Resolve merge conflict in agent_session.py

Co-authored-by: openhands <openhands@all-hands.dev>

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

@@ -36,6 +36,8 @@ jobs:
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
+      - name: Install tmux
+        run: sudo apt-get update && sudo apt-get install -y tmux
       - name: Install poetry via pipx
         run: pipx install poetry
       - name: Set up Python

.github/workflows/eval-runner.yml

@@ -29,6 +29,8 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v4
 
+      - name: Install tmux
+        run: sudo apt-get update && sudo apt-get install -y tmux
       - name: Install poetry via pipx
         run: pipx install poetry
 

.github/workflows/ghcr-build.yml

@@ -56,7 +56,7 @@ jobs:
           docker-images: false
           swap-storage: true
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3.0.0
+        uses: docker/setup-qemu-action@v3.2.0
         with:
           image: tonistiigi/binfmt:latest
       - name: Login to GHCR
@@ -119,7 +119,7 @@ jobs:
           docker-images: false
           swap-storage: true
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3.0.0
+        uses: docker/setup-qemu-action@v3.2.0
         with:
           image: tonistiigi/binfmt:latest
       - name: Login to GHCR

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

@@ -31,6 +31,8 @@ jobs:
           key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
           restore-keys: |
             ${{ runner.os }}-poetry-
+      - name: Install tmux
+        run: brew install tmux
       - name: Install poetry via pipx
         run: pipx install poetry
       - name: Install Python dependencies using Poetry

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

@@ -30,6 +30,8 @@ jobs:
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
+      - name: Install tmux
+        run: sudo apt-get update && sudo apt-get install -y tmux
       - name: Install poetry via pipx
         run: pipx install poetry
       - name: Set up Python

.openhands/microagents/repo.md

@@ -1,6 +1,7 @@
 ---
 name: repo
-agent: CodeAct
+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).

CODE_OF_CONDUCT.md

@@ -18,24 +18,24 @@ diverse, inclusive, and healthy community.
 Examples of behavior that contributes to a positive environment for our
 community include:
 
-* Demonstrating empathy and kindness toward other people
-* Being respectful of differing opinions, viewpoints, and experiences
-* Giving and gracefully accepting constructive feedback
+* Demonstrating empathy and kindness toward other people.
+* Being respectful of differing opinions, viewpoints, and experiences.
+* Giving and gracefully accepting constructive feedback.
 * Accepting responsibility and apologizing to those affected by our mistakes,
-  and learning from the experience
+  and learning from the experience.
 * Focusing on what is best not just for us as individuals, but for the overall
-  community
+  community.
 
 Examples of unacceptable behavior include:
 
 * The use of sexualized language or imagery, and sexual attention or advances of
-  any kind
-* Trolling, insulting or derogatory comments, and personal or political attacks
-* Public or private harassment
+  any kind.
+* Trolling, insulting or derogatory comments, and personal or political attacks.
+* Public or private harassment.
 * Publishing others' private information, such as a physical or email address,
-  without their explicit permission
+  without their explicit permission.
 * Other conduct which could reasonably be considered inappropriate in a
-  professional setting
+  professional setting.
 
 ## Enforcement Responsibilities
 
@@ -61,7 +61,7 @@ representative at an online or offline event.
 
 Instances of abusive, harassing, or otherwise unacceptable behavior may be
 reported to the community leaders responsible for enforcement at
-contact@all-hands.dev
+contact@all-hands.dev.
 All complaints will be reviewed and investigated promptly and fairly.
 
 All community leaders are obligated to respect the privacy and security of the

CONTRIBUTING.md

@@ -11,11 +11,11 @@ To understand the codebase, please refer to the README in each module:
    - [agenthub](./openhands/agenthub/README.md)
    - [server](./openhands/server/README.md)
 
-## Setting up your development environment
+## Setting up Your Development Environment
 
 We have a separate doc [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) that tells you how to set up a development workflow.
 
-## How can I contribute?
+## How Can I Contribute?
 
 There are many ways that you can contribute:
 
@@ -23,7 +23,7 @@ There are many ways that you can contribute:
 2. **Send feedback** after each session by [clicking the thumbs-up thumbs-down buttons](https://docs.all-hands.dev/modules/usage/feedback), so we can see where things are working and failing, and also build an open dataset for training code agents.
 3. **Improve the Codebase** by sending [PRs](#sending-pull-requests-to-openhands) (see details below). In particular, we have some [good first issues](https://github.com/All-Hands-AI/OpenHands/labels/good%20first%20issue) that may be ones to start on.
 
-## What can I build?
+## What Can I Build?
 Here are a few ways you can help improve the codebase.
 
 #### UI/UX
@@ -35,7 +35,7 @@ of the application, please open an issue first, or better, join the #frontend ch
 to gather consensus from our design team first.
 
 #### Improving the agent
-Our main agent is the CodeAct agent. You can [see its prompts here](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/agenthub/codeact_agent)
+Our main agent is the CodeAct agent. You can [see its prompts here](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/agenthub/codeact_agent).
 
 Changes to these prompts, and to the underlying behavior in Python, can have a huge impact on user experience.
 You can try modifying the prompts to see how they change the behavior of the agent as you use the app
@@ -63,7 +63,7 @@ At the moment, we have two kinds of tests: [`unit`](./tests/unit) and [`integrat
 ## Sending Pull Requests to OpenHands
 
 You'll need to fork our repository to send us a Pull Request. You can learn more
-about how to fork a GitHub repo and open a PR with your changes in [this article](https://medium.com/swlh/forks-and-pull-requests-how-to-contribute-to-github-repos-8843fac34ce8)
+about how to fork a GitHub repo and open a PR with your changes in [this article](https://medium.com/swlh/forks-and-pull-requests-how-to-contribute-to-github-repos-8843fac34ce8).
 
 ### Pull Request title
 As described [here](https://github.com/commitizen/conventional-commit-types/blob/master/index.json), a valid PR title should begin with one of the following prefixes:
@@ -103,7 +103,7 @@ Further, if you see an issue you like, please leave a "thumbs-up" or a comment,
 
 ### Making Pull Requests
 
-We're generally happy to consider all [PRs](https://github.com/All-Hands-AI/OpenHands/pulls), with the evaluation process varying based on the type of change:
+We're generally happy to consider all pull requests with the evaluation process varying based on the type of change:
 
 #### For Small Improvements
 

Development.md

@@ -3,7 +3,7 @@ This guide is for people working on OpenHands and editing the source code.
 If you wish to contribute your changes, check out the [CONTRIBUTING.md](https://github.com/All-Hands-AI/OpenHands/blob/main/CONTRIBUTING.md) on how to clone and setup the project initially before moving on.
 Otherwise, you can clone the OpenHands project directly.
 
-## Start the server for development
+## Start the Server for Development
 ### 1. Requirements
 * Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)  [Ubuntu <= 22.04]
 * [Docker](https://docs.docker.com/engine/install/) (For those on MacOS, make sure to allow the default Docker socket to be used from advanced settings!)
@@ -58,7 +58,7 @@ See [our documentation](https://docs.all-hands.dev/modules/usage/llms) for recom
 
 ### 4. Running the application
 #### Option A: Run the Full Application
-Once the setup is complete, launching OpenHands is as simple as running a single command. This command starts both the backend and frontend servers seamlessly, allowing you to interact with OpenHands:
+Once the setup is complete, this command starts both the backend and frontend servers, allowing you to interact with OpenHands:
 ```bash
 make run
 ```
@@ -75,11 +75,11 @@ make run
     ```
 
 ### 6. LLM Debugging
-If you encounter any issues with the Language Model (LM) or you're simply curious, you can inspect the actual LLM prompts and responses. To do so, export DEBUG=1 in the environment and restart the backend.
-OpenHands will then log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
+If you encounter any issues with the Language Model (LM) or you're simply curious, export DEBUG=1 in the environment and restart the backend.
+OpenHands will log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
 
 ### 7. Help
-Need assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenHands.
+Need help or info on available targets and commands? Use the help command for all the guidance you need with OpenHands.
 ```bash
 make help
  ```
@@ -93,14 +93,14 @@ poetry run pytest ./tests/unit/test_*.py
 ```
 
 ### 9. Add or update dependency
-1. Add your dependency in `pyproject.toml` or use `poetry add xxx`
-2. Update the poetry.lock file via `poetry lock --no-update`
+1. Add your dependency in `pyproject.toml` or use `poetry add xxx`.
+2. Update the poetry.lock file via `poetry lock --no-update`.
 
 ### 9. Use existing Docker image
 To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker container image by
 setting the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
 
-Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.17-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.19-nikolaik`
 
 ## Develop inside Docker container
 
@@ -110,7 +110,7 @@ TL;DR
 make docker-dev
 ```
 
-See more details [here](./containers/dev/README.md)
+See more details [here](./containers/dev/README.md).
 
 If you are just interested in running `OpenHands` without installing all the required tools on your host.
 

ISSUE_TRIAGE.md

@@ -2,8 +2,8 @@
 These are the procedures and guidelines on how issues are triaged in this repo by the maintainers.
 
 ## General
-* Most issues must be tagged with **enhancement** or **bug**
-* Issues may be tagged with what it relates to (**backend**, **frontend**, **agent quality**, etc.)
+* Most issues must be tagged with **enhancement** or **bug**.
+* Issues may be tagged with what it relates to (**backend**, **frontend**, **agent quality**, etc.).
 
 ## Severity
 * **Low**: Minor issues or affecting single user.
@@ -11,10 +11,10 @@ These are the procedures and guidelines on how issues are triaged in this repo b
 * **Critical**: Affecting all users or potential security issues.
 
 ## Effort
-* Issues may be estimated with effort required (**small effort**, **medium effort**, **large effort**)
+* Issues may be estimated with effort required (**small effort**, **medium effort**, **large effort**).
 
 ## Difficulty
-* Issues with low implementation difficulty may be tagged with **good first issue**
+* Issues with low implementation difficulty may be tagged with **good first issue**.
 
 ## Not Enough Information
 * User is asked to provide more information (logs, how to reproduce, etc.) when the issue is not clear.

Makefile

@@ -106,7 +106,7 @@ check-poetry:
 	@if command -v poetry > /dev/null; then \
 		POETRY_VERSION=$(shell poetry --version 2>&1 | sed -E 's/Poetry \(version ([0-9]+\.[0-9]+\.[0-9]+)\)/\1/'); \
 		IFS='.' read -r -a POETRY_VERSION_ARRAY <<< "$$POETRY_VERSION"; \
-		if [ $${POETRY_VERSION_ARRAY[0]} -ge 1 ] && [ $${POETRY_VERSION_ARRAY[1]} -ge 8 ]; then \
+		if [ $${POETRY_VERSION_ARRAY[0]} -gt 1 ] || ([ $${POETRY_VERSION_ARRAY[0]} -eq 1 ] && [ $${POETRY_VERSION_ARRAY[1]} -ge 8 ]); then \
 			echo "$(BLUE)$(shell poetry --version) is already installed.$(RESET)"; \
 		else \
 			echo "$(RED)Poetry 1.8 or later is required. You can install poetry by running the following command, then adding Poetry to your PATH:"; \
@@ -190,7 +190,7 @@ build-frontend:
 # Start backend
 start-backend:
 	@echo "$(YELLOW)Starting backend...$(RESET)"
-	@poetry run uvicorn openhands.server.listen:app --host $(BACKEND_HOST) --port $(BACKEND_PORT) --reload --reload-exclude "$(shell pwd)/workspace"
+	@poetry run uvicorn openhands.server.listen:app --host $(BACKEND_HOST) --port $(BACKEND_PORT) --reload --reload-exclude "./workspace"
 
 # Start frontend
 start-frontend:

README.md

@@ -43,17 +43,17 @@ See the [Installation](https://docs.all-hands.dev/modules/usage/installation) gu
 system requirements and more information.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.17
+    docker.all-hands.dev/all-hands-ai/openhands:0.19
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
@@ -64,16 +64,16 @@ works best, but you have [many options](https://docs.all-hands.dev/modules/usage
 
 ---
 
-You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes),
+You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes#connecting-to-your-filesystem),
 run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
 interact with it via a [friendly CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode),
-or run it on tagged issues with [a github action](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/resolver/README.md).
+or run it on tagged issues with [a github action](https://docs.all-hands.dev/modules/usage/how-to/github-action).
 
 Visit [Installation](https://docs.all-hands.dev/modules/usage/installation) for more information and setup instructions.
 
 > [!CAUTION]
 > OpenHands is meant to be run by a single user on their local workstation.
-> It is not appropriate for multi-tenant deployments, where multiple users share the same instance--there is no built-in isolation or scalability.
+> It is not appropriate for multi-tenant deployments where multiple users share the same instance. There is no built-in isolation or scalability.
 >
 > If you're interested in running OpenHands in a multi-tenant environment, please
 > [get in touch with us](https://docs.google.com/forms/d/e/1FAIpQLSet3VbGaz8z32gW9Wm-Grl4jpt5WgMXPgJ4EDPVmCETCBpJtQ/viewform)
@@ -86,7 +86,7 @@ Having issues? The [Troubleshooting Guide](https://docs.all-hands.dev/modules/us
 ## 📖 Documentation
 
 To learn more about the project, and for tips on using OpenHands,
-**check out our [documentation](https://docs.all-hands.dev/modules/usage/getting-started)**.
+check out our [documentation](https://docs.all-hands.dev/modules/usage/getting-started).
 
 There you'll find resources on how to use different LLM providers,
 troubleshooting resources, and advanced configuration options.

compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.17-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.19-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

config.template.toml

@@ -180,6 +180,12 @@ model = "gpt-4o"
 # https://docs.litellm.ai/docs/completion/token_usage
 #custom_tokenizer = ""
 
+# Whether to use native tool calling if supported by the model. Can be true, false, or None by default, which chooses the model's default behavior based on the evaluation.
+# ATTENTION: Based on evaluation, enabling native function calling may lead to worse results
+# in some scenarios. Use with caution and consider testing with your specific use case.
+# https://github.com/All-Hands-AI/OpenHands/pull/4711
+#native_tool_calling = None
+
 [llm.gpt4o-mini]
 api_key = "your-api-key"
 model = "gpt-4o"
@@ -192,6 +198,16 @@ model = "gpt-4o"
 # agent.CodeActAgent
 ##############################################################################
 [agent]
+
+# whether the browsing tool is enabled
+codeact_enable_browsing = true
+
+# whether the LLM draft editor is enabled
+codeact_enable_llm_editor = false
+
+# whether the IPython tool is enabled
+codeact_enable_jupyter = true
+
 # Name of the micro agent to use for this agent
 #micro_agent_name = ""
 
@@ -204,6 +220,12 @@ model = "gpt-4o"
 # LLM config group to use
 #llm_config = 'your-llm-config-group'
 
+# Whether to use microagents at all
+#use_microagents = true
+
+# List of microagents to disable
+#disabled_microagents = []
+
 [agent.RepoExplorerAgent]
 # Example: use a cheaper model for RepoExplorerAgent to reduce cost, especially
 # useful when an agent doesn't demand high quality but uses a lot of tokens

containers/app/Dockerfile

@@ -71,6 +71,7 @@ ENV VIRTUAL_ENV=/app/.venv \
 COPY --chown=openhands:app --chmod=770 --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
 RUN playwright install --with-deps chromium
 
+COPY --chown=openhands:app --chmod=770 ./microagents ./microagents
 COPY --chown=openhands:app --chmod=770 ./openhands ./openhands
 COPY --chown=openhands:app --chmod=777 ./openhands/runtime/plugins ./openhands/runtime/plugins
 COPY --chown=openhands:app --chmod=770 ./openhands/agenthub ./openhands/agenthub

containers/dev/compose.yml

@@ -11,7 +11,7 @@ services:
       - BACKEND_HOST=${BACKEND_HOST:-"0.0.0.0"}
       - SANDBOX_API_HOSTNAME=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.17-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.19-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docs/DOC_STYLE_GUIDE.md

@@ -0,0 +1,48 @@
+# Documentation Style Guide
+
+## General Writing Principles
+
+- **Clarity & Conciseness**: Always prioritize clarity and brevity. Avoid unnecessary jargon or overly complex explanations.
+Keep sentences short and to the point.
+- **Gradual Complexity**: Start with the simplest, most basic setup, and then gradually introduce more advanced
+concepts and configurations.
+
+## Formatting Guidelines
+
+### Headers
+
+Use **Title Case** for the first and second level headers.
+
+Example:
+  - **Basic Usage**
+  - **Advanced Configuration Options**
+
+### Lists
+
+When listing items or options, use bullet points to enhance readability.
+
+Example:
+  - Option A
+  - Option B
+  - Option C
+
+### Procedures
+
+For instructions or processes that need to be followed in a specific order, use numbered steps.
+
+Example:
+  1. Step one: Do this.
+  2. Step two: Complete this action.
+  3. Step three: Verify the result.
+
+### Code Blocks
+
+* Use code blocks for multi-line inputs, outputs, commands and code samples.
+
+Example:
+```bash
+docker run -it \
+    -e THIS=this \
+    -e THAT=that
+    ...
+```

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -52,7 +52,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -61,7 +61,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.17 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.19 \
     python -m openhands.core.cli
 ```
 

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -46,7 +46,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -56,6 +56,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.17 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.19 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/installation.mdx

@@ -13,16 +13,16 @@
 La façon la plus simple d'exécuter OpenHands est avec Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.17
+    docker.all-hands.dev/all-hands-ai/openhands:0.19
 ```
 
 Vous pouvez également exécuter OpenHands en mode [headless scriptable](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), en tant que [CLI interactive](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), ou en utilisant l'[Action GitHub OpenHands](https://docs.all-hands.dev/modules/usage/how-to/github-action).

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

@@ -13,7 +13,7 @@ C'est le Runtime par défaut qui est utilisé lorsque vous démarrez OpenHands.
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -50,7 +50,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -59,7 +59,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.17 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.19 \
     python -m openhands.core.cli
 ```
 

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -47,7 +47,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -57,6 +57,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.17 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.19 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/installation.mdx

@@ -11,16 +11,16 @@
 在 Docker 中运行 OpenHands 是最简单的方式。
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.17
+    docker.all-hands.dev/all-hands-ai/openhands:0.19
 ```
 
 你也可以在可脚本化的[无头模式](https://docs.all-hands.dev/modules/usage/how-to/headless-mode)下运行 OpenHands，作为[交互式 CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode)，或使用 [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action)。

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/runtimes.md

@@ -11,7 +11,7 @@
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/modules/usage/about.md

@@ -4,10 +4,9 @@
 
 Achieving full replication of production-grade applications with LLMs is a complex endeavor. Our strategy involves:
 
-1. **Core Technical Research:** Focusing on foundational research to understand and improve the technical aspects of code generation and handling
-2. **Specialist Abilities:** Enhancing the effectiveness of core components through data curation, training methods, and more
-3. **Task Planning:** Developing capabilities for bug detection, codebase management, and optimization
-4. **Evaluation:** Establishing comprehensive evaluation metrics to better understand and improve our models
+- **Core Technical Research:** Focusing on foundational research to understand and improve the technical aspects of code generation and handling.
+- **Task Planning:** Developing capabilities for bug detection, codebase management, and optimization.
+- **Evaluation:** Establishing comprehensive evaluation metrics to better understand and improve our agents.
 
 ## Default Agent
 
@@ -15,11 +14,14 @@ Our default Agent is currently the [CodeActAgent](agents), which is capable of g
 
 ## Built With
 
-OpenHands is built using a combination of powerful frameworks and libraries, providing a robust foundation for its development. Here are the key technologies used in the project:
+OpenHands is built using a combination of powerful frameworks and libraries, providing a robust foundation for its
+development. Here are the key technologies used in the project:
 
 ![FastAPI](https://img.shields.io/badge/FastAPI-black?style=for-the-badge) ![uvicorn](https://img.shields.io/badge/uvicorn-black?style=for-the-badge) ![LiteLLM](https://img.shields.io/badge/LiteLLM-black?style=for-the-badge) ![Docker](https://img.shields.io/badge/Docker-black?style=for-the-badge) ![Ruff](https://img.shields.io/badge/Ruff-black?style=for-the-badge) ![MyPy](https://img.shields.io/badge/MyPy-black?style=for-the-badge) ![LlamaIndex](https://img.shields.io/badge/LlamaIndex-black?style=for-the-badge) ![React](https://img.shields.io/badge/React-black?style=for-the-badge)
 
-Please note that the selection of these technologies is in progress, and additional technologies may be added or existing ones may be removed as the project evolves. We strive to adopt the most suitable and efficient tools to enhance the capabilities of OpenHands.
+Please note that the selection of these technologies is in progress, and additional technologies may be added or
+existing ones may be removed as the project evolves. We strive to adopt the most suitable and efficient tools to
+enhance the capabilities of OpenHands.
 
 ## License
 

docs/modules/usage/configuration-options.md

@@ -11,7 +11,7 @@ take precedence.
 
 # Table of Contents
 
-1. [Core Configuration](#core-configuration)
+- [Core Configuration](#core-configuration)
    - [API Keys](#api-keys)
    - [Workspace](#workspace)
    - [Debugging and Logging](#debugging-and-logging)
@@ -21,7 +21,7 @@ take precedence.
    - [Task Management](#task-management)
    - [Sandbox Configuration](#sandbox-configuration)
    - [Miscellaneous](#miscellaneous)
-2. [LLM Configuration](#llm-configuration)
+- [LLM Configuration](#llm-configuration)
    - [AWS Credentials](#aws-credentials)
    - [API Configuration](#api-configuration)
    - [Custom LLM Provider](#custom-llm-provider)
@@ -30,20 +30,20 @@ take precedence.
    - [Model Selection](#model-selection)
    - [Retrying](#retrying)
    - [Advanced Options](#advanced-options)
-3. [Agent Configuration](#agent-configuration)
+- [Agent Configuration](#agent-configuration)
    - [Microagent Configuration](#microagent-configuration)
    - [Memory Configuration](#memory-configuration)
    - [LLM Configuration](#llm-configuration-2)
    - [ActionSpace Configuration](#actionspace-configuration)
    - [Microagent Usage](#microagent-usage)
-4. [Sandbox Configuration](#sandbox-configuration-2)
+- [Sandbox Configuration](#sandbox-configuration)
    - [Execution](#execution)
    - [Container Image](#container-image)
    - [Networking](#networking)
    - [Linting and Plugins](#linting-and-plugins)
    - [Dependencies and Environment](#dependencies-and-environment)
    - [Evaluation](#evaluation)
-5. [Security Configuration](#security-configuration)
+- [Security Configuration](#security-configuration)
    - [Confirmation Mode](#confirmation-mode)
    - [Security Analyzer](#security-analyzer)
 

docs/modules/usage/feedback.md

@@ -1,10 +1,14 @@
 # ✅ Providing Feedback
 
-When using OpenHands, you will encounter cases where things work well, and others where they don't. We encourage you to provide feedback when you use OpenHands to help give feedback to the development team, and perhaps more importantly, create an open corpus of coding agent training examples -- Share-OpenHands!
+When using OpenHands, you will encounter cases where things work well, and others where they don't. We encourage you to
+provide feedback when you use OpenHands to help give feedback to the development team, and perhaps more importantly,
+create an open corpus of coding agent training examples -- Share-OpenHands!
 
 ## 📝 How to Provide Feedback
 
-Providing feedback is easy! When you are using OpenHands, you can press the thumbs-up or thumbs-down button at any point during your interaction. You will be prompted to provide your email address (e.g. so we can contact you if we want to ask any follow-up questions), and you can choose whether you want to provide feedback publicly or privately.
+Providing feedback is easy! When you are using OpenHands, you can press the thumbs-up or thumbs-down button at any point
+during your interaction. You will be prompted to provide your email address
+(e.g. so we can contact you if we want to ask any follow-up questions), and you can choose whether you want to provide feedback publicly or privately.
 
 <iframe width="560" height="315" src="https://www.youtube.com/embed/5rFx-StMVV0?si=svo7xzp6LhGK_GXr" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
 
@@ -14,8 +18,11 @@ Providing feedback is easy! When you are using OpenHands, you can press the thum
 
 When you submit data, you can submit it either publicly or privately.
 
-* **Public** data will be distributed under the MIT License, like OpenHands itself, and can be used by the community to train and test models. Obviously, feedback that you can make public will be more valuable for the community as a whole, so when you are not dealing with sensitive information, we would encourage you to choose this option!
-* **Private** data will only be shared with the OpenHands team for the purpose of improving OpenHands.
+- **Public** data will be distributed under the MIT License, like OpenHands itself, and can be used by the community to
+train and test models. Obviously, feedback that you can make public will be more valuable for the community as a whole,
+so when you are not dealing with sensitive information, we would encourage you to choose this option!
+- **Private** data will be made available to the OpenHands team for the purpose of improving OpenHands.
+However, a link with a unique ID will still be created that you can share publicly with others.
 
 ### Who collects and stores the data?
 
@@ -27,13 +34,17 @@ The public data will be released when we hit fixed milestones, such as 1,000 pub
 At this time, we will follow the following release process:
 
 1. All people who contributed public feedback will receive an email describing the data release and being given an opportunity to opt out.
-2. The person or people in charge of the data release will perform quality control of the data, removing low-quality feedback, removing email submitter email addresses, and attempting to remove any sensitive information.
+2. The person or people in charge of the data release will perform quality control of the data, removing low-quality feedback,
+removing email submitter email addresses, and attempting to remove any sensitive information.
 3. The data will be released publicly under the MIT license through commonly used sites such as github or Hugging Face.
 
 ### What if I want my data deleted?
 
 For data on the All Hands AI servers, we are happy to delete it at request:
 
-**One Piece of Data:** If you want one piece of data deleted, we will shortly be adding a mechanism to delete pieces of data using the link and password that is displayed on the interface when you submit data.
+**One Piece of Data:** If you want one piece of data deleted, we will shortly be adding a mechanism to delete pieces of
+data using the link and password that is displayed on the interface when you submit data.
 
-**All Data:** If you would like all pieces of your data deleted, or you do not have the ID and password that you received when submitting the data, please contact `contact@all-hands.dev` from the email address that you registered when you originally submitted the data.
+**All Data:** If you would like all pieces of your data deleted, or you do not have the ID and password that you
+received when submitting the data, please contact `contact@all-hands.dev` from the email address that you registered
+when you originally submitted the data.

docs/modules/usage/getting-started.mdx

@@ -44,7 +44,7 @@ For example, we might build a TODO app:
 
 We can keep iterating on the app once the skeleton is there:
 
-> Please allow adding an optional due date to every task
+> Please allow adding an optional due date to every task.
 
 Just like with normal development, it's good to commit and push your code frequently.
 This way you can always revert back to an old state if the agent goes off track.
@@ -59,15 +59,15 @@ OpenHands can also do a great job adding new code to an existing code base.
 
 For example, you can ask OpenHands to add a new GitHub action to your project
 which lints your code. OpenHands may take a peek at your codebase to see what language
-it should use, but then it can just drop a new file into `./github/workflows/lint.yml`
+it should use and then drop a new file into `./github/workflows/lint.yml`.
 
-> Please add a GitHub action that lints the code in this repository
+> Please add a GitHub action that lints the code in this repository.
 
 Some tasks might require a bit more context. While OpenHands can use `ls` and `grep`
 to search through your codebase, providing context up front allows it to move faster,
 and more accurately. And it'll cost you fewer tokens!
 
-> Please modify ./backend/api/routes.js to add a new route that returns a list of all tasks
+> Please modify ./backend/api/routes.js to add a new route that returns a list of all tasks.
 
 > Please add a new React component that displays a list of Widgets to the ./frontend/components
 > directory. It should use the existing Widget component.
@@ -78,15 +78,15 @@ OpenHands does great at refactoring existing code, especially in small chunks.
 You probably don't want to try rearchitecting your whole codebase, but breaking up
 long files and functions, renaming variables, etc. tend to work very well.
 
-> Please rename all the single-letter variables in ./app.go
+> Please rename all the single-letter variables in ./app.go.
 
-> Please break the function `build_and_deploy_widgets` into two functions, `build_widgets` and `deploy_widgets` in widget.php
+> Please break the function `build_and_deploy_widgets` into two functions, `build_widgets` and `deploy_widgets` in widget.php.
 
-> Please break ./api/routes.js into separate files for each route
+> Please break ./api/routes.js into separate files for each route.
 
 ## Bug Fixes
 
-OpenHands can also help you track down and fix bugs in your code. But, as any
+OpenHands can also help you track down and fix bugs in your code. But as any
 developer knows, bug fixing can be extremely tricky, and often OpenHands will need more context.
 It helps if you've diagnosed the bug, but want OpenHands to figure out the logic.
 
@@ -94,18 +94,18 @@ It helps if you've diagnosed the bug, but want OpenHands to figure out the logic
 
 > The `search_widgets` function in ./app.py is doing a case-sensitive search. Please make it case-insensitive.
 
-It often helps to do test-driven development when bugfixing with an agent.
+It often helps to do test-driven development when bug fixing with an agent.
 You can ask the agent to write a new test, and then iterate until it fixes the bug:
 
 > The `hello` function crashes on the empty string. Please write a test that reproduces this bug, then fix the code so it passes.
 
 ## More
 
-OpenHands is capable of helping out on just about any coding task. But it takes some practice
+OpenHands is capable of helping out on just about any coding task but it takes some practice
 to get the most out of it. Remember to:
-* Keep your tasks small
-* Be as specific as possible
-* Provide as much context as possible
-* Commit and push frequently
+* Keep your tasks small.
+* Be as specific as possible.
+* Provide as much context as possible.
+* Commit and push frequently.
 
 See [Prompting Best Practices](./prompting/prompting-best-practices) for more tips on how to get the most out of OpenHands.

docs/modules/usage/how-to/cli-mode.md

@@ -6,10 +6,9 @@ This mode is different from the [headless mode](headless-mode), which is non-int
 
 ## With Python
 
-To start an interactive OpenHands session via the command line, follow these steps:
+To start an interactive OpenHands session via the command line:
 
 1. Ensure you have followed the [Development setup instructions](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
-
 2. Run the following command:
 
 ```bash
@@ -21,45 +20,32 @@ This command will start an interactive session where you can input tasks and rec
 You'll need to be sure to set your model, API key, and other settings via environment variables
 [or the `config.toml` file](https://github.com/All-Hands-AI/OpenHands/blob/main/config.template.toml).
 
-
 ## With Docker
 
-To run OpenHands in CLI mode with Docker, follow these steps:
+To run OpenHands in CLI mode with Docker:
 
-1. Set `WORKSPACE_BASE` to the directory you want OpenHands to edit:
+1. Set the following environmental variables in your terminal:
 
-```bash
-WORKSPACE_BASE=$(pwd)/workspace
-```
+- `WORKSPACE_BASE` to the directory you want OpenHands to edit (Ex: `export WORKSPACE_BASE=$(pwd)/workspace`).
+- `LLM_MODEL` to the model to use (Ex: `export LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"`).
+- `LLM_API_KEY` to the API key (Ex: `export LLM_API_KEY="sk_test_12345"`).
 
-2. Set `LLM_MODEL` to the model you want to use:
-
-```bash
-LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"
-
-```
-
-3. Set `LLM_API_KEY` to your API key:
-
-```bash
-LLM_API_KEY="sk_test_12345"
-```
-
-4. Run the following Docker command:
+2. Run the following Docker command:
 
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
     -e LLM_MODEL=$LLM_MODEL \
     -v $WORKSPACE_BASE:/opt/workspace_base \
     -v /var/run/docker.sock:/var/run/docker.sock \
+    -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.17 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.19 \
     python -m openhands.core.cli
 ```
 

docs/modules/usage/how-to/custom-sandbox-guide.md

@@ -9,8 +9,8 @@ as python and Node.js but may need other software installed by default.
 
 You have two options for customization:
 
-1. Use an existing image with the required software.
-2. Create your own custom Docker image.
+- Use an existing image with the required software.
+- Create your own custom Docker image.
 
 If you choose the first option, you can skip the `Create Your Docker Image` section.
 
@@ -58,7 +58,3 @@ sandbox_base_container_image="custom-image"
 ### Run
 
 Run OpenHands by running ```make run``` in the top level directory.
-
-## Technical Explanation
-
-Please refer to [custom docker image section of the runtime documentation](https://docs.all-hands.dev/modules/usage/architecture/runtime#advanced-how-openhands-builds-and-maintains-od-runtime-images) for more details.

docs/modules/usage/how-to/github-action.md

@@ -21,10 +21,10 @@ the [README for the OpenHands Resolver](https://github.com/All-Hands-AI/OpenHand
 ### Iterative resolution
 
 1. Create an issue in the repository.
-2. Add the `fix-me` label to the issue, or leave a comment starting with `@openhands-agent`
-3. Review the attempt to resolve the issue by checking the pull request
-4. Follow up with feedback through general comments, review comments, or inline thread comments
-5. Add the `fix-me` label to the pull request, or address a specific comment by starting with `@openhands-agent`
+2. Add the `fix-me` label to the issue, or leave a comment starting with `@openhands-agent`.
+3. Review the attempt to resolve the issue by checking the pull request.
+4. Follow up with feedback through general comments, review comments, or inline thread comments.
+5. Add the `fix-me` label to the pull request, or address a specific comment by starting with `@openhands-agent`.
 
 ### Label versus Macro
 

docs/modules/usage/how-to/gui-mode.md

@@ -2,12 +2,12 @@
 
 ## Introduction
 
-OpenHands provides a user-friendly Graphical User Interface (GUI) mode for interacting with the AI assistant. This mode offers an intuitive way to set up the environment, manage settings, and communicate with the AI.
+OpenHands provides a user-friendly Graphical User Interface (GUI) mode for interacting with the AI assistant.
+This mode offers an intuitive way to set up the environment, manage settings, and communicate with the AI.
 
 ## Installation and Setup
 
 1. Follow the instructions in the [Installation](../installation) guide to install OpenHands.
-
 2. After running the command, access OpenHands at [http://localhost:3000](http://localhost:3000).
 
 ## Interacting with the GUI
@@ -23,39 +23,39 @@ OpenHands provides a user-friendly Graphical User Interface (GUI) mode for inter
 
 OpenHands automatically exports a `GITHUB_TOKEN` to the shell environment if it is available. This can happen in two ways:
 
-1. **Locally (OSS)**: The user directly inputs their GitHub token
-2. **Online (SaaS)**: The token is obtained through GitHub OAuth authentication
+- **Locally (OSS)**: The user directly inputs their GitHub token.
+- **Online (SaaS)**: The token is obtained through GitHub OAuth authentication.
 
 #### Setting Up a Local GitHub Token
 
 1. **Generate a Personal Access Token (PAT)**:
-   - Go to GitHub Settings > Developer Settings > Personal Access Tokens > Tokens (classic)
-   - Click "Generate new token (classic)"
+   - Go to GitHub Settings > Developer Settings > Personal Access Tokens > Tokens (classic).
+   - Click "Generate new token (classic)".
    - Required scopes:
      - `repo` (Full control of private repositories)
      - `workflow` (Update GitHub Action workflows)
      - `read:org` (Read organization data)
 
 2. **Enter Token in OpenHands**:
-   - Click the Settings button (gear icon) in the top right
-   - Navigate to the "GitHub" section
-   - Paste your token in the "GitHub Token" field
-   - Click "Save" to apply the changes
+   - Click the Settings button (gear icon) in the top right.
+   - Navigate to the "GitHub" section.
+   - Paste your token in the "GitHub Token" field.
+   - Click "Save" to apply the changes.
 
 #### Organizational Token Policies
 
 If you're working with organizational repositories, additional setup may be required:
 
 1. **Check Organization Requirements**:
-   - Organization admins may enforce specific token policies
-   - Some organizations require tokens to be created with SSO enabled
-   - Review your organization's [token policy settings](https://docs.github.com/en/organizations/managing-programmatic-access-to-your-organization/setting-a-personal-access-token-policy-for-your-organization)
+   - Organization admins may enforce specific token policies.
+   - Some organizations require tokens to be created with SSO enabled.
+   - Review your organization's [token policy settings](https://docs.github.com/en/organizations/managing-programmatic-access-to-your-organization/setting-a-personal-access-token-policy-for-your-organization).
 
 2. **Verify Organization Access**:
-   - Go to your token settings on GitHub
-   - Look for the organization under "Organization access"
-   - If required, click "Enable SSO" next to your organization
-   - Complete the SSO authorization process
+   - Go to your token settings on GitHub.
+   - Look for the organization under "Organization access".
+   - If required, click "Enable SSO" next to your organization.
+   - Complete the SSO authorization process.
 
 #### OAuth Authentication (Online Mode)
 
@@ -67,31 +67,31 @@ When using OpenHands in online mode, the GitHub OAuth flow:
    - Organization read access
 
 2. Authentication steps:
-   - Click "Sign in with GitHub" when prompted
-   - Review the requested permissions
-   - Authorize OpenHands to access your GitHub account
-   - If using an organization, authorize organization access if prompted
+   - Click "Sign in with GitHub" when prompted.
+   - Review the requested permissions.
+   - Authorize OpenHands to access your GitHub account.
+   - If using an organization, authorize organization access if prompted.
 
 #### Troubleshooting
 
 Common issues and solutions:
 
 1. **Token Not Recognized**:
-   - Ensure the token is properly saved in settings
-   - Check that the token hasn't expired
-   - Verify the token has the required scopes
-   - Try regenerating the token
+   - Ensure the token is properly saved in settings.
+   - Check that the token hasn't expired.
+   - Verify the token has the required scopes.
+   - Try regenerating the token.
 
 2. **Organization Access Denied**:
-   - Check if SSO is required but not enabled
-   - Verify organization membership
-   - Contact organization admin if token policies are blocking access
+   - Check if SSO is required but not enabled.
+   - Verify organization membership.
+   - Contact organization admin if token policies are blocking access.
 
 3. **Verifying Token Works**:
-   - The app will show a green checkmark if the token is valid
-   - Try accessing a repository to confirm permissions
-   - Check the browser console for any error messages
-   - Use the "Test Connection" button in settings if available
+   - The app will show a green checkmark if the token is valid.
+   - Try accessing a repository to confirm permissions.
+   - Check the browser console for any error messages.
+   - Use the "Test Connection" button in settings if available.
 
 ### Advanced Settings
 
@@ -103,11 +103,11 @@ Common issues and solutions:
 
 The main interface consists of several key components:
 
-1. **Chat Window**: The central area where you can view the conversation history with the AI assistant.
-2. **Input Box**: Located at the bottom of the screen, use this to type your messages or commands to the AI.
-3. **Send Button**: Click this to send your message to the AI.
-4. **Settings Button**: A gear icon that opens the settings modal, allowing you to adjust your configuration at any time.
-5. **Workspace Panel**: Displays the files and folders in your workspace, allowing you to navigate and view files, or the agent's past commands or web browsing history.
+- **Chat Window**: The central area where you can view the conversation history with the AI assistant.
+- **Input Box**: Located at the bottom of the screen, use this to type your messages or commands to the AI.
+- **Send Button**: Click this to send your message to the AI.
+- **Settings Button**: A gear icon that opens the settings modal, allowing you to adjust your configuration at any time.
+- **Workspace Panel**: Displays the files and folders in your workspace, allowing you to navigate and view files, or the agent's past commands or web browsing history.
 
 ### Interacting with the AI
 
@@ -118,8 +118,9 @@ The main interface consists of several key components:
 
 ## Tips for Effective Use
 
-1. Be specific in your requests to get the most accurate and helpful responses, as described in the [prompting best practices](../prompting/prompting-best-practices).
-2. Use the workspace panel to explore your project structure.
-3. Use one of the recommended models, as described in the [LLMs section](usage/llms/llms.md).
+- Be specific in your requests to get the most accurate and helpful responses, as described in the [prompting best practices](../prompting/prompting-best-practices).
+- Use the workspace panel to explore your project structure.
+- Use one of the recommended models, as described in the [LLMs section](usage/llms/llms.md).
 
-Remember, the GUI mode of OpenHands is designed to make your interaction with the AI assistant as smooth and intuitive as possible. Don't hesitate to explore its features to maximize your productivity.
+Remember, the GUI mode of OpenHands is designed to make your interaction with the AI assistant as smooth and intuitive
+as possible. Don't hesitate to explore its features to maximize your productivity.

docs/modules/usage/how-to/headless-mode.md

@@ -7,12 +7,11 @@ This is different from [CLI Mode](cli-mode), which is interactive, and better fo
 
 ## With Python
 
-To run OpenHands in headless mode with Python,
-[follow the Development setup instructions](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md),
-and then run:
-
+To run OpenHands in headless mode with Python:
+1. Ensure you have followed the [Development setup instructions](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
+2. Run the following command:
 ```bash
-poetry run python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
+poetry run python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 
 You'll need to be sure to set your model, API key, and other settings via environment variables
@@ -20,31 +19,20 @@ You'll need to be sure to set your model, API key, and other settings via enviro
 
 ## With Docker
 
-1. Set `WORKSPACE_BASE` to the directory you want OpenHands to edit:
+To run OpenHands in Headless mode with Docker:
 
-```bash
-WORKSPACE_BASE=$(pwd)/workspace
-```
+1. Set the following environmental variables in your terminal:
 
-2. Set `LLM_MODEL` to the model you want to use:
+- `WORKSPACE_BASE` to the directory you want OpenHands to edit (Ex: `export WORKSPACE_BASE=$(pwd)/workspace`).
+- `LLM_MODEL` to the model to use (Ex: `export LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"`).
+- `LLM_API_KEY` to the API key (Ex: `export LLM_API_KEY="sk_test_12345"`).
 
-```bash
-LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"
-
-```
-
-3. Set `LLM_API_KEY` to your API key:
-
-```bash
-LLM_API_KEY="sk_test_12345"
-```
-
-4. Run the following Docker command:
+2. Run the following Docker command:
 
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -52,8 +40,17 @@ docker run -it \
     -e LOG_ALL_EVENTS=true \
     -v $WORKSPACE_BASE:/opt/workspace_base \
     -v /var/run/docker.sock:/var/run/docker.sock \
+    -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.17 \
-    python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
+    docker.all-hands.dev/all-hands-ai/openhands:0.19 \
+    python -m openhands.core.main -t "write a bash script that prints hi"
 ```
+
+## Advanced Headless Configurations
+
+To view all available configuration options for headless mode, run the Python command with the `--help` flag.
+
+### Additional Logs
+
+For the headless mode to log all the agent actions, in the terminal run: `export LOG_ALL_EVENTS=true`

docs/modules/usage/how-to/persist-session-data.md

@@ -1,6 +1,6 @@
 # Persisting Session Data
 
-Using the standard installation, the session data is stored in memory. Currently, if OpenHands' service is restarted,
+Using the standard Development Workflow, the session data is stored in memory. Currently, if OpenHands' service is restarted,
 previous sessions become invalid (a new secret is generated) and thus not recoverable.
 
 ## How to Persist Session Data

docs/modules/usage/installation.mdx

@@ -2,34 +2,37 @@
 
 ## System Requirements
 
-* Docker version 26.0.0+ or Docker Desktop 4.31.0+.
-* You must be using Linux or Mac OS.
-  * If you are on Windows, you must use [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
+- Docker version 26.0.0+ or Docker Desktop 4.31.0+.
+- You must be using Linux or Mac OS.
+  - If you are on Windows, you must use [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
 
 ## Start the app
 
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.17
+    docker.all-hands.dev/all-hands-ai/openhands:0.19
 ```
 
-You can also run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), as an [interactive CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), or using the [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action).
+You'll find OpenHands running at http://localhost:3000!
+
+You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes#connecting-to-your-filesystem),
+run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
+interact with it via a [friendly CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode),
+or run it on tagged issues with [a github action](https://docs.all-hands.dev/modules/usage/how-to/github-action).
 
 ## Setup
 
-After running the command above, you'll find OpenHands running at [http://localhost:3000](http://localhost:3000).
-
 Upon launching OpenHands, you'll see a settings modal. You **must** select an `LLM Provider` and `LLM Model` and enter a corresponding `API Key`.
 These can be changed at any time by selecting the `Settings` button (gear icon) in the UI.
 

docs/modules/usage/llms/azure-llms.md

@@ -18,17 +18,18 @@ docker run -it --pull=always \
     ...
 ```
 
-Then set the following in the OpenHands UI through the Settings:
+Then in the OpenHands UI Settings:
 
 :::note
 You will need your ChatGPT deployment name which can be found on the deployments page in Azure. This is referenced as
 <deployment-name> below.
 :::
 
-* Enable `Advanced Options`
-* `Custom Model` to azure/<deployment-name>
-* `Base URL` to your Azure API Base URL (e.g. `https://example-endpoint.openai.azure.com`)
-* `API Key` to your Azure API key
+1. Enable `Advanced Options`
+2. Set the following:
+   - `Custom Model` to azure/<deployment-name>
+   - `Base URL` to your Azure API Base URL (e.g. `https://example-endpoint.openai.azure.com`)
+   - `API Key` to your Azure API key
 
 ## Embeddings
 

docs/modules/usage/llms/google-llms.md

@@ -8,10 +8,10 @@ OpenHands uses LiteLLM to make calls to Google's chat models. You can find their
 ## Gemini - Google AI Studio Configs
 
 When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings:
-* `LLM Provider` to `Gemini`
-* `LLM Model` to the model you will be using.
+- `LLM Provider` to `Gemini`
+- `LLM Model` to the model you will be using.
 If the model is not in the list, toggle `Advanced Options`, and enter it in `Custom Model` (e.g. gemini/<model-name> like `gemini/gemini-1.5-pro`).
-* `API Key` to your Gemini API key
+- `API Key` to your Gemini API key
 
 ## VertexAI - Google Cloud Platform Configs
 
@@ -25,6 +25,6 @@ VERTEXAI_LOCATION="<your-gcp-location>"
 ```
 
 Then set the following in the OpenHands UI through the Settings:
-* `LLM Provider` to `VertexAI`
-* `LLM Model` to the model you will be using.
+- `LLM Provider` to `VertexAI`
+- `LLM Model` to the model you will be using.
 If the model is not in the list, toggle `Advanced Options`, and enter it in `Custom Model` (e.g. vertex_ai/&lt;model-name&gt;).

docs/modules/usage/llms/groq.md

@@ -5,19 +5,20 @@ OpenHands uses LiteLLM to make calls to chat models on Groq. You can find their
 ## Configuration
 
 When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings:
-* `LLM Provider` to `Groq`
-* `LLM Model` to the model you will be using. [Visit here to see the list of
+- `LLM Provider` to `Groq`
+- `LLM Model` to the model you will be using. [Visit here to see the list of
 models that Groq hosts](https://console.groq.com/docs/models). If the model is not in the list, toggle
 `Advanced Options`, and enter it in `Custom Model` (e.g. groq/<model-name> like `groq/llama3-70b-8192`).
-* `API key` to your Groq API key. To find or create your Groq API Key, [see here](https://console.groq.com/keys).
+- `API key` to your Groq API key. To find or create your Groq API Key, [see here](https://console.groq.com/keys).
 
 
 
 ## Using Groq as an OpenAI-Compatible Endpoint
 
 The Groq endpoint for chat completion is [mostly OpenAI-compatible](https://console.groq.com/docs/openai). Therefore, you can access Groq models as you
-would access any OpenAI-compatible endpoint. You can set the following in the OpenHands UI through the Settings:
-* Enable `Advanced Options`
-* `Custom Model` to the prefix `openai/` + the model you will be using (e.g. `openai/llama3-70b-8192`)
-* `Base URL` to `https://api.groq.com/openai/v1`
-* `API Key` to your Groq API key
+would access any OpenAI-compatible endpoint. In the OpenHands UI through the Settings:
+1. Enable `Advanced Options`
+2. Set the following:
+   - `Custom Model` to the prefix `openai/` + the model you will be using (e.g. `openai/llama3-70b-8192`)
+   - `Base URL` to `https://api.groq.com/openai/v1`
+   - `API Key` to your Groq API key

docs/modules/usage/llms/llms.md

@@ -4,7 +4,9 @@ OpenHands can connect to any LLM supported by LiteLLM. However, it requires a po
 
 ## Model Recommendations
 
-Based on our evaluations of language models for coding tasks (using the SWE-bench dataset), we can provide some recommendations for model selection. Some analyses can be found in [this blog article comparing LLMs](https://www.all-hands.dev/blog/evaluation-of-llms-as-coding-agents-on-swe-bench-at-30x-speed) and [this blog article with some more recent results](https://www.all-hands.dev/blog/openhands-codeact-21-an-open-state-of-the-art-software-development-agent).
+Based on our evaluations of language models for coding tasks (using the SWE-bench dataset), we can provide some
+recommendations for model selection. Some analyses can be found in [this blog article comparing LLMs](https://www.all-hands.dev/blog/evaluation-of-llms-as-coding-agents-on-swe-bench-at-30x-speed) and
+[this blog article with some more recent results](https://www.all-hands.dev/blog/openhands-codeact-21-an-open-state-of-the-art-software-development-agent).
 
 When choosing a model, consider both the quality of outputs and the associated costs. Here's a summary of the findings:
 
@@ -69,9 +71,11 @@ We have a few guides for running OpenHands with specific model providers:
 
 ### API retries and rate limits
 
-LLM providers typically have rate limits, sometimes very low, and may require retries. OpenHands will automatically retry requests if it receives a Rate Limit Error (429 error code), API connection error, or other transient errors.
+LLM providers typically have rate limits, sometimes very low, and may require retries. OpenHands will automatically
+retry requests if it receives a Rate Limit Error (429 error code), API connection error, or other transient errors.
 
-You can customize these options as you need for the provider you're using. Check their documentation, and set the following environment variables to control the number of retries and the time between retries:
+You can customize these options as you need for the provider you're using. Check their documentation, and set the
+following environment variables to control the number of retries and the time between retries:
 
 - `LLM_NUM_RETRIES` (Default of 8)
 - `LLM_RETRY_MIN_WAIT` (Default of 15 seconds)

docs/modules/usage/llms/openai-llms.md

@@ -17,8 +17,9 @@ Just as for OpenAI Chat completions, we use LiteLLM for OpenAI-compatible endpoi
 
 ## Using an OpenAI Proxy
 
-If you're using an OpenAI proxy, you'll need to set the following in the OpenHands UI through the Settings:
-* Enable `Advanced Options`
-* `Custom Model` to openai/<model-name> (e.g. `openai/gpt-4o` or openai/<proxy-prefix>/<model-name>)
-* `Base URL` to the URL of your OpenAI proxy
-* `API Key` to your OpenAI API key
+If you're using an OpenAI proxy, in the OpenHands UI through the Settings:
+1. Enable `Advanced Options`
+2. Set the following:
+   - `Custom Model` to openai/<model-name> (e.g. `openai/gpt-4o` or openai/<proxy-prefix>/<model-name>)
+   - `Base URL` to the URL of your OpenAI proxy
+   - `API Key` to your OpenAI API key

docs/modules/usage/prompting/customization.md

@@ -1,67 +0,0 @@
-# Customizing Agent Behavior
-
-OpenHands can be customized to work more effectively with specific repositories by providing repository-specific context and guidelines. This section explains how to optimize OpenHands for your project.
-
-## Repository Configuration
-
-You can customize OpenHands' behavior for your repository by creating a `.openhands` directory in your repository's root. At minimum, it should contain the file
-`.openhands/microagents/repo.md`, which includes instructions that will
-be given to the agent every time it works with this repository.
-
-We suggest including the following information:
-1. **Repository Overview**: A brief description of your project's purpose and architecture
-2. **Directory Structure**: Key directories and their purposes
-3. **Development Guidelines**: Project-specific coding standards and practices
-4. **Testing Requirements**: How to run tests and what types of tests are required
-5. **Setup Instructions**: Steps needed to build and run the project
-
-### Example Repository Configuration
-Example `.openhands/microagents/repo.md` file:
-```
-Repository: MyProject
-Description: A web application for task management
-
-Directory Structure:
-- src/: Main application code
-- tests/: Test files
-- docs/: Documentation
-
-Setup:
-- Run `npm install` to install dependencies
-- Use `npm run dev` for development
-- Run `npm test` for testing
-
-Guidelines:
-- Follow ESLint configuration
-- Write tests for all new features
-- Use TypeScript for new code
-```
-
-### Customizing Prompts
-
-When working with a customized repository:
-
-1. **Reference Project Standards**: Mention specific coding standards or patterns used in your project
-2. **Include Context**: Reference relevant documentation or existing implementations
-3. **Specify Testing Requirements**: Include project-specific testing requirements in your prompts
-
-Example customized prompt:
-```
-Add a new task completion feature to src/components/TaskList.tsx following our existing component patterns.
-Include unit tests in tests/components/ and update the documentation in docs/features/.
-The component should use our shared styling from src/styles/components.
-```
-
-### Best Practices for Repository Customization
-
-1. **Keep Instructions Updated**: Regularly update your `.openhands` directory as your project evolves
-2. **Be Specific**: Include specific paths, patterns, and requirements unique to your project
-3. **Document Dependencies**: List all tools and dependencies required for development
-4. **Include Examples**: Provide examples of good code patterns from your project
-5. **Specify Conventions**: Document naming conventions, file organization, and code style preferences
-
-By customizing OpenHands for your repository, you'll get more accurate and consistent results that align with your project's standards and requirements.
-
-## Other Microagents
-You can create other instructions in the `.openhands/microagents/` directory
-that will be sent to the agent if a particular keyword is found, like `test`, `frontend`, or `migration`. See [Microagents](microagents.md) for more information.

docs/modules/usage/prompting/microagents-public.md

@@ -0,0 +1,214 @@
+# Public Micro-Agents
+
+OpenHands uses specialized micro-agents to handle specific tasks and contexts efficiently. These micro-agents are small,
+focused components that provide specialized behavior and knowledge for particular scenarios.
+
+## Overview
+
+Public micro-agents are defined in markdown files under the
+[`microagents/knowledge/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge) directory.
+Each micro-agent is configured with:
+
+- A unique name.
+- The agent type (typically CodeActAgent).
+- Trigger keywords that activate the agent.
+- Specific instructions and capabilities.
+
+### Integration
+
+Public micro-agents are automatically integrated into OpenHands' workflow. They:
+- Monitor incoming commands for their trigger words.
+- Activate when relevant triggers are detected.
+- Apply their specialized knowledge and capabilities.
+- Follow their specific guidelines and restrictions.
+
+## Available Public Micro-Agents
+
+For more information about specific micro-agents, refer to their individual documentation files in
+the [`micro-agents`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents) directory.
+
+### GitHub Agent
+**File**: `github.md`
+**Triggers**: `github`, `git`
+
+The GitHub agent specializes in GitHub API interactions and repository management. It:
+- Has access to a `GITHUB_TOKEN` for API authentication.
+- Follows strict guidelines for repository interactions.
+- Handles branch management and pull requests.
+- Uses the GitHub API instead of web browser interactions.
+
+Key features:
+- Branch protection (prevents direct pushes to main/master)
+- Automated PR creation
+- Git configuration management
+- API-first approach for GitHub operations
+
+Usage Example:
+
+```bash
+git checkout -b feature-branch
+git commit -m "Add new feature"
+git push origin feature-branch
+```
+
+### NPM Agent
+**File**: `npm.md`
+**Triggers**: `npm`
+
+Specializes in handling npm package management with specific focus on:
+- Non-interactive shell operations.
+- Automated confirmation handling using Unix 'yes' command.
+- Package installation automation.
+
+Usage Example:
+
+```bash
+yes | npm install package-name
+```
+
+### Custom Public Micro-Agents
+
+You can create your own public micro-agents by adding new markdown files to the `microagents/knowledge/` directory.
+Each file should follow this structure:
+
+```markdown
+---
+name: agent_name
+agent: CodeActAgent
+triggers:
+- trigger_word1
+- trigger_word2
+---
+
+Instructions and capabilities for the micro-agent...
+```
+
+## Working With Public Micro-Agents
+
+When working with public micro-agents:
+- **Use Appropriate Triggers**: Ensure your commands include the relevant trigger words to activate the correct micro-agent.
+- **Follow Agent Guidelines**: Each agent has specific instructions and limitations. Respect these for optimal results.
+- **API-First Approach**: When available, use API endpoints rather than web interfaces.
+- **Automation Friendly**: Design commands that work well in non-interactive environments.
+
+## Contributing a Public Micro-Agent
+
+Best practices for creating public micro-agents:
+
+- **Clear Scope**: Keep the micro-agent focused on a specific domain or task.
+- **Explicit Instructions**: Provide clear, unambiguous guidelines.
+- **Useful Examples**: Include practical examples of common use cases.
+- **Safety First**: Include necessary warnings and constraints.
+- **Integration Awareness**: Consider how the micro-agent interacts with other components.
+
+To contribute a new micro-agent to OpenHands:
+
+### 1. Plan the Public Micro-Agent
+
+Before creating a public micro-agent, consider:
+- What specific problem or use case will it address?
+- What unique capabilities or knowledge should it have?
+- What trigger words make sense for activating it?
+- What constraints or guidelines should it follow?
+
+### 2. File Structure
+
+Create a new markdown file in `microagents/knowledge/` with a descriptive name (e.g., `docker.md` for a Docker-focused agent).
+
+### 3. Required Components
+
+The micro-agent file must include:
+
+- **Front Matter**: YAML metadata at the start of the file:
+```markdown
+---
+name: your_agent_name
+agent: CodeActAgent
+triggers:
+- trigger_word1
+- trigger_word2
+---
+```
+
+- **Instructions**: Clear, specific guidelines for the agent's behavior:
+```markdown
+You are responsible for [specific task/domain].
+
+Key responsibilities:
+1. [Responsibility 1]
+2. [Responsibility 2]
+
+Guidelines:
+- [Guideline 1]
+- [Guideline 2]
+
+Examples of usage:
+[Example 1]
+[Example 2]
+```
+
+### 4. Testing the Public Micro-Agent
+
+Before submitting:
+- Test the agent with various prompts.
+- Verify trigger words activate the agent correctly.
+- Ensure instructions are clear and comprehensive.
+- Check for potential conflicts with existing agents.
+
+### 5. Submission Process
+
+Submit a pull request with:
+- The new micro-agent file.
+- Updated documentation if needed.
+- Description of the agent's purpose and capabilities.
+
+### Example Public Micro-Agent Implementation
+
+Here's a template for a new micro-agent:
+
+```markdown
+---
+name: docker
+agent: CodeActAgent
+triggers:
+- docker
+- container
+---
+
+You are responsible for Docker container management and Dockerfile creation.
+
+Key responsibilities:
+1. Create and modify Dockerfiles
+2. Manage container lifecycle
+3. Handle Docker Compose configurations
+
+Guidelines:
+- Always use official base images when possible
+- Include necessary security considerations
+- Follow Docker best practices for layer optimization
+
+Examples:
+1. Creating a Dockerfile:
+   FROM node:18-alpine
+   WORKDIR /app
+   COPY package*.json ./
+   RUN npm install
+   COPY . .
+   CMD ["npm", "start"]
+
+2. Docker Compose usage:
+   version: '3'
+   services:
+     web:
+       build: .
+       ports:
+         - "3000:3000"
+
+Remember to:
+- Validate Dockerfile syntax
+- Check for security vulnerabilities
+- Optimize for build time and image size
+```
+
+Remember that micro-agents are a powerful way to extend OpenHands' capabilities in specific domains. Well-designed
+agents can significantly improve the system's ability to handle specialized tasks.

docs/modules/usage/prompting/microagents-repo.md

@@ -0,0 +1,66 @@
+# Repository Micro-Agents
+
+OpenHands can be customized to work more effectively with specific repositories by providing repository-specific context
+and guidelines. This section explains how to optimize OpenHands for your project.
+
+## Repository Configuration
+
+You can customize OpenHands' behavior for your repository by creating a `.openhands/microagents/` directory in your repository's root.
+At minimum, it should contain the file
+`.openhands/microagents/repo.md`, which includes instructions that will
+be given to the agent every time it works with this repository.
+
+We suggest including the following information:
+- **Repository Overview**: A brief description of your project's purpose and architecture.
+- **Directory Structure**: Key directories and their purposes.
+- **Development Guidelines**: Project-specific coding standards and practices.
+- **Testing Requirements**: How to run tests and what types of tests are required.
+- **Setup Instructions**: Steps needed to build and run the project.
+
+### Example Repository Configuration
+Example `.openhands/microagents/repo.md` file:
+```
+Repository: MyProject
+Description: A web application for task management
+
+Directory Structure:
+- src/: Main application code
+- tests/: Test files
+- docs/: Documentation
+
+Setup:
+- Run `npm install` to install dependencies
+- Use `npm run dev` for development
+- Run `npm test` for testing
+
+Guidelines:
+- Follow ESLint configuration
+- Write tests for all new features
+- Use TypeScript for new code
+```
+
+### Customizing Prompts
+
+You may also add customized prompts to the `.openhands/microagents/repo.md` file when working with a repository.
+These could:
+
+- **Reference Project Standards**: Mention specific coding standards or patterns used in your project.
+- **Include Context**: Reference relevant documentation or existing implementations.
+- **Specify Testing Requirements**: Include project-specific testing requirements in your prompts.
+
+Example customized prompt:
+```
+Add a new task completion feature to src/components/TaskList.tsx following our existing component patterns.
+Include unit tests in tests/components/ and update the documentation in docs/features/.
+The component should use our shared styling from src/styles/components.
+```
+
+### Best Practices for Repository Customization
+
+- **Keep Instructions Updated**: Regularly update your `.openhands/microagents/` directory as your project evolves.
+- **Be Specific**: Include specific paths, patterns, and requirements unique to your project.
+- **Document Dependencies**: List all tools and dependencies required for development.
+- **Include Examples**: Provide examples of good code patterns from your project.
+- **Specify Conventions**: Document naming conventions, file organization, and code style preferences.
+
+By customizing OpenHands for your repository, you'll get more accurate and consistent results that align with your project's standards and requirements.

docs/modules/usage/prompting/microagents.md

@@ -1,209 +0,0 @@
-# Micro-Agents
-
-OpenHands uses specialized micro-agents to handle specific tasks and contexts efficiently. These micro-agents are small, focused components that provide specialized behavior and knowledge for particular scenarios.
-
-## Overview
-
-Micro-agents are defined in markdown files under the `openhands/agenthub/codeact_agent/micro/` directory. Each micro-agent is configured with:
-
-- A unique name
-- The agent type (typically CodeActAgent)
-- Trigger keywords that activate the agent
-- Specific instructions and capabilities
-
-## Available Micro-Agents
-
-### GitHub Agent
-**File**: `github.md`
-**Triggers**: `github`, `git`
-
-The GitHub agent specializes in GitHub API interactions and repository management. It:
-- Has access to a `GITHUB_TOKEN` for API authentication
-- Follows strict guidelines for repository interactions
-- Handles branch management and pull requests
-- Uses the GitHub API instead of web browser interactions
-
-Key features:
-- Branch protection (prevents direct pushes to main/master)
-- Automated PR creation
-- Git configuration management
-- API-first approach for GitHub operations
-
-### NPM Agent
-**File**: `npm.md`
-**Triggers**: `npm`
-
-Specializes in handling npm package management with specific focus on:
-- Non-interactive shell operations
-- Automated confirmation handling using Unix 'yes' command
-- Package installation automation
-
-### Custom Micro-Agents
-
-You can create your own micro-agents by adding new markdown files to the micro-agents directory. Each file should follow this structure:
-
-```markdown
----
-name: agent_name
-agent: CodeActAgent
-triggers:
-- trigger_word1
-- trigger_word2
----
-
-Instructions and capabilities for the micro-agent...
-```
-
-## Best Practices
-
-When working with micro-agents:
-
-1. **Use Appropriate Triggers**: Ensure your commands include the relevant trigger words to activate the correct micro-agent
-2. **Follow Agent Guidelines**: Each agent has specific instructions and limitations - respect these for optimal results
-3. **API-First Approach**: When available, use API endpoints rather than web interfaces
-4. **Automation Friendly**: Design commands that work well in non-interactive environments
-
-## Integration
-
-Micro-agents are automatically integrated into OpenHands' workflow. They:
-- Monitor incoming commands for their trigger words
-- Activate when relevant triggers are detected
-- Apply their specialized knowledge and capabilities
-- Follow their specific guidelines and restrictions
-
-## Example Usage
-
-```bash
-# GitHub agent example
-git checkout -b feature-branch
-git commit -m "Add new feature"
-git push origin feature-branch
-
-# NPM agent example
-yes | npm install package-name
-```
-
-For more information about specific agents, refer to their individual documentation files in the micro-agents directory.
-
-## Contributing a Micro-Agent
-
-To contribute a new micro-agent to OpenHands, follow these guidelines:
-
-### 1. Planning Your Micro-Agent
-
-Before creating a micro-agent, consider:
-- What specific problem or use case will it address?
-- What unique capabilities or knowledge should it have?
-- What trigger words make sense for activating it?
-- What constraints or guidelines should it follow?
-
-### 2. File Structure
-
-Create a new markdown file in `openhands/agenthub/codeact_agent/micro/` with a descriptive name (e.g., `docker.md` for a Docker-focused agent).
-
-### 3. Required Components
-
-Your micro-agent file must include:
-
-1. **Front Matter**: YAML metadata at the start of the file:
-```markdown
----
-name: your_agent_name
-agent: CodeActAgent
-triggers:
-- trigger_word1
-- trigger_word2
----
-```
-
-2. **Instructions**: Clear, specific guidelines for the agent's behavior:
-```markdown
-You are responsible for [specific task/domain].
-
-Key responsibilities:
-1. [Responsibility 1]
-2. [Responsibility 2]
-
-Guidelines:
-- [Guideline 1]
-- [Guideline 2]
-
-Examples of usage:
-[Example 1]
-[Example 2]
-```
-
-### 4. Best Practices for Micro-Agent Development
-
-1. **Clear Scope**: Keep the agent focused on a specific domain or task
-2. **Explicit Instructions**: Provide clear, unambiguous guidelines
-3. **Useful Examples**: Include practical examples of common use cases
-4. **Safety First**: Include necessary warnings and constraints
-5. **Integration Awareness**: Consider how the agent interacts with other components
-
-### 5. Testing Your Micro-Agent
-
-Before submitting:
-1. Test the agent with various prompts
-2. Verify trigger words activate the agent correctly
-3. Ensure instructions are clear and comprehensive
-4. Check for potential conflicts with existing agents
-
-### 6. Example Implementation
-
-Here's a template for a new micro-agent:
-
-```markdown
----
-name: docker
-agent: CodeActAgent
-triggers:
-- docker
-- container
----
-
-You are responsible for Docker container management and Dockerfile creation.
-
-Key responsibilities:
-1. Create and modify Dockerfiles
-2. Manage container lifecycle
-3. Handle Docker Compose configurations
-
-Guidelines:
-- Always use official base images when possible
-- Include necessary security considerations
-- Follow Docker best practices for layer optimization
-
-Examples:
-1. Creating a Dockerfile:
-   FROM node:18-alpine
-   WORKDIR /app
-   COPY package*.json ./
-   RUN npm install
-   COPY . .
-   CMD ["npm", "start"]
-
-2. Docker Compose usage:
-   version: '3'
-   services:
-     web:
-       build: .
-       ports:
-         - "3000:3000"
-
-Remember to:
-- Validate Dockerfile syntax
-- Check for security vulnerabilities
-- Optimize for build time and image size
-```
-
-### 7. Submission Process
-
-1. Create your micro-agent file in the correct directory
-2. Test thoroughly
-3. Submit a pull request with:
-   - The new micro-agent file
-   - Updated documentation if needed
-   - Description of the agent's purpose and capabilities
-
-Remember that micro-agents are a powerful way to extend OpenHands' capabilities in specific domains. Well-designed agents can significantly improve the system's ability to handle specialized tasks.

docs/modules/usage/prompting/prompting-best-practices.md

@@ -6,35 +6,31 @@ When working with OpenHands AI software developer, it's crucial to provide clear
 
 Good prompts are:
 
-1. **Concrete**: They explain exactly what functionality should be added or what error needs to be fixed.
-2. **Location-specific**: If known, they explain the locations in the code base that should be modified.
-3. **Appropriately scoped**: They should be the size of a single feature, typically not exceeding 100 lines of code.
+- **Concrete**: They explain exactly what functionality should be added or what error needs to be fixed.
+- **Location-specific**: If known, they explain the locations in the code base that should be modified.
+- **Appropriately scoped**: They should be the size of a single feature, typically not exceeding 100 lines of code.
 
 ## Examples
 
 ### Good Prompt Examples
 
-1. "Add a function `calculate_average` in `utils/math_operations.py` that takes a list of numbers as input and returns their average."
-
-2. "Fix the TypeError in `frontend/src/components/UserProfile.tsx` occurring on line 42. The error suggests we're trying to access a property of undefined."
-
-3. "Implement input validation for the email field in the registration form. Update `frontend/src/components/RegistrationForm.tsx` to check if the email is in a valid format before submission."
+- "Add a function `calculate_average` in `utils/math_operations.py` that takes a list of numbers as input and returns their average."
+- "Fix the TypeError in `frontend/src/components/UserProfile.tsx` occurring on line 42. The error suggests we're trying to access a property of undefined."
+- "Implement input validation for the email field in the registration form. Update `frontend/src/components/RegistrationForm.tsx` to check if the email is in a valid format before submission."
 
 ### Bad Prompt Examples
 
-1. "Make the code better." (Too vague, not concrete)
-
-2. "Rewrite the entire backend to use a different framework." (Not appropriately scoped)
-
-3. "There's a bug somewhere in the user authentication. Can you find and fix it?" (Lacks specificity and location information)
+- "Make the code better." (Too vague, not concrete)
+- "Rewrite the entire backend to use a different framework." (Not appropriately scoped)
+- "There's a bug somewhere in the user authentication. Can you find and fix it?" (Lacks specificity and location information)
 
 ## Tips for Effective Prompting
 
-1. Be as specific as possible about the desired outcome or the problem to be solved.
-2. Provide context, including relevant file paths and line numbers if available.
-3. Break down large tasks into smaller, manageable prompts.
-4. Include any relevant error messages or logs.
-5. Specify the programming language or framework if it's not obvious from the context.
+- Be as specific as possible about the desired outcome or the problem to be solved.
+- Provide context, including relevant file paths and line numbers if available.
+- Break down large tasks into smaller, manageable prompts.
+- Include any relevant error messages or logs.
+- Specify the programming language or framework if it's not obvious from the context.
 
 Remember, the more precise and informative your prompt is, the better the AI can assist you in developing or modifying the OpenHands software.
 

docs/modules/usage/runtimes.md

@@ -16,7 +16,7 @@ some flags being passed to `docker run` that make this possible:
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```
@@ -26,30 +26,29 @@ that contains our Runtime server, as well as some basic utilities for Python and
 You can also [build your own runtime image](how-to/custom-sandbox-guide).
 
 ### Connecting to Your filesystem
-One useful feature here is the ability to connect to your local filesystem.
+One useful feature here is the ability to connect to your local filesystem. To mount your filesystem into the runtime:
+1. Set `WORKSPACE_BASE`:
 
-To mount your filesystem into the runtime, first set WORKSPACE_BASE:
-```bash
-export WORKSPACE_BASE=/path/to/your/code
+    ```bash
+    export WORKSPACE_BASE=/path/to/your/code
 
-# Linux and Mac Example
-# export WORKSPACE_BASE=$HOME/OpenHands
-# Will set $WORKSPACE_BASE to /home/<username>/OpenHands
-#
-# WSL on Windows Example
-# export WORKSPACE_BASE=/mnt/c/dev/OpenHands
-# Will set $WORKSPACE_BASE to C:\dev\OpenHands
-```
+    # Linux and Mac Example
+    # export WORKSPACE_BASE=$HOME/OpenHands
+    # Will set $WORKSPACE_BASE to /home/<username>/OpenHands
+    #
+    # WSL on Windows Example
+    # export WORKSPACE_BASE=/mnt/c/dev/OpenHands
+    # Will set $WORKSPACE_BASE to C:\dev\OpenHands
+    ```
+2. Add the following options to the `docker run` command:
 
-then add the following options to the `docker run` command:
-
-```bash
-docker run # ...
-    -e SANDBOX_USER_ID=$(id -u) \
-    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
-    -v $WORKSPACE_BASE:/opt/workspace_base \
-    # ...
-```
+    ```bash
+    docker run # ...
+        -e SANDBOX_USER_ID=$(id -u) \
+        -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
+        -v $WORKSPACE_BASE:/opt/workspace_base \
+        # ...
+    ```
 
 Be careful! There's nothing stopping the OpenHands agent from deleting or modifying
 any files that are mounted into its workspace.
@@ -59,7 +58,7 @@ but seems to work well on most systems.
 
 ## All Hands Runtime
 The All Hands Runtime is currently in beta. You can request access by joining
-the #remote-runtime-limited-beta channel on Slack ([see the README](https://github.com/All-Hands-AI/OpenHands?tab=readme-ov-file#-join-our-community) for an invite).
+the #remote-runtime-limited-beta channel on Slack ([see the README](https://github.com/All-Hands-AI/OpenHands?tab=readme-ov-file#-how-to-join-the-community) for an invite).
 
 To use the All Hands Runtime, set the following environment variables when
 starting OpenHands:

docs/package.json

@@ -15,10 +15,10 @@
     "typecheck": "tsc"
   },
   "dependencies": {
-    "@docusaurus/core": "^3.6.3",
-    "@docusaurus/plugin-content-pages": "^3.6.3",
-    "@docusaurus/preset-classic": "^3.6.3",
-    "@docusaurus/theme-mermaid": "^3.6.3",
+    "@docusaurus/core": "^3.7.0",
+    "@docusaurus/plugin-content-pages": "^3.7.0",
+    "@docusaurus/preset-classic": "^3.7.0",
+    "@docusaurus/theme-mermaid": "^3.7.0",
     "@mdx-js/react": "^3.1.0",
     "clsx": "^2.0.0",
     "prism-react-renderer": "^2.4.1",
@@ -29,7 +29,7 @@
   },
   "devDependencies": {
     "@docusaurus/module-type-aliases": "^3.5.1",
-    "@docusaurus/tsconfig": "^3.6.3",
+    "@docusaurus/tsconfig": "^3.7.0",
     "@docusaurus/types": "^3.5.1",
     "typescript": "~5.7.2"
   },

docs/sidebars.ts

@@ -23,15 +23,21 @@ const sidebars: SidebarsConfig = {
           id: 'usage/prompting/prompting-best-practices',
         },
         {
-          type: 'doc',
-          label: 'Customization',
-          id: 'usage/prompting/customization',
-        },
-        {
-          type: 'doc',
-          label: 'Microagents',
-          id: 'usage/prompting/microagents',
-        },
+          type: 'category',
+          label: 'Micro-Agents',
+          items: [
+            {
+              type: 'doc',
+              label: 'Public',
+              id: 'usage/prompting/microagents-public',
+            },
+            {
+              type: 'doc',
+              label: 'Repository',
+              id: 'usage/prompting/microagents-repo',
+            },
+          ],
+        }
       ],
     },
     {

docs/static/img/backend_architecture.puml

@@ -123,7 +123,6 @@ class openhands.state.State {
   updated_info: List[Tuple[Action, Observation]]
 }
 class openhands.observation.CmdOutputObservation {
-  command_id: int
   command: str
   exit_code: int
   observation: str

dummy_eval_output_dir/dummy_dataset_descrption/CodeActAgent/claude-3-5-sonnet-20241022_maxiter_10_N_dummy_eval_note/metadata.json

@@ -0,0 +1 @@
+{"agent_class": "CodeActAgent", "llm_config": {"model": "claude-3-5-sonnet-20241022", "api_key": null, "base_url": null, "api_version": null, "embedding_model": "local", "embedding_base_url": null, "embedding_deployment_name": null, "aws_access_key_id": null, "aws_secret_access_key": null, "aws_region_name": null, "openrouter_site_url": "https://docs.all-hands.dev/", "openrouter_app_name": "OpenHands", "num_retries": 8, "retry_multiplier": 2, "retry_min_wait": 15, "retry_max_wait": 120, "timeout": null, "max_message_chars": 30000, "temperature": 0.0, "top_p": 1.0, "custom_llm_provider": null, "max_input_tokens": null, "max_output_tokens": null, "input_cost_per_token": null, "output_cost_per_token": null, "ollama_base_url": null, "drop_params": true, "modify_params": true, "disable_vision": null, "caching_prompt": true, "log_completions": false, "log_completions_folder": "/workspace/OpenHands/logs/completions", "draft_editor": null, "custom_tokenizer": null, "native_tool_calling": null}, "max_iterations": 10, "eval_output_dir": "./dummy_eval_output_dir/dummy_dataset_descrption/CodeActAgent/claude-3-5-sonnet-20241022_maxiter_10_N_dummy_eval_note", "start_time": "2025-01-08 18:01:01", "git_commit": "007052c8aa15ea5149fff31583a3412ea7b8625a", "dataset": "dummy_dataset_descrption", "data_split": null, "details": {}, "condenser_config": {"type": "noop"}}

evaluation/benchmarks/EDA/run_infer.py

@@ -75,6 +75,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/agent_bench/run_infer.py

@@ -59,6 +59,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     return config
 
 
@@ -135,7 +137,6 @@ def complete_runtime(
 
         action = CmdRunAction(
             command=f'chmod +x ./{script_name} && ./{script_name}',
-            keep_prompt=False,
         )
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
@@ -162,8 +163,7 @@ def complete_runtime(
             logger.info(f'Running get ground truth cmd: {script_name}')
 
             action = CmdRunAction(
-                command=f'chmod +x ./{script_name} && ./{script_name}',
-                keep_prompt=False,
+                command=f'chmod +x ./{script_name} && ./{script_name}'
             )
             logger.info(action, extra={'msg_type': 'ACTION'})
             obs = runtime.run_action(action)

evaluation/benchmarks/aider_bench/run_infer.py

@@ -67,6 +67,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
 
     # copy 'draft_editor' config if exists
     config_copy = copy.deepcopy(config)
@@ -143,10 +145,7 @@ def complete_runtime(
         )
         logger.info(f'Running test file: {script_name}')
 
-    action = CmdRunAction(
-        command=f'python3 -m unittest {script_name}',
-        keep_prompt=False,
-    )
+    action = CmdRunAction(command=f'python3 -m unittest {script_name}')
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})

evaluation/benchmarks/biocoder/run_infer.py

@@ -73,6 +73,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     return config
 
 
@@ -197,7 +199,7 @@ def complete_runtime(
     if obs.exit_code == 0:
         test_result['metadata']['1_copy_change_success'] = True
 
-        action = CmdRunAction(command=f'cat {generated_path}', keep_prompt=False)
+        action = CmdRunAction(command=f'cat {generated_path}')
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         assert obs.exit_code == 0
@@ -221,9 +223,7 @@ def complete_runtime(
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     assert obs.exit_code == 0
 
-    action = CmdRunAction(
-        command='cat /testing_files/results_biocoder.json', keep_prompt=False
-    )
+    action = CmdRunAction(command='cat /testing_files/results_biocoder.json')
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     if obs.exit_code == 0:

evaluation/benchmarks/bird/README.md

@@ -127,7 +127,6 @@ For each problem, OpenHands is given a set number of iterations to fix the faili
         "observation": "run",
         "content": "california_schools/california_schools.sqlite\r\n[(1.0,)]",
         "extras": {
-          "command_id": -1,
           "command": "python3 0.py",
           "exit_code": 0
         }

evaluation/benchmarks/bird/run_infer.py

@@ -86,6 +86,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     return config
 
 
@@ -266,10 +268,7 @@ def initialize_runtime(
     runtime.copy_to(db_file, '/workspace')
 
     # Check the database is copied
-    action = CmdRunAction(
-        command='cd /workspace && ls -l',
-        keep_prompt=False,
-    )
+    action = CmdRunAction(command='cd /workspace && ls -l')
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     assert obs.exit_code == 0
@@ -298,10 +297,7 @@ def complete_runtime(
     instance_id = instance.instance_id.replace('/', '__')
     path = os.path.join('/workspace', f'{instance_id}.py')
 
-    action = CmdRunAction(
-        command=f'cat {path}',
-        keep_prompt=False,
-    )
+    action = CmdRunAction(command=f'cat {path}')
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
 

evaluation/benchmarks/browsing_delegation/run_infer.py

@@ -50,6 +50,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/discoverybench/run_infer.py

@@ -77,6 +77,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     agent_config = AgentConfig(
         function_calling=False,
         codeact_enable_jupyter=True,

evaluation/benchmarks/gaia/run_infer.py

@@ -62,6 +62,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/gorilla/run_infer.py

@@ -55,6 +55,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/gpqa/run_infer.py

@@ -76,6 +76,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/humanevalfix/README.md

@@ -71,7 +71,6 @@ For each problem, OpenHands is given a set number of iterations to fix the faili
                 "observation": "run",
                 "content": "[File: /workspace/Python__2.py (14 lines total)]\r\n1:def truncate_number(number: float) -> float:\r\n2:    return number % 1.0 + 1.0\r\n3:\r\n4:\r\n5:\r\n6:\r\n7:\r\n8:\r\n9:def check(truncate_number):\r\n10:    assert truncate_number(3.5) == 0.5\r\n11:    assert abs(truncate_number(1.33) - 0.33) < 1e-6\r\n12:    assert abs(truncate_number(123.456) - 0.456) < 1e-6\r\n13:\r\n14:check(truncate_number)",
                 "extras": {
-                    "command_id": -1,
                     "command": "open Python__2.py",
                     "exit_code": 0
                 }
@@ -98,7 +97,6 @@ For each problem, OpenHands is given a set number of iterations to fix the faili
                 "observation": "run",
                 "content": "> > [File: /workspace/Python__2.py (14 lines total)]\r\n1:def truncate_number(number: float) -> float:\r\n2:    return number % 1.0\r\n3:\r\n4:\r\n5:\r\n6:\r\n7:\r\n8:\r\n9:def check(truncate_number):\r\n10:    assert truncate_number(3.5) == 0.5\r\n11:    assert abs(truncate_number(1.33) - 0.33) < 1e-6\r\n12:    assert abs(truncate_number(123.456) - 0.456) < 1e-6\r\n13:\r\n14:check(truncate_number)\r\nFile updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.",
                 "extras": {
-                    "command_id": -1,
                     "command": "edit 2:2 <<EOF\n    return number % 1.0\nEOF",
                     "exit_code": 0
                 }
@@ -125,7 +123,6 @@ For each problem, OpenHands is given a set number of iterations to fix the faili
                 "observation": "run",
                 "content": "",
                 "extras": {
-                    "command_id": -1,
                     "command": "python3 Python__2.py",
                     "exit_code": 0
                 }

evaluation/benchmarks/humanevalfix/run_infer.py

@@ -97,6 +97,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     return config
 
 
@@ -169,9 +171,7 @@ def complete_runtime(
     num_workers = LANGUAGE_TO_NUM_WORKERS[language]
     python_imports = '\n'.join(IMPORT_HELPER[language])
 
-    action = CmdRunAction(
-        command=f'cat /workspace/{_get_instance_id(instance)}.py', keep_prompt=False
-    )
+    action = CmdRunAction(command=f'cat /workspace/{_get_instance_id(instance)}.py')
     obs = runtime.run_action(action)
     assert obs.exit_code == 0
 

evaluation/benchmarks/logic_reasoning/run_infer.py

@@ -61,6 +61,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/mint/run_infer.py

@@ -119,6 +119,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/ml_bench/run_infer.py

@@ -92,6 +92,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     return config
 
 
@@ -161,7 +163,7 @@ def complete_runtime(
     eval_script = os.path.join(task_path, 'run.sh')
     logger.info(f'Running evaluation script: {eval_script}')
 
-    action = CmdRunAction(command=f'cat {eval_script}', keep_prompt=False)
+    action = CmdRunAction(command=f'cat {eval_script}')
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     if obs.exit_code == 0:

evaluation/benchmarks/scienceagentbench/run_infer.py

@@ -121,10 +121,7 @@ def initialize_runtime(
     runtime.copy_to(dataset_dir, '/workspace/benchmark/datasets', recursive=True)
 
     # Check the dataset exists
-    action = CmdRunAction(
-        command='cd /workspace/benchmark/datasets && ls',
-        keep_prompt=False,
-    )
+    action = CmdRunAction(command='cd /workspace/benchmark/datasets && ls')
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     assert obs.exit_code == 0
@@ -154,10 +151,7 @@ def complete_runtime(
 
     assert obs.exit_code == 0
 
-    action = CmdRunAction(
-        command=f'cat pred_programs/{instance.pred_program_name}',
-        keep_prompt=False,
-    )
+    action = CmdRunAction(command=f'cat pred_programs/{instance.pred_program_name}')
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
 

evaluation/benchmarks/swe_bench/README.md

@@ -204,7 +204,7 @@ Then, in a separate Python environment with `streamlit` library, you can run the
 ```bash
 # Make sure you are inside the cloned `evaluation` repo
 conda activate streamlit # if you follow the optional conda env setup above
-streamlit app.py --server.port 8501 --server.address 0.0.0.0
+streamlit run app.py --server.port 8501 --server.address 0.0.0.0
 ```
 
 Then you can access the SWE-Bench trajectory visualizer at `localhost:8501`.

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -98,6 +98,7 @@ def process_instance(
     metadata: EvalMetadata,
     reset_logger: bool = True,
     log_dir: str | None = None,
+    runtime_failure_count: int = 0,
 ) -> EvalOutput:
     """
     Evaluate agent performance on a SWE-bench problem instance.
@@ -146,6 +147,16 @@ def process_instance(
             metadata=metadata,
         )
 
+    # Increase resource_factor with increasing attempt_id
+    if runtime_failure_count > 0:
+        config.sandbox.remote_runtime_resource_factor = min(
+            config.sandbox.remote_runtime_resource_factor * (2**runtime_failure_count),
+            4,  # hardcode maximum resource factor to 4
+        )
+        logger.warning(
+            f'This is the second attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
+        )
+
     runtime = create_runtime(config)
     call_async_from_sync(runtime.connect)
     # Get patch and save it to /tmp/patch.diff
@@ -177,7 +188,7 @@ def process_instance(
         "(patch --batch --fuzz=5 -p1 -i /tmp/patch.diff && echo 'APPLY_PATCH_PASS' || "
         "echo 'APPLY_PATCH_FAIL')))"
     )
-    action = CmdRunAction(command=exec_command, keep_prompt=False)
+    action = CmdRunAction(command=exec_command)
     action.timeout = 600
     obs = runtime.run_action(action)
     assert isinstance(obs, CmdOutputObservation)
@@ -200,9 +211,7 @@ def process_instance(
 
             # Run eval script in background and save output to log file
             log_file = '/tmp/eval_output.log'
-            action = CmdRunAction(
-                command=f'/tmp/eval.sh > {log_file} 2>&1 & echo $!', keep_prompt=False
-            )
+            action = CmdRunAction(command=f'/tmp/eval.sh > {log_file} 2>&1 & echo $!')
             action.timeout = 60  # Short timeout just to get the process ID
             obs = runtime.run_action(action)
 
@@ -224,7 +233,7 @@ def process_instance(
                         instance['test_result']['report']['test_timeout'] = True
                         break
                     check_action = CmdRunAction(
-                        command=f'ps -p {pid} > /dev/null; echo $?', keep_prompt=False
+                        command=f'ps -p {pid} > /dev/null; echo $?'
                     )
                     check_action.timeout = 60
                     check_obs = runtime.run_action(check_action)
@@ -242,7 +251,7 @@ def process_instance(
                     time.sleep(30)  # Wait for 30 seconds before checking again
 
                 # Read the log file
-                cat_action = CmdRunAction(command=f'cat {log_file}', keep_prompt=False)
+                cat_action = CmdRunAction(command=f'cat {log_file}')
                 cat_action.timeout = 300
                 cat_obs = runtime.run_action(cat_action)
 

evaluation/benchmarks/swe_bench/run_infer.py

@@ -15,6 +15,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     assert_and_raise,
     codeact_user_response,
+    get_metrics,
     is_fatal_evaluation_error,
     make_metadata,
     prepare_dataset,
@@ -148,6 +149,7 @@ def get_config(
         codeact_enable_jupyter=False,
         codeact_enable_browsing=RUN_WITH_BROWSING,
         codeact_enable_llm_editor=False,
+        condenser=metadata.condenser_config,
     )
     config.set_agent_config(agent_config)
     return config
@@ -282,6 +284,16 @@ def initialize_runtime(
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     assert_and_raise(obs.exit_code == 0, f'Failed to remove git remotes: {str(obs)}')
 
+    action = CmdRunAction(command='which python')
+    action.timeout = 600
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0 and 'testbed' in obs.content,
+        f'Expected to find python interpreter from testbed, but got: {str(obs)}',
+    )
+
     logger.info('-' * 30)
     logger.info('END Runtime Initialization Fn')
     logger.info('-' * 30)
@@ -337,8 +349,7 @@ def complete_runtime(
     git_patch = None
     while n_retries < 5:
         action = CmdRunAction(
-            command=f'git diff --no-color --cached {instance["base_commit"]}',
-            keep_prompt=False,
+            command=f'git diff --no-color --cached {instance["base_commit"]}'
         )
         action.timeout = 600 + 100 * n_retries
         logger.info(action, extra={'msg_type': 'ACTION'})
@@ -385,7 +396,7 @@ def process_instance(
     if runtime_failure_count > 0:
         config.sandbox.remote_runtime_resource_factor = min(
             config.sandbox.remote_runtime_resource_factor * (2**runtime_failure_count),
-            2,  # hardcode maximum resource factor to 2
+            8,
         )
         logger.warning(
             f'This is the second attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
@@ -439,7 +450,7 @@ def process_instance(
 
     # NOTE: this is NO LONGER the event stream, but an agent history that includes delegate agent's events
     histories = [event_to_dict(event) for event in state.history]
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
 
     # Save the output
     output = EvalOutput(
@@ -535,4 +546,5 @@ if __name__ == '__main__':
         args.eval_num_workers,
         process_instance,
         timeout_seconds=120 * 60,  # 2 hour PER instance should be more than enough
+        max_retries=5,
     )

evaluation/benchmarks/swe_bench/scripts/eval/compare_outputs.py

@@ -1,13 +1,20 @@
 #!/usr/bin/env python3
 import argparse
+import os
 
 import pandas as pd
+from termcolor import colored
 
 parser = argparse.ArgumentParser(
     description='Compare two swe_bench output JSONL files and print the resolved diff'
 )
 parser.add_argument('input_file_1', type=str)
 parser.add_argument('input_file_2', type=str)
+parser.add_argument(
+    '--show-paths',
+    action='store_true',
+    help='Show visualization paths for failed instances',
+)
 args = parser.parse_args()
 
 df1 = pd.read_json(args.input_file_1, orient='records', lines=True)
@@ -58,10 +65,60 @@ df_diff_y_only = df_diff[~df_diff['resolved_x'] & df_diff['resolved_y']].sort_va
 print(f'# y resolved but x not={df_diff_y_only.shape[0]}')
 print(df_diff_y_only[['instance_id', 'report_x', 'report_y']])
 # get instance_id from df_diff_y_only
-print('-' * 100)
-print('Instances that x resolved but y not:')
-print(df_diff_x_only['instance_id'].tolist())
+
+x_only_by_repo = {}
+for instance_id in df_diff_x_only['instance_id'].tolist():
+    repo = instance_id.split('__')[0]
+    x_only_by_repo.setdefault(repo, []).append(instance_id)
+y_only_by_repo = {}
+for instance_id in df_diff_y_only['instance_id'].tolist():
+    repo = instance_id.split('__')[0]
+    y_only_by_repo.setdefault(repo, []).append(instance_id)
 
 print('-' * 100)
-print('Instances that y resolved but x not:')
-print(df_diff_y_only['instance_id'].tolist())
+print(
+    colored('Repository comparison (x resolved vs y resolved):', 'cyan', attrs=['bold'])
+)
+all_repos = sorted(set(list(x_only_by_repo.keys()) + list(y_only_by_repo.keys())))
+
+# Calculate diffs and sort repos by diff magnitude
+repo_diffs = []
+for repo in all_repos:
+    x_count = len(x_only_by_repo.get(repo, []))
+    y_count = len(y_only_by_repo.get(repo, []))
+    diff = abs(x_count - y_count)
+    repo_diffs.append((repo, diff))
+
+# Sort by diff (descending) and then by repo name
+repo_diffs.sort(key=lambda x: (-x[1], x[0]))
+threshold = max(
+    3, sum(d[1] for d in repo_diffs) / len(repo_diffs) * 1.5 if repo_diffs else 0
+)
+
+x_input_file_folder = os.path.join(os.path.dirname(args.input_file_1), 'output.viz')
+
+for repo, diff in repo_diffs:
+    x_instances = x_only_by_repo.get(repo, [])
+    y_instances = y_only_by_repo.get(repo, [])
+
+    # Determine if this repo has a significant diff
+    is_significant = diff >= threshold
+    repo_color = 'red' if is_significant else 'yellow'
+
+    print(f"\n{colored(repo, repo_color, attrs=['bold'])}:")
+    print(colored(f'Difference: {diff} instances!', repo_color, attrs=['bold']))
+    print(colored(f'X resolved but Y failed: ({len(x_instances)} instances)', 'green'))
+    if x_instances:
+        print('  ' + str(x_instances))
+    print(colored(f'Y resolved but X failed: ({len(y_instances)} instances)', 'red'))
+    if y_instances:
+        print('  ' + str(y_instances))
+        if args.show_paths:
+            print(
+                colored('    Visualization path for X failed:', 'cyan', attrs=['bold'])
+            )
+            for instance_id in y_instances:
+                instance_file = os.path.join(
+                    x_input_file_folder, f'false.{instance_id}.md'
+                )
+                print(f'    {instance_file}')

evaluation/benchmarks/swe_bench/scripts/eval/convert_oh_output_to_md.py

@@ -20,6 +20,13 @@ output_md_folder = args.oh_output_file.replace('.jsonl', '.viz')
 print(f'Converting {args.oh_output_file} to markdown files in {output_md_folder}')
 
 oh_format = pd.read_json(args.oh_output_file, orient='records', lines=True)
+
+swebench_eval_file = args.oh_output_file.replace('.jsonl', '.swebench_eval.jsonl')
+if os.path.exists(swebench_eval_file):
+    eval_output_df = pd.read_json(swebench_eval_file, orient='records', lines=True)
+else:
+    eval_output_df = None
+
 # model name is the folder name of oh_output_file
 model_name = os.path.basename(os.path.dirname(args.oh_output_file))
 
@@ -50,7 +57,7 @@ def convert_history_to_str(history):
     return ret
 
 
-def write_row_to_md_file(row):
+def write_row_to_md_file(row, instance_id_to_test_result):
     if 'git_patch' in row:
         model_patch = row['git_patch']
     elif 'test_result' in row and 'git_patch' in row['test_result']:
@@ -58,8 +65,21 @@ def write_row_to_md_file(row):
     else:
         raise ValueError(f'Row {row} does not have a git_patch')
 
-    if 'report' in row:
-        resolved = row['report'].get('resolved', False)
+    test_output = None
+    if row['instance_id'] in instance_id_to_test_result:
+        report = instance_id_to_test_result[row['instance_id']].get('report', {})
+        resolved = report.get('resolved', False)
+        test_output = instance_id_to_test_result[row['instance_id']].get(
+            'test_output', None
+        )
+    elif 'report' in row and row['report'] is not None:
+        if not isinstance(row['report'], dict):
+            resolved = None
+            print(
+                f'ERROR: Report is not a dict, but a {type(row["report"])}. Row: {row}'
+            )
+        else:
+            resolved = row['report'].get('resolved', False)
     else:
         resolved = None
 
@@ -84,5 +104,18 @@ def write_row_to_md_file(row):
         f.write('## Model Patch\n')
         f.write(f'{process_git_patch(model_patch)}\n')
 
+        f.write('## Test Output\n')
+        f.write(str(test_output))
 
-oh_format.progress_apply(write_row_to_md_file, axis=1)
+
+instance_id_to_test_result = {}
+if eval_output_df is not None:
+    instance_id_to_test_result = (
+        eval_output_df[['instance_id', 'test_result']]
+        .set_index('instance_id')['test_result']
+        .to_dict()
+    )
+
+oh_format.progress_apply(
+    write_row_to_md_file, axis=1, instance_id_to_test_result=instance_id_to_test_result
+)

evaluation/benchmarks/swe_bench/scripts/eval/update_output_with_eval.py

@@ -111,6 +111,11 @@ elif os.path.exists(openhands_remote_report_jsonl):
         instance_id_to_status[row['instance_id']] = row['test_result']['report']
     df['report'] = df.apply(apply_report, axis=1)
 
+    report_is_dict = df['report'].apply(lambda x: isinstance(x, dict))
+    if not report_is_dict.all():
+        print(df[~report_is_dict])
+        raise ValueError(f'Report is not a dict, but a {type(row["report"])}')
+
     _n_instances = len(df)
     _n_resolved = len(df[df['report'].apply(lambda x: x.get('resolved', False))])
     _n_unresolved = _n_instances - _n_resolved

evaluation/benchmarks/toolqa/run_infer.py

@@ -56,6 +56,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/webarena/run_infer.py

@@ -77,6 +77,8 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.use_microagents = False
     return config
 
 

evaluation/integration_tests/tests/t01_fix_simple_typo.py

@@ -24,7 +24,7 @@ class Test(BaseIntegrationTest):
     @classmethod
     def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
         # check if the file /workspace/bad.txt has been fixed
-        action = CmdRunAction(command='cat /workspace/bad.txt', keep_prompt=False)
+        action = CmdRunAction(command='cat /workspace/bad.txt')
         obs = runtime.run_action(action)
         if obs.exit_code != 0:
             return TestResult(

evaluation/integration_tests/tests/t02_add_bash_hello.py

@@ -10,14 +10,14 @@ class Test(BaseIntegrationTest):
 
     @classmethod
     def initialize_runtime(cls, runtime: Runtime) -> None:
-        action = CmdRunAction(command='mkdir -p /workspace', keep_prompt=False)
+        action = CmdRunAction(command='mkdir -p /workspace')
         obs = runtime.run_action(action)
         assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
 
     @classmethod
     def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
         # check if the file /workspace/hello.sh exists
-        action = CmdRunAction(command='cat /workspace/hello.sh', keep_prompt=False)
+        action = CmdRunAction(command='cat /workspace/hello.sh')
         obs = runtime.run_action(action)
         if obs.exit_code != 0:
             return TestResult(
@@ -26,7 +26,7 @@ class Test(BaseIntegrationTest):
             )
 
         # execute the script
-        action = CmdRunAction(command='bash /workspace/hello.sh', keep_prompt=False)
+        action = CmdRunAction(command='bash /workspace/hello.sh')
         obs = runtime.run_action(action)
         if obs.exit_code != 0:
             return TestResult(

evaluation/integration_tests/tests/t03_jupyter_write_file.py

@@ -10,14 +10,14 @@ class Test(BaseIntegrationTest):
 
     @classmethod
     def initialize_runtime(cls, runtime: Runtime) -> None:
-        action = CmdRunAction(command='mkdir -p /workspace', keep_prompt=False)
+        action = CmdRunAction(command='mkdir -p /workspace')
         obs = runtime.run_action(action)
         assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
 
     @classmethod
     def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
         # check if the file /workspace/hello.sh exists
-        action = CmdRunAction(command='cat /workspace/test.txt', keep_prompt=False)
+        action = CmdRunAction(command='cat /workspace/test.txt')
         obs = runtime.run_action(action)
         if obs.exit_code != 0:
             return TestResult(
@@ -26,7 +26,7 @@ class Test(BaseIntegrationTest):
             )
 
         # execute the script
-        action = CmdRunAction(command='cat /workspace/test.txt', keep_prompt=False)
+        action = CmdRunAction(command='cat /workspace/test.txt')
         obs = runtime.run_action(action)
 
         if obs.exit_code != 0:

evaluation/integration_tests/tests/t04_git_staging.py

@@ -10,31 +10,29 @@ class Test(BaseIntegrationTest):
 
     @classmethod
     def initialize_runtime(cls, runtime: Runtime) -> None:
-        action = CmdRunAction(command='mkdir -p /workspace', keep_prompt=False)
+        action = CmdRunAction(command='mkdir -p /workspace')
         obs = runtime.run_action(action)
         assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
 
         # git init
-        action = CmdRunAction(command='git init', keep_prompt=False)
+        action = CmdRunAction(command='git init')
         obs = runtime.run_action(action)
         assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
 
         # create README.md
-        action = CmdRunAction(
-            command='echo \'print("hello world")\' > hello.py', keep_prompt=False
-        )
+        action = CmdRunAction(command='echo \'print("hello world")\' > hello.py')
         obs = runtime.run_action(action)
         assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
 
         # git add README.md
-        action = CmdRunAction(command='git add hello.py', keep_prompt=False)
+        action = CmdRunAction(command='git add hello.py')
         obs = runtime.run_action(action)
         assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
 
     @classmethod
     def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
         # check if the file /workspace/hello.py exists
-        action = CmdRunAction(command='cat /workspace/hello.py', keep_prompt=False)
+        action = CmdRunAction(command='cat /workspace/hello.py')
         obs = runtime.run_action(action)
         if obs.exit_code != 0:
             return TestResult(
@@ -43,7 +41,7 @@ class Test(BaseIntegrationTest):
             )
 
         # check if the staging area is empty
-        action = CmdRunAction(command='git status', keep_prompt=False)
+        action = CmdRunAction(command='git status')
         obs = runtime.run_action(action)
         if obs.exit_code != 0:
             return TestResult(

evaluation/integration_tests/tests/t05_simple_browsing.py

@@ -83,11 +83,11 @@ class Test(BaseIntegrationTest):
 
     @classmethod
     def initialize_runtime(cls, runtime: Runtime) -> None:
-        action = CmdRunAction(command='mkdir -p /workspace', keep_prompt=False)
+        action = CmdRunAction(command='mkdir -p /workspace')
         obs = runtime.run_action(action)
         assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
 
-        action = CmdRunAction(command='mkdir -p /tmp/server', keep_prompt=False)
+        action = CmdRunAction(command='mkdir -p /tmp/server')
         obs = runtime.run_action(action)
         assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
 
@@ -101,8 +101,7 @@ class Test(BaseIntegrationTest):
 
         # create README.md
         action = CmdRunAction(
-            command='cd /tmp/server && nohup python3 -m http.server 8000 &',
-            keep_prompt=False,
+            command='cd /tmp/server && nohup python3 -m http.server 8000 &'
         )
         obs = runtime.run_action(action)
 

evaluation/utils/shared.py

@@ -17,6 +17,10 @@ from tqdm import tqdm
 
 from openhands.controller.state.state import State
 from openhands.core.config import LLMConfig
+from openhands.core.config.condenser_config import (
+    CondenserConfig,
+    NoOpCondenserConfig,
+)
 from openhands.core.exceptions import (
     AgentRuntimeBuildError,
     AgentRuntimeDisconnectedError,
@@ -33,6 +37,7 @@ from openhands.events.action.message import MessageAction
 from openhands.events.event import Event
 from openhands.events.serialization.event import event_to_dict
 from openhands.events.utils import get_pairs_from_events
+from openhands.memory.condenser import get_condensation_metadata
 
 
 class EvalMetadata(BaseModel):
@@ -45,11 +50,17 @@ class EvalMetadata(BaseModel):
     dataset: str | None = None
     data_split: str | None = None
     details: dict[str, Any] | None = None
+    condenser_config: CondenserConfig | None = None
 
     def model_dump(self, *args, **kwargs):
         dumped_dict = super().model_dump(*args, **kwargs)
         # avoid leaking sensitive information
         dumped_dict['llm_config'] = self.llm_config.to_safe_dict()
+        if hasattr(self.condenser_config, 'llm_config'):
+            dumped_dict['condenser_config']['llm_config'] = (
+                self.condenser_config.llm_config.to_safe_dict()
+            )
+
         return dumped_dict
 
     def model_dump_json(self, *args, **kwargs):
@@ -57,6 +68,11 @@ class EvalMetadata(BaseModel):
         dumped_dict = json.loads(dumped)
         # avoid leaking sensitive information
         dumped_dict['llm_config'] = self.llm_config.to_safe_dict()
+        if hasattr(self.condenser_config, 'llm_config'):
+            dumped_dict['condenser_config']['llm_config'] = (
+                self.condenser_config.llm_config.to_safe_dict()
+            )
+
         logger.debug(f'Dumped metadata: {dumped_dict}')
         return json.dumps(dumped_dict)
 
@@ -192,6 +208,7 @@ def make_metadata(
     eval_output_dir: str,
     data_split: str | None = None,
     details: dict[str, Any] | None = None,
+    condenser_config: CondenserConfig | None = None,
 ) -> EvalMetadata:
     model_name = llm_config.model.split('/')[-1]
     model_path = model_name.replace(':', '_').replace('@', '-')
@@ -222,6 +239,9 @@ def make_metadata(
         dataset=dataset_name,
         data_split=data_split,
         details=details,
+        condenser_config=condenser_config
+        if condenser_config
+        else NoOpCondenserConfig(),
     )
     metadata_json = metadata.model_dump_json()
     logger.info(f'Metadata: {metadata_json}')
@@ -376,7 +396,12 @@ def _process_instance_wrapper(
                 + '\n'
             )
             if isinstance(
-                e, (AgentRuntimeDisconnectedError, AgentRuntimeUnavailableError)
+                e,
+                (
+                    AgentRuntimeDisconnectedError,
+                    AgentRuntimeUnavailableError,
+                    AgentRuntimeNotFoundError,
+                ),
             ):
                 runtime_failure_count += 1
                 msg += f'Runtime disconnected error detected for instance {instance.instance_id}, runtime failure count: {runtime_failure_count}'
@@ -546,3 +571,10 @@ def is_fatal_evaluation_error(error: str | None) -> bool:
         return True
 
     return False
+
+
+def get_metrics(state: State) -> dict[str, Any]:
+    """Extract metrics from the state."""
+    metrics = state.metrics.get() if state.metrics else {}
+    metrics['condenser'] = get_condensation_metadata(state)
+    return metrics

frontend/.eslintrc

@@ -73,6 +73,7 @@
             }
           }
         ],
+        "react/prop-types": "off",
         "react/no-array-index-key": "off",
         "react-hooks/exhaustive-deps": "off",
         "import/no-extraneous-dependencies": "off",

frontend/__tests__/components/chat/chat-input.test.tsx

@@ -218,4 +218,30 @@ describe("ChatInput", () => {
     // Verify image paste was handled
     expect(onImagePaste).toHaveBeenCalledWith([file]);
   });
+
+  it("should not submit when Enter is pressed during IME composition", async () => {
+    const user = userEvent.setup();
+    render(<ChatInput onSubmit={onSubmitMock} />);
+    const textarea = screen.getByRole("textbox");
+
+    await user.type(textarea, "こんにちは");
+
+    // Simulate Enter during IME composition
+    fireEvent.keyDown(textarea, {
+      key: "Enter",
+      isComposing: true,
+      nativeEvent: { isComposing: true },
+    });
+
+    expect(onSubmitMock).not.toHaveBeenCalled();
+
+    // Simulate normal Enter after composition is done
+    fireEvent.keyDown(textarea, {
+      key: "Enter",
+      isComposing: false,
+      nativeEvent: { isComposing: false },
+    });
+
+    expect(onSubmitMock).toHaveBeenCalledWith("こんにちは");
+  });
 });

frontend/__tests__/components/features/conversation-panel/conversation-card.test.tsx

@@ -3,6 +3,7 @@ import { afterEach, describe, expect, it, test, vi } from "vitest";
 import userEvent from "@testing-library/user-event";
 import { formatTimeDelta } from "#/utils/format-time-delta";
 import { ConversationCard } from "#/components/features/conversation-panel/conversation-card";
+import { clickOnEditButton } from "./utils";
 
 describe("ConversationCard", () => {
   const onClick = vi.fn();
@@ -19,9 +20,9 @@ describe("ConversationCard", () => {
         onDelete={onDelete}
         onClick={onClick}
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
     const expectedDate = `${formatTimeDelta(new Date("2021-10-01T12:00:00Z"))} ago`;
@@ -33,20 +34,20 @@ describe("ConversationCard", () => {
     within(card).getByText(expectedDate);
   });
 
-  it("should render the repo if available", () => {
+  it("should render the selectedRepository if available", () => {
     const { rerender } = render(
       <ConversationCard
         onDelete={onDelete}
         onClick={onClick}
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
 
     expect(
-      screen.queryByTestId("conversation-card-repo"),
+      screen.queryByTestId("conversation-card-selected-repository"),
     ).not.toBeInTheDocument();
 
     rerender(
@@ -54,13 +55,13 @@ describe("ConversationCard", () => {
         onDelete={onDelete}
         onClick={onClick}
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo="org/repo"
-        lastUpdated="2021-10-01T12:00:00Z"
+        title="Conversation 1"
+        selectedRepository="org/selectedRepository"
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
 
-    screen.getByTestId("conversation-card-repo");
+    screen.getByTestId("conversation-card-selected-repository");
   });
 
   it("should call onClick when the card is clicked", async () => {
@@ -70,9 +71,9 @@ describe("ConversationCard", () => {
         onDelete={onDelete}
         onClick={onClick}
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
 
@@ -89,9 +90,9 @@ describe("ConversationCard", () => {
         onDelete={onDelete}
         onClick={onClick}
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
 
@@ -114,9 +115,9 @@ describe("ConversationCard", () => {
         onClick={onClick}
         onDelete={onDelete}
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
 
@@ -131,21 +132,23 @@ describe("ConversationCard", () => {
     expect(onDelete).toHaveBeenCalled();
   });
 
-  test("clicking the repo should not trigger the onClick handler", async () => {
+  test("clicking the selectedRepository should not trigger the onClick handler", async () => {
     const user = userEvent.setup();
     render(
       <ConversationCard
         onClick={onClick}
         onDelete={onDelete}
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo="org/repo"
-        lastUpdated="2021-10-01T12:00:00Z"
+        title="Conversation 1"
+        selectedRepository="org/selectedRepository"
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
 
-    const repo = screen.getByTestId("conversation-card-repo");
-    await user.click(repo);
+    const selectedRepository = screen.getByTestId(
+      "conversation-card-selected-repository",
+    );
+    await user.click(selectedRepository);
 
     expect(onClick).not.toHaveBeenCalled();
   });
@@ -156,14 +159,22 @@ describe("ConversationCard", () => {
       <ConversationCard
         onClick={onClick}
         onDelete={onDelete}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
         onChangeTitle={onChangeTitle}
       />,
     );
 
     const title = screen.getByTestId("conversation-card-title");
+    expect(title).toBeDisabled();
+
+    await clickOnEditButton(user);
+
+    expect(title).toBeEnabled();
+    expect(screen.queryByTestId("context-menu")).not.toBeInTheDocument();
+    // expect to be focused
+    expect(document.activeElement).toBe(title);
 
     await user.clear(title);
     await user.type(title, "New Conversation Name   ");
@@ -171,6 +182,7 @@ describe("ConversationCard", () => {
 
     expect(onChangeTitle).toHaveBeenCalledWith("New Conversation Name");
     expect(title).toHaveValue("New Conversation Name");
+    expect(title).toBeDisabled();
   });
 
   it("should reset title and not call onChangeTitle when the title is empty", async () => {
@@ -180,12 +192,14 @@ describe("ConversationCard", () => {
         onClick={onClick}
         onDelete={onDelete}
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
 
+    await clickOnEditButton(user);
+
     const title = screen.getByTestId("conversation-card-title");
 
     await user.clear(title);
@@ -202,9 +216,9 @@ describe("ConversationCard", () => {
         onClick={onClick}
         onDelete={onDelete}
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
 
@@ -221,9 +235,9 @@ describe("ConversationCard", () => {
         onClick={onClick}
         onDelete={onDelete}
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
 
@@ -239,19 +253,19 @@ describe("ConversationCard", () => {
   });
 
   describe("state indicator", () => {
-    it("should render the 'cold' indicator by default", () => {
+    it("should render the 'STOPPED' indicator by default", () => {
       render(
         <ConversationCard
           onClick={onClick}
           onDelete={onDelete}
           onChangeTitle={onChangeTitle}
-          name="Conversation 1"
-          repo={null}
-          lastUpdated="2021-10-01T12:00:00Z"
+          title="Conversation 1"
+          selectedRepository={null}
+          lastUpdatedAt="2021-10-01T12:00:00Z"
         />,
       );
 
-      screen.getByTestId("cold-indicator");
+      screen.getByTestId("STOPPED-indicator");
     });
 
     it("should render the other indicators when provided", () => {
@@ -260,15 +274,15 @@ describe("ConversationCard", () => {
           onClick={onClick}
           onDelete={onDelete}
           onChangeTitle={onChangeTitle}
-          name="Conversation 1"
-          repo={null}
-          lastUpdated="2021-10-01T12:00:00Z"
-          state="warm"
+          title="Conversation 1"
+          selectedRepository={null}
+          lastUpdatedAt="2021-10-01T12:00:00Z"
+          status="RUNNING"
         />,
       );
 
-      expect(screen.queryByTestId("cold-indicator")).not.toBeInTheDocument();
-      screen.getByTestId("warm-indicator");
+      expect(screen.queryByTestId("STOPPED-indicator")).not.toBeInTheDocument();
+      screen.getByTestId("RUNNING-indicator");
     });
   });
 });

frontend/__tests__/components/features/conversation-panel/conversation-panel.test.tsx

@@ -9,6 +9,7 @@ import userEvent from "@testing-library/user-event";
 import { ConversationPanel } from "#/components/features/conversation-panel/conversation-panel";
 import OpenHands from "#/api/open-hands";
 import { AuthProvider } from "#/context/auth-context";
+import { clickOnEditButton } from "./utils";
 
 describe("ConversationPanel", () => {
   const onCloseMock = vi.fn();
@@ -52,6 +53,8 @@ describe("ConversationPanel", () => {
     renderConversationPanel();
     const cards = await screen.findAllByTestId("conversation-card");
 
+    // NOTE that we filter out conversations that don't have a created_at property
+    // (mock data has 4 conversations, but only 3 have a created_at property)
     expect(cards).toHaveLength(3);
   });
 
@@ -169,13 +172,15 @@ describe("ConversationPanel", () => {
     const cards = await screen.findAllByTestId("conversation-card");
     const title = within(cards[0]).getByTestId("conversation-card-title");
 
+    await clickOnEditButton(user);
+
     await user.clear(title);
     await user.type(title, "Conversation 1 Renamed");
     await user.tab();
 
     // Ensure the conversation is renamed
     expect(updateUserConversationSpy).toHaveBeenCalledWith("3", {
-      name: "Conversation 1 Renamed",
+      title: "Conversation 1 Renamed",
     });
   });
 
@@ -196,6 +201,8 @@ describe("ConversationPanel", () => {
     // Ensure the conversation is not renamed
     expect(updateUserConversationSpy).not.toHaveBeenCalled();
 
+    await clickOnEditButton(user);
+
     await user.type(title, "Conversation 1");
     await user.click(title);
     await user.tab();
@@ -217,51 +224,4 @@ describe("ConversationPanel", () => {
 
     expect(onCloseMock).toHaveBeenCalledOnce();
   });
-
-  describe("New Conversation Button", () => {
-    it("should display a confirmation modal when clicking", async () => {
-      const user = userEvent.setup();
-      renderConversationPanel();
-
-      expect(
-        screen.queryByTestId("confirm-new-conversation-modal"),
-      ).not.toBeInTheDocument();
-
-      const newProjectButton = screen.getByTestId("new-conversation-button");
-      await user.click(newProjectButton);
-
-      const modal = screen.getByTestId("confirm-new-conversation-modal");
-      expect(modal).toBeInTheDocument();
-    });
-
-    it("should call endSession and close panel after confirming", async () => {
-      const user = userEvent.setup();
-      renderConversationPanel();
-
-      const newProjectButton = screen.getByTestId("new-conversation-button");
-      await user.click(newProjectButton);
-
-      const confirmButton = screen.getByText("Confirm");
-      await user.click(confirmButton);
-
-      expect(endSessionMock).toHaveBeenCalledOnce();
-      expect(onCloseMock).toHaveBeenCalledOnce();
-    });
-
-    it("should close the modal when cancelling", async () => {
-      const user = userEvent.setup();
-      renderConversationPanel();
-
-      const newProjectButton = screen.getByTestId("new-conversation-button");
-      await user.click(newProjectButton);
-
-      const cancelButton = screen.getByText("Cancel");
-      await user.click(cancelButton);
-
-      expect(endSessionMock).not.toHaveBeenCalled();
-      expect(
-        screen.queryByTestId("confirm-new-conversation-modal"),
-      ).not.toBeInTheDocument();
-    });
-  });
 });

frontend/__tests__/components/features/conversation-panel/utils.ts

@@ -0,0 +1,12 @@
+import { screen, within } from "@testing-library/react";
+import { UserEvent } from "@testing-library/user-event";
+
+export const clickOnEditButton = async (user: UserEvent) => {
+  const ellipsisButton = screen.getByTestId("ellipsis-button");
+  await user.click(ellipsisButton);
+
+  const menu = screen.getByTestId("context-menu");
+  const editButton = within(menu).getByTestId("edit-button");
+
+  await user.click(editButton);
+};

frontend/__tests__/components/features/github/github-repo-selector.test.tsx

@@ -0,0 +1,79 @@
+import { screen } from "@testing-library/react";
+import { describe, expect, it, vi } from "vitest";
+import { renderWithProviders } from "test-utils";
+import { GitHubRepositorySelector } from "#/components/features/github/github-repo-selector";
+import OpenHands from "#/api/open-hands";
+import * as GitHubAPI from "#/api/github";
+
+describe("GitHubRepositorySelector", () => {
+  const onInputChangeMock = vi.fn();
+  const onSelectMock = vi.fn();
+
+  it("should render the search input", () => {
+    renderWithProviders(
+      <GitHubRepositorySelector
+        onInputChange={onInputChangeMock}
+        onSelect={onSelectMock}
+        publicRepositories={[]}
+        userRepositories={[]}
+      />,
+    );
+
+    expect(
+      screen.getByPlaceholderText("Select a GitHub project"),
+    ).toBeInTheDocument();
+  });
+
+  it("should show the GitHub login button in OSS mode", () => {
+    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+    getConfigSpy.mockResolvedValue({
+      APP_MODE: "oss",
+      APP_SLUG: "openhands",
+      GITHUB_CLIENT_ID: "test-client-id",
+      POSTHOG_CLIENT_KEY: "test-posthog-key",
+    });
+
+    renderWithProviders(
+      <GitHubRepositorySelector
+        onInputChange={onInputChangeMock}
+        onSelect={onSelectMock}
+        publicRepositories={[]}
+        userRepositories={[]}
+      />,
+    );
+
+    expect(screen.getByTestId("github-repo-selector")).toBeInTheDocument();
+  });
+
+  it("should show the search results", () => {
+    const mockSearchedRepos = [
+      {
+        id: 1,
+        full_name: "test/repo1",
+        stargazers_count: 100,
+      },
+      {
+        id: 2,
+        full_name: "test/repo2",
+        stargazers_count: 200,
+      },
+    ];
+
+    const searchPublicRepositoriesSpy = vi.spyOn(
+      GitHubAPI,
+      "searchPublicRepositories",
+    );
+    searchPublicRepositoriesSpy.mockResolvedValue(mockSearchedRepos);
+
+    renderWithProviders(
+      <GitHubRepositorySelector
+        onInputChange={onInputChangeMock}
+        onSelect={onSelectMock}
+        publicRepositories={[]}
+        userRepositories={[]}
+      />,
+    );
+
+    expect(screen.getByTestId("github-repo-selector")).toBeInTheDocument();
+  });
+});

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

@@ -4,7 +4,7 @@ import { describe, expect, it } from "vitest";
 import { renderWithProviders } from "test-utils";
 import { createRoutesStub } from "react-router";
 import { Sidebar } from "#/components/features/sidebar/sidebar";
-import { MULTI_CONVO_UI_IS_ENABLED } from "#/utils/constants";
+import { MULTI_CONVERSATION_UI } from "#/utils/feature-flags";
 
 const renderSidebar = () => {
   const RouterStub = createRoutesStub([
@@ -18,7 +18,7 @@ const renderSidebar = () => {
 };
 
 describe("Sidebar", () => {
-  it.skipIf(!MULTI_CONVO_UI_IS_ENABLED)(
+  it.skipIf(!MULTI_CONVERSATION_UI)(
     "should have the conversation panel open by default",
     () => {
       renderSidebar();
@@ -26,7 +26,7 @@ describe("Sidebar", () => {
     },
   );
 
-  it.skipIf(!MULTI_CONVO_UI_IS_ENABLED)(
+  it.skipIf(!MULTI_CONVERSATION_UI)(
     "should toggle the conversation panel",
     async () => {
       const user = userEvent.setup();

frontend/__tests__/components/shared/modals/settings/runtime-size-selector.test.tsx

@@ -0,0 +1,35 @@
+import { screen } from "@testing-library/react";
+import { describe, it, expect } from "vitest";
+import { renderWithProviders } from "test-utils";
+import { RuntimeSizeSelector } from "#/components/shared/modals/settings/runtime-size-selector";
+
+const renderRuntimeSizeSelector = () =>
+  renderWithProviders(<RuntimeSizeSelector isDisabled={false} />);
+
+describe("RuntimeSizeSelector", () => {
+  it("should show both runtime size options", () => {
+    renderRuntimeSizeSelector();
+    // The options are in the hidden select element
+    const select = screen.getByRole("combobox", { hidden: true });
+    expect(select).toHaveValue("1");
+    expect(select).toHaveDisplayValue("1x (2 core, 8G)");
+    expect(select.children).toHaveLength(3); // Empty option + 2 size options
+  });
+
+  it("should show the full description text for disabled options", async () => {
+    renderRuntimeSizeSelector();
+
+    // Click the button to open the dropdown
+    const button = screen.getByRole("button", {
+      name: "1x (2 core, 8G) SETTINGS_FORM$RUNTIME_SIZE_LABEL",
+    });
+    button.click();
+
+    // Wait for the dropdown to open and find the description text
+    const description = await screen.findByText(
+      "Runtime sizes over 1 are disabled by default, please contact contact@all-hands.dev to get access to larger runtimes.",
+    );
+    expect(description).toBeInTheDocument();
+    expect(description).toHaveClass("whitespace-normal", "break-words");
+  });
+});

frontend/__tests__/components/shared/modals/settings/settings-form.test.tsx

@@ -0,0 +1,45 @@
+import { screen, fireEvent } from "@testing-library/react";
+import { describe, it, expect, vi } from "vitest";
+import { renderWithProviders } from "test-utils";
+import { createRoutesStub } from "react-router";
+import { DEFAULT_SETTINGS } from "#/services/settings";
+import { SettingsForm } from "#/components/shared/modals/settings/settings-form";
+import OpenHands from "#/api/open-hands";
+
+describe("SettingsForm", () => {
+  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+  getConfigSpy.mockResolvedValue({
+    APP_MODE: "saas",
+    GITHUB_CLIENT_ID: "123",
+    POSTHOG_CLIENT_KEY: "123",
+  });
+
+  const RouterStub = createRoutesStub([
+    {
+      Component: () => (
+        <SettingsForm
+          settings={DEFAULT_SETTINGS}
+          models={[]}
+          agents={[]}
+          securityAnalyzers={[]}
+          onClose={() => {}}
+        />
+      ),
+      path: "/",
+    },
+  ]);
+
+  it("should not show runtime size selector by default", () => {
+    renderWithProviders(<RouterStub />);
+    expect(screen.queryByText("Runtime Size")).not.toBeInTheDocument();
+  });
+
+  it("should show runtime size selector when advanced options are enabled", async () => {
+    renderWithProviders(<RouterStub />);
+    const advancedSwitch = screen.getByRole("switch", {
+      name: "SETTINGS_FORM$ADVANCED_OPTIONS_LABEL",
+    });
+    fireEvent.click(advancedSwitch);
+    await screen.findByText("SETTINGS_FORM$RUNTIME_SIZE_LABEL");
+  });
+});

frontend/__tests__/context/ws-client-provider.test.tsx

@@ -0,0 +1,30 @@
+import { describe, it, expect, vi } from "vitest";
+import { render, screen } from "@testing-library/react";
+import * as ChatSlice from "#/state/chat-slice";
+import {
+  updateStatusWhenErrorMessagePresent,
+} from "#/context/ws-client-provider";
+
+describe("Propagate error message", () => {
+  it("should do nothing when no message was passed from server", () => {
+    const addErrorMessageSpy = vi.spyOn(ChatSlice, "addErrorMessage");
+    updateStatusWhenErrorMessagePresent(null)
+    updateStatusWhenErrorMessagePresent(undefined)
+    updateStatusWhenErrorMessagePresent({})
+    updateStatusWhenErrorMessagePresent({message: null})
+
+    expect(addErrorMessageSpy).not.toHaveBeenCalled();
+  });
+
+  it("should display error to user when present", () => {
+    const message = "We have a problem!"
+    const addErrorMessageSpy = vi.spyOn(ChatSlice, "addErrorMessage")
+    updateStatusWhenErrorMessagePresent({message})
+
+    expect(addErrorMessageSpy).toHaveBeenCalledWith({
+      message,
+      status_update: true,
+      type: 'error'
+     });
+  });
+});

frontend/__tests__/routes/_oh.app.test.tsx

@@ -5,7 +5,7 @@ import { screen, waitFor } from "@testing-library/react";
 import toast from "react-hot-toast";
 import App from "#/routes/_oh.app/route";
 import OpenHands from "#/api/open-hands";
-import { MULTI_CONVO_UI_IS_ENABLED } from "#/utils/constants";
+import { MULTI_CONVERSATION_UI } from "#/utils/feature-flags";
 
 describe("App", () => {
   const RouteStub = createRoutesStub([
@@ -35,7 +35,7 @@ describe("App", () => {
     await screen.findByTestId("app-route");
   });
 
-  it.skipIf(!MULTI_CONVO_UI_IS_ENABLED)(
+  it.skipIf(!MULTI_CONVERSATION_UI)(
     "should call endSession if the user does not have permission to view conversation",
     async () => {
       const errorToastSpy = vi.spyOn(toast, "error");
@@ -59,10 +59,11 @@ describe("App", () => {
 
     getConversationSpy.mockResolvedValue({
       conversation_id: "9999",
-      lastUpdated: "",
-      name: "",
-      repo: "",
-      state: "cold",
+      last_updated_at: "",
+      created_at: "",
+      title: "",
+      selected_repository: "",
+      status: "STOPPED",
     });
     const { rerender } = renderWithProviders(
       <RouteStub initialEntries={["/conversation/9999"]} />,

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.17.0",
+  "version": "0.19.0",
   "private": true,
   "type": "module",
   "engines": {
@@ -8,32 +8,32 @@
   },
   "dependencies": {
     "@monaco-editor/react": "^4.7.0-rc.0",
-    "@nextui-org/react": "^2.6.10",
+    "@nextui-org/react": "^2.6.11",
     "@react-router/node": "^7.1.1",
     "@react-router/serve": "^7.1.1",
     "@react-types/shared": "^3.25.0",
     "@reduxjs/toolkit": "^2.5.0",
-    "@tanstack/react-query": "^5.62.11",
+    "@tanstack/react-query": "^5.63.0",
     "@vitejs/plugin-react": "^4.3.2",
     "@xterm/addon-fit": "^0.10.0",
     "@xterm/xterm": "^5.4.0",
     "axios": "^1.7.9",
     "clsx": "^2.1.1",
     "eslint-config-airbnb-typescript": "^18.0.0",
-    "i18next": "^24.2.0",
+    "i18next": "^24.2.1",
     "i18next-browser-languagedetector": "^8.0.2",
     "i18next-http-backend": "^3.0.1",
-    "isbot": "^5.1.19",
+    "isbot": "^5.1.20",
     "jose": "^5.9.4",
     "monaco-editor": "^0.52.2",
-    "posthog-js": "^1.203.2",
+    "posthog-js": "^1.205.0",
     "react": "^19.0.0",
     "react-dom": "^19.0.0",
     "react-highlight": "^0.15.0",
-    "react-hot-toast": "^2.4.1",
+    "react-hot-toast": "^2.5.1",
     "react-i18next": "^15.4.0",
     "react-icons": "^5.4.0",
-    "react-markdown": "^9.0.1",
+    "react-markdown": "^9.0.3",
     "react-redux": "^9.2.0",
     "react-router": "^7.1.1",
     "react-syntax-highlighter": "^15.6.1",
@@ -78,13 +78,13 @@
     "@mswjs/socket.io-binding": "^0.1.1",
     "@playwright/test": "^1.49.1",
     "@react-router/dev": "^7.1.1",
-    "@tailwindcss/typography": "^0.5.15",
-    "@tanstack/eslint-plugin-query": "^5.62.9",
+    "@tailwindcss/typography": "^0.5.16",
+    "@tanstack/eslint-plugin-query": "^5.62.16",
     "@testing-library/jest-dom": "^6.6.1",
     "@testing-library/react": "^16.1.0",
     "@testing-library/user-event": "^14.5.2",
-    "@types/node": "^22.10.2",
-    "@types/react": "^19.0.2",
+    "@types/node": "^22.10.5",
+    "@types/react": "^19.0.3",
     "@types/react-dom": "^19.0.2",
     "@types/react-highlight": "^0.12.8",
     "@types/react-syntax-highlighter": "^15.5.13",
@@ -110,7 +110,7 @@
     "postcss": "^8.4.47",
     "prettier": "^3.4.2",
     "tailwindcss": "^3.4.17",
-    "typescript": "^5.6.3",
+    "typescript": "^5.7.2",
     "vite-plugin-svgr": "^4.2.0",
     "vite-tsconfig-paths": "^5.1.4",
     "vitest": "^1.6.0"

frontend/src/api/github.ts

@@ -104,6 +104,26 @@ export const retrieveGitHubUser = async () => {
   return user;
 };
 
+export const searchPublicRepositories = async (
+  query: string,
+  per_page = 5,
+  sort: "" | "updated" | "stars" | "forks" = "stars",
+  order: "desc" | "asc" = "desc",
+): Promise<GitHubRepository[]> => {
+  const response = await github.get<{ items: GitHubRepository[] }>(
+    "/search/repositories",
+    {
+      params: {
+        q: query,
+        per_page,
+        sort,
+        order,
+      },
+    },
+  );
+  return response.data.items;
+};
+
 export const retrieveLatestGitHubCommit = async (
   repository: string,
 ): Promise<GitHubCommit | null> => {

frontend/src/api/open-hands.ts

@@ -9,6 +9,7 @@ import {
   GetVSCodeUrlResponse,
   AuthenticateResponse,
   Conversation,
+  ResultSet,
 } from "./open-hands.types";
 import { openHands } from "./open-hands-axios";
 import { ApiSettings } from "#/services/settings";
@@ -222,8 +223,10 @@ class OpenHands {
   }
 
   static async getUserConversations(): Promise<Conversation[]> {
-    const { data } = await openHands.get<Conversation[]>("/api/conversations");
-    return data;
+    const { data } = await openHands.get<ResultSet<Conversation>>(
+      "/api/conversations?limit=9",
+    );
+    return data.results;
   }
 
   static async deleteUserConversation(conversationId: string): Promise<void> {
@@ -232,9 +235,9 @@ class OpenHands {
 
   static async updateUserConversation(
     conversationId: string,
-    conversation: Partial<Omit<Conversation, "id">>,
+    conversation: Partial<Omit<Conversation, "conversation_id">>,
   ): Promise<void> {
-    await openHands.put(`/api/conversations/${conversationId}`, conversation);
+    await openHands.patch(`/api/conversations/${conversationId}`, conversation);
   }
 
   static async createConversation(

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

@@ -1,4 +1,4 @@
-import { ProjectState } from "#/components/features/conversation-panel/conversation-state-indicator";
+import { ProjectStatus } from "#/components/features/conversation-panel/conversation-state-indicator";
 
 export interface ErrorResponse {
   error: string;
@@ -62,8 +62,14 @@ export interface AuthenticateResponse {
 
 export interface Conversation {
   conversation_id: string;
-  name: string;
-  repo: string | null;
-  lastUpdated: string;
-  state: ProjectState;
+  title: string;
+  selected_repository: string | null;
+  last_updated_at: string;
+  created_at: string;
+  status: ProjectStatus;
+}
+
+export interface ResultSet<T> {
+  results: T[];
+  next_page_id: string | null;
 }