more debug logs

.github/scripts/check_version_consistency.py

@@ -1,66 +0,0 @@
-#!/usr/bin/env python3
-import os
-import re
-import sys
-from typing import Set, Tuple
-
-
-def find_version_references(directory: str) -> Tuple[Set[str], Set[str]]:
-    openhands_versions = set()
-    runtime_versions = set()
-
-    version_pattern_openhands = re.compile(r'openhands:(\d{1})\.(\d{2})')
-    version_pattern_runtime = re.compile(r'runtime:(\d{1})\.(\d{2})')
-
-    for root, _, files in os.walk(directory):
-        # Skip .git directory
-        if '.git' in root:
-            continue
-
-        for file in files:
-            if file.endswith(
-                ('.md', '.yml', '.yaml', '.txt', '.html', '.py', '.js', '.ts')
-            ):
-                file_path = os.path.join(root, file)
-                try:
-                    with open(file_path, 'r', encoding='utf-8') as f:
-                        content = f.read()
-
-                        # Find all openhands version references
-                        matches = version_pattern_openhands.findall(content)
-                        openhands_versions.update(matches)
-
-                        # Find all runtime version references
-                        matches = version_pattern_runtime.findall(content)
-                        runtime_versions.update(matches)
-                except Exception as e:
-                    print(f'Error reading {file_path}: {e}', file=sys.stderr)
-
-    return openhands_versions, runtime_versions
-
-
-def main():
-    repo_root = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '..'))
-    openhands_versions, runtime_versions = find_version_references(repo_root)
-
-    exit_code = 0
-
-    if len(openhands_versions) > 1:
-        print('Error: Multiple openhands versions found:', file=sys.stderr)
-        print('Found versions:', sorted(openhands_versions), file=sys.stderr)
-        exit_code = 1
-    elif len(openhands_versions) == 0:
-        print('Warning: No openhands version references found', file=sys.stderr)
-
-    if len(runtime_versions) > 1:
-        print('Error: Multiple runtime versions found:', file=sys.stderr)
-        print('Found versions:', sorted(runtime_versions), file=sys.stderr)
-        exit_code = 1
-    elif len(runtime_versions) == 0:
-        print('Warning: No runtime version references found', file=sys.stderr)
-
-    sys.exit(exit_code)
-
-
-if __name__ == '__main__':
-    main()

.github/workflows/lint.yml

@@ -53,16 +53,3 @@ jobs:
         run: pip install pre-commit==3.7.0
       - name: Run pre-commit hooks
         run: pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
-
-  # Check version consistency across documentation
-  check-version-consistency:
-    name: Check version consistency
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up python
-        uses: actions/setup-python@v5
-        with:
-          python-version: 3.12
-      - name: Run version consistency check
-        run: .github/scripts/check_version_consistency.py

.github/workflows/openhands-resolver.yml

@@ -185,17 +185,12 @@ jobs:
 
       - name: Install OpenHands
         uses: actions/github-script@v7
-        env:
-          COMMENT_BODY: ${{ github.event.comment.body || '' }}
-          REVIEW_BODY: ${{ github.event.review.body || '' }}
-          LABEL_NAME: ${{ github.event.label.name || '' }}
-          EVENT_NAME: ${{ github.event_name }}
         with:
           script: |
-            const commentBody = process.env.COMMENT_BODY.trim();
-            const reviewBody = process.env.REVIEW_BODY.trim();
-            const labelName = process.env.LABEL_NAME.trim();
-            const eventName = process.env.EVENT_NAME.trim();
+            const commentBody = `${{ github.event.comment.body || '' }}`.trim();
+            const reviewBody = `${{ github.event.review.body || '' }}`.trim();
+            const labelName = `${{ github.event.label.name || '' }}`.trim();
+            const eventName = `${{ github.event_name }}`.trim();
 
             // Check conditions
             const isExperimentalLabel = labelName === "fix-me-experimental";

.openhands/microagents/repo.md

@@ -1,7 +1,6 @@
 ---
 name: repo
-type: repo
-agent: CodeActAgent
+agent: CodeAct
 ---
 This repository contains the code for OpenHands, an automated AI software engineer. It has a Python backend
 (in the `openhands` directory) and React frontend (in the `frontend` directory).

Development.md

@@ -8,7 +8,7 @@ Otherwise, you can clone the OpenHands project directly.
 * Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)  [Ubuntu <= 22.04]
 * [Docker](https://docs.docker.com/engine/install/) (For those on MacOS, make sure to allow the default Docker socket to be used from advanced settings!)
 * [Python](https://www.python.org/downloads/) = 3.12
-* [NodeJS](https://nodejs.org/en/download/package-manager) >= 20.x
+* [NodeJS](https://nodejs.org/en/download/package-manager) >= 18.17.1
 * [Poetry](https://python-poetry.org/docs/#installing-with-the-official-installer) >= 1.8
 * OS-specific dependencies:
   - Ubuntu: build-essential => `sudo apt-get install build-essential`
@@ -100,7 +100,7 @@ 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:0.18-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.17-nikolaik`
 
 ## Develop inside Docker container
 

Makefile

@@ -81,10 +81,10 @@ check-nodejs:
 	@if command -v node > /dev/null; then \
 		NODE_VERSION=$(shell node --version | sed -E 's/v//g'); \
 		IFS='.' read -r -a NODE_VERSION_ARRAY <<< "$$NODE_VERSION"; \
-		if [ "$${NODE_VERSION_ARRAY[0]}" -ge 20 ]; then \
+		if [ "$${NODE_VERSION_ARRAY[0]}" -gt 18 ] || ([ "$${NODE_VERSION_ARRAY[0]}" -eq 18 ] && [ "$${NODE_VERSION_ARRAY[1]}" -gt 17 ]) || ([ "$${NODE_VERSION_ARRAY[0]}" -eq 18 ] && [ "$${NODE_VERSION_ARRAY[1]}" -eq 17 ] && [ "$${NODE_VERSION_ARRAY[2]}" -ge 1 ]); then \
 			echo "$(BLUE)Node.js $$NODE_VERSION is already installed.$(RESET)"; \
 		else \
-			echo "$(RED)Node.js 20.x or later is required. Please install Node.js 20.x or later to continue.$(RESET)"; \
+			echo "$(RED)Node.js 18.17.1 or later is required. Please install Node.js 18.17.1 or later to continue.$(RESET)"; \
 			exit 1; \
 		fi; \
 	else \

README.md

@@ -43,17 +43,17 @@ See the [Installation](https://docs.all-hands.dev/modules/usage/installation) gu
 system requirements and more information.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18
+    docker.all-hands.dev/all-hands-ai/openhands:0.17
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
@@ -64,16 +64,16 @@ works best, but you have [many options](https://docs.all-hands.dev/modules/usage
 
 ---
 
-You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes#connecting-to-your-filesystem),
+You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes),
 run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
 interact with it via a [friendly CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode),
-or run it on tagged issues with [a github action](https://docs.all-hands.dev/modules/usage/how-to/github-action).
+or run it on tagged issues with [a github action](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/resolver/README.md).
 
 Visit [Installation](https://docs.all-hands.dev/modules/usage/installation) for more information and setup instructions.
 
 > [!CAUTION]
 > OpenHands is meant to be run by a single user on their local workstation.
-> It is not appropriate for multi-tenant deployments where multiple users share the same instance. There is no built-in isolation or scalability.
+> It is not appropriate for multi-tenant deployments, where multiple users share the same instance--there is no built-in isolation or scalability.
 >
 > If you're interested in running OpenHands in a multi-tenant environment, please
 > [get in touch with us](https://docs.google.com/forms/d/e/1FAIpQLSet3VbGaz8z32gW9Wm-Grl4jpt5WgMXPgJ4EDPVmCETCBpJtQ/viewform)
@@ -86,7 +86,7 @@ Having issues? The [Troubleshooting Guide](https://docs.all-hands.dev/modules/us
 ## 📖 Documentation
 
 To learn more about the project, and for tips on using OpenHands,
-check out our [documentation](https://docs.all-hands.dev/modules/usage/getting-started).
+**check out our [documentation](https://docs.all-hands.dev/modules/usage/getting-started)**.
 
 There you'll find resources on how to use different LLM providers,
 troubleshooting resources, and advanced configuration options.

compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.18-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.17-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

config.template.toml

@@ -180,12 +180,6 @@ model = "gpt-4o"
 # https://docs.litellm.ai/docs/completion/token_usage
 #custom_tokenizer = ""
 
-# Whether to use native tool calling if supported by the model. Can be true, false, or None by default, which chooses the model's default behavior based on the evaluation.
-# ATTENTION: Based on evaluation, enabling native function calling may lead to worse results
-# in some scenarios. Use with caution and consider testing with your specific use case.
-# https://github.com/All-Hands-AI/OpenHands/pull/4711
-#native_tool_calling = None
-
 [llm.gpt4o-mini]
 api_key = "your-api-key"
 model = "gpt-4o"

containers/app/Dockerfile

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

containers/dev/compose.yml

@@ -11,7 +11,7 @@ services:
       - BACKEND_HOST=${BACKEND_HOST:-"0.0.0.0"}
       - SANDBOX_API_HOSTNAME=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.18-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.17-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docs/DOC_STYLE_GUIDE.md

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

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

@@ -52,7 +52,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -61,7 +61,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.16 \
     python -m openhands.core.cli
 ```
 

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

@@ -46,7 +46,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -56,6 +56,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.16 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

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

@@ -13,16 +13,16 @@
 La façon la plus simple d'exécuter OpenHands est avec Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18
+    docker.all-hands.dev/all-hands-ai/openhands:0.16
 ```
 
 Vous pouvez également exécuter OpenHands en mode [headless scriptable](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), en tant que [CLI interactive](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), ou en utilisant l'[Action GitHub OpenHands](https://docs.all-hands.dev/modules/usage/how-to/github-action).

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

@@ -13,7 +13,7 @@ C'est le Runtime par défaut qui est utilisé lorsque vous démarrez OpenHands.
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

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

@@ -50,7 +50,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -59,7 +59,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.16 \
     python -m openhands.core.cli
 ```
 

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

@@ -47,7 +47,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -57,6 +57,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.16 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

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

@@ -11,16 +11,16 @@
 在 Docker 中运行 OpenHands 是最简单的方式。
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18
+    docker.all-hands.dev/all-hands-ai/openhands:0.16
 ```
 
 你也可以在可脚本化的[无头模式](https://docs.all-hands.dev/modules/usage/how-to/headless-mode)下运行 OpenHands，作为[交互式 CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode)，或使用 [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action)。

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

@@ -11,7 +11,7 @@
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/modules/usage/about.md

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

docs/modules/usage/configuration-options.md

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

docs/modules/usage/feedback.md

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

docs/modules/usage/getting-started.mdx

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

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

@@ -6,9 +6,10 @@ This mode is different from the [headless mode](headless-mode), which is non-int
 
 ## With Python
 
-To start an interactive OpenHands session via the command line:
+To start an interactive OpenHands session via the command line, follow these steps:
 
 1. Ensure you have followed the [Development setup instructions](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
+
 2. Run the following command:
 
 ```bash
@@ -20,32 +21,45 @@ This command will start an interactive session where you can input tasks and rec
 You'll need to be sure to set your model, API key, and other settings via environment variables
 [or the `config.toml` file](https://github.com/All-Hands-AI/OpenHands/blob/main/config.template.toml).
 
+
 ## With Docker
 
-To run OpenHands in CLI mode with Docker:
+To run OpenHands in CLI mode with Docker, follow these steps:
 
-1. Set the following environmental variables in your terminal:
+1. Set `WORKSPACE_BASE` to the directory you want OpenHands to edit:
 
-- `WORKSPACE_BASE` to the directory you want OpenHands to edit (Ex: `export WORKSPACE_BASE=$(pwd)/workspace`).
-- `LLM_MODEL` to the model to use (Ex: `export LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"`).
-- `LLM_API_KEY` to the API key (Ex: `export LLM_API_KEY="sk_test_12345"`).
+```bash
+WORKSPACE_BASE=$(pwd)/workspace
+```
 
-2. Run the following Docker command:
+2. Set `LLM_MODEL` to the model you want to use:
+
+```bash
+LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"
+
+```
+
+3. Set `LLM_API_KEY` to your API key:
+
+```bash
+LLM_API_KEY="sk_test_12345"
+```
+
+4. Run the following Docker command:
 
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
     -e LLM_MODEL=$LLM_MODEL \
     -v $WORKSPACE_BASE:/opt/workspace_base \
     -v /var/run/docker.sock:/var/run/docker.sock \
-    -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.17 \
     python -m openhands.core.cli
 ```
 

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

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

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

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

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

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

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

@@ -7,9 +7,10 @@ This is different from [CLI Mode](cli-mode), which is interactive, and better fo
 
 ## With Python
 
-To run OpenHands in headless mode with Python:
-1. Ensure you have followed the [Development setup instructions](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
-2. Run the following command:
+To run OpenHands in headless mode with Python,
+[follow the Development setup instructions](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md),
+and then run:
+
 ```bash
 poetry run python -m openhands.core.main -t "write a bash script that prints hi"
 ```
@@ -19,20 +20,31 @@ You'll need to be sure to set your model, API key, and other settings via enviro
 
 ## With Docker
 
-To run OpenHands in Headless mode with Docker:
+1. Set `WORKSPACE_BASE` to the directory you want OpenHands to edit:
 
-1. Set the following environmental variables in your terminal:
+```bash
+WORKSPACE_BASE=$(pwd)/workspace
+```
 
-- `WORKSPACE_BASE` to the directory you want OpenHands to edit (Ex: `export WORKSPACE_BASE=$(pwd)/workspace`).
-- `LLM_MODEL` to the model to use (Ex: `export LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"`).
-- `LLM_API_KEY` to the API key (Ex: `export LLM_API_KEY="sk_test_12345"`).
+2. Set `LLM_MODEL` to the model you want to use:
 
-2. Run the following Docker command:
+```bash
+LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"
+
+```
+
+3. Set `LLM_API_KEY` to your API key:
+
+```bash
+LLM_API_KEY="sk_test_12345"
+```
+
+4. Run the following Docker command:
 
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -40,17 +52,8 @@ docker run -it \
     -e LOG_ALL_EVENTS=true \
     -v $WORKSPACE_BASE:/opt/workspace_base \
     -v /var/run/docker.sock:/var/run/docker.sock \
-    -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
-    python -m openhands.core.main -t "write a bash script that prints hi"
+    docker.all-hands.dev/all-hands-ai/openhands:0.17 \
+    python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```
-
-## Advanced Headless Configurations
-
-To view all available configuration options for headless mode, run the Python command with the `--help` flag.
-
-### Additional Logs
-
-For the headless mode to log all the agent actions, in the terminal run: `export LOG_ALL_EVENTS=true`

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

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

docs/modules/usage/installation.mdx

@@ -2,37 +2,34 @@
 
 ## System Requirements
 
-- Docker version 26.0.0+ or Docker Desktop 4.31.0+.
-- You must be using Linux or Mac OS.
-  - If you are on Windows, you must use [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
+* Docker version 26.0.0+ or Docker Desktop 4.31.0+.
+* You must be using Linux or Mac OS.
+  * If you are on Windows, you must use [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
 
 ## Start the app
 
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18
+    docker.all-hands.dev/all-hands-ai/openhands:0.17
 ```
 
-You'll find OpenHands running at http://localhost:3000!
-
-You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes#connecting-to-your-filesystem),
-run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
-interact with it via a [friendly CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode),
-or run it on tagged issues with [a github action](https://docs.all-hands.dev/modules/usage/how-to/github-action).
+You can also run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), as an [interactive CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), or using the [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action).
 
 ## Setup
 
+After running the command above, you'll find OpenHands running at [http://localhost:3000](http://localhost:3000).
+
 Upon launching OpenHands, you'll see a settings modal. You **must** select an `LLM Provider` and `LLM Model` and enter a corresponding `API Key`.
 These can be changed at any time by selecting the `Settings` button (gear icon) in the UI.
 

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

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

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

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

docs/modules/usage/llms/groq.md

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

docs/modules/usage/llms/llms.md

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

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

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

docs/modules/usage/prompting/customization.md

@@ -9,11 +9,11 @@ You can customize OpenHands' behavior for your repository by creating a `.openha
 be given to the agent every time it works with this repository.
 
 We suggest including the following information:
-- **Repository Overview**: A brief description of your project's purpose and architecture.
-- **Directory Structure**: Key directories and their purposes.
-- **Development Guidelines**: Project-specific coding standards and practices.
-- **Testing Requirements**: How to run tests and what types of tests are required.
-- **Setup Instructions**: Steps needed to build and run the project.
+1. **Repository Overview**: A brief description of your project's purpose and architecture
+2. **Directory Structure**: Key directories and their purposes
+3. **Development Guidelines**: Project-specific coding standards and practices
+4. **Testing Requirements**: How to run tests and what types of tests are required
+5. **Setup Instructions**: Steps needed to build and run the project
 
 ### Example Repository Configuration
 Example `.openhands/microagents/repo.md` file:
@@ -39,11 +39,11 @@ Guidelines:
 
 ### Customizing Prompts
 
-When working with a repository:
+When working with a customized repository:
 
-- **Reference Project Standards**: Mention specific coding standards or patterns used in your project.
-- **Include Context**: Reference relevant documentation or existing implementations.
-- **Specify Testing Requirements**: Include project-specific testing requirements in your prompts.
+1. **Reference Project Standards**: Mention specific coding standards or patterns used in your project
+2. **Include Context**: Reference relevant documentation or existing implementations
+3. **Specify Testing Requirements**: Include project-specific testing requirements in your prompts
 
 Example customized prompt:
 ```
@@ -54,14 +54,14 @@ The component should use our shared styling from src/styles/components.
 
 ### Best Practices for Repository Customization
 
-- **Keep Instructions Updated**: Regularly update your `.openhands` directory as your project evolves.
-- **Be Specific**: Include specific paths, patterns, and requirements unique to your project.
-- **Document Dependencies**: List all tools and dependencies required for development.
-- **Include Examples**: Provide examples of good code patterns from your project.
-- **Specify Conventions**: Document naming conventions, file organization, and code style preferences.
+1. **Keep Instructions Updated**: Regularly update your `.openhands` directory as your project evolves
+2. **Be Specific**: Include specific paths, patterns, and requirements unique to your project
+3. **Document Dependencies**: List all tools and dependencies required for development
+4. **Include Examples**: Provide examples of good code patterns from your project
+5. **Specify Conventions**: Document naming conventions, file organization, and code style preferences
 
 By customizing OpenHands for your repository, you'll get more accurate and consistent results that align with your project's standards and requirements.
 
 ## Other Microagents
 You can create other instructions in the `.openhands/microagents/` directory
-that will be sent to the agent if a particular keyword is found, like `test`, `frontend`, or `migration`. See [Micro-Agents](microagents.md) for more information.
+that will be sent to the agent if a particular keyword is found, like `test`, `frontend`, or `migration`. See [Microagents](microagents.md) for more information.

docs/modules/usage/prompting/microagents.md

@@ -6,10 +6,10 @@ OpenHands uses specialized micro-agents to handle specific tasks and contexts ef
 
 Micro-agents are defined in markdown files under the `openhands/agenthub/codeact_agent/micro/` directory. Each micro-agent is configured with:
 
-- A unique name.
-- The agent type (typically CodeActAgent).
-- Trigger keywords that activate the agent.
-- Specific instructions and capabilities.
+- A unique name
+- The agent type (typically CodeActAgent)
+- Trigger keywords that activate the agent
+- Specific instructions and capabilities
 
 ## Available Micro-Agents
 
@@ -18,10 +18,10 @@ Micro-agents are defined in markdown files under the `openhands/agenthub/codeact
 **Triggers**: `github`, `git`
 
 The GitHub agent specializes in GitHub API interactions and repository management. It:
-- Has access to a `GITHUB_TOKEN` for API authentication.
-- Follows strict guidelines for repository interactions.
-- Handles branch management and pull requests.
-- Uses the GitHub API instead of web browser interactions.
+- Has access to a `GITHUB_TOKEN` for API authentication
+- Follows strict guidelines for repository interactions
+- Handles branch management and pull requests
+- Uses the GitHub API instead of web browser interactions
 
 Key features:
 - Branch protection (prevents direct pushes to main/master)
@@ -34,14 +34,13 @@ Key features:
 **Triggers**: `npm`
 
 Specializes in handling npm package management with specific focus on:
-- Non-interactive shell operations.
-- Automated confirmation handling using Unix 'yes' command.
-- Package installation automation.
+- Non-interactive shell operations
+- Automated confirmation handling using Unix 'yes' command
+- Package installation automation
 
 ### Custom Micro-Agents
 
-You can create your own micro-agents by adding new markdown files to the micro-agents directory.
-Each file should follow this structure:
+You can create your own micro-agents by adding new markdown files to the micro-agents directory. Each file should follow this structure:
 
 ```markdown
 ---
@@ -58,18 +57,19 @@ Instructions and capabilities for the micro-agent...
 ## Best Practices
 
 When working with micro-agents:
-- **Use Appropriate Triggers**: Ensure your commands include the relevant trigger words to activate the correct micro-agent.
-- **Follow Agent Guidelines**: Each agent has specific instructions and limitations. Respect these for optimal results.
-- **API-First Approach**: When available, use API endpoints rather than web interfaces.
-- **Automation Friendly**: Design commands that work well in non-interactive environments.
+
+1. **Use Appropriate Triggers**: Ensure your commands include the relevant trigger words to activate the correct micro-agent
+2. **Follow Agent Guidelines**: Each agent has specific instructions and limitations - respect these for optimal results
+3. **API-First Approach**: When available, use API endpoints rather than web interfaces
+4. **Automation Friendly**: Design commands that work well in non-interactive environments
 
 ## Integration
 
 Micro-agents are automatically integrated into OpenHands' workflow. They:
-- Monitor incoming commands for their trigger words.
-- Activate when relevant triggers are detected.
-- Apply their specialized knowledge and capabilities.
-- Follow their specific guidelines and restrictions.
+- Monitor incoming commands for their trigger words
+- Activate when relevant triggers are detected
+- Apply their specialized knowledge and capabilities
+- Follow their specific guidelines and restrictions
 
 ## Example Usage
 
@@ -105,7 +105,7 @@ Create a new markdown file in `openhands/agenthub/codeact_agent/micro/` with a d
 
 Your micro-agent file must include:
 
-- **Front Matter**: YAML metadata at the start of the file:
+1. **Front Matter**: YAML metadata at the start of the file:
 ```markdown
 ---
 name: your_agent_name
@@ -116,7 +116,7 @@ triggers:
 ---
 ```
 
-- **Instructions**: Clear, specific guidelines for the agent's behavior:
+2. **Instructions**: Clear, specific guidelines for the agent's behavior:
 ```markdown
 You are responsible for [specific task/domain].
 
@@ -135,19 +135,19 @@ Examples of usage:
 
 ### 4. Best Practices for Micro-Agent Development
 
-- **Clear Scope**: Keep the agent focused on a specific domain or task.
-- **Explicit Instructions**: Provide clear, unambiguous guidelines.
-- **Useful Examples**: Include practical examples of common use cases.
-- **Safety First**: Include necessary warnings and constraints.
-- **Integration Awareness**: Consider how the agent interacts with other components.
+1. **Clear Scope**: Keep the agent focused on a specific domain or task
+2. **Explicit Instructions**: Provide clear, unambiguous guidelines
+3. **Useful Examples**: Include practical examples of common use cases
+4. **Safety First**: Include necessary warnings and constraints
+5. **Integration Awareness**: Consider how the agent interacts with other components
 
 ### 5. Testing Your Micro-Agent
 
 Before submitting:
-- Test the agent with various prompts.
-- Verify trigger words activate the agent correctly.
-- Ensure instructions are clear and comprehensive.
-- Check for potential conflicts with existing agents.
+1. Test the agent with various prompts
+2. Verify trigger words activate the agent correctly
+3. Ensure instructions are clear and comprehensive
+4. Check for potential conflicts with existing agents
 
 ### 6. Example Implementation
 
@@ -199,12 +199,11 @@ Remember to:
 
 ### 7. Submission Process
 
-1. Create your micro-agent file in the correct directory.
-2. Test thoroughly.
+1. Create your micro-agent file in the correct directory
+2. Test thoroughly
 3. Submit a pull request with:
-   - The new micro-agent file.
-   - Updated documentation if needed.
-   - Description of the agent's purpose and capabilities.
+   - The new micro-agent file
+   - Updated documentation if needed
+   - Description of the agent's purpose and capabilities
 
-Remember that micro-agents are a powerful way to extend OpenHands' capabilities in specific domains. Well-designed
-agents can significantly improve the system's ability to handle specialized tasks.
+Remember that micro-agents are a powerful way to extend OpenHands' capabilities in specific domains. Well-designed agents can significantly improve the system's ability to handle specialized tasks.

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

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

docs/modules/usage/runtimes.md

@@ -16,7 +16,7 @@ some flags being passed to `docker run` that make this possible:
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```
@@ -26,29 +26,30 @@ that contains our Runtime server, as well as some basic utilities for Python and
 You can also [build your own runtime image](how-to/custom-sandbox-guide).
 
 ### Connecting to Your filesystem
-One useful feature here is the ability to connect to your local filesystem. To mount your filesystem into the runtime:
-1. Set `WORKSPACE_BASE`:
+One useful feature here is the ability to connect to your local filesystem.
 
-    ```bash
-    export WORKSPACE_BASE=/path/to/your/code
+To mount your filesystem into the runtime, first set WORKSPACE_BASE:
+```bash
+export WORKSPACE_BASE=/path/to/your/code
 
-    # Linux and Mac Example
-    # export WORKSPACE_BASE=$HOME/OpenHands
-    # Will set $WORKSPACE_BASE to /home/<username>/OpenHands
-    #
-    # WSL on Windows Example
-    # export WORKSPACE_BASE=/mnt/c/dev/OpenHands
-    # Will set $WORKSPACE_BASE to C:\dev\OpenHands
-    ```
-2. Add the following options to the `docker run` command:
+# Linux and Mac Example
+# export WORKSPACE_BASE=$HOME/OpenHands
+# Will set $WORKSPACE_BASE to /home/<username>/OpenHands
+#
+# WSL on Windows Example
+# export WORKSPACE_BASE=/mnt/c/dev/OpenHands
+# Will set $WORKSPACE_BASE to C:\dev\OpenHands
+```
 
-    ```bash
-    docker run # ...
-        -e SANDBOX_USER_ID=$(id -u) \
-        -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
-        -v $WORKSPACE_BASE:/opt/workspace_base \
-        # ...
-    ```
+then add the following options to the `docker run` command:
+
+```bash
+docker run # ...
+    -e SANDBOX_USER_ID=$(id -u) \
+    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
+    -v $WORKSPACE_BASE:/opt/workspace_base \
+    # ...
+```
 
 Be careful! There's nothing stopping the OpenHands agent from deleting or modifying
 any files that are mounted into its workspace.
@@ -58,7 +59,7 @@ but seems to work well on most systems.
 
 ## All Hands Runtime
 The All Hands Runtime is currently in beta. You can request access by joining
-the #remote-runtime-limited-beta channel on Slack ([see the README](https://github.com/All-Hands-AI/OpenHands?tab=readme-ov-file#-how-to-join-the-community) for an invite).
+the #remote-runtime-limited-beta channel on Slack ([see the README](https://github.com/All-Hands-AI/OpenHands?tab=readme-ov-file#-join-our-community) for an invite).
 
 To use the All Hands Runtime, set the following environment variables when
 starting OpenHands:

docs/src/pages/index.tsx

@@ -1,13 +1,14 @@
-import useDocusaurusContext from '@docusaurus/useDocusaurusContext';
-import Layout from '@theme/Layout';
-import { HomepageHeader } from '../components/HomepageHeader/HomepageHeader';
+import useDocusaurusContext from "@docusaurus/useDocusaurusContext";
+import Layout from "@theme/Layout";
+import { HomepageHeader } from "../components/HomepageHeader/HomepageHeader";
+import { Welcome } from "../components/Welcome/Welcome";
 import { translate } from '@docusaurus/Translate';
 
 export function Header({ title, summary }): JSX.Element {
   return (
     <div>
       <h1>{title}</h1>
-      <h2 style={{ fontSize: '3rem' }}>{summary}</h2>
+      <h2 style={{ fontSize: "3rem" }}>{summary}</h2>
     </div>
   );
 }
@@ -22,7 +23,7 @@ export default function Home(): JSX.Element {
         message: 'Code Less, Make More',
       })}
     >
-      <HomepageHeader />
+    <HomepageHeader />
     </Layout>
   );
 }

evaluation/benchmarks/EDA/run_infer.py

@@ -63,7 +63,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='docker',
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='python:3.12-bookworm',
@@ -75,8 +75,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/agent_bench/run_infer.py

@@ -43,7 +43,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'docker'),
+        runtime=os.environ.get('RUNTIME', 'eventstream'),
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='python:3.12-slim',
@@ -59,8 +59,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/aider_bench/run_infer.py

@@ -50,7 +50,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'docker'),
+        runtime=os.environ.get('RUNTIME', 'eventstream'),
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='python:3.11-bookworm',
@@ -67,8 +67,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
 
     # copy 'draft_editor' config if exists
     config_copy = copy.deepcopy(config)

evaluation/benchmarks/biocoder/run_infer.py

@@ -61,7 +61,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='docker',
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image=BIOCODER_BENCH_CONTAINER_IMAGE,
@@ -73,8 +73,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/bird/run_infer.py

@@ -74,7 +74,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='docker',
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='python:3.12-bookworm',
@@ -86,8 +86,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/browsing_delegation/run_infer.py

@@ -39,7 +39,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='docker',
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='python:3.12-bookworm',
@@ -50,8 +50,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/commit0_bench/run_infer.py

@@ -124,7 +124,7 @@ def get_config(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         max_iterations=metadata.max_iterations,
-        runtime=os.environ.get('RUNTIME', 'docker'),
+        runtime=os.environ.get('RUNTIME', 'eventstream'),
         sandbox=SandboxConfig(
             base_container_image=base_container_image,
             enable_auto_lint=True,

evaluation/benchmarks/discoverybench/run_infer.py

@@ -65,7 +65,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='docker',
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='python:3.12-bookworm',
@@ -77,8 +77,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     agent_config = AgentConfig(
         function_calling=False,
         codeact_enable_jupyter=True,

evaluation/benchmarks/gaia/run_infer.py

@@ -50,7 +50,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='docker',
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='python:3.12-bookworm',
@@ -62,8 +62,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/gorilla/run_infer.py

@@ -43,7 +43,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='docker',
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='python:3.12-bookworm',
@@ -55,8 +55,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/gpqa/run_infer.py

@@ -64,7 +64,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='docker',
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='python:3.12-bookworm',
@@ -76,8 +76,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/humanevalfix/run_infer.py

@@ -85,7 +85,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='docker',
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='python:3.12-bookworm',
@@ -97,8 +97,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/logic_reasoning/run_infer.py

@@ -48,7 +48,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='docker',
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='xingyaoww/od-eval-logic-reasoning:v1.0',
@@ -61,8 +61,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/miniwob/run_infer.py

@@ -58,7 +58,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'docker'),
+        runtime=os.environ.get('RUNTIME', 'eventstream'),
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='xingyaoww/od-eval-miniwob:v1.0',

evaluation/benchmarks/mint/run_infer.py

@@ -106,7 +106,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='docker',
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='xingyaoww/od-eval-mint:v1.0',
@@ -119,8 +119,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/ml_bench/run_infer.py

@@ -80,7 +80,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='docker',
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='public.ecr.aws/i5g0m1f6/ml-bench',
@@ -92,8 +92,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/scienceagentbench/run_infer.py

@@ -62,7 +62,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'docker'),
+        runtime=os.environ.get('RUNTIME', 'eventstream'),
         max_budget_per_task=4,
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -76,7 +76,7 @@ def get_config(instance: pd.Series) -> AppConfig:
     )
     config = AppConfig(
         run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'docker'),
+        runtime=os.environ.get('RUNTIME', 'eventstream'),
         sandbox=SandboxConfig(
             base_container_image=base_container_image,
             use_host_network=False,

evaluation/benchmarks/swe_bench/run_infer.py

@@ -121,7 +121,7 @@ def get_config(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         max_iterations=metadata.max_iterations,
-        runtime=os.environ.get('RUNTIME', 'docker'),
+        runtime=os.environ.get('RUNTIME', 'eventstream'),
         sandbox=SandboxConfig(
             base_container_image=base_container_image,
             enable_auto_lint=True,

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

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

evaluation/benchmarks/the_agent_company/README.md

@@ -5,7 +5,7 @@ This folder contains the evaluation harness that we built on top of the original
 The evaluation consists of three steps:
 
 1. Environment setup: [install python environment](../../README.md#development-environment), [configure LLM config](../../README.md#configure-openhands-and-your-llm), [launch services](https://github.com/TheAgentCompany/TheAgentCompany/blob/main/docs/SETUP.md).
-2. [Run Evaluation](#run-inference-on-the-agent-company-tasks): Run all tasks and get the evaluation results.
+2. [Run Evaluation](#run-inference-on-the-agent-company-instances): Run all tasks and get the evaluation results.
 
 ## Setup Environment and LLM Configuration
 

evaluation/benchmarks/the_agent_company/scripts/summarise_results.py

@@ -1,316 +0,0 @@
-###########################################################################################################
-# Adapted from https://github.com/TheAgentCompany/TheAgentCompany/blob/main/evaluation/summarise_results.py
-###########################################################################################################
-
-
-import glob
-import json
-import os
-import re
-import sys
-from typing import Dict, Tuple
-
-
-def calculate_cost(model: str, prompt_tokens: int, completion_tokens: int) -> float:
-    """
-    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
-    elif 'gpt-4o' in model.lower():
-        # https://openai.com/api/pricing/, accessed 12/11/2024
-        return 0.0000025 * prompt_tokens + 0.00001 * completion_tokens
-    elif 'gemini-1.5-pro' in model.lower():
-        # https://ai.google.dev/pricing#1_5pro, accessed 12/11/2024
-        # assuming prompts up to 128k tokens
-        cost = 0.00000125 * prompt_tokens + 0.000005 * completion_tokens
-        if prompt_tokens > 128000:
-            cost *= 2
-        return cost
-    elif 'gemini-2.0-flash-exp' in model.lower():
-        # price unknown for gemini-2.0-flash-exp, assuming same price as gemini-1.5-flash
-        cost = 0.000000075 * prompt_tokens + 0.0000003 * completion_tokens
-        if prompt_tokens > 128000:
-            cost *= 2
-        return cost
-    elif 'qwen2-72b' in model.lower():
-        # assuming hosted on Together
-        # https://www.together.ai/pricing, accessed 12/11/2024
-        return 0.0000009 * (prompt_tokens + completion_tokens)
-    elif 'qwen2p5-72b' in model.lower():
-        # assuming hosted on Together
-        # https://www.together.ai/pricing, accessed 12/14/2024
-        return 0.0000012 * (prompt_tokens + completion_tokens)
-    elif 'llama-v3p1-405b-instruct' in model.lower():
-        # assuming hosted on Fireworks AI
-        # https://fireworks.ai/pricing, accessed 12/11/2024
-        return 0.000003 * (prompt_tokens + completion_tokens)
-    elif 'llama-v3p1-70b-instruct' in model.lower():
-        # assuming hosted on Fireworks AI
-        return 0.0000009 * (prompt_tokens + completion_tokens)
-    elif 'llama-v3p3-70b-instruct' in model.lower():
-        # assuming hosted on Fireworks AI
-        return 0.0000009 * (prompt_tokens + completion_tokens)
-    elif 'amazon.nova-pro-v1:0' in model.lower():
-        # assuming hosted on Amazon Bedrock
-        # https://aws.amazon.com/bedrock/pricing/, accessed 12/11/2024
-        return 0.0000008 * prompt_tokens + 0.0000032 * completion_tokens
-    else:
-        raise ValueError(f'Unknown model: {model}')
-
-
-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.
-
-    Args:
-        filepath: Path to the JSON file
-
-    Returns:
-        Tuple containing (total, result) from final_score
-    """
-    try:
-        with open(filepath, 'r') as f:
-            data = json.load(f)
-
-        final_score = data.get('final_score', {})
-        return (final_score.get('total', 0), final_score.get('result', 0))
-    except json.JSONDecodeError as e:
-        print(f'Error decoding JSON in {filepath}: {e}')
-        return (0, 0)
-    except Exception as e:
-        print(f'Error processing {filepath}: {e}')
-        return (0, 0)
-
-
-def analyze_traj_json_file(filepath: str) -> Tuple[int, float]:
-    """
-    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.
-    """
-    steps: int = 0
-    cost: float = 0.0
-    with open(filepath, 'r') as f:
-        data = json.load(f)
-        response_id = None
-        for action in data:
-            if 'tool_call_metadata' in action:
-                if action['tool_call_metadata']['model_response']['id'] != response_id:
-                    response_id = action['tool_call_metadata']['model_response']['id']
-                else:
-                    # openhands displays the same model response meta data multiple times, when
-                    # a single LLM call leads to multiple actions and observations.
-                    continue
-                steps += 1
-                usage = action['tool_call_metadata']['model_response']['usage']
-                model: str = action['tool_call_metadata']['model_response']['model']
-                prompt_tokens = usage['prompt_tokens']
-                completion_tokens = usage['completion_tokens']
-                cost += calculate_cost(model, prompt_tokens, completion_tokens)
-
-    return (steps, cost)
-
-
-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.
-
-    Args:
-        folder_path: Path to the folder containing JSON files
-
-    Returns:
-        dictionaries:
-        - eval_results: Dictionary with filename as key and (total, result) tuple as value
-        - traj_results: Dictionary with filename as key and (steps, cost) tuple as value
-    """
-    eval_results = {}
-    traj_results = {}
-
-    eval_pattern = os.path.join(folder_path, 'eval_*.json')
-    traj_pattern = os.path.join(folder_path, 'traj_*.json')
-
-    for filepath in glob.glob(eval_pattern):
-        filename = os.path.basename(filepath)
-        total, result = analyze_eval_json_file(filepath)
-        key = re.search(r'eval_(.+)\.json', filename).group(1)
-        eval_results[key] = (total, result)
-
-    for filepath in glob.glob(traj_pattern):
-        filename = os.path.basename(filepath)
-        steps, cost = analyze_traj_json_file(filepath)
-        key = re.search(r'traj_(.+)\.json', filename).group(1)
-        traj_results[key] = (steps, cost)
-
-    return eval_results, traj_results
-
-
-def get_task_nature_category(task_name: str) -> str:
-    """
-    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
-    else:
-        return 'other'
-
-
-def calculate_score(total: int, result: int) -> float:
-    """
-    Calculate the score as a number between 0 and 1.
-
-    Formula: score = (result / total) * 0.5 + (result // total) * 0.5
-    Explanation:
-    - (result / total) * 0.5: This is the completion ratio, scaled down to a 0-0.5 range.
-    - (result // total) * 0.5: This is a binary score indicating whether the task was completed or not.
-
-    Args:
-        total: Total possible points
-        result: Actual points achieved
-
-    Returns:
-        Score as a number between 0 and 1
-    """
-    return (result / total * 0.5) + (result // total * 0.5)
-
-
-def is_perfect_completion(total: int, result: int) -> bool:
-    """
-    Check if the task achieved perfect completion.
-
-    Args:
-        total: Total possible points
-        result: Actual points achieved
-
-    Returns:
-        True if result equals total, False otherwise
-    """
-    return total > 0 and total == result
-
-
-def main():
-    if len(sys.argv) != 2:
-        print('Usage: poetry run python summarise_results.py <folder_path>')
-        sys.exit(1)
-
-    folder_path = sys.argv[1]
-
-    if not os.path.isdir(folder_path):
-        print(f"Error: '{folder_path}' is not a valid directory")
-        sys.exit(1)
-
-    eval_results, traj_results = analyze_folder(folder_path)
-
-    if not eval_results:
-        print(f'No eval_*.json files found in {folder_path}')
-        return
-
-    # Create list of results with completion ratios for sorting
-    detailed_results = [
-        (
-            task_name,
-            total,
-            result,
-            calculate_score(total, result),
-            is_perfect_completion(total, result),
-            get_task_nature_category(task_name),
-        )
-        for task_name, (total, result) in eval_results.items()
-    ]
-
-    # Sort by score in descending order
-    detailed_results.sort(key=lambda x: (-x[3], x[0]))
-
-    # Calculate perfect completion stats
-    perfect_completions = sum(
-        1 for _, _, _, _, is_perfect, _ in detailed_results if is_perfect
-    )
-
-    # Print header
-    print('\n# Evaluation Results Report')
-    print('\n## Results per File')
-    print('\n*Sorted by score (⭐ indicates perfect completion)*\n')
-
-    # Print table header
-    print(
-        '| Filename | Total | Result | Score | Steps | Cost (assuming no prompt caching)|'
-    )
-    print('|----------|--------|---------|-------|-------|------|')
-
-    # Print individual file results
-    for task_name, total, result, score, is_perfect, task_nature in detailed_results:
-        perfect_marker = ' ⭐' if is_perfect else ''
-        print(
-            f'| {task_name} | {total:,} | {result:,} | {score:.2f}{perfect_marker} | {traj_results[task_name][0]} | {traj_results[task_name][1]:.2f} |'
-        )
-
-    # Print summary section
-    print('\n## Summary\n')
-    print(f'**Tasks Evaluated:** {len(eval_results)}\n')
-    print(
-        f'**Perfect Completions:** {perfect_completions}/{len(eval_results)} ({(perfect_completions/len(eval_results)*100):.2f}%)\n'
-    )
-
-    overall_score = (
-        sum(score for _, _, _, score, _, _ in detailed_results)
-        / len(detailed_results)
-        * 100
-    )
-    avg_steps = sum(steps for steps, _ in traj_results.values()) / len(traj_results)
-    avg_cost = sum(cost for _, cost in traj_results.values()) / len(traj_results)
-    print(f'**Overall Score:** {overall_score:.2f}%\n')
-    print(f'**Average Steps:** {avg_steps:.2f}\n')
-    print(f'**Average Cost (USD):** {avg_cost:.2f}\n')
-
-    # Additional statistics
-    if detailed_results:
-        highest_score = max(score for _, _, _, score, _, _ in detailed_results)
-        lowest_score = min(score for _, _, _, score, _, _ in detailed_results)
-        median_score = detailed_results[len(detailed_results) // 2][3]
-        avg_score = sum(score for _, _, _, score, _, _ in detailed_results) / len(
-            detailed_results
-        )
-
-        print('\n## Statistics\n')
-        print('| Metric | Value |')
-        print('|---------|--------|')
-        print(f'| Highest Task Score | {highest_score*100:.2f}% |')
-        print(f'| Lowest Task Score | {lowest_score*100:.2f}% |')
-        print(f'| Median Task Score | {median_score*100:.2f}% |')
-        print(f'| Average Task Score | {avg_score*100:.2f}% |')
-
-        # compute avg score per nature category
-        print('\n## Statistics per Nature Category\n')
-        print('| Metric | Value |')
-        print('|---------|--------|')
-        for task_nature in ['sde', 'pm', 'ds', 'admin', 'hr', 'finance', 'other']:
-            num_of_tasks = sum(
-                1
-                for _, _, _, _, _, nature_category in detailed_results
-                if nature_category == task_nature
-            )
-            task_nature_score = (
-                sum(
-                    score
-                    for _, _, _, score, _, nature_category in detailed_results
-                    if nature_category == task_nature
-                )
-                / num_of_tasks
-            )
-            perfect_completions = sum(
-                1
-                for _, _, _, _, is_perfect, nature_category in detailed_results
-                if nature_category == task_nature and is_perfect
-            )
-            print(
-                f'| Perfect Completions for {task_nature} | {perfect_completions}/{num_of_tasks} ({perfect_completions/num_of_tasks*100:.2f}%) |'
-            )
-            print(f'| Average Score for {task_nature} | {task_nature_score*100:.2f}% |')
-
-
-if __name__ == '__main__':
-    main()

evaluation/benchmarks/toolqa/run_infer.py

@@ -44,7 +44,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='docker',
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='python:3.12-bookworm',
@@ -56,8 +56,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     return config
 
 

evaluation/benchmarks/webarena/run_infer.py

@@ -53,7 +53,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='docker',
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='python:3.12-bookworm',
@@ -77,8 +77,6 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
     return config
 
 

evaluation/integration_tests/run_infer.py

@@ -42,7 +42,7 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'docker'),
+        runtime=os.environ.get('RUNTIME', 'eventstream'),
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             # use default base_container_image

evaluation/utils/shared.py

@@ -376,12 +376,7 @@ def _process_instance_wrapper(
                 + '\n'
             )
             if isinstance(
-                e,
-                (
-                    AgentRuntimeDisconnectedError,
-                    AgentRuntimeUnavailableError,
-                    AgentRuntimeNotFoundError,
-                ),
+                e, (AgentRuntimeDisconnectedError, AgentRuntimeUnavailableError)
             ):
                 runtime_failure_count += 1
                 msg += f'Runtime disconnected error detected for instance {instance.instance_id}, runtime failure count: {runtime_failure_count}'

frontend/.eslintrc

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

frontend/__tests__/api/github.test.ts

@@ -1,47 +0,0 @@
-import { describe, expect, it, vi } from "vitest";
-import { retrieveLatestGitHubCommit } from "../../src/api/github";
-
-describe("retrieveLatestGitHubCommit", () => {
-  const { githubGetMock } = vi.hoisted(() => ({
-    githubGetMock: vi.fn(),
-  }));
-
-  vi.mock("../../src/api/github-axios-instance", () => ({
-    github: {
-      get: githubGetMock,
-    },
-  }));
-
-  it("should return the latest commit when repository has commits", async () => {
-    const mockCommit = {
-      sha: "123abc",
-      commit: {
-        message: "Initial commit",
-      },
-    };
-
-    githubGetMock.mockResolvedValueOnce({
-      data: [mockCommit],
-    });
-
-    const result = await retrieveLatestGitHubCommit("user/repo");
-    expect(result).toEqual(mockCommit);
-  });
-
-  it("should return null when repository is empty", async () => {
-    const error = new Error("Repository is empty");
-    (error as any).response = { status: 409 };
-    githubGetMock.mockRejectedValueOnce(error);
-
-    const result = await retrieveLatestGitHubCommit("user/empty-repo");
-    expect(result).toBeNull();
-  });
-
-  it("should throw error for other error cases", async () => {
-    const error = new Error("Network error");
-    (error as any).response = { status: 500 };
-    githubGetMock.mockRejectedValueOnce(error);
-
-    await expect(retrieveLatestGitHubCommit("user/repo")).rejects.toThrow();
-  });
-});

frontend/__tests__/components/context-menu/account-settings-context-menu.test.tsx

@@ -28,8 +28,8 @@ describe("AccountSettingsContextMenu", () => {
     expect(
       screen.getByTestId("account-settings-context-menu"),
     ).toBeInTheDocument();
-    expect(screen.getByText("ACCOUNT_SETTINGS$SETTINGS")).toBeInTheDocument();
-    expect(screen.getByText("ACCOUNT_SETTINGS$LOGOUT")).toBeInTheDocument();
+    expect(screen.getByText("Account Settings")).toBeInTheDocument();
+    expect(screen.getByText("Logout")).toBeInTheDocument();
   });
 
   it("should call onClickAccountSettings when the account settings option is clicked", async () => {
@@ -42,7 +42,7 @@ describe("AccountSettingsContextMenu", () => {
       />,
     );
 
-    const accountSettingsOption = screen.getByText("ACCOUNT_SETTINGS$SETTINGS");
+    const accountSettingsOption = screen.getByText("Account Settings");
     await user.click(accountSettingsOption);
 
     expect(onClickAccountSettingsMock).toHaveBeenCalledOnce();
@@ -58,7 +58,7 @@ describe("AccountSettingsContextMenu", () => {
       />,
     );
 
-    const logoutOption = screen.getByText("ACCOUNT_SETTINGS$LOGOUT");
+    const logoutOption = screen.getByText("Logout");
     await user.click(logoutOption);
 
     expect(onLogoutMock).toHaveBeenCalledOnce();
@@ -74,7 +74,7 @@ describe("AccountSettingsContextMenu", () => {
       />,
     );
 
-    const logoutOption = screen.getByText("ACCOUNT_SETTINGS$LOGOUT");
+    const logoutOption = screen.getByText("Logout");
     await user.click(logoutOption);
 
     expect(onLogoutMock).not.toHaveBeenCalled();
@@ -90,7 +90,7 @@ describe("AccountSettingsContextMenu", () => {
       />,
     );
 
-    const accountSettingsButton = screen.getByText("ACCOUNT_SETTINGS$SETTINGS");
+    const accountSettingsButton = screen.getByText("Account Settings");
     await user.click(accountSettingsButton);
     await user.click(document.body);
 

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

@@ -1,274 +0,0 @@
-import { render, screen, within } from "@testing-library/react";
-import { afterEach, describe, expect, it, test, vi } from "vitest";
-import userEvent from "@testing-library/user-event";
-import { formatTimeDelta } from "#/utils/format-time-delta";
-import { ConversationCard } from "#/components/features/conversation-panel/conversation-card";
-
-describe("ConversationCard", () => {
-  const onClick = vi.fn();
-  const onDelete = vi.fn();
-  const onChangeTitle = vi.fn();
-
-  afterEach(() => {
-    vi.clearAllMocks();
-  });
-
-  it("should render the conversation card", () => {
-    render(
-      <ConversationCard
-        onDelete={onDelete}
-        onClick={onClick}
-        onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
-      />,
-    );
-    const expectedDate = `${formatTimeDelta(new Date("2021-10-01T12:00:00Z"))} ago`;
-
-    const card = screen.getByTestId("conversation-card");
-    const title = within(card).getByTestId("conversation-card-title");
-
-    expect(title).toHaveValue("Conversation 1");
-    within(card).getByText(expectedDate);
-  });
-
-  it("should render the repo if available", () => {
-    const { rerender } = render(
-      <ConversationCard
-        onDelete={onDelete}
-        onClick={onClick}
-        onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
-      />,
-    );
-
-    expect(
-      screen.queryByTestId("conversation-card-repo"),
-    ).not.toBeInTheDocument();
-
-    rerender(
-      <ConversationCard
-        onDelete={onDelete}
-        onClick={onClick}
-        onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo="org/repo"
-        lastUpdated="2021-10-01T12:00:00Z"
-      />,
-    );
-
-    screen.getByTestId("conversation-card-repo");
-  });
-
-  it("should call onClick when the card is clicked", async () => {
-    const user = userEvent.setup();
-    render(
-      <ConversationCard
-        onDelete={onDelete}
-        onClick={onClick}
-        onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
-      />,
-    );
-
-    const card = screen.getByTestId("conversation-card");
-    await user.click(card);
-
-    expect(onClick).toHaveBeenCalled();
-  });
-
-  it("should toggle a context menu when clicking the ellipsis button", async () => {
-    const user = userEvent.setup();
-    render(
-      <ConversationCard
-        onDelete={onDelete}
-        onClick={onClick}
-        onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
-      />,
-    );
-
-    expect(screen.queryByTestId("context-menu")).not.toBeInTheDocument();
-
-    const ellipsisButton = screen.getByTestId("ellipsis-button");
-    await user.click(ellipsisButton);
-
-    screen.getByTestId("context-menu");
-
-    await user.click(ellipsisButton);
-
-    expect(screen.queryByTestId("context-menu")).not.toBeInTheDocument();
-  });
-
-  it("should call onDelete when the delete button is clicked", async () => {
-    const user = userEvent.setup();
-    render(
-      <ConversationCard
-        onClick={onClick}
-        onDelete={onDelete}
-        onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
-      />,
-    );
-
-    const ellipsisButton = screen.getByTestId("ellipsis-button");
-    await user.click(ellipsisButton);
-
-    const menu = screen.getByTestId("context-menu");
-    const deleteButton = within(menu).getByTestId("delete-button");
-
-    await user.click(deleteButton);
-
-    expect(onDelete).toHaveBeenCalled();
-  });
-
-  test("clicking the repo should not trigger the onClick handler", async () => {
-    const user = userEvent.setup();
-    render(
-      <ConversationCard
-        onClick={onClick}
-        onDelete={onDelete}
-        onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo="org/repo"
-        lastUpdated="2021-10-01T12:00:00Z"
-      />,
-    );
-
-    const repo = screen.getByTestId("conversation-card-repo");
-    await user.click(repo);
-
-    expect(onClick).not.toHaveBeenCalled();
-  });
-
-  test("conversation title should call onChangeTitle when changed and blurred", async () => {
-    const user = userEvent.setup();
-    render(
-      <ConversationCard
-        onClick={onClick}
-        onDelete={onDelete}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
-        onChangeTitle={onChangeTitle}
-      />,
-    );
-
-    const title = screen.getByTestId("conversation-card-title");
-
-    await user.clear(title);
-    await user.type(title, "New Conversation Name   ");
-    await user.tab();
-
-    expect(onChangeTitle).toHaveBeenCalledWith("New Conversation Name");
-    expect(title).toHaveValue("New Conversation Name");
-  });
-
-  it("should reset title and not call onChangeTitle when the title is empty", async () => {
-    const user = userEvent.setup();
-    render(
-      <ConversationCard
-        onClick={onClick}
-        onDelete={onDelete}
-        onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
-      />,
-    );
-
-    const title = screen.getByTestId("conversation-card-title");
-
-    await user.clear(title);
-    await user.tab();
-
-    expect(onChangeTitle).not.toHaveBeenCalled();
-    expect(title).toHaveValue("Conversation 1");
-  });
-
-  test("clicking the title should not trigger the onClick handler", async () => {
-    const user = userEvent.setup();
-    render(
-      <ConversationCard
-        onClick={onClick}
-        onDelete={onDelete}
-        onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
-      />,
-    );
-
-    const title = screen.getByTestId("conversation-card-title");
-    await user.click(title);
-
-    expect(onClick).not.toHaveBeenCalled();
-  });
-
-  test("clicking the delete button should not trigger the onClick handler", async () => {
-    const user = userEvent.setup();
-    render(
-      <ConversationCard
-        onClick={onClick}
-        onDelete={onDelete}
-        onChangeTitle={onChangeTitle}
-        name="Conversation 1"
-        repo={null}
-        lastUpdated="2021-10-01T12:00:00Z"
-      />,
-    );
-
-    const ellipsisButton = screen.getByTestId("ellipsis-button");
-    await user.click(ellipsisButton);
-
-    const menu = screen.getByTestId("context-menu");
-    const deleteButton = within(menu).getByTestId("delete-button");
-
-    await user.click(deleteButton);
-
-    expect(onClick).not.toHaveBeenCalled();
-  });
-
-  describe("state indicator", () => {
-    it("should render the 'cold' indicator by default", () => {
-      render(
-        <ConversationCard
-          onClick={onClick}
-          onDelete={onDelete}
-          onChangeTitle={onChangeTitle}
-          name="Conversation 1"
-          repo={null}
-          lastUpdated="2021-10-01T12:00:00Z"
-        />,
-      );
-
-      screen.getByTestId("cold-indicator");
-    });
-
-    it("should render the other indicators when provided", () => {
-      render(
-        <ConversationCard
-          onClick={onClick}
-          onDelete={onDelete}
-          onChangeTitle={onChangeTitle}
-          name="Conversation 1"
-          repo={null}
-          lastUpdated="2021-10-01T12:00:00Z"
-          state="warm"
-        />,
-      );
-
-      expect(screen.queryByTestId("cold-indicator")).not.toBeInTheDocument();
-      screen.getByTestId("warm-indicator");
-    });
-  });
-});

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

@@ -1,267 +0,0 @@
-import { render, screen, within } from "@testing-library/react";
-import { beforeAll, beforeEach, describe, expect, it, vi } from "vitest";
-import {
-  QueryClientProvider,
-  QueryClient,
-  QueryClientConfig,
-} from "@tanstack/react-query";
-import userEvent from "@testing-library/user-event";
-import { ConversationPanel } from "#/components/features/conversation-panel/conversation-panel";
-import OpenHands from "#/api/open-hands";
-import { AuthProvider } from "#/context/auth-context";
-
-describe("ConversationPanel", () => {
-  const onCloseMock = vi.fn();
-
-  const renderConversationPanel = (config?: QueryClientConfig) =>
-    render(<ConversationPanel onClose={onCloseMock} />, {
-      wrapper: ({ children }) => (
-        <AuthProvider>
-          <QueryClientProvider client={new QueryClient(config)}>
-            {children}
-          </QueryClientProvider>
-        </AuthProvider>
-      ),
-    });
-
-  const { endSessionMock } = vi.hoisted(() => ({
-    endSessionMock: vi.fn(),
-  }));
-
-  beforeAll(() => {
-    vi.mock("react-router", async (importOriginal) => ({
-      ...(await importOriginal<typeof import("react-router")>()),
-      Link: ({ children }: React.PropsWithChildren) => children,
-      useNavigate: vi.fn(() => vi.fn()),
-      useLocation: vi.fn(() => ({ pathname: "/conversation" })),
-      useParams: vi.fn(() => ({ conversationId: "2" })),
-    }));
-
-    vi.mock("#/hooks/use-end-session", async (importOriginal) => ({
-      ...(await importOriginal<typeof import("#/hooks/use-end-session")>()),
-      useEndSession: vi.fn(() => endSessionMock),
-    }));
-  });
-
-  beforeEach(() => {
-    vi.clearAllMocks();
-    vi.restoreAllMocks();
-  });
-
-  it("should render the conversations", async () => {
-    renderConversationPanel();
-    const cards = await screen.findAllByTestId("conversation-card");
-
-    expect(cards).toHaveLength(3);
-  });
-
-  it("should display an empty state when there are no conversations", async () => {
-    const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
-    getUserConversationsSpy.mockResolvedValue([]);
-
-    renderConversationPanel();
-
-    const emptyState = await screen.findByText("No conversations found");
-    expect(emptyState).toBeInTheDocument();
-  });
-
-  it("should handle an error when fetching conversations", async () => {
-    const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
-    getUserConversationsSpy.mockRejectedValue(
-      new Error("Failed to fetch conversations"),
-    );
-
-    renderConversationPanel({
-      defaultOptions: {
-        queries: {
-          retry: false,
-        },
-      },
-    });
-
-    const error = await screen.findByText("Failed to fetch conversations");
-    expect(error).toBeInTheDocument();
-  });
-
-  it("should cancel deleting a conversation", async () => {
-    const user = userEvent.setup();
-    renderConversationPanel();
-
-    let cards = await screen.findAllByTestId("conversation-card");
-    expect(
-      within(cards[0]).queryByTestId("delete-button"),
-    ).not.toBeInTheDocument();
-
-    const ellipsisButton = within(cards[0]).getByTestId("ellipsis-button");
-    await user.click(ellipsisButton);
-    const deleteButton = screen.getByTestId("delete-button");
-
-    // Click the first delete button
-    await user.click(deleteButton);
-
-    // Cancel the deletion
-    const cancelButton = screen.getByText("Cancel");
-    await user.click(cancelButton);
-
-    expect(screen.queryByText("Cancel")).not.toBeInTheDocument();
-
-    // Ensure the conversation is not deleted
-    cards = await screen.findAllByTestId("conversation-card");
-    expect(cards).toHaveLength(3);
-  });
-
-  it("should call endSession after deleting a conversation that is the current session", async () => {
-    const user = userEvent.setup();
-    renderConversationPanel();
-
-    let cards = await screen.findAllByTestId("conversation-card");
-    const ellipsisButton = within(cards[1]).getByTestId("ellipsis-button");
-    await user.click(ellipsisButton);
-    const deleteButton = screen.getByTestId("delete-button");
-
-    // Click the second delete button
-    await user.click(deleteButton);
-
-    // Confirm the deletion
-    const confirmButton = screen.getByText("Confirm");
-    await user.click(confirmButton);
-
-    expect(screen.queryByText("Confirm")).not.toBeInTheDocument();
-
-    // Ensure the conversation is deleted
-    cards = await screen.findAllByTestId("conversation-card");
-    expect(cards).toHaveLength(2);
-
-    expect(endSessionMock).toHaveBeenCalledOnce();
-  });
-
-  it("should delete a conversation", async () => {
-    const user = userEvent.setup();
-    renderConversationPanel();
-
-    let cards = await screen.findAllByTestId("conversation-card");
-    const ellipsisButton = within(cards[0]).getByTestId("ellipsis-button");
-    await user.click(ellipsisButton);
-    const deleteButton = screen.getByTestId("delete-button");
-
-    // Click the first delete button
-    await user.click(deleteButton);
-
-    // Confirm the deletion
-    const confirmButton = screen.getByText("Confirm");
-    await user.click(confirmButton);
-
-    expect(screen.queryByText("Confirm")).not.toBeInTheDocument();
-
-    // Ensure the conversation is deleted
-    cards = await screen.findAllByTestId("conversation-card");
-    expect(cards).toHaveLength(1);
-  });
-
-  it("should rename a conversation", async () => {
-    const updateUserConversationSpy = vi.spyOn(
-      OpenHands,
-      "updateUserConversation",
-    );
-
-    const user = userEvent.setup();
-    renderConversationPanel();
-    const cards = await screen.findAllByTestId("conversation-card");
-    const title = within(cards[0]).getByTestId("conversation-card-title");
-
-    await user.clear(title);
-    await user.type(title, "Conversation 1 Renamed");
-    await user.tab();
-
-    // Ensure the conversation is renamed
-    expect(updateUserConversationSpy).toHaveBeenCalledWith("3", {
-      name: "Conversation 1 Renamed",
-    });
-  });
-
-  it("should not rename a conversation when the name is unchanged", async () => {
-    const updateUserConversationSpy = vi.spyOn(
-      OpenHands,
-      "updateUserConversation",
-    );
-
-    const user = userEvent.setup();
-    renderConversationPanel();
-    const cards = await screen.findAllByTestId("conversation-card");
-    const title = within(cards[0]).getByTestId("conversation-card-title");
-
-    await user.click(title);
-    await user.tab();
-
-    // Ensure the conversation is not renamed
-    expect(updateUserConversationSpy).not.toHaveBeenCalled();
-
-    await user.type(title, "Conversation 1");
-    await user.click(title);
-    await user.tab();
-
-    expect(updateUserConversationSpy).toHaveBeenCalledTimes(1);
-
-    await user.click(title);
-    await user.tab();
-
-    expect(updateUserConversationSpy).toHaveBeenCalledTimes(1);
-  });
-
-  it("should call onClose after clicking a card", async () => {
-    renderConversationPanel();
-    const cards = await screen.findAllByTestId("conversation-card");
-    const firstCard = cards[0];
-
-    await userEvent.click(firstCard);
-
-    expect(onCloseMock).toHaveBeenCalledOnce();
-  });
-
-  describe("New Conversation Button", () => {
-    it("should display a confirmation modal when clicking", async () => {
-      const user = userEvent.setup();
-      renderConversationPanel();
-
-      expect(
-        screen.queryByTestId("confirm-new-conversation-modal"),
-      ).not.toBeInTheDocument();
-
-      const newProjectButton = screen.getByTestId("new-conversation-button");
-      await user.click(newProjectButton);
-
-      const modal = screen.getByTestId("confirm-new-conversation-modal");
-      expect(modal).toBeInTheDocument();
-    });
-
-    it("should call endSession and close panel after confirming", async () => {
-      const user = userEvent.setup();
-      renderConversationPanel();
-
-      const newProjectButton = screen.getByTestId("new-conversation-button");
-      await user.click(newProjectButton);
-
-      const confirmButton = screen.getByText("Confirm");
-      await user.click(confirmButton);
-
-      expect(endSessionMock).toHaveBeenCalledOnce();
-      expect(onCloseMock).toHaveBeenCalledOnce();
-    });
-
-    it("should close the modal when cancelling", async () => {
-      const user = userEvent.setup();
-      renderConversationPanel();
-
-      const newProjectButton = screen.getByTestId("new-conversation-button");
-      await user.click(newProjectButton);
-
-      const cancelButton = screen.getByText("Cancel");
-      await user.click(cancelButton);
-
-      expect(endSessionMock).not.toHaveBeenCalled();
-      expect(
-        screen.queryByTestId("confirm-new-conversation-modal"),
-      ).not.toBeInTheDocument();
-    });
-  });
-});

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

@@ -1,76 +0,0 @@
-import { screen } from "@testing-library/react";
-import { describe, expect, it, vi } from "vitest";
-import { renderWithProviders } from "test-utils";
-import { GitHubRepositorySelector } from "#/components/features/github/github-repo-selector";
-import OpenHands from "#/api/open-hands";
-import * as GitHubAPI from "#/api/github";
-
-describe("GitHubRepositorySelector", () => {
-  const onInputChangeMock = vi.fn();
-  const onSelectMock = vi.fn();
-
-  it("should render the search input", () => {
-    renderWithProviders(
-      <GitHubRepositorySelector
-        onInputChange={onInputChangeMock}
-        onSelect={onSelectMock}
-        repositories={[]}
-      />,
-    );
-
-    expect(
-      screen.getByPlaceholderText("Select a GitHub project"),
-    ).toBeInTheDocument();
-  });
-
-  it("should show the GitHub login button in OSS mode", () => {
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    getConfigSpy.mockResolvedValue({
-      APP_MODE: "oss",
-      APP_SLUG: "openhands",
-      GITHUB_CLIENT_ID: "test-client-id",
-      POSTHOG_CLIENT_KEY: "test-posthog-key",
-    });
-
-    renderWithProviders(
-      <GitHubRepositorySelector
-        onInputChange={onInputChangeMock}
-        onSelect={onSelectMock}
-        repositories={[]}
-      />,
-    );
-
-    expect(screen.getByTestId("github-repo-selector")).toBeInTheDocument();
-  });
-
-  it("should show the search results", () => {
-    const mockSearchedRepos = [
-      {
-        id: 1,
-        full_name: "test/repo1",
-        stargazers_count: 100,
-      },
-      {
-        id: 2,
-        full_name: "test/repo2",
-        stargazers_count: 200,
-      },
-    ];
-
-    const searchPublicRepositoriesSpy = vi.spyOn(
-      GitHubAPI,
-      "searchPublicRepositories",
-    );
-    searchPublicRepositoriesSpy.mockResolvedValue(mockSearchedRepos);
-
-    renderWithProviders(
-      <GitHubRepositorySelector
-        onInputChange={onInputChangeMock}
-        onSelect={onSelectMock}
-        repositories={[]}
-      />,
-    );
-
-    expect(screen.getByTestId("github-repo-selector")).toBeInTheDocument();
-  });
-});

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

@@ -1,46 +0,0 @@
-import { screen } from "@testing-library/react";
-import userEvent from "@testing-library/user-event";
-import { describe, expect, it } from "vitest";
-import { renderWithProviders } from "test-utils";
-import { createRoutesStub } from "react-router";
-import { Sidebar } from "#/components/features/sidebar/sidebar";
-import { MULTI_CONVO_UI_IS_ENABLED } from "#/utils/constants";
-
-const renderSidebar = () => {
-  const RouterStub = createRoutesStub([
-    {
-      path: "/conversation/:conversationId",
-      Component: Sidebar,
-    },
-  ]);
-
-  renderWithProviders(<RouterStub initialEntries={["/conversation/123"]} />);
-};
-
-describe("Sidebar", () => {
-  it.skipIf(!MULTI_CONVO_UI_IS_ENABLED)(
-    "should have the conversation panel open by default",
-    () => {
-      renderSidebar();
-      expect(screen.getByTestId("conversation-panel")).toBeInTheDocument();
-    },
-  );
-
-  it.skipIf(!MULTI_CONVO_UI_IS_ENABLED)(
-    "should toggle the conversation panel",
-    async () => {
-      const user = userEvent.setup();
-      renderSidebar();
-
-      const projectPanelButton = screen.getByTestId(
-        "toggle-conversation-panel",
-      );
-
-      await user.click(projectPanelButton);
-
-      expect(
-        screen.queryByTestId("conversation-panel"),
-      ).not.toBeInTheDocument();
-    },
-  );
-});

frontend/__tests__/components/modals/base-modal/base-modal.test.tsx

@@ -52,10 +52,14 @@ describe("BaseModal", () => {
     expect(screen.getByText("Save")).toBeInTheDocument();
     expect(screen.getByText("Cancel")).toBeInTheDocument();
 
-    await userEvent.click(screen.getByText("Save"));
+    await act(async () => {
+      await userEvent.click(screen.getByText("Save"));
+    });
     expect(onPrimaryClickMock).toHaveBeenCalledTimes(1);
 
-    await userEvent.click(screen.getByText("Cancel"));
+    await act(async () => {
+      await userEvent.click(screen.getByText("Cancel"));
+    });
     expect(onSecondaryClickMock).toHaveBeenCalledTimes(1);
   });
 
@@ -76,7 +80,9 @@ describe("BaseModal", () => {
       />,
     );
 
-    await userEvent.click(screen.getByText("Save"));
+    await act(async () => {
+      await userEvent.click(screen.getByText("Save"));
+    });
     expect(onOpenChangeMock).toHaveBeenCalledTimes(1);
   });
 

frontend/__tests__/components/user-actions.test.tsx

@@ -58,7 +58,7 @@ describe("UserActions", () => {
     const userAvatar = screen.getByTestId("user-avatar");
     await user.click(userAvatar);
 
-    const accountSettingsOption = screen.getByText("ACCOUNT_SETTINGS$SETTINGS");
+    const accountSettingsOption = screen.getByText("Account Settings");
     await user.click(accountSettingsOption);
 
     expect(onClickAccountSettingsMock).toHaveBeenCalledOnce();
@@ -79,7 +79,7 @@ describe("UserActions", () => {
     const userAvatar = screen.getByTestId("user-avatar");
     await user.click(userAvatar);
 
-    const logoutOption = screen.getByText("ACCOUNT_SETTINGS$LOGOUT");
+    const logoutOption = screen.getByText("Logout");
     await user.click(logoutOption);
 
     expect(onLogoutMock).toHaveBeenCalledOnce();
@@ -99,7 +99,7 @@ describe("UserActions", () => {
     const userAvatar = screen.getByTestId("user-avatar");
     await user.click(userAvatar);
 
-    const logoutOption = screen.getByText("ACCOUNT_SETTINGS$LOGOUT");
+    const logoutOption = screen.getByText("Logout");
     await user.click(logoutOption);
 
     expect(onLogoutMock).not.toHaveBeenCalled();

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

@@ -1,83 +0,0 @@
-import { createRoutesStub } from "react-router";
-import { afterEach, beforeAll, describe, expect, it, vi } from "vitest";
-import { renderWithProviders } from "test-utils";
-import { screen, waitFor } from "@testing-library/react";
-import toast from "react-hot-toast";
-import App from "#/routes/_oh.app/route";
-import OpenHands from "#/api/open-hands";
-import { MULTI_CONVO_UI_IS_ENABLED } from "#/utils/constants";
-
-describe("App", () => {
-  const RouteStub = createRoutesStub([
-    { Component: App, path: "/conversation/:conversationId" },
-  ]);
-
-  const { endSessionMock } = vi.hoisted(() => ({
-    endSessionMock: vi.fn(),
-  }));
-
-  beforeAll(() => {
-    vi.mock("#/hooks/use-end-session", () => ({
-      useEndSession: vi.fn(() => endSessionMock),
-    }));
-
-    vi.mock("#/hooks/use-terminal", () => ({
-      useTerminal: vi.fn(),
-    }));
-  });
-
-  afterEach(() => {
-    vi.clearAllMocks();
-  });
-
-  it("should render", async () => {
-    renderWithProviders(<RouteStub initialEntries={["/conversation/123"]} />);
-    await screen.findByTestId("app-route");
-  });
-
-  it.skipIf(!MULTI_CONVO_UI_IS_ENABLED)(
-    "should call endSession if the user does not have permission to view conversation",
-    async () => {
-      const errorToastSpy = vi.spyOn(toast, "error");
-      const getConversationSpy = vi.spyOn(OpenHands, "getConversation");
-
-      getConversationSpy.mockResolvedValue(null);
-      renderWithProviders(
-        <RouteStub initialEntries={["/conversation/9999"]} />,
-      );
-
-      await waitFor(() => {
-        expect(endSessionMock).toHaveBeenCalledOnce();
-        expect(errorToastSpy).toHaveBeenCalledOnce();
-      });
-    },
-  );
-
-  it("should not call endSession if the user has permission", async () => {
-    const errorToastSpy = vi.spyOn(toast, "error");
-    const getConversationSpy = vi.spyOn(OpenHands, "getConversation");
-
-    getConversationSpy.mockResolvedValue({
-      conversation_id: "9999",
-      lastUpdated: "",
-      name: "",
-      repo: "",
-      state: "cold",
-    });
-    const { rerender } = renderWithProviders(
-      <RouteStub initialEntries={["/conversation/9999"]} />,
-    );
-
-    await waitFor(() => {
-      expect(endSessionMock).not.toHaveBeenCalled();
-      expect(errorToastSpy).not.toHaveBeenCalled();
-    });
-
-    rerender(<RouteStub initialEntries={["/conversation"]} />);
-
-    await waitFor(() => {
-      expect(endSessionMock).not.toHaveBeenCalled();
-      expect(errorToastSpy).not.toHaveBeenCalled();
-    });
-  });
-});

frontend/package-lock.json

@@ -1,20 +1,20 @@
 {
   "name": "openhands-frontend",
-  "version": "0.18.0",
+  "version": "0.17.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "openhands-frontend",
-      "version": "0.18.0",
+      "version": "0.17.0",
       "dependencies": {
-        "@monaco-editor/react": "^4.7.0-rc.0",
+        "@monaco-editor/react": "^4.6.0",
         "@nextui-org/react": "^2.6.10",
         "@react-router/node": "^7.1.1",
         "@react-router/serve": "^7.1.1",
         "@react-types/shared": "^3.25.0",
         "@reduxjs/toolkit": "^2.5.0",
-        "@tanstack/react-query": "^5.62.12",
+        "@tanstack/react-query": "^5.62.10",
         "@vitejs/plugin-react": "^4.3.2",
         "@xterm/addon-fit": "^0.10.0",
         "@xterm/xterm": "^5.4.0",
@@ -27,12 +27,12 @@
         "isbot": "^5.1.19",
         "jose": "^5.9.4",
         "monaco-editor": "^0.52.2",
-        "posthog-js": "^1.203.3",
-        "react": "^19.0.0",
-        "react-dom": "^19.0.0",
+        "posthog-js": "^1.203.1",
+        "react": "^18.3.1",
+        "react-dom": "^18.3.1",
         "react-highlight": "^0.15.0",
-        "react-hot-toast": "^2.5.1",
-        "react-i18next": "^15.4.0",
+        "react-hot-toast": "^2.4.1",
+        "react-i18next": "^15.2.0",
         "react-icons": "^5.4.0",
         "react-markdown": "^9.0.1",
         "react-redux": "^9.2.0",
@@ -43,12 +43,11 @@
         "sirv-cli": "^3.0.0",
         "socket.io-client": "^4.8.1",
         "tailwind-merge": "^2.6.0",
-        "vite": "^5.4.11",
+        "vite": "^5.4.9",
         "web-vitals": "^3.5.2",
         "ws": "^8.18.0"
       },
       "devDependencies": {
-        "@mswjs/socket.io-binding": "^0.1.1",
         "@playwright/test": "^1.49.1",
         "@react-router/dev": "^7.1.1",
         "@tailwindcss/typography": "^0.5.15",
@@ -56,9 +55,9 @@
         "@testing-library/jest-dom": "^6.6.1",
         "@testing-library/react": "^16.1.0",
         "@testing-library/user-event": "^14.5.2",
-        "@types/node": "^22.10.5",
-        "@types/react": "^19.0.2",
-        "@types/react-dom": "^19.0.2",
+        "@types/node": "^22.10.2",
+        "@types/react": "^18.3.11",
+        "@types/react-dom": "^18.3.0",
         "@types/react-highlight": "^0.12.8",
         "@types/react-syntax-highlighter": "^15.5.13",
         "@types/ws": "^8.5.12",
@@ -78,12 +77,12 @@
         "eslint-plugin-react-hooks": "^4.6.2",
         "husky": "^9.1.6",
         "jsdom": "^25.0.1",
-        "lint-staged": "^15.3.0",
+        "lint-staged": "^15.2.11",
         "msw": "^2.6.6",
         "postcss": "^8.4.47",
         "prettier": "^3.4.2",
         "tailwindcss": "^3.4.17",
-        "typescript": "^5.7.2",
+        "typescript": "^5.6.3",
         "vite-plugin-svgr": "^4.2.0",
         "vite-tsconfig-paths": "^5.1.4",
         "vitest": "^1.6.0"
@@ -1596,17 +1595,17 @@
       }
     },
     "node_modules/@monaco-editor/react": {
-      "version": "4.7.0-rc.0",
-      "resolved": "https://registry.npmjs.org/@monaco-editor/react/-/react-4.7.0-rc.0.tgz",
-      "integrity": "sha512-YfjXkDK0bcwS0zo8PXptvQdCQfOPPtzGsAzmIv7PnoUGFdIohsR+NVDyjbajMddF+3cWUm/3q9NzP/DUke9a+w==",
+      "version": "4.6.0",
+      "resolved": "https://registry.npmjs.org/@monaco-editor/react/-/react-4.6.0.tgz",
+      "integrity": "sha512-RFkU9/i7cN2bsq/iTkurMWOEErmYcY6JiQI3Jn+WeR/FGISH8JbHERjpS9oRuSOPvDMJI0Z8nJeKkbOs9sBYQw==",
       "license": "MIT",
       "dependencies": {
         "@monaco-editor/loader": "^1.4.0"
       },
       "peerDependencies": {
         "monaco-editor": ">= 0.25.0 < 1",
-        "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0",
-        "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0"
+        "react": "^16.8.0 || ^17.0.0 || ^18.0.0",
+        "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0"
       }
     },
     "node_modules/@mswjs/interceptors": {
@@ -1627,21 +1626,6 @@
         "node": ">=18"
       }
     },
-    "node_modules/@mswjs/socket.io-binding": {
-      "version": "0.1.1",
-      "resolved": "https://registry.npmjs.org/@mswjs/socket.io-binding/-/socket.io-binding-0.1.1.tgz",
-      "integrity": "sha512-mtFDHC5XMeti43toe3HBynD4uBxvUA2GfJVC6TDfhOQlH+G2hf5znNTSa75A30XdWL0P6aNqUKpcNo6L0Wop+A==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "@mswjs/interceptors": "^0.37.1",
-        "engine.io-parser": "^5.2.3",
-        "socket.io-parser": "^4.2.4"
-      },
-      "peerDependencies": {
-        "@mswjs/interceptors": "*"
-      }
-    },
     "node_modules/@nextui-org/accordion": {
       "version": "2.2.6",
       "resolved": "https://registry.npmjs.org/@nextui-org/accordion/-/accordion-2.2.6.tgz",
@@ -2257,23 +2241,6 @@
         "react-dom": ">=18 || >=19.0.0-rc.0"
       }
     },
-    "node_modules/@nextui-org/listbox/node_modules/@tanstack/react-virtual": {
-      "version": "3.10.9",
-      "resolved": "https://registry.npmjs.org/@tanstack/react-virtual/-/react-virtual-3.10.9.tgz",
-      "integrity": "sha512-OXO2uBjFqA4Ibr2O3y0YMnkrRWGVNqcvHQXmGvMu6IK8chZl3PrDxFXdGZ2iZkSrKh3/qUYoFqYe+Rx23RoU0g==",
-      "license": "MIT",
-      "dependencies": {
-        "@tanstack/virtual-core": "3.10.9"
-      },
-      "funding": {
-        "type": "github",
-        "url": "https://github.com/sponsors/tannerlinsley"
-      },
-      "peerDependencies": {
-        "react": "^16.8.0 || ^17.0.0 || ^18.0.0",
-        "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0"
-      }
-    },
     "node_modules/@nextui-org/menu": {
       "version": "2.2.8",
       "resolved": "https://registry.npmjs.org/@nextui-org/menu/-/menu-2.2.8.tgz",
@@ -2612,23 +2579,6 @@
         "react-dom": ">=18 || >=19.0.0-rc.0"
       }
     },
-    "node_modules/@nextui-org/select/node_modules/@tanstack/react-virtual": {
-      "version": "3.10.9",
-      "resolved": "https://registry.npmjs.org/@tanstack/react-virtual/-/react-virtual-3.10.9.tgz",
-      "integrity": "sha512-OXO2uBjFqA4Ibr2O3y0YMnkrRWGVNqcvHQXmGvMu6IK8chZl3PrDxFXdGZ2iZkSrKh3/qUYoFqYe+Rx23RoU0g==",
-      "license": "MIT",
-      "dependencies": {
-        "@tanstack/virtual-core": "3.10.9"
-      },
-      "funding": {
-        "type": "github",
-        "url": "https://github.com/sponsors/tannerlinsley"
-      },
-      "peerDependencies": {
-        "react": "^16.8.0 || ^17.0.0 || ^18.0.0",
-        "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0"
-      }
-    },
     "node_modules/@nextui-org/shared-icons": {
       "version": "2.1.1",
       "resolved": "https://registry.npmjs.org/@nextui-org/shared-icons/-/shared-icons-2.1.1.tgz",
@@ -5361,20 +5311,22 @@
       }
     },
     "node_modules/@tanstack/query-core": {
-      "version": "5.62.12",
-      "resolved": "https://registry.npmjs.org/@tanstack/query-core/-/query-core-5.62.12.tgz",
-      "integrity": "sha512-6igFeBgymHkCxVgaEk+yiLwkMf9haui/EQLmI3o9CatOyDThEoFKe8toLWvWliZC/Jf+h7NwHi/zjfyLArr1ow==",
+      "version": "5.62.9",
+      "resolved": "https://registry.npmjs.org/@tanstack/query-core/-/query-core-5.62.9.tgz",
+      "integrity": "sha512-lwePd8hNYhyQ4nM/iRQ+Wz2cDtspGeZZHFZmCzHJ7mfKXt+9S301fULiY2IR2byJYY6Z03T427E5PoVfMexHjw==",
+      "license": "MIT",
       "funding": {
         "type": "github",
         "url": "https://github.com/sponsors/tannerlinsley"
       }
     },
     "node_modules/@tanstack/react-query": {
-      "version": "5.62.12",
-      "resolved": "https://registry.npmjs.org/@tanstack/react-query/-/react-query-5.62.12.tgz",
-      "integrity": "sha512-yt8p7l5MlHA3QCt6xF1Cu9dw1Anf93yTK+DMDJQ64h/mshAymVAtcwj8TpsyyBrZNWAAZvza/m76bnTSR79ZtQ==",
+      "version": "5.62.10",
+      "resolved": "https://registry.npmjs.org/@tanstack/react-query/-/react-query-5.62.10.tgz",
+      "integrity": "sha512-1e1WpHM5oGf27nWM/NWLY62/X9pbMBWa6ErWYmeuK0OqB9/g9UzA59ogiWbxCmS2wtAFQRhOdHhfSofrkhPl2g==",
+      "license": "MIT",
       "dependencies": {
-        "@tanstack/query-core": "5.62.12"
+        "@tanstack/query-core": "5.62.9"
       },
       "funding": {
         "type": "github",
@@ -5384,6 +5336,23 @@
         "react": "^18 || ^19"
       }
     },
+    "node_modules/@tanstack/react-virtual": {
+      "version": "3.10.9",
+      "resolved": "https://registry.npmjs.org/@tanstack/react-virtual/-/react-virtual-3.10.9.tgz",
+      "integrity": "sha512-OXO2uBjFqA4Ibr2O3y0YMnkrRWGVNqcvHQXmGvMu6IK8chZl3PrDxFXdGZ2iZkSrKh3/qUYoFqYe+Rx23RoU0g==",
+      "license": "MIT",
+      "dependencies": {
+        "@tanstack/virtual-core": "3.10.9"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/tannerlinsley"
+      },
+      "peerDependencies": {
+        "react": "^16.8.0 || ^17.0.0 || ^18.0.0",
+        "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0"
+      }
+    },
     "node_modules/@tanstack/virtual-core": {
       "version": "3.10.9",
       "resolved": "https://registry.npmjs.org/@tanstack/virtual-core/-/virtual-core-3.10.9.tgz",
@@ -5625,31 +5594,39 @@
       "license": "MIT"
     },
     "node_modules/@types/node": {
-      "version": "22.10.5",
-      "resolved": "https://registry.npmjs.org/@types/node/-/node-22.10.5.tgz",
-      "integrity": "sha512-F8Q+SeGimwOo86fiovQh8qiXfFEh2/ocYv7tU5pJ3EXMSSxk1Joj5wefpFK2fHTf/N6HKGSxIDBT9f3gCxXPkQ==",
+      "version": "22.10.2",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-22.10.2.tgz",
+      "integrity": "sha512-Xxr6BBRCAOQixvonOye19wnzyDiUtTeqldOOmj3CkeblonbccA12PFwlufvRdrpjXxqnmUaeiU5EOA+7s5diUQ==",
       "devOptional": true,
+      "license": "MIT",
       "dependencies": {
         "undici-types": "~6.20.0"
       }
     },
+    "node_modules/@types/prop-types": {
+      "version": "15.7.14",
+      "resolved": "https://registry.npmjs.org/@types/prop-types/-/prop-types-15.7.14.tgz",
+      "integrity": "sha512-gNMvNH49DJ7OJYv+KAKn0Xp45p8PLl6zo2YnvDIbTd4J6MER2BmWN49TG7n9LvkyihINxeKW8+3bfS2yDC9dzQ==",
+      "license": "MIT"
+    },
     "node_modules/@types/react": {
-      "version": "19.0.2",
-      "resolved": "https://registry.npmjs.org/@types/react/-/react-19.0.2.tgz",
-      "integrity": "sha512-USU8ZI/xyKJwFTpjSVIrSeHBVAGagkHQKPNbxeWwql/vDmnTIBgx+TJnhFnj1NXgz8XfprU0egV2dROLGpsBEg==",
+      "version": "18.3.18",
+      "resolved": "https://registry.npmjs.org/@types/react/-/react-18.3.18.tgz",
+      "integrity": "sha512-t4yC+vtgnkYjNSKlFx1jkAhH8LgTo2N/7Qvi83kdEaUtMDiwpbLAktKDaAMlRcJ5eSxZkH74eEGt1ky31d7kfQ==",
       "license": "MIT",
       "dependencies": {
+        "@types/prop-types": "*",
         "csstype": "^3.0.2"
       }
     },
     "node_modules/@types/react-dom": {
-      "version": "19.0.2",
-      "resolved": "https://registry.npmjs.org/@types/react-dom/-/react-dom-19.0.2.tgz",
-      "integrity": "sha512-c1s+7TKFaDRRxr1TxccIX2u7sfCnc3RxkVyBIUA2lCpyqCF+QoAwQ/CBg7bsMdVwP120HEH143VQezKtef5nCg==",
+      "version": "18.3.5",
+      "resolved": "https://registry.npmjs.org/@types/react-dom/-/react-dom-18.3.5.tgz",
+      "integrity": "sha512-P4t6saawp+b/dFrUr2cvkVsfvPguwsxtH6dNIYRllMsefqFzkZk5UIjzyDOv5g1dXIPdG4Sp1yCR4Z6RCUsG/Q==",
       "dev": true,
       "license": "MIT",
       "peerDependencies": {
-        "@types/react": "^19.0.0"
+        "@types/react": "^18.0.0"
       }
     },
     "node_modules/@types/react-highlight": {
@@ -8147,9 +8124,9 @@
       "license": "MIT"
     },
     "node_modules/es-abstract": {
-      "version": "1.23.8",
-      "resolved": "https://registry.npmjs.org/es-abstract/-/es-abstract-1.23.8.tgz",
-      "integrity": "sha512-lfab8IzDn6EpI1ibZakcgS6WsfEBiB+43cuJo+wgylx1xKXf+Sp+YR3vFuQwC/u3sxYwV8Cxe3B0DpVUu/WiJQ==",
+      "version": "1.23.7",
+      "resolved": "https://registry.npmjs.org/es-abstract/-/es-abstract-1.23.7.tgz",
+      "integrity": "sha512-OygGC8kIcDhXX+6yAZRGLqwi2CmEXCbLQixeGUgYeR+Qwlppqmo7DIDr8XibtEBZp+fJcoYpoatp5qwLMEdcqQ==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -8188,10 +8165,8 @@
         "object-inspect": "^1.13.3",
         "object-keys": "^1.1.1",
         "object.assign": "^4.1.7",
-        "own-keys": "^1.0.0",
         "regexp.prototype.flags": "^1.5.3",
         "safe-array-concat": "^1.1.3",
-        "safe-push-apply": "^1.0.0",
         "safe-regex-test": "^1.1.0",
         "string.prototype.trim": "^1.2.10",
         "string.prototype.trimend": "^1.0.9",
@@ -11204,13 +11179,13 @@
       "license": "MIT"
     },
     "node_modules/lint-staged": {
-      "version": "15.3.0",
-      "resolved": "https://registry.npmjs.org/lint-staged/-/lint-staged-15.3.0.tgz",
-      "integrity": "sha512-vHFahytLoF2enJklgtOtCtIjZrKD/LoxlaUusd5nh7dWv/dkKQJY74ndFSzxCdv7g0ueGg1ORgTSt4Y9LPZn9A==",
+      "version": "15.2.11",
+      "resolved": "https://registry.npmjs.org/lint-staged/-/lint-staged-15.2.11.tgz",
+      "integrity": "sha512-Ev6ivCTYRTGs9ychvpVw35m/bcNDuBN+mnTeObCL5h+boS5WzBEC6LHI4I9F/++sZm1m+J2LEiy0gxL/R9TBqQ==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
-        "chalk": "~5.4.1",
+        "chalk": "~5.3.0",
         "commander": "~12.1.0",
         "debug": "~4.4.0",
         "execa": "~8.0.1",
@@ -11232,9 +11207,9 @@
       }
     },
     "node_modules/lint-staged/node_modules/chalk": {
-      "version": "5.4.1",
-      "resolved": "https://registry.npmjs.org/chalk/-/chalk-5.4.1.tgz",
-      "integrity": "sha512-zgVZuo2WcZgfUEmsn6eO3kINexW8RAE4maiQ8QNs8CtpPCSyMiYsULR3HQYkm3w8FIA3SberyMJMSldGsW+U3w==",
+      "version": "5.3.0",
+      "resolved": "https://registry.npmjs.org/chalk/-/chalk-5.3.0.tgz",
+      "integrity": "sha512-dLitG79d+GV1Nb/VYcCDFivJeK1hiukt9QjRNVOsUtTy1rR1YJsmpGGTZ3qJos+uw7WmWF4wUwBd9jxjocFC2w==",
       "dev": true,
       "license": "MIT",
       "engines": {
@@ -11569,7 +11544,6 @@
       "version": "1.4.0",
       "resolved": "https://registry.npmjs.org/loose-envify/-/loose-envify-1.4.0.tgz",
       "integrity": "sha512-lyuxPGr/Wfhrlem2CL/UcnUc1zcqKAImBDzukY7Y5F/yQiNdko6+fRLevlw1HgMySw7f611UIY408EtxRSoK3Q==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "js-tokens": "^3.0.0 || ^4.0.0"
@@ -13295,24 +13269,6 @@
       "dev": true,
       "license": "MIT"
     },
-    "node_modules/own-keys": {
-      "version": "1.0.1",
-      "resolved": "https://registry.npmjs.org/own-keys/-/own-keys-1.0.1.tgz",
-      "integrity": "sha512-qFOyK5PjiWZd+QQIh+1jhdb9LpxTF0qs7Pm8o5QHYZ0M3vKqSqzsZaEB6oWlxZ+q2sJBMI/Ktgd2N5ZwQoRHfg==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "get-intrinsic": "^1.2.6",
-        "object-keys": "^1.1.1",
-        "safe-push-apply": "^1.0.0"
-      },
-      "engines": {
-        "node": ">= 0.4"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/ljharb"
-      }
-    },
     "node_modules/p-limit": {
       "version": "3.1.0",
       "resolved": "https://registry.npmjs.org/p-limit/-/p-limit-3.1.0.tgz",
@@ -13596,14 +13552,14 @@
       }
     },
     "node_modules/pkg-types": {
-      "version": "1.3.0",
-      "resolved": "https://registry.npmjs.org/pkg-types/-/pkg-types-1.3.0.tgz",
-      "integrity": "sha512-kS7yWjVFCkIw9hqdJBoMxDdzEngmkr5FXeWZZfQ6GoYacjVnsW6l2CcYW/0ThD0vF4LPJgVYnrg4d0uuhwYQbg==",
+      "version": "1.2.1",
+      "resolved": "https://registry.npmjs.org/pkg-types/-/pkg-types-1.2.1.tgz",
+      "integrity": "sha512-sQoqa8alT3nHjGuTjuKgOnvjo4cljkufdtLMnO2LBP/wRwuDlo1tkaEdMxCRhyGRPacv/ztlZgDPm2b7FAmEvw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
         "confbox": "^0.1.8",
-        "mlly": "^1.7.3",
+        "mlly": "^1.7.2",
         "pathe": "^1.1.2"
       }
     },
@@ -13807,9 +13763,10 @@
       "license": "MIT"
     },
     "node_modules/posthog-js": {
-      "version": "1.203.3",
-      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.203.3.tgz",
-      "integrity": "sha512-DTK6LfL87xC7PPleKDParEIfkXl7hXtuDeSOPfhcyCXLuVspq0z7YyRB5dQE9Pbalf3yoGqUKvomYFp/BGVfQg==",
+      "version": "1.203.1",
+      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.203.1.tgz",
+      "integrity": "sha512-r/WiSyz6VNbIKEV/30+aD5gdrYkFtmZwvqNa6h9frl8hG638v098FrXaq3EYzMcCdkQf3phaZTDIAFKegpiTjw==",
+      "license": "MIT",
       "dependencies": {
         "core-js": "^3.38.1",
         "fflate": "^0.4.8",
@@ -13824,9 +13781,9 @@
       "license": "Apache-2.0"
     },
     "node_modules/preact": {
-      "version": "10.25.4",
-      "resolved": "https://registry.npmjs.org/preact/-/preact-10.25.4.tgz",
-      "integrity": "sha512-jLdZDb+Q+odkHJ+MpW/9U5cODzqnB+fy2EiHSZES7ldV5LK7yjlVzTp7R8Xy6W6y75kfK8iWYtFVH7lvjwrCMA==",
+      "version": "10.25.3",
+      "resolved": "https://registry.npmjs.org/preact/-/preact-10.25.3.tgz",
+      "integrity": "sha512-dzQmIFtM970z+fP9ziQ3yG4e3ULIbwZzJ734vaMVUTaKQ2+Ru1Ou/gjshOYVHCcd1rpAelC6ngjvjDXph98unQ==",
       "license": "MIT",
       "funding": {
         "type": "opencollective",
@@ -14110,24 +14067,28 @@
       }
     },
     "node_modules/react": {
-      "version": "19.0.0",
-      "resolved": "https://registry.npmjs.org/react/-/react-19.0.0.tgz",
-      "integrity": "sha512-V8AVnmPIICiWpGfm6GLzCR/W5FXLchHop40W4nXBmdlEceh16rCN8O8LNWm5bh5XUX91fh7KpA+W0TgMKmgTpQ==",
+      "version": "18.3.1",
+      "resolved": "https://registry.npmjs.org/react/-/react-18.3.1.tgz",
+      "integrity": "sha512-wS+hAgJShR0KhEvPJArfuPVN1+Hz1t0Y6n5jLrGQbkb4urgPE/0Rve+1kMB1v/oWgHgm4WIcV+i7F2pTVj+2iQ==",
       "license": "MIT",
+      "dependencies": {
+        "loose-envify": "^1.1.0"
+      },
       "engines": {
         "node": ">=0.10.0"
       }
     },
     "node_modules/react-dom": {
-      "version": "19.0.0",
-      "resolved": "https://registry.npmjs.org/react-dom/-/react-dom-19.0.0.tgz",
-      "integrity": "sha512-4GV5sHFG0e/0AD4X+ySy6UJd3jVl1iNsNHdpad0qhABJ11twS3TTBnseqsKurKcsNqCEFeGL3uLpVChpIO3QfQ==",
+      "version": "18.3.1",
+      "resolved": "https://registry.npmjs.org/react-dom/-/react-dom-18.3.1.tgz",
+      "integrity": "sha512-5m4nQKp+rZRb09LNH59GM4BxTh9251/ylbKIbpe7TpGxfJ+9kv6BLkLBXIjjspbgbnIBNqlI23tRnTWT0snUIw==",
       "license": "MIT",
       "dependencies": {
-        "scheduler": "^0.25.0"
+        "loose-envify": "^1.1.0",
+        "scheduler": "^0.23.2"
       },
       "peerDependencies": {
-        "react": "^19.0.0"
+        "react": "^18.3.1"
       }
     },
     "node_modules/react-highlight": {
@@ -14140,12 +14101,12 @@
       }
     },
     "node_modules/react-hot-toast": {
-      "version": "2.5.1",
-      "resolved": "https://registry.npmjs.org/react-hot-toast/-/react-hot-toast-2.5.1.tgz",
-      "integrity": "sha512-54Gq1ZD1JbmAb4psp9bvFHjS7lje+8ubboUmvKZkCsQBLH6AOpZ9JemfRvIdHcfb9AZXRaFLrb3qUobGYDJhFQ==",
+      "version": "2.4.1",
+      "resolved": "https://registry.npmjs.org/react-hot-toast/-/react-hot-toast-2.4.1.tgz",
+      "integrity": "sha512-j8z+cQbWIM5LY37pR6uZR6D4LfseplqnuAO4co4u8917hBUvXlEqyP1ZzqVLcqoyUesZZv/ImreoCeHVDpE5pQ==",
+      "license": "MIT",
       "dependencies": {
-        "csstype": "^3.1.3",
-        "goober": "^2.1.16"
+        "goober": "^2.1.10"
       },
       "engines": {
         "node": ">=10"
@@ -14156,9 +14117,9 @@
       }
     },
     "node_modules/react-i18next": {
-      "version": "15.4.0",
-      "resolved": "https://registry.npmjs.org/react-i18next/-/react-i18next-15.4.0.tgz",
-      "integrity": "sha512-Py6UkX3zV08RTvL6ZANRoBh9sL/ne6rQq79XlkHEdd82cZr2H9usbWpUNVadJntIZP2pu3M2rL1CN+5rQYfYFw==",
+      "version": "15.2.0",
+      "resolved": "https://registry.npmjs.org/react-i18next/-/react-i18next-15.2.0.tgz",
+      "integrity": "sha512-iJNc8111EaDtVTVMKigvBtPHyrJV+KblWG73cUxqp+WmJCcwkzhWNFXmkAD5pwP2Z4woeDj/oXDdbjDsb3Gutg==",
       "license": "MIT",
       "dependencies": {
         "@babel/runtime": "^7.25.0",
@@ -14927,30 +14888,6 @@
       ],
       "license": "MIT"
     },
-    "node_modules/safe-push-apply": {
-      "version": "1.0.0",
-      "resolved": "https://registry.npmjs.org/safe-push-apply/-/safe-push-apply-1.0.0.tgz",
-      "integrity": "sha512-iKE9w/Z7xCzUMIZqdBsp6pEQvwuEebH4vdpjcDWnyzaI6yl6O9FHvVpmGelvEHNsoY6wGblkxR6Zty/h00WiSA==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "es-errors": "^1.3.0",
-        "isarray": "^2.0.5"
-      },
-      "engines": {
-        "node": ">= 0.4"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/ljharb"
-      }
-    },
-    "node_modules/safe-push-apply/node_modules/isarray": {
-      "version": "2.0.5",
-      "resolved": "https://registry.npmjs.org/isarray/-/isarray-2.0.5.tgz",
-      "integrity": "sha512-xHjhDr3cNBK0BzdUJSPXZntQUx/mwMS5Rw4A7lPJ90XGAO6ISP/ePDNuo0vhqOZU+UD5JoodwCAAoZQd3FeAKw==",
-      "dev": true,
-      "license": "MIT"
-    },
     "node_modules/safe-regex-test": {
       "version": "1.1.0",
       "resolved": "https://registry.npmjs.org/safe-regex-test/-/safe-regex-test-1.1.0.tgz",
@@ -14989,10 +14926,13 @@
       }
     },
     "node_modules/scheduler": {
-      "version": "0.25.0",
-      "resolved": "https://registry.npmjs.org/scheduler/-/scheduler-0.25.0.tgz",
-      "integrity": "sha512-xFVuu11jh+xcO7JOAGJNOXld8/TcEHK/4CituBUeUb5hqxJLj9YuemAEuvm9gQ/+pgXYfbQuqAkiYu+u7YEsNA==",
-      "license": "MIT"
+      "version": "0.23.2",
+      "resolved": "https://registry.npmjs.org/scheduler/-/scheduler-0.23.2.tgz",
+      "integrity": "sha512-UOShsPwz7NrMUqhR6t0hWjFduvOzbtv7toDH1/hIrfRNIDBnnBWd0CwJTGvTpngVlmwGCdP9/Zl/tVrDqcuYzQ==",
+      "license": "MIT",
+      "dependencies": {
+        "loose-envify": "^1.1.0"
+      }
     },
     "node_modules/scroll-into-view-if-needed": {
       "version": "3.0.10",

frontend/package.json

@@ -1,19 +1,19 @@
 {
   "name": "openhands-frontend",
-  "version": "0.18.0",
+  "version": "0.17.0",
   "private": true,
   "type": "module",
   "engines": {
     "node": ">=20.0.0"
   },
   "dependencies": {
-    "@monaco-editor/react": "^4.7.0-rc.0",
+    "@monaco-editor/react": "^4.6.0",
     "@nextui-org/react": "^2.6.10",
     "@react-router/node": "^7.1.1",
     "@react-router/serve": "^7.1.1",
     "@react-types/shared": "^3.25.0",
     "@reduxjs/toolkit": "^2.5.0",
-    "@tanstack/react-query": "^5.62.12",
+    "@tanstack/react-query": "^5.62.10",
     "@vitejs/plugin-react": "^4.3.2",
     "@xterm/addon-fit": "^0.10.0",
     "@xterm/xterm": "^5.4.0",
@@ -26,12 +26,12 @@
     "isbot": "^5.1.19",
     "jose": "^5.9.4",
     "monaco-editor": "^0.52.2",
-    "posthog-js": "^1.203.3",
-    "react": "^19.0.0",
-    "react-dom": "^19.0.0",
+    "posthog-js": "^1.203.1",
+    "react": "^18.3.1",
+    "react-dom": "^18.3.1",
     "react-highlight": "^0.15.0",
-    "react-hot-toast": "^2.5.1",
-    "react-i18next": "^15.4.0",
+    "react-hot-toast": "^2.4.1",
+    "react-i18next": "^15.2.0",
     "react-icons": "^5.4.0",
     "react-markdown": "^9.0.1",
     "react-redux": "^9.2.0",
@@ -42,7 +42,7 @@
     "sirv-cli": "^3.0.0",
     "socket.io-client": "^4.8.1",
     "tailwind-merge": "^2.6.0",
-    "vite": "^5.4.11",
+    "vite": "^5.4.9",
     "web-vitals": "^3.5.2",
     "ws": "^8.18.0"
   },
@@ -75,7 +75,6 @@
     ]
   },
   "devDependencies": {
-    "@mswjs/socket.io-binding": "^0.1.1",
     "@playwright/test": "^1.49.1",
     "@react-router/dev": "^7.1.1",
     "@tailwindcss/typography": "^0.5.15",
@@ -83,9 +82,9 @@
     "@testing-library/jest-dom": "^6.6.1",
     "@testing-library/react": "^16.1.0",
     "@testing-library/user-event": "^14.5.2",
-    "@types/node": "^22.10.5",
-    "@types/react": "^19.0.2",
-    "@types/react-dom": "^19.0.2",
+    "@types/node": "^22.10.2",
+    "@types/react": "^18.3.11",
+    "@types/react-dom": "^18.3.0",
     "@types/react-highlight": "^0.12.8",
     "@types/react-syntax-highlighter": "^15.5.13",
     "@types/ws": "^8.5.12",
@@ -105,12 +104,12 @@
     "eslint-plugin-react-hooks": "^4.6.2",
     "husky": "^9.1.6",
     "jsdom": "^25.0.1",
-    "lint-staged": "^15.3.0",
+    "lint-staged": "^15.2.11",
     "msw": "^2.6.6",
     "postcss": "^8.4.47",
     "prettier": "^3.4.2",
     "tailwindcss": "^3.4.17",
-    "typescript": "^5.7.2",
+    "typescript": "^5.6.3",
     "vite-plugin-svgr": "^4.2.0",
     "vite-tsconfig-paths": "^5.1.4",
     "vitest": "^1.6.0"

frontend/public/mockServiceWorker.js

@@ -8,8 +8,8 @@
  * - Please do NOT serve this file on production.
  */
 
-const PACKAGE_VERSION = '2.7.0'
-const INTEGRITY_CHECKSUM = '00729d72e3b82faf54ca8b9621dbb96f'
+const PACKAGE_VERSION = '2.6.6'
+const INTEGRITY_CHECKSUM = 'ca7800994cc8bfb5eb961e037c877074'
 const IS_MOCKED_RESPONSE = Symbol('isMockedResponse')
 const activeClientIds = new Set()
 
@@ -199,19 +199,7 @@ async function getResponse(event, client, requestId) {
     // Remove the "accept" header value that marked this request as passthrough.
     // This prevents request alteration and also keeps it compliant with the
     // user-defined CORS policies.
-    const acceptHeader = headers.get('accept')
-    if (acceptHeader) {
-      const values = acceptHeader.split(',').map((value) => value.trim())
-      const filteredValues = values.filter(
-        (value) => value !== 'msw/passthrough',
-      )
-
-      if (filteredValues.length > 0) {
-        headers.set('accept', filteredValues.join(', '))
-      } else {
-        headers.delete('accept')
-      }
-    }
+    headers.delete('accept', 'msw/passthrough')
 
     return fetch(requestClone, { headers })
   }

frontend/src/api/github.ts

@@ -104,55 +104,17 @@ export const retrieveGitHubUser = async () => {
   return user;
 };
 
-export const searchPublicRepositories = async (
-  query: string,
-  per_page = 5,
-  sort: "" | "updated" | "stars" | "forks" = "stars",
-  order: "desc" | "asc" = "desc",
-): Promise<GitHubRepository[]> => {
-  const sanitizedQuery = query.trim();
-  if (!sanitizedQuery) {
-    return [];
-  }
-
-  const response = await github.get<{ items: GitHubRepository[] }>(
-    "/search/repositories",
+export const retrieveLatestGitHubCommit = async (
+  repository: string,
+): Promise<GitHubCommit> => {
+  const response = await github.get<GitHubCommit[]>(
+    `/repos/${repository}/commits`,
     {
       params: {
-        q: sanitizedQuery,
-        per_page,
-        sort,
-        order,
+        per_page: 1,
       },
     },
   );
-  return response.data.items;
-};
 
-export const retrieveLatestGitHubCommit = async (
-  repository: string,
-): Promise<GitHubCommit | null> => {
-  try {
-    const response = await github.get<GitHubCommit[]>(
-      `/repos/${repository}/commits`,
-      {
-        params: {
-          per_page: 1,
-        },
-      },
-    );
-    return response.data[0] || null;
-  } catch (error) {
-    if (!error || typeof error !== "object") {
-      throw new Error("Unknown error occurred");
-    }
-    const axiosError = error as { response?: { status: number } };
-    if (axiosError.response?.status === 409) {
-      // Repository is empty, no commits yet
-      return null;
-    }
-    throw new Error(
-      error instanceof Error ? error.message : "Unknown error occurred",
-    );
-  }
+  return response.data[0];
 };

frontend/src/api/open-hands.ts

@@ -8,10 +8,8 @@ import {
   GetConfigResponse,
   GetVSCodeUrlResponse,
   AuthenticateResponse,
-  Conversation,
 } from "./open-hands.types";
 import { openHands } from "./open-hands-axios";
-import { ApiSettings } from "#/services/settings";
 
 class OpenHands {
   /**
@@ -221,52 +219,6 @@ class OpenHands {
     return data;
   }
 
-  static async getUserConversations(): Promise<Conversation[]> {
-    const { data } = await openHands.get<Conversation[]>("/api/conversations");
-    return data;
-  }
-
-  static async deleteUserConversation(conversationId: string): Promise<void> {
-    await openHands.delete(`/api/conversations/${conversationId}`);
-  }
-
-  static async updateUserConversation(
-    conversationId: string,
-    conversation: Partial<Omit<Conversation, "id">>,
-  ): Promise<void> {
-    await openHands.put(`/api/conversations/${conversationId}`, conversation);
-  }
-
-  static async createConversation(
-    githubToken?: string,
-    selectedRepository?: string,
-  ): Promise<Conversation> {
-    const body = {
-      github_token: githubToken,
-      selected_repository: selectedRepository,
-    };
-
-    const { data } = await openHands.post<Conversation>(
-      "/api/conversations",
-      body,
-    );
-
-    // TODO: remove this once we have a multi-conversation UI
-    localStorage.setItem("latest_conversation_id", data.conversation_id);
-
-    return data;
-  }
-
-  static async getConversation(
-    conversationId: string,
-  ): Promise<Conversation | null> {
-    const { data } = await openHands.get<Conversation | null>(
-      `/api/conversations/${conversationId}`,
-    );
-
-    return data;
-  }
-
   static async searchEvents(
     conversationId: string,
     params: {
@@ -296,22 +248,22 @@ class OpenHands {
     return data;
   }
 
-  /**
-   * Get the settings from the server or use the default settings if not found
-   */
-  static async getSettings(): Promise<ApiSettings> {
-    const { data } = await openHands.get<ApiSettings>("/api/settings");
+  static async newConversation(params: {
+    githubToken?: string;
+    args?: Record<string, unknown>;
+    selectedRepository?: string;
+  }): Promise<{ conversation_id: string }> {
+    const { data } = await openHands.post<{
+      conversation_id: string;
+    }>("/api/conversations", {
+      github_token: params.githubToken,
+      args: params.args,
+      selected_repository: params.selectedRepository,
+    });
+    // TODO: remove this once we have a multi-conversation UI
+    localStorage.setItem("latest_conversation_id", data.conversation_id);
     return data;
   }
-
-  /**
-   * Save the settings to the server. Only valid settings are saved.
-   * @param settings - the settings to save
-   */
-  static async saveSettings(settings: Partial<ApiSettings>): Promise<boolean> {
-    const data = await openHands.post("/api/settings", settings);
-    return data.status === 200;
-  }
 }
 
 export default OpenHands;

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

@@ -1,5 +1,3 @@
-import { ProjectState } from "#/components/features/conversation-panel/conversation-state-indicator";
-
 export interface ErrorResponse {
   error: string;
 }
@@ -59,11 +57,3 @@ export interface AuthenticateResponse {
   message?: string;
   error?: string;
 }
-
-export interface Conversation {
-  conversation_id: string;
-  name: string;
-  repo: string | null;
-  lastUpdated: string;
-  state: ProjectState;
-}

frontend/src/assets/arrow.tsx

@@ -1,6 +1,6 @@
 import React from "react";
 
-function ArrowIcon() {
+function ArrowIcon(): JSX.Element {
   return (
     <svg
       xmlns="http://www.w3.org/2000/svg"

frontend/src/assets/cog-tooth.tsx

@@ -1,6 +1,6 @@
 import React from "react";
 
-function CogTooth() {
+function CogTooth(): JSX.Element {
   return (
     <svg
       xmlns="http://www.w3.org/2000/svg"

frontend/src/assets/confirm.tsx

@@ -1,6 +1,6 @@
 import React from "react";
 
-function ConfirmIcon() {
+function ConfirmIcon(): JSX.Element {
   return (
     <svg
       xmlns="http://www.w3.org/2000/svg"

frontend/src/assets/pause.tsx

@@ -1,6 +1,6 @@
 import React from "react";
 
-function PauseIcon() {
+function PauseIcon(): JSX.Element {
   return (
     <svg
       xmlns="http://www.w3.org/2000/svg"

frontend/src/assets/play.tsx

@@ -1,6 +1,6 @@
 import React from "react";
 
-function PlayIcon() {
+function PlayIcon(): JSX.Element {
   return (
     <svg
       xmlns="http://www.w3.org/2000/svg"

frontend/src/assets/reject.tsx

@@ -1,6 +1,6 @@
 import React from "react";
 
-function RejectIcon() {
+function RejectIcon(): JSX.Element {
   return (
     <svg
       xmlns="http://www.w3.org/2000/svg"

frontend/src/assets/stop.tsx

@@ -1,6 +1,6 @@
 import React from "react";
 
-function StopIcon() {
+function StopIcon(): JSX.Element {
   return (
     <svg
       xmlns="http://www.w3.org/2000/svg"

frontend/src/components/extension-icon-map.constant.tsx

@@ -8,7 +8,7 @@ import {
   FaPython,
 } from "react-icons/fa";
 
-export const EXTENSION_ICON_MAP: Record<string, React.ReactNode> = {
+export const EXTENSION_ICON_MAP: Record<string, JSX.Element> = {
   js: <DiJavascript />,
   ts: <DiJavascript />,
   py: <FaPython />,

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

@@ -1,4 +1,3 @@
-import React from "react";
 import { ChatMessage } from "#/components/features/chat/chat-message";
 import { ConfirmationButtons } from "#/components/shared/buttons/confirmation-buttons";
 import { ImageCarousel } from "../images/image-carousel";
@@ -9,36 +8,32 @@ interface MessagesProps {
   isAwaitingUserConfirmation: boolean;
 }
 
-export const Messages: React.FC<MessagesProps> = React.memo(
-  ({ messages, isAwaitingUserConfirmation }) =>
-    messages.map((message, index) => {
-      if (message.type === "error" || message.type === "action") {
-        return (
-          <ExpandableMessage
-            key={index}
-            type={message.type}
-            id={message.translationID}
-            message={message.content}
-            success={message.success}
-          />
-        );
-      }
-
+export function Messages({
+  messages,
+  isAwaitingUserConfirmation,
+}: MessagesProps) {
+  return messages.map((message, index) => {
+    if (message.type === "error" || message.type === "action") {
       return (
-        <ChatMessage
+        <ExpandableMessage
           key={index}
-          type={message.sender}
+          type={message.type}
+          id={message.translationID}
           message={message.content}
-        >
-          {message.imageUrls && message.imageUrls.length > 0 && (
-            <ImageCarousel size="small" images={message.imageUrls} />
-          )}
-          {messages.length - 1 === index &&
-            message.sender === "assistant" &&
-            isAwaitingUserConfirmation && <ConfirmationButtons />}
-        </ChatMessage>
+          success={message.success}
+        />
       );
-    }),
-);
+    }
 
-Messages.displayName = "Messages";
+    return (
+      <ChatMessage key={index} type={message.sender} message={message.content}>
+        {message.imageUrls && message.imageUrls.length > 0 && (
+          <ImageCarousel size="small" images={message.imageUrls} />
+        )}
+        {messages.length - 1 === index &&
+          message.sender === "assistant" &&
+          isAwaitingUserConfirmation && <ConfirmationButtons />}
+      </ChatMessage>
+    );
+  });
+}

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

@@ -1,9 +1,7 @@
-import { useTranslation } from "react-i18next";
 import { ContextMenu } from "./context-menu";
 import { ContextMenuListItem } from "./context-menu-list-item";
 import { ContextMenuSeparator } from "./context-menu-separator";
 import { useClickOutsideElement } from "#/hooks/use-click-outside-element";
-import { I18nKey } from "#/i18n/declaration";
 
 interface AccountSettingsContextMenuProps {
   onClickAccountSettings: () => void;
@@ -19,7 +17,6 @@ export function AccountSettingsContextMenu({
   isLoggedIn,
 }: AccountSettingsContextMenuProps) {
   const ref = useClickOutsideElement<HTMLUListElement>(onClose);
-  const { t } = useTranslation();
 
   return (
     <ContextMenu
@@ -28,11 +25,11 @@ export function AccountSettingsContextMenu({
       className="absolute left-full -top-1 z-10"
     >
       <ContextMenuListItem onClick={onClickAccountSettings}>
-        {t(I18nKey.ACCOUNT_SETTINGS$SETTINGS)}
+        Account Settings
       </ContextMenuListItem>
       <ContextMenuSeparator />
       <ContextMenuListItem onClick={onLogout} isDisabled={!isLoggedIn}>
-        {t(I18nKey.ACCOUNT_SETTINGS$LOGOUT)}
+        Logout
       </ContextMenuListItem>
     </ContextMenu>
   );

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

@@ -1,20 +1,18 @@
 import { cn } from "#/utils/utils";
 
 interface ContextMenuListItemProps {
-  testId?: string;
-  onClick: (event: React.MouseEvent<HTMLButtonElement>) => void;
+  onClick: () => void;
   isDisabled?: boolean;
 }
 
 export function ContextMenuListItem({
   children,
-  testId,
   onClick,
   isDisabled,
 }: React.PropsWithChildren<ContextMenuListItemProps>) {
   return (
     <button
-      data-testid={testId || "context-menu-list-item"}
+      data-testid="context-menu-list-item"
       type="button"
       onClick={onClick}
       disabled={isDisabled}

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

@@ -2,19 +2,13 @@ import React from "react";
 import { cn } from "#/utils/utils";
 
 interface ContextMenuProps {
-  ref?: React.RefObject<HTMLUListElement | null>;
   testId?: string;
   children: React.ReactNode;
   className?: React.HTMLAttributes<HTMLUListElement>["className"];
 }
 
-export function ContextMenu({
-  testId,
-  children,
-  className,
-  ref,
-}: ContextMenuProps) {
-  return (
+export const ContextMenu = React.forwardRef<HTMLUListElement, ContextMenuProps>(
+  ({ testId, children, className }, ref) => (
     <ul
       data-testid={testId}
       ref={ref}
@@ -22,5 +16,7 @@ export function ContextMenu({
     >
       {children}
     </ul>
-  );
-}
+  ),
+);
+
+ContextMenu.displayName = "ContextMenu";

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

@@ -1,36 +0,0 @@
-import { ModalButton } from "#/components/shared/buttons/modal-button";
-import {
-  BaseModalDescription,
-  BaseModalTitle,
-} from "#/components/shared/modals/confirmation-modals/base-modal";
-import { ModalBackdrop } from "#/components/shared/modals/modal-backdrop";
-import { ModalBody } from "#/components/shared/modals/modal-body";
-
-interface ConfirmDeleteModalProps {
-  onConfirm: () => void;
-  onCancel: () => void;
-}
-
-export function ConfirmDeleteModal({
-  onConfirm,
-  onCancel,
-}: ConfirmDeleteModalProps) {
-  return (
-    <ModalBackdrop>
-      <ModalBody className="items-start">
-        <div className="flex flex-col gap-2">
-          <BaseModalTitle title="Are you sure you want to delete this project?" />
-          <BaseModalDescription description="All data associated with this project will be lost." />
-        </div>
-        <div className="flex flex-col gap-2 w-full">
-          <ModalButton
-            onClick={onConfirm}
-            className="bg-[#4465DB]"
-            text="Confirm"
-          />
-          <ModalButton onClick={onCancel} className="bg-danger" text="Cancel" />
-        </div>
-      </ModalBody>
-    </ModalBackdrop>
-  );
-}

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

@@ -1,102 +0,0 @@
-import React from "react";
-import { formatTimeDelta } from "#/utils/format-time-delta";
-import { ConversationRepoLink } from "./conversation-repo-link";
-import {
-  ProjectState,
-  ConversationStateIndicator,
-} from "./conversation-state-indicator";
-import { ContextMenu } from "../context-menu/context-menu";
-import { ContextMenuListItem } from "../context-menu/context-menu-list-item";
-import { EllipsisButton } from "./ellipsis-button";
-
-interface ProjectCardProps {
-  onClick: () => void;
-  onDelete: () => void;
-  onChangeTitle: (title: string) => void;
-  name: string;
-  repo: string | null;
-  lastUpdated: string; // ISO 8601
-  state?: ProjectState;
-}
-
-export function ConversationCard({
-  onClick,
-  onDelete,
-  onChangeTitle,
-  name,
-  repo,
-  lastUpdated,
-  state = "cold",
-}: ProjectCardProps) {
-  const [contextMenuVisible, setContextMenuVisible] = React.useState(false);
-  const inputRef = React.useRef<HTMLInputElement>(null);
-
-  const handleBlur = () => {
-    if (inputRef.current?.value) {
-      const trimmed = inputRef.current.value.trim();
-      onChangeTitle(trimmed);
-      inputRef.current!.value = trimmed;
-    } else {
-      // reset the value if it's empty
-      inputRef.current!.value = name;
-    }
-  };
-
-  const handleInputClick = (event: React.MouseEvent<HTMLInputElement>) => {
-    event.stopPropagation();
-  };
-
-  const handleDelete = (event: React.MouseEvent<HTMLButtonElement>) => {
-    event.stopPropagation();
-    onDelete();
-  };
-
-  return (
-    <div
-      data-testid="conversation-card"
-      onClick={onClick}
-      className="h-[100px] w-full px-[18px] py-4 border-b border-neutral-600"
-    >
-      <div className="flex items-center justify-between">
-        <input
-          ref={inputRef}
-          data-testid="conversation-card-title"
-          onClick={handleInputClick}
-          onBlur={handleBlur}
-          type="text"
-          defaultValue={name}
-          className="text-sm leading-6 font-semibold bg-transparent"
-        />
-
-        <div className="flex items-center gap-2 relative">
-          <ConversationStateIndicator state={state} />
-          <EllipsisButton
-            onClick={(event) => {
-              event.stopPropagation();
-              setContextMenuVisible((prev) => !prev);
-            }}
-          />
-          {contextMenuVisible && (
-            <ContextMenu testId="context-menu" className="absolute left-full">
-              <ContextMenuListItem
-                testId="delete-button"
-                onClick={handleDelete}
-              >
-                Delete
-              </ContextMenuListItem>
-            </ContextMenu>
-          )}
-        </div>
-      </div>
-      {repo && (
-        <ConversationRepoLink
-          repo={repo}
-          onClick={(e) => e.stopPropagation()}
-        />
-      )}
-      <p className="text-xs text-neutral-400">
-        <time>{formatTimeDelta(new Date(lastUpdated))} ago</time>
-      </p>
-    </div>
-  );
-}

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

@@ -1,128 +0,0 @@
-import React from "react";
-import { useLocation, useNavigate, useParams } from "react-router";
-import { ConversationCard } from "./conversation-card";
-import { useUserConversations } from "#/hooks/query/use-user-conversations";
-import { useDeleteConversation } from "#/hooks/mutation/use-delete-conversation";
-import { ConfirmDeleteModal } from "./confirm-delete-modal";
-import { NewConversationButton } from "./new-conversation-button";
-import { LoadingSpinner } from "#/components/shared/loading-spinner";
-import { useUpdateConversation } from "#/hooks/mutation/use-update-conversation";
-import { useEndSession } from "#/hooks/use-end-session";
-import { ExitConversationModal } from "./exit-conversation-modal";
-
-interface ConversationPanelProps {
-  onClose: () => void;
-}
-
-export function ConversationPanel({ onClose }: ConversationPanelProps) {
-  const { conversationId: cid } = useParams();
-  const navigate = useNavigate();
-  const location = useLocation();
-
-  const endSession = useEndSession();
-
-  const [confirmDeleteModalVisible, setConfirmDeleteModalVisible] =
-    React.useState(false);
-  const [
-    confirmExitConversationModalVisible,
-    setConfirmExitConversationModalVisible,
-  ] = React.useState(false);
-  const [selectedConversationId, setSelectedConversationId] = React.useState<
-    string | null
-  >(null);
-
-  const { data: conversations, isFetching, error } = useUserConversations();
-
-  const { mutate: deleteConversation } = useDeleteConversation();
-  const { mutate: updateConversation } = useUpdateConversation();
-
-  const handleDeleteProject = (conversationId: string) => {
-    setConfirmDeleteModalVisible(true);
-    setSelectedConversationId(conversationId);
-  };
-
-  const handleConfirmDelete = () => {
-    if (selectedConversationId) {
-      deleteConversation({ conversationId: selectedConversationId });
-      setConfirmDeleteModalVisible(false);
-
-      if (cid === selectedConversationId) {
-        endSession();
-      }
-    }
-  };
-
-  const handleChangeTitle = (
-    conversationId: string,
-    oldTitle: string,
-    newTitle: string,
-  ) => {
-    if (oldTitle !== newTitle)
-      updateConversation({
-        id: conversationId,
-        conversation: { name: newTitle },
-      });
-  };
-
-  const handleClickCard = (conversationId: string) => {
-    navigate(`/conversations/${conversationId}`);
-    onClose();
-  };
-
-  return (
-    <div
-      data-testid="conversation-panel"
-      className="w-[350px] h-full border border-neutral-700 bg-neutral-800 rounded-xl"
-    >
-      <div className="pt-4 px-4 flex items-center justify-between">
-        {location.pathname.startsWith("/conversation") && (
-          <NewConversationButton
-            onClick={() => setConfirmExitConversationModalVisible(true)}
-          />
-        )}
-        {isFetching && <LoadingSpinner size="small" />}
-      </div>
-      {error && (
-        <div className="flex flex-col items-center justify-center h-full">
-          <p className="text-danger">{error.message}</p>
-        </div>
-      )}
-      {conversations?.length === 0 && (
-        <div className="flex flex-col items-center justify-center h-full">
-          <p className="text-neutral-400">No conversations found</p>
-        </div>
-      )}
-      {conversations?.map((project) => (
-        <ConversationCard
-          key={project.conversation_id}
-          onClick={() => handleClickCard(project.conversation_id)}
-          onDelete={() => handleDeleteProject(project.conversation_id)}
-          onChangeTitle={(title) =>
-            handleChangeTitle(project.conversation_id, project.name, title)
-          }
-          name={project.name}
-          repo={project.repo}
-          lastUpdated={project.lastUpdated}
-          state={project.state}
-        />
-      ))}
-
-      {confirmDeleteModalVisible && (
-        <ConfirmDeleteModal
-          onConfirm={handleConfirmDelete}
-          onCancel={() => setConfirmDeleteModalVisible(false)}
-        />
-      )}
-
-      {confirmExitConversationModalVisible && (
-        <ExitConversationModal
-          onConfirm={() => {
-            endSession();
-            onClose();
-          }}
-          onClose={() => setConfirmExitConversationModalVisible(false)}
-        />
-      )}
-    </div>
-  );
-}

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

@@ -1,21 +0,0 @@
-interface ConversationRepoLinkProps {
-  repo: string;
-  onClick?: (event: React.MouseEvent<HTMLAnchorElement>) => void;
-}
-
-export function ConversationRepoLink({
-  repo,
-  onClick,
-}: ConversationRepoLinkProps) {
-  return (
-    <a
-      data-testid="conversation-card-repo"
-      href={`https://github.com/${repo}`}
-      target="_blank noopener noreferrer"
-      onClick={onClick}
-      className="text-xs text-neutral-400 hover:text-neutral-200"
-    >
-      {repo}
-    </a>
-  );
-}

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

@@ -1,40 +0,0 @@
-import ColdIcon from "./state-indicators/cold.svg?react";
-import CoolingIcon from "./state-indicators/cooling.svg?react";
-import FinishedIcon from "./state-indicators/finished.svg?react";
-import RunningIcon from "./state-indicators/running.svg?react";
-import WaitingIcon from "./state-indicators/waiting.svg?react";
-import WarmIcon from "./state-indicators/warm.svg?react";
-
-type SVGIcon = React.FunctionComponent<React.SVGProps<SVGSVGElement>>;
-export type ProjectState =
-  | "cold"
-  | "cooling"
-  | "finished"
-  | "running"
-  | "waiting"
-  | "warm";
-
-const INDICATORS: Record<ProjectState, SVGIcon> = {
-  cold: ColdIcon,
-  cooling: CoolingIcon,
-  finished: FinishedIcon,
-  running: RunningIcon,
-  waiting: WaitingIcon,
-  warm: WarmIcon,
-};
-
-interface ConversationStateIndicatorProps {
-  state: ProjectState;
-}
-
-export function ConversationStateIndicator({
-  state,
-}: ConversationStateIndicatorProps) {
-  const StateIcon = INDICATORS[state];
-
-  return (
-    <div data-testid={`${state}-indicator`}>
-      <StateIcon />
-    </div>
-  );
-}