Merge branch 'main' into fix-timeout-message-tests

- Updated TIMEOUT_MESSAGE_TEMPLATE in bash_constants.py to include specific key combinations ('C-c', 'C-z', 'C-d')
- Modified bash.py to use TIMEOUT_MESSAGE_TEMPLATE instead of hardcoded message
- Modified windows_bash.py to use TIMEOUT_MESSAGE_TEMPLATE instead of hardcoded message
- Ensures consistent timeout message format across all bash implementations
- Fixes failing runtime tests related to timeout error prompt changes

.github/CODEOWNERS

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

.github/scripts/update_pr_description.sh

@@ -0,0 +1,71 @@
+#!/bin/bash
+
+set -euxo pipefail
+
+# This script updates the PR description with commands to run the PR locally
+# It adds both Docker and uvx commands
+
+# Get the branch name for the PR
+BRANCH_NAME=$(gh pr view "$PR_NUMBER" --json headRefName --jq .headRefName)
+
+# Define the Docker command
+DOCKER_RUN_COMMAND="docker run -it --rm \
+  -p 3000:3000 \
+  -v /var/run/docker.sock:/var/run/docker.sock \
+  --add-host host.docker.internal:host-gateway \
+  -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:${SHORT_SHA}-nikolaik \
+  --name openhands-app-${SHORT_SHA} \
+  docker.all-hands.dev/all-hands-ai/openhands:${SHORT_SHA}"
+
+# Define the uvx command
+UVX_RUN_COMMAND="uvx --python 3.12 --from git+https://github.com/All-Hands-AI/OpenHands@${BRANCH_NAME} openhands"
+
+# Get the current PR body
+PR_BODY=$(gh pr view "$PR_NUMBER" --json body --jq .body)
+
+# Prepare the new PR body with both commands
+if echo "$PR_BODY" | grep -q "To run this PR locally, use the following command:"; then
+  # For existing PR descriptions, use a more robust approach
+  # Split the PR body at the "To run this PR locally" section and replace everything after it
+  BEFORE_SECTION=$(echo "$PR_BODY" | sed '/To run this PR locally, use the following command:/,$d')
+  NEW_PR_BODY=$(cat <<EOF
+${BEFORE_SECTION}
+
+To run this PR locally, use the following command:
+
+GUI with Docker:
+\`\`\`
+${DOCKER_RUN_COMMAND}
+\`\`\`
+
+CLI with uvx:
+\`\`\`
+${UVX_RUN_COMMAND}
+\`\`\`
+EOF
+)
+else
+  # For new PR descriptions: use heredoc safely without indentation
+  NEW_PR_BODY=$(cat <<EOF
+$PR_BODY
+
+---
+
+To run this PR locally, use the following command:
+
+GUI with Docker:
+\`\`\`
+${DOCKER_RUN_COMMAND}
+\`\`\`
+
+CLI with uvx:
+\`\`\`
+${UVX_RUN_COMMAND}
+\`\`\`
+EOF
+)
+fi
+
+# Update the PR description
+echo "Updating PR description with Docker and uvx commands"
+gh pr edit "$PR_NUMBER" --body "$NEW_PR_BODY"

.github/workflows/e2e-tests.yml

@@ -0,0 +1,223 @@
+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@v3
+        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 -v --no-header --capture=no --timeout=600
+
+      - 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/ghcr-build.yml

@@ -332,29 +332,5 @@ jobs:
           SHORT_SHA: ${{ steps.short_sha.outputs.SHORT_SHA }}
         shell: bash
         run: |
-          echo "updating PR description"
-          DOCKER_RUN_COMMAND="docker run -it --rm \
-            -p 3000:3000 \
-            -v /var/run/docker.sock:/var/run/docker.sock \
-            --add-host host.docker.internal:host-gateway \
-            -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:$SHORT_SHA-nikolaik \
-            --name openhands-app-$SHORT_SHA \
-            docker.all-hands.dev/all-hands-ai/openhands:$SHORT_SHA"
-
-          PR_BODY=$(gh pr view $PR_NUMBER --json body --jq .body)
-
-          if echo "$PR_BODY" | grep -q "To run this PR locally, use the following command:"; then
-            UPDATED_PR_BODY=$(echo "${PR_BODY}" | sed -E "s|docker run -it --rm.*|$DOCKER_RUN_COMMAND|")
-          else
-            UPDATED_PR_BODY="${PR_BODY}
-
-          ---
-
-          To run this PR locally, use the following command:
-          \`\`\`
-          $DOCKER_RUN_COMMAND
-          \`\`\`"
-          fi
-
-          echo "updated body: $UPDATED_PR_BODY"
-          gh pr edit $PR_NUMBER --body "$UPDATED_PR_BODY"
+          echo "Updating PR description with Docker and uvx commands"
+          bash ${GITHUB_WORKSPACE}/.github/scripts/update_pr_description.sh

.github/workflows/py-tests.yml

@@ -48,11 +48,9 @@ jobs:
       - name: Build Environment
         run: make build
       - name: Run Unit Tests
-        run: poetry run pytest --forked -n auto -svv ./tests/unit
+        run: PYTHONPATH=".:$PYTHONPATH" poetry run pytest --forked -n auto -svv ./tests/unit
       - name: Run Runtime Tests with CLIRuntime
-        run: TEST_RUNTIME=cli poetry run pytest -svv tests/runtime/test_bash.py
-      - name: Run E2E Tests
-        run: poetry run pytest -svv tests/e2e
+        run: PYTHONPATH=".:$PYTHONPATH" TEST_RUNTIME=cli poetry run pytest -svv tests/runtime/test_bash.py
 
   # Run specific Windows python tests
   test-on-windows:
@@ -77,9 +75,11 @@ jobs:
       - name: Run Windows unit tests
         run: poetry run pytest -svv tests/unit/test_windows_bash.py
         env:
+          PYTHONPATH: ".;$env:PYTHONPATH"
           DEBUG: "1"
       - name: Run Windows runtime tests with LocalRuntime
         run: $env:TEST_RUNTIME="local"; poetry run pytest -svv tests/runtime/test_bash.py
         env:
+          PYTHONPATH: ".;$env:PYTHONPATH"
           TEST_RUNTIME: local
           DEBUG: "1"

.github/workflows/stale.yml

@@ -12,11 +12,11 @@ jobs:
     steps:
       - uses: actions/stale@v9
         with:
-          stale-issue-message: 'This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
-          stale-pr-message: 'This PR is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
-          days-before-stale: 30
+          stale-issue-message: 'This issue is stale because it has been open for 40 days with no activity. Remove the stale label or leave a comment, otherwise it will be closed in 10 days.'
+          stale-pr-message: 'This PR is stale because it has been open for 40 days with no activity. Remove the stale label or leave a comment, otherwise it will be closed in 10 days.'
+          days-before-stale: 40
           exempt-issue-labels: 'roadmap'
-          close-issue-message: 'This issue was closed because it has been stalled for over 30 days with no activity.'
-          close-pr-message: 'This PR was closed because it has been stalled for over 30 days with no activity.'
-          days-before-close: 7
+          close-issue-message: 'This issue was automatically closed due to 50 days of inactivity. We do this to help keep the issues somewhat manageable and focus on active issues.'
+          close-pr-message: 'This PR was closed because it had no activity for 50 days. If you feel this was closed in error, and you would like to continue the PR, please resubmit or let us know.'
+          days-before-close: 10
           operations-per-run: 150

.gitignore

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

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:0.53-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:0.53-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:0.53-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:0.53
 ```
 
+</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:0.53-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:0.53-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:0.53
 ```
 
 > **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:0.53-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:0.53-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:0.53
 ```
 
 **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/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:0.53-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

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

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

docker-compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.53-nikolaik}
       #- SANDBOX_USER_ID=${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/docs.json

@@ -71,6 +71,7 @@
                     {
                       "group": "Providers",
                       "pages": [
+                        "usage/llms/openhands-llms",
                         "usage/llms/azure-llms",
                         "usage/llms/google-llms",
                         "usage/llms/groq",
@@ -78,7 +79,6 @@
                         "usage/llms/litellm-proxy",
                         "usage/llms/moonshot",
                         "usage/llms/openai-llms",
-                        "usage/llms/openhands-llms",
                         "usage/llms/openrouter"
                       ]
                     }

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/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:0.53-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e SANDBOX_VOLUMES=$SANDBOX_VOLUMES \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -112,7 +128,7 @@ docker run -it \
     -v ~/.openhands:/.openhands \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.51 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.53 \
     python -m openhands.cli.main --override-cli-mode true
 ```
 

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

@@ -7,6 +7,67 @@ description: High level overview of the Graphical User Interface (GUI) in OpenHa
 
 - [OpenHands is running](/usage/local-setup)
 
+## Launching the GUI Server
+
+### Using the CLI Command
+
+You can launch the OpenHands GUI server directly from the command line using the `serve` command:
+
+<Callout type="info">
+**Prerequisites**: You need to have the [OpenHands CLI installed](/usage/how-to/cli-mode) first, OR have `uv` installed and run `uvx --python 3.12 --from openhands-ai openhands serve`. Otherwise, you'll need to use Docker directly (see the [Docker section](#using-docker-directly) below).
+</Callout>
+
+```bash
+openhands serve
+```
+
+This command will:
+- Check that Docker is installed and running
+- Pull the required Docker images
+- Launch the OpenHands GUI server at http://localhost:3000
+- Use the same configuration directory (`~/.openhands`) as the CLI mode
+
+#### Mounting Your Current Directory
+
+To mount your current working directory into the GUI server container, use the `--mount-cwd` flag:
+
+```bash
+openhands serve --mount-cwd
+```
+
+This is useful when you want to work on files in your current directory through the GUI. The directory will be mounted at `/workspace` inside the container.
+
+#### Using GPU Support
+
+If you have NVIDIA GPUs and want to make them available to the OpenHands container, use the `--gpu` flag:
+
+```bash
+openhands serve --gpu
+```
+
+This will enable GPU support via nvidia-docker, mounting all available GPUs into the container. You can combine this with other flags:
+
+```bash
+openhands serve --gpu --mount-cwd
+```
+
+**Prerequisites for GPU support:**
+- NVIDIA GPU drivers must be installed on your host system
+- [NVIDIA Container Toolkit (nvidia-docker2)](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html) must be installed and configured
+
+#### Requirements
+
+Before using the `openhands serve` command, ensure that:
+- Docker is installed and running on your system
+- You have internet access to pull the required Docker images
+- Port 3000 is available on your system
+
+The CLI will automatically check these requirements and provide helpful error messages if anything is missing.
+
+### Using Docker Directly
+
+Alternatively, you can run the GUI server using Docker directly. See the [local setup guide](/usage/local-setup) for detailed Docker instructions.
+
 ## Overview
 
 ### Initial Setup

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:0.53-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:0.53 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/usage/llms/llms.mdx

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

docs/usage/llms/local-llms.mdx

@@ -68,23 +68,23 @@ Download and install the LM Studio desktop app from [lmstudio.ai](https://lmstud
 1. Check [the installation guide](/usage/local-setup) and ensure all prerequisites are met before running OpenHands, then run:
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.53-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:0.53-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:0.53
 ```
 
 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:0.53
 Starting OpenHands...
 Running OpenHands as root
 14:22:13 - openhands:INFO: server_config.py:50 - Using config class None

docs/usage/llms/openhands-llms.mdx

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

docs/usage/local-setup.mdx

@@ -66,20 +66,64 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
 
 ### Start the App
 
+#### Option 1: Using the CLI Launcher with uv (Recommended)
+
+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
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.51-nikolaik
+# 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
+pip install openhands-ai
+
+# Launch the GUI server
+openhands serve
+```
+
+Note that you'll still need `uv` installed for the default MCP servers to work properly.
+
+</Accordion>
+
+#### Option 2: Using Docker Directly
+
+<Accordion title="Docker Command (Click to expand)">
+
+```bash
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.53-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:0.53-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:0.53
 ```
 
+</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!
@@ -100,6 +144,16 @@ OpenHands requires an API key to access most language models. Here's how to get
 
 <AccordionGroup>
 
+<Accordion title="OpenHands (Recommended)">
+
+1. [Log in to OpenHands Cloud](https://app.all-hands.dev).
+2. Go to the Settings page and navigate to the `API Keys` tab.
+3. Copy your `LLM API Key`.
+
+OpenHands provides access to state-of-the-art agentic coding models with competitive pricing. [Learn more about OpenHands LLM provider](/usage/llms/openhands-llms).
+
+</Accordion>
+
 <Accordion title="Anthropic (Claude)">
 
 1. [Create an Anthropic account](https://console.anthropic.com/).

evaluation/benchmarks/EDA/run_infer.py

@@ -18,8 +18,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -172,7 +172,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--answerer_model', '-a', default='gpt-3.5-turbo', help='answerer model'
     )

evaluation/benchmarks/commit0/run_infer.py

@@ -26,8 +26,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -506,7 +506,6 @@ def commit0_setup(dataset: pd.DataFrame, repo_split: str) -> pd.DataFrame:
     Returns:
         Filtered dataset based on split type
     """
-
     filtered_dataset = pd.concat(
         [
             dataset[dataset['repo'].str.split('/').str[1] == repo]
@@ -525,7 +524,7 @@ def commit0_setup(dataset: pd.DataFrame, repo_split: str) -> pd.DataFrame:
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/discoverybench/run_infer.py

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

evaluation/benchmarks/gaia/run_infer.py

@@ -10,7 +10,6 @@ import huggingface_hub
 import pandas as pd
 from datasets import load_dataset
 from PIL import Image
-from pydantic import SecretStr
 
 from evaluation.benchmarks.gaia.scorer import question_scorer
 from evaluation.benchmarks.gaia.utils import (
@@ -31,8 +30,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
     load_from_toml,
 )
 from openhands.core.config.utils import get_agent_config_arg
@@ -80,8 +79,7 @@ def get_config(
 
     config_copy = copy.deepcopy(config)
     load_from_toml(config_copy)
-    if config_copy.search_api_key:
-        config.search_api_key = SecretStr(config_copy.search_api_key)
+    config.search_api_key = config_copy.search_api_key
     return config
 
 
@@ -294,7 +292,7 @@ Here is the task:
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--level',
         type=str,

evaluation/benchmarks/gorilla/run_infer.py

@@ -20,8 +20,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -134,7 +134,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--hubs',
         type=str,

evaluation/benchmarks/gpqa/run_infer.py

@@ -38,8 +38,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -312,7 +312,7 @@ Ok now its time to start solving the question. Good luck!
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     # data split must be one of 'gpqa_main', 'gqpa_diamond', 'gpqa_experts', 'gpqa_extended'
     parser.add_argument(
         '--data-split',

evaluation/benchmarks/lca_ci_build_repair/eval_infer.py

@@ -21,7 +21,7 @@ from evaluation.utils.shared import (
 from openhands.core.config import (
     LLMConfig,
     OpenHandsConfig,
-    get_parser,
+    get_evaluation_parser,
     load_openhands_config,
 )
 from openhands.core.logger import openhands_logger as logger
@@ -167,7 +167,7 @@ def process_predictions(predictions_path: str):
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '-s',
         '--eval-split',

evaluation/benchmarks/lca_ci_build_repair/run_infer.py

@@ -30,8 +30,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
     load_openhands_config,
 )
 from openhands.core.logger import openhands_logger as logger
@@ -358,7 +358,7 @@ Be thorough in your exploration, testing, and reasoning. It's fine if your think
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '-s',
         '--eval-split',

evaluation/benchmarks/logic_reasoning/run_infer.py

@@ -18,8 +18,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -267,7 +267,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/mint/run_infer.py

@@ -23,8 +23,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -229,7 +229,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
 
     SUBSETS = [
         # Eurus subset: https://arxiv.org/abs/2404.02078

evaluation/benchmarks/ml_bench/run_analysis.py

@@ -4,7 +4,11 @@ import pprint
 
 import tqdm
 
-from openhands.core.config import get_llm_config_arg, get_parser, load_openhands_config
+from openhands.core.config import (
+    get_evaluation_parser,
+    get_llm_config_arg,
+    load_openhands_config,
+)
 from openhands.core.logger import openhands_logger as logger
 from openhands.llm.llm import LLM
 
@@ -111,7 +115,7 @@ def classify_error(llm: LLM, failed_case: dict) -> str:
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--json_file_path',
         type=str,

evaluation/benchmarks/ml_bench/run_infer.py

@@ -34,8 +34,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
     load_openhands_config,
 )
 from openhands.core.logger import openhands_logger as logger
@@ -273,7 +273,7 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '-s',
         '--eval-split',

evaluation/benchmarks/multi_swe_bench/eval_infer.py

@@ -30,7 +30,7 @@ from evaluation.utils.shared import (
 from openhands.core.config import (
     LLMConfig,
     OpenHandsConfig,
-    get_parser,
+    get_evaluation_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime
@@ -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.
@@ -323,7 +322,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--input-file',
         type=str,

evaluation/benchmarks/multi_swe_bench/run_infer.py

@@ -32,8 +32,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -772,7 +772,7 @@ def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
 
 if __name__ == '__main__':
     # pdb.set_trace()
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/scienceagentbench/run_infer.py

@@ -21,8 +21,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -239,7 +239,7 @@ If the program uses some packages that are incompatible, please figure out alter
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--use-knowledge',
         type=str,

evaluation/benchmarks/swe_bench/README.md

@@ -2,6 +2,8 @@
 
 This folder contains the evaluation harness that we built on top of the original [SWE-Bench benchmark](https://www.swebench.com/) ([paper](https://arxiv.org/abs/2310.06770)).
 
+**UPDATE (8/12/2025): We now support running SWE-rebench evaluation (see the paper [here](https://arxiv.org/abs/2505.20411))! For how to run it, checkout [this README](./SWE-rebench.md).**
+
 **UPDATE (6/15/2025): We now support running SWE-bench-Live evaluation (see the paper [here](https://arxiv.org/abs/2505.23419))! For how to run it, checkout [this README](./SWE-bench-Live.md).**
 
 **UPDATE (5/26/2025): We now support running interactive SWE-Bench evaluation (see the paper [here](https://arxiv.org/abs/2502.13069))! For how to run it, checkout [this README](./SWE-Interact.md).**
@@ -183,24 +185,7 @@ The final results will be saved to `evaluation/evaluation_outputs/outputs/swe_be
 - `report.json`: a JSON file that contains keys like `"resolved_ids"` pointing to instance IDs that are resolved by the agent.
 - `logs/`: a directory of test logs
 
-### Run evaluation with `RemoteRuntime`
 
-OpenHands Remote Runtime is currently in beta (read [here](https://runtime.all-hands.dev/) for more details), it allows you to run rollout in parallel in the cloud, so you don't need a powerful machine to run evaluation.
-Fill out [this form](https://docs.google.com/forms/d/e/1FAIpQLSckVz_JFwg2_mOxNZjCtr7aoBFI2Mwdan3f75J_TrdMS1JV2g/viewform) to apply if you want to try this out!
-
-```bash
-./evaluation/benchmarks/swe_bench/scripts/eval_infer_remote.sh [output.jsonl filepath] [num_workers]
-
-# Example - This evaluates patches generated by CodeActAgent on Llama-3.1-70B-Instruct-Turbo on "princeton-nlp/SWE-bench_Lite"'s test set, with 16 number of workers running in parallel
-ALLHANDS_API_KEY="YOUR-API-KEY" RUNTIME=remote SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev" EVAL_DOCKER_IMAGE_PREFIX="us-central1-docker.pkg.dev/evaluation-092424/swe-bench-images" \
-evaluation/benchmarks/swe_bench/scripts/eval_infer_remote.sh evaluation/evaluation_outputs/outputs/swe-bench-lite/CodeActAgent/Llama-3.1-70B-Instruct-Turbo_maxiter_100_N_v1.9-no-hint/output.jsonl 16 "princeton-nlp/SWE-bench_Lite" "test"
-```
-
-To clean-up all existing runtimes that you've already started, run:
-
-```bash
-ALLHANDS_API_KEY="YOUR-API-KEY" ./evaluation/utils/scripts/cleanup_remote_runtime.sh
-```
 
 ## SWT-Bench Evaluation
 

evaluation/benchmarks/swe_bench/SWE-rebench.md

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

evaluation/benchmarks/swe_bench/binary_patch_utils.py

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

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -26,7 +26,7 @@ from evaluation.utils.shared import (
 from openhands.core.config import (
     LLMConfig,
     OpenHandsConfig,
-    get_parser,
+    get_evaluation_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime
@@ -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.
@@ -353,7 +352,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--input-file',
         type=str,

evaluation/benchmarks/swe_bench/loc_eval/loc_evaluator.py

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

evaluation/benchmarks/swe_bench/loc_eval/loc_utils.py

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

evaluation/benchmarks/swe_bench/prompts/swe_claude.j2

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

evaluation/benchmarks/swe_bench/prompts/swe_gemini.j2

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

evaluation/benchmarks/swe_bench/run_infer.py

@@ -43,8 +43,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.config.condenser_config import NoOpCondenserConfig
 from openhands.core.config.utils import get_condenser_config_arg
@@ -80,6 +80,8 @@ def set_dataset_type(dataset_name: str) -> str:
         DATASET_TYPE = 'SWE-Gym'
     elif 'swe-bench-live' in name_lower:
         DATASET_TYPE = 'SWE-bench-Live'
+    elif 'swe-rebench' in name_lower:
+        DATASET_TYPE = 'SWE-rebench'
     elif 'multimodal' in name_lower:
         DATASET_TYPE = 'Multimodal'
     else:
@@ -109,9 +111,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageActio
     if mode.startswith('swt'):
         template_name = 'swt.j2'
     elif mode == 'swe':
-        if 'claude' in llm_model:
-            template_name = 'swe_default.j2'
-        elif 'gpt-4.1' in llm_model:
+        if 'gpt-4.1' in llm_model:
             template_name = 'swe_gpt4.j2'
         else:
             template_name = (
@@ -180,6 +180,8 @@ def get_instance_docker_image(
             docker_image_prefix = 'docker.io/starryzhang/'
         elif DATASET_TYPE == 'SWE-bench':
             docker_image_prefix = 'docker.io/swebench/'
+        elif DATASET_TYPE == 'SWE-rebench':
+            docker_image_prefix = 'docker.io/swerebench/'
         repo, name = instance_id.split('__')
         image_name = f'{docker_image_prefix.rstrip("/")}/sweb.eval.x86_64.{repo}_1776_{name}:latest'.lower()
         logger.debug(f'Using official SWE-Bench image: {image_name}')
@@ -320,6 +322,8 @@ def initialize_runtime(
         # inject the instance swe entry
         if DATASET_TYPE == 'SWE-bench-Live':
             entry_script_path = 'instance_swe_entry_live.sh'
+        elif DATASET_TYPE == 'SWE-rebench':
+            entry_script_path = 'instance_swe_entry_rebench.sh'
         else:
             entry_script_path = 'instance_swe_entry.sh'
         runtime.copy_to(
@@ -732,7 +736,7 @@ def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/swe_bench/run_infer_interact.py

@@ -28,8 +28,8 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.config.condenser_config import NoOpCondenserConfig
 from openhands.core.config.utils import get_condenser_config_arg
@@ -201,7 +201,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/swe_bench/run_localize.py

@@ -31,8 +31,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -644,7 +644,7 @@ SWEGYM_EXCLUDE_IDS = [
 ]
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

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

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

evaluation/benchmarks/swe_bench/scripts/eval_infer_remote.sh

@@ -1,46 +0,0 @@
-#!/usr/bin/env bash
-set -eo pipefail
-
-INPUT_FILE=$1
-NUM_WORKERS=$2
-DATASET=$3
-SPLIT=$4
-
-if [ -z "$INPUT_FILE" ]; then
-  echo "INPUT_FILE not specified (should be a path to a jsonl file)"
-  exit 1
-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 "$NUM_WORKERS" ]; then
-  echo "NUM_WORKERS not specified, use default 1"
-  NUM_WORKERS=1
-fi
-
-echo "... Evaluating on $INPUT_FILE ..."
-
-COMMAND="poetry run python evaluation/benchmarks/swe_bench/eval_infer.py \
-  --eval-num-workers $NUM_WORKERS \
-  --input-file $INPUT_FILE \
-  --dataset $DATASET \
-  --split $SPLIT"
-
-if [ -n "$EVAL_LIMIT" ]; then
-  echo "EVAL_LIMIT: $EVAL_LIMIT"
-  COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
-fi
-
-# Run the command
-eval $COMMAND
-
-# update the output with evaluation results
-poetry run python evaluation/benchmarks/swe_bench/scripts/eval/update_output_with_eval.py $INPUT_FILE

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

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

evaluation/benchmarks/testgeneval/NOTES.md

@@ -5,8 +5,7 @@ pynguin_ids = ['pydata__xarray-6548-16541', 'pydata__xarray-7003-16557', 'pydata
 ids = ['pydata__xarray-3114-16452', 'pydata__xarray-3151-16453', 'pydata__xarray-3156-16454', 'pydata__xarray-3239-16456', 'pydata__xarray-3239-16457', 'pydata__xarray-3239-16458', 'pydata__xarray-3302-16459', 'pydata__xarray-3364-16461', 'pydata__xarray-3677-16471', 'pydata__xarray-3905-16478', 'pydata__xarray-4182-16484', 'pydata__xarray-4248-16486', 'pydata__xarray-4339-16487', 'pydata__xarray-4419-16488', 'pydata__xarray-4629-16492', 'pydata__xarray-4750-16496', 'pydata__xarray-4802-16505', 'pydata__xarray-4966-16515', 'pydata__xarray-4994-16516', 'pydata__xarray-5033-16517', 'pydata__xarray-5126-16518', 'pydata__xarray-5126-16519', 'pydata__xarray-5131-16520', 'pydata__xarray-5365-16529', 'pydata__xarray-5455-16530', 'pydata__xarray-5662-16532', 'pydata__xarray-5731-16534', 'pydata__xarray-6135-16535', 'pydata__xarray-6135-16536', 'pydata__xarray-6386-16537', 'pydata__xarray-6394-16538', 'pydata__xarray-6400-16539', 'pydata__xarray-6461-16540', 'pydata__xarray-6548-16541', 'pydata__xarray-6599-16543', 'pydata__xarray-6601-16544', 'pydata__xarray-6882-16548', 'pydata__xarray-6889-16549', 'pydata__xarray-7003-16557', 'pydata__xarray-7147-16571', 'pydata__xarray-7150-16572', 'pydata__xarray-7203-16577', 'pydata__xarray-7229-16578', 'pydata__xarray-7393-16581', 'pydata__xarray-7400-16582']
 
 
-Command eval (our approach):
-poetry run ./evaluation/benchmarks/testgeneval/scripts/eval_infer_remote.sh evaluation/evaluation_outputs/outputs/kjain14__testgeneval-test/CodeActAgent/gpt-4o_maxiter_25_N_v0.20.0-no-hint-run_1/output.jsonl 10 kjain14/testgeneval test true
+
 
 Command run (our approach):
 ./evaluation/benchmarks/testgeneval/scripts/run_infer.sh llm.eval_gpt HEAD CodeActAgent -1 25 10 kjain14/testgeneval test 1 ../TestGenEval/results/testgeneval/preds/gpt-4o-2024-08-06__testgeneval__0.2__test.jsonl

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

@@ -41,7 +41,7 @@ from evaluation.utils.shared import (
     reset_logger_for_multiprocessing,
     run_evaluation,
 )
-from openhands.core.config import OpenHandsConfig, SandboxConfig, get_parser
+from openhands.core.config import OpenHandsConfig, SandboxConfig, get_evaluation_parser
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime
 from openhands.events.action import CmdRunAction
@@ -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.
 
@@ -484,7 +481,7 @@ def count_and_log_fields(evaluated_predictions, fields, key):
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--input-file', type=str, required=True, help='Path to input predictions file'
     )

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/run_infer.py

@@ -37,8 +37,8 @@ from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
     SandboxConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -491,7 +491,7 @@ def prepare_dataset_pre(dataset: pd.DataFrame, filter_column: str) -> pd.DataFra
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

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

@@ -18,8 +18,8 @@ from openhands.core.config import (
     LLMConfig,
     OpenHandsConfig,
     get_agent_config_arg,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.config.agent_config import AgentConfig
 from openhands.core.logger import openhands_logger as logger
@@ -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'
@@ -197,7 +196,7 @@ def run_evaluator(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--task-image-name',
         type=str,

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

@@ -19,8 +19,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -157,7 +157,7 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/versicode/inference_utils/api_code_migration.py

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

evaluation/benchmarks/versicode/inference_utils/api_test_block_completion.py

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

evaluation/benchmarks/versicode/inference_utils/test_block.py

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

evaluation/benchmarks/versicode/inference_utils/test_migration.py

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

evaluation/benchmarks/versicode/metric/compute_ism_pm_score.py

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

evaluation/benchmarks/versicode/metric/compute_migration_cdc_score.py

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

evaluation/benchmarks/versicode/metric/compute_versicode_cdc_score.py

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

evaluation/benchmarks/versicode/metric/compute_versicode_em_score.py

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

evaluation/benchmarks/versicode/output_processing/choose_core_line_from_block_versicode.py

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

evaluation/benchmarks/versicode/output_processing/choose_core_line_from_migration_versicode.py

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

evaluation/benchmarks/versicode/output_processing/clear_ans.py

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

evaluation/benchmarks/visual_swe_bench/run_infer.py

@@ -31,8 +31,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -565,7 +565,7 @@ SWEGYM_EXCLUDE_IDS = [
 ]
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/utils/shared.py

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