Merge branch 'main' into fix-cli-command-interruption

- Double-press Ctrl+C within 400ms to send interrupt to running command
- Single Ctrl+C pauses (legacy) when command running or not
- Honor CLI config in dialogs and avoid blocking event loop via to_thread
- Debounce interrupts with asyncio.Lock to prevent races
- Use bounded reverse search on EventStream with EventFilter; rely on exit_code
- Pass config through start_pause_listener; remove ad-hoc OpenHandsConfig()
- Update help text for clarity

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

.github/workflows/e2e-tests.yml

@@ -187,7 +187,6 @@ jobs:
             test_settings.py::test_github_token_configuration \
             test_conversation.py::test_conversation_start \
             test_browsing_catchphrase.py::test_browsing_catchphrase \
-            test_multi_conversation_resume.py::test_multi_conversation_resume \
             -v --no-header --capture=no --timeout=900
 
       - name: Upload test results

.github/workflows/ghcr-build.yml

@@ -225,7 +225,7 @@ jobs:
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
           TEST_IN_CI=true \
           RUN_AS_OPENHANDS=false \
-          poetry run pytest -n 0 -raRs --reruns 2 --reruns-delay 5 -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py --durations=10
+          poetry run pytest -n 7 -raRs --reruns 2 --reruns-delay 5 -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py --durations=10
         env:
           DEBUG: "1"
 
@@ -284,7 +284,7 @@ jobs:
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
           TEST_IN_CI=true \
           RUN_AS_OPENHANDS=true \
-          poetry run pytest -n 0 -raRs --reruns 2 --reruns-delay 5 -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py --durations=10
+          poetry run pytest -n 7 -raRs --reruns 2 --reruns-delay 5 -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py --durations=10
         env:
           DEBUG: "1"
 

.github/workflows/stale.yml

@@ -15,7 +15,7 @@ jobs:
           stale-issue-message: 'This issue is stale because it has been open for 40 days with no activity. Remove the stale label or leave a comment, otherwise it will be closed in 10 days.'
           stale-pr-message: 'This PR is stale because it has been open for 40 days with no activity. Remove the stale label or leave a comment, otherwise it will be closed in 10 days.'
           days-before-stale: 40
-          exempt-issue-labels: roadmap,backlog
+          exempt-issue-labels: 'roadmap'
           close-issue-message: 'This issue was automatically closed due to 50 days of inactivity. We do this to help keep the issues somewhat manageable and focus on active issues.'
           close-pr-message: 'This PR was closed because it had no activity for 50 days. If you feel this was closed in error, and you would like to continue the PR, please resubmit or let us know.'
           days-before-close: 10

.gitignore

@@ -257,5 +257,3 @@ containers/runtime/code
 
 # test results
 test-results
-.sessions
-.eval_sessions

Development.md

@@ -159,7 +159,7 @@ poetry run pytest ./tests/unit/test_*.py
 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:0.55-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.54-nikolaik`
 
 ## Develop inside Docker container
 

README.md

@@ -79,17 +79,17 @@ You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)
 You can also run OpenHands directly with Docker:
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.55-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.55-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.55
+    docker.all-hands.dev/all-hands-ai/openhands:0.54
 ```
 
 </details>
@@ -130,6 +130,7 @@ If you want to modify the OpenHands source code, check out [Development.md](http
 Having issues? The [Troubleshooting Guide](https://docs.all-hands.dev/usage/troubleshooting) can help.
 
 ## 📖 Documentation
+  <a href="https://deepwiki.com/All-Hands-AI/OpenHands"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki" title="Autogenerated Documentation by DeepWiki"></a>
 
 To learn more about the project, and for tips on using OpenHands,
 check out our [documentation](https://docs.all-hands.dev/usage/getting-started).

README_CN.md

@@ -51,17 +51,17 @@ OpenHands也可以使用Docker在本地系统上运行。
 
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.55-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.55-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.55
+    docker.all-hands.dev/all-hands-ai/openhands:0.54
 ```
 
 > **注意**: 如果您在0.44版本之前使用过OpenHands，您可能需要运行 `mv ~/.openhands-state ~/.openhands` 来将对话历史迁移到新位置。

README_JA.md

@@ -42,17 +42,17 @@ OpenHandsはDockerを利用してローカル環境でも実行できます。
 > 公共ネットワークで実行していますか？[Hardened Docker Installation Guide](https://docs.all-hands.dev/usage/runtimes/docker#hardened-docker-installation)を参照して、ネットワークバインディングの制限や追加のセキュリティ対策を実施してください。
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.55-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.55-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.55
+    docker.all-hands.dev/all-hands-ai/openhands:0.54
 ```
 
 **注**: バージョン0.44以前のOpenHandsを使用していた場合は、会話履歴を移行するために `mv ~/.openhands-state ~/.openhands` を実行してください。

config.template.toml

@@ -363,11 +363,10 @@ classpath = "my_package.my_module.MyCustomAgent"
 #confirmation_mode = false
 
 # The security analyzer to use (For Headless / CLI only -  In Web this is overridden by Session Init)
-# Available options: 'llm' (default), 'invariant'
-#security_analyzer = "llm"
+#security_analyzer = ""
 
 # Whether to enable security analyzer
-#enable_security_analyzer = true
+#enable_security_analyzer = false
 
 #################################### Condenser #################################
 # Condensers control how conversation history is managed and compressed when

containers/app/Dockerfile

@@ -58,34 +58,34 @@ RUN sed -i 's/^UID_MIN.*/UID_MIN 499/' /etc/login.defs
 # Default is 60000, but we've seen up to 200000
 RUN sed -i 's/^UID_MAX.*/UID_MAX 1000000/' /etc/login.defs
 
-RUN groupadd --gid $OPENHANDS_USER_ID openhands
+RUN groupadd --gid $OPENHANDS_USER_ID app
 RUN useradd -l -m -u $OPENHANDS_USER_ID --gid $OPENHANDS_USER_ID -s /bin/bash openhands && \
-    usermod -aG openhands openhands && \
+    usermod -aG app openhands && \
     usermod -aG sudo openhands && \
     echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
-RUN chown -R openhands:openhands /app && chmod -R 770 /app
-RUN sudo chown -R openhands:openhands $WORKSPACE_BASE && sudo chmod -R 770 $WORKSPACE_BASE
+RUN chown -R openhands:app /app && chmod -R 770 /app
+RUN sudo chown -R openhands:app $WORKSPACE_BASE && sudo chmod -R 770 $WORKSPACE_BASE
 USER openhands
 
 ENV VIRTUAL_ENV=/app/.venv \
     PATH="/app/.venv/bin:$PATH" \
     PYTHONPATH='/app'
 
-COPY --chown=openhands:openhands --chmod=770 --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
+COPY --chown=openhands:app --chmod=770 --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
 
-COPY --chown=openhands:openhands --chmod=770 ./microagents ./microagents
-COPY --chown=openhands:openhands --chmod=770 ./openhands ./openhands
-COPY --chown=openhands:openhands --chmod=777 ./openhands/runtime/plugins ./openhands/runtime/plugins
-COPY --chown=openhands:openhands pyproject.toml poetry.lock README.md MANIFEST.in LICENSE ./
+COPY --chown=openhands:app --chmod=770 ./microagents ./microagents
+COPY --chown=openhands:app --chmod=770 ./openhands ./openhands
+COPY --chown=openhands:app --chmod=777 ./openhands/runtime/plugins ./openhands/runtime/plugins
+COPY --chown=openhands:app pyproject.toml poetry.lock README.md MANIFEST.in LICENSE ./
 
 # This is run as "openhands" user, and will create __pycache__ with openhands:openhands ownership
 RUN python openhands/core/download.py # No-op to download assets
 # Add this line to set group ownership of all files/directories not already in "app" group
-# openhands:openhands -> openhands:openhands
-RUN find /app \! -group openhands -exec chgrp openhands {} +
+# openhands:openhands -> openhands:app
+RUN find /app \! -group app -exec chgrp app {} +
 
-COPY --chown=openhands:openhands --chmod=770 --from=frontend-builder /app/build ./frontend/build
-COPY --chown=openhands:openhands --chmod=770 ./containers/app/entrypoint.sh /app/entrypoint.sh
+COPY --chown=openhands:app --chmod=770 --from=frontend-builder /app/build ./frontend/build
+COPY --chown=openhands:app --chmod=770 ./containers/app/entrypoint.sh /app/entrypoint.sh
 
 USER root
 

containers/app/entrypoint.sh

@@ -54,7 +54,7 @@ else
       fi
     fi
   fi
-  usermod -aG openhands enduser
+  usermod -aG app enduser
   # get the user group of /var/run/docker.sock and set openhands to that group
   DOCKER_SOCKET_GID=$(stat -c '%g' /var/run/docker.sock)
   echo "Docker socket group id: $DOCKER_SOCKET_GID"

containers/dev/compose.yml

@@ -12,7 +12,7 @@ services:
       - SANDBOX_API_HOSTNAME=host.docker.internal
       - DOCKER_HOST_ADDR=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.55-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.54-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docker-compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.55-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik}
       #- SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234} # enable this only if you want a specific non-root sandbox user but you will have to manually adjust permissions of ~/.openhands for this user
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docs/usage/cloud/project-management/jira-dc-integration.mdx

@@ -1,5 +1,5 @@
 ---
-title: Jira Data Center Integration (Coming soon...)
+title: Jira Data Center Integration (Beta)
 description: Complete guide for setting up Jira Data Center integration with OpenHands Cloud, including service account creation, personal access token generation, webhook configuration, and workspace integration setup.
 ---
 

docs/usage/cloud/project-management/jira-integration.mdx

@@ -1,5 +1,5 @@
 ---
-title: Jira Cloud Integration (Coming soon...)
+title: Jira Cloud Integration
 description: Complete guide for setting up Jira Cloud integration with OpenHands Cloud, including service account creation, API token generation, webhook configuration, and workspace integration setup.
 ---
 

docs/usage/cloud/project-management/linear-integration.mdx

@@ -1,5 +1,5 @@
 ---
-title: Linear Integration (Coming soon...)
+title: Linear Integration
 description: Complete guide for setting up Linear integration with OpenHands Cloud, including service account creation, API key generation, webhook configuration, and workspace integration setup.
 ---
 

docs/usage/cloud/project-management/overview.mdx

@@ -1,5 +1,5 @@
 ---
-title: Project Management Tool Integrations (Coming soon...)
+title: Project Management Tool Integrations
 description: Overview of OpenHands Cloud integrations with project management platforms including Jira Cloud, Jira Data Center, and Linear. Learn about setup requirements, usage methods, and troubleshooting.
 ---
 
@@ -18,9 +18,9 @@ Integration requires two levels of setup:
 2. **Workspace Integration** - Self-service configuration through the OpenHands Cloud UI to link your OpenHands account to the target workspace
 
 ### Platform-Specific Setup Guides:
-- [Jira Cloud Integration (Coming soon...)](./jira-integration.md)
-- [Jira Data Center Integration (Coming soon...)](./jira-dc-integration.md)
-- [Linear Integration (Coming soon...)](./linear-integration.md)
+- [Jira Cloud Integration](./jira-integration.md)
+- [Jira Data Center Integration](./jira-dc-integration.md)
+- [Linear Integration](./linear-integration.md)
 
 ## Usage
 

docs/usage/confirmation-mode.mdx

@@ -1,52 +0,0 @@
-# Confirmation Mode and Security Analyzers
-
-OpenHands provides a security framework to help protect users from potentially risky actions through **Confirmation Mode** and **Security Analyzers**. This system analyzes agent actions and prompts users for confirmation when high-risk operations are detected.
-
-## Overview
-
-The security system consists of two main components:
-
-1. **Confirmation Mode**: When enabled, the agent will pause and ask for user confirmation before executing actions that are flagged as high-risk by the security analyzer.
-
-2. **Security Analyzers**: These are modules that evaluate the risk level of agent actions and determine whether user confirmation is required.
-
-## Configuration
-
-### CLI
-In CLI mode, confirmation is enabled by default. You will have an option to uses the LLM Analyzer and will automatically confirm LOW and MEDIUM risk actions, only prompting for HIGH risk actions.
-
-## Security Analyzers
-
-OpenHands includes multiple analyzers:
-
-- **No Analyzer**: Do not use any security analyzer. The agent will prompt you to confirm *EVERY* action.
-- **LLM Risk Analyzer** (default): Uses the same LLM as the agent to assess action risk levels
-- **Invariant Analyzer**: Uses Invariant Labs' policy engine to evaluate action traces against security policies
-
-### LLM Risk Analyzer
-The default analyzer that leverages the agent's LLM to evaluate the security risk of each action. It considers the action type, parameters, and context to assign risk levels.
-
-### Invariant Analyzer
-An advanced analyzer that:
-- Collects conversation events and parses them into a trace
-- Checks the trace against an Invariant policy to classify risk (low, medium, high)
-- Manages an Invariant server container automatically if needed
-- Supports optional browsing-alignment and harmful-content checks
-
-## How It Works
-
-1. **Action Analysis**: When the agent wants to perform an action, the selected security analyzer evaluates its risk level.
-
-2. **Risk Assessment**: The analyzer returns one of three risk levels:
-   - **LOW**: Action proceeds without confirmation
-   - **MEDIUM**: Action proceeds without confirmation (may be configurable in future)
-   - **HIGH**: Action is paused, and user confirmation is requested
-
-3. **User Confirmation**: For high-risk actions, a confirmation dialog appears with:
-   - Description of the action
-   - Risk assessment explanation
-   - Options to approve or deny action
-
-4. **Action Execution**: Based on user response:
-   - **Approve**: Action proceeds as planned
-   - **Deny**: Action is cancelled

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

@@ -87,13 +87,19 @@ source ~/.bashrc  # or source ~/.zshrc
 
 </AccordionGroup>
 
+3. Launch an interactive OpenHands conversation from the command line:
+```bash
+# If using uvx (recommended)
+uvx --python 3.12 --from openhands-ai openhands
+```
+
 <Note>
   If you have cloned the repository, you can also run the CLI directly using Poetry:
 
   poetry run openhands
 </Note>
 
-3. Set your model, API key, and other preferences using the UI (or alternatively environment variables, below).
+4. Set your model, API key, and other preferences using the UI (or alternatively environment variables, below).
 
 This command opens an interactive prompt where you can type tasks or commands and get responses from OpenHands.
 The first time you run the CLI, it will take you through configuring the required LLM
@@ -113,7 +119,7 @@ The conversation history will be saved in `~/.openhands/sessions`.
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.55-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e SANDBOX_VOLUMES=$SANDBOX_VOLUMES \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -122,7 +128,7 @@ docker run -it \
     -v ~/.openhands:/.openhands \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.55 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.54 \
     python -m openhands.cli.entry --override-cli-mode true
 ```
 

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

@@ -61,7 +61,7 @@ export GITHUB_TOKEN="your-token"  # Required for repository operations
 # Run OpenHands
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.55-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e SANDBOX_VOLUMES=$SANDBOX_VOLUMES \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -73,7 +73,7 @@ docker run -it \
     -v ~/.openhands:/.openhands \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.55 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.54 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/usage/llms/local-llms.mdx

@@ -68,23 +68,23 @@ Download and install the LM Studio desktop app from [lmstudio.ai](https://lmstud
 1. Check [the installation guide](/usage/local-setup) and ensure all prerequisites are met before running OpenHands, then run:
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.55-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.55-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.55
+    docker.all-hands.dev/all-hands-ai/openhands:0.54
 ```
 
 2. Wait until the server is running (see log below):
 ```
 Digest: sha256:e72f9baecb458aedb9afc2cd5bc935118d1868719e55d50da73190d3a85c674f
-Status: Image is up to date for docker.all-hands.dev/all-hands-ai/openhands:0.55
+Status: Image is up to date for docker.all-hands.dev/all-hands-ai/openhands:0.54
 Starting OpenHands...
 Running OpenHands as root
 14:22:13 - openhands:INFO: server_config.py:50 - Using config class None

docs/usage/local-setup.mdx

@@ -45,13 +45,6 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
   1. [Install WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
   2. Run `wsl --version` in powershell and confirm `Default Version: 2`.
 
-  **Ubuntu (Linux Distribution)**
-
-  1. Install Ubuntu: `wsl --install -d Ubuntu` in PowerShell as Administrator.
-  2. Restart computer when prompted.
-  3. Open Ubuntu from Start menu to complete setup.
-  4. Verify installation: `wsl --list` should show Ubuntu.
-
   **Docker Desktop**
 
   1. [Install Docker Desktop on Windows](https://docs.docker.com/desktop/setup/install/windows-install).
@@ -60,7 +53,7 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
   - Resources > WSL Integration: `Enable integration with my default WSL distro` is enabled.
 
   <Note>
-  The docker command below to start the app must be run inside the WSL terminal. Use `wsl -d Ubuntu` in PowerShell or search "Ubuntu" in the Start menu to access the Ubuntu terminal.
+  The docker command below to start the app must be run inside the WSL terminal.
   </Note>
 
   **Alternative: Windows without WSL**
@@ -116,17 +109,17 @@ Note that you'll still need `uv` installed for the default MCP servers to work p
 <Accordion title="Docker Command (Click to expand)">
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.55-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.55-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.55
+    docker.all-hands.dev/all-hands-ai/openhands:0.54
 ```
 
 </Accordion>

docs/usage/runtimes/e2b.mdx

@@ -22,7 +22,7 @@ SDK to spawn and control these sandboxes.
 
 You can use the E2B CLI to create a custom sandbox with a Dockerfile. Read the full guide
 [here](https://e2b.dev/docs/guide/custom-sandbox). The premade OpenHands sandbox for E2B is set up in the `containers`
-directory, and it's called `openhands`.
+directory. and it's called `openhands`.
 
 ## Debugging
 

docs/usage/troubleshooting/troubleshooting.mdx

@@ -38,16 +38,6 @@ On initial prompt, an error is seen with `Permission Denied` or `PermissionError
 * If mounting a local directory, ensure your `WORKSPACE_BASE` has the necessary permissions for the user running
   OpenHands.
 
-### On Linux, Getting ConnectTimeout Error
-
-**Description**
-
-When running on Linux, you might run into the error `ERROR:root:<class 'httpx.ConnectTimeout'>: timed out`.
-
-**Resolution**
-
-* Add the `--network host` to the docker run command.
-
 ### Internal Server Error. Ports are not available
 
 **Description**

evaluation/benchmarks/EDA/run_infer.py

@@ -9,8 +9,8 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -61,15 +61,18 @@ AGENT_CLS_TO_INST_SUFFIX = {
 def get_config(
     metadata: EvalMetadata,
 ) -> OpenHandsConfig:
-    # Create config with EDA-specific container image
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'python:3.12-bookworm'
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
-
-    # Override the container image for EDA
-    config.sandbox.base_container_image = 'python:3.12-bookworm'
-
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
     agent_config.enable_prompt_extensions = False

evaluation/benchmarks/agent_bench/run_infer.py

@@ -17,8 +17,8 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -41,12 +41,19 @@ from openhands.utils.async_utils import call_async_from_sync
 def get_config(
     metadata: EvalMetadata,
 ) -> OpenHandsConfig:
-    # Create config with agent_bench-specific container image
-    config = get_openhands_config_for_eval(metadata=metadata)
-
-    # Override the container image for agent_bench
-    config.sandbox.base_container_image = 'python:3.12-slim'
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'python:3.12-slim'
 
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
+        runtime=os.environ.get('RUNTIME', 'docker'),
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
+    )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
     agent_config.enable_prompt_extensions = False

evaluation/benchmarks/aider_bench/run_infer.py

@@ -18,7 +18,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -51,10 +50,15 @@ def get_config(
 ) -> OpenHandsConfig:
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = 'python:3.11-bookworm'
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
-        sandbox_config=sandbox_config,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime=os.environ.get('RUNTIME', 'docker'),
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/benchmarks/biocoder/run_infer.py

@@ -16,7 +16,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -62,10 +61,15 @@ def get_config(
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = BIOCODER_BENCH_CONTAINER_IMAGE
 
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/benchmarks/bird/run_infer.py

@@ -19,7 +19,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -76,10 +75,15 @@ def get_config(
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = 'python:3.12-bookworm'
 
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/benchmarks/browsing_delegation/run_infer.py

@@ -12,7 +12,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -41,8 +40,14 @@ def get_config(
     )
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = get_openhands_config_for_eval(
-        metadata=metadata, runtime='docker', sandbox_config=sandbox_config
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
+        runtime='docker',
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/benchmarks/commit0/run_infer.py

@@ -17,7 +17,6 @@ from evaluation.utils.shared import (
     codeact_user_response,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -115,11 +114,16 @@ def get_config(
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = base_container_image
 
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
-        sandbox_config=sandbox_config,
-        runtime=os.environ.get('RUNTIME', 'docker'),
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
+        max_iterations=metadata.max_iterations,
         enable_browser=RUN_WITH_BROWSING,
+        runtime=os.environ.get('RUNTIME', 'docker'),
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(
         update_llm_config_for_completions_logging(

evaluation/benchmarks/discoverybench/run_infer.py

@@ -18,7 +18,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -66,10 +65,15 @@ def get_config(
 ) -> OpenHandsConfig:
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/benchmarks/gaia/run_infer.py

@@ -23,7 +23,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -61,10 +60,15 @@ def get_config(
 ) -> OpenHandsConfig:
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = 'nikolaik/python-nodejs:python3.12-nodejs22'
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
-        sandbox_config=sandbox_config,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     if metadata.agent_config:

evaluation/benchmarks/gorilla/run_infer.py

@@ -13,7 +13,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -44,10 +43,15 @@ def get_config(
 ) -> OpenHandsConfig:
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/benchmarks/gpqa/run_infer.py

@@ -31,7 +31,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -65,10 +64,15 @@ def get_config(
 ) -> OpenHandsConfig:
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/benchmarks/humanevalfix/run_infer.py

@@ -24,7 +24,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -86,10 +85,15 @@ def get_config(
 ) -> OpenHandsConfig:
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/benchmarks/lca_ci_build_repair/eval_infer.py

@@ -16,7 +16,6 @@ import ruamel.yaml
 from evaluation.utils.shared import (
     EvalMetadata,
     get_default_sandbox_config_for_eval,
-    get_openhands_config_for_eval,
     make_metadata,
 )
 from openhands.core.config import (
@@ -38,10 +37,15 @@ def get_config(
 ) -> OpenHandsConfig:
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/benchmarks/lca_ci_build_repair/run_infer.py

@@ -23,7 +23,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -49,10 +48,15 @@ def get_config(
 ) -> OpenHandsConfig:
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/benchmarks/logic_reasoning/run_infer.py

@@ -11,7 +11,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -53,10 +52,15 @@ def get_config(
         '$OH_INTERPRETER_PATH -m pip install scitools-pyke'
     )
 
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/benchmarks/miniwob/run_infer.py

@@ -14,7 +14,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -59,10 +58,15 @@ def get_config(
 ) -> OpenHandsConfig:
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = 'xingyaoww/od-eval-miniwob:v1.0'
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime=os.environ.get('RUNTIME', 'docker'),
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(
         update_llm_config_for_completions_logging(

evaluation/benchmarks/mint/run_infer.py

@@ -16,7 +16,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -111,10 +110,15 @@ def get_config(
         f'$OH_INTERPRETER_PATH -m pip install {" ".join(MINT_DEPENDENCIES)}'
     )
 
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/benchmarks/ml_bench/run_infer.py

@@ -27,7 +27,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -81,10 +80,15 @@ def get_config(
 ) -> OpenHandsConfig:
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = 'public.ecr.aws/i5g0m1f6/ml-bench'
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/benchmarks/multi_swe_bench/eval_infer.py

@@ -23,7 +23,6 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     get_default_sandbox_config_for_eval,
-    get_openhands_config_for_eval,
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
@@ -88,9 +87,13 @@ def get_config(metadata: EvalMetadata, instance: pd.Series) -> OpenHandsConfig:
         dataset_name=metadata.dataset,
         instance_id=instance['instance_id'],
     )
-    config = get_openhands_config_for_eval(
+    config = OpenHandsConfig(
+        run_as_openhands=False,
         runtime=os.environ.get('RUNTIME', 'docker'),
-        sandbox_config=sandbox_config,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     return config
 

evaluation/benchmarks/multi_swe_bench/run_infer.py

@@ -21,7 +21,6 @@ from evaluation.utils.shared import (
     codeact_user_response,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     is_fatal_evaluation_error,
     make_metadata,
     prepare_dataset,
@@ -342,11 +341,16 @@ def get_config(
         instance_id=instance['instance_id'],
     )
 
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
+        max_iterations=metadata.max_iterations,
         enable_browser=RUN_WITH_BROWSING,
         runtime=os.environ.get('RUNTIME', 'docker'),
-        sandbox_config=sandbox_config,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(
         update_llm_config_for_completions_logging(

evaluation/benchmarks/nocode_bench/run_infer_nc.py

@@ -31,7 +31,6 @@ from evaluation.utils.shared import (
     codeact_user_response,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     is_fatal_evaluation_error,
     make_metadata,
     prepare_dataset,
@@ -175,10 +174,15 @@ def get_config(
         instance_id=instance['instance_id'],
     )
 
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
+        max_iterations=metadata.max_iterations,
         runtime=os.environ.get('RUNTIME', 'docker'),
-        sandbox_config=sandbox_config,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
 
     config.set_llm_config(

evaluation/benchmarks/scienceagentbench/run_infer.py

@@ -13,7 +13,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -65,10 +64,16 @@ def get_config(
     sandbox_config.base_container_image = (
         'docker.io/xingyaoww/openhands-eval-scienceagentbench'
     )
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime=os.environ.get('RUNTIME', 'docker'),
-        sandbox_config=sandbox_config,
+        max_budget_per_task=4,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(
         update_llm_config_for_completions_logging(

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -19,7 +19,6 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     get_default_sandbox_config_for_eval,
-    get_openhands_config_for_eval,
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
@@ -84,9 +83,13 @@ def get_config(metadata: EvalMetadata, instance: pd.Series) -> OpenHandsConfig:
         dataset_name=metadata.dataset,
         instance_id=instance['instance_id'],
     )
-    config = get_openhands_config_for_eval(
+    config = OpenHandsConfig(
+        run_as_openhands=False,
         runtime=os.environ.get('RUNTIME', 'docker'),
-        sandbox_config=sandbox_config,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     return config
 

evaluation/benchmarks/swe_bench/run_infer.py

@@ -32,7 +32,6 @@ from evaluation.utils.shared import (
     codeact_user_response,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     is_fatal_evaluation_error,
     make_metadata,
     prepare_dataset,
@@ -228,11 +227,16 @@ def get_config(
         instance_id=instance['instance_id'],
     )
 
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
+        max_iterations=metadata.max_iterations,
         enable_browser=RUN_WITH_BROWSING,
         runtime=os.environ.get('RUNTIME', 'docker'),
-        sandbox_config=sandbox_config,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
 
     config.set_llm_config(

evaluation/benchmarks/swe_bench/run_localize.py

@@ -20,7 +20,6 @@ from evaluation.utils.shared import (
     codeact_user_response,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     is_fatal_evaluation_error,
     make_metadata,
     prepare_dataset,
@@ -200,11 +199,16 @@ def get_config(
         'REPO_PATH': f'/workspace/{workspace_dir_name}/',
     }
 
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
+        max_iterations=metadata.max_iterations,
         enable_browser=RUN_WITH_BROWSING,
         runtime=os.environ.get('RUNTIME', 'docker'),
-        sandbox_config=sandbox_config,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(
         update_llm_config_for_completions_logging(

evaluation/benchmarks/swe_bench/scripts/rollout_swegym.sh

@@ -13,7 +13,6 @@ N_RUNS=${4:-1}
 export EXP_NAME=$EXP_NAME
 # use 2x resources for rollout since some codebases are pretty resource-intensive
 export DEFAULT_RUNTIME_RESOURCE_FACTOR=2
-export ITERATIVE_EVAL_MODE=false
 echo "MODEL: $MODEL"
 echo "EXP_NAME: $EXP_NAME"
 DATASET="SWE-Gym/SWE-Gym"  # change this to the "/SWE-Gym-Lite" if you want to rollout the lite subset

evaluation/benchmarks/testgeneval/eval_infer.py

@@ -37,7 +37,6 @@ from evaluation.benchmarks.testgeneval.utils import load_testgeneval_dataset
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
-    get_openhands_config_for_eval,
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
@@ -59,21 +58,20 @@ def get_config(instance: pd.Series) -> OpenHandsConfig:
         f'Invalid container image for instance {instance["instance_id_swebench"]}.'
     )
     logger.info(f'Using instance container image: {base_container_image}.')
-
-    # Create custom sandbox config for testgeneval with specific requirements
-    sandbox_config = SandboxConfig(
-        base_container_image=base_container_image,
-        use_host_network=False,
-        timeout=1800,  # Longer timeout than default (300)
-        api_key=os.environ.get('ALLHANDS_API_KEY'),
-        remote_runtime_api_url=os.environ.get(
-            'SANDBOX_REMOTE_RUNTIME_API_URL', 'http://localhost:8000'
+    return OpenHandsConfig(
+        run_as_openhands=False,
+        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        sandbox=SandboxConfig(
+            base_container_image=base_container_image,
+            use_host_network=False,
+            timeout=1800,
+            api_key=os.environ.get('ALLHANDS_API_KEY'),
+            remote_runtime_api_url=os.environ.get(
+                'SANDBOX_REMOTE_RUNTIME_API_URL', 'http://localhost:8000'
+            ),
         ),
-    )
-
-    return get_openhands_config_for_eval(
-        sandbox_config=sandbox_config,
-        runtime=os.environ.get('RUNTIME', 'docker'),  # Different default runtime
+        workspace_base=None,
+        workspace_mount_path=None,
     )
 
 

evaluation/benchmarks/testgeneval/run_infer.py

@@ -25,7 +25,6 @@ from evaluation.utils.shared import (
     assert_and_raise,
     codeact_user_response,
     get_metrics,
-    get_openhands_config_for_eval,
     is_fatal_evaluation_error,
     make_metadata,
     prepare_dataset,
@@ -127,26 +126,29 @@ def get_config(
         f'Submit an issue on https://github.com/All-Hands-AI/OpenHands if you run into any issues.'
     )
 
-    sandbox_config = SandboxConfig(
-        base_container_image=base_container_image,
-        enable_auto_lint=True,
-        use_host_network=False,
-        # large enough timeout, since some testcases take very long to run
-        timeout=300,
-        # Add platform to the sandbox config to solve issue 4401
-        platform='linux/amd64',
-        api_key=os.environ.get('ALLHANDS_API_KEY', None),
-        remote_runtime_api_url=os.environ.get(
-            'SANDBOX_REMOTE_RUNTIME_API_URL', 'http://localhost:8000'
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
+        max_iterations=metadata.max_iterations,
+        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        sandbox=SandboxConfig(
+            base_container_image=base_container_image,
+            enable_auto_lint=True,
+            use_host_network=False,
+            # large enough timeout, since some testcases take very long to run
+            timeout=300,
+            # Add platform to the sandbox config to solve issue 4401
+            platform='linux/amd64',
+            api_key=os.environ.get('ALLHANDS_API_KEY', None),
+            remote_runtime_api_url=os.environ.get(
+                'SANDBOX_REMOTE_RUNTIME_API_URL', 'http://localhost:8000'
+            ),
+            keep_runtime_alive=False,
+            remote_runtime_init_timeout=3600,
         ),
-        keep_runtime_alive=False,
-        remote_runtime_init_timeout=3600,
-    )
-
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
-        sandbox_config=sandbox_config,
-        runtime=os.environ.get('RUNTIME', 'docker'),
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(
         update_llm_config_for_completions_logging(

evaluation/benchmarks/the_agent_company/run_infer.py

@@ -12,10 +12,7 @@ import tempfile
 import yaml
 from browsing import pre_login
 
-from evaluation.utils.shared import (
-    get_default_sandbox_config_for_eval,
-    get_openhands_config_for_eval,
-)
+from evaluation.utils.shared import get_default_sandbox_config_for_eval
 from openhands.controller.state.state import State
 from openhands.core.config import (
     LLMConfig,
@@ -45,17 +42,19 @@ def get_config(
     sandbox_config.enable_auto_lint = True
     # If the web services are running on the host machine, this must be set to True
     sandbox_config.use_host_network = True
-    config = get_openhands_config_for_eval(
+    config = OpenHandsConfig(
+        run_as_openhands=False,
+        max_budget_per_task=4,
         max_iterations=100,
+        save_trajectory_path=os.path.join(
+            mount_path_on_host, f'traj_{task_short_name}.json'
+        ),
+        sandbox=sandbox_config,
         # we mount trajectories path so that trajectories, generated by OpenHands
         # controller, can be accessible to the evaluator file in the runtime container
-        sandbox_config=sandbox_config,
         workspace_mount_path=mount_path_on_host,
+        workspace_mount_path_in_sandbox='/outputs',
     )
-    config.save_trajectory_path = os.path.join(
-        mount_path_on_host, f'traj_{task_short_name}.json'
-    )
-    config.max_budget_per_task = 4
     config.set_llm_config(llm_config)
     if agent_config:
         config.set_agent_config(agent_config)

evaluation/benchmarks/toolqa/run_infer.py

@@ -12,7 +12,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -45,10 +44,15 @@ def get_config(
 ) -> OpenHandsConfig:
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/benchmarks/visual_swe_bench/run_infer.py

@@ -20,7 +20,6 @@ from evaluation.utils.shared import (
     codeact_user_response,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     is_fatal_evaluation_error,
     make_metadata,
     prepare_dataset,
@@ -161,11 +160,16 @@ def get_config(
         instance_id=instance['instance_id'],
     )
 
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
+        max_iterations=metadata.max_iterations,
         enable_browser=RUN_WITH_BROWSING,
         runtime=os.environ.get('RUNTIME', 'docker'),
-        sandbox_config=sandbox_config,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(
         update_llm_config_for_completions_logging(

evaluation/benchmarks/visualwebarena/run_infer.py

@@ -13,7 +13,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -74,10 +73,16 @@ def get_config(
         'VWA_WIKIPEDIA': f'{base_url}:8888',
         'VWA_HOMEPAGE': f'{base_url}:4399',
     }
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
+        attach_to_existing=True,
     )
     config.set_llm_config(
         update_llm_config_for_completions_logging(

evaluation/benchmarks/webarena/run_infer.py

@@ -13,7 +13,6 @@ from evaluation.utils.shared import (
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -66,10 +65,15 @@ def get_config(
         'MAP': f'{base_url}:3000',
         'HOMEPAGE': f'{base_url}:4399',
     }
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime='docker',
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)

evaluation/integration_tests/run_infer.py

@@ -10,7 +10,6 @@ from evaluation.utils.shared import (
     EvalOutput,
     get_default_sandbox_config_for_eval,
     get_metrics,
-    get_openhands_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -46,12 +45,18 @@ def get_config(
 ) -> OpenHandsConfig:
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.platform = 'linux/amd64'
-    config = get_openhands_config_for_eval(
-        metadata=metadata,
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
         runtime=os.environ.get('RUNTIME', 'docker'),
-        sandbox_config=sandbox_config,
+        max_iterations=metadata.max_iterations,
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
+        # debug
+        debug=True,
     )
-    config.debug = True
     config.set_llm_config(
         update_llm_config_for_completions_logging(
             metadata.llm_config, metadata.eval_output_dir, instance_id

evaluation/utils/scripts/aggregate_token_usage.py

@@ -1,209 +0,0 @@
-#!/usr/bin/env python3
-"""
-Script to aggregate token usage metrics from LLM completion files.
-
-Usage:
-    python aggregate_token_usage.py <directory_path> [--input-cost <cost>] [--output-cost <cost>] [--cached-cost <cost>]
-
-Arguments:
-    directory_path: Path to the directory containing completion files
-    --input-cost: Cost per input token (default: 0.0)
-    --output-cost: Cost per output token (default: 0.0)
-    --cached-cost: Cost per cached token (default: 0.0)
-"""
-
-import argparse
-import json
-import os
-from pathlib import Path
-
-
-def aggregate_token_usage(
-    directory_path, input_cost=0.0, output_cost=0.0, cached_cost=0.0
-):
-    """
-    Aggregate token usage metrics from all JSON completion files in the directory.
-
-    Args:
-        directory_path (str): Path to directory containing completion files
-        input_cost (float): Cost per input token
-        output_cost (float): Cost per output token
-        cached_cost (float): Cost per cached token
-    """
-
-    # Initialize counters
-    totals = {
-        'input_tokens': 0,
-        'output_tokens': 0,
-        'cached_tokens': 0,
-        'total_tokens': 0,
-        'files_processed': 0,
-        'files_with_errors': 0,
-        'cost': 0,
-    }
-
-    # Find all JSON files recursively
-    json_files = list(Path(directory_path).rglob('*.json'))
-
-    print(f'Found {len(json_files)} JSON files to process...')
-
-    for json_file in json_files:
-        try:
-            with open(json_file, 'r', encoding='utf-8') as f:
-                data = json.load(f)
-
-            # Look for usage data in response or fncall_response
-            usage_data = None
-            if (
-                'response' in data
-                and isinstance(data['response'], dict)
-                and 'usage' in data['response']
-            ):
-                usage_data = data['response']['usage']
-            elif (
-                'fncall_response' in data
-                and isinstance(data['fncall_response'], dict)
-                and 'usage' in data['fncall_response']
-            ):
-                usage_data = data['fncall_response']['usage']
-
-            if usage_data:
-                # Extract token counts
-                completion_tokens = usage_data.get('completion_tokens', 0)
-                prompt_tokens = usage_data.get('prompt_tokens', 0)
-                cached_tokens = usage_data.get('cached_tokens', 0)
-
-                # Handle cases where cached_tokens might be in prompt_tokens_details
-                if cached_tokens == 0 and 'prompt_tokens_details' in usage_data:
-                    details = usage_data['prompt_tokens_details']
-                    if isinstance(details, dict) and 'cached_tokens' in details:
-                        cached_tokens = details.get('cached_tokens', 0) or 0
-
-                # Calculate non-cached input tokens
-                non_cached_input = prompt_tokens - cached_tokens
-
-                # Update totals
-                totals['input_tokens'] += non_cached_input
-                totals['output_tokens'] += completion_tokens
-                totals['cached_tokens'] += cached_tokens
-                totals['total_tokens'] += prompt_tokens + completion_tokens
-
-            if 'cost' in data:
-                totals['cost'] += data['cost']
-            totals['files_processed'] += 1
-
-            # Progress indicator
-            if totals['files_processed'] % 1000 == 0:
-                print(f'Processed {totals["files_processed"]} files...')
-
-        except Exception as e:
-            totals['files_with_errors'] += 1
-            if totals['files_with_errors'] <= 5:  # Only show first 5 errors
-                print(f'Error processing {json_file}: {e}')
-
-    # Calculate costs
-    input_cost_total = totals['input_tokens'] * input_cost
-    output_cost_total = totals['output_tokens'] * output_cost
-    cached_cost_total = totals['cached_tokens'] * cached_cost
-    total_cost = input_cost_total + output_cost_total + cached_cost_total
-
-    # Print results
-    print('\n' + '=' * 60)
-    print('TOKEN USAGE AGGREGATION RESULTS')
-    print('=' * 60)
-    print(f'Files processed: {totals["files_processed"]:,}')
-    print(f'Files with errors: {totals["files_with_errors"]:,}')
-    print()
-    print('TOKEN COUNTS:')
-    print(f'  Input tokens (non-cached):             {totals["input_tokens"]:,}')
-    print(f'  Output tokens:                         {totals["output_tokens"]:,}')
-    print(f'  Cached tokens:                         {totals["cached_tokens"]:,}')
-    print(f'  Total tokens:                          {totals["total_tokens"]:,}')
-    print(f'  Total costs (based on returned value): ${totals["cost"]:.6f}')
-    print()
-
-    if input_cost > 0 or output_cost > 0 or cached_cost > 0:
-        print('COST CALCULATED BASED ON PROVIDED RATE:')
-        print(
-            f'  Input cost:   ${input_cost_total:.6f} ({totals["input_tokens"]:,} × ${input_cost:.6f})'
-        )
-        print(
-            f'  Output cost:  ${output_cost_total:.6f} ({totals["output_tokens"]:,} × ${output_cost:.6f})'
-        )
-        print(
-            f'  Cached cost:  ${cached_cost_total:.6f} ({totals["cached_tokens"]:,} × ${cached_cost:.6f})'
-        )
-        print(f'  Total cost:   ${total_cost:.6f}')
-        print()
-
-    print('SUMMARY:')
-    print(
-        f'  Total input tokens:  {totals["input_tokens"] + totals["cached_tokens"]:,}'
-    )
-    print(f'  Total output tokens: {totals["output_tokens"]:,}')
-    print(f'  Grand total tokens:  {totals["total_tokens"]:,}')
-
-    return totals
-
-
-def main():
-    parser = argparse.ArgumentParser(
-        description='Aggregate token usage metrics from LLM completion files',
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-        epilog="""
-Examples:
-  python aggregate_token_usage.py /path/to/completions
-  python aggregate_token_usage.py /path/to/completions --input-cost 0.000001 --output-cost 0.000002
-  python aggregate_token_usage.py /path/to/completions --input-cost 0.000001 --output-cost 0.000002 --cached-cost 0.0000005
-        """,
-    )
-
-    parser.add_argument(
-        'directory_path', help='Path to directory containing completion files'
-    )
-
-    parser.add_argument(
-        '--input-cost',
-        type=float,
-        default=0.0,
-        help='Cost per input token (default: 0.0)',
-    )
-
-    parser.add_argument(
-        '--output-cost',
-        type=float,
-        default=0.0,
-        help='Cost per output token (default: 0.0)',
-    )
-
-    parser.add_argument(
-        '--cached-cost',
-        type=float,
-        default=0.0,
-        help='Cost per cached token (default: 0.0)',
-    )
-
-    args = parser.parse_args()
-
-    # Validate directory path
-    if not os.path.exists(args.directory_path):
-        print(f"Error: Directory '{args.directory_path}' does not exist.")
-        return 1
-
-    if not os.path.isdir(args.directory_path):
-        print(f"Error: '{args.directory_path}' is not a directory.")
-        return 1
-
-    # Run aggregation
-    try:
-        aggregate_token_usage(
-            args.directory_path, args.input_cost, args.output_cost, args.cached_cost
-        )
-        return 0
-    except Exception as e:
-        print(f'Error during aggregation: {e}')
-        return 1
-
-
-if __name__ == '__main__':
-    exit(main())

evaluation/utils/shared.py

@@ -703,79 +703,3 @@ def get_default_sandbox_config_for_eval() -> SandboxConfig:
         remote_runtime_enable_retries=True,
         remote_runtime_class='sysbox',
     )
-
-
-def get_openhands_config_for_eval(
-    metadata: EvalMetadata | None = None,
-    sandbox_config: SandboxConfig | None = None,
-    runtime: str | None = None,
-    max_iterations: int | None = None,
-    default_agent: str | None = None,
-    enable_browser: bool = False,
-    workspace_base: str | None = None,
-    workspace_mount_path: str | None = None,
-):
-    """Create an OpenHandsConfig with common patterns used across evaluation scripts.
-
-    This function provides a standardized way to create OpenHands configurations
-    for evaluation runs, with sensible defaults that match the patterns used in
-    most run_infer.py scripts. Individual evaluation scripts can override specific
-    attributes as needed.
-
-    Args:
-        metadata: EvalMetadata containing agent class, max iterations, etc.
-        sandbox_config: Custom sandbox config. If None, uses get_default_sandbox_config_for_eval()
-        runtime: Runtime type. If None, uses environment RUNTIME or 'docker'
-        max_iterations: Max iterations for the agent. If None, uses metadata.max_iterations
-        default_agent: Agent class name. If None, uses metadata.agent_class
-        enable_browser: Whether to enable browser functionality
-        workspace_base: Workspace base path. Defaults to None
-        workspace_mount_path: Workspace mount path. Defaults to None
-
-    Returns:
-        OpenHandsConfig: Configured for evaluation with eval-specific overrides applied
-    """
-    # Defer import to avoid circular imports at module load time
-    from openhands.core.config.openhands_config import (
-        OpenHandsConfig as _OHConfig,  # type: ignore
-    )
-
-    # Use provided sandbox config or get default
-    if sandbox_config is None:
-        sandbox_config = get_default_sandbox_config_for_eval()
-
-    # Extract values from metadata if provided
-    if metadata is not None:
-        if max_iterations is None:
-            max_iterations = metadata.max_iterations
-        if default_agent is None:
-            default_agent = metadata.agent_class
-
-    # Use environment runtime or default
-    if runtime is None:
-        runtime = os.environ.get('RUNTIME', 'docker')
-
-    # Provide sensible defaults if still None
-    if default_agent is None:
-        default_agent = 'CodeActAgent'
-    if max_iterations is None:
-        max_iterations = 50
-
-    # Always use repo-local .eval_sessions directory (absolute path)
-    eval_store = os.path.abspath(os.path.join(os.getcwd(), '.eval_sessions'))
-
-    # Create the base config with evaluation-specific overrides
-    config = _OHConfig(
-        default_agent=default_agent,
-        run_as_openhands=False,
-        runtime=runtime,
-        max_iterations=max_iterations,
-        enable_browser=enable_browser,
-        sandbox=sandbox_config,
-        workspace_base=workspace_base,
-        workspace_mount_path=workspace_mount_path,
-        file_store='local',
-        file_store_path=eval_store,
-    )
-
-    return config

frontend/__tests__/components/features/home/repo-connector.test.tsx

@@ -54,14 +54,12 @@ const MOCK_RESPOSITORIES: GitRepository[] = [
     full_name: "rbren/polaris",
     git_provider: "github",
     is_public: true,
-    main_branch: "main",
   },
   {
     id: "2",
     full_name: "All-Hands-AI/OpenHands",
     git_provider: "github",
     is_public: true,
-    main_branch: "main",
   },
 ];
 
@@ -101,15 +99,16 @@ describe("RepoConnector", () => {
 
     // First select the provider
     const providerDropdown = await waitFor(() =>
-      screen.getByTestId("git-provider-dropdown"),
+      screen.getByText("Select Provider"),
     );
     await userEvent.click(providerDropdown);
-    await userEvent.click(screen.getByText("GitHub"));
+    await userEvent.click(screen.getByText("Github"));
 
     // Then interact with the repository dropdown
-    const repoInput = await waitFor(() =>
-      screen.getByTestId("git-repo-dropdown"),
+    const repoDropdown = await waitFor(() =>
+      screen.getByTestId("repo-dropdown"),
     );
+    const repoInput = within(repoDropdown).getByRole("combobox");
     await userEvent.click(repoInput);
 
     // Wait for the options to be loaded and displayed
@@ -135,23 +134,23 @@ describe("RepoConnector", () => {
     expect(launchButton).toBeDisabled();
 
     // Mock the repository branches API call
-    vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue({ branches: [
+    vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue([
       { name: "main", commit_sha: "123", protected: false },
       { name: "develop", commit_sha: "456", protected: false },
-    ], has_next_page: false, current_page: 1, per_page: 30, total_count: 2 });
+    ]);
 
     // First select the provider
     const providerDropdown = await waitFor(() =>
-      screen.getByTestId("git-provider-dropdown"),
+      screen.getByText("Select Provider"),
     );
     await userEvent.click(providerDropdown);
-    await userEvent.click(screen.getByText("GitHub"));
+    await userEvent.click(screen.getByText("Github"));
 
     // Then select the repository
-    const repoInput = await waitFor(() =>
-      screen.getByTestId("git-repo-dropdown"),
+    const repoDropdown = await waitFor(() =>
+      screen.getByTestId("repo-dropdown"),
     );
-
+    const repoInput = within(repoDropdown).getByRole("combobox");
     await userEvent.click(repoInput);
 
     // Wait for the options to be loaded and displayed
@@ -162,8 +161,7 @@ describe("RepoConnector", () => {
 
     // Wait for the branch to be auto-selected
     await waitFor(() => {
-      const branchInput = screen.getByTestId("git-branch-dropdown-input");
-      expect(branchInput).toHaveValue("main");
+      expect(screen.getByText("main")).toBeInTheDocument();
     });
 
     expect(launchButton).toBeEnabled();
@@ -226,19 +224,6 @@ describe("RepoConnector", () => {
 
   it("should create a conversation and redirect with the selected repo when pressing the launch button", async () => {
     const createConversationSpy = vi.spyOn(OpenHands, "createConversation");
-    createConversationSpy.mockResolvedValue({
-      conversation_id: "mock-conversation-id",
-      title: "Test Conversation",
-      selected_repository: "user/repo1",
-      selected_branch: "main",
-      git_provider: "github",
-      last_updated_at: "2023-01-01T00:00:00Z",
-      created_at: "2023-01-01T00:00:00Z",
-      status: "STARTING",
-      runtime_status: null,
-      url: null,
-      session_api_key: null,
-    });
     const retrieveUserGitRepositoriesSpy = vi.spyOn(
       OpenHands,
       "retrieveUserGitRepositories",
@@ -259,23 +244,23 @@ describe("RepoConnector", () => {
     expect(createConversationSpy).not.toHaveBeenCalled();
 
     // Mock the repository branches API call
-    vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue({ branches: [
+    vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue([
       { name: "main", commit_sha: "123", protected: false },
       { name: "develop", commit_sha: "456", protected: false },
-    ], has_next_page: false, current_page: 1, per_page: 30, total_count: 2 });
+    ]);
 
     // First select the provider
     const providerDropdown = await waitFor(() =>
-      screen.getByTestId("git-provider-dropdown"),
+      screen.getByText("Select Provider"),
     );
     await userEvent.click(providerDropdown);
-    await userEvent.click(screen.getByText("GitHub"));
+    await userEvent.click(screen.getByText("Github"));
 
     // Then select the repository
-    const repoInput = await waitFor(() =>
-      within(repoConnector).getByTestId("git-repo-dropdown"),
+    const repoDropdown = await waitFor(() =>
+      within(repoConnector).getByTestId("repo-dropdown"),
     );
-
+    const repoInput = within(repoDropdown).getByRole("combobox");
     await userEvent.click(repoInput);
 
     // Wait for the options to be loaded and displayed
@@ -286,8 +271,7 @@ describe("RepoConnector", () => {
 
     // Wait for the branch to be auto-selected
     await waitFor(() => {
-      const branchInput = screen.getByTestId("git-branch-dropdown-input");
-      expect(branchInput).toHaveValue("main");
+      expect(screen.getByText("main")).toBeInTheDocument();
     });
 
     await userEvent.click(launchButton);
@@ -304,8 +288,6 @@ describe("RepoConnector", () => {
   });
 
   it("should change the launch button text to 'Loading...' when creating a conversation", async () => {
-    const createConversationSpy = vi.spyOn(OpenHands, "createConversation");
-    createConversationSpy.mockImplementation(() => new Promise(() => {})); // Never resolves to keep loading state
     const retrieveUserGitRepositoriesSpy = vi.spyOn(
       OpenHands,
       "retrieveUserGitRepositories",
@@ -316,10 +298,10 @@ describe("RepoConnector", () => {
     });
 
     // Mock the repository branches API call
-    vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue({ branches: [
+    vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue([
       { name: "main", commit_sha: "123", protected: false },
       { name: "develop", commit_sha: "456", protected: false },
-    ], has_next_page: false, current_page: 1, per_page: 30, total_count: 2 });
+    ]);
 
     renderRepoConnector();
 
@@ -327,16 +309,16 @@ describe("RepoConnector", () => {
 
     // First select the provider
     const providerDropdown = await waitFor(() =>
-      screen.getByTestId("git-provider-dropdown"),
+      screen.getByText("Select Provider"),
     );
     await userEvent.click(providerDropdown);
-    await userEvent.click(screen.getByText("GitHub"));
+    await userEvent.click(screen.getByText("Github"));
 
     // Then select the repository
-    const repoInput = await waitFor(() =>
-      screen.getByTestId("git-repo-dropdown"),
+    const repoDropdown = await waitFor(() =>
+      screen.getByTestId("repo-dropdown"),
     );
-
+    const repoInput = within(repoDropdown).getByRole("combobox");
     await userEvent.click(repoInput);
 
     // Wait for the options to be loaded and displayed
@@ -347,8 +329,7 @@ describe("RepoConnector", () => {
 
     // Wait for the branch to be auto-selected
     await waitFor(() => {
-      const branchInput = screen.getByTestId("git-branch-dropdown-input");
-      expect(branchInput).toHaveValue("main");
+      expect(screen.getByText("main")).toBeInTheDocument();
     });
 
     await userEvent.click(launchButton);
@@ -377,7 +358,7 @@ describe("RepoConnector", () => {
     const goToSettingsButton = await screen.findByTestId(
       "navigate-to-settings-button",
     );
-    const dropdown = screen.queryByTestId("git-repo-dropdown");
+    const dropdown = screen.queryByTestId("repo-dropdown");
     const launchButton = screen.queryByTestId("repo-launch-button");
     const providerLinks = screen.queryAllByText(/add git(hub|lab) repos/i);
 

frontend/__tests__/components/features/home/repo-selection-form.test.tsx

@@ -151,7 +151,7 @@ describe("RepositorySelectionForm", () => {
     });
 
     renderForm();
-    expect(await screen.findByTestId("git-repo-dropdown")).toBeInTheDocument();
+    expect(await screen.findByTestId("repo-dropdown")).toBeInTheDocument();
   });
 
   it("shows error message when repository fetch fails", async () => {
@@ -168,10 +168,10 @@ describe("RepositorySelectionForm", () => {
     renderForm();
 
     expect(
-      await screen.findByTestId("dropdown-error"),
+      await screen.findByTestId("repo-dropdown-error"),
     ).toBeInTheDocument();
     expect(
-      screen.getByText("Failed to load data"),
+      screen.getByText("HOME$FAILED_TO_LOAD_REPOSITORIES"),
     ).toBeInTheDocument();
   });
 
@@ -231,7 +231,11 @@ describe("RepositorySelectionForm", () => {
 
     renderForm();
 
-    const input = await screen.findByTestId("git-repo-dropdown");
+    const dropdown = await screen.findByTestId("repo-dropdown");
+    const input = dropdown.querySelector(
+      'input[type="text"]',
+    ) as HTMLInputElement;
+    expect(input).toBeInTheDocument();
 
     await userEvent.type(input, "https://github.com/kubernetes/kubernetes");
     expect(searchGitReposSpy).toHaveBeenLastCalledWith(
@@ -266,7 +270,11 @@ describe("RepositorySelectionForm", () => {
 
     renderForm();
 
-    const input = await screen.findByTestId("git-repo-dropdown");
+    const dropdown = await screen.findByTestId("repo-dropdown");
+    const input = dropdown.querySelector(
+      'input[type="text"]',
+    ) as HTMLInputElement;
+    expect(input).toBeInTheDocument();
 
     await userEvent.type(input, "https://github.com/kubernetes/kubernetes");
     expect(searchGitReposSpy).toHaveBeenLastCalledWith(

frontend/__tests__/routes/home-screen.test.tsx

@@ -37,27 +37,34 @@ const selectRepository = async (repoName: string) => {
 
   // First select the provider
   const providerDropdown = await waitFor(() =>
-    screen.getByTestId("git-provider-dropdown"),
+    screen.getByText("Select Provider"),
   );
   await userEvent.click(providerDropdown);
-  await userEvent.click(screen.getByText("GitHub"));
+  await userEvent.click(screen.getByText("Github"));
 
   // Then select the repository
-  const repoInput = within(repoConnector).getByTestId("git-repo-dropdown");
+  const dropdown = within(repoConnector).getByTestId("repo-dropdown");
+  const repoInput = within(dropdown).getByRole("combobox");
   await userEvent.click(repoInput);
 
   // Wait for the options to be loaded and displayed
   await waitFor(() => {
-    const dropdownMenu = screen.getByTestId("git-repo-dropdown-menu");
-    expect(within(dropdownMenu).getByText(repoName)).toBeInTheDocument();
+    const options = screen.getAllByText(repoName);
+    // Find the option in the dropdown (it will have role="option")
+    const dropdownOption = options.find(
+      (el) => el.getAttribute("role") === "option",
+    );
+    expect(dropdownOption).toBeInTheDocument();
   });
-  const dropdownMenu = screen.getByTestId("git-repo-dropdown-menu");
-  await userEvent.click(within(dropdownMenu).getByText(repoName));
+  const options = screen.getAllByText(repoName);
+  const dropdownOption = options.find(
+    (el) => el.getAttribute("role") === "option",
+  );
+  await userEvent.click(dropdownOption!);
 
   // Wait for the branch to be auto-selected
   await waitFor(() => {
-    const branchInput = screen.getByTestId("git-branch-dropdown-input");
-    expect(branchInput).toHaveValue("main");
+    expect(screen.getByText("main")).toBeInTheDocument();
   });
 };
 
@@ -78,14 +85,12 @@ const MOCK_RESPOSITORIES: GitRepository[] = [
     full_name: "octocat/hello-world",
     git_provider: "github",
     is_public: true,
-    main_branch: "main",
   },
   {
     id: "2",
     full_name: "octocat/earth",
     git_provider: "github",
     is_public: true,
-    main_branch: "main",
   },
 ];
 
@@ -135,10 +140,10 @@ describe("HomeScreen", () => {
         await screen.findAllByTestId("task-launch-button");
 
       // Mock the repository branches API call
-      vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue({ branches: [
+      vi.spyOn(OpenHands, "getRepositoryBranches").mockResolvedValue([
         { name: "main", commit_sha: "123", protected: false },
         { name: "develop", commit_sha: "456", protected: false },
-      ], has_next_page: false, current_page: 1, per_page: 30, total_count: 2 });
+      ]);
 
       // Select a repository to enable the repo launch button
       await selectRepository("octocat/hello-world");

frontend/__tests__/routes/llm-settings.test.tsx

@@ -79,35 +79,6 @@ describe("Content", () => {
         expect(screen.getByTestId("set-indicator")).toBeInTheDocument();
       });
     });
-
-    it("should conditionally show security analyzer based on confirmation mode", async () => {
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      const confirmation = screen.getByTestId("enable-confirmation-mode-switch");
-
-      // Initially confirmation mode is false, so security analyzer should not be visible
-      expect(confirmation).not.toBeChecked();
-      expect(
-        screen.queryByTestId("security-analyzer-input"),
-      ).not.toBeInTheDocument();
-
-      // Enable confirmation mode
-      await userEvent.click(confirmation);
-      expect(confirmation).toBeChecked();
-
-      // Security analyzer should now be visible
-      screen.getByTestId("security-analyzer-input");
-
-      // Disable confirmation mode again
-      await userEvent.click(confirmation);
-      expect(confirmation).not.toBeChecked();
-
-      // Security analyzer should be hidden again
-      expect(
-        screen.queryByTestId("security-analyzer-input"),
-      ).not.toBeInTheDocument();
-    });
   });
 
   describe("Advanced form", () => {
@@ -136,6 +107,7 @@ describe("Content", () => {
       within(advancedForm).getByTestId("llm-api-key-input");
       within(advancedForm).getByTestId("llm-api-key-help-anchor-advanced");
       within(advancedForm).getByTestId("agent-input");
+      within(advancedForm).getByTestId("enable-confirmation-mode-switch");
       within(advancedForm).getByTestId("enable-memory-condenser-switch");
 
       await userEvent.click(advancedSwitch);
@@ -158,6 +130,9 @@ describe("Content", () => {
       const baseUrl = screen.getByTestId("base-url-input");
       const apiKey = screen.getByTestId("llm-api-key-input");
       const agent = screen.getByTestId("agent-input");
+      const confirmation = screen.getByTestId(
+        "enable-confirmation-mode-switch",
+      );
       const condensor = screen.getByTestId("enable-memory-condenser-switch");
 
       expect(model).toHaveValue("openhands/claude-sonnet-4-20250514");
@@ -165,7 +140,15 @@ describe("Content", () => {
       expect(apiKey).toHaveValue("");
       expect(apiKey).toHaveProperty("placeholder", "");
       expect(agent).toHaveValue("CodeActAgent");
+      expect(confirmation).not.toBeChecked();
       expect(condensor).toBeChecked();
+
+      // check that security analyzer is present
+      expect(
+        screen.queryByTestId("security-analyzer-input"),
+      ).not.toBeInTheDocument();
+      await userEvent.click(confirmation);
+      screen.getByTestId("security-analyzer-input");
     });
 
     it("should render the advanced form if existings settings are advanced", async () => {
@@ -194,7 +177,7 @@ describe("Content", () => {
         agent: "CoActAgent",
         confirmation_mode: true,
         enable_default_condenser: false,
-        security_analyzer: "none",
+        security_analyzer: "mock-invariant",
       });
 
       renderLlmSettingsScreen();
@@ -220,7 +203,7 @@ describe("Content", () => {
         expect(agent).toHaveValue("CoActAgent");
         expect(confirmation).toBeChecked();
         expect(condensor).not.toBeChecked();
-        expect(securityAnalyzer).toHaveValue("SETTINGS$SECURITY_ANALYZER_NONE");
+        expect(securityAnalyzer).toHaveValue("mock-invariant");
       });
     });
   });
@@ -310,7 +293,7 @@ describe("Form submission", () => {
     // select security analyzer
     const securityAnalyzer = screen.getByTestId("security-analyzer-input");
     await userEvent.click(securityAnalyzer);
-    const securityAnalyzerOption = screen.getByText("SETTINGS$SECURITY_ANALYZER_NONE");
+    const securityAnalyzerOption = screen.getByText("mock-invariant");
     await userEvent.click(securityAnalyzerOption);
 
     const submitButton = screen.getByTestId("submit-button");
@@ -323,7 +306,7 @@ describe("Form submission", () => {
         agent: "CoActAgent",
         confirmation_mode: true,
         enable_default_condenser: false,
-        security_analyzer: null,
+        security_analyzer: "mock-invariant",
       }),
     );
   });
@@ -392,10 +375,8 @@ describe("Form submission", () => {
     const baseUrl = await screen.findByTestId("base-url-input");
     const apiKey = await screen.findByTestId("llm-api-key-input");
     const agent = await screen.findByTestId("agent-input");
-    const condensor = await screen.findByTestId("enable-memory-condenser-switch");
-
-    // Confirmation mode switch is now in basic settings, always visible
     const confirmation = await screen.findByTestId("enable-confirmation-mode-switch");
+    const condensor = await screen.findByTestId("enable-memory-condenser-switch");
 
     // enter custom model
     await userEvent.type(model, "-mini");
@@ -470,17 +451,14 @@ describe("Form submission", () => {
     // select security analyzer
     const securityAnalyzer = await screen.findByTestId("security-analyzer-input");
     await userEvent.click(securityAnalyzer);
-    const securityAnalyzerOption = screen.getByText("SETTINGS$SECURITY_ANALYZER_NONE");
+    const securityAnalyzerOption = screen.getByText("mock-invariant");
     await userEvent.click(securityAnalyzerOption);
-    expect(securityAnalyzer).toHaveValue("SETTINGS$SECURITY_ANALYZER_NONE");
+    expect(securityAnalyzer).toHaveValue("mock-invariant");
 
     expect(submitButton).not.toBeDisabled();
 
-    // revert back to original value
-    await userEvent.click(securityAnalyzer);
-    const originalSecurityAnalyzerOption = screen.getByText("SETTINGS$SECURITY_ANALYZER_LLM_DEFAULT");
-    await userEvent.click(originalSecurityAnalyzerOption);
-    expect(securityAnalyzer).toHaveValue("SETTINGS$SECURITY_ANALYZER_LLM_DEFAULT");
+    await userEvent.clear(securityAnalyzer);
+    expect(securityAnalyzer).toHaveValue("");
     expect(submitButton).toBeDisabled();
   });
 
@@ -574,7 +552,7 @@ describe("Form submission", () => {
       expect.objectContaining({
         llm_model: "openhands/claude-sonnet-4-20250514",
         llm_base_url: "",
-        confirmation_mode: true, // Confirmation mode is now a basic setting, should be preserved
+        confirmation_mode: false,
       }),
     );
   });

frontend/__tests__/routes/secrets-settings.test.tsx

@@ -107,7 +107,9 @@ describe("Content", () => {
       expect(screen.queryByTestId("add-secret-button")).not.toBeInTheDocument(),
     );
     const button = await screen.findByTestId("connect-git-button");
-    expect(button).toHaveAttribute("href", "/settings/integrations");
+    await userEvent.click(button);
+
+    screen.getByTestId("git-settings-screen");
   });
 
   it("should render an empty table when there are no existing secrets", async () => {

frontend/__tests__/utils/has-advanced-settings-set.test.ts

@@ -29,5 +29,23 @@ describe("hasAdvancedSettingsSet", () => {
         }),
       ).toBe(true);
     });
+
+    test("CONFIRMATION_MODE is true", () => {
+      expect(
+        hasAdvancedSettingsSet({
+          ...DEFAULT_SETTINGS,
+          CONFIRMATION_MODE: true,
+        }),
+      ).toBe(true);
+    });
+
+    test("SECURITY_ANALYZER is set", () => {
+      expect(
+        hasAdvancedSettingsSet({
+          ...DEFAULT_SETTINGS,
+          SECURITY_ANALYZER: "test",
+        }),
+      ).toBe(true);
+    });
   });
 });

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.55.0",
+  "version": "0.54.0",
   "private": true,
   "type": "module",
   "engines": {
@@ -11,50 +11,50 @@
     "@heroui/use-infinite-scroll": "^2.2.10",
     "@microlink/react-json-view": "^1.26.2",
     "@monaco-editor/react": "^4.7.0-rc.0",
-    "@react-router/node": "^7.8.2",
-    "@react-router/serve": "^7.8.2",
-    "@react-types/shared": "^3.32.0",
+    "@react-router/node": "^7.8.0",
+    "@react-router/serve": "^7.8.0",
+    "@react-types/shared": "^3.31.0",
     "@reduxjs/toolkit": "^2.8.2",
-    "@stripe/react-stripe-js": "^3.9.2",
-    "@stripe/stripe-js": "^7.9.0",
+    "@stripe/react-stripe-js": "^3.9.0",
+    "@stripe/stripe-js": "^7.8.0",
     "@tailwindcss/postcss": "^4.1.12",
     "@tailwindcss/vite": "^4.1.12",
-    "@tanstack/react-query": "^5.85.5",
+    "@tanstack/react-query": "^5.85.3",
     "@uidotdev/usehooks": "^2.4.1",
-    "@vitejs/plugin-react": "^5.0.2",
+    "@vitejs/plugin-react": "^5.0.0",
     "@xterm/addon-fit": "^0.10.0",
     "@xterm/xterm": "^5.4.0",
     "axios": "^1.11.0",
     "clsx": "^2.1.1",
     "date-fns": "^4.1.0",
-    "downshift": "^9.0.10",
     "eslint-config-airbnb-typescript": "^18.0.0",
     "framer-motion": "^12.23.12",
-    "i18next": "^25.4.2",
+    "i18next": "^25.3.6",
     "i18next-browser-languagedetector": "^8.2.0",
     "i18next-http-backend": "^3.0.2",
-    "isbot": "^5.1.30",
-    "jose": "^6.1.0",
-    "lucide-react": "^0.542.0",
+    "isbot": "^5.1.29",
+    "jose": "^6.0.12",
+    "lucide-react": "^0.539.0",
     "monaco-editor": "^0.52.2",
-    "posthog-js": "^1.261.0",
+    "posthog-js": "^1.260.1",
     "react": "^19.1.1",
     "react-dom": "^19.1.1",
     "react-highlight": "^0.15.0",
-    "react-hot-toast": "^2.6.0",
-    "react-i18next": "^15.7.2",
+    "react-hot-toast": "^2.5.1",
+    "react-i18next": "^15.6.1",
     "react-icons": "^5.5.0",
     "react-markdown": "^10.1.0",
     "react-redux": "^9.2.0",
-    "react-router": "^7.8.2",
-    "react-syntax-highlighter": "^15.6.6",
+    "react-router": "^7.8.0",
+    "react-select": "^5.10.2",
+    "react-syntax-highlighter": "^15.6.1",
     "react-textarea-autosize": "^8.5.9",
     "remark-breaks": "^4.0.0",
     "remark-gfm": "^4.0.1",
     "sirv-cli": "^3.0.1",
     "socket.io-client": "^4.8.1",
     "tailwind-merge": "^3.3.1",
-    "vite": "^7.1.3",
+    "vite": "^7.1.1",
     "web-vitals": "^5.1.0",
     "ws": "^8.18.2"
   },
@@ -88,17 +88,17 @@
     "@babel/traverse": "^7.28.3",
     "@babel/types": "^7.28.2",
     "@mswjs/socket.io-binding": "^0.2.0",
-    "@playwright/test": "^1.55.0",
-    "@react-router/dev": "^7.8.2",
+    "@playwright/test": "^1.54.2",
+    "@react-router/dev": "^7.8.0",
     "@tailwindcss/typography": "^0.5.16",
     "@tanstack/eslint-plugin-query": "^5.83.1",
     "@testing-library/dom": "^10.4.1",
-    "@testing-library/jest-dom": "^6.8.0",
+    "@testing-library/jest-dom": "^6.7.0",
     "@testing-library/react": "^16.3.0",
     "@testing-library/user-event": "^14.6.1",
-    "@types/node": "^24.3.0",
-    "@types/react": "^19.1.12",
-    "@types/react-dom": "^19.1.9",
+    "@types/node": "^24.2.0",
+    "@types/react": "^19.1.9",
+    "@types/react-dom": "^19.1.7",
     "@types/react-highlight": "^0.12.8",
     "@types/react-syntax-highlighter": "^15.5.13",
     "@types/ws": "^8.18.1",
@@ -117,16 +117,16 @@
     "eslint-plugin-prettier": "^5.5.4",
     "eslint-plugin-react": "^7.37.5",
     "eslint-plugin-react-hooks": "^4.6.2",
-    "eslint-plugin-unused-imports": "^4.2.0",
+    "eslint-plugin-unused-imports": "^4.1.4",
     "husky": "^9.1.7",
     "jsdom": "^26.1.0",
     "lint-staged": "^16.1.4",
     "msw": "^2.6.6",
     "prettier": "^3.6.2",
-    "stripe": "^18.5.0",
+    "stripe": "^18.4.0",
     "tailwindcss": "^4.1.8",
     "typescript": "^5.9.2",
-    "vite-plugin-svgr": "^4.5.0",
+    "vite-plugin-svgr": "^4.2.0",
     "vite-tsconfig-paths": "^5.1.4",
     "vitest": "^3.0.2"
   },

frontend/src/api/open-hands.ts

@@ -21,12 +21,7 @@ import {
 } from "./open-hands.types";
 import { openHands } from "./open-hands-axios";
 import { ApiSettings, PostApiSettings, Provider } from "#/types/settings";
-import {
-  GitUser,
-  GitRepository,
-  PaginatedBranchesResponse,
-  Branch,
-} from "#/types/git";
+import { GitUser, GitRepository, Branch } from "#/types/git";
 import { SuggestedTask } from "#/components/features/home/tasks/task.types";
 import { extractNextPageFromLink } from "#/utils/extract-next-page-from-link";
 import { RepositoryMicroagent } from "#/types/microagent-management";
@@ -572,35 +567,11 @@ class OpenHands {
     };
   }
 
-  static async getRepositoryBranches(
-    repository: string,
-    page: number = 1,
-    perPage: number = 30,
-  ): Promise<PaginatedBranchesResponse> {
-    const { data } = await openHands.get<PaginatedBranchesResponse>(
-      `/api/user/repository/branches?repository=${encodeURIComponent(repository)}&page=${page}&per_page=${perPage}`,
-    );
-
-    return data;
-  }
-
-  static async searchRepositoryBranches(
-    repository: string,
-    query: string,
-    perPage: number = 30,
-    selectedProvider?: Provider,
-  ): Promise<Branch[]> {
+  static async getRepositoryBranches(repository: string): Promise<Branch[]> {
     const { data } = await openHands.get<Branch[]>(
-      `/api/user/search/branches`,
-      {
-        params: {
-          repository,
-          query,
-          per_page: perPage,
-          selected_provider: selectedProvider,
-        },
-      },
+      `/api/user/repository/branches?repository=${encodeURIComponent(repository)}`,
     );
+
     return data;
   }
 
@@ -755,27 +726,6 @@ class OpenHands {
     );
     return data;
   }
-
-  static async getMicroagentManagementConversations(
-    selectedRepository: string,
-    pageId?: string,
-    limit: number = 100,
-  ): Promise<Conversation[]> {
-    const params: Record<string, string | number> = {
-      limit,
-      selected_repository: selectedRepository,
-    };
-
-    if (pageId) {
-      params.page_id = pageId;
-    }
-
-    const { data } = await openHands.get<ResultSet<Conversation>>(
-      "/api/microagent-management/conversations",
-      { params },
-    );
-    return data.results;
-  }
 }
 
 export default OpenHands;

frontend/src/components/common/git-branch-dropdown.tsx

@@ -0,0 +1,69 @@
+import { useMemo } from "react";
+import { useRepositoryBranches } from "../../hooks/query/use-repository-branches";
+import { ReactSelectDropdown, SelectOption } from "./react-select-dropdown";
+
+export interface GitBranchDropdownProps {
+  repositoryName?: string | null;
+  value?: string | null;
+  placeholder?: string;
+  className?: string;
+  errorMessage?: string;
+  disabled?: boolean;
+  onChange?: (branchName: string | null) => void;
+}
+
+export function GitBranchDropdown({
+  repositoryName,
+  value,
+  placeholder = "Select branch...",
+  className,
+  errorMessage,
+  disabled = false,
+  onChange,
+}: GitBranchDropdownProps) {
+  const { data: branches, isLoading } = useRepositoryBranches(
+    repositoryName || null,
+  );
+
+  const options: SelectOption[] = useMemo(
+    () =>
+      branches?.map((branch) => ({
+        value: branch.name,
+        label: branch.name,
+      })) || [],
+    [branches],
+  );
+
+  const hasNoBranches = !isLoading && branches && branches.length === 0;
+
+  const selectedOption = useMemo(
+    () => options.find((option) => option.value === value) || null,
+    [options, value],
+  );
+
+  const handleChange = (option: SelectOption | null) => {
+    onChange?.(option?.value || null);
+  };
+
+  const isDisabled = disabled || !repositoryName || isLoading || hasNoBranches;
+
+  const displayPlaceholder = hasNoBranches ? "No branches found" : placeholder;
+  const displayErrorMessage = hasNoBranches
+    ? "This repository has no branches"
+    : errorMessage;
+
+  return (
+    <ReactSelectDropdown
+      options={options}
+      value={selectedOption}
+      placeholder={displayPlaceholder}
+      className={className}
+      errorMessage={displayErrorMessage}
+      disabled={isDisabled}
+      isClearable={false}
+      isSearchable
+      isLoading={isLoading}
+      onChange={handleChange}
+    />
+  );
+}

frontend/src/components/common/git-provider-dropdown.tsx

@@ -0,0 +1,58 @@
+import { useMemo } from "react";
+import { Provider } from "../../types/settings";
+import { ReactSelectDropdown, SelectOption } from "./react-select-dropdown";
+
+export interface GitProviderDropdownProps {
+  providers: Provider[];
+  value?: Provider | null;
+  placeholder?: string;
+  className?: string;
+  errorMessage?: string;
+  disabled?: boolean;
+  isLoading?: boolean;
+  onChange?: (provider: Provider | null) => void;
+}
+
+export function GitProviderDropdown({
+  providers,
+  value,
+  placeholder = "Select Provider",
+  className,
+  errorMessage,
+  disabled = false,
+  isLoading = false,
+  onChange,
+}: GitProviderDropdownProps) {
+  const options: SelectOption[] = useMemo(
+    () =>
+      providers.map((provider) => ({
+        value: provider,
+        label: provider.charAt(0).toUpperCase() + provider.slice(1),
+      })),
+    [providers],
+  );
+
+  const selectedOption = useMemo(
+    () => options.find((option) => option.value === value) || null,
+    [options, value],
+  );
+
+  const handleChange = (option: SelectOption | null) => {
+    onChange?.(option?.value as Provider | null);
+  };
+
+  return (
+    <ReactSelectDropdown
+      options={options}
+      value={selectedOption}
+      placeholder={placeholder}
+      className={className}
+      errorMessage={errorMessage}
+      disabled={disabled}
+      isClearable={false}
+      isSearchable={false}
+      isLoading={isLoading}
+      onChange={handleChange}
+    />
+  );
+}

frontend/src/components/common/git-repository-dropdown.tsx

@@ -0,0 +1,208 @@
+import { useCallback, useMemo, useState } from "react";
+import { useTranslation } from "react-i18next";
+import { Provider } from "../../types/settings";
+import { useGitRepositories } from "../../hooks/query/use-git-repositories";
+import { useSearchRepositories } from "../../hooks/query/use-search-repositories";
+import { useDebounce } from "../../hooks/use-debounce";
+import OpenHands from "../../api/open-hands";
+import { GitRepository } from "../../types/git";
+import {
+  ReactSelectAsyncDropdown,
+  AsyncSelectOption,
+} from "./react-select-async-dropdown";
+
+export interface GitRepositoryDropdownProps {
+  provider: Provider;
+  value?: string | null;
+  placeholder?: string;
+  className?: string;
+  errorMessage?: string;
+  disabled?: boolean;
+  onChange?: (repository?: GitRepository) => void;
+}
+
+export function GitRepositoryDropdown({
+  provider,
+  value,
+  placeholder = "Search repositories...",
+  className,
+  errorMessage,
+  disabled = false,
+  onChange,
+}: GitRepositoryDropdownProps) {
+  const { t } = useTranslation();
+  const [searchInput, setSearchInput] = useState("");
+  const debouncedSearchInput = useDebounce(searchInput, 300);
+
+  // Process search input to handle URLs
+  const processedSearchInput = useMemo(() => {
+    if (debouncedSearchInput.startsWith("https://")) {
+      const match = debouncedSearchInput.match(
+        /https:\/\/[^/]+\/([^/]+\/[^/]+)/,
+      );
+      return match ? match[1] : debouncedSearchInput;
+    }
+    return debouncedSearchInput;
+  }, [debouncedSearchInput]);
+
+  const {
+    data,
+    fetchNextPage,
+    hasNextPage,
+    isLoading,
+    isFetchingNextPage,
+    isError,
+  } = useGitRepositories({
+    provider,
+    enabled: !disabled,
+  });
+
+  // Search query for processed input (handles URLs)
+  const { data: searchData, isLoading: isSearchLoading } =
+    useSearchRepositories(processedSearchInput, provider);
+
+  const allOptions: AsyncSelectOption[] = useMemo(
+    () =>
+      data?.pages
+        ? data.pages.flatMap((page) =>
+            page.data.map((repo) => ({
+              value: repo.id,
+              label: repo.full_name,
+            })),
+          )
+        : [],
+    [data],
+  );
+
+  const searchOptions: AsyncSelectOption[] = useMemo(
+    () =>
+      searchData
+        ? searchData.map((repo) => ({
+            value: repo.id,
+            label: repo.full_name,
+          }))
+        : [],
+    [searchData],
+  );
+
+  const selectedOption = useMemo(() => {
+    // First check in loaded pages
+    const option = allOptions.find((opt) => opt.value === value);
+    if (option) return option;
+
+    // If not found, check in search results
+    const searchOption = searchOptions.find((opt) => opt.value === value);
+    if (searchOption) return searchOption;
+
+    return null;
+  }, [allOptions, searchOptions, value]);
+
+  const loadOptions = useCallback(
+    async (inputValue: string): Promise<AsyncSelectOption[]> => {
+      // Update search input to trigger debounced search
+      setSearchInput(inputValue);
+
+      // If empty input, show all loaded options
+      if (!inputValue.trim()) {
+        return allOptions;
+      }
+
+      // For very short inputs, do local filtering
+      if (inputValue.length < 2) {
+        return allOptions.filter((option) =>
+          option.label.toLowerCase().includes(inputValue.toLowerCase()),
+        );
+      }
+
+      // Handle URL inputs by performing direct search
+      if (inputValue.startsWith("https://")) {
+        const match = inputValue.match(/https:\/\/[^/]+\/([^/]+\/[^/]+)/);
+        if (match) {
+          const repoName = match[1];
+          try {
+            // Perform direct search for URL-based inputs
+            const repositories = await OpenHands.searchGitRepositories(
+              repoName,
+              3,
+              provider,
+            );
+            return repositories.map((repo) => ({
+              value: repo.full_name,
+              label: repo.full_name,
+              data: repo,
+            }));
+          } catch (error) {
+            // Fall back to local filtering if search fails
+            return allOptions.filter((option) =>
+              option.label.toLowerCase().includes(repoName.toLowerCase()),
+            );
+          }
+        }
+      }
+
+      // For regular text inputs, use hook-based search results if available
+      if (searchOptions.length > 0 && processedSearchInput === inputValue) {
+        return searchOptions;
+      }
+
+      // Fallback to local filtering while search is loading
+      return allOptions.filter((option) =>
+        option.label.toLowerCase().includes(inputValue.toLowerCase()),
+      );
+    },
+    [allOptions, searchOptions, processedSearchInput, provider],
+  );
+
+  const handleChange = (option: AsyncSelectOption | null) => {
+    if (!option) {
+      onChange?.(undefined);
+      return;
+    }
+
+    // First check in loaded pages
+    let repo = data?.pages
+      ?.flatMap((p) => p.data)
+      .find((r) => r.id === option.value);
+
+    // If not found, check in search results
+    if (!repo) {
+      repo = searchData?.find((r) => r.id === option.value);
+    }
+
+    onChange?.(repo);
+  };
+
+  const handleMenuScrollToBottom = useCallback(() => {
+    if (hasNextPage && !isFetchingNextPage && !isLoading) {
+      fetchNextPage();
+    }
+  }, [hasNextPage, isFetchingNextPage, isLoading, fetchNextPage]);
+
+  return (
+    <>
+      <ReactSelectAsyncDropdown
+        testId="repo-dropdown"
+        loadOptions={loadOptions}
+        value={selectedOption}
+        placeholder={placeholder}
+        className={className}
+        errorMessage={errorMessage}
+        disabled={disabled}
+        isClearable={false}
+        isLoading={isLoading || isFetchingNextPage || isSearchLoading}
+        cacheOptions
+        defaultOptions={allOptions}
+        onChange={handleChange}
+        onMenuScrollToBottom={handleMenuScrollToBottom}
+      />
+      {isError && (
+        <div
+          data-testid="repo-dropdown-error"
+          className="text-red-500 text-sm mt-1"
+        >
+          {t("HOME$FAILED_TO_LOAD_REPOSITORIES")}
+        </div>
+      )}
+    </>
+  );
+}

frontend/src/components/common/react-select-async-dropdown.tsx

@@ -0,0 +1,79 @@
+import { useCallback, useMemo } from "react";
+import AsyncSelect from "react-select/async";
+import { cn } from "#/utils/utils";
+import { SelectOptionBase, getCustomStyles } from "./react-select-styles";
+
+export type AsyncSelectOption = SelectOptionBase;
+
+export interface ReactSelectAsyncDropdownProps {
+  loadOptions: (inputValue: string) => Promise<AsyncSelectOption[]>;
+  testId?: string;
+  placeholder?: string;
+  value?: AsyncSelectOption | null;
+  defaultValue?: AsyncSelectOption | null;
+  className?: string;
+  errorMessage?: string;
+  disabled?: boolean;
+  isClearable?: boolean;
+  isLoading?: boolean;
+  cacheOptions?: boolean;
+  defaultOptions?: boolean | AsyncSelectOption[];
+  onChange?: (option: AsyncSelectOption | null) => void;
+  onMenuScrollToBottom?: () => void;
+}
+
+export function ReactSelectAsyncDropdown({
+  loadOptions,
+  testId,
+  placeholder = "Search...",
+  value,
+  defaultValue,
+  className,
+  errorMessage,
+  disabled = false,
+  isClearable = false,
+  isLoading = false,
+  cacheOptions = true,
+  defaultOptions = true,
+  onChange,
+  onMenuScrollToBottom,
+}: ReactSelectAsyncDropdownProps) {
+  const customStyles = useMemo(() => getCustomStyles<AsyncSelectOption>(), []);
+
+  const handleLoadOptions = useCallback(
+    (inputValue: string, callback: (options: AsyncSelectOption[]) => void) => {
+      loadOptions(inputValue)
+        .then((options) => callback(options))
+        .catch(() => callback([]));
+    },
+    [loadOptions],
+  );
+
+  return (
+    <div data-testid={testId} className={cn("w-full", className)}>
+      <AsyncSelect
+        loadOptions={handleLoadOptions}
+        value={value}
+        defaultValue={defaultValue}
+        placeholder={placeholder}
+        isDisabled={disabled}
+        isClearable={isClearable}
+        isLoading={isLoading}
+        cacheOptions={cacheOptions}
+        defaultOptions={defaultOptions}
+        onChange={onChange}
+        onMenuScrollToBottom={onMenuScrollToBottom}
+        styles={customStyles}
+        className="w-full"
+      />
+      {errorMessage && (
+        <p
+          data-testid="repo-dropdown-error"
+          className="text-red-500 text-sm mt-1"
+        >
+          {errorMessage}
+        </p>
+      )}
+    </div>
+  );
+}

frontend/src/components/common/react-select-dropdown.tsx

@@ -0,0 +1,57 @@
+import { useMemo } from "react";
+import Select from "react-select";
+import { cn } from "#/utils/utils";
+import { SelectOptionBase, getCustomStyles } from "./react-select-styles";
+
+export type SelectOption = SelectOptionBase;
+
+export interface ReactSelectDropdownProps {
+  options: SelectOption[];
+  placeholder?: string;
+  value?: SelectOption | null;
+  defaultValue?: SelectOption | null;
+  className?: string;
+  errorMessage?: string;
+  disabled?: boolean;
+  isClearable?: boolean;
+  isSearchable?: boolean;
+  isLoading?: boolean;
+  onChange?: (option: SelectOption | null) => void;
+}
+
+export function ReactSelectDropdown({
+  options,
+  placeholder = "Select option...",
+  value,
+  defaultValue,
+  className,
+  errorMessage,
+  disabled = false,
+  isClearable = false,
+  isSearchable = true,
+  isLoading = false,
+  onChange,
+}: ReactSelectDropdownProps) {
+  const customStyles = useMemo(() => getCustomStyles<SelectOption>(), []);
+
+  return (
+    <div className={cn("w-full", className)}>
+      <Select
+        options={options}
+        value={value}
+        defaultValue={defaultValue}
+        placeholder={placeholder}
+        isDisabled={disabled}
+        isClearable={isClearable}
+        isSearchable={isSearchable}
+        isLoading={isLoading}
+        onChange={onChange}
+        styles={customStyles}
+        className="w-full"
+      />
+      {errorMessage && (
+        <p className="text-red-500 text-sm mt-1">{errorMessage}</p>
+      )}
+    </div>
+  );
+}

frontend/src/components/common/react-select-styles.ts

@@ -0,0 +1,92 @@
+import { StylesConfig } from "react-select";
+
+export interface SelectOptionBase {
+  value: string;
+  label: string;
+}
+
+export const getCustomStyles = <T extends SelectOptionBase>(): StylesConfig<
+  T,
+  false
+> => ({
+  control: (provided, state) => ({
+    ...provided,
+    backgroundColor: state.isDisabled ? "#363636" : "#454545", // darker tertiary when disabled
+    border: "1px solid #717888",
+    borderRadius: "0.125rem",
+    minHeight: "2.5rem",
+    padding: "0 0.5rem",
+    boxShadow: state.isFocused ? "0 0 0 1px #717888" : "none",
+    opacity: state.isDisabled ? 0.6 : 1,
+    cursor: state.isDisabled ? "not-allowed" : "pointer",
+    "&:hover": {
+      borderColor: "#717888",
+    },
+  }),
+  input: (provided) => ({
+    ...provided,
+    color: "#ECEDEE", // content
+  }),
+  placeholder: (provided) => ({
+    ...provided,
+    fontStyle: "italic",
+    color: "#B7BDC2", // tertiary-light
+  }),
+  singleValue: (provided, state) => ({
+    ...provided,
+    color: state.isDisabled ? "#B7BDC2" : "#ECEDEE", // tertiary-light when disabled, content otherwise
+  }),
+  menu: (provided) => ({
+    ...provided,
+    backgroundColor: "#454545", // tertiary
+    border: "1px solid #717888",
+    borderRadius: "0.75rem",
+    overflow: "hidden", // ensure menu items don't overflow rounded corners
+  }),
+  menuList: (provided) => ({
+    ...provided,
+    padding: "0.25rem", // add some padding around menu items
+  }),
+  option: (provided, state) => {
+    let backgroundColor = "transparent";
+    if (state.isSelected) {
+      backgroundColor = "#C9B974"; // primary for selected
+    } else if (state.isFocused) {
+      backgroundColor = "#24272E"; // base-secondary for hover/focus
+    }
+
+    return {
+      ...provided,
+      backgroundColor,
+      color: state.isSelected ? "#000000" : "#ECEDEE", // black text on yellow, white on gray
+      borderRadius: "0.5rem", // rounded menu items
+      margin: "0.125rem 0", // small gap between items
+      "&:hover": {
+        backgroundColor: state.isSelected ? "#C9B974" : "#24272E", // keep yellow if selected, else gray
+        color: state.isSelected ? "#000000" : "#ECEDEE", // maintain text color on hover
+      },
+      "&:active": {
+        backgroundColor: state.isSelected ? "#C9B974" : "#24272E",
+        color: state.isSelected ? "#000000" : "#ECEDEE",
+      },
+    };
+  },
+  clearIndicator: (provided) => ({
+    ...provided,
+    color: "#B7BDC2", // tertiary-light
+    "&:hover": {
+      color: "#ECEDEE", // content
+    },
+  }),
+  dropdownIndicator: (provided) => ({
+    ...provided,
+    color: "#B7BDC2", // tertiary-light
+    "&:hover": {
+      color: "#ECEDEE", // content
+    },
+  }),
+  loadingIndicator: (provided) => ({
+    ...provided,
+    color: "#B7BDC2", // tertiary-light
+  }),
+});

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

@@ -9,7 +9,6 @@ import { CopyToClipboardButton } from "#/components/shared/buttons/copy-to-clipb
 import { anchor } from "../markdown/anchor";
 import { OpenHandsSourceType } from "#/types/core/base";
 import { paragraph } from "../markdown/paragraph";
-import { TooltipButton } from "#/components/shared/buttons/tooltip-button";
 
 interface ChatMessageProps {
   type: OpenHandsSourceType;
@@ -17,7 +16,6 @@ interface ChatMessageProps {
   actions?: Array<{
     icon: React.ReactNode;
     onClick: () => void;
-    tooltip?: string;
   }>;
 }
 
@@ -68,35 +66,17 @@ export function ChatMessage({
           "items-center gap-1",
         )}
       >
-        {actions?.map((action, index) =>
-          action.tooltip ? (
-            <TooltipButton
-              key={index}
-              tooltip={action.tooltip}
-              ariaLabel={action.tooltip}
-              placement="top"
-            >
-              <button
-                type="button"
-                onClick={action.onClick}
-                className="button-base p-1 cursor-pointer"
-                aria-label={`Action ${index + 1}`}
-              >
-                {action.icon}
-              </button>
-            </TooltipButton>
-          ) : (
-            <button
-              key={index}
-              type="button"
-              onClick={action.onClick}
-              className="button-base p-1 cursor-pointer"
-              aria-label={`Action ${index + 1}`}
-            >
-              {action.icon}
-            </button>
-          ),
-        )}
+        {actions?.map((action, index) => (
+          <button
+            key={index}
+            type="button"
+            onClick={action.onClick}
+            className="button-base p-1 cursor-pointer"
+            aria-label={`Action ${index + 1}`}
+          >
+            {action.icon}
+          </button>
+        ))}
 
         <CopyToClipboardButton
           isHidden={!isHovering}

frontend/src/components/features/chat/event-content-helpers/get-observation-content.ts

@@ -72,9 +72,6 @@ const getRecallObservationContent = (event: RecallObservation): string => {
     if (event.extras.repo_instructions) {
       content += `\n\n**Repository Instructions:**\n\n${event.extras.repo_instructions}`;
     }
-    if (event.extras.conversation_instructions) {
-      content += `\n\n**Conversation Instructions:**\n\n${event.extras.conversation_instructions}`;
-    }
     if (event.extras.additional_agent_instructions) {
       content += `\n\n**Additional Instructions:**\n\n${event.extras.additional_agent_instructions}`;
     }

frontend/src/components/features/chat/event-message.tsx

@@ -46,7 +46,6 @@ interface EventMessageProps {
   actions?: Array<{
     icon: React.ReactNode;
     onClick: () => void;
-    tooltip?: string;
   }>;
   isInLast10Actions: boolean;
 }

frontend/src/components/features/chat/messages.tsx

@@ -1,5 +1,4 @@
 import React from "react";
-import { useTranslation } from "react-i18next";
 import { createPortal } from "react-dom";
 import { OpenHandsAction } from "#/types/core/actions";
 import { OpenHandsObservation } from "#/types/core/observations";
@@ -25,17 +24,6 @@ import { AgentState } from "#/types/agent-state";
 import { getFirstPRUrl } from "#/utils/parse-pr-url";
 import MemoryIcon from "#/icons/memory_icon.svg?react";
 
-const isErrorEvent = (evt: unknown): evt is { error: true; message: string } =>
-  typeof evt === "object" &&
-  evt !== null &&
-  "error" in evt &&
-  evt.error === true;
-
-const isAgentStatusError = (evt: unknown): boolean =>
-  isOpenHandsEvent(evt) &&
-  isAgentStateChangeObservation(evt) &&
-  evt.extras.agent_state === AgentState.ERROR;
-
 interface MessagesProps {
   messages: (OpenHandsAction | OpenHandsObservation)[];
   isAwaitingUserConfirmation: boolean;
@@ -43,11 +31,8 @@ interface MessagesProps {
 
 export const Messages: React.FC<MessagesProps> = React.memo(
   ({ messages, isAwaitingUserConfirmation }) => {
-    const {
-      createConversationAndSubscribe,
-      isPending,
-      unsubscribeFromConversation,
-    } = useCreateConversationAndSubscribeMultiple();
+    const { createConversationAndSubscribe, isPending } =
+      useCreateConversationAndSubscribeMultiple();
     const { getOptimisticUserMessage } = useOptimisticUserMessage();
     const { conversationId } = useConversationId();
     const { data: conversation } = useUserConversation(conversationId);
@@ -63,8 +48,6 @@ export const Messages: React.FC<MessagesProps> = React.memo(
       EventMicroagentStatus[]
     >([]);
 
-    const { t } = useTranslation();
-
     const actionHasObservationPair = React.useCallback(
       (event: OpenHandsAction | OpenHandsObservation): boolean => {
         if (isOpenHandsAction(event)) {
@@ -110,6 +93,20 @@ export const Messages: React.FC<MessagesProps> = React.memo(
 
     const handleMicroagentEvent = React.useCallback(
       (socketEvent: unknown, microagentConversationId: string) => {
+        // Handle error events
+        const isErrorEvent = (
+          evt: unknown,
+        ): evt is { error: true; message: string } =>
+          typeof evt === "object" &&
+          evt !== null &&
+          "error" in evt &&
+          evt.error === true;
+
+        const isAgentStatusError = (evt: unknown): boolean =>
+          isOpenHandsEvent(evt) &&
+          isAgentStateChangeObservation(evt) &&
+          evt.extras.agent_state === AgentState.ERROR;
+
         if (isErrorEvent(socketEvent) || isAgentStatusError(socketEvent)) {
           setMicroagentStatuses((prev) =>
             prev.map((statusEntry) =>
@@ -122,11 +119,7 @@ export const Messages: React.FC<MessagesProps> = React.memo(
           isOpenHandsEvent(socketEvent) &&
           isAgentStateChangeObservation(socketEvent)
         ) {
-          // Handle completion states
-          if (
-            socketEvent.extras.agent_state === AgentState.FINISHED ||
-            socketEvent.extras.agent_state === AgentState.AWAITING_USER_INPUT
-          ) {
+          if (socketEvent.extras.agent_state === AgentState.FINISHED) {
             setMicroagentStatuses((prev) =>
               prev.map((statusEntry) =>
                 statusEntry.conversationId === microagentConversationId
@@ -134,8 +127,6 @@ export const Messages: React.FC<MessagesProps> = React.memo(
                   : statusEntry,
               ),
             );
-
-            unsubscribeFromConversation(microagentConversationId);
           }
         } else if (
           isOpenHandsEvent(socketEvent) &&
@@ -156,27 +147,9 @@ export const Messages: React.FC<MessagesProps> = React.memo(
               ),
             );
           }
-
-          unsubscribeFromConversation(microagentConversationId);
-        } else {
-          // For any other event, transition from WAITING to CREATING if still waiting
-          setMicroagentStatuses((prev) => {
-            const currentStatus = prev.find(
-              (entry) => entry.conversationId === microagentConversationId,
-            )?.status;
-
-            if (currentStatus === MicroagentStatus.WAITING) {
-              return prev.map((statusEntry) =>
-                statusEntry.conversationId === microagentConversationId
-                  ? { ...statusEntry, status: MicroagentStatus.CREATING }
-                  : statusEntry,
-              );
-            }
-            return prev; // No change needed
-          });
         }
       },
-      [setMicroagentStatuses, unsubscribeFromConversation],
+      [setMicroagentStatuses],
     );
 
     const handleLaunchMicroagent = (
@@ -205,13 +178,13 @@ export const Messages: React.FC<MessagesProps> = React.memo(
         },
         onSuccessCallback: (newConversationId: string) => {
           setShowLaunchMicroagentModal(false);
-          // Update status with conversation ID - start with WAITING
+          // Update status with conversation ID
           setMicroagentStatuses((prev) => [
             ...prev.filter((status) => status.eventId !== selectedEventId),
             {
               eventId: selectedEventId,
               conversationId: newConversationId,
-              status: MicroagentStatus.WAITING,
+              status: MicroagentStatus.CREATING,
             },
           ]);
         },
@@ -246,7 +219,6 @@ export const Messages: React.FC<MessagesProps> = React.memo(
                         setSelectedEventId(message.id);
                         setShowLaunchMicroagentModal(true);
                       },
-                      tooltip: t("MICROAGENT$ADD_TO_MEMORY"),
                     },
                   ]
                 : undefined

frontend/src/components/features/chat/microagent/launch-microagent-modal.tsx

@@ -76,10 +76,6 @@ export function LaunchMicroagentModal({
             </button>
           </div>
 
-          <span className="text-sm text-[#A3A3A3] font-normal leading-5">
-            {t("MICROAGENT$DEFINITION")}
-          </span>
-
           <form
             data-testid="launch-microagent-modal"
             onSubmit={onSubmit}

frontend/src/components/features/chat/microagent/microagent-status-indicator.tsx

@@ -19,8 +19,6 @@ export function MicroagentStatusIndicator({
 
   const getStatusText = () => {
     switch (status) {
-      case MicroagentStatus.WAITING:
-        return t("MICROAGENT$STATUS_WAITING");
       case MicroagentStatus.CREATING:
         return t("MICROAGENT$STATUS_CREATING");
       case MicroagentStatus.COMPLETED:
@@ -37,8 +35,6 @@ export function MicroagentStatusIndicator({
 
   const getStatusIcon = () => {
     switch (status) {
-      case MicroagentStatus.WAITING:
-        return <Spinner size="sm" />;
       case MicroagentStatus.CREATING:
         return <Spinner size="sm" />;
       case MicroagentStatus.COMPLETED:

frontend/src/components/features/chat/microagent/microagent-status-toast.tsx

@@ -10,11 +10,6 @@ interface ConversationCreatedToastProps {
   onClose: () => void;
 }
 
-interface ConversationStartingToastProps {
-  conversationId: string;
-  onClose: () => void;
-}
-
 function ConversationCreatedToast({
   conversationId,
   onClose,
@@ -42,33 +37,6 @@ function ConversationCreatedToast({
   );
 }
 
-function ConversationStartingToast({
-  conversationId,
-  onClose,
-}: ConversationStartingToastProps) {
-  const { t } = useTranslation();
-  return (
-    <div className="flex items-start gap-2">
-      <Spinner size="sm" />
-      <div>
-        {t("MICROAGENT$CONVERSATION_STARTING")}
-        <br />
-        <a
-          href={`/conversations/${conversationId}`}
-          target="_blank"
-          rel="noopener noreferrer"
-          className="underline"
-        >
-          {t("MICROAGENT$VIEW_CONVERSATION")}
-        </a>
-      </div>
-      <button type="button" onClick={onClose}>
-        <CloseIcon />
-      </button>
-    </div>
-  );
-}
-
 interface ConversationFinishedToastProps {
   conversationId: string;
   onClose: () => void;
@@ -110,18 +78,10 @@ function ConversationErroredToast({
   errorMessage,
   onClose,
 }: ConversationErroredToastProps) {
-  const { t } = useTranslation();
-
-  // Check if the error message is a translation key
-  const displayMessage =
-    errorMessage === "MICROAGENT$UNKNOWN_ERROR"
-      ? t(errorMessage)
-      : errorMessage;
-
   return (
     <div className="flex items-start gap-2">
       <SuccessIndicator status="error" />
-      <div>{displayMessage}</div>
+      <div>{errorMessage}</div>
       <button type="button" onClick={onClose}>
         <CloseIcon />
       </button>
@@ -176,18 +136,3 @@ export const renderConversationErroredToast = (
       duration: 5000,
     },
   );
-
-export const renderConversationStartingToast = (conversationId: string) =>
-  toast(
-    (toastInstance) => (
-      <ConversationStartingToast
-        conversationId={conversationId}
-        onClose={() => toast.dismiss(toastInstance.id)}
-      />
-    ),
-    {
-      ...TOAST_OPTIONS,
-      id: `starting-${conversationId}`,
-      duration: 10000, // Show for 10 seconds or until dismissed
-    },
-  );

frontend/src/components/features/controls/controls.tsx

@@ -7,10 +7,11 @@ import { ConversationCard } from "../conversation-panel/conversation-card";
 import { Provider } from "#/types/settings";
 
 interface ControlsProps {
+  setSecurityOpen: (isOpen: boolean) => void;
   showSecurityLock: boolean;
 }
 
-export function Controls({ showSecurityLock }: ControlsProps) {
+export function Controls({ setSecurityOpen, showSecurityLock }: ControlsProps) {
   const { data: conversation } = useActiveConversation();
   const [contextMenuOpen, setContextMenuOpen] = React.useState(false);
 
@@ -20,7 +21,9 @@ export function Controls({ showSecurityLock }: ControlsProps) {
         <AgentControlBar />
         <AgentStatusBar />
 
-        {showSecurityLock && <SecurityLock />}
+        {showSecurityLock && (
+          <SecurityLock onClick={() => setSecurityOpen(true)} />
+        )}
       </div>
 
       <ConversationCard

frontend/src/components/features/controls/security-lock.tsx

@@ -1,28 +1,17 @@
 import { IoLockClosed } from "react-icons/io5";
-import { Tooltip } from "@heroui/react";
-import { useTranslation } from "react-i18next";
-import { Link } from "react-router";
-import { I18nKey } from "#/i18n/declaration";
 
-export function SecurityLock() {
-  const { t } = useTranslation();
+interface SecurityLockProps {
+  onClick: () => void;
+}
 
+export function SecurityLock({ onClick }: SecurityLockProps) {
   return (
-    <Tooltip
-      content={
-        <div className="max-w-xs p-2">
-          {t(I18nKey.SETTINGS$CONFIRMATION_MODE_LOCK_TOOLTIP)}
-        </div>
-      }
-      placement="top"
+    <div
+      className="cursor-pointer hover:opacity-80 transition-all"
+      style={{ marginRight: "8px" }}
+      onClick={onClick}
     >
-      <Link
-        to="/settings"
-        className="mr-2 cursor-pointer hover:opacity-80 transition-all"
-        aria-label={t(I18nKey.SETTINGS$TITLE)}
-      >
-        <IoLockClosed size={20} />
-      </Link>
-    </Tooltip>
+      <IoLockClosed size={20} />
+    </div>
   );
 }

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

@@ -23,9 +23,9 @@ export function ConfirmStopModal({
     <ModalBackdrop>
       <ModalBody className="items-start border border-tertiary">
         <div className="flex flex-col gap-2">
-          <BaseModalTitle title={t(I18nKey.CONVERSATION$CONFIRM_PAUSE)} />
+          <BaseModalTitle title={t(I18nKey.CONVERSATION$CONFIRM_STOP)} />
           <BaseModalDescription
-            description={t(I18nKey.CONVERSATION$PAUSE_WARNING)}
+            description={t(I18nKey.CONVERSATION$STOP_WARNING)}
           />
         </div>
         <div

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

@@ -129,7 +129,7 @@ export function ConversationCardContextMenu({
 
       {onStop && (
         <ContextMenuListItem testId="stop-button" onClick={onStop}>
-          <ContextMenuIconText icon={Power} text={t(I18nKey.BUTTON$PAUSE)} />
+          <ContextMenuIconText icon={Power} text={t(I18nKey.BUTTON$STOP)} />
         </ContextMenuListItem>
       )}
 

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

@@ -1,6 +1,4 @@
 import { ConversationStatus } from "#/types/conversation-status";
-import ArchivedIcon from "./state-indicators/archived.svg?react";
-import ErrorIcon from "./state-indicators/error.svg?react";
 import RunningIcon from "./state-indicators/running.svg?react";
 import StartingIcon from "./state-indicators/starting.svg?react";
 import StoppedIcon from "./state-indicators/stopped.svg?react";
@@ -11,8 +9,6 @@ const CONVERSATION_STATUS_INDICATORS: Record<ConversationStatus, SVGIcon> = {
   STOPPED: StoppedIcon,
   RUNNING: RunningIcon,
   STARTING: StartingIcon,
-  ARCHIVED: ArchivedIcon,
-  ERROR: ErrorIcon,
 };
 
 interface ConversationStateIndicatorProps {

frontend/src/components/features/conversation-panel/state-indicators/archived.svg

@@ -1 +0,0 @@
-<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 0 24 24" width="24px" fill="#A7A9AC"><path d="M0 0h24v24H0V0z" fill="none"/><path d="M17 7h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1 0 1.43-.98 2.63-2.31 2.98l1.46 1.46C20.88 15.61 22 13.95 22 12c0-2.76-2.24-5-5-5zm-1 4h-2.19l2 2H16zM2 4.27l3.11 3.11C3.29 8.12 2 9.91 2 12c0 2.76 2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1 0-1.59 1.21-2.9 2.76-3.07L8.73 11H8v2h2.73L13 15.27V17h1.73l4.01 4L20 19.74 3.27 3 2 4.27z"/><path d="M0 24V0" fill="none"/></svg>

frontend/src/components/features/conversation-panel/state-indicators/error.svg

@@ -1 +0,0 @@
-<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 0 24 24" width="24px" fill="#e7000b"><path d="M0 0h24v24H0z" fill="none"/><path d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm1 15h-2v-2h2v2zm0-4h-2V7h2v6z"/></svg>

frontend/src/components/features/home/git-branch-dropdown/branch-dropdown-menu.tsx

@@ -1,86 +0,0 @@
-import React from "react";
-import {
-  UseComboboxGetMenuPropsOptions,
-  UseComboboxGetItemPropsOptions,
-} from "downshift";
-import { Branch } from "#/types/git";
-import { DropdownItem } from "../shared/dropdown-item";
-import { GenericDropdownMenu, EmptyState } from "../shared";
-
-export interface BranchDropdownMenuProps {
-  isOpen: boolean;
-  filteredBranches: Branch[];
-  inputValue: string;
-  highlightedIndex: number;
-  selectedItem: Branch | null;
-  getMenuProps: <Options>(
-    options?: UseComboboxGetMenuPropsOptions & Options,
-  ) => any; // eslint-disable-line @typescript-eslint/no-explicit-any
-  getItemProps: <Options>(
-    options: UseComboboxGetItemPropsOptions<Branch> & Options,
-  ) => any; // eslint-disable-line @typescript-eslint/no-explicit-any
-  onScroll: (event: React.UIEvent<HTMLUListElement>) => void;
-  menuRef: React.RefObject<HTMLUListElement | null>;
-}
-
-export function BranchDropdownMenu({
-  isOpen,
-  filteredBranches,
-  inputValue,
-  highlightedIndex,
-  selectedItem,
-  getMenuProps,
-  getItemProps,
-  onScroll,
-  menuRef,
-}: BranchDropdownMenuProps) {
-  const renderItem = (
-    branch: Branch,
-    index: number,
-    currentHighlightedIndex: number,
-    currentSelectedItem: Branch | null,
-    currentGetItemProps: <Options>(
-      options: UseComboboxGetItemPropsOptions<Branch> & Options,
-    ) => any, // eslint-disable-line @typescript-eslint/no-explicit-any
-  ) => (
-    <DropdownItem
-      key={branch.name}
-      item={branch}
-      index={index}
-      isHighlighted={currentHighlightedIndex === index}
-      isSelected={currentSelectedItem?.name === branch.name}
-      getItemProps={currentGetItemProps}
-      getDisplayText={(branchItem) => branchItem.name}
-      getItemKey={(branchItem) => branchItem.name}
-    />
-  );
-
-  const renderEmptyState = (currentInputValue: string) => (
-    <li className="px-3 py-2">
-      <EmptyState
-        inputValue={currentInputValue}
-        searchMessage="No branches found"
-        emptyMessage="No branches available"
-        testId="git-branch-dropdown-empty"
-      />
-    </li>
-  );
-
-  return (
-    <div data-testid="git-branch-dropdown-menu">
-      <GenericDropdownMenu
-        isOpen={isOpen}
-        filteredItems={filteredBranches}
-        inputValue={inputValue}
-        highlightedIndex={highlightedIndex}
-        selectedItem={selectedItem}
-        getMenuProps={getMenuProps}
-        getItemProps={getItemProps}
-        onScroll={onScroll}
-        menuRef={menuRef}
-        renderItem={renderItem}
-        renderEmptyState={renderEmptyState}
-      />
-    </div>
-  );
-}

frontend/src/components/features/home/git-branch-dropdown/git-branch-dropdown.tsx

@@ -1,236 +0,0 @@
-import React, {
-  useState,
-  useMemo,
-  useCallback,
-  useRef,
-  useEffect,
-} from "react";
-import { useCombobox } from "downshift";
-import { Branch } from "#/types/git";
-import { Provider } from "#/types/settings";
-import { useDebounce } from "#/hooks/use-debounce";
-import { cn } from "#/utils/utils";
-import { useBranchData } from "#/hooks/query/use-branch-data";
-import { LoadingSpinner } from "../shared/loading-spinner";
-import { ClearButton } from "../shared/clear-button";
-import { ToggleButton } from "../shared/toggle-button";
-import { ErrorMessage } from "../shared/error-message";
-import { BranchDropdownMenu } from "./branch-dropdown-menu";
-
-export interface GitBranchDropdownProps {
-  repository: string | null;
-  provider: Provider;
-  selectedBranch: Branch | null;
-  onBranchSelect: (branch: Branch | null) => void;
-  defaultBranch?: string | null;
-  placeholder?: string;
-  disabled?: boolean;
-  className?: string;
-}
-
-export function GitBranchDropdown({
-  repository,
-  provider,
-  selectedBranch,
-  onBranchSelect,
-  defaultBranch,
-  placeholder = "Select branch...",
-  disabled = false,
-  className,
-}: GitBranchDropdownProps) {
-  const [inputValue, setInputValue] = useState("");
-  const [userManuallyCleared, setUserManuallyCleared] = useState(false);
-  const debouncedInputValue = useDebounce(inputValue, 300);
-  const menuRef = useRef<HTMLUListElement>(null);
-
-  // Process search input (debounced and filtered)
-  const processedSearchInput = useMemo(
-    () =>
-      debouncedInputValue.trim().length > 0 ? debouncedInputValue.trim() : "",
-    [debouncedInputValue],
-  );
-
-  // Use the new branch data hook with default branch prioritization
-  const {
-    branches: filteredBranches,
-    isLoading,
-    isError,
-    fetchNextPage,
-    hasNextPage,
-    isFetchingNextPage,
-    isSearchLoading,
-  } = useBranchData(
-    repository,
-    provider,
-    defaultBranch || null,
-    processedSearchInput,
-    inputValue,
-    selectedBranch,
-  );
-
-  const error = isError ? new Error("Failed to load branches") : null;
-
-  // Handle clear
-  const handleClear = useCallback(() => {
-    setInputValue("");
-    onBranchSelect(null);
-    setUserManuallyCleared(true); // Mark that user manually cleared the branch
-  }, [onBranchSelect]);
-
-  // Handle branch selection
-  const handleBranchSelect = useCallback(
-    (branch: Branch | null) => {
-      onBranchSelect(branch);
-      setInputValue("");
-    },
-    [onBranchSelect],
-  );
-
-  // Handle input value change
-  const handleInputValueChange = useCallback(
-    ({ inputValue: newInputValue }: { inputValue?: string }) => {
-      if (newInputValue !== undefined) {
-        setInputValue(newInputValue);
-      }
-    },
-    [],
-  );
-
-  // Handle menu scroll for infinite loading
-  const handleMenuScroll = useCallback(
-    (event: React.UIEvent<HTMLUListElement>) => {
-      const { scrollTop, scrollHeight, clientHeight } = event.currentTarget;
-      if (
-        scrollHeight - scrollTop <= clientHeight * 1.5 &&
-        hasNextPage &&
-        !isFetchingNextPage
-      ) {
-        fetchNextPage();
-      }
-    },
-    [hasNextPage, isFetchingNextPage, fetchNextPage],
-  );
-
-  // Downshift configuration
-  const {
-    isOpen,
-    selectedItem,
-    highlightedIndex,
-    getInputProps,
-    getItemProps,
-    getMenuProps,
-    getToggleButtonProps,
-  } = useCombobox({
-    items: filteredBranches,
-    selectedItem: selectedBranch,
-    itemToString: (item) => item?.name || "",
-    onSelectedItemChange: ({ selectedItem: newSelectedItem }) => {
-      handleBranchSelect(newSelectedItem || null);
-    },
-    onInputValueChange: handleInputValueChange,
-    inputValue,
-  });
-
-  // Reset branch selection when repository changes
-  useEffect(() => {
-    if (repository) {
-      onBranchSelect(null);
-      setUserManuallyCleared(false); // Reset the manual clear flag when repository changes
-    }
-  }, [repository, onBranchSelect]);
-
-  // Auto-select default branch when branches are loaded and no branch is selected
-  // But only if the user hasn't manually cleared the branch
-  useEffect(() => {
-    if (
-      repository &&
-      defaultBranch &&
-      !selectedBranch &&
-      !userManuallyCleared && // Don't auto-select if user manually cleared
-      filteredBranches.length > 0 &&
-      !isLoading
-    ) {
-      const defaultBranchObj = filteredBranches.find(
-        (branch) => branch.name === defaultBranch,
-      );
-
-      if (defaultBranchObj) {
-        onBranchSelect(defaultBranchObj);
-      }
-    }
-  }, [
-    repository,
-    defaultBranch,
-    selectedBranch,
-    userManuallyCleared,
-    filteredBranches,
-    onBranchSelect,
-    isLoading,
-  ]);
-
-  // Reset input when repository changes
-  useEffect(() => {
-    setInputValue("");
-  }, [repository]);
-
-  // Initialize input value when selectedBranch changes (but not when user is typing)
-  useEffect(() => {
-    if (selectedBranch && !isOpen && inputValue !== selectedBranch.name) {
-      setInputValue(selectedBranch.name);
-    } else if (!selectedBranch && !isOpen && inputValue) {
-      setInputValue("");
-    }
-  }, [selectedBranch, isOpen, inputValue]);
-
-  const isLoadingState = isLoading || isSearchLoading || isFetchingNextPage;
-
-  return (
-    <div className={cn("relative", className)}>
-      <div className="relative">
-        <input
-          // eslint-disable-next-line react/jsx-props-no-spreading
-          {...getInputProps({
-            disabled: disabled || !repository,
-            placeholder,
-            className: cn(
-              "w-full px-3 py-2 border border-[#717888] rounded-sm shadow-sm min-h-[2.5rem]",
-              "bg-[#454545] text-[#ECEDEE] placeholder:text-[#B7BDC2] placeholder:italic",
-              "focus:outline-none focus:ring-1 focus:ring-[#717888] focus:border-[#717888]",
-              "disabled:bg-[#363636] disabled:cursor-not-allowed disabled:opacity-60",
-              "pr-10", // Space for toggle button
-            ),
-          })}
-          data-testid="git-branch-dropdown-input"
-        />
-
-        <div className="absolute right-2 top-1/2 transform -translate-y-1/2 flex items-center gap-1">
-          {selectedBranch && (
-            <ClearButton disabled={disabled} onClear={handleClear} />
-          )}
-
-          <ToggleButton
-            isOpen={isOpen}
-            disabled={disabled || !repository}
-            getToggleButtonProps={getToggleButtonProps}
-          />
-        </div>
-
-        {isLoadingState && <LoadingSpinner hasSelection={!!selectedBranch} />}
-      </div>
-
-      <BranchDropdownMenu
-        isOpen={isOpen}
-        filteredBranches={filteredBranches}
-        inputValue={inputValue}
-        highlightedIndex={highlightedIndex}
-        selectedItem={selectedItem}
-        getMenuProps={getMenuProps}
-        getItemProps={getItemProps}
-        onScroll={handleMenuScroll}
-        menuRef={menuRef}
-      />
-
-      <ErrorMessage isError={!!error} />
-    </div>
-  );
-}

frontend/src/components/features/home/git-branch-dropdown/index.ts

@@ -1,3 +0,0 @@
-export { GitBranchDropdown } from "./git-branch-dropdown";
-export { BranchDropdownMenu } from "./branch-dropdown-menu";
-export type { GitBranchDropdownProps } from "./git-branch-dropdown";

frontend/src/components/features/home/git-provider-dropdown/git-provider-dropdown.tsx

@@ -1,193 +0,0 @@
-import React, { useState, useMemo, useEffect } from "react";
-import { useCombobox } from "downshift";
-import { Provider } from "#/types/settings";
-import { cn } from "#/utils/utils";
-import { DropdownItem } from "../shared/dropdown-item";
-import { GenericDropdownMenu } from "../shared/generic-dropdown-menu";
-import { ToggleButton } from "../shared/toggle-button";
-import { LoadingSpinner } from "../shared/loading-spinner";
-import { ErrorMessage } from "../shared/error-message";
-import { EmptyState } from "../shared/empty-state";
-
-export interface GitProviderDropdownProps {
-  providers: Provider[];
-  value?: Provider | null;
-  placeholder?: string;
-  className?: string;
-  errorMessage?: string;
-  disabled?: boolean;
-  isLoading?: boolean;
-  onChange?: (provider: Provider | null) => void;
-}
-
-export function GitProviderDropdown({
-  providers,
-  value,
-  placeholder = "Select Provider",
-  className,
-  errorMessage,
-  disabled = false,
-  isLoading = false,
-  onChange,
-}: GitProviderDropdownProps) {
-  const [inputValue, setInputValue] = useState("");
-  const [localSelectedItem, setLocalSelectedItem] = useState<Provider | null>(
-    value || null,
-  );
-
-  // Format provider names for display
-  const formatProviderName = (provider: Provider): string => {
-    switch (provider) {
-      case "github":
-        return "GitHub";
-      case "gitlab":
-        return "GitLab";
-      case "bitbucket":
-        return "Bitbucket";
-      case "enterprise_sso":
-        return "Enterprise SSO";
-      default:
-        // Fallback for any future provider types
-        return (
-          (provider as string).charAt(0).toUpperCase() +
-          (provider as string).slice(1)
-        );
-    }
-  };
-
-  // Filter providers based on input value
-  const filteredProviders = useMemo(() => {
-    // If we have a selected provider and the input matches it exactly, show all providers
-    if (
-      localSelectedItem &&
-      inputValue === formatProviderName(localSelectedItem)
-    ) {
-      return providers;
-    }
-
-    // If no input value, show all providers
-    if (!inputValue || !inputValue.trim()) {
-      return providers;
-    }
-
-    // Filter providers based on input
-    return providers.filter((provider) =>
-      formatProviderName(provider)
-        .toLowerCase()
-        .includes(inputValue.toLowerCase()),
-    );
-  }, [providers, inputValue, localSelectedItem]);
-
-  const {
-    isOpen,
-    getToggleButtonProps,
-    getMenuProps,
-    getInputProps,
-    highlightedIndex,
-    getItemProps,
-    selectedItem,
-  } = useCombobox({
-    items: filteredProviders,
-    itemToString: (item) => (item ? formatProviderName(item) : ""),
-    selectedItem: localSelectedItem,
-    onSelectedItemChange: ({ selectedItem: newSelectedItem }) => {
-      setLocalSelectedItem(newSelectedItem || null);
-      onChange?.(newSelectedItem || null);
-    },
-    onInputValueChange: ({ inputValue: newInputValue }) => {
-      setInputValue(newInputValue || "");
-    },
-    inputValue,
-  });
-
-  // Sync with external value prop
-  useEffect(() => {
-    if (value !== localSelectedItem) {
-      setLocalSelectedItem(value || null);
-    }
-  }, [value, localSelectedItem]);
-
-  // Update input value when selection changes (but not when user is typing)
-  useEffect(() => {
-    if (selectedItem && !isOpen) {
-      setInputValue(formatProviderName(selectedItem));
-    } else if (!selectedItem) {
-      setInputValue("");
-    }
-  }, [selectedItem, isOpen]);
-
-  const renderItem = (
-    item: Provider,
-    index: number,
-    currentHighlightedIndex: number,
-    currentSelectedItem: Provider | null,
-    currentGetItemProps: any, // eslint-disable-line @typescript-eslint/no-explicit-any
-  ) => (
-    <DropdownItem
-      key={item}
-      item={item}
-      index={index}
-      isHighlighted={index === currentHighlightedIndex}
-      isSelected={item === currentSelectedItem}
-      getItemProps={currentGetItemProps}
-      getDisplayText={formatProviderName}
-      getItemKey={(provider) => provider}
-    />
-  );
-
-  const renderEmptyState = (currentInputValue: string) => (
-    <EmptyState
-      inputValue={currentInputValue}
-      searchMessage="No providers found"
-      emptyMessage="No providers available"
-      testId="git-provider-dropdown-empty"
-    />
-  );
-
-  return (
-    <div className={cn("relative", className)}>
-      <div className="relative">
-        <input
-          // eslint-disable-next-line react/jsx-props-no-spreading
-          {...getInputProps({
-            disabled,
-            placeholder,
-            readOnly: true, // Make it non-searchable like the original
-            className: cn(
-              "w-full px-3 py-2 border border-[#717888] rounded-sm shadow-sm min-h-[2.5rem]",
-              "bg-[#454545] text-[#ECEDEE] placeholder:text-[#B7BDC2] placeholder:italic",
-              "focus:outline-none focus:ring-1 focus:ring-[#717888] focus:border-[#717888]",
-              "disabled:bg-[#363636] disabled:cursor-not-allowed disabled:opacity-60",
-              "pr-10 cursor-pointer", // Space for toggle button and pointer cursor
-            ),
-          })}
-          data-testid="git-provider-dropdown"
-        />
-
-        <div className="absolute right-2 top-1/2 transform -translate-y-1/2 flex items-center gap-1">
-          <ToggleButton
-            isOpen={isOpen}
-            disabled={disabled}
-            getToggleButtonProps={getToggleButtonProps}
-          />
-        </div>
-
-        {isLoading && <LoadingSpinner hasSelection={!!selectedItem} />}
-      </div>
-
-      <GenericDropdownMenu
-        isOpen={isOpen}
-        filteredItems={filteredProviders}
-        inputValue={inputValue}
-        highlightedIndex={highlightedIndex}
-        selectedItem={selectedItem}
-        getMenuProps={getMenuProps}
-        getItemProps={getItemProps}
-        renderItem={renderItem}
-        renderEmptyState={renderEmptyState}
-      />
-
-      <ErrorMessage isError={!!errorMessage} message={errorMessage} />
-    </div>
-  );
-}

frontend/src/components/features/home/git-provider-dropdown/index.ts

@@ -1,2 +0,0 @@
-export { GitProviderDropdown } from "./git-provider-dropdown";
-export type { GitProviderDropdownProps } from "./git-provider-dropdown";

frontend/src/components/features/home/git-repo-dropdown/dropdown-menu.tsx

@@ -1,79 +0,0 @@
-import React from "react";
-import {
-  UseComboboxGetMenuPropsOptions,
-  UseComboboxGetItemPropsOptions,
-} from "downshift";
-import { GitRepository } from "#/types/git";
-import { DropdownItem } from "../shared/dropdown-item";
-import { GenericDropdownMenu, EmptyState } from "../shared";
-
-interface DropdownMenuProps {
-  isOpen: boolean;
-  filteredRepositories: GitRepository[];
-  inputValue: string;
-  highlightedIndex: number;
-  selectedItem: GitRepository | null;
-  getMenuProps: <Options>(
-    options?: UseComboboxGetMenuPropsOptions & Options,
-  ) => any; // eslint-disable-line @typescript-eslint/no-explicit-any
-  getItemProps: <Options>(
-    options: UseComboboxGetItemPropsOptions<GitRepository> & Options,
-  ) => any; // eslint-disable-line @typescript-eslint/no-explicit-any
-  onScroll: (event: React.UIEvent<HTMLUListElement>) => void;
-  menuRef: React.RefObject<HTMLUListElement | null>;
-}
-
-export function DropdownMenu({
-  isOpen,
-  filteredRepositories,
-  inputValue,
-  highlightedIndex,
-  selectedItem,
-  getMenuProps,
-  getItemProps,
-  onScroll,
-  menuRef,
-}: DropdownMenuProps) {
-  const renderItem = (
-    repository: GitRepository,
-    index: number,
-    currentHighlightedIndex: number,
-    currentSelectedItem: GitRepository | null,
-    currentGetItemProps: <Options>(
-      options: UseComboboxGetItemPropsOptions<GitRepository> & Options,
-    ) => any, // eslint-disable-line @typescript-eslint/no-explicit-any
-  ) => (
-    <DropdownItem
-      key={repository.id}
-      item={repository}
-      index={index}
-      isHighlighted={currentHighlightedIndex === index}
-      isSelected={currentSelectedItem?.id === repository.id}
-      getItemProps={currentGetItemProps}
-      getDisplayText={(repo) => repo.full_name}
-      getItemKey={(repo) => repo.id.toString()}
-    />
-  );
-
-  const renderEmptyState = (currentInputValue: string) => (
-    <EmptyState inputValue={currentInputValue} />
-  );
-
-  return (
-    <div data-testid="git-repo-dropdown-menu">
-      <GenericDropdownMenu
-        isOpen={isOpen}
-        filteredItems={filteredRepositories}
-        inputValue={inputValue}
-        highlightedIndex={highlightedIndex}
-        selectedItem={selectedItem}
-        getMenuProps={getMenuProps}
-        getItemProps={getItemProps}
-        onScroll={onScroll}
-        menuRef={menuRef}
-        renderItem={renderItem}
-        renderEmptyState={renderEmptyState}
-      />
-    </div>
-  );
-}

frontend/src/components/features/home/git-repo-dropdown/git-repo-dropdown.tsx

@@ -1,243 +0,0 @@
-import React, {
-  useState,
-  useMemo,
-  useCallback,
-  useRef,
-  useEffect,
-} from "react";
-import { useCombobox } from "downshift";
-import { Provider } from "#/types/settings";
-import { GitRepository } from "#/types/git";
-import { useDebounce } from "#/hooks/use-debounce";
-import { cn } from "#/utils/utils";
-import { LoadingSpinner } from "../shared/loading-spinner";
-import { ClearButton } from "../shared/clear-button";
-import { ToggleButton } from "../shared/toggle-button";
-import { ErrorMessage } from "../shared/error-message";
-import { useUrlSearch } from "./use-url-search";
-import { useRepositoryData } from "./use-repository-data";
-import { DropdownMenu } from "./dropdown-menu";
-
-export interface GitRepoDropdownProps {
-  provider: Provider;
-  value?: string | null;
-  placeholder?: string;
-  className?: string;
-  disabled?: boolean;
-  onChange?: (repository?: GitRepository) => void;
-}
-
-export function GitRepoDropdown({
-  provider,
-  value,
-  placeholder = "Search repositories...",
-  className,
-  disabled = false,
-  onChange,
-}: GitRepoDropdownProps) {
-  const [inputValue, setInputValue] = useState("");
-  const [localSelectedItem, setLocalSelectedItem] =
-    useState<GitRepository | null>(null);
-  const debouncedInputValue = useDebounce(inputValue, 300);
-  const menuRef = useRef<HTMLUListElement>(null);
-
-  // Process search input to handle URLs
-  const processedSearchInput = useMemo(() => {
-    if (debouncedInputValue.startsWith("https://")) {
-      const match = debouncedInputValue.match(
-        /https:\/\/[^/]+\/([^/]+\/[^/]+)/,
-      );
-      return match ? match[1] : debouncedInputValue;
-    }
-    return debouncedInputValue;
-  }, [debouncedInputValue]);
-
-  // URL search functionality
-  const { urlSearchResults, isUrlSearchLoading } = useUrlSearch(
-    inputValue,
-    provider,
-  );
-
-  // Repository data management
-  const {
-    repositories,
-    selectedRepository,
-    fetchNextPage,
-    hasNextPage,
-    isLoading,
-    isFetchingNextPage,
-    isError,
-    isSearchLoading,
-  } = useRepositoryData(
-    provider,
-    disabled,
-    processedSearchInput,
-    urlSearchResults,
-    inputValue,
-    value,
-  );
-
-  // Filter repositories based on input value
-  const filteredRepositories = useMemo(() => {
-    // If we have URL search results, show them directly (no filtering needed)
-    if (urlSearchResults.length > 0) {
-      return repositories;
-    }
-
-    // If we have a selected repository and the input matches it exactly, show all repositories
-    if (selectedRepository && inputValue === selectedRepository.full_name) {
-      return repositories;
-    }
-
-    // If no input value, show all repositories
-    if (!inputValue || !inputValue.trim()) {
-      return repositories;
-    }
-
-    // For URL inputs, use the processed search input for filtering
-    const filterText = inputValue.startsWith("https://")
-      ? processedSearchInput
-      : inputValue;
-
-    return repositories.filter((repo) =>
-      repo.full_name.toLowerCase().includes(filterText.toLowerCase()),
-    );
-  }, [
-    repositories,
-    inputValue,
-    selectedRepository,
-    urlSearchResults,
-    processedSearchInput,
-  ]);
-
-  // Handle selection
-  const handleSelectionChange = useCallback(
-    (selectedItem: GitRepository | null) => {
-      setLocalSelectedItem(selectedItem);
-      onChange?.(selectedItem || undefined);
-      // Update input value to show selected item
-      if (selectedItem) {
-        setInputValue(selectedItem.full_name);
-      }
-    },
-    [onChange],
-  );
-
-  // Handle clear selection
-  const handleClear = useCallback(() => {
-    setLocalSelectedItem(null);
-    handleSelectionChange(null);
-    setInputValue("");
-  }, [handleSelectionChange]);
-
-  // Handle input value change
-  const handleInputValueChange = useCallback(
-    ({ inputValue: newInputValue }: { inputValue?: string }) => {
-      setInputValue(newInputValue || "");
-    },
-    [],
-  );
-
-  // Handle scroll to bottom for pagination
-  const handleMenuScroll = useCallback(
-    (event: React.UIEvent<HTMLUListElement>) => {
-      const { scrollTop, scrollHeight, clientHeight } = event.currentTarget;
-      const isNearBottom = scrollTop + clientHeight >= scrollHeight - 10;
-
-      if (isNearBottom && hasNextPage && !isFetchingNextPage) {
-        fetchNextPage();
-      }
-    },
-    [hasNextPage, isFetchingNextPage, fetchNextPage],
-  );
-
-  const {
-    isOpen,
-    getToggleButtonProps,
-    getMenuProps,
-    getInputProps,
-    highlightedIndex,
-    getItemProps,
-    selectedItem,
-  } = useCombobox({
-    items: filteredRepositories,
-    itemToString: (item) => item?.full_name || "",
-    selectedItem: localSelectedItem,
-    onSelectedItemChange: ({ selectedItem: newSelectedItem }) => {
-      handleSelectionChange(newSelectedItem);
-    },
-    onInputValueChange: handleInputValueChange,
-    inputValue,
-  });
-
-  // Sync localSelectedItem with external value prop
-  useEffect(() => {
-    if (selectedRepository) {
-      setLocalSelectedItem(selectedRepository);
-    } else if (value === null) {
-      setLocalSelectedItem(null);
-    }
-  }, [selectedRepository, value]);
-
-  // Initialize input value when selectedRepository changes (but not when user is typing)
-  useEffect(() => {
-    if (selectedRepository && !isOpen) {
-      setInputValue(selectedRepository.full_name);
-    }
-  }, [selectedRepository, isOpen]);
-
-  const isLoadingState =
-    isLoading || isSearchLoading || isFetchingNextPage || isUrlSearchLoading;
-
-  return (
-    <div className={cn("relative", className)}>
-      <div className="relative">
-        <input
-          // eslint-disable-next-line react/jsx-props-no-spreading
-          {...getInputProps({
-            disabled,
-            placeholder,
-            className: cn(
-              "w-full px-3 py-2 border border-[#717888] rounded-sm shadow-sm min-h-[2.5rem]",
-              "bg-[#454545] text-[#ECEDEE] placeholder:text-[#B7BDC2] placeholder:italic",
-              "focus:outline-none focus:ring-1 focus:ring-[#717888] focus:border-[#717888]",
-              "disabled:bg-[#363636] disabled:cursor-not-allowed disabled:opacity-60",
-              "pr-10", // Space for toggle button
-            ),
-          })}
-          data-testid="git-repo-dropdown"
-        />
-
-        <div className="absolute right-2 top-1/2 transform -translate-y-1/2 flex items-center gap-1">
-          {selectedRepository && (
-            <ClearButton disabled={disabled} onClear={handleClear} />
-          )}
-
-          <ToggleButton
-            isOpen={isOpen}
-            disabled={disabled}
-            getToggleButtonProps={getToggleButtonProps}
-          />
-        </div>
-
-        {isLoadingState && (
-          <LoadingSpinner hasSelection={!!selectedRepository} />
-        )}
-      </div>
-
-      <DropdownMenu
-        isOpen={isOpen}
-        filteredRepositories={filteredRepositories}
-        inputValue={inputValue}
-        highlightedIndex={highlightedIndex}
-        selectedItem={selectedItem}
-        getMenuProps={getMenuProps}
-        getItemProps={getItemProps}
-        onScroll={handleMenuScroll}
-        menuRef={menuRef}
-      />
-
-      <ErrorMessage isError={isError} />
-    </div>
-  );
-}

frontend/src/components/features/home/git-repo-dropdown/index.tsx

@@ -1,10 +0,0 @@
-// Main component
-export { GitRepoDropdown } from "./git-repo-dropdown";
-export type { GitRepoDropdownProps } from "./git-repo-dropdown";
-
-// Repository-specific UI Components
-export { DropdownMenu } from "./dropdown-menu";
-
-// Repository-specific Custom Hooks
-export { useUrlSearch } from "./use-url-search";
-export { useRepositoryData } from "./use-repository-data";

frontend/src/components/features/home/git-repo-dropdown/use-repository-data.tsx

@@ -1,118 +0,0 @@
-import { useMemo, useEffect } from "react";
-import { Provider } from "#/types/settings";
-import { GitRepository } from "#/types/git";
-import { useGitRepositories } from "#/hooks/query/use-git-repositories";
-import { useSearchRepositories } from "#/hooks/query/use-search-repositories";
-
-export function useRepositoryData(
-  provider: Provider,
-  disabled: boolean,
-  processedSearchInput: string,
-  urlSearchResults: GitRepository[],
-  inputValue: string,
-  value?: string | null,
-) {
-  // Fetch user repositories with pagination
-  const {
-    data: repoData,
-    fetchNextPage,
-    hasNextPage,
-    isLoading,
-    isFetchingNextPage,
-    isError,
-  } = useGitRepositories({
-    provider,
-    enabled: !disabled,
-  });
-
-  // Search repositories when user types
-  const { data: searchData, isLoading: isSearchLoading } =
-    useSearchRepositories(processedSearchInput, provider);
-
-  // Combine all repositories from paginated data
-  const allRepositories = useMemo(
-    () => repoData?.pages?.flatMap((page) => page.data) || [],
-    [repoData],
-  );
-
-  // Find selected repository from all possible sources
-  const selectedRepository = useMemo(() => {
-    if (!value) return null;
-
-    // Search in all possible repository sources
-    const allPossibleRepos = [
-      ...allRepositories,
-      ...urlSearchResults,
-      ...(searchData || []),
-    ];
-
-    return allPossibleRepos.find((repo) => repo.id === value) || null;
-  }, [allRepositories, urlSearchResults, searchData, value]);
-
-  // Get repositories to display (URL search, regular search, or all repos)
-  const repositories = useMemo(() => {
-    // Prioritize URL search results when available
-    if (urlSearchResults.length > 0) {
-      return urlSearchResults;
-    }
-
-    // Don't use search results if input exactly matches selected repository
-    const shouldUseSearch =
-      processedSearchInput &&
-      searchData &&
-      !(selectedRepository && inputValue === selectedRepository.full_name);
-
-    if (shouldUseSearch) {
-      return searchData;
-    }
-    return allRepositories;
-  }, [
-    urlSearchResults,
-    processedSearchInput,
-    searchData,
-    allRepositories,
-    selectedRepository,
-    inputValue,
-  ]);
-
-  // Auto-load more repositories when there aren't enough items to create a scrollable dropdown
-  // This is particularly important for SaaS mode with installations that might have very few repos
-  useEffect(() => {
-    const shouldAutoLoad =
-      !disabled &&
-      !isLoading &&
-      !isFetchingNextPage &&
-      !isSearchLoading &&
-      hasNextPage &&
-      !processedSearchInput && // Not during search (use all repos, not search results)
-      urlSearchResults.length === 0 &&
-      repositories.length > 0 && // Have some repositories loaded
-      repositories.length < 10; // But not enough to create a scrollable dropdown
-
-    if (shouldAutoLoad) {
-      fetchNextPage();
-    }
-  }, [
-    disabled,
-    isLoading,
-    isFetchingNextPage,
-    isSearchLoading,
-    hasNextPage,
-    processedSearchInput,
-    urlSearchResults.length,
-    repositories.length,
-    fetchNextPage,
-  ]);
-
-  return {
-    repositories,
-    allRepositories,
-    selectedRepository,
-    fetchNextPage,
-    hasNextPage,
-    isLoading,
-    isFetchingNextPage,
-    isError,
-    isSearchLoading,
-  };
-}

frontend/src/components/features/home/git-repo-dropdown/use-url-search.tsx

@@ -1,41 +0,0 @@
-import { useState, useEffect } from "react";
-import { Provider } from "#/types/settings";
-import { GitRepository } from "#/types/git";
-import OpenHands from "#/api/open-hands";
-
-export function useUrlSearch(inputValue: string, provider: Provider) {
-  const [urlSearchResults, setUrlSearchResults] = useState<GitRepository[]>([]);
-  const [isUrlSearchLoading, setIsUrlSearchLoading] = useState(false);
-
-  useEffect(() => {
-    const handleUrlSearch = async () => {
-      if (inputValue.startsWith("https://")) {
-        const match = inputValue.match(/https:\/\/[^/]+\/([^/]+\/[^/]+)/);
-        if (match) {
-          const repoName = match[1];
-
-          setIsUrlSearchLoading(true);
-          try {
-            const repositories = await OpenHands.searchGitRepositories(
-              repoName,
-              3,
-              provider,
-            );
-
-            setUrlSearchResults(repositories);
-          } catch (error) {
-            setUrlSearchResults([]);
-          } finally {
-            setIsUrlSearchLoading(false);
-          }
-        }
-      } else {
-        setUrlSearchResults([]);
-      }
-    };
-
-    handleUrlSearch();
-  }, [inputValue, provider]);
-
-  return { urlSearchResults, isUrlSearchLoading };
-}