replace raise for status

This reverts commit 8fa40a9499.

.devcontainer/README.md

@@ -1 +0,0 @@
-This way of running OpenHands is not officially supported. It is maintained by the community.

.devcontainer/devcontainer.json

@@ -1,19 +0,0 @@
-// For format details, see: https://aka.ms/devcontainer.json
-{
-	"name": "Python 3",
-	// Documentation for this image:
-	// - https://github.com/devcontainers/templates/tree/main/src/python
-	// - https://github.com/microsoft/vscode-remote-try-python
-	// - https://hub.docker.com/r/microsoft/devcontainers-python
-	"image": "mcr.microsoft.com/devcontainers/python:1-3.12-bullseye",
-	"features": {
-		"ghcr.io/devcontainers/features/docker-outside-of-docker:1": {},
-		"ghcr.io/devcontainers-extra/features/poetry:2": {},
-		"ghcr.io/devcontainers/features/node:1": {},
-	},
-	"postCreateCommand": ".devcontainer/setup.sh",
-	"runArgs": ["--add-host=host.docker.internal:host-gateway"],
-	"containerEnv": {
-		"DOCKER_HOST_ADDR": "host.docker.internal"
-	},
-}

.devcontainer/setup.sh

@@ -1,14 +0,0 @@
-#!/bin/bash
-
-# Mark the current repository as safe for Git to prevent "dubious ownership" errors,
-# which can occur in containerized environments when directory ownership doesn't match the current user.
-git config --global --add safe.directory "$(realpath .)"
-
-# Install `nc`
-sudo apt update && sudo apt install netcat -y
-
-# Install `uv` and `uvx`
-wget -qO- https://astral.sh/uv/install.sh | sh
-
-# Do common setup tasks
-source .openhands/setup.sh

.dockerignore

@@ -1,23 +1,5 @@
-# NodeJS
 frontend/node_modules
-
-# Configuration (except pyproject.toml)
-*.ini
-*.toml
-!pyproject.toml
-*.yml
-
-# Documentation (except README.md)
-*.md
-!README.md
-
-# Hidden files and directories
-.*
-__pycache__
-
-# Unneded files and directories
-/dev_config/
-/docs/
-/evaluation/
-/tests/
-CITATION.cff
+config.toml
+.envrc
+.env
+.git

.editorconfig

@@ -1,5 +0,0 @@
-[*]
-# force *nix line endings so files don't look modified in container run from Windows clone
-end_of_line = lf
-trim_trailing_whitespace = true
-insert_final_newline = true

.gitattributes

@@ -1,7 +1 @@
 *.ipynb linguist-vendored
-
-# force *nix line endings so files don't look modified in container run from Windows clone
-* text eol=lf
-# Git incorrectly thinks some media is text
-*.png -text
-*.mp4 -text

.github/.codecov.yml

@@ -0,0 +1,19 @@
+codecov:
+  notify:
+    wait_for_ci: true
+    # our project is large, so 6 builds are typically uploaded. this waits till 5/6
+    # See https://docs.codecov.com/docs/notifications#section-preventing-notifications-until-after-n-builds
+    after_n_builds: 5
+
+coverage:
+  status:
+    patch:
+      default:
+        threshold: 100% # allow patch coverage to be lower than project coverage by any amount
+    project:
+      default:
+        threshold: 5% # allow project coverage to drop at most 5%
+
+comment: false
+github_checks:
+    annotations: false

.github/CODEOWNERS

@@ -1,8 +0,0 @@
-# CODEOWNERS file for OpenHands repository
-# See https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-code-owners
-
-/frontend/ @amanape @hieptl
-/openhands-ui/ @amanape @hieptl
-/openhands/ @tofarr @malhotra5 @hieptl
-/enterprise/ @chuckbutkus @tofarr @malhotra5
-/evaluation/ @xingyaoww @neubig

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -5,12 +5,11 @@ labels: ['bug']
 body:
   - type: markdown
     attributes:
-      value: Thank you for taking the time to fill out this bug report. Please provide as much information as possible
-       to help us understand and address the issue effectively.
+      value: Thank you for taking the time to fill out this bug report. Please provide as much information as possible to help us understand and address the issue effectively.
 
   - type: checkboxes
     attributes:
-      label: Is there an existing issue for the same bug? (If one exists, thumbs up or comment on the issue instead).
+      label: Is there an existing issue for the same bug?
       description: Please check if an issue already exists for the bug you encountered.
       options:
       - label: I have checked the existing issues.
@@ -33,7 +32,6 @@ body:
         - Docker command in README
         - GitHub resolver
         - Development workflow
-        - CLI
         - app.all-hands.dev
         - Other
       default: 0
@@ -45,13 +43,6 @@ body:
       description: What version of OpenHands are you using?
       placeholder: ex. 0.9.8, main, etc.
 
-  - type: input
-    id: model-name
-    attributes:
-      label: Model Name
-      description: What model are you using?
-      placeholder: ex. gpt-4o, claude-3-5-sonnet, openrouter/deepseek-r1, etc.
-
   - type: dropdown
     id: os
     attributes:

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,6 +1,6 @@
 ---
-name: Feature Request or Enhancement
-about: Suggest an idea for an OpenHands feature or enhancement
+name: Feature Request
+about: Suggest an idea for OpenHands features
 title: ''
 labels: 'enhancement'
 assignees: ''
@@ -9,9 +9,10 @@ assignees: ''
 
 **What problem or use case are you trying to solve?**
 
-**Describe the UX or technical implementation you have in mind**
+**Describe the UX of the solution you'd like**
+
+**Do you have thoughts on the technical implementation?**
+
+**Describe alternatives you've considered**
 
 **Additional context**
-
-
-### If you find this feature request or enhancement useful, make sure to add a 👍 to the issue

.github/ISSUE_TEMPLATE/technical_proposal.md

@@ -0,0 +1,18 @@
+---
+name: Technical Proposal
+about: Propose a new architecture or technology
+title: ''
+labels: 'proposal'
+assignees: ''
+
+---
+
+**Summary**
+
+**Motivation**
+
+**Technical Design**
+
+**Alternatives to Consider**
+
+**Additional context**

.github/dependabot.yml

@@ -10,12 +10,15 @@ updates:
       pre-commit:
         patterns:
           - "pre-commit"
+      llama:
+        patterns:
+          - "llama*"
+      chromadb:
+        patterns:
+          - "chromadb"
       browsergym:
         patterns:
           - "browsergym*"
-      mcp-packages:
-        patterns:
-          - "mcp"
       security-all:
         applies-to: "security-updates"
         patterns:
@@ -72,9 +75,3 @@ updates:
     directory: "/"
     schedule:
       interval: "weekly"
-
-  - package-ecosystem: "docker"
-    directories:
-      - "containers/*"
-    schedule:
-      interval: "weekly"

.github/pull_request_template.md

@@ -1,38 +1,11 @@
-<!-- Ideally you should open a PR when it is ready for review. Draft PRs will not be reviewed -->
+**End-user friendly description of the problem this fixes or functionality that this introduces**
 
-## Summary of PR
+- [ ] Include this change in the Release Notes. If checked, you must provide an **end-user friendly** description for your change below
 
-<!-- Summarize what the PR does -->
+---
+**Give a summary of what the PR does, explaining any non-trivial design decisions**
 
-## Demo Screenshots/Videos
 
-<!-- AI/LLM AGENTS: This section is intended for a human author to add screenshots or videos demonstrating the PR in action (optional). While many pull requests may be generated by AI/LLM agents, we are fine with this as long as a human author has reviewed and tested the changes to ensure accuracy and functionality. -->
 
-## Change Type
-
-<!-- Choose the types that apply to your PR -->
-
-- [ ] Bug fix
-- [ ] New feature
-- [ ] Breaking change
-- [ ] Refactor
-- [ ] Other (dependency update, docs, typo fixes, etc.)
-
-## Checklist
-<!-- AI/LLM AGENTS: This checklist is for a human author to complete. Do NOT check either of the two boxes below. Leave them unchecked until a human has personally reviewed and tested the changes. -->
-
-- [ ] I have read and reviewed the code and I understand what the code is doing.
-- [ ] I have tested the code to the best of my ability and ensured it works as expected.
-
-## Fixes
-
-<!-- If this resolves an issue, link it here so it will close automatically upon merge. -->
-
-Resolves #(issue)
-
-## Release Notes
-
-<!-- Check the box if this change is worth adding to the release notes. If checked, you must provide an
-end-user friendly description for your change below the checkbox. -->
-
-- [ ] Include this change in the Release Notes.
+---
+**Link of any specific issues this addresses**

.github/scripts/check_version_consistency.py

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

.github/scripts/update_pr_description.sh

@@ -1,58 +0,0 @@
-#!/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.openhands.dev/openhands/runtime:${SHORT_SHA}-nikolaik \
-  --name openhands-app-${SHORT_SHA} \
-  docker.openhands.dev/openhands/openhands:${SHORT_SHA}"
-
-# Get the current PR body
-PR_BODY=$(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}
-\`\`\`
-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:
-\`\`\`
-${DOCKER_RUN_COMMAND}
-\`\`\`
-EOF
-)
-fi
-
-# Update the PR description
-echo "Updating PR description with Docker and uvx commands"
-gh pr edit "$PR_NUMBER" --body "$NEW_PR_BODY"

.github/workflows/check-package-versions.yml

@@ -1,65 +0,0 @@
-name: Check Package Versions
-
-on:
-  push:
-    branches: [main]
-  pull_request:
-  workflow_dispatch:
-
-jobs:
-  check-package-versions:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v6
-        with:
-          python-version: "3.12"
-
-      - name: Check for any 'rev' fields in pyproject.toml
-        run: |
-          python - <<'PY'
-          import sys, tomllib, pathlib
-
-          path = pathlib.Path("pyproject.toml")
-          if not path.exists():
-              print("❌ ERROR: pyproject.toml not found")
-              sys.exit(1)
-
-          try:
-              data = tomllib.loads(path.read_text(encoding="utf-8"))
-          except Exception as e:
-              print(f"❌ ERROR: Failed to parse pyproject.toml: {e}")
-              sys.exit(1)
-
-          poetry = data.get("tool", {}).get("poetry", {})
-          sections = {
-              "dependencies": poetry.get("dependencies", {}),
-          }
-
-          errors = []
-
-          print("🔍 Checking for any dependencies with 'rev' fields...\n")
-          for section_name, deps in sections.items():
-              if not isinstance(deps, dict):
-                  continue
-
-              for pkg_name, cfg in deps.items():
-                  if isinstance(cfg, dict) and "rev" in cfg:
-                      msg = f"  ✖ {pkg_name} in [{section_name}] uses rev='{cfg['rev']}' (NOT ALLOWED)"
-                      print(msg)
-                      errors.append(msg)
-                  else:
-                      print(f"  • {pkg_name}: OK")
-
-          if errors:
-              print("\n❌ FAILED: Found dependencies using 'rev' fields:\n" + "\n".join(errors))
-              print("\nPlease use versioned releases instead, e.g.:")
-              print('  my-package = "1.0.0"')
-              sys.exit(1)
-
-          print("\n✅ SUCCESS: No 'rev' fields found. All dependencies are using proper versioned releases.")
-          PY

.github/workflows/clean-up.yml

@@ -0,0 +1,69 @@
+# Workflow that cleans up outdated and old workflows to prevent out of disk issues
+name: Delete old workflow runs
+
+# This workflow is currently only triggered manually
+on:
+  workflow_dispatch:
+    inputs:
+      days:
+        description: 'Days-worth of runs to keep for each workflow'
+        required: true
+        default: '30'
+      minimum_runs:
+        description: 'Minimum runs to keep for each workflow'
+        required: true
+        default: '10'
+      delete_workflow_pattern:
+        description: 'Name or filename of the workflow (if not set, all workflows are targeted)'
+        required: false
+      delete_workflow_by_state_pattern:
+        description: 'Filter workflows by state: active, deleted, disabled_fork, disabled_inactivity, disabled_manually'
+        required: true
+        default: "ALL"
+        type: choice
+        options:
+          - "ALL"
+          - active
+          - deleted
+          - disabled_inactivity
+          - disabled_manually
+      delete_run_by_conclusion_pattern:
+        description: 'Remove runs based on conclusion: action_required, cancelled, failure, skipped, success'
+        required: true
+        default: 'ALL'
+        type: choice
+        options:
+          - 'ALL'
+          - 'Unsuccessful: action_required,cancelled,failure,skipped'
+          - action_required
+          - cancelled
+          - failure
+          - skipped
+          - success
+      dry_run:
+        description: 'Logs simulated changes, no deletions are performed'
+        required: false
+
+jobs:
+  del_runs:
+    runs-on: ubuntu-latest
+    permissions:
+      actions: write
+      contents: read
+    steps:
+      - name: Delete workflow runs
+        uses: Mattraks/delete-workflow-runs@v2
+        with:
+          token: ${{ github.token }}
+          repository: ${{ github.repository }}
+          retain_days: ${{ github.event.inputs.days }}
+          keep_minimum_runs: ${{ github.event.inputs.minimum_runs }}
+          delete_workflow_pattern: ${{ github.event.inputs.delete_workflow_pattern }}
+          delete_workflow_by_state_pattern: ${{ github.event.inputs.delete_workflow_by_state_pattern }}
+          delete_run_by_conclusion_pattern: >-
+            ${{
+              startsWith(github.event.inputs.delete_run_by_conclusion_pattern, 'Unsuccessful:')
+              && 'action_required,cancelled,failure,skipped'
+              || github.event.inputs.delete_run_by_conclusion_pattern
+            }}
+          dry_run: ${{ github.event.inputs.dry_run }}

.github/workflows/deploy-docs.yml

@@ -0,0 +1,74 @@
+# Workflow that builds and deploys the documentation website
+name: Deploy Docs to GitHub Pages
+
+# * Always run on "main"
+# * Run on PRs that target the "main" branch and have changes in the "docs" folder or this workflow
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    paths:
+      - 'docs/**'
+      - '.github/workflows/deploy-docs.yml'
+    branches:
+      - main
+
+# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
+concurrency:
+  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  # Build the documentation website
+  build:
+    if: github.repository == 'All-Hands-AI/OpenHands'
+    name: Build Docusaurus
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 18
+          cache: npm
+          cache-dependency-path: docs/package-lock.json
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      - name: Generate Python Docs
+        run: rm -rf docs/modules/python && pip install pydoc-markdown && pydoc-markdown
+      - name: Install dependencies
+        run: cd docs && npm ci
+      - name: Build website
+        run: cd docs && npm run build
+      - name: Upload Build Artifact
+        if: github.ref == 'refs/heads/main'
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: docs/build
+
+  # Deploy the documentation website
+  deploy:
+    if: github.ref == 'refs/heads/main' && github.repository == 'All-Hands-AI/OpenHands'
+    name: Deploy to GitHub Pages
+    runs-on: ubuntu-latest
+    # This job only runs on "main" so only run one of these jobs at a time
+    # otherwise it will fail if one is already running
+    concurrency:
+      group: ${{ github.workflow }}-${{ github.ref }}
+    needs: build
+    # Grant GITHUB_TOKEN the permissions required to make a Pages deployment
+    permissions:
+      pages: write # to deploy to Pages
+      id-token: write # to verify the deployment originates from an appropriate source
+    # Deploy to the github-pages environment
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

.github/workflows/dummy-agent-test.yml

@@ -0,0 +1,63 @@
+# Workflow that uses the DummyAgent to run a simple task
+name: Run E2E test with dummy agent
+
+# Always run on "main"
+# Always run on PRs
+on:
+  push:
+    branches:
+    - main
+  pull_request:
+
+# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
+concurrency:
+  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Install tmux
+        run: sudo apt-get update && sudo apt-get install -y tmux
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+          cache: 'poetry'
+      - name: Install Python dependencies using Poetry
+        run: poetry install --without evaluation,llama-index
+      - name: Build Environment
+        run: make build
+      - name: Run tests
+        run: |
+          set -e
+          SANDBOX_FORCE_REBUILD_RUNTIME=True poetry run python3 openhands/core/main.py -t "do a flip" -d ./workspace/ -c DummyAgent
+      - name: Check exit code
+        run: |
+          if [ $? -ne 0 ]; then
+            echo "Test failed"
+            exit 1
+          else
+            echo "Test passed"
+          fi

.github/workflows/e2e-tests.yml

@@ -1,228 +0,0 @@
-name: End-to-End Tests
-
-on:
-  pull_request:
-    types: [opened, synchronize, reopened, labeled]
-    branches:
-      - main
-      - develop
-  workflow_dispatch:
-
-jobs:
-  e2e-tests:
-    if: contains(github.event.pull_request.labels.*.name, 'end-to-end') || github.event_name == 'workflow_dispatch'
-    runs-on: ubuntu-latest
-    timeout-minutes: 60
-
-    env:
-      GITHUB_REPO_NAME: ${{ github.repository }}
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        uses: abatilo/actions-poetry@v4
-        with:
-          poetry-version: 2.1.3
-
-      - name: Set up Python
-        uses: actions/setup-python@v6
-        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@v6
-        with:
-          node-version: '22'
-          cache: 'npm'
-          cache-dependency-path: 'frontend/package-lock.json'
-
-      - name: Setup environment for end-to-end tests
-        run: |
-          # Create test results directory
-          mkdir -p test-results
-
-          # Create downloads directory for OpenHands (use a directory in the home folder)
-          mkdir -p $HOME/downloads
-          sudo chown -R $USER:$USER $HOME/downloads
-          sudo chmod -R 755 $HOME/downloads
-
-      - name: Build OpenHands
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          LLM_MODEL: ${{ secrets.LLM_MODEL || 'gpt-4o' }}
-          LLM_API_KEY: ${{ secrets.LLM_API_KEY || 'test-key' }}
-          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-          INSTALL_DOCKER: 1
-          RUNTIME: docker
-          FRONTEND_PORT: 12000
-          FRONTEND_HOST: 0.0.0.0
-          BACKEND_HOST: 0.0.0.0
-          BACKEND_PORT: 3000
-          ENABLE_BROWSER: true
-          INSTALL_PLAYWRIGHT: 1
-        run: |
-          # Fix poetry.lock file if needed
-          echo "Fixing poetry.lock file if needed..."
-          poetry lock
-
-          # Build OpenHands using make build
-          echo "Running make build..."
-          make build
-
-          # Install Chromium Headless Shell for Playwright (needed for pytest-playwright)
-          echo "Installing Chromium Headless Shell for Playwright..."
-          poetry run playwright install chromium-headless-shell
-
-          # Verify Playwright browsers are installed (for e2e tests only)
-          echo "Verifying Playwright browsers installation for e2e tests..."
-          BROWSER_CHECK=$(poetry run python tests/e2e/check_playwright.py 2>/dev/null)
-
-          if [ "$BROWSER_CHECK" != "chromium_found" ]; then
-            echo "ERROR: Chromium browser not found or not working for e2e tests"
-            echo "$BROWSER_CHECK"
-            exit 1
-          else
-            echo "Playwright browsers are properly installed for e2e tests."
-          fi
-
-          # Docker runtime will handle workspace directory creation
-
-          # Start the application using make run with custom parameters and reduced logging
-          echo "Starting OpenHands using make run..."
-          # Set environment variables to reduce logging verbosity
-          export PYTHONUNBUFFERED=1
-          export LOG_LEVEL=WARNING
-          export UVICORN_LOG_LEVEL=warning
-          export OPENHANDS_LOG_LEVEL=WARNING
-          FRONTEND_PORT=12000 FRONTEND_HOST=0.0.0.0 BACKEND_HOST=0.0.0.0 make run > /tmp/openhands-e2e-test.log 2>&1 &
-
-          # Store the PID of the make run process
-          MAKE_PID=$!
-          echo "OpenHands started with PID: $MAKE_PID"
-
-          # Wait for the application to start
-          echo "Waiting for OpenHands to start..."
-          max_attempts=15
-          attempt=1
-
-          while [ $attempt -le $max_attempts ]; do
-            echo "Checking if OpenHands is running (attempt $attempt of $max_attempts)..."
-
-            # Check if the process is still running
-            if ! ps -p $MAKE_PID > /dev/null; then
-              echo "ERROR: OpenHands process has terminated unexpectedly"
-              echo "Last 50 lines of the log:"
-              tail -n 50 /tmp/openhands-e2e-test.log
-              exit 1
-            fi
-
-            # Check if frontend port is open
-            if nc -z localhost 12000; then
-              # Verify we can get HTML content
-              if curl -s http://localhost:12000 | grep -q "<html"; then
-                echo "SUCCESS: OpenHands is running and serving HTML content on port 12000"
-                break
-              else
-                echo "Port 12000 is open but not serving HTML content yet"
-              fi
-            else
-              echo "Frontend port 12000 is not open yet"
-            fi
-
-            # Show log output on each attempt
-            echo "Recent log output:"
-            tail -n 20 /tmp/openhands-e2e-test.log
-
-            # Wait before next attempt
-            echo "Waiting 10 seconds before next check..."
-            sleep 10
-            attempt=$((attempt + 1))
-
-            # Exit if we've reached the maximum number of attempts
-            if [ $attempt -gt $max_attempts ]; then
-              echo "ERROR: OpenHands failed to start after $max_attempts attempts"
-              echo "Last 50 lines of the log:"
-              tail -n 50 /tmp/openhands-e2e-test.log
-              exit 1
-            fi
-          done
-
-          # Final verification that the app is running
-          if ! nc -z localhost 12000 || ! curl -s http://localhost:12000 | grep -q "<html"; then
-            echo "ERROR: OpenHands is not running properly on port 12000"
-            echo "Last 50 lines of the log:"
-            tail -n 50 /tmp/openhands-e2e-test.log
-            exit 1
-          fi
-
-          # Print success message
-          echo "OpenHands is running successfully on port 12000"
-
-      - name: Run end-to-end tests
-        env:
-          GITHUB_TOKEN: ${{ secrets.E2E_TEST_GITHUB_TOKEN }}
-          LLM_MODEL: ${{ secrets.LLM_MODEL || 'gpt-4o' }}
-          LLM_API_KEY: ${{ secrets.LLM_API_KEY || 'test-key' }}
-          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-        run: |
-          # Check if the application is running
-          if ! nc -z localhost 12000; then
-            echo "ERROR: OpenHands is not running on port 12000"
-            echo "Last 50 lines of the log:"
-            tail -n 50 /tmp/openhands-e2e-test.log
-            exit 1
-          fi
-
-          # Run the tests with detailed output
-          cd tests/e2e
-          poetry run python -m pytest \
-            test_settings.py::test_github_token_configuration \
-            test_conversation.py::test_conversation_start \
-            test_browsing_catchphrase.py::test_browsing_catchphrase \
-            test_multi_conversation_resume.py::test_multi_conversation_resume \
-            -v --no-header --capture=no --timeout=900
-
-      - name: Upload test results
-        if: always()
-        uses: actions/upload-artifact@v6
-        with:
-          name: playwright-report
-          path: tests/e2e/test-results/
-          retention-days: 30
-
-      - name: Upload OpenHands logs
-        if: always()
-        uses: actions/upload-artifact@v6
-        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/enterprise-check-migrations.yml

@@ -1,52 +0,0 @@
-name: Enterprise Check Migrations
-
-on:
-  pull_request:
-    paths:
-      - 'enterprise/migrations/**'
-
-jobs:
-  check-sync:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout PR branch
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.pull_request.head.sha }}
-          fetch-depth: 0
-
-
-      - name: Fetch base branch
-        run: git fetch origin ${{ github.event.pull_request.base.ref }}
-
-      - name: Check if base branch is ancestor of PR
-        id: check_up_to_date
-        shell: bash
-        run: |
-          BASE="origin/${{ github.event.pull_request.base.ref }}"
-          HEAD="${{ github.event.pull_request.head.sha }}"
-          if git merge-base --is-ancestor "$BASE" "$HEAD"; then
-            echo "We're up to date with base $BASE"
-            exit 0
-          else
-            echo "NOT up to date with base $BASE"
-            exit 1
-          fi
-
-      - name: Find Comment
-        uses: peter-evans/find-comment@v3
-        id: find-comment
-        with:
-          issue-number: ${{ github.event.pull_request.number }}
-          comment-author: 'github-actions[bot]'
-          body-includes: |
-            ⚠️ This PR contains **migrations**
-
-      - name: Comment warning on PR
-        uses: peter-evans/create-or-update-comment@v5
-        with:
-          issue-number: ${{ github.event.pull_request.number }}
-          comment-id: ${{ steps.find-comment.outputs.comment-id }}
-          edit-mode: replace
-          body: |
-            ⚠️ This PR contains **migrations**. Please synchronize before merging to prevent conflicts.

.github/workflows/enterprise-preview.yml

@@ -1,29 +0,0 @@
-# Feature branch preview for enterprise code
-name: Enterprise Preview
-
-# Run on PRs labeled
-on:
-  pull_request:
-    types: [labeled]
-
-# Match ghcr-build.yml, but don't interrupt it.
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: false
-
-jobs:
-  # This must happen for the PR Docker workflow when the label is present,
-  # and also if it's added after the fact. Thus, it exists in both places.
-  enterprise-preview:
-    name: Enterprise preview
-    if: github.event.label.name == 'deploy'
-    runs-on: blacksmith-4vcpu-ubuntu-2204
-    steps:
-      # This should match the version in ghcr-build.yml
-      - name: Trigger remote job
-        run: |
-          curl --fail-with-body -sS -X POST \
-            -H "Authorization: Bearer ${{ secrets.ALLHANDS_BOT_GITHUB_PAT }}" \
-            -H "Accept: application/vnd.github+json" \
-            -d "{\"ref\": \"main\", \"inputs\": {\"openhandsPrNumber\": \"${{ github.event.pull_request.number }}\", \"deployEnvironment\": \"feature\", \"enterpriseImageTag\": \"pr-${{ github.event.pull_request.number }}\" }}" \
-            https://api.github.com/repos/OpenHands/deploy/actions/workflows/deploy.yaml/dispatches

.github/workflows/eval-runner.yml

@@ -0,0 +1,139 @@
+name: Run SWE-Bench Evaluation
+
+on:
+  pull_request:
+    types: [labeled]
+  workflow_dispatch:
+    inputs:
+      reason:
+        description: "Reason for manual trigger"
+        required: true
+        default: ""
+
+env:
+  N_PROCESSES: 32 # Global configuration for number of parallel processes for evaluation
+
+jobs:
+  run-evaluation:
+    if: github.event.label.name == 'eval-this' || github.event_name != 'pull_request'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: "read"
+      id-token: "write"
+      pull-requests: "write"
+      issues: "write"
+    strategy:
+      matrix:
+        python-version: ["3.12"]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Install tmux
+        run: sudo apt-get update && sudo apt-get install -y tmux
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "poetry"
+
+      - name: Comment on PR if 'eval-this' label is present
+        if: github.event_name == 'pull_request' && github.event.label.name == 'eval-this'
+        uses: KeisukeYamashita/create-comment@v1
+        with:
+          unique: false
+          comment: |
+            Hi! I started running the evaluation on your PR. You will receive a comment with the results shortly.
+
+      - name: Install Python dependencies using Poetry
+        run: poetry install
+
+      - name: Configure config.toml for evaluation
+        env:
+          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_LLM_API_KEY }}
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"deepseek/deepseek-chat\"" >> config.toml
+          echo "api_key = \"$DEEPSEEK_API_KEY\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+
+      - name: Run SWE-Bench evaluation
+        env:
+          ALLHANDS_API_KEY: ${{ secrets.ALLHANDS_EVAL_RUNTIME_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
+
+        run: |
+          poetry run ./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.eval HEAD CodeActAgent 300 30 $N_PROCESSES "princeton-nlp/SWE-bench_Lite" test
+          OUTPUT_FOLDER=$(find evaluation/evaluation_outputs/outputs/princeton-nlp__SWE-bench_Lite-test/CodeActAgent -name "deepseek-chat_maxiter_50_N_*-no-hint-run_1" -type d | head -n 1)
+          echo "OUTPUT_FOLDER for SWE-bench evaluation: $OUTPUT_FOLDER"
+          poetry run ./evaluation/benchmarks/swe_bench/scripts/eval_infer_remote.sh $OUTPUT_FOLDER/output.jsonl $N_PROCESSES "princeton-nlp/SWE-bench_Lite" test
+
+          poetry run ./evaluation/benchmarks/swe_bench/scripts/eval/summarize_outputs.py $OUTPUT_FOLDER/output.jsonl > summarize_outputs.log 2>&1
+          echo "SWEBENCH_REPORT<<EOF" >> $GITHUB_ENV
+          cat summarize_outputs.log >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      - name: Create tar.gz of evaluation outputs
+        run: |
+          TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
+          tar -czvf evaluation_outputs_${TIMESTAMP}.tar.gz evaluation/evaluation_outputs/outputs
+
+      - name: Upload evaluation results as artifact
+        uses: actions/upload-artifact@v4
+        id: upload_results_artifact
+        with:
+          name: evaluation-outputs
+          path: evaluation_outputs_*.tar.gz
+
+      - name: Get artifact URL
+        run: echo "ARTIFACT_URL=${{ steps.upload_results_artifact.outputs.artifact-url }}" >> $GITHUB_ENV
+
+      - name: Authenticate to Google Cloud
+        uses: 'google-github-actions/auth@v2'
+        with:
+          credentials_json: ${{ secrets.GCP_RESEARCH_OBJECT_CREATOR_SA_KEY }}
+
+      - name: Set timestamp and trigger reason
+        run: |
+          echo "TIMESTAMP=$(date +'%Y-%m-%d-%H-%M')" >> $GITHUB_ENV
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            echo "TRIGGER_REASON=pr-${{ github.event.pull_request.number }}" >> $GITHUB_ENV
+          elif [[ "${{ github.event_name }}" == "schedule" ]]; then
+            echo "TRIGGER_REASON=schedule" >> $GITHUB_ENV
+          else
+            echo "TRIGGER_REASON=manual-${{ github.event.inputs.reason }}" >> $GITHUB_ENV
+          fi
+
+      - name: Upload evaluation results to Google Cloud Storage
+        uses: 'google-github-actions/upload-cloud-storage@v2'
+        with:
+          path: 'evaluation/evaluation_outputs/outputs'
+          destination: 'openhands-oss-eval-results/${{ env.TIMESTAMP }}-${{ env.TRIGGER_REASON }}'
+
+      - name: Comment with evaluation results and artifact link
+        id: create_comment
+        uses: KeisukeYamashita/create-comment@v1
+        with:
+          number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || 4504 }}
+          unique: false
+          comment: |
+              Trigger by: ${{ github.event_name == 'pull_request' && format('Pull Request (eval-this label on PR #{0})', github.event.pull_request.number) || github.event_name == 'schedule' && 'Daily Schedule' || format('Manual Trigger: {0}', github.event.inputs.reason) }}
+              Commit: ${{ github.sha }}
+              **SWE-Bench Evaluation Report**
+              ${{ env.SWEBENCH_REPORT }}
+              ---
+              You can download the full evaluation outputs [here](${{ env.ARTIFACT_URL }}).
+
+      - name: Post to a Slack channel
+        id: slack
+        uses: slackapi/slack-github-action@v2.0.0
+        with:
+          channel-id: 'C07SVQSCR6F'
+          slack-message: "*Evaluation Trigger:* ${{ github.event_name == 'pull_request' && format('Pull Request (eval-this label on PR #{0})', github.event.pull_request.number) || github.event_name == 'schedule' && 'Daily Schedule' || format('Manual Trigger: {0}', github.event.inputs.reason) }}\n\nLink to summary: [here](https://github.com/${{ github.repository }}/issues/${{ github.event_name == 'pull_request' && github.event.pull_request.number || 4504 }}#issuecomment-${{ steps.create_comment.outputs.comment-id }})"
+        env:
+          SLACK_BOT_TOKEN: ${{ secrets.EVAL_NOTIF_SLACK_BOT_TOKEN }}

.github/workflows/fe-e2e-tests.yml

@@ -1,47 +0,0 @@
-# Workflow that runs frontend e2e tests with Playwright
-name: Run Frontend E2E Tests
-
-on:
-  push:
-    branches:
-      - main
-  pull_request:
-    paths:
-      - "frontend/**"
-      - ".github/workflows/fe-e2e-tests.yml"
-
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  fe-e2e-test:
-    name: FE E2E Tests
-    runs-on: blacksmith-4vcpu-ubuntu-2204
-    strategy:
-      matrix:
-        node-version: [22]
-      fail-fast: true
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Set up Node.js
-        uses: useblacksmith/setup-node@v5
-        with:
-          node-version: ${{ matrix.node-version }}
-      - name: Install dependencies
-        working-directory: ./frontend
-        run: npm ci
-      - name: Install Playwright browsers
-        working-directory: ./frontend
-        run: npx playwright install --with-deps chromium
-      - name: Run Playwright tests
-        working-directory: ./frontend
-        run: npx playwright test --project=chromium
-      - name: Upload Playwright report
-        uses: actions/upload-artifact@v6
-        if: always()
-        with:
-          name: playwright-report
-          path: frontend/playwright-report/
-          retention-days: 30

.github/workflows/fe-unit-tests.yml

@@ -9,8 +9,8 @@ on:
       - main
   pull_request:
     paths:
-      - "frontend/**"
-      - ".github/workflows/fe-unit-tests.yml"
+      - 'frontend/**'
+      -  '.github/workflows/fe-unit-tests.yml'
 
 # If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
 concurrency:
@@ -21,16 +21,16 @@ jobs:
   # Run frontend unit tests
   fe-test:
     name: FE Unit Tests
-    runs-on: blacksmith-4vcpu-ubuntu-2204
+    runs-on: ubuntu-latest
     strategy:
       matrix:
-        node-version: [22]
+        node-version: [20, 22]
       fail-fast: true
     steps:
       - name: Checkout
         uses: actions/checkout@v4
       - name: Set up Node.js
-        uses: useblacksmith/setup-node@v5
+        uses: actions/setup-node@v4
         with:
           node-version: ${{ matrix.node-version }}
       - name: Install dependencies
@@ -38,7 +38,11 @@ jobs:
         run: npm ci
       - name: Run TypeScript compilation
         working-directory: ./frontend
-        run: npm run build
+        run: npm run make-i18n && tsc
       - name: Run tests and collect coverage
         working-directory: ./frontend
         run: npm run test:coverage
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

.github/workflows/ghcr-build.yml

@@ -10,14 +10,14 @@ on:
     branches:
       - main
     tags:
-      - "*"
+      - '*'
   pull_request:
   workflow_dispatch:
     inputs:
       reason:
-        description: "Reason for manual trigger"
+        description: 'Reason for manual trigger'
         required: true
-        default: ""
+        default: ''
 
 # If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
 concurrency:
@@ -25,45 +25,38 @@ concurrency:
   cancel-in-progress: true
 
 env:
+  BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST: nikolaik/python-nodejs:python3.12-nodejs22
   RELEVANT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
 
 jobs:
-  define-matrix:
-    runs-on: blacksmith
-    outputs:
-      base_image: ${{ steps.define-base-images.outputs.base_image }}
-    steps:
-      - name: Define base images
-        shell: bash
-        id: define-base-images
-        run: |
-          if [[ "$GITHUB_EVENT_NAME" == "pull_request" ]]; then
-            json=$(jq -n -c '[
-                { image: "nikolaik/python-nodejs:python3.12-nodejs22", tag: "nikolaik" }
-              ]')
-          else
-            json=$(jq -n -c '[
-                { image: "nikolaik/python-nodejs:python3.12-nodejs22", tag: "nikolaik" },
-                { image: "ubuntu:24.04", tag: "ubuntu" }
-              ]')
-          fi
-          echo "base_image=$json" >> "$GITHUB_OUTPUT"
-
   # Builds the OpenHands Docker images
   ghcr_build_app:
     name: Build App Image
-    runs-on: blacksmith-4vcpu-ubuntu-2204
-    if: "!(github.event_name == 'push' && startsWith(github.ref, 'refs/tags/ext-v'))"
+    runs-on: ubuntu-latest
     permissions:
       contents: read
       packages: write
+    outputs:
+      hash_from_app_image: ${{ steps.get_hash_in_app_image.outputs.hash_from_app_image }}
     steps:
       - name: Checkout
         uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
         with:
-          ref: ${{ github.event.pull_request.head.sha }}
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3.7.0
+        uses: docker/setup-qemu-action@v3.3.0
         with:
           image: tonistiigi/binfmt:latest
       - name: Login to GHCR
@@ -75,33 +68,58 @@ jobs:
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
-      - name: Lowercase Repository Owner
-        run: |
-          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
       - name: Build and push app image
         if: "!github.event.pull_request.head.repo.fork"
         run: |
-          ./containers/build.sh -i openhands -o ${{ env.REPO_OWNER }} --push
+          ./containers/build.sh -i openhands -o ${{ github.repository_owner }} --push
+      - name: Build app image
+        if: "github.event.pull_request.head.repo.fork"
+        run: |
+          ./containers/build.sh -i openhands -o ${{ github.repository_owner }} --load
+      - name: Get hash in App Image
+        id: get_hash_in_app_image
+        run: |
+          # Lowercase the repository owner
+          export REPO_OWNER=${{ github.repository_owner }}
+          REPO_OWNER=$(echo $REPO_OWNER | tr '[:upper:]' '[:lower:]')
+          # Run the build script in the app image
+          docker run -e SANDBOX_USER_ID=0 -v /var/run/docker.sock:/var/run/docker.sock ghcr.io/${REPO_OWNER}/openhands:${{ env.RELEVANT_SHA }} /bin/bash -c "mkdir -p containers/runtime; python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild" 2>&1 | tee docker-outputs.txt
+          # Get the hash from the build script
+          hash_from_app_image=$(cat docker-outputs.txt | grep "Hash for docker build directory" | awk -F "): " '{print $2}' | uniq | head -n1)
+          echo "hash_from_app_image=$hash_from_app_image" >> $GITHUB_OUTPUT
+          echo "Hash from app image: $hash_from_app_image"
 
   # Builds the runtime Docker images
   ghcr_build_runtime:
-    name: Build Runtime Image
-    runs-on: blacksmith-8vcpu-ubuntu-2204
-    if: "!(github.event_name == 'push' && startsWith(github.ref, 'refs/tags/ext-v'))"
+    name: Build Image
+    runs-on: ubuntu-latest
     permissions:
       contents: read
       packages: write
-    needs: define-matrix
     strategy:
       matrix:
-        base_image: ${{ fromJson(needs.define-matrix.outputs.base_image) }}
+        base_image:
+          - image: 'nikolaik/python-nodejs:python3.12-nodejs22'
+            tag: nikolaik
     steps:
       - name: Checkout
         uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
         with:
-          ref: ${{ github.event.pull_request.head.sha }}
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3.7.0
+        uses: docker/setup-qemu-action@v3.3.0
         with:
           image: tonistiigi/binfmt:latest
       - name: Login to GHCR
@@ -113,161 +131,277 @@ jobs:
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      - name: Cache Poetry dependencies
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
       - name: Install poetry via pipx
         run: pipx install poetry
-      - name: Set up Python
-        uses: useblacksmith/setup-python@v6
-        with:
-          python-version: "3.12"
-          cache: poetry
       - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies POETRY_GROUP=main INSTALL_PLAYWRIGHT=0
+        run: make install-python-dependencies
       - name: Create source distribution and Dockerfile
-        run: poetry run python3 -m openhands.runtime.utils.runtime_build --base_image ${{ matrix.base_image.image }} --build_folder containers/runtime --force_rebuild
-      - name: Lowercase Repository Owner
-        run: |
-          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
-      - name: Short SHA
-        run: |
-          echo SHORT_SHA=$(git rev-parse --short "$RELEVANT_SHA") >> $GITHUB_ENV
-      - name: Determine docker build params
-        if: github.event.pull_request.head.repo.fork != true
-        shell: bash
-        run: |
-
-          ./containers/build.sh -i runtime -o ${{ env.REPO_OWNER }} -t ${{ matrix.base_image.tag }} --dry
-
-          DOCKER_BUILD_JSON=$(jq -c . < docker-build-dry.json)
-          echo "DOCKER_TAGS=$(echo "$DOCKER_BUILD_JSON" | jq -r '.tags | join(",")')" >> $GITHUB_ENV
-          echo "DOCKER_PLATFORM=$(echo "$DOCKER_BUILD_JSON" | jq -r '.platform')" >> $GITHUB_ENV
-          echo "DOCKER_BUILD_ARGS=$(echo "$DOCKER_BUILD_JSON" | jq -r '.build_args | join(",")')" >> $GITHUB_ENV
+        run: poetry run python3 openhands/runtime/utils/runtime_build.py --base_image ${{ matrix.base_image.image }} --build_folder containers/runtime --force_rebuild
       - name: Build and push runtime image ${{ matrix.base_image.image }}
         if: github.event.pull_request.head.repo.fork != true
-        uses: useblacksmith/build-push-action@v1
-        with:
-          push: true
-          tags: ${{ env.DOCKER_TAGS }}
-          platforms: ${{ env.DOCKER_PLATFORM }}
-          # Caching directives to boost performance
-          cache-from: type=registry,ref=ghcr.io/${{ env.REPO_OWNER }}/runtime:buildcache-${{ matrix.base_image.tag }}
-          cache-to: type=registry,ref=ghcr.io/${{ env.REPO_OWNER }}/runtime:buildcache-${{ matrix.base_image.tag }},mode=max
-          build-args: ${{ env.DOCKER_BUILD_ARGS }}
-          context: containers/runtime
-          provenance: false
-      # Forked repos can't push to GHCR, so we just build in order to populate the cache for rebuilding
+        run: |
+          ./containers/build.sh -i runtime -o ${{ github.repository_owner }} --push -t ${{ matrix.base_image.tag }}
+      # Forked repos can't push to GHCR, so we need to upload the image as an artifact
       - name: Build runtime image ${{ matrix.base_image.image }} for fork
         if: github.event.pull_request.head.repo.fork
-        uses: useblacksmith/build-push-action@v1
+        uses: docker/build-push-action@v6
         with:
-          tags: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+          tags: ghcr.io/all-hands-ai/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+          outputs: type=docker,dest=/tmp/runtime-${{ matrix.base_image.tag }}.tar
           context: containers/runtime
-      - name: Upload runtime source for fork
+      - name: Upload runtime image for fork
         if: github.event.pull_request.head.repo.fork
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v4
         with:
-          name: runtime-src-${{ matrix.base_image.tag }}
-          path: containers/runtime
+          name: runtime-${{ matrix.base_image.tag }}
+          path: /tmp/runtime-${{ matrix.base_image.tag }}.tar
 
-  ghcr_build_enterprise:
-    name: Push Enterprise Image
-    runs-on: blacksmith-8vcpu-ubuntu-2204
-    permissions:
-      contents: read
-      packages: write
-    needs: [define-matrix, ghcr_build_app]
-    # Do not build enterprise in forks
-    if: github.event.pull_request.head.repo.fork != true
+  verify_hash_equivalence_in_runtime_and_app:
+    name: Verify Hash Equivalence in Runtime and Docker images
+    runs-on: ubuntu-latest
+    needs: [ghcr_build_runtime, ghcr_build_app]
+    strategy:
+      fail-fast: false
+      matrix:
+        base_image: ['nikolaik']
     steps:
-      - name: Checkout
-        uses: actions/checkout@v4
+      - uses: actions/checkout@v4
+      - name: Cache Poetry dependencies
+        uses: actions/cache@v4
         with:
-          ref: ${{ github.event.pull_request.head.sha }}
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies
+      - name: Get hash in App Image
+        run: |
+          echo "Hash from app image: ${{ needs.ghcr_build_app.outputs.hash_from_app_image }}"
+          echo "hash_from_app_image=${{ needs.ghcr_build_app.outputs.hash_from_app_image }}" >> $GITHUB_ENV
 
-      # Set up Docker Buildx for better performance
+      - name: Get hash using code (development mode)
+        run: |
+          mkdir -p containers/runtime
+          poetry run python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild > output.txt 2>&1
+          hash_from_code=$(cat output.txt | grep "Hash for docker build directory" | awk -F "): " '{print $2}' | uniq | head -n1)
+          echo "hash_from_code=$hash_from_code" >> $GITHUB_ENV
+
+      - name: Compare hashes
+        run: |
+          echo "Hash from App Image: ${{ env.hash_from_app_image }}"
+          echo "Hash from Code: ${{ env.hash_from_code }}"
+          if [ "${{ env.hash_from_app_image }}" = "${{ env.hash_from_code }}" ]; then
+            echo "Hashes match!"
+          else
+            echo "Hashes do not match!"
+            exit 1
+          fi
+
+  # Run unit tests with the EventStream runtime Docker images as root
+  test_runtime_root:
+    name: RT Unit Tests (Root)
+    needs: [ghcr_build_runtime]
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        base_image: ['nikolaik']
+    steps:
+      - uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
       - name: Set up Docker Buildx
+        id: buildx
         uses: docker/setup-buildx-action@v3
+      # Forked repos can't push to GHCR, so we need to download the image as an artifact
+      - name: Download runtime image for fork
+        if: github.event.pull_request.head.repo.fork
+        uses: actions/download-artifact@v4
         with:
-          driver-opts: network=host
+          name: runtime-${{ matrix.base_image }}
+          path: /tmp
+      - name: Load runtime image for fork
+        if: github.event.pull_request.head.repo.fork
+        run: |
+          docker load --input /tmp/runtime-${{ matrix.base_image }}.tar
+      - name: Cache Poetry dependencies
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies
+      - name: Run runtime tests
+        run: |
+          # We install pytest-xdist in order to run tests across CPUs
+          poetry run pip install pytest-xdist
 
-      - name: Login to GHCR
-        uses: docker/login-action@v3
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
+          # Install to be able to retry on failures for flaky tests
+          poetry run pip install pytest-rerunfailures
 
-      - name: Extract metadata (tags, labels) for Docker
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ghcr.io/openhands/enterprise-server
-          tags: |
-            type=ref,event=branch
-            type=ref,event=pr
-            type=sha
-            type=sha,format=long
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-            type=semver,pattern={{major}}
-          flavor: |
-            latest=auto
-            prefix=
-            suffix=
+          image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
+          image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
+
+          TEST_RUNTIME=eventstream \
+          SANDBOX_USER_ID=$(id -u) \
+          SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
+          TEST_IN_CI=true \
+          RUN_AS_OPENHANDS=false \
+          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5
         env:
-          DOCKER_METADATA_PR_HEAD_SHA: true
-      - name: Determine app image tag
-        shell: bash
-        run: |
-          # Duplicated with build.sh
-          sanitized_ref_name=$(echo "$GITHUB_REF_NAME" | sed 's/[^a-zA-Z0-9.-]\+/-/g')
-          OPENHANDS_BUILD_VERSION=$sanitized_ref_name
-          sanitized_ref_name=$(echo "$sanitized_ref_name" | tr '[:upper:]' '[:lower:]') # lower case is required in tagging
-          echo "OPENHANDS_DOCKER_TAG=${sanitized_ref_name}" >> $GITHUB_ENV
-      - name: Build and push Docker image
-        uses: useblacksmith/build-push-action@v1
-        with:
-          context: .
-          file: enterprise/Dockerfile
-          push: true
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}
-          build-args: |
-            OPENHANDS_VERSION=${{ env.OPENHANDS_DOCKER_TAG }}
-          platforms: linux/amd64
-          # Add build provenance
-          provenance: true
-          # Add build attestations for better security
-          sbom: true
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
 
-  enterprise-preview:
-    name: Enterprise preview
-    if: github.event_name == 'pull_request' && contains(github.event.pull_request.labels.*.name, 'deploy')
-    runs-on: blacksmith-4vcpu-ubuntu-2204
-    needs: [ghcr_build_enterprise]
+  # Run unit tests with the EventStream runtime Docker images as openhands user
+  test_runtime_oh:
+    name: RT Unit Tests (openhands)
+    runs-on: ubuntu-latest
+    needs: [ghcr_build_runtime]
+    strategy:
+      matrix:
+        base_image: ['nikolaik']
     steps:
-      # This should match the version in enterprise-preview.yml
-      - name: Trigger remote job
+      - uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      # Forked repos can't push to GHCR, so we need to download the image as an artifact
+      - name: Download runtime image for fork
+        if: github.event.pull_request.head.repo.fork
+        uses: actions/download-artifact@v4
+        with:
+          name: runtime-${{ matrix.base_image }}
+          path: /tmp
+      - name: Load runtime image for fork
+        if: github.event.pull_request.head.repo.fork
         run: |
-          curl --fail-with-body -sS -X POST \
-            -H "Authorization: Bearer ${{ secrets.ALLHANDS_BOT_GITHUB_PAT }}" \
-            -H "Accept: application/vnd.github+json" \
-            -d "{\"ref\": \"main\", \"inputs\": {\"openhandsPrNumber\": \"${{ github.event.pull_request.number }}\", \"deployEnvironment\": \"feature\", \"enterpriseImageTag\": \"pr-${{ github.event.pull_request.number }}\" }}" \
-            https://api.github.com/repos/OpenHands/deploy/actions/workflows/deploy.yaml/dispatches
+          docker load --input /tmp/runtime-${{ matrix.base_image }}.tar
+      - name: Cache Poetry dependencies
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies
+      - name: Run runtime tests
+        run: |
+          # We install pytest-xdist in order to run tests across CPUs
+          poetry run pip install pytest-xdist
 
+          # Install to be able to retry on failures for flaky tests
+          poetry run pip install pytest-rerunfailures
+
+          image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
+          image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
+
+          TEST_RUNTIME=eventstream \
+          SANDBOX_USER_ID=$(id -u) \
+          SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
+          TEST_IN_CI=true \
+          RUN_AS_OPENHANDS=true \
+          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+  # The two following jobs (named identically) are to check whether all the runtime tests have passed as the
   # "All Runtime Tests Passed" is a required job for PRs to merge
-  # We can remove this once the config changes
+  # Due to this bug: https://github.com/actions/runner/issues/2566, we want to create a job that runs when the
+  # prerequisites have been cancelled or failed so merging is disallowed, otherwise Github considers "skipped" as "success"
   runtime_tests_check_success:
     name: All Runtime Tests Passed
-    runs-on: blacksmith-4vcpu-ubuntu-2204
+    if: ${{ !cancelled() && !contains(needs.*.result, 'failure') && !contains(needs.*.result, 'cancelled') }}
+    runs-on: ubuntu-latest
+    needs: [test_runtime_root, test_runtime_oh, verify_hash_equivalence_in_runtime_and_app]
     steps:
       - name: All tests passed
         run: echo "All runtime tests have passed successfully!"
 
+  runtime_tests_check_fail:
+    name: All Runtime Tests Passed
+    if: ${{ cancelled() || contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled') }}
+    runs-on: ubuntu-latest
+    needs: [test_runtime_root, test_runtime_oh, verify_hash_equivalence_in_runtime_and_app]
+    steps:
+      - name: Some tests failed
+        run: |
+          echo "Some runtime tests failed or were cancelled"
+          exit 1
   update_pr_description:
     name: Update PR Description
     if: github.event_name == 'pull_request' && !github.event.pull_request.head.repo.fork && github.actor != 'dependabot[bot]'
     needs: [ghcr_build_runtime]
-    runs-on: blacksmith-4vcpu-ubuntu-2204
+    runs-on: ubuntu-latest
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -282,7 +416,30 @@ jobs:
           PR_NUMBER: ${{ github.event.pull_request.number }}
           REPO: ${{ github.repository }}
           SHORT_SHA: ${{ steps.short_sha.outputs.SHORT_SHA }}
-        shell: bash
         run: |
-          echo "Updating PR description with Docker and uvx commands"
-          bash ${GITHUB_WORKSPACE}/.github/scripts/update_pr_description.sh
+          echo "updating PR description"
+          DOCKER_RUN_COMMAND="docker run -it --rm \
+            -p 3000:3000 \
+            -v /var/run/docker.sock:/var/run/docker.sock \
+            --add-host host.docker.internal:host-gateway \
+            -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:$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"

.github/workflows/integration-runner.yml

@@ -0,0 +1,262 @@
+name: Run Integration Tests
+
+on:
+  pull_request:
+    types: [labeled]
+  workflow_dispatch:
+    inputs:
+      reason:
+        description: 'Reason for manual trigger'
+        required: true
+        default: ''
+  schedule:
+    - cron: '30 22 * * *'  # Runs at 10:30pm UTC every day
+
+env:
+  N_PROCESSES: 10 # Global configuration for number of parallel processes for evaluation
+
+jobs:
+  run-integration-tests:
+    if: github.event.label.name == 'integration-test' || github.event_name == 'workflow_dispatch' || github.event_name == 'schedule'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: "read"
+      id-token: "write"
+      pull-requests: "write"
+      issues: "write"
+    strategy:
+      matrix:
+        python-version: ["3.12"]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "poetry"
+
+      - name: Comment on PR if 'integration-test' label is present
+        if: github.event_name == 'pull_request' && github.event.label.name == 'integration-test'
+        uses: KeisukeYamashita/create-comment@v1
+        with:
+          unique: false
+          comment: |
+            Hi! I started running the integration tests on your PR. You will receive a comment with the results shortly.
+
+      - name: Install Python dependencies using Poetry
+        run: poetry install --without evaluation,llama-index
+
+      - name: Configure config.toml for testing with Haiku
+        env:
+          LLM_MODEL: "litellm_proxy/claude-3-5-haiku-20241022"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 10
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+
+      - name: Build environment
+        run: make build
+
+      - name: Run integration test evaluation for Haiku
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' 10 $N_PROCESSES '' 'haiku_run'
+
+          # get integration tests report
+          REPORT_FILE_HAIKU=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/*haiku*_maxiter_10_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE: $REPORT_FILE_HAIKU"
+          echo "INTEGRATION_TEST_REPORT_HAIKU<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_HAIKU >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      - name: Wait a little bit
+        run: sleep 10
+
+      - name: Configure config.toml for testing with DeepSeek
+        env:
+          LLM_MODEL: "litellm_proxy/deepseek-chat"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 10
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+
+      - name: Run integration test evaluation for DeepSeek
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' 10 $N_PROCESSES '' 'deepseek_run'
+
+          # get integration tests report
+          REPORT_FILE_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/deepseek*_maxiter_10_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE: $REPORT_FILE_DEEPSEEK"
+          echo "INTEGRATION_TEST_REPORT_DEEPSEEK<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_DEEPSEEK >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      # -------------------------------------------------------------
+      # Run DelegatorAgent tests for Haiku, limited to t01 and t02
+      - name: Wait a little bit (again)
+        run: sleep 5
+
+      - name: Configure config.toml for testing DelegatorAgent (Haiku)
+        env:
+          LLM_MODEL: "litellm_proxy/claude-3-5-haiku-20241022"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 30
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+
+      - name: Run integration test evaluation for DelegatorAgent (Haiku)
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD DelegatorAgent '' 30 $N_PROCESSES "t01_fix_simple_typo,t02_add_bash_hello" 'delegator_haiku_run'
+
+          # Find and export the delegator test results
+          REPORT_FILE_DELEGATOR_HAIKU=$(find evaluation/evaluation_outputs/outputs/integration_tests/DelegatorAgent/*haiku*_maxiter_30_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE_DELEGATOR_HAIKU: $REPORT_FILE_DELEGATOR_HAIKU"
+          echo "INTEGRATION_TEST_REPORT_DELEGATOR_HAIKU<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_DELEGATOR_HAIKU >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      # -------------------------------------------------------------
+      # Run DelegatorAgent tests for DeepSeek, limited to t01 and t02
+      - name: Wait a little bit (again)
+        run: sleep 5
+
+      - name: Configure config.toml for testing DelegatorAgent (DeepSeek)
+        env:
+          LLM_MODEL: "litellm_proxy/deepseek-chat"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 30
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+      - name: Run integration test evaluation for DelegatorAgent (DeepSeek)
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD DelegatorAgent '' 30 $N_PROCESSES "t01_fix_simple_typo,t02_add_bash_hello" 'delegator_deepseek_run'
+
+          # Find and export the delegator test results
+          REPORT_FILE_DELEGATOR_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/DelegatorAgent/deepseek*_maxiter_30_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE_DELEGATOR_DEEPSEEK: $REPORT_FILE_DELEGATOR_DEEPSEEK"
+          echo "INTEGRATION_TEST_REPORT_DELEGATOR_DEEPSEEK<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_DELEGATOR_DEEPSEEK >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+      # -------------------------------------------------------------
+      # Run VisualBrowsingAgent tests for DeepSeek, limited to t05 and t06
+      - name: Wait a little bit (again)
+        run: sleep 5
+
+      - name: Configure config.toml for testing VisualBrowsingAgent (DeepSeek)
+        env:
+          LLM_MODEL: "litellm_proxy/deepseek-chat"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 15
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+      - name: Run integration test evaluation for VisualBrowsingAgent (DeepSeek)
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD VisualBrowsingAgent '' 15 $N_PROCESSES "t05_simple_browsing,t06_github_pr_browsing.py" 'visualbrowsing_deepseek_run'
+
+          # Find and export the visual browsing agent test results
+          REPORT_FILE_VISUALBROWSING_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/VisualBrowsingAgent/deepseek*_maxiter_15_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE_VISUALBROWSING_DEEPSEEK: $REPORT_FILE_VISUALBROWSING_DEEPSEEK"
+          echo "INTEGRATION_TEST_REPORT_VISUALBROWSING_DEEPSEEK<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_VISUALBROWSING_DEEPSEEK >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      - name: Create archive of evaluation outputs
+        run: |
+          TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
+          cd evaluation/evaluation_outputs/outputs  # Change to the outputs directory
+          tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/* integration_tests/DelegatorAgent/* integration_tests/VisualBrowsingAgent/* # Only include the actual result directories
+
+      - name: Upload evaluation results as artifact
+        uses: actions/upload-artifact@v4
+        id: upload_results_artifact
+        with:
+          name: integration-test-outputs-${{ github.run_id }}-${{ github.run_attempt }}
+          path: integration_tests_*.tar.gz
+
+      - name: Get artifact URLs
+        run: |
+          echo "ARTIFACT_URL=${{ steps.upload_results_artifact.outputs.artifact-url }}" >> $GITHUB_ENV
+
+      - name: Set timestamp and trigger reason
+        run: |
+          echo "TIMESTAMP=$(date +'%Y-%m-%d-%H-%M')" >> $GITHUB_ENV
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            echo "TRIGGER_REASON=pr-${{ github.event.pull_request.number }}" >> $GITHUB_ENV
+          elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
+            echo "TRIGGER_REASON=manual-${{ github.event.inputs.reason }}" >> $GITHUB_ENV
+          else
+            echo "TRIGGER_REASON=nightly-scheduled" >> $GITHUB_ENV
+          fi
+
+      - name: Comment with results and artifact link
+        id: create_comment
+        uses: KeisukeYamashita/create-comment@v1
+        with:
+          # if triggered by PR, use PR number, otherwise use 5318 as fallback issue number for manual triggers
+          number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || 5318 }}
+          unique: false
+          comment: |
+              Trigger by: ${{ github.event_name == 'pull_request' && format('Pull Request (integration-test label on PR #{0})', github.event.pull_request.number) || (github.event_name == 'workflow_dispatch' && format('Manual Trigger: {0}', github.event.inputs.reason)) || 'Nightly Scheduled Run' }}
+              Commit: ${{ github.sha }}
+              **Integration Tests Report (Haiku)**
+              Haiku LLM Test Results:
+              ${{ env.INTEGRATION_TEST_REPORT_HAIKU }}
+              ---
+              **Integration Tests Report (DeepSeek)**
+              DeepSeek LLM Test Results:
+              ${{ env.INTEGRATION_TEST_REPORT_DEEPSEEK }}
+              ---
+                **Integration Tests Report Delegator (Haiku)**
+              ${{ env.INTEGRATION_TEST_REPORT_DELEGATOR_HAIKU }}
+              ---
+              **Integration Tests Report Delegator (DeepSeek)**
+              ${{ env.INTEGRATION_TEST_REPORT_DELEGATOR_DEEPSEEK }}
+              ---
+              **Integration Tests Report VisualBrowsing (DeepSeek)**
+              ${{ env.INTEGRATION_TEST_REPORT_VISUALBROWSING_DEEPSEEK }}
+              ---
+              Download testing outputs (includes both Haiku and DeepSeek results): [Download](${{ steps.upload_results_artifact.outputs.artifact-url }})

.github/workflows/lint-fix.yml

@@ -9,7 +9,7 @@ jobs:
   lint-fix-frontend:
     if: github.event.label.name == 'lint-fix'
     name: Fix frontend linting issues
-    runs-on: blacksmith-4vcpu-ubuntu-2204
+    runs-on: ubuntu-latest
     permissions:
       contents: write
       pull-requests: write
@@ -21,20 +21,14 @@ jobs:
           fetch-depth: 0
           token: ${{ secrets.GITHUB_TOKEN }}
 
-      - name: Install Node.js 22
-        uses: useblacksmith/setup-node@v5
+      - name: Install Node.js 20
+        uses: actions/setup-node@v4
         with:
-          node-version: 22
+          node-version: 20
       - name: Install frontend dependencies
         run: |
           cd frontend
           npm install --frozen-lockfile
-      - name: Generate i18n and route types
-        run: |
-          cd frontend
-          npm run make-i18n
-          npx react-router typegen || true
-
       - name: Fix frontend lint issues
         run: |
           cd frontend
@@ -51,14 +45,14 @@ jobs:
           git config --local user.email "openhands@all-hands.dev"
           git config --local user.name "OpenHands Bot"
           git add -A
-          git commit -m "🤖 Auto-fix frontend linting issues" --no-verify
+          git commit -m "🤖 Auto-fix frontend linting issues"
           git push
 
   # Python lint fixes
   lint-fix-python:
     if: github.event.label.name == 'lint-fix'
     name: Fix Python linting issues
-    runs-on: blacksmith-4vcpu-ubuntu-2204
+    runs-on: ubuntu-latest
     permissions:
       contents: write
       pull-requests: write
@@ -71,16 +65,16 @@ jobs:
           token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Set up python
-        uses: useblacksmith/setup-python@v6
+        uses: actions/setup-python@v5
         with:
           python-version: 3.12
-          cache: "pip"
+          cache: 'pip'
       - name: Install pre-commit
         run: pip install pre-commit==3.7.0
       - name: Fix python lint issues
         run: |
           # Run all pre-commit hooks and continue even if they modify files (exit code 1)
-          pre-commit run --config ./dev_config/python/.pre-commit-config.yaml --all-files || true
+          pre-commit run --config ./dev_config/python/.pre-commit-config.yaml --files openhands/**/* evaluation/**/* tests/**/* || true
 
       # Commit and push changes if any
       - name: Check for changes
@@ -93,5 +87,5 @@ jobs:
           git config --local user.email "openhands@all-hands.dev"
           git config --local user.name "OpenHands Bot"
           git add -A
-          git commit -m "🤖 Auto-fix Python linting issues" --no-verify
+          git commit -m "🤖 Auto-fix Python linting issues"
           git push

.github/workflows/lint.yml

@@ -7,7 +7,7 @@ name: Lint
 on:
   push:
     branches:
-      - main
+    - main
   pull_request:
 
 # If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
@@ -19,56 +19,50 @@ jobs:
   # Run lint on the frontend code
   lint-frontend:
     name: Lint frontend
-    runs-on: blacksmith-4vcpu-ubuntu-2204
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - name: Install Node.js 22
-        uses: useblacksmith/setup-node@v5
+      - name: Install Node.js 20
+        uses: actions/setup-node@v4
         with:
-          node-version: 22
+          node-version: 20
       - name: Install dependencies
         run: |
           cd frontend
           npm install --frozen-lockfile
-      - name: Lint, TypeScript compilation, and translation checks
+      - name: Lint and TypeScript compilation
         run: |
           cd frontend
           npm run lint
           npm run make-i18n && tsc
-          npm run check-translation-completeness
 
   # Run lint on the python code
   lint-python:
     name: Lint python
-    runs-on: blacksmith-4vcpu-ubuntu-2204
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
       - name: Set up python
-        uses: useblacksmith/setup-python@v6
+        uses: actions/setup-python@v5
         with:
           python-version: 3.12
-          cache: "pip"
+          cache: 'pip'
       - name: Install pre-commit
         run: pip install pre-commit==3.7.0
       - name: Run pre-commit hooks
-        run: pre-commit run --all-files --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
+        run: pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
 
-  lint-enterprise-python:
-    name: Lint enterprise python
-    runs-on: blacksmith-4vcpu-ubuntu-2204
+  # Check version consistency across documentation
+  check-version-consistency:
+    name: Check version consistency
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
       - name: Set up python
-        uses: useblacksmith/setup-python@v6
+        uses: actions/setup-python@v5
         with:
           python-version: 3.12
-          cache: "pip"
-      - name: Install pre-commit
-        run: pip install pre-commit==4.2.0
-      - name: Run pre-commit hooks
-        working-directory: ./enterprise
-        run: pre-commit run --all-files --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
+      - name: Run version consistency check
+        run: .github/scripts/check_version_consistency.py

.github/workflows/npm-publish-ui.yml

@@ -1,108 +0,0 @@
-name: Publish OpenHands UI Package
-
-# * Always run on "main"
-# * Run on PRs that have changes in the "openhands-ui" folder or this workflow
-on:
-  push:
-    branches:
-      - main
-    paths:
-      - "openhands-ui/**"
-      - ".github/workflows/npm-publish-ui.yml"
-
-# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
-concurrency:
-  group: npm-publish-ui
-  cancel-in-progress: false
-
-jobs:
-  check-version:
-    name: Check if version has changed
-    runs-on: blacksmith-4vcpu-ubuntu-2204
-    defaults:
-      run:
-        shell: bash
-    outputs:
-      should-publish: ${{ steps.version-check.outputs.should-publish }}
-      current-version: ${{ steps.version-check.outputs.current-version }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 2 # Need previous commit to compare
-
-      - name: Check if version changed
-        id: version-check
-        run: |
-          # Get current version from package.json
-          CURRENT_VERSION=$(jq -r .version openhands-ui/package.json)
-          echo "current-version=$CURRENT_VERSION" >> $GITHUB_OUTPUT
-
-          # Check if package.json version changed in this commit
-          if git diff HEAD~1 HEAD --name-only | grep -q "openhands-ui/package.json"; then
-            # Check if the version field specifically changed
-            if git diff HEAD~1 HEAD openhands-ui/package.json | grep -q '"version"'; then
-              echo "Version changed in package.json, will publish"
-              echo "should-publish=true" >> $GITHUB_OUTPUT
-            else
-              echo "package.json changed but version did not change, skipping publish"
-              echo "should-publish=false" >> $GITHUB_OUTPUT
-            fi
-          else
-            echo "package.json did not change, skipping publish"
-            echo "should-publish=false" >> $GITHUB_OUTPUT
-          fi
-
-  publish:
-    name: Publish to npm
-    runs-on: blacksmith-4vcpu-ubuntu-2204
-    needs: check-version
-    if: needs.check-version.outputs.should-publish == 'true'
-    defaults:
-      run:
-        shell: bash
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Setup Bun
-        uses: oven-sh/setup-bun@v2
-        with:
-          bun-version-file: "openhands-ui/.bun-version"
-
-      - name: Install dependencies
-        working-directory: ./openhands-ui
-        run: bun install --frozen-lockfile
-
-      - name: Build package
-        working-directory: ./openhands-ui
-        run: bun run build
-
-      - name: Check if package already exists on npm
-        id: npm-check
-        working-directory: ./openhands-ui
-        run: |
-          PACKAGE_NAME=$(jq -r .name package.json)
-          VERSION="${{ needs.check-version.outputs.current-version }}"
-
-          # Check if this version already exists on npm
-          if npm view "$PACKAGE_NAME@$VERSION" version 2>/dev/null; then
-            echo "Version $VERSION already exists on npm, skipping publish"
-            echo "already-exists=true" >> $GITHUB_OUTPUT
-          else
-            echo "Version $VERSION does not exist on npm, proceeding with publish"
-            echo "already-exists=false" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Setup npm authentication
-        if: steps.npm-check.outputs.already-exists == 'false'
-        run: |
-          echo "//registry.npmjs.org/:_authToken=${{ secrets.NPM_TOKEN }}" > ~/.npmrc
-
-      - name: Publish to npm
-        if: steps.npm-check.outputs.already-exists == 'false'
-        working-directory: ./openhands-ui
-        run: |
-          # The prepublishOnly script will run automatically and build the package
-          npm publish
-          echo "✅ Successfully published @openhands/ui@${{ needs.check-version.outputs.current-version }} to npm"

.github/workflows/openhands-resolver.yml

@@ -16,28 +16,15 @@ on:
         type: string
         default: "main"
         description: "Target branch to pull and create PR against"
-      pr_type:
-        required: false
-        type: string
-        default: "draft"
-        description: "The PR type that is going to be created (draft, ready)"
       LLM_MODEL:
         required: false
         type: string
-        default: "anthropic/claude-sonnet-4-20250514"
-      LLM_API_VERSION:
-        required: false
-        type: string
-        default: ""
+        default: "anthropic/claude-3-5-sonnet-20241022"
       base_container_image:
         required: false
         type: string
         default: ""
         description: "Custom sandbox env"
-      runner:
-        required: false
-        type: string
-        default: "ubuntu-latest"
     secrets:
       LLM_MODEL:
         required: false
@@ -83,27 +70,26 @@ jobs:
         (github.event.review.author_association == 'OWNER' || github.event.review.author_association == 'COLLABORATOR' || github.event.review.author_association == 'MEMBER')
         )
       )
-    runs-on: "${{ inputs.runner || 'ubuntu-latest' }}"
+    runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
 
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v5
         with:
           python-version: "3.12"
-      - name: Upgrade pip
-        run: |
-          python -m pip install --upgrade pip
 
       - name: Get latest versions and create requirements.txt
         run: |
           python -m pip index versions openhands-ai > openhands_versions.txt
           OPENHANDS_VERSION=$(head -n 1 openhands_versions.txt | awk '{print $2}' | tr -d '()')
-
-          # Create a new requirements.txt locally within the workflow, ensuring no reference to the repo's file
-          echo "openhands-ai==${OPENHANDS_VERSION}" > /tmp/requirements.txt
-          cat /tmp/requirements.txt
+          # Ensure requirements.txt ends with newline before appending
+          if [ -f requirements.txt ] && [ -s requirements.txt ]; then
+            sed -i -e '$a\' requirements.txt
+          fi
+          echo "openhands-ai==${OPENHANDS_VERSION}" >> requirements.txt
+          cat requirements.txt
 
       - name: Cache pip dependencies
         if: |
@@ -118,19 +104,18 @@ jobs:
               contains(github.event.review.body, '@openhands-agent-exp')
             )
           )
-        uses: actions/cache@v5
+        uses: actions/cache@v4
         with:
           path: ${{ env.pythonLocation }}/lib/python3.12/site-packages/*
-          key: ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('/tmp/requirements.txt') }}
+          key: ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }}
           restore-keys: |
-            ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('/tmp/requirements.txt') }}
+            ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }}
 
       - name: Check required environment variables
         env:
           LLM_MODEL: ${{ secrets.LLM_MODEL || inputs.LLM_MODEL }}
           LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
           LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-          LLM_API_VERSION: ${{ inputs.LLM_API_VERSION }}
           PAT_TOKEN: ${{ secrets.PAT_TOKEN }}
           PAT_USERNAME: ${{ secrets.PAT_USERNAME }}
           GITHUB_TOKEN: ${{ github.token }}
@@ -157,15 +142,13 @@ jobs:
           fi
 
       - name: Set environment variables
-        env:
-          REVIEW_BODY: ${{ github.event.review.body || '' }}
         run: |
           # Handle pull request events first
           if [ -n "${{ github.event.pull_request.number }}" ]; then
             echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
             echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
           # Handle pull request review events
-          elif [ -n "$REVIEW_BODY" ]; then
+          elif [ -n "${{ github.event.review.body }}" ]; then
             echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
             echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
           # Handle issue comment events that reference a PR
@@ -178,7 +161,7 @@ jobs:
             echo "ISSUE_TYPE=issue" >> $GITHUB_ENV
           fi
 
-          if [ -n "$REVIEW_BODY" ]; then
+          if [ -n "${{ github.event.review.body }}" ]; then
             echo "COMMENT_ID=${{ github.event.review.id || 'None' }}" >> $GITHUB_ENV
           else
             echo "COMMENT_ID=${{ github.event.comment.id || 'None' }}" >> $GITHUB_ENV
@@ -186,10 +169,10 @@ jobs:
 
           echo "MAX_ITERATIONS=${{ inputs.max_iterations || 50 }}" >> $GITHUB_ENV
           echo "SANDBOX_ENV_GITHUB_TOKEN=${{ secrets.PAT_TOKEN || github.token }}" >> $GITHUB_ENV
-          echo "SANDBOX_BASE_CONTAINER_IMAGE=${{ inputs.base_container_image }}" >> $GITHUB_ENV
+          echo "SANDBOX_ENV_BASE_CONTAINER_IMAGE=${{ inputs.base_container_image }}" >> $GITHUB_ENV
 
           # Set branch variables
-          echo "TARGET_BRANCH=${{ inputs.target_branch || 'main' }}" >> $GITHUB_ENV
+          echo "TARGET_BRANCH=${{ inputs.target_branch }}" >> $GITHUB_ENV
 
       - name: Comment on issue with start message
         uses: actions/github-script@v7
@@ -201,7 +184,7 @@ jobs:
               issue_number: ${{ env.ISSUE_NUMBER }},
               owner: context.repo.owner,
               repo: context.repo.repo,
-              body: `[OpenHands](https://github.com/OpenHands/OpenHands) started fixing the ${issueType}! You can monitor the progress [here](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}).`
+              body: `[OpenHands](https://github.com/All-Hands-AI/OpenHands) started fixing the ${issueType}! You can monitor the progress [here](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}).`
             });
 
       - name: Install OpenHands
@@ -232,27 +215,25 @@ jobs:
             // Perform package installation
             if (isExperimentalLabel || isIssueCommentExperimental || isReviewCommentExperimental) {
               console.log("Installing experimental OpenHands...");
-
-              await exec.exec("pip install git+https://github.com/openhands/openhands.git");
+              await exec.exec("python -m pip install --upgrade pip");
+              await exec.exec("pip install git+https://github.com/all-hands-ai/openhands.git");
             } else {
               console.log("Installing from requirements.txt...");
-
-              await exec.exec("pip install -r /tmp/requirements.txt");
+              await exec.exec("python -m pip install --upgrade pip");
+              await exec.exec("pip install -r requirements.txt");
             }
 
       - name: Attempt to resolve issue
         env:
           GITHUB_TOKEN: ${{ secrets.PAT_TOKEN || github.token }}
           GITHUB_USERNAME: ${{ secrets.PAT_USERNAME || 'openhands-agent' }}
-          GIT_USERNAME: ${{ secrets.PAT_USERNAME || 'openhands-agent' }}
           LLM_MODEL: ${{ secrets.LLM_MODEL || inputs.LLM_MODEL }}
           LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
           LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-          LLM_API_VERSION: ${{ inputs.LLM_API_VERSION }}
           PYTHONPATH: ""
         run: |
           cd /tmp && python -m openhands.resolver.resolve_issue \
-            --selected-repo ${{ github.repository }} \
+            --repo ${{ github.repository }} \
             --issue-number ${{ env.ISSUE_NUMBER }} \
             --issue-type ${{ env.ISSUE_TYPE }} \
             --max-iterations ${{ env.MAX_ITERATIONS }} \
@@ -269,7 +250,7 @@ jobs:
           fi
 
       - name: Upload output.jsonl as artifact
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v4
         if: always() # Upload even if the previous steps fail
         with:
           name: resolver-output
@@ -281,20 +262,17 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.PAT_TOKEN || github.token }}
           GITHUB_USERNAME: ${{ secrets.PAT_USERNAME || 'openhands-agent' }}
-          GIT_USERNAME: ${{ secrets.PAT_USERNAME || 'openhands-agent' }}
           LLM_MODEL: ${{ secrets.LLM_MODEL || inputs.LLM_MODEL }}
           LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
           LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-          LLM_API_VERSION: ${{ inputs.LLM_API_VERSION }}
           PYTHONPATH: ""
         run: |
           if [ "${{ steps.check_result.outputs.RESOLUTION_SUCCESS }}" == "true" ]; then
             cd /tmp && python -m openhands.resolver.send_pull_request \
               --issue-number ${{ env.ISSUE_NUMBER }} \
-              --target-branch ${{ env.TARGET_BRANCH }} \
-              --pr-type ${{ inputs.pr_type || 'draft' }} \
+              --pr-type draft \
               --reviewer ${{ github.actor }} | tee pr_result.txt && \
-              grep "PR created" pr_result.txt | sed 's/.*\///g' > pr_number.txt
+              grep "draft created" pr_result.txt | sed 's/.*\///g' > pr_number.txt
           else
             cd /tmp && python -m openhands.resolver.send_pull_request \
               --issue-number ${{ env.ISSUE_NUMBER }} \
@@ -309,12 +287,11 @@ jobs:
         if: always()
         env:
           AGENT_RESPONDED: ${{ env.AGENT_RESPONDED || 'false' }}
-          ISSUE_NUMBER: ${{ env.ISSUE_NUMBER }}
         with:
           github-token: ${{ secrets.PAT_TOKEN || github.token }}
           script: |
             const fs = require('fs');
-            const issueNumber = process.env.ISSUE_NUMBER;
+            const issueNumber = ${{ env.ISSUE_NUMBER }};
             let logContent = '';
 
             try {
@@ -345,15 +322,13 @@ jobs:
         if: always() # Comment on issue even if the previous steps fail
         env:
           AGENT_RESPONDED: ${{ env.AGENT_RESPONDED || 'false' }}
-          ISSUE_NUMBER: ${{ env.ISSUE_NUMBER }}
-          RESOLUTION_SUCCESS: ${{ steps.check_result.outputs.RESOLUTION_SUCCESS }}
         with:
           github-token: ${{ secrets.PAT_TOKEN || github.token }}
           script: |
             const fs = require('fs');
             const path = require('path');
-            const issueNumber = process.env.ISSUE_NUMBER;
-            const success = process.env.RESOLUTION_SUCCESS === 'true';
+            const issueNumber = ${{ env.ISSUE_NUMBER }};
+            const success = ${{ steps.check_result.outputs.RESOLUTION_SUCCESS }};
 
             let prNumber = '';
             let branchName = '';
@@ -418,12 +393,10 @@ jobs:
       - name: Fallback Error Comment
         uses: actions/github-script@v7
         if: ${{ env.AGENT_RESPONDED == 'false' }} # Only run if no conditions were met in previous steps
-        env:
-          ISSUE_NUMBER: ${{ env.ISSUE_NUMBER }}
         with:
           github-token: ${{ secrets.PAT_TOKEN || github.token }}
           script: |
-            const issueNumber = process.env.ISSUE_NUMBER;
+            const issueNumber = ${{ env.ISSUE_NUMBER }};
 
             github.rest.issues.createComment({
               issue_number: issueNumber,

.github/workflows/py-tests.yml

@@ -1,127 +0,0 @@
-# Workflow that runs python tests
-name: Run Python Tests
-
-# The jobs in this workflow are required, so they must run at all times
-# * Always run on "main"
-# * Always run on PRs
-on:
-  push:
-    branches:
-      - main
-  pull_request:
-
-# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  # Run python tests on Linux
-  test-on-linux:
-    name: Python Tests on Linux
-    runs-on: blacksmith-4vcpu-ubuntu-2404
-    env:
-      INSTALL_DOCKER: "0" # Set to '0' to skip Docker installation
-    strategy:
-      matrix:
-        python-version: ["3.12"]
-    permissions:
-      # For coverage comment and python-coverage-comment-action branch
-      pull-requests: write
-      contents: write
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-      - name: Install tmux
-        run: sudo apt-get update && sudo apt-get install -y tmux
-      - name: Setup Node.js
-        uses: useblacksmith/setup-node@v5
-        with:
-          node-version: "22.x"
-      - name: Install poetry via pipx
-        run: pipx install poetry
-      - name: Set up Python
-        uses: useblacksmith/setup-python@v6
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-      - name: Install Python dependencies using Poetry
-        run: |
-          poetry install --with dev,test,runtime
-          poetry run pip install pytest-xdist
-          poetry run pip install pytest-rerunfailures
-      - name: Build Environment
-        run: make build
-      - name: Run Unit Tests
-        run: PYTHONPATH=".:$PYTHONPATH" poetry run pytest --forked -n auto -s ./tests/unit --cov=openhands --cov-branch
-        env:
-          COVERAGE_FILE: ".coverage.${{ matrix.python_version }}"
-      - name: Run Runtime Tests with CLIRuntime
-        run: PYTHONPATH=".:$PYTHONPATH" TEST_RUNTIME=cli poetry run pytest -n 5 --reruns 2 --reruns-delay 3 -s tests/runtime/test_bash.py --cov=openhands --cov-branch
-        env:
-          COVERAGE_FILE: ".coverage.runtime.${{ matrix.python_version }}"
-      - name: Store coverage file
-        uses: actions/upload-artifact@v6
-        with:
-          name: coverage-openhands
-          path: |
-            .coverage.${{ matrix.python_version }}
-            .coverage.runtime.${{ matrix.python_version }}
-          include-hidden-files: true
-
-  test-enterprise:
-    name: Enterprise Python Unit Tests
-    runs-on: blacksmith-4vcpu-ubuntu-2404
-    strategy:
-      matrix:
-        python-version: ["3.12"]
-    steps:
-      - uses: actions/checkout@v4
-      - name: Install poetry via pipx
-        run: pipx install poetry
-      - name: Set up Python
-        uses: useblacksmith/setup-python@v6
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-      - name: Install Python dependencies using Poetry
-        working-directory: ./enterprise
-        run: poetry install --with dev,test
-      - name: Run Unit Tests
-        # Use base working directory for coverage paths to line up.
-        run: PYTHONPATH=".:$PYTHONPATH" poetry run --project=enterprise pytest --forked -n auto -s -p no:ddtrace -p no:ddtrace.pytest_bdd -p no:ddtrace.pytest_benchmark ./enterprise/tests/unit --cov=enterprise --cov-branch
-        env:
-          COVERAGE_FILE: ".coverage.enterprise.${{ matrix.python_version }}"
-      - name: Store coverage file
-        uses: actions/upload-artifact@v6
-        with:
-          name: coverage-enterprise
-          path: ".coverage.enterprise.${{ matrix.python_version }}"
-          include-hidden-files: true
-
-  coverage-comment:
-    name: Coverage Comment
-    if: github.event_name == 'pull_request'
-    runs-on: ubuntu-latest
-    needs: [test-on-linux, test-enterprise]
-
-    permissions:
-      pull-requests: write
-      contents: write
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/download-artifact@v6
-        id: download
-        with:
-          pattern: coverage-*
-          merge-multiple: true
-
-      - name: Coverage comment
-        id: coverage_comment
-        uses: py-cov-action/python-coverage-comment-action@v3
-        with:
-          GITHUB_TOKEN: ${{ github.token }}
-          MERGE_COVERAGE_FILES: true

.github/workflows/py-unit-tests-mac.yml

@@ -0,0 +1,98 @@
+# Workflow that runs python unit tests on mac
+name: Run Python Unit Tests Mac
+
+# This job is flaky so only run it nightly
+on:
+  schedule:
+    - cron: '0 0 * * *'
+
+jobs:
+  # Run python unit tests on macOS
+  test-on-macos:
+    name: Python Unit Tests on macOS
+    runs-on: macos-14
+    env:
+      INSTALL_DOCKER: '1' # Set to '0' to skip Docker installation
+    strategy:
+      matrix:
+        python-version: ['3.12']
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Cache Poetry dependencies
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+      - name: Install tmux
+        run: brew install tmux
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Install Python dependencies using Poetry
+        run: poetry install --without evaluation,llama-index
+      - name: Install & Start Docker
+        if: env.INSTALL_DOCKER == '1'
+        run: |
+          INSTANCE_NAME="colima-${GITHUB_RUN_ID}"
+
+          # Uninstall colima to upgrade to the latest version
+          if brew list colima &>/dev/null; then
+            brew uninstall colima
+            # unlinking colima dependency: go
+            brew uninstall go@1.21
+          fi
+          rm -rf ~/.colima ~/.lima
+          brew install --HEAD colima
+          brew install docker
+
+          start_colima() {
+            # Find a free port in the range 10000-20000
+            RANDOM_PORT=$((RANDOM % 10001 + 10000))
+
+            # Original line:
+            if ! colima start --network-address --arch x86_64 --cpu=1 --memory=1 --verbose --ssh-port $RANDOM_PORT; then
+              echo "Failed to start Colima."
+              return 1
+            fi
+            return 0
+          }
+
+          # Attempt to start Colima for 5 total attempts:
+          ATTEMPT_LIMIT=5
+          for ((i=1; i<=ATTEMPT_LIMIT; i++)); do
+
+            if start_colima; then
+              echo "Colima started successfully."
+              break
+            else
+              colima stop -f
+              sleep 10
+              colima delete -f
+              if [ $i -eq $ATTEMPT_LIMIT ]; then
+                exit 1
+              fi
+              sleep 10
+            fi
+          done
+
+          # For testcontainers to find the Colima socket
+          # https://github.com/abiosoft/colima/blob/main/docs/FAQ.md#cannot-connect-to-the-docker-daemon-at-unixvarrundockersock-is-the-docker-daemon-running
+          sudo ln -sf $HOME/.colima/default/docker.sock /var/run/docker.sock
+      - name: Build Environment
+        run: make build
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Run Tests
+        run: poetry run pytest --forked --cov=openhands --cov-report=xml ./tests/unit --ignore=tests/unit/test_memory.py
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

.github/workflows/py-unit-tests.yml

@@ -0,0 +1,51 @@
+# Workflow that runs python unit tests
+name: Run Python Unit Tests
+
+# The jobs in this workflow are required, so they must run at all times
+# * Always run on "main"
+# * Always run on PRs
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
+concurrency:
+  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  # Run python unit tests on Linux
+  test-on-linux:
+    name: Python Unit Tests on Linux
+    runs-on: ubuntu-latest
+    env:
+      INSTALL_DOCKER: '0' # Set to '0' to skip Docker installation
+    strategy:
+      matrix:
+        python-version: ['3.12']
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Install tmux
+        run: sudo apt-get update && sudo apt-get install -y tmux
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'poetry'
+      - name: Install Python dependencies using Poetry
+        run: poetry install --without evaluation,llama-index
+      - name: Build Environment
+        run: make build
+      - name: Run Tests
+        run: poetry run pytest --forked -n auto --cov=openhands --cov-report=xml -svv ./tests/unit --ignore=tests/unit/test_memory.py
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

.github/workflows/pypi-release.yml

@@ -1,30 +1,21 @@
 # Publishes the OpenHands PyPi package
 name: Publish PyPi Package
 
+# Triggered manually
 on:
   workflow_dispatch:
     inputs:
       reason:
-        description: "What are you publishing?"
+        description: 'Reason for manual trigger'
         required: true
-        type: choice
-        options:
-          - app server
-        default: app server
-  push:
-    tags:
-      - "*"
+        default: ''
 
 jobs:
   release:
-    runs-on: blacksmith-4vcpu-ubuntu-2204
-    # Run when manually dispatched for "app server" OR for tag pushes that don't contain '-cli'
-    if: |
-      (github.event_name == 'workflow_dispatch' && github.event.inputs.reason == 'app server')
-      || (github.event_name == 'push' && startsWith(github.ref, 'refs/tags/') && !contains(github.ref, '-cli'))
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: useblacksmith/setup-python@v6
+      - uses: actions/setup-python@v5
         with:
           python-version: 3.12
       - name: Install Poetry

.github/workflows/run-eval.yml

@@ -0,0 +1,53 @@
+# Run evaluation on a PR
+name: Run Eval
+
+# Runs when a PR is labeled with one of the "run-eval-" labels
+on:
+  pull_request:
+    types: [labeled]
+
+jobs:
+  trigger-job:
+    name: Trigger remote eval job
+    if: ${{ github.event.label.name == 'run-eval-xs' || github.event.label.name == 'run-eval-s' || github.event.label.name == 'run-eval-m' }}
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout PR branch
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.head_ref }}
+
+      - name: Trigger remote job
+        run: |
+          REPO_URL="https://github.com/${{ github.repository }}"
+          PR_BRANCH="${{ github.head_ref }}"
+          echo "Repository URL: $REPO_URL"
+          echo "PR Branch: $PR_BRANCH"
+
+          if [[ "${{ github.event.label.name }}" == "run-eval-xs" ]]; then
+            EVAL_INSTANCES="1"
+          elif [[ "${{ github.event.label.name }}" == "run-eval-s" ]]; then
+            EVAL_INSTANCES="5"
+          elif [[ "${{ github.event.label.name }}" == "run-eval-m" ]]; then
+            EVAL_INSTANCES="30"
+          fi
+
+          curl -X POST \
+            -H "Authorization: Bearer ${{ secrets.PAT_TOKEN }}" \
+            -H "Accept: application/vnd.github+json" \
+            -d "{\"ref\": \"main\", \"inputs\": {\"github-repo\": \"${REPO_URL}\", \"github-branch\": \"${PR_BRANCH}\", \"pr-number\": \"${{ github.event.pull_request.number }}\", \"eval-instances\": \"${EVAL_INSTANCES}\"}}" \
+            https://api.github.com/repos/All-Hands-AI/evaluation/actions/workflows/create-branch.yml/dispatches
+
+          # Send Slack message
+          PR_URL="https://github.com/${{ github.repository }}/pull/${{ github.event.pull_request.number }}"
+          slack_text="PR $PR_URL has triggered evaluation on $EVAL_INSTANCES instances..."
+          curl -X POST -H 'Content-type: application/json' --data '{"text":"'"$slack_text"'"}' \
+            https://hooks.slack.com/services/${{ secrets.SLACK_TOKEN }}
+
+      - name: Comment on PR
+        uses: KeisukeYamashita/create-comment@v1
+        with:
+          unique: false
+          comment: |
+            Running evaluation on the PR. Once eval is done, the results will be posted.

.github/workflows/stale.yml

@@ -8,16 +8,14 @@ on:
 
 jobs:
   stale:
-    runs-on: blacksmith-4vcpu-ubuntu-2204
-    if: github.repository == 'OpenHands/OpenHands'
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/stale@v9
         with:
-          stale-issue-message: 'This issue is stale because it has been open for 40 days with no activity. Remove the stale label or leave a comment, otherwise it will be closed in 10 days.'
-          stale-pr-message: 'This PR is stale because it has been open for 40 days with no activity. Remove the stale label or leave a comment, otherwise it will be closed in 10 days.'
-          days-before-stale: 40
-          exempt-issue-labels: roadmap,backlog,app-team
-          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: 300
+          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
+          exempt-issue-labels: 'tracked'
+          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

.github/workflows/ui-build.yml

@@ -1,34 +0,0 @@
-name: Run UI Component Build
-
-# * Always run on "main"
-# * Run on PRs that have changes in the "openhands-ui" folder or this workflow
-on:
-  push:
-    branches:
-      - main
-  pull_request:
-    paths:
-      - 'openhands-ui/**'
-      -  '.github/workflows/ui-build.yml'
-
-# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  ui-build:
-    name: Build openhands-ui
-    runs-on: blacksmith-4vcpu-ubuntu-2204
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - uses: oven-sh/setup-bun@v2
-        with:
-          bun-version-file: "openhands-ui/.bun-version"
-      - name: Install dependencies
-        working-directory: ./openhands-ui
-        run: bun install --frozen-lockfile
-      - name: Build package
-        working-directory:  ./openhands-ui
-        run: bun run build

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

@@ -1,51 +0,0 @@
-name: Welcome Good First Issue
-
-on:
-  issues:
-    types: [labeled]
-
-permissions:
-  issues: write
-
-jobs:
-  comment-on-good-first-issue:
-    if: github.event.label.name == 'good first issue'
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check if welcome comment already exists
-        id: check_comment
-        uses: actions/github-script@v7
-        with:
-          result-encoding: string
-          script: |
-            const issueNumber = context.issue.number;
-            const comments = await github.rest.issues.listComments({
-              ...context.repo,
-              issue_number: issueNumber
-            });
-
-            const alreadyCommented = comments.data.some(
-              (comment) =>
-                comment.body.includes('<!-- auto-comment:good-first-issue -->')
-            );
-
-            return alreadyCommented ? 'true' : 'false';
-
-      - name: Leave welcome comment
-        if: steps.check_comment.outputs.result == 'false'
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const repoUrl = `https://github.com/${context.repo.owner}/${context.repo.repo}`;
-
-            await github.rest.issues.createComment({
-              ...context.repo,
-              issue_number: context.issue.number,
-              body: "🙌 **Hey there, future contributor!** 🙌\n\n" +
-                    "This issue has been labeled as **good first issue**, which means it's a great place to get started with the OpenHands project.\n\n" +
-                    "If you're interested in working on it, feel free to! No need to ask for permission.\n\n" +
-                    "Be sure to check out our [development setup guide](" + repoUrl + "/blob/main/Development.md) to get your environment set up, and follow our [contribution guidelines](" + repoUrl + "/blob/main/CONTRIBUTING.md) when you're ready to submit a fix.\n\n" +
-                    "Feel free to join our developer community on [Slack](https://openhands.dev/joinslack). You can ask for [help](https://openhands-ai.slack.com/archives/C078L0FUGUX), [feedback](https://openhands-ai.slack.com/archives/C086ARSNMGA), and even ask for a [PR review](https://openhands-ai.slack.com/archives/C08D8FJ5771).\n\n" +
-                    "🙌 Happy hacking! 🙌\n\n" +
-                    "<!-- auto-comment:good-first-issue -->"
-            });

.gitignore

@@ -161,32 +161,8 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 .idea/
-
-# VS Code: Ignore all but certain files that specify repo-specific settings.
-# https://stackoverflow.com/questions/32964920/should-i-commit-the-vscode-folder-to-source-control
-.vscode/**/*
-!.vscode/extensions.json
-!.vscode/settings.json
-!.vscode/tasks.json
-
-# VS Code extensions/forks:
+.vscode/
 .cursorignore
-.rooignore
-.clineignore
-.windsurfignore
-.cursorrules
-.roorules
-.clinerules
-.windsurfrules
-.cursor/rules
-.roo/rules
-.cline/rules
-.windsurf/rules
-.repomix
-repomix-output.txt
-
-# Emacs backup
-*~
 
 # evaluation
 evaluation/evaluation_outputs
@@ -257,8 +233,3 @@ containers/runtime/Dockerfile
 containers/runtime/project.tar.gz
 containers/runtime/code
 **/node_modules/
-
-# test results
-test-results
-.sessions
-.eval_sessions

.openhands/microagents/documentation.md

@@ -1,33 +0,0 @@
----
-name: documentation
-type: knowledge
-version: 1.0.0
-agent: CodeActAgent
-triggers:
-- documentation
-- docs
-- document
----
-
-# Documentation Guidelines
-
-All documentation must be grounded in fact, so you must not make anything up without proper evidence. When you have finished writing documentation, convey to the user what reference source, including web pages, source code, or other sources of documentation you referenced when writing each new fact in the documentation. If you cannot reference a source for anything do not include it in the pull request.
-
-## Best Practices for Documentation
-
-1. **Be Factual**: Only include information that can be verified from reliable sources.
-2. **Cite Sources**: Always reference the source of information (code, web pages, official documentation).
-3. **Be Clear and Concise**: Use simple language and avoid unnecessary jargon.
-4. **Use Examples**: Include practical examples to illustrate concepts.
-5. **Structure Properly**: Use headings, lists, and code blocks to organize information.
-6. **Keep Updated**: Ensure documentation reflects the current state of the code or system.
-
-## Documentation Process
-
-1. Research and gather information from reliable sources
-2. Draft documentation based on verified facts
-3. Review for accuracy and completeness
-4. Include references for all factual statements
-5. Submit only when all information is properly sourced
-
-Remember: If you cannot verify a piece of information, it's better to exclude it than to include potentially incorrect information.

.openhands/microagents/glossary.md

@@ -1,172 +0,0 @@
-# OpenHands Glossary
-
-### Agent
-The core AI entity in OpenHands that can perform software development tasks by interacting with tools, browsing the web, and modifying code.
-
-#### Agent Controller
-A component that manages the agent's lifecycle, handles its state, and coordinates interactions between the agent and various tools.
-
-#### Agent Delegation
-The ability of an agent to hand off specific tasks to other specialized agents for better task completion.
-
-#### Agent Hub
-A central registry of different agent types and their capabilities, allowing for easy agent selection and instantiation.
-
-#### Agent Skill
-A specific capability or function that an agent can perform, such as file manipulation, web browsing, or code editing.
-
-#### Agent State
-The current context and status of an agent, including its memory, active tools, and ongoing tasks.
-
-#### CodeAct Agent
-[A generalist agent in OpenHands](https://arxiv.org/abs/2407.16741) designed to perform tasks by editing and executing code.
-
-### Browser
-A system for web-based interactions and tasks.
-
-#### Browser Gym
-A testing and evaluation environment for browser-based agent interactions and tasks.
-
-#### Web Browser Tool
-A tool that enables agents to interact with web pages and perform web-based tasks.
-
-### Commands
-Terminal and execution related functionality.
-
-#### Bash Session
-A persistent terminal session that maintains state and history for bash command execution.
-This uses tmux under the hood.
-
-### Configuration
-System-wide settings and options.
-
-#### Agent Configuration
-Settings that define an agent's behavior, capabilities, and limitations, including available tools and runtime settings.
-
-#### Configuration Options
-Settings that control various aspects of OpenHands behavior, including runtime, security, and agent settings.
-
-#### LLM Config
-Configuration settings for language models used by agents, including model selection and parameters.
-
-#### LLM Draft Config
-Settings for draft mode operations with language models, typically used for faster, lower-quality responses.
-
-#### Runtime Configuration
-Settings that define how the runtime environment should be set up and operated.
-
-#### Security Options
-Configuration settings that control security features and restrictions.
-
-### Conversation
-A sequence of interactions between a user and an agent, including messages, actions, and their results.
-
-#### Conversation Info
-Metadata about a conversation, including its status, participants, and timeline.
-
-#### Conversation Manager
-A component that handles the creation, storage, and retrieval of conversations.
-
-#### Conversation Metadata
-Additional information about conversations, such as tags, timestamps, and related resources.
-
-#### Conversation Status
-The current state of a conversation, including whether it's active, completed, or failed.
-
-#### Conversation Store
-A storage system for maintaining conversation history and related data.
-
-### Events
-
-#### Event
-Every Conversation comprises a series of Events. Each Event is either an Action or an Observation.
-
-#### Event Stream
-A continuous flow of events that represents the ongoing activities and interactions in the system.
-
-#### Action
-A specific operation or command that an agent executes through available tools, such as running a command or editing a file.
-
-#### Observation
-The response or result returned by a tool after an agent's action, providing feedback about the action's outcome.
-
-### Interface
-Different ways to interact with OpenHands.
-
-#### CLI Mode
-A command-line interface mode for interacting with OpenHands agents without a graphical interface.
-
-#### GUI Mode
-A graphical user interface mode for interacting with OpenHands agents through a web interface.
-
-#### Headless Mode
-A mode of operation where OpenHands runs without a user interface, suitable for automation and scripting.
-
-### Agent Memory
-The system that decides which parts of the Event Stream (i.e. the conversation history) should be passed into each LLM prompt.
-
-#### Memory Store
-A storage system for maintaining agent memory and context across sessions.
-
-#### Condenser
-A component that processes and summarizes conversation history to maintain context while staying within token limits.
-
-#### Truncation
-A very simple Condenser strategy. Reduces conversation history or content to stay within token limits.
-
-### Microagent
-A specialized prompt that enhances OpenHands with domain-specific knowledge, repository-specific context, and task-specific workflows.
-
-#### Microagent Registry
-A central repository of available microagents and their configurations.
-
-#### Public Microagent
-A general-purpose microagent available to all OpenHands users, triggered by specific keywords. Located in `microagents/`.
-
-#### Repository Microagent
-A type of microagent that provides repository-specific context and guidelines, stored in the `.openhands/microagents/` directory.
-
-### Prompt
-Components for managing and processing prompts.
-
-#### Prompt Caching
-A system for caching and reusing common prompts to improve performance.
-
-#### Prompt Manager
-A component that handles the loading, processing, and management of prompts used by agents, including microagents.
-
-#### Response Parsing
-The process of interpreting and structuring responses from language models and tools.
-
-### Runtime
-The execution environment where agents perform their tasks, which can be local, remote, or containerized.
-
-#### Action Execution Server
-A REST API that receives agent actions (e.g. bash commands, python code, browsing actions), executes them in the runtime environment, and returns the results.
-
-#### Action Execution Client
-A component that handles the execution of actions in the runtime environment, managing the communication between the agent and the runtime.
-
-#### Docker Runtime
-A containerized runtime environment that provides isolation and reproducibility for agent operations.
-
-#### E2B Runtime
-A specialized runtime environment built on E2B for secure and isolated code execution.
-
-#### Local Runtime
-A runtime environment that executes on the local machine, suitable for development and testing.
-
-#### Modal Runtime
-A runtime environment built on Modal for scalable and distributed agent operations.
-
-#### Remote Runtime
-A sandboxed environment that executes code and commands remotely, providing isolation and security for agent operations.
-
-#### Runtime Builder
-A component that builds a Docker image for the Action Execution Server based on a user-specified base image.
-
-### Security
-Security-related components and features.
-
-#### Security Analyzer
-A component that checks agent actions for potential security risks.

.openhands/microagents/repo.md

@@ -0,0 +1,42 @@
+---
+name: repo
+type: repo
+agent: CodeActAgent
+---
+This repository contains the code for OpenHands, an automated AI software engineer. It has a Python backend
+(in the `openhands` directory) and React frontend (in the `frontend` directory).
+
+## General Setup:
+To set up the entire repo, including frontend and backend, run `make build`.
+You don't need to do this unless the user asks you to, or if you're trying to run the entire application.
+
+Before pushing any changes, you should ensure that any lint errors or simple test errors have been fixed.
+
+* If you've made changes to the backend, you should run `pre-commit run --all-files --config ./dev_config/python/.pre-commit-config.yaml`
+* If you've made changes to the frontend, you should run `cd frontend && npm run lint:fix && npm run build ; cd ..`
+
+If either command fails, it may have automatically fixed some issues. You should fix any issues that weren't automatically fixed,
+then re-run the command to ensure it passes.
+
+## Repository Structure
+Backend:
+- Located in the `openhands` directory
+- Testing:
+  - All tests are in `tests/unit/test_*.py`
+  - To test new code, run `poetry run pytest tests/unit/test_xxx.py` where `xxx` is the appropriate file for the current functionality
+  - Write all tests with pytest
+
+Frontend:
+- Located in the `frontend` directory
+- Prerequisites: A recent version of NodeJS / NPM
+- Setup: Run `npm install` in the frontend directory
+- Testing:
+  - Run tests: `npm run test`
+  - To run specific tests: `npm run test -- -t "TestName"`
+- Building:
+  - Build for production: `npm run build`
+- Environment Variables:
+  - Set in `frontend/.env` or as environment variables
+  - Available variables: VITE_BACKEND_HOST, VITE_USE_TLS, VITE_INSECURE_SKIP_VERIFY, VITE_FRONTEND_PORT
+- Internationalization:
+  - Generate i18n declaration file: `npm run make-i18n`

.openhands/pre-commit.sh

@@ -1,124 +0,0 @@
-#!/bin/bash
-
-echo "Running OpenHands pre-commit hook..."
-echo "This hook runs selective linting based on changed files."
-
-# Store the exit code to return at the end
-# This allows us to be additive to existing pre-commit hooks
-EXIT_CODE=0
-
-# Get the list of staged files
-STAGED_FILES=$(git diff --cached --name-only)
-
-# Check if any files match specific patterns
-has_frontend_changes=false
-has_backend_changes=false
-
-# Check each file individually to avoid issues with grep
-for file in $STAGED_FILES; do
-    if [[ $file == frontend/* ]]; then
-        has_frontend_changes=true
-    elif [[ $file == openhands/* || $file == evaluation/* || $file == tests/* ]]; then
-        has_backend_changes=true
-    fi
-done
-
-echo "Analyzing changes..."
-echo "- Frontend changes: $has_frontend_changes"
-echo "- Backend changes: $has_backend_changes"
-
-# Run frontend linting if needed
-if [ "$has_frontend_changes" = true ]; then
-    # Check if we're in a CI environment or if frontend dependencies are missing
-    if [ -n "$CI" ] || ! command -v react-router &> /dev/null || ! command -v vitest &> /dev/null; then
-        echo "Skipping frontend checks (CI environment or missing dependencies detected)."
-        echo "WARNING: Frontend files have changed but frontend checks are being skipped."
-        echo "Please run 'make lint-frontend' manually before submitting your PR."
-    else
-        echo "Running frontend linting..."
-        make lint-frontend
-        if [ $? -ne 0 ]; then
-            echo "Frontend linting failed. Please fix the issues before committing."
-            EXIT_CODE=1
-        else
-            echo "Frontend linting checks passed!"
-        fi
-
-        # Run additional frontend checks
-        if [ -d "frontend" ]; then
-            echo "Running additional frontend checks..."
-            cd frontend || exit 1
-
-            # Run build
-            echo "Running npm build..."
-            npm run build
-            if [ $? -ne 0 ]; then
-                echo "Frontend build failed. Please fix the issues before committing."
-                EXIT_CODE=1
-            fi
-
-            # Run tests
-            echo "Running npm test..."
-            npm test
-            if [ $? -ne 0 ]; then
-                echo "Frontend tests failed. Please fix the failing tests before committing."
-                EXIT_CODE=1
-            fi
-
-            cd ..
-        fi
-    fi
-else
-    echo "Skipping frontend checks (no frontend changes detected)."
-fi
-
-# Run backend linting if needed
-if [ "$has_backend_changes" = true ]; then
-    echo "Running backend linting..."
-    make lint-backend
-    if [ $? -ne 0 ]; then
-        echo "Backend linting failed. Please fix the issues before committing."
-        EXIT_CODE=1
-    else
-        echo "Backend linting checks passed!"
-    fi
-else
-    echo "Skipping backend checks (no backend changes detected)."
-fi
-
-
-# If no specific code changes detected, run basic checks
-if [ "$has_frontend_changes" = false ] && [ "$has_backend_changes" = false ]; then
-    echo "No specific code changes detected. Running basic checks..."
-    if [ -n "$STAGED_FILES" ]; then
-        # Run only basic pre-commit hooks for non-code files
-        poetry run pre-commit run --files $(echo "$STAGED_FILES" | tr '\n' ' ') --hook-stage commit --config ./dev_config/python/.pre-commit-config.yaml
-        if [ $? -ne 0 ]; then
-            echo "Basic checks failed. Please fix the issues before committing."
-            EXIT_CODE=1
-        else
-            echo "Basic checks passed!"
-        fi
-    else
-        echo "No files changed. Skipping basic checks."
-    fi
-fi
-
-# Run any existing pre-commit hooks that might have been installed by the user
-# This makes our hook additive rather than replacing existing hooks
-if [ -f ".git/hooks/pre-commit.local" ]; then
-    echo "Running existing pre-commit hooks..."
-    bash .git/hooks/pre-commit.local
-    if [ $? -ne 0 ]; then
-        echo "Existing pre-commit hooks failed."
-        EXIT_CODE=1
-    fi
-fi
-
-if [ $EXIT_CODE -eq 0 ]; then
-    echo "All pre-commit checks passed!"
-else
-    echo "Some pre-commit checks failed. Please fix the issues before committing."
-fi
-
-exit $EXIT_CODE

.openhands/setup.sh

@@ -1,13 +0,0 @@
-#! /bin/bash
-
-echo "Setting up the environment..."
-
-# Install pre-commit package
-python -m pip install pre-commit
-
-# Install pre-commit hooks if .git directory exists
-if [ -d ".git" ]; then
-    echo "Installing pre-commit hooks..."
-    pre-commit install
-    make install-pre-commit-hooks
-fi

.vscode/settings.json

@@ -1,22 +0,0 @@
-{
-    // force *nix line endings so files don't look modified in container run from Windows clone
-    "files.eol": "\n",
-    "files.trimTrailingWhitespace": true,
-    "files.insertFinalNewline": true,
-
-    "python.defaultInterpreterPath": "./.venv/bin/python",
-    "python.terminal.activateEnvironment": true,
-    "python.analysis.autoImportCompletions": true,
-    "python.analysis.autoSearchPaths": true,
-    "python.analysis.extraPaths": [
-        "./.venv/lib/python3.12/site-packages"
-    ],
-    "python.analysis.packageIndexDepths": [
-        {
-            "name": "openhands",
-            "depth": 10,
-            "includeAllSymbols": true
-        }
-    ],
-    "python.analysis.stubPath": "./.venv/lib/python3.12/site-packages",
-}

AGENTS.md

@@ -1,344 +0,0 @@
-This repository contains the code for OpenHands, an automated AI software engineer. It has a Python backend
-(in the `openhands` directory) and React frontend (in the `frontend` directory).
-
-## General Setup:
-To set up the entire repo, including frontend and backend, run `make build`.
-You don't need to do this unless the user asks you to, or if you're trying to run the entire application.
-
-## Running OpenHands with OpenHands:
-To run the full application to debug issues:
-```bash
-export INSTALL_DOCKER=0
-export RUNTIME=local
-make build && make run FRONTEND_PORT=12000 FRONTEND_HOST=0.0.0.0 BACKEND_HOST=0.0.0.0 &> /tmp/openhands-log.txt &
-```
-
-IMPORTANT: Before making any changes to the codebase, ALWAYS run `make install-pre-commit-hooks` to ensure pre-commit hooks are properly installed.
-
-Before pushing any changes, you MUST ensure that any lint errors or simple test errors have been fixed.
-
-* If you've made changes to the backend, you should run `pre-commit run --config ./dev_config/python/.pre-commit-config.yaml` (this will run on staged files).
-* If you've made changes to the frontend, you should run `cd frontend && npm run lint:fix && npm run build ; cd ..`
-* If you've made changes to the VSCode extension, you should run `cd openhands/integrations/vscode && npm run lint:fix && npm run compile ; cd ../../..`
-
-The pre-commit hooks MUST pass successfully before pushing any changes to the repository. This is a mandatory requirement to maintain code quality and consistency.
-
-If either command fails, it may have automatically fixed some issues. You should fix any issues that weren't automatically fixed,
-then re-run the command to ensure it passes. Common issues include:
-- Mypy type errors
-- Ruff formatting issues
-- Trailing whitespace
-- Missing newlines at end of files
-
-## Git Best Practices
-
-- Prefer specific `git add <filename>` instead of `git add .` to avoid accidentally staging unintended files
-- Be especially careful with `git reset --hard` after staging files, as it will remove accidentally staged files
-- When remote has new changes, use `git fetch upstream && git rebase upstream/<branch>` on the same branch
-
-## Repository Structure
-Backend:
-- Located in the `openhands` directory
-- Testing:
-  - All tests are in `tests/unit/test_*.py`
-  - To test new code, run `poetry run pytest tests/unit/test_xxx.py` where `xxx` is the appropriate file for the current functionality
-  - Write all tests with pytest
-
-Frontend:
-- Located in the `frontend` directory
-- Prerequisites: A recent version of NodeJS / NPM
-- Setup: Run `npm install` in the frontend directory
-- Testing:
-  - Run tests: `npm run test`
-  - To run specific tests: `npm run test -- -t "TestName"`
-  - Our test framework is vitest
-- Building:
-  - Build for production: `npm run build`
-- Environment Variables:
-  - Set in `frontend/.env` or as environment variables
-  - Available variables: VITE_BACKEND_HOST, VITE_USE_TLS, VITE_INSECURE_SKIP_VERIFY, VITE_FRONTEND_PORT
-- Internationalization:
-  - Generate i18n declaration file: `npm run make-i18n`
-- Data Fetching & Cache Management:
-  - We use TanStack Query (fka React Query) for data fetching and cache management
-  - Data Access Layer: API client methods are located in `frontend/src/api` and should never be called directly from UI components - they must always be wrapped with TanStack Query
-  - Custom hooks are located in `frontend/src/hooks/query/` and `frontend/src/hooks/mutation/`
-  - Query hooks should follow the pattern use[Resource] (e.g., `useConversationSkills`)
-  - Mutation hooks should follow the pattern use[Action] (e.g., `useDeleteConversation`)
-  - Architecture rule: UI components → TanStack Query hooks → Data Access Layer (`frontend/src/api`) → API endpoints
-
-VSCode Extension:
-- Located in the `openhands/integrations/vscode` directory
-- Setup: Run `npm install` in the extension directory
-- Linting:
-  - Run linting with fixes: `npm run lint:fix`
-  - Check only: `npm run lint`
-  - Type checking: `npm run typecheck`
-- Building:
-  - Compile TypeScript: `npm run compile`
-  - Package extension: `npm run package-vsix`
-- Testing:
-  - Run tests: `npm run test`
-- Development Best Practices:
-  - Use `vscode.window.createOutputChannel()` for debug logging instead of `showErrorMessage()` popups
-  - Pre-commit process runs both frontend and backend checks when committing extension changes
-
-## Enterprise Directory
-
-The `enterprise/` directory contains additional functionality that extends the open-source OpenHands codebase. This includes:
-- Authentication and user management (Keycloak integration)
-- Database migrations (Alembic)
-- Integration services (GitHub, GitLab, Jira, Linear, Slack)
-- Billing and subscription management (Stripe)
-- Telemetry and analytics (PostHog, custom metrics framework)
-
-### Enterprise Development Setup
-
-**Prerequisites:**
-- Python 3.12
-- Poetry (for dependency management)
-- Node.js 22.x (for frontend)
-- Docker (optional)
-
-**Setup Steps:**
-1. First, build the main OpenHands project: `make build`
-2. Then install enterprise dependencies: `cd enterprise && poetry install --with dev,test` (This can take a very long time. Be patient.)
-3. Set up enterprise pre-commit hooks: `poetry run pre-commit install --config ./dev_config/python/.pre-commit-config.yaml`
-
-**Running Enterprise Tests:**
-```bash
-# Enterprise unit tests (full suite)
-PYTHONPATH=".:$PYTHONPATH" poetry run --project=enterprise pytest --forked -n auto -s -p no:ddtrace -p no:ddtrace.pytest_bdd -p no:ddtrace.pytest_benchmark ./enterprise/tests/unit --cov=enterprise --cov-branch
-
-# Test specific modules (faster for development)
-cd enterprise
-PYTHONPATH=".:$PYTHONPATH" poetry run pytest tests/unit/telemetry/ --confcutdir=tests/unit/telemetry
-
-# Enterprise linting (IMPORTANT: use --show-diff-on-failure to match GitHub CI)
-poetry run pre-commit run --all-files --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
-```
-
-**Running Enterprise Server:**
-```bash
-cd enterprise
-make start-backend  # Development mode with hot reload
-# or
-make run  # Full application (backend + frontend)
-```
-
-**Key Configuration Files:**
-- `enterprise/pyproject.toml` - Enterprise-specific dependencies
-- `enterprise/Makefile` - Enterprise build and run commands
-- `enterprise/dev_config/python/` - Linting and type checking configuration
-- `enterprise/migrations/` - Database migration files
-
-**Database Migrations:**
-Enterprise uses Alembic for database migrations. When making schema changes:
-1. Create migration files in `enterprise/migrations/versions/`
-2. Test migrations thoroughly
-3. The CI will check for migration conflicts on PRs
-
-**Integration Development:**
-The enterprise codebase includes integrations for:
-- **GitHub** - PR management, webhooks, app installations
-- **GitLab** - Similar to GitHub but for GitLab instances
-- **Jira** - Issue tracking and project management
-- **Linear** - Modern issue tracking
-- **Slack** - Team communication and notifications
-
-Each integration follows a consistent pattern with service classes, storage models, and API endpoints.
-
-**Important Notes:**
-- Enterprise code is licensed under Polyform Free Trial License (30-day limit)
-- The enterprise server extends the OpenHands server through dynamic imports
-- Database changes require careful migration planning in `enterprise/migrations/`
-- Always test changes in both OpenHands and enterprise contexts
-- Use the enterprise-specific Makefile commands for development
-
-**Enterprise Testing Best Practices:**
-
-**Database Testing:**
-- Use SQLite in-memory databases (`sqlite:///:memory:`) for unit tests instead of real PostgreSQL
-- Create module-specific `conftest.py` files with database fixtures
-- Mock external database connections in unit tests to avoid dependency on running services
-- Use real database connections only for integration tests
-
-**Import Patterns:**
-- Use relative imports without `enterprise.` prefix in enterprise code
-- Example: `from storage.database import session_maker` not `from enterprise.storage.database import session_maker`
-- This ensures code works in both OpenHands and enterprise contexts
-
-**Test Structure:**
-- Place tests in `enterprise/tests/unit/` following the same structure as the source code
-- Use `--confcutdir=tests/unit/[module]` when testing specific modules
-- Create comprehensive fixtures for complex objects (databases, external services)
-- Write platform-agnostic tests (avoid hardcoded OS-specific assertions)
-
-**Mocking Strategy:**
-- Use `AsyncMock` for async operations and `MagicMock` for complex objects
-- Mock all external dependencies (databases, APIs, file systems) in unit tests
-- Use `patch` with correct import paths (e.g., `telemetry.registry.logger` not `enterprise.telemetry.registry.logger`)
-- Test both success and failure scenarios with proper error handling
-
-**Coverage Goals:**
-- Aim for 90%+ test coverage on new enterprise modules
-- Focus on critical business logic and error handling paths
-- Use `--cov-report=term-missing` to identify uncovered lines
-
-**Troubleshooting:**
-- If tests fail, ensure all dependencies are installed: `poetry install --with dev,test`
-- For database issues, check migration status and run migrations if needed
-- For frontend issues, ensure the main OpenHands frontend is built: `make build`
-- Check logs in the `logs/` directory for runtime issues
-- If tests fail with import errors, verify `PYTHONPATH=".:$PYTHONPATH"` is set
-- **If GitHub CI fails but local linting passes**: Always use `--show-diff-on-failure` flag to match CI behavior exactly
-
-## Template for Github Pull Request
-
-If you are starting a pull request (PR), please follow the template in `.github/pull_request_template.md`.
-
-## Implementation Details
-
-These details may or may not be useful for your current task.
-
-### Microagents
-
-Microagents are specialized prompts that enhance OpenHands with domain-specific knowledge and task-specific workflows. They are Markdown files that can include frontmatter for configuration.
-
-#### Types:
-- **Public Microagents**: Located in `microagents/`, available to all users
-- **Repository Microagents**: Located in `.openhands/microagents/`, specific to this repository
-
-#### Loading Behavior:
-- **Without frontmatter**: Always loaded into LLM context
-- **With triggers in frontmatter**: Only loaded when user's message matches the specified trigger keywords
-
-#### Structure:
-```yaml
----
-triggers:
-- keyword1
-- keyword2
----
-# Microagent Content
-Your specialized knowledge and instructions here...
-```
-
-### Frontend
-
-#### Action Handling:
-- Actions are defined in `frontend/src/types/action-type.ts`
-- The `HANDLED_ACTIONS` array in `frontend/src/state/chat-slice.ts` determines which actions are displayed as collapsible UI elements
-- To add a new action type to the UI:
-  1. Add the action type to the `HANDLED_ACTIONS` array
-  2. Implement the action handling in `addAssistantAction` function in chat-slice.ts
-  3. Add a translation key in the format `ACTION_MESSAGE$ACTION_NAME` to the i18n files
-- Actions with `thought` property are displayed in the UI based on their action type:
-  - Regular actions (like "run", "edit") display the thought as a separate message
-  - Special actions (like "think") are displayed as collapsible elements only
-
-#### Adding User Settings:
-- To add a new user setting to OpenHands, follow these steps:
-  1. Add the setting to the frontend:
-     - Add the setting to the `Settings` type in `frontend/src/types/settings.ts`
-     - Add the setting to the `ApiSettings` type in the same file
-     - Add the setting with an appropriate default value to `DEFAULT_SETTINGS` in `frontend/src/services/settings.ts`
-     - Update the `useSettings` hook in `frontend/src/hooks/query/use-settings.ts` to map the API response
-     - Update the `useSaveSettings` hook in `frontend/src/hooks/mutation/use-save-settings.ts` to include the setting in API requests
-     - Add UI components (like toggle switches) in the appropriate settings screen (e.g., `frontend/src/routes/app-settings.tsx`)
-     - Add i18n translations for the setting name and any tooltips in `frontend/src/i18n/translation.json`
-     - Add the translation key to `frontend/src/i18n/declaration.ts`
-  2. Add the setting to the backend:
-     - Add the setting to the `Settings` model in `openhands/storage/data_models/settings.py`
-     - Update any relevant backend code to apply the setting (e.g., in session creation)
-
-#### Settings UI Patterns:
-
-There are two main patterns for saving settings in the OpenHands frontend:
-
-**Pattern 1: Entity-based Resources (Immediate Save)**
-- Used for: API Keys, Secrets, MCP Servers
-- Behavior: Changes are saved immediately when user performs actions (add/edit/delete)
-- Implementation:
-  - No "Save Changes" button
-  - No local state management or `isDirty` tracking
-  - Uses dedicated mutation hooks for each operation (e.g., `use-add-mcp-server.ts`, `use-delete-mcp-server.ts`)
-  - Each mutation triggers immediate API call with query invalidation for UI updates
-  - Example: MCP settings, API Keys & Secrets tabs
-- Benefits: Simpler UX, no risk of losing changes, consistent with modern web app patterns
-
-**Pattern 2: Form-based Settings (Manual Save)**
-- Used for: Application settings, LLM configuration
-- Behavior: Changes are accumulated locally and saved when user clicks "Save Changes"
-- Implementation:
-  - Has "Save Changes" button that becomes enabled when changes are detected
-  - Uses local state management with `isDirty` tracking
-  - Uses `useSaveSettings` hook to save all changes at once
-  - Example: LLM tab, Application tab
-- Benefits: Allows bulk changes, explicit save action, can validate all fields before saving
-
-**When to use each pattern:**
-- Use Pattern 1 (Immediate Save) for entity management where each item is independent
-- Use Pattern 2 (Manual Save) for configuration forms where settings are interdependent or need validation
-
-### Adding New LLM Models
-
-To add a new LLM model to OpenHands, you need to update multiple files across both frontend and backend:
-
-#### Model Configuration Procedure:
-
-1. **Frontend Model Arrays** (`frontend/src/utils/verified-models.ts`):
-   - Add the model to `VERIFIED_MODELS` array (main list of all verified models)
-   - Add to provider-specific arrays based on the model's provider:
-     - `VERIFIED_OPENAI_MODELS` for OpenAI models
-     - `VERIFIED_ANTHROPIC_MODELS` for Anthropic models
-     - `VERIFIED_MISTRAL_MODELS` for Mistral models
-     - `VERIFIED_OPENHANDS_MODELS` for models available through OpenHands provider
-
-2. **Backend CLI Integration** (`openhands/cli/utils.py`):
-   - Add the model to the appropriate `VERIFIED_*_MODELS` arrays
-   - This ensures the model appears in CLI model selection
-
-3. **Backend Model List** (`openhands/utils/llm.py`):
-   - **CRITICAL**: Add the model to the `openhands_models` list (lines 57-66) if using OpenHands provider
-   - This is required for the model to appear in the frontend model selector
-   - Format: `'openhands/model-name'` (e.g., `'openhands/o3'`)
-
-4. **Backend LLM Configuration** (`openhands/llm/llm.py`):
-   - Add to feature-specific arrays based on model capabilities:
-     - `FUNCTION_CALLING_SUPPORTED_MODELS` if the model supports function calling
-     - `REASONING_EFFORT_SUPPORTED_MODELS` if the model supports reasoning effort parameters
-     - `CACHE_PROMPT_SUPPORTED_MODELS` if the model supports prompt caching
-     - `MODELS_WITHOUT_STOP_WORDS` if the model doesn't support stop words
-
-5. **Validation**:
-   - Run backend linting: `pre-commit run --config ./dev_config/python/.pre-commit-config.yaml`
-   - Run frontend linting: `cd frontend && npm run lint:fix`
-   - Run frontend build: `cd frontend && npm run build`
-
-#### Model Verification Arrays:
-
-- **VERIFIED_MODELS**: Main array of all verified models shown in the UI
-- **VERIFIED_OPENAI_MODELS**: OpenAI models (LiteLLM doesn't return provider prefix)
-- **VERIFIED_ANTHROPIC_MODELS**: Anthropic models (LiteLLM doesn't return provider prefix)
-- **VERIFIED_MISTRAL_MODELS**: Mistral models (LiteLLM doesn't return provider prefix)
-- **VERIFIED_OPENHANDS_MODELS**: Models available through OpenHands managed provider
-
-#### Model Feature Support Arrays:
-
-- **FUNCTION_CALLING_SUPPORTED_MODELS**: Models that support structured function calling
-- **REASONING_EFFORT_SUPPORTED_MODELS**: Models that support reasoning effort parameters (like o1, o3)
-- **CACHE_PROMPT_SUPPORTED_MODELS**: Models that support prompt caching for efficiency
-- **MODELS_WITHOUT_STOP_WORDS**: Models that don't support stop word parameters
-
-#### Frontend Model Integration:
-
-- Models are automatically available in the model selector UI once added to verified arrays
-- The `extractModelAndProvider` utility automatically detects provider from model arrays
-- Provider-specific models are grouped and prioritized in the UI selection
-
-#### CLI Model Integration:
-
-- Models appear in CLI provider selection based on the verified arrays
-- The `organize_models_and_providers` function groups models by provider
-- Default model selection prioritizes verified models for each provider

CITATION.cff

@@ -1,55 +0,0 @@
-cff-version: 1.2.0
-message: "If you use this software, please cite it using the following metadata."
-title: "OpenHands: An Open Platform for AI Software Developers as Generalist Agents"
-authors:
-  - family-names: Wang
-    given-names: Xingyao
-  - family-names: Li
-    given-names: Boxuan
-  - family-names: Song
-    given-names: Yufan
-  - family-names: Xu
-    given-names: Frank F.
-  - family-names: Tang
-    given-names: Xiangru
-  - family-names: Zhuge
-    given-names: Mingchen
-  - family-names: Pan
-    given-names: Jiayi
-  - family-names: Song
-    given-names: Yueqi
-  - family-names: Li
-    given-names: Bowen
-  - family-names: Singh
-    given-names: Jaskirat
-  - family-names: Tran
-    given-names: Hoang H.
-  - family-names: Li
-    given-names: Fuqiang
-  - family-names: Ma
-    given-names: Ren
-  - family-names: Zheng
-    given-names: Mingzhang
-  - family-names: Qian
-    given-names: Bill
-  - family-names: Shao
-    given-names: Yanjun
-  - family-names: Muennighoff
-    given-names: Niklas
-  - family-names: Zhang
-    given-names: Yizhe
-  - family-names: Hui
-    given-names: Binyuan
-  - family-names: Lin
-    given-names: Junyang
-  - family-names: Brennan
-    given-names: Robert
-  - family-names: Peng
-    given-names: Hao
-  - family-names: Ji
-    given-names: Heng
-  - family-names: Neubig
-    given-names: Graham
-year: 2024
-doi: "10.48550/arXiv.2407.16741"
-url: "https://arxiv.org/abs/2407.16741"

CNAME

@@ -1 +0,0 @@
-docs.all-hands.dev

CODE_OF_CONDUCT.md

@@ -61,7 +61,7 @@ representative at an online or offline event.
 
 Instances of abusive, harassing, or otherwise unacceptable behavior may be
 reported to the community leaders responsible for enforcement at
-contact@openhands.dev.
+contact@all-hands.dev.
 All complaints will be reviewed and investigated promptly and fairly.
 
 All community leaders are obligated to respect the privacy and security of the
@@ -113,24 +113,19 @@ individual, or aggression toward or disparagement of classes of individuals.
 **Consequence**: A permanent ban from any sort of public interaction within the
 community.
 
-### Slack Etiquettes
+### Slack and Discord Etiquettes
 
-These Slack etiquette guidelines are designed to foster an inclusive, respectful, and productive environment for all
-community members. By following these best practices, we ensure effective communication and collaboration while
-minimizing disruptions. Let’s work together to build a supportive and welcoming community!
+These Slack and Discord etiquette guidelines are designed to foster an inclusive, respectful, and productive environment for all community members. By following these best practices, we ensure effective communication and collaboration while minimizing disruptions. Let’s work together to build a supportive and welcoming community!
 
 - Communicate respectfully and professionally, avoiding sarcasm or harsh language, and remember that tone can be difficult to interpret in text.
 - Use threads for specific discussions to keep channels organized and easier to follow.
 - Tag others only when their input is critical or urgent, and use @here, @channel or @everyone sparingly to minimize disruptions.
 - Be patient, as open-source contributors and maintainers often have other commitments and may need time to respond.
-- Post questions or discussions in the most relevant channel (e.g., for [slack - #general](https://openhands-ai.slack.com/archives/C06P5NCGSFP) for general topics, [slack - #questions](https://openhands-ai.slack.com/archives/C06U8UTKSAD) for queries/questions.
+- Post questions or discussions in the most relevant channel (e.g., for [slack - #general](https://app.slack.com/client/T06P212QSEA/C06P5NCGSFP) for general topics, [slack - #questions](https://openhands-ai.slack.com/archives/C06U8UTKSAD) for queries/questions, [discord - #general](https://discord.com/channels/1222935860639563850/1222935861386018885)).
 - When asking for help or raising issues, include necessary details like links, screenshots, or clear explanations to provide context.
 - Keep discussions in public channels whenever possible to allow others to benefit from the conversation, unless the matter is sensitive or private.
-- Always adhere to [our standards](https://github.com/OpenHands/OpenHands/blob/main/CODE_OF_CONDUCT.md#our-standards) to ensure a welcoming and collaborative environment.
-- If you choose to mute a channel, consider setting up alerts for topics that still interest you to stay engaged.
-   For Slack, Go to Settings → Notifications → My Keywords to add specific keywords that will notify you when mentioned.
-   For example, if you're here for discussions about LLMs, mute the channel if it’s too busy, but set notifications to
-   alert you only when “LLMs” appears in messages.
+- Always adhere to [our standards](https://github.com/All-Hands-AI/OpenHands/blob/main/CODE_OF_CONDUCT.md#our-standards) to ensure a welcoming and collaborative environment.
+- If you choose to mute a channel, consider setting up alerts for topics that still interest you to stay engaged. For Slack, Go to Settings → Notifications → My Keywords to add specific keywords that will notify you when mentioned. For example, if you're here for discussions about LLMs, mute the channel if it’s too busy, but set notifications to alert you only when “LLMs” appears in messages. Also for Discord, go to the channel notifications and choose the option that best describes your need.
 
 ## Attribution
 

COMMUNITY.md

@@ -1,58 +1,43 @@
-# The OpenHands Community
+# 🙌 The OpenHands Community
 
-OpenHands is a community of engineers, academics, and enthusiasts reimagining software development for an AI-powered
-world.
+The OpenHands community is built around the belief that (1) AI and AI agents are going to fundamentally change the way
+we build software, and (2) if this is true, we should do everything we can to make sure that the benefits provided by
+such powerful technology are accessible to everyone.
 
-## Mission
+If this resonates with you, we'd love to have you join us in our quest!
 
-It’s very clear that AI is changing software development. We want the developer community to drive that change
-organically, through open source.
+## 🤝 How to Join
 
-So we’re not just building friendly interfaces for AI-driven development. We’re publishing _building blocks_ that
-empower developers to create new experiences, tailored to your own habits, needs, and imagination.
+Check out our [How to Join the Community section.](https://github.com/All-Hands-AI/OpenHands?tab=readme-ov-file#-how-to-join-the-community)
 
-## Ethos
+## 💪 Becoming a Contributor
 
-We have two core values: **high openness** and **high agency**. While we don’t expect everyone in the community to
-embody these values, we want to establish them as norms.
+We welcome contributions from everyone! Whether you're a developer, a researcher, or simply enthusiastic about advancing
+the field of software engineering with AI, there are many ways to get involved:
 
-### High Openness
+- **Code Contributions:** Help us develop new core functionality, improve our agents, improve the frontend and other
+interfaces, or anything else that would help make OpenHands better.
+- **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in
+evaluating the models, or suggest improvements.
+- **Feedback and Testing:** Use the OpenHands toolset, report bugs, suggest features, or provide feedback on usability.
 
-We welcome anyone and everyone into our community by default. You don’t have to be a software developer to help us
-build. You don’t have to be pro-AI to help us learn.
+For details, please check [CONTRIBUTING.md](./CONTRIBUTING.md).
 
-Our plans, our work, our successes, and our failures are all public record. We want the world to see not just the
-fruits of our work, but the whole process of growing it.
+## Code of Conduct
 
-We welcome thoughtful criticism, whether it’s a comment on a PR or feedback on the community as a whole.
+We have a [Code of Conduct](./CODE_OF_CONDUCT.md) that we expect all contributors to adhere to.
+Long story short, we are aiming for an open, welcoming, diverse, inclusive, and healthy community.
+All contributors are expected to contribute to building this sort of community.
 
-### High Agency
+## 🛠️ Becoming a Maintainer
 
-Everyone should feel empowered to contribute to OpenHands. Whether it’s by making a PR, hosting an event, sharing
-feedback, or just asking a question, don’t hold back!
+For contributors who have made significant and sustained contributions to the project, there is a possibility of joining
+the maintainer team. The process for this is as follows:
 
-OpenHands gives everyone the building blocks to create state-of-the-art developer experiences. We experiment constantly
-and love building new things.
+1. Any contributor who has made sustained and high-quality contributions to the codebase can be nominated by any
+maintainer. If you feel that you may qualify you can reach out to any of the maintainers that have reviewed your PRs and ask if you can be nominated.
+2. Once a maintainer nominates a new maintainer, there will be a discussion period among the maintainers for at least 3 days.
+3. If no concerns are raised the nomination will be accepted by acclamation, and if concerns are raised there will be a discussion and possible vote.
 
-Coding, development practices, and communities are changing rapidly. We won’t hesitate to change direction and make big bets.
-
-## Relationship to All Hands
-
-OpenHands is supported by the for-profit organization [All Hands AI, Inc](https://www.openhands.dev/).
-
-All Hands was founded by three of the first major contributors to OpenHands:
-
-- Xingyao Wang, a UIUC PhD candidate who got OpenHands to the top of the SWE-bench leaderboards
-- Graham Neubig, a CMU Professor who rallied the academic community around OpenHands
-- Robert Brennan, a software engineer who architected the user-facing features of OpenHands
-
-All Hands is an important part of the OpenHands ecosystem. We’ve raised over $20M--mainly to hire developers and
-researchers who can work on OpenHands full-time, and to provide them with expensive infrastructure. ([Join us!](https://allhandsai.applytojob.com/apply/))
-
-But we see OpenHands as much larger, and ultimately more important, than All Hands. When our financial responsibility
-to investors is at odds with our social responsibility to the community—as it inevitably will be, from time to time—we
-promise to navigate that conflict thoughtfully and transparently.
-
-At some point, we may transfer custody of OpenHands to an open source foundation. But for now,
-the [Benevolent Dictator approach](http://www.catb.org/~esr/writings/cathedral-bazaar/homesteading/ar01s16.html) helps us move forward with speed and intention. If we ever forget the
-“benevolent” part, please: fork us.
+Note that just making many PRs does not immediately imply that you will become a maintainer. We will be looking
+at sustained high-quality contributions over a period of time, as well as good teamwork and adherence to our [Code of Conduct](./CODE_OF_CONDUCT.md).

CONTRIBUTING.md

@@ -13,33 +13,29 @@ To understand the codebase, please refer to the README in each module:
 
 ## Setting up Your Development Environment
 
-We have a separate doc [Development.md](https://github.com/OpenHands/OpenHands/blob/main/Development.md) that tells
-you how to set up a development workflow.
+We have a separate doc [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) that tells you how to set up a development workflow.
 
 ## How Can I Contribute?
 
 There are many ways that you can contribute:
 
-1. **Download and use** OpenHands, and send [issues](https://github.com/OpenHands/OpenHands/issues) when you encounter something that isn't working or a feature that you'd like to see.
-2. **Send feedback** after each session by [clicking the thumbs-up thumbs-down buttons](https://docs.openhands.dev/usage/feedback), so we can see where things are working and failing, and also build an open dataset for training code agents.
-3. **Improve the Codebase** by sending [PRs](#sending-pull-requests-to-openhands) (see details below). In particular, we have some [good first issues](https://github.com/OpenHands/OpenHands/labels/good%20first%20issue) that may be ones to start on.
+1. **Download and use** OpenHands, and send [issues](https://github.com/All-Hands-AI/OpenHands/issues) when you encounter something that isn't working or a feature that you'd like to see.
+2. **Send feedback** after each session by [clicking the thumbs-up thumbs-down buttons](https://docs.all-hands.dev/modules/usage/feedback), so we can see where things are working and failing, and also build an open dataset for training code agents.
+3. **Improve the Codebase** by sending [PRs](#sending-pull-requests-to-openhands) (see details below). In particular, we have some [good first issues](https://github.com/All-Hands-AI/OpenHands/labels/good%20first%20issue) that may be ones to start on.
 
 ## What Can I Build?
-
 Here are a few ways you can help improve the codebase.
 
 #### UI/UX
-
 We're always looking to improve the look and feel of the application. If you've got a small fix
 for something that's bugging you, feel free to open up a PR that changes the [`./frontend`](./frontend) directory.
 
 If you're looking to make a bigger change, add a new UI element, or significantly alter the style
-of the application, please open an issue first, or better, join the #dev-ui-ux channel in our Slack
+of the application, please open an issue first, or better, join the #frontend channel in our Slack
 to gather consensus from our design team first.
 
 #### Improving the agent
-
-Our main agent is the CodeAct agent. You can [see its prompts here](https://github.com/OpenHands/OpenHands/tree/main/openhands/agenthub/codeact_agent).
+Our main agent is the CodeAct agent. You can [see its prompts here](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/agenthub/codeact_agent).
 
 Changes to these prompts, and to the underlying behavior in Python, can have a huge impact on user experience.
 You can try modifying the prompts to see how they change the behavior of the agent as you use the app
@@ -50,24 +46,19 @@ We use the [SWE-bench](https://www.swebench.com/) benchmark to test our agent. Y
 channel in Slack to learn more.
 
 #### Adding a new agent
-
 You may want to experiment with building new types of agents. You can add an agent to [`openhands/agenthub`](./openhands/agenthub)
 to help expand the capabilities of OpenHands.
 
 #### Adding a new runtime
-
 The agent needs a place to run code and commands. When you run OpenHands on your laptop, it uses a Docker container
 to do this by default. But there are other ways of creating a sandbox for the agent.
 
 If you work for a company that provides a cloud-based runtime, you could help us add support for that runtime
-by implementing the [interface specified here](https://github.com/OpenHands/OpenHands/blob/main/openhands/runtime/base.py).
+by implementing the [interface specified here](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/base.py).
 
 #### Testing
-
-When you write code, it is also good to write tests. Please navigate to the [`./tests`](./tests) folder to see existing
-test suites. At the moment, we have these kinds of tests: [`unit`](./tests/unit), [`runtime`](./tests/runtime), and [`end-to-end (e2e)`](./tests/e2e).
-Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure
-quality of the project.
+When you write code, it is also good to write tests. Please navigate to the [`./tests`](./tests) folder to see existing test suites.
+At the moment, we have two kinds of tests: [`unit`](./tests/unit) and [`integration`](./evaluation/integration_tests). Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
 
 ## Sending Pull Requests to OpenHands
 
@@ -75,8 +66,7 @@ You'll need to fork our repository to send us a Pull Request. You can learn more
 about how to fork a GitHub repo and open a PR with your changes in [this article](https://medium.com/swlh/forks-and-pull-requests-how-to-contribute-to-github-repos-8843fac34ce8).
 
 ### Pull Request title
-
-As described [here](https://github.com/commitizen/conventional-commit-types/blob/master/index.json), ideally a valid PR title should begin with one of the following prefixes:
+As described [here](https://github.com/commitizen/conventional-commit-types/blob/master/index.json), a valid PR title should begin with one of the following prefixes:
 
 - `feat`: A new feature
 - `fix`: A bug fix
@@ -94,10 +84,9 @@ For example, a PR title could be:
 - `refactor: modify package path`
 - `feat(frontend): xxxx`, where `(frontend)` means that this PR mainly focuses on the frontend component.
 
-You may also check out previous PRs in the [PR list](https://github.com/OpenHands/OpenHands/pulls).
+You may also check out previous PRs in the [PR list](https://github.com/All-Hands-AI/OpenHands/pulls).
 
 ### Pull Request description
-
 - If your PR is small (such as a typo fix), you can go brief.
 - If it contains a lot of changes, it's better to write more details.
 
@@ -108,9 +97,7 @@ please include a short message that we can add to our changelog.
 
 ### Opening Issues
 
-If you notice any bugs or have any feature requests please open them via the [issues page](https://github.com/OpenHands/OpenHands/issues). We will triage
-based on how critical the bug is or how potentially useful the improvement is, discuss, and implement the ones that
-the community has interest/effort for.
+If you notice any bugs or have any feature requests please open them via the [issues page](https://github.com/All-Hands-AI/OpenHands/issues). We will triage based on how critical the bug is or how potentially useful the improvement is, discuss, and implement the ones that the community has interest/effort for.
 
 Further, if you see an issue you like, please leave a "thumbs-up" or a comment, which will help us prioritize.
 
@@ -121,13 +108,11 @@ We're generally happy to consider all pull requests with the evaluation process
 #### For Small Improvements
 
 Small improvements with few downsides are typically reviewed and approved quickly.
-One thing to check when making changes is to ensure that all continuous integration tests pass, which you can check
-before getting a review.
+One thing to check when making changes is to ensure that all continuous integration tests pass, which you can check before getting a review.
 
 #### For Core Agent Changes
 
-We need to be more careful with changes to the core agent, as it is imperative to maintain high quality. These PRs are
-evaluated based on three key metrics:
+We need to be more careful with changes to the core agent, as it is imperative to maintain high quality. These PRs are evaluated based on three key metrics:
 
 1. **Accuracy**
 2. **Efficiency**

CREDITS.md

@@ -2,13 +2,11 @@
 
 ## Contributors
 
-We would like to thank all the [contributors](https://github.com/OpenHands/OpenHands/graphs/contributors) who have
-helped make OpenHands possible. We greatly appreciate your dedication and hard work.
+We would like to thank all the [contributors](https://github.com/All-Hands-AI/OpenHands/graphs/contributors) who have helped make OpenHands possible. We greatly appreciate your dedication and hard work.
 
 ## Open Source Projects
 
-OpenHands includes and adapts the following open source projects. We are grateful for their contributions to the
-open source community:
+OpenHands includes and adapts the following open source projects. We are grateful for their contributions to the open source community:
 
 #### [SWE Agent](https://github.com/princeton-nlp/swe-agent)
    - License: MIT License
@@ -16,14 +14,14 @@ open source community:
 
 #### [Aider](https://github.com/paul-gauthier/aider)
    - License: Apache License 2.0
-   - Description: AI pair programming tool. OpenHands has adapted and integrated its linter module for code-related tasks in [`agentskills utilities`](https://github.com/OpenHands/OpenHands/tree/main/openhands/runtime/plugins/agent_skills/utils/aider)
+   - Description: AI pair programming tool. OpenHands has adapted and integrated its linter module for code-related tasks in [`agentskills utilities`](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/runtime/plugins/agent_skills/utils/aider)
 
 #### [BrowserGym](https://github.com/ServiceNow/BrowserGym)
    - License: Apache License 2.0
    - Description: Adapted in implementing the browsing agent
 
-### Reference Implementations for Evaluation Benchmarks
 
+### Reference Implementations for Evaluation Benchmarks
 OpenHands integrates code of the reference implementations for the following agent evaluation benchmarks:
 
 #### [HumanEval](https://github.com/openai/human-eval)
@@ -54,44 +52,28 @@ OpenHands integrates code of the reference implementations for the following age
 #### [ProntoQA](https://github.com/asaparov/prontoqa)
    - License: Apache License 2.0
 
+
 ## Open Source licenses
 
 ### MIT License
 
-Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated
-documentation files (the "Software"), to deal in the Software without restriction, including without limitation the
-rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit
-persons to whom the Software is furnished to do so, subject to the following conditions:
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
 
-The above copyright notice and this permission notice shall be included in all copies or substantial portions of the
-Software.
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
 
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO
-THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS
-OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
-OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 ### BSD 3-Clause License
 
-Redistribution and use in source and binary forms, with or without modification, are permitted provided that the
-following conditions are met:
+Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
 
-1. Redistributions of source code must retain the above copyright notice, this list of conditions and the following
-   disclaimer.
+1. Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
 
-2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following
-   disclaimer in the documentation and/or other materials provided with the distribution.
+2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
 
-3. Neither the name of the copyright holder nor the names of its contributors may be used to endorse or promote
-   products derived from this software without specific prior written permission.
+3. Neither the name of the copyright holder nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
 
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
-INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
-SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
-WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 ### Apache License 2.0
 
@@ -286,6 +268,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
    Copyright [yyyy] [name of copyright owner]
 
+
+
 ### Non-Open Source Reference Implementations:
 
 #### [MultiPL-E](https://github.com/nuprl/MultiPL-E)

Development.md

@@ -1,41 +1,23 @@
 # Development Guide
-
 This guide is for people working on OpenHands and editing the source code.
-If you wish to contribute your changes, check out the
-[CONTRIBUTING.md](https://github.com/OpenHands/OpenHands/blob/main/CONTRIBUTING.md)
-on how to clone and setup the project initially before moving on. Otherwise,
-you can clone the OpenHands project directly.
+If you wish to contribute your changes, check out the [CONTRIBUTING.md](https://github.com/All-Hands-AI/OpenHands/blob/main/CONTRIBUTING.md) on how to clone and setup the project initially before moving on.
+Otherwise, you can clone the OpenHands project directly.
 
 ## Start the Server for Development
-
 ### 1. Requirements
-
-- Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install) [Ubuntu >= 22.04]
-- [Docker](https://docs.docker.com/engine/install/) (For those on MacOS, make sure to allow the default Docker socket to be used from advanced settings!)
-- [Python](https://www.python.org/downloads/) = 3.12
-- [NodeJS](https://nodejs.org/en/download/package-manager) >= 22.x
-- [Poetry](https://python-poetry.org/docs/#installing-with-the-official-installer) >= 1.8
-- OS-specific dependencies:
-  - Ubuntu: build-essential => `sudo apt-get install build-essential python3.12-dev`
+* Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)  [Ubuntu >= 22.04]
+* [Docker](https://docs.docker.com/engine/install/) (For those on MacOS, make sure to allow the default Docker socket to be used from advanced settings!)
+* [Python](https://www.python.org/downloads/) = 3.12
+* [NodeJS](https://nodejs.org/en/download/package-manager) >= 20.x
+* [Poetry](https://python-poetry.org/docs/#installing-with-the-official-installer) >= 1.8
+* OS-specific dependencies:
+  - Ubuntu: build-essential => `sudo apt-get install build-essential`
   - WSL: netcat => `sudo apt-get install netcat`
 
 Make sure you have all these dependencies installed before moving on to `make build`.
 
-#### Dev container
-
-There is a [dev container](https://containers.dev/) available which provides a
-pre-configured environment with all the necessary dependencies installed if you
-are using a [supported editor or tool](https://containers.dev/supporting). For
-example, if you are using Visual Studio Code (VS Code) with the
-[Dev Containers](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers)
-extension installed, you can open the project in a dev container by using the
-_Dev Container: Reopen in Container_ command from the Command Palette
-(Ctrl+Shift+P).
-
 #### Develop without sudo access
-
-If you want to develop without system admin/sudo access to upgrade/install `Python` and/or `NodeJS`, you can use
-`conda` or `mamba` to manage the packages for you:
+If you want to develop without system admin/sudo access to upgrade/install `Python` and/or `NodeJs`, you can use `conda` or `mamba` to manage the packages for you:
 
 ```bash
 # Download and install Mamba (a faster version of conda)
@@ -49,102 +31,61 @@ mamba install conda-forge::poetry
 ```
 
 ### 2. Build and Setup The Environment
-
-Begin by building the project which includes setting up the environment and installing dependencies. This step ensures
-that OpenHands is ready to run on your system:
+Begin by building the project which includes setting up the environment and installing dependencies. This step ensures that OpenHands is ready to run on your system:
 
 ```bash
 make build
 ```
 
 ### 3. Configuring the Language Model
-
 OpenHands supports a diverse array of Language Models (LMs) through the powerful [litellm](https://docs.litellm.ai) library.
+By default, we've chosen Claude Sonnet 3.5 as our go-to model, but the world is your oyster! You can unleash the
+potential of any other LM that piques your interest.
 
 To configure the LM of your choice, run:
 
-```bash
-make setup-config
-```
+   ```bash
+   make setup-config
+   ```
 
-This command will prompt you to enter the LLM API key, model name, and other variables ensuring that OpenHands is
-tailored to your specific needs. Note that the model name will apply only when you run headless. If you use the UI,
-please set the model in the UI.
+   This command will prompt you to enter the LLM API key, model name, and other variables ensuring that OpenHands is tailored to your specific needs. Note that the model name will apply only when you run headless. If you use the UI, please set the model in the UI.
 
-Note: If you have previously run OpenHands using the docker command, you may have already set some environment
-variables in your terminal. The final configurations are set from highest to lowest priority:
-Environment variables > config.toml variables > default variables
+   Note: If you have previously run OpenHands using the docker command, you may have already set some environmental variables in your terminal. The final configurations are set from highest to lowest priority:
+   Environment variables > config.toml variables > default variables
 
 **Note on Alternative Models:**
-See [our documentation](https://docs.openhands.dev/usage/llms) for recommended models.
+See [our documentation](https://docs.all-hands.dev/modules/usage/llms) for recommended models.
 
 ### 4. Running the application
-
 #### Option A: Run the Full Application
-
 Once the setup is complete, this command starts both the backend and frontend servers, allowing you to interact with OpenHands:
-
 ```bash
 make run
 ```
 
 #### Option B: Individual Server Startup
+- **Start the Backend Server:** If you prefer, you can start the backend server independently to focus on backend-related tasks or configurations.
+    ```bash
+    make start-backend
+    ```
 
-- **Start the Backend Server:** If you prefer, you can start the backend server independently to focus on
-  backend-related tasks or configurations.
-
-  ```bash
-  make start-backend
-  ```
-
-- **Start the Frontend Server:** Similarly, you can start the frontend server on its own to work on frontend-related
-  components or interface enhancements.
-  ```bash
-  make start-frontend
-  ```
-
-### 5. Running OpenHands with OpenHands
-
-You can use OpenHands to develop and improve OpenHands itself! This is a powerful way to leverage AI assistance for contributing to the project.
-
-#### Quick Start
-
-1. **Build and run OpenHands:**
-
-   ```bash
-   export INSTALL_DOCKER=0
-   export RUNTIME=local
-   make build && make run
-   ```
-
-2. **Access the interface:**
-
-   - Local development: http://localhost:3001
-   - Remote/cloud environments: Use the appropriate external URL
-
-3. **Configure for external access (if needed):**
-   ```bash
-   # For external access (e.g., cloud environments)
-   make run FRONTEND_PORT=12000 FRONTEND_HOST=0.0.0.0 BACKEND_HOST=0.0.0.0
-   ```
+- **Start the Frontend Server:** Similarly, you can start the frontend server on its own to work on frontend-related components or interface enhancements.
+    ```bash
+    make start-frontend
+    ```
 
 ### 6. LLM Debugging
-
 If you encounter any issues with the Language Model (LM) or you're simply curious, export DEBUG=1 in the environment and restart the backend.
 OpenHands will log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
 
 ### 7. Help
-
 Need help or info on available targets and commands? Use the help command for all the guidance you need with OpenHands.
-
 ```bash
 make help
-```
+ ```
 
 ### 8. Testing
-
 To run tests, refer to the following:
-
 #### Unit tests
 
 ```bash
@@ -152,16 +93,14 @@ poetry run pytest ./tests/unit/test_*.py
 ```
 
 ### 9. Add or update dependency
-
 1. Add your dependency in `pyproject.toml` or use `poetry add xxx`.
 2. Update the poetry.lock file via `poetry lock --no-update`.
 
-### 10. Use existing Docker image
+### 9. Use existing Docker image
+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.
 
-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/openhands/runtime:1.2-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.21-nikolaik`
 
 ## Develop inside Docker container
 
@@ -187,20 +126,3 @@ cd ./containers/dev
 ```
 
 You do need [Docker](https://docs.docker.com/engine/install/) installed on your host though.
-
-## Key Documentation Resources
-
-Here's a guide to the important documentation files in the repository:
-
-- [/README.md](./README.md): Main project overview, features, and basic setup instructions
-- [/Development.md](./Development.md) (this file): Comprehensive guide for developers working on OpenHands
-- [/CONTRIBUTING.md](./CONTRIBUTING.md): Guidelines for contributing to the project, including code style and PR process
-- [DOC_STYLE_GUIDE.md](https://github.com/OpenHands/docs/blob/main/openhands/DOC_STYLE_GUIDE.md): Standards for writing and maintaining project documentation
-- [/openhands/README.md](./openhands/README.md): Details about the backend Python implementation
-- [/frontend/README.md](./frontend/README.md): Frontend React application setup and development guide
-- [/containers/README.md](./containers/README.md): Information about Docker containers and deployment
-- [/tests/unit/README.md](./tests/unit/README.md): Guide to writing and running unit tests
-- [/evaluation/README.md](./evaluation/README.md): Documentation for the evaluation framework and benchmarks
-- [/skills/README.md](./skills/README.md): Information about the skills architecture and implementation
-- [/openhands/server/README.md](./openhands/server/README.md): Server implementation details and API documentation
-- [/openhands/runtime/README.md](./openhands/runtime/README.md): Documentation for the runtime environment and execution model

ISSUE_TRIAGE.md

@@ -2,26 +2,24 @@
 These are the procedures and guidelines on how issues are triaged in this repo by the maintainers.
 
 ## General
-* All issues must be tagged with **enhancement**, **bug** or **troubleshooting/help**.
-* Issues may be tagged with what it relates to (**llm**, **app tab**, **UI/UX**, etc.).
+* Most issues must be tagged with **enhancement** or **bug**.
+* Issues may be tagged with what it relates to (**backend**, **frontend**, **agent quality**, etc.).
 
 ## Severity
-* **High**: High visibility issues or affecting many users.
+* **Low**: Minor issues or affecting single user.
+* **Medium**: Affecting multiple users.
 * **Critical**: Affecting all users or potential security issues.
 
+## Effort
+* Issues may be estimated with effort required (**small effort**, **medium effort**, **large effort**).
+
 ## Difficulty
-* Issues good for newcomers may be tagged with **good first issue**.
+* Issues with low implementation difficulty may be tagged with **good first issue**.
 
 ## Not Enough Information
 * User is asked to provide more information (logs, how to reproduce, etc.) when the issue is not clear.
-* If an issue is unclear and the author does not provide more information or respond to a request,
-the issue may be closed as **not planned** (Usually after a week).
+* If an issue is unclear and the author does not provide more information or respond to a request, the issue may be closed as **not planned** (Usually after a week).
 
 ## Multiple Requests/Fixes in One Issue
 * These issues will be narrowed down to one request/fix so the issue is more easily tracked and fixed.
 * Issues may be broken down into multiple issues if required.
-
-## Stale and Auto Closures
-* In order to keep a maintainable backlog, issues that have no activity within 40 days are automatically marked as **Stale**.
-* If issues marked as **Stale** continue to have no activity for 10 more days, they will automatically be closed as not planned.
-* Issues may be reopened by maintainers if deemed important.

LICENSE

@@ -1,12 +1,7 @@
-Portions of this software are licensed as follows:
-* All content that resides under the enterprise/ directory is licensed under the license defined in "enterprise/LICENSE".
-* Content outside of the above mentioned directories or restrictions above is available under the MIT license as defined below.
-
+The MIT License (MIT)
 =====================
 
-The MIT License (MIT)
-
-Copyright © 2025
+Copyright © 2023
 
 Permission is hereby granted, free of charge, to any person
 obtaining a copy of this software and associated documentation

Makefile

@@ -1,18 +1,16 @@
-SHELL=/usr/bin/env bash
+SHELL=/bin/bash
 # Makefile for OpenHands project
 
 # Variables
 BACKEND_HOST ?= "127.0.0.1"
-BACKEND_PORT ?= 3000
+BACKEND_PORT = 3000
 BACKEND_HOST_PORT = "$(BACKEND_HOST):$(BACKEND_PORT)"
-FRONTEND_HOST ?= "127.0.0.1"
-FRONTEND_PORT ?= 3001
+FRONTEND_PORT = 3001
 DEFAULT_WORKSPACE_DIR = "./workspace"
 DEFAULT_MODEL = "gpt-4o"
 CONFIG_FILE = config.toml
 PRE_COMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
 PYTHON_VERSION = 3.12
-KIND_CLUSTER_NAME = "local-hands"
 
 # ANSI color codes
 GREEN=$(shell tput -Txterm setaf 2)
@@ -41,7 +39,6 @@ ifeq ($(INSTALL_DOCKER),)
 	@$(MAKE) -s check-docker
 endif
 	@$(MAKE) -s check-poetry
-	@$(MAKE) -s check-tmux
 	@echo "$(GREEN)Dependencies checked successfully.$(RESET)"
 
 check-system:
@@ -84,10 +81,10 @@ check-nodejs:
 	@if command -v node > /dev/null; then \
 		NODE_VERSION=$(shell node --version | sed -E 's/v//g'); \
 		IFS='.' read -r -a NODE_VERSION_ARRAY <<< "$$NODE_VERSION"; \
-		if [ "$${NODE_VERSION_ARRAY[0]}" -ge 22 ]; then \
+		if [ "$${NODE_VERSION_ARRAY[0]}" -ge 20 ]; then \
 			echo "$(BLUE)Node.js $$NODE_VERSION is already installed.$(RESET)"; \
 		else \
-			echo "$(RED)Node.js 22.x or later is required. Please install Node.js 22.x or later to continue.$(RESET)"; \
+			echo "$(RED)Node.js 20.x or later is required. Please install Node.js 20.x or later to continue.$(RESET)"; \
 			exit 1; \
 		fi; \
 	else \
@@ -104,18 +101,6 @@ check-docker:
 		exit 1; \
 	fi
 
-check-tmux:
-	@echo "$(YELLOW)Checking tmux installation...$(RESET)"
-	@if command -v tmux > /dev/null; then \
-		echo "$(BLUE)$(shell tmux -V) is already installed.$(RESET)"; \
-	else \
-		echo "$(YELLOW)╔════════════════════════════════════════════════════════════════════════════╗$(RESET)"; \
-		echo "$(YELLOW)║ OPTIONAL: tmux is not installed.                                          ║$(RESET)"; \
-		echo "$(YELLOW)║ Some advanced terminal features may not work without tmux.                ║$(RESET)"; \
-		echo "$(YELLOW)║ You can install it if needed, but it's not required for development.      ║$(RESET)"; \
-		echo "$(YELLOW)╚════════════════════════════════════════════════════════════════════════════╝$(RESET)"; \
-	fi
-
 check-poetry:
 	@echo "$(YELLOW)Checking Poetry installation...$(RESET)"
 	@if command -v poetry > /dev/null; then \
@@ -148,33 +133,24 @@ install-python-dependencies:
 		export HNSWLIB_NO_NATIVE=1; \
 		poetry run pip install chroma-hnswlib; \
 	fi
-	@if [ -n "${POETRY_GROUP}" ]; then \
-		echo "Installing only POETRY_GROUP=${POETRY_GROUP}"; \
-		poetry install --only $${POETRY_GROUP}; \
+	@poetry install --without llama-index
+	@if [ -f "/etc/manjaro-release" ]; then \
+		echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
+		poetry run pip install playwright; \
+		poetry run playwright install chromium; \
 	else \
-		poetry install --with dev,test,runtime; \
-	fi
-	@if [ "${INSTALL_PLAYWRIGHT}" != "false" ] && [ "${INSTALL_PLAYWRIGHT}" != "0" ]; then \
-		if [ -f "/etc/manjaro-release" ]; then \
-			echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
-			poetry run pip install playwright; \
-			poetry run playwright install chromium; \
+		if [ ! -f cache/playwright_chromium_is_installed.txt ]; then \
+			echo "Running playwright install --with-deps chromium..."; \
+			poetry run playwright install --with-deps chromium; \
+			mkdir -p cache; \
+			touch cache/playwright_chromium_is_installed.txt; \
 		else \
-			if [ ! -f cache/playwright_chromium_is_installed.txt ]; then \
-				echo "Running playwright install --with-deps chromium..."; \
-				poetry run playwright install --with-deps chromium; \
-				mkdir -p cache; \
-				touch cache/playwright_chromium_is_installed.txt; \
-			else \
-				echo "Setup already done. Skipping playwright installation."; \
-			fi \
+			echo "Setup already done. Skipping playwright installation."; \
 		fi \
-	else \
-		echo "Skipping Playwright installation (INSTALL_PLAYWRIGHT=${INSTALL_PLAYWRIGHT})."; \
 	fi
 	@echo "$(GREEN)Python dependencies installed successfully.$(RESET)"
 
-install-frontend-dependencies: check-npm check-nodejs
+install-frontend-dependencies:
 	@echo "$(YELLOW)Setting up frontend environment...$(RESET)"
 	@echo "$(YELLOW)Detect Node.js version...$(RESET)"
 	@cd frontend && node ./scripts/detect-node-version.js
@@ -182,17 +158,17 @@ install-frontend-dependencies: check-npm check-nodejs
 	@cd frontend && npm install
 	@echo "$(GREEN)Frontend dependencies installed successfully.$(RESET)"
 
-install-pre-commit-hooks: check-python check-poetry install-python-dependencies
+install-pre-commit-hooks:
 	@echo "$(YELLOW)Installing pre-commit hooks...$(RESET)"
 	@git config --unset-all core.hooksPath || true
 	@poetry run pre-commit install --config $(PRE_COMMIT_CONFIG_PATH)
 	@echo "$(GREEN)Pre-commit hooks installed successfully.$(RESET)"
 
-lint-backend: install-pre-commit-hooks
+lint-backend:
 	@echo "$(YELLOW)Running linters...$(RESET)"
-	@poetry run pre-commit run --all-files --show-diff-on-failure --config $(PRE_COMMIT_CONFIG_PATH)
+	@poetry run pre-commit run --files openhands/**/* agenthub/**/* evaluation/**/* --show-diff-on-failure --config $(PRE_COMMIT_CONFIG_PATH)
 
-lint-frontend: install-frontend-dependencies
+lint-frontend:
 	@echo "$(YELLOW)Running linters for frontend...$(RESET)"
 	@cd frontend && npm run lint
 
@@ -200,40 +176,6 @@ lint:
 	@$(MAKE) -s lint-frontend
 	@$(MAKE) -s lint-backend
 
-kind:
-	@echo "$(YELLOW)Checking if kind is installed...$(RESET)"
-	@if ! command -v kind > /dev/null; then \
-		echo "$(RED)kind is not installed. Please install kind with `brew install kind` to continue$(RESET)"; \
-		exit 1; \
-	else \
-		echo "$(BLUE)kind $(shell kind version) is already installed.$(RESET)"; \
-	fi
-	@echo "$(YELLOW)Checking if kind cluster '$(KIND_CLUSTER_NAME)' already exists...$(RESET)"
-	@if kind get clusters | grep -q "^$(KIND_CLUSTER_NAME)$$"; then \
-		echo "$(BLUE)Kind cluster '$(KIND_CLUSTER_NAME)' already exists.$(RESET)"; \
-		kubectl config use-context kind-$(KIND_CLUSTER_NAME); \
-	else \
-		echo "$(YELLOW)Creating kind cluster '$(KIND_CLUSTER_NAME)'...$(RESET)"; \
-		kind create cluster --name $(KIND_CLUSTER_NAME) --config kind/cluster.yaml; \
-	fi
-	@echo "$(YELLOW)Checking if mirrord is installed...$(RESET)"
-	@if ! command -v mirrord > /dev/null; then \
-		echo "$(RED)mirrord is not installed. Please install mirrord with `brew install metalbear-co/mirrord/mirrord` to continue$(RESET)"; \
-		exit 1; \
-	else \
-		echo "$(BLUE)mirrord $(shell mirrord --version) is already installed.$(RESET)"; \
-	fi
-	@echo "$(YELLOW)Installing k8s mirrord resources...$(RESET)"
-	@kubectl apply -f kind/manifests
-	@echo "$(GREEN)Mirrord resources installed successfully.$(RESET)"
-	@echo "$(YELLOW)Waiting for Mirrord pod to be ready.$(RESET)"
-	@sleep 5
-	@kubectl wait --for=condition=Available deployment/ubuntu-dev
-	@echo "$(YELLOW)Waiting for Nginx to be ready.$(RESET)"
-	@kubectl -n ingress-nginx wait --for=condition=Available deployment/ingress-nginx-controller
-	@echo "$(YELLOW)Running make run inside of mirrord.$(RESET)"
-	@mirrord exec --target deployment/ubuntu-dev -- make run
-
 test-frontend:
 	@echo "$(YELLOW)Running tests for frontend...$(RESET)"
 	@cd frontend && npm run test
@@ -243,7 +185,7 @@ test:
 
 build-frontend:
 	@echo "$(YELLOW)Building frontend...$(RESET)"
-	@cd frontend && npm run prepare && npm run build
+	@cd frontend && npm run build
 
 # Start backend
 start-backend:
@@ -253,14 +195,7 @@ start-backend:
 # Start frontend
 start-frontend:
 	@echo "$(YELLOW)Starting frontend...$(RESET)"
-	@cd frontend && \
-	if grep -qi microsoft /proc/version 2>/dev/null; then \
-		echo "Detected WSL environment. Using 'dev_wsl'"; \
-		SCRIPT=dev_wsl; \
-	else \
-		SCRIPT=dev; \
-	fi; \
-	VITE_BACKEND_HOST=$(BACKEND_HOST_PORT) VITE_FRONTEND_PORT=$(FRONTEND_PORT) npm run $$SCRIPT -- --port $(FRONTEND_PORT) --host $(BACKEND_HOST)
+	@cd frontend && VITE_BACKEND_HOST=$(BACKEND_HOST_PORT) VITE_FRONTEND_PORT=$(FRONTEND_PORT) npm run dev -- --port $(FRONTEND_PORT) --host $(BACKEND_HOST)
 
 # Common setup for running the app (non-callable)
 _run_setup:
@@ -296,6 +231,12 @@ docker-run:
 		docker compose up $(OPTIONS); \
 	fi
 
+# Run the app (WSL mode)
+run-wsl:
+	@echo "$(YELLOW)Running the app in WSL mode...$(RESET)"
+	@$(MAKE) -s _run_setup
+	@cd frontend && echo "$(BLUE)Starting frontend with npm (WSL mode)...$(RESET)" && npm run dev_wsl -- --port $(FRONTEND_PORT)
+	@echo "$(GREEN)Application started successfully in WSL mode.$(RESET)"
 
 # Setup config.toml
 setup-config:
@@ -324,15 +265,35 @@ setup-config-prompts:
 	@read -p "Enter your LLM base URL [mostly used for local LLMs, leave blank if not needed - example: http://localhost:5001/v1/]: " llm_base_url; \
 	 if [[ ! -z "$$llm_base_url" ]]; then echo "base_url=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; fi
 
-setup-config-basic:
-	@printf '%s\n' \
-	'[core]' \
-	'workspace_base="./workspace"' \
-	> config.toml
-	@echo "$(GREEN)config.toml created.$(RESET)"
+	@echo "Enter your LLM Embedding Model"; \
+		echo "Choices are:"; \
+		echo "  - openai"; \
+		echo "  - azureopenai"; \
+		echo "  - Embeddings available only with OllamaEmbedding:"; \
+		echo "    - llama2"; \
+		echo "    - mxbai-embed-large"; \
+		echo "    - nomic-embed-text"; \
+		echo "    - all-minilm"; \
+		echo "    - stable-code"; \
+		echo "    - bge-m3"; \
+		echo "    - bge-large"; \
+		echo "    - paraphrase-multilingual"; \
+		echo "    - snowflake-arctic-embed"; \
+		echo "  - Leave blank to default to 'BAAI/bge-small-en-v1.5' via huggingface"; \
+		read -p "> " llm_embedding_model; \
+		echo "embedding_model=\"$$llm_embedding_model\"" >> $(CONFIG_FILE).tmp; \
+		if [ "$$llm_embedding_model" = "llama2" ] || [ "$$llm_embedding_model" = "mxbai-embed-large" ] || [ "$$llm_embedding_model" = "nomic-embed-text" ] || [ "$$llm_embedding_model" = "all-minilm" ] || [ "$$llm_embedding_model" = "stable-code" ]; then \
+			read -p "Enter the local model URL for the embedding model (will set llm.embedding_base_url): " llm_embedding_base_url; \
+				echo "embedding_base_url=\"$$llm_embedding_base_url\"" >> $(CONFIG_FILE).tmp; \
+		elif [ "$$llm_embedding_model" = "azureopenai" ]; then \
+			read -p "Enter the Azure endpoint URL (will overwrite llm.base_url): " llm_base_url; \
+				echo "base_url=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
+			read -p "Enter the Azure LLM Embedding Deployment Name: " llm_embedding_deployment_name; \
+				echo "embedding_deployment_name=\"$$llm_embedding_deployment_name\"" >> $(CONFIG_FILE).tmp; \
+			read -p "Enter the Azure API Version: " llm_api_version; \
+				echo "api_version=\"$$llm_api_version\"" >> $(CONFIG_FILE).tmp; \
+		fi
 
-openhands-cloud-run:
-	@$(MAKE) run BACKEND_HOST="0.0.0.0" BACKEND_PORT="12000" FRONTEND_HOST="0.0.0.0" FRONTEND_PORT="12001"
 
 # Develop in container
 docker-dev:
@@ -367,5 +328,5 @@ help:
 	@echo "  $(GREEN)help$(RESET)                - Display this help message, providing information on available targets."
 
 # Phony targets
-.PHONY: build check-dependencies check-system check-python check-npm check-nodejs check-docker check-poetry install-python-dependencies install-frontend-dependencies install-pre-commit-hooks lint-backend lint-frontend lint test-frontend test build-frontend start-backend start-frontend _run_setup run run-wsl setup-config setup-config-prompts setup-config-basic openhands-cloud-run docker-dev docker-run clean help
-.PHONY: kind
+.PHONY: build check-dependencies check-python check-npm check-docker check-poetry install-python-dependencies install-frontend-dependencies install-pre-commit-hooks lint start-backend start-frontend run run-wsl setup-config setup-config-prompts help
+.PHONY: docker-dev docker-run

README.md

@@ -1,86 +1,137 @@
 <a name="readme-top"></a>
 
 <div align="center">
-  <img src="https://raw.githubusercontent.com/OpenHands/docs/main/openhands/static/img/logo.png" alt="Logo" width="200">
-  <h1 align="center" style="border-bottom: none">OpenHands: AI-Driven Development</h1>
+  <img src="./docs/static/img/logo.png" alt="Logo" width="200">
+  <h1 align="center">OpenHands: Code Less, Make More</h1>
 </div>
 
 
 <div align="center">
-  <a href="https://github.com/OpenHands/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/badge/LICENSE-MIT-20B2AA?style=for-the-badge" alt="MIT License"></a>
-  <a href="https://docs.google.com/spreadsheets/d/1wOUdFCMyY6Nt0AIqF705KN4JKOWgeI4wUGUP60krXXs/edit?gid=811504672#gid=811504672"><img src="https://img.shields.io/badge/SWEBench-77.6-00cc00?logoColor=FFE165&style=for-the-badge" alt="Benchmark Score"></a>
+  <a href="https://github.com/All-Hands-AI/OpenHands/graphs/contributors"><img src="https://img.shields.io/github/contributors/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="Contributors"></a>
+  <a href="https://github.com/All-Hands-AI/OpenHands/stargazers"><img src="https://img.shields.io/github/stars/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="Stargazers"></a>
+  <a href="https://codecov.io/github/All-Hands-AI/OpenHands?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/All-Hands-AI/OpenHands?style=for-the-badge&color=blue"></a>
+  <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/github/license/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="MIT License"></a>
   <br/>
-  <a href="https://docs.openhands.dev/sdk"><img src="https://img.shields.io/badge/Documentation-000?logo=googledocs&logoColor=FFE165&style=for-the-badge" alt="Check out the documentation"></a>
-  <a href="https://arxiv.org/abs/2511.03690"><img src="https://img.shields.io/badge/Paper-000?logoColor=FFE165&logo=arxiv&style=for-the-badge" alt="Tech Report"></a>
-
-
-  <!-- Keep these links. Translations will automatically update with the README. -->
-  <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=de">Deutsch</a> |
-  <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=es">Español</a> |
-  <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=fr">français</a> |
-  <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=ja">日本語</a> |
-  <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=ko">한국어</a> |
-  <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=pt">Português</a> |
-  <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=ru">Русский</a> |
-  <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=zh">中文</a>
-
+  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2ypg5jweb-d~6hObZDbXi_HEL8PDrbHg"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
+  <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
+  <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="Credits"></a>
+  <br/>
+  <a href="https://docs.all-hands.dev/modules/usage/getting-started"><img src="https://img.shields.io/badge/Documentation-000?logo=googledocs&logoColor=FFE165&style=for-the-badge" alt="Check out the documentation"></a>
+  <a href="https://arxiv.org/abs/2407.16741"><img src="https://img.shields.io/badge/Paper%20on%20Arxiv-000?logoColor=FFE165&logo=arxiv&style=for-the-badge" alt="Paper on Arxiv"></a>
+  <a href="https://huggingface.co/spaces/OpenHands/evaluation"><img src="https://img.shields.io/badge/Benchmark%20score-000?logoColor=FFE165&logo=huggingface&style=for-the-badge" alt="Evaluation Benchmark Score"></a>
+  <hr>
 </div>
 
-<hr>
+Welcome to OpenHands (formerly OpenDevin), a platform for software development agents powered by AI.
 
-🙌 Welcome to OpenHands, a [community](COMMUNITY.md) focused on AI-driven development. We’d love for you to [join us on Slack](https://dub.sh/openhands).
+OpenHands agents can do anything a human developer can: modify code, run commands, browse the web,
+call APIs, and yes—even copy code snippets from StackOverflow.
 
-There are a few ways to work with OpenHands:
+Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or jump to the [Quick Start](#-quick-start).
 
-### OpenHands Software Agent SDK
-The SDK is a composable Python library that contains all of our agentic tech. It's the engine that powers everything else below.
+> [!IMPORTANT]
+> Using OpenHands for work? We'd love to chat! Fill out
+> [this short form](https://docs.google.com/forms/d/e/1FAIpQLSet3VbGaz8z32gW9Wm-Grl4jpt5WgMXPgJ4EDPVmCETCBpJtQ/viewform)
+> to join our Design Partner program, where you'll get early access to commercial features and the opportunity to provide input on our product roadmap.
 
-Define agents in code, then run them locally, or scale to 1000s of agents in the cloud.
+![App screenshot](./docs/static/img/screenshot.png)
 
-[Check out the docs](https://docs.openhands.dev/sdk) or [view the source](https://github.com/OpenHands/software-agent-sdk/)
+## ⚡ Quick Start
 
-### OpenHands CLI
-The CLI is the easiest way to start using OpenHands. The experience will be familiar to anyone who has worked
-with e.g. Claude Code or Codex. You can power it with Claude, GPT, or any other LLM.
+The easiest way to run OpenHands is in Docker.
+See the [Running OpenHands](https://docs.all-hands.dev/modules/usage/installation) guide for
+system requirements and more information.
 
-[Check out the docs](https://docs.openhands.dev/openhands/usage/run-openhands/cli-mode) or [view the source](https://github.com/OpenHands/OpenHands-CLI)
+```bash
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.21-nikolaik
 
-### OpenHands Local GUI
-Use the Local GUI for running agents on your laptop. It comes with a REST API and a single-page React application.
-The experience will be familiar to anyone who has used Devin or Jules.
+docker run -it --rm --pull=always \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.21-nikolaik \
+    -e LOG_ALL_EVENTS=true \
+    -v /var/run/docker.sock:/var/run/docker.sock \
+    -v ~/.openhands-state:/.openhands-state \
+    -p 3000:3000 \
+    --add-host host.docker.internal:host-gateway \
+    --name openhands-app \
+    docker.all-hands.dev/all-hands-ai/openhands:0.21
+```
 
-[Check out the docs](https://docs.openhands.dev/openhands/usage/run-openhands/local-setup) or view the source in this repo.
+You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
 
-### OpenHands Cloud
-This is a deployment of OpenHands GUI, running on hosted infrastructure.
+Finally, you'll need a model provider and API key.
+[Anthropic's Claude 3.5 Sonnet](https://www.anthropic.com/api) (`anthropic/claude-3-5-sonnet-20241022`)
+works best, but you have [many options](https://docs.all-hands.dev/modules/usage/llms).
 
-You can try it with a free $10 credit by [signing in with your GitHub or GitLab account](https://app.all-hands.dev).
+---
 
-OpenHands Cloud comes with source-available features and integrations:
-- Integrations with Slack, Jira, and Linear
-- Multi-user support
-- RBAC and permissions
-- Collaboration features (e.g., conversation sharing)
+You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes#connecting-to-your-filesystem),
+run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
+interact with it via a [friendly CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode),
+or run it on tagged issues with [a github action](https://docs.all-hands.dev/modules/usage/how-to/github-action).
 
-### OpenHands Enterprise
-Large enterprises can work with us to self-host OpenHands Cloud in their own VPC, via Kubernetes.
-OpenHands Enterprise can also work with the CLI and SDK above.
+Visit [Running OpenHands](https://docs.all-hands.dev/modules/usage/installation) for more information and setup instructions.
 
-OpenHands Enterprise is source-available--you can see all the source code here in the enterprise/ directory,
-but you'll need to purchase a license if you want to run it for more than one month.
+> [!CAUTION]
+> OpenHands is meant to be run by a single user on their local workstation.
+> It is not appropriate for multi-tenant deployments where multiple users share the same instance. There is no built-in isolation or scalability.
+>
+> If you're interested in running OpenHands in a multi-tenant environment, please
+> [get in touch with us](https://docs.google.com/forms/d/e/1FAIpQLSet3VbGaz8z32gW9Wm-Grl4jpt5WgMXPgJ4EDPVmCETCBpJtQ/viewform)
+> for advanced deployment options.
 
-Enterprise contracts also come with extended support and access to our research team.
+If you want to modify the OpenHands source code, check out [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
 
-Learn more at [openhands.dev/enterprise](https://openhands.dev/enterprise)
+Having issues? The [Troubleshooting Guide](https://docs.all-hands.dev/modules/usage/troubleshooting) can help.
 
-### Everything Else
+## 📖 Documentation
 
-Check out our [Product Roadmap](https://github.com/orgs/openhands/projects/1), and feel free to
-[open up an issue](https://github.com/OpenHands/OpenHands/issues) if there's something you'd like to see!
+To learn more about the project, and for tips on using OpenHands,
+check out our [documentation](https://docs.all-hands.dev/modules/usage/getting-started).
 
-You might also be interested in our [evaluation infrastructure](https://github.com/OpenHands/benchmarks), our [chrome extension](https://github.com/OpenHands/openhands-chrome-extension/), or our [Theory-of-Mind module](https://github.com/OpenHands/ToM-SWE).
+There you'll find resources on how to use different LLM providers,
+troubleshooting resources, and advanced configuration options.
 
-All our work is available under the MIT license, except for the `enterprise/` directory in this repository (see the [enterprise license](enterprise/LICENSE) for details).
-The core `openhands` and `agent-server` Docker images are fully MIT-licensed as well.
+## 🤝 How to Join the Community
 
-If you need help with anything, or just want to chat, [come find us on Slack](https://dub.sh/openhands).
+OpenHands is a community-driven project, and we welcome contributions from everyone. We do most of our communication
+through Slack, so this is the best place to start, but we also are happy to have you contact us on Discord or Github:
+
+- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-2ypg5jweb-d~6hObZDbXi_HEL8PDrbHg) - Here we talk about research, architecture, and future development.
+- [Join our Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
+- [Read or post Github Issues](https://github.com/All-Hands-AI/OpenHands/issues) - Check out the issues we're working on, or add your own ideas.
+
+See more about the community in [COMMUNITY.md](./COMMUNITY.md) or find details on contributing in [CONTRIBUTING.md](./CONTRIBUTING.md).
+
+## 📈 Progress
+
+See the monthly OpenHands roadmap [here](https://github.com/orgs/All-Hands-AI/projects/1) (updated at the maintainer's meeting at the end of each month).
+
+<p align="center">
+  <a href="https://star-history.com/#All-Hands-AI/OpenHands&Date">
+    <img src="https://api.star-history.com/svg?repos=All-Hands-AI/OpenHands&type=Date" width="500" alt="Star History Chart">
+  </a>
+</p>
+
+## 📜 License
+
+Distributed under the MIT License. See [`LICENSE`](./LICENSE) for more information.
+
+## 🙏 Acknowledgements
+
+OpenHands is built by a large number of contributors, and every contribution is greatly appreciated! We also build upon other open source projects, and we are deeply thankful for their work.
+
+For a list of open source projects and licenses used in OpenHands, please see our [CREDITS.md](./CREDITS.md) file.
+
+## 📚 Cite
+
+```
+@misc{openhands,
+      title={{OpenHands: An Open Platform for AI Software Developers as Generalist Agents}},
+      author={Xingyao Wang and Boxuan Li and Yufan Song and Frank F. Xu and Xiangru Tang and Mingchen Zhuge and Jiayi Pan and Yueqi Song and Bowen Li and Jaskirat Singh and Hoang H. Tran and Fuqiang Li and Ren Ma and Mingzhang Zheng and Bill Qian and Yanjun Shao and Niklas Muennighoff and Yizhe Zhang and Binyuan Hui and Junyang Lin and Robert Brennan and Hao Peng and Heng Ji and Graham Neubig},
+      year={2024},
+      eprint={2407.16741},
+      archivePrefix={arXiv},
+      primaryClass={cs.SE},
+      url={https://arxiv.org/abs/2407.16741},
+}
+```

build.sh

@@ -1,4 +1,5 @@
-#!/usr/bin/env bash
+#!/bin/bash
 set -e
 
+cp pyproject.toml poetry.lock openhands
 poetry build -v

config.template.toml

@@ -10,28 +10,35 @@
 # General core configurations
 ##############################################################################
 [core]
-# API keys and configuration for core services
+# API key for E2B
+#e2b_api_key = ""
+
+# API key for Modal
+#modal_api_token_id = ""
+#modal_api_token_secret = ""
 
 # Base path for the workspace
-#workspace_base = "./workspace"
+workspace_base = "./workspace"
 
 # Cache directory path
 #cache_dir = "/tmp/cache"
 
+# Reasoning effort for o1 models (low, medium, high, or not set)
+#reasoning_effort = "medium"
+
 # Debugging enabled
 #debug = false
 
 # Disable color in terminal output
 #disable_color = false
 
+# Enable saving and restoring the session when run from CLI
+#enable_cli_session = false
+
 # Path to store trajectories, can be a folder or a file
 # If it's a folder, the session id will be used as the file name
 #save_trajectory_path="./trajectories"
 
-# Whether to save screenshots in the trajectory
-# The screenshots are encoded and can make trajectory json files very large
-#save_screenshots_in_trajectory = false
-
 # Path to replay a trajectory, must be a file path
 # If provided, trajectory will be loaded and replayed before the
 # agent responds to any user instruction
@@ -43,17 +50,17 @@
 # File store type
 #file_store = "memory"
 
+# List of allowed file extensions for uploads
+#file_uploads_allowed_extensions = [".*"]
+
 # Maximum file size for uploads, in megabytes
 #file_uploads_max_file_size_mb = 0
 
-# Enable the browser environment
-#enable_browser = true
-
 # Maximum budget per task, 0.0 means no limit
 #max_budget_per_task = 0.0
 
 # Maximum number of iterations
-#max_iterations = 500
+#max_iterations = 100
 
 # Path to mount the workspace in the sandbox
 #workspace_mount_path_in_sandbox = "/workspace"
@@ -82,17 +89,6 @@
 # List of allowed file extensions for uploads
 #file_uploads_allowed_extensions = [".*"]
 
-# Whether to enable the default LLM summarizing condenser when no condenser is specified in config
-# When true, a LLMSummarizingCondenserConfig will be used as the default condenser
-# When false, a NoOpCondenserConfig (no summarization) will be used
-#enable_default_condenser = true
-
-# Maximum number of concurrent conversations per user
-#max_concurrent_conversations = 3
-
-# Maximum age of conversations in seconds before they are automatically closed
-#conversation_max_age_seconds = 864000  # 10 days
-
 #################################### LLM #####################################
 # Configuration for LLM models (group name starts with 'llm')
 # use 'llm' for the default LLM config
@@ -108,7 +104,7 @@
 #aws_secret_access_key = ""
 
 # API key to use (For Headless / CLI only -  In Web this is overridden by Session Init)
-api_key = ""
+api_key = "your-api-key"
 
 # API base URL (For Headless / CLI only -  In Web this is overridden by Session Init)
 #base_url = ""
@@ -116,9 +112,6 @@ api_key = ""
 # API version
 #api_version = ""
 
-# Reasoning effort for OpenAI o-series models (low, medium, high, or not set)
-#reasoning_effort = "medium"
-
 # Cost per input token
 #input_cost_per_token = 0.0
 
@@ -128,6 +121,15 @@ api_key = ""
 # Custom LLM provider
 #custom_llm_provider = ""
 
+# Embedding API base URL
+#embedding_base_url = ""
+
+# Embedding deployment name
+#embedding_deployment_name = ""
+
+# Embedding model to use
+embedding_model = "local"
+
 # Maximum number of characters in an observation's content
 #max_message_chars = 10000
 
@@ -189,44 +191,13 @@ model = "gpt-4o"
 # Whether to use native tool calling if supported by the model. Can be true, false, or None by default, which chooses the model's default behavior based on the evaluation.
 # ATTENTION: Based on evaluation, enabling native function calling may lead to worse results
 # in some scenarios. Use with caution and consider testing with your specific use case.
-# https://github.com/OpenHands/OpenHands/pull/4711
+# https://github.com/All-Hands-AI/OpenHands/pull/4711
 #native_tool_calling = None
 
-
-# Safety settings for models that support them (e.g., Mistral AI, Gemini)
-# Example for Mistral AI:
-# safety_settings = [
-#   { "category" = "hate", "threshold" = "low" },
-#   { "category" = "harassment", "threshold" = "low" },
-#   { "category" = "sexual", "threshold" = "low" },
-#   { "category" = "dangerous", "threshold" = "low" }
-# ]
-#
-# Example for Gemini:
-# safety_settings = [
-#   { "category" = "HARM_CATEGORY_HARASSMENT", "threshold" = "BLOCK_NONE" },
-#   { "category" = "HARM_CATEGORY_HATE_SPEECH", "threshold" = "BLOCK_NONE" },
-#   { "category" = "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold" = "BLOCK_NONE" },
-#   { "category" = "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold" = "BLOCK_NONE" }
-# ]
-#safety_settings = []
-
-[llm.draft_editor]
-# The number of times llm_editor tries to fix an error when editing.
-correct_num = 5
-
 [llm.gpt4o-mini]
-api_key = ""
+api_key = "your-api-key"
 model = "gpt-4o"
 
-# Example routing LLM configuration for multimodal model routing
-# Uncomment and configure to enable model routing with a secondary model
-#[llm.secondary_model]
-#model = "kimi-k2"
-#api_key = ""
-#for_routing = true
-#max_input_tokens = 128000
-
 
 #################################### Agent ###################################
 # Configuration for agents (group name starts with 'agent')
@@ -236,28 +207,23 @@ model = "gpt-4o"
 ##############################################################################
 [agent]
 
-# Whether the browsing tool is enabled
-# Note: when this is set to true, enable_browser in the core config must also be true
-enable_browsing = true
+# whether the browsing tool is enabled
+codeact_enable_browsing = true
 
-# Whether the LLM draft editor is enabled
-enable_llm_editor = false
+# whether the LLM draft editor is enabled
+codeact_enable_llm_editor = false
 
-# Whether the standard editor tool (str_replace_editor) is enabled
-# Only has an effect if enable_llm_editor is False
-enable_editor = true
+# whether the IPython tool is enabled
+codeact_enable_jupyter = true
 
-# Whether the IPython tool is enabled
-enable_jupyter = true
+# Name of the micro agent to use for this agent
+#micro_agent_name = ""
 
-# Whether the command tool is enabled
-enable_cmd = true
+# Memory enabled
+#memory_enabled = false
 
-# Whether the think tool is enabled
-enable_think = true
-
-# Whether the finish tool is enabled
-enable_finish = true
+# Memory maximum threads
+#memory_max_threads = 3
 
 # LLM config group to use
 #llm_config = 'your-llm-config-group'
@@ -268,23 +234,11 @@ enable_finish = true
 # List of microagents to disable
 #disabled_microagents = []
 
-# Whether history should be truncated to continue the session when hitting LLM context
-# length limit
-enable_history_truncation = true
-
-# Whether the condensation request tool is enabled
-enable_condensation_request = false
-
 [agent.RepoExplorerAgent]
 # Example: use a cheaper model for RepoExplorerAgent to reduce cost, especially
 # useful when an agent doesn't demand high quality but uses a lot of tokens
 llm_config = 'gpt3'
 
-[agent.CustomAgent]
-# Example: use a custom agent from a different package
-# This will be automatically be registered as a new agent named "CustomAgent"
-classpath = "my_package.my_module.MyCustomAgent"
-
 #################################### Sandbox ###################################
 # Configuration for the sandbox
 ##############################################################################
@@ -301,7 +255,7 @@ classpath = "my_package.my_module.MyCustomAgent"
 # Use host network
 #use_host_network = false
 
-# Runtime extra build args
+# runtime extra build args
 #runtime_extra_build_args = ["--network=host", "--add-host=host.docker.internal:host-gateway"]
 
 # Enable auto linting after editing
@@ -319,49 +273,6 @@ classpath = "my_package.my_module.MyCustomAgent"
 # BrowserGym environment to use for evaluation
 #browsergym_eval_env = ""
 
-# Platform to use for building the runtime image (e.g., "linux/amd64")
-#platform = ""
-
-# Force rebuild of runtime image even if it exists
-#force_rebuild_runtime = false
-
-# Runtime container image to use (if not provided, will be built from base_container_image)
-#runtime_container_image = ""
-
-# Keep runtime alive after session ends
-#keep_runtime_alive = false
-
-# Pause closed runtimes instead of stopping them
-#pause_closed_runtimes = false
-
-# Delay in seconds before closing idle runtimes
-#close_delay = 300
-
-# Remove all containers when stopping the runtime
-#rm_all_containers = false
-
-# Enable GPU support in the runtime
-#enable_gpu = false
-
-# When there are multiple cards, you can specify the GPU by ID
-#cuda_visible_devices = ''
-
-# Additional Docker runtime kwargs
-#docker_runtime_kwargs = {}
-
-# Specific port to use for VSCode. If not set, a random port will be chosen.
-# Useful when deploying OpenHands in a remote machine where you need to expose a specific port.
-#vscode_port = 41234
-
-# Volume mounts in the format 'host_path:container_path[:mode]'
-# e.g. '/my/host/dir:/workspace:rw'
-# Multiple mounts can be specified using commas
-# e.g. '/path1:/workspace/path1,/path2:/workspace/path2:ro'
-
-# Configure volumes under the [sandbox] section:
-# [sandbox]
-# volumes = "/my/host/dir:/workspace:rw,/path2:/workspace/path2:ro"
-
 #################################### Security ###################################
 # Configuration for security features
 ##############################################################################
@@ -371,172 +282,9 @@ classpath = "my_package.my_module.MyCustomAgent"
 #confirmation_mode = false
 
 # The security analyzer to use (For Headless / CLI only -  In Web this is overridden by Session Init)
-# Available options: 'llm' (default), 'invariant'
-#security_analyzer = "llm"
-
-# Whether to enable security analyzer
-#enable_security_analyzer = true
-
-#################################### Condenser #################################
-# Condensers control how conversation history is managed and compressed when
-# the context grows too large. Each agent uses one condenser configuration.
-##############################################################################
-[condenser]
-# The type of condenser to use. Available options:
-# - "noop": No condensing, keeps full history (default)
-# - "observation_masking": Keeps full event structure but masks older observations
-# - "recent": Keeps only recent events and discards older ones
-# - "llm": Uses an LLM to summarize conversation history
-# - "amortized": Intelligently forgets older events while preserving important context
-# - "llm_attention": Uses an LLM to prioritize most relevant context
-type = "noop"
-
-# Examples for each condenser type (uncomment and modify as needed):
-
-# 1. NoOp Condenser - No additional settings needed
-#type = "noop"
-
-# 2. Observation Masking Condenser
-#type = "observation_masking"
-# Number of most-recent events where observations will not be masked
-#attention_window = 100
-
-# 3. Recent Events Condenser
-#type = "recent"
-# Number of initial events to always keep (typically includes task description)
-#keep_first = 1
-# Maximum number of events to keep in history
-#max_events = 100
-
-# 4. LLM Summarizing Condenser
-#type = "llm"
-# Reference to an LLM config to use for summarization
-#llm_config = "condenser"
-# Number of initial events to always keep (typically includes task description)
-#keep_first = 1
-# Maximum size of history before triggering summarization
-#max_size = 100
-
-# 5. Amortized Forgetting Condenser
-#type = "amortized"
-# Number of initial events to always keep (typically includes task description)
-#keep_first = 1
-# Maximum size of history before triggering forgetting
-#max_size = 100
-
-# 6. LLM Attention Condenser
-#type = "llm_attention"
-# Reference to an LLM config to use for attention scoring
-#llm_config = "condenser"
-# Number of initial events to always keep (typically includes task description)
-#keep_first = 1
-# Maximum size of history before triggering attention mechanism
-#max_size = 100
-
-# Example of a custom LLM configuration for condensers that require an LLM
-# If not provided, it falls back to the default LLM
-#[llm.condenser]
-#model = "gpt-4o"
-#temperature = 0.1
-#max_input_tokens = 1024
+#security_analyzer = ""
 
 #################################### Eval ####################################
 # Configuration for the evaluation, please refer to the specific evaluation
 # plugin for the available options
 ##############################################################################
-
-
-########################### Kubernetes #######################################
-# Kubernetes configuration when using the Kubernetes runtime
-##############################################################################
-[kubernetes]
-# The Kubernetes namespace to use for OpenHands resources
-#namespace = "default"
-
-# Domain for ingress resources
-#ingress_domain = "localhost"
-
-# Size of the persistent volume claim
-#pvc_storage_size = "2Gi"
-
-# Storage class for persistent volume claims
-#pvc_storage_class = "standard"
-
-# CPU request for runtime pods
-#resource_cpu_request = "1"
-
-# Memory request for runtime pods
-#resource_memory_request = "1Gi"
-
-# Memory limit for runtime pods
-#resource_memory_limit = "2Gi"
-
-# Optional name of image pull secret for private registries
-#image_pull_secret = ""
-
-# Optional name of TLS secret for ingress
-#ingress_tls_secret = ""
-
-# Optional node selector key for pod scheduling
-#node_selector_key = ""
-
-# Optional node selector value for pod scheduling
-#node_selector_val = ""
-
-# Optional YAML string defining pod tolerations
-#tolerations_yaml = ""
-
-# Run the runtime sandbox container in privileged mode for use with docker-in-docker
-#privileged = false
-
-#################################### MCP #####################################
-# Configuration for Model Context Protocol (MCP) servers
-# MCP allows OpenHands to communicate with external tool servers
-##############################################################################
-[mcp]
-# SSE servers - Server-Sent Events transport (legacy)
-#sse_servers = [
-#    # Basic SSE server with just a URL
-#    "http://localhost:8080/mcp/sse",
-#
-#    # SSE server with authentication
-#    {url = "https://api.example.com/mcp/sse", api_key = "your-api-key"}
-#]
-
-# SHTTP servers - Streamable HTTP transport (recommended)
-#shttp_servers = [
-#    # Basic SHTTP server with default 60s timeout
-#    "https://api.example.com/mcp/shttp",
-#
-#    # SHTTP server with custom timeout for long-running tools
-#    {
-#        url = "https://api.example.com/mcp/shttp",
-#        api_key = "your-api-key",
-#        timeout = 180  # 3 minutes for processing-heavy tools (1-3600 seconds)
-#    }
-#]
-
-# Stdio servers - Direct process communication (development only)
-#stdio_servers = [
-#    # Basic stdio server
-#    {name = "filesystem", command = "npx", args = ["@modelcontextprotocol/server-filesystem", "/"]},
-#
-#    # Stdio server with environment variables
-#    {
-#        name = "fetch",
-#        command = "uvx",
-#        args = ["mcp-server-fetch"],
-#        env = {DEBUG = "true"}
-#    }
-#]
-
-#################################### Model Routing ############################
-# Configuration for experimental model routing feature
-# Enables intelligent switching between different LLM models for specific purposes
-##############################################################################
-[model_routing]
-# Router to use for model selection
-# Available options:
-# - "noop_router" (default): No routing, always uses primary LLM
-# - "multimodal_router": A router that switches between primary and secondary models, depending on whether the input is multimodal or not
-#router_name = "noop_router"

containers/app/Dockerfile

@@ -1,16 +1,16 @@
 ARG OPENHANDS_BUILD_VERSION=dev
-FROM node:25.2-trixie-slim AS frontend-builder
+FROM node:21.7.2-bookworm-slim AS frontend-builder
 
 WORKDIR /app
 
-COPY frontend/package.json frontend/package-lock.json ./
+COPY ./frontend/package.json frontend/package-lock.json ./
+RUN npm install -g npm@10.5.1
 RUN npm ci
 
-COPY frontend ./
+COPY ./frontend ./
 RUN npm run build
 
-FROM python:3.13.7-slim-trixie AS base
-FROM base AS backend-builder
+FROM python:3.12.3-slim AS backend-builder
 
 WORKDIR /app
 ENV PYTHONPATH='/app'
@@ -21,19 +21,18 @@ ENV POETRY_NO_INTERACTION=1 \
     POETRY_CACHE_DIR=/tmp/poetry_cache
 
 RUN apt-get update -y \
-    && apt-get install -y curl make git build-essential jq gettext \
-    && python3 -m pip install poetry --break-system-packages
+    && apt-get install -y curl make git build-essential \
+    && python3 -m pip install poetry==1.8.2  --break-system-packages
 
-COPY pyproject.toml poetry.lock ./
+COPY ./pyproject.toml ./poetry.lock ./
 RUN touch README.md
-RUN export POETRY_CACHE_DIR && poetry install --no-root && rm -rf $POETRY_CACHE_DIR
+RUN export POETRY_CACHE_DIR && poetry install --without evaluation,llama-index --no-root && rm -rf $POETRY_CACHE_DIR
 
-FROM base AS openhands-app
+FROM python:3.12.3-slim AS openhands-app
 
 WORKDIR /app
 
-# re-declare for this section
-ARG OPENHANDS_BUILD_VERSION
+ARG OPENHANDS_BUILD_VERSION #re-declare for this section
 
 ENV RUN_AS_OPENHANDS=true
 # A random number--we need this to be different from the user's UID on the host machine
@@ -44,48 +43,52 @@ ENV WORKSPACE_BASE=/opt/workspace_base
 ENV OPENHANDS_BUILD_VERSION=$OPENHANDS_BUILD_VERSION
 ENV SANDBOX_USER_ID=0
 ENV FILE_STORE=local
-ENV FILE_STORE_PATH=/.openhands
-ENV INIT_GIT_IN_EMPTY_WORKSPACE=1
+ENV FILE_STORE_PATH=/.openhands-state
 RUN mkdir -p $FILE_STORE_PATH
 RUN mkdir -p $WORKSPACE_BASE
 
 RUN apt-get update -y \
-    && apt-get install -y curl ssh sudo \
-    && rm -rf /var/lib/apt/lists/*
+    && apt-get install -y curl ssh sudo
 
 # Default is 1000, but OSX is often 501
 RUN sed -i 's/^UID_MIN.*/UID_MIN 499/' /etc/login.defs
 # Default is 60000, but we've seen up to 200000
 RUN sed -i 's/^UID_MAX.*/UID_MAX 1000000/' /etc/login.defs
 
-RUN groupadd --gid $OPENHANDS_USER_ID openhands
-RUN useradd -l -m -u $OPENHANDS_USER_ID --gid $OPENHANDS_USER_ID -s /bin/bash openhands && \
-    usermod -aG openhands openhands && \
+RUN groupadd app
+RUN useradd -l -m -u $OPENHANDS_USER_ID -s /bin/bash openhands && \
+    usermod -aG app openhands && \
     usermod -aG sudo openhands && \
     echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
-RUN chown -R openhands:openhands /app && chmod -R 770 /app
-RUN sudo chown -R openhands:openhands $WORKSPACE_BASE && sudo chmod -R 770 $WORKSPACE_BASE
+RUN chown -R openhands:app /app && chmod -R 770 /app
+RUN sudo chown -R openhands:app $WORKSPACE_BASE && sudo chmod -R 770 $WORKSPACE_BASE
 USER openhands
 
 ENV VIRTUAL_ENV=/app/.venv \
     PATH="/app/.venv/bin:$PATH" \
     PYTHONPATH='/app'
 
-COPY --chown=openhands:openhands --chmod=770 --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
+COPY --chown=openhands:app --chmod=770 --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
+RUN playwright install --with-deps chromium
 
-COPY --chown=openhands:openhands --chmod=770 ./skills ./skills
-COPY --chown=openhands:openhands --chmod=770 ./openhands ./openhands
-COPY --chown=openhands:openhands --chmod=777 ./openhands/runtime/plugins ./openhands/runtime/plugins
-COPY --chown=openhands:openhands pyproject.toml poetry.lock README.md MANIFEST.in LICENSE ./
+COPY --chown=openhands:app --chmod=770 ./microagents ./microagents
+COPY --chown=openhands:app --chmod=770 ./openhands ./openhands
+COPY --chown=openhands:app --chmod=777 ./openhands/runtime/plugins ./openhands/runtime/plugins
+COPY --chown=openhands:app --chmod=770 ./openhands/agenthub ./openhands/agenthub
+COPY --chown=openhands:app ./pyproject.toml ./pyproject.toml
+COPY --chown=openhands:app ./poetry.lock ./poetry.lock
+COPY --chown=openhands:app ./README.md ./README.md
+COPY --chown=openhands:app ./MANIFEST.in ./MANIFEST.in
+COPY --chown=openhands:app ./LICENSE ./LICENSE
 
 # This is run as "openhands" user, and will create __pycache__ with openhands:openhands ownership
 RUN python openhands/core/download.py # No-op to download assets
 # Add this line to set group ownership of all files/directories not already in "app" group
-# openhands:openhands -> openhands:openhands
-RUN find /app \! -group openhands -exec chgrp openhands {} +
+# openhands:openhands -> openhands:app
+RUN find /app \! -group app -exec chgrp app {} +
 
-COPY --chown=openhands:openhands --chmod=770 --from=frontend-builder /app/build ./frontend/build
-COPY --chown=openhands:openhands --chmod=770 ./containers/app/entrypoint.sh /app/entrypoint.sh
+COPY --chown=openhands:app --chmod=770 --from=frontend-builder /app/build ./frontend/build
+COPY --chown=openhands:app --chmod=770 ./containers/app/entrypoint.sh /app/entrypoint.sh
 
 USER root
 

containers/app/config.sh

@@ -1,4 +1,4 @@
 DOCKER_REGISTRY=ghcr.io
-DOCKER_ORG=openhands
+DOCKER_ORG=all-hands-ai
 DOCKER_IMAGE=openhands
 DOCKER_BASE_DIR="."

containers/app/entrypoint.sh

@@ -23,21 +23,13 @@ if [ -z "$WORKSPACE_MOUNT_PATH" ]; then
   unset WORKSPACE_BASE
 fi
 
-if [[ "$INSTALL_THIRD_PARTY_RUNTIMES" == "true" ]]; then
-  echo "Downloading and installing third_party_runtimes..."
-  echo "Warning: Third-party runtimes are provided as-is, not actively supported and may be removed in future releases."
-
-  if pip install 'openhands-ai[third_party_runtimes]' -qqq 2> >(tee /dev/stderr); then
-    echo "third_party_runtimes installed successfully."
-  else
-    echo "Failed to install third_party_runtimes." >&2
-    exit 1
-  fi
-fi
-
 if [[ "$SANDBOX_USER_ID" -eq 0 ]]; then
   echo "Running OpenHands as root"
   export RUN_AS_OPENHANDS=false
+  mkdir -p /root/.cache/ms-playwright/
+  if [ -d "/home/openhands/.cache/ms-playwright/" ]; then
+    mv /home/openhands/.cache/ms-playwright/ /root/.cache/
+  fi
   "$@"
 else
   echo "Setting up enduser with id $SANDBOX_USER_ID"
@@ -54,7 +46,7 @@ else
       fi
     fi
   fi
-  usermod -aG openhands enduser
+  usermod -aG app enduser
   # get the user group of /var/run/docker.sock and set openhands to that group
   DOCKER_SOCKET_GID=$(stat -c '%g' /var/run/docker.sock)
   echo "Docker socket group id: $DOCKER_SOCKET_GID"
@@ -66,6 +58,10 @@ else
   fi
 
   mkdir -p /home/enduser/.cache/huggingface/hub/
+  mkdir -p /home/enduser/.cache/ms-playwright/
+  if [ -d "/home/openhands/.cache/ms-playwright/" ]; then
+    mv /home/openhands/.cache/ms-playwright/ /home/enduser/.cache/
+  fi
 
   usermod -aG $DOCKER_SOCKET_GID enduser
   echo "Running as enduser"

containers/build.sh

@@ -1,4 +1,4 @@
-#!/usr/bin/env bash
+#!/bin/bash
 set -eo pipefail
 
 # Initialize variables with default values
@@ -7,17 +7,15 @@ org_name=""
 push=0
 load=0
 tag_suffix=""
-dry_run=0
 
 # Function to display usage information
 usage() {
-    echo "Usage: $0 -i <image_name> [-o <org_name>] [--push] [--load] [-t <tag_suffix>] [--dry]"
+    echo "Usage: $0 -i <image_name> [-o <org_name>] [--push] [--load] [-t <tag_suffix>]"
     echo "  -i: Image name (required)"
     echo "  -o: Organization name"
     echo "  --push: Push the image"
     echo "  --load: Load the image"
     echo "  -t: Tag suffix"
-    echo "  --dry: Don't build, only create build-args.json"
     exit 1
 }
 
@@ -29,7 +27,6 @@ while [[ $# -gt 0 ]]; do
         --push) push=1; shift ;;
         --load) load=1; shift ;;
         -t) tag_suffix="$2"; shift 2 ;;
-        --dry) dry_run=1; shift ;;
         *) usage ;;
     esac
 done
@@ -116,13 +113,10 @@ echo "Repo: $DOCKER_REPOSITORY"
 echo "Base dir: $DOCKER_BASE_DIR"
 
 args=""
-full_tags=()
 for tag in "${tags[@]}"; do
   args+=" -t $DOCKER_REPOSITORY:$tag"
-  full_tags+=("$DOCKER_REPOSITORY:$tag")
 done
 
-
 if [[ $push -eq 1 ]]; then
   args+=" --push"
   args+=" --cache-to=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag,mode=max"
@@ -142,26 +136,6 @@ else
   # For push or without load, build for multiple platforms
   platform="linux/amd64,linux/arm64"
 fi
-if [[ $dry_run -eq 1 ]]; then
-  echo "Dry Run is enabled. Writing build config to docker-build-dry.json"
-  jq -n \
-    --argjson tags "$(printf '%s\n' "${full_tags[@]}" | jq -R . | jq -s .)" \
-    --arg platform "$platform" \
-    --arg openhands_build_version "$OPENHANDS_BUILD_VERSION" \
-    --arg dockerfile "$dir/Dockerfile" \
-    '{
-      tags: $tags,
-      platform: $platform,
-      build_args: [
-        "OPENHANDS_BUILD_VERSION=" + $openhands_build_version
-      ],
-      dockerfile: $dockerfile
-    }' > docker-build-dry.json
-
-    exit 0
-fi
-
-
 
 echo "Building for platform(s): $platform"
 

containers/dev/Dockerfile

@@ -61,8 +61,8 @@ RUN add-apt-repository ppa:deadsnakes/ppa \
     && apt-get install -y python3.12 python3.12-venv python3.12-dev python3-pip \
     && ln -s /usr/bin/python3.12 /usr/bin/python
 
-# NodeJS >= 22.x
-RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \
+# NodeJS >= 18.17.1
+RUN curl -fsSL https://deb.nodesource.com/setup_18.x | bash - \
     && apt-get install -y nodejs
 
 # Poetry >= 1.8
@@ -104,14 +104,11 @@ RUN apt-get update && apt-get install -y \
 	&& apt-get clean \
 	&& apt-get autoremove -y
 
-# mark /app as safe git directory to avoid pre-commit errors
-RUN git config --system --add safe.directory /app
-
 WORKDIR /app
 
 # cache build dependencies
 RUN \
-  --mount=type=bind,source=./,target=/app/,rw \
+  --mount=type=bind,source=./,target=/app/ \
   <<EOF
 #!/bin/bash
 make -s clean

containers/dev/README.md

@@ -1,7 +1,7 @@
 # Develop in Docker
 
 > [!WARNING]
-> This way of running OpenHands is not officially supported. It is maintained by the community and may not work.
+> This is not officially supported and may not work.
 
 Install [Docker](https://docs.docker.com/engine/install/) on your host machine and run:
 

containers/dev/compose.yml

@@ -10,10 +10,8 @@ services:
     environment:
       - BACKEND_HOST=${BACKEND_HOST:-"0.0.0.0"}
       - SANDBOX_API_HOSTNAME=host.docker.internal
-      - DOCKER_HOST_ADDR=host.docker.internal
       #
-      - AGENT_SERVER_IMAGE_REPOSITORY=${AGENT_SERVER_IMAGE_REPOSITORY:-ghcr.io/openhands/runtime}
-      - AGENT_SERVER_IMAGE_TAG=${AGENT_SERVER_IMAGE_TAG:-1.2-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.21-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

containers/dev/dev.sh

@@ -1,4 +1,4 @@
-#!/usr/bin/env bash
+#!/bin/bash
 set -o pipefail
 
 function get_docker() {

containers/e2b-sandbox/Dockerfile

@@ -1,4 +1,4 @@
-FROM ubuntu:24.04
+FROM ubuntu:22.04
 
 # install basic packages
 RUN apt-get update && apt-get install -y \

containers/runtime/README.md

@@ -6,7 +6,7 @@ that depends on the `base_image` **AND** a [Python source distribution](https://
 The following command will generate a `Dockerfile` file for `nikolaik/python-nodejs:python3.12-nodejs22` (the default base image), an updated `config.sh` and the runtime source distribution files/folders into `containers/runtime`:
 
 ```bash
-poetry run python3 -m openhands.runtime.utils.runtime_build \
+poetry run python3 openhands/runtime/utils/runtime_build.py \
     --base_image nikolaik/python-nodejs:python3.12-nodejs22 \
     --build_folder containers/runtime
 ```

containers/runtime/config.sh

@@ -1,5 +1,5 @@
 DOCKER_REGISTRY=ghcr.io
-DOCKER_ORG=openhands
+DOCKER_ORG=all-hands-ai
 DOCKER_BASE_DIR="./containers/runtime"
 DOCKER_IMAGE=runtime
 # These variables will be appended by the runtime_build.py script

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

@@ -1,65 +1,43 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v4.5.0
     hooks:
       - id: trailing-whitespace
-        exclude: ^(docs/|modules/|python/|openhands-ui/|third_party/|enterprise/)
+        exclude: docs/modules/python
       - id: end-of-file-fixer
-        exclude: ^(docs/|modules/|python/|openhands-ui/|third_party/|enterprise/)
+        exclude: docs/modules/python
       - id: check-yaml
-        args: ["--allow-multiple-documents"]
       - id: debug-statements
 
-
-  - repo: local
-    hooks:
-      - id: warn-appmode-oss
-        name: "Warn on AppMode.OSS in backend (use AppMode.OPENHANDS)"
-        language: system
-        entry: bash -lc 'if rg -n "\\bAppMode\\.OSS\\b" openhands tests/unit; then echo "Found AppMode.OSS usage. Prefer AppMode.OPENHANDS."; exit 1; fi'
-        pass_filenames: false
-
   - repo: https://github.com/tox-dev/pyproject-fmt
-    rev: v2.5.1
+    rev: 1.7.0
     hooks:
       - id: pyproject-fmt
   - repo: https://github.com/abravalheri/validate-pyproject
-    rev: v0.24.1
+    rev: v0.16
     hooks:
       - id: validate-pyproject
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.11.8
+    rev: v0.4.1
     hooks:
       # Run the linter.
       - id: ruff
         entry: ruff check --config dev_config/python/ruff.toml
         types_or: [python, pyi, jupyter]
-        args: [--fix, --unsafe-fixes]
-        exclude: ^(third_party/|enterprise/)
+        args: [--fix]
       # Run the formatter.
       - id: ruff-format
         entry: ruff format --config dev_config/python/ruff.toml
         types_or: [python, pyi, jupyter]
-        exclude: ^(third_party/|enterprise/)
 
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.15.0
+    rev: v1.9.0
     hooks:
       - id: mypy
         additional_dependencies:
-          [
-            types-requests,
-            types-setuptools,
-            types-pyyaml,
-            types-toml,
-            types-docker,
-            types-Markdown,
-            pydantic,
-            lxml,
-          ]
-        # To see gaps add `--html-report mypy-report/`
+          [types-requests, types-setuptools, types-pyyaml, types-toml]
         entry: mypy --config-file dev_config/python/mypy.ini openhands/
         always_run: true
         pass_filenames: false

dev_config/python/mypy.ini

@@ -7,10 +7,3 @@ warn_unreachable = True
 warn_redundant_casts = True
 no_implicit_optional = True
 strict_optional = True
-disable_error_code = type-abstract
-
-# Exclude third-party runtime directory from type checking
-exclude = (third_party/|enterprise/)
-
-[mypy-openhands.memory.condenser.impl.*]
-disable_error_code = override

dev_config/python/ruff.toml

@@ -1,6 +1,3 @@
-# Exclude third-party runtime directory from linting
-exclude = ["third_party/", "enterprise/"]
-
 [lint]
 select = [
     "E",
@@ -9,10 +6,6 @@ select = [
     "I",
     "Q",
     "B",
-    "ASYNC",
-    "UP006",  # Use `list` instead of `List` for annotations
-    "UP007",  # Use `X | Y` instead of `Union[X, Y]`
-    "UP008",  # Use `X | None` instead of `Optional[X]`
 ]
 
 ignore = [
@@ -23,12 +16,6 @@ ignore = [
     "B010",
     "B904",
     "B018",
-    # Temporarily ignore ASYNC rules until they can be properly fixed in a separate PR
-    "ASYNC110",
-    "ASYNC220",
-    "ASYNC221",
-    "ASYNC230",
-    "ASYNC251",
 ]
 
 [lint.flake8-quotes]
@@ -37,6 +24,3 @@ inline-quotes = "single"
 
 [format]
 quote-style = "single"
-
-[lint.flake8-bugbear]
-extend-immutable-calls = ["Depends", "fastapi.Depends", "fastapi.params.Depends"]

docker-compose.yml

@@ -7,9 +7,8 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - AGENT_SERVER_IMAGE_REPOSITORY=${AGENT_SERVER_IMAGE_REPOSITORY:-ghcr.io/openhands/agent-server}
-      - AGENT_SERVER_IMAGE_TAG=${AGENT_SERVER_IMAGE_TAG:-31536c8-python}
-      #- SANDBOX_USER_ID=${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
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.21-nikolaik}
+      #- SANDBOX_USER_ID=${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-state for this user
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:
       - "3000:3000"
@@ -17,7 +16,7 @@ services:
       - "host.docker.internal:host-gateway"
     volumes:
       - /var/run/docker.sock:/var/run/docker.sock
-      - ~/.openhands:/.openhands
+      - ~/.openhands-state:/.openhands-state
       - ${WORKSPACE_BASE:-$PWD/workspace}:/opt/workspace_base
     pull_policy: build
     stdin_open: true

docs/.gitignore

@@ -0,0 +1,20 @@
+# Dependencies
+/node_modules
+
+# Production
+/build
+
+# Generated files
+.docusaurus
+.cache-loader
+
+# Misc
+.DS_Store
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*

docs/DOC_STYLE_GUIDE.md

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

docs/README.md

@@ -0,0 +1,41 @@
+# Website
+
+This website is built using [Docusaurus](https://docusaurus.io/), a modern static website generator.
+
+### Installation
+
+```
+$ yarn
+```
+
+### Local Development
+
+```
+$ yarn start
+```
+
+This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.
+
+### Build
+
+```
+$ yarn build
+```
+
+This command generates static content into the `build` directory and can be served using any static contents hosting service.
+
+### Deployment
+
+Using SSH:
+
+```
+$ USE_SSH=true yarn deploy
+```
+
+Not using SSH:
+
+```
+$ GIT_USER=<Your GitHub username> yarn deploy
+```
+
+If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the `gh-pages` branch.

docs/babel.config.js

@@ -0,0 +1,3 @@
+module.exports = {
+  presets: [require.resolve('@docusaurus/core/lib/babel/preset')],
+};

docs/docusaurus.config.ts

@@ -0,0 +1,107 @@
+import type * as Preset from "@docusaurus/preset-classic";
+import type { Config } from "@docusaurus/types";
+import { themes as prismThemes } from "prism-react-renderer";
+
+const config: Config = {
+  title: "OpenHands",
+  tagline: "Code Less, Make More",
+  favicon: "img/logo-square.png",
+
+  // Set the production url of your site here
+  url: "https://docs.all-hands.dev",
+  baseUrl: "/",
+
+  // GitHub pages deployment config.
+  organizationName: "All-Hands-AI",
+  projectName: "OpenHands",
+  trailingSlash: false,
+
+  onBrokenLinks: "throw",
+  onBrokenMarkdownLinks: "warn",
+
+  // Even if you don't use internationalization, you can use this field to set
+  // useful metadata like html lang. For example, if your site is Chinese, you
+  // may want to replace "en" with "zh-Hans".
+  i18n: {
+    defaultLocale: 'en',
+    locales: ['en', 'fr', 'zh-Hans'],
+    localeConfigs: {
+      en: {
+        htmlLang: 'en-GB',
+      },
+    },
+  },
+
+  markdown: {
+    mermaid: true,
+  },
+  themes: ['@docusaurus/theme-mermaid'],
+  presets: [
+    [
+      "classic",
+      {
+        docs: {
+          path: "modules",
+          routeBasePath: "modules",
+          sidebarPath: "./sidebars.ts",
+          exclude: [
+            // '**/_*.{js,jsx,ts,tsx,md,mdx}',
+            // '**/_*/**',
+            "**/*.test.{js,jsx,ts,tsx}",
+            "**/__tests__/**",
+          ],
+        },
+        blog: {
+          showReadingTime: true,
+        },
+        theme: {
+          customCss: "./src/css/custom.css",
+        },
+      } satisfies Preset.Options,
+    ],
+  ],
+  themeConfig: {
+    image: "img/docusaurus.png",
+    navbar: {
+      title: "OpenHands",
+      logo: {
+        alt: "OpenHands",
+        src: "img/logo.png",
+      },
+      items: [
+        {
+          type: "docSidebar",
+          sidebarId: "docsSidebar",
+          position: "left",
+          label: "User Guides",
+        },
+        {
+          type: "docSidebar",
+          sidebarId: "apiSidebar",
+          position: "left",
+          label: "Python API",
+        },
+        {
+          type: 'localeDropdown',
+          position: 'left',
+        },
+        {
+          href: "https://all-hands.dev",
+          label: "Company",
+          position: "right",
+        },
+        {
+          href: "https://github.com/All-Hands-AI/OpenHands",
+          label: "GitHub",
+          position: "right",
+        },
+      ],
+    },
+    prism: {
+      theme: prismThemes.oneLight,
+      darkTheme: prismThemes.oneDark,
+    },
+  } satisfies Preset.ThemeConfig,
+};
+
+export default config;

docs/i18n/fr/code.json

@@ -0,0 +1,406 @@
+{
+  "footer.title": {
+    "message": "OpenHands"
+  },
+  "footer.docs": {
+    "message": "Documents"
+  },
+  "footer.community": {
+    "message": "Communauté"
+  },
+  "footer.copyright": {
+    "message": "© {year} OpenHands"
+  },
+  "faq.title": {
+    "message": "Questions Fréquemment Posées",
+    "description": "FAQ Title"
+  },
+  "faq.description": {
+    "message": "Questions Fréquemment Posées"
+  },
+  "faq.section.title.1": {
+    "message": "Qu'est-ce qu'OpenHands ?",
+    "description": "First Section Title"
+  },
+  "faq.section.highlight": {
+    "message": "OpenHands",
+    "description": "Highlight Text"
+  },
+  "faq.section.description.1": {
+    "message": "est un ingénieur logiciel autonome qui peut résoudre des tâches d'ingénierie logicielle et de navigation web à tout moment. Il peut exécuter des requêtes en sciences des données, telles que \"Trouver le nombre de demandes de pull à l'repository OpenHands dans les derniers mois\", et des tâches d'ingénierie logicielle, comme \"Veuillez ajouter des tests à ce fichier et vérifier si tous les tests passent. Si ce n'est pas le cas, réparez le fichier.\"",
+    "description": "Description for OpenHands"
+  },
+  "faq.section.description.2": {
+    "message": "De plus, OpenHands est une plateforme et communauté pour les développeurs d'agents qui souhaitent tester et évaluer de nouveaux agents.",
+    "description": "Further Description for OpenHands"
+  },
+  "faq.section.title.2": {
+    "message": "Support",
+    "description": "Support Section Title"
+  },
+  "faq.section.support.answer": {
+    "message": "Si vous rencontrez un problème que d'autres utilisateurs peuvent également avoir, merci de le signaler sur {githubLink}. Si vous avez des difficultés à l'installation ou des questions générales, rejoignez-vous sur {discordLink} ou {slackLink}.",
+    "description": "Support Answer"
+  },
+  "faq.section.title.3": {
+    "message": "Comment résoudre un problème sur GitHub avec OpenHands ?",
+    "description": "GitHub Issue Section Title"
+  },
+  "faq.section.github.steps.intro": {
+    "message": "Pour résoudre un problème sur GitHub en utilisant OpenHands, envoyez une commande à OpenHands demandant qu'il suit des étapes comme les suivantes :",
+    "description": "GitHub Steps Introduction"
+  },
+  "faq.section.github.step1": {
+    "message": "Lisez l'issue https://github.com/All-Hands-AI/OpenHands/issues/1611",
+    "description": "GitHub Step 1"
+  },
+  "faq.section.github.step2": {
+    "message": "Cloner le dépôt et vérifier une nouvelle branche",
+    "description": "GitHub Step 2"
+  },
+  "faq.section.github.step3": {
+    "message": "Sur la base des instructions dans la description de l'issue, modifiez les fichiers pour résoudre le problème",
+    "description": "GitHub Step 3"
+  },
+  "faq.section.github.step4": {
+    "message": "Pousser le résultat à GitHub en utilisant la variable d'environnement GITHUB_TOKEN",
+    "description": "GitHub Step 4"
+  },
+  "faq.section.github.step5": {
+    "message": "Dites-moi le lien que je dois utiliser pour envoyer une demande de pull",
+    "description": "GitHub Step 5"
+  },
+  "faq.section.github.steps.preRun": {
+    "message": "Avant de lancer OpenHands, vous pouvez faire :",
+    "description": "GitHub Steps Pre-Run"
+  },
+  "faq.section.github.steps.tokenInfo": {
+    "message": "où XXX est un jeton GitHub que vous avez créé et qui a les autorisations pour pousser dans le dépôt OpenHands. Si vous n'avez pas d'autorisations de modification du dépôt OpenHands, vous devrez peut-être changer cela en :",
+    "description": "GitHub Steps Token Info"
+  },
+  "faq.section.github.steps.usernameInfo": {
+    "message": "où USERNAME est votre nom GitHub.",
+    "description": "GitHub Steps Username Info"
+  },
+  "faq.section.title.4": {
+    "message": "Comment OpenHands est-il différent de Devin ?",
+    "description": "Devin Section Title"
+  },
+  "faq.section.openhands.linkText": {
+    "message": "Devin",
+    "description": "Devin Link Text"
+  },
+  "faq.section.openhands.description": {
+    "message": "est un produit commercial par Cognition Inc., qui a servi d'inspiration initiale pour OpenHands. Les deux visent à bien faire le travail d'ingénierie logicielle, mais vous pouvez télécharger, utiliser et modifier OpenHands, tandis que Devin peut être utilisé uniquement via le site de Cognition. De plus, OpenHands a évolué au-delà de l'inspiration initiale, et est maintenant un écosystème communautaire pour le développement d'agents en général, et nous serions ravis de vous voir rejoindre et",
+    "description": "Devin Description"
+  },
+  "faq.section.openhands.contribute": {
+    "message": "contribuer",
+    "description": "Contribute Link"
+  },
+  "faq.section.title.5": {
+    "message": "Comment OpenHands est-il différent de ChatGPT ?",
+    "description": "ChatGPT Section Title"
+  },
+  "faq.section.chatgpt.description": {
+    "message": "ChatGPT vous pouvez accéder en ligne, il ne se connecte pas aux fichiers locaux et ses capacités d'exécution du code sont limitées. Alors qu'il peut écrire du code, mais c'est difficile à tester ou à exécuter.",
+    "description": "ChatGPT Description"
+  },
+  "homepage.description": {
+    "message": "Génération d'code AI pour l'ingénierie logicielle.",
+    "description": "The homepage description"
+  },
+  "homepage.getStarted": {
+    "message": "Commencer"
+  },
+  "welcome.message": {
+    "message": "Bienvenue à OpenHands, un système d'IA autonome ingénieur logiciel capable d'exécuter des tâches d'ingénierie complexes et de collaborer activement avec les utilisateurs sur les projets de développement logiciel."
+  },
+  "theme.ErrorPageContent.title": {
+    "message": "Cette page a planté.",
+    "description": "The title of the fallback page when the page crashed"
+  },
+  "theme.BackToTopButton.buttonAriaLabel": {
+    "message": "Retourner en haut de la page",
+    "description": "The ARIA label for the back to top button"
+  },
+  "theme.blog.archive.title": {
+    "message": "Archives",
+    "description": "The page & hero title of the blog archive page"
+  },
+  "theme.blog.archive.description": {
+    "message": "Archives",
+    "description": "The page & hero description of the blog archive page"
+  },
+  "theme.blog.paginator.navAriaLabel": {
+    "message": "Pagination des listes d'articles du blog",
+    "description": "The ARIA label for the blog pagination"
+  },
+  "theme.blog.paginator.newerEntries": {
+    "message": "Nouvelles entrées",
+    "description": "The label used to navigate to the newer blog posts page (previous page)"
+  },
+  "theme.blog.paginator.olderEntries": {
+    "message": "Anciennes entrées",
+    "description": "The label used to navigate to the older blog posts page (next page)"
+  },
+  "theme.blog.post.paginator.navAriaLabel": {
+    "message": "Pagination des articles du blog",
+    "description": "The ARIA label for the blog posts pagination"
+  },
+  "theme.blog.post.paginator.newerPost": {
+    "message": "Article plus récent",
+    "description": "The blog post button label to navigate to the newer/previous post"
+  },
+  "theme.blog.post.paginator.olderPost": {
+    "message": "Article plus ancien",
+    "description": "The blog post button label to navigate to the older/next post"
+  },
+  "theme.blog.post.plurals": {
+    "message": "Un article|{count} articles",
+    "description": "Pluralized label for \"{count} posts\". Use as much plural forms (separated by \"|\") as your language support (see https://www.unicode.org/cldr/cldr-aux/charts/34/supplemental/language_plural_rules.html)"
+  },
+  "theme.blog.tagTitle": {
+    "message": "{nPosts} tags avec « {tagName} »",
+    "description": "The title of the page for a blog tag"
+  },
+  "theme.tags.tagsPageLink": {
+    "message": "Voir tous les tags",
+    "description": "The label of the link targeting the tag list page"
+  },
+  "theme.colorToggle.ariaLabel": {
+    "message": "Basculer entre le mode sombre et clair (actuellement {mode})",
+    "description": "The ARIA label for the navbar color mode toggle"
+  },
+  "theme.colorToggle.ariaLabel.mode.dark": {
+    "message": "mode sombre",
+    "description": "The name for the dark color mode"
+  },
+  "theme.colorToggle.ariaLabel.mode.light": {
+    "message": "mode clair",
+    "description": "The name for the light color mode"
+  },
+  "theme.docs.breadcrumbs.navAriaLabel": {
+    "message": "Bouton de navigation des liens de la page",
+    "description": "The ARIA label for the breadcrumbs"
+  },
+  "theme.docs.DocCard.categoryDescription.plurals": {
+    "message": "1 élément|{count} éléments",
+    "description": "The default description for a category card in the generated index about how many items this category includes"
+  },
+  "theme.docs.paginator.navAriaLabel": {
+    "message": "Pages de documentation",
+    "description": "The ARIA label for the docs pagination"
+  },
+  "theme.docs.paginator.previous": {
+    "message": "Précédent",
+    "description": "The label used to navigate to the previous doc"
+  },
+  "theme.docs.paginator.next": {
+    "message": "Suivant",
+    "description": "The label used to navigate to the next doc"
+  },
+  "theme.docs.tagDocListPageTitle.nDocsTagged": {
+    "message": "Un document tagué|{count} documents tagués",
+    "description": "Pluralized label for \"{count} docs tagged\". Use as much plural forms (separated by \"|\") as your language support (see https://www.unicode.org/cldr/cldr-aux/charts/34/supplemental/language_plural_rules.html)"
+  },
+  "theme.docs.tagDocListPageTitle": {
+    "message": "{nDocsTagged} avec \"{tagName}\"",
+    "description": "The title of the page for a docs tag"
+  },
+  "theme.docs.versionBadge.label": {
+    "message": "Version: {versionLabel}"
+  },
+  "theme.docs.versions.unreleasedVersionLabel": {
+    "message": "Ceci est la documentation de la prochaine version {versionLabel} de {siteTitle}.",
+    "description": "The label used to tell the user that he's browsing an unreleased doc version"
+  },
+  "theme.docs.versions.unmaintainedVersionLabel": {
+    "message": "Ceci est la documentation de {siteTitle} {versionLabel}, qui n'est plus activement maintenue.",
+    "description": "The label used to tell the user that he's browsing an unmaintained doc version"
+  },
+  "theme.docs.versions.latestVersionSuggestionLabel": {
+    "message": "Pour une documentation à jour, consultez la {latestVersionLink} ({versionLabel}).",
+    "description": "The label used to tell the user to check the latest version"
+  },
+  "theme.docs.versions.latestVersionLinkLabel": {
+    "message": "dernière version",
+    "description": "The label used for the latest version suggestion link label"
+  },
+  "theme.common.editThisPage": {
+    "message": "Éditer cette page",
+    "description": "The link label to edit the current page"
+  },
+  "theme.common.headingLinkTitle": {
+    "message": "Lien direct vers {heading}",
+    "description": "Title for link to heading"
+  },
+  "theme.lastUpdated.atDate": {
+    "message": " le {date}",
+    "description": "The words used to describe on which date a page has been last updated"
+  },
+  "theme.lastUpdated.byUser": {
+    "message": " par {user}",
+    "description": "The words used to describe by who the page has been last updated"
+  },
+  "theme.lastUpdated.lastUpdatedAtBy": {
+    "message": "Dernière mise à jour{atDate}{byUser}",
+    "description": "The sentence used to display when a page has been last updated, and by who"
+  },
+  "theme.navbar.mobileVersionsDropdown.label": {
+    "message": "Versions",
+    "description": "The label for the navbar versions dropdown on mobile view"
+  },
+  "theme.NotFound.title": {
+    "message": "Page introuvable",
+    "description": "The title of the 404 page"
+  },
+  "theme.tags.tagsListLabel": {
+    "message": "Tags :",
+    "description": "The label alongside a tag list"
+  },
+  "theme.admonition.caution": {
+    "message": "prudence",
+    "description": "The default label used for the Caution admonition (:::caution)"
+  },
+  "theme.admonition.danger": {
+    "message": "danger",
+    "description": "The default label used for the Danger admonition (:::danger)"
+  },
+  "theme.admonition.info": {
+    "message": "information",
+    "description": "The default label used for the Info admonition (:::info)"
+  },
+  "theme.admonition.note": {
+    "message": "remarque",
+    "description": "The default label used for the Note admonition (:::note)"
+  },
+  "theme.admonition.tip": {
+    "message": "astuce",
+    "description": "The default label used for the Tip admonition (:::tip)"
+  },
+  "theme.admonition.warning": {
+    "message": "prudence",
+    "description": "The default label used for the Warning admonition (:::warning)"
+  },
+  "theme.AnnouncementBar.closeButtonAriaLabel": {
+    "message": "Fermer",
+    "description": "The ARIA label for close button of announcement bar"
+  },
+  "theme.blog.sidebar.navAriaLabel": {
+    "message": "Navigation vers les articles récents du blog",
+    "description": "The ARIA label for recent posts in the blog sidebar"
+  },
+  "theme.CodeBlock.copied": {
+    "message": "Copié",
+    "description": "The copied button label on code blocks"
+  },
+  "theme.CodeBlock.copyButtonAriaLabel": {
+    "message": "Copier le code",
+    "description": "The ARIA label for copy code blocks button"
+  },
+  "theme.CodeBlock.copy": {
+    "message": "Copier",
+    "description": "The copy button label on code blocks"
+  },
+  "theme.CodeBlock.wordWrapToggle": {
+    "message": "Activer/désactiver le retour à la ligne",
+    "description": "The title attribute for toggle word wrapping button of code block lines"
+  },
+  "theme.DocSidebarItem.expandCategoryAriaLabel": {
+    "message": "Développer la catégorie '{label}' de la barre latérale",
+    "description": "The ARIA label to expand the sidebar category"
+  },
+  "theme.DocSidebarItem.collapseCategoryAriaLabel": {
+    "message": "Réduire la catégorie '{label}' de la barre latérale",
+    "description": "The ARIA label to collapse the sidebar category"
+  },
+  "theme.NavBar.navAriaLabel": {
+    "message": "Main",
+    "description": "The ARIA label for the main navigation"
+  },
+  "theme.navbar.mobileLanguageDropdown.label": {
+    "message": "Langues",
+    "description": "The label for the mobile language switcher dropdown"
+  },
+  "theme.NotFound.p1": {
+    "message": "Nous n'avons pas trouvé ce que vous recherchez.",
+    "description": "The first paragraph of the 404 page"
+  },
+  "theme.NotFound.p2": {
+    "message": "Veuillez contacter le propriétaire du site qui vous a lié à l'URL d'origine et leur faire savoir que leur lien est cassé.",
+    "description": "The 2nd paragraph of the 404 page"
+  },
+  "theme.TOCCollapsible.toggleButtonLabel": {
+    "message": "Sur cette page",
+    "description": "The label used by the button on the collapsible TOC component"
+  },
+  "theme.blog.post.readMore": {
+    "message": "Lire plus",
+    "description": "The label used in blog post item excerpts to link to full blog posts"
+  },
+  "theme.blog.post.readMoreLabel": {
+    "message": "En savoir plus sur {title}",
+    "description": "The ARIA label for the link to full blog posts from excerpts"
+  },
+  "theme.blog.post.readingTime.plurals": {
+    "message": "Une minute de lecture|{readingTime} minutes de lecture",
+    "description": "Pluralized label for \"{readingTime} min read\". Use as much plural forms (separated by \"|\") as your language support (see https://www.unicode.org/cldr/cldr-aux/charts/34/supplemental/language_plural_rules.html)"
+  },
+  "theme.docs.breadcrumbs.home": {
+    "message": "Page d'accueil",
+    "description": "The ARIA label for the home page in the breadcrumbs"
+  },
+  "theme.docs.sidebar.collapseButtonTitle": {
+    "message": "Réduire le menu latéral",
+    "description": "The title attribute for collapse button of doc sidebar"
+  },
+  "theme.docs.sidebar.collapseButtonAriaLabel": {
+    "message": "Réduire le menu latérale",
+    "description": "The title attribute for collapse button of doc sidebar"
+  },
+  "theme.docs.sidebar.navAriaLabel": {
+    "message": "Barre de navigation latérale des docs",
+    "description": "The ARIA label for the sidebar navigation"
+  },
+  "theme.docs.sidebar.closeSidebarButtonAriaLabel": {
+    "message": "Fermer la barre de navigation",
+    "description": "The ARIA label for close button of mobile sidebar"
+  },
+  "theme.navbar.mobileSidebarSecondaryMenu.backButtonLabel": {
+    "message": "← Retour au menu principal",
+    "description": "The label of the back button to return to main menu, inside the mobile navbar sidebar secondary menu (notably used to display the docs sidebar)"
+  },
+  "theme.docs.sidebar.toggleSidebarButtonAriaLabel": {
+    "message": "Ouvrir/fermer la barre de navigation",
+    "description": "The ARIA label for hamburger menu button of mobile navigation"
+  },
+  "theme.docs.sidebar.expandButtonTitle": {
+    "message": "Déplier le menu latéral",
+    "description": "The ARIA label and title attribute for expand button of doc sidebar"
+  },
+  "theme.docs.sidebar.expandButtonAriaLabel": {
+    "message": "Déployer le menu latérale",
+    "description": "The ARIA label and title attribute for expand button of doc sidebar"
+  },
+  "theme.ErrorPageContent.tryAgain": {
+    "message": "Réessayer",
+    "description": "The label of the button to try again rendering when the React error boundary captures an error"
+  },
+  "theme.common.skipToMainContent": {
+    "message": "Aller directement au contenu principal",
+    "description": "The skip to content label used for accessibility, allowing to rapidly navigate to main content with keyboard tab/enter navigation"
+  },
+  "theme.tags.tagsPageTitle": {
+    "message": "Tags",
+    "description": "The title of the tag list page"
+  },
+  "theme.unlistedContent.title": {
+    "message": "Page non répertoriée",
+    "description": "The unlisted content banner title"
+  },
+  "theme.unlistedContent.message": {
+    "message": "Cette page n'est pas répertoriée. Les moteurs de recherche ne l'indexeront pas, et seuls les utilisateurs ayant un lien direct peuvent y accéder.",
+    "description": "The unlisted content banner message"
+  }
+}

docs/i18n/fr/docusaurus-plugin-content-blog/options.json

@@ -0,0 +1,14 @@
+{
+  "title": {
+    "message": "Blog",
+    "description": "The title for the blog used in SEO"
+  },
+  "description": {
+    "message": "Blog",
+    "description": "The description for the blog used in SEO"
+  },
+  "sidebar.title": {
+    "message": "Articles récents",
+    "description": "The label for the left sidebar"
+  }
+}

docs/i18n/fr/docusaurus-plugin-content-docs/current.json

@@ -0,0 +1,18 @@
+{
+  "version.label": {
+    "message": "Next",
+    "description": "The label for version current"
+  },
+  "sidebar.docsSidebar.category.🤖 Backends LLM": {
+    "message": "🤖 Backends LLM",
+    "description": "The label for category 🤖 Backends LLM in sidebar docsSidebar"
+  },
+  "sidebar.docsSidebar.category.🚧 Dépannage": {
+    "message": "🚧 Dépannage",
+    "description": "The label for category 🚧 Dépannage in sidebar docsSidebar"
+  },
+  "sidebar.apiSidebar.category.Backend": {
+    "message": "Backend",
+    "description": "The label for category Backend in sidebar apiSidebar"
+  }
+}

docs/i18n/fr/docusaurus-plugin-content-docs/current/python/python.md

@@ -0,0 +1,5 @@
+
+
+# Documentation Python
+
+La documentation apparaîtra ici après le déploiement.

docs/i18n/fr/docusaurus-plugin-content-docs/current/python/sidebar.json

@@ -0,0 +1,5 @@
+{
+  "items": ["python/python"],
+  "label": "Backend",
+  "type": "categorie"
+}

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

@@ -0,0 +1,28 @@
+
+
+# À propos d'OpenHands
+
+## Stratégie de recherche
+
+La réplication complète d'applications de niveau production avec des LLM est une entreprise complexe. Notre stratégie implique :
+
+1. **Recherche technique fondamentale :** Se concentrer sur la recherche fondamentale pour comprendre et améliorer les aspects techniques de la génération et de la gestion du code
+2. **Capacités spécialisées :** Améliorer l'efficacité des composants de base grâce à la curation des données, aux méthodes d'entraînement, et plus encore
+3. **Planification des tâches :** Développer des capacités pour la détection des bugs, la gestion des bases de code et l'optimisation
+4. **Évaluation :** Établir des métriques d'évaluation complètes pour mieux comprendre et améliorer nos modèles
+
+## Agent par défaut
+
+Notre Agent par défaut est actuellement le [CodeActAgent](agents), qui est capable de générer du code et de gérer des fichiers.
+
+## Construit avec
+
+OpenHands est construit en utilisant une combinaison de frameworks et de bibliothèques puissants, fournissant une base solide pour son développement. Voici les principales technologies utilisées dans le projet :
+
+![FastAPI](https://img.shields.io/badge/FastAPI-black?style=for-the-badge) ![uvicorn](https://img.shields.io/badge/uvicorn-black?style=for-the-badge) ![LiteLLM](https://img.shields.io/badge/LiteLLM-black?style=for-the-badge) ![Docker](https://img.shields.io/badge/Docker-black?style=for-the-badge) ![Ruff](https://img.shields.io/badge/Ruff-black?style=for-the-badge) ![MyPy](https://img.shields.io/badge/MyPy-black?style=for-the-badge) ![LlamaIndex](https://img.shields.io/badge/LlamaIndex-black?style=for-the-badge) ![React](https://img.shields.io/badge/React-black?style=for-the-badge)
+
+Veuillez noter que la sélection de ces technologies est en cours et que des technologies supplémentaires peuvent être ajoutées ou des technologies existantes peuvent être supprimées à mesure que le projet évolue. Nous nous efforçons d'adopter les outils les plus appropriés et les plus efficaces pour améliorer les capacités d'OpenHands.
+
+## Licence
+
+Distribué sous la [Licence](https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE) MIT.

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

@@ -0,0 +1,25 @@
+
+
+# 🧠 Agent Principal et Capacités
+
+## CodeActAgent
+
+### Description
+
+Cet agent implémente l'idée de CodeAct ([article](https://arxiv.org/abs/2402.01030), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) qui consolide les **act**ions des agents LLM dans un espace d'action de **code** unifié à la fois pour la _simplicité_ et la _performance_.
+
+L'idée conceptuelle est illustrée ci-dessous. À chaque tour, l'agent peut :
+
+1. **Converser** : Communiquer avec les humains en langage naturel pour demander des clarifications, des confirmations, etc.
+2. **CodeAct** : Choisir d'effectuer la tâche en exécutant du code
+
+- Exécuter n'importe quelle commande Linux `bash` valide
+- Exécuter n'importe quel code `Python` valide avec [un interpréteur Python interactif](https://ipython.org/). Ceci est simulé via une commande `bash`, voir le système de plugin ci-dessous pour plus de détails.
+
+![image](https://github.com/All-Hands-AI/OpenHands/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
+
+### Démo
+
+https://github.com/All-Hands-AI/OpenHands/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
+
+_Exemple de CodeActAgent avec `gpt-4-turbo-2024-04-09` effectuant une tâche de science des données (régression linéaire)_.

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

@@ -0,0 +1,50 @@
+---
+sidebar_position: 4
+---
+
+# 🏛️ Aperçu de l'Architecture Système
+
+Voici un aperçu de haut niveau de l'architecture du système. Le système est divisé en deux composants principaux : le frontend et le backend. Le frontend est responsable de la gestion des interactions avec l'utilisateur et de l'affichage des résultats. Le backend est responsable de la gestion de la logique métier et de l'exécution des agents.
+
+![system_architecture.svg](/img/system_architecture.svg)
+
+Cet aperçu est simplifié pour montrer les principaux composants et leurs interactions. Pour une vue plus détaillée de l'architecture du backend, consultez la section [Architecture du Backend](#backend-architecture-fr).
+
+# Architecture du Backend {#backend-architecture-fr}
+
+_**Avertissement**: L'architecture du backend est en cours de développement et est sujette à modifications. Le schéma suivant montre l'architecture actuelle du backend basée sur le commit indiqué dans le pied de page du schéma._
+
+![backend_architecture.svg](/img/backend_architecture.svg)
+
+<details>
+  <summary>Mise à jour de ce Schéma</summary>
+  <div>
+    La génération du schéma d'architecture du backend est partiellement automatisée.
+    Le schéma est généré à partir des annotations de type dans le code en utilisant l'outil py2puml.
+    Le schéma est ensuite revu manuellement, ajusté et exporté en PNG et SVG.
+
+    ## Prérequis
+
+    - Un environnement Python dans lequel openhands est exécutable
+    (selon les instructions du fichier README.md à la racine du dépôt)
+    - [py2puml](https://github.com/lucsorel/py2puml) installé
+
+## Étapes
+
+1.  Générez automatiquement le schéma en exécutant la commande suivante depuis la racine du dépôt :
+    `py2puml openhands openhands > docs/architecture/backend_architecture.puml`
+
+2.  Ouvrez le fichier généré dans un éditeur PlantUML, par exemple Visual Studio Code avec l'extension PlantUML ou [PlantText](https://www.planttext.com/)
+
+3.  Révisez le PUML généré et apportez toutes les modifications nécessaires au schéma (ajoutez les parties manquantes, corrigez les erreurs, améliorez l'agencement).
+    _py2puml crée le schéma à partir des annotations de type dans le code, donc les annotations de type manquantes ou incorrectes peuvent entraîner un schéma incomplet ou incorrect._
+
+4.  Examinez la différence entre le nouveau schéma et le précédent et vérifiez manuellement si les modifications sont correctes.
+    _Assurez-vous de ne pas supprimer les parties ajoutées manuellement au schéma par le passé et qui sont toujours pertinentes._
+
+5.  Ajoutez le hash du commit qui a été utilisé pour générer le schéma dans le pied de page du schéma.
+
+6.  Exporte le schéma sous forme de fichiers PNG et SVG et remplacez les schémas existants dans le répertoire `docs/architecture`. Cela peut être fait avec (par exemple [PlantText](https://www.planttext.com/))
+
+  </div>
+</details>

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

@@ -0,0 +1,54 @@
+
+
+# 🏛️ Architecture du Système
+
+<div style={{ textAlign: 'center' }}>
+  <img src="https://github.com/All-Hands-AI/OpenHands/assets/16201837/97d747e3-29d8-4ccb-8d34-6ad1adb17f38" alt="OpenHands System Architecture Diagram Jul 4 2024" />
+  <p><em>Diagramme de l'Architecture du Système OpenHands (4 juillet 2024)</em></p>
+</div>
+
+Ceci est une vue d'ensemble de haut niveau de l'architecture du système. Le système est divisé en deux composants principaux : le frontend et le backend. Le frontend est responsable de la gestion des interactions utilisateur et de l'affichage des résultats. Le backend est responsable de la gestion de la logique métier et de l'exécution des agents.
+
+# Architecture du Frontend {#frontend-architecture-fr}
+
+![system_architecture.svg](/img/system_architecture.svg)
+
+Cette vue d'ensemble est simplifiée pour montrer les principaux composants et leurs interactions. Pour une vue plus détaillée de l'architecture du backend, voir la section Architecture du Backend ci-dessous.
+
+# Architecture du Backend {#backend-architecture-fr}
+
+_**Avertissement** : L'architecture du backend est en cours de développement et est sujette à changement. Le diagramme suivant montre l'architecture actuelle du backend basée sur le commit indiqué dans le pied de page du diagramme._
+
+![backend_architecture.svg](/img/backend_architecture.svg)
+
+<details>
+  <summary>Mise à jour de ce Diagramme</summary>
+  <div>
+    La génération du diagramme d'architecture du backend est partiellement automatisée.
+    Le diagramme est généré à partir des indications de type dans le code en utilisant l'outil py2puml. Le diagramme est ensuite manuellement revu, ajusté et exporté en PNG et SVG.
+
+    ## Prérequis
+
+    - Environnement python fonctionnel dans lequel openhands est exécutable
+    (selon les instructions du fichier README.md à la racine du dépôt)
+    - [py2puml](https://github.com/lucsorel/py2puml) installé
+
+## Étapes
+
+1.  Générer automatiquement le diagramme en exécutant la commande suivante depuis la racine du dépôt :
+    `py2puml openhands openhands > docs/architecture/backend_architecture.puml`
+
+2.  Ouvrir le fichier généré dans un éditeur PlantUML, par ex. Visual Studio Code avec l'extension PlantUML ou [PlantText](https://www.planttext.com/)
+
+3.  Revoir le PUML généré et effectuer tous les ajustements nécessaires au diagramme (ajouter les parties manquantes, corriger les erreurs, améliorer le positionnement).
+    _py2puml crée le diagramme en se basant sur les indications de type dans le code, donc des indications manquantes ou incorrectes peuvent entraîner un diagramme incomplet ou incorrect._
+
+4.  Revoir la différence entre le nouveau diagramme et le précédent et vérifier manuellement si les changements sont corrects.
+    _S'assurer de ne pas supprimer des parties qui ont été ajoutées manuellement au diagramme par le passé et qui sont toujours pertinentes._
+
+5.  Ajouter le hash du commit qui a été utilisé pour générer le diagramme dans le pied de page du diagramme.
+
+6.  Exporter le diagramme sous forme de fichiers PNG et SVG et remplacer les diagrammes existants dans le répertoire `docs/architecture`. Cela peut être fait avec (par ex. [PlantText](https://www.planttext.com/))
+
+  </div>
+</details>

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

@@ -0,0 +1,138 @@
+
+
+# 📦 Runtime EventStream
+
+Le Runtime EventStream d'OpenHands est le composant principal qui permet l'exécution sécurisée et flexible des actions des agents d'IA.
+Il crée un environnement en bac à sable (sandbox) en utilisant Docker, où du code arbitraire peut être exécuté en toute sécurité sans risquer le système hôte.
+
+## Pourquoi avons-nous besoin d'un runtime en bac à sable ?
+
+OpenHands doit exécuter du code arbitraire dans un environnement sécurisé et isolé pour plusieurs raisons :
+
+1. Sécurité : L'exécution de code non fiable peut poser des risques importants pour le système hôte. Un environnement en bac à sable empêche le code malveillant d'accéder ou de modifier les ressources du système hôte
+2. Cohérence : Un environnement en bac à sable garantit que l'exécution du code est cohérente sur différentes machines et configurations, éliminant les problèmes du type "ça fonctionne sur ma machine"
+3. Contrôle des ressources : Le bac à sable permet un meilleur contrôle de l'allocation et de l'utilisation des ressources, empêchant les processus incontrôlés d'affecter le système hôte
+4. Isolation : Différents projets ou utilisateurs peuvent travailler dans des environnements isolés sans interférer les uns avec les autres ou avec le système hôte
+5. Reproductibilité : Les environnements en bac à sable facilitent la reproduction des bugs et des problèmes, car l'environnement d'exécution est cohérent et contrôlable
+
+## Comment fonctionne le Runtime ?
+
+Le système Runtime d'OpenHands utilise une architecture client-serveur implémentée avec des conteneurs Docker. Voici un aperçu de son fonctionnement :
+
+```mermaid
+graph TD
+    A[Image Docker personnalisée fournie par l'utilisateur] --> B[Backend OpenHands]
+    B -->|Construit| C[Image OH Runtime]
+    C -->|Lance| D[Exécuteur d'actions]
+    D -->|Initialise| E[Navigateur]
+    D -->|Initialise| F[Shell Bash]
+    D -->|Initialise| G[Plugins]
+    G -->|Initialise| L[Serveur Jupyter]
+
+    B -->|Génère| H[Agent]
+    B -->|Génère| I[EventStream]
+    I <--->|Exécute l'action pour
+    obtenir l'observation
+    via l'API REST
+    | D
+
+    H -->|Génère l'action| I
+    I -->|Obtient l'observation| H
+
+    subgraph "Conteneur Docker"
+    D
+    E
+    F
+    G
+    L
+    end
+```
+
+1. Entrée utilisateur : L'utilisateur fournit une image Docker de base personnalisée
+2. Construction de l'image : OpenHands construit une nouvelle image Docker (l'"image OH runtime") basée sur l'image fournie par l'utilisateur. Cette nouvelle image inclut le code spécifique à OpenHands, principalement le "client runtime"
+3. Lancement du conteneur : Lorsqu'OpenHands démarre, il lance un conteneur Docker en utilisant l'image OH runtime
+4. Initialisation du serveur d'exécution des actions : Le serveur d'exécution des actions initialise un `ActionExecutor` à l'intérieur du conteneur, mettant en place les composants nécessaires comme un shell bash et chargeant les plugins spécifiés
+5. Communication : Le backend OpenHands (`openhands/runtime/impl/eventstream/eventstream_runtime.py`) communique avec le serveur d'exécution des actions via une API RESTful, envoyant des actions et recevant des observations
+6. Exécution des actions : Le client runtime reçoit les actions du backend, les exécute dans l'environnement en bac à sable et renvoie les observations
+7. Retour des observations : Le serveur d'exécution des actions renvoie les résultats d'exécution au backend OpenHands sous forme d'observations
+
+
+Le rôle du client :
+- Il agit comme un intermédiaire entre le backend OpenHands et l'environnement en bac à sable
+- Il exécute différents types d'actions (commandes shell, opérations sur les fichiers, code Python, etc.) en toute sécurité dans le conteneur
+- Il gère l'état de l'environnement en bac à sable, y compris le répertoire de travail courant et les plugins chargés
+- Il formate et renvoie les observations au backend, assurant une interface cohérente pour le traitement des résultats
+
+
+## Comment OpenHands construit et maintient les images OH Runtime
+
+L'approche d'OpenHands pour la construction et la gestion des images runtime assure l'efficacité, la cohérence et la flexibilité dans la création et la maintenance des images Docker pour les environnements de production et de développement.
+
+Consultez le [code pertinent](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/utils/runtime_build.py) si vous souhaitez plus de détails.
+
+### Système de balises d'images
+
+OpenHands utilise un système à trois balises pour ses images runtime afin d'équilibrer la reproductibilité et la flexibilité.
+Les balises peuvent être dans l'un des 2 formats suivants :
+
+- **Balise versionnée** : `oh_v{openhands_version}_{base_image}` (ex : `oh_v0.9.9_nikolaik_s_python-nodejs_t_python3.12-nodejs22`)
+- **Balise de verrouillage** : `oh_v{openhands_version}_{16_digit_lock_hash}` (ex : `oh_v0.9.9_1234567890abcdef`)
+- **Balise source** : `oh_v{openhands_version}_{16_digit_lock_hash}_{16_digit_source_hash}`
+  (ex : `oh_v0.9.9_1234567890abcdef_1234567890abcdef`)
+
+
+#### Balise source - La plus spécifique
+
+Il s'agit des 16 premiers chiffres du MD5 du hash du répertoire pour le répertoire source. Cela donne un hash
+uniquement pour la source d'openhands
+
+
+#### Balise de verrouillage
+
+Ce hash est construit à partir des 16 premiers chiffres du MD5 de :
+- Le nom de l'image de base sur laquelle l'image a été construite (ex : `nikolaik/python-nodejs:python3.12-nodejs22`)
+- Le contenu du `pyproject.toml` inclus dans l'image.
+- Le contenu du `poetry.lock` inclus dans l'image.
+
+Cela donne effectivement un hash pour les dépendances d'Openhands indépendamment du code source.
+
+#### Balise versionnée - La plus générique
+
+Cette balise est une concaténation de la version d'openhands et du nom de l'image de base (transformé pour s'adapter au standard des balises).
+
+#### Processus de construction
+
+Lors de la génération d'une image...
+
+- **Pas de reconstruction** : OpenHands vérifie d'abord si une image avec la même **balise source la plus spécifique** existe. S'il existe une telle image,
+  aucune construction n'est effectuée - l'image existante est utilisée.
+- **Reconstruction la plus rapide** : OpenHands vérifie ensuite si une image avec la **balise de verrouillage générique** existe. S'il existe une telle image,
+  OpenHands construit une nouvelle image basée sur celle-ci, en contournant toutes les étapes d'installation (comme `poetry install` et
+  `apt-get`) sauf une opération finale pour copier le code source actuel. La nouvelle image est balisée avec une
+  balise **source** uniquement.
+- **Reconstruction correcte** : Si ni une balise **source** ni une balise **de verrouillage** n'existe, une image sera construite sur la base de l'image avec la balise **versionnée**.
+  Dans l'image avec la balise versionnée, la plupart des dépendances devraient déjà être installées, ce qui permet de gagner du temps.
+- **Reconstruction la plus lente** : Si les trois balises n'existent pas, une toute nouvelle image est construite à partir de
+  l'image de base (ce qui est une opération plus lente). Cette nouvelle image est balisée avec toutes les balises **source**, **de verrouillage** et **versionnée**.
+
+Cette approche de balisage permet à OpenHands de gérer efficacement les environnements de développement et de production.
+
+1. Un code source et un Dockerfile identiques produisent toujours la même image (via des balises basées sur des hashs)
+2. Le système peut reconstruire rapidement les images lorsque des changements mineurs se produisent (en s'appuyant sur des images compatibles récentes)
+3. La balise **de verrouillage** (ex : `runtime:oh_v0.9.3_1234567890abcdef`) pointe toujours vers la dernière version pour une combinaison particulière d'image de base, de dépendances et de version d'OpenHands
+
+## Système de plugins du Runtime
+
+Le Runtime d'OpenHands prend en charge un système de plugins qui permet d'étendre les fonctionnalités et de personnaliser l'environnement d'exécution. Les plugins sont initialisés lorsque le client runtime démarre.
+
+Consultez [un exemple de plugin Jupyter ici](https://github.com/All-Hands-AI/OpenHands/blob/ecf4aed28b0cf7c18d4d8ff554883ba182fc6bdd/openhands/runtime/plugins/jupyter/__init__.py#L21-L55) si vous souhaitez implémenter votre propre plugin.
+
+*Plus de détails sur le système de plugins sont encore en construction - les contributions sont les bienvenues !*
+
+Aspects clés du système de plugins :
+
+1. Définition des plugins : Les plugins sont définis comme des classes Python qui héritent d'une classe de base `Plugin`
+2. Enregistrement des plugins : Les plugins disponibles sont enregistrés dans un dictionnaire `ALL_PLUGINS`
+3. Spécification des plugins : Les plugins sont associés à `Agent.sandbox_plugins: list[PluginRequirement]`. Les utilisateurs peuvent spécifier quels plugins charger lors de l'initialisation du runtime
+4. Initialisation : Les plugins sont initialisés de manière asynchrone lorsque le client runtime démarre
+5. Utilisation : Le client runtime peut utiliser les plugins initialisés pour étendre ses capacités (par exemple, le JupyterPlugin pour exécuter des cellules IPython)

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

@@ -0,0 +1,395 @@
+# Options de configuration
+
+Ce guide détaille toutes les options de configuration disponibles pour OpenHands, vous aidant à personnaliser son comportement et à l'intégrer avec d'autres services.
+
+:::note
+Si vous exécutez en [Mode GUI](https://docs.all-hands.dev/modules/usage/how-to/gui-mode), les paramètres disponibles dans l'interface utilisateur des paramètres auront toujours
+la priorité.
+:::
+
+---
+
+# Table des matières
+
+1. [Configuration de base](#configuration-de-base)
+   - [Clés API](#clés-api)
+   - [Espace de travail](#espace-de-travail)
+   - [Débogage et journalisation](#débogage-et-journalisation)
+   - [Gestion des sessions](#gestion-des-sessions)
+   - [Trajectoires](#trajectoires)
+   - [Stockage de fichiers](#stockage-de-fichiers)
+   - [Gestion des tâches](#gestion-des-tâches)
+   - [Configuration du bac à sable](#configuration-du-bac-à-sable)
+   - [Divers](#divers)
+2. [Configuration LLM](#configuration-llm)
+   - [Informations d'identification AWS](#informations-didentification-aws)
+   - [Configuration de l'API](#configuration-de-lapi)
+   - [Fournisseur LLM personnalisé](#fournisseur-llm-personnalisé)
+   - [Embeddings](#embeddings)
+   - [Gestion des messages](#gestion-des-messages)
+   - [Sélection du modèle](#sélection-du-modèle)
+   - [Nouvelles tentatives](#nouvelles-tentatives)
+   - [Options avancées](#options-avancées)
+3. [Configuration de l'agent](#configuration-de-lagent)
+   - [Configuration du micro-agent](#configuration-du-micro-agent)
+   - [Configuration de la mémoire](#configuration-de-la-mémoire)
+   - [Configuration LLM](#configuration-llm-2)
+   - [Configuration de l'espace d'action](#configuration-de-lespace-daction)
+   - [Utilisation du micro-agent](#utilisation-du-micro-agent)
+4. [Configuration du bac à sable](#configuration-du-bac-à-sable-2)
+   - [Exécution](#exécution)
+   - [Image de conteneur](#image-de-conteneur)
+   - [Mise en réseau](#mise-en-réseau)
+   - [Linting et plugins](#linting-et-plugins)
+   - [Dépendances et environnement](#dépendances-et-environnement)
+   - [Évaluation](#évaluation)
+5. [Configuration de sécurité](#configuration-de-sécurité)
+   - [Mode de confirmation](#mode-de-confirmation)
+   - [Analyseur de sécurité](#analyseur-de-sécurité)
+
+---
+
+## Configuration de base
+
+Les options de configuration de base sont définies dans la section `[core]` du fichier `config.toml`.
+
+**Clés API**
+- `e2b_api_key`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : Clé API pour E2B
+
+- `modal_api_token_id`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : ID du jeton API pour Modal
+
+- `modal_api_token_secret`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : Secret du jeton API pour Modal
+
+**Espace de travail**
+- `workspace_base`
+  - Type : `str`
+  - Valeur par défaut : `"./workspace"`
+  - Description : Chemin de base pour l'espace de travail
+
+- `cache_dir`
+  - Type : `str`
+  - Valeur par défaut : `"/tmp/cache"`
+  - Description : Chemin du répertoire de cache
+
+**Débogage et journalisation**
+- `debug`
+  - Type : `bool`
+  - Valeur par défaut : `false`
+  - Description : Activer le débogage
+
+- `disable_color`
+  - Type : `bool`
+  - Valeur par défaut : `false`
+  - Description : Désactiver la couleur dans la sortie du terminal
+
+**Trajectoires**
+- `save_trajectory_path`
+  - Type : `str`
+  - Valeur par défaut : `"./trajectories"`
+  - Description : Chemin pour stocker les trajectoires (peut être un dossier ou un fichier). Si c'est un dossier, les trajectoires seront enregistrées dans un fichier nommé avec l'ID de session et l'extension .json, dans ce dossier.
+
+**Stockage de fichiers**
+- `file_store_path`
+  - Type : `str`
+  - Valeur par défaut : `"/tmp/file_store"`
+  - Description : Chemin de stockage des fichiers
+
+- `file_store`
+  - Type : `str`
+  - Valeur par défaut : `"memory"`
+  - Description : Type de stockage de fichiers
+
+- `file_uploads_allowed_extensions`
+  - Type : `list of str`
+  - Valeur par défaut : `[".*"]`
+  - Description : Liste des extensions de fichiers autorisées pour les téléchargements
+
+- `file_uploads_max_file_size_mb`
+  - Type : `int`
+  - Valeur par défaut : `0`
+  - Description : Taille maximale des fichiers pour les téléchargements, en mégaoctets
+
+- `file_uploads_restrict_file_types`
+  - Type : `bool`
+  - Valeur par défaut : `false`
+  - Description : Restreindre les types de fichiers pour les téléchargements de fichiers
+
+- `file_uploads_allowed_extensions`
+  - Type : `list of str`
+  - Valeur par défaut : `[".*"]`
+  - Description : Liste des extensions de fichiers autorisées pour les téléchargements
+
+**Gestion des tâches**
+- `max_budget_per_task`
+  - Type : `float`
+  - Valeur par défaut : `0.0`
+  - Description : Budget maximal par tâche (0.0 signifie aucune limite)
+
+- `max_iterations`
+  - Type : `int`
+  - Valeur par défaut : `100`
+  - Description : Nombre maximal d'itérations
+
+**Configuration du bac à sable**
+- `workspace_mount_path_in_sandbox`
+  - Type : `str`
+  - Valeur par défaut : `"/workspace"`
+  - Description : Chemin de montage de l'espace de travail dans le bac à sable
+
+- `workspace_mount_path`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : Chemin de montage de l'espace de travail
+
+- `workspace_mount_rewrite`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : Chemin pour réécrire le chemin de montage de l'espace de travail. Vous pouvez généralement ignorer cela, cela fait référence à des cas spéciaux d'exécution à l'intérieur d'un autre conteneur.
+
+**Divers**
+- `run_as_openhands`
+  - Type : `bool`
+  - Valeur par défaut : `true`
+  - Description : Exécuter en tant qu'OpenHands
+
+- `runtime`
+  - Type : `str`
+  - Valeur par défaut : `"eventstream"`
+  - Description : Environnement d'exécution
+
+- `default_agent`
+  - Type : `str`
+  - Valeur par défaut : `"CodeActAgent"`
+  - Description : Nom de l'agent par défaut
+
+- `jwt_secret`
+  - Type : `str`
+  - Valeur par défaut : `uuid.uuid4().hex`
+  - Description : Secret JWT pour l'authentification. Veuillez le définir sur votre propre valeur.
+
+## Configuration LLM
+
+Les options de configuration LLM (Large Language Model) sont définies dans la section `[llm]` du fichier `config.toml`.
+
+Pour les utiliser avec la commande docker, passez `-e LLM_<option>`. Exemple : `-e LLM_NUM_RETRIES`.
+
+:::note
+Pour les configurations de développement, vous pouvez également définir des configurations LLM personnalisées. Voir [Configurations LLM personnalisées](./llms/custom-llm-configs) pour plus de détails.
+:::
+
+**Informations d'identification AWS**
+- `aws_access_key_id`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : ID de clé d'accès AWS
+
+- `aws_region_name`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : Nom de la région AWS
+
+- `aws_secret_access_key`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : Clé d'accès secrète AWS
+
+**Configuration de l'API**
+- `api_key`
+  - Type : `str`
+  - Valeur par défaut : `None`
+  - Description : Clé API à utiliser
+
+- `base_url`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : URL de base de l'API
+
+- `api_version`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : Version de l'API
+
+- `input_cost_per_token`
+  - Type : `float`
+  - Valeur par défaut : `0.0`
+  - Description : Coût par jeton d'entrée
+
+- `output_cost_per_token`
+  - Type : `float`
+  - Valeur par défaut : `0.0`
+  - Description : Coût par jeton de sortie
+
+**Fournisseur LLM personnalisé**
+- `custom_llm_provider`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : Fournisseur LLM personnalisé
+
+**Embeddings**
+- `embedding_base_url`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : URL de base de l'API d'embedding
+
+- `embedding_deployment_name`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : Nom du déploiement d'embedding
+
+- `embedding_model`
+  - Type : `str`
+  - Valeur par défaut : `"local"`
+  - Description : Modèle d'embedding à utiliser
+
+**Gestion des messages**
+- `max_message_chars`
+  - Type : `int`
+  - Valeur par défaut : `30000`
+  - Description : Le nombre maximum approximatif de caractères dans le contenu d'un événement inclus dans l'invite au LLM. Les observations plus grandes sont tronquées.
+
+- `max_input_tokens`
+  - Type : `int`
+  - Valeur par défaut : `0`
+  - Description : Nombre maximal de jetons d'entrée
+
+- `max_output_tokens`
+  - Type : `int`
+  - Valeur par défaut : `0`
+  - Description : Nombre maximal de jetons de sortie
+
+**Sélection du modèle**
+- `model`
+  - Type : `str`
+  - Valeur par défaut : `"claude-3-5-sonnet-20241022"`
+  - Description : Modèle à utiliser
+
+**Nouvelles tentatives**
+- `num_retries`
+  - Type : `int`
+  - Valeur par défaut : `8`
+  - Description : Nombre de nouvelles tentatives à effectuer
+
+- `retry_max_wait`
+  - Type : `int`
+  - Valeur par défaut : `120`
+  - Description : Temps d'attente maximal (en secondes) entre les tentatives de nouvelle tentative
+
+- `retry_min_wait`
+  - Type : `int`
+  - Valeur par défaut : `15`
+  - Description : Temps d'attente minimal (en secondes) entre les tentatives de nouvelle tentative
+
+- `retry_multiplier`
+  - Type : `float`
+  - Valeur par défaut : `2.0`
+  - Description : Multiplicateur pour le calcul du backoff exponentiel
+
+**Options avancées**
+- `drop_params`
+  - Type : `bool`
+  - Valeur par défaut : `false`
+  - Description : Supprimer tous les paramètres non mappés (non pris en charge) sans provoquer d'exception
+
+- `caching_prompt`
+  - Type : `bool`
+  - Valeur par défaut : `true`
+  - Description : Utiliser la fonctionnalité de mise en cache des invites si elle est fournie par le LLM et prise en charge
+
+- `ollama_base_url`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : URL de base pour l'API OLLAMA
+
+- `temperature`
+  - Type : `float`
+  - Valeur par défaut : `0.0`
+  - Description : Température pour l'API
+
+- `timeout`
+  - Type : `int`
+  - Valeur par défaut : `0`
+  - Description : Délai d'expiration pour l'API
+
+- `top_p`
+  - Type : `float`
+  - Valeur par défaut : `1.0`
+  - Description : Top p pour l'API
+
+- `disable_vision`
+  - Type : `bool`
+  - Valeur par défaut : `None`
+  - Description : Si le modèle est capable de vision, cette option permet de désactiver le traitement des images (utile pour réduire les coûts)
+
+## Configuration de l'agent
+
+Les options de configuration de l'agent sont définies dans les sections `[agent]` et `[agent.<agent_name>]` du fichier `config.toml`.
+
+**Configuration du micro-agent**
+- `micro_agent_name`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : Nom du micro-agent à utiliser pour cet agent
+
+**Configuration de la mémoire**
+- `memory_enabled`
+  - Type : `bool`
+  - Valeur par défaut : `false`
+  - Description : Si la mémoire à long terme (embeddings) est activée
+
+- `memory_max_threads`
+  - Type : `int`
+  - Valeur par défaut : `3`
+  - Description : Le nombre maximum de threads indexant en même temps pour les embeddings
+
+**Configuration LLM**
+- `llm_config`
+  - Type : `str`
+  - Valeur par défaut : `'your-llm-config-group'`
+  - Description : Le nom de la configuration LLM à utiliser
+
+**Configuration de l'espace d'action**
+- `function_calling`
+  - Type : `bool`
+  - Valeur par défaut : `true`
+  - Description : Si l'appel de fonction est activé
+
+- `codeact_enable_browsing`
+  - Type : `bool`
+  - Valeur par défaut : `false`
+  - Description : Si le délégué de navigation est activé dans l'espace d'action (fonctionne uniquement avec l'appel de fonction)
+
+- `codeact_enable_llm_editor`
+  - Type : `bool`
+  - Valeur par défaut : `false`
+  - Description : Si l'éditeur LLM est activé dans l'espace d'action (fonctionne uniquement avec l'appel de fonction)
+
+**Utilisation du micro-agent**
+- `enable_prompt_extensions`
+  - Type : `bool`
+  - Valeur par défaut : `true`
+  - Description : Indique si l'utilisation des micro-agents est activée ou non
+
+- `disabled_microagents`
+  - Type : `list of str`
+  - Valeur par défaut : `None`
+  - Description : Liste des micro-agents à désactiver
+
+### Exécution
+- `timeout`
+  - Type : `int`
+  - Valeur par défaut : `120`
+  - Description : Délai d'expiration du bac à sable, en secondes
+
+- `user_id`
+  - Type : `int`
+  - Valeur par défaut : `1000`
+  - Description : ID de l'utilisateur du bac à sable

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

@@ -0,0 +1,97 @@
+# 💿 Comment Créer un Soutien Docker sur Mesure
+
+Le sandbox par défaut OpenHands est équipé d'une configuration ubuntu minimaliste. Votre cas d'utilisation pourrait nécessiter des logiciels installés par défaut. Cet article vous enseignera comment réaliser cela en utilisant une image docker personnalisée.
+
+## Configuration
+
+Assurez-vous de pouvoir utiliser OpenHands en suivant la documentation [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
+
+## Créer Votre Image Docker
+
+Ensuite, vous devez créer votre image docker personnalisée qui doit être basée sur debian/ubuntu. Par exemple, si nous souhaitons que OpenHands ait accès au "node" binaire, nous utiliserions ce Dockerfile:
+
+```bash
+# Commencez avec l'image ubuntu la plus récente
+FROM ubuntu:latest
+
+# Effectuez les mises à jour nécessaires
+RUN apt-get update && apt-get install
+
+# Installez nodejs
+RUN apt-get install -y nodejs
+```
+
+Ensuite, construisez votre image docker avec le nom de votre choix. Par exemple "image_personnalisée". Pour cela, créez un répertoire et placez le fichier à l'intérieur avec le nom "Dockerfile", puis dans le répertoire exécutez cette commande:
+
+```bash
+docker build -t image_personnalisée .
+```
+
+Cela produira une nouvelle image appelée ```image_personnalisée``` qui sera disponible dans Docker Engine.
+
+> Remarque: Dans la configuration décrite ici, OpenHands va fonctionner en tant que utilisateur "openhands" à l'intérieur du sandbox et donc tous les packages installés via le Dockerfile seront disponibles pour tous les utilisateurs sur le système, pas seulement root.
+>
+> L'installation avec apt-get ci-dessus installe nodejs pour tous les utilisateurs.
+
+## Spécifiez votre image personnalisée dans le fichier config.toml
+
+La configuration OpenHands se fait via le fichier de niveau supérieur ```config.toml``` .
+Créez un fichier ```config.toml``` dans le répertoire OpenHands et entrez ces contenus:
+
+```toml
+[core]
+workspace_base="./workspace"
+run_as_openhands=true
+sandbox_base_container_image="image_personnalisée"
+```
+
+> Assurez-vous que ```sandbox_base_container_image``` est défini sur le nom de votre image personnalisée précédente.
+
+## Exécution
+
+Exécutez OpenHands en exécutant ```make run``` dans le répertoire racine.
+
+Naviguez vers ```localhost:3001``` et vérifiez si vos dépendances souhaitées sont disponibles.
+
+Dans le cas de l'exemple ci-dessus, la commande ```node -v``` dans la console produit ```v18.19.1```
+
+Félicitations !
+
+## Explication technique
+
+Lorsqu'une image personnalisée est utilisée pour la première fois, elle ne sera pas trouvée et donc elle sera construite (à l'exécution ultérieure, l'image construite sera trouvée et renvoyée).
+
+L'image personnalisée est construite avec [_build_sandbox_image()](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/docker/image_agnostic_util.py#L29), qui crée un fichier docker en utilisant votre image personnalisée comme base et configure ensuite l'environnement pour OpenHands, comme ceci:
+
+```python
+dockerfile_content = (
+        f'FROM {base_image}\n'
+        'RUN apt update && apt install -y openssh-server wget sudo\n'
+        'RUN mkdir -p -m0755 /var/run/sshd\n'
+        'RUN mkdir -p /openhands && mkdir -p /openhands/logs && chmod 777 /openhands/logs\n'
+        'RUN wget "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"\n'
+        'RUN bash Miniforge3-$(uname)-$(uname -m).sh -b -p /openhands/miniforge3\n'
+        'RUN bash -c ". /openhands/miniforge3/etc/profile.d/conda.sh && conda config --set changeps1 False && conda config --append channels conda-forge"\n'
+        'RUN echo "export PATH=/openhands/miniforge3/bin:$PATH" >> ~/.bashrc\n'
+        'RUN echo "export PATH=/openhands/miniforge3/bin:$PATH" >> /openhands/bash.bashrc\n'
+    ).strip()
+```
+
+> Remarque: Le nom de l'image est modifié via [_get_new_image_name()](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/docker/image_agnostic_util.py#L63) et c'est ce nom modifié qui sera recherché lors des exécutions ultérieures.
+
+## Dépannage / Erreurs
+
+### Erreur: ```useradd: UID 1000 est non unique```
+Si vous voyez cette erreur dans la sortie de la console, il s'agit du fait que OpenHands essaie de créer le utilisateur openhands dans le sandbox avec un ID d'utilisateur de 1000, cependant cet ID d'utilisateur est déjà utilisé dans l'image (pour une raison inconnue). Pour résoudre ce problème, changez la valeur du champ sandbox_user_id dans le fichier config.toml en une valeur différente:
+
+```toml
+[core]
+workspace_base="./workspace"
+run_as_openhands=true
+sandbox_base_container_image="image_personnalisée"
+sandbox_user_id="1001"
+```
+
+### Erreurs de port d'utilisation
+
+Si vous voyez un message d'erreur indiquant que le port est utilisé ou indisponible, essayez de supprimer toutes les containers docker en cours d'exécution (exécutez `docker ps` et `docker rm` des containers concernés) puis ré-exécutez ```make run```

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

@@ -0,0 +1,41 @@
+
+
+# ✅ Fournir des commentaires
+
+Lorsque vous utilisez OpenHands, vous rencontrerez des cas où les choses fonctionnent bien, et d'autres où elles ne fonctionnent pas. Nous vous encourageons à fournir des commentaires lorsque vous utilisez OpenHands pour aider à donner des retours à l'équipe de développement, et peut-être plus important encore, créer un corpus ouvert d'exemples d'entraînement d'agents de codage -- Share-OpenHands !
+
+## 📝 Comment fournir des commentaires
+
+Fournir des commentaires est facile ! Lorsque vous utilisez OpenHands, vous pouvez appuyer sur le bouton pouce vers le haut ou pouce vers le bas à tout moment pendant votre interaction. Vous serez invité à fournir votre adresse e-mail (par exemple, afin que nous puissions vous contacter si nous voulons poser des questions de suivi), et vous pouvez choisir si vous souhaitez fournir des commentaires publiquement ou en privé.
+
+<iframe width="560" height="315" src="https://www.youtube.com/embed/5rFx-StMVV0?si=svo7xzp6LhGK_GXr" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
+
+## 📜 Utilisation des données et confidentialité
+
+### Paramètres de partage des données
+
+Lorsque vous soumettez des données, vous pouvez les soumettre publiquement ou en privé.
+
+* Les données **publiques** seront distribuées sous la licence MIT, comme OpenHands lui-même, et pourront être utilisées par la communauté pour entraîner et tester des modèles. Évidemment, les commentaires que vous pouvez rendre publics seront plus précieux pour la communauté dans son ensemble, donc lorsque vous ne traitez pas d'informations sensibles, nous vous encourageons à choisir cette option !
+* Les données **privées** ne seront partagées qu'avec l'équipe OpenHands dans le but d'améliorer OpenHands.
+
+### Qui collecte et stocke les données ?
+
+Les données sont collectées et stockées par [All Hands AI](https://all-hands.dev), une entreprise fondée par les mainteneurs d'OpenHands pour soutenir et améliorer OpenHands.
+
+### Comment les données publiques seront-elles publiées ?
+
+Les données publiques seront publiées lorsque nous atteindrons des jalons fixes, tels que 1 000 exemples publics, 10 000 exemples publics, etc.
+À ce moment-là, nous suivrons le processus de publication suivant :
+
+1. Toutes les personnes qui ont contribué à des commentaires publics recevront un e-mail décrivant la publication des données et auront la possibilité de se retirer.
+2. La ou les personnes en charge de la publication des données effectueront un contrôle de la qualité des données, en supprimant les commentaires de mauvaise qualité, en supprimant les adresses e-mail des soumissionnaires et en essayant de supprimer toute information sensible.
+3. Les données seront publiées publiquement sous la licence MIT via des sites couramment utilisés tels que GitHub ou Hugging Face.
+
+### Que faire si je veux que mes données soient supprimées ?
+
+Pour les données sur les serveurs d'All Hands AI, nous sommes heureux de les supprimer sur demande :
+
+**Une pièce de données :** Si vous souhaitez supprimer une pièce de données, nous ajouterons prochainement un mécanisme pour supprimer les pièces de données en utilisant le lien et le mot de passe qui s'affichent sur l'interface lorsque vous soumettez des données.
+
+**Toutes les données :** Si vous souhaitez que toutes vos données soient supprimées, ou si vous n'avez pas l'ID et le mot de passe que vous avez reçus lors de la soumission des données, veuillez contacter `contact@all-hands.dev` à partir de l'adresse e-mail que vous avez enregistrée lorsque vous avez initialement soumis les données.

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

@@ -0,0 +1,113 @@
+
+
+# Démarrer avec OpenHands
+
+Vous avez donc [installé OpenHands](./installation) et avez
+[configuré votre LLM](./installation#setup). Et maintenant ?
+
+OpenHands peut vous aider à aborder une grande variété de tâches d'ingénierie. Mais la technologie
+est encore nouvelle, et nous sommes loin d'avoir des agents capables de prendre en charge des tâches
+d'ingénierie vastes et compliquées sans aucune aide. Il est donc important de se faire une idée de ce que l'agent
+fait bien, et où il pourrait avoir besoin d'un coup de main.
+
+## Hello World
+
+La première chose que vous voudrez peut-être essayer est un simple exemple "hello world".
+Cela peut être plus compliqué qu'il n'y paraît !
+
+Essayez de demander à l'agent :
+> Veuillez écrire un script bash hello.sh qui affiche "hello world!"
+
+Vous devriez constater que l'agent non seulement écrit le script, mais définit également les
+permissions correctes et exécute le script pour vérifier la sortie.
+
+Vous pouvez continuer à demander à l'agent d'affiner votre code. C'est une excellente façon de
+travailler avec les agents. Commencez simplement, et itérez.
+
+> Veuillez modifier hello.sh pour qu'il accepte un nom comme premier argument, mais par défaut "world"
+
+Vous pouvez également travailler dans n'importe quel langage dont vous avez besoin, bien que l'agent puisse avoir besoin de passer du
+temps à configurer son environnement !
+
+> Veuillez convertir hello.sh en un script Ruby, et l'exécuter
+
+## Construire à partir de zéro
+
+Les agents se débrouillent exceptionnellement bien pour les tâches "greenfield" (tâches où ils n'ont pas besoin
+de contexte sur une base de code existante) et ils peuvent simplement commencer à partir de zéro.
+
+Il est préférable de commencer par une tâche simple, puis d'itérer. Il est également préférable d'être
+aussi précis que possible sur ce que vous voulez, sur la pile technologique à utiliser, etc.
+
+Par exemple, nous pourrions construire une application TODO :
+
+> Veuillez créer une application basique de liste de tâches en React. Elle devrait être uniquement frontend, et tout l'état
+> devrait être conservé dans localStorage.
+
+Nous pouvons continuer à itérer sur l'application une fois le squelette en place :
+
+> Veuillez permettre d'ajouter une date d'échéance optionnelle à chaque tâche
+
+Tout comme avec le développement normal, il est bon de commiter et de pousser votre code fréquemment.
+De cette façon, vous pouvez toujours revenir à un ancien état si l'agent dévie.
+Vous pouvez demander à l'agent de commiter et de pousser pour vous :
+
+> Veuillez commiter les changements et les pousser sur une nouvelle branche appelée "feature/due-dates"
+
+
+## Ajouter du nouveau code
+
+OpenHands peut également faire un excellent travail en ajoutant du nouveau code à une base de code existante.
+
+Par exemple, vous pouvez demander à OpenHands d'ajouter une nouvelle action GitHub à votre projet
+qui analyse votre code. OpenHands peut jeter un coup d'œil à votre base de code pour voir quel langage
+il doit utiliser, mais ensuite il peut simplement déposer un nouveau fichier dans `./github/workflows/lint.yml`
+
+> Veuillez ajouter une action GitHub qui analyse le code dans ce dépôt
+
+Certaines tâches peuvent nécessiter un peu plus de contexte. Bien qu'OpenHands puisse utiliser `ls` et `grep`
+pour rechercher dans votre base de code, fournir le contexte à l'avance lui permet d'aller plus vite,
+et plus précisément. Et cela vous coûtera moins de tokens !
+
+> Veuillez modifier ./backend/api/routes.js pour ajouter une nouvelle route qui renvoie une liste de toutes les tâches
+
+> Veuillez ajouter un nouveau composant React qui affiche une liste de Widgets dans le répertoire ./frontend/components.
+> Il devrait utiliser le composant Widget existant.
+
+## Refactoring
+
+OpenHands est excellent pour refactoriser du code existant, surtout par petits morceaux.
+Vous ne voulez probablement pas essayer de réarchitecturer toute votre base de code, mais diviser
+les longs fichiers et fonctions, renommer les variables, etc. ont tendance à très bien fonctionner.
+
+> Veuillez renommer toutes les variables à une lettre dans ./app.go
+
+> Veuillez diviser la fonction `build_and_deploy_widgets` en deux fonctions, `build_widgets` et `deploy_widgets` dans widget.php
+
+> Veuillez diviser ./api/routes.js en fichiers séparés pour chaque route
+
+## Corrections de bugs
+
+OpenHands peut également vous aider à traquer et corriger des bugs dans votre code. Mais, comme tout
+développeur le sait, la correction de bugs peut être extrêmement délicate, et souvent OpenHands aura besoin de plus de contexte.
+Cela aide si vous avez diagnostiqué le bug, mais que vous voulez qu'OpenHands comprenne la logique.
+
+> Actuellement, le champ email dans le point de terminaison `/subscribe` rejette les domaines .io. Veuillez corriger cela.
+
+> La fonction `search_widgets` dans ./app.py effectue une recherche sensible à la casse. Veuillez la rendre insensible à la casse.
+
+Il est souvent utile de faire du développement piloté par les tests lors de la correction de bugs avec un agent.
+Vous pouvez demander à l'agent d'écrire un nouveau test, puis d'itérer jusqu'à ce qu'il corrige le bug :
+
+> La fonction `hello` plante sur la chaîne vide. Veuillez écrire un test qui reproduit ce bug, puis corrigez le code pour qu'il passe.
+
+## Plus
+
+OpenHands est capable d'aider sur à peu près n'importe quelle tâche de codage. Mais il faut de la pratique
+pour en tirer le meilleur parti. N'oubliez pas de :
+* Garder vos tâches petites
+* Être aussi précis que possible
+* Fournir autant de contexte que possible
+* Commiter et pousser fréquemment
+
+Voir [Bonnes pratiques de prompting](./prompting/prompting-best-practices) pour plus de conseils sur la façon de tirer le meilleur parti d'OpenHands.

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

@@ -0,0 +1,112 @@
+
+
+# Mode CLI
+
+OpenHands peut être exécuté en mode CLI interactif, ce qui permet aux utilisateurs de démarrer une session interactive via la ligne de commande.
+
+Ce mode est différent du [mode headless](headless-mode), qui est non interactif et mieux adapté aux scripts.
+
+## Avec Python
+
+Pour démarrer une session OpenHands interactive via la ligne de commande, suivez ces étapes :
+
+1. Assurez-vous d'avoir suivi les [instructions de configuration de développement](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
+
+2. Exécutez la commande suivante :
+
+```bash
+poetry run python -m openhands.core.cli
+```
+
+Cette commande démarrera une session interactive où vous pourrez saisir des tâches et recevoir des réponses d'OpenHands.
+
+Vous devrez vous assurer de définir votre modèle, votre clé API et d'autres paramètres via des variables d'environnement
+[ou le fichier `config.toml`](https://github.com/All-Hands-AI/OpenHands/blob/main/config.template.toml).
+
+
+## Avec Docker
+
+Pour exécuter OpenHands en mode CLI avec Docker, suivez ces étapes :
+
+1. Définissez `WORKSPACE_BASE` sur le répertoire que vous voulez qu'OpenHands modifie :
+
+```bash
+WORKSPACE_BASE=$(pwd)/workspace
+```
+
+2. Définissez `LLM_MODEL` sur le modèle que vous voulez utiliser :
+
+```bash
+LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"
+
+```
+
+3. Définissez `LLM_API_KEY` sur votre clé API :
+
+```bash
+LLM_API_KEY="sk_test_12345"
+```
+
+4. Exécutez la commande Docker suivante :
+
+```bash
+docker run -it \
+    --pull=always \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.21-nikolaik \
+    -e SANDBOX_USER_ID=$(id -u) \
+    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
+    -e LLM_API_KEY=$LLM_API_KEY \
+    -e LLM_MODEL=$LLM_MODEL \
+    -v $WORKSPACE_BASE:/opt/workspace_base \
+    -v /var/run/docker.sock:/var/run/docker.sock \
+    --add-host host.docker.internal:host-gateway \
+    --name openhands-app-$(date +%Y%m%d%H%M%S) \
+    docker.all-hands.dev/all-hands-ai/openhands:0.21 \
+    python -m openhands.core.cli
+```
+
+Cette commande démarrera une session interactive dans Docker où vous pourrez saisir des tâches et recevoir des réponses d'OpenHands.
+
+## Exemples de commandes CLI et de sorties attendues
+
+Voici quelques exemples de commandes CLI et leurs sorties attendues :
+
+### Exemple 1 : Tâche simple
+
+```bash
+How can I help? >> Écrivez un script Python qui affiche "Hello, World!"
+```
+
+Sortie attendue :
+
+```bash
+🤖 Bien sûr ! Voici un script Python qui affiche "Hello, World!" :
+
+❯ print("Hello, World!")
+```
+
+### Exemple 2 : Commande Bash
+
+```bash
+How can I help? >> Créez un répertoire nommé "test_dir"
+```
+
+Sortie attendue :
+
+```bash
+🤖 Création d'un répertoire nommé "test_dir" :
+
+❯ mkdir test_dir
+```
+
+### Exemple 3 : Gestion des erreurs
+
+```bash
+How can I help? >> Supprimez un fichier inexistant
+```
+
+Sortie attendue :
+
+```bash
+🤖 Une erreur s'est produite. Veuillez réessayer.
+```

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/custom-sandbox-guide.md

@@ -0,0 +1,61 @@
+
+
+# Sandbox Personnalisé
+
+Le sandbox est l'endroit où l'agent effectue ses tâches. Au lieu d'exécuter des commandes directement sur votre ordinateur (ce qui pourrait être risqué), l'agent les exécute à l'intérieur d'un conteneur Docker.
+
+Le sandbox OpenHands par défaut (`python-nodejs:python3.12-nodejs22` de [nikolaik/python-nodejs](https://hub.docker.com/r/nikolaik/python-nodejs)) est livré avec certains paquets installés tels que Python et Node.js mais peut nécessiter l'installation d'autres logiciels par défaut.
+
+Vous avez deux options pour la personnalisation :
+
+1. Utiliser une image existante avec les logiciels requis.
+2. Créer votre propre image Docker personnalisée.
+
+Si vous choisissez la première option, vous pouvez passer la section `Créer Votre Image Docker`.
+
+## Créer Votre Image Docker
+
+Pour créer une image Docker personnalisée, elle doit être basée sur Debian.
+
+Par exemple, si vous voulez qu'OpenHands ait `ruby` installé, créez un `Dockerfile` avec le contenu suivant :
+
+```dockerfile
+FROM debian:latest
+
+# Installer les paquets requis
+RUN apt-get update && apt-get install -y ruby
+```
+
+Enregistrez ce fichier dans un dossier. Ensuite, construisez votre image Docker (par exemple, nommée custom-image) en naviguant vers le dossier dans le terminal et en exécutant :
+
+```bash
+docker build -t custom-image .
+```
+
+Cela produira une nouvelle image appelée `custom-image`, qui sera disponible dans Docker.
+
+> Notez que dans la configuration décrite dans ce document, OpenHands s'exécutera en tant qu'utilisateur "openhands" à l'intérieur du sandbox et donc tous les paquets installés via le docker file devraient être disponibles pour tous les utilisateurs du système, pas seulement root.
+
+## Utilisation du Workflow de Développement
+
+### Configuration
+
+Tout d'abord, assurez-vous de pouvoir exécuter OpenHands en suivant les instructions dans [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
+
+### Spécifier l'Image de Base du Sandbox
+
+Dans le fichier `config.toml` dans le répertoire OpenHands, définissez `sandbox_base_container_image` sur l'image que vous souhaitez utiliser. Cela peut être une image que vous avez déjà extraite ou une que vous avez construite :
+
+```bash
+[core]
+...
+sandbox_base_container_image="custom-image"
+```
+
+### Exécution
+
+Exécutez OpenHands en exécutant ```make run``` dans le répertoire de niveau supérieur.
+
+## Explication Technique
+
+Veuillez vous référer à la [section image docker personnalisée de la documentation d'exécution](https://docs.all-hands.dev/modules/usage/architecture/runtime#advanced-how-openhands-builds-and-maintains-od-runtime-images) pour plus de détails.

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

@@ -0,0 +1,73 @@
+
+
+# Débogage
+
+Ce qui suit est destiné à servir d'introduction au débogage d'OpenHands à des fins de développement.
+
+## Serveur / VSCode
+
+Le `launch.json` suivant permettra de déboguer les éléments agent, contrôleur et serveur, mais pas le bac à sable (qui s'exécute dans docker). Il ignorera toutes les modifications à l'intérieur du répertoire `workspace/` :
+
+```
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "OpenHands CLI",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "openhands.core.cli",
+            "justMyCode": false
+        },
+        {
+            "name": "OpenHands WebApp",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "uvicorn",
+            "args": [
+                "openhands.server.listen:app",
+                "--reload",
+                "--reload-exclude",
+                "${workspaceFolder}/workspace",
+                "--port",
+                "3000"
+            ],
+            "justMyCode": false
+        }
+    ]
+}
+```
+
+Des configurations de débogage plus spécifiques qui incluent plus de paramètres peuvent être spécifiées :
+
+```
+    ...
+    {
+      "name": "Debug CodeAct",
+      "type": "debugpy",
+      "request": "launch",
+      "module": "openhands.core.main",
+      "args": [
+        "-t",
+        "Demandez-moi quelle est votre tâche.",
+        "-d",
+        "${workspaceFolder}/workspace",
+        "-c",
+        "CodeActAgent",
+        "-l",
+        "llm.o1",
+        "-n",
+        "prompts"
+      ],
+      "justMyCode": false
+    }
+    ...
+```
+
+Les valeurs dans l'extrait ci-dessus peuvent être mises à jour de telle sorte que :
+
+    * *t* : la tâche
+    * *d* : le répertoire de l'espace de travail openhands
+    * *c* : l'agent
+    * *l* : la configuration LLM (prédéfinie dans config.toml)
+    * *n* : le nom de la session (par exemple, le nom du flux d'événements)

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/evaluation-harness.md

@@ -0,0 +1,280 @@
+
+
+# Évaluation
+
+Ce guide fournit un aperçu de la façon d'intégrer votre propre benchmark d'évaluation dans le framework OpenHands.
+
+## Configuration de l'environnement et de la configuration LLM
+
+Veuillez suivre les instructions [ici](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) pour configurer votre environnement de développement local.
+OpenHands en mode développement utilise `config.toml` pour garder une trace de la plupart des configurations.
+
+Voici un exemple de fichier de configuration que vous pouvez utiliser pour définir et utiliser plusieurs LLMs :
+
+```toml
+[llm]
+# IMPORTANT : ajoutez votre clé API ici et définissez le modèle que vous souhaitez évaluer
+model = "claude-3-5-sonnet-20241022"
+api_key = "sk-XXX"
+
+[llm.eval_gpt4_1106_preview_llm]
+model = "gpt-4-1106-preview"
+api_key = "XXX"
+temperature = 0.0
+
+[llm.eval_some_openai_compatible_model_llm]
+model = "openai/MODEL_NAME"
+base_url = "https://OPENAI_COMPATIBLE_URL/v1"
+api_key = "XXX"
+temperature = 0.0
+```
+
+
+## Comment utiliser OpenHands en ligne de commande
+
+OpenHands peut être exécuté depuis la ligne de commande en utilisant le format suivant :
+
+```bash
+poetry run python ./openhands/core/main.py \
+        -i <max_iterations> \
+        -t "<task_description>" \
+        -c <agent_class> \
+        -l <llm_config>
+```
+
+Par exemple :
+
+```bash
+poetry run python ./openhands/core/main.py \
+        -i 10 \
+        -t "Écrivez-moi un script bash qui affiche hello world." \
+        -c CodeActAgent \
+        -l llm
+```
+
+Cette commande exécute OpenHands avec :
+- Un maximum de 10 itérations
+- La description de tâche spécifiée
+- En utilisant CodeActAgent
+- Avec la configuration LLM définie dans la section `llm` de votre fichier `config.toml`
+
+## Comment fonctionne OpenHands
+
+Le point d'entrée principal d'OpenHands se trouve dans `openhands/core/main.py`. Voici un flux simplifié de son fonctionnement :
+
+1. Analyse des arguments de ligne de commande et chargement de la configuration
+2. Création d'un environnement d'exécution à l'aide de `create_runtime()`
+3. Initialisation de l'agent spécifié
+4. Exécution du contrôleur à l'aide de `run_controller()`, qui :
+   - Attache l'environnement d'exécution à l'agent
+   - Exécute la tâche de l'agent
+   - Renvoie un état final une fois terminé
+
+La fonction `run_controller()` est le cœur de l'exécution d'OpenHands. Elle gère l'interaction entre l'agent, l'environnement d'exécution et la tâche, en gérant des choses comme la simulation d'entrée utilisateur et le traitement des événements.
+
+
+## Le moyen le plus simple de commencer : Explorer les benchmarks existants
+
+Nous vous encourageons à examiner les différents benchmarks d'évaluation disponibles dans le [répertoire `evaluation/benchmarks/`](https://github.com/All-Hands-AI/OpenHands/blob/main/evaluation/benchmarks) de notre dépôt.
+
+Pour intégrer votre propre benchmark, nous vous suggérons de commencer par celui qui ressemble le plus à vos besoins. Cette approche peut considérablement rationaliser votre processus d'intégration, vous permettant de vous appuyer sur les structures existantes et de les adapter à vos exigences spécifiques.
+
+## Comment créer un workflow d'évaluation
+
+
+Pour créer un workflow d'évaluation pour votre benchmark, suivez ces étapes :
+
+1. Importez les utilitaires OpenHands pertinents :
+   ```python
+    import openhands.agenthub
+    from evaluation.utils.shared import (
+        EvalMetadata,
+        EvalOutput,
+        make_metadata,
+        prepare_dataset,
+        reset_logger_for_multiprocessing,
+        run_evaluation,
+    )
+    from openhands.controller.state.state import State
+    from openhands.core.config import (
+        AppConfig,
+        SandboxConfig,
+        get_llm_config_arg,
+        parse_arguments,
+    )
+    from openhands.core.logger import openhands_logger as logger
+    from openhands.core.main import create_runtime, run_controller
+    from openhands.events.action import CmdRunAction
+    from openhands.events.observation import CmdOutputObservation, ErrorObservation
+    from openhands.runtime.runtime import Runtime
+   ```
+
+2. Créez une configuration :
+   ```python
+   def get_config(instance: pd.Series, metadata: EvalMetadata) -> AppConfig:
+       config = AppConfig(
+           default_agent=metadata.agent_class,
+           runtime='eventstream',
+           max_iterations=metadata.max_iterations,
+           sandbox=SandboxConfig(
+               base_container_image='your_container_image',
+               enable_auto_lint=True,
+               timeout=300,
+           ),
+       )
+       config.set_llm_config(metadata.llm_config)
+       return config
+   ```
+
+3. Initialisez l'environnement d'exécution et configurez l'environnement d'évaluation :
+   ```python
+   def initialize_runtime(runtime: Runtime, instance: pd.Series):
+       # Configurez votre environnement d'évaluation ici
+       # Par exemple, définir des variables d'environnement, préparer des fichiers, etc.
+       pass
+   ```
+
+4. Créez une fonction pour traiter chaque instance :
+   ```python
+   from openhands.utils.async_utils import call_async_from_sync
+   def process_instance(instance: pd.Series, metadata: EvalMetadata) -> EvalOutput:
+       config = get_config(instance, metadata)
+       runtime = create_runtime(config)
+       call_async_from_sync(runtime.connect)
+       initialize_runtime(runtime, instance)
+
+       instruction = get_instruction(instance, metadata)
+
+       state = run_controller(
+           config=config,
+           task_str=instruction,
+           runtime=runtime,
+           fake_user_response_fn=your_user_response_function,
+       )
+
+       # Évaluez les actions de l'agent
+       evaluation_result = await evaluate_agent_actions(runtime, instance)
+
+       return EvalOutput(
+           instance_id=instance.instance_id,
+           instruction=instruction,
+           test_result=evaluation_result,
+           metadata=metadata,
+           history=compatibility_for_eval_history_pairs(state.history),
+           metrics=state.metrics.get() if state.metrics else None,
+           error=state.last_error if state and state.last_error else None,
+       )
+   ```
+
+5. Exécutez l'évaluation :
+   ```python
+   metadata = make_metadata(llm_config, dataset_name, agent_class, max_iterations, eval_note, eval_output_dir)
+   output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
+   instances = prepare_dataset(your_dataset, output_file, eval_n_limit)
+
+   await run_evaluation(
+       instances,
+       metadata,
+       output_file,
+       num_workers,
+       process_instance
+   )
+   ```
+
+Ce workflow configure la configuration, initialise l'environnement d'exécution, traite chaque instance en exécutant l'agent et en évaluant ses actions, puis collecte les résultats dans un objet `EvalOutput`. La fonction `run_evaluation` gère la parallélisation et le suivi de la progression.
+
+N'oubliez pas de personnaliser les fonctions `get_instruction`, `your_user_response_function` et `evaluate_agent_actions` en fonction des exigences spécifiques de votre benchmark.
+
+En suivant cette structure, vous pouvez créer un workflow d'évaluation robuste pour votre benchmark dans le framework OpenHands.
+
+
+## Comprendre la `user_response_fn`
+
+La `user_response_fn` est un composant crucial dans le workflow d'évaluation d'OpenHands. Elle simule l'interaction de l'utilisateur avec l'agent, permettant des réponses automatisées pendant le processus d'évaluation. Cette fonction est particulièrement utile lorsque vous voulez fournir des réponses cohérentes et prédéfinies aux requêtes ou actions de l'agent.
+
+
+### Workflow et interaction
+
+Le workflow correct pour gérer les actions et la `user_response_fn` est le suivant :
+
+1. L'agent reçoit une tâche et commence à la traiter
+2. L'agent émet une Action
+3. Si l'Action est exécutable (par exemple, CmdRunAction, IPythonRunCellAction) :
+   - Le Runtime traite l'Action
+   - Le Runtime renvoie une Observation
+4. Si l'Action n'est pas exécutable (généralement une MessageAction) :
+   - La `user_response_fn` est appelée
+   - Elle renvoie une réponse utilisateur simulée
+5. L'agent reçoit soit l'Observation, soit la réponse simulée
+6. Les étapes 2 à 5 se répètent jusqu'à ce que la tâche soit terminée ou que le nombre maximum d'itérations soit atteint
+
+Voici une représentation visuelle plus précise :
+
+```
+                 [Agent]
+                    |
+                    v
+               [Émettre une Action]
+                    |
+                    v
+            [L'Action est-elle exécutable ?]
+           /                       \
+         Oui                        Non
+          |                          |
+          v                          v
+     [Runtime]               [user_response_fn]
+          |                          |
+          v                          v
+  [Renvoyer une Observation]    [Réponse simulée]
+           \                        /
+            \                      /
+             v                    v
+           [L'agent reçoit le feedback]
+                    |
+                    v
+         [Continuer ou terminer la tâche]
+```
+
+Dans ce workflow :
+
+- Les actions exécutables (comme l'exécution de commandes ou de code) sont gérées directement par le Runtime
+- Les actions non exécutables (généralement lorsque l'agent veut communiquer ou demander des clarifications) sont gérées par la `user_response_fn`
+- L'agent traite ensuite le feedback, qu'il s'agisse d'une Observation du Runtime ou d'une réponse simulée de la `user_response_fn`
+
+Cette approche permet une gestion automatisée des actions concrètes et des interactions utilisateur simulées, ce qui la rend adaptée aux scénarios d'évaluation où vous voulez tester la capacité de l'agent à accomplir des tâches avec une intervention humaine minimale.
+
+### Exemple d'implémentation
+
+Voici un exemple de `user_response_fn` utilisée dans l'évaluation SWE-Bench :
+
+```python
+def codeact_user_response(state: State | None) -> str:
+    msg = (
+        'Veuillez continuer à travailler sur la tâche avec l\'approche que vous jugez appropriée.\n'
+        'Si vous pensez avoir résolu la tâche, veuillez d\'abord envoyer votre réponse à l\'utilisateur via un message, puis <execute_bash> exit </execute_bash>.\n'
+        'IMPORTANT : VOUS NE DEVEZ JAMAIS DEMANDER DE L\'AIDE HUMAINE.\n'
+    )
+
+    if state and state.history:
+        # vérifier si l'agent a essayé de parler à l'utilisateur 3 fois, si oui, faire savoir à l'agent qu'il peut abandonner
+        user_msgs = [
+            event
+            for event in state.history
+            if isinstance(event, MessageAction) and event.source == 'user'
+        ]
+        if len(user_msgs) >= 2:
+            # faire savoir à l'agent qu'il peut abandonner quand il a essayé 3 fois
+            return (
+                msg
+                + 'Si vous voulez abandonner, exécutez : <execute_bash> exit </execute_bash>.\n'
+            )
+    return msg
+```
+
+Cette fonction fait ce qui suit :
+
+1. Fournit un message standard encourageant l'agent à continuer à travailler
+2. Vérifie combien de fois l'agent a tenté de communiquer avec l'utilisateur
+3. Si l'agent a fait plusieurs tentatives, il lui donne la possibilité d'abandonner
+
+En utilisant cette fonction, vous pouvez assurer un comportement cohérent sur plusieurs exécutions d'évaluation et empêcher l'agent de rester bloqué en attendant une entrée humaine.