tests(LLM): add concurrency and provider-mapping reinit tests; fix style

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

.github/CODEOWNERS

@@ -2,7 +2,7 @@
 # See https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-code-owners
 
 # Frontend code owners
-/frontend/ @rbren @amanape
+/frontend/ @amanape
 /openhands-ui/ @amanape
 
 # Evaluation code owners

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:0.51-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.52-nikolaik`
 
 ## Develop inside Docker container
 

README.md

@@ -52,37 +52,63 @@ which comes with $20 in free credits for new users.
 
 ## 💻 Running OpenHands Locally
 
-OpenHands can also run on your local system using Docker.
-See the [Running OpenHands](https://docs.all-hands.dev/usage/installation) guide for
-system requirements and more information.
+### Option 1: CLI Launcher (Recommended)
 
-> [!WARNING]
-> On a public network? See our [Hardened Docker Installation Guide](https://docs.all-hands.dev/usage/runtimes/docker#hardened-docker-installation)
-> to secure your deployment by restricting network binding and implementing additional security measures.
+The easiest way to run OpenHands locally is using the CLI launcher with [uv](https://docs.astral.sh/uv/). This provides better isolation from your current project's virtual environment and is required for OpenHands' default MCP servers.
 
+**Install uv** (if you haven't already):
+
+See the [uv installation guide](https://docs.astral.sh/uv/getting-started/installation/) for the latest installation instructions for your platform.
+
+**Launch OpenHands**:
+```bash
+# Launch the GUI server
+uvx --python 3.12 --from openhands-ai openhands serve
+
+# Or launch the CLI
+uvx --python 3.12 --from openhands-ai openhands
+```
+
+You'll find OpenHands running at [http://localhost:3000](http://localhost:3000) (for GUI mode)!
+
+### Option 2: Docker
+
+<details>
+<summary>Click to expand Docker command</summary>
+
+You can also run OpenHands directly with Docker:
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.52-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.52-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:0.51
+    docker.all-hands.dev/all-hands-ai/openhands:0.52
 ```
 
+</details>
+
 > **Note**: If you used OpenHands before version 0.44, you may want to run `mv ~/.openhands-state ~/.openhands` to migrate your conversation history to the new location.
 
-You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
+> [!WARNING]
+> On a public network? See our [Hardened Docker Installation Guide](https://docs.all-hands.dev/usage/runtimes/docker#hardened-docker-installation)
+> to secure your deployment by restricting network binding and implementing additional security measures.
+
+### Getting Started
 
 When you open the application, you'll be asked to choose an LLM provider and add an API key.
 [Anthropic's Claude Sonnet 4](https://www.anthropic.com/api) (`anthropic/claude-sonnet-4-20250514`)
 works best, but you have [many options](https://docs.all-hands.dev/usage/llms).
 
+See the [Running OpenHands](https://docs.all-hands.dev/usage/installation) guide for
+system requirements and more information.
+
 ## 💡 Other ways to run OpenHands
 
 > [!WARNING]
@@ -93,8 +119,8 @@ works best, but you have [many options](https://docs.all-hands.dev/usage/llms).
 > [OpenHands Cloud Helm Chart](https://github.com/all-Hands-AI/OpenHands-cloud)
 
 You can [connect OpenHands to your local filesystem](https://docs.all-hands.dev/usage/runtimes/docker#connecting-to-your-filesystem),
-run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/usage/how-to/headless-mode),
 interact with it via a [friendly CLI](https://docs.all-hands.dev/usage/how-to/cli-mode),
+run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/usage/how-to/headless-mode),
 or run it on tagged issues with [a github action](https://docs.all-hands.dev/usage/how-to/github-action).
 
 Visit [Running OpenHands](https://docs.all-hands.dev/usage/installation) for more information and setup instructions.

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:0.51-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.52-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.52-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:0.51
+    docker.all-hands.dev/all-hands-ai/openhands:0.52
 ```
 
 > **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:0.51-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.52-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.52-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:0.51
+    docker.all-hands.dev/all-hands-ai/openhands:0.52
 ```
 
 **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。

build_vscode.py

@@ -93,8 +93,7 @@ def build_vscode_extension():
 
 
 def build(setup_kwargs):
-    """
-    This function is called by Poetry during the build process.
+    """This function is called by Poetry during the build process.
     `setup_kwargs` is a dictionary that will be passed to `setuptools.setup()`.
     """
     print('--- Running custom Poetry build script (build_vscode.py) ---')

config.template.toml

@@ -360,28 +360,13 @@ classpath = "my_package.my_module.MyCustomAgent"
 [security]
 
 # Enable confirmation mode (For Headless / CLI only -  In Web this is overridden by Session Init)
-# When using command_approval analyzer, this should be enabled
-confirmation_mode = true
+#confirmation_mode = false
 
 # The security analyzer to use (For Headless / CLI only -  In Web this is overridden by Session Init)
-# Available options: "invariant", "command_approval"
-# For CLI with confirmation mode, "command_approval" is recommended
-security_analyzer = "command_approval"
+#security_analyzer = ""
 
 # Whether to enable security analyzer
-# When using command_approval analyzer, this should be enabled
-enable_security_analyzer = true
-
-# Dictionary of approved commands that don't require confirmation
-# The key is the command, and the value is a boolean (true to approve)
-#approved_commands = { "ls -la" = true, "git status" = true }
-
-# List of approved command patterns (regex) that don't require confirmation
-#approved_command_patterns = [
-#  { pattern = "^ls( -[a-zA-Z]+)?( \\S+)?$", description = "List directory contents" },
-#  { pattern = "^cd \\S+$", description = "Change directory" },
-#  { pattern = "^git (status|log|diff)$", description = "Basic git commands" }
-#]
+#enable_security_analyzer = false
 
 #################################### Condenser #################################
 # Condensers control how conversation history is managed and compressed when

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=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.51-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.52-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

dev_config/python/.pre-commit-config.yaml

@@ -40,7 +40,7 @@ repos:
     hooks:
       - id: mypy
         additional_dependencies:
-          [types-requests, types-setuptools, types-pyyaml, types-toml, types-docker, pydantic, lxml]
+          [types-requests, types-setuptools, types-pyyaml, types-toml, types-docker, types-Markdown, pydantic, lxml]
         # To see gaps add `--html-report mypy-report/`
         entry: mypy --config-file dev_config/python/mypy.ini openhands/
         always_run: true

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:0.51-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.52-nikolaik}
       #- SANDBOX_USER_ID=${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/how-to/cli-mode.mdx

@@ -20,27 +20,42 @@ for scripting.
 
 ### Running with Python
 
-**Note** - OpenHands requires Python version 3.12 or higher (Python 3.14 is not currently supported) and `uvx` for the default `fetch` MCP server (more details below).
+**Note** - OpenHands requires Python version 3.12 or higher (Python 3.14 is not currently supported) and `uv` for the default `fetch` MCP server (more details below).
 
-1. Install OpenHands using pip:
-```bash
-pip install openhands-ai
-```
+#### Recommended: Using uv
 
-  Or if you prefer not to manage your own Python environment, you can use `uvx`:
+We recommend using [uv](https://docs.astral.sh/uv/) for the best OpenHands experience. uv provides better isolation from your current project's virtual environment and is required for OpenHands' default MCP servers.
 
+1. **Install uv** (if you haven't already):
+
+   See the [uv installation guide](https://docs.astral.sh/uv/getting-started/installation/) for the latest installation instructions for your platform.
+
+2. **Launch OpenHands CLI**:
 ```bash
 uvx --python 3.12 --from openhands-ai openhands
 ```
 
 <AccordionGroup>
 
+<Accordion title="Alternative: Traditional pip installation">
+
+If you prefer to use pip:
+
+```bash
+# Install OpenHands
+pip install openhands-ai
+```
+
+Note that you'll still need `uv` installed for the default MCP servers to work properly.
+
+</Accordion>
+
 <Accordion title="Create shell aliases for easy access across environments">
 
 Add the following to your shell configuration file (`.bashrc`, `.zshrc`, etc.):
 
 ```bash
-# Add OpenHands aliases
+# Add OpenHands aliases (recommended)
 alias openhands="uvx --python 3.12 --from openhands-ai openhands"
 alias oh="uvx --python 3.12 --from openhands-ai openhands"
 ```
@@ -72,18 +87,19 @@ source ~/.bashrc  # or source ~/.zshrc
 
 </AccordionGroup>
 
-2. Launch an interactive OpenHands conversation from the command line:
+3. Launch an interactive OpenHands conversation from the command line:
 ```bash
-openhands
+# 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 python -m openhands.cli.main
+  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
@@ -103,7 +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:0.51-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.52-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e SANDBOX_VOLUMES=$SANDBOX_VOLUMES \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -112,7 +128,7 @@ docker run -it \
     -v ~/.openhands:/.openhands \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.51 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.52 \
     python -m openhands.cli.main --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:0.51-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.52-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:0.51 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.52 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/usage/llms/llms.mdx

@@ -18,7 +18,7 @@ Based on these findings and community feedback, these are the latest models that
 ### Cloud / API-Based Models
 
 - [anthropic/claude-sonnet-4-20250514](https://www.anthropic.com/api) (recommended)
-- [openai/o4-mini](https://openai.com/index/introducing-o3-and-o4-mini/)
+- [openai/gpt-5-2025-08-07](https://openai.com/api/) (recommended)
 - [gemini/gemini-2.5-pro](https://blog.google/technology/google-deepmind/gemini-model-thinking-updates-march-2025/)
 - [deepseek/deepseek-chat](https://api-docs.deepseek.com/)
 - [moonshot/kimi-k2-0711-preview](https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2)

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:0.51-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.52-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.52-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:0.51
+    docker.all-hands.dev/all-hands-ai/openhands:0.52
 ```
 
 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:0.51
+Status: Image is up to date for docker.all-hands.dev/all-hands-ai/openhands:0.52
 Starting OpenHands...
 Running OpenHands as root
 14:22:13 - openhands:INFO: server_config.py:50 - Using config class None

docs/usage/llms/openhands-llms.mdx

@@ -32,4 +32,4 @@ When running OpenHands, you'll need to set the following in the OpenHands UI thr
 
 Pricing follows official API provider rates. [You can view model prices here.](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json)
 
-For `qwen3-coder-480b`, we charge the cheapest FP8 rate available on openrouter: $0.4 per million input tokens and $1.6 per million output tokens.
+For `qwen3-coder-480b`, we charge the cheapest FP8 rate available on openrouter: \$0.4 per million input tokens and \$1.6 per million output tokens.

docs/usage/local-setup.mdx

@@ -66,9 +66,31 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
 
 ### Start the App
 
-#### Option 1: Using the CLI Launcher (Recommended)
+#### Option 1: Using the CLI Launcher with uv (Recommended)
 
-If you have Python 3.12+ installed, you can use the CLI launcher for a simpler experience:
+We recommend using [uv](https://docs.astral.sh/uv/) for the best OpenHands experience. uv provides better isolation from your current project's virtual environment and is required for OpenHands' default MCP servers (like the [fetch MCP server](https://github.com/modelcontextprotocol/servers/tree/main/src/fetch)).
+
+**Install uv** (if you haven't already):
+
+See the [uv installation guide](https://docs.astral.sh/uv/getting-started/installation/) for the latest installation instructions for your platform.
+
+**Launch OpenHands**:
+```bash
+# Launch the GUI server
+uvx --python 3.12 --from openhands-ai openhands serve
+
+# Or with GPU support (requires nvidia-docker)
+uvx --python 3.12 --from openhands-ai openhands serve --gpu
+
+# Or with current directory mounted
+uvx --python 3.12 --from openhands-ai openhands serve --mount-cwd
+```
+
+This will automatically handle Docker requirements checking, image pulling, and launching the GUI server. The `--gpu` flag enables GPU support via nvidia-docker, and `--mount-cwd` mounts your current directory into the container.
+
+<Accordion title="Alternative: Traditional pip installation">
+
+If you prefer to use pip and have Python 3.12+ installed:
 
 ```bash
 # Install OpenHands
@@ -76,34 +98,32 @@ pip install openhands-ai
 
 # Launch the GUI server
 openhands serve
-
-# Or with GPU support (requires nvidia-docker)
-openhands serve --gpu
-
-# Or with current directory mounted
-openhands serve --mount-cwd
 ```
 
-Or using `uvx --python 3.12 --from openhands-ai openhands serve` if you have [uv](https://docs.astral.sh/uv/) installed.
+Note that you'll still need `uv` installed for the default MCP servers to work properly.
 
-This will automatically handle Docker requirements checking, image pulling, and launching the GUI server. The `--gpu` flag enables GPU support via nvidia-docker, and `--mount-cwd` mounts your current directory into the container.
+</Accordion>
 
 #### Option 2: Using Docker Directly
 
+<Accordion title="Docker Command (Click to expand)">
+
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.52-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.52-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:0.51
+    docker.all-hands.dev/all-hands-ai/openhands:0.52
 ```
 
+</Accordion>
+
 > **Note**: If you used OpenHands before version 0.44, you may want to run `mv ~/.openhands-state ~/.openhands` to migrate your conversation history to the new location.
 
 You'll find OpenHands running at http://localhost:3000!

evaluation/benchmarks/commit0/run_infer.py

@@ -506,7 +506,6 @@ def commit0_setup(dataset: pd.DataFrame, repo_split: str) -> pd.DataFrame:
     Returns:
         Filtered dataset based on split type
     """
-
     filtered_dataset = pd.concat(
         [
             dataset[dataset['repo'].str.split('/').str[1] == repo]

evaluation/benchmarks/discoverybench/run_infer.py

@@ -89,8 +89,7 @@ def get_config(
 def get_dv_query_for_real(
     datasets, question, domain_knowledge=None, workflow_tags=None
 ):
-    """
-    Prepare a structured query for the agent to execute on the specified datasets.
+    """Prepare a structured query for the agent to execute on the specified datasets.
 
     This function constructs a query by compiling metadata from the provided datasets, along with any relevant domain knowledge and workflow tags.
 
@@ -104,7 +103,6 @@ def get_dv_query_for_real(
         query_to_dv: Query to be run on the dataset
         dataset_meta: Metadata of the dataset
     """
-
     dataset_meta = ''
     for dataset_metadata in datasets:
         dataset_meta += 'Dataset name: ' + dataset_metadata['name']
@@ -140,8 +138,7 @@ def get_dv_query_for_real(
 
 
 def initialize_runtime(runtime: Runtime, data_files: list[str]):
-    """
-    Initialize the runtime for the agent.
+    """Initialize the runtime for the agent.
 
     This function is called before the runtime is used to run the agent.
     """
@@ -231,8 +228,7 @@ def process_instance(
     metadata: EvalMetadata,
     reset_logger: bool = True,
 ):
-    """
-    Process and evaluate a single instance of the dataset.
+    """Process and evaluate a single instance of the dataset.
 
     This function executes the OpenHands agent
     for a specific instance of the dataset. It retrieves
@@ -247,7 +243,6 @@ def process_instance(
     Returns:
         output: EvalOutput object
     """
-
     config = get_config(metadata)
 
     # Setup the logger properly, so you can run
@@ -356,8 +351,7 @@ def list_csv_files(list_of_datasets):
 
 
 def create_dataset(repo_location: str, split: str = 'test'):
-    """
-    Create a dataset from the discoverybench repository
+    """Create a dataset from the discoverybench repository
     by walking through the repository and extracting metadata
     from the metadata_{}.json files
 
@@ -368,7 +362,6 @@ def create_dataset(repo_location: str, split: str = 'test'):
     Returns:
         df: DataFrame containing the dataset instances
     """
-
     data_dict = {}
 
     data_location = os.path.join(repo_location, 'discoverybench', 'real', split)

evaluation/benchmarks/gaia/run_infer.py

@@ -10,7 +10,6 @@ import huggingface_hub
 import pandas as pd
 from datasets import load_dataset
 from PIL import Image
-from pydantic import SecretStr
 
 from evaluation.benchmarks.gaia.scorer import question_scorer
 from evaluation.benchmarks.gaia.utils import (
@@ -80,8 +79,7 @@ def get_config(
 
     config_copy = copy.deepcopy(config)
     load_from_toml(config_copy)
-    if config_copy.search_api_key:
-        config.search_api_key = SecretStr(config_copy.search_api_key)
+    config.search_api_key = config_copy.search_api_key
     return config
 
 

evaluation/benchmarks/multi_swe_bench/eval_infer.py

@@ -105,8 +105,7 @@ def process_instance(
     log_dir: str | None = None,
     runtime_failure_count: int = 0,
 ) -> EvalOutput:
-    """
-    Evaluate agent performance on a SWE-bench problem instance.
+    """Evaluate agent performance on a SWE-bench problem instance.
 
     Note that this signature differs from the expected input to `run_evaluation`. Use
     `functools.partial` to provide optional arguments before passing to the evaluation harness.

evaluation/benchmarks/swe_bench/README.md

@@ -2,6 +2,8 @@
 
 This folder contains the evaluation harness that we built on top of the original [SWE-Bench benchmark](https://www.swebench.com/) ([paper](https://arxiv.org/abs/2310.06770)).
 
+**UPDATE (8/12/2025): We now support running SWE-rebench evaluation (see the paper [here](https://arxiv.org/abs/2505.20411))! For how to run it, checkout [this README](./SWE-rebench.md).**
+
 **UPDATE (6/15/2025): We now support running SWE-bench-Live evaluation (see the paper [here](https://arxiv.org/abs/2505.23419))! For how to run it, checkout [this README](./SWE-bench-Live.md).**
 
 **UPDATE (5/26/2025): We now support running interactive SWE-Bench evaluation (see the paper [here](https://arxiv.org/abs/2502.13069))! For how to run it, checkout [this README](./SWE-Interact.md).**

evaluation/benchmarks/swe_bench/SWE-rebench.md

@@ -0,0 +1,84 @@
+# SWE-rebench
+
+<p align="center">
+<a href="https://arxiv.org/abs/2505.20411">📃 Paper</a>
+•
+<a href="https://huggingface.co/datasets/nebius/SWE-rebench">🤗 HuggingFace</a>
+•
+<a href="https://swe-rebench.com/leaderboard">📊 Leaderboard</a>
+</p>
+
+SWE-rebench is a large-scale dataset for verifiable software engineering tasks.
+It comes in **two datasets**:
+
+* **[`nebius/SWE-rebench-leaderboard`](https://huggingface.co/datasets/nebius/SWE-rebench-leaderboard)** – updatable benchmark used for [leaderboard evaluation](https://swe-rebench.com/leaderboard).
+* **[`nebius/SWE-rebench`](https://huggingface.co/datasets/nebius/SWE-rebench)** – full dataset with **21,302 tasks**, suitable for training or large-scale offline evaluation.
+
+This document explains how to run OpenHands on SWE-rebench, using the leaderboard split as the main example.
+To run on the full dataset, simply replace the dataset name.
+
+
+## Setting Up
+
+Set up your development environment and configure your LLM provider by following the [SWE-bench README](README.md) in this directory.
+
+
+## Running Inference
+
+Use the existing SWE-bench inference script, changing the dataset to `nebius/SWE-rebench-leaderboard` and selecting the split (`test` for leaderboard submission):
+
+```bash
+./evaluation/benchmarks/swe_bench/scripts/run_infer.sh \
+    llm.your_llm HEAD CodeActAgent 30 50 1 nebius/SWE-rebench-leaderboard test
+```
+
+Arguments:
+
+* `llm.your_llm` – your model configuration key
+* `HEAD` – commit reference for reproducibility
+* `CodeActAgent` – agent type
+* `10` – number of examples to evaluate
+* `50` – maximum iterations per task (increase if needed)
+* `1` – number of workers
+* `nebius/SWE-rebench-leaderboard` – Hugging Face dataset name
+* `test` – dataset split
+
+**Tip:** To run on the **full 21k dataset**, replace `nebius/SWE-rebench-leaderboard` with `nebius/SWE-rebench`.
+
+
+## Evaluating Results
+
+After inference completes, evaluate using the [SWE-bench-fork evaluation harness](https://github.com/SWE-rebench/SWE-bench-fork).
+
+1. Convert the OpenHands output to SWE-bench evaluation format:
+
+```bash
+python evaluation/benchmarks/swe_bench/scripts/live/convert.py \
+  --output_jsonl path/to/evaluation/output.jsonl > preds.jsonl
+```
+
+2. Clone the SWE-bench-fork repo (https://github.com/SWE-rebench/SWE-bench-fork) and follow its README to install dependencies.
+
+
+3. Run the evaluation using the fork:
+
+```bash
+python -m swebench.harness.run_evaluation \
+    --dataset_name nebius/SWE-rebench-leaderboard \
+    --split test \
+    --predictions_path preds.jsonl \
+    --max_workers 10 \
+    --run_id openhands
+```
+
+
+## Citation
+
+```bibtex
+@article{badertdinov2025swerebench,
+  title={SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents},
+  author={Badertdinov, Ibragim and Golubev, Alexander and Nekrashevich, Maksim and Shevtsov, Anton and Karasik, Simon and Andriushchenko, Andrei and Trofimova, Maria and Litvintseva, Daria and Yangel, Boris},
+  journal={arXiv preprint arXiv:2505.20411},
+  year={2025}
+}
+```

evaluation/benchmarks/swe_bench/binary_patch_utils.py

@@ -1,11 +1,8 @@
-"""
-Utilities for handling binary files and patch generation in SWE-bench evaluation.
-"""
+"""Utilities for handling binary files and patch generation in SWE-bench evaluation."""
 
 
 def remove_binary_diffs(patch_text):
-    """
-    Remove binary file diffs from a git patch.
+    """Remove binary file diffs from a git patch.
 
     Args:
         patch_text (str): The git patch text
@@ -36,8 +33,7 @@ def remove_binary_diffs(patch_text):
 
 
 def remove_binary_files_from_git():
-    """
-    Generate a bash command to remove binary files from git staging.
+    """Generate a bash command to remove binary files from git staging.
 
     Returns:
         str: A bash command that removes binary files from git staging

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -111,8 +111,7 @@ def process_instance(
     runtime_failure_count: int = 0,
     conditional_imports: ConditionalImports | None = None,
 ) -> EvalOutput:
-    """
-    Evaluate agent performance on a SWE-bench problem instance.
+    """Evaluate agent performance on a SWE-bench problem instance.
 
     Note that this signature differs from the expected input to `run_evaluation`. Use
     `functools.partial` to provide optional arguments before passing to the evaluation harness.

evaluation/benchmarks/swe_bench/loc_eval/loc_evaluator.py

@@ -16,8 +16,7 @@ from openhands.core.logger import openhands_logger as logger
 
 class LocEvaluator:
     def __init__(self, args):
-        """
-        Localization evaluation.
+        """Localization evaluation.
 
         Args:
             args: all main arguments
@@ -76,8 +75,7 @@ class LocEvaluator:
         self.task_resolved = False
 
     def _init_dir(self, directory_path):
-        """
-        Check if a directory exists and create it if it doesn't.
+        """Check if a directory exists and create it if it doesn't.
 
         Args:
             directory_path (str): Path to the directory to check/create
@@ -207,8 +205,7 @@ class LocEvaluator:
         self._compute_avg_over_all()
 
     def _write_to_json(self, data, file_name):
-        """
-        Writes the current object data to a JSON file.
+        """Writes the current object data to a JSON file.
 
         Returns:
             bool: True if writing was successful, False otherwise.
@@ -225,8 +222,7 @@ class LocEvaluator:
             return False
 
     def read_from_json(self, file_path):
-        """
-        Reads data from a JSON file and loads it into the current object.
+        """Reads data from a JSON file and loads it into the current object.
 
         Returns:
             dict: The loaded JSON data, or an empty dict if the file doesn't exist
@@ -253,8 +249,7 @@ class LocEvaluator:
             return {}
 
     def read_from_jsonl(self, file_path):
-        """
-        Reads data from a JSON file and loads it into the current object.
+        """Reads data from a JSON file and loads it into the current object.
 
         Returns:
             dict: The loaded JSON data, or an empty dict if the file doesn't exist
@@ -294,8 +289,7 @@ class LocEvaluator:
             history_idx += 1
 
     def _parse_string_to_dict(self, dict_string) -> dict:
-        """
-        Convert a string representation of a dictionary to an actual dictionary.
+        """Convert a string representation of a dictionary to an actual dictionary.
 
         Args:
             dict_string (str): String representation of a dictionary
@@ -328,8 +322,7 @@ class LocEvaluator:
         return None
 
     def _parse_value_from_args(self, argument_str: str, key: str) -> str:
-        """
-        Parse a specific key's value from argument string.
+        """Parse a specific key's value from argument string.
 
         Args:
             argument_str (str): The argument string containing key-value pairs
@@ -407,8 +400,7 @@ class LocEvaluator:
             return ''
 
     def _parse_path_from_args(self, argument_str: str) -> str:
-        """
-        Parse path from argument string.
+        """Parse path from argument string.
 
         Args:
             argument_str (str): The argument string containing path information
@@ -419,8 +411,7 @@ class LocEvaluator:
         return self._parse_value_from_args(argument_str, 'path')
 
     def _parse_func_names_from_str(self, code_patch) -> list:
-        """
-        Parse function names from the new_str code patch.
+        """Parse function names from the new_str code patch.
 
         Args:
             code_patch: Either a string (argument string) or already extracted new_str code
@@ -801,8 +792,7 @@ class LocEvaluator:
 
 
 def swe_data_loader(args):
-    """
-    Loading SWE-Bench data.
+    """Loading SWE-Bench data.
 
     Args:
         args: Main arguments.
@@ -834,8 +824,7 @@ def swe_data_loader(args):
 
 
 def infer_data_loader(args):
-    """
-    Load instance IDs.
+    """Load instance IDs.
 
     Args:
         args: Main arguments.
@@ -868,8 +857,7 @@ def infer_data_loader(args):
 
 
 def infer_cost_calculator(args):
-    """
-    Calculate total and average costs from metric JSON files with detailed output.
+    """Calculate total and average costs from metric JSON files with detailed output.
 
     Args:
         args: Main arguments.

evaluation/benchmarks/swe_bench/loc_eval/loc_utils.py

@@ -28,8 +28,7 @@ class LocalizationInfo:
     hunks_per_file: dict[str, int]  # File -> number of hunks
 
     def to_dict(self) -> dict[str, Any]:
-        """
-        Convert LocalizationInfo to a dictionary for JSON serialization.
+        """Convert LocalizationInfo to a dictionary for JSON serialization.
 
         Returns:
             Dictionary representation of the localization information
@@ -58,8 +57,7 @@ class LocalizationInfo:
 
     @classmethod
     def from_dict(cls, data: dict[str, Any]) -> 'LocalizationInfo':
-        """
-        Create LocalizationInfo from a dictionary (for loading from JSON).
+        """Create LocalizationInfo from a dictionary (for loading from JSON).
 
         Args:
             data: Dictionary containing localization information
@@ -91,8 +89,7 @@ class LocalizationInfo:
 
 
 class LocMeta:
-    """
-    SWE-Bench dataset loader and ground-truth localization parser.
+    """SWE-Bench dataset loader and ground-truth localization parser.
 
     This class handles loading SWE-Bench datasets and extracting ground-truth
     localization information from patches for code localization evaluation.
@@ -104,8 +101,7 @@ class LocMeta:
         dataset_name: str = 'princeton-nlp/SWE-bench_Verified',
         split: str = 'test',
     ):
-        """
-        Initialize LocMeta with a SWE-Bench dataset.
+        """Initialize LocMeta with a SWE-Bench dataset.
 
         Args:
             dataset_name: HuggingFace dataset name (e.g., "princeton-nlp/SWE-bench_Verified")
@@ -124,8 +120,7 @@ class LocMeta:
         self._init_swe_dataset()
 
     def _init_swe_dataset(self) -> None:
-        """
-        Load and initialize the SWE-Bench dataset from HuggingFace.
+        """Load and initialize the SWE-Bench dataset from HuggingFace.
         Converts to pandas DataFrame for easy manipulation.
         """
         try:
@@ -150,8 +145,7 @@ class LocMeta:
             raise
 
     def get_instance_by_id(self, instance_id: str) -> pd.Series:
-        """
-        Retrieve a specific instance by its ID.
+        """Retrieve a specific instance by its ID.
 
         Args:
             instance_id: The instance identifier
@@ -169,8 +163,7 @@ class LocMeta:
         return self.df.iloc[idx]
 
     def parse_instance_loc(self, instance: Union[pd.Series, str]) -> LocalizationInfo:
-        """
-        Parse ground-truth localization information from a SWE-Bench instance.
+        """Parse ground-truth localization information from a SWE-Bench instance.
 
         Args:
             instance: Either a pandas Series with instance data or an instance_id string
@@ -218,8 +211,7 @@ class LocMeta:
     def _parse_file_patch_lines(
         self, file_patch: str
     ) -> tuple[list[tuple[int, int]], int, int]:
-        """
-        Parse line ranges and count changes from a single file patch.
+        """Parse line ranges and count changes from a single file patch.
 
         Args:
             file_patch: Patch content for a single file
@@ -253,8 +245,7 @@ class LocMeta:
     def _parse_code_structures_from_patch(
         self, file_patch: str, file_path: str
     ) -> tuple[list[str], list[str]]:
-        """
-        Extract function and class names from patch context (fallback method).
+        """Extract function and class names from patch context (fallback method).
 
         Args:
             file_patch: Patch content for a single file
@@ -311,8 +302,7 @@ class LocMeta:
     def _parse_patch_localization(
         self, patch_content: str, instance_id: str
     ) -> LocalizationInfo:
-        """
-        Parse localization information from a git patch (improved method).
+        """Parse localization information from a git patch (improved method).
 
         Args:
             patch_content: The git patch content
@@ -390,8 +380,7 @@ class LocMeta:
     def _extract_code_structures_from_patch(
         self, file_patch: str, file_path: str
     ) -> tuple[list[str], list[str]]:
-        """
-        Extract function and class names from patch context and content.
+        """Extract function and class names from patch context and content.
 
         Args:
             file_patch: Patch content for a single file
@@ -519,8 +508,7 @@ class LocMeta:
     def _parse_patch_localization_with_runtime(
         self, patch_content: str, instance_id: str, runtime: Runtime
     ) -> LocalizationInfo:
-        """
-        Parse localization information from a git patch using OpenHands runtime.
+        """Parse localization information from a git patch using OpenHands runtime.
         This is the superior method when runtime is available.
 
         Args:
@@ -596,8 +584,7 @@ class LocMeta:
     def parse_instance_loc_with_runtime(
         self, instance: Union[pd.Series, str], runtime: Runtime = None
     ) -> LocalizationInfo:
-        """
-        Parse ground-truth localization information using OpenHands runtime.
+        """Parse ground-truth localization information using OpenHands runtime.
 
         Args:
             instance: Either a pandas Series with instance data or an instance_id string
@@ -634,8 +621,7 @@ class LocMeta:
     def _analyze_source_code_with_runtime(
         self, runtime: Runtime, file_path: str, affected_lines: list[int]
     ) -> tuple[list[str], list[str], dict[int, str], dict[int, str]]:
-        """
-        Analyze source code using OpenHands runtime to find functions and classes.
+        """Analyze source code using OpenHands runtime to find functions and classes.
 
         Args:
             runtime: OpenHands runtime object
@@ -695,8 +681,7 @@ class LocMeta:
     def _parse_cython_content_with_line_mapping(
         self, content: str, affected_lines: list[int]
     ) -> tuple[list[str], list[str], dict[int, str], dict[int, str]]:
-        """
-        Parse Cython content to extract functions and classes with line mapping.
+        """Parse Cython content to extract functions and classes with line mapping.
         Since Cython files can't be parsed with Python's AST, we use regex-based parsing.
 
         Args:
@@ -828,8 +813,7 @@ class LocMeta:
     def _parse_python_content_with_line_mapping(
         self, content: str, affected_lines: list[int]
     ) -> tuple[list[str], list[str], dict[int, str], dict[int, str]]:
-        """
-        Parse Python content to extract functions and classes with accurate line mapping.
+        """Parse Python content to extract functions and classes with accurate line mapping.
 
         Args:
             content: Python source code content
@@ -914,8 +898,7 @@ class LocMeta:
     def _parse_python_content(
         self, content: str, affected_lines: list[int]
     ) -> tuple[list[str], list[str], dict[int, str], dict[int, str]]:
-        """
-        Parse Python content to extract functions and classes.
+        """Parse Python content to extract functions and classes.
 
         Args:
             content: Python source code content
@@ -989,8 +972,7 @@ class LocMeta:
             return [], [], {}, {}
 
     def _split_patch_by_files(self, patch_content: str) -> dict[str, str]:
-        """
-        Split a multi-file patch into individual file patches.
+        """Split a multi-file patch into individual file patches.
 
         Args:
             patch_content: Complete patch content
@@ -1049,8 +1031,7 @@ class LocMeta:
     def _empty_localization_info(
         self, instance_id: str = 'unknown'
     ) -> LocalizationInfo:
-        """
-        Return an empty LocalizationInfo object.
+        """Return an empty LocalizationInfo object.
 
         Args:
             instance_id: Instance identifier
@@ -1072,8 +1053,7 @@ class LocMeta:
         )
 
     def get_dataset_statistics(self) -> dict[str, Any]:
-        """
-        Get statistics about the loaded dataset.
+        """Get statistics about the loaded dataset.
 
         Returns:
             Dictionary containing dataset statistics
@@ -1095,8 +1075,7 @@ class LocMeta:
         return stats
 
     def get_instances_by_repo(self, repo_name: str) -> pd.DataFrame:
-        """
-        Get all instances for a specific repository.
+        """Get all instances for a specific repository.
 
         Args:
             repo_name: Repository name (e.g., "django/django")

evaluation/benchmarks/swe_bench/prompts/swe_claude.j2

@@ -1,65 +0,0 @@
-<uploaded_files>
-/workspace/{{ workspace_dir_name }}
-</uploaded_files>
-
-I've uploaded a python code repository in the directory {{ workspace_dir_name }}. Consider the following issue description:
-
-<issue_description>
-{{ instance.problem_statement }}
-</issue_description>
-
-Can you help me implement the necessary changes to the repository so that the requirements specified in the <issue_description> are met?
-I've already taken care of all changes to any of the test files described in the <issue_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!
-Also the development Python environment is already set up for you (i.e., all dependencies already installed), so you don't need to install other packages.
-Your task is to make the minimal changes to non-test files in the /workspace/{{ workspace_dir_name }} directory to ensure the <issue_description> is satisfied.
-
-Follow these phases to resolve the issue:
-
-Phase 1. READING: read the problem and reword it in clearer terms
-   1.1 If there are code or config snippets. Express in words any best practices or conventions in them.
-   1.2 Hightlight message errors, method names, variables, file names, stack traces, and technical details.
-   1.3 Explain the problem in clear terms.
-   1.4 Enumerate the steps to reproduce the problem.
-   1.5 Hightlight any best practices to take into account when testing and fixing the issue
-
-Phase 2. RUNNING: install and run the tests on the repository
-   2.1 Follow the readme
-   2.2 Install the environment and anything needed
-   2.2 Iterate and figure out how to run the tests
-
-Phase 3. EXPLORATION: find the files that are related to the problem and possible solutions
-   3.1 Use `grep` to search for relevant methods, classes, keywords and error messages.
-   3.2 Identify all files related to the problem statement.
-   3.3 Propose the methods and files to fix the issue and explain why.
-   3.4 From the possible file locations, select the most likely location to fix the issue.
-
-Phase 4. TEST CREATION: before implementing any fix, create a script to reproduce and verify the issue.
-   4.1 Look at existing test files in the repository to understand the test format/structure.
-   4.2 Create a minimal reproduction script that reproduces the located issue.
-   4.3 Run the reproduction script to confirm you are reproducing the issue.
-   4.4 Adjust the reproduction script as necessary.
-
-Phase 5. FIX ANALYSIS: state clearly the problem and how to fix it
-   5.1 State clearly what the problem is.
-   5.2 State clearly where the problem is located.
-   5.3 State clearly how the test reproduces the issue.
-   5.4 State clearly the best practices to take into account in the fix.
-   5.5 State clearly how to fix the problem.
-
-Phase 6. FIX IMPLEMENTATION: Edit the source code to implement your chosen solution.
-   6.1 Make minimal, focused changes to fix the issue.
-
-Phase 7. VERIFICATION: Test your implementation thoroughly.
-   7.1 Run your reproduction script to verify the fix works.
-   7.2 Add edge cases to your test script to ensure comprehensive coverage.
-   7.3 Run existing tests related to the modified code to ensure you haven't broken anything.
-
-8. FINAL REVIEW: Carefully re-read the problem description and compare your changes with the base commit {{ instance.base_commit }}.
-   8.1 Ensure you've fully addressed all requirements.
-   8.2 Run any tests in the repository related to:
-     8.2.1 The issue you are fixing
-     8.2.2 The files you modified
-     8.2.3 The functions you changed
-   8.3 If any tests fail, revise your implementation until all tests pass
-
-Be thorough in your exploration, testing, and reasoning. It's fine if your thinking process is lengthy - quality and completeness are more important than brevity.

evaluation/benchmarks/swe_bench/prompts/swe_gemini.j2

@@ -1,45 +0,0 @@
-# Task: Fix Issue in Python Repository
-
-## Repository Context
-You are provided with a Python code repository that contains an issue requiring your attention. The repository is located in a sandboxed environment, and you have access to the codebase to implement the necessary changes.
-The code repository is located at: `/workspace/{{ workspace_dir_name }}`
-(This path is provided for context; use file system tools to confirm paths before access).
-
-## Goal
-Your goal is to fix the issue described in the **Issue Description** section below. Implement the necessary changes to **non-test files only** within the repository, ensuring that **all relevant tests pass** after your changes.
-
-## Key Requirements & Constraints
-
-1.  **Understand the problem** very well: it is a bug report, and you know humans don't always write good descriptions. Explore the codebase to understand the related code and the problem in depth. It is possible that the solution needs to be a bit more extensive than just the stated text. Don't exagerate though: don't do unrelated refactoring, but also don't interpret the description too strictly.
-2.  **Focus on the issues:** Implement the fix focusing on non-test files related to the issue.
-2.  **Environment Ready:** The Python environment is pre-configured with all dependencies. Do not install packages.
-3.  **Mandatory Testing Procedure:**
-    *   **Create Test to Reproduce the Issue:** *Before* implementing any fix, you MUST create a *new test* (separate from existing tests) that specifically reproduces the issue.
-            * Take existing tests as example to understand the testing format/structure.
-            * Enhance this test with edge cases.
-            * Run this test to confirm reproduction.
-    *   **Verify Fix:** After implementing the fix, run your test again to verify the issue is resolved.
-    *   **Identify ALL Relevant Tests:** You MUST perform a **dedicated search and analysis** to identify **all** existing unit tests potentially affected by your changes. This includes:
-        *   Tests in the same module/directory as the changed files (e.g., `tests/` subdirectories).
-        *   Tests explicitly importing or using the modified code/classes/functions.
-        *   Tests mentioned in the issue description or related documentation.
-        *   Tests covering functionalities that *depend on* the modified code (analyze callers/dependencies if necessary).
-        **If you cannot confidently identify a specific subset, you MUST identify and plan to run the entire test suite for the modified application or module(s). State your identified test scope clearly.**
-    *   **Run Identified Relevant Tests:** You MUST execute the **complete set** of relevant existing unit tests you identified in the previous step. Ensure you are running the *correct and comprehensive set* of tests. You MUST NOT modify these existing tests.
-    *   **Final Check & Verification:** Before finishing, ensure **all** identified relevant existing tests pass. **Explicitly confirm that you have considered potential omissions in your test selection and believe the executed tests comprehensively cover the impact of your changes.** Failing to identify and run the *complete* relevant set constitutes a failure. If any identified tests fail, revise your fix. Passing all relevant tests is the primary measure of success.
-4.  **Defensive Programming:** Actively practice defensive programming: anticipate and handle potential edge cases, unexpected inputs, and different ways the affected code might be called **to ensure the fix works reliably and allows relevant tests to pass.** Analyze the potential impact on other parts of the codebase.
-5.  **Final Review:** Compare your solution against the original issue and the base commit ({{ instance.base_commit }}) to ensure completeness and test passage.
-
-## General Workflow Guidance
-
-*   Prioritize understanding the problem, exploring the code, planning your fix, implementing it carefully using the required diff format, and **thoroughly testing** according to the **Mandatory Testing Procedure**.
-*   Consider trade-offs between different solutions. The goal is a **robust change that makes the relevant tests pass.** Quality, correctness, and reliability are key.
-*   Actively practice defensive programming: anticipate and handle potential edge cases, unexpected inputs, and different ways the affected code might be called **to ensure the fix works reliably and allows relevant tests to pass.** Analyze the potential impact on other parts of the codebase.
-
-*   IMPORTANT: Your solution will be tested by additional hidden tests, so do not assume the task is complete just because visible tests pass! Refine the solution until you are confident that it is robust and comprehensive according to the **Defensive Programming** requirement.
-
-## Final Note
-Be thorough in your exploration, testing, and reasoning. It's fine if your thinking process is lengthy - quality and completeness are more important than brevity.
-
-## Issue Description
-{{ instance.problem_statement }}

evaluation/benchmarks/swe_bench/run_infer.py

@@ -80,6 +80,8 @@ def set_dataset_type(dataset_name: str) -> str:
         DATASET_TYPE = 'SWE-Gym'
     elif 'swe-bench-live' in name_lower:
         DATASET_TYPE = 'SWE-bench-Live'
+    elif 'swe-rebench' in name_lower:
+        DATASET_TYPE = 'SWE-rebench'
     elif 'multimodal' in name_lower:
         DATASET_TYPE = 'Multimodal'
     else:
@@ -109,9 +111,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageActio
     if mode.startswith('swt'):
         template_name = 'swt.j2'
     elif mode == 'swe':
-        if 'claude' in llm_model:
-            template_name = 'swe_default.j2'
-        elif 'gpt-4.1' in llm_model:
+        if 'gpt-4.1' in llm_model:
             template_name = 'swe_gpt4.j2'
         else:
             template_name = (
@@ -180,6 +180,8 @@ def get_instance_docker_image(
             docker_image_prefix = 'docker.io/starryzhang/'
         elif DATASET_TYPE == 'SWE-bench':
             docker_image_prefix = 'docker.io/swebench/'
+        elif DATASET_TYPE == 'SWE-rebench':
+            docker_image_prefix = 'docker.io/swerebench/'
         repo, name = instance_id.split('__')
         image_name = f'{docker_image_prefix.rstrip("/")}/sweb.eval.x86_64.{repo}_1776_{name}:latest'.lower()
         logger.debug(f'Using official SWE-Bench image: {image_name}')
@@ -320,6 +322,8 @@ def initialize_runtime(
         # inject the instance swe entry
         if DATASET_TYPE == 'SWE-bench-Live':
             entry_script_path = 'instance_swe_entry_live.sh'
+        elif DATASET_TYPE == 'SWE-rebench':
+            entry_script_path = 'instance_swe_entry_rebench.sh'
         else:
             entry_script_path = 'instance_swe_entry.sh'
         runtime.copy_to(

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

@@ -6,8 +6,7 @@ from openhands.core.logger import openhands_logger as logger
 
 
 def verify_instance_costs(row: pd.Series) -> float:
-    """
-    Verifies that the accumulated_cost matches the sum of individual costs in metrics.
+    """Verifies that the accumulated_cost matches the sum of individual costs in metrics.
     Also checks for duplicate consecutive costs which might indicate buggy counting.
     If the consecutive costs are identical, the file is affected by this bug:
     https://github.com/All-Hands-AI/OpenHands/issues/5383

evaluation/benchmarks/swe_bench/scripts/setup/instance_swe_entry_rebench.sh

@@ -0,0 +1,45 @@
+#!/usr/bin/env bash
+
+source ~/.bashrc
+SWEUTIL_DIR=/swe_util
+
+# FIXME: Cannot read SWE_INSTANCE_ID from the environment variable
+# SWE_INSTANCE_ID=django__django-11099
+if [ -z "$SWE_INSTANCE_ID" ]; then
+    echo "Error: SWE_INSTANCE_ID is not set." >&2
+    exit 1
+fi
+
+# Read the swe-bench-test-lite.json file and extract the required item based on instance_id
+item=$(jq --arg INSTANCE_ID "$SWE_INSTANCE_ID" '.[] | select(.instance_id == $INSTANCE_ID)' $SWEUTIL_DIR/eval_data/instances/swe-bench-instance.json)
+
+if [[ -z "$item" ]]; then
+  echo "No item found for the provided instance ID."
+  exit 1
+fi
+
+
+WORKSPACE_NAME=$(echo "$item" | jq -r '(.repo | tostring) + "__" + (.version | tostring) | gsub("/"; "__")')
+
+echo "WORKSPACE_NAME: $WORKSPACE_NAME"
+
+# Clear the workspace
+if [ -d /workspace ]; then
+    rm -rf /workspace/*
+else
+    mkdir /workspace
+fi
+# Copy repo to workspace
+if [ -d /workspace/$WORKSPACE_NAME ]; then
+    rm -rf /workspace/$WORKSPACE_NAME
+fi
+mkdir -p /workspace
+cp -r /testbed /workspace/$WORKSPACE_NAME
+
+# Activate instance-specific environment
+if [ -d /opt/miniconda3 ]; then
+    . /opt/miniconda3/etc/profile.d/conda.sh
+    conda activate testbed
+fi
+
+export PATH=/opt/conda/envs/testbed/bin:$PATH

evaluation/benchmarks/testgeneval/compute_readability.py

@@ -181,9 +181,7 @@ def distinct_methods_stats(tree, num_lines):
 
 
 def loops_stats(tree, num_lines):
-    """
-    Calculate the average number of loops.
-    """
+    """Calculate the average number of loops."""
     total_loops = 0
 
     def traverse(node):
@@ -199,9 +197,7 @@ def loops_stats(tree, num_lines):
 
 
 def branches_stats(tree, num_lines):
-    """
-    Calculate the average number of branches (conditional statements).
-    """
+    """Calculate the average number of branches (conditional statements)."""
     total_branches = 0
 
     def traverse(node):

evaluation/benchmarks/testgeneval/eval_infer.py

@@ -192,8 +192,7 @@ def run_mutation_testing(
 def grade_test_output(
     test_suite: str, instance: pd.Series, test_output: str, test_spec: TestSpec, runtime
 ):
-    """
-    Two-pass test grading with short-circuiting:
+    """Two-pass test grading with short-circuiting:
     1. Run all tests to identify passing/failing tests
     2. If no failing tests, evaluate coverage immediately
     3. Otherwise, run only passing tests for coverage analysis
@@ -280,8 +279,7 @@ def process_instance(
     reset_logger: bool = True,
     log_dir: str | None = None,
 ) -> EvalOutput:
-    """
-    Evaluate agent performance on a TestGenEval problem instance.
+    """Evaluate agent performance on a TestGenEval problem instance.
 
     Note that this signature differs from the expected input to `run_evaluation`. Use
     `functools.partial` to provide optional arguments before passing to the evaluation harness.
@@ -453,8 +451,7 @@ def process_instance(
 
 
 def count_and_log_fields(evaluated_predictions, fields, key):
-    """
-    Count and log the sum of specified fields in the evaluated predictions,
+    """Count and log the sum of specified fields in the evaluated predictions,
     ignoring fields with a value of -1. If all values for a field are -1,
     return -1.
 

evaluation/benchmarks/testgeneval/log_parsers.py

@@ -4,8 +4,7 @@ from evaluation.benchmarks.testgeneval.constants import TestStatus
 
 
 def parse_log_pytest(log: str) -> dict[str, str]:
-    """
-    Parser for test logs generated with PyTest framework
+    """Parser for test logs generated with PyTest framework
 
     Args:
         log (str): log content
@@ -26,8 +25,7 @@ def parse_log_pytest(log: str) -> dict[str, str]:
 
 
 def parse_log_pytest_options(log: str) -> dict[str, str]:
-    """
-    Parser for test logs generated with PyTest framework with options
+    """Parser for test logs generated with PyTest framework with options
 
     Args:
         log (str): log content
@@ -61,8 +59,7 @@ def parse_log_pytest_options(log: str) -> dict[str, str]:
 
 
 def parse_log_django(log: str) -> dict[str, str]:
-    """
-    Parser for test logs generated with Django tester framework
+    """Parser for test logs generated with Django tester framework
 
     Args:
         log (str): log content
@@ -141,8 +138,7 @@ def parse_log_django(log: str) -> dict[str, str]:
 
 
 def parse_log_pytest_v2(log: str) -> dict[str, str]:
-    """
-    Parser for test logs generated with PyTest framework (Later Version)
+    """Parser for test logs generated with PyTest framework (Later Version)
 
     Args:
         log (str): log content
@@ -170,8 +166,7 @@ def parse_log_pytest_v2(log: str) -> dict[str, str]:
 
 
 def parse_log_seaborn(log: str) -> dict[str, str]:
-    """
-    Parser for test logs generated with seaborn testing framework
+    """Parser for test logs generated with seaborn testing framework
 
     Args:
         log (str): log content
@@ -196,8 +191,7 @@ def parse_log_seaborn(log: str) -> dict[str, str]:
 
 
 def parse_log_sympy(log: str) -> dict[str, str]:
-    """
-    Parser for test logs generated with Sympy framework
+    """Parser for test logs generated with Sympy framework
 
     Args:
         log (str): log content
@@ -229,8 +223,7 @@ def parse_log_sympy(log: str) -> dict[str, str]:
 
 
 def parse_log_matplotlib(log: str) -> dict[str, str]:
-    """
-    Parser for test logs generated with PyTest framework
+    """Parser for test logs generated with PyTest framework
 
     Args:
         log (str): log content

evaluation/benchmarks/testgeneval/metrics.py

@@ -12,8 +12,7 @@ if sys.getrecursionlimit() < 10_000:
 
 
 def bleu(gold: list[str], pred: list[str]) -> float:
-    """
-    Calculate BLEU score, using smoothing method 2 with auto reweighting, in the range of 0~100.
+    """Calculate BLEU score, using smoothing method 2 with auto reweighting, in the range of 0~100.
 
     :param gold: list of gold tokens
     :param pred: list of predicted tokens
@@ -30,8 +29,7 @@ def bleu(gold: list[str], pred: list[str]) -> float:
 
 
 def batch_bleu(golds: list[list[str]], preds: list[list[str]]) -> list[float]:
-    """
-    Calculate BLEU score for a batch of sentences.
+    """Calculate BLEU score for a batch of sentences.
 
     :param golds: list of gold sentences
     :param preds: list of predicted sentences
@@ -43,8 +41,7 @@ def batch_bleu(golds: list[list[str]], preds: list[list[str]]) -> list[float]:
 
 
 def corpus_bleu(golds: list[list[str]], preds: list[list[str]]) -> float:
-    """
-    Calculate corpus-level BLEU score for a batch of sentences.
+    """Calculate corpus-level BLEU score for a batch of sentences.
 
     :param golds: list of gold sentences
     :param preds: list of predicted sentences
@@ -63,8 +60,7 @@ def corpus_bleu(golds: list[list[str]], preds: list[list[str]]) -> float:
 def edit_sim(
     gold: Union[str, list[str]], pred: Union[str, list[str]], sep: str = ' '
 ) -> float:
-    """
-    Calculate char-level edit similarity, in the range of 0~100.
+    """Calculate char-level edit similarity, in the range of 0~100.
 
     :param gold: gold sentence or list of gold tokens
     :param pred: predicted sentence or list of predicted tokens
@@ -85,8 +81,7 @@ def batch_edit_sim(
     preds: list[Union[str, list[str]]],
     sep: str = ' ',
 ) -> list[float]:
-    """
-    Calculate char-level edit similarity for a batch of sentences.
+    """Calculate char-level edit similarity for a batch of sentences.
 
     :param golds: list of gold sentences
     :param preds: list of predicted sentences
@@ -102,8 +97,7 @@ T = TypeVar('T')
 
 
 def exact_match(gold: T, pred: T) -> float:
-    """
-    Calculate exact match accuracy, in the range of {0, 100}.
+    """Calculate exact match accuracy, in the range of {0, 100}.
 
     :param gold: gold sentence or list of gold tokens
     :param pred: predicted sentence or list of predicted tokens
@@ -115,8 +109,7 @@ def exact_match(gold: T, pred: T) -> float:
 
 
 def batch_exact_match(golds: list[T], preds: list[T]) -> list[float]:
-    """
-    Calculate exact match accuracy for a batch of sentences.
+    """Calculate exact match accuracy for a batch of sentences.
 
     :param golds: list of gold sentences
     :param preds: list of predicted sentences
@@ -130,8 +123,7 @@ def batch_exact_match(golds: list[T], preds: list[T]) -> list[float]:
 def rouge_l(
     gold: Union[str, list[str]], pred: Union[str, list[str]], sep: str = ' '
 ) -> dict[str, float]:
-    """
-    Calculate ROUGE-L F1, precision, and recall scores, in the range of 0~100.
+    """Calculate ROUGE-L F1, precision, and recall scores, in the range of 0~100.
 
     :param gold: gold sentence or list of gold tokens
     :param pred: predicted sentence or list of predicted tokens
@@ -156,8 +148,7 @@ def batch_rouge_l(
     preds: list[Union[str, list[str]]],
     sep: str = ' ',
 ) -> dict[str, list[float]]:
-    """
-    Calculate ROUGE-L F1, precision, and recall scores for a batch of sentences.
+    """Calculate ROUGE-L F1, precision, and recall scores for a batch of sentences.
 
     :param golds: list of gold sentences
     :param preds: list of predicted sentences
@@ -175,8 +166,7 @@ def accuracy(
     pred: list[str],
     ignore: Optional[Sequence[str]] = None,
 ) -> float:
-    """
-    Calculate token-level accuracy, in the range of 0~100.
+    """Calculate token-level accuracy, in the range of 0~100.
     If gold and pred are not the same length, the longer one would be truncated.
 
     :param gold: list of gold tokens
@@ -210,8 +200,7 @@ def batch_accuracy(
     preds: list[list[str]],
     ignore: Optional[Sequence[str]] = None,
 ) -> list[float]:
-    """
-    Calculate token-level accuracy for a batch of sentences.
+    """Calculate token-level accuracy for a batch of sentences.
 
     :param golds: list of gold sentences
     :param preds: list of predicted sentences
@@ -226,8 +215,7 @@ def batch_accuracy(
 def first_match_to_topk(
     first_match_list: list[int], k_values: list[int]
 ) -> dict[int, list[float]]:
-    """
-    Calculate top-k accuracy with the first match ranks (1-indexed).
+    """Calculate top-k accuracy with the first match ranks (1-indexed).
 
     :param first_match: first match ranks (1-indexed)
     :param k_values: k values to consider
@@ -237,8 +225,7 @@ def first_match_to_topk(
 
 
 def pass_at_k(n: int, c: int, k: int) -> float:
-    """
-    Sample pass@k metric according to the Codex paper, but in the scale of 0~100.
+    """Sample pass@k metric according to the Codex paper, but in the scale of 0~100.
     :param n: total number of samples
     :param c: number of correct samples
     :param k: k in pass@$k$
@@ -251,8 +238,7 @@ def pass_at_k(n: int, c: int, k: int) -> float:
 
 
 def self_bleu(samples: list[list[str]]) -> float:
-    """
-    Calculate self-BLEU among the samples.
+    """Calculate self-BLEU among the samples.
     :param samples: the chosen m samples
     :return: self-BLEU
     """
@@ -274,8 +260,7 @@ def self_bleu(samples: list[list[str]]) -> float:
 
 
 def self_edit_distance(samples: list[Union[str, list[str]]], sep=' ') -> float:
-    """
-    Calculate self-edit-distance among the samples.
+    """Calculate self-edit-distance among the samples.
     :param samples: the chosen m samples
     :param sep: the separator between tokens
     :return: self-edit-distance

evaluation/benchmarks/testgeneval/report_utils.py

@@ -30,8 +30,7 @@ def check_mutation(mutation_output):
 
 
 def count_methods(code_str):
-    """
-    Counts the number of methods/functions in a given string of code.
+    """Counts the number of methods/functions in a given string of code.
 
     Args:
     code_str (str): A string containing code.
@@ -46,8 +45,7 @@ def count_methods(code_str):
 
 
 def get_lines_of_code(code_str):
-    """
-    Extracts lines of code from a given string.
+    """Extracts lines of code from a given string.
 
     Args:
     code_str (str): A string containing code.

evaluation/benchmarks/testgeneval/scripts/eval/build_outputs_ablation.py

@@ -7,8 +7,7 @@ import traceback
 
 
 def insert_line_in_string(input_string, new_str, insert_line):
-    """
-    Inserts a new line into a string at the specified line number.
+    """Inserts a new line into a string at the specified line number.
 
     :param input_string: The original string.
     :param new_str: The string to insert.
@@ -29,8 +28,7 @@ def insert_line_in_string(input_string, new_str, insert_line):
 
 
 def print_string_diff(original, modified):
-    """
-    Prints the differences between two strings line by line.
+    """Prints the differences between two strings line by line.
 
     :param original: The original string.
     :param modified: The modified string.

evaluation/benchmarks/testgeneval/test_filter.py

@@ -37,8 +37,7 @@ def extract_preamble_classes_and_functions(code):
     current_position = 0
 
     def extract_class_body(code: str, start_index: int) -> tuple[str, int]:
-        """
-        Extracts the body of a class from the given code starting from the specified index.
+        """Extracts the body of a class from the given code starting from the specified index.
         Returns the class body and the end index of the class body.
         """
         if not code or start_index < 0 or start_index >= len(code):
@@ -168,8 +167,8 @@ def extract_preamble_classes_and_functions(code):
 def filter_passing_tests(
     test_content: str, test_output: str, repo: str
 ) -> tuple[str, list[str], list[str]]:
-    """
-    Filter tests based on their execution results.
+    """Filter tests based on their execution results.
+
     Returns:
         Tuple containing:
         - Modified test content with only passing tests
@@ -246,8 +245,7 @@ def filter_passing_tests(
 def filter_tests(
     test_content: str, test_output: str, repo: str
 ) -> tuple[str, list[str], list[str]]:
-    """
-    Filter tests using AST parsing to remove failing test functions from the test file.
+    """Filter tests using AST parsing to remove failing test functions from the test file.
     Non-test functions (e.g. setup or helper methods) and classes (even if all test methods are failing)
     are preserved.
 

evaluation/benchmarks/testgeneval/test_spec.py

@@ -20,9 +20,7 @@ DIFF_MODIFIED_FILE_REGEX = r'--- a/(.*)'
 
 @dataclass
 class TestSpec:
-    """
-    A dataclass that represents a test specification for a single instance of SWE-bench.
-    """
+    """A dataclass that represents a test specification for a single instance of SWE-bench."""
 
     instance_id: str
     id: str
@@ -86,10 +84,7 @@ def make_test_setup(specs, env_name, repo_directory, includes_tox=False):
 
 
 def make_test_script_list(test_cmd, specs, env_name, repo_directory):
-    """
-    Runs the tests.
-    """
-
+    """Runs the tests."""
     includes_tox = 'tox' in test_cmd
     eval_commands = make_test_setup(specs, env_name, repo_directory, includes_tox)
     eval_commands += [
@@ -104,10 +99,7 @@ def make_test_script_list(test_cmd, specs, env_name, repo_directory):
 
 
 def make_mutation_script_list(specs, env_name, repo_directory, mutation_timeout):
-    """
-    Runs the tests.
-    """
-
+    """Runs the tests."""
     eval_commands = make_test_setup(specs, env_name, repo_directory)
     eval_commands += [
         'cosmic-ray init mutation.toml mutation.sqlite',

evaluation/benchmarks/testgeneval/utils.py

@@ -11,8 +11,7 @@ from evaluation.benchmarks.testgeneval.constants import (
 
 
 def get_test_directives(instance: TestGenEvalInstance) -> list:
-    """
-    Get test directives from the test_patch of a task instance
+    """Get test directives from the test_patch of a task instance
 
     Args:
         instance (dict): task instance
@@ -43,9 +42,7 @@ def get_test_directives(instance: TestGenEvalInstance) -> list:
 def load_testgeneval_dataset(
     name='kjain14/testgeneval', split='test', ids=None
 ) -> list[TestGenEvalInstance]:
-    """
-    Load SWE-bench dataset from Hugging Face Datasets or local .json/.jsonl file
-    """
+    """Load SWE-bench dataset from Hugging Face Datasets or local .json/.jsonl file"""
     # check that all instance IDs are in the dataset
     if ids:
         ids = set(ids)

evaluation/benchmarks/the_agent_company/browsing.py

@@ -24,9 +24,7 @@ class ActionType(Enum):
 
 @dataclass
 class Selector:
-    """
-    Represents either a direct anchor ID or a descriptive selector
-    """
+    """Represents either a direct anchor ID or a descriptive selector"""
 
     value: str
     is_anchor: bool = False
@@ -149,8 +147,7 @@ def find_matching_anchor(content: str, selector: str) -> str | None:
 
 
 def resolve_action(action: BrowserAction, content: str) -> BrowserAction:
-    """
-    Resolve any descriptive selectors in the action to anchor IDs based on the content.
+    """Resolve any descriptive selectors in the action to anchor IDs based on the content.
     Returns a new action with resolved selectors.
     """
     if isinstance(action, (InputAction, ClickAction)):
@@ -174,8 +171,7 @@ def pre_login(
     save_screenshots=True,
     screenshots_dir='screenshots',
 ):
-    """
-    Logs in to all the websites that are needed for the evaluation.
+    """Logs in to all the websites that are needed for the evaluation.
     Once logged in, the sessions would be cached in the browser, so OpenHands
     agent doesn't need to log in to these websites again.
     """

evaluation/benchmarks/the_agent_company/run_infer.py

@@ -68,8 +68,7 @@ def get_config(
 
 
 def load_dependencies(runtime: Runtime) -> list[str]:
-    """
-    Every task has a dependencies.yml file, which lists all the services that the
+    """Every task has a dependencies.yml file, which lists all the services that the
     task depends on. This function loads the file and returns all dependent service names.
     """
     command = 'cat /utils/dependencies.yml'

evaluation/benchmarks/the_agent_company/scripts/summarise_results.py

@@ -11,9 +11,7 @@ import sys
 
 
 def calculate_cost(model: str, prompt_tokens: int, completion_tokens: int) -> float:
-    """
-    Calculate the cost of the model call.
-    """
+    """Calculate the cost of the model call."""
     if 'claude-3-5-sonnet' in model.lower():
         # https://www.anthropic.com/pricing#anthropic-api, accessed 12/11/2024
         return 0.000003 * prompt_tokens + 0.000015 * completion_tokens
@@ -60,8 +58,7 @@ def calculate_cost(model: str, prompt_tokens: int, completion_tokens: int) -> fl
 
 
 def analyze_eval_json_file(filepath: str) -> tuple[int, int]:
-    """
-    Analyze a single eval JSON file and extract the total and result from final_score.
+    """Analyze a single eval JSON file and extract the total and result from final_score.
 
     Args:
         filepath: Path to the JSON file
@@ -84,8 +81,7 @@ def analyze_eval_json_file(filepath: str) -> tuple[int, int]:
 
 
 def analyze_traj_json_file(filepath: str) -> tuple[int, float]:
-    """
-    Analyze a single trajectory JSON file and extract the steps and tokens
+    """Analyze a single trajectory JSON file and extract the steps and tokens
     for each step. Then estimate the cost based on the tokens and the model type.
     Note: this is assuming there's no prompt caching at all.
     """
@@ -115,8 +111,7 @@ def analyze_traj_json_file(filepath: str) -> tuple[int, float]:
 def analyze_folder(
     folder_path: str,
 ) -> tuple[dict[str, tuple[int, int]], dict[str, tuple[int, float]]]:
-    """
-    Analyze all eval_*.json & traj_*.json files in the specified folder.
+    """Analyze all eval_*.json & traj_*.json files in the specified folder.
 
     Args:
         folder_path: Path to the folder containing JSON files
@@ -148,9 +143,7 @@ def analyze_folder(
 
 
 def get_task_nature_category(task_name: str) -> str:
-    """
-    Get the nature category of the task.
-    """
+    """Get the nature category of the task."""
     task_nature = task_name.split('-')[0]
     if task_nature.lower() in ['sde', 'pm', 'ds', 'admin', 'hr', 'finance']:
         return task_nature
@@ -159,8 +152,7 @@ def get_task_nature_category(task_name: str) -> str:
 
 
 def calculate_score(total: int, result: int) -> float:
-    """
-    Calculate the score as a number between 0 and 1.
+    """Calculate the score as a number between 0 and 1.
 
     Formula: score = (result / total) * 0.5 + (result // total) * 0.5
     Explanation:
@@ -178,8 +170,7 @@ def calculate_score(total: int, result: int) -> float:
 
 
 def is_perfect_completion(total: int, result: int) -> bool:
-    """
-    Check if the task achieved perfect completion.
+    """Check if the task achieved perfect completion.
 
     Args:
         total: Total possible points

evaluation/benchmarks/versicode/inference_utils/api_code_migration.py

@@ -1,6 +1,4 @@
-"""
-GPT performs line level generation prediction and truncates overly long tokens
-"""
+"""GPT performs line level generation prediction and truncates overly long tokens"""
 
 import json
 import os
@@ -56,8 +54,7 @@ def predict(content, model_name):
 
 
 def bulid_prompt(description, old_version, old_code, new_version) -> str:
-    """
-    build prompt
+    """Build prompt
     :param version:
     :param description:
     :param masked_code:

evaluation/benchmarks/versicode/inference_utils/api_test_block_completion.py

@@ -1,6 +1,4 @@
-"""
-GPT performs line level generation prediction and truncates overly long tokens
-"""
+"""GPT performs line level generation prediction and truncates overly long tokens"""
 
 import json
 import os
@@ -56,8 +54,7 @@ def predict(content, model_name):
 
 
 def bulid_prompt(version, description) -> str:
-    """
-    build prompt
+    """Build prompt
     :param version:
     :param description:
     :param masked_code:

evaluation/benchmarks/versicode/inference_utils/test_block.py

@@ -1,6 +1,4 @@
-"""
-block completion
-"""
+"""block completion"""
 
 import copy
 import gc
@@ -79,8 +77,7 @@ def run_inference(model_name, origin_data_list):
 
 
 def bulid_prompt(version, description) -> str:
-    """
-    build prompt
+    """Build prompt
     :param version:
     :param description:
     :param masked_code:

evaluation/benchmarks/versicode/inference_utils/test_migration.py

@@ -1,6 +1,4 @@
-"""
-code migration
-"""
+"""code migration"""
 
 import copy
 import gc
@@ -81,8 +79,7 @@ def run_inference(model_name, origin_data_list):
 
 
 def bulid_prompt(description, old_version, old_code, new_version) -> str:
-    """
-    build prompt
+    """Build prompt
     :param version:
     :param description:
     :param masked_code:

evaluation/benchmarks/versicode/metric/compute_ism_pm_score.py

@@ -1,5 +1,4 @@
-"""
-评测block的预测能力
+"""评测block的预测能力
 1、判断是否包含正确的函数名
 2、判断是否合法
 3、计算ISM，和PM
@@ -22,8 +21,7 @@ def is_code_valid(code):
 
 
 def longest_common_prefix_between_lists_with_elements(list1, list2):
-    """
-    计算两个字符串列表中元素的最长前缀匹配长度
+    """计算两个字符串列表中元素的最长前缀匹配长度
     :param list1:
     :param list2:
     :return:
@@ -46,8 +44,7 @@ def longest_common_prefix_between_lists_with_elements(list1, list2):
 
 
 def get_token(ans_code: str, output_code: str):
-    """
-    对代码进行词法分析，分解成标识符，返回两个标识符列表
+    """对代码进行词法分析，分解成标识符，返回两个标识符列表
     :param ans_code:
     :param output_code:
     :return:
@@ -94,8 +91,7 @@ def get_token(ans_code: str, output_code: str):
 
 
 def get_token_per_line(code: str):
-    """
-    对每一行代码进行词法分析，记录每一行的标识符
+    """对每一行代码进行词法分析，记录每一行的标识符
     :param code: 代码字符串
     :return: 每一行的标识符列表组成的列表
     """
@@ -117,8 +113,7 @@ def get_token_per_line(code: str):
 
 
 def get_ISM(answer_code: str, model_output_list: list, answer_name: str) -> list:
-    """
-    计算ISM，返回一个有序的得分列表
+    """计算ISM，返回一个有序的得分列表
     :return:
     """
     score_list = []
@@ -157,8 +152,7 @@ def get_ISM(answer_code: str, model_output_list: list, answer_name: str) -> list
 def get_ISM_without_verification(
     answer_code: str, model_output_list: list, answer_name: str
 ) -> list:
-    """
-    计算ISM，返回一个有序的得分列表
+    """计算ISM，返回一个有序的得分列表
     :return:
     """
     score_list = []
@@ -190,8 +184,7 @@ def get_ISM_without_verification(
 
 
 def longest_common_prefix_with_lengths(list1, list2):
-    """
-    计算两个二维列表中每个子列表的最长前缀匹配长度，并记录拥有最长前缀匹配长度的两个子列表的长度
+    """计算两个二维列表中每个子列表的最长前缀匹配长度，并记录拥有最长前缀匹配长度的两个子列表的长度
     :param list1: 第一个二维列表
     :param list2: 第二个二维列表
     :return: 最长前缀匹配长度以及拥有最长前缀匹配长度的两个子列表的长度
@@ -216,8 +209,7 @@ def longest_common_prefix_with_lengths(list1, list2):
 
 
 def get_PM(answer_code: str, model_output_list: list, answer_name: str) -> list:
-    """
-    计算PM，返回一个有序的得分列表
+    """计算PM，返回一个有序的得分列表
     :return:
     """
     score_list = []
@@ -254,8 +246,7 @@ def get_PM(answer_code: str, model_output_list: list, answer_name: str) -> list:
 
 
 def get_score(score_list: list, k):
-    """
-    计算score@n,k
+    """计算score@n,k
     :param score_list:
     :param k:
     :return:

evaluation/benchmarks/versicode/metric/compute_migration_cdc_score.py

@@ -1,6 +1,4 @@
-"""
-Calculate the cdc score for migration
-"""
+"""Calculate the cdc score for migration"""
 
 import json
 import math
@@ -11,8 +9,7 @@ import re
 
 
 def is_correct_parameter_count(function_name, correct_code, test_code):
-    """
-    判断参数数量是否一致
+    """判断参数数量是否一致
     :param function_name:
     :param correct_code:
     :param test_code:
@@ -43,8 +40,7 @@ def is_correct_parameter_count(function_name, correct_code, test_code):
 
 
 def check_keyword_parameters(function_name, correct_code, test_code):
-    """
-    判断关键词参数赋值是否正确使用
+    """判断关键词参数赋值是否正确使用
     :param function_name:
     :param correct_code:
     :param test_code:
@@ -82,8 +78,7 @@ def check_keyword_parameters(function_name, correct_code, test_code):
 
 
 def with_correct(answer_code: str, model_output: str) -> bool:
-    """
-    当answer是with结构时，判断模型生成的是不是with结构
+    """当answer是with结构时，判断模型生成的是不是with结构
     :param answer_code:
     :param model_output:
     :return:
@@ -105,9 +100,7 @@ def compute_block_score_k(
     core_line_in_core_block,
     core_line_in_output_clear,
 ):
-    """
-    cdc需要满足五个条件，em只需要满足第一个条件
-    """
+    """cdc需要满足五个条件，em只需要满足第一个条件"""
     c = 0
     n = len(model_output)
     for index, code in enumerate(model_output):

evaluation/benchmarks/versicode/metric/compute_versicode_cdc_score.py

@@ -1,6 +1,4 @@
-"""
-Calculate the cdc score for line and block
-"""
+"""Calculate the cdc score for line and block"""
 
 import json
 import math
@@ -19,8 +17,7 @@ def is_code_valid(code):
 
 
 def is_correct_parameter_count(function_name, correct_code, test_code):
-    """
-    判断参数数量是否一致
+    """判断参数数量是否一致
     :param function_name:
     :param correct_code:
     :param test_code:
@@ -51,8 +48,7 @@ def is_correct_parameter_count(function_name, correct_code, test_code):
 
 
 def check_keyword_parameters(function_name, correct_code, test_code):
-    """
-    判断关键词参数赋值是否正确使用
+    """判断关键词参数赋值是否正确使用
     :param function_name:
     :param correct_code:
     :param test_code:
@@ -90,8 +86,7 @@ def check_keyword_parameters(function_name, correct_code, test_code):
 
 
 def with_correct(answer_code: str, model_output: str) -> bool:
-    """
-    当answer是with结构时，判断模型生成的是不是with结构
+    """当answer是with结构时，判断模型生成的是不是with结构
     :param answer_code:
     :param model_output:
     :return:

evaluation/benchmarks/versicode/metric/compute_versicode_em_score.py

@@ -1,6 +1,4 @@
-"""
-Calculate the cdc score for line and block
-"""
+"""Calculate the cdc score for line and block"""
 
 import json
 import math
@@ -19,8 +17,7 @@ def is_code_valid(code):
 
 
 def is_correct_parameter_count(function_name, correct_code, test_code):
-    """
-    判断参数数量是否一致
+    """判断参数数量是否一致
     :param function_name:
     :param correct_code:
     :param test_code:
@@ -51,8 +48,7 @@ def is_correct_parameter_count(function_name, correct_code, test_code):
 
 
 def check_keyword_parameters(function_name, correct_code, test_code):
-    """
-    判断关键词参数赋值是否正确使用
+    """判断关键词参数赋值是否正确使用
     :param function_name:
     :param correct_code:
     :param test_code:
@@ -90,8 +86,7 @@ def check_keyword_parameters(function_name, correct_code, test_code):
 
 
 def with_correct(answer_code: str, model_output: str) -> bool:
-    """
-    当answer是with结构时，判断模型生成的是不是with结构
+    """当answer是with结构时，判断模型生成的是不是with结构
     :param answer_code:
     :param model_output:
     :return:

evaluation/benchmarks/versicode/output_processing/choose_core_line_from_block_versicode.py

@@ -1,6 +1,4 @@
-"""
-Find the line of code generated by the model using the block in the version code
-"""
+"""Find the line of code generated by the model using the block in the version code"""
 
 import json
 import os

evaluation/benchmarks/versicode/output_processing/choose_core_line_from_migration_versicode.py

@@ -1,6 +1,4 @@
-"""
-Find the line of code generated by the model using the block in the version code
-"""
+"""Find the line of code generated by the model using the block in the version code"""
 
 import json
 import os

evaluation/benchmarks/versicode/output_processing/clear_ans.py

@@ -1,6 +1,4 @@
-"""
-Clear the<start>and<end>generated by the model in inference
-"""
+"""Clear the<start>and<end>generated by the model in inference"""
 
 import json
 

evaluation/utils/shared.py

@@ -263,19 +263,20 @@ def prepare_dataset(
             f'Randomly sampling {eval_n_limit} unique instances with random seed 42.'
         )
 
-    def make_serializable(instance: pd.Series) -> dict:
+    def make_serializable(instance_dict: dict) -> dict:
         import numpy as np
 
-        instance_dict = instance.to_dict()
         for k, v in instance_dict.items():
             if isinstance(v, np.ndarray):
                 instance_dict[k] = v.tolist()
             elif isinstance(v, pd.Timestamp):
                 instance_dict[k] = str(v)
+            elif isinstance(v, dict):
+                instance_dict[k] = make_serializable(v)
         return instance_dict
 
     new_dataset = [
-        make_serializable(instance)
+        make_serializable(instance.to_dict())
         for _, instance in dataset.iterrows()
         if str(instance[id_column]) not in finished_ids
     ]
@@ -621,8 +622,7 @@ def compatibility_for_eval_history_pairs(
 
 
 def is_fatal_evaluation_error(error: str | None) -> bool:
-    """
-    The AgentController class overrides last error for certain exceptions
+    """The AgentController class overrides last error for certain exceptions
     We want to ensure those exeption do not overlap with fatal exceptions defined here
     This is because we do a comparisino against the stringified error
     """

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

@@ -85,9 +85,10 @@ describe("ConversationPanel", () => {
     vi.clearAllMocks();
     vi.restoreAllMocks();
     // Setup default mock for getUserConversations
-    vi.spyOn(OpenHands, "getUserConversations").mockResolvedValue([
-      ...mockConversations,
-    ]);
+    vi.spyOn(OpenHands, "getUserConversations").mockResolvedValue({
+      results: [...mockConversations],
+      next_page_id: null,
+    });
   });
 
   it("should render the conversations", async () => {
@@ -101,7 +102,10 @@ describe("ConversationPanel", () => {
 
   it("should display an empty state when there are no conversations", async () => {
     const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
-    getUserConversationsSpy.mockResolvedValue([]);
+    getUserConversationsSpy.mockResolvedValue({
+      results: [],
+      next_page_id: null,
+    });
 
     renderConversationPanel();
 
@@ -195,7 +199,10 @@ describe("ConversationPanel", () => {
     ];
 
     const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
-    getUserConversationsSpy.mockImplementation(async () => mockData);
+    getUserConversationsSpy.mockImplementation(async () => ({
+      results: mockData,
+      next_page_id: null,
+    }));
 
     const deleteUserConversationSpy = vi.spyOn(
       OpenHands,
@@ -249,7 +256,10 @@ describe("ConversationPanel", () => {
   it("should refetch data on rerenders", async () => {
     const user = userEvent.setup();
     const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
-    getUserConversationsSpy.mockResolvedValue([...mockConversations]);
+    getUserConversationsSpy.mockResolvedValue({
+      results: [...mockConversations],
+      next_page_id: null,
+    });
 
     function PanelWithToggle() {
       const [isOpen, setIsOpen] = React.useState(true);
@@ -343,7 +353,10 @@ describe("ConversationPanel", () => {
     ];
 
     const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
-    getUserConversationsSpy.mockResolvedValue(mockRunningConversations);
+    getUserConversationsSpy.mockResolvedValue({
+      results: mockRunningConversations,
+      next_page_id: null,
+    });
 
     renderConversationPanel();
 
@@ -407,7 +420,10 @@ describe("ConversationPanel", () => {
     ];
 
     const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
-    getUserConversationsSpy.mockImplementation(async () => mockData);
+    getUserConversationsSpy.mockImplementation(async () => ({
+      results: mockData,
+      next_page_id: null,
+    }));
 
     const stopConversationSpy = vi.spyOn(OpenHands, "stopConversation");
     stopConversationSpy.mockImplementation(async (id: string) => {
@@ -492,7 +508,10 @@ describe("ConversationPanel", () => {
     ];
 
     const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
-    getUserConversationsSpy.mockResolvedValue(mockMixedStatusConversations);
+    getUserConversationsSpy.mockResolvedValue({
+      results: mockMixedStatusConversations,
+      next_page_id: null,
+    });
 
     renderConversationPanel();
 

frontend/__tests__/components/features/maintenance/maintenance-banner.test.tsx

@@ -1,16 +1,18 @@
-import { render, screen } from "@testing-library/react";
-import { describe, expect, it, vi } from "vitest";
+import { fireEvent, render, screen, within } from "@testing-library/react";
+import { afterEach, describe, expect, it, vi } from "vitest";
+import { act } from "react";
 import { MaintenanceBanner } from "#/components/features/maintenance/maintenance-banner";
 
 // Mock react-i18next
 vi.mock("react-i18next", async () => {
-  const actual = await vi.importActual<typeof import("react-i18next")>("react-i18next");
+  const actual =
+    await vi.importActual<typeof import("react-i18next")>("react-i18next");
   return {
     ...actual,
     useTranslation: () => ({
       t: (key: string, options?: { time?: string }) => {
         const translations: Record<string, string> = {
-          "MAINTENANCE$SCHEDULED_MESSAGE": `Scheduled maintenance will begin at ${options?.time || "{{time}}"}`,
+          MAINTENANCE$SCHEDULED_MESSAGE: `Scheduled maintenance will begin at ${options?.time || "{{time}}"}`,
         };
         return translations[key] || key;
       },
@@ -19,34 +21,91 @@ vi.mock("react-i18next", async () => {
 });
 
 describe("MaintenanceBanner", () => {
+  afterEach(() => {
+    localStorage.clear();
+  });
+
   it("renders maintenance banner with formatted time", () => {
     const startTime = "2024-01-15T10:00:00-05:00"; // EST timestamp
 
     const { container } = render(<MaintenanceBanner startTime={startTime} />);
 
     // Check if the banner is rendered
-    expect(screen.getByText(/Scheduled maintenance will begin at/)).toBeInTheDocument();
+    const banner = screen.queryByTestId("maintenance-banner");
+    expect(banner).toBeInTheDocument();
 
     // Check if the warning icon (SVG) is present
-    const svgIcon = container.querySelector('svg');
+    const svgIcon = container.querySelector("svg");
     expect(svgIcon).toBeInTheDocument();
+
+    // Check if the button to close is present
+    const button = within(banner!).queryByTestId("dismiss-button");
+    expect(button).toBeInTheDocument();
   });
 
+  // maintenance-banner
+
   it("handles invalid date gracefully", () => {
     const invalidTime = "invalid-date";
 
     render(<MaintenanceBanner startTime={invalidTime} />);
 
-    // Should still render the banner with the original string
-    expect(screen.getByText(/Scheduled maintenance will begin at invalid-date/)).toBeInTheDocument();
+    // Check if the banner is rendered
+    const banner = screen.queryByTestId("maintenance-banner");
+    expect(banner).not.toBeInTheDocument();
   });
 
-  it("formats ISO date string correctly", () => {
-    const isoTime = "2024-01-15T15:30:00.000Z";
+  it("click on dismiss button removes banner", () => {
+    const startTime = "2024-01-15T10:00:00-05:00"; // EST timestamp
 
-    render(<MaintenanceBanner startTime={isoTime} />);
+    render(<MaintenanceBanner startTime={startTime} />);
 
-    // Should render the banner (exact time format will depend on user's timezone)
-    expect(screen.getByText(/Scheduled maintenance will begin at/)).toBeInTheDocument();
+    // Check if the banner is rendered
+    const banner = screen.queryByTestId("maintenance-banner");
+
+    const button = within(banner!).queryByTestId("dismiss-button");
+    act(() => {
+      fireEvent.click(button!);
+    });
+
+    expect(banner).not.toBeInTheDocument();
+  });
+  it("banner reappears after dismissing on next maintenance event(future time)", () => {
+    const startTime = "2024-01-15T10:00:00-05:00"; // EST timestamp
+    const nextStartTime = "2025-01-15T10:00:00-05:00"; // EST timestamp
+
+    const { rerender } = render(<MaintenanceBanner startTime={startTime} />);
+
+    // Check if the banner is rendered
+    const banner = screen.queryByTestId("maintenance-banner");
+    const button = within(banner!).queryByTestId("dismiss-button");
+
+    act(() => {
+      fireEvent.click(button!);
+    });
+
+    expect(banner).not.toBeInTheDocument();
+    rerender(<MaintenanceBanner startTime={nextStartTime} />);
+
+    expect(screen.queryByTestId("maintenance-banner")).toBeInTheDocument();
+  });
+  it("banner doesn't reappear after dismissing on next maintenance event(past time)", () => {
+    const startTime = "2024-01-15T10:00:00-05:00"; // EST timestamp
+    const nextStartTime = "2023-01-15T10:00:00-05:00"; // EST timestamp
+
+    const { rerender } = render(<MaintenanceBanner startTime={startTime} />);
+
+    // Check if the banner is rendered
+    const banner = screen.queryByTestId("maintenance-banner");
+    const button = within(banner!).queryByTestId("dismiss-button");
+
+    act(() => {
+      fireEvent.click(button!);
+    });
+
+    expect(banner).not.toBeInTheDocument();
+    rerender(<MaintenanceBanner startTime={nextStartTime} />);
+
+    expect(screen.queryByTestId("maintenance-banner")).not.toBeInTheDocument();
   });
 });

frontend/__tests__/hooks/use-document-title-from-state.test.tsx

@@ -0,0 +1,135 @@
+import { describe, it, expect, vi, beforeEach, afterEach } from "vitest";
+import { renderHook } from "@testing-library/react";
+import { useDocumentTitleFromState } from "#/hooks/use-document-title-from-state";
+import { useActiveConversation } from "#/hooks/query/use-active-conversation";
+
+// Mock the useActiveConversation hook
+vi.mock("#/hooks/query/use-active-conversation");
+
+const mockUseActiveConversation = vi.mocked(useActiveConversation);
+
+describe("useDocumentTitleFromState", () => {
+  const originalTitle = document.title;
+
+  beforeEach(() => {
+    vi.clearAllMocks();
+    document.title = "Test";
+  });
+
+  afterEach(() => {
+    document.title = originalTitle;
+    vi.resetAllMocks();
+  });
+
+  it("should set document title to default suffix when no conversation", () => {
+    mockUseActiveConversation.mockReturnValue({
+      data: null,
+    } as any);
+
+    renderHook(() => useDocumentTitleFromState());
+
+    expect(document.title).toBe("OpenHands");
+  });
+
+  it("should set document title to custom suffix when no conversation", () => {
+    mockUseActiveConversation.mockReturnValue({
+      data: null,
+    } as any);
+
+    renderHook(() => useDocumentTitleFromState("Custom App"));
+
+    expect(document.title).toBe("Custom App");
+  });
+
+  it("should set document title with conversation title", () => {
+    mockUseActiveConversation.mockReturnValue({
+      data: {
+        conversation_id: "123",
+        title: "My Conversation",
+        status: "RUNNING",
+      },
+    } as any);
+
+    renderHook(() => useDocumentTitleFromState());
+
+    expect(document.title).toBe("My Conversation | OpenHands");
+  });
+
+  it("should update document title when conversation title changes", () => {
+    // Initial state - no conversation
+    mockUseActiveConversation.mockReturnValue({
+      data: null,
+    } as any);
+
+    const { rerender } = renderHook(() => useDocumentTitleFromState());
+    expect(document.title).toBe("OpenHands");
+
+    // Conversation with initial title
+    mockUseActiveConversation.mockReturnValue({
+      data: {
+        conversation_id: "123",
+        title: "Conversation 65e29",
+        status: "RUNNING",
+      },
+    } as any);
+    rerender();
+    expect(document.title).toBe("Conversation 65e29 | OpenHands");
+
+    // Conversation title updated to human-readable title
+    mockUseActiveConversation.mockReturnValue({
+      data: {
+        conversation_id: "123",
+        title: "Help me build a React app",
+        status: "RUNNING",
+      },
+    } as any);
+    rerender();
+    expect(document.title).toBe("Help me build a React app | OpenHands");
+  });
+
+  it("should handle conversation without title", () => {
+    mockUseActiveConversation.mockReturnValue({
+      data: {
+        conversation_id: "123",
+        title: undefined,
+        status: "RUNNING",
+      },
+    } as any);
+
+    renderHook(() => useDocumentTitleFromState());
+
+    expect(document.title).toBe("OpenHands");
+  });
+
+  it("should handle empty conversation title", () => {
+    mockUseActiveConversation.mockReturnValue({
+      data: {
+        conversation_id: "123",
+        title: "",
+        status: "RUNNING",
+      },
+    } as any);
+
+    renderHook(() => useDocumentTitleFromState());
+
+    expect(document.title).toBe("OpenHands");
+  });
+
+  it("should reset document title on cleanup", () => {
+    mockUseActiveConversation.mockReturnValue({
+      data: {
+        conversation_id: "123",
+        title: "My Conversation",
+        status: "RUNNING",
+      },
+    } as any);
+
+    const { unmount } = renderHook(() => useDocumentTitleFromState());
+
+    expect(document.title).toBe("My Conversation | OpenHands");
+
+    unmount();
+
+    expect(document.title).toBe("OpenHands");
+  });
+});

frontend/package-lock.json

@@ -1,31 +1,33 @@
 {
   "name": "openhands-frontend",
-  "version": "0.51.1",
+  "version": "0.52.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "openhands-frontend",
-      "version": "0.51.1",
+      "version": "0.52.1",
       "dependencies": {
         "@heroui/react": "^2.8.2",
         "@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": "^7.7.1",
-        "@react-router/serve": "^7.7.1",
+        "@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": "^3.9.0",
         "@stripe/stripe-js": "^7.8.0",
         "@tailwindcss/postcss": "^4.1.11",
         "@tailwindcss/vite": "^4.1.11",
-        "@tanstack/react-query": "^5.84.1",
-        "@vitejs/plugin-react": "^4.7.0",
+        "@tanstack/react-query": "^5.84.2",
+        "@uidotdev/usehooks": "^2.4.1",
+        "@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",
         "eslint-config-airbnb-typescript": "^18.0.0",
         "framer-motion": "^12.23.12",
         "i18next": "^25.3.2",
@@ -33,9 +35,9 @@
         "i18next-http-backend": "^3.0.2",
         "isbot": "^5.1.29",
         "jose": "^6.0.12",
-        "lucide-react": "^0.536.0",
+        "lucide-react": "^0.539.0",
         "monaco-editor": "^0.52.2",
-        "posthog-js": "^1.258.5",
+        "posthog-js": "^1.259.0",
         "react": "^19.1.1",
         "react-dom": "^19.1.1",
         "react-highlight": "^0.15.0",
@@ -44,7 +46,7 @@
         "react-icons": "^5.5.0",
         "react-markdown": "^10.1.0",
         "react-redux": "^9.2.0",
-        "react-router": "^7.7.1",
+        "react-router": "^7.8.0",
         "react-select": "^5.10.2",
         "react-syntax-highlighter": "^15.6.1",
         "react-textarea-autosize": "^8.5.9",
@@ -53,7 +55,7 @@
         "sirv-cli": "^3.0.1",
         "socket.io-client": "^4.8.1",
         "tailwind-merge": "^3.3.1",
-        "vite": "^7.0.6",
+        "vite": "^7.1.1",
         "web-vitals": "^5.1.0",
         "ws": "^8.18.2"
       },
@@ -63,7 +65,7 @@
         "@babel/types": "^7.28.2",
         "@mswjs/socket.io-binding": "^0.2.0",
         "@playwright/test": "^1.54.2",
-        "@react-router/dev": "^7.7.1",
+        "@react-router/dev": "^7.8.0",
         "@tailwindcss/typography": "^0.5.16",
         "@tanstack/eslint-plugin-query": "^5.83.1",
         "@testing-library/dom": "^10.4.1",
@@ -3394,9 +3396,9 @@
       }
     },
     "node_modules/@jridgewell/gen-mapping": {
-      "version": "0.3.12",
-      "resolved": "https://registry.npmjs.org/@jridgewell/gen-mapping/-/gen-mapping-0.3.12.tgz",
-      "integrity": "sha512-OuLGC46TjB5BbN1dH8JULVVZY4WTdkF7tV9Ys6wLL1rubZnCMstOhNHueU5bLCrnRuDhKPDM4g6sw4Bel5Gzqg==",
+      "version": "0.3.13",
+      "resolved": "https://registry.npmjs.org/@jridgewell/gen-mapping/-/gen-mapping-0.3.13.tgz",
+      "integrity": "sha512-2kkt/7niJ6MgEPxF0bYdQ6etZaA+fQvDcLKckhy1yIQOzaoKjBBjSj63/aLVjYE3qhRt5dvM+uUyfCg6UKCBbA==",
       "license": "MIT",
       "dependencies": {
         "@jridgewell/sourcemap-codec": "^1.5.0",
@@ -3413,15 +3415,15 @@
       }
     },
     "node_modules/@jridgewell/sourcemap-codec": {
-      "version": "1.5.4",
-      "resolved": "https://registry.npmjs.org/@jridgewell/sourcemap-codec/-/sourcemap-codec-1.5.4.tgz",
-      "integrity": "sha512-VT2+G1VQs/9oz078bLrYbecdZKs912zQlkelYpuf+SXF+QvZDYJlbx/LSx+meSAwdDFnF8FVXW92AVjjkVmgFw==",
+      "version": "1.5.5",
+      "resolved": "https://registry.npmjs.org/@jridgewell/sourcemap-codec/-/sourcemap-codec-1.5.5.tgz",
+      "integrity": "sha512-cYQ9310grqxueWbl+WuIUIaiUaDcj7WOq5fVhEljNVgRfOUhY9fy2zTvfoqWsnebh8Sl70VScFbICvJnLKB0Og==",
       "license": "MIT"
     },
     "node_modules/@jridgewell/trace-mapping": {
-      "version": "0.3.29",
-      "resolved": "https://registry.npmjs.org/@jridgewell/trace-mapping/-/trace-mapping-0.3.29.tgz",
-      "integrity": "sha512-uw6guiW/gcAGPDhLmd77/6lW8QLeiV5RUTsAX46Db6oLhGaVj4lhnPwb184s1bkc8kdVg/+h988dro8GRDpmYQ==",
+      "version": "0.3.30",
+      "resolved": "https://registry.npmjs.org/@jridgewell/trace-mapping/-/trace-mapping-0.3.30.tgz",
+      "integrity": "sha512-GQ7Nw5G2lTu/BtHTKfXhKHok2WGetd4XYcVKGx00SjAk8GMwgJM3zr6zORiPGuOE+/vkc90KtTosSSvaCjKb2Q==",
       "license": "MIT",
       "dependencies": {
         "@jridgewell/resolve-uri": "^3.1.0",
@@ -4388,9 +4390,9 @@
       }
     },
     "node_modules/@react-router/dev": {
-      "version": "7.7.1",
-      "resolved": "https://registry.npmjs.org/@react-router/dev/-/dev-7.7.1.tgz",
-      "integrity": "sha512-ByfgHmAyfx/JQYN/QwUx1sFJlBA5Z3HQAZ638wHSb+m6khWtHqSaKCvPqQh1P00wdEAeV3tX5L1aUM/ceCF6+w==",
+      "version": "7.8.0",
+      "resolved": "https://registry.npmjs.org/@react-router/dev/-/dev-7.8.0.tgz",
+      "integrity": "sha512-5NA9yLZComM+kCD3zNPL3rjrAFjzzODY8hjAJlpz/6jpyXoF28W8QTSo8rxc56XVNLONM75Y5nq1wzeEcWFFKA==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -4402,7 +4404,9 @@
         "@babel/traverse": "^7.27.7",
         "@babel/types": "^7.27.7",
         "@npmcli/package-json": "^4.0.1",
-        "@react-router/node": "7.7.1",
+        "@react-router/node": "7.8.0",
+        "@vitejs/plugin-react": "^4.5.2",
+        "@vitejs/plugin-rsc": "0.4.11",
         "arg": "^5.0.1",
         "babel-dead-code-elimination": "^1.0.6",
         "chokidar": "^4.0.0",
@@ -4429,8 +4433,8 @@
         "node": ">=20.0.0"
       },
       "peerDependencies": {
-        "@react-router/serve": "^7.7.1",
-        "react-router": "^7.7.1",
+        "@react-router/serve": "^7.8.0",
+        "react-router": "^7.8.0",
         "typescript": "^5.1.0",
         "vite": "^5.1.0 || ^6.0.0 || ^7.0.0",
         "wrangler": "^3.28.2 || ^4.0.0"
@@ -4447,6 +4451,44 @@
         }
       }
     },
+    "node_modules/@react-router/dev/node_modules/@rolldown/pluginutils": {
+      "version": "1.0.0-beta.27",
+      "resolved": "https://registry.npmjs.org/@rolldown/pluginutils/-/pluginutils-1.0.0-beta.27.tgz",
+      "integrity": "sha512-+d0F4MKMCbeVUJwG96uQ4SgAznZNSq93I3V+9NHA4OpvqG8mRCpGdKmK8l/dl02h2CCDHwW2FqilnTyDcAnqjA==",
+      "dev": true,
+      "license": "MIT"
+    },
+    "node_modules/@react-router/dev/node_modules/@vitejs/plugin-react": {
+      "version": "4.7.0",
+      "resolved": "https://registry.npmjs.org/@vitejs/plugin-react/-/plugin-react-4.7.0.tgz",
+      "integrity": "sha512-gUu9hwfWvvEDBBmgtAowQCojwZmJ5mcLn3aufeCsitijs3+f2NsrPtlAWIR6OPiqljl96GVCUbLe0HyqIpVaoA==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@babel/core": "^7.28.0",
+        "@babel/plugin-transform-react-jsx-self": "^7.27.1",
+        "@babel/plugin-transform-react-jsx-source": "^7.27.1",
+        "@rolldown/pluginutils": "1.0.0-beta.27",
+        "@types/babel__core": "^7.20.5",
+        "react-refresh": "^0.17.0"
+      },
+      "engines": {
+        "node": "^14.18.0 || >=16.0.0"
+      },
+      "peerDependencies": {
+        "vite": "^4.2.0 || ^5.0.0 || ^6.0.0 || ^7.0.0"
+      }
+    },
+    "node_modules/@react-router/dev/node_modules/@vitejs/plugin-react/node_modules/react-refresh": {
+      "version": "0.17.0",
+      "resolved": "https://registry.npmjs.org/react-refresh/-/react-refresh-0.17.0.tgz",
+      "integrity": "sha512-z6F7K9bV85EfseRCp2bzrpyQ0Gkw1uLoCel9XBVWPg/TjRj94SkJzUTGfOa4bs7iJvBWtQG0Wq7wnI0syw3EBQ==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=0.10.0"
+      }
+    },
     "node_modules/@react-router/dev/node_modules/jsesc": {
       "version": "3.0.2",
       "resolved": "https://registry.npmjs.org/jsesc/-/jsesc-3.0.2.tgz",
@@ -4461,19 +4503,19 @@
       }
     },
     "node_modules/@react-router/express": {
-      "version": "7.7.1",
-      "resolved": "https://registry.npmjs.org/@react-router/express/-/express-7.7.1.tgz",
-      "integrity": "sha512-OEZwIM7i/KPSDjwVRg3LqeNIwG41U+SeFOwMjhZRFfyrnwghHfvWsDajf73r4ccMh+RRHcP1GIN6VSU3XZk7MA==",
+      "version": "7.8.0",
+      "resolved": "https://registry.npmjs.org/@react-router/express/-/express-7.8.0.tgz",
+      "integrity": "sha512-lNUwux5IfMqczIL3gXZ/mauPUoVz65fSLPnUTkP7hkh/P7fcsPtYkmcixuaWb+882lY+Glf157OdoIMbcSMBaA==",
       "license": "MIT",
       "dependencies": {
-        "@react-router/node": "7.7.1"
+        "@react-router/node": "7.8.0"
       },
       "engines": {
         "node": ">=20.0.0"
       },
       "peerDependencies": {
         "express": "^4.17.1 || ^5",
-        "react-router": "7.7.1",
+        "react-router": "7.8.0",
         "typescript": "^5.1.0"
       },
       "peerDependenciesMeta": {
@@ -4483,9 +4525,9 @@
       }
     },
     "node_modules/@react-router/node": {
-      "version": "7.7.1",
-      "resolved": "https://registry.npmjs.org/@react-router/node/-/node-7.7.1.tgz",
-      "integrity": "sha512-EHd6PEcw2nmcJmcYTPA0MmRWSqOaJ/meycfCp0ADA9T/6b7+fUHfr9XcNyf7UeZtYwu4zGyuYfPmLU5ic6Ugyg==",
+      "version": "7.8.0",
+      "resolved": "https://registry.npmjs.org/@react-router/node/-/node-7.8.0.tgz",
+      "integrity": "sha512-/FFN9vqI2EHPwDCHTvsMInhrYvwJ5SlCeyUr1oWUxH47JyYkooVFks5++M4VkrTgj2ZBsMjPPKy0xRNTQdtBDA==",
       "license": "MIT",
       "dependencies": {
         "@mjackson/node-fetch-server": "^0.2.0"
@@ -4494,7 +4536,7 @@
         "node": ">=20.0.0"
       },
       "peerDependencies": {
-        "react-router": "7.7.1",
+        "react-router": "7.8.0",
         "typescript": "^5.1.0"
       },
       "peerDependenciesMeta": {
@@ -4504,13 +4546,13 @@
       }
     },
     "node_modules/@react-router/serve": {
-      "version": "7.7.1",
-      "resolved": "https://registry.npmjs.org/@react-router/serve/-/serve-7.7.1.tgz",
-      "integrity": "sha512-LyAiX+oI+6O6j2xWPUoKW+cgayUf3USBosSMv73Jtwi99XUhSDu2MUhM+BB+AbrYRubauZ83QpZTROiXoaf8jA==",
+      "version": "7.8.0",
+      "resolved": "https://registry.npmjs.org/@react-router/serve/-/serve-7.8.0.tgz",
+      "integrity": "sha512-DokCv1GfOMt9KHu+k3WYY9sP5nOEzq7za+Vi3dWPHoY5oP0wgv8S4DnTPU08ASY8iFaF38NAzapbSFfu6Xfr0Q==",
       "license": "MIT",
       "dependencies": {
-        "@react-router/express": "7.7.1",
-        "@react-router/node": "7.7.1",
+        "@react-router/express": "7.8.0",
+        "@react-router/node": "7.8.0",
         "compression": "^1.7.4",
         "express": "^4.19.2",
         "get-port": "5.1.1",
@@ -4524,7 +4566,7 @@
         "node": ">=20.0.0"
       },
       "peerDependencies": {
-        "react-router": "7.7.1"
+        "react-router": "7.8.0"
       }
     },
     "node_modules/@react-stately/calendar": {
@@ -5226,9 +5268,9 @@
       }
     },
     "node_modules/@rolldown/pluginutils": {
-      "version": "1.0.0-beta.27",
-      "resolved": "https://registry.npmjs.org/@rolldown/pluginutils/-/pluginutils-1.0.0-beta.27.tgz",
-      "integrity": "sha512-+d0F4MKMCbeVUJwG96uQ4SgAznZNSq93I3V+9NHA4OpvqG8mRCpGdKmK8l/dl02h2CCDHwW2FqilnTyDcAnqjA==",
+      "version": "1.0.0-beta.30",
+      "resolved": "https://registry.npmjs.org/@rolldown/pluginutils/-/pluginutils-1.0.0-beta.30.tgz",
+      "integrity": "sha512-whXaSoNUFiyDAjkUF8OBpOm77Szdbk5lGNqFe6CbVbJFrhCCPinCbRA3NjawwlNHla1No7xvXXh+CpSxnPfUEw==",
       "license": "MIT"
     },
     "node_modules/@rollup/pluginutils": {
@@ -6175,9 +6217,9 @@
       }
     },
     "node_modules/@tanstack/react-query": {
-      "version": "5.84.1",
-      "resolved": "https://registry.npmjs.org/@tanstack/react-query/-/react-query-5.84.1.tgz",
-      "integrity": "sha512-zo7EUygcWJMQfFNWDSG7CBhy8irje/XY0RDVKKV4IQJAysb+ZJkkJPcnQi+KboyGUgT+SQebRFoTqLuTtfoDLw==",
+      "version": "5.85.0",
+      "resolved": "https://registry.npmjs.org/@tanstack/react-query/-/react-query-5.85.0.tgz",
+      "integrity": "sha512-t1HMfToVMGfwEJRya6GG7gbK0luZJd+9IySFNePL1BforU1F3LqQ3tBC2Rpvr88bOrlU6PXyMLgJD0Yzn4ztUw==",
       "license": "MIT",
       "dependencies": {
         "@tanstack/query-core": "5.83.1"
@@ -6447,9 +6489,9 @@
       "license": "MIT"
     },
     "node_modules/@types/node": {
-      "version": "24.2.0",
-      "resolved": "https://registry.npmjs.org/@types/node/-/node-24.2.0.tgz",
-      "integrity": "sha512-3xyG3pMCq3oYCNg7/ZP+E1ooTaGB4cG8JWRsqqOYQdbWNY4zbaV0Ennrd7stjiJEFZCaybcIgpTjJWHRfBSIDw==",
+      "version": "24.2.1",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-24.2.1.tgz",
+      "integrity": "sha512-DRh5K+ka5eJic8CjH7td8QpYEV6Zo10gfRkjHCO3weqZHWDtAaSTFtl4+VMqOJ4N5jcuhZ9/l+yy8rVgw7BQeQ==",
       "devOptional": true,
       "license": "MIT",
       "dependencies": {
@@ -6463,9 +6505,9 @@
       "license": "MIT"
     },
     "node_modules/@types/react": {
-      "version": "19.1.9",
-      "resolved": "https://registry.npmjs.org/@types/react/-/react-19.1.9.tgz",
-      "integrity": "sha512-WmdoynAX8Stew/36uTSVMcLJJ1KRh6L3IZRx1PZ7qJtBqT3dYTgyDTx8H1qoRghErydW7xw9mSJ3wS//tCRpFA==",
+      "version": "19.1.10",
+      "resolved": "https://registry.npmjs.org/@types/react/-/react-19.1.10.tgz",
+      "integrity": "sha512-EhBeSYX0Y6ye8pNebpKrwFJq7BoQ8J5SO6NlvNwwHjSj6adXJViPQrKlsyPw7hLBLvckEMO1yxeGdR82YBBlDg==",
       "license": "MIT",
       "dependencies": {
         "csstype": "^3.0.2"
@@ -6633,14 +6675,14 @@
       }
     },
     "node_modules/@typescript-eslint/project-service": {
-      "version": "8.39.0",
-      "resolved": "https://registry.npmjs.org/@typescript-eslint/project-service/-/project-service-8.39.0.tgz",
-      "integrity": "sha512-CTzJqaSq30V/Z2Og9jogzZt8lJRR5TKlAdXmWgdu4hgcC9Kww5flQ+xFvMxIBWVNdxJO7OifgdOK4PokMIWPew==",
+      "version": "8.39.1",
+      "resolved": "https://registry.npmjs.org/@typescript-eslint/project-service/-/project-service-8.39.1.tgz",
+      "integrity": "sha512-8fZxek3ONTwBu9ptw5nCKqZOSkXshZB7uAxuFF0J/wTMkKydjXCzqqga7MlFMpHi9DoG4BadhmTkITBcg8Aybw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
-        "@typescript-eslint/tsconfig-utils": "^8.39.0",
-        "@typescript-eslint/types": "^8.39.0",
+        "@typescript-eslint/tsconfig-utils": "^8.39.1",
+        "@typescript-eslint/types": "^8.39.1",
         "debug": "^4.3.4"
       },
       "engines": {
@@ -6655,9 +6697,9 @@
       }
     },
     "node_modules/@typescript-eslint/project-service/node_modules/@typescript-eslint/types": {
-      "version": "8.39.0",
-      "resolved": "https://registry.npmjs.org/@typescript-eslint/types/-/types-8.39.0.tgz",
-      "integrity": "sha512-ArDdaOllnCj3yn/lzKn9s0pBQYmmyme/v1HbGIGB0GB/knFI3fWMHloC+oYTJW46tVbYnGKTMDK4ah1sC2v0Kg==",
+      "version": "8.39.1",
+      "resolved": "https://registry.npmjs.org/@typescript-eslint/types/-/types-8.39.1.tgz",
+      "integrity": "sha512-7sPDKQQp+S11laqTrhHqeAbsCfMkwJMrV7oTDvtDds4mEofJYir414bYKUEb8YPUm9QL3U+8f6L6YExSoAGdQw==",
       "dev": true,
       "license": "MIT",
       "engines": {
@@ -6687,9 +6729,9 @@
       }
     },
     "node_modules/@typescript-eslint/tsconfig-utils": {
-      "version": "8.39.0",
-      "resolved": "https://registry.npmjs.org/@typescript-eslint/tsconfig-utils/-/tsconfig-utils-8.39.0.tgz",
-      "integrity": "sha512-Fd3/QjmFV2sKmvv3Mrj8r6N8CryYiCS8Wdb/6/rgOXAWGcFuc+VkQuG28uk/4kVNVZBQuuDHEDUpo/pQ32zsIQ==",
+      "version": "8.39.1",
+      "resolved": "https://registry.npmjs.org/@typescript-eslint/tsconfig-utils/-/tsconfig-utils-8.39.1.tgz",
+      "integrity": "sha512-ePUPGVtTMR8XMU2Hee8kD0Pu4NDE1CN9Q1sxGSGd/mbOtGZDM7pnhXNJnzW63zk/q+Z54zVzj44HtwXln5CvHA==",
       "dev": true,
       "license": "MIT",
       "engines": {
@@ -6798,16 +6840,16 @@
       }
     },
     "node_modules/@typescript-eslint/utils": {
-      "version": "8.39.0",
-      "resolved": "https://registry.npmjs.org/@typescript-eslint/utils/-/utils-8.39.0.tgz",
-      "integrity": "sha512-4GVSvNA0Vx1Ktwvf4sFE+exxJ3QGUorQG1/A5mRfRNZtkBT2xrA/BCO2H0eALx/PnvCS6/vmYwRdDA41EoffkQ==",
+      "version": "8.39.1",
+      "resolved": "https://registry.npmjs.org/@typescript-eslint/utils/-/utils-8.39.1.tgz",
+      "integrity": "sha512-VF5tZ2XnUSTuiqZFXCZfZs1cgkdd3O/sSYmdo2EpSyDlC86UM/8YytTmKnehOW3TGAlivqTDT6bS87B/GQ/jyg==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
         "@eslint-community/eslint-utils": "^4.7.0",
-        "@typescript-eslint/scope-manager": "8.39.0",
-        "@typescript-eslint/types": "8.39.0",
-        "@typescript-eslint/typescript-estree": "8.39.0"
+        "@typescript-eslint/scope-manager": "8.39.1",
+        "@typescript-eslint/types": "8.39.1",
+        "@typescript-eslint/typescript-estree": "8.39.1"
       },
       "engines": {
         "node": "^18.18.0 || ^20.9.0 || >=21.1.0"
@@ -6822,14 +6864,14 @@
       }
     },
     "node_modules/@typescript-eslint/utils/node_modules/@typescript-eslint/scope-manager": {
-      "version": "8.39.0",
-      "resolved": "https://registry.npmjs.org/@typescript-eslint/scope-manager/-/scope-manager-8.39.0.tgz",
-      "integrity": "sha512-8QOzff9UKxOh6npZQ/4FQu4mjdOCGSdO3p44ww0hk8Vu+IGbg0tB/H1LcTARRDzGCC8pDGbh2rissBuuoPgH8A==",
+      "version": "8.39.1",
+      "resolved": "https://registry.npmjs.org/@typescript-eslint/scope-manager/-/scope-manager-8.39.1.tgz",
+      "integrity": "sha512-RkBKGBrjgskFGWuyUGz/EtD8AF/GW49S21J8dvMzpJitOF1slLEbbHnNEtAHtnDAnx8qDEdRrULRnWVx27wGBw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
-        "@typescript-eslint/types": "8.39.0",
-        "@typescript-eslint/visitor-keys": "8.39.0"
+        "@typescript-eslint/types": "8.39.1",
+        "@typescript-eslint/visitor-keys": "8.39.1"
       },
       "engines": {
         "node": "^18.18.0 || ^20.9.0 || >=21.1.0"
@@ -6840,9 +6882,9 @@
       }
     },
     "node_modules/@typescript-eslint/utils/node_modules/@typescript-eslint/types": {
-      "version": "8.39.0",
-      "resolved": "https://registry.npmjs.org/@typescript-eslint/types/-/types-8.39.0.tgz",
-      "integrity": "sha512-ArDdaOllnCj3yn/lzKn9s0pBQYmmyme/v1HbGIGB0GB/knFI3fWMHloC+oYTJW46tVbYnGKTMDK4ah1sC2v0Kg==",
+      "version": "8.39.1",
+      "resolved": "https://registry.npmjs.org/@typescript-eslint/types/-/types-8.39.1.tgz",
+      "integrity": "sha512-7sPDKQQp+S11laqTrhHqeAbsCfMkwJMrV7oTDvtDds4mEofJYir414bYKUEb8YPUm9QL3U+8f6L6YExSoAGdQw==",
       "dev": true,
       "license": "MIT",
       "engines": {
@@ -6854,16 +6896,16 @@
       }
     },
     "node_modules/@typescript-eslint/utils/node_modules/@typescript-eslint/typescript-estree": {
-      "version": "8.39.0",
-      "resolved": "https://registry.npmjs.org/@typescript-eslint/typescript-estree/-/typescript-estree-8.39.0.tgz",
-      "integrity": "sha512-ndWdiflRMvfIgQRpckQQLiB5qAKQ7w++V4LlCHwp62eym1HLB/kw7D9f2e8ytONls/jt89TEasgvb+VwnRprsw==",
+      "version": "8.39.1",
+      "resolved": "https://registry.npmjs.org/@typescript-eslint/typescript-estree/-/typescript-estree-8.39.1.tgz",
+      "integrity": "sha512-EKkpcPuIux48dddVDXyQBlKdeTPMmALqBUbEk38McWv0qVEZwOpVJBi7ugK5qVNgeuYjGNQxrrnoM/5+TI/BPw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
-        "@typescript-eslint/project-service": "8.39.0",
-        "@typescript-eslint/tsconfig-utils": "8.39.0",
-        "@typescript-eslint/types": "8.39.0",
-        "@typescript-eslint/visitor-keys": "8.39.0",
+        "@typescript-eslint/project-service": "8.39.1",
+        "@typescript-eslint/tsconfig-utils": "8.39.1",
+        "@typescript-eslint/types": "8.39.1",
+        "@typescript-eslint/visitor-keys": "8.39.1",
         "debug": "^4.3.4",
         "fast-glob": "^3.3.2",
         "is-glob": "^4.0.3",
@@ -6883,13 +6925,13 @@
       }
     },
     "node_modules/@typescript-eslint/utils/node_modules/@typescript-eslint/visitor-keys": {
-      "version": "8.39.0",
-      "resolved": "https://registry.npmjs.org/@typescript-eslint/visitor-keys/-/visitor-keys-8.39.0.tgz",
-      "integrity": "sha512-ldgiJ+VAhQCfIjeOgu8Kj5nSxds0ktPOSO9p4+0VDH2R2pLvQraaM5Oen2d7NxzMCm+Sn/vJT+mv2H5u6b/3fA==",
+      "version": "8.39.1",
+      "resolved": "https://registry.npmjs.org/@typescript-eslint/visitor-keys/-/visitor-keys-8.39.1.tgz",
+      "integrity": "sha512-W8FQi6kEh2e8zVhQ0eeRnxdvIoOkAp/CPAahcNio6nO9dsIwb9b34z90KOlheoyuVf6LSOEdjlkxSkapNEc+4A==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
-        "@typescript-eslint/types": "8.39.0",
+        "@typescript-eslint/types": "8.39.1",
         "eslint-visitor-keys": "^4.2.1"
       },
       "engines": {
@@ -6944,6 +6986,19 @@
         "url": "https://opencollective.com/typescript-eslint"
       }
     },
+    "node_modules/@uidotdev/usehooks": {
+      "version": "2.4.1",
+      "resolved": "https://registry.npmjs.org/@uidotdev/usehooks/-/usehooks-2.4.1.tgz",
+      "integrity": "sha512-1I+RwWyS+kdv3Mv0Vmc+p0dPYH0DTRAo04HLyXReYBL9AeseDWUJyi4THuksBJcu9F0Pih69Ak150VDnqbVnXg==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=16"
+      },
+      "peerDependencies": {
+        "react": ">=18.0.0",
+        "react-dom": ">=18.0.0"
+      }
+    },
     "node_modules/@ungap/structured-clone": {
       "version": "1.3.0",
       "resolved": "https://registry.npmjs.org/@ungap/structured-clone/-/structured-clone-1.3.0.tgz",
@@ -6951,20 +7006,20 @@
       "license": "ISC"
     },
     "node_modules/@vitejs/plugin-react": {
-      "version": "4.7.0",
-      "resolved": "https://registry.npmjs.org/@vitejs/plugin-react/-/plugin-react-4.7.0.tgz",
-      "integrity": "sha512-gUu9hwfWvvEDBBmgtAowQCojwZmJ5mcLn3aufeCsitijs3+f2NsrPtlAWIR6OPiqljl96GVCUbLe0HyqIpVaoA==",
+      "version": "5.0.0",
+      "resolved": "https://registry.npmjs.org/@vitejs/plugin-react/-/plugin-react-5.0.0.tgz",
+      "integrity": "sha512-Jx9JfsTa05bYkS9xo0hkofp2dCmp1blrKjw9JONs5BTHOvJCgLbaPSuZLGSVJW6u2qe0tc4eevY0+gSNNi0YCw==",
       "license": "MIT",
       "dependencies": {
         "@babel/core": "^7.28.0",
         "@babel/plugin-transform-react-jsx-self": "^7.27.1",
         "@babel/plugin-transform-react-jsx-source": "^7.27.1",
-        "@rolldown/pluginutils": "1.0.0-beta.27",
+        "@rolldown/pluginutils": "1.0.0-beta.30",
         "@types/babel__core": "^7.20.5",
         "react-refresh": "^0.17.0"
       },
       "engines": {
-        "node": "^14.18.0 || >=16.0.0"
+        "node": "^20.19.0 || >=22.12.0"
       },
       "peerDependencies": {
         "vite": "^4.2.0 || ^5.0.0 || ^6.0.0 || ^7.0.0"
@@ -6979,6 +7034,34 @@
         "node": ">=0.10.0"
       }
     },
+    "node_modules/@vitejs/plugin-rsc": {
+      "version": "0.4.11",
+      "resolved": "https://registry.npmjs.org/@vitejs/plugin-rsc/-/plugin-rsc-0.4.11.tgz",
+      "integrity": "sha512-+4H4wLi+Y9yF58znBfKgGfX8zcqUGt8ngnmNgzrdGdF1SVz7EO0sg7WnhK5fFVHt6fUxsVEjmEabsCWHKPL1Tw==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@mjackson/node-fetch-server": "^0.7.0",
+        "es-module-lexer": "^1.7.0",
+        "estree-walker": "^3.0.3",
+        "magic-string": "^0.30.17",
+        "periscopic": "^4.0.2",
+        "turbo-stream": "^3.1.0",
+        "vitefu": "^1.1.1"
+      },
+      "peerDependencies": {
+        "react": "*",
+        "react-dom": "*",
+        "vite": "*"
+      }
+    },
+    "node_modules/@vitejs/plugin-rsc/node_modules/@mjackson/node-fetch-server": {
+      "version": "0.7.0",
+      "resolved": "https://registry.npmjs.org/@mjackson/node-fetch-server/-/node-fetch-server-0.7.0.tgz",
+      "integrity": "sha512-un8diyEBKU3BTVj3GzlTPA1kIjCkGdD+AMYQy31Gf9JCkfoZzwgJ79GUtHrF2BN3XPNMLpubbzPcxys+a3uZEw==",
+      "dev": true,
+      "license": "MIT"
+    },
     "node_modules/@vitest/coverage-v8": {
       "version": "3.2.4",
       "resolved": "https://registry.npmjs.org/@vitest/coverage-v8/-/coverage-v8-3.2.4.tgz",
@@ -7740,9 +7823,9 @@
       }
     },
     "node_modules/browserslist": {
-      "version": "4.25.1",
-      "resolved": "https://registry.npmjs.org/browserslist/-/browserslist-4.25.1.tgz",
-      "integrity": "sha512-KGj0KoOMXLpSNkkEI6Z6mShmQy0bc1I+T7K9N81k4WWMrfz+6fQ6es80B/YLAeRoKvjYE1YSHHOW1qe9xIVzHw==",
+      "version": "4.25.2",
+      "resolved": "https://registry.npmjs.org/browserslist/-/browserslist-4.25.2.tgz",
+      "integrity": "sha512-0si2SJK3ooGzIawRu61ZdPCO1IncZwS8IzuX73sPZsXW6EQ/w/DAfPyKI8l1ETTCr2MnvqWitmlCUxgdul45jA==",
       "funding": [
         {
           "type": "opencollective",
@@ -7759,8 +7842,8 @@
       ],
       "license": "MIT",
       "dependencies": {
-        "caniuse-lite": "^1.0.30001726",
-        "electron-to-chromium": "^1.5.173",
+        "caniuse-lite": "^1.0.30001733",
+        "electron-to-chromium": "^1.5.199",
         "node-releases": "^2.0.19",
         "update-browserslist-db": "^1.1.3"
       },
@@ -7867,9 +7950,9 @@
       }
     },
     "node_modules/caniuse-lite": {
-      "version": "1.0.30001731",
-      "resolved": "https://registry.npmjs.org/caniuse-lite/-/caniuse-lite-1.0.30001731.tgz",
-      "integrity": "sha512-lDdp2/wrOmTRWuoB5DpfNkC0rJDU8DqRa6nYL6HK6sytw70QMopt/NIc/9SM7ylItlBWfACXk0tEn37UWM/+mg==",
+      "version": "1.0.30001734",
+      "resolved": "https://registry.npmjs.org/caniuse-lite/-/caniuse-lite-1.0.30001734.tgz",
+      "integrity": "sha512-uhE1Ye5vgqju6OI71HTQqcBCZrvHugk0MjLak7Q+HfoBgoq5Bi+5YnwjP4fjDgrtYr/l8MVRBvzz9dPD4KyK0A==",
       "funding": [
         {
           "type": "opencollective",
@@ -8587,6 +8670,16 @@
         "url": "https://github.com/sponsors/ljharb"
       }
     },
+    "node_modules/date-fns": {
+      "version": "4.1.0",
+      "resolved": "https://registry.npmjs.org/date-fns/-/date-fns-4.1.0.tgz",
+      "integrity": "sha512-Ukq0owbQXxa/U3EGtsdVBkR1w7KOQ5gIBqdH2hkvknzZPYvBxb/aa6E8L7tmjFtkwZBu3UXBbjIgPo/Ez4xaNg==",
+      "license": "MIT",
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/kossnocorp"
+      }
+    },
     "node_modules/debug": {
       "version": "4.4.1",
       "resolved": "https://registry.npmjs.org/debug/-/debug-4.4.1.tgz",
@@ -8841,9 +8934,9 @@
       "license": "MIT"
     },
     "node_modules/electron-to-chromium": {
-      "version": "1.5.197",
-      "resolved": "https://registry.npmjs.org/electron-to-chromium/-/electron-to-chromium-1.5.197.tgz",
-      "integrity": "sha512-m1xWB3g7vJ6asIFz+2pBUbq3uGmfmln1M9SSvBe4QIFWYrRHylP73zL/3nMjDmwz8V+1xAXQDfBd6+HPW0WvDQ==",
+      "version": "1.5.200",
+      "resolved": "https://registry.npmjs.org/electron-to-chromium/-/electron-to-chromium-1.5.200.tgz",
+      "integrity": "sha512-rFCxROw7aOe4uPTfIAx+rXv9cEcGx+buAF4npnhtTqCJk5KDFRnh3+KYj7rdVh6lsFt5/aPs+Irj9rZ33WMA7w==",
       "license": "ISC"
     },
     "node_modules/emoji-regex": {
@@ -10987,9 +11080,9 @@
       }
     },
     "node_modules/i18next": {
-      "version": "25.3.2",
-      "resolved": "https://registry.npmjs.org/i18next/-/i18next-25.3.2.tgz",
-      "integrity": "sha512-JSnbZDxRVbphc5jiptxr3o2zocy5dEqpVm9qCGdJwRNO+9saUJS0/u4LnM/13C23fUEWxAylPqKU/NpMV/IjqA==",
+      "version": "25.3.4",
+      "resolved": "https://registry.npmjs.org/i18next/-/i18next-25.3.4.tgz",
+      "integrity": "sha512-AHklEYFLiRRxW1Cb6zE9lfnEtYvsydRC8nRS3RSKGX3zCqZ8nLZwMaUsrb80YuccPNv2RNokDL8LkTNnp+6mDw==",
       "funding": [
         {
           "type": "individual",
@@ -11517,6 +11610,16 @@
       "dev": true,
       "license": "MIT"
     },
+    "node_modules/is-reference": {
+      "version": "3.0.3",
+      "resolved": "https://registry.npmjs.org/is-reference/-/is-reference-3.0.3.tgz",
+      "integrity": "sha512-ixkJoqQvAP88E6wLydLGGqCJsrFUnqoH6HnaczB8XmDH1oaWU+xxdptvikTgaEhtZ53Ky6YXiBuUI2WXLMCwjw==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@types/estree": "^1.0.6"
+      }
+    },
     "node_modules/is-regex": {
       "version": "1.2.1",
       "resolved": "https://registry.npmjs.org/is-regex/-/is-regex-1.2.1.tgz",
@@ -12222,13 +12325,13 @@
       "license": "MIT"
     },
     "node_modules/lint-staged": {
-      "version": "16.1.4",
-      "resolved": "https://registry.npmjs.org/lint-staged/-/lint-staged-16.1.4.tgz",
-      "integrity": "sha512-xy7rnzQrhTVGKMpv6+bmIA3C0yET31x8OhKBYfvGo0/byeZ6E0BjGARrir3Kg/RhhYHutpsi01+2J5IpfVoueA==",
+      "version": "16.1.5",
+      "resolved": "https://registry.npmjs.org/lint-staged/-/lint-staged-16.1.5.tgz",
+      "integrity": "sha512-uAeQQwByI6dfV7wpt/gVqg+jAPaSp8WwOA8kKC/dv1qw14oGpnpAisY65ibGHUGDUv0rYaZ8CAJZ/1U8hUvC2A==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
-        "chalk": "^5.4.1",
+        "chalk": "^5.5.0",
         "commander": "^14.0.0",
         "debug": "^4.4.1",
         "lilconfig": "^3.1.3",
@@ -12237,7 +12340,7 @@
         "nano-spawn": "^1.0.2",
         "pidtree": "^0.6.0",
         "string-argv": "^0.3.2",
-        "yaml": "^2.8.0"
+        "yaml": "^2.8.1"
       },
       "bin": {
         "lint-staged": "bin/lint-staged.js"
@@ -12625,9 +12728,9 @@
       }
     },
     "node_modules/lucide-react": {
-      "version": "0.536.0",
-      "resolved": "https://registry.npmjs.org/lucide-react/-/lucide-react-0.536.0.tgz",
-      "integrity": "sha512-2PgvNa9v+qz4Jt/ni8vPLt4jwoFybXHuubQT8fv4iCW5TjDxkbZjNZZHa485ad73NSEn/jdsEtU57eE1g+ma8A==",
+      "version": "0.539.0",
+      "resolved": "https://registry.npmjs.org/lucide-react/-/lucide-react-0.539.0.tgz",
+      "integrity": "sha512-VVISr+VF2krO91FeuCrm1rSOLACQUYVy7NQkzrOty52Y8TlTPcXcMdQFj9bYzBgXbWCiywlwSZ3Z8u6a+6bMlg==",
       "license": "ISC",
       "peerDependencies": {
         "react": "^16.5.1 || ^17.0.0 || ^18.0.0 || ^19.0.0"
@@ -14524,6 +14627,18 @@
         "node": ">= 14.16"
       }
     },
+    "node_modules/periscopic": {
+      "version": "4.0.2",
+      "resolved": "https://registry.npmjs.org/periscopic/-/periscopic-4.0.2.tgz",
+      "integrity": "sha512-sqpQDUy8vgB7ycLkendSKS6HnVz1Rneoc3Rc+ZBUCe2pbqlVuCC5vF52l0NJ1aiMg/r1qfYF9/myz8CZeI2rjA==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@types/estree": "*",
+        "is-reference": "^3.0.2",
+        "zimmerframe": "^1.0.0"
+      }
+    },
     "node_modules/picocolors": {
       "version": "1.1.1",
       "resolved": "https://registry.npmjs.org/picocolors/-/picocolors-1.1.1.tgz",
@@ -14648,9 +14763,9 @@
       "license": "MIT"
     },
     "node_modules/posthog-js": {
-      "version": "1.258.6",
-      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.258.6.tgz",
-      "integrity": "sha512-vL5AGG+rOoRg3LGquMfBPO55jD4bGl0CiV44SHdHAoBnOVDDAqxczRGDqMdxor+VLx3/ofTFOJ2FNprfAHp70Q==",
+      "version": "1.259.0",
+      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.259.0.tgz",
+      "integrity": "sha512-6usLnJshky8fQ82ask7PIJh4BSFOU0VkRbFg8Zanm/HIlYMG1VOdRWlToA63JXeO7Bzm9TuREq1wFm5U2VEVCg==",
       "license": "SEE LICENSE IN LICENSE",
       "dependencies": {
         "core-js": "^3.38.1",
@@ -15126,9 +15241,9 @@
       }
     },
     "node_modules/react-router": {
-      "version": "7.7.1",
-      "resolved": "https://registry.npmjs.org/react-router/-/react-router-7.7.1.tgz",
-      "integrity": "sha512-jVKHXoWRIsD/qS6lvGveckwb862EekvapdHJN/cGmzw40KnJH5gg53ujOJ4qX6EKIK9LSBfFed/xiQ5yeXNrUA==",
+      "version": "7.8.0",
+      "resolved": "https://registry.npmjs.org/react-router/-/react-router-7.8.0.tgz",
+      "integrity": "sha512-r15M3+LHKgM4SOapNmsH3smAizWds1vJ0Z9C4mWaKnT9/wD7+d/0jYcj6LmOvonkrO4Rgdyp4KQ/29gWN2i1eg==",
       "license": "MIT",
       "dependencies": {
         "cookie": "^1.0.1",
@@ -17180,6 +17295,13 @@
       "integrity": "sha512-oJFu94HQb+KVduSUQL7wnpmqnfmLsOA/nAh6b6EH0wCEoK0/mPeXU6c3wKDV83MkOuHPRHtSXKKU99IBazS/2w==",
       "license": "0BSD"
     },
+    "node_modules/turbo-stream": {
+      "version": "3.1.0",
+      "resolved": "https://registry.npmjs.org/turbo-stream/-/turbo-stream-3.1.0.tgz",
+      "integrity": "sha512-tVI25WEXl4fckNEmrq70xU1XumxUwEx/FZD5AgEcV8ri7Wvrg2o7GEq8U7htrNx3CajciGm+kDyhRf5JB6t7/A==",
+      "dev": true,
+      "license": "MIT"
+    },
     "node_modules/type-check": {
       "version": "0.4.0",
       "resolved": "https://registry.npmjs.org/type-check/-/type-check-0.4.0.tgz",
@@ -17638,16 +17760,16 @@
       }
     },
     "node_modules/vite": {
-      "version": "7.0.6",
-      "resolved": "https://registry.npmjs.org/vite/-/vite-7.0.6.tgz",
-      "integrity": "sha512-MHFiOENNBd+Bd9uvc8GEsIzdkn1JxMmEeYX35tI3fv0sJBUTfW5tQsoaOwuY4KhBI09A3dUJ/DXf2yxPVPUceg==",
+      "version": "7.1.2",
+      "resolved": "https://registry.npmjs.org/vite/-/vite-7.1.2.tgz",
+      "integrity": "sha512-J0SQBPlQiEXAF7tajiH+rUooJPo0l8KQgyg4/aMunNtrOa7bwuZJsJbDWzeljqQpgftxuq5yNJxQ91O9ts29UQ==",
       "license": "MIT",
       "dependencies": {
         "esbuild": "^0.25.0",
         "fdir": "^6.4.6",
         "picomatch": "^4.0.3",
         "postcss": "^8.5.6",
-        "rollup": "^4.40.0",
+        "rollup": "^4.43.0",
         "tinyglobby": "^0.2.14"
       },
       "bin": {
@@ -17816,6 +17938,26 @@
         "url": "https://github.com/sponsors/jonschlinkert"
       }
     },
+    "node_modules/vitefu": {
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/vitefu/-/vitefu-1.1.1.tgz",
+      "integrity": "sha512-B/Fegf3i8zh0yFbpzZ21amWzHmuNlLlmJT6n7bu5e+pCHUKQIfXSYokrqOBGEMMe9UG2sostKQF9mml/vYaWJQ==",
+      "dev": true,
+      "license": "MIT",
+      "workspaces": [
+        "tests/deps/*",
+        "tests/projects/*",
+        "tests/projects/workspace/packages/*"
+      ],
+      "peerDependencies": {
+        "vite": "^3.0.0 || ^4.0.0 || ^5.0.0 || ^6.0.0 || ^7.0.0-beta.0"
+      },
+      "peerDependenciesMeta": {
+        "vite": {
+          "optional": true
+        }
+      }
+    },
     "node_modules/vitest": {
       "version": "3.2.4",
       "resolved": "https://registry.npmjs.org/vitest/-/vitest-3.2.4.tgz",
@@ -18418,6 +18560,13 @@
         "url": "https://github.com/sponsors/sindresorhus"
       }
     },
+    "node_modules/zimmerframe": {
+      "version": "1.1.2",
+      "resolved": "https://registry.npmjs.org/zimmerframe/-/zimmerframe-1.1.2.tgz",
+      "integrity": "sha512-rAbqEGa8ovJy4pyBxZM70hg4pE6gDgaQ0Sl9M3enG3I0d6H4XSAM3GeNGLKnsBpuijUow064sf7ww1nutC5/3w==",
+      "dev": true,
+      "license": "MIT"
+    },
     "node_modules/zwitch": {
       "version": "2.0.4",
       "resolved": "https://registry.npmjs.org/zwitch/-/zwitch-2.0.4.tgz",

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.51.1",
+  "version": "0.52.1",
   "private": true,
   "type": "module",
   "engines": {
@@ -11,20 +11,22 @@
     "@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": "^7.7.1",
-    "@react-router/serve": "^7.7.1",
+    "@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": "^3.9.0",
     "@stripe/stripe-js": "^7.8.0",
     "@tailwindcss/postcss": "^4.1.11",
     "@tailwindcss/vite": "^4.1.11",
-    "@tanstack/react-query": "^5.84.1",
-    "@vitejs/plugin-react": "^4.7.0",
+    "@tanstack/react-query": "^5.84.2",
+    "@uidotdev/usehooks": "^2.4.1",
+    "@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",
     "eslint-config-airbnb-typescript": "^18.0.0",
     "framer-motion": "^12.23.12",
     "i18next": "^25.3.2",
@@ -32,9 +34,9 @@
     "i18next-http-backend": "^3.0.2",
     "isbot": "^5.1.29",
     "jose": "^6.0.12",
-    "lucide-react": "^0.536.0",
+    "lucide-react": "^0.539.0",
     "monaco-editor": "^0.52.2",
-    "posthog-js": "^1.258.5",
+    "posthog-js": "^1.259.0",
     "react": "^19.1.1",
     "react-dom": "^19.1.1",
     "react-highlight": "^0.15.0",
@@ -43,7 +45,7 @@
     "react-icons": "^5.5.0",
     "react-markdown": "^10.1.0",
     "react-redux": "^9.2.0",
-    "react-router": "^7.7.1",
+    "react-router": "^7.8.0",
     "react-select": "^5.10.2",
     "react-syntax-highlighter": "^15.6.1",
     "react-textarea-autosize": "^8.5.9",
@@ -52,7 +54,7 @@
     "sirv-cli": "^3.0.1",
     "socket.io-client": "^4.8.1",
     "tailwind-merge": "^3.3.1",
-    "vite": "^7.0.6",
+    "vite": "^7.1.1",
     "web-vitals": "^5.1.0",
     "ws": "^8.18.2"
   },
@@ -87,7 +89,7 @@
     "@babel/types": "^7.28.2",
     "@mswjs/socket.io-binding": "^0.2.0",
     "@playwright/test": "^1.54.2",
-    "@react-router/dev": "^7.7.1",
+    "@react-router/dev": "^7.8.0",
     "@tailwindcss/typography": "^0.5.16",
     "@tanstack/eslint-plugin-query": "^5.83.1",
     "@testing-library/dom": "^10.4.1",

frontend/src/api/open-hands.ts

@@ -283,17 +283,27 @@ class OpenHands {
     return data;
   }
 
-  static async getUserConversations(): Promise<Conversation[]> {
+  static async getUserConversations(
+    limit: number = 20,
+    pageId?: string,
+  ): Promise<ResultSet<Conversation>> {
+    const params = new URLSearchParams();
+    params.append("limit", limit.toString());
+
+    if (pageId) {
+      params.append("page_id", pageId);
+    }
+
     const { data } = await openHands.get<ResultSet<Conversation>>(
-      "/api/conversations?limit=100",
+      `/api/conversations?${params.toString()}`,
     );
-    return data.results;
+    return data;
   }
 
   static async searchConversations(
     selectedRepository?: string,
     conversationTrigger?: string,
-    limit: number = 20,
+    limit: number = 100,
   ): Promise<Conversation[]> {
     const params = new URLSearchParams();
     params.append("limit", limit.toString());

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

@@ -53,7 +53,7 @@ export function ChatMessage({
       onMouseEnter={() => setIsHovering(true)}
       onMouseLeave={() => setIsHovering(false)}
       className={cn(
-        "rounded-xl relative w-fit",
+        "rounded-xl relative w-fit max-w-full",
         "flex flex-col gap-2",
         type === "user" && " p-4 bg-tertiary self-end",
         type === "agent" && "mt-6 max-w-full bg-transparent",

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

@@ -83,7 +83,7 @@ const getRecallObservationContent = (event: RecallObservation): string => {
   ) {
     content += `\n\n**Triggered Microagent Knowledge:**`;
     for (const knowledge of event.extras.microagent_knowledge) {
-      content += `\n\n- **${knowledge.name}** (triggered by keyword: ${knowledge.trigger})\n\n\`\`\`\n${knowledge.content}\n\`\`\``;
+      content += `\n\n- **${knowledge.name}** (triggered by keyword: ${knowledge.trigger})\n\n${knowledge.content}`;
     }
   }
 

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

@@ -1,8 +1,10 @@
+import { Lock } from "lucide-react";
 import { useTranslation } from "react-i18next";
 import { ContextMenu } from "./context-menu";
 import { ContextMenuListItem } from "./context-menu-list-item";
 import { useClickOutsideElement } from "#/hooks/use-click-outside-element";
 import { I18nKey } from "#/i18n/declaration";
+import { ContextMenuIconText } from "./context-menu-icon-text";
 
 interface AccountSettingsContextMenuProps {
   onLogout: () => void;
@@ -23,7 +25,10 @@ export function AccountSettingsContextMenu({
       className="absolute right-full md:left-full -top-1 z-10 w-fit"
     >
       <ContextMenuListItem onClick={onLogout} data-testid="logout-button">
-        {t(I18nKey.ACCOUNT_SETTINGS$LOGOUT)}
+        <ContextMenuIconText
+          icon={Lock}
+          text={t(I18nKey.ACCOUNT_SETTINGS$LOGOUT)}
+        />
       </ContextMenuListItem>
     </ContextMenu>
   );

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

@@ -3,7 +3,8 @@ import { NavLink, useParams, useNavigate } from "react-router";
 import { useTranslation } from "react-i18next";
 import { I18nKey } from "#/i18n/declaration";
 import { ConversationCard } from "./conversation-card";
-import { useUserConversations } from "#/hooks/query/use-user-conversations";
+import { usePaginatedConversations } from "#/hooks/query/use-paginated-conversations";
+import { useInfiniteScroll } from "#/hooks/use-infinite-scroll";
 import { useDeleteConversation } from "#/hooks/mutation/use-delete-conversation";
 import { useStopConversation } from "#/hooks/mutation/use-stop-conversation";
 import { ConfirmDeleteModal } from "./confirm-delete-modal";
@@ -40,12 +41,30 @@ export function ConversationPanel({ onClose }: ConversationPanelProps) {
     string | null
   >(null);
 
-  const { data: conversations, isFetching, error } = useUserConversations();
+  const {
+    data,
+    isFetching,
+    error,
+    hasNextPage,
+    isFetchingNextPage,
+    fetchNextPage,
+  } = usePaginatedConversations();
+
+  // Flatten all pages into a single array of conversations
+  const conversations = data?.pages.flatMap((page) => page.results) ?? [];
 
   const { mutate: deleteConversation } = useDeleteConversation();
   const { mutate: stopConversation } = useStopConversation();
   const { mutate: updateConversation } = useUpdateConversation();
 
+  // Set up infinite scroll
+  const scrollContainerRef = useInfiniteScroll({
+    hasNextPage: !!hasNextPage,
+    isFetchingNextPage,
+    fetchNextPage,
+    threshold: 200, // Load more when 200px from bottom
+  });
+
   const handleDeleteProject = (conversationId: string) => {
     setConfirmDeleteModalVisible(true);
     setSelectedConversationId(conversationId);
@@ -102,11 +121,16 @@ export function ConversationPanel({ onClose }: ConversationPanelProps) {
 
   return (
     <div
-      ref={ref}
+      ref={(node) => {
+        // TODO: Combine both refs somehow
+        if (ref.current !== node) ref.current = node;
+        if (scrollContainerRef.current !== node)
+          scrollContainerRef.current = node;
+      }}
       data-testid="conversation-panel"
       className="w-[350px] h-full border border-neutral-700 bg-base-secondary rounded-xl overflow-y-auto absolute"
     >
-      {isFetching && (
+      {isFetching && conversations.length === 0 && (
         <div className="w-full h-full absolute flex justify-center items-center">
           <LoadingSpinner size="small" />
         </div>
@@ -156,6 +180,13 @@ export function ConversationPanel({ onClose }: ConversationPanelProps) {
         </NavLink>
       ))}
 
+      {/* Loading indicator for fetching more conversations */}
+      {isFetchingNextPage && (
+        <div className="flex justify-center py-4">
+          <LoadingSpinner size="small" />
+        </div>
+      )}
+
       {confirmDeleteModalVisible && (
         <ConfirmDeleteModal
           onConfirm={() => {

frontend/src/components/features/home/connect-to-provider-message.tsx

@@ -13,6 +13,7 @@ export function ConnectToProviderMessage() {
       <Link
         data-testid="navigate-to-settings-button"
         to="/settings/integrations"
+        className="self-start"
       >
         <BrandButton type="button" variant="primary" isDisabled={isLoading}>
           {!isLoading && t("SETTINGS$TITLE")}

frontend/src/components/features/maintenance/maintenance-banner.tsx

@@ -1,5 +1,10 @@
 import { useTranslation } from "react-i18next";
+import { useMemo } from "react";
+import { isBefore } from "date-fns";
+import { useLocalStorage } from "@uidotdev/usehooks";
 import { FaTriangleExclamation } from "react-icons/fa6";
+import CloseIcon from "#/icons/close.svg?react";
+import { cn } from "#/utils/utils";
 
 interface MaintenanceBannerProps {
   startTime: string;
@@ -7,6 +12,11 @@ interface MaintenanceBannerProps {
 
 export function MaintenanceBanner({ startTime }: MaintenanceBannerProps) {
   const { t } = useTranslation();
+  const [dismissedAt, setDismissedAt] = useLocalStorage<string | null>(
+    "maintenance_banner_dismissed_at",
+    null,
+  );
+
   // Convert EST timestamp to user's local timezone
   const formatMaintenanceTime = (estTimeString: string): string => {
     try {
@@ -52,8 +62,28 @@ export function MaintenanceBanner({ startTime }: MaintenanceBannerProps) {
 
   const localTime = formatMaintenanceTime(startTime);
 
+  const isBannerVisible = useMemo(() => {
+    const isValid = !Number.isNaN(new Date(startTime).getTime());
+    if (!isValid) {
+      return false;
+    }
+    return !dismissedAt
+      ? true
+      : isBefore(new Date(dismissedAt), new Date(startTime));
+  }, [dismissedAt, startTime]);
+
+  if (!isBannerVisible) {
+    return null;
+  }
+
   return (
-    <div className="bg-primary text-[#0D0F11] p-4 rounded">
+    <div
+      data-testid="maintenance-banner"
+      className={cn(
+        "bg-primary text-[#0D0F11] p-4 rounded",
+        "flex flex-row items-center justify-between",
+      )}
+    >
       <div className="flex items-center">
         <div className="flex-shrink-0">
           <FaTriangleExclamation className="text-white align-middle" />
@@ -64,6 +94,17 @@ export function MaintenanceBanner({ startTime }: MaintenanceBannerProps) {
           </p>
         </div>
       </div>
+
+      <button
+        type="button"
+        data-testid="dismiss-button"
+        onClick={() => setDismissedAt(localTime)}
+        className={cn(
+          "bg-[#0D0F11] rounded-full w-5 h-5 flex items-center justify-center cursor-pointer",
+        )}
+      >
+        <CloseIcon />
+      </button>
     </div>
   );
 }

frontend/src/components/features/settings/git-settings/bitbucket-token-input.tsx

@@ -3,6 +3,7 @@ import { I18nKey } from "#/i18n/declaration";
 import { SettingsInput } from "../settings-input";
 import { BitbucketTokenHelpAnchor } from "./bitbucket-token-help-anchor";
 import { KeyStatusIcon } from "../key-status-icon";
+import { cn } from "#/utils/utils";
 
 interface BitbucketTokenInputProps {
   onChange: (value: string) => void;
@@ -10,6 +11,7 @@ interface BitbucketTokenInputProps {
   isBitbucketTokenSet: boolean;
   name: string;
   bitbucketHostSet: string | null | undefined;
+  className?: string;
 }
 
 export function BitbucketTokenInput({
@@ -18,11 +20,12 @@ export function BitbucketTokenInput({
   isBitbucketTokenSet,
   name,
   bitbucketHostSet,
+  className,
 }: BitbucketTokenInputProps) {
   const { t } = useTranslation();
 
   return (
-    <div className="flex flex-col gap-6">
+    <div className={cn("flex flex-col gap-6", className)}>
       <SettingsInput
         testId={name}
         name={name}

frontend/src/components/features/settings/git-settings/github-token-input.tsx

@@ -3,6 +3,7 @@ import { I18nKey } from "#/i18n/declaration";
 import { SettingsInput } from "../settings-input";
 import { GitHubTokenHelpAnchor } from "./github-token-help-anchor";
 import { KeyStatusIcon } from "../key-status-icon";
+import { cn } from "#/utils/utils";
 
 interface GitHubTokenInputProps {
   onChange: (value: string) => void;
@@ -10,6 +11,7 @@ interface GitHubTokenInputProps {
   isGitHubTokenSet: boolean;
   name: string;
   githubHostSet: string | null | undefined;
+  className?: string;
 }
 
 export function GitHubTokenInput({
@@ -18,11 +20,12 @@ export function GitHubTokenInput({
   isGitHubTokenSet,
   name,
   githubHostSet,
+  className,
 }: GitHubTokenInputProps) {
   const { t } = useTranslation();
 
   return (
-    <div className="flex flex-col gap-6">
+    <div className={cn("flex flex-col gap-6", className)}>
       <SettingsInput
         testId={name}
         name={name}

frontend/src/components/features/settings/git-settings/gitlab-token-input.tsx

@@ -3,6 +3,7 @@ import { I18nKey } from "#/i18n/declaration";
 import { SettingsInput } from "../settings-input";
 import { GitLabTokenHelpAnchor } from "./gitlab-token-help-anchor";
 import { KeyStatusIcon } from "../key-status-icon";
+import { cn } from "#/utils/utils";
 
 interface GitLabTokenInputProps {
   onChange: (value: string) => void;
@@ -10,6 +11,7 @@ interface GitLabTokenInputProps {
   isGitLabTokenSet: boolean;
   name: string;
   gitlabHostSet: string | null | undefined;
+  className?: string;
 }
 
 export function GitLabTokenInput({
@@ -18,11 +20,12 @@ export function GitLabTokenInput({
   isGitLabTokenSet,
   name,
   gitlabHostSet,
+  className,
 }: GitLabTokenInputProps) {
   const { t } = useTranslation();
 
   return (
-    <div className="flex flex-col gap-6">
+    <div className={cn("flex flex-col gap-6", className)}>
       <SettingsInput
         testId={name}
         name={name}

frontend/src/components/features/settings/mcp-settings/mcp-json-editor.tsx

@@ -1,4 +1,4 @@
-import React, { useState } from "react";
+import React, { useState, useRef, useEffect } from "react";
 import { useTranslation, Trans } from "react-i18next";
 import { MCPConfig } from "#/types/settings";
 import { I18nKey } from "#/i18n/declaration";
@@ -11,6 +11,11 @@ interface MCPJsonEditorProps {
   onCancel: () => void;
 }
 
+const MCP_DEFAULT_CONFIG: MCPConfig = {
+  sse_servers: [],
+  stdio_servers: [],
+};
+
 export function MCPJsonEditor({
   mcpConfig,
   onChange,
@@ -20,10 +25,17 @@ export function MCPJsonEditor({
   const [configText, setConfigText] = useState(() =>
     mcpConfig
       ? JSON.stringify(mcpConfig, null, 2)
-      : t(I18nKey.SETTINGS$MCP_DEFAULT_CONFIG),
+      : JSON.stringify(MCP_DEFAULT_CONFIG, null, 2),
   );
+
   const [error, setError] = useState<string | null>(null);
 
+  const textareaRef = useRef<HTMLTextAreaElement>(null);
+
+  useEffect(() => {
+    textareaRef.current?.focus();
+  }, []);
+
   const handleTextChange = (e: React.ChangeEvent<HTMLTextAreaElement>) => {
     setConfigText(e.target.value);
   };
@@ -89,6 +101,7 @@ export function MCPJsonEditor({
         />
       </p>
       <textarea
+        ref={textareaRef}
         className={cn(
           "w-full h-64 resize-y p-2 rounded-sm text-sm font-mono",
           "bg-tertiary border border-[#717888]",
@@ -118,7 +131,7 @@ export function MCPJsonEditor({
           {t(I18nKey.BUTTON$CANCEL)}
         </BrandButton>
         <BrandButton type="button" variant="primary" onClick={handleSave}>
-          {t(I18nKey.SETTINGS$MCP_CONFIRM_CHANGES)}
+          {t(I18nKey.SETTINGS$MCP_PREVIEW_CHANGES)}
         </BrandButton>
       </div>
     </div>

frontend/src/hooks/mutation/use-save-settings.ts

@@ -25,6 +25,7 @@ const saveSettingsMutationFn = async (settings: Partial<PostSettings>) => {
     mcp_config: settings.MCP_CONFIG,
     enable_proactive_conversation_starters:
       settings.ENABLE_PROACTIVE_CONVERSATION_STARTERS,
+    enable_solvability_analysis: settings.ENABLE_SOLVABILITY_ANALYSIS,
     search_api_key: settings.SEARCH_API_KEY?.trim() || "",
     max_budget_per_task: settings.MAX_BUDGET_PER_TASK,
     git_user_name:

frontend/src/hooks/query/use-paginated-conversations.ts

@@ -0,0 +1,16 @@
+import { useInfiniteQuery } from "@tanstack/react-query";
+import OpenHands from "#/api/open-hands";
+import { useIsAuthed } from "./use-is-authed";
+
+export const usePaginatedConversations = (limit: number = 20) => {
+  const { data: userIsAuthenticated } = useIsAuthed();
+
+  return useInfiniteQuery({
+    queryKey: ["user", "conversations", "paginated", limit],
+    queryFn: ({ pageParam }) =>
+      OpenHands.getUserConversations(limit, pageParam),
+    enabled: !!userIsAuthenticated,
+    getNextPageParam: (lastPage) => lastPage.next_page_id,
+    initialPageParam: undefined as string | undefined,
+  });
+};

frontend/src/hooks/query/use-search-conversations.ts

@@ -4,7 +4,7 @@ import OpenHands from "#/api/open-hands";
 export const useSearchConversations = (
   selectedRepository?: string,
   conversationTrigger?: string,
-  limit: number = 20,
+  limit: number = 100,
   cacheDisabled: boolean = false,
 ) =>
   useQuery({

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

@@ -25,6 +25,7 @@ const getSettingsQueryFn = async (): Promise<Settings> => {
     ENABLE_SOUND_NOTIFICATIONS: apiSettings.enable_sound_notifications,
     ENABLE_PROACTIVE_CONVERSATION_STARTERS:
       apiSettings.enable_proactive_conversation_starters,
+    ENABLE_SOLVABILITY_ANALYSIS: apiSettings.enable_solvability_analysis,
     USER_CONSENTS_TO_ANALYTICS: apiSettings.user_consents_to_analytics,
     SEARCH_API_KEY: apiSettings.search_api_key || "",
     MAX_BUDGET_PER_TASK: apiSettings.max_budget_per_task,

frontend/src/hooks/query/use-user-conversations.ts

@@ -1,13 +0,0 @@
-import { useQuery } from "@tanstack/react-query";
-import OpenHands from "#/api/open-hands";
-import { useIsAuthed } from "./use-is-authed";
-
-export const useUserConversations = () => {
-  const { data: userIsAuthenticated } = useIsAuthed();
-
-  return useQuery({
-    queryKey: ["user", "conversations"],
-    queryFn: OpenHands.getUserConversations,
-    enabled: !!userIsAuthenticated,
-  });
-};

frontend/src/hooks/use-document-title-from-state.ts

@@ -22,5 +22,5 @@ export function useDocumentTitleFromState(suffix = "OpenHands") {
     return () => {
       document.title = suffix;
     };
-  }, [conversation, suffix]);
+  }, [conversation?.title, suffix]);
 }

frontend/src/hooks/use-infinite-scroll.ts

@@ -0,0 +1,42 @@
+import { useEffect, useRef, useCallback } from "react";
+
+interface UseInfiniteScrollOptions {
+  hasNextPage: boolean;
+  isFetchingNextPage: boolean;
+  fetchNextPage: () => void;
+  threshold?: number;
+}
+
+export const useInfiniteScroll = ({
+  hasNextPage,
+  isFetchingNextPage,
+  fetchNextPage,
+  threshold = 100,
+}: UseInfiniteScrollOptions) => {
+  const containerRef = useRef<HTMLDivElement>(null);
+
+  const handleScroll = useCallback(() => {
+    if (!containerRef.current || isFetchingNextPage || !hasNextPage) {
+      return;
+    }
+
+    const { scrollTop, scrollHeight, clientHeight } = containerRef.current;
+    const isNearBottom = scrollTop + clientHeight >= scrollHeight - threshold;
+
+    if (isNearBottom) {
+      fetchNextPage();
+    }
+  }, [hasNextPage, isFetchingNextPage, fetchNextPage, threshold]);
+
+  useEffect(() => {
+    const container = containerRef.current;
+    if (!container) return undefined;
+
+    container.addEventListener("scroll", handleScroll);
+    return () => {
+      container.removeEventListener("scroll", handleScroll);
+    };
+  }, [handleScroll]);
+
+  return containerRef;
+};

frontend/src/i18n/declaration.ts

@@ -51,7 +51,7 @@ export enum I18nKey {
   SETTINGS$NAV_MCP = "SETTINGS$NAV_MCP",
   SETTINGS$MCP_CONFIGURATION = "SETTINGS$MCP_CONFIGURATION",
   SETTINGS$MCP_EDIT_CONFIGURATION = "SETTINGS$MCP_EDIT_CONFIGURATION",
-  SETTINGS$MCP_CONFIRM_CHANGES = "SETTINGS$MCP_CONFIRM_CHANGES",
+  SETTINGS$MCP_PREVIEW_CHANGES = "SETTINGS$MCP_PREVIEW_CHANGES",
   SETTINGS$MCP_CONFIG_DESCRIPTION = "SETTINGS$MCP_CONFIG_DESCRIPTION",
   SETTINGS$MCP_CONFIG_ERROR = "SETTINGS$MCP_CONFIG_ERROR",
   SETTINGS$MCP_CONFIG_EXAMPLE = "SETTINGS$MCP_CONFIG_EXAMPLE",
@@ -71,7 +71,6 @@ export enum I18nKey {
   SETTINGS$MCP_ERROR_SSE_URL = "SETTINGS$MCP_ERROR_SSE_URL",
   SETTINGS$MCP_ERROR_STDIO_PROPS = "SETTINGS$MCP_ERROR_STDIO_PROPS",
   SETTINGS$MCP_ERROR_INVALID_JSON = "SETTINGS$MCP_ERROR_INVALID_JSON",
-  SETTINGS$MCP_DEFAULT_CONFIG = "SETTINGS$MCP_DEFAULT_CONFIG",
   HOME$CONNECT_PROVIDER_MESSAGE = "HOME$CONNECT_PROVIDER_MESSAGE",
   HOME$LETS_START_BUILDING = "HOME$LETS_START_BUILDING",
   HOME$OPENHANDS_DESCRIPTION = "HOME$OPENHANDS_DESCRIPTION",
@@ -147,10 +146,12 @@ export enum I18nKey {
   SUGGESTIONS$CLEAN_DEPENDENCIES = "SUGGESTIONS$CLEAN_DEPENDENCIES",
   SETTINGS$LLM_SETTINGS = "SETTINGS$LLM_SETTINGS",
   SETTINGS$GIT_SETTINGS = "SETTINGS$GIT_SETTINGS",
+  SETTINGS$GIT_SETTINGS_DESCRIPTION = "SETTINGS$GIT_SETTINGS_DESCRIPTION",
   SETTINGS$SOUND_NOTIFICATIONS = "SETTINGS$SOUND_NOTIFICATIONS",
   SETTINGS$MAX_BUDGET_PER_TASK = "SETTINGS$MAX_BUDGET_PER_TASK",
   SETTINGS$MAX_BUDGET_PER_CONVERSATION = "SETTINGS$MAX_BUDGET_PER_CONVERSATION",
   SETTINGS$PROACTIVE_CONVERSATION_STARTERS = "SETTINGS$PROACTIVE_CONVERSATION_STARTERS",
+  SETTINGS$SOLVABILITY_ANALYSIS = "SETTINGS$SOLVABILITY_ANALYSIS",
   SETTINGS$SEARCH_API_KEY = "SETTINGS$SEARCH_API_KEY",
   SETTINGS$SEARCH_API_KEY_OPTIONAL = "SETTINGS$SEARCH_API_KEY_OPTIONAL",
   SETTINGS$SEARCH_API_KEY_INSTRUCTIONS = "SETTINGS$SEARCH_API_KEY_INSTRUCTIONS",

frontend/src/i18n/translation.json

@@ -815,21 +815,21 @@
         "de": "Konfiguration bearbeiten",
         "uk": "Редагувати налаштування"
     },
-    "SETTINGS$MCP_CONFIRM_CHANGES": {
-        "en": "Confirm Changes",
-        "ja": "変更を確定",
-        "zh-CN": "确认更改",
-        "zh-TW": "確認變更",
-        "ko-KR": "변경 사항 확인",
-        "no": "Bekreft endringer",
-        "it": "Conferma modifiche",
-        "pt": "Confirmar alterações",
-        "es": "Confirmar cambios",
-        "ar": "تأكيد التغييرات",
-        "fr": "Confirmer les modifications",
-        "tr": "Değişiklikleri Onayla",
-        "de": "Änderungen bestätigen",
-        "uk": "Підтвердити зміни"
+    "SETTINGS$MCP_PREVIEW_CHANGES": {
+        "en": "Preview Changes",
+        "ja": "変更内容をプレビュー",
+        "zh-CN": "预览更改",
+        "zh-TW": "預覽變更",
+        "ko-KR": "변경 사항 미리보기",
+        "no": "Forhåndsvis endringer",
+        "it": "Anteprima modifiche",
+        "pt": "Visualizar alterações",
+        "es": "Vista previa de los cambios",
+        "ar": "معاينة التغييرات",
+        "fr": "Aperçu des modifications",
+        "tr": "Değişiklikleri Önizle",
+        "de": "Änderungen anzeigen",
+        "uk": "Переглянути зміни"
     },
     "SETTINGS$MCP_CONFIG_DESCRIPTION": {
     "en": "Edit the JSON configuration for MCP servers below. The configuration must include both sse_servers and stdio_servers arrays. For full configuration details and integration examples, see the <a>documentation</a>.",
@@ -1135,22 +1135,6 @@
         "de": "Ungültiges JSON",
         "uk": "Невірний JSON"
     },
-    "SETTINGS$MCP_DEFAULT_CONFIG": {
-        "en": "{\n  \"sse_servers\": [],\n  \"stdio_servers\": []\n}",
-        "ja": "{\n  \"sse_servers\": [],\n  \"stdio_servers\": []\n}",
-        "zh-CN": "{\n  \"sse_servers\": [],\n  \"stdio_servers\": []\n}",
-        "zh-TW": "{\n  \"sse_servers\": [],\n  \"stdio_servers\": []\n}",
-        "ko-KR": "{\n  \"sse_servers\": [],\n  \"stdio_servers\": []\n}",
-        "no": "{\n  \"sse_servers\": [],\n  \"stdio_servers\": []\n}",
-        "it": "{\n  \"sse_servers\": [],\n  \"stdio_servers\": []\n}",
-        "pt": "{\n  \"sse_servers\": [],\n  \"stdio_servers\": []\n}",
-        "es": "{\n  \"sse_servers\": [],\n  \"stdio_servers\": []\n}",
-        "ar": "{\n  \"sse_servers\": [],\n  \"stdio_servers\": []\n}",
-        "fr": "{\n  \"sse_servers\": [],\n  \"stdio_servers\": []\n}",
-        "tr": "{\n  \"sse_servers\": [],\n  \"stdio_servers\": []\n}",
-        "de": "{\n  \"sse_servers\": [],\n  \"stdio_servers\": []\n}",
-        "uk": "{\n  \"sse_servers\": [],\n  \"stdio_servers\": []\n}"
-    },
     "HOME$CONNECT_PROVIDER_MESSAGE": {
         "en": "To get started with suggested tasks, please connect your GitHub, GitLab, or Bitbucket account.",
         "ja": "提案されたタスクを始めるには、GitHub、GitLab、またはBitbucketアカウントを接続してください。",
@@ -2351,6 +2335,22 @@
         "tr": "Git Ayarları",
         "uk": "Git налаштування"
     },
+    "SETTINGS$GIT_SETTINGS_DESCRIPTION": {
+        "en": "Configure the username and email that OpenHands uses to commit changes.",
+        "ja": "OpenHandsがコミットに使用するユーザー名とメールを設定します。",
+        "zh-CN": "配置OpenHands用于提交更改的用户名和电子邮件。",
+        "zh-TW": "配置OpenHands用於提交更改的用戶名和電子郵件。",
+        "ko-KR": "OpenHands가 변경 사항을 커밋할 때 사용하는 사용자 이름과 이메일을 구성합니다.",
+        "de": "Konfigurieren Sie den Benutzernamen und die E-Mail, die OpenHands zum Committen von Änderungen verwendet.",
+        "no": "Konfigurer brukernavnet og e-posten som OpenHands bruker for å committe endringer.",
+        "it": "Configura il nome utente e l'email che OpenHands utilizza per committare le modifiche.",
+        "pt": "Configure o nome de usuário e o email que o OpenHands usa para fazer commits de alterações.",
+        "es": "Configure el nombre de usuario y el correo electrónico que OpenHands utiliza para confirmar cambios.",
+        "ar": "قم بتكوين اسم المستخدم والبريد الإلكتروني الذي يستخدمه OpenHands لارتكاب التغييرات.",
+        "fr": "Configurez le nom d'utilisateur et l'email qu'OpenHands utilise pour valider les modifications.",
+        "tr": "OpenHands'ın değişiklikleri commit etmek için kullandığı kullanıcı adını ve e-postayı yapılandırın.",
+        "uk": "Налаштуйте ім'я користувача та електронну пошту, які OpenHands використовує для фіксації змін."
+    },
     "SETTINGS$SOUND_NOTIFICATIONS": {
         "en": "Sound Notifications",
         "ja": "サウンド通知",
@@ -2415,6 +2415,22 @@
         "tr": "GitHub'da Görevler Öner",
         "uk": "Запропонувати завдання на GitHub"
     },
+    "SETTINGS$SOLVABILITY_ANALYSIS": {
+        "en": "Enable Solvability Analysis",
+        "ja": "解決可能性分析を有効にする",
+        "zh-CN": "启用可解决性分析",
+        "zh-TW": "啟用可解決性分析",
+        "ko-KR": "해결 가능성 분석 활성화",
+        "de": "Lösbarkeitsanalyse aktivieren",
+        "no": "Aktiver løsningsanalyse",
+        "it": "Abilita analisi di risolvibilità",
+        "pt": "Ativar análise de solucionabilidade",
+        "es": "Habilitar análisis de solvencia",
+        "ar": "تمكين تحليل القابلية للحل",
+        "fr": "Activer l'analyse de solvabilité",
+        "tr": "Çözünürlük Analizini Etkinleştir",
+        "uk": "Увімкнути аналіз розв'язності"
+    },
     "SETTINGS$SEARCH_API_KEY": {
         "en": "Search API Key (Tavily)",
         "ja": "検索APIキー (Tavily)",

frontend/src/mocks/handlers.ts

@@ -30,6 +30,7 @@ export const MOCK_DEFAULT_USER_SETTINGS: ApiSettings | PostApiSettings = {
   enable_sound_notifications: DEFAULT_SETTINGS.ENABLE_SOUND_NOTIFICATIONS,
   enable_proactive_conversation_starters:
     DEFAULT_SETTINGS.ENABLE_PROACTIVE_CONVERSATION_STARTERS,
+  enable_solvability_analysis: DEFAULT_SETTINGS.ENABLE_SOLVABILITY_ANALYSIS,
   user_consents_to_analytics: DEFAULT_SETTINGS.USER_CONSENTS_TO_ANALYTICS,
   max_budget_per_task: DEFAULT_SETTINGS.MAX_BUDGET_PER_TASK,
 };

frontend/src/routes/app-settings.tsx

@@ -38,6 +38,10 @@ function AppSettingsScreen() {
     proactiveConversationsSwitchHasChanged,
     setProactiveConversationsSwitchHasChanged,
   ] = React.useState(false);
+  const [
+    solvabilityAnalysisSwitchHasChanged,
+    setSolvabilityAnalysisSwitchHasChanged,
+  ] = React.useState(false);
   const [maxBudgetPerTaskHasChanged, setMaxBudgetPerTaskHasChanged] =
     React.useState(false);
   const [gitUserNameHasChanged, setGitUserNameHasChanged] =
@@ -61,6 +65,9 @@ function AppSettingsScreen() {
       formData.get("enable-proactive-conversations-switch")?.toString() ===
       "on";
 
+    const enableSolvabilityAnalysis =
+      formData.get("enable-solvability-analysis-switch")?.toString() === "on";
+
     const maxBudgetPerTaskValue = formData
       .get("max-budget-per-task-input")
       ?.toString();
@@ -79,6 +86,7 @@ function AppSettingsScreen() {
         user_consents_to_analytics: enableAnalytics,
         ENABLE_SOUND_NOTIFICATIONS: enableSoundNotifications,
         ENABLE_PROACTIVE_CONVERSATION_STARTERS: enableProactiveConversations,
+        ENABLE_SOLVABILITY_ANALYSIS: enableSolvabilityAnalysis,
         MAX_BUDGET_PER_TASK: maxBudgetPerTask,
         GIT_USER_NAME: gitUserName,
         GIT_USER_EMAIL: gitUserEmail,
@@ -136,6 +144,13 @@ function AppSettingsScreen() {
     );
   };
 
+  const checkIfSolvabilityAnalysisSwitchHasChanged = (checked: boolean) => {
+    const currentSolvabilityAnalysis = !!settings?.ENABLE_SOLVABILITY_ANALYSIS;
+    setSolvabilityAnalysisSwitchHasChanged(
+      checked !== currentSolvabilityAnalysis,
+    );
+  };
+
   const checkIfMaxBudgetPerTaskHasChanged = (value: string) => {
     const newValue = parseMaxBudgetPerTask(value);
     const currentValue = settings?.MAX_BUDGET_PER_TASK;
@@ -157,6 +172,7 @@ function AppSettingsScreen() {
     !analyticsSwitchHasChanged &&
     !soundNotificationsSwitchHasChanged &&
     !proactiveConversationsSwitchHasChanged &&
+    !solvabilityAnalysisSwitchHasChanged &&
     !maxBudgetPerTaskHasChanged &&
     !gitUserNameHasChanged &&
     !gitUserEmailHasChanged;
@@ -209,6 +225,17 @@ function AppSettingsScreen() {
             </SettingsSwitch>
           )}
 
+          {config?.APP_MODE === "saas" && (
+            <SettingsSwitch
+              testId="enable-solvability-analysis-switch"
+              name="enable-solvability-analysis-switch"
+              defaultIsToggled={!!settings.ENABLE_SOLVABILITY_ANALYSIS}
+              onToggle={checkIfSolvabilityAnalysisSwitchHasChanged}
+            >
+              {t(I18nKey.SETTINGS$SOLVABILITY_ANALYSIS)}
+            </SettingsSwitch>
+          )}
+
           <SettingsInput
             testId="max-budget-per-task-input"
             name="max-budget-per-task-input"
@@ -223,9 +250,12 @@ function AppSettingsScreen() {
           />
 
           <div className="border-t border-t-tertiary pt-6 mt-2">
-            <h3 className="text-lg font-medium mb-4">
+            <h3 className="text-lg font-medium mb-2">
               {t(I18nKey.SETTINGS$GIT_SETTINGS)}
             </h3>
+            <p className="text-xs mb-4">
+              {t(I18nKey.SETTINGS$GIT_SETTINGS_DESCRIPTION)}
+            </p>
             <div className="flex flex-col gap-6">
               <SettingsInput
                 testId="git-user-name-input"

frontend/src/routes/git-settings.tsx

@@ -154,47 +154,49 @@ function GitSettingsScreen() {
             </div>
           )}
 
-          {!isSaas && (
-            <GitHubTokenInput
-              name="github-token-input"
-              isGitHubTokenSet={isGitHubTokenSet}
-              onChange={(value) => {
-                setGithubTokenInputHasValue(!!value);
-              }}
-              onGitHubHostChange={(value) => {
-                setGithubHostInputHasValue(!!value);
-              }}
-              githubHostSet={existingGithubHost}
-            />
-          )}
+          <div className="flex flex-col gap-4">
+            {!isSaas && (
+              <GitHubTokenInput
+                name="github-token-input"
+                isGitHubTokenSet={isGitHubTokenSet}
+                onChange={(value) => {
+                  setGithubTokenInputHasValue(!!value);
+                }}
+                onGitHubHostChange={(value) => {
+                  setGithubHostInputHasValue(!!value);
+                }}
+                githubHostSet={existingGithubHost}
+              />
+            )}
 
-          {!isSaas && (
-            <GitLabTokenInput
-              name="gitlab-token-input"
-              isGitLabTokenSet={isGitLabTokenSet}
-              onChange={(value) => {
-                setGitlabTokenInputHasValue(!!value);
-              }}
-              onGitLabHostChange={(value) => {
-                setGitlabHostInputHasValue(!!value);
-              }}
-              gitlabHostSet={existingGitlabHost}
-            />
-          )}
+            {!isSaas && (
+              <GitLabTokenInput
+                name="gitlab-token-input"
+                isGitLabTokenSet={isGitLabTokenSet}
+                onChange={(value) => {
+                  setGitlabTokenInputHasValue(!!value);
+                }}
+                onGitLabHostChange={(value) => {
+                  setGitlabHostInputHasValue(!!value);
+                }}
+                gitlabHostSet={existingGitlabHost}
+              />
+            )}
 
-          {!isSaas && (
-            <BitbucketTokenInput
-              name="bitbucket-token-input"
-              isBitbucketTokenSet={isBitbucketTokenSet}
-              onChange={(value) => {
-                setBitbucketTokenInputHasValue(!!value);
-              }}
-              onBitbucketHostChange={(value) => {
-                setBitbucketHostInputHasValue(!!value);
-              }}
-              bitbucketHostSet={existingBitbucketHost}
-            />
-          )}
+            {!isSaas && (
+              <BitbucketTokenInput
+                name="bitbucket-token-input"
+                isBitbucketTokenSet={isBitbucketTokenSet}
+                onChange={(value) => {
+                  setBitbucketTokenInputHasValue(!!value);
+                }}
+                onBitbucketHostChange={(value) => {
+                  setBitbucketHostInputHasValue(!!value);
+                }}
+                bitbucketHostSet={existingBitbucketHost}
+              />
+            )}
+          </div>
         </div>
       )}
 

frontend/src/routes/mcp-settings.tsx

@@ -1,4 +1,4 @@
-import React, { useState } from "react";
+import React, { useState, useEffect } from "react";
 import { useTranslation } from "react-i18next";
 import posthog from "posthog-js";
 import { useSettings } from "#/hooks/query/use-settings";
@@ -18,11 +18,15 @@ function MCPSettingsScreen() {
   const { data: settings, isLoading } = useSettings();
   const { mutate: saveSettings, isPending } = useSaveSettings();
 
-  const [mcpConfig, setMcpConfig] = useState<MCPConfig | undefined>(
-    settings?.MCP_CONFIG,
-  );
+  const [mcpConfig, setMcpConfig] = useState<MCPConfig | undefined>(undefined);
   const [isDirty, setIsDirty] = useState(false);
 
+  useEffect(() => {
+    if (!mcpConfig && settings?.MCP_CONFIG) {
+      setMcpConfig(settings.MCP_CONFIG);
+    }
+  }, [settings, mcpConfig]);
+
   const handleConfigChange = (config: MCPConfig) => {
     setMcpConfig(config);
     setIsDirty(true);

frontend/src/routes/root-layout.tsx

@@ -203,16 +203,17 @@ export default function MainApp() {
     >
       <Sidebar />
 
-      <div
-        id="root-outlet"
-        className="h-[calc(100%-50px)] md:h-full w-full relative overflow-auto"
-      >
+      <div className="flex flex-col w-full h-[calc(100%-50px)] md:h-full gap-3">
         {config.data?.MAINTENANCE && (
-          <MaintenanceBanner startTime={config.data.MAINTENANCE.startTime} />
+          <div className="flex-shrink-0">
+            <MaintenanceBanner startTime={config.data.MAINTENANCE.startTime} />
+          </div>
         )}
-        <EmailVerificationGuard>
-          <Outlet />
-        </EmailVerificationGuard>
+        <div id="root-outlet" className="flex-1 relative overflow-auto">
+          <EmailVerificationGuard>
+            <Outlet />
+          </EmailVerificationGuard>
+        </div>
       </div>
 
       {renderAuthModal && (

frontend/src/routes/secrets-settings.tsx

@@ -89,6 +89,7 @@ function SecretsSettingsScreen() {
           to="/settings/integrations"
           data-testid="connect-git-button"
           type="button"
+          className="self-start"
         >
           <BrandButton type="button" variant="secondary">
             {t(I18nKey.SECRETS$CONNECT_GIT_PROVIDER)}

frontend/src/services/settings.ts

@@ -17,6 +17,7 @@ export const DEFAULT_SETTINGS: Settings = {
   ENABLE_SOUND_NOTIFICATIONS: false,
   USER_CONSENTS_TO_ANALYTICS: false,
   ENABLE_PROACTIVE_CONVERSATION_STARTERS: false,
+  ENABLE_SOLVABILITY_ANALYSIS: false,
   SEARCH_API_KEY: "",
   IS_NEW_USER: true,
   MAX_BUDGET_PER_TASK: null,

frontend/src/types/settings.ts

@@ -43,6 +43,7 @@ export type Settings = {
   ENABLE_DEFAULT_CONDENSER: boolean;
   ENABLE_SOUND_NOTIFICATIONS: boolean;
   ENABLE_PROACTIVE_CONVERSATION_STARTERS: boolean;
+  ENABLE_SOLVABILITY_ANALYSIS: boolean;
   USER_CONSENTS_TO_ANALYTICS: boolean | null;
   SEARCH_API_KEY?: string;
   IS_NEW_USER?: boolean;
@@ -68,6 +69,7 @@ export type ApiSettings = {
   enable_default_condenser: boolean;
   enable_sound_notifications: boolean;
   enable_proactive_conversation_starters: boolean;
+  enable_solvability_analysis: boolean;
   user_consents_to_analytics: boolean | null;
   search_api_key?: string;
   provider_tokens_set: Partial<Record<Provider, string | null>>;

frontend/src/utils/status.ts

@@ -47,7 +47,8 @@ export function getIndicatorColor(
     webSocketStatus === "DISCONNECTED" ||
     conversationStatus === "STOPPED" ||
     runtimeStatus === "STATUS$STOPPED" ||
-    agentState === AgentState.STOPPED
+    agentState === AgentState.STOPPED ||
+    agentState === AgentState.ERROR
   ) {
     return IndicatorColor.RED;
   }

openhands/agenthub/codeact_agent/codeact_agent.py

@@ -106,10 +106,15 @@ class CodeActAgent(Agent):
     def _get_tools(self) -> list['ChatCompletionToolParam']:
         # For these models, we use short tool descriptions ( < 1024 tokens)
         # to avoid hitting the OpenAI token limit for tool descriptions.
-        SHORT_TOOL_DESCRIPTION_LLM_SUBSTRS = ['gpt-', 'o3', 'o1', 'o4']
+        SHORT_TOOL_DESCRIPTION_LLM_SUBSTRS = ['gpt-4', 'o3', 'o1', 'o4']
 
         use_short_tool_desc = False
         if self.llm is not None:
+            # For historical reasons, previously OpenAI enforces max function description length of 1k characters
+            # https://community.openai.com/t/function-call-description-max-length/529902
+            # But it no longer seems to be an issue recently
+            # https://community.openai.com/t/was-the-character-limit-for-schema-descriptions-upgraded/1225975
+            # Tested on GPT-5 and longer description still works. But we still keep the logic to be safe for older models.
             use_short_tool_desc = any(
                 model_substr in self.llm.config.model
                 for model_substr in SHORT_TOOL_DESCRIPTION_LLM_SUBSTRS

openhands/agenthub/codeact_agent/prompts/system_prompt.j2

@@ -66,6 +66,11 @@ Your primary role is to assist users by executing commands, modifying code, and
 * Use APIs to work with GitHub or other platforms, unless the user asks otherwise or your task requires browsing.
 </SECURITY>
 
+<EXTERNAL_SERVICES>
+* When interacting with external services like GitHub, GitLab, or Bitbucket, use their respective APIs instead of browser-based interactions whenever possible.
+* Only resort to browser-based interactions with these services if specifically requested by the user or if the required operation cannot be performed via API.
+</EXTERNAL_SERVICES>
+
 <ENVIRONMENT_SETUP>
 * When user asks you to run an application, don't stop if the application is not installed. Instead, please install the application and run the command again.
 * If you encounter missing dependencies:

openhands/agenthub/codeact_agent/prompts/system_prompt_interactive.j2

@@ -1,79 +1,4 @@
-You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.
-
-<ROLE>
-Your primary role is to assist users by executing commands, modifying code, and solving technical problems effectively. You should be thorough, methodical, and prioritize quality over speed.
-* If the user asks a question, like "why is X happening", don't try to fix the problem. Just give an answer to the question.
-</ROLE>
-
-<EFFICIENCY>
-* Each action you take is somewhat expensive. Wherever possible, combine multiple actions into a single action, e.g. combine multiple bash commands into one, using sed and grep to edit/view multiple files at once.
-* When exploring the codebase, use efficient tools like find, grep, and git commands with appropriate filters to minimize unnecessary operations.
-</EFFICIENCY>
-
-<FILE_SYSTEM_GUIDELINES>
-* When a user provides a file path, do NOT assume it's relative to the current working directory. First explore the file system to locate the file before working on it.
-* If asked to edit a file, edit the file directly, rather than creating a new file with a different filename.
-* For global search-and-replace operations, consider using `sed` instead of opening file editors multiple times.
-</FILE_SYSTEM_GUIDELINES>
-
-<CODE_QUALITY>
-* Write clean, efficient code with minimal comments. Avoid redundancy in comments: Do not repeat information that can be easily inferred from the code itself.
-* When implementing solutions, focus on making the minimal changes needed to solve the problem.
-* Before implementing any changes, first thoroughly understand the codebase through exploration.
-* If you are adding a lot of code to a function or file, consider splitting the function or file into smaller pieces when appropriate.
-* Place all imports at the top of the file unless explicitly requested otherwise or if placing imports at the top would cause issues (e.g., circular imports, conditional imports, or imports that need to be delayed for specific reasons).
-</CODE_QUALITY>
-
-<VERSION_CONTROL>
-* If there are existing git user credentials already configured, use them and add Co-authored-by: openhands <openhands@all-hands.dev> to any commits messages you make. if a git config doesn't exist use "openhands" as the user.name and "openhands@all-hands.dev" as the user.email by default, unless explicitly instructed otherwise.
-* Exercise caution with git operations. Do NOT make potentially dangerous changes (e.g., pushing to main, deleting repositories) unless explicitly asked to do so.
-* When committing changes, use `git status` to see all modified files, and stage all files necessary for the commit. Use `git commit -a` whenever possible.
-* Do NOT commit files that typically shouldn't go into version control (e.g., node_modules/, .env files, build directories, cache files, large binaries) unless explicitly instructed by the user.
-* If unsure about committing certain files, check for the presence of .gitignore files or ask the user for clarification.
-</VERSION_CONTROL>
-
-<PULL_REQUESTS>
-* **Important**: Do not push to the remote branch and/or start a pull request unless explicitly asked to do so.
-* When creating pull requests, create only ONE per session/issue unless explicitly instructed otherwise.
-* When working with an existing PR, update it with new commits rather than creating additional PRs for the same issue.
-* When updating a PR, preserve the original PR title and purpose, updating description only when necessary.
-</PULL_REQUESTS>
-
-<PROBLEM_SOLVING_WORKFLOW>
-1. EXPLORATION: Thoroughly explore relevant files and understand the context before proposing solutions
-2. ANALYSIS: Consider multiple approaches and select the most promising one
-3. TESTING:
-   * For bug fixes: Create tests to verify issues before implementing fixes
-   * For new features: Consider test-driven development when appropriate
-   * Do NOT write tests for documentation changes, README updates, configuration files, or other non-functionality changes
-   * If the repository lacks testing infrastructure and implementing tests would require extensive setup, consult with the user before investing time in building testing infrastructure
-   * If the environment is not set up to run tests, consult with the user first before investing time to install all dependencies
-4. IMPLEMENTATION: Make focused, minimal changes to address the problem
-5. VERIFICATION: If the environment is set up to run tests, test your implementation thoroughly, including edge cases. If the environment is not set up to run tests, consult with the user first before investing time to run tests.
-</PROBLEM_SOLVING_WORKFLOW>
-
-<SECURITY>
-* Only use GITHUB_TOKEN and other credentials in ways the user has explicitly requested and would expect.
-* Use APIs to work with GitHub or other platforms, unless the user asks otherwise or your task requires browsing.
-</SECURITY>
-
-<ENVIRONMENT_SETUP>
-* When user asks you to run an application, don't stop if the application is not installed. Instead, please install the application and run the command again.
-* If you encounter missing dependencies:
-  1. First, look around in the repository for existing dependency files (requirements.txt, pyproject.toml, package.json, Gemfile, etc.)
-  2. If dependency files exist, use them to install all dependencies at once (e.g., `pip install -r requirements.txt`, `npm install`, etc.)
-  3. Only install individual packages directly if no dependency files are found or if only specific packages are needed
-* Similarly, if you encounter missing dependencies for essential tools requested by the user, install them when possible.
-</ENVIRONMENT_SETUP>
-
-<TROUBLESHOOTING>
-* If you've made repeated attempts to solve a problem but tests still fail or the user reports it's still broken:
-  1. Step back and reflect on 5-7 different possible sources of the problem
-  2. Assess the likelihood of each possible cause
-  3. Methodically address the most likely causes, starting with the highest probability
-  4. Document your reasoning process
-* When you run into any major issue while executing a plan from the user, please don't try to directly work around it. Instead, propose a new plan and confirm with the user before proceeding.
-</TROUBLESHOOTING>
+{% include "system_prompt.j2" %}
 
 <INTERACTION_RULES>
 * When the user instructions are high-level or vague, explore the codebase before implementing solutions or interacting with users to figure out the best approach.

openhands/agenthub/codeact_agent/prompts/system_prompt_long_horizon.j2

@@ -1,55 +1,4 @@
-You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.
-
-<ROLE>
-Your primary role is to assist users by executing commands, modifying code, and solving technical problems effectively. You should be thorough, methodical, and prioritize quality over speed.
-* If the user asks a question, like "why is X happening", don't try to fix the problem. Just give an answer to the question.
-</ROLE>
-
-<EFFICIENCY>
-* Each action you take is somewhat expensive. Wherever possible, combine multiple actions into a single action, e.g. combine multiple bash commands into one, using sed and grep to edit/view multiple files at once.
-* When exploring the codebase, use efficient tools like find, grep, and git commands with appropriate filters to minimize unnecessary operations.
-</EFFICIENCY>
-
-<FILE_SYSTEM_GUIDELINES>
-* When a user provides a file path, do NOT assume it's relative to the current working directory. First explore the file system to locate the file before working on it.
-* If asked to edit a file, edit the file directly, rather than creating a new file with a different filename.
-* For global search-and-replace operations, consider using `sed` instead of opening file editors multiple times.
-</FILE_SYSTEM_GUIDELINES>
-
-<CODE_QUALITY>
-* Write clean, efficient code with minimal comments. Avoid redundancy in comments: Do not repeat information that can be easily inferred from the code itself.
-* When implementing solutions, focus on making the minimal changes needed to solve the problem.
-* Before implementing any changes, first thoroughly understand the codebase through exploration.
-* If you are adding a lot of code to a function or file, consider splitting the function or file into smaller pieces when appropriate.
-* Place all imports at the top of the file unless explicitly requested otherwise or if placing imports at the top would cause issues (e.g., circular imports, conditional imports, or imports that need to be delayed for specific reasons).
-</CODE_QUALITY>
-
-<VERSION_CONTROL>
-* If there are existing git user credentials already configured, use them and add Co-authored-by: openhands <openhands@all-hands.dev> to any commits messages you make. if a git config doesn't exist use "openhands" as the user.name and "openhands@all-hands.dev" as the user.email by default, unless explicitly instructed otherwise.
-* Exercise caution with git operations. Do NOT make potentially dangerous changes (e.g., pushing to main, deleting repositories) unless explicitly asked to do so.
-* When committing changes, use `git status` to see all modified files, and stage all files necessary for the commit. Use `git commit -a` whenever possible.
-* Do NOT commit files that typically shouldn't go into version control (e.g., node_modules/, .env files, build directories, cache files, large binaries) unless explicitly instructed by the user.
-* If unsure about committing certain files, check for the presence of .gitignore files or ask the user for clarification.
-</VERSION_CONTROL>
-
-<PULL_REQUESTS>
-* When creating pull requests, create only ONE per session/issue unless explicitly instructed otherwise.
-* When working with an existing PR, update it with new commits rather than creating additional PRs for the same issue.
-* When updating a PR, preserve the original PR title and purpose, updating description only when necessary.
-</PULL_REQUESTS>
-
-<PROBLEM_SOLVING_WORKFLOW>
-1. EXPLORATION: Thoroughly explore relevant files and understand the context before proposing solutions
-2. ANALYSIS: Consider multiple approaches and select the most promising one
-3. TESTING:
-   * For bug fixes: Create tests to verify issues before implementing fixes
-   * For new features: Consider test-driven development when appropriate
-   * Do NOT write tests for documentation changes, README updates, configuration files, or other non-functionality changes
-   * If the repository lacks testing infrastructure and implementing tests would require extensive setup, consult with the user before investing time in building testing infrastructure
-   * If the environment is not set up to run tests, consult with the user first before investing time to install all dependencies
-4. IMPLEMENTATION: Make focused, minimal changes to address the problem
-5. VERIFICATION: If the environment is set up to run tests, test your implementation thoroughly, including edge cases. If the environment is not set up to run tests, consult with the user first before investing time to run tests.
-</PROBLEM_SOLVING_WORKFLOW>
+{% include "system_prompt.j2" %}
 
 <TASK_MANAGEMENT>
 * For complex, long-horizon tasks, create a TODO.md file to track progress:
@@ -88,26 +37,3 @@ Your primary role is to assist users by executing commands, modifying code, and
     d. Once complete, check off the item in TODO.md
     e. Proceed to the next unchecked item
 </TASK_MANAGEMENT>
-
-<SECURITY>
-* Only use GITHUB_TOKEN and other credentials in ways the user has explicitly requested and would expect.
-* Use APIs to work with GitHub or other platforms, unless the user asks otherwise or your task requires browsing.
-</SECURITY>
-
-<ENVIRONMENT_SETUP>
-* When user asks you to run an application, don't stop if the application is not installed. Instead, please install the application and run the command again.
-* If you encounter missing dependencies:
-  1. First, look around in the repository for existing dependency files (requirements.txt, pyproject.toml, package.json, Gemfile, etc.)
-  2. If dependency files exist, use them to install all dependencies at once (e.g., `pip install -r requirements.txt`, `npm install`, etc.)
-  3. Only install individual packages directly if no dependency files are found or if only specific packages are needed
-* Similarly, if you encounter missing dependencies for essential tools requested by the user, install them when possible.
-</ENVIRONMENT_SETUP>
-
-<TROUBLESHOOTING>
-* If you've made repeated attempts to solve a problem but tests still fail or the user reports it's still broken:
-  1. Step back and reflect on 5-7 different possible sources of the problem
-  2. Assess the likelihood of each possible cause
-  3. Methodically address the most likely causes, starting with the highest probability
-  4. Document your reasoning process
-* When you run into any major issue while executing a plan from the user, please don't try to directly work around it. Instead, propose a new plan and confirm with the user before proceeding.
-</TROUBLESHOOTING>

openhands/agenthub/codeact_agent/tools/bash.py

@@ -1,7 +1,6 @@
-import sys
-
 from litellm import ChatCompletionToolParam, ChatCompletionToolParamFunctionChunk
 
+from openhands.agenthub.codeact_agent.tools.prompt import refine_prompt
 from openhands.llm.tool_names import EXECUTE_BASH_TOOL_NAME
 
 _DETAILED_BASH_DESCRIPTION = """Execute a bash command in the terminal within a persistent shell session.
@@ -35,12 +34,6 @@ _SHORT_BASH_DESCRIPTION = """Execute a bash command in the terminal.
 * One command at a time: You can only execute one bash command at a time. If you need to run multiple commands sequentially, you can use `&&` or `;` to chain them together."""
 
 
-def refine_prompt(prompt: str):
-    if sys.platform == 'win32':
-        return prompt.replace('bash', 'powershell')
-    return prompt
-
-
 def create_cmd_run_tool(
     use_short_description: bool = False,
 ) -> ChatCompletionToolParam:

openhands/agenthub/codeact_agent/tools/prompt.py

@@ -0,0 +1,28 @@
+import re
+import sys
+
+
+def refine_prompt(prompt: str):
+    """Refines the prompt based on the platform.
+
+    On Windows systems, replaces 'bash' with 'powershell' and 'execute_bash' with 'execute_powershell'
+    to ensure commands work correctly on the Windows platform.
+
+    Args:
+        prompt: The prompt text to refine
+
+    Returns:
+        The refined prompt text
+    """
+    if sys.platform == 'win32':
+        # Replace 'bash' with 'powershell' including tool names like 'execute_bash'
+        # First replace 'execute_bash' with 'execute_powershell' to handle tool names
+        result = re.sub(
+            r'\bexecute_bash\b', 'execute_powershell', prompt, flags=re.IGNORECASE
+        )
+        # Then replace standalone 'bash' with 'powershell'
+        result = re.sub(
+            r'(?<!execute_)(?<!_)\bbash\b', 'powershell', result, flags=re.IGNORECASE
+        )
+        return result
+    return prompt

openhands/agenthub/readonly_agent/readonly_agent.py

@@ -1,6 +1,4 @@
-"""
-ReadOnlyAgent - A specialized version of CodeActAgent that only uses read-only tools.
-"""
+"""ReadOnlyAgent - A specialized version of CodeActAgent that only uses read-only tools."""
 
 import os
 from typing import TYPE_CHECKING

openhands/cli/main.py

@@ -236,43 +236,8 @@ async def run_session(
                     )
                     return
 
-                # Get the pending action from the agent controller
-                pending_action = controller._pending_action
-                command = ''
-                if pending_action:
-                    if hasattr(pending_action, 'command'):
-                        command = pending_action.command
-                    elif hasattr(pending_action, 'code'):
-                        command = pending_action.code
-
-                confirmation_status = await read_confirmation_input(
-                    config, command, pending_action
-                )
-
-                # Handle different confirmation responses
-                if confirmation_status == 'always':
-                    # Set always confirm mode to skip future confirmations
-                    always_confirm_mode = True
-                    event_stream.add_event(
-                        ChangeAgentStateAction(AgentState.USER_CONFIRMED),
-                        EventSource.USER,
-                    )
-                elif confirmation_status.startswith('remember:'):
-                    # Parse the remember response: remember:pattern:description
-                    parts = confirmation_status.split(':', 2)
-                    if len(parts) == 3:
-                        _, pattern, description = parts
-                        # Save the command pattern to config
-                        from openhands.cli.utils import save_approved_command_to_config
-
-                        save_approved_command_to_config(
-                            command, pattern=pattern, description=description
-                        )
-                    event_stream.add_event(
-                        ChangeAgentStateAction(AgentState.USER_CONFIRMED),
-                        EventSource.USER,
-                    )
-                elif confirmation_status == 'yes':
+                confirmation_status = await read_confirmation_input(config)
+                if confirmation_status in ('yes', 'always'):
                     event_stream.add_event(
                         ChangeAgentStateAction(AgentState.USER_CONFIRMED),
                         EventSource.USER,
@@ -758,9 +723,6 @@ def run_cli_command(args):
     except ConnectionRefusedError as e:
         print_formatted_text(f'Connection refused: {e}')
         sys.exit(1)
-    except Exception as e:
-        print_formatted_text(f'An error occurred: {e}')
-        sys.exit(1)
     finally:
         try:
             # Cancel all running tasks

openhands/cli/settings.py

@@ -1,4 +1,5 @@
 from pathlib import Path
+from typing import Optional
 
 from prompt_toolkit import PromptSession, print_formatted_text
 from prompt_toolkit.completion import FuzzyWordCompleter
@@ -19,6 +20,7 @@ from openhands.cli.utils import (
     VERIFIED_OPENAI_MODELS,
     VERIFIED_OPENHANDS_MODELS,
     VERIFIED_PROVIDERS,
+    extract_model_and_provider,
     organize_models_and_providers,
 )
 from openhands.controller.agent import Agent
@@ -124,12 +126,36 @@ async def get_validated_input(
     completer=None,
     validator=None,
     error_message: str = 'Input cannot be empty',
+    *,
+    default_value: str = '',
+    enter_keeps_value: Optional[str] = None,
 ) -> str:
+    """
+    Get validated input from user.
+
+    Args:
+        session: PromptSession instance
+        prompt_text: The text to display before the input
+        completer: Completer instance
+        validator: Function to validate input
+        error_message: Error message to display if input is invalid
+        default_value: Value to show prefilled in the prompt (prompt placeholder)
+        enter_keeps_value: If provided, pressing Enter on an empty input will
+            return this value (useful for keeping existing sensitive values)
+
+    Returns:
+        str: The validated input
+    """
+
     session.completer = completer
     value = None
 
     while True:
-        value = await session.prompt_async(prompt_text)
+        value = await session.prompt_async(prompt_text, default=default_value)
+
+        # If user submits empty input and a keep-value is provided, use it.
+        if not value.strip() and enter_keeps_value is not None:
+            value = enter_keeps_value
 
         if validator:
             is_valid = validator(value)
@@ -160,6 +186,50 @@ def save_settings_confirmation(config: OpenHandsConfig) -> bool:
     )
 
 
+def _get_current_values_for_modification_basic(
+    config: OpenHandsConfig,
+) -> tuple[str, str, str]:
+    llm_config = config.get_llm_config()
+    current_provider = ''
+    current_model = ''
+    current_api_key = (
+        llm_config.api_key.get_secret_value() if llm_config.api_key else ''
+    )
+    if llm_config.model:
+        model_info = extract_model_and_provider(llm_config.model)
+        current_provider = model_info.provider or ''
+        current_model = model_info.model or ''
+    return current_provider, current_model, current_api_key
+
+
+def _get_default_provider(provider_list: list[str]) -> str:
+    if 'anthropic' in provider_list:
+        return 'anthropic'
+    else:
+        return provider_list[0] if provider_list else ''
+
+
+def _get_initial_provider_index(
+    verified_providers: list[str],
+    current_provider: str,
+    default_provider: str,
+    provider_choices: list[str],
+) -> int:
+    if (current_provider or default_provider) in verified_providers:
+        return verified_providers.index(current_provider or default_provider)
+    elif current_provider or default_provider:
+        return len(provider_choices) - 1
+    return 0
+
+
+def _get_initial_model_index(
+    verified_models: list[str], current_model: str, default_model: str
+) -> int:
+    if (current_model or default_model) in verified_models:
+        return verified_models.index(current_model or default_model)
+    return 0
+
+
 async def modify_llm_settings_basic(
     config: OpenHandsConfig, settings_store: FileSettingsStore
 ) -> None:
@@ -174,23 +244,32 @@ async def modify_llm_settings_basic(
     provider_completer = FuzzyWordCompleter(provider_list)
     session = PromptSession(key_bindings=kb_cancel())
 
-    # Set default provider - prefer 'anthropic' if available, otherwise use first
-    provider = 'anthropic' if 'anthropic' in provider_list else provider_list[0]
+    current_provider, current_model, current_api_key = (
+        _get_current_values_for_modification_basic(config)
+    )
+
+    default_provider = _get_default_provider(provider_list)
+
+    provider = None
     model = None
     api_key = None
 
     try:
         # Show the default provider but allow changing it
         print_formatted_text(
-            HTML(f'\n<grey>Default provider: </grey><green>{provider}</green>')
+            HTML(f'\n<grey>Default provider: </grey><green>{default_provider}</green>')
         )
 
         # Show verified providers plus "Select another provider" option
         provider_choices = verified_providers + ['Select another provider']
+
         provider_choice = cli_confirm(
             config,
             '(Step 1/3) Select LLM Provider:',
             provider_choices,
+            initial_selection=_get_initial_provider_index(
+                verified_providers, current_provider, default_provider, provider_choices
+            ),
         )
 
         # Ensure provider_choice is an integer (for test compatibility)
@@ -211,8 +290,19 @@ async def modify_llm_settings_basic(
                 completer=provider_completer,
                 validator=lambda x: x in organized_models,
                 error_message='Invalid provider selected',
+                default_value=(
+                    # Prefill only for unverified providers.
+                    current_provider
+                    if current_provider not in verified_providers
+                    else ''
+                ),
             )
 
+        # Reset current model and api key if provider changes
+        if provider != current_provider:
+            current_model = ''
+            current_api_key = ''
+
         # Make sure the provider exists in organized_models
         if provider not in organized_models:
             # If the provider doesn't exist, prefer 'anthropic' if available,
@@ -276,6 +366,9 @@ async def modify_llm_settings_basic(
                     + 'LLM usage is billed at the providers’ rates with no markup. Details: https://docs.all-hands.dev/usage/llms/openhands-llms'
                 ),
                 model_choices,
+                initial_selection=_get_initial_model_index(
+                    VERIFIED_OPENHANDS_MODELS, current_model, default_model
+                ),
             )
 
             # Get the selected model from the list
@@ -291,6 +384,9 @@ async def modify_llm_settings_basic(
                     config,
                     'Do you want to use a different model?',
                     [f'Use {default_model}', 'Select another model'],
+                    initial_selection=0
+                    if (current_model or default_model) == default_model
+                    else 1,
                 )
                 == 1
             )
@@ -320,6 +416,10 @@ async def modify_llm_settings_basic(
                     completer=model_completer,
                     validator=model_validator,
                     error_message='Model name cannot be empty',
+                    default_value=(
+                        # Prefill only for models that are not the default model.
+                        current_model if current_model != default_model else ''
+                    ),
                 )
             else:
                 # Use the default model
@@ -332,10 +432,15 @@ async def modify_llm_settings_basic(
                 )
             )
 
+        prompt_text = '(Step 3/3) Enter API Key (CTRL-c to cancel): '
+        if current_api_key:
+            prompt_text = f'(Step 3/3) Enter API Key [{current_api_key[:4]}***{current_api_key[-4:]}] (CTRL-c to cancel, ENTER to keep current, type new to change): '
         api_key = await get_validated_input(
             session,
-            '(Step 3/3) Enter API Key (CTRL-c to cancel): ',
+            prompt_text,
             error_message='API Key cannot be empty',
+            default_value='',
+            enter_keeps_value=current_api_key,
         )
 
     except (
@@ -386,6 +491,7 @@ async def modify_llm_settings_advanced(
     config: OpenHandsConfig, settings_store: FileSettingsStore
 ) -> None:
     session = PromptSession(key_bindings=kb_cancel())
+    llm_config = config.get_llm_config()
 
     custom_model = None
     base_url = None
@@ -397,18 +503,28 @@ async def modify_llm_settings_advanced(
             session,
             '(Step 1/6) Custom Model (CTRL-c to cancel): ',
             error_message='Custom Model cannot be empty',
+            default_value=llm_config.model or '',
         )
 
         base_url = await get_validated_input(
             session,
             '(Step 2/6) Base URL (CTRL-c to cancel): ',
             error_message='Base URL cannot be empty',
+            default_value=llm_config.base_url or '',
         )
 
+        prompt_text = '(Step 3/6) API Key (CTRL-c to cancel): '
+        current_api_key = (
+            llm_config.api_key.get_secret_value() if llm_config.api_key else ''
+        )
+        if current_api_key:
+            prompt_text = f'(Step 3/6) API Key [{current_api_key[:4]}***{current_api_key[-4:]}] (CTRL-c to cancel, ENTER to keep current, type new to change): '
         api_key = await get_validated_input(
             session,
-            '(Step 3/6) API Key (CTRL-c to cancel): ',
+            prompt_text,
             error_message='API Key cannot be empty',
+            default_value='',
+            enter_keeps_value=current_api_key,
         )
 
         agent_list = Agent.list_agents()
@@ -419,6 +535,7 @@ async def modify_llm_settings_advanced(
             completer=agent_completer,
             validator=lambda x: x in agent_list,
             error_message='Invalid agent selected',
+            default_value=config.default_agent or '',
         )
 
         enable_confirmation_mode = (
@@ -426,6 +543,7 @@ async def modify_llm_settings_advanced(
                 config,
                 question='(Step 5/6) Confirmation Mode (CTRL-c to cancel):',
                 choices=['Enable', 'Disable'],
+                initial_selection=0 if config.security.confirmation_mode else 1,
             )
             == 0
         )
@@ -435,6 +553,7 @@ async def modify_llm_settings_advanced(
                 config,
                 question='(Step 6/6) Memory Condensation (CTRL-c to cancel):',
                 choices=['Enable', 'Disable'],
+                initial_selection=0 if config.enable_default_condenser else 1,
             )
             == 0
         )
@@ -463,6 +582,7 @@ async def modify_llm_settings_advanced(
     config.default_agent = agent
 
     config.security.confirmation_mode = enable_confirmation_mode
+    config.enable_default_condenser = enable_memory_condensation
 
     agent_config = config.get_agent_config(config.default_agent)
     if enable_memory_condensation:

openhands/cli/suppress_warnings.py

@@ -5,7 +5,6 @@ import warnings
 
 def suppress_cli_warnings():
     """Suppress common warnings that appear during CLI usage."""
-
     # Suppress pydub warning about ffmpeg/avconv
     warnings.filterwarnings(
         'ignore',

openhands/cli/tui.py

@@ -11,6 +11,7 @@ import threading
 import time
 from typing import Generator
 
+import markdown  # type: ignore
 from prompt_toolkit import PromptSession, print_formatted_text
 from prompt_toolkit.application import Application
 from prompt_toolkit.completion import CompleteEvent, Completer, Completion
@@ -65,6 +66,7 @@ MAX_RECENT_THOUGHTS = 5
 # Color and styling constants
 COLOR_GOLD = '#FFD700'
 COLOR_GREY = '#808080'
+COLOR_AGENT_BLUE = '#4682B4'  # Steel blue - less saturated, works well on both light and dark backgrounds
 DEFAULT_STYLE = Style.from_dict(
     {
         'gold': COLOR_GOLD,
@@ -236,13 +238,18 @@ def display_mcp_errors() -> None:
 
 
 # Prompt output display functions
-def display_thought_if_new(thought: str) -> None:
-    """Display a thought only if it hasn't been displayed recently."""
+def display_thought_if_new(thought: str, is_agent_message: bool = False) -> None:
+    """Display a thought only if it hasn't been displayed recently.
+
+    Args:
+        thought: The thought to display
+        is_agent_message: If True, apply agent styling and markdown rendering
+    """
     global recent_thoughts
     if thought and thought.strip():
         # Check if this thought was recently displayed
         if thought not in recent_thoughts:
-            display_message(thought)
+            display_message(thought, is_agent_message=is_agent_message)
             recent_thoughts.append(thought)
             # Keep only the most recent thoughts
             if len(recent_thoughts) > MAX_RECENT_THOUGHTS:
@@ -255,7 +262,7 @@ def display_event(event: Event, config: OpenHandsConfig) -> None:
         if isinstance(event, CmdRunAction):
             # For CmdRunAction, display thought first, then command
             if hasattr(event, 'thought') and event.thought:
-                display_message(event.thought)
+                display_thought_if_new(event.thought)
 
             # Only display the command if it's not already confirmed
             # Commands are always shown when AWAITING_CONFIRMATION, so we don't need to show them again when CONFIRMED
@@ -269,14 +276,15 @@ def display_event(event: Event, config: OpenHandsConfig) -> None:
         elif isinstance(event, Action):
             # For other actions, display thoughts normally
             if hasattr(event, 'thought') and event.thought:
-                display_message(event.thought)
+                display_thought_if_new(event.thought)
             if hasattr(event, 'final_thought') and event.final_thought:
-                display_message(event.final_thought)
+                # Display final thoughts with agent styling
+                display_message(event.final_thought, is_agent_message=True)
 
         if isinstance(event, MessageAction):
             if event.source == EventSource.AGENT:
-                # Check if this message content is a duplicate thought
-                display_thought_if_new(event.content)
+                # Display agent messages with styling and markdown rendering
+                display_thought_if_new(event.content, is_agent_message=True)
         elif isinstance(event, CmdOutputObservation):
             display_command_output(event.content)
         elif isinstance(event, FileEditObservation):
@@ -291,11 +299,74 @@ def display_event(event: Event, config: OpenHandsConfig) -> None:
             display_error(event.content)
 
 
-def display_message(message: str) -> None:
+def display_message(message: str, is_agent_message: bool = False) -> None:
+    """Display a message in the terminal with markdown rendering.
+
+    Args:
+        message: The message to display
+        is_agent_message: If True, apply agent styling (blue color)
+    """
     message = message.strip()
 
     if message:
-        print_formatted_text(f'\n{message}')
+        # Add spacing before the message
+        print_formatted_text('')
+
+        try:
+            # Convert markdown to HTML for all messages
+            html_content = convert_markdown_to_html(message)
+
+            if is_agent_message:
+                # Use prompt_toolkit's HTML renderer with the agent color
+                print_formatted_text(
+                    HTML(f'<style fg="{COLOR_AGENT_BLUE}">{html_content}</style>')
+                )
+            else:
+                # Regular message display with HTML rendering but default color
+                print_formatted_text(HTML(html_content))
+        except Exception as e:
+            # If HTML rendering fails, fall back to plain text
+            print(f'Warning: HTML rendering failed: {str(e)}', file=sys.stderr)
+            if is_agent_message:
+                print_formatted_text(
+                    FormattedText([('fg:' + COLOR_AGENT_BLUE, message)])
+                )
+            else:
+                print_formatted_text(message)
+
+
+def convert_markdown_to_html(text: str) -> str:
+    """Convert markdown to HTML for prompt_toolkit's HTML renderer using the markdown library.
+
+    Args:
+        text: Markdown text to convert
+
+    Returns:
+        HTML formatted text with custom styling for headers and bullet points
+    """
+    if not text:
+        return text
+
+    # Use the markdown library to convert markdown to HTML
+    # Enable the 'extra' extension for tables, fenced code, etc.
+    html = markdown.markdown(text, extensions=['extra'])
+
+    # Customize headers
+    for i in range(1, 7):
+        # Get the appropriate number of # characters for this heading level
+        prefix = '#' * i + ' '
+
+        # Replace <h1> with the prefix and bold text
+        html = html.replace(f'<h{i}>', f'<b>{prefix}')
+        html = html.replace(f'</h{i}>', '</b>\n')
+
+    # Customize bullet points to use dashes instead of dots with compact spacing
+    html = html.replace('<ul>', '')
+    html = html.replace('</ul>', '')
+    html = html.replace('<li>', '- ')
+    html = html.replace('</li>', '')
+
+    return html
 
 
 def display_error(error: str) -> None:
@@ -700,140 +771,12 @@ async def read_prompt_input(
         return '/exit'
 
 
-def _generate_single_command_pattern(command: str) -> list[str]:
-    """Generate candidate regex patterns for a single command based on prefixes.
-
-    Args:
-        command: The single command to generate patterns for.
-
-    Returns:
-        list[str]: List of candidate regex patterns that match similar commands.
-    """
-    import re
-
-    # Split command into parts
-    parts = command.split()
-    if not parts:
-        return [f'^{re.escape(command)}$']
-
-    patterns = []
-
-    # Generate patterns for first word, first two words, first three words
-    for i in range(1, min(4, len(parts) + 1)):
-        prefix_parts = parts[:i]
-        escaped_prefix = '\\s+'.join(re.escape(part) for part in prefix_parts)
-
-        # Create pattern: prefix followed by word boundary and anything until end of line
-        # This prevents matching partial words (e.g., "ls" won't match "lsof")
-        if i == 1:
-            # For single word, add word boundary to prevent partial matches
-            pattern = f'^{escaped_prefix}(\\s.*|$)'
-        else:
-            # For multiple words, the space already acts as a boundary
-            pattern = f'^{escaped_prefix}.*$'
-        patterns.append(pattern)
-
-    return patterns
-
-
-def _parse_piped_command(command: str) -> list[str]:
-    """Parse a command that may contain pipes into individual commands.
-
-    Args:
-        command: The command string to parse.
-
-    Returns:
-        list[str]: List of individual commands split by pipes.
-    """
-    import shlex
-
-    # Handle edge cases first
-    if not command or not command.strip():
-        return []
-
-    # Use shlex to split the command, which handles quotes and escapes properly
-    try:
-        # Split the entire command into tokens
-        tokens = shlex.split(command, posix=True)
-    except ValueError:
-        # If shlex fails (e.g., unmatched quotes), fall back to simple split
-        return [part.strip() for part in command.split('|') if part.strip()]
-
-    # Find pipe tokens and split the command accordingly
-    parts = []
-    current_part: list[str] = []
-
-    for token in tokens:
-        if token == '|':
-            if current_part:
-                parts.append(' '.join(current_part))
-                current_part = []
-        else:
-            current_part.append(token)
-
-    # Add the last part if it exists
-    if current_part:
-        parts.append(' '.join(current_part))
-
-    # If no pipes were found in tokens, check if the original command has pipes
-    # This handles cases where pipes are not separated by spaces
-    if len(parts) <= 1 and '|' in command:
-        return [part.strip() for part in command.split('|') if part.strip()]
-
-    return parts
-
-
-def _generate_command_patterns(command: str) -> list[str]:
-    """Generate candidate regex patterns for a command that can match similar commands.
-
-    This function handles both simple commands and piped commands.
-    For piped commands, it generates patterns for each sub-command.
-
-    Args:
-        command: The command to generate patterns for (may contain pipes).
-
-    Returns:
-        list[str]: List of candidate regex patterns that match similar commands.
-    """
-    # Parse the command to handle pipes
-    sub_commands = _parse_piped_command(command)
-
-    if len(sub_commands) <= 1:
-        # Single command or empty, return all candidate patterns
-        return _generate_single_command_pattern(command)
-    else:
-        # Piped command, generate pattern for each sub-command
-        # For simplicity, we'll just use the first pattern from each sub-command
-        sub_patterns = []
-        for sub_command in sub_commands:
-            patterns = _generate_single_command_pattern(sub_command.strip())
-            if patterns:
-                # Use the most specific pattern (first one)
-                sub_pattern = patterns[0]
-                # Remove the ^ and $ anchors from sub-patterns
-                if sub_pattern.startswith('^'):
-                    sub_pattern = sub_pattern[1:]
-                if sub_pattern.endswith('$'):
-                    sub_pattern = sub_pattern[:-1]
-                sub_patterns.append(sub_pattern)
-
-        if sub_patterns:
-            # Join sub-patterns with pipe separator (allowing flexible whitespace around pipes)
-            pattern = '\\s*\\|\\s*'.join(sub_patterns)
-            return [f'^{pattern}$']
-        else:
-            return []
-
-
-async def read_confirmation_input(
-    config: OpenHandsConfig, command: str = '', pending_action=None
-) -> str:
+async def read_confirmation_input(config: OpenHandsConfig) -> str:
     try:
         choices = [
             'Yes, proceed',
             'No (and allow to enter instructions)',
-            'Always proceed (skip all confirmations)',
-            "Yes, and don't ask again for similar commands",
+            "Always proceed (don't ask again)",
         ]
 
         # keep the outer coroutine responsive by using asyncio.to_thread which puts the blocking call app.run() of cli_confirm() in a separate thread
@@ -841,89 +784,7 @@ async def read_confirmation_input(
             cli_confirm, config, 'Choose an option:', choices
         )
 
-        result = {0: 'yes', 1: 'no', 2: 'always', 3: 'remember'}.get(index, 'no')
-
-        # If the user chose "remember", show pattern selection options
-        if result == 'remember' and command:
-            return await _handle_pattern_selection(config, command)
-
-        return result
-
-    except (KeyboardInterrupt, EOFError):
-        return 'no'
-
-
-async def _handle_pattern_selection(config: OpenHandsConfig, command: str) -> str:
-    """Handle pattern selection when user chooses to remember similar commands."""
-    try:
-        # Generate candidate patterns
-        patterns = _generate_command_patterns(command)
-
-        # Create pattern descriptions
-        pattern_choices = []
-        pattern_data = []
-
-        # Add exact command option
-        import re
-
-        exact_pattern = f'^{re.escape(command)}$'
-        pattern_choices.append(f'Exact command: {command}')
-        pattern_data.append(('exact', exact_pattern, f'Exact command: {command}'))
-
-        # Add prefix-based patterns
-        parts = command.split()
-        if parts:
-            for i, pattern in enumerate(patterns):
-                if i < len(parts):
-                    prefix = ' '.join(parts[: i + 1])
-                    description = f'Commands starting with: {prefix}'
-                    pattern_choices.append(description)
-                    pattern_data.append(('pattern', pattern, description))
-
-        # Add custom pattern option
-        pattern_choices.append('Enter custom pattern')
-        pattern_data.append(('custom', '', 'Custom pattern'))
-
-        # Show pattern selection menu
-        pattern_index = await asyncio.to_thread(
-            cli_confirm, config, 'Choose which commands to remember:', pattern_choices
-        )
-
-        if pattern_index < len(pattern_data):
-            pattern_type, pattern_value, description = pattern_data[pattern_index]
-
-            if pattern_type == 'custom':
-                # Get custom pattern from user
-                prompt_session = create_prompt_session(config)
-                print_formatted_text(
-                    HTML(
-                        '<gold>Enter a custom regex pattern (example: ^ls.*$ for all ls commands):</gold>'
-                    )
-                )
-                try:
-                    custom_pattern = await prompt_session.prompt_async('Pattern: ')
-                    if custom_pattern.strip():
-                        # Validate the regex pattern
-                        import re
-
-                        try:
-                            re.compile(custom_pattern.strip())
-                            return f'remember:{custom_pattern.strip()}:Custom pattern: {custom_pattern.strip()}'
-                        except re.error:
-                            print_formatted_text(
-                                HTML(
-                                    '<ansired>Invalid regex pattern. Using exact command instead.</ansired>'
-                                )
-                            )
-                            return f'remember:^{re.escape(command)}$:Exact command: {command}'
-                    else:
-                        return 'no'
-                except (KeyboardInterrupt, EOFError):
-                    return 'no'
-            else:
-                return f'remember:{pattern_value}:{description}'
-
-        return 'no'
+        return {0: 'yes', 1: 'no', 2: 'always'}.get(index, 'no')
 
     except (KeyboardInterrupt, EOFError):
         return 'no'
@@ -981,6 +842,7 @@ def cli_confirm(
     config: OpenHandsConfig,
     question: str = 'Are you sure?',
     choices: list[str] | None = None,
+    initial_selection: int = 0,
 ) -> int:
     """Display a confirmation prompt with the given question and choices.
 
@@ -988,7 +850,7 @@ def cli_confirm(
     """
     if choices is None:
         choices = ['Yes', 'No']
-    selected = [0]  # Using list to allow modification in closure
+    selected = [initial_selection]  # Using list to allow modification in closure
 
     def get_choice_text() -> list:
         return [