fix: Pass base commit to send_pull_request to ensure consistent repository state

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

.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/openhands-resolver.yml

@@ -259,16 +259,19 @@ jobs:
           LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
           PYTHONPATH: ""
         run: |
+          cd /tmp && BASE_COMMIT=$(cd repo && git rev-parse HEAD) && \
           if [ "${{ steps.check_result.outputs.RESOLUTION_SUCCESS }}" == "true" ]; then
-            cd /tmp && python -m openhands.resolver.send_pull_request \
+            python -m openhands.resolver.send_pull_request \
               --issue-number ${{ env.ISSUE_NUMBER }} \
               --pr-type draft \
-              --reviewer ${{ github.actor }} | tee pr_result.txt && \
+              --reviewer ${{ github.actor }} \
+              --base-commit "$BASE_COMMIT" | tee pr_result.txt && \
               grep "draft created" pr_result.txt | sed 's/.*\///g' > pr_number.txt
           else
-            cd /tmp && python -m openhands.resolver.send_pull_request \
+            python -m openhands.resolver.send_pull_request \
               --issue-number ${{ env.ISSUE_NUMBER }} \
               --pr-type branch \
+              --base-commit "$BASE_COMMIT" \
               --send-on-failure | tee branch_result.txt && \
               grep "branch created" branch_result.txt | sed 's/.*\///g; s/.expand=1//g' > branch_name.txt
           fi

.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

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:0.18-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:0.18-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:0.18-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:0.18
+    docker.all-hands.dev/all-hands-ai/openhands:0.19
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!

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:0.18-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

@@ -198,6 +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 = ""
 
@@ -210,6 +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/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:0.18-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/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:0.18-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:0.18 \
+    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:0.18-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:0.18 \
+    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:0.18-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:0.18-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:0.18
+    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:0.18-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:0.18-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:0.18 \
+    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:0.18-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:0.18 \
+    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:0.18-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:0.18-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:0.18
+    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:0.18-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/how-to/cli-mode.md

@@ -35,7 +35,7 @@ To run OpenHands in CLI mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-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=$LLM_API_KEY \
@@ -45,7 +45,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.19 \
     python -m openhands.core.cli
 ```
 

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

@@ -32,7 +32,7 @@ To run OpenHands in Headless mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-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=$LLM_API_KEY \
@@ -43,7 +43,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.19 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/modules/usage/installation.mdx

@@ -11,17 +11,17 @@
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.18-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:0.18-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:0.18
+    docker.all-hands.dev/all-hands-ai/openhands:0.19
 ```
 
 You'll find OpenHands running at http://localhost:3000!

docs/modules/usage/llms/llms.md

@@ -5,23 +5,14 @@ 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).
-
-When choosing a model, consider both the quality of outputs and the associated costs. Here's a summary of the findings:
-
-- Claude 3.5 Sonnet is the best by a fair amount, achieving a 53% resolve rate on SWE-Bench Verified with the default agent in OpenHands.
-- GPT-4o lags behind, and o1-mini actually performed somewhat worse than GPT-4o. We went in and analyzed the results a little, and briefly it seemed like o1 was sometimes "overthinking" things, performing extra environment configuration tasks when it could just go ahead and finish the task.
-- Finally, the strongest open models were Llama 3.1 405 B and deepseek-v2.5, and they performed reasonably, even besting some of the closed models.
-
-Please refer to the [full article](https://www.all-hands.dev/blog/evaluation-of-llms-as-coding-agents-on-swe-bench-at-30x-speed) for more details.
+recommendations for model selection. Our latest benchmarking results can be found in [this spreadsheet](https://docs.google.com/spreadsheets/d/1wOUdFCMyY6Nt0AIqF705KN4JKOWgeI4wUGUP60krXXs/edit?gid=0).
 
 Based on these findings and community feedback, the following models have been verified to work reasonably well with OpenHands:
 
-- claude-3-5-sonnet (recommended)
-- gpt-4 / gpt-4o
-- llama-3.1-405b
-- deepseek-v2.5
+- anthropic/claude-3-5-sonnet-20241022 (recommended)
+- anthropic/claude-3-5-haiku-20241022
+- deepseek/deepseek-chat
+- gpt-4o
 
 :::warning
 OpenHands will issue many prompts to the LLM you configure. Most of these LLMs cost money, so be sure to set spending

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

@@ -1,17 +1,31 @@
-# Micro-Agents
+# 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.
+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:
+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.
 
-## Available Micro-Agents
+### 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`
@@ -29,6 +43,14 @@ Key features:
 - 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`
@@ -38,9 +60,15 @@ Specializes in handling npm package management with specific focus on:
 - Automated confirmation handling using Unix 'yes' command.
 - Package installation automation.
 
-### Custom Micro-Agents
+Usage Example:
 
-You can create your own micro-agents by adding new markdown files to the micro-agents directory.
+```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
@@ -55,43 +83,29 @@ triggers:
 Instructions and capabilities for the micro-agent...
 ```
 
-## Best Practices
+## Working With Public Micro-Agents
 
-When working with 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.
 
-## Integration
+## Contributing a Public Micro-Agent
 
-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.
+Best practices for creating public micro-agents:
 
-## Example Usage
+- **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.
 
-```bash
-# GitHub agent example
-git checkout -b feature-branch
-git commit -m "Add new feature"
-git push origin feature-branch
+To contribute a new micro-agent to OpenHands:
 
-# NPM agent example
-yes | npm install package-name
-```
+### 1. Plan the Public Micro-Agent
 
-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:
+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?
@@ -99,11 +113,11 @@ Before creating a micro-agent, consider:
 
 ### 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).
+Create a new markdown file in `microagents/knowledge/` with a descriptive name (e.g., `docker.md` for a Docker-focused agent).
 
 ### 3. Required Components
 
-Your micro-agent file must include:
+The micro-agent file must include:
 
 - **Front Matter**: YAML metadata at the start of the file:
 ```markdown
@@ -133,15 +147,7 @@ Examples of usage:
 [Example 2]
 ```
 
-### 4. Best Practices for Micro-Agent Development
-
-- **Clear Scope**: Keep the 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 agent interacts with other components.
-
-### 5. Testing Your Micro-Agent
+### 4. Testing the Public Micro-Agent
 
 Before submitting:
 - Test the agent with various prompts.
@@ -149,7 +155,14 @@ Before submitting:
 - Ensure instructions are clear and comprehensive.
 - Check for potential conflicts with existing agents.
 
-### 6. Example Implementation
+### 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:
 
@@ -197,14 +210,5 @@ Remember to:
 - 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/microagents-repo.md

@@ -1,10 +1,12 @@
-# Customizing Agent Behavior
+# 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.
+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
+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.
 
@@ -39,7 +41,8 @@ Guidelines:
 
 ### Customizing Prompts
 
-When working with a repository:
+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.
@@ -54,14 +57,10 @@ The component should use our shared styling from src/styles/components.
 
 ### Best Practices for Repository Customization
 
-- **Keep Instructions Updated**: Regularly update your `.openhands` directory as your project evolves.
+- **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.
-
-## 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 [Micro-Agents](microagents.md) for more information.

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:0.18-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/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

evaluation/benchmarks/agent_bench/run_infer.py

@@ -137,7 +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)
@@ -164,8 +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

@@ -145,10 +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

@@ -199,7 +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
@@ -223,9 +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

@@ -268,10 +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
@@ -300,10 +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/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

@@ -171,9 +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/ml_bench/run_infer.py

@@ -163,7 +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

@@ -104,9 +104,9 @@ for repo, diff in repo_diffs:
     # Determine if this repo has a significant diff
     is_significant = diff >= threshold
     repo_color = 'red' if is_significant else 'yellow'
-    print(colored(f'Difference: {diff} instances!', repo_color, attrs=['bold']))
 
     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))

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/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}')
@@ -551,3 +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/__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();
@@ -17,11 +18,11 @@ describe("ConversationCard", () => {
     render(
       <ConversationCard
         onDelete={onDelete}
-        onClick={onClick}
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
+        isActive
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
     const expectedDate = `${formatTimeDelta(new Date("2021-10-01T12:00:00Z"))} ago`;
@@ -33,53 +34,34 @@ 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"
+        isActive
+        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(
       <ConversationCard
         onDelete={onDelete}
-        onClick={onClick}
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo="org/repo"
-        lastUpdated="2021-10-01T12:00:00Z"
+        isActive
+        title="Conversation 1"
+        selectedRepository="org/selectedRepository"
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
 
-    screen.getByTestId("conversation-card-repo");
-  });
-
-  it("should call onClick when the card is clicked", async () => {
-    const user = userEvent.setup();
-    render(
-      <ConversationCard
-        onDelete={onDelete}
-        onClick={onClick}
-        onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
-      />,
-    );
-
-    const card = screen.getByTestId("conversation-card");
-    await user.click(card);
-
-    expect(onClick).toHaveBeenCalled();
+    screen.getByTestId("conversation-card-selected-repository");
   });
 
   it("should toggle a context menu when clicking the ellipsis button", async () => {
@@ -87,11 +69,11 @@ describe("ConversationCard", () => {
     render(
       <ConversationCard
         onDelete={onDelete}
-        onClick={onClick}
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
+        isActive
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
 
@@ -111,12 +93,12 @@ describe("ConversationCard", () => {
     const user = userEvent.setup();
     render(
       <ConversationCard
-        onClick={onClick}
         onDelete={onDelete}
+        isActive
         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 +113,23 @@ 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}
+        isActive
         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();
   });
@@ -154,16 +138,24 @@ describe("ConversationCard", () => {
     const user = userEvent.setup();
     render(
       <ConversationCard
-        onClick={onClick}
         onDelete={onDelete}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
+        isActive
+        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   ");
@@ -171,21 +163,24 @@ 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 () => {
     const user = userEvent.setup();
     render(
       <ConversationCard
-        onClick={onClick}
         onDelete={onDelete}
+        isActive
         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);
@@ -199,12 +194,12 @@ describe("ConversationCard", () => {
     const user = userEvent.setup();
     render(
       <ConversationCard
-        onClick={onClick}
         onDelete={onDelete}
+        isActive
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
 
@@ -218,12 +213,12 @@ describe("ConversationCard", () => {
     const user = userEvent.setup();
     render(
       <ConversationCard
-        onClick={onClick}
         onDelete={onDelete}
+        isActive
         onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
       />,
     );
 
@@ -239,36 +234,36 @@ 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}
+          isActive
           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", () => {
       render(
         <ConversationCard
-          onClick={onClick}
           onDelete={onDelete}
+          isActive
           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

@@ -6,15 +6,23 @@ import {
   QueryClientConfig,
 } from "@tanstack/react-query";
 import userEvent from "@testing-library/user-event";
+import { createRoutesStub } from "react-router";
 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();
+  const RouterStub = createRoutesStub([
+    {
+      Component: () => <ConversationPanel onClose={onCloseMock} />,
+      path: "/",
+    },
+  ]);
 
   const renderConversationPanel = (config?: QueryClientConfig) =>
-    render(<ConversationPanel onClose={onCloseMock} />, {
+    render(<RouterStub />, {
       wrapper: ({ children }) => (
         <AuthProvider>
           <QueryClientProvider client={new QueryClient(config)}>
@@ -52,6 +60,8 @@ 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 +179,15 @@ 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 +208,8 @@ 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 +231,4 @@ 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

@@ -14,7 +14,8 @@ describe("GitHubRepositorySelector", () => {
       <GitHubRepositorySelector
         onInputChange={onInputChangeMock}
         onSelect={onSelectMock}
-        repositories={[]}
+        publicRepositories={[]}
+        userRepositories={[]}
       />,
     );
 
@@ -36,7 +37,8 @@ describe("GitHubRepositorySelector", () => {
       <GitHubRepositorySelector
         onInputChange={onInputChangeMock}
         onSelect={onSelectMock}
-        repositories={[]}
+        publicRepositories={[]}
+        userRepositories={[]}
       />,
     );
 
@@ -67,7 +69,8 @@ describe("GitHubRepositorySelector", () => {
       <GitHubRepositorySelector
         onInputChange={onInputChangeMock}
         onSelect={onSelectMock}
-        repositories={[]}
+        publicRepositories={[]}
+        userRepositories={[]}
       />,
     );
 

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": "0.18.0",
+  "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": "^5.62.12",
+    "@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": "^1.203.3",
+    "posthog-js": "^1.205.0",
     "react": "^19.0.0",
     "react-dom": "^19.0.0",
     "react-highlight": "^0.15.0",
     "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": "^22.10.5",
-    "@types/react": "^19.0.2",
+    "@types/react": "^19.0.3",
     "@types/react-dom": "^19.0.2",
     "@types/react-highlight": "^0.12.8",
     "@types/react-syntax-highlighter": "^15.5.13",

frontend/src/api/github.ts

@@ -110,16 +110,11 @@ export const searchPublicRepositories = async (
   sort: "" | "updated" | "stars" | "forks" = "stars",
   order: "desc" | "asc" = "desc",
 ): Promise<GitHubRepository[]> => {
-  const sanitizedQuery = query.trim();
-  if (!sanitizedQuery) {
-    return [];
-  }
-
   const response = await github.get<{ items: GitHubRepository[] }>(
     "/search/repositories",
     {
       params: {
-        q: sanitizedQuery,
+        q: query,
         per_page,
         sort,
         order,

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;
 }

frontend/src/components/agent-status-map.constant.ts

@@ -61,4 +61,8 @@ export const AGENT_STATUS_MAP: {
     message: I18nKey.CHAT_INTERFACE$AGENT_ACTION_USER_REJECTED_MESSAGE,
     indicator: IndicatorColor.RED,
   },
+  [AgentState.RATE_LIMITED]: {
+    message: I18nKey.CHAT_INTERFACE$AGENT_RATE_LIMITED_MESSAGE,
+    indicator: IndicatorColor.YELLOW,
+  },
 };

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

@@ -94,7 +94,12 @@ export function ChatInput({
   };
 
   const handleKeyPress = (event: React.KeyboardEvent<HTMLTextAreaElement>) => {
-    if (event.key === "Enter" && !event.shiftKey && !disabled) {
+    if (
+      event.key === "Enter" &&
+      !event.shiftKey &&
+      !disabled &&
+      !event.nativeEvent.isComposing
+    ) {
       event.preventDefault();
       handleSubmitMessage();
     }

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

@@ -154,7 +154,8 @@ export function ChatInterface() {
           onStop={handleStop}
           isDisabled={
             curAgentState === AgentState.LOADING ||
-            curAgentState === AgentState.AWAITING_USER_CONFIRMATION
+            curAgentState === AgentState.AWAITING_USER_CONFIRMATION ||
+            curAgentState === AgentState.RATE_LIMITED
           }
           mode={curAgentState === AgentState.RUNNING ? "stop" : "submit"}
           value={messageToSend ?? undefined}

frontend/src/components/features/context-menu/context-menu.tsx

@@ -18,7 +18,7 @@ export function ContextMenu({
     <ul
       data-testid={testId}
       ref={ref}
-      className={cn("bg-[#404040] rounded-md w-[224px]", className)}
+      className={cn("bg-[#404040] rounded-md w-[140px]", className)}
     >
       {children}
     </ul>

frontend/src/components/features/conversation-panel/confirm-delete-modal.tsx

@@ -25,10 +25,14 @@ export function ConfirmDeleteModal({
         <div className="flex flex-col gap-2 w-full">
           <ModalButton
             onClick={onConfirm}
-            className="bg-[#4465DB]"
+            className="bg-danger font-bold"
             text="Confirm"
           />
-          <ModalButton onClick={onCancel} className="bg-danger" text="Cancel" />
+          <ModalButton
+            onClick={onCancel}
+            className="bg-neutral-500 font-bold"
+            text="Cancel"
+          />
         </div>
       </ModalBody>
     </ModalBackdrop>

frontend/src/components/features/conversation-panel/conversation-card-context-menu.tsx

@@ -0,0 +1,32 @@
+import { useClickOutsideElement } from "#/hooks/use-click-outside-element";
+import { ContextMenu } from "../context-menu/context-menu";
+import { ContextMenuListItem } from "../context-menu/context-menu-list-item";
+
+interface ConversationCardContextMenuProps {
+  onClose: () => void;
+  onDelete: (event: React.MouseEvent<HTMLButtonElement>) => void;
+  onEdit: (event: React.MouseEvent<HTMLButtonElement>) => void;
+}
+
+export function ConversationCardContextMenu({
+  onClose,
+  onDelete,
+  onEdit,
+}: ConversationCardContextMenuProps) {
+  const ref = useClickOutsideElement<HTMLUListElement>(onClose);
+
+  return (
+    <ContextMenu
+      ref={ref}
+      testId="context-menu"
+      className="left-full float-right"
+    >
+      <ContextMenuListItem testId="delete-button" onClick={onDelete}>
+        Delete
+      </ContextMenuListItem>
+      <ContextMenuListItem testId="edit-button" onClick={onEdit}>
+        Edit Title
+      </ContextMenuListItem>
+    </ContextMenu>
+  );
+}

frontend/src/components/features/conversation-panel/conversation-card.tsx

@@ -2,33 +2,33 @@ import React from "react";
 import { formatTimeDelta } from "#/utils/format-time-delta";
 import { ConversationRepoLink } from "./conversation-repo-link";
 import {
-  ProjectState,
+  ProjectStatus,
   ConversationStateIndicator,
 } from "./conversation-state-indicator";
-import { ContextMenu } from "../context-menu/context-menu";
-import { ContextMenuListItem } from "../context-menu/context-menu-list-item";
 import { EllipsisButton } from "./ellipsis-button";
+import { ConversationCardContextMenu } from "./conversation-card-context-menu";
 
-interface ProjectCardProps {
-  onClick: () => void;
+interface ConversationCardProps {
   onDelete: () => void;
   onChangeTitle: (title: string) => void;
-  name: string;
-  repo: string | null;
-  lastUpdated: string; // ISO 8601
-  state?: ProjectState;
+  isActive: boolean;
+  title: string;
+  selectedRepository: string | null;
+  lastUpdatedAt: string; // ISO 8601
+  status?: ProjectStatus;
 }
 
 export function ConversationCard({
-  onClick,
   onDelete,
   onChangeTitle,
-  name,
-  repo,
-  lastUpdated,
-  state = "cold",
-}: ProjectCardProps) {
+  isActive,
+  title,
+  selectedRepository,
+  lastUpdatedAt,
+  status = "STOPPED",
+}: ConversationCardProps) {
   const [contextMenuVisible, setContextMenuVisible] = React.useState(false);
+  const [titleMode, setTitleMode] = React.useState<"view" | "edit">("view");
   const inputRef = React.useRef<HTMLInputElement>(null);
 
   const handleBlur = () => {
@@ -38,64 +38,89 @@ export function ConversationCard({
       inputRef.current!.value = trimmed;
     } else {
       // reset the value if it's empty
-      inputRef.current!.value = name;
+      inputRef.current!.value = title;
+    }
+
+    setTitleMode("view");
+  };
+
+  const handleKeyUp = (event: React.KeyboardEvent<HTMLInputElement>) => {
+    if (event.key === "Enter") {
+      event.currentTarget.blur();
     }
   };
 
   const handleInputClick = (event: React.MouseEvent<HTMLInputElement>) => {
+    event.preventDefault();
     event.stopPropagation();
   };
 
   const handleDelete = (event: React.MouseEvent<HTMLButtonElement>) => {
+    event.preventDefault();
     event.stopPropagation();
     onDelete();
   };
 
+  const handleEdit = (event: React.MouseEvent<HTMLButtonElement>) => {
+    event.preventDefault();
+    event.stopPropagation();
+    setTitleMode("edit");
+    setContextMenuVisible(false);
+  };
+
+  React.useEffect(() => {
+    if (titleMode === "edit") {
+      inputRef.current?.focus();
+    }
+  }, [titleMode]);
+
   return (
     <div
       data-testid="conversation-card"
-      onClick={onClick}
-      className="h-[100px] w-full px-[18px] py-4 border-b border-neutral-600"
+      className="h-[100px] w-full px-[18px] py-4 border-b border-neutral-600 cursor-pointer"
     >
       <div className="flex items-center justify-between">
-        <input
-          ref={inputRef}
-          data-testid="conversation-card-title"
-          onClick={handleInputClick}
-          onBlur={handleBlur}
-          type="text"
-          defaultValue={name}
-          className="text-sm leading-6 font-semibold bg-transparent"
-        />
+        <div className="flex items-center gap-2 w-full">
+          {isActive && <span className="w-2 h-2 bg-blue-500 rounded-full" />}
+          <input
+            ref={inputRef}
+            disabled={titleMode === "view"}
+            data-testid="conversation-card-title"
+            onClick={handleInputClick}
+            onBlur={handleBlur}
+            onKeyUp={handleKeyUp}
+            type="text"
+            defaultValue={title}
+            className="text-sm leading-6 font-semibold bg-transparent w-full"
+          />
+        </div>
 
         <div className="flex items-center gap-2 relative">
-          <ConversationStateIndicator state={state} />
+          <ConversationStateIndicator status={status} />
           <EllipsisButton
             onClick={(event) => {
+              event.preventDefault();
               event.stopPropagation();
               setContextMenuVisible((prev) => !prev);
             }}
           />
-          {contextMenuVisible && (
-            <ContextMenu testId="context-menu" className="absolute left-full">
-              <ContextMenuListItem
-                testId="delete-button"
-                onClick={handleDelete}
-              >
-                Delete
-              </ContextMenuListItem>
-            </ContextMenu>
-          )}
         </div>
       </div>
-      {repo && (
+      {contextMenuVisible && (
+        <ConversationCardContextMenu
+          onClose={() => setContextMenuVisible(false)}
+          onDelete={handleDelete}
+          onEdit={handleEdit}
+        />
+      )}
+      {selectedRepository && (
         <ConversationRepoLink
-          repo={repo}
+          selectedRepository={selectedRepository}
           onClick={(e) => e.stopPropagation()}
         />
       )}
       <p className="text-xs text-neutral-400">
-        <time>{formatTimeDelta(new Date(lastUpdated))} ago</time>
+        <time>{formatTimeDelta(new Date(lastUpdatedAt))} ago</time>
       </p>
     </div>
   );

frontend/src/components/features/conversation-panel/conversation-panel-wrapper.tsx

@@ -0,0 +1,22 @@
+import ReactDOM from "react-dom";
+
+interface ConversationPanelWrapperProps {
+  isOpen: boolean;
+}
+
+export function ConversationPanelWrapper({
+  isOpen,
+  children,
+}: React.PropsWithChildren<ConversationPanelWrapperProps>) {
+  if (!isOpen) return null;
+
+  const portalTarget = document.getElementById("root-outlet");
+  if (!portalTarget) return null;
+
+  return ReactDOM.createPortal(
+    <div className="absolute h-full w-full left-0 top-0 z-20 bg-black/80 rounded-xl">
+      {children}
+    </div>,
+    portalTarget,
+  );
+}

frontend/src/components/features/conversation-panel/conversation-panel.tsx

@@ -1,14 +1,14 @@
 import React from "react";
-import { useLocation, useNavigate, useParams } from "react-router";
+import { NavLink, useParams } from "react-router";
 import { ConversationCard } from "./conversation-card";
 import { useUserConversations } from "#/hooks/query/use-user-conversations";
 import { useDeleteConversation } from "#/hooks/mutation/use-delete-conversation";
 import { ConfirmDeleteModal } from "./confirm-delete-modal";
-import { NewConversationButton } from "./new-conversation-button";
 import { LoadingSpinner } from "#/components/shared/loading-spinner";
 import { useUpdateConversation } from "#/hooks/mutation/use-update-conversation";
 import { useEndSession } from "#/hooks/use-end-session";
 import { ExitConversationModal } from "./exit-conversation-modal";
+import { useClickOutsideElement } from "#/hooks/use-click-outside-element";
 
 interface ConversationPanelProps {
   onClose: () => void;
@@ -16,10 +16,8 @@ interface ConversationPanelProps {
 
 export function ConversationPanel({ onClose }: ConversationPanelProps) {
   const { conversationId: cid } = useParams();
-  const navigate = useNavigate();
-  const location = useLocation();
-
   const endSession = useEndSession();
+  const ref = useClickOutsideElement<HTMLDivElement>(onClose);
 
   const [confirmDeleteModalVisible, setConfirmDeleteModalVisible] =
     React.useState(false);
@@ -60,26 +58,17 @@ export function ConversationPanel({ onClose }: ConversationPanelProps) {
     if (oldTitle !== newTitle)
       updateConversation({
         id: conversationId,
-        conversation: { name: newTitle },
+        conversation: { title: newTitle },
       });
   };
 
-  const handleClickCard = (conversationId: string) => {
-    navigate(`/conversations/${conversationId}`);
-    onClose();
-  };
-
   return (
     <div
+      ref={ref}
       data-testid="conversation-panel"
-      className="w-[350px] h-full border border-neutral-700 bg-neutral-800 rounded-xl"
+      className="w-[350px] h-full border border-neutral-700 bg-neutral-800 rounded-xl overflow-y-auto"
     >
       <div className="pt-4 px-4 flex items-center justify-between">
-        {location.pathname.startsWith("/conversation") && (
-          <NewConversationButton
-            onClick={() => setConfirmExitConversationModalVisible(true)}
-          />
-        )}
         {isFetching && <LoadingSpinner size="small" />}
       </div>
       {error && (
@@ -93,18 +82,25 @@ export function ConversationPanel({ onClose }: ConversationPanelProps) {
         </div>
       )}
       {conversations?.map((project) => (
-        <ConversationCard
+        <NavLink
           key={project.conversation_id}
-          onClick={() => handleClickCard(project.conversation_id)}
-          onDelete={() => handleDeleteProject(project.conversation_id)}
-          onChangeTitle={(title) =>
-            handleChangeTitle(project.conversation_id, project.name, title)
-          }
-          name={project.name}
-          repo={project.repo}
-          lastUpdated={project.lastUpdated}
-          state={project.state}
-        />
+          to={`/conversations/${project.conversation_id}`}
+          onClick={onClose}
+        >
+          {({ isActive }) => (
+            <ConversationCard
+              isActive={isActive}
+              onDelete={() => handleDeleteProject(project.conversation_id)}
+              onChangeTitle={(title) =>
+                handleChangeTitle(project.conversation_id, project.title, title)
+              }
+              title={project.title}
+              selectedRepository={project.selected_repository}
+              lastUpdatedAt={project.last_updated_at}
+              status={project.status}
+            />
+          )}
+        </NavLink>
       ))}
 
       {confirmDeleteModalVisible && (

frontend/src/components/features/conversation-panel/conversation-repo-link.tsx

@@ -1,21 +1,21 @@
 interface ConversationRepoLinkProps {
-  repo: string;
+  selectedRepository: string;
   onClick?: (event: React.MouseEvent<HTMLAnchorElement>) => void;
 }
 
 export function ConversationRepoLink({
-  repo,
+  selectedRepository,
   onClick,
 }: ConversationRepoLinkProps) {
   return (
     <a
-      data-testid="conversation-card-repo"
-      href={`https://github.com/${repo}`}
+      data-testid="conversation-card-selected-repository"
+      href={`https://github.com/${selectedRepository}`}
       target="_blank noopener noreferrer"
       onClick={onClick}
       className="text-xs text-neutral-400 hover:text-neutral-200"
     >
-      {repo}
+      {selectedRepository}
     </a>
   );
 }

frontend/src/components/features/conversation-panel/conversation-state-indicator.tsx

@@ -1,39 +1,25 @@
 import ColdIcon from "./state-indicators/cold.svg?react";
-import CoolingIcon from "./state-indicators/cooling.svg?react";
-import FinishedIcon from "./state-indicators/finished.svg?react";
 import RunningIcon from "./state-indicators/running.svg?react";
-import WaitingIcon from "./state-indicators/waiting.svg?react";
-import WarmIcon from "./state-indicators/warm.svg?react";
 
 type SVGIcon = React.FunctionComponent<React.SVGProps<SVGSVGElement>>;
-export type ProjectState =
-  | "cold"
-  | "cooling"
-  | "finished"
-  | "running"
-  | "waiting"
-  | "warm";
+export type ProjectStatus = "RUNNING" | "STOPPED";
 
-const INDICATORS: Record<ProjectState, SVGIcon> = {
-  cold: ColdIcon,
-  cooling: CoolingIcon,
-  finished: FinishedIcon,
-  running: RunningIcon,
-  waiting: WaitingIcon,
-  warm: WarmIcon,
+const INDICATORS: Record<ProjectStatus, SVGIcon> = {
+  STOPPED: ColdIcon,
+  RUNNING: RunningIcon,
 };
 
 interface ConversationStateIndicatorProps {
-  state: ProjectState;
+  status: ProjectStatus;
 }
 
 export function ConversationStateIndicator({
-  state,
+  status,
 }: ConversationStateIndicatorProps) {
-  const StateIcon = INDICATORS[state];
+  const StateIcon = INDICATORS[status];
 
   return (
-    <div data-testid={`${state}-indicator`}>
+    <div data-testid={`${status}-indicator`}>
       <StateIcon />
     </div>
   );

frontend/src/components/features/github/github-repo-selector.tsx

@@ -1,46 +1,48 @@
 import React from "react";
-import { Autocomplete, AutocompleteItem } from "@nextui-org/react";
+import {
+  Autocomplete,
+  AutocompleteItem,
+  AutocompleteSection,
+} from "@nextui-org/react";
 import { useDispatch } from "react-redux";
 import posthog from "posthog-js";
 import { setSelectedRepository } from "#/state/initial-query-slice";
 import { useConfig } from "#/hooks/query/use-config";
-
-interface GitHubRepositoryWithPublic extends GitHubRepository {
-  is_public?: boolean;
-}
+import { sanitizeQuery } from "#/utils/sanitize-query";
 
 interface GitHubRepositorySelectorProps {
   onInputChange: (value: string) => void;
   onSelect: () => void;
-  repositories: GitHubRepositoryWithPublic[];
+  userRepositories: GitHubRepository[];
+  publicRepositories: GitHubRepository[];
 }
 
 export function GitHubRepositorySelector({
   onInputChange,
   onSelect,
-  repositories,
+  userRepositories,
+  publicRepositories,
 }: GitHubRepositorySelectorProps) {
   const { data: config } = useConfig();
   const [selectedKey, setSelectedKey] = React.useState<string | null>(null);
 
+  const allRepositories: GitHubRepository[] = [
+    ...publicRepositories.filter(
+      (repo) => !publicRepositories.find((r) => r.id === repo.id),
+    ),
+    ...userRepositories,
+  ];
+
   const dispatch = useDispatch();
 
   const handleRepoSelection = (id: string | null) => {
-    const repo = repositories.find((r) => r.id.toString() === id);
-    if (!repo) return;
-
-    if (repo.id === -1000) {
-      window.open(
-        `https://github.com/apps/${config?.APP_SLUG}/installations/new`,
-        "_blank",
-      );
-      return;
+    const repo = allRepositories.find((r) => r.id.toString() === id);
+    if (repo) {
+      dispatch(setSelectedRepository(repo.full_name));
+      posthog.capture("repository_selected");
+      onSelect();
+      setSelectedKey(id);
     }
-
-    dispatch(setSelectedRepository(repo.full_name));
-    posthog.capture("repository_selected");
-    onSelect();
-    setSelectedKey(id);
   };
 
   const handleClearSelection = () => {
@@ -55,8 +57,8 @@ export function GitHubRepositorySelector({
       name="repo"
       aria-label="GitHub Repository"
       placeholder="Select a GitHub project"
+      isVirtualized={false}
       selectedKey={selectedKey}
-      items={repositories}
       inputProps={{
         classNames: {
           inputWrapper:
@@ -65,27 +67,61 @@ export function GitHubRepositorySelector({
       }}
       onSelectionChange={(id) => handleRepoSelection(id?.toString() ?? null)}
       onInputChange={onInputChange}
-      clearButtonProps={{ onPress: handleClearSelection }}
+      clearButtonProps={{ onClick: handleClearSelection }}
       listboxProps={{
         emptyContent,
       }}
+      defaultFilter={(textValue, inputValue) =>
+        !inputValue ||
+        sanitizeQuery(textValue).includes(sanitizeQuery(inputValue))
+      }
     >
-      {(item) => (
-        <AutocompleteItem
-          data-testid="github-repo-item"
-          key={item.id}
-          value={item.id}
-          textValue={item.full_name}
-        >
-          <div className="flex items-center justify-between">
-            {item.full_name}
-            {item.is_public && !!item.stargazers_count && (
-              <span className="text-xs text-gray-400">
-                ({item.stargazers_count}⭐)
+      {config?.APP_MODE === "saas" &&
+        config?.APP_SLUG &&
+        ((
+          <AutocompleteItem key="install">
+            <a
+              href={`https://github.com/apps/${config.APP_SLUG}/installations/new`}
+              target="_blank"
+              rel="noreferrer noopener"
+              onClick={(e) => e.stopPropagation()}
+            >
+              Add more repositories...
+            </a>
+          </AutocompleteItem> // eslint-disable-next-line @typescript-eslint/no-explicit-any
+        ) as any)}
+      {userRepositories.length > 0 && (
+        <AutocompleteSection showDivider title="Your Repos">
+          {userRepositories.map((repo) => (
+            <AutocompleteItem
+              data-testid="github-repo-item"
+              key={repo.id}
+              value={repo.id}
+              className="data-[selected=true]:bg-default-100"
+              textValue={repo.full_name}
+            >
+              {repo.full_name}
+            </AutocompleteItem>
+          ))}
+        </AutocompleteSection>
+      )}
+      {publicRepositories.length > 0 && (
+        <AutocompleteSection showDivider title="Public Repos">
+          {publicRepositories.map((repo) => (
+            <AutocompleteItem
+              data-testid="github-repo-item"
+              key={repo.id}
+              value={repo.id}
+              className="data-[selected=true]:bg-default-100"
+              textValue={repo.full_name}
+            >
+              {repo.full_name}
+              <span className="ml-1 text-gray-400">
+                ({repo.stargazers_count || 0}⭐)
               </span>
-            )}
-          </div>
-        </AutocompleteItem>
+            </AutocompleteItem>
+          ))}
+        </AutocompleteSection>
       )}
     </Autocomplete>
   );

frontend/src/components/features/github/github-repositories-suggestion-box.tsx

@@ -11,7 +11,6 @@ import { useSearchRepositories } from "#/hooks/query/use-search-repositories";
 import { useUserRepositories } from "#/hooks/query/use-user-repositories";
 import { sanitizeQuery } from "#/utils/sanitize-query";
 import { useDebounce } from "#/hooks/use-debounce";
-import { useConfig } from "#/hooks/query/use-config";
 
 interface GitHubRepositoriesSuggestionBoxProps {
   handleSubmit: () => void;
@@ -29,7 +28,6 @@ export function GitHubRepositoriesSuggestionBox({
   const [searchQuery, setSearchQuery] = React.useState<string>("");
   const debouncedSearchQuery = useDebounce(searchQuery, 300);
 
-  const { data: config } = useConfig();
   // TODO: Use `useQueries` to fetch all repositories in parallel
   const { data: appRepositories } = useAppRepositories();
   const { data: userRepositories } = useUserRepositories();
@@ -37,19 +35,6 @@ export function GitHubRepositoriesSuggestionBox({
     sanitizeQuery(debouncedSearchQuery),
   );
 
-  const saasPlaceholderRepository = React.useMemo(() => {
-    if (config?.APP_MODE === "saas" && config?.APP_SLUG) {
-      return [
-        {
-          id: -1000,
-          full_name: "Add more repositories...",
-        },
-      ];
-    }
-
-    return [];
-  }, [config]);
-
   const repositories =
     userRepositories?.pages.flatMap((page) => page.data) ||
     appRepositories?.pages.flatMap((page) => page.data) ||
@@ -74,11 +59,8 @@ export function GitHubRepositoriesSuggestionBox({
             <GitHubRepositorySelector
               onInputChange={setSearchQuery}
               onSelect={handleSubmit}
-              repositories={[
-                ...saasPlaceholderRepository,
-                ...searchedRepos,
-                ...repositories,
-              ]}
+              publicRepositories={searchedRepos}
+              userRepositories={repositories}
             />
           ) : (
             <ModalButton

frontend/src/components/features/project-menu/project-menu-details.tsx

@@ -16,16 +16,24 @@ export function ProjectMenuDetails({
 }: ProjectMenuDetailsProps) {
   const { t } = useTranslation();
   return (
-    <div className="flex flex-col">
+    <div className="flex flex-col min-w-0">
       <a
         href={`https://github.com/${repoName}`}
         target="_blank"
         rel="noreferrer noopener"
-        className="flex items-center gap-2"
+        className="flex items-center gap-2 min-w-0"
       >
-        {avatar && <img src={avatar} alt="" className="w-4 h-4 rounded-full" />}
-        <span className="text-sm leading-6 font-semibold">{repoName}</span>
-        <ExternalLinkIcon width={16} height={16} />
+        {avatar && (
+          <img
+            src={avatar}
+            alt=""
+            className="w-4 h-4 rounded-full flex-shrink-0"
+          />
+        )}
+        <span className="text-sm leading-6 font-semibold truncate flex-1">
+          {repoName}
+        </span>
+        <ExternalLinkIcon width={16} height={16} className="flex-shrink-0" />
       </a>
       <a
         href={lastCommit.html_url}

frontend/src/components/features/sidebar/sidebar.tsx

@@ -1,6 +1,6 @@
 import React from "react";
-import { useLocation } from "react-router";
-import FolderIcon from "#/icons/docs.svg?react";
+import { FaListUl } from "react-icons/fa";
+import { useDispatch } from "react-redux";
 import { useAuth } from "#/context/auth-context";
 import { useGitHubUser } from "#/hooks/query/use-github-user";
 import { useIsAuthed } from "#/hooks/query/use-is-authed";
@@ -11,16 +11,20 @@ import { ExitProjectButton } from "#/components/shared/buttons/exit-project-butt
 import { SettingsButton } from "#/components/shared/buttons/settings-button";
 import { LoadingSpinner } from "#/components/shared/loading-spinner";
 import { AccountSettingsModal } from "#/components/shared/modals/account-settings/account-settings-modal";
-import { ExitProjectConfirmationModal } from "#/components/shared/modals/exit-project-confirmation-modal";
 import { SettingsModal } from "#/components/shared/modals/settings/settings-modal";
 import { useSettingsUpToDate } from "#/context/settings-up-to-date-context";
 import { useSettings } from "#/hooks/query/use-settings";
 import { ConversationPanel } from "../conversation-panel/conversation-panel";
-import { cn } from "#/utils/utils";
-import { MULTI_CONVO_UI_IS_ENABLED } from "#/utils/constants";
+import { MULTI_CONVERSATION_UI } from "#/utils/feature-flags";
+import { useEndSession } from "#/hooks/use-end-session";
+import { setCurrentAgentState } from "#/state/agent-slice";
+import { AgentState } from "#/types/agent-state";
+import { TooltipButton } from "#/components/shared/buttons/tooltip-button";
+import { ConversationPanelWrapper } from "../conversation-panel/conversation-panel-wrapper";
 
 export function Sidebar() {
-  const location = useLocation();
+  const dispatch = useDispatch();
+  const endSession = useEndSession();
   const user = useGitHubUser();
   const { data: isAuthed } = useIsAuthed();
   const { logout } = useAuth();
@@ -30,11 +34,9 @@ export function Sidebar() {
   const [accountSettingsModalOpen, setAccountSettingsModalOpen] =
     React.useState(false);
   const [settingsModalIsOpen, setSettingsModalIsOpen] = React.useState(false);
-  const [startNewProjectModalIsOpen, setStartNewProjectModalIsOpen] =
+
+  const [conversationPanelIsOpen, setConversationPanelIsOpen] =
     React.useState(false);
-  const [conversationPanelIsOpen, setConversationPanelIsOpen] = React.useState(
-    MULTI_CONVO_UI_IS_ENABLED,
-  );
 
   React.useEffect(() => {
     // If the github token is invalid, open the account settings modal again
@@ -43,6 +45,11 @@ export function Sidebar() {
     }
   }, [user.isError]);
 
+  const handleEndSession = () => {
+    dispatch(setCurrentAgentState(AgentState.LOADING));
+    endSession();
+  };
+
   const handleAccountSettingsModalClose = () => {
     // If the user closes the modal without connecting to GitHub,
     // we need to log them out to clear the invalid token from the
@@ -51,22 +58,30 @@ export function Sidebar() {
     setAccountSettingsModalOpen(false);
   };
 
-  const handleClickLogo = () => {
-    if (location.pathname.startsWith("/conversations/"))
-      setStartNewProjectModalIsOpen(true);
-  };
-
   const showSettingsModal =
     isAuthed && (!settingsAreUpToDate || settingsModalIsOpen);
 
   return (
     <>
-      <aside className="h-[40px] md:h-auto px-1 flex flex-row md:flex-col gap-1 relative">
+      <aside className="h-[40px] md:h-auto px-1 flex flex-row md:flex-col gap-1">
         <nav className="flex flex-row md:flex-col items-center gap-[18px]">
-          <div className="w-[34px] h-[34px] flex items-center justify-center">
-            <AllHandsLogoButton onClick={handleClickLogo} />
+          <div className="w-[34px] h-[34px] flex items-center justify-center mb-7">
+            <AllHandsLogoButton onClick={handleEndSession} />
           </div>
           {user.isLoading && <LoadingSpinner size="small" />}
+          <ExitProjectButton onClick={handleEndSession} />
+          {MULTI_CONVERSATION_UI && (
+            <TooltipButton
+              data-testid="toggle-conversation-panel"
+              tooltip="Conversations"
+              ariaLabel="Conversations"
+              onClick={() => setConversationPanelIsOpen((prev) => !prev)}
+            >
+              <FaListUl size={22} />
+            </TooltipButton>
+          )}
+          <DocsButton />
+          <SettingsButton onClick={() => setSettingsModalIsOpen(true)} />
           {!user.isLoading && (
             <UserActions
               user={
@@ -76,33 +91,14 @@ export function Sidebar() {
               onClickAccountSettings={() => setAccountSettingsModalOpen(true)}
             />
           )}
-          <SettingsButton onClick={() => setSettingsModalIsOpen(true)} />
-          {MULTI_CONVO_UI_IS_ENABLED && (
-            <button
-              data-testid="toggle-conversation-panel"
-              type="button"
-              onClick={() => setConversationPanelIsOpen((prev) => !prev)}
-              className={cn(
-                conversationPanelIsOpen ? "border-b-2 border-[#FFE165]" : "",
-              )}
-            >
-              <FolderIcon width={28} height={28} />
-            </button>
-          )}
-          <DocsButton />
-          <ExitProjectButton
-            onClick={() => setStartNewProjectModalIsOpen(true)}
-          />
         </nav>
 
         {conversationPanelIsOpen && (
-          <div
-            className="absolute h-full left-[calc(100%+12px)] top-0 z-20" // 12px padding (sidebar parent)
-          >
+          <ConversationPanelWrapper isOpen={conversationPanelIsOpen}>
             <ConversationPanel
               onClose={() => setConversationPanelIsOpen(false)}
             />
-          </div>
+          </ConversationPanelWrapper>
         )}
       </aside>
 
@@ -116,11 +112,6 @@ export function Sidebar() {
             onClose={() => setSettingsModalIsOpen(false)}
           />
         ))}
-      {startNewProjectModalIsOpen && (
-        <ExitProjectConfirmationModal
-          onClose={() => setStartNewProjectModalIsOpen(false)}
-        />
-      )}
     </>
   );
 }

frontend/src/components/features/sidebar/user-avatar.tsx

@@ -1,8 +1,8 @@
-import { Tooltip } from "@nextui-org/react";
 import { LoadingSpinner } from "#/components/shared/loading-spinner";
 import DefaultUserAvatar from "#/icons/default-user.svg?react";
 import { cn } from "#/utils/utils";
 import { Avatar } from "./avatar";
+import { TooltipButton } from "#/components/shared/buttons/tooltip-button";
 
 interface UserAvatarProps {
   onClick: () => void;
@@ -11,10 +11,11 @@ interface UserAvatarProps {
 }
 
 export function UserAvatar({ onClick, avatarUrl, isLoading }: UserAvatarProps) {
-  const buttonContent = (
-    <button
-      data-testid="user-avatar"
-      type="button"
+  return (
+    <TooltipButton
+      testId="user-avatar"
+      tooltip="Account settings"
+      ariaLabel="Account settings"
       onClick={onClick}
       className={cn(
         "w-8 h-8 rounded-full flex items-center justify-center border-2 border-gray-200",
@@ -30,12 +31,6 @@ export function UserAvatar({ onClick, avatarUrl, isLoading }: UserAvatarProps) {
         />
       )}
       {isLoading && <LoadingSpinner size="small" />}
-    </button>
-  );
-
-  return (
-    <Tooltip content="Account settings" closeDelay={100}>
-      {buttonContent}
-    </Tooltip>
+    </TooltipButton>
   );
 }

frontend/src/components/shared/buttons/all-hands-logo-button.tsx

@@ -12,7 +12,7 @@ export function AllHandsLogoButton({ onClick }: AllHandsLogoButtonProps) {
       ariaLabel="All Hands Logo"
       onClick={onClick}
     >
-      <AllHandsLogo width={34} height={23} />
+      <AllHandsLogo width={44} height={30} />
     </TooltipButton>
   );
 }

frontend/src/components/shared/buttons/exit-project-button.tsx

@@ -13,7 +13,7 @@ export function ExitProjectButton({ onClick }: ExitProjectButtonProps) {
       onClick={onClick}
       testId="new-project-button"
     >
-      <NewProjectIcon width={28} height={28} />
+      <NewProjectIcon width={26} height={26} />
     </TooltipButton>
   );
 }

frontend/src/components/shared/buttons/settings-button.tsx

@@ -1,4 +1,4 @@
-import CogTooth from "#/assets/cog-tooth";
+import { FaCog } from "react-icons/fa";
 import { TooltipButton } from "./tooltip-button";
 
 interface SettingsButtonProps {
@@ -13,7 +13,7 @@ export function SettingsButton({ onClick }: SettingsButtonProps) {
       ariaLabel="Settings"
       onClick={onClick}
     >
-      <CogTooth />
+      <FaCog size={24} />
     </TooltipButton>
   );
 }

frontend/src/components/shared/buttons/tooltip-button.tsx

@@ -1,5 +1,6 @@
 import { Tooltip } from "@nextui-org/react";
-import { ReactNode } from "react";
+import React, { ReactNode } from "react";
+import { cn } from "#/utils/utils";
 
 interface TooltipButtonProps {
   children: ReactNode;
@@ -8,6 +9,7 @@ interface TooltipButtonProps {
   href?: string;
   ariaLabel: string;
   testId?: string;
+  className?: React.HTMLAttributes<HTMLButtonElement>["className"];
 }
 
 export function TooltipButton({
@@ -17,6 +19,7 @@ export function TooltipButton({
   href,
   ariaLabel,
   testId,
+  className,
 }: TooltipButtonProps) {
   const buttonContent = (
     <button
@@ -24,7 +27,7 @@ export function TooltipButton({
       aria-label={ariaLabel}
       data-testid={testId}
       onClick={onClick}
-      className="w-8 h-8 rounded-full hover:opacity-80 flex items-center justify-center"
+      className={cn("hover:opacity-80", className)}
     >
       {children}
     </button>
@@ -35,7 +38,7 @@ export function TooltipButton({
       href={href}
       target="_blank"
       rel="noreferrer noopener"
-      className="w-8 h-8 rounded-full hover:opacity-80 flex items-center justify-center"
+      className={cn("hover:opacity-80", className)}
       aria-label={ariaLabel}
     >
       {children}
@@ -45,7 +48,7 @@ export function TooltipButton({
   );
 
   return (
-    <Tooltip content={tooltip} closeDelay={100}>
+    <Tooltip content={tooltip} closeDelay={100} placement="right">
       {content}
     </Tooltip>
   );

frontend/src/components/shared/inputs/advanced-option-switch.tsx

@@ -20,7 +20,7 @@ export function AdvancedOptionSwitch({
     <Switch
       isDisabled={isDisabled}
       name="use-advanced-options"
-      isSelected={showAdvancedOptions}
+      defaultSelected={showAdvancedOptions}
       onValueChange={setShowAdvancedOptions}
       classNames={{
         thumb: cn(

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

@@ -0,0 +1,52 @@
+import { useTranslation } from "react-i18next";
+import { Select, SelectItem } from "@nextui-org/react";
+
+interface RuntimeSizeSelectorProps {
+  isDisabled: boolean;
+  defaultValue?: number;
+}
+
+export function RuntimeSizeSelector({
+  isDisabled,
+  defaultValue,
+}: RuntimeSizeSelectorProps) {
+  const { t } = useTranslation();
+
+  return (
+    <fieldset className="flex flex-col gap-2">
+      <label
+        htmlFor="runtime-size"
+        className="font-[500] text-[#A3A3A3] text-xs"
+      >
+        {t("SETTINGS_FORM$RUNTIME_SIZE_LABEL")}
+      </label>
+      <Select
+        id="runtime-size"
+        name="runtime-size"
+        defaultSelectedKeys={[String(defaultValue || 1)]}
+        isDisabled={isDisabled}
+        aria-label={t("SETTINGS_FORM$RUNTIME_SIZE_LABEL")}
+        classNames={{
+          trigger: "bg-[#27272A] rounded-md text-sm px-3 py-[10px]",
+        }}
+      >
+        <SelectItem key="1" value={1}>
+          1x (2 core, 8G)
+        </SelectItem>
+        <SelectItem
+          key="2"
+          value={2}
+          isDisabled
+          classNames={{
+            description:
+              "whitespace-normal break-words min-w-[300px] max-w-[300px]",
+            base: "min-w-[300px] max-w-[300px]",
+          }}
+          description="Runtime sizes over 1 are disabled by default, please contact contact@all-hands.dev to get access to larger runtimes."
+        >
+          2x (4 core, 16G)
+        </SelectItem>
+      </Select>
+    </fieldset>
+  );
+}

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

@@ -21,6 +21,9 @@ import { ModalBackdrop } from "../modal-backdrop";
 import { ModelSelector } from "./model-selector";
 import { useSaveSettings } from "#/hooks/mutation/use-save-settings";
 
+import { RuntimeSizeSelector } from "./runtime-size-selector";
+import { useConfig } from "#/hooks/query/use-config";
+
 interface SettingsFormProps {
   disabled?: boolean;
   settings: Settings;
@@ -40,6 +43,7 @@ export function SettingsForm({
 }: SettingsFormProps) {
   const { mutateAsync: saveSettings } = useSaveSettings();
   const endSession = useEndSession();
+  const { data: config } = useConfig();
 
   const location = useLocation();
   const { t } = useTranslation();
@@ -97,6 +101,8 @@ export function SettingsForm({
     posthog.capture("settings_saved", {
       LLM_MODEL: newSettings.LLM_MODEL,
       LLM_API_KEY: newSettings.LLM_API_KEY ? "SET" : "UNSET",
+      REMOTE_RUNTIME_RESOURCE_FACTOR:
+        newSettings.REMOTE_RUNTIME_RESOURCE_FACTOR,
     });
   };
 
@@ -122,6 +128,8 @@ export function SettingsForm({
     }
   };
 
+  const isSaasMode = config?.APP_MODE === "saas";
+
   return (
     <div>
       <form
@@ -164,16 +172,21 @@ export function SettingsForm({
             isSet={settings.LLM_API_KEY === "SET"}
           />
 
-          {showAdvancedOptions && (
-            <AgentInput
-              isDisabled={!!disabled}
-              defaultValue={settings.AGENT}
-              agents={agents}
-            />
-          )}
-
           {showAdvancedOptions && (
             <>
+              <AgentInput
+                isDisabled={!!disabled}
+                defaultValue={settings.AGENT}
+                agents={agents}
+              />
+
+              {isSaasMode && (
+                <RuntimeSizeSelector
+                  isDisabled={!!disabled}
+                  defaultValue={settings.REMOTE_RUNTIME_RESOURCE_FACTOR}
+                />
+              )}
+
               <SecurityAnalyzerInput
                 isDisabled={!!disabled}
                 defaultValue={settings.SECURITY_ANALYZER}

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

@@ -16,7 +16,7 @@ export function SettingsModal({ onClose, settings }: SettingsModalProps) {
     <ModalBackdrop onClose={onClose}>
       <div
         data-testid="ai-config-modal"
-        className="bg-root-primary w-[384px] p-6 rounded-xl flex flex-col gap-2"
+        className="bg-root-primary min-w-[384px] max-w-[700px] p-6 rounded-xl flex flex-col gap-2"
       >
         {aiConfigOptions.error && (
           <p className="text-danger text-xs">{aiConfigOptions.error.message}</p>

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

@@ -2,12 +2,18 @@ import posthog from "posthog-js";
 import React from "react";
 import { io, Socket } from "socket.io-client";
 import EventLogger from "#/utils/event-logger";
-import { handleAssistantMessage } from "#/services/actions";
+import {
+  handleAssistantMessage,
+  handleStatusMessage,
+} from "#/services/actions";
 import { useRate } from "#/hooks/use-rate";
 import { OpenHandsParsedEvent } from "#/types/core";
-import { AgentStateChangeObservation } from "#/types/core/observations";
+import {
+  AssistantMessageAction,
+  UserMessageAction,
+} from "#/types/core/actions";
 
-const isOpenHandsMessage = (event: unknown): event is OpenHandsParsedEvent =>
+const isOpenHandsEvent = (event: unknown): event is OpenHandsParsedEvent =>
   typeof event === "object" &&
   event !== null &&
   "id" in event &&
@@ -15,10 +21,26 @@ const isOpenHandsMessage = (event: unknown): event is OpenHandsParsedEvent =>
   "message" in event &&
   "timestamp" in event;
 
-const isAgentStateChangeObservation = (
+const isUserMessage = (
   event: OpenHandsParsedEvent,
-): event is AgentStateChangeObservation =>
-  "observation" in event && event.observation === "agent_state_changed";
+): event is UserMessageAction =>
+  "source" in event &&
+  "type" in event &&
+  event.source === "user" &&
+  event.type === "message";
+
+const isAssistantMessage = (
+  event: OpenHandsParsedEvent,
+): event is AssistantMessageAction =>
+  "source" in event &&
+  "type" in event &&
+  event.source === "agent" &&
+  event.type === "message";
+
+const isMessageAction = (
+  event: OpenHandsParsedEvent,
+): event is UserMessageAction | AssistantMessageAction =>
+  isUserMessage(event) || isAssistantMessage(event);
 
 export enum WsClientProviderStatus {
   CONNECTED,
@@ -43,16 +65,28 @@ const WsClientContext = React.createContext<UseWsClient>({
 
 interface WsClientProviderProps {
   conversationId: string;
-  ghToken: string | null;
+}
+
+export function updateStatusWhenErrorMessagePresent(data: unknown) {
+  if (
+    data &&
+    typeof data === "object" &&
+    "message" in data &&
+    typeof data.message === "string"
+  ) {
+    handleStatusMessage({
+      type: "error",
+      message: data.message,
+      status_update: true,
+    });
+  }
 }
 
 export function WsClientProvider({
-  ghToken,
   conversationId,
   children,
 }: React.PropsWithChildren<WsClientProviderProps>) {
   const sioRef = React.useRef<Socket | null>(null);
-  const ghTokenRef = React.useRef<string | null>(ghToken);
   const [status, setStatus] = React.useState(
     WsClientProviderStatus.DISCONNECTED,
   );
@@ -74,7 +108,7 @@ export function WsClientProvider({
   }
 
   function handleMessage(event: Record<string, unknown>) {
-    if (isOpenHandsMessage(event) && !isAgentStateChangeObservation(event)) {
+    if (isOpenHandsEvent(event) && isMessageAction(event)) {
       messageRateHandler.record(new Date().getTime());
     }
     setEvents((prevEvents) => [...prevEvents, event]);
@@ -85,7 +119,7 @@ export function WsClientProvider({
     handleAssistantMessage(event);
   }
 
-  function handleDisconnect() {
+  function handleDisconnect(data: unknown) {
     setStatus(WsClientProviderStatus.DISCONNECTED);
     const sio = sioRef.current;
     if (!sio) {
@@ -93,13 +127,19 @@ export function WsClientProvider({
     }
     sio.io.opts.query = sio.io.opts.query || {};
     sio.io.opts.query.latest_event_id = lastEventRef.current?.id;
+    updateStatusWhenErrorMessagePresent(data);
   }
 
-  function handleError() {
-    posthog.capture("socket_error");
+  function handleError(data: unknown) {
     setStatus(WsClientProviderStatus.DISCONNECTED);
+    updateStatusWhenErrorMessagePresent(data);
+    posthog.capture("socket_error");
   }
 
+  React.useEffect(() => {
+    lastEventRef.current = null;
+  }, [conversationId]);
+
   React.useEffect(() => {
     if (!conversationId) {
       throw new Error("No conversation ID provided");
@@ -118,9 +158,6 @@ export function WsClientProvider({
 
     sio = io(baseUrl, {
       transports: ["websocket"],
-      auth: {
-        github_token: ghToken || undefined,
-      },
       query,
     });
     sio.on("connect", handleConnect);
@@ -130,7 +167,6 @@ export function WsClientProvider({
     sio.on("disconnect", handleDisconnect);
 
     sioRef.current = sio;
-    ghTokenRef.current = ghToken;
 
     return () => {
       sio.off("connect", handleConnect);
@@ -139,7 +175,7 @@ export function WsClientProvider({
       sio.off("connect_failed", handleError);
       sio.off("disconnect", handleDisconnect);
     };
-  }, [ghToken, conversationId]);
+  }, [conversationId]);
 
   React.useEffect(
     () => () => {

frontend/src/hooks/mutation/use-create-conversation.ts

@@ -13,13 +13,18 @@ export const useCreateConversation = () => {
   const { gitHubToken } = useAuth();
   const queryClient = useQueryClient();
 
-  const { selectedRepository, files } = useSelector(
+  const { selectedRepository, files, importedProjectZip } = useSelector(
     (state: RootState) => state.initialQuery,
   );
 
   return useMutation({
     mutationFn: (variables: { q?: string }) => {
-      if (!variables.q?.trim() && !selectedRepository && files.length === 0) {
+      if (
+        !variables.q?.trim() &&
+        !selectedRepository &&
+        files.length === 0 &&
+        !importedProjectZip
+      ) {
         throw new Error("No query provided");
       }
 

frontend/src/hooks/mutation/use-upload-files.ts

@@ -0,0 +1,16 @@
+import { useMutation } from "@tanstack/react-query";
+import OpenHands from "#/api/open-hands";
+import { useConversation } from "#/context/conversation-context";
+
+type UploadFilesArgs = {
+  files: File[];
+};
+
+export const useUploadFiles = () => {
+  const { conversationId } = useConversation();
+
+  return useMutation({
+    mutationFn: ({ files }: UploadFilesArgs) =>
+      OpenHands.uploadFiles(conversationId, files),
+  });
+};

frontend/src/hooks/query/get-conversation-permissions.ts

@@ -1,11 +1,11 @@
 import { useQuery } from "@tanstack/react-query";
 import OpenHands from "#/api/open-hands";
-import { MULTI_CONVO_UI_IS_ENABLED } from "#/utils/constants";
+import { MULTI_CONVERSATION_UI } from "#/utils/feature-flags";
 
 export const useUserConversation = (cid: string | null) =>
   useQuery({
     queryKey: ["user", "conversation", cid],
     queryFn: () => OpenHands.getConversation(cid!),
-    enabled: MULTI_CONVO_UI_IS_ENABLED && !!cid,
+    enabled: MULTI_CONVERSATION_UI && !!cid,
     retry: false,
   });

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

@@ -18,6 +18,8 @@ const getSettingsQueryFn = async () => {
         CONFIRMATION_MODE: apiSettings.confirmation_mode,
         SECURITY_ANALYZER: apiSettings.security_analyzer,
         LLM_API_KEY: apiSettings.llm_api_key,
+        REMOTE_RUNTIME_RESOURCE_FACTOR:
+          apiSettings.remote_runtime_resource_factor,
       };
     }
 

frontend/src/hooks/use-maybe-migrate-settings.ts

@@ -3,8 +3,8 @@
 import React from "react";
 import { useSettingsUpToDate } from "#/context/settings-up-to-date-context";
 import {
-  DEFAULT_SETTINGS,
   getCurrentSettingsVersion,
+  DEFAULT_SETTINGS,
   getLocalStorageSettings,
 } from "#/services/settings";
 import { useSaveSettings } from "./mutation/use-save-settings";