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

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

.github/workflows/e2e-tests.yml

@@ -0,0 +1,227 @@
+name: End-to-End Tests
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened, labeled]
+    branches:
+      - main
+      - develop
+  workflow_dispatch:
+
+jobs:
+  e2e-tests:
+    if: contains(github.event.pull_request.labels.*.name, 'end-to-end') || github.event_name == 'workflow_dispatch'
+    runs-on: ubuntu-latest
+    timeout-minutes: 60
+
+    env:
+      GITHUB_REPO_NAME: ${{ github.repository }}
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        uses: abatilo/actions-poetry@v4
+        with:
+          poetry-version: 2.1.3
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+          cache: 'poetry'
+
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libgtk-3-0 libnotify4 libnss3 libxss1 libxtst6 xauth xvfb libgbm1 libasound2t64 netcat-openbsd
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '22'
+          cache: 'npm'
+          cache-dependency-path: 'frontend/package-lock.json'
+
+      - name: Setup environment for end-to-end tests
+        run: |
+          # Create test results directory
+          mkdir -p test-results
+
+          # Create downloads directory for OpenHands (use a directory in the home folder)
+          mkdir -p $HOME/downloads
+          sudo chown -R $USER:$USER $HOME/downloads
+          sudo chmod -R 755 $HOME/downloads
+
+      - name: Build OpenHands
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          LLM_MODEL: ${{ secrets.LLM_MODEL || 'gpt-4o' }}
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY || 'test-key' }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          INSTALL_DOCKER: 1
+          RUNTIME: docker
+          FRONTEND_PORT: 12000
+          FRONTEND_HOST: 0.0.0.0
+          BACKEND_HOST: 0.0.0.0
+          BACKEND_PORT: 3000
+          ENABLE_BROWSER: true
+          INSTALL_PLAYWRIGHT: 1
+        run: |
+          # Fix poetry.lock file if needed
+          echo "Fixing poetry.lock file if needed..."
+          poetry lock
+
+          # Build OpenHands using make build
+          echo "Running make build..."
+          make build
+
+          # Install Chromium Headless Shell for Playwright (needed for pytest-playwright)
+          echo "Installing Chromium Headless Shell for Playwright..."
+          poetry run playwright install chromium-headless-shell
+
+          # Verify Playwright browsers are installed (for e2e tests only)
+          echo "Verifying Playwright browsers installation for e2e tests..."
+          BROWSER_CHECK=$(poetry run python tests/e2e/check_playwright.py 2>/dev/null)
+
+          if [ "$BROWSER_CHECK" != "chromium_found" ]; then
+            echo "ERROR: Chromium browser not found or not working for e2e tests"
+            echo "$BROWSER_CHECK"
+            exit 1
+          else
+            echo "Playwright browsers are properly installed for e2e tests."
+          fi
+
+          # Docker runtime will handle workspace directory creation
+
+          # Start the application using make run with custom parameters and reduced logging
+          echo "Starting OpenHands using make run..."
+          # Set environment variables to reduce logging verbosity
+          export PYTHONUNBUFFERED=1
+          export LOG_LEVEL=WARNING
+          export UVICORN_LOG_LEVEL=warning
+          export OPENHANDS_LOG_LEVEL=WARNING
+          FRONTEND_PORT=12000 FRONTEND_HOST=0.0.0.0 BACKEND_HOST=0.0.0.0 make run > /tmp/openhands-e2e-test.log 2>&1 &
+
+          # Store the PID of the make run process
+          MAKE_PID=$!
+          echo "OpenHands started with PID: $MAKE_PID"
+
+          # Wait for the application to start
+          echo "Waiting for OpenHands to start..."
+          max_attempts=15
+          attempt=1
+
+          while [ $attempt -le $max_attempts ]; do
+            echo "Checking if OpenHands is running (attempt $attempt of $max_attempts)..."
+
+            # Check if the process is still running
+            if ! ps -p $MAKE_PID > /dev/null; then
+              echo "ERROR: OpenHands process has terminated unexpectedly"
+              echo "Last 50 lines of the log:"
+              tail -n 50 /tmp/openhands-e2e-test.log
+              exit 1
+            fi
+
+            # Check if frontend port is open
+            if nc -z localhost 12000; then
+              # Verify we can get HTML content
+              if curl -s http://localhost:12000 | grep -q "<html"; then
+                echo "SUCCESS: OpenHands is running and serving HTML content on port 12000"
+                break
+              else
+                echo "Port 12000 is open but not serving HTML content yet"
+              fi
+            else
+              echo "Frontend port 12000 is not open yet"
+            fi
+
+            # Show log output on each attempt
+            echo "Recent log output:"
+            tail -n 20 /tmp/openhands-e2e-test.log
+
+            # Wait before next attempt
+            echo "Waiting 10 seconds before next check..."
+            sleep 10
+            attempt=$((attempt + 1))
+
+            # Exit if we've reached the maximum number of attempts
+            if [ $attempt -gt $max_attempts ]; then
+              echo "ERROR: OpenHands failed to start after $max_attempts attempts"
+              echo "Last 50 lines of the log:"
+              tail -n 50 /tmp/openhands-e2e-test.log
+              exit 1
+            fi
+          done
+
+          # Final verification that the app is running
+          if ! nc -z localhost 12000 || ! curl -s http://localhost:12000 | grep -q "<html"; then
+            echo "ERROR: OpenHands is not running properly on port 12000"
+            echo "Last 50 lines of the log:"
+            tail -n 50 /tmp/openhands-e2e-test.log
+            exit 1
+          fi
+
+          # Print success message
+          echo "OpenHands is running successfully on port 12000"
+
+      - name: Run end-to-end tests
+        env:
+          GITHUB_TOKEN: ${{ secrets.E2E_TEST_GITHUB_TOKEN }}
+          LLM_MODEL: ${{ secrets.LLM_MODEL || 'gpt-4o' }}
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY || 'test-key' }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+        run: |
+          # Check if the application is running
+          if ! nc -z localhost 12000; then
+            echo "ERROR: OpenHands is not running on port 12000"
+            echo "Last 50 lines of the log:"
+            tail -n 50 /tmp/openhands-e2e-test.log
+            exit 1
+          fi
+
+          # Run the tests with detailed output
+          cd tests/e2e
+          poetry run python -m pytest \
+            test_settings.py::test_github_token_configuration \
+            test_conversation.py::test_conversation_start \
+            test_browsing_catchphrase.py::test_browsing_catchphrase \
+            -v --no-header --capture=no --timeout=900
+
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: playwright-report
+          path: tests/e2e/test-results/
+          retention-days: 30
+
+      - name: Upload OpenHands logs
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: openhands-logs
+          path: |
+            /tmp/openhands-e2e-test.log
+            /tmp/openhands-e2e-build.log
+            /tmp/openhands-backend.log
+            /tmp/openhands-frontend.log
+            /tmp/backend-health-check.log
+            /tmp/frontend-check.log
+            /tmp/vite-config.log
+            /tmp/makefile-contents.log
+          retention-days: 30
+
+      - name: Cleanup
+        if: always()
+        run: |
+          # Stop OpenHands processes
+          echo "Stopping OpenHands processes..."
+          pkill -f "python -m openhands.server" || true
+          pkill -f "npm run dev" || true
+          pkill -f "make run" || true
+
+          # Print process status for debugging
+          echo "Checking if any OpenHands processes are still running:"
+          ps aux | grep -E "openhands|npm run dev" || true

.github/workflows/lint-fix.yml

@@ -29,6 +29,12 @@ jobs:
         run: |
           cd frontend
           npm install --frozen-lockfile
+      - name: Generate i18n and route types
+        run: |
+          cd frontend
+          npm run make-i18n
+          npx react-router typegen || true
+
       - name: Fix frontend lint issues
         run: |
           cd frontend
@@ -45,7 +51,7 @@ jobs:
           git config --local user.email "openhands@all-hands.dev"
           git config --local user.name "OpenHands Bot"
           git add -A
-          git commit -m "🤖 Auto-fix frontend linting issues"
+          git commit -m "🤖 Auto-fix frontend linting issues" --no-verify
           git push
 
   # Python lint fixes
@@ -87,5 +93,5 @@ jobs:
           git config --local user.email "openhands@all-hands.dev"
           git config --local user.name "OpenHands Bot"
           git add -A
-          git commit -m "🤖 Auto-fix Python linting issues"
+          git commit -m "🤖 Auto-fix Python linting issues" --no-verify
           git push

.github/workflows/py-tests.yml

@@ -51,8 +51,6 @@ jobs:
         run: PYTHONPATH=".:$PYTHONPATH" poetry run pytest --forked -n auto -svv ./tests/unit
       - name: Run Runtime Tests with CLIRuntime
         run: PYTHONPATH=".:$PYTHONPATH" TEST_RUNTIME=cli poetry run pytest -svv tests/runtime/test_bash.py
-      - name: Run E2E Tests
-        run: PYTHONPATH=".:$PYTHONPATH" poetry run pytest -svv tests/e2e
 
   # Run specific Windows python tests
   test-on-windows:
@@ -75,7 +73,7 @@ jobs:
       - name: Install Python dependencies using Poetry
         run: poetry install --with dev,test,runtime
       - name: Run Windows unit tests
-        run: poetry run pytest -svv tests/unit/test_windows_bash.py
+        run: poetry run pytest -svv tests/unit/runtime/utils/test_windows_bash.py
         env:
           PYTHONPATH: ".;$env:PYTHONPATH"
           DEBUG: "1"

.github/workflows/welcome-good-first-issue.yml

@@ -0,0 +1,50 @@
+name: Welcome Good First Issue
+
+on:
+  issues:
+    types: [labeled]
+
+permissions:
+  issues: write
+
+jobs:
+  comment-on-good-first-issue:
+    if: github.event.label.name == 'good first issue'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check if welcome comment already exists
+        id: check_comment
+        uses: actions/github-script@v7
+        with:
+          result-encoding: string
+          script: |
+            const issueNumber = context.issue.number;
+            const comments = await github.rest.issues.listComments({
+              ...context.repo,
+              issue_number: issueNumber
+            });
+
+            const alreadyCommented = comments.data.some(
+              (comment) =>
+                comment.body.includes('<!-- auto-comment:good-first-issue -->')
+            );
+
+            return alreadyCommented ? 'true' : 'false';
+
+      - name: Leave welcome comment
+        if: steps.check_comment.outputs.result == 'false'
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const repoUrl = `https://github.com/${context.repo.owner}/${context.repo.repo}`;
+
+            await github.rest.issues.createComment({
+              ...context.repo,
+              issue_number: context.issue.number,
+              body: "🙌 **Hey there, future contributor!** 🙌\n\n" +
+                    "This issue has been labeled as **good first issue**, which means it's a great place to get started with the OpenHands project.\n\n" +
+                    "If you're interested in working on it, feel free to! No need to ask for permission.\n\n" +
+                    "Be sure to check out our [development setup guide](" + repoUrl + "/blob/main/Development.md) to get your environment set up, and follow our [contribution guidelines](" + repoUrl + "/blob/main/CONTRIBUTING.md) when you're ready to submit a fix.\n\n" +
+                    "🙌 Happy hacking! 🙌\n\n" +
+                    "<!-- auto-comment:good-first-issue -->"
+            });

.gitignore

@@ -254,3 +254,6 @@ containers/runtime/Dockerfile
 containers/runtime/project.tar.gz
 containers/runtime/code
 **/node_modules/
+
+# test results
+test-results

.openhands/microagents/repo.md

@@ -87,6 +87,8 @@ VSCode Extension:
 
 If you are starting a pull request (PR), please follow the template in `.github/pull_request_template.md`.
 
+If you need to add labels when opening a PR, check the existing labels defined on that repository and select from existing ones. Do not invent your own labels.
+
 ## Implementation Details
 
 These details may or may not be useful for your current task.
@@ -142,6 +144,35 @@ Your specialized knowledge and instructions here...
      - Add the setting to the `Settings` model in `openhands/storage/data_models/settings.py`
      - Update any relevant backend code to apply the setting (e.g., in session creation)
 
+#### Settings UI Patterns:
+
+There are two main patterns for saving settings in the OpenHands frontend:
+
+**Pattern 1: Entity-based Resources (Immediate Save)**
+- Used for: API Keys, Secrets, MCP Servers
+- Behavior: Changes are saved immediately when user performs actions (add/edit/delete)
+- Implementation:
+  - No "Save Changes" button
+  - No local state management or `isDirty` tracking
+  - Uses dedicated mutation hooks for each operation (e.g., `use-add-mcp-server.ts`, `use-delete-mcp-server.ts`)
+  - Each mutation triggers immediate API call with query invalidation for UI updates
+  - Example: MCP settings, API Keys & Secrets tabs
+- Benefits: Simpler UX, no risk of losing changes, consistent with modern web app patterns
+
+**Pattern 2: Form-based Settings (Manual Save)**
+- Used for: Application settings, LLM configuration
+- Behavior: Changes are accumulated locally and saved when user clicks "Save Changes"
+- Implementation:
+  - Has "Save Changes" button that becomes enabled when changes are detected
+  - Uses local state management with `isDirty` tracking
+  - Uses `useSaveSettings` hook to save all changes at once
+  - Example: LLM tab, Application tab
+- Benefits: Allows bulk changes, explicit save action, can validate all fields before saving
+
+**When to use each pattern:**
+- Use Pattern 1 (Immediate Save) for entity management where each item is independent
+- Use Pattern 2 (Manual Save) for configuration forms where settings are interdependent or need validation
+
 ### Adding New LLM Models
 
 To add a new LLM model to OpenHands, you need to update multiple files across both frontend and backend:

Development.md

@@ -159,7 +159,7 @@ poetry run pytest ./tests/unit/test_*.py
 To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker
 container image by setting the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
 
-Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.51-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.54-nikolaik`
 
 ## Develop inside Docker container
 

README.md

@@ -52,37 +52,63 @@ which comes with $20 in free credits for new users.
 
 ## 💻 Running OpenHands Locally
 
-OpenHands can also run on your local system using Docker.
-See the [Running OpenHands](https://docs.all-hands.dev/usage/installation) guide for
-system requirements and more information.
+### Option 1: CLI Launcher (Recommended)
 
-> [!WARNING]
-> On a public network? See our [Hardened Docker Installation Guide](https://docs.all-hands.dev/usage/runtimes/docker#hardened-docker-installation)
-> to secure your deployment by restricting network binding and implementing additional security measures.
+The easiest way to run OpenHands locally is using the CLI launcher with [uv](https://docs.astral.sh/uv/). This provides better isolation from your current project's virtual environment and is required for OpenHands' default MCP servers.
 
+**Install uv** (if you haven't already):
+
+See the [uv installation guide](https://docs.astral.sh/uv/getting-started/installation/) for the latest installation instructions for your platform.
+
+**Launch OpenHands**:
+```bash
+# Launch the GUI server
+uvx --python 3.12 --from openhands-ai openhands serve
+
+# Or launch the CLI
+uvx --python 3.12 --from openhands-ai openhands
+```
+
+You'll find OpenHands running at [http://localhost:3000](http://localhost:3000) (for GUI mode)!
+
+### Option 2: Docker
+
+<details>
+<summary>Click to expand Docker command</summary>
+
+You can also run OpenHands directly with Docker:
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.51
+    docker.all-hands.dev/all-hands-ai/openhands:0.54
 ```
 
+</details>
+
 > **Note**: If you used OpenHands before version 0.44, you may want to run `mv ~/.openhands-state ~/.openhands` to migrate your conversation history to the new location.
 
-You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
+> [!WARNING]
+> On a public network? See our [Hardened Docker Installation Guide](https://docs.all-hands.dev/usage/runtimes/docker#hardened-docker-installation)
+> to secure your deployment by restricting network binding and implementing additional security measures.
+
+### Getting Started
 
 When you open the application, you'll be asked to choose an LLM provider and add an API key.
 [Anthropic's Claude Sonnet 4](https://www.anthropic.com/api) (`anthropic/claude-sonnet-4-20250514`)
 works best, but you have [many options](https://docs.all-hands.dev/usage/llms).
 
+See the [Running OpenHands](https://docs.all-hands.dev/usage/installation) guide for
+system requirements and more information.
+
 ## 💡 Other ways to run OpenHands
 
 > [!WARNING]
@@ -93,8 +119,8 @@ works best, but you have [many options](https://docs.all-hands.dev/usage/llms).
 > [OpenHands Cloud Helm Chart](https://github.com/all-Hands-AI/OpenHands-cloud)
 
 You can [connect OpenHands to your local filesystem](https://docs.all-hands.dev/usage/runtimes/docker#connecting-to-your-filesystem),
-run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/usage/how-to/headless-mode),
 interact with it via a [friendly CLI](https://docs.all-hands.dev/usage/how-to/cli-mode),
+run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/usage/how-to/headless-mode),
 or run it on tagged issues with [a github action](https://docs.all-hands.dev/usage/how-to/github-action).
 
 Visit [Running OpenHands](https://docs.all-hands.dev/usage/installation) for more information and setup instructions.

README_CN.md

@@ -51,17 +51,17 @@ OpenHands也可以使用Docker在本地系统上运行。
 
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.51
+    docker.all-hands.dev/all-hands-ai/openhands:0.54
 ```
 
 > **注意**: 如果您在0.44版本之前使用过OpenHands，您可能需要运行 `mv ~/.openhands-state ~/.openhands` 来将对话历史迁移到新位置。

README_JA.md

@@ -42,17 +42,17 @@ OpenHandsはDockerを利用してローカル環境でも実行できます。
 > 公共ネットワークで実行していますか？[Hardened Docker Installation Guide](https://docs.all-hands.dev/usage/runtimes/docker#hardened-docker-installation)を参照して、ネットワークバインディングの制限や追加のセキュリティ対策を実施してください。
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.51
+    docker.all-hands.dev/all-hands-ai/openhands:0.54
 ```
 
 **注**: バージョン0.44以前のOpenHandsを使用していた場合は、会話履歴を移行するために `mv ~/.openhands-state ~/.openhands` を実行してください。

build_vscode.py

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

containers/app/Dockerfile

@@ -21,7 +21,7 @@ ENV POETRY_NO_INTERACTION=1 \
     POETRY_CACHE_DIR=/tmp/poetry_cache
 
 RUN apt-get update -y \
-    && apt-get install -y curl make git build-essential \
+    && apt-get install -y curl make git build-essential jq gettext \
     && python3 -m pip install poetry --break-system-packages
 
 COPY pyproject.toml poetry.lock ./

containers/dev/compose.yml

@@ -12,7 +12,7 @@ services:
       - SANDBOX_API_HOSTNAME=host.docker.internal
       - DOCKER_HOST_ADDR=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.51-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.54-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docker-compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik}
       #- SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234} # enable this only if you want a specific non-root sandbox user but you will have to manually adjust permissions of ~/.openhands for this user
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docs/usage/architecture/backend.mdx

@@ -2,55 +2,102 @@
 title: Backend Architecture
 ---
 
-<div style={{ textAlign: 'center' }}>
-  <img src="https://github.com/All-Hands-AI/OpenHands/assets/16201837/97d747e3-29d8-4ccb-8d34-6ad1adb17f38" alt="OpenHands System Architecture Diagram Jul 4 2024" />
-  <p><em>OpenHands System Architecture Diagram (July 4, 2024)</em></p>
-</div>
 
 This is a high-level overview of the system architecture. The system is divided into two main components: the frontend and the backend. The frontend is responsible for handling user interactions and displaying the results. The backend is responsible for handling the business logic and executing the agents.
 
-# Frontend architecture
+# System overview
 
-![system_architecture.svg](/static/img/system_architecture.svg)
+```mermaid
+flowchart LR
+  U["User"] --> FE["Frontend (SPA)"]
+  FE -- "HTTP/WS" --> BE["OpenHands Backend"]
+  BE --> ES["EventStream"]
+  BE --> ST["Storage"]
+  BE --> RT["Runtime Interface"]
+  BE --> LLM["LLM Providers"]
+
+  subgraph Runtime
+    direction TB
+    RT --> DRT["Docker Runtime"]
+    RT --> LRT["Local Runtime"]
+    RT --> RRT["Remote Runtime"]
+    DRT --> AES["Action Execution Server"]
+    LRT --> AES
+    RRT --> AES
+    AES --> Bash["Bash Session"]
+    AES --> Jupyter["Jupyter Plugin"]
+    AES --> Browser["BrowserEnv"]
+  end
+```
 
 This Overview is simplified to show the main components and their interactions. For a more detailed view of the backend architecture, see the Backend Architecture section below.
 
 # Backend Architecture
 
-_**Disclaimer**: The backend architecture is a work in progress and is subject to change. The following diagram shows the current architecture of the backend based on the commit that is shown in the footer of the diagram._
 
-![backend_architecture.svg](/static/img/backend_architecture.svg)
+```mermaid
+classDiagram
+  class Agent {
+    <<abstract>>
+    +sandbox_plugins: list[PluginRequirement]
+  }
+  class CodeActAgent {
+    +tools
+  }
+  Agent <|-- CodeActAgent
+
+  class EventStream
+  class Observation
+  class Action
+  Action --> Observation
+  Agent --> EventStream
+
+  class Runtime {
+    +connect()
+    +send_action_for_execution()
+  }
+  class ActionExecutionClient {
+    +_send_action_server_request()
+  }
+  class DockerRuntime
+  class LocalRuntime
+  class RemoteRuntime
+  Runtime <|-- ActionExecutionClient
+  ActionExecutionClient <|-- DockerRuntime
+  ActionExecutionClient <|-- LocalRuntime
+  ActionExecutionClient <|-- RemoteRuntime
+
+  class ActionExecutionServer {
+    +/execute_action
+    +/alive
+  }
+  class BashSession
+  class JupyterPlugin
+  class BrowserEnv
+  ActionExecutionServer --> BashSession
+  ActionExecutionServer --> JupyterPlugin
+  ActionExecutionServer --> BrowserEnv
+
+  Agent --> Runtime
+  Runtime ..> ActionExecutionServer : REST
+```
 
 <details>
   <summary>Updating this Diagram</summary>
   <div>
-    The generation of the backend architecture diagram is partially automated.
-    The diagram is generated from the type hints in the code using the py2puml
-    tool. The diagram is then manually reviewed, adjusted and exported to PNG
-    and SVG.
+    We maintain architecture diagrams inline with Mermaid in this MDX.
 
-    ## Prerequisites
-
-    - Running python environment in which openhands is executable
-    (according to the instructions in the README.md file in the root of the repository)
-    - [py2puml](https://github.com/lucsorel/py2puml) installed
-
-## Steps
-
-1.  Autogenerate the diagram by running the following command from the root of the repository:
-    `py2puml openhands openhands > docs/architecture/backend_architecture.puml`
-
-2.  Open the generated file in a PlantUML editor, e.g. Visual Studio Code with the PlantUML extension or [PlantText](https://www.planttext.com/)
-
-3.  Review the generated PUML and make all necessary adjustments to the diagram (add missing parts, fix mistakes, improve positioning).
-    _py2puml creates the diagram based on the type hints in the code, so missing or incorrect type hints may result in an incomplete or incorrect diagram._
-
-4.  Review the diff between the new and the previous diagram and manually check if the changes are correct.
-    _Make sure not to remove parts that were manually added to the diagram in the past and are still relevant._
-
-5.  Add the commit hash of the commit that was used to generate the diagram to the diagram footer.
-
-6.  Export the diagram as PNG and SVG files and replace the existing diagrams in the `docs/architecture` directory. This can be done with (e.g. [PlantText](https://www.planttext.com/))
+    Guidance:
+    - Edit the Mermaid blocks directly (flowchart/classDiagram).
+    - Quote labels and edge text for GitHub preview compatibility.
+    - Keep relationships concise and reflect stable abstractions (agents, runtime client/server, plugins).
+    - Verify accuracy against code:
+      - openhands/runtime/impl/action_execution/action_execution_client.py
+      - openhands/runtime/impl/docker/docker_runtime.py
+      - openhands/runtime/impl/local/local_runtime.py
+      - openhands/runtime/action_execution_server.py
+      - openhands/runtime/plugins/*
+    - Build docs locally or view on GitHub to confirm diagrams render.
 
   </div>
 </details>

docs/usage/architecture/runtime.mdx

@@ -52,7 +52,7 @@ graph TD
 2. Image Building: OpenHands builds a new Docker image (the "OH runtime image") based on the user-provided image. This new image includes OpenHands-specific code, primarily the "runtime client"
 3. Container Launch: When OpenHands starts, it launches a Docker container using the OH runtime image
 4. Action Execution Server Initialization: The action execution server initializes an `ActionExecutor` inside the container, setting up necessary components like a bash shell and loading any specified plugins
-5. Communication: The OpenHands backend (`openhands/runtime/impl/eventstream/eventstream_runtime.py`) communicates with the action execution server over RESTful API, sending actions and receiving observations
+5. Communication: The OpenHands backend (client: `openhands/runtime/impl/action_execution/action_execution_client.py`; runtimes: `openhands/runtime/impl/docker/docker_runtime.py`, `openhands/runtime/impl/local/local_runtime.py`) communicates with the action execution server over RESTful API, sending actions and receiving observations
 6. Action Execution: The runtime client receives actions from the backend, executes them in the sandboxed environment, and sends back observations
 7. Observation Return: The action execution server sends execution results back to the OpenHands backend as observations
 
@@ -72,7 +72,7 @@ Check out the [relevant code](https://github.com/All-Hands-AI/OpenHands/blob/mai
 ### Image Tagging System
 
 OpenHands uses a three-tag system for its runtime images to balance reproducibility with flexibility.
-Tags may be in one of 2 formats:
+The tags are:
 
 - **Versioned Tag**: `oh_v{openhands_version}_{base_image}` (e.g.: `oh_v0.9.9_nikolaik_s_python-nodejs_t_python3.12-nodejs22`)
 - **Lock Tag**: `oh_v{openhands_version}_{16_digit_lock_hash}` (e.g.: `oh_v0.9.9_1234567890abcdef`)
@@ -119,18 +119,52 @@ This tagging approach allows OpenHands to efficiently manage both development an
 2. The system can quickly rebuild images when minor changes occur (by leveraging recent compatible images)
 3. The **lock** tag (e.g., `runtime:oh_v0.9.3_1234567890abcdef`) always points to the latest build for a particular base image, dependency, and OpenHands version combination
 
+## Volume mounts: named volumes and overlay
+
+OpenHands supports both bind mounts and Docker named volumes in SandboxConfig.volumes:
+
+- Bind mount: "/abs/host/path:/container/path[:mode]"
+- Named volume: "volume:<name>:/container/path[:mode]" or any non-absolute host spec treated as a named volume
+
+Overlay mode (copy-on-write layer) is supported for bind mounts by appending ":overlay" to the mode (e.g., ":ro,overlay").
+To enable overlay COW, set SANDBOX_VOLUME_OVERLAYS to a writable host directory; per-container upper/work dirs are created under it. If SANDBOX_VOLUME_OVERLAYS is unset, overlay mounts are skipped.
+
+Implementation references:
+- openhands/runtime/impl/docker/docker_runtime.py (named volumes in _build_docker_run_args; overlay mounts in _process_overlay_mounts)
+- openhands/core/config/sandbox_config.py (volumes field)
+
+
 ## Runtime Plugin System
 
-The OpenHands Runtime supports a plugin system that allows for extending functionality and customizing the runtime environment. Plugins are initialized when the runtime client starts up.
+The OpenHands Runtime supports a plugin system that allows for extending functionality and customizing the runtime environment. Plugins are initialized when the action execution server starts up inside the runtime.
 
-Check [an example of Jupyter plugin here](https://github.com/All-Hands-AI/OpenHands/blob/ecf4aed28b0cf7c18d4d8ff554883ba182fc6bdd/openhands/runtime/plugins/jupyter/__init__.py#L21-L55) if you want to implement your own plugin.
+## Ports and URLs
 
-*More details about the Plugin system are still under construction - contributions are welcomed!*
+- Host port allocation uses file-locked ranges for stability and concurrency:
+  - Main runtime port: find_available_port_with_lock on configured range
+  - VSCode port: SandboxConfig.sandbox.vscode_port if provided, else find_available_port_with_lock in VSCODE_PORT_RANGE
+  - App ports: two additional ranges for plugin/web apps
+- DOCKER_HOST_ADDR (if set) adjusts how URLs are formed for LocalRuntime/Docker environments.
+- VSCode URL is exposed with a connection token from the action execution server endpoint /vscode/connection_token and rendered as:
+  - Docker/Local: http://localhost:{port}/?tkn={token}&folder={workspace_mount_path_in_sandbox}
+  - RemoteRuntime: scheme://vscode-{host}/?tkn={token}&folder={workspace_mount_path_in_sandbox}
+
+References:
+- openhands/runtime/impl/docker/docker_runtime.py (port ranges, locking, DOCKER_HOST_ADDR, vscode_url)
+- openhands/runtime/impl/local/local_runtime.py (vscode_url factory)
+- openhands/runtime/impl/remote/remote_runtime.py (vscode_url mapping)
+- openhands/runtime/action_execution_server.py (/vscode/connection_token)
+
+
+Examples:
+- Jupyter: openhands/runtime/plugins/jupyter/__init__.py (JupyterPlugin, Kernel Gateway)
+- VS Code: openhands/runtime/plugins/vscode/* (VSCodePlugin, exposes tokenized URL)
+- Agent Skills: openhands/runtime/plugins/agent_skills/*
 
 Key aspects of the plugin system:
 
 1. Plugin Definition: Plugins are defined as Python classes that inherit from a base `Plugin` class
-2. Plugin Registration: Available plugins are registered in an `ALL_PLUGINS` dictionary
+2. Plugin Registration: Available plugins are registered in `openhands/runtime/plugins/__init__.py` via `ALL_PLUGINS`
 3. Plugin Specification: Plugins are associated with `Agent.sandbox_plugins: list[PluginRequirement]`. Users can specify which plugins to load when initializing the runtime
-4. Initialization: Plugins are initialized asynchronously when the runtime client starts
-5. Usage: The runtime client can use initialized plugins to extend its capabilities (e.g., the JupyterPlugin for running IPython cells)
+4. Initialization: Plugins are initialized asynchronously when the runtime starts and are accessible to actions
+5. Usage: Plugins extend capabilities (e.g., Jupyter for IPython cells); the server exposes any web endpoints (ports) via host port mapping

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

@@ -78,6 +78,14 @@ description: Complete guide for setting up Jira Data Center integration with Ope
          - **Service Account API Key**: The personal access token from Step 2 above
          - Ensure **Active** toggle is enabled
 
+<Note>
+Workspace name is the host name of your Jira Data Center instance.
+
+Eg: http://jira.all-hands.dev/projects/OH/issues/OH-77
+
+Here the workspace name is **jira.all-hands.dev**.
+</Note>
+
 3. **Complete OAuth Flow**
    - You'll be redirected to Jira Data Center to complete OAuth verification
    - Grant the necessary permissions to verify your workspace access. If you have access to multiple workspaces, select the correct one that you initially provided
@@ -101,18 +109,18 @@ description: Complete guide for setting up Jira Data Center integration with Ope
 
 <AccordionGroup>
 <Accordion title="Workspace link flow">
-![workspace-link.png](/static/img/workspace-link.png)
+![workspace-link.png](/static/img/jira-dc-user-link.png)
 </Accordion>
 
 <Accordion title="Workspace Configure flow">
-![workspace-link.png](/static/img/workspace-configure.png)
+![workspace-link.png](/static/img/jira-dc-admin-configure.png)
 </Accordion>
 
 <Accordion title="Edit view as a user">
-![workspace-link.png](/static/img/workspace-user-edit.png)
+![workspace-link.png](/static/img/jira-dc-user-unlink.png)
 </Accordion>
 
 <Accordion title="Edit view as the workspace creator">
-![workspace-link.png](/static/img/workspace-admin-edit.png)
+![workspace-link.png](/static/img/jira-dc-admin-edit.png)
 </Accordion>
 </AccordionGroup>

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

@@ -15,28 +15,27 @@ description: Complete guide for setting up Jira Cloud integration with OpenHands
    - Go to **Directory** > **Users**
 
 2. **Create OpenHands Service Account**
-   - Click **Add user**
-   - Email: `openhands@yourcompany.com` (replace with your preferred service account email)
-   - Display name: `OpenHands Agent`
-   - Send invitation: **No** (you'll set password manually)
-   - Click **Add user**
-
-3. **Configure Account**
-   - Locate the created user and click on it
-   - Set a secure password
-   - Add to relevant Jira projects with appropriate permissions
+   - Click **Service accounts**
+   - Click **Create a service account**
+   - Name: `OpenHands Agent`
+   - Click **Next**
+   - Select **User** role for Jira app
+   - Click **Create**
 
 ### Step 2: Generate API Token
 
-1. **Access API Token Management**
-   - Log in as the OpenHands service account
-   - Go to [API Tokens](https://id.atlassian.com/manage-profile/security/api-tokens)
-
-2. **Create API Token**
+1. **Access Service Account Configuration**
+   - Locate the created service account from above step and click on it
    - Click **Create API token**
-   - Label: `OpenHands Cloud Integration`
-   - Expiry: Set appropriate expiration (recommend 1 year)
-   - Click **Create**
+   - Set the expiry to 365 days (maximum allowed value)
+   - Click **Next**
+   - In **Select token scopes** screen, filter by following values
+      - App: Jira
+      - Scope type: Classic
+      - Scope actions: Write, Read
+   - Select `read:jira-work` and `write:jira-work` scopes
+   - Click **Next**
+   - Review and create API token
    - **Important**: Copy and securely store the token immediately
 
 ### Step 3: Configure Webhook
@@ -83,6 +82,14 @@ description: Complete guide for setting up Jira Cloud integration with OpenHands
          - **Service Account API Key**: The API token from Step 2 above
          - Ensure **Active** toggle is enabled
 
+<Note>
+Workspace name is the host name when accessing a resource in Jira Cloud.
+
+Eg: https://all-hands.atlassian.net/browse/OH-55
+
+Here the workspace name is **all-hands**.
+</Note>
+
 3. **Complete OAuth Flow**
    - You'll be redirected to Jira Cloud to complete OAuth verification
    - Grant the necessary permissions to verify your workspace access.
@@ -106,18 +113,18 @@ description: Complete guide for setting up Jira Cloud integration with OpenHands
 
 <AccordionGroup>
 <Accordion title="Workspace link flow">
-![workspace-link.png](/static/img/workspace-link.png)
+![workspace-link.png](/static/img/jira-user-link.png)
 </Accordion>
 
 <Accordion title="Workspace Configure flow">
-![workspace-link.png](/static/img/workspace-configure.png)
+![workspace-link.png](/static/img/jira-admin-configure.png)
 </Accordion>
 
 <Accordion title="Edit view as a user">
-![workspace-link.png](/static/img/workspace-user-edit.png)
+![workspace-link.png](/static/img/jira-user-unlink.png)
 </Accordion>
 
 <Accordion title="Edit view as the workspace creator">
-![workspace-link.png](/static/img/workspace-admin-edit.png)
+![workspace-link.png](/static/img/jira-admin-edit.png)
 </Accordion>
 </AccordionGroup>

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

@@ -28,7 +28,7 @@ description: Complete guide for setting up Linear integration with OpenHands Clo
 
 1. **Access API Settings**
    - Log in as the service account
-   - Go to **Settings** > **API**
+   - Go to **Settings** > **Security & access**
 
 2. **Create Personal API Key**
    - Click **Create new key**
@@ -82,6 +82,14 @@ description: Complete guide for setting up Linear integration with OpenHands Clo
          - **Service Account API Key**: The API key from Step 2 above
          - Ensure **Active** toggle is enabled
 
+<Note>
+Workspace name is the identifier after the host name when accessing a resource in Linear.
+
+Eg: https://linear.app/allhands/issue/OH-37
+
+Here the workspace name is **allhands**.
+</Note>
+
 3. **Complete OAuth Flow**
    - You'll be redirected to Linear to complete OAuth verification
    - Grant the necessary permissions to verify your workspace access. If you have access to multiple workspaces, select the correct one that you initially provided
@@ -105,15 +113,15 @@ description: Complete guide for setting up Linear integration with OpenHands Clo
 
 <AccordionGroup>
 <Accordion title="Workspace link flow">
-![workspace-link.png](/static/img/workspace-link.png)
+![workspace-link.png](/static/img/linear-user-link.png)
 </Accordion>
 
 <Accordion title="Workspace Configure flow">
-![workspace-link.png](/static/img/workspace-configure.png)
+![workspace-link.png](/static/img/linear-admin-configure.png)
 </Accordion>
 
 <Accordion title="Edit view as a user">
-![workspace-link.png](/static/img/workspace-user-edit.png)
+![workspace-link.png](/static/img/linear-admin-edit.png)
 </Accordion>
 
 <Accordion title="Edit view as the workspace creator">

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

@@ -58,17 +58,18 @@ The OpenHands agent needs to identify which Git repository to work with when pro
 
 ### Platform Configuration Issues
 - **Webhook not triggering**: Verify the webhook URL is correct and the proper event types are selected (Comment, Issue updated)
-- **API authentication failing**: Check API key/token validity and ensure required scopes are granted
+- **API authentication failing**: Check API key/token validity and ensure required scopes are granted. If your current API token is expired, make sure to update it in the respective integration settings
 - **Permission errors**: Ensure the service account has access to relevant projects/teams and appropriate permissions
 
 ### Workspace Integration Issues
 - **Workspace linking requests credentials**: If there are no active workspace integrations for the workspace you specified, you need to configure it first. Contact your platform administrator that you want to integrate with (eg: Jira, Linear)
-- **OAuth flow fails**: Ensure you're signing in with the same Git provider account that contains the repositories you want OpenHands to work on
 - **Integration not found**: Verify the workspace name matches exactly and that platform configuration was completed first
+- **OAuth flow fails**: Make sure that you're authorizing with the correct account with proper workspace access
 
 ### General Issues
 - **Agent not responding**: Check webhook logs in your platform settings and verify service account status
 - **Authentication errors**: Verify Git provider permissions and OpenHands Cloud access
+- **Agent fails to identify git repo**: Ensure you're signing in with the same Git provider account that contains the repositories you want OpenHands to work on
 - **Partial functionality**: Ensure both platform configuration and workspace integration are properly completed
 
 ### Getting Help

docs/usage/cloud/slack-installation.mdx

@@ -65,7 +65,7 @@ To send follow-up messages for the same conversation, mention `@openhands` in a
 
 Conversation is started by mentioning `@openhands`.
 
-![slack-create-convo.png](/static/img/slack-create-convo.png)
+![slack-create-conversation.png](/static/img/slack-create-conversation.png)
 
 ### See agent response and send follow up messages
 

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

@@ -20,27 +20,42 @@ for scripting.
 
 ### Running with Python
 
-**Note** - OpenHands requires Python version 3.12 or higher (Python 3.14 is not currently supported) and `uvx` for the default `fetch` MCP server (more details below).
+**Note** - OpenHands requires Python version 3.12 or higher (Python 3.14 is not currently supported) and `uv` for the default `fetch` MCP server (more details below).
 
-1. Install OpenHands using pip:
-```bash
-pip install openhands-ai
-```
+#### Recommended: Using uv
 
-  Or if you prefer not to manage your own Python environment, you can use `uvx`:
+We recommend using [uv](https://docs.astral.sh/uv/) for the best OpenHands experience. uv provides better isolation from your current project's virtual environment and is required for OpenHands' default MCP servers.
 
+1. **Install uv** (if you haven't already):
+
+   See the [uv installation guide](https://docs.astral.sh/uv/getting-started/installation/) for the latest installation instructions for your platform.
+
+2. **Launch OpenHands CLI**:
 ```bash
 uvx --python 3.12 --from openhands-ai openhands
 ```
 
 <AccordionGroup>
 
+<Accordion title="Alternative: Traditional pip installation">
+
+If you prefer to use pip:
+
+```bash
+# Install OpenHands
+pip install openhands-ai
+```
+
+Note that you'll still need `uv` installed for the default MCP servers to work properly.
+
+</Accordion>
+
 <Accordion title="Create shell aliases for easy access across environments">
 
 Add the following to your shell configuration file (`.bashrc`, `.zshrc`, etc.):
 
 ```bash
-# Add OpenHands aliases
+# Add OpenHands aliases (recommended)
 alias openhands="uvx --python 3.12 --from openhands-ai openhands"
 alias oh="uvx --python 3.12 --from openhands-ai openhands"
 ```
@@ -72,18 +87,19 @@ source ~/.bashrc  # or source ~/.zshrc
 
 </AccordionGroup>
 
-2. Launch an interactive OpenHands conversation from the command line:
+3. Launch an interactive OpenHands conversation from the command line:
 ```bash
-openhands
+# If using uvx (recommended)
+uvx --python 3.12 --from openhands-ai openhands
 ```
 
 <Note>
   If you have cloned the repository, you can also run the CLI directly using Poetry:
 
-  poetry run python -m openhands.cli.main
+  poetry run openhands
 </Note>
 
-3. Set your model, API key, and other preferences using the UI (or alternatively environment variables, below).
+4. Set your model, API key, and other preferences using the UI (or alternatively environment variables, below).
 
 This command opens an interactive prompt where you can type tasks or commands and get responses from OpenHands.
 The first time you run the CLI, it will take you through configuring the required LLM
@@ -103,7 +119,7 @@ The conversation history will be saved in `~/.openhands/sessions`.
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e SANDBOX_VOLUMES=$SANDBOX_VOLUMES \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -112,8 +128,8 @@ docker run -it \
     -v ~/.openhands:/.openhands \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.51 \
-    python -m openhands.cli.main --override-cli-mode true
+    docker.all-hands.dev/all-hands-ai/openhands:0.54 \
+    python -m openhands.cli.entry --override-cli-mode true
 ```
 
 <Note>

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

@@ -61,7 +61,7 @@ export GITHUB_TOKEN="your-token"  # Required for repository operations
 # Run OpenHands
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e SANDBOX_VOLUMES=$SANDBOX_VOLUMES \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -73,7 +73,7 @@ docker run -it \
     -v ~/.openhands:/.openhands \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.51 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.54 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/usage/llms/local-llms.mdx

@@ -68,23 +68,23 @@ Download and install the LM Studio desktop app from [lmstudio.ai](https://lmstud
 1. Check [the installation guide](/usage/local-setup) and ensure all prerequisites are met before running OpenHands, then run:
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.51
+    docker.all-hands.dev/all-hands-ai/openhands:0.54
 ```
 
 2. Wait until the server is running (see log below):
 ```
 Digest: sha256:e72f9baecb458aedb9afc2cd5bc935118d1868719e55d50da73190d3a85c674f
-Status: Image is up to date for docker.all-hands.dev/all-hands-ai/openhands:0.51
+Status: Image is up to date for docker.all-hands.dev/all-hands-ai/openhands:0.54
 Starting OpenHands...
 Running OpenHands as root
 14:22:13 - openhands:INFO: server_config.py:50 - Using config class None

docs/usage/local-setup.mdx

@@ -66,9 +66,31 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
 
 ### Start the App
 
-#### Option 1: Using the CLI Launcher (Recommended)
+#### Option 1: Using the CLI Launcher with uv (Recommended)
 
-If you have Python 3.12+ installed, you can use the CLI launcher for a simpler experience:
+We recommend using [uv](https://docs.astral.sh/uv/) for the best OpenHands experience. uv provides better isolation from your current project's virtual environment and is required for OpenHands' default MCP servers (like the [fetch MCP server](https://github.com/modelcontextprotocol/servers/tree/main/src/fetch)).
+
+**Install uv** (if you haven't already):
+
+See the [uv installation guide](https://docs.astral.sh/uv/getting-started/installation/) for the latest installation instructions for your platform.
+
+**Launch OpenHands**:
+```bash
+# Launch the GUI server
+uvx --python 3.12 --from openhands-ai openhands serve
+
+# Or with GPU support (requires nvidia-docker)
+uvx --python 3.12 --from openhands-ai openhands serve --gpu
+
+# Or with current directory mounted
+uvx --python 3.12 --from openhands-ai openhands serve --mount-cwd
+```
+
+This will automatically handle Docker requirements checking, image pulling, and launching the GUI server. The `--gpu` flag enables GPU support via nvidia-docker, and `--mount-cwd` mounts your current directory into the container.
+
+<Accordion title="Alternative: Traditional pip installation">
+
+If you prefer to use pip and have Python 3.12+ installed:
 
 ```bash
 # Install OpenHands
@@ -76,34 +98,32 @@ pip install openhands-ai
 
 # Launch the GUI server
 openhands serve
-
-# Or with GPU support (requires nvidia-docker)
-openhands serve --gpu
-
-# Or with current directory mounted
-openhands serve --mount-cwd
 ```
 
-Or using `uvx --python 3.12 --from openhands-ai openhands serve` if you have [uv](https://docs.astral.sh/uv/) installed.
+Note that you'll still need `uv` installed for the default MCP servers to work properly.
 
-This will automatically handle Docker requirements checking, image pulling, and launching the GUI server. The `--gpu` flag enables GPU support via nvidia-docker, and `--mount-cwd` mounts your current directory into the container.
+</Accordion>
 
 #### Option 2: Using Docker Directly
 
+<Accordion title="Docker Command (Click to expand)">
+
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.54-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.51
+    docker.all-hands.dev/all-hands-ai/openhands:0.54
 ```
 
+</Accordion>
+
 > **Note**: If you used OpenHands before version 0.44, you may want to run `mv ~/.openhands-state ~/.openhands` to migrate your conversation history to the new location.
 
 You'll find OpenHands running at http://localhost:3000!

docs/usage/runtimes/docker.mdx

@@ -130,3 +130,28 @@ docker run # ... \
 <Note>
 **Docker Desktop Required**: Network isolation features, including custom networks and `host.docker.internal` routing, require Docker Desktop. Docker Engine alone does not support these features on localhost across custom networks. If you're using Docker Engine without Docker Desktop, network isolation may not work as expected.
 </Note>
+
+### Sidecar Containers
+
+If you want to run sidecar containers to the sandbox 'runner' containers without exposing the sandbox containers to the host network, you can use the `SANDBOX_ADDITIONAL_NETWORKS` environment variable to specify additional Docker network names that should be added to the sandbox containers.
+
+```bash
+docker network create openhands-sccache
+
+docker run -d \
+  --hostname openhandsredis \
+  --network openhands-sccache \
+  redis
+
+docker run # ...
+    -e SANDBOX_ADDITIONAL_NETWORKS='["openhands-sccache"]' \
+    # ...
+```
+
+Then all sandbox instances will have to access a shared redis instance at `openhandsredis:6379`.
+
+#### Docker Compose gotcha
+
+Note that Docker Compose adds a prefix (a scope) by default to created networks, which is not taken into account by the additional networks config. Therefore when using docker compose you have to either:
+- specify a network name via the `name` field to remove the scoping (https://docs.docker.com/reference/compose-file/networks/#name) 
+- or provide the scope within the given config (e.g. `SANDBOX_ADDITIONAL_NETWORKS: '["myscope_openhands-sccache"]'` where `myscope` is the docker-compose assigned prefix). 

evaluation/benchmarks/EDA/run_infer.py

@@ -10,6 +10,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -146,7 +147,7 @@ def process_instance(
 
     logger.info(f'Final message: {final_message} | Ground truth: {instance["text"]}')
     test_result = game.reward()
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
 
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here

evaluation/benchmarks/agent_bench/run_infer.py

@@ -18,6 +18,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -273,7 +274,7 @@ def process_instance(
     # remove when it becomes unnecessary
     histories = compatibility_for_eval_history_pairs(state.history)
 
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
 
     # Save the output
     output = EvalOutput(

evaluation/benchmarks/aider_bench/run_infer.py

@@ -17,6 +17,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -246,7 +247,7 @@ def process_instance(
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
     histories = compatibility_for_eval_history_pairs(state.history)
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
 
     # Save the output
     output = EvalOutput(

evaluation/benchmarks/biocoder/run_infer.py

@@ -15,6 +15,7 @@ from evaluation.utils.shared import (
     codeact_user_response,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -294,7 +295,7 @@ def process_instance(
         raise ValueError('State should not be None.')
 
     test_result = complete_runtime(runtime, instance)
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary

evaluation/benchmarks/bird/run_infer.py

@@ -18,6 +18,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -422,7 +423,7 @@ def process_instance(
     # You can simply get the LAST `MessageAction` from the returned `state.history` and parse it for evaluation.
     if state is None:
         raise ValueError('State should not be None.')
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
 
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here

evaluation/benchmarks/browsing_delegation/run_infer.py

@@ -11,6 +11,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -88,7 +89,7 @@ def process_instance(
     if state is None:
         raise ValueError('State should not be None.')
 
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary

evaluation/benchmarks/commit0/run_infer.py

@@ -16,6 +16,7 @@ from evaluation.utils.shared import (
     assert_and_raise,
     codeact_user_response,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -480,7 +481,7 @@ def process_instance(
 
     # NOTE: this is NO LONGER the event stream, but an agent history that includes delegate agent's events
     histories = [event_to_dict(event) for event in state.history]
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
 
     # Save the output
     output = EvalOutput(
@@ -506,7 +507,6 @@ def commit0_setup(dataset: pd.DataFrame, repo_split: str) -> pd.DataFrame:
     Returns:
         Filtered dataset based on split type
     """
-
     filtered_dataset = pd.concat(
         [
             dataset[dataset['repo'].str.split('/').str[1] == repo]

evaluation/benchmarks/discoverybench/run_infer.py

@@ -17,6 +17,7 @@ from evaluation.utils.shared import (
     codeact_user_response,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -89,8 +90,7 @@ def get_config(
 def get_dv_query_for_real(
     datasets, question, domain_knowledge=None, workflow_tags=None
 ):
-    """
-    Prepare a structured query for the agent to execute on the specified datasets.
+    """Prepare a structured query for the agent to execute on the specified datasets.
 
     This function constructs a query by compiling metadata from the provided datasets, along with any relevant domain knowledge and workflow tags.
 
@@ -104,7 +104,6 @@ def get_dv_query_for_real(
         query_to_dv: Query to be run on the dataset
         dataset_meta: Metadata of the dataset
     """
-
     dataset_meta = ''
     for dataset_metadata in datasets:
         dataset_meta += 'Dataset name: ' + dataset_metadata['name']
@@ -140,8 +139,7 @@ def get_dv_query_for_real(
 
 
 def initialize_runtime(runtime: Runtime, data_files: list[str]):
-    """
-    Initialize the runtime for the agent.
+    """Initialize the runtime for the agent.
 
     This function is called before the runtime is used to run the agent.
     """
@@ -231,8 +229,7 @@ def process_instance(
     metadata: EvalMetadata,
     reset_logger: bool = True,
 ):
-    """
-    Process and evaluate a single instance of the dataset.
+    """Process and evaluate a single instance of the dataset.
 
     This function executes the OpenHands agent
     for a specific instance of the dataset. It retrieves
@@ -247,7 +244,6 @@ def process_instance(
     Returns:
         output: EvalOutput object
     """
-
     config = get_config(metadata)
 
     # Setup the logger properly, so you can run
@@ -299,7 +295,7 @@ def process_instance(
     if state is None:
         raise ValueError('State should not be None.')
 
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
     test_result = complete_runtime(state)
 
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
@@ -356,8 +352,7 @@ def list_csv_files(list_of_datasets):
 
 
 def create_dataset(repo_location: str, split: str = 'test'):
-    """
-    Create a dataset from the discoverybench repository
+    """Create a dataset from the discoverybench repository
     by walking through the repository and extracting metadata
     from the metadata_{}.json files
 
@@ -368,7 +363,6 @@ def create_dataset(repo_location: str, split: str = 'test'):
     Returns:
         df: DataFrame containing the dataset instances
     """
-
     data_dict = {}
 
     data_location = os.path.join(repo_location, 'discoverybench', 'real', split)

evaluation/benchmarks/gaia/run_infer.py

@@ -22,6 +22,7 @@ from evaluation.utils.shared import (
     codeact_user_response,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -269,7 +270,7 @@ Here is the task:
         'model_answer': model_answer,
         'ground_truth': instance['Final answer'],
     }
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
 
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here

evaluation/benchmarks/gorilla/run_infer.py

@@ -12,6 +12,7 @@ from evaluation.utils.shared import (
     codeact_user_response,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -108,7 +109,7 @@ def process_instance(
     # attempt to parse model_answer
     ast_eval_fn = instance['ast_eval']
     correct, hallucination = ast_eval_fn(instance_id, model_answer_raw)
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
     logger.info(
         f'Final message: {model_answer_raw} | Correctness: {correct} | Hallucination: {hallucination}'
     )

evaluation/benchmarks/gpqa/run_infer.py

@@ -30,6 +30,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -292,7 +293,7 @@ Ok now its time to start solving the question. Good luck!
     if state is None:
         raise ValueError('State should not be None.')
 
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
 
     # Save the output
     output = EvalOutput(

evaluation/benchmarks/humanevalfix/run_infer.py

@@ -23,6 +23,7 @@ from evaluation.utils.shared import (
     codeact_user_response,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -248,7 +249,7 @@ def process_instance(
 
     if state is None:
         raise ValueError('State should not be None.')
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
     test_result = complete_runtime(runtime, instance)
 
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)

evaluation/benchmarks/lca_ci_build_repair/run_infer.py

@@ -22,6 +22,7 @@ from evaluation.utils.shared import (
     codeact_user_response,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -335,7 +336,7 @@ Be thorough in your exploration, testing, and reasoning. It's fine if your think
         )
     )
     assert state is not None
-    metrics = state.metrics.get() if state.metrics else {}
+    metrics = get_metrics(state)
 
     test_result = complete_runtime(runtime, instance)
 

evaluation/benchmarks/logic_reasoning/run_infer.py

@@ -10,6 +10,7 @@ from evaluation.utils.shared import (
     codeact_user_response,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -247,7 +248,7 @@ def process_instance(
     )
     test_result['final_message'] = final_message
 
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary

evaluation/benchmarks/miniwob/run_infer.py

@@ -13,6 +13,7 @@ from evaluation.utils.shared import (
     codeact_user_response,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -174,7 +175,7 @@ def process_instance(
     if state is None:
         raise ValueError('State should not be None.')
 
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
 
     # Instruction is the first message from the USER
     instruction = ''

evaluation/benchmarks/mint/run_infer.py

@@ -15,6 +15,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -205,7 +206,7 @@ def process_instance(
         task_state = state.extra_data['task_state']
         logger.info('Task state: ' + str(task_state.to_dict()))
 
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
 
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here

evaluation/benchmarks/ml_bench/run_infer.py

@@ -26,6 +26,7 @@ from evaluation.utils.shared import (
     codeact_user_response,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -250,7 +251,7 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
         )
     )
     assert state is not None
-    metrics = state.metrics.get() if state.metrics else {}
+    metrics = get_metrics(state)
 
     test_result = complete_runtime(runtime)
 

evaluation/benchmarks/multi_swe_bench/eval_infer.py

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

evaluation/benchmarks/nocode_bench/README.md

@@ -0,0 +1,45 @@
+# Evaluate OpenHands on NoCode-bench
+
+## LLM Setup
+
+Please follow [here](../../README.md#setup).
+
+
+## Docker image download
+
+Evaluating OpenHands on NoCode-bench need instance-level docker image.
+Please follow the instructions of NoCode-bench image setup to build or download all instance-level dokcer [here](https://github.com/NoCode-bench/NoCode-bench).
+
+## Generate patch
+
+Please follow the instructions [here](../swe_bench/README.md#running-locally-with-docker)
+For example,
+```bash
+bash ./evaluation/benchmarks/nocode_bench/scripts/run_infer_nc.sh llm.claude HEAD CodeActAgent 114 100 10 NoCode-bench/NoCode-bench_Verified test
+```
+The results will be generated in evaluation/evaluation_outputs/outputs/XXX/CodeActAgent/YYY/output.jsonl.
+
+## Runing evaluation
+
+First, install [NoCode-bench](https://github.com/NoCode-bench/NoCode-bench).
+
+Second, convert the output.jsonl to patch.jsonl with [script](scripts/eval/convert.py).
+
+```bash
+python evaluation/benchmarks/multi_swe_bench/scripts/eval/convert.py
+```
+
+Finally, evaluate with NoCode-bench.
+
+```bash
+export PYTHONPATH=$PYTHONPATH:$(pwd)
+python ./evaluation/eval.py \
+    --predictions_path ./all_preds.jsonl \  # <path_to_your_predictions>
+    --log_dir ./evaluation/logs \ # <path_to_your_log_dir>
+    --bench_tasks NoCode-bench/NoCode-bench_Verified \ # <dataset_name>
+    --max_workers 110 \ # <number_of_workers>
+    --output_file eval_result.txt \ # <path_to_your_output_file>
+    --image_level repo \ # <cache_image_level>
+    --timeout 600 \ # <timeout_in_seconds>
+    --proxy None # <proxy_if_needed>
+```

evaluation/benchmarks/nocode_bench/binary_patch_utils.py

@@ -0,0 +1,52 @@
+"""
+Utilities for handling binary files and patch generation in SWE-bench evaluation.
+"""
+
+
+def remove_binary_diffs(patch_text):
+    """
+    Remove binary file diffs from a git patch.
+
+    Args:
+        patch_text (str): The git patch text
+
+    Returns:
+        str: The cleaned patch text with binary diffs removed
+    """
+    lines = patch_text.splitlines()
+    cleaned_lines = []
+    block = []
+    is_binary_block = False
+
+    for line in lines:
+        if line.startswith('diff --git '):
+            if block and not is_binary_block:
+                cleaned_lines.extend(block)
+            block = [line]
+            is_binary_block = False
+        elif 'Binary files' in line:
+            is_binary_block = True
+            block.append(line)
+        else:
+            block.append(line)
+
+    if block and not is_binary_block:
+        cleaned_lines.extend(block)
+    return '\n'.join(cleaned_lines)
+
+
+def remove_binary_files_from_git():
+    """
+    Generate a bash command to remove binary files from git staging.
+
+    Returns:
+        str: A bash command that removes binary files from git staging
+    """
+    return """
+    for file in $(git status --porcelain | grep -E "^(M| M|\\?\\?|A| A)" | cut -c4-); do
+        if [ -f "$file" ] && (file "$file" | grep -q "executable" || git check-attr binary "$file" | grep -q "binary: set"); then
+            git rm -f "$file" 2>/dev/null || rm -f "$file"
+            echo "Removed: $file"
+        fi
+    done
+    """.strip()

evaluation/benchmarks/nocode_bench/consistants.py

@@ -0,0 +1,545 @@
+DOCPATH_PATTERNS = [
+    r'docs/',
+    r'^CHANGES\.rst$',
+    r'doc/',
+    r'ChangeLog',
+    r'^changelog/',
+    r'^CHANGES$',
+]
+
+MATPLOTLIB_CONFIG = {
+    k: {
+        'python': '3.11',
+        'conda_env': 'matplotlib_35',
+        'install': 'python -m pip install -e .',
+        'test_cmd': 'pytest -rA --color=no',
+    }
+    for k in ['3.5', '3.6', '3.7', '3.8', '3.9']
+}
+MATPLOTLIB_CONFIG.update(
+    {
+        k: {
+            'python': '3.8',
+            'conda_env': 'matplotlib_31',
+            'install': 'python -m pip install -e .',
+            'test_cmd': 'pytest -rA --color=no',
+        }
+        for k in ['3.1', '3.2', '3.3', '3.4']
+    }
+)
+MATPLOTLIB_CONFIG.update(
+    {
+        k: {
+            'python': '3.5',
+            'install': 'python setup.py build; python setup.py install',
+            'conda_env': 'matplotlib_11',
+            'nonroot': True,
+            'test_cmd': 'pytest -rA --color=no',
+        }
+        for k in ['2.0', '2.1', '2.2', '1.0', '1.1', '1.2', '1.3', '1.4', '1.5']
+    }
+)
+for k in ['3.8', '3.9']:
+    MATPLOTLIB_CONFIG[k]['install'] = (
+        'python -m pip install --no-build-isolation -e ".[dev]"'
+    )
+
+
+SYMPY_CONFIG = {}
+SYMPY_CONFIG.update(
+    {
+        '1.0': {
+            'conda_env': 'sympy_10',
+            'install': 'pip install -e .',
+            'test_cmd': 'bin/test -C -v',
+            # testfile -k testname
+        }
+    }
+)
+
+REQUESTS_CONFIG = {}
+REQUESTS_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'requests_227',
+            'install': 'pip install -r requirements-dev.txt',
+            'test_cmd': 'pytest -rA',
+        }
+        for k in ['2.27']
+    }
+)
+REQUESTS_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'requests_226',
+            'install': 'pip install -e .',
+            'test_cmd': 'pytest -rA',
+        }
+        for k in ['2.26']
+    }
+)
+
+PYTEST_CONFIG = {}
+PYTEST_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'pytest_33',
+            'install': 'pip install -e .',
+            'test_cmd': 'pytest -v --color=no',
+        }
+        for k in ['4.4', '4.1', '3.7', '3.4', '3.3']
+    }
+)
+
+PYLINT_CONFIG = {}
+PYLINT_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'pylint_210',
+            'install': 'pip install -r requirements_test.txt',
+            'test_cmd': 'pytest -rA --color=no',
+        }
+        for k in [
+            '2.10',
+            '2.11',
+            '2.13',
+            '2.14',
+            '2.15',
+            '2.16',
+            '2.17',
+            '3.0',
+            '3.1',
+            '3.2',
+            '3.3',
+        ]
+    }
+)
+PYLINT_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'pylint_210',
+            'pre_install': [
+                r"sed -i 's/setuptools==[0-9.]\+/setuptools==58.0.0/' requirements_test_min.txt"
+            ],
+            'install': 'pip install -r requirements_test.txt',
+            'test_cmd': 'pytest -rA --color=no',
+        }
+        for k in ['3.0', '3.1', '3.2', '3.3']
+    }
+)
+
+ASTROPY_CONFIG = {}
+ASTROPY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'astropy_11',
+            'install': 'python -m pip install -e .[test] --verbose',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['1.1', '1.2', '1.3', '2.0']
+    }
+)
+ASTROPY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'astropy_30',
+            'pre_install': """echo '[pytest]
+filterwarnings =
+    ignore::DeprecationWarning' > pytest.ini""",
+            'install': 'python -m pip install -e .[test] --verbose',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['3.0', '3.1', '3.2']
+    }
+)
+ASTROPY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'astropy_40',
+            'pre_install': [
+                r"""sed -i 's/requires = \["setuptools",/requires = \["setuptools==68.0.0",/' pyproject.toml"""
+            ],
+            'install': 'python -m pip install -e .[test] --verbose',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['4.0']
+    }
+)
+ASTROPY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'astropy_41',
+            'pre_install': [
+                r"""sed -i 's/requires = \["setuptools",/requires = \["setuptools==68.0.0",/' pyproject.toml""",
+                """sed -i 's/^qt_no_exception_capture = 1$/; qt_no_exception_capture = 1/' setup.cfg""",
+                r"""sed -i '/setuptools==68.0.0",/a \    "markupsafe==2.0.1",' pyproject.tomlsed -i '/setuptools==68.0.0",/a \    "markupsafe==2.0.1",' pyproject.toml""",
+            ],
+            'install': 'python -m pip install -e .[test] --verbose',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['4.1']
+    }
+)
+ASTROPY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'astropy_42',
+            'pre_install': [
+                r"""sed -i 's/requires = \["setuptools",/requires = \["setuptools==68.0.0",/' pyproject.toml""",
+                r"""sed -i '/setuptools==68.0.0",/a \    "markupsafe==2.0.1",' pyproject.tomlsed -i '/setuptools==68.0.0",/a \    "markupsafe==2.0.1",' pyproject.toml""",
+            ],
+            'install': 'python -m pip install -e .[test] --verbose',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['4.2', '4.3', '5.0', '5.1']
+    }
+)
+
+ASTROPY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'astropy_52',
+            'pre_install': [
+                r"""sed -i 's/requires = \["setuptools",/requires = \["setuptools==68.0.0",/' pyproject.toml"""
+            ],
+            'install': 'python -m pip install -e .[test] --verbose',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['5.2', '5.3', '6.0', '6.1', '7.0']
+    }
+)
+
+DJANGO_CONFIG = {}
+DJANGO_CONFIG.update(
+    {
+        k: {
+            'install': 'pip install -e .',
+            'conda_env': 'django_22',
+            'test_cmd': 'python tests/runtests.py --verbosity 2',
+        }
+        for k in ['1.9', '2.2']
+    }
+)
+DJANGO_CONFIG.update(
+    {
+        '3.2': {
+            'install': 'pip install -e .',
+            'conda_env': 'django_32',
+            'test_cmd': 'python tests/runtests.py --verbosity 2',
+        },
+        '4.2': {
+            'install': 'pip install -e .',
+            'conda_env': 'django_42',
+            'test_cmd': 'python tests/runtests.py --verbosity 2',
+        },
+        '5.1': {
+            'install': 'pip install -e .',
+            'conda_env': 'django_51',
+            'test_cmd': 'python tests/runtests.py --verbosity 2',
+        },
+    }
+)
+SPHINX_CONFIG = {}
+SPHINX_CONFIG.update(
+    {  # 1.x 版本问题，实际无用
+        k: {
+            'conda_env': 'sphinx_20',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': ["sed -i 's/pytest/pytest -rA/' tox.ini"],
+            'test_cmd': 'tox --current-env -epy37 -v --',
+        }
+        for k in ['1.3', '1.4', '1.5', '1.6', '1.7', '1.8']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_20',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+                "sed -i 's/Jinja2>=2.3/Jinja2<3.0/' setup.py",
+            ],
+            'test_cmd': 'tox --current-env -epy37 -v --',
+        }
+        for k in ['2.0', '2.1', '2.2', '2.3', '2.4']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_30',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+                "sed -i 's/Jinja2>=2.3/Jinja2<3.0/' setup.py",
+                "sed -i 's/sphinxcontrib-applehelp/sphinxcontrib-applehelp<=1.0.7/' setup.py",
+                "sed -i 's/sphinxcontrib-devhelp/sphinxcontrib-devhelp<=1.0.5/' setup.py",
+                "sed -i 's/sphinxcontrib-qthelp/sphinxcontrib-qthelp<=1.0.6/' setup.py",
+                "sed -i 's/alabaster>=0.7,<0.8/alabaster>=0.7,<0.7.12/' setup.py",
+                "sed -i \"s/'packaging',/'packaging', 'markupsafe<=2.0.1',/\" setup.py",
+                "sed -i 's/sphinxcontrib-htmlhelp/sphinxcontrib-htmlhelp<=2.0.4/' setup.py",
+                "sed -i 's/sphinxcontrib-serializinghtml/sphinxcontrib-serializinghtml<=1.1.9/' setup.py",
+            ],
+            'test_cmd': 'tox --current-env -epy37 -v --',
+        }
+        for k in ['3.0', '3.1', '3.2', '3.3', '3.4', '3.5', '4.0']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_30',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+                "sed -i 's/Jinja2>=2.3/Jinja2<3.0/' setup.py",
+                "sed -i 's/sphinxcontrib-applehelp/sphinxcontrib-applehelp<=1.0.7/' setup.py",
+                "sed -i 's/sphinxcontrib-devhelp/sphinxcontrib-devhelp<=1.0.5/' setup.py",
+                "sed -i 's/sphinxcontrib-qthelp/sphinxcontrib-qthelp<=1.0.6/' setup.py",
+                "sed -i 's/alabaster>=0.7,<0.8/alabaster>=0.7,<0.7.12/' setup.py",
+                "sed -i \"s/'packaging',/'packaging', 'markupsafe<=2.0.1',/\" setup.py",
+                (
+                    "grep -q 'sphinxcontrib-htmlhelp>=2.0.0' setup.py && "
+                    "sed -i 's/sphinxcontrib-htmlhelp>=2.0.0/sphinxcontrib-htmlhelp>=2.0.0,<=2.0.4/' setup.py || "
+                    "sed -i 's/sphinxcontrib-htmlhelp/sphinxcontrib-htmlhelp<=2.0.4/' setup.py"
+                ),
+                (
+                    "grep -q 'sphinxcontrib-serializinghtml>=1.1.5' setup.py && "
+                    "sed -i 's/sphinxcontrib-serializinghtml>=1.1.5/sphinxcontrib-serializinghtml>=1.1.5,<=1.1.9/' setup.py || "
+                    "sed -i 's/sphinxcontrib-serializinghtml/sphinxcontrib-serializinghtml<=1.1.9/' setup.py"
+                ),
+            ],
+            'test_cmd': 'tox --current-env -epy37 -v --',
+        }
+        for k in ['4.1']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_30',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+                "sed -i 's/Jinja2>=2.3/Jinja2<3.0/' setup.py",
+                "sed -i 's/sphinxcontrib-applehelp/sphinxcontrib-applehelp<=1.0.7/' setup.py",
+                "sed -i 's/sphinxcontrib-devhelp/sphinxcontrib-devhelp<=1.0.5/' setup.py",
+                "sed -i 's/sphinxcontrib-qthelp/sphinxcontrib-qthelp<=1.0.6/' setup.py",
+                "sed -i 's/alabaster>=0.7,<0.8/alabaster>=0.7,<0.7.12/' setup.py",
+                "sed -i \"s/'packaging',/'packaging', 'markupsafe<=2.0.1',/\" setup.py",
+                "sed -i 's/sphinxcontrib-htmlhelp>=2.0.0/sphinxcontrib-htmlhelp>=2.0.0,<=2.0.4/' setup.py",
+                "sed -i 's/sphinxcontrib-serializinghtml>=1.1.5/sphinxcontrib-serializinghtml>=1.1.5,<=1.1.9/' setup.py",
+            ],
+            'test_cmd': 'tox --current-env -epy37 -v --',
+        }
+        for k in ['4.2', '4.3', '4.4']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_30',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+            ],
+            'test_cmd': 'tox --current-env -epy37 -v --',
+        }
+        for k in ['4.5', '5.0', '5.1', '5.2']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_60',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+            ],
+            'test_cmd': 'tox --current-env -epy39 -v --',
+        }
+        for k in ['6.0', '6.2', '7.0', '7.1']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_72',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+                'apt-get update && apt-get install -y graphviz',
+            ],
+            'test_cmd': 'tox --current-env -epy39 -v --',
+        }
+        for k in ['7.2', '7.3', '7.4']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_80',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+            ],
+            'test_cmd': 'tox --current-env -epy310 -v --',
+        }
+        for k in ['8.0', '8.1']
+    }
+)
+
+
+SKLEARN_CONFIG = {}
+SKLEARN_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'skl_020',
+            'install': 'pip install -v --no-use-pep517 --no-build-isolation -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['0.20', '0.21', '0.22']
+    }
+)
+SKLEARN_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'skl_100',
+            'install': 'pip install -v --no-use-pep517 --no-build-isolation -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['0.23', '0.24', '1.00', '1.01', '1.02']
+    }
+)
+SKLEARN_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'skl_104',
+            'install': 'pip install -v --no-use-pep517 --no-build-isolation -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['1.03', '1.04', '1.05']
+    }
+)
+
+SEABORN_CONFIG = {}
+SEABORN_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'seaborn_010',
+            'install': 'pip install -e .[dev]',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['0.3', '0.4', '0.5', '0.6', '0.11', '0.12', '0.13', '0.14']
+    }
+)
+
+XARRAY_CONFIG = {}
+XARRAY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'xarray_0014',
+            'install': 'pip install -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['0014', '0015', '0016']
+    }
+)
+XARRAY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'xarray_0017',
+            'install': 'pip install -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['0017', '0018', '0019', '0020', '0021']
+    }
+)
+XARRAY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'xarray_2203',
+            'install': 'pip install -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['2203', '2206', '2209', '2210', '2211', '2212']
+    }
+)
+XARRAY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'xarray_2303',
+            'install': 'pip install -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in [
+            '2303',
+            '2304',
+            '2305',
+            '2306',
+            '2308',
+            '2309',
+            '2310',
+            '2311',
+            '2312',
+        ]
+    }
+)
+XARRAY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'xarray_2401',
+            'install': 'pip install -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['2401', '2402', '2403', '2405', '2407', '2409', '2410', '2411']
+    }
+)
+
+SKLEARN_CONFIG = {}
+SKLEARN_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'skl_020',
+            'install': 'pip install -v --no-use-pep517 --no-build-isolation -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['0.20', '0.21', '0.22']
+    }
+)
+SKLEARN_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'skl_100',
+            'install': 'pip install -v --no-use-pep517 --no-build-isolation -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['0.23', '0.24', '1.00', '1.01', '1.02']
+    }
+)
+SKLEARN_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'skl_104',
+            'install': 'pip install -v --no-use-pep517 --no-build-isolation -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['1.03', '1.04', '1.05', '1.06', '1.07']
+    }
+)
+
+
+MAP_REPO_TO_CONFIG = {
+    'pydata/xarray': XARRAY_CONFIG,
+    'mwaskom/seaborn': SEABORN_CONFIG,
+    'scikit-learn/scikit-learn': SKLEARN_CONFIG,
+    'sphinx-doc/sphinx': SPHINX_CONFIG,
+    'django/django': DJANGO_CONFIG,
+    'astropy/astropy': ASTROPY_CONFIG,
+    'pylint-dev/pylint': PYLINT_CONFIG,
+    'pytest-dev/pytest': PYTEST_CONFIG,
+    'psf/requests': REQUESTS_CONFIG,
+    'sympy/sympy': SYMPY_CONFIG,
+    'matplotlib/matplotlib': MATPLOTLIB_CONFIG,
+}

evaluation/benchmarks/nocode_bench/prompts/nc.j2

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

evaluation/benchmarks/nocode_bench/resource/mapping.py

@@ -0,0 +1,39 @@
+"""Mapping instance_id to resource_factor.
+
+Different instances may have different resource requirements.
+e.g., some instances may require more memory/CPU to run inference.
+This file tracks the resource requirements of different instances.
+"""
+
+import json
+import os
+
+from openhands.core.logger import openhands_logger as logger
+
+CUR_DIR = os.path.dirname(os.path.abspath(__file__))
+DEFAULT_RUNTIME_RESOURCE_FACTOR = int(
+    os.environ.get('DEFAULT_RUNTIME_RESOURCE_FACTOR', 1)
+)
+
+# dataset to resource mapping
+_global_resource_mapping: dict[str, dict[str, float]] = {}
+
+
+def get_resource_mapping(dataset_name: str) -> dict[str, float]:
+    if dataset_name not in _global_resource_mapping:
+        file_path = os.path.join(CUR_DIR, f'{dataset_name}.json')
+        if not os.path.exists(file_path):
+            logger.info(f'Resource mapping for {dataset_name} not found.')
+            return None
+
+        with open(file_path, 'r') as f:
+            _global_resource_mapping[dataset_name] = json.load(f)
+        logger.debug(f'Loaded resource mapping for {dataset_name}')
+    return _global_resource_mapping[dataset_name]
+
+
+def get_instance_resource_factor(dataset_name: str, instance_id: str) -> int:
+    resource_mapping = get_resource_mapping(dataset_name)
+    if resource_mapping is None:
+        return DEFAULT_RUNTIME_RESOURCE_FACTOR
+    return int(resource_mapping.get(instance_id, DEFAULT_RUNTIME_RESOURCE_FACTOR))

evaluation/benchmarks/nocode_bench/run_infer_nc.py

@@ -0,0 +1,909 @@
+import asyncio
+import copy
+import json
+import os
+import tempfile
+from typing import Any, Literal
+
+import numpy as np
+import pandas as pd
+import toml
+from datasets import load_dataset
+from jinja2 import Environment, FileSystemLoader
+
+import openhands.agenthub
+from evaluation.benchmarks.nocode_bench.binary_patch_utils import (
+    remove_binary_diffs,
+    remove_binary_files_from_git,
+)
+from evaluation.benchmarks.nocode_bench.consistants import MAP_REPO_TO_CONFIG
+from evaluation.benchmarks.nocode_bench.resource.mapping import (
+    get_instance_resource_factor,
+)
+from evaluation.benchmarks.nocode_bench.scripts.utils.evaluation_utils import (
+    run_evaluation_nocode_bench,
+)
+from evaluation.utils.shared import (
+    EvalException,
+    EvalMetadata,
+    EvalOutput,
+    assert_and_raise,
+    codeact_user_response,
+    get_default_sandbox_config_for_eval,
+    get_metrics,
+    is_fatal_evaluation_error,
+    make_metadata,
+    prepare_dataset,
+    reset_logger_for_multiprocessing,
+    update_llm_config_for_completions_logging,
+)
+from openhands.controller.state.state import State
+from openhands.core.config import (
+    AgentConfig,
+    OpenHandsConfig,
+    get_evaluation_parser,
+    get_llm_config_arg,
+)
+from openhands.core.config.condenser_config import NoOpCondenserConfig
+from openhands.core.config.utils import get_condenser_config_arg
+from openhands.core.logger import openhands_logger as logger
+from openhands.core.main import create_runtime, run_controller
+from openhands.critic import AgentFinishedCritic
+from openhands.events.action import CmdRunAction, FileReadAction, MessageAction
+from openhands.events.observation import (
+    CmdOutputObservation,
+    ErrorObservation,
+    FileReadObservation,
+)
+from openhands.events.serialization.event import event_from_dict, event_to_dict
+from openhands.runtime.base import Runtime
+from openhands.utils.async_utils import call_async_from_sync
+from openhands.utils.shutdown_listener import sleep_if_should_continue
+
+USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
+RUN_WITH_BROWSING = os.environ.get('RUN_WITH_BROWSING', 'false').lower() == 'true'
+ENABLE_LLM_EDITOR = os.environ.get('ENABLE_LLM_EDITOR', 'false').lower() == 'true'
+BenchMode = Literal['swe', 'swt', 'swt-ci']
+
+# Global variable to track dataset type
+DATASET_TYPE = 'nc_bench'
+
+
+def set_dataset_type(dataset_name: str) -> str:
+    """Set dataset type based on dataset name."""
+    global DATASET_TYPE
+    DATASET_TYPE = 'nc_bench'
+
+    logger.info(f'Dataset type set to: {DATASET_TYPE}')
+
+
+AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
+    'CodeActAgent': codeact_user_response,
+}
+
+
+def _get_swebench_workspace_dir_name(instance: pd.Series) -> str:
+    return f'{instance.repo.split("/")[-1]}'
+
+
+def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageAction:
+    workspace_dir_name = _get_swebench_workspace_dir_name(instance)
+    metadata.details['mode']
+
+    # Determine the template file based on mode and LLM
+
+    template_name = 'nc.j2'
+
+    # Set up Jinja2 environment
+    # Assuming templates are in 'evaluation/benchmarks/swe_bench/prompts' relative to this script
+    prompts_dir = os.path.join(os.path.dirname(__file__), 'prompts')
+    env = Environment(loader=FileSystemLoader(prompts_dir))
+    template = env.get_template(template_name)
+
+    # Prepare context for rendering
+    context = {
+        'instance': instance,
+        'workspace_dir_name': workspace_dir_name,
+        'metadata': metadata,  # Pass metadata if needed in templates
+    }
+
+    context['test_instructions'] = ''  # Ensure it's defined for other modes
+
+    # Render the instruction
+    instruction = template.render(context)
+
+    if RUN_WITH_BROWSING:
+        instruction += (
+            '<IMPORTANT!>\nYou SHOULD NEVER attempt to browse the web. </IMPORTANT!>\n'
+        )
+
+    if 'image_assets' in instance:
+        assets = json.loads(instance['image_assets'])
+        assert 'problem_statement' in assets, (
+            'problem_statement is required in image_assets'
+        )
+        image_urls = assets['problem_statement']
+        return MessageAction(content=instruction, image_urls=image_urls)
+    return MessageAction(content=instruction)
+
+
+DEFAULT_DOCKER_IMAGE_PREFIX = os.environ.get(
+    'EVAL_DOCKER_IMAGE_PREFIX', 'docker.io/xingyaoww/'
+)
+logger.info(f'Default docker image prefix: {DEFAULT_DOCKER_IMAGE_PREFIX}')
+
+
+def get_instance_docker_image(
+    instance_id: str,
+    swebench_official_image: bool = False,
+) -> str:
+    if swebench_official_image:
+        # Official NoCode-Bench image
+        image_name = f'ncbench_{instance_id}:latest'.lower()
+        logger.debug(f'Using official NoCode-Bench image: {image_name}')
+        return image_name
+    else:
+        raise
+
+
+def get_config(
+    instance: pd.Series,
+    metadata: EvalMetadata,
+) -> OpenHandsConfig:
+    # We use a different instance image for the each instance of NoCode-bench eval
+    use_swebench_official_image = True
+
+    base_container_image = get_instance_docker_image(
+        instance['instance_id'],
+        swebench_official_image=use_swebench_official_image,
+    )
+    logger.info(
+        f'Using instance container image: {base_container_image}. '
+        f'Please make sure this image exists. '
+        f'Submit an issue on https://github.com/All-Hands-AI/OpenHands if you run into any issues.'
+    )
+
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = base_container_image
+    sandbox_config.enable_auto_lint = True
+    sandbox_config.use_host_network = False
+    # Add platform to the sandbox config to solve issue 4401
+    sandbox_config.platform = 'linux/amd64'
+    sandbox_config.remote_runtime_resource_factor = get_instance_resource_factor(
+        dataset_name=metadata.dataset,
+        instance_id=instance['instance_id'],
+    )
+
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
+        max_iterations=metadata.max_iterations,
+        runtime=os.environ.get('RUNTIME', 'docker'),
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
+    )
+
+    config.set_llm_config(
+        update_llm_config_for_completions_logging(
+            metadata.llm_config, metadata.eval_output_dir, instance['instance_id']
+        )
+    )
+    # get 'draft_editor' config if exists
+    config.set_llm_config(get_llm_config_arg('draft_editor'), 'draft_editor')
+
+    agent_config = AgentConfig(
+        enable_jupyter=False,
+        enable_browsing=RUN_WITH_BROWSING,
+        enable_llm_editor=ENABLE_LLM_EDITOR,
+        enable_mcp=False,
+        condenser=metadata.condenser_config,
+        enable_prompt_extensions=False,
+    )
+    config.set_agent_config(agent_config)
+    return config
+
+
+def make_serializable(obj):
+    if isinstance(obj, pd.Series):
+        obj = obj.to_dict()
+    if isinstance(obj, dict):
+        return {k: make_serializable(v) for k, v in obj.items()}
+    elif isinstance(obj, list):
+        return [make_serializable(v) for v in obj]
+    elif isinstance(obj, tuple):
+        return tuple(make_serializable(v) for v in obj)
+    elif isinstance(obj, np.ndarray):
+        return obj.tolist()
+    elif isinstance(obj, pd.Timestamp):
+        return str(obj)
+    else:
+        return obj
+
+
+def initialize_runtime(
+    runtime: Runtime,
+    instance: pd.Series,  # this argument is not required
+    metadata: EvalMetadata,
+):
+    """Initialize the runtime for the agent.
+
+    This function is called before the runtime is used to run the agent.
+    """
+    logger.info('-' * 30)
+    logger.info('BEGIN Runtime Initialization Fn')
+    logger.info('-' * 30)
+    workspace_dir_name = _get_swebench_workspace_dir_name(instance)
+    obs: CmdOutputObservation
+
+    # Set instance id and git configuration
+    action = CmdRunAction(
+        command=f"""echo 'export SWE_INSTANCE_ID={instance['instance_id']}' >> ~/.bashrc && echo 'export PIP_CACHE_DIR=~/.cache/pip' >> ~/.bashrc && echo "alias git='git --no-pager'" >> ~/.bashrc && git config --global core.pager "" && git config --global diff.binary false"""
+    )
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0,
+        f'Failed to export SWE_INSTANCE_ID and configure git: {str(obs)}',
+    )
+
+    action = CmdRunAction(command="""export USER=$(whoami); echo USER=${USER} """)
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(obs.exit_code == 0, f'Failed to export USER: {str(obs)}')
+
+    # inject the init script
+    script_dir = os.path.dirname(__file__)
+
+    # inject the instance info
+    action = CmdRunAction(command='mkdir -p /swe_util/eval_data/instances')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0,
+        f'Failed to create /swe_util/eval_data/instances: {str(obs)}',
+    )
+
+    swe_instance_json_name = 'swe-bench-instance.json'
+    with tempfile.TemporaryDirectory() as temp_dir:
+        # Construct the full path for the desired file name within the temporary directory
+        temp_file_path = os.path.join(temp_dir, swe_instance_json_name)
+        # Write to the file with the desired name within the temporary directory
+
+        with open(temp_file_path, 'w') as f:
+            if not isinstance(instance, dict):
+                instance_dict = make_serializable(instance)
+            else:
+                instance_dict = dict(instance)
+
+            if DATASET_TYPE == 'nc_bench':
+                config = MAP_REPO_TO_CONFIG.get(instance['repo'], {}).get(
+                    instance['version'], []
+                )
+                docker_conda_env_name = config['conda_env']
+                instance_dict['conda_env'] = docker_conda_env_name
+
+            json.dump([instance_dict], f)
+
+        # Copy the file to the desired location
+        runtime.copy_to(temp_file_path, '/swe_util/eval_data/instances/')
+
+        # inject the instance swe entry
+        entry_script_path = 'instance_nc_entry.sh'
+
+        runtime.copy_to(
+            str(os.path.join(script_dir, f'scripts/setup/{entry_script_path}')),
+            '/swe_util/',
+        )
+
+    action = CmdRunAction(command='cat ~/.bashrc')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(obs.exit_code == 0, f'Failed to cat ~/.bashrc: {str(obs)}')
+
+    action = CmdRunAction(command='source ~/.bashrc')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    if isinstance(obs, ErrorObservation):
+        logger.error(f'Failed to source ~/.bashrc: {str(obs)}')
+    assert_and_raise(obs.exit_code == 0, f'Failed to source ~/.bashrc: {str(obs)}')
+
+    action = CmdRunAction(command=f'source /swe_util/{entry_script_path}')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0,
+        f'Failed to source /swe_util/{entry_script_path}: {str(obs)}',
+    )
+
+    action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0,
+        f'Failed to cd to /workspace/{workspace_dir_name}: {str(obs)}',
+    )
+
+    action = CmdRunAction(command='git reset --hard')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(obs.exit_code == 0, f'Failed to git reset --hard: {str(obs)}')
+
+    action = CmdRunAction(
+        command='for remote_name in $(git remote); do git remote remove "${remote_name}"; done'
+    )
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(obs.exit_code == 0, f'Failed to remove git remotes: {str(obs)}')
+
+    if DATASET_TYPE != 'Multimodal' and DATASET_TYPE != 'SWE-bench-Live':
+        # Only for non-multimodal datasets, we need to activate the testbed environment for Python
+        # SWE-Bench multimodal datasets and SWE-bench-Live are not using the testbed environment
+        action = CmdRunAction(command='which python')
+        action.set_hard_timeout(600)
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+        assert_and_raise(
+            obs.exit_code == 0,
+            f'Expected to find python interpreter, but got: {str(obs)}',
+        )
+
+    logger.info('-' * 30)
+    logger.info('END Runtime Initialization Fn')
+    logger.info('-' * 30)
+
+
+def complete_runtime(
+    runtime: Runtime,
+    instance: pd.Series,  # this argument is not required, but it is used to get the workspace_dir_name
+) -> dict[str, Any]:
+    """Complete the runtime for the agent.
+
+    This function is called before the runtime is used to run the agent.
+    If you need to do something in the sandbox to get the correctness metric after
+    the agent has run, modify this function.
+    """
+    logger.info('-' * 30)
+    logger.info('BEGIN Runtime Completion Fn')
+    logger.info('-' * 30)
+    obs: CmdOutputObservation
+    workspace_dir_name = _get_swebench_workspace_dir_name(instance)
+
+    action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+    if obs.exit_code == -1:
+        # The previous command is still running
+        # We need to kill previous command
+        logger.info('The previous command is still running, trying to kill it...')
+        action = CmdRunAction(command='C-c')
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+        # Then run the command again
+        action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
+        action.set_hard_timeout(600)
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+    if obs.exit_code == -1:
+        # The previous command is still running
+        # We need to kill previous command
+        logger.info('The previous command is still running, trying to ctrl+z it...')
+        action = CmdRunAction(command='C-z')
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+        # Then run the command again
+        action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
+        action.set_hard_timeout(600)
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to cd to /workspace/{workspace_dir_name}: {str(obs)}',
+    )
+
+    action = CmdRunAction(command='git config --global core.pager ""')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to git config --global core.pager "": {str(obs)}',
+    )
+
+    # First check for any git repositories in subdirectories
+    action = CmdRunAction(command='find . -type d -name .git -not -path "./.git"')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to find git repositories: {str(obs)}',
+    )
+
+    git_dirs = [p for p in obs.content.strip().split('\n') if p]
+    if git_dirs:
+        # Remove all .git directories in subdirectories
+        for git_dir in git_dirs:
+            action = CmdRunAction(command=f'rm -rf "{git_dir}"')
+            action.set_hard_timeout(600)
+            logger.info(action, extra={'msg_type': 'ACTION'})
+            obs = runtime.run_action(action)
+            logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+            assert_and_raise(
+                isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+                f'Failed to remove git directory {git_dir}: {str(obs)}',
+            )
+
+    # add all files
+    action = CmdRunAction(command='git add -A')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to git add -A: {str(obs)}',
+    )
+
+    # Remove binary files from git staging
+    action = CmdRunAction(command=remove_binary_files_from_git())
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to remove binary files: {str(obs)}',
+    )
+
+    n_retries = 0
+    git_patch = None
+    while n_retries < 5:
+        action = CmdRunAction(
+            command=f'git diff --no-color --cached {instance["base_commit"]} > patch.diff'
+        )
+        action.set_hard_timeout(max(300 + 100 * n_retries, 600))
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+        n_retries += 1
+        if isinstance(obs, CmdOutputObservation):
+            if obs.exit_code == 0:
+                # Read the patch file
+                action = FileReadAction(path='patch.diff')
+                action.set_hard_timeout(max(300 + 100 * n_retries, 600))
+                logger.info(action, extra={'msg_type': 'ACTION'})
+                obs = runtime.run_action(action)
+                logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+                if isinstance(obs, FileReadObservation):
+                    git_patch = obs.content
+                    break
+                elif isinstance(obs, ErrorObservation):
+                    # Fall back to cat "patch.diff" to get the patch
+                    assert 'File could not be decoded as utf-8' in obs.content
+                    action = CmdRunAction(command='cat patch.diff')
+                    action.set_hard_timeout(max(300 + 100 * n_retries, 600))
+                    logger.info(action, extra={'msg_type': 'ACTION'})
+                    obs = runtime.run_action(action)
+                    assert isinstance(obs, CmdOutputObservation) and obs.exit_code == 0
+                    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+                    git_patch = obs.content
+                    break
+                else:
+                    assert_and_raise(False, f'Unexpected observation type: {str(obs)}')
+            else:
+                logger.info('Failed to get git diff, retrying...')
+                sleep_if_should_continue(10)
+        elif isinstance(obs, ErrorObservation):
+            logger.error(f'Error occurred: {obs.content}. Retrying...')
+            sleep_if_should_continue(10)
+        else:
+            assert_and_raise(False, f'Unexpected observation type: {str(obs)}')
+
+    assert_and_raise(git_patch is not None, 'Failed to get git diff (None)')
+
+    # Remove binary diffs from the patch
+    git_patch = remove_binary_diffs(git_patch)
+
+    logger.info('-' * 30)
+    logger.info('END Runtime Completion Fn')
+    logger.info('-' * 30)
+    return {'git_patch': git_patch}
+
+
+def process_instance(
+    instance: pd.Series,
+    metadata: EvalMetadata,
+    reset_logger: bool = True,
+    runtime_failure_count: int = 0,
+) -> EvalOutput:
+    config = get_config(instance, metadata)
+
+    # Setup the logger properly, so you can run multi-processing to parallelize the evaluation
+    if reset_logger:
+        log_dir = os.path.join(metadata.eval_output_dir, 'infer_logs')
+        reset_logger_for_multiprocessing(logger, instance.instance_id, log_dir)
+    else:
+        logger.info(f'Starting evaluation for instance {instance.instance_id}.')
+
+    # Increase resource_factor with increasing attempt_id
+    if runtime_failure_count > 0:
+        config.sandbox.remote_runtime_resource_factor = min(
+            config.sandbox.remote_runtime_resource_factor * (2**runtime_failure_count),
+            8,
+        )
+        logger.warning(
+            f'This is the {runtime_failure_count + 1}th attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
+        )
+
+    metadata = copy.deepcopy(metadata)
+    metadata.details['runtime_failure_count'] = runtime_failure_count
+    metadata.details['remote_runtime_resource_factor'] = (
+        config.sandbox.remote_runtime_resource_factor
+    )
+
+    runtime = create_runtime(config)
+    call_async_from_sync(runtime.connect)
+
+    try:
+        initialize_runtime(runtime, instance, metadata)
+
+        message_action = get_instruction(instance, metadata)
+
+        # Here's how you can run the agent (similar to the `main` function) and get the final task state
+        state: State | None = asyncio.run(
+            run_controller(
+                config=config,
+                initial_user_action=message_action,
+                runtime=runtime,
+                fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN[
+                    metadata.agent_class
+                ],
+            )
+        )
+
+        # if fatal error, throw EvalError to trigger re-run
+        if is_fatal_evaluation_error(state.last_error):
+            raise EvalException('Fatal error detected: ' + state.last_error)
+
+        # ======= THIS IS SWE-Bench specific =======
+        # Get git patch
+        if DATASET_TYPE == 'SWE-bench-Live':
+            from evaluation.benchmarks.swe_bench.live_utils import (
+                complete_runtime as complete_runtime_fn,
+            )
+        else:
+            complete_runtime_fn = complete_runtime
+        return_val = complete_runtime_fn(runtime, instance)
+        git_patch = return_val['git_patch']
+        logger.info(
+            f'Got git diff for instance {instance.instance_id}:\n--------\n{git_patch}\n--------'
+        )
+    finally:
+        runtime.close()
+    # ==========================================
+
+    # ======= Attempt to evaluate the agent's edits =======
+    # we use eval_infer.sh to evaluate the agent's edits, not here
+    # because the agent may alter the environment / testcases
+    test_result = {
+        'git_patch': git_patch,
+    }
+
+    # If you are working on some simpler benchmark that only evaluates the final model output (e.g., in a MessageAction)
+    # You can simply get the LAST `MessageAction` from the returned `state.history` and parse it for evaluation.
+    if state is None:
+        raise ValueError('State should not be None.')
+
+    # NOTE: this is NO LONGER the event stream, but an agent history that includes delegate agent's events
+    histories = [event_to_dict(event) for event in state.history]
+    metrics = get_metrics(state)
+
+    # Save the output
+    instruction = message_action.content
+    if message_action.image_urls:
+        instruction += (
+            '\n\n<image_urls>' + '\n'.join(message_action.image_urls) + '</image_urls>'
+        )
+    output = EvalOutput(
+        instance_id=instance.instance_id,
+        instruction=instruction,
+        instance=instance.to_dict(),  # SWE Bench specific
+        test_result=test_result,
+        metadata=metadata,
+        history=histories,
+        metrics=metrics,
+        error=state.last_error if state and state.last_error else None,
+    )
+    return output
+
+
+def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
+    file_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'config.toml')
+    if os.path.exists(file_path):
+        with open(file_path, 'r') as file:
+            data = toml.load(file)
+            if 'selected_ids' in data:
+                selected_ids = data['selected_ids']
+                logger.info(
+                    f'Filtering {len(selected_ids)} tasks from "selected_ids"...'
+                )
+                subset = dataset[dataset[filter_column].isin(selected_ids)]
+                logger.info(f'Retained {subset.shape[0]} tasks after filtering')
+                return subset
+            if 'selected_repos' in data:
+                # repos for the swe-bench instances:
+                # ['astropy/astropy', 'django/django', 'matplotlib/matplotlib', 'mwaskom/seaborn', 'pallets/flask', 'psf/requests', 'pydata/xarray', 'pylint-dev/pylint', 'pytest-dev/pytest', 'scikit-learn/scikit-learn', 'sphinx-doc/sphinx', 'sympy/sympy']
+                selected_repos = data['selected_repos']
+                if isinstance(selected_repos, str):
+                    selected_repos = [selected_repos]
+                assert isinstance(selected_repos, list)
+                logger.info(
+                    f'Filtering {selected_repos} tasks from "selected_repos"...'
+                )
+                subset = dataset[dataset['repo'].isin(selected_repos)]
+                logger.info(f'Retained {subset.shape[0]} tasks after filtering')
+                return subset
+
+    skip_ids = os.environ.get('SKIP_IDS', '').split(',')
+    if len(skip_ids) > 0:
+        logger.info(f'Filtering {len(skip_ids)} tasks from "SKIP_IDS"...')
+        return dataset[~dataset[filter_column].isin(skip_ids)]
+    return dataset
+
+
+if __name__ == '__main__':
+    parser = get_evaluation_parser()
+    parser.add_argument(
+        '--dataset',
+        type=str,
+        default='NoCode-bench/NoCode-bench_Verified',
+        help='data set to evaluate on, either full-test or lite-test',
+    )
+    parser.add_argument(
+        '--split',
+        type=str,
+        default='test',
+        help='split to evaluate on',
+    )
+    parser.add_argument(
+        '--mode',
+        type=str,
+        default='swe',
+        choices=['swe', 'swt', 'swt-ci'],
+        help="mode to run the evaluation, either 'swe', 'swt', or 'swt-ci'",
+    )
+
+    args, _ = parser.parse_known_args()
+
+    # NOTE: It is preferable to load datasets from huggingface datasets and perform post-processing
+    # so we don't need to manage file uploading to OpenHands's repo
+
+    dataset = load_dataset(args.dataset, args.split)
+
+    # Set the global dataset type based on dataset name
+    set_dataset_type(args.dataset)
+
+    swe_bench_tests = filter_dataset(dataset.to_pandas(), 'instance_id')
+    logger.info(
+        f'Loaded dataset {args.dataset} with split {args.split}: {len(swe_bench_tests)} tasks'
+    )
+
+    llm_config = None
+    if args.llm_config:
+        llm_config = get_llm_config_arg(args.llm_config)
+        llm_config.log_completions = True
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
+
+    if llm_config is None:
+        raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
+
+    # Get condenser config from environment variable
+    condenser_name = os.environ.get('EVAL_CONDENSER')
+    if condenser_name:
+        condenser_config = get_condenser_config_arg(condenser_name)
+        if condenser_config is None:
+            raise ValueError(
+                f'Could not find Condenser config: EVAL_CONDENSER={condenser_name}'
+            )
+    else:
+        # If no specific condenser config is provided via env var, default to NoOpCondenser
+        condenser_config = NoOpCondenserConfig()
+        logger.debug(
+            'No Condenser config provided via EVAL_CONDENSER, using NoOpCondenser.'
+        )
+
+    details = {'mode': args.mode}
+    _agent_cls = openhands.agenthub.Agent.get_cls(args.agent_cls)
+
+    dataset_descrption = (
+        args.dataset.replace('/', '__') + '-' + args.split.replace('/', '__')
+    )
+    metadata = make_metadata(
+        llm_config,
+        dataset_descrption,
+        args.agent_cls,
+        args.max_iterations,
+        args.eval_note,
+        args.eval_output_dir,
+        details=details,
+        condenser_config=condenser_config,
+    )
+
+    output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
+    print(f'### OUTPUT FILE: {output_file} ###')
+
+    # Run evaluation in iterative mode:
+    # If a rollout fails to output AgentFinishAction, we will try again until it succeeds OR total 3 attempts have been made.
+    ITERATIVE_EVAL_MODE = (
+        os.environ.get('ITERATIVE_EVAL_MODE', 'false').lower() == 'true'
+    )
+    ITERATIVE_EVAL_MODE_MAX_ATTEMPTS = int(
+        os.environ.get('ITERATIVE_EVAL_MODE_MAX_ATTEMPTS', '3')
+    )
+
+    if not ITERATIVE_EVAL_MODE:
+        # load the dataset
+        instances = prepare_dataset(swe_bench_tests, output_file, args.eval_n_limit)
+        if len(instances) > 0 and not isinstance(
+            instances['PASS2PASS'][instances['PASS2PASS'].index[0]], str
+        ):
+            for col in ['PASS2PASS', 'FAIL2PASS']:
+                instances[col] = instances[col].apply(lambda x: str(x))
+
+        run_evaluation_nocode_bench(
+            instances,
+            metadata,
+            output_file,
+            args.eval_num_workers,
+            process_instance,
+            timeout_seconds=8
+            * 60
+            * 60,  # 8 hour PER instance should be more than enough
+            max_retries=5,
+        )
+    else:
+        critic = AgentFinishedCritic()
+
+        def get_cur_output_file_path(attempt: int) -> str:
+            return (
+                f'{output_file.removesuffix(".jsonl")}.critic_attempt_{attempt}.jsonl'
+            )
+
+        eval_ids = None
+        for attempt in range(1, ITERATIVE_EVAL_MODE_MAX_ATTEMPTS + 1):
+            cur_output_file = get_cur_output_file_path(attempt)
+            logger.info(
+                f'Running evaluation with critic {critic.__class__.__name__} for attempt {attempt} of {ITERATIVE_EVAL_MODE_MAX_ATTEMPTS}.'
+            )
+
+            # For deterministic eval, we set temperature to 0.1 for (>1) attempt
+            # so hopefully we get slightly different results
+            if attempt > 1 and metadata.llm_config.temperature == 0:
+                logger.info(
+                    f'Detected temperature is 0 for (>1) attempt {attempt}. Setting temperature to 0.1...'
+                )
+                metadata.llm_config.temperature = 0.1
+
+            # Load instances - at first attempt, we evaluate all instances
+            # On subsequent attempts, we only evaluate the instances that failed the previous attempt determined by critic
+            instances = prepare_dataset(
+                swe_bench_tests, cur_output_file, args.eval_n_limit, eval_ids=eval_ids
+            )
+            if len(instances) > 0 and not isinstance(
+                instances['PASS2PASS'][instances['PASS2PASS'].index[0]], str
+            ):
+                for col in ['PASS2PASS', 'FAIL2PASS']:
+                    instances[col] = instances[col].apply(lambda x: str(x))
+
+            # Run evaluation - but save them to cur_output_file
+            logger.info(
+                f'Evaluating {len(instances)} instances for attempt {attempt}...'
+            )
+            run_evaluation_nocode_bench(
+                instances,
+                metadata,
+                cur_output_file,
+                args.eval_num_workers,
+                process_instance,
+                timeout_seconds=8
+                * 60
+                * 60,  # 8 hour PER instance should be more than enough
+                max_retries=5,
+            )
+
+            # When eval is done, we update eval_ids to the instances that failed the current attempt
+            instances_failed = []
+            logger.info(
+                f'Use critic {critic.__class__.__name__} to check {len(instances)} instances for attempt {attempt}...'
+            )
+            with open(cur_output_file, 'r') as f:
+                for line in f:
+                    instance = json.loads(line)
+                    try:
+                        history = [
+                            event_from_dict(event) for event in instance['history']
+                        ]
+                        critic_result = critic.evaluate(
+                            history, instance['test_result'].get('git_patch', '')
+                        )
+                        if not critic_result.success:
+                            instances_failed.append(instance['instance_id'])
+                    except Exception as e:
+                        logger.error(
+                            f'Error loading history for instance {instance["instance_id"]}: {e}'
+                        )
+                        instances_failed.append(instance['instance_id'])
+            logger.info(
+                f'{len(instances_failed)} instances failed the current attempt {attempt}: {instances_failed}'
+            )
+            eval_ids = instances_failed
+
+            # If no instances failed, we break
+            if len(instances_failed) == 0:
+                break
+
+        # Then we should aggregate the results from all attempts into the original output file
+        # and remove the intermediate files
+        logger.info(
+            'Aggregating results from all attempts into the original output file...'
+        )
+        fout = open(output_file, 'w')
+        added_instance_ids = set()
+        for attempt in reversed(range(1, ITERATIVE_EVAL_MODE_MAX_ATTEMPTS + 1)):
+            cur_output_file = get_cur_output_file_path(attempt)
+            if not os.path.exists(cur_output_file):
+                logger.warning(
+                    f'Intermediate output file {cur_output_file} does not exist. Skipping...'
+                )
+                continue
+
+            with open(cur_output_file, 'r') as f:
+                for line in f:
+                    instance = json.loads(line)
+                    # Also make sure git_patch is not empty - otherwise we fall back to previous attempt (empty patch is worse than anything else)
+                    if (
+                        instance['instance_id'] not in added_instance_ids
+                        and instance['test_result'].get('git_patch', '').strip()
+                    ):
+                        fout.write(line)
+                        added_instance_ids.add(instance['instance_id'])
+            logger.info(
+                f'Aggregated instances from {cur_output_file}. Total instances added so far: {len(added_instance_ids)}'
+            )
+        fout.close()
+        logger.info(
+            f'Done! Total {len(added_instance_ids)} instances added to {output_file}'
+        )

evaluation/benchmarks/nocode_bench/scripts/eval/convert.py

@@ -0,0 +1,33 @@
+import argparse
+import json
+
+
+def main(output_jsonl: str):
+    with open(output_jsonl, 'r') as f:
+        for line in f:
+            try:
+                output = json.loads(line)
+                pred = {
+                    'instance_id': output['instance_id'],
+                    'model_name_or_path': output['metadata']['llm_config']['model'],
+                    'model_patch': output['test_result']['git_patch'],
+                }
+            except Exception as e:
+                print(
+                    f'Error while reading output of instance {output["instance_id"]}: {e}'
+                )
+
+            print(json.dumps(pred))
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '--output_jsonl',
+        type=str,
+        required=True,
+        help='Path to the prediction file (.../outputs.jsonl)',
+    )
+    args = parser.parse_args()
+
+    main(args.output_jsonl)

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

@@ -0,0 +1,104 @@
+import argparse
+
+import pandas as pd
+
+from openhands.core.logger import openhands_logger as logger
+
+
+def verify_instance_costs(row: pd.Series) -> float:
+    """
+    Verifies that the accumulated_cost matches the sum of individual costs in metrics.
+    Also checks for duplicate consecutive costs which might indicate buggy counting.
+    If the consecutive costs are identical, the file is affected by this bug:
+    https://github.com/All-Hands-AI/OpenHands/issues/5383
+
+    Args:
+        row: DataFrame row containing instance data with metrics
+    Returns:
+        float: The verified total cost for this instance (corrected if needed)
+    """
+    try:
+        metrics = row.get('metrics')
+        if not metrics:
+            logger.warning(f'Instance {row["instance_id"]}: No metrics found')
+            return 0.0
+
+        accumulated = metrics.get('accumulated_cost')
+        costs = metrics.get('costs', [])
+
+        if accumulated is None:
+            logger.warning(
+                f'Instance {row["instance_id"]}: No accumulated_cost in metrics'
+            )
+            return 0.0
+
+        # Check for duplicate consecutive costs and systematic even-odd pairs
+        has_duplicate = False
+        all_pairs_match = True
+
+        # Check each even-odd pair (0-1, 2-3, etc.)
+        for i in range(0, len(costs) - 1, 2):
+            if abs(costs[i]['cost'] - costs[i + 1]['cost']) < 1e-6:
+                has_duplicate = True
+                logger.debug(
+                    f'Instance {row["instance_id"]}: Possible buggy double-counting detected! '
+                    f'Steps {i} and {i + 1} have identical costs: {costs[i]["cost"]:.2f}'
+                )
+            else:
+                all_pairs_match = False
+                break
+
+        # Calculate total cost, accounting for buggy double counting if detected
+        if len(costs) >= 2 and has_duplicate and all_pairs_match:
+            paired_steps_cost = sum(
+                cost_entry['cost']
+                for cost_entry in costs[: -1 if len(costs) % 2 else None]
+            )
+            real_paired_cost = paired_steps_cost / 2
+
+            unpaired_cost = costs[-1]['cost'] if len(costs) % 2 else 0
+            total_cost = real_paired_cost + unpaired_cost
+
+        else:
+            total_cost = sum(cost_entry['cost'] for cost_entry in costs)
+
+        if not abs(total_cost - accumulated) < 1e-6:
+            logger.warning(
+                f'Instance {row["instance_id"]}: Cost mismatch: '
+                f'accumulated: {accumulated:.2f}, sum of costs: {total_cost:.2f}, '
+            )
+
+        return total_cost
+
+    except Exception as e:
+        logger.error(
+            f'Error verifying costs for instance {row.get("instance_id", "UNKNOWN")}: {e}'
+        )
+        return 0.0
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description='Verify costs in SWE-bench output file'
+    )
+    parser.add_argument(
+        'input_filepath', type=str, help='Path to the output.jsonl file'
+    )
+    args = parser.parse_args()
+
+    try:
+        # Load and verify the JSONL file
+        df = pd.read_json(args.input_filepath, lines=True)
+        logger.info(f'Loaded {len(df)} instances from {args.input_filepath}')
+
+        # Verify costs for each instance and sum up total
+        total_cost = df.apply(verify_instance_costs, axis=1).sum()
+        logger.info(f'Total verified cost across all instances: ${total_cost:.2f}')
+
+    except Exception as e:
+        logger.error(f'Failed to process file: {e}')
+        raise
+
+
+if __name__ == '__main__':
+    main()

evaluation/benchmarks/nocode_bench/scripts/run_infer_nc.sh

@@ -0,0 +1,146 @@
+#!/usr/bin/env bash
+set -eo pipefail
+
+source "evaluation/utils/version_control.sh"
+
+MODEL_CONFIG=$1
+COMMIT_HASH=$2
+AGENT=$3
+EVAL_LIMIT=$4
+MAX_ITER=$5
+NUM_WORKERS=$6
+DATASET=$7
+SPLIT=$8
+N_RUNS=$9
+MODE=${10}
+
+
+if [ -z "$NUM_WORKERS" ]; then
+  NUM_WORKERS=1
+  echo "Number of workers not specified, use default $NUM_WORKERS"
+fi
+checkout_eval_branch
+
+if [ -z "$AGENT" ]; then
+  echo "Agent not specified, use default CodeActAgent"
+  AGENT="CodeActAgent"
+fi
+
+if [ -z "$MAX_ITER" ]; then
+  echo "MAX_ITER not specified, use default 100"
+  MAX_ITER=100
+fi
+
+if [ -z "$RUN_WITH_BROWSING" ]; then
+  echo "RUN_WITH_BROWSING not specified, use default false"
+  RUN_WITH_BROWSING=false
+fi
+
+
+if [ -z "$DATASET" ]; then
+  echo "DATASET not specified, use default princeton-nlp/SWE-bench_Lite"
+  DATASET="princeton-nlp/SWE-bench_Lite"
+fi
+
+if [ -z "$SPLIT" ]; then
+  echo "SPLIT not specified, use default test"
+  SPLIT="test"
+fi
+
+if [ -z "$MODE" ]; then
+  MODE="swe"
+  echo "MODE not specified, use default $MODE"
+fi
+
+if [ -n "$EVAL_CONDENSER" ]; then
+  echo "Using Condenser Config: $EVAL_CONDENSER"
+else
+  echo "No Condenser Config provided via EVAL_CONDENSER, use default (NoOpCondenser)."
+fi
+
+export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
+echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
+
+get_openhands_version
+
+echo "AGENT: $AGENT"
+echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "MODEL_CONFIG: $MODEL_CONFIG"
+echo "DATASET: $DATASET"
+echo "SPLIT: $SPLIT"
+echo "MAX_ITER: $MAX_ITER"
+echo "NUM_WORKERS: $NUM_WORKERS"
+echo "COMMIT_HASH: $COMMIT_HASH"
+echo "MODE: $MODE"
+echo "EVAL_CONDENSER: $EVAL_CONDENSER"
+
+# Default to NOT use Hint
+if [ -z "$USE_HINT_TEXT" ]; then
+  export USE_HINT_TEXT=false
+fi
+echo "USE_HINT_TEXT: $USE_HINT_TEXT"
+EVAL_NOTE="$OPENHANDS_VERSION"
+# if not using Hint, add -no-hint to the eval note
+if [ "$USE_HINT_TEXT" = false ]; then
+  EVAL_NOTE="$EVAL_NOTE-no-hint"
+fi
+
+if [ "$RUN_WITH_BROWSING" = true ]; then
+  EVAL_NOTE="$EVAL_NOTE-with-browsing"
+fi
+
+if [ -n "$EXP_NAME" ]; then
+  EVAL_NOTE="$EVAL_NOTE-$EXP_NAME"
+fi
+# if mode != swe, add mode to the eval note
+if [ "$MODE" != "swe" ]; then
+  EVAL_NOTE="${EVAL_NOTE}-${MODE}"
+fi
+# Add condenser config to eval note if provided
+if [ -n "$EVAL_CONDENSER" ]; then
+  EVAL_NOTE="${EVAL_NOTE}-${EVAL_CONDENSER}"
+fi
+
+function run_eval() {
+  local eval_note="${1}"
+  COMMAND="poetry run python evaluation/benchmarks/nocode_bench/run_infer_nc.py \
+    --agent-cls $AGENT \
+    --llm-config $MODEL_CONFIG \
+    --max-iterations $MAX_ITER \
+    --eval-num-workers $NUM_WORKERS \
+    --eval-note $eval_note \
+    --dataset $DATASET \
+    --split $SPLIT \
+    --mode $MODE"
+
+
+
+  if [ -n "$EVAL_LIMIT" ]; then
+    echo "EVAL_LIMIT: $EVAL_LIMIT"
+    COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
+  fi
+
+  # Run the command
+  eval $COMMAND
+}
+
+unset SANDBOX_ENV_GITHUB_TOKEN # prevent the agent from using the github token to push
+if [ -z "$N_RUNS" ]; then
+  N_RUNS=1
+  echo "N_RUNS not specified, use default $N_RUNS"
+fi
+
+# Skip runs if the run number is in the SKIP_RUNS list
+# read from env variable SKIP_RUNS as a comma separated list of run numbers
+SKIP_RUNS=(${SKIP_RUNS//,/ })
+for i in $(seq 1 $N_RUNS); do
+  if [[ " ${SKIP_RUNS[@]} " =~ " $i " ]]; then
+    echo "Skipping run $i"
+    continue
+  fi
+  current_eval_note="$EVAL_NOTE-run_$i"
+  echo "EVAL_NOTE: $current_eval_note"
+  run_eval $current_eval_note
+done
+
+checkout_original_branch

evaluation/benchmarks/nocode_bench/scripts/setup/compare_patch_filename.py

@@ -0,0 +1,54 @@
+"""This script compares gold patches with OpenHands-generated patches and check whether
+OpenHands found the right (set of) files to modify.
+"""
+
+import argparse
+import json
+import re
+
+
+def extract_modified_files(patch):
+    modified_files = set()
+    file_pattern = re.compile(r'^diff --git a/(.*?) b/')
+
+    for line in patch.split('\n'):
+        match = file_pattern.match(line)
+        if match:
+            modified_files.add(match.group(1))
+
+    return modified_files
+
+
+def process_report(oh_output_file):
+    succ = 0
+    fail = 0
+    for line in open(oh_output_file):
+        line = json.loads(line)
+        instance_id = line['instance_id']
+        gold_patch = line['swe_instance']['patch']
+        generated_patch = line['git_patch']
+        gold_modified_files = extract_modified_files(gold_patch)
+        # swe-bench lite only: a gold patch always contains exactly one file
+        assert len(gold_modified_files) == 1
+        generated_modified_files = extract_modified_files(generated_patch)
+
+        # Check if all files in gold_patch are also in generated_patch
+        all_files_in_generated = gold_modified_files.issubset(generated_modified_files)
+        if all_files_in_generated:
+            succ += 1
+        else:
+            fail += 1
+            print(
+                f'{instance_id}: file mismatch, gold = {gold_modified_files}, generated = {generated_modified_files}'
+            )
+    print(
+        f'\nSUMMARY: {succ} out of {succ + fail} instances found correct files to edit, success rate = {succ / float(succ + fail)}'
+    )
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--oh_output_file', help='Path to the OH output file')
+    args = parser.parse_args()
+
+    process_report(args.oh_output_file)

evaluation/benchmarks/nocode_bench/scripts/setup/instance_nc_entry.sh

@@ -0,0 +1,53 @@
+#!/usr/bin/env bash
+
+source ~/.bashrc
+SWEUTIL_DIR=/swe_util
+
+if [ -z "$SWE_INSTANCE_ID" ]; then
+    echo "Error: SWE_INSTANCE_ID is not set." >&2
+    exit 1
+fi
+
+
+item=$(jq --arg INSTANCE_ID "$SWE_INSTANCE_ID" '.[] | select(.instance_id == $INSTANCE_ID)' $SWEUTIL_DIR/eval_data/instances/swe-bench-instance.json)
+
+
+if [[ -z "$item" ]]; then
+  echo "No item found for the provided instance ID."
+  exit 1
+fi
+
+REPO_NAME=$(echo "$item" | jq -r '.repo | split("/")[-1]')
+WORKSPACE_NAME="$REPO_NAME"
+
+
+echo "WORKSPACE_NAME: $WORKSPACE_NAME"
+
+
+# Clear the workspace
+if [ -d /workspace ]; then
+    rm -rf /workspace/*
+else
+    mkdir /workspace
+fi
+# Copy repo to workspace
+if [ -d /workspace/$WORKSPACE_NAME ]; then
+    rm -rf /workspace/$WORKSPACE_NAME
+fi
+mkdir -p /workspace
+
+SRC_DIR="/root/$REPO_NAME"
+DEST_DIR="/workspace/$WORKSPACE_NAME"
+
+cp -r "$SRC_DIR" "$DEST_DIR"
+
+
+
+echo ">> Extracting conda environment name..."
+CONDA_ENV_NAME=$(echo "$item" | jq -r '.conda_env // empty')
+
+# Activate instance-specific environment
+if [ -d /opt/miniconda3 ]; then
+    . /opt/miniconda3/etc/profile.d/conda.sh
+    conda activate $CONDA_ENV_NAME
+fi

evaluation/benchmarks/nocode_bench/scripts/utils/evaluation_utils.py

@@ -0,0 +1,154 @@
+import json
+import multiprocessing as mp
+from typing import Awaitable, Callable, TextIO
+
+import numpy as np
+import pandas as pd
+from pydantic import SecretStr
+from tqdm import tqdm
+
+from evaluation.utils.shared import (
+    EvalMetadata,
+    EvalOutput,
+    _process_instance_wrapper,
+    _process_instance_wrapper_mp,
+)
+from openhands.core.logger import openhands_logger as logger
+
+
+def update_progress_nc(
+    result: EvalOutput,
+    pbar: tqdm,
+    output_fp: TextIO,
+):
+    """Update the progress bar and write the result to the output file."""
+    pbar.update(1)
+    pbar.set_description(f'Instance {result.instance_id}')
+    pbar.set_postfix_str(f'Test Result: {str(result.test_result)[:300]}...')
+    logger.info(
+        f'Finished evaluation for instance {result.instance_id}: '
+        f'{str(result.test_result)[:300]}...\n'
+    )
+
+    def make_serializable(obj):
+        if isinstance(obj, pd.Series):
+            return make_serializable(obj.to_dict())
+
+        if isinstance(obj, dict):
+            return {k: make_serializable(v) for k, v in obj.items()}
+
+        elif isinstance(obj, (list, tuple, set)):
+            converted = [make_serializable(v) for v in obj]
+            if isinstance(obj, list):
+                return converted
+            elif isinstance(obj, tuple):
+                return tuple(converted)
+            else:  # set
+                return converted
+
+        elif isinstance(obj, np.ndarray):
+            return obj.tolist()
+
+        elif isinstance(obj, np.generic):
+            return obj.item()
+
+        elif isinstance(obj, pd.Timestamp):
+            return obj.isoformat()
+
+        elif SecretStr is not None and isinstance(obj, SecretStr):
+            return str(obj)
+
+        else:
+            return obj
+
+    try:
+        raw_data = result.model_dump(mode='python', round_trip=False)
+        safe_data = make_serializable(raw_data)
+        output_fp.write(json.dumps(safe_data, ensure_ascii=False) + '\n')
+        output_fp.flush()
+
+    except Exception as e:
+        logger.error(f'Failed to write full result: {e}')
+
+        fallback = {
+            'instance_id': result.instance_id,
+            'model_patch': result.test_result.get('git_patch', ''),
+        }
+        try:
+            output_fp.write(json.dumps(fallback, ensure_ascii=False) + '\n')
+            output_fp.flush()
+            logger.info(
+                f'Wrote fallback result for instance {result.instance_id}: only instance_id and model_patch.'
+            )
+        except Exception as e2:
+            logger.error(f'Failed to write fallback result: {e2}')
+
+
+def cleanup():
+    print('Cleaning up child processes...')
+    for process in mp.active_children():
+        print(f'Terminating child process: {process.name}')
+        process.terminate()
+        process.join()
+
+
+def run_evaluation_nocode_bench(
+    dataset: pd.DataFrame,
+    metadata: EvalMetadata | None,
+    output_file: str,
+    num_workers: int,
+    process_instance_func: Callable[
+        [pd.Series, EvalMetadata, bool], Awaitable[EvalOutput]
+    ],
+    max_retries: int = 5,  # number of retries for each instance
+    timeout_seconds: int | None = None,
+):
+    use_multiprocessing = num_workers > 1
+
+    if metadata is not None:
+        logger.info(
+            f'Evaluation started with Agent {metadata.agent_class}:\n'
+            f'model {metadata.llm_config.model}, max iterations {metadata.max_iterations}.\n'
+        )
+    else:
+        logger.warning('Running evaluation without metadata.')
+        logger.info(f'Evaluation started with {num_workers} workers.')
+
+    total_instances = len(dataset)
+    pbar = tqdm(total=total_instances, desc='Instances processed')
+    output_fp = open(output_file, 'a')
+
+    try:
+        if use_multiprocessing:
+            with mp.Pool(num_workers) as pool:
+                args_iter = (
+                    (
+                        process_instance_func,
+                        instance,
+                        metadata,
+                        True,
+                        max_retries,
+                        timeout_seconds,
+                    )
+                    for _, instance in dataset.iterrows()
+                )
+                results = pool.imap_unordered(_process_instance_wrapper_mp, args_iter)
+                for result in results:
+                    update_progress_nc(result, pbar, output_fp)
+        else:
+            for _, instance in dataset.iterrows():
+                result = _process_instance_wrapper(
+                    process_instance_func=process_instance_func,
+                    instance=instance,
+                    metadata=metadata,
+                    use_mp=False,
+                    max_retries=max_retries,
+                )
+                update_progress_nc(result, pbar, output_fp)
+
+    except KeyboardInterrupt:
+        print('\nKeyboardInterrupt received. Cleaning up...\n')
+        cleanup()
+
+    output_fp.close()
+    logger.info('\nEvaluation finished.\n')

evaluation/benchmarks/scienceagentbench/run_infer.py

@@ -12,6 +12,7 @@ from evaluation.utils.shared import (
     codeact_user_response,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -218,7 +219,7 @@ If the program uses some packages that are incompatible, please figure out alter
     # You can simply get the LAST `MessageAction` from the returned `state.history` and parse it for evaluation.
     if state is None:
         raise ValueError('State should not be None.')
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
 
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here

evaluation/benchmarks/swe_bench/README.md

@@ -93,6 +93,9 @@ export USE_HINT_TEXT=true # Ignore this if you are not sure.
 
 # Specify a condenser configuration for memory management (default: NoOpCondenser)
 export EVAL_CONDENSER=summarizer_for_eval # Name of the condenser config group in config.toml
+
+# Specify the instruction prompt template file name
+export INSTRUCTION_TEMPLATE_NAME=swe_custom.j2 # Name of the file in the swe_bench/prompts folder.
 ```
 
 Let's say you'd like to run 10 instances using `llm.eval_gpt4_1106_preview` and CodeActAgent,

evaluation/benchmarks/swe_bench/binary_patch_utils.py

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

evaluation/benchmarks/swe_bench/eval_infer.py

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

evaluation/benchmarks/swe_bench/loc_eval/loc_evaluator.py

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

evaluation/benchmarks/swe_bench/loc_eval/loc_utils.py

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

evaluation/benchmarks/swe_bench/run_infer.py

@@ -108,7 +108,9 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageActio
     llm_model = metadata.llm_config.model
 
     # Determine the template file based on mode and LLM
-    if mode.startswith('swt'):
+    if metadata.instruction_template_name:
+        template_name = metadata.instruction_template_name
+    elif mode.startswith('swt'):
         template_name = 'swt.j2'
     elif mode == 'swe':
         if 'gpt-4.1' in llm_model:
@@ -122,6 +124,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageActio
         logger.error(f'Unexpected evaluation mode: {mode}. Falling back to default.')
         template_name = 'swe_default.j2'
 
+    logger.debug(f'Using instruction template file: {template_name}')
     # Set up Jinja2 environment
     # Assuming templates are in 'evaluation/benchmarks/swe_bench/prompts' relative to this script
     prompts_dir = os.path.join(os.path.dirname(__file__), 'prompts')

evaluation/benchmarks/swe_bench/run_infer_interact.py

@@ -21,6 +21,7 @@ from evaluation.utils.shared import (
     EvalException,
     EvalMetadata,
     EvalOutput,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -179,7 +180,7 @@ def process_instance(
         raise ValueError('State should not be None.')
 
     histories = [event_to_dict(event) for event in state.history]
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
 
     # Save the output
     instruction = message_action.content

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

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

evaluation/benchmarks/testgeneval/compute_readability.py

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

evaluation/benchmarks/testgeneval/eval_infer.py

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

evaluation/benchmarks/testgeneval/log_parsers.py

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

evaluation/benchmarks/testgeneval/metrics.py

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

evaluation/benchmarks/testgeneval/report_utils.py

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

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

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

evaluation/benchmarks/testgeneval/test_filter.py

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

evaluation/benchmarks/testgeneval/test_spec.py

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

evaluation/benchmarks/testgeneval/utils.py

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

evaluation/benchmarks/the_agent_company/browsing.py

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

evaluation/benchmarks/the_agent_company/run_infer.py

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

evaluation/benchmarks/the_agent_company/scripts/summarise_results.py

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

evaluation/benchmarks/toolqa/run_infer.py

@@ -11,6 +11,7 @@ from evaluation.utils.shared import (
     codeact_user_response,
     compatibility_for_eval_history_pairs,
     get_default_sandbox_config_for_eval,
+    get_metrics,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -134,7 +135,7 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
     correct = eval_answer(str(model_answer_raw), str(answer))
     logger.info(f'Final message: {model_answer_raw} | Correctness: {correct}')
 
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
 
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here

evaluation/benchmarks/versicode/inference_utils/api_code_migration.py

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