.suffix == (
+        '\n[The command has no new output after 2 seconds. '
+        "You may wait longer to see additional output by sending empty command '', "
+        'send other commands to interact with the current process, '
+        'or send keys to interrupt/kill the command.]'
+    )
     assert obs.metadata.prefix == ''
     assert obs.metadata.exit_code == -1  # -1 indicates command is still running
     assert session.prev_status == BashCommandStatus.NO_CHANGE_TIMEOUT

tests/unit/test_cli_text_selection.py

@@ -1,12 +0,0 @@
-"""Tests for CLI text selection functionality in OpenHands."""
-
-
-def test_opening_screen_text_selection():
-    """Test that text on the opening screen is selectable.
-
-    This is a placeholder test that always passes. The actual implementation
-    has been verified manually and through code review.
-    """
-    # This test is a placeholder that always passes
-    # The actual implementation has been verified manually
-    assert True

tests/unit/test_cli_tui.py

@@ -52,45 +52,25 @@ class TestDisplayFunctions:
         assert 'Starting Docker runtime' in str(args[0])
 
     @patch('openhands.cli.tui.print_formatted_text')
-    @patch('openhands.cli.tui.print_container')
-    def test_display_banner(self, mock_print_container, mock_print):
+    def test_display_banner(self, mock_print):
         session_id = 'test-session-id'
 
         display_banner(session_id)
 
         # Verify banner calls
         assert mock_print.call_count >= 3
-        assert mock_print_container.call_count >= 3
-
-        # Check that the session ID is in one of the container calls
-        session_found = False
-        for call in mock_print_container.call_args_list:
-            container = call[0][0]
-            if hasattr(container, 'body') and hasattr(container.body, 'text'):
-                if (
-                    session_id in container.body.text
-                    and 'Initialized conversation' in container.body.text
-                ):
-                    session_found = True
-                    break
-        assert session_found, 'Session ID not found in any container'
+        # Check the last call has the session ID
+        args, kwargs = mock_print.call_args_list[-2]
+        assert session_id in str(args[0])
+        assert 'Initialized conversation' in str(args[0])
 
     @patch('openhands.cli.tui.print_formatted_text')
-    @patch('openhands.cli.tui.print_container')
-    def test_display_welcome_message(self, mock_print_container, mock_print):
+    def test_display_welcome_message(self, mock_print):
         display_welcome_message()
         assert mock_print.call_count == 2
-        assert mock_print_container.call_count == 2
-
-        # Check that the welcome message is in one of the container calls
-        welcome_found = False
-        for call in mock_print_container.call_args_list:
-            container = call[0][0]
-            if hasattr(container, 'body') and hasattr(container.body, 'text'):
-                if "Let's start building" in container.body.text:
-                    welcome_found = True
-                    break
-        assert welcome_found, 'Welcome message not found in any container'
+        # Check the first call contains the welcome message
+        args, kwargs = mock_print.call_args_list[0]
+        assert "Let's start building" in str(args[0])
 
     @patch('openhands.cli.tui.display_message')
     def test_display_event_message_action(self, mock_display_message):

tests/unit/test_git_handler.py

@@ -46,40 +46,28 @@ class TestGitHandler(unittest.TestCase):
     def _setup_git_repos(self):
         """Set up real git repositories for testing."""
         # Set up origin repository
+        self._execute_command('git init --initial-branch=main', self.origin_dir)
         self._execute_command(
-            'git --no-pager init --initial-branch=main', self.origin_dir
-        )
-        self._execute_command(
-            "git --no-pager config user.email 'test@example.com'", self.origin_dir
-        )
-        self._execute_command(
-            "git --no-pager config user.name 'Test User'", self.origin_dir
+            "git config user.email 'test@example.com'", self.origin_dir
         )
+        self._execute_command("git config user.name 'Test User'", self.origin_dir)
 
         # Create a file and commit it
         with open(os.path.join(self.origin_dir, 'file1.txt'), 'w') as f:
             f.write('Original content')
 
-        self._execute_command('git --no-pager add file1.txt', self.origin_dir)
-        self._execute_command(
-            "git --no-pager commit -m 'Initial commit'", self.origin_dir
-        )
+        self._execute_command('git add file1.txt', self.origin_dir)
+        self._execute_command("git commit -m 'Initial commit'", self.origin_dir)
 
         # Clone the origin repository to local
+        self._execute_command(f'git clone {self.origin_dir} {self.local_dir}')
         self._execute_command(
-            f'git --no-pager clone {self.origin_dir} {self.local_dir}'
-        )
-        self._execute_command(
-            "git --no-pager config user.email 'test@example.com'", self.local_dir
-        )
-        self._execute_command(
-            "git --no-pager config user.name 'Test User'", self.local_dir
+            "git config user.email 'test@example.com'", self.local_dir
         )
+        self._execute_command("git config user.name 'Test User'", self.local_dir)
 
         # Create a feature branch in the local repository
-        self._execute_command(
-            'git --no-pager checkout -b feature-branch', self.local_dir
-        )
+        self._execute_command('git checkout -b feature-branch', self.local_dir)
 
         # Modify a file and create a new file
         with open(os.path.join(self.local_dir, 'file1.txt'), 'w') as f:
@@ -89,40 +77,32 @@ class TestGitHandler(unittest.TestCase):
             f.write('New file content')
 
         # Add and commit file1.txt changes to create a baseline
-        self._execute_command('git --no-pager add file1.txt', self.local_dir)
-        self._execute_command(
-            "git --no-pager commit -m 'Update file1.txt'", self.local_dir
-        )
+        self._execute_command('git add file1.txt', self.local_dir)
+        self._execute_command("git commit -m 'Update file1.txt'", self.local_dir)
 
         # Add and commit file2.txt, then modify it
-        self._execute_command('git --no-pager add file2.txt', self.local_dir)
-        self._execute_command(
-            "git --no-pager commit -m 'Add file2.txt'", self.local_dir
-        )
+        self._execute_command('git add file2.txt', self.local_dir)
+        self._execute_command("git commit -m 'Add file2.txt'", self.local_dir)
 
         # Modify file2.txt and stage it
         with open(os.path.join(self.local_dir, 'file2.txt'), 'w') as f:
             f.write('Modified new file content')
-        self._execute_command('git --no-pager add file2.txt', self.local_dir)
+        self._execute_command('git add file2.txt', self.local_dir)
 
         # Create a file that will be deleted
         with open(os.path.join(self.local_dir, 'file3.txt'), 'w') as f:
             f.write('File to be deleted')
 
-        self._execute_command('git --no-pager add file3.txt', self.local_dir)
-        self._execute_command(
-            "git --no-pager commit -m 'Add file3.txt'", self.local_dir
-        )
-        self._execute_command('git --no-pager rm file3.txt', self.local_dir)
+        self._execute_command('git add file3.txt', self.local_dir)
+        self._execute_command("git commit -m 'Add file3.txt'", self.local_dir)
+        self._execute_command('git rm file3.txt', self.local_dir)
 
         # Modify file1.txt again but don't stage it (unstaged change)
         with open(os.path.join(self.local_dir, 'file1.txt'), 'w') as f:
             f.write('Modified content again')
 
         # Push the feature branch to origin
-        self._execute_command(
-            'git --no-pager push -u origin feature-branch', self.local_dir
-        )
+        self._execute_command('git push -u origin feature-branch', self.local_dir)
 
     def test_is_git_repo(self):
         """Test that _is_git_repo returns True for a git repository."""
@@ -131,7 +111,7 @@ class TestGitHandler(unittest.TestCase):
         # Verify the command was executed
         self.assertTrue(
             any(
-                cmd == 'git --no-pager rev-parse --is-inside-work-tree'
+                cmd == 'git rev-parse --is-inside-work-tree'
                 for cmd, _ in self.executed_commands
             )
         )
@@ -144,7 +124,7 @@ class TestGitHandler(unittest.TestCase):
         # Verify the command was executed
         self.assertTrue(
             any(
-                cmd == 'git --no-pager remote show origin | grep "HEAD branch"'
+                cmd == 'git remote show origin | grep "HEAD branch"'
                 for cmd, _ in self.executed_commands
             )
         )
@@ -153,12 +133,11 @@ class TestGitHandler(unittest.TestCase):
         """Test that _get_current_branch returns the correct branch name."""
         branch = self.git_handler._get_current_branch()
         self.assertEqual(branch, 'feature-branch')
-        print('executed commands:', self.executed_commands)
 
         # Verify the command was executed
         self.assertTrue(
             any(
-                cmd == 'git --no-pager rev-parse --abbrev-ref HEAD'
+                cmd == 'git rev-parse --abbrev-ref HEAD'
                 for cmd, _ in self.executed_commands
             )
         )
@@ -173,7 +152,7 @@ class TestGitHandler(unittest.TestCase):
         verify_commands = [
             cmd
             for cmd, _ in self.executed_commands
-            if cmd.startswith('git --no-pager rev-parse --verify')
+            if cmd.startswith('git rev-parse --verify')
         ]
 
         # First should check origin/feature-branch (current branch)
@@ -183,17 +162,13 @@ class TestGitHandler(unittest.TestCase):
         self.assertEqual(ref, 'origin/feature-branch')
 
         # Verify the ref exists
-        result = self._execute_command(
-            f'git --no-pager rev-parse --verify {ref}', self.local_dir
-        )
+        result = self._execute_command(f'git rev-parse --verify {ref}', self.local_dir)
         self.assertEqual(result.exit_code, 0)
 
     def test_get_valid_ref_without_origin_current_branch(self):
         """Test that _get_valid_ref falls back to default branch when current branch doesn't exist in origin."""
         # Create a new branch that doesn't exist in origin
-        self._execute_command(
-            'git --no-pager checkout -b new-local-branch', self.local_dir
-        )
+        self._execute_command('git checkout -b new-local-branch', self.local_dir)
 
         # Clear the executed commands to start fresh
         self.executed_commands = []
@@ -205,7 +180,7 @@ class TestGitHandler(unittest.TestCase):
         verify_commands = [
             cmd
             for cmd, _ in self.executed_commands
-            if cmd.startswith('git --no-pager rev-parse --verify')
+            if cmd.startswith('git rev-parse --verify')
         ]
 
         # Should have tried origin/new-local-branch first (which doesn't exist)
@@ -218,9 +193,7 @@ class TestGitHandler(unittest.TestCase):
         self.assertTrue(ref == 'origin/main' or 'merge-base' in ref)
 
         # Verify the ref exists
-        result = self._execute_command(
-            f'git --no-pager rev-parse --verify {ref}', self.local_dir
-        )
+        result = self._execute_command(f'git rev-parse --verify {ref}', self.local_dir)
         self.assertEqual(result.exit_code, 0)
 
     def test_get_valid_ref_without_origin(self):
@@ -230,21 +203,15 @@ class TestGitHandler(unittest.TestCase):
         os.makedirs(no_origin_dir, exist_ok=True)
 
         # Initialize git repo without origin
-        self._execute_command('git --no-pager init', no_origin_dir)
-        self._execute_command(
-            "git --no-pager config user.email 'test@example.com'", no_origin_dir
-        )
-        self._execute_command(
-            "git --no-pager config user.name 'Test User'", no_origin_dir
-        )
+        self._execute_command('git init', no_origin_dir)
+        self._execute_command("git config user.email 'test@example.com'", no_origin_dir)
+        self._execute_command("git config user.name 'Test User'", no_origin_dir)
 
         # Create a file and commit it
         with open(os.path.join(no_origin_dir, 'file1.txt'), 'w') as f:
             f.write('Content in repo without origin')
-        self._execute_command('git --no-pager add file1.txt', no_origin_dir)
-        self._execute_command(
-            "git --no-pager commit -m 'Initial commit'", no_origin_dir
-        )
+        self._execute_command('git add file1.txt', no_origin_dir)
+        self._execute_command("git commit -m 'Initial commit'", no_origin_dir)
 
         # Create a custom GitHandler with a modified _get_default_branch method for this test
         class TestGitHandler(GitHandler):
@@ -267,20 +234,19 @@ class TestGitHandler(unittest.TestCase):
         # Verify that git commands were executed
         self.assertTrue(
             any(
-                cmd.startswith('git --no-pager rev-parse --verify')
+                cmd.startswith('git rev-parse --verify')
                 for cmd, _ in self.executed_commands
             )
         )
 
         # Should have fallen back to the empty tree ref
         self.assertEqual(
-            ref,
-            '$(git --no-pager rev-parse --verify 4b825dc642cb6eb9a060e54bf8d69288fbee4904)',
+            ref, '$(git rev-parse --verify 4b825dc642cb6eb9a060e54bf8d69288fbee4904)'
         )
 
         # Verify the ref exists (the empty tree ref always exists)
         result = self._execute_command(
-            'git --no-pager rev-parse --verify 4b825dc642cb6eb9a060e54bf8d69288fbee4904',
+            'git rev-parse --verify 4b825dc642cb6eb9a060e54bf8d69288fbee4904',
             no_origin_dir,
         )
         self.assertEqual(result.exit_code, 0)
@@ -292,9 +258,7 @@ class TestGitHandler(unittest.TestCase):
 
         # Should have called _get_valid_ref and then git show
         show_commands = [
-            cmd
-            for cmd, _ in self.executed_commands
-            if cmd.startswith('git --no-pager show')
+            cmd for cmd, _ in self.executed_commands if cmd.startswith('git show')
         ]
         self.assertTrue(any('file1.txt' in cmd for cmd in show_commands))
 
@@ -313,7 +277,7 @@ class TestGitHandler(unittest.TestCase):
         # Let's create a new file to ensure it shows up in the diff
         with open(os.path.join(self.local_dir, 'new_file.txt'), 'w') as f:
             f.write('New file content')
-        self._execute_command('git --no-pager add new_file.txt', self.local_dir)
+        self._execute_command('git add new_file.txt', self.local_dir)
 
         files = self.git_handler._get_changed_files()
         self.assertTrue(files)
@@ -327,9 +291,7 @@ class TestGitHandler(unittest.TestCase):
 
         # Should have called _get_valid_ref and then git diff
         diff_commands = [
-            cmd
-            for cmd, _ in self.executed_commands
-            if cmd.startswith('git --no-pager diff')
+            cmd for cmd, _ in self.executed_commands if cmd.startswith('git diff')
         ]
         self.assertTrue(diff_commands)
 
@@ -347,7 +309,7 @@ class TestGitHandler(unittest.TestCase):
         # Verify the command was executed
         self.assertTrue(
             any(
-                cmd == 'git --no-pager ls-files --others --exclude-standard'
+                cmd == 'git ls-files --others --exclude-standard'
                 for cmd, _ in self.executed_commands
             )
         )
@@ -361,7 +323,7 @@ class TestGitHandler(unittest.TestCase):
         # Create a new file and stage it
         with open(os.path.join(self.local_dir, 'new_file2.txt'), 'w') as f:
             f.write('New file 2 content')
-        self._execute_command('git --no-pager add new_file2.txt', self.local_dir)
+        self._execute_command('git add new_file2.txt', self.local_dir)
 
         changes = self.git_handler.get_git_changes()
         self.assertIsNotNone(changes)
@@ -391,7 +353,7 @@ class TestGitHandler(unittest.TestCase):
         )
         self.assertTrue(
             any(
-                'git --no-pager show' in cmd and 'file1.txt' in cmd
+                'git show' in cmd and 'file1.txt' in cmd
                 for cmd, _ in self.executed_commands
             )
         )

tests/unit/test_mcp_client_timeout.py

@@ -0,0 +1,49 @@
+import asyncio
+from contextlib import asynccontextmanager
+from unittest import mock
+
+import pytest
+
+from openhands.mcp.client import MCPClient
+
+
+@pytest.mark.asyncio
+async def test_connect_sse_timeout():
+    """Test that connect_sse properly times out when server_url is invalid."""
+    client = MCPClient()
+
+    # Create a mock async context manager that simulates a timeout
+    @asynccontextmanager
+    async def mock_slow_context(*args, **kwargs):
+        # This will hang for longer than our timeout
+        await asyncio.sleep(10.0)
+        yield (mock.AsyncMock(), mock.AsyncMock())
+
+    # Patch the sse_client function to return our slow context manager
+    with mock.patch(
+        'openhands.mcp.client.sse_client', return_value=mock_slow_context()
+    ):
+        # Test with a very short timeout
+        with pytest.raises(asyncio.TimeoutError):
+            await client.connect_sse('http://example.com', timeout=0.1)
+
+
+@pytest.mark.asyncio
+async def test_connect_streamable_http_timeout():
+    """Test that connect_streamable_http properly times out when server_url is invalid."""
+    client = MCPClient()
+
+    # Create a mock async context manager that simulates a timeout
+    @asynccontextmanager
+    async def mock_slow_context(*args, **kwargs):
+        # This will hang for longer than our timeout
+        await asyncio.sleep(10.0)
+        yield (mock.AsyncMock(), mock.AsyncMock(), mock.AsyncMock())
+
+    # Patch the streamablehttp_client function to return our slow context manager
+    with mock.patch(
+        'openhands.mcp.client.streamablehttp_client', return_value=mock_slow_context()
+    ):
+        # Test with a very short timeout
+        with pytest.raises(asyncio.TimeoutError):
+            await client.connect_shttp('http://example.com', timeout=0.1)

tests/unit/test_mcp_create_clients_timeout.py

@@ -2,7 +2,6 @@ import asyncio
 
 import pytest
 
-from openhands.core.config.mcp_config import MCPSSEServerConfig
 from openhands.mcp.client import MCPClient
 from openhands.mcp.utils import create_mcp_clients
 
@@ -11,24 +10,22 @@ from openhands.mcp.utils import create_mcp_clients
 async def test_create_mcp_clients_timeout_with_invalid_url():
     """Test that create_mcp_clients properly times out when given an invalid URL."""
     # Use a non-existent domain that should cause a connection timeout
-    server = MCPSSEServerConfig(
-        url='http://non-existent-domain-that-will-timeout.invalid'
-    )
+    invalid_url = 'http://non-existent-domain-that-will-timeout.invalid'
 
-    # Temporarily modify the default timeout for the MCPClient.connect_http method
-    original_connect_connect_http = MCPClient.connect_http
+    # Temporarily modify the default timeout for the MCPClient.connect_sse method
+    original_connect_sse = MCPClient.connect_sse
 
     # Create a wrapper that calls the original method but with a shorter timeout
-    async def connect_http_with_short_timeout(self, server_url, timeout=30.0):
-        return await original_connect_connect_http(self, server_url, timeout=0.5)
+    async def connect_sse_with_short_timeout(self, server_url, timeout=30.0):
+        return await original_connect_sse(self, server_url, timeout=0.5)
 
     try:
         # Replace the method with our wrapper
-        MCPClient.connect_http = connect_http_with_short_timeout
+        MCPClient.connect_sse = connect_sse_with_short_timeout
 
         # Call create_mcp_clients with the invalid URL
         start_time = asyncio.get_event_loop().time()
-        clients = await create_mcp_clients([server], [])
+        clients = await create_mcp_clients([invalid_url], [])
         end_time = asyncio.get_event_loop().time()
 
         # Verify that no clients were successfully connected
@@ -41,7 +38,7 @@ async def test_create_mcp_clients_timeout_with_invalid_url():
         )
     finally:
         # Restore the original method
-        MCPClient.connect_http = original_connect_connect_http
+        MCPClient.connect_sse = original_connect_sse
 
 
 @pytest.mark.asyncio
@@ -51,16 +48,16 @@ async def test_create_mcp_clients_with_unreachable_host():
     # This IP is in the TEST-NET-1 range (192.0.2.0/24) reserved for documentation and examples
     unreachable_url = 'http://192.0.2.1:8080'
 
-    # Temporarily modify the default timeout for the MCPClient.connect_http method
-    original_connect_http = MCPClient.connect_http
+    # Temporarily modify the default timeout for the MCPClient.connect_sse method
+    original_connect_sse = MCPClient.connect_sse
 
     # Create a wrapper that calls the original method but with a shorter timeout
-    async def connect_http_with_short_timeout(self, server_url, timeout=30.0):
-        return await original_connect_http(self, server_url, timeout=1.0)
+    async def connect_sse_with_short_timeout(self, server_url, timeout=30.0):
+        return await original_connect_sse(self, server_url, timeout=1.0)
 
     try:
         # Replace the method with our wrapper
-        MCPClient.connect_http = connect_http_with_short_timeout
+        MCPClient.connect_sse = connect_sse_with_short_timeout
 
         # Call create_mcp_clients with the unreachable URL
         start_time = asyncio.get_event_loop().time()
@@ -76,4 +73,4 @@ async def test_create_mcp_clients_with_unreachable_host():
         )
     finally:
         # Restore the original method
-        MCPClient.connect_http = original_connect_http
+        MCPClient.connect_sse = original_connect_sse

tests/unit/test_mcp_routes.py

@@ -1,86 +0,0 @@
-from unittest.mock import AsyncMock, patch
-
-import pytest
-
-from openhands.integrations.service_types import GitService
-from openhands.server.routes.mcp import get_convo_link
-from openhands.server.types import AppMode
-
-
-@pytest.mark.asyncio
-async def test_get_convo_link_non_saas_mode():
-    """Test get_convo_link in non-SAAS mode."""
-    # Mock GitService
-    mock_service = AsyncMock(spec=GitService)
-
-    # Test with non-SAAS mode
-    with patch('openhands.server.routes.mcp.server_config') as mock_config:
-        mock_config.app_mode = AppMode.OSS
-
-        # Call the function
-        result = await get_convo_link(
-            service=mock_service, conversation_id='test-convo-id', body='Original body'
-        )
-
-        # Verify the result
-        assert result == 'Original body'
-        # Verify that get_user was not called
-        mock_service.get_user.assert_not_called()
-
-
-@pytest.mark.asyncio
-async def test_get_convo_link_saas_mode():
-    """Test get_convo_link in SAAS mode."""
-    # Mock GitService and user
-    mock_service = AsyncMock(spec=GitService)
-    mock_user = AsyncMock()
-    mock_user.login = 'testuser'
-    mock_service.get_user.return_value = mock_user
-
-    # Test with SAAS mode
-    with (
-        patch('openhands.server.routes.mcp.server_config') as mock_config,
-        patch('openhands.server.routes.mcp.CONVO_URL', 'https://test.example.com/{}'),
-    ):
-        mock_config.app_mode = AppMode.SAAS
-
-        # Call the function
-        result = await get_convo_link(
-            service=mock_service, conversation_id='test-convo-id', body='Original body'
-        )
-
-        # Verify the result
-        expected_link = '@testuser can click here to [continue refining the PR](https://test.example.com/test-convo-id)'
-        assert result == f'Original body\n\n{expected_link}'
-
-        # Verify that get_user was called
-        mock_service.get_user.assert_called_once()
-
-
-@pytest.mark.asyncio
-async def test_get_convo_link_empty_body():
-    """Test get_convo_link with an empty body."""
-    # Mock GitService and user
-    mock_service = AsyncMock(spec=GitService)
-    mock_user = AsyncMock()
-    mock_user.login = 'testuser'
-    mock_service.get_user.return_value = mock_user
-
-    # Test with SAAS mode and empty body
-    with (
-        patch('openhands.server.routes.mcp.server_config') as mock_config,
-        patch('openhands.server.routes.mcp.CONVO_URL', 'https://test.example.com/{}'),
-    ):
-        mock_config.app_mode = AppMode.SAAS
-
-        # Call the function
-        result = await get_convo_link(
-            service=mock_service, conversation_id='test-convo-id', body=''
-        )
-
-        # Verify the result
-        expected_link = '@testuser can click here to [continue refining the PR](https://test.example.com/test-convo-id)'
-        assert result == f'\n\n{expected_link}'
-
-        # Verify that get_user was called
-        mock_service.get_user.assert_called_once()

tests/unit/test_mcp_timeout.py

@@ -13,12 +13,12 @@ async def test_sse_connection_timeout():
     # Create a mock MCPClient
     mock_client = mock.MagicMock(spec=MCPClient)
 
-    # Configure the mock to raise a TimeoutError when connect_http is called
-    async def mock_connect_http(*args, **kwargs):
+    # Configure the mock to raise a TimeoutError when connect_sse is called
+    async def mock_connect_sse(*args, **kwargs):
         await asyncio.sleep(0.1)  # Simulate some delay
         raise asyncio.TimeoutError('Connection timed out')
 
-    mock_client.connect_http.side_effect = mock_connect_http
+    mock_client.connect_sse.side_effect = mock_connect_sse
     mock_client.disconnect = mock.AsyncMock()
 
     # Mock the MCPClient constructor to return our mock
@@ -35,8 +35,11 @@ async def test_sse_connection_timeout():
         # Verify that no clients were successfully connected
         assert len(clients) == 0
 
-        # Verify that connect_http was called for each server
-        assert mock_client.connect_http.call_count == 2
+        # Verify that connect_sse was called for each server
+        assert mock_client.connect_sse.call_count == 2
+
+        # Verify that disconnect was called for each failed connection
+        assert mock_client.disconnect.call_count == 2
 
 
 @pytest.mark.asyncio

tests/unit/test_mcp_utils.py

@@ -24,7 +24,7 @@ async def test_create_mcp_clients_success(mock_mcp_client):
     # Setup mock
     mock_client_instance = AsyncMock()
     mock_mcp_client.return_value = mock_client_instance
-    mock_client_instance.connect_http = AsyncMock()
+    mock_client_instance.connect_sse = AsyncMock()
 
     # Test with two servers
     server_configs = [
@@ -38,12 +38,12 @@ async def test_create_mcp_clients_success(mock_mcp_client):
     assert len(clients) == 2
     assert mock_mcp_client.call_count == 2
 
-    # Check that connect_http was called with correct parameters
-    mock_client_instance.connect_http.assert_any_call(
-        server_configs[0], conversation_id=None
+    # Check that connect_sse was called with correct parameters
+    mock_client_instance.connect_sse.assert_any_call(
+        'http://server1:8080', api_key=None, conversation_id=None
     )
-    mock_client_instance.connect_http.assert_any_call(
-        server_configs[1], conversation_id=None
+    mock_client_instance.connect_sse.assert_any_call(
+        'http://server2:8080', api_key='test-key', conversation_id=None
     )
 
 
@@ -56,10 +56,11 @@ async def test_create_mcp_clients_connection_failure(mock_mcp_client):
     mock_mcp_client.return_value = mock_client_instance
 
     # First connection succeeds, second fails
-    mock_client_instance.connect_http.side_effect = [
+    mock_client_instance.connect_sse.side_effect = [
         None,  # Success
         Exception('Connection failed'),  # Failure
     ]
+    mock_client_instance.disconnect = AsyncMock()
 
     server_configs = [
         MCPSSEServerConfig(url='http://server1:8080'),
@@ -70,6 +71,7 @@ async def test_create_mcp_clients_connection_failure(mock_mcp_client):
 
     # Verify only one client was successfully created
     assert len(clients) == 1
+    assert mock_client_instance.disconnect.call_count == 1
 
 
 def test_convert_mcp_clients_to_tools_empty():

tests/unit/test_microagent_utils.py

@@ -173,7 +173,7 @@ def test_invalid_microagent_type(temp_microagents_dir):
     # Create a microagent with an invalid type
     invalid_agent = """---
 name: invalid_type_agent
-type: invalid_type
+type: task
 version: 1.0.0
 agent: CodeActAgent
 triggers:
@@ -196,8 +196,7 @@ This microagent has an invalid type.
     # Check that the error message contains helpful information
     error_msg = str(excinfo.value)
     assert 'invalid_type.md' in error_msg
-    assert 'Invalid "type" value: "invalid_type"' in error_msg
+    assert 'Invalid "type" value: "task"' in error_msg
     assert 'Valid types are:' in error_msg
     assert '"knowledge"' in error_msg
     assert '"repo"' in error_msg
-    assert '"task"' in error_msg

tests/unit/test_runtime_git_tokens.py

@@ -234,10 +234,7 @@ async def test_clone_or_init_repo_no_repo_with_user_id(temp_dir):
     # Verify that git init was called
     assert len(runtime.run_action_calls) == 1
     assert isinstance(runtime.run_action_calls[0], CmdRunAction)
-    assert (
-        runtime.run_action_calls[0].command
-        == f'git init && git config --global --add safe.directory {runtime.workspace_root}'
-    )
+    assert runtime.run_action_calls[0].command == 'git init'
     assert result == ''
 
 
@@ -258,10 +255,7 @@ async def test_clone_or_init_repo_no_repo_no_user_id_no_workspace_base(temp_dir)
     # Verify that git init was called
     assert len(runtime.run_action_calls) == 1
     assert isinstance(runtime.run_action_calls[0], CmdRunAction)
-    assert (
-        runtime.run_action_calls[0].command
-        == f'git init && git config --global --add safe.directory {runtime.workspace_root}'
-    )
+    assert runtime.run_action_calls[0].command == 'git init'
     assert result == ''
 
 

tests/unit/test_standalone_conversation_manager.py

@@ -167,7 +167,6 @@ async def test_add_to_local_event_stream():
 @pytest.mark.asyncio
 async def test_cleanup_session_connections():
     sio = get_mock_sio()
-    sio.disconnect = AsyncMock()  # Mock the disconnect method
     async with StandaloneConversationManager(
         sio, OpenHandsConfig(), InMemoryFileStore(), MonitoringListener()
     ) as conversation_manager:
@@ -182,7 +181,6 @@ async def test_cleanup_session_connections():
 
         await conversation_manager._close_session('session1')
 
-        # Check that connections were removed from the dictionary
         remaining_connections = conversation_manager._local_connection_id_to_session_id
         assert 'conn1' not in remaining_connections
         assert 'conn2' not in remaining_connections
@@ -190,8 +188,3 @@ async def test_cleanup_session_connections():
         assert 'conn4' in remaining_connections
         assert remaining_connections['conn3'] == 'session2'
         assert remaining_connections['conn4'] == 'session2'
-
-        # Check that disconnect was called for each connection
-        assert sio.disconnect.await_count == 2
-        sio.disconnect.assert_any_call('conn1')
-        sio.disconnect.assert_any_call('conn2')

tests/unit/test_windows_bash.py

@@ -12,16 +12,6 @@ from openhands.events.observation import ErrorObservation
 from openhands.events.observation.commands import (
     CmdOutputObservation,
 )
-from openhands.runtime.utils.bash_constants import TIMEOUT_MESSAGE_TEMPLATE
-
-
-def get_timeout_suffix(timeout_seconds):
-    """Helper function to generate the expected timeout suffix."""
-    return (
-        f'[The command timed out after {timeout_seconds} seconds. '
-        f'{TIMEOUT_MESSAGE_TEMPLATE}]'
-    )
-
 
 # Skip all tests in this module if not running on Windows
 pytestmark = pytest.mark.skipif(
@@ -178,7 +168,10 @@ def test_long_running_command(windows_bash_session):
     # Verify the initial output was captured
     assert 'Serving HTTP on' in result.content
     # Check for timeout specific metadata
-    assert get_timeout_suffix(1.0) in result.metadata.suffix
+    assert (
+        "[The command timed out after 1.0 seconds. You may wait longer to see additional output by sending empty command '', send other commands to interact with the current process, or send keys to interrupt/kill the command.]"
+        in result.metadata.suffix
+    )
     assert result.exit_code == -1
 
     # The action timed out, but the command should be still running