Update microagent documentation to clarify that type field is optional

Co-authored-by: openhands <openhands@all-hands.dev>
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>

.devcontainer/devcontainer.json

@@ -12,4 +12,5 @@
 		"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

docs/docs.json

@@ -38,7 +38,6 @@
                 ]
               },
               "usage/cloud/cloud-ui",
-              "usage/cloud/cloud-issue-resolver",
               "usage/cloud/cloud-api"
             ]
           },

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

@@ -1,33 +0,0 @@
----
-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

@@ -1,28 +1,36 @@
 ---
 title: 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.
+description: The Cloud UI provides a web interface for interacting with OpenHands. This page explains how to use the
+ OpenHands Cloud UI.
 ---
 
+## Landing Page
 
-## Accessing the UI
+The landing page is where you can:
 
-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.
-
-
-## Key Features
-
-For detailed information about the features available in the OpenHands Cloud UI, please refer to the [Key Features](../key-features) section of the documentation.
+- [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`.
 
 ## Settings
 
-The settings page allows you to:
+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.
+- [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.
 
 ## Next Steps
 
-- [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.
+- [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.

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 issues!
+  set up, it will allow OpenHands to work with your GitHub repository through the Cloud UI or straight from GitHub!
 ---
 
 ## 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 session!
+click on `Launch` to start the conversation!
 
 ![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
 
-- [Access the Cloud UI](./cloud-ui) to interact with the web interface
-- [Use the Cloud API](./cloud-api) to programmatically interact with OpenHands
+- [Learn about the Cloud UI](/usage/cloud/cloud-ui).
+- [Use the Cloud API](/usage/cloud/cloud-api) to programmatically interact with OpenHands.

docs/usage/cloud/gitlab-installation.mdx

@@ -1,23 +1,25 @@
 ---
 title: GitLab Integration
-description: This guide walks you through the process of installing and configuring OpenHands Cloud for your GitLab repositories.
+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.
 ---
 
 ## Prerequisites
 
-- A GitLab account
-- Access to OpenHands Cloud
+- Signed in to [OpenHands Cloud](https://app.all-hands.dev) with [a GitLab account](/usage/cloud/openhands-cloud).
 
-## Installation Steps
+## Adding GitLab Repository Access
 
-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
+Upon signing into OpenHands Cloud with a GitLab account, OpenHands will have access to your repositories.
 
+## 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
 
-- [Access the Cloud UI](./cloud-ui) to interact with the web interface
-- [Use the Cloud API](./cloud-api) to programmatically interact with OpenHands
+- [Learn about the Cloud UI](/usage/cloud/cloud-ui).
+- [Use the Cloud API](/usage/cloud/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](./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
+- [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.

docs/usage/prompting/microagents-keyword.mdx

@@ -5,26 +5,111 @@ description: Keyword-triggered microagents provide OpenHands with specific instr
 
 ## Usage
 
-These microagents are only loaded when a prompt includes one of the trigger words.
+Keyword-triggered microagents are only loaded when a prompt includes one of the trigger words. There are two types of keyword-triggered microagents:
+
+1. **Standard Keyword Microagents**: Triggered by keywords embedded in text
+2. **Command-Style Microagents**: Triggered by command-style inputs (e.g., `/fix_test`) that can prompt for user input
+
+Additionally, there's a special type of microagent that's always active:
+
+3. **Repository Microagents**: Always active for a specific repository, providing repository-specific context and tools
 
 ## Frontmatter Syntax
 
 Frontmatter is required for keyword-triggered microagents. It must be placed at the top of the file,
-above the guidelines.
+above the guidelines. Enclose the frontmatter in triple dashes (---).
 
-Enclose the frontmatter in triple dashes (---) and include the following fields:
+### Standard Keyword Microagents
+
+For standard keyword microagents, include the following fields:
 
 | Field      | Description                                      | Required | Default          |
 |------------|--------------------------------------------------|----------|------------------|
+| `name`     | The name of the microagent                       | No       | Filename         |
+| `type`     | The type of microagent (`knowledge`)             | No       | Inferred         |
 | `triggers` | A list of keywords that activate the microagent. | Yes      | None             |
-| `agent`    | The agent this microagent applies to.            | No       | 'CodeActAgent'   |
 
+### Command-Style Microagents
 
-## Example
+For command-style microagents that require user input, include the following fields:
 
-Keyword-triggered microagent file example located at `.openhands/microagents/yummy.md`:
-```
+| Field      | Description                                                | Required | Default          |
+|------------|------------------------------------------------------------|----------|------------------|
+| `name`     | The name of the microagent                                 | No       | Filename         |
+| `type`     | The type of microagent (`task`)                            | No       | Inferred         |
+| `triggers` | A list of command triggers (e.g., `/fix_test`)             | No       | `/[name]`        |
+| `inputs`   | A list of input variables the microagent requires          | Yes      | None             |
+
+### Repository Microagents
+
+Repository microagents are always active for a specific repository. They provide repository-specific context and tools.
+
+| Field      | Description                                                | Required | Default          |
+|------------|------------------------------------------------------------|----------|------------------|
+| `name`     | The name of the microagent                                 | No       | Filename         |
+| `type`     | The type of microagent (`repo`)                            | No       | Inferred         |
+
+#### Repository Microagent Example
+
+Here's an example of a repository microagent:
+
+```yaml
 ---
+# The type field is optional and will be inferred as 'repo' when no triggers are present
+---
+
+# Repository Guidelines
+
+This repository follows these coding standards:
+1. Use PEP 8 for Python code
+2. Use ESLint for JavaScript code
+3. Write unit tests for all new features
+```
+
+This microagent is always active when working with the repository and provides repository-specific guidelines.
+
+### MCP Tools Support
+
+Microagents can also provide additional MCP (Model-Code-Prompt) tools to the agent. This is useful for extending the agent's capabilities with custom tools.
+
+| Field        | Description                                                | Required | Default          |
+|--------------|-----------------------------------------------------------|----------|------------------|
+| `mcp_tools`  | Configuration for additional MCP tools                     | No       | None             |
+
+#### MCP Tools Example
+
+Here's an example of a microagent that provides an additional MCP tool (the `fetch` tool for accessing web content):
+
+```yaml
+---
+# The type field is optional and will be inferred as 'repo' when no triggers are present
+mcp_tools:
+  stdio_servers:
+    - name: "fetch"
+      command: uvx
+      args:
+        - mcp-server-fetch
+---
+```
+
+This microagent is a repository microagent (always active) that adds the `fetch` tool to the agent's capabilities.
+
+Each input in the `inputs` list requires:
+
+| Field         | Description                                      | Required |
+|---------------|--------------------------------------------------|----------|
+| `name`        | The name of the input variable                   | Yes      |
+| `description` | A description of what the input should contain   | Yes      |
+
+
+## Examples
+
+### Standard Keyword Microagent Example
+
+Standard keyword microagent file example located at `.openhands/microagents/yummy.md`:
+```yaml
+---
+# The type field is optional and will be inferred as 'knowledge' when triggers are present
 triggers:
 - yummyhappy
 - happyyummy
@@ -33,4 +118,58 @@ triggers:
 The user has said the magic word. Respond with "That was delicious!"
 ```
 
-[See examples of microagents triggered by keywords in the official OpenHands repository](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents)
+### Command-Style Microagent Example
+
+Command-style microagent file example located at `.openhands/microagents/fix_test.md`:
+```yaml
+---
+# The type field is optional and will be inferred as 'task' when inputs are present
+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.
+```
+
+## Using Command-Style Microagents
+
+Command-style microagents are designed to streamline common development tasks by providing structured templates for specific operations. They are triggered using a command-style format and will prompt the user for any required inputs.
+
+### How to Use
+
+1. Type `/` in the chat input to see available command-style microagents
+2. Select a microagent from the dropdown or type its name (e.g., `/fix_test`)
+3. The agent will prompt you for any required inputs
+4. Provide the requested information
+5. The agent will execute the task with your inputs
+
+### Template Variables
+
+In the body of a command-style microagent, you can reference input variables using the `{{ VARIABLE_NAME }}` syntax. These will be replaced with the user-provided values when the microagent is triggered.
+
+### Available Command-Style Microagents
+
+OpenHands includes several built-in command-style microagents:
+
+| Command              | Description                                           |
+|----------------------|-------------------------------------------------------|
+| `/fix_test`          | Fix failing tests by modifying a specific function    |
+| `/update_test`       | Update tests for a new implementation                 |
+| `/update_pr`         | Update a pull request description                     |
+| `/address_pr_comments` | Address comments on a pull request                  |
+| `/add_repo_instruction` | Add instructions to the repository microagent      |
+
+[See examples of microagents in the official OpenHands repository](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents)

docs/usage/prompting/microagents-overview.mdx

@@ -8,10 +8,10 @@ description: Microagents are specialized prompts that enhance OpenHands with dom
 Currently OpenHands supports the following types of microagents:
 
 - [General Microagents](./microagents-repo): General guidelines for OpenHands about the repository.
-- [Keyword-Triggered Microagents](./microagents-keyword): Guidelines activated by specific keywords in prompts.
+- [Keyword-Triggered Microagents](./microagents-keyword): Guidelines activated by specific keywords in prompts, including command-style microagents that prompt for user inputs.
 
 To customize OpenHands' behavior, create a .openhands/microagents/ directory in the root of your repository and
-add `<microagent_name>.md` files inside.
+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).
 
 <Note>
 Loaded microagents take up space in the context window.
@@ -34,7 +34,7 @@ some-repository/
 Each microagent file may include frontmatter that provides additional information. In some cases, this frontmatter
 is required:
 
-| Microagent Type                 | Required |
-|---------------------------------|----------|
-| `General Microagents`           | No       |
-| `Keyword-Triggered Microagents` | Yes      |
+| Microagent Type                                | Required |
+|------------------------------------------------|----------|
+| `General Microagents`                          | No       |
+| `Keyword-Triggered Microagents (all types)`    | Yes      |

docs/usage/prompting/microagents-repo.mdx

@@ -17,13 +17,45 @@ Frontmatter should be enclosed in triple dashes (---) and may include the follow
 |-----------|-----------------------------------------|----------|----------------|
 | `agent`   | The agent this microagent applies to    | No       | 'CodeActAgent' |
 
-## Example
+## Creating a Comprehensive Repository Agent
+
+To create an effective repository agent, you can ask OpenHands to analyze your repository with a prompt like:
 
-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

@@ -71,7 +71,6 @@ 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/hooks/query/use-settings.ts

@@ -45,6 +45,7 @@ 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/i18n/declaration.ts

@@ -567,6 +567,7 @@ 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/routes/user-settings.tsx

@@ -50,9 +50,12 @@ function EmailInputSection({
             data-testid="email-input"
           />
         </div>
-        
+
         {isEmailChanged && !isEmailValid && (
-          <div className="text-red-500 text-sm mt-1" data-testid="email-validation-error">
+          <div
+            className="text-red-500 text-sm mt-1"
+            data-testid="email-validation-error"
+          >
             {t("SETTINGS$INVALID_EMAIL_FORMAT")}
           </div>
         )}

frontend/src/utils/tips.ts

@@ -30,7 +30,7 @@ export const TIPS: Tip[] = [
   },
   {
     key: I18nKey.TIPS$GITHUB_HOOK,
-    link: "https://docs.all-hands.dev/usage/cloud/cloud-issue-resolver",
+    link: "https://docs.all-hands.dev/usage/cloud/github-installation#working-on-github-issues-and-pull-requests-using-openhands",
   },
   {
     key: I18nKey.TIPS$BLOG_SIGNUP,

microagents/README.md

@@ -117,7 +117,10 @@ 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

@@ -1,20 +1,17 @@
 ---
-name: add_agent
-type: knowledge
-version: 1.0.0
-agent: CodeActAgent
 triggers:
-  - new agent
-  - new microagent
-  - create agent
-  - create an agent
-  - create microagent
-  - create a microagent
-  - add agent
-  - add an agent
-  - add microagent
-  - add a microagent
-  - microagent template
+- new agent
+- new microagent
+- create agent
+- create an agent
+- create microagent
+- create a microagent
+- add agent
+- add an agent
+- add microagent
+- add a microagent
+- microagent template
+type: knowledge
 ---
 
 This agent helps create new microagents in the `.openhands/microagents` directory by providing guidance and templates.
@@ -38,4 +35,4 @@ 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)
+- [Example GitHub Microagent](https://github.com/All-Hands-AI/OpenHands/blob/main/microagents/github.md)

microagents/add_repo_inst.md

@@ -0,0 +1,61 @@
+---
+inputs:
+- description: Branch for the agent to work on
+  name: REPO_FOLDER_NAME
+triggers:
+- /add_repo_inst
+---
+
+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

@@ -0,0 +1,15 @@
+---
+inputs:
+- description: URL of the pull request
+  name: PR_URL
+- description: Branch name corresponds to the pull request
+  name: BRANCH_NAME
+triggers:
+- /address_pr_comments
+---
+
+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/agent_memory.md

@@ -1,10 +1,7 @@
 ---
-name: agent_memory
-type: knowledge
-version: 1.0.0
-agent: CodeActAgent
 triggers:
 - /remember
+type: knowledge
 ---
 
 * Repository memory: Use .openhands/microagents/repo.md under each repository root to store and access important information.
@@ -29,4 +26,4 @@ triggers:
   - If you've only explored a portion of the codebase, clearly note this limitation in the repository structure documentation
   - If you don't know the essential commands for working with the repository, such as lint or typecheck, ask the user and suggest adding them to repo.md for future reference (with permission)
 
-When you receive this message, please review and summarize your recent actions and observations, then present a list of valuable information that should be saved in repo.md to the user.
+When you receive this message, please review and summarize your recent actions and observations, then present a list of valuable information that should be saved in repo.md to the user.

microagents/default-tools.md

@@ -1,15 +1,9 @@
 ---
-# This is a repo microagent that is always activated
-# to include necessary default tools implemented with MCP
-name: default-tools
-type: repo
-version: 1.0.0
-agent: CodeActAgent
 mcp_tools:
   stdio_servers:
-    - name: "fetch"
-      command: "uvx"
-      args: ["mcp-server-fetch"]
-# We leave the body empty because MCP tools will automatically add the
-# tool description for LLMs in tool calls, so there's no need to add extra descriptions.
----
+  - args:
+    - mcp-server-fetch
+    command: uvx
+    name: fetch
+type: repo
+---

microagents/docker.md

@@ -1,11 +1,8 @@
 ---
-name: docker
-type: knowledge
-version: 1.0.0
-agent: CodeActAgent
 triggers:
 - docker
 - container
+type: knowledge
 ---
 
 # Docker Installation and Usage Guide
@@ -52,4 +49,4 @@ To verify Docker is working correctly, run the hello-world container:
 
 ```bash
 sudo docker run hello-world
-```
+```

microagents/fix_test.md

@@ -0,0 +1,20 @@
+---
+inputs:
+- description: Branch for the agent to work on
+  name: BRANCH_NAME
+- description: The test command you want the agent to work on. For example, `pytest
+    tests/unit/test_bash_parsing.py`
+  name: TEST_COMMAND_TO_RUN
+- description: The name of function to fix
+  name: FUNCTION_TO_FIX
+- description: The path of the file that contains the function
+  name: FILE_FOR_FUNCTION
+triggers:
+- /fix_test
+---
+
+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/flarglebargle.md

@@ -1,11 +1,8 @@
 ---
-name: flarglebargle
-type: knowledge
-version: 1.0.0
-agent: CodeActAgent
 triggers:
 - flarglebargle
+type: knowledge
 ---
 
 IMPORTANT! The user has said the magic word "flarglebargle". You must
-only respond with a message telling them how smart they are
+only respond with a message telling them how smart they are

microagents/github.md

@@ -1,11 +1,8 @@
 ---
-name: github
-type: knowledge
-version: 1.0.0
-agent: CodeActAgent
 triggers:
 - github
 - git
+type: knowledge
 ---
 
 You have access to an environment variable, `GITHUB_TOKEN`, which allows you to interact with
@@ -32,4 +29,4 @@ Here are some instructions for pushing, but ONLY do this if the user asks you to
 ```bash
 git remote -v && git branch # to find the current org, repo and branch
 git checkout -b create-widget && git add . && git commit -m "Create widget" && git push -u origin create-widget
-```
+```

microagents/gitlab.md

@@ -1,11 +1,8 @@
 ---
-name: gitlab
-type: knowledge
-version: 1.0.0
-agent: CodeActAgent
 triggers:
 - gitlab
 - git
+type: knowledge
 ---
 
 You have access to an environment variable, `GITLAB_TOKEN`, which allows you to interact with
@@ -31,4 +28,4 @@ Here are some instructions for pushing, but ONLY do this if the user asks you to
 ```bash
 git remote -v && git branch # to find the current org, repo and branch
 git checkout -b create-widget && git add . && git commit -m "Create widget" && git push -u origin create-widget
-```
+```

microagents/kubernetes.md

@@ -1,12 +1,9 @@
 ---
-name: kubernetes
-type: knowledge
-version: 1.0.0
-agent: CodeActAgent
 triggers:
 - kubernetes
 - k8s
 - kube
+type: knowledge
 ---
 
 # Kubernetes Local Development with KIND
@@ -47,4 +44,4 @@ Create a basic KIND cluster:
 
 ```bash
 kind create cluster
-```
+```

microagents/npm.md

@@ -1,11 +1,8 @@
 ---
-name: npm
-type: knowledge
-version: 1.0.0
-agent: CodeActAgent
 triggers:
 - npm
+type: knowledge
 ---
 
 When using npm to install packages, you will not be able to use an interactive shell, and it may be hard to confirm your actions.
-As an alternative, you can pipe in the output of the unix "yes" command to confirm your actions.
+As an alternative, you can pipe in the output of the unix "yes" command to confirm your actions.

microagents/pdflatex.md

@@ -1,10 +1,7 @@
 ---
-name: pdflatex
-type: knowledge
-version: 1.0.0
-agent: CodeActAgent
 triggers:
 - pdflatex
+type: knowledge
 ---
 
 PdfLatex is a tool that converts Latex sources into PDF. This is specifically very important for researchers, as they use it to publish their findings. It could be installed very easily using Linux terminal, though this seems an annoying task on Windows. Installation commands are given below.
@@ -33,4 +30,4 @@ Once installed as above, you may be able to create PDF files from latex sources
 pdflatex latex_source_name.tex
 ```
 
-Ref: http://kkpradeeban.blogspot.com/2014/04/installing-latexpdflatex-on-ubuntu.html
+Ref: http://kkpradeeban.blogspot.com/2014/04/installing-latexpdflatex-on-ubuntu.html

microagents/security.md

@@ -1,15 +1,13 @@
 ---
-name: security
-type: knowledge
-version: 1.0.0
-agent: CodeActAgent
 triggers:
-  - security
-  - vulnerability
-  - authentication
-  - authorization
-  - permissions
+- security
+- vulnerability
+- authentication
+- authorization
+- permissions
+type: knowledge
 ---
+
 This document provides guidance on security best practices
 
 You should always be considering security implications when developing.
@@ -31,4 +29,4 @@ You should always complete the task requested. If there are security concerns pl
 - Never expose sensitive information in error messages
 - Log security events appropriately
 - Implement proper exception handling
-- Use secure error reporting mechanisms
+- Use secure error reporting mechanisms

microagents/ssh.md

@@ -1,16 +1,13 @@
 ---
-name: SSH Microagent
-type: knowledge
-version: 1.0.0
-agent: CodeActAgent
 triggers:
-  - ssh
-  - remote server
-  - remote machine
-  - remote host
-  - remote connection
-  - secure shell
-  - ssh keys
+- ssh
+- remote server
+- remote machine
+- remote host
+- remote connection
+- secure shell
+- ssh keys
+type: knowledge
 ---
 
 # SSH Microagent
@@ -134,4 +131,4 @@ chmod 600 ~/.ssh/id_ed25519
 chmod 644 ~/.ssh/id_ed25519.pub
 # Set correct permissions for SSH directory
 chmod 700 ~/.ssh
-```
+```

microagents/swift-linux.md

@@ -1,12 +1,9 @@
 ---
- name: swift-linux
- type: knowledge
- agent: CodeActAgent
- version: 1.0.0
- triggers:
- - swift-linux
- - swift-debian
- - swift-installation
+triggers:
+- swift-linux
+- swift-debian
+- swift-installation
+type: knowledge
 ---
 
 # Swift Installation Guide for Debian Linux
@@ -80,4 +77,4 @@ Verify that Swift is correctly installed by running:
 
 ```bash
 swift --version
-```
+```

microagents/update_pr_description.md

@@ -0,0 +1,17 @@
+---
+inputs:
+- description: URL of the pull request
+  name: PR_URL
+  type: string
+  validation:
+    pattern: ^https://github.com/.+/.+/pull/[0-9]+$
+- description: Branch name corresponds to the pull request
+  name: BRANCH_NAME
+  type: string
+triggers:
+- /update_pr_description
+---
+
+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

@@ -0,0 +1,16 @@
+---
+inputs:
+- description: Branch for the agent to work on
+  name: BRANCH_NAME
+- description: The test command you want the agent to work on. For example, `pytest
+    tests/unit/test_bash_parsing.py`
+  name: TEST_COMMAND_TO_RUN
+triggers:
+- /update_test
+---
+
+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/integrations/templates/resolver/summary_prompt.j2

@@ -1,5 +1,8 @@
-Please summarize your work.
+Please send a final message summarizing your work.
 
-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.
+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.

openhands/mcp/client.py

@@ -73,7 +73,7 @@ class MCPClient(BaseModel):
             )
 
             if conversation_id:
-                headers['X-OpenHands-Conversation-ID'] = conversation_id
+                headers['X-OpenHands-ServerConversation-ID'] = conversation_id
 
             # Instantiate custom transports due to custom headers
             if isinstance(server, MCPSHTTPServerConfig):

openhands/microagent/microagent.py

@@ -1,4 +1,5 @@
 import io
+import re
 from pathlib import Path
 from typing import Union
 
@@ -9,7 +10,7 @@ from openhands.core.exceptions import (
     MicroagentValidationError,
 )
 from openhands.core.logger import openhands_logger as logger
-from openhands.microagent.types import MicroagentMetadata, MicroagentType
+from openhands.microagent.types import InputMetadata, MicroagentMetadata, MicroagentType
 
 
 class BaseMicroagent(BaseModel):
@@ -91,13 +92,26 @@ class BaseMicroagent(BaseModel):
         subclass_map = {
             MicroagentType.KNOWLEDGE: KnowledgeMicroagent,
             MicroagentType.REPO_KNOWLEDGE: RepoMicroagent,
+            MicroagentType.TASK: TaskMicroagent,
         }
 
         # Infer the agent type:
-        # 1. If triggers exist -> KNOWLEDGE (optional)
-        # 2. Else (no triggers) -> REPO (always active)
+        # 1. If inputs exist -> TASK
+        # 2. If triggers exist -> KNOWLEDGE
+        # 3. Else (no triggers) -> REPO (always active)
         inferred_type: MicroagentType
-        if metadata.triggers:
+        if metadata.inputs:
+            inferred_type = MicroagentType.TASK
+            # Add a trigger for the agent name if not already present
+            # Use derived_name if available, otherwise use metadata.name
+            agent_name = derived_name if derived_name is not None and (metadata.name == 'default' or not metadata.name) else metadata.name
+            trigger = f'/{agent_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:
             inferred_type = MicroagentType.KNOWLEDGE
         else:
             # No triggers, default to REPO
@@ -109,7 +123,11 @@ class BaseMicroagent(BaseModel):
             raise ValueError(f'Could not determine microagent type for: {path}')
 
         # Use derived_name if available (from relative path), otherwise fallback to metadata.name
-        agent_name = derived_name if derived_name is not None else metadata.name
+        # If metadata.name is still the default 'default', use the derived_name
+        if derived_name is not None and (metadata.name == 'default' or not metadata.name):
+            agent_name = derived_name
+        else:
+            agent_name = metadata.name
 
         agent_class = subclass_map[inferred_type]
         return agent_class(
@@ -122,7 +140,9 @@ 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
@@ -131,8 +151,8 @@ class KnowledgeMicroagent(BaseMicroagent):
 
     def __init__(self, **data):
         super().__init__(**data)
-        if self.type != MicroagentType.KNOWLEDGE:
-            raise ValueError('KnowledgeMicroagent must have type KNOWLEDGE')
+        if self.type not in [MicroagentType.KNOWLEDGE, MicroagentType.TASK]:
+            raise ValueError('KnowledgeMicroagent must have type KNOWLEDGE or TASK')
 
     def match_trigger(self, message: str) -> str | None:
         """Match a trigger in the message.
@@ -171,6 +191,57 @@ 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]]:
@@ -182,7 +253,7 @@ def load_microagents_from_dir(
         microagent_dir: Path to the microagents directory (e.g. .openhands/microagents)
 
     Returns:
-        Tuple of (repo_agents, knowledge_agents, task_agents) dictionaries
+        Tuple of (repo_agents, knowledge_agents) dictionaries
     """
     if isinstance(microagent_dir, str):
         microagent_dir = Path(microagent_dir)
@@ -202,6 +273,7 @@ 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

@@ -12,6 +12,14 @@ 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):
@@ -19,9 +27,12 @@ class MicroagentMetadata(BaseModel):
 
     name: str = 'default'
     type: MicroagentType = Field(default=MicroagentType.REPO_KNOWLEDGE)
-    version: str = Field(default='1.0.0')
-    agent: str = Field(default='CodeActAgent')
+    # Keep these fields for backward compatibility but they're not used
+    version: str = Field(default='1.0.0', exclude=True)
+    agent: str = Field(default='CodeActAgent', exclude=True)
+    author: str = Field(default='', exclude=True)
     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/server/routes/mcp.py

@@ -49,7 +49,7 @@ async def get_convo_link(service: GitService, conversation_id: str, body: str) -
 
 
 async def save_pr_metadata(
-    user_id: str, conversation_id: str, tool_result: str
+    user_id: str | None, conversation_id: str, tool_result: str
 ) -> None:
     conversation_store = await ConversationStoreImpl.get_instance(config, user_id)
     conversation: ConversationMetadata = await conversation_store.get_metadata(
@@ -70,7 +70,11 @@ 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)
 
 
@@ -124,7 +128,7 @@ async def create_pr(
             body=body,
         )
 
-        if conversation_id and user_id:
+        if conversation_id:
             await save_pr_metadata(user_id, conversation_id, response)
 
     except Exception as e:

tests/runtime/test_microagent.py

@@ -1,6 +1,7 @@
 """Tests for microagent loading in runtime."""
 
 import os
+import tempfile
 from pathlib import Path
 from unittest.mock import AsyncMock, MagicMock, patch
 
@@ -13,7 +14,13 @@ 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 import KnowledgeMicroagent, RepoMicroagent
+from openhands.microagent.microagent import (
+    BaseMicroagent,
+    KnowledgeMicroagent,
+    RepoMicroagent,
+    TaskMicroagent,
+)
+from openhands.microagent.types import MicroagentType
 
 
 def _create_test_microagents(test_dir: str):
@@ -173,6 +180,176 @@ 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
@@ -196,9 +373,9 @@ def test_default_tools_microagent_exists():
     assert 'type: repo' in content, 'default-tools.md should be a repo microagent'
 
     # Verify it has the fetch tool configured
-    assert 'name: "fetch"' in content, 'default-tools.md should have a fetch tool'
-    assert 'command: "uvx"' in content, 'default-tools.md should use uvx command'
-    assert 'args: ["mcp-server-fetch"]' in content, (
+    assert 'name: "fetch"' in content or 'name: fetch' in content, 'default-tools.md should have a fetch tool'
+    assert 'command: uvx' in content, 'default-tools.md should use uvx command'
+    assert 'mcp-server-fetch' in content, (
         'default-tools.md should use mcp-server-fetch'
     )
 

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: task
+type: invalid_type
 version: 1.0.0
 agent: CodeActAgent
 triggers:
@@ -196,7 +196,8 @@ 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: "task"' in error_msg
+    assert 'Invalid "type" value: "invalid_type"' 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