Merge branch 'main' into fix-basic-settings

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

.devcontainer/README.md

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

.devcontainer/devcontainer.json

@@ -0,0 +1,19 @@
+// 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

@@ -0,0 +1,14 @@
+#!/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

@@ -0,0 +1,23 @@
+# 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

.editorconfig

@@ -0,0 +1,5 @@
+[*]
+# 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 +1,7 @@
-*.ipynb linguist-vendored
+*.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/CODEOWNERS

@@ -0,0 +1,8 @@
+# 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_report.md

@@ -1,40 +0,0 @@
----
-name: Bug Report
-about: Report a problem with OpenDevin
-title: ''
-labels: 'bug'
-assignees: ''
-
----
-<!-- You MUST fill out this template. We will close issues that don't include enough information to reproduce -->
-#### Describe the bug
-<!-- a short description of the problem -->
-
-#### Setup and configuration
-**Current version**:
-<!-- run `git log -n 1` to see this -->
-```bash
-```
-
-<!-- tell us everything about your environment -->
-**My config.toml and environment vars** (be sure to redact API keys):
-```toml
-```
-
-**My model and agent** (you can see these settings in the UI):
-* Model:
-* Agent:
-
-**Commands I ran to install and run OpenDevin**:
-```
-```
-
-**Steps to Reproduce**:
-1.
-2.
-3.
-
-**Logs, error messages, and screenshots**:
-
-#### Additional Context
-

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -0,0 +1,166 @@
+name: Bug
+description: Report a problem with OpenHands
+title: '[Bug]: '
+labels: ['bug']
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## Thank you for reporting a bug! 🐛
+
+        **Please fill out all required fields.** Issues missing critical information (version, installation method, reproduction steps, etc.) will be delayed or closed until complete details are provided.
+
+        Clear, detailed reports help us resolve issues faster.
+
+  - type: checkboxes
+    attributes:
+      label: Is there an existing issue for the same bug?
+      description: Please search existing issues before creating a new one. If found, react or comment to the duplicate issue instead of making a new one.
+      options:
+      - label: I have searched existing issues and this is not a duplicate.
+        required: true
+
+  - type: textarea
+    id: bug-description
+    attributes:
+      label: Bug Description
+      description: Clearly describe what went wrong. Be specific and concise.
+      placeholder: Example - "When I run a Python task, OpenHands crashes after 30 seconds with a connection timeout error."
+    validations:
+      required: true
+
+  - type: textarea
+    id: expected-behavior
+    attributes:
+      label: Expected Behavior
+      description: What did you expect to happen?
+      placeholder: Example - "OpenHands should execute the Python script and return results."
+    validations:
+      required: false
+
+  - type: textarea
+    id: actual-behavior
+    attributes:
+      label: Actual Behavior
+      description: What actually happened?
+      placeholder: Example - "Connection timed out after 30 seconds, task failed with error code 500."
+    validations:
+      required: false
+
+  - type: textarea
+    id: reproduction-steps
+    attributes:
+      label: Steps to Reproduce
+      description: Provide clear, step-by-step instructions to reproduce the bug.
+      placeholder: |
+        1. Install OpenHands using Docker
+        2. Configure with Claude 3.5 Sonnet
+        3. Run command: `openhands run "write a python script"`
+        4. Wait 30 seconds
+        5. Error appears
+    validations:
+      required: false
+
+  - type: dropdown
+    id: installation
+    attributes:
+      label: OpenHands Installation Method
+      description: How are you running OpenHands?
+      options:
+        - CLI (uv tool install)
+        - CLI (executable binary)
+        - CLI (Docker)
+        - Local GUI (Docker web interface)
+        - OpenHands Cloud (app.all-hands.dev)
+        - SDK (Python library)
+        - Development workflow
+        - Other
+      default: 0
+    validations:
+      required: false
+
+  - type: input
+    id: installation-other
+    attributes:
+      label: If you selected "Other", please specify
+      description: Describe your installation method
+      placeholder: ex. Custom Kubernetes deployment, pip install from source, etc.
+
+  - type: input
+    id: openhands-version
+    attributes:
+      label: OpenHands Version
+      description: What version are you using? Find this in settings or by running `openhands --version`
+      placeholder: ex. 0.9.8, main, commit hash, etc.
+    validations:
+      required: false
+
+  - type: checkboxes
+    id: version-confirmation
+    attributes:
+      label: Version Confirmation
+      description: Bugs on older versions may already be fixed. Please upgrade before submitting.
+      options:
+        - label: "I have confirmed this bug exists on the LATEST version of OpenHands"
+          required: false
+
+  - type: input
+    id: model-name
+    attributes:
+      label: Model Name
+      description: Which LLM model are you using?
+      placeholder: ex. gpt-4o, claude-3-5-sonnet-20241022, openrouter/deepseek-r1, etc.
+    validations:
+      required: false
+
+  - type: dropdown
+    id: os
+    attributes:
+      label: Operating System
+      options:
+        - MacOS
+        - Linux
+        - WSL on Windows
+        - Windows (Docker Desktop)
+        - Other
+    validations:
+      required: false
+
+  - type: input
+    id: browser
+    attributes:
+      label: Browser (if using web UI)
+      description: |
+        If applicable, which browser and version?
+
+      placeholder: ex. Chrome 131, Firefox 133, Safari 17.2
+
+  - type: textarea
+    id: logs
+    attributes:
+      label: Logs and Error Messages
+      description: |
+        **Paste relevant logs, error messages, or stack traces.** Use code blocks (```) for formatting.
+
+        LLM logs are in `logs/llm/default/`. Include timestamps if errors occurred at a specific time.
+      placeholder: |
+        ```
+        Paste error logs here
+        ```
+
+  - type: textarea
+    id: additional-context
+    attributes:
+      label: Screenshots and Additional Context
+      description: |
+        Add screenshots, videos, runtime environment, or other context that helps explain the issue.
+
+        💡 **Share conversation history:** In the OpenHands chat UI, click the 👎 or 👍 button (above the message input) to generate a shareable link to your conversation.
+
+      placeholder: Drag and drop screenshots here, paste links, or add additional context.
+
+  - type: markdown
+    attributes:
+      value: |
+        ---
+        **Note:** Issues with incomplete information may be closed or deprioritized. Maintainers and community members have limited bandwidth and prioritize well-documented bugs that are easier to reproduce and fix. Thank you for your understanding!

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,18 +0,0 @@
----
-name: Feature Request
-about: Suggest an idea for OpenDevin features
-title: ''
-labels: 'enhancement'
-assignees: ''
-
----
-
-**What problem or use case are you trying to solve?**
-
-**Describe the UX of the solution you'd like**
-
-**Do you have thoughts on the technical implementation?**
-
-**Describe alternatives you've considered**
-
-**Additional context**

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,105 @@
+name: Feature Request or Enhancement
+description: Suggest a new feature or improvement for OpenHands
+title: '[Feature]: '
+labels: ['enhancement']
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## Thank you for suggesting a feature! 💡
+
+        **Please provide detailed information.** Vague or low-effort requests may be closed. Well-documented feature requests with strong community support are more likely to be added to the roadmap.
+
+  - type: checkboxes
+    attributes:
+      label: Is there an existing feature request for this?
+      description: Please search existing issues and feature requests before creating a new one. If found, react or comment to the duplicate issue instead of making a new one.
+      options:
+      - label: I have searched existing issues and feature requests, and this is not a duplicate.
+        required: true
+
+  - type: textarea
+    id: problem-statement
+    attributes:
+      label: Problem or Use Case
+      description: What problem are you trying to solve? What use case would this feature enable?
+      placeholder: |
+        Example - "As a developer working on large codebases, I need to search across multiple files simultaneously. Currently, I have to search file-by-file which is time-consuming and inefficient."
+    validations:
+      required: true
+
+  - type: textarea
+    id: proposed-solution
+    attributes:
+      label: Proposed Solution
+      description: Describe your ideal solution. What should this feature do? How should it work?
+      placeholder: |
+        Example - "Add a global search feature that allows searching across all files in the workspace. Results should show file name, line number, and context around matches. Include regex support and filtering options."
+    validations:
+      required: true
+
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Alternatives Considered
+      description: Have you considered any alternative solutions or workarounds? What are their limitations?
+      placeholder: Example - "I tried using grep in the terminal, but it's not integrated with the UI and doesn't provide click-to-navigate functionality."
+
+  - type: dropdown
+    id: priority
+    attributes:
+      label: Priority / Severity
+      description: How important is this feature to your workflow?
+      options:
+        - "Critical - Blocking my work, no workaround available"
+        - "High - Significant impact on productivity"
+        - "Medium - Would improve experience"
+        - "Low - Nice to have"
+      default: 2
+    validations:
+      required: true
+
+  - type: dropdown
+    id: scope
+    attributes:
+      label: Estimated Scope
+      description: To the best of your knowledge, how complex do you think this feature would be to implement?
+      options:
+        - "Small - UI tweak, config option, or minor change"
+        - "Medium - New feature with moderate complexity"
+        - "Large - Significant feature requiring architecture changes"
+        - "Unknown - Not sure about the technical complexity"
+      default: 3
+
+  - type: dropdown
+    id: feature-area
+    attributes:
+      label: Feature Area
+      description: Which part of OpenHands does this feature relate to? If you select "Other", please specify the area in the Additional Context section below.
+      options:
+        - "Agent / AI behavior"
+        - "User Interface / UX"
+        - "CLI / Command-line interface"
+        - "File system / Workspace management"
+        - "Configuration / Settings"
+        - "Integrations (GitHub, GitLab, etc.)"
+        - "Performance / Optimization"
+        - "Documentation"
+        - "Other"
+    validations:
+      required: true
+
+  - type: textarea
+    id: technical-details
+    attributes:
+      label: Technical Implementation Ideas (Optional)
+      description: If you have technical expertise, share implementation ideas, API suggestions, or relevant technical details.
+      placeholder: |
+        Example - "Could use ripgrep library for fast search. Expose results via /api/search endpoint. Frontend can use virtualized list for rendering large result sets."
+
+  - type: textarea
+    id: additional-context
+    attributes:
+      label: Additional Context
+      description: Add any other context, screenshots, mockups, or examples that help illustrate this feature request.
+      placeholder: Drag and drop screenshots, mockups, or links here.

.github/ISSUE_TEMPLATE/technical_proposal.md

@@ -1,18 +0,0 @@
----
-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

@@ -0,0 +1,80 @@
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "daily"
+    open-pull-requests-limit: 1
+    groups:
+      # put packages in their own group if they have a history of breaking the build or needing to be reverted
+      pre-commit:
+        patterns:
+          - "pre-commit"
+      browsergym:
+        patterns:
+          - "browsergym*"
+      mcp-packages:
+        patterns:
+          - "mcp"
+      security-all:
+        applies-to: "security-updates"
+        patterns:
+          - "*"
+      version-all:
+        applies-to: "version-updates"
+        patterns:
+          - "*"
+
+  - package-ecosystem: "npm"
+    directory: "/frontend"
+    schedule:
+      interval: "daily"
+    open-pull-requests-limit: 1
+    groups:
+      docusaurus:
+        patterns:
+          - "*docusaurus*"
+      eslint:
+        patterns:
+          - "*eslint*"
+      security-all:
+        applies-to: "security-updates"
+        patterns:
+          - "*"
+      version-all:
+        applies-to: "version-updates"
+        patterns:
+          - "*"
+
+  - package-ecosystem: "npm"
+    directory: "/docs"
+    schedule:
+      interval: "weekly"
+      day: "wednesday"
+    open-pull-requests-limit: 1
+    groups:
+      docusaurus:
+        patterns:
+          - "*docusaurus*"
+      eslint:
+        patterns:
+          - "*eslint*"
+      security-all:
+        applies-to: "security-updates"
+        patterns:
+          - "*"
+      version-all:
+        applies-to: "version-updates"
+        patterns:
+          - "*"
+
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+
+  - package-ecosystem: "docker"
+    directories:
+      - "containers/*"
+    schedule:
+      interval: "weekly"

.github/pull_request_template.md

@@ -0,0 +1,38 @@
+<!-- If you are still working on the PR, please mark it as draft. Maintainers will review PRs marked ready for review, which leads to lost time if your PR is actually not ready yet. Keep the PR marked as draft until it is finally ready for review -->
+
+## Summary of PR
+
+<!-- Summarize what the PR does -->
+
+## 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.

.github/scripts/update_pr_description.sh

@@ -0,0 +1,58 @@
+#!/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/build_run-tests.yml

@@ -1,47 +0,0 @@
-name: Build & Run Tests
-
-on: [push, pull_request]
-
-jobs:
-  on-macos:
-    runs-on: macos-latest
-    strategy:
-      matrix:
-        python-version: ["3.11", "3.12"]
-
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
-        with:
-          python-version: ${{ matrix.python-version }}
-      - name: Install & Start Docker
-        run: |
-          brew install colima docker
-          colima start
-      - name: Install and configure Poetry
-        uses: snok/install-poetry@v1
-        with:
-          version: latest
-      - name: Build Environment
-        run: make build
-      - name: Run Tests
-        run: poetry run pytest ./tests
-  on-linux:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version: ["3.11", "3.12"]
-
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
-        with:
-          python-version: ${{ matrix.python-version }}
-      - name: Install Poetry
-        run: curl -sSL https://install.python-poetry.org | python3 -
-      - name: Build Environment
-        run: make build
-      - name: Run Tests
-        run: poetry run pytest ./tests

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

@@ -0,0 +1,65 @@
+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/dogfood.yml

@@ -1,116 +0,0 @@
-name: Use OpenDevin to Resolve GitHub Issue
-
-on:
-  issues:
-    types: [labeled]
-
-permissions:
-  contents: write
-  pull-requests: write
-  issues: write
-
-jobs:
-  open-devin:
-    if: github.event.label.name == 'dogfood-this'
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Checkout Repository
-      uses: actions/checkout@v4
-
-    - name: Install poetry 
-      run: pipx install poetry 
-
-    - name: Set up Python
-      uses: actions/setup-python@v5
-      with:
-        python-version: '3.12'
-        cache: 'poetry'
-    
-    - name: Install Dependencies
-      run: |
-        make build
-
-    - name: Write Task File
-      env:
-        ISSUE_TITLE: ${{ github.event.issue.title }}
-        ISSUE_BODY: ${{ github.event.issue.body }}
-      run: |
-        echo "TITLE:" > task.txt
-        echo "${ISSUE_TITLE}" >> task.txt
-        echo "" >> task.txt
-        echo "BODY:" >> task.txt
-        echo "${ISSUE_BODY}" >> task.txt
-
-    - name: Run OpenDevin
-      env:
-        ISSUE_TITLE: ${{ github.event.issue.title }}
-        ISSUE_BODY: ${{ github.event.issue.body }}
-        LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-      run: |
-        poetry run python ./opendevin/main.py -d "./" -i 50 -f task.txt
-
-    - name: Setup Git, Create Branch, and Commit Changes
-      run: |
-        # Setup Git configuration
-        git config --global user.name 'OpenDevin'
-        git config --global user.email 'OpenDevin@users.noreply.github.com'
-
-        # Create a unique branch name with a timestamp
-        BRANCH_NAME="fix/${{ github.event.issue.number }}-$(date +%Y%m%d%H%M%S)"
-
-        # Checkout new branch
-        git checkout -b $BRANCH_NAME
-
-        # Add all changes to staging, except task.txt
-        git add --all -- ':!task.txt'
-
-        # Commit the changes, if any
-        git commit -m "OpenDevin: Resolve Issue #${{ github.event.issue.number }}"
-        if [ $? -ne 0 ]; then
-          echo "No changes to commit."
-          exit 0
-        fi
-
-        # Push changes
-        git push --set-upstream origin $BRANCH_NAME
-
-    - name: Install GitHub CLI
-      run: |
-        sudo apt-get install gh
-
-    - name: Fetch Default Branch
-      env:
-        GH_TOKEN: ${{ github.token }}
-      run: |
-        # Fetch the default branch using gh cli
-        DEFAULT_BRANCH=$(gh repo view --json defaultBranchRef --jq .defaultBranchRef.name)
-        echo "Default branch is $DEFAULT_BRANCH"
-        echo "DEFAULT_BRANCH=$DEFAULT_BRANCH" >> $GITHUB_ENV
-
-    - name: Generate PR
-      env:
-        GH_TOKEN: ${{ github.token }}
-      run: |
-        # Create PR and capture URL
-        PR_URL=$(gh pr create \
-          --title "OpenDevin: Resolve Issue #2" \
-          --body "This PR was generated by OpenDevin to resolve issue #2" \
-          --repo "foragerr/OpenDevin" \
-          --head "${{ github.head_ref }}" \
-          --base "${{ env.DEFAULT_BRANCH }}" \
-          | grep -o 'https://github.com/[^ ]*')
-        
-        # Extract PR number from URL
-        PR_NUMBER=$(echo "$PR_URL" | grep -o '[0-9]\+$')
-        
-        # Set environment vars
-        echo "PR_URL=$PR_URL" >> $GITHUB_ENV
-        echo "PR_NUMBER=$PR_NUMBER" >> $GITHUB_ENV
-
-    - name: Post Comment
-      env:
-        GH_TOKEN: ${{ github.token }}
-      run: |
-        gh issue comment ${{ github.event.issue.number }} \
-          -b "OpenDevin raised [PR #${{ env.PR_NUMBER }}](${{ env.PR_URL }}) to resolve this issue."

.github/workflows/e2e-tests.yml

@@ -0,0 +1,228 @@
+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

@@ -0,0 +1,52 @@
+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

@@ -0,0 +1,29 @@
+# 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/fe-e2e-tests.yml

@@ -0,0 +1,47 @@
+# 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

@@ -0,0 +1,44 @@
+# Workflow that runs frontend unit tests
+name: Run Frontend Unit Tests
+
+# * Always run on "main"
+# * Run on PRs that have changes in the "frontend" folder or this workflow
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    paths:
+      - "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:
+  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  # Run frontend unit tests
+  fe-test:
+    name: FE Unit 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: Run TypeScript compilation
+        working-directory: ./frontend
+        run: npm run build
+      - name: Run tests and collect coverage
+        working-directory: ./frontend
+        run: npm run test:coverage

.github/workflows/ghcr-build.yml

@@ -0,0 +1,288 @@
+# Workflow that builds, tests and then pushes the OpenHands and runtime docker images to the ghcr.io repository
+name: Docker
+
+# Always run on "main"
+# Always run on tags
+# Always run on PRs
+# Can also be triggered manually
+on:
+  push:
+    branches:
+      - main
+    tags:
+      - "*"
+  pull_request:
+  workflow_dispatch:
+    inputs:
+      reason:
+        description: "Reason for manual trigger"
+        required: true
+        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:
+  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  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'))"
+    permissions:
+      contents: read
+      packages: write
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.pull_request.head.sha }}
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3.7.0
+        with:
+          image: tonistiigi/binfmt:latest
+      - name: Login to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Lowercase Repository Owner
+        run: |
+          echo REPO_OWNER=$(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
+
+  # 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'))"
+    permissions:
+      contents: read
+      packages: write
+    needs: define-matrix
+    strategy:
+      matrix:
+        base_image: ${{ fromJson(needs.define-matrix.outputs.base_image) }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.pull_request.head.sha }}
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3.7.0
+        with:
+          image: tonistiigi/binfmt:latest
+      - name: Login to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - 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
+      - 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
+      - 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
+      - name: Build runtime image ${{ matrix.base_image.image }} for fork
+        if: github.event.pull_request.head.repo.fork
+        uses: useblacksmith/build-push-action@v1
+        with:
+          tags: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+          context: containers/runtime
+      - name: Upload runtime source for fork
+        if: github.event.pull_request.head.repo.fork
+        uses: actions/upload-artifact@v6
+        with:
+          name: runtime-src-${{ matrix.base_image.tag }}
+          path: containers/runtime
+
+  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
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.pull_request.head.sha }}
+
+      # Set up Docker Buildx for better performance
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+        with:
+          driver-opts: network=host
+
+      - name: Login to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ghcr.io/openhands/enterprise-server
+          tags: |
+            type=ref,event=branch
+            type=ref,event=pr
+            type=sha
+            type=sha,format=long
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=semver,pattern={{major}}
+          flavor: |
+            latest=auto
+            prefix=
+            suffix=
+        env:
+          DOCKER_METADATA_PR_HEAD_SHA: true
+      - name: Determine app image tag
+        shell: bash
+        run: |
+          # Duplicated with build.sh
+          sanitized_ref_name=$(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
+
+  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]
+    steps:
+      # This should match the version in enterprise-preview.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-${{ github.event.pull_request.number }}\" }}" \
+            https://api.github.com/repos/OpenHands/deploy/actions/workflows/deploy.yaml/dispatches
+
+  # "All Runtime Tests Passed" is a required job for PRs to merge
+  # We can remove this once the config changes
+  runtime_tests_check_success:
+    name: All Runtime Tests Passed
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    steps:
+      - name: All tests passed
+        run: echo "All runtime tests have passed successfully!"
+
+  update_pr_description:
+    name: Update PR Description
+    if: github.event_name == 'pull_request' && !github.event.pull_request.head.repo.fork && github.actor != 'dependabot[bot]'
+    needs: [ghcr_build_runtime]
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Get short SHA
+        id: short_sha
+        run: echo "SHORT_SHA=$(echo ${{ github.event.pull_request.head.sha }} | cut -c1-7)" >> $GITHUB_OUTPUT
+
+      - name: Update PR Description
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          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

.github/workflows/ghcr.yml

@@ -1,59 +0,0 @@
-name: Build and publish multi-arch container images
-
-on:
-  push:
-    branches: [ main ]
-  workflow_dispatch:
-    inputs:
-      reason:
-        description: 'Reason for manual trigger'
-        required: true
-        default: ''
-
-jobs:
-  ghcr_build_and_push:
-    runs-on: ubuntu-latest
-    if: github.event_name == 'push' || github.event.inputs.reason != ''
-
-    steps:
-      - name: checkout
-        uses: actions/checkout@v4
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Log-in to ghcr.io
-        run: echo "${{ secrets.GITHUB_TOKEN }}" | docker login ghcr.io -u ${{ github.actor }} --password-stdin
-
-      - name: Build and push multi-arch container images
-        run: |
-          # set env for fork repo
-          DOCKER_BUILD_ORG=$(echo "${{ github.repository }}" | tr '[A-Z]' '[a-z]' | cut -d '/' -f 1)
-          # Find directories containing Dockerfile but not containing .dockerfileignore
-          while IFS= read -r dockerfile_dir; do
-          
-            # Check if .dockerfileignore exists in the directory
-            if [ -f "$dockerfile_dir/.dockerfileignore" ]; then
-                echo "$dockerfile_dir/.dockerfileignore exists, skipping build and push"
-                continue
-            fi
-          
-            # Check if image was already exist in ghcr.io
-            pushd "$dockerfile_dir" > /dev/null
-            FULL_IMAGE=$(make get-full-image DOCKER_BUILD_ORG=$DOCKER_BUILD_ORG)
-            popd > /dev/null
-            EXISTS=$(docker manifest inspect "$FULL_IMAGE" > /dev/null 2>&1 && echo "true" || echo "false")
-            if [ "$EXISTS" == "true" ]; then
-              echo "Image $FULL_IMAGE already exists in ghcr.io, skipping build and push"
-              continue
-            fi
-          
-            # Build and push the image to ghcr.io
-            pushd "$dockerfile_dir" > /dev/null
-            make all DOCKER_BUILD_ORG=$DOCKER_BUILD_ORG
-            popd > /dev/null
-          done < <(find . -type f -name Dockerfile -exec dirname {} \; | sort -u)

.github/workflows/lint-fix.yml

@@ -0,0 +1,97 @@
+name: Lint Fix
+
+on:
+  pull_request:
+    types: [labeled]
+
+jobs:
+  # Frontend lint fixes
+  lint-fix-frontend:
+    if: github.event.label.name == 'lint-fix'
+    name: Fix frontend linting issues
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    permissions:
+      contents: write
+      pull-requests: write
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.head_ref }}
+          repository: ${{ github.event.pull_request.head.repo.full_name }}
+          fetch-depth: 0
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Install Node.js 22
+        uses: useblacksmith/setup-node@v5
+        with:
+          node-version: 22
+      - 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
+          npm run lint:fix
+
+      # Commit and push changes if any
+      - name: Check for changes
+        id: git-check
+        run: |
+          git diff --quiet || echo "changes=true" >> $GITHUB_OUTPUT
+      - name: Commit and push if there are changes
+        if: steps.git-check.outputs.changes == 'true'
+        run: |
+          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 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
+    permissions:
+      contents: write
+      pull-requests: write
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.head_ref }}
+          repository: ${{ github.event.pull_request.head.repo.full_name }}
+          fetch-depth: 0
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set up python
+        uses: useblacksmith/setup-python@v6
+        with:
+          python-version: 3.12
+          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
+
+      # Commit and push changes if any
+      - name: Check for changes
+        id: git-check
+        run: |
+          git diff --quiet || echo "changes=true" >> $GITHUB_OUTPUT
+      - name: Commit and push if there are changes
+        if: steps.git-check.outputs.changes == 'true'
+        run: |
+          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 push

.github/workflows/lint.yml

@@ -1,43 +1,74 @@
+# Workflow that runs lint on the frontend and python code
 name: Lint
 
-on: [push, pull_request]
+# 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 lint on the frontend code
   lint-frontend:
-    runs-on: ubuntu-latest
+    name: Lint frontend
+    runs-on: blacksmith-4vcpu-ubuntu-2204
     steps:
       - uses: actions/checkout@v4
-
-      - name: Install Node.js 20
-        uses: actions/setup-node@v4
+      - name: Install Node.js 22
+        uses: useblacksmith/setup-node@v5
         with:
-          node-version: 20
-
+          node-version: 22
       - name: Install dependencies
         run: |
           cd frontend
           npm install --frozen-lockfile
-
-      - name: Lint
+      - name: Lint, TypeScript compilation, and translation checks
         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: ubuntu-latest
+    runs-on: blacksmith-4vcpu-ubuntu-2204
     steps:
       - uses: actions/checkout@v4
-      - name: Set up python
-        uses: actions/setup-python@v5
         with:
-          python-version: 3.11
-      - name: Create mypy cache directory
-        run: mkdir -p .mypy_cache
-      - name: Install dependencies
-        run: pip install ruff mypy types-PyYAML types-toml
-      - name: Run mypy
-        run: python -m mypy --install-types --non-interactive --config-file dev_config/python/mypy.ini opendevin/ agenthub/
-      - name: Run ruff
-        run: ruff check --config dev_config/python/ruff.toml opendevin/ agenthub/
-      
+          fetch-depth: 0
+      - name: Set up python
+        uses: useblacksmith/setup-python@v6
+        with:
+          python-version: 3.12
+          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
+
+  lint-enterprise-python:
+    name: Lint enterprise python
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Set up python
+        uses: useblacksmith/setup-python@v6
+        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

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

@@ -0,0 +1,108 @@
+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

@@ -0,0 +1,433 @@
+name: Auto-Fix Tagged Issue with OpenHands
+
+on:
+  workflow_call:
+    inputs:
+      max_iterations:
+        required: false
+        type: number
+        default: 50
+      macro:
+        required: false
+        type: string
+        default: "@openhands-agent"
+      target_branch:
+        required: false
+        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: ""
+      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
+      LLM_API_KEY:
+        required: true
+      LLM_BASE_URL:
+        required: false
+      PAT_TOKEN:
+        required: false
+      PAT_USERNAME:
+        required: false
+
+  issues:
+    types: [labeled]
+  pull_request:
+    types: [labeled]
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  pull_request_review:
+    types: [submitted]
+
+permissions:
+  contents: write
+  pull-requests: write
+  issues: write
+
+jobs:
+  auto-fix:
+    if: |
+      github.event_name == 'workflow_call' ||
+      github.event.label.name == 'fix-me' ||
+      github.event.label.name == 'fix-me-experimental' ||
+      (
+        ((github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment') &&
+        contains(github.event.comment.body, inputs.macro || '@openhands-agent') &&
+        (github.event.comment.author_association == 'OWNER' || github.event.comment.author_association == 'COLLABORATOR' || github.event.comment.author_association == 'MEMBER')
+        ) ||
+
+        (github.event_name == 'pull_request_review' &&
+        contains(github.event.review.body, inputs.macro || '@openhands-agent') &&
+        (github.event.review.author_association == 'OWNER' || github.event.review.author_association == 'COLLABORATOR' || github.event.review.author_association == 'MEMBER')
+        )
+      )
+    runs-on: "${{ inputs.runner || 'ubuntu-latest' }}"
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: "3.12"
+      - name: Upgrade pip
+        run: |
+          python -m pip install --upgrade pip
+
+      - name: Get latest versions and create requirements.txt
+        run: |
+          python -m pip index versions openhands-ai > openhands_versions.txt
+          OPENHANDS_VERSION=$(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
+
+      - name: Cache pip dependencies
+        if: |
+          !(
+            github.event.label.name == 'fix-me-experimental' ||
+            (
+              (github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment') &&
+              contains(github.event.comment.body, '@openhands-agent-exp')
+            ) ||
+            (
+              github.event_name == 'pull_request_review' &&
+              contains(github.event.review.body, '@openhands-agent-exp')
+            )
+          )
+        uses: actions/cache@v5
+        with:
+          path: ${{ env.pythonLocation }}/lib/python3.12/site-packages/*
+          key: ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('/tmp/requirements.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('/tmp/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: ${{ github.token }}
+        run: |
+          required_vars=("LLM_API_KEY")
+          for var in "${required_vars[@]}"; do
+            if [ -z "${!var}" ]; then
+              echo "Error: Required environment variable $var is not set."
+              exit 1
+            fi
+          done
+
+          # Check optional variables and warn about fallbacks
+          if [ -z "$LLM_BASE_URL" ]; then
+            echo "Warning: LLM_BASE_URL is not set, will use default API endpoint"
+          fi
+
+          if [ -z "$PAT_TOKEN" ]; then
+            echo "Warning: PAT_TOKEN is not set, falling back to GITHUB_TOKEN"
+          fi
+
+          if [ -z "$PAT_USERNAME" ]; then
+            echo "Warning: PAT_USERNAME is not set, will use openhands-agent"
+          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
+            echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
+            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
+          # Handle issue comment events that reference a PR
+          elif [ -n "${{ github.event.issue.pull_request }}" ]; then
+            echo "ISSUE_NUMBER=${{ github.event.issue.number }}" >> $GITHUB_ENV
+            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
+          # Handle regular issue events
+          else
+            echo "ISSUE_NUMBER=${{ github.event.issue.number }}" >> $GITHUB_ENV
+            echo "ISSUE_TYPE=issue" >> $GITHUB_ENV
+          fi
+
+          if [ -n "$REVIEW_BODY" ]; then
+            echo "COMMENT_ID=${{ github.event.review.id || 'None' }}" >> $GITHUB_ENV
+          else
+            echo "COMMENT_ID=${{ github.event.comment.id || 'None' }}" >> $GITHUB_ENV
+          fi
+
+          echo "MAX_ITERATIONS=${{ 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 }}" >> $GITHUB_ENV
+
+          # Set branch variables
+          echo "TARGET_BRANCH=${{ inputs.target_branch || 'main' }}" >> $GITHUB_ENV
+
+      - name: Comment on issue with start message
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.PAT_TOKEN || github.token }}
+          script: |
+            const issueType = process.env.ISSUE_TYPE;
+            github.rest.issues.createComment({
+              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}).`
+            });
+
+      - name: Install OpenHands
+        id: install_openhands
+        uses: actions/github-script@v7
+        env:
+          COMMENT_BODY: ${{ github.event.comment.body || '' }}
+          REVIEW_BODY: ${{ github.event.review.body || '' }}
+          LABEL_NAME: ${{ github.event.label.name || '' }}
+          EVENT_NAME: ${{ github.event_name }}
+        with:
+          script: |
+            const commentBody = process.env.COMMENT_BODY.trim();
+            const reviewBody = process.env.REVIEW_BODY.trim();
+            const labelName = process.env.LABEL_NAME.trim();
+            const eventName = process.env.EVENT_NAME.trim();
+            // Check conditions
+            const isExperimentalLabel = labelName === "fix-me-experimental";
+            const isIssueCommentExperimental =
+              (eventName === "issue_comment" || eventName === "pull_request_review_comment") &&
+              commentBody.includes("@openhands-agent-exp");
+            const isReviewCommentExperimental =
+              eventName === "pull_request_review" && reviewBody.includes("@openhands-agent-exp");
+
+            // Set output variable
+            core.setOutput('isExperimental', isExperimentalLabel || isIssueCommentExperimental || isReviewCommentExperimental);
+
+            // Perform package installation
+            if (isExperimentalLabel || isIssueCommentExperimental || isReviewCommentExperimental) {
+              console.log("Installing experimental OpenHands...");
+
+              await exec.exec("pip install git+https://github.com/openhands/openhands.git");
+            } else {
+              console.log("Installing from requirements.txt...");
+
+              await exec.exec("pip install -r /tmp/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 }} \
+            --issue-number ${{ env.ISSUE_NUMBER }} \
+            --issue-type ${{ env.ISSUE_TYPE }} \
+            --max-iterations ${{ env.MAX_ITERATIONS }} \
+            --comment-id ${{ env.COMMENT_ID }} \
+            --is-experimental ${{ steps.install_openhands.outputs.isExperimental }}
+
+      - name: Check resolution result
+        id: check_result
+        run: |
+          if cd /tmp && grep -q '"success":true' output/output.jsonl; then
+            echo "RESOLUTION_SUCCESS=true" >> $GITHUB_OUTPUT
+          else
+            echo "RESOLUTION_SUCCESS=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Upload output.jsonl as artifact
+        uses: actions/upload-artifact@v6
+        if: always() # Upload even if the previous steps fail
+        with:
+          name: resolver-output
+          path: /tmp/output/output.jsonl
+          retention-days: 30 # Keep the artifact for 30 days
+
+      - name: Create draft PR or push branch
+        if: always() # Create PR or branch even if the previous steps fail
+        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' }} \
+              --reviewer ${{ github.actor }} | tee pr_result.txt && \
+              grep "PR 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 }} \
+              --pr-type branch \
+              --send-on-failure | tee branch_result.txt && \
+              grep "branch created" branch_result.txt | sed 's/.*\///g; s/.expand=1//g' > branch_name.txt
+          fi
+
+      # Step leaves comment for when agent is invoked on PR
+      - name: Analyze Push Logs (Updated PR or No Changes) # Skip comment if PR update was successful OR leave comment if the agent made no code changes
+        uses: actions/github-script@v7
+        if: always()
+        env:
+          AGENT_RESPONDED: ${{ env.AGENT_RESPONDED || 'false' }}
+          ISSUE_NUMBER: ${{ env.ISSUE_NUMBER }}
+        with:
+          github-token: ${{ secrets.PAT_TOKEN || github.token }}
+          script: |
+            const fs = require('fs');
+            const issueNumber = process.env.ISSUE_NUMBER;
+            let logContent = '';
+
+            try {
+              logContent = fs.readFileSync('/tmp/pr_result.txt', 'utf8').trim();
+            } catch (error) {
+              console.error('Error reading pr_result.txt file:', error);
+            }
+
+            const noChangesMessage = `No changes to commit for issue #${issueNumber}. Skipping commit.`;
+
+            // Check logs from send_pull_request.py (pushes code to GitHub)
+            if (logContent.includes("Updated pull request")) {
+              console.log("Updated pull request found. Skipping comment.");
+              process.env.AGENT_RESPONDED = 'true';
+            } else if (logContent.includes(noChangesMessage)) {
+              github.rest.issues.createComment({
+                issue_number: issueNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: `The workflow to fix this issue encountered an error. Openhands failed to create any code changes.`
+              });
+              process.env.AGENT_RESPONDED = 'true';
+            }
+
+      # Step leaves comment for when agent is invoked on issue
+      - name: Comment on issue # Comment link to either PR or branch created by agent
+        uses: actions/github-script@v7
+        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: ${{ secrets.PAT_TOKEN || github.token }}
+          script: |
+            const fs = require('fs');
+            const path = require('path');
+            const issueNumber = process.env.ISSUE_NUMBER;
+            const success = process.env.RESOLUTION_SUCCESS === 'true';
+
+            let prNumber = '';
+            let branchName = '';
+            let resultExplanation = '';
+
+            try {
+              if (success) {
+                prNumber = fs.readFileSync('/tmp/pr_number.txt', 'utf8').trim();
+              } else {
+                branchName = fs.readFileSync('/tmp/branch_name.txt', 'utf8').trim();
+              }
+            } catch (error) {
+              console.error('Error reading file:', error);
+            }
+
+
+            try {
+              if (!success){
+                // Read result_explanation from JSON file for failed resolution
+                const outputFilePath = path.resolve('/tmp/output/output.jsonl');
+                if (fs.existsSync(outputFilePath)) {
+                  const outputContent = fs.readFileSync(outputFilePath, 'utf8');
+                  const jsonLines = outputContent.split('\n').filter(line => line.trim() !== '');
+
+                  if (jsonLines.length > 0) {
+                    // First entry in JSON lines has the key 'result_explanation'
+                    const firstEntry = JSON.parse(jsonLines[0]);
+                    resultExplanation = firstEntry.result_explanation || '';
+                  }
+                }
+              }
+            } catch (error){
+              console.error('Error reading file:', error);
+            }
+
+            // Check "success" log from resolver output
+            if (success && prNumber) {
+              github.rest.issues.createComment({
+                issue_number: issueNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: `A potential fix has been generated and a draft PR #${prNumber} has been created. Please review the changes.`
+              });
+              process.env.AGENT_RESPONDED = 'true';
+            } else if (!success && branchName) {
+              let commentBody = `An attempt was made to automatically fix this issue, but it was unsuccessful. A branch named '${branchName}' has been created with the attempted changes. You can view the branch [here](https://github.com/${context.repo.owner}/${context.repo.repo}/tree/${branchName}). Manual intervention may be required.`;
+
+              if (resultExplanation) {
+                commentBody += `\n\nAdditional details about the failure:\n${resultExplanation}`;
+              }
+
+              github.rest.issues.createComment({
+                issue_number: issueNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: commentBody
+              });
+              process.env.AGENT_RESPONDED = 'true';
+            }
+
+      # Leave error comment when both PR/Issue comment handling fail
+      - 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: ${{ secrets.PAT_TOKEN || github.token }}
+          script: |
+            const issueNumber = process.env.ISSUE_NUMBER;
+
+            github.rest.issues.createComment({
+              issue_number: issueNumber,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: `The workflow to fix this issue encountered an error. Please check the [workflow logs](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}) for more information.`
+            });

.github/workflows/py-tests.yml

@@ -0,0 +1,127 @@
+# 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/pypi-release.yml

@@ -0,0 +1,40 @@
+# Publishes the OpenHands PyPi package
+name: Publish PyPi Package
+
+on:
+  workflow_dispatch:
+    inputs:
+      reason:
+        description: "What are you publishing?"
+        required: true
+        type: choice
+        options:
+          - app server
+        default: app server
+  push:
+    tags:
+      - "*"
+
+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'))
+    steps:
+      - uses: actions/checkout@v4
+      - uses: useblacksmith/setup-python@v6
+        with:
+          python-version: 3.12
+      - name: Install Poetry
+        uses: snok/install-poetry@v1.4.1
+        with:
+          virtualenvs-in-project: true
+          virtualenvs-path: ~/.virtualenvs
+      - name: Install Poetry Dependencies
+        run: poetry install --no-interaction --no-root
+      - name: Build poetry project
+        run: ./build.sh
+      - name: publish
+        run: poetry publish -u __token__ -p ${{ secrets.PYPI_TOKEN }}

.github/workflows/run-tests.yml

@@ -1,20 +0,0 @@
-name: Run Tests
-
-on: [push]
-
-jobs:
-  test:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up Python
-        uses: actions/setup-python@v2
-        with:
-          python-version: '3.11'
-      - name: Set up environment
-        run: |
-          curl -sSL https://install.python-poetry.org | python3 -
-          poetry install --without evaluation
-      - name: Run tests
-        run: |
-          poetry run pytest ./tests

.github/workflows/stale.yml

@@ -0,0 +1,23 @@
+# Workflow that marks issues and PRs with no activity for 30 days with "Stale" and closes them after 7 more days of no activity
+name: 'Close stale issues'
+
+# Runs every day at 01:30
+on:
+  schedule:
+    - cron: '30 1 * * *'
+
+jobs:
+  stale:
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    if: github.repository == 'OpenHands/OpenHands'
+    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

.github/workflows/ui-build.yml

@@ -0,0 +1,34 @@
+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

@@ -0,0 +1,51 @@
+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

@@ -57,7 +57,6 @@ cover/
 *.pot
 
 # Django stuff:
-*.log
 local_settings.py
 db.sqlite3
 db.sqlite3-journal
@@ -122,11 +121,13 @@ celerybeat.pid
 
 # Environments
 .env
+frontend/.env
 .venv
 env/
 venv/
 ENV/
 env.bak/
+.env.bak
 venv.bak/
 *venv/
 
@@ -160,15 +161,52 @@ 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/
-.vscode/
+
+# 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:
+.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
+evaluation/outputs
+evaluation/swe_bench/eval_workspace*
 evaluation/SWE-bench/data
+evaluation/webarena/scripts/webarena_env.sh
+evaluation/bird/data
+evaluation/gaia/data
+evaluation/gorilla/data
+evaluation/toolqa/data
+evaluation/scienceagentbench/benchmark
+evaluation/commit0_bench/repos
+
+# openhands resolver
+output/
 
 # frontend
 
 # dependencies
-frontend/node_modules
 frontend/.pnp
 frontend/bun.lockb
 frontend/yarn.lock
@@ -176,6 +214,8 @@ frontend/yarn.lock
 
 # testing
 frontend/coverage
+test_results*
+/_test_files_tmp/
 
 # production
 frontend/build
@@ -197,8 +237,28 @@ logs
 # agent
 .envrc
 /workspace
+/_test_workspace
 /debug
 cache
 
 # configuration
 config.toml
+config.toml_
+config.toml.bak
+
+# swe-bench-eval
+image_build_logs
+run_instance_logs
+
+runtime_*.tar
+
+# docker build
+containers/runtime/Dockerfile
+containers/runtime/project.tar.gz
+containers/runtime/code
+**/node_modules/
+
+# test results
+test-results
+.sessions
+.eval_sessions

.nvmrc

@@ -0,0 +1 @@
+22

.openhands/microagents/documentation.md

@@ -0,0 +1,33 @@
+---
+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

@@ -0,0 +1,172 @@
+# 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/pre-commit.sh

@@ -0,0 +1,124 @@
+#!/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

@@ -0,0 +1,13 @@
+#! /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

@@ -0,0 +1,22 @@
+{
+    // 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

@@ -0,0 +1,344 @@
+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

@@ -0,0 +1,55 @@
+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

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

CODE_OF_CONDUCT.md

@@ -18,24 +18,24 @@ diverse, inclusive, and healthy community.
 Examples of behavior that contributes to a positive environment for our
 community include:
 
-* Demonstrating empathy and kindness toward other people
-* Being respectful of differing opinions, viewpoints, and experiences
-* Giving and gracefully accepting constructive feedback
+* Demonstrating empathy and kindness toward other people.
+* Being respectful of differing opinions, viewpoints, and experiences.
+* Giving and gracefully accepting constructive feedback.
 * Accepting responsibility and apologizing to those affected by our mistakes,
-  and learning from the experience
+  and learning from the experience.
 * Focusing on what is best not just for us as individuals, but for the overall
-  community
+  community.
 
 Examples of unacceptable behavior include:
 
 * The use of sexualized language or imagery, and sexual attention or advances of
-  any kind
-* Trolling, insulting or derogatory comments, and personal or political attacks
-* Public or private harassment
+  any kind.
+* Trolling, insulting or derogatory comments, and personal or political attacks.
+* Public or private harassment.
 * Publishing others' private information, such as a physical or email address,
-  without their explicit permission
+  without their explicit permission.
 * Other conduct which could reasonably be considered inappropriate in a
-  professional setting
+  professional setting.
 
 ## Enforcement Responsibilities
 
@@ -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@rbren.io
+contact@openhands.dev.
 All complaints will be reviewed and investigated promptly and fairly.
 
 All community leaders are obligated to respect the privacy and security of the
@@ -113,6 +113,25 @@ 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
+
+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!
+
+- 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.
+- 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.
+
 ## Attribution
 
 This Code of Conduct is adapted from the [Contributor Covenant][homepage],

COMMUNITY.md

@@ -0,0 +1,58 @@
+# The OpenHands Community
+
+OpenHands is a community of engineers, academics, and enthusiasts reimagining software development for an AI-powered
+world.
+
+## Mission
+
+It’s very clear that AI is changing software development. We want the developer community to drive that change
+organically, through open source.
+
+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.
+
+## Ethos
+
+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.
+
+### High Openness
+
+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.
+
+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.
+
+We welcome thoughtful criticism, whether it’s a comment on a PR or feedback on the community as a whole.
+
+### High Agency
+
+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!
+
+OpenHands gives everyone the building blocks to create state-of-the-art developer experiences. We experiment constantly
+and love building new things.
+
+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.

CONTRIBUTING.md

@@ -1,63 +1,93 @@
 # Contributing
 
-Thanks for your interest in contributing to OpenDevin! We welcome and appreciate contributions.
-To report bugs, create a [GitHub issue](https://github.com/OpenDevin/OpenDevin/issues/new/choose).
+Thanks for your interest in contributing to OpenHands! We welcome and appreciate contributions.
 
-## Contribution Guide
-### 1. Fork the Official Repository
+## Understanding OpenHands's CodeBase
 
-Fork [OpenDevin repository](https://github.com/OpenDevin/OpenDevin) into your own account.
-Clone your own forked repository into your local environment.
+To understand the codebase, please refer to the README in each module:
+- [frontend](./frontend/README.md)
+- [openhands](./openhands/README.md)
+   - [agenthub](./openhands/agenthub/README.md)
+   - [server](./openhands/server/README.md)
 
-```shell
-git clone git@github.com:<YOUR-USERNAME>/OpenDevin.git
-```
+For benchmarks and evaluation, see the [OpenHands/benchmarks](https://github.com/OpenHands/benchmarks) repository.
 
-### 2. Configure Git
+## Setting up Your Development Environment
 
-Set the official repository as your [upstream](https://www.atlassian.com/git/tutorials/git-forks-and-upstreams) to synchronize with the latest update in the official repository.
-Add the original repository as upstream
+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.
 
-```shell
-cd OpenDevin
-git remote add upstream git@github.com:OpenDevin/OpenDevin.git
-```
+## How Can I Contribute?
 
-Verify that the remote is set.
-```shell
-git remote -v
-```
-You should see both `origin` and `upstream` in the output.
+There are many ways that you can contribute:
 
-### 3. Synchronize with Official Repository
-Synchronize latest commit with official repository before coding.
+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.
 
-```shell
-git fetch upstream
-git checkout main
-git merge upstream/main
-git push origin main
-```
+## What Can I Build?
 
-### 4. Create a New Branch And Open a Pull Request
-After you finish implementation, open forked repository. The source branch is your new branch, and the target branch is `OpenDevin/OpenDevin` `main` branch. Then PR should appears in [OpenDevin PRs](https://github.com/OpenDevin/OpenDevin/pulls).
+Here are a few ways you can help improve the codebase.
 
-Then OpenDevin team will review your code.
+#### UI/UX
 
-## PR Rules
+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.
 
-### 1. Pull Request title
+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
+to gather consensus from our design team first.
 
-As described in [here](https://github.com/commitizen/conventional-commit-types/blob/master/index.json), a valid PR title should begin with one of the following prefixes:
+#### 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).
+
+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
+locally, but we will need to do an end-to-end evaluation of any changes here to ensure that the agent
+is getting better over time.
+
+We use the [SWE-bench](https://www.swebench.com/) benchmark to test our agent. You can join the #evaluation
+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).
+
+#### 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.
+
+## Sending Pull Requests to OpenHands
+
+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:
 
 - `feat`: A new feature
 - `fix`: A bug fix
-- `doc`: Documentation only changes
+- `docs`: Documentation only changes
+- `style`: Changes that do not affect the meaning of the code (white space, formatting, missing semicolons, etc.)
 - `refactor`: A code change that neither fixes a bug nor adds a feature
-- `style`: A refactoring that improves code style
 - `perf`: A code change that improves performance
 - `test`: Adding missing tests or correcting existing tests
-- `ci`: Changes to CI configuration files and scripts (example scopes: `.github`, `ci` (Buildkite))
+- `build`: Changes that affect the build system or external dependencies (example scopes: gulp, broccoli, npm)
+- `ci`: Changes to our CI configuration files and scripts (example scopes: Travis, Circle, BrowserStack, SauceLabs)
 - `chore`: Other changes that don't modify src or test files
 - `revert`: Reverts a previous commit
 
@@ -65,25 +95,45 @@ 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/OpenDevin/OpenDevin/pulls).
+You may also check out previous PRs in the [PR list](https://github.com/OpenHands/OpenHands/pulls).
 
-As described in [here](https://github.com/OpenDevin/OpenDevin/labels), we create several labels. Every PR should be tagged with the corresponding labels.
-
-### 2. Pull Request description
+### Pull Request description
 
 - If your PR is small (such as a typo fix), you can go brief.
-- If it is large and you have changed a lot, it's better to write more details.
+- If it contains a lot of changes, it's better to write more details.
 
+If your changes are user-facing (e.g. a new feature in the UI, a change in behavior, or a bugfix)
+please include a short message that we can add to our changelog.
 
-## How to begin
-Please refer to the README in each module:
-- [frontend](./frontend/README.md)
-- [agenthub](./agenthub/README.md)
-- [evaluation](./evaluation/README.md)
-- [opendevin](./opendevin/README.md)
-    - [server](./opendevin/server/README.md)
-    - [mock server](./opendevin/mock/README.md)
+## How to Make Effective Contributions
 
-## Tests
-TODO: make sure code pass the test before submit.
+### 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.
+
+Further, if you see an issue you like, please leave a "thumbs-up" or a comment, which will help us prioritize.
+
+### Making Pull Requests
+
+We're generally happy to consider all pull requests with the evaluation process varying based on the type of change:
+
+#### 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.
+
+#### 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:
+
+1. **Accuracy**
+2. **Efficiency**
+3. **Code Complexity**
+
+If it improves accuracy, efficiency, or both with only a minimal change to code quality, that's great we're happy to merge it in!
+If there are bigger tradeoffs (e.g. helping efficiency a lot and hurting accuracy a little) we might want to put it behind a feature flag.
+Either way, please feel free to discuss on github issues or slack, and we will give guidance and preliminary feedback.

CREDITS.md

@@ -0,0 +1,328 @@
+# Credits
+
+## 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.
+
+## Open Source Projects
+
+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
+   - Description: Adapted for use in OpenHands's agent hub
+
+#### [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)
+
+#### [BrowserGym](https://github.com/ServiceNow/BrowserGym)
+   - License: Apache License 2.0
+   - Description: Adapted in implementing the browsing agent
+
+### 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)
+   - License: MIT License
+
+#### [DSP](https://github.com/microsoft/DataScienceProblems)
+   - License: MIT License
+
+#### [HumanEvalPack](https://github.com/bigcode-project/bigcode-evaluation-harness)
+   - License: Apache License 2.0
+
+#### [AgentBench](https://github.com/THUDM/AgentBench)
+   - License: Apache License 2.0
+
+#### [SWE-Bench](https://github.com/princeton-nlp/SWE-bench)
+   - License: MIT License
+
+#### [BIRD](https://bird-bench.github.io/)
+   - License: MIT License
+   - Dataset: CC-BY-SA 4.0
+
+#### [Gorilla APIBench](https://github.com/ShishirPatil/gorilla)
+   - License: Apache License 2.0
+
+#### [GPQA](https://github.com/idavidrein/gpqa)
+   - License: MIT License
+
+#### [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:
+
+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.
+
+### 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:
+
+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.
+
+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.
+
+### Apache License 2.0
+
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+### Non-Open Source Reference Implementations:
+
+#### [MultiPL-E](https://github.com/nuprl/MultiPL-E)
+   - License: BSD 3-Clause License with Machine Learning Restriction
+
+BSD 3-Clause License with Machine Learning Restriction
+
+Copyright (c) 2022, Northeastern University, Oberlin College, Roblox Inc,
+Stevens Institute of Technology, University of Massachusetts Amherst, and
+Wellesley College.
+
+All rights reserved.
+
+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.
+
+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.
+
+4.  The contents of this repository may not be used as training data for any
+    machine learning model, including but not limited to neural networks.
+
+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.

Development.md

@@ -0,0 +1,206 @@
+# 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.
+
+## 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`
+  - 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:
+
+```bash
+# Download and install Mamba (a faster version of conda)
+curl -L -O "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"
+bash Miniforge3-$(uname)-$(uname -m).sh
+
+# Install Python 3.12, nodejs, and poetry
+mamba install python=3.12
+mamba install conda-forge::nodejs
+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:
+
+```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.
+
+To configure the LM of your choice, run:
+
+```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.
+
+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 on Alternative Models:**
+See [our documentation](https://docs.openhands.dev/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 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
+   ```
+
+### 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
+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
+
+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`
+
+## Develop inside Docker container
+
+TL;DR
+
+```bash
+make docker-dev
+```
+
+See more details [here](./containers/dev/README.md).
+
+If you are just interested in running `OpenHands` without installing all the required tools on your host.
+
+```bash
+make docker-run
+```
+
+If you do not have `make` on your host, run:
+
+```bash
+cd ./containers/dev
+./dev.sh
+```
+
+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
+- [OpenHands/benchmarks](https://github.com/OpenHands/benchmarks): 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

@@ -0,0 +1,27 @@
+# Issue Triage
+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.).
+
+## Severity
+* **High**: High visibility issues or affecting many users.
+* **Critical**: Affecting all users or potential security issues.
+
+## Difficulty
+* Issues good for newcomers 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).
+
+## 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

@@ -1,7 +1,12 @@
-The MIT License (MIT)
+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.
+
 =====================
 
-Copyright © 2023
+The MIT License (MIT)
+
+Copyright © 2025
 
 Permission is hereby granted, free of charge, to any person
 obtaining a copy of this software and associated documentation

MANIFEST.in

@@ -0,0 +1,5 @@
+# Exclude all Python bytecode files
+global-exclude *.pyc
+
+# Exclude Python cache directories
+global-exclude __pycache__

Makefile

@@ -1,46 +1,72 @@
-# Makefile for OpenDevin project
+SHELL=/usr/bin/env bash
+# Makefile for OpenHands project
 
 # Variables
-DOCKER_IMAGE = ghcr.io/opendevin/sandbox
-BACKEND_PORT = 3000
-BACKEND_HOST = "127.0.0.1:$(BACKEND_PORT)"
-FRONTEND_PORT = 3001
+BACKEND_HOST ?= "127.0.0.1"
+BACKEND_PORT ?= 3000
+BACKEND_HOST_PORT = "$(BACKEND_HOST):$(BACKEND_PORT)"
+FRONTEND_HOST ?= "127.0.0.1"
+FRONTEND_PORT ?= 3001
 DEFAULT_WORKSPACE_DIR = "./workspace"
-DEFAULT_MODEL = "gpt-3.5-turbo-1106"
+DEFAULT_MODEL = "gpt-4o"
 CONFIG_FILE = config.toml
-PRECOMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
+PRE_COMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
+PYTHON_VERSION = 3.12
+KIND_CLUSTER_NAME = "local-hands"
 
 # ANSI color codes
-GREEN=\033[0;32m
-YELLOW=\033[0;33m
-RED=\033[0;31m
-BLUE=\033[0;34m
-RESET=\033[0m
+GREEN=$(shell tput -Txterm setaf 2)
+YELLOW=$(shell tput -Txterm setaf 3)
+RED=$(shell tput -Txterm setaf 1)
+BLUE=$(shell tput -Txterm setaf 6)
+RESET=$(shell tput -Txterm sgr0)
 
 # Build
 build:
 	@echo "$(GREEN)Building project...$(RESET)"
 	@$(MAKE) -s check-dependencies
-	@$(MAKE) -s pull-docker-image
 	@$(MAKE) -s install-python-dependencies
 	@$(MAKE) -s install-frontend-dependencies
-	@$(MAKE) -s install-precommit-hooks
+	@$(MAKE) -s install-pre-commit-hooks
+	@$(MAKE) -s build-frontend
 	@echo "$(GREEN)Build completed successfully.$(RESET)"
 
 check-dependencies:
 	@echo "$(YELLOW)Checking dependencies...$(RESET)"
+	@$(MAKE) -s check-system
 	@$(MAKE) -s check-python
 	@$(MAKE) -s check-npm
+	@$(MAKE) -s check-nodejs
+ifeq ($(INSTALL_DOCKER),)
 	@$(MAKE) -s check-docker
+endif
 	@$(MAKE) -s check-poetry
+	@$(MAKE) -s check-tmux
 	@echo "$(GREEN)Dependencies checked successfully.$(RESET)"
 
+check-system:
+	@echo "$(YELLOW)Checking system...$(RESET)"
+	@if [ "$(shell uname)" = "Darwin" ]; then \
+		echo "$(BLUE)macOS detected.$(RESET)"; \
+	elif [ "$(shell uname)" = "Linux" ]; then \
+		if [ -f "/etc/manjaro-release" ]; then \
+			echo "$(BLUE)Manjaro Linux detected.$(RESET)"; \
+		else \
+			echo "$(BLUE)Linux detected.$(RESET)"; \
+		fi; \
+	elif [ "$$(uname -r | grep -i microsoft)" ]; then \
+		echo "$(BLUE)Windows Subsystem for Linux detected.$(RESET)"; \
+	else \
+		echo "$(RED)Unsupported system detected. Please use macOS, Linux, or Windows Subsystem for Linux (WSL).$(RESET)"; \
+		exit 1; \
+	fi
+
 check-python:
 	@echo "$(YELLOW)Checking Python installation...$(RESET)"
-	@if command -v python3 > /dev/null; then \
-		echo "$(BLUE)$(shell python3 --version) is already installed.$(RESET)"; \
+	@if command -v python$(PYTHON_VERSION) > /dev/null; then \
+		echo "$(BLUE)$(shell python$(PYTHON_VERSION) --version) is already installed.$(RESET)"; \
 	else \
-		echo "$(RED)Python 3 is not installed. Please install Python 3 to continue.$(RESET)"; \
+		echo "$(RED)Python $(PYTHON_VERSION) is not installed. Please install Python $(PYTHON_VERSION) to continue.$(RESET)"; \
 		exit 1; \
 	fi
 
@@ -53,6 +79,22 @@ check-npm:
 		exit 1; \
 	fi
 
+check-nodejs:
+	@echo "$(YELLOW)Checking Node.js installation...$(RESET)"
+	@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 \
+			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.$(RESET)"; \
+			exit 1; \
+		fi; \
+	else \
+		echo "$(RED)Node.js is not installed. Please install Node.js to continue.$(RESET)"; \
+		exit 1; \
+	fi
+
 check-docker:
 	@echo "$(YELLOW)Checking Docker installation...$(RESET)"
 	@if command -v docker > /dev/null; then \
@@ -62,75 +104,199 @@ 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...$(RESET)"
 	@if command -v poetry > /dev/null; then \
-		echo "$(BLUE)$(shell poetry --version) is already installed.$(RESET)"; \
+		POETRY_VERSION=$(shell poetry --version 2>&1 | sed -E 's/Poetry \(version ([0-9]+\.[0-9]+\.[0-9]+)\)/\1/'); \
+		IFS='.' read -r -a POETRY_VERSION_ARRAY <<< "$$POETRY_VERSION"; \
+		if [ $${POETRY_VERSION_ARRAY[0]} -gt 1 ] || ([ $${POETRY_VERSION_ARRAY[0]} -eq 1 ] && [ $${POETRY_VERSION_ARRAY[1]} -ge 8 ]); then \
+			echo "$(BLUE)$(shell poetry --version) is already installed.$(RESET)"; \
+		else \
+			echo "$(RED)Poetry 1.8 or later is required. You can install poetry by running the following command, then adding Poetry to your PATH:"; \
+			echo "$(RED) curl -sSL https://install.python-poetry.org | python$(PYTHON_VERSION) -$(RESET)"; \
+			echo "$(RED)More detail here: https://python-poetry.org/docs/#installing-with-the-official-installer$(RESET)"; \
+			exit 1; \
+		fi; \
 	else \
 		echo "$(RED)Poetry is not installed. You can install poetry by running the following command, then adding Poetry to your PATH:"; \
-		echo "$(RED) curl -sSL https://install.python-poetry.org | python3 -$(RESET)"; \
+		echo "$(RED) curl -sSL https://install.python-poetry.org | python$(PYTHON_VERSION) -$(RESET)"; \
 		echo "$(RED)More detail here: https://python-poetry.org/docs/#installing-with-the-official-installer$(RESET)"; \
 		exit 1; \
 	fi
 
-pull-docker-image:
-	@echo "$(YELLOW)Pulling Docker image...$(RESET)"
-	@docker pull $(DOCKER_IMAGE)
-	@echo "$(GREEN)Docker image pulled successfully.$(RESET)"
-
 install-python-dependencies:
 	@echo "$(GREEN)Installing Python dependencies...$(RESET)"
+	@if [ -z "${TZ}" ]; then \
+		echo "Defaulting TZ (timezone) to UTC"; \
+		export TZ="UTC"; \
+	fi
+	poetry env use python$(PYTHON_VERSION)
 	@if [ "$(shell uname)" = "Darwin" ]; then \
-		echo "$(BLUE)Installing `chroma-hnswlib`...$(RESET)"; \
+		echo "$(BLUE)Installing chroma-hnswlib...$(RESET)"; \
 		export HNSWLIB_NO_NATIVE=1; \
 		poetry run pip install chroma-hnswlib; \
 	fi
-	@poetry install --without evaluation
+	@if [ -n "${POETRY_GROUP}" ]; then \
+		echo "Installing only POETRY_GROUP=${POETRY_GROUP}"; \
+		poetry install --only $${POETRY_GROUP}; \
+	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; \
+		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 \
+		fi \
+	else \
+		echo "Skipping Playwright installation (INSTALL_PLAYWRIGHT=${INSTALL_PLAYWRIGHT})."; \
+	fi
 	@echo "$(GREEN)Python dependencies installed successfully.$(RESET)"
 
-install-frontend-dependencies:
+install-frontend-dependencies: check-npm check-nodejs
 	@echo "$(YELLOW)Setting up frontend environment...$(RESET)"
 	@echo "$(YELLOW)Detect Node.js version...$(RESET)"
 	@cd frontend && node ./scripts/detect-node-version.js
-	@cd frontend && \
-		echo "$(BLUE)Installing frontend dependencies with npm...$(RESET)" && \
-		npm install && \
-		echo "$(BLUE)Running make-i18n with npm...$(RESET)" && \
-		npm run make-i18n
+	echo "$(BLUE)Installing frontend dependencies with npm...$(RESET)"
+	@cd frontend && npm install
 	@echo "$(GREEN)Frontend dependencies installed successfully.$(RESET)"
 
-install-precommit-hooks:
+install-pre-commit-hooks: check-python check-poetry install-python-dependencies
 	@echo "$(YELLOW)Installing pre-commit hooks...$(RESET)"
 	@git config --unset-all core.hooksPath || true
-	@poetry run pre-commit install --config $(PRECOMMIT_CONFIG_PATH)
+	@poetry run pre-commit install --config $(PRE_COMMIT_CONFIG_PATH)
 	@echo "$(GREEN)Pre-commit hooks installed successfully.$(RESET)"
 
+lint-backend: install-pre-commit-hooks
+	@echo "$(YELLOW)Running linters...$(RESET)"
+	@poetry run pre-commit run --all-files --show-diff-on-failure --config $(PRE_COMMIT_CONFIG_PATH)
+
+lint-frontend: install-frontend-dependencies
+	@echo "$(YELLOW)Running linters for frontend...$(RESET)"
+	@cd frontend && npm run lint
+
+lint:
+	@$(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
+
+test:
+	@$(MAKE) -s test-frontend
+
+build-frontend:
+	@echo "$(YELLOW)Building frontend...$(RESET)"
+	@cd frontend && npm run prepare && npm run build
+
 # Start backend
 start-backend:
 	@echo "$(YELLOW)Starting backend...$(RESET)"
-	@poetry run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT)
+	@poetry run uvicorn openhands.server.listen:app --host $(BACKEND_HOST) --port $(BACKEND_PORT) --reload --reload-exclude "./workspace"
 
 # Start frontend
 start-frontend:
 	@echo "$(YELLOW)Starting frontend...$(RESET)"
-	@cd frontend && BACKEND_HOST=$(BACKEND_HOST) FRONTEND_PORT=$(FRONTEND_PORT) npm run start
+	@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)
 
-# Run the app
-run:
-	@echo "$(YELLOW)Running the app...$(RESET)"
+# Common setup for running the app (non-callable)
+_run_setup:
 	@if [ "$(OS)" = "Windows_NT" ]; then \
-		echo "$(RED)`make run` is not supported on Windows. Please run `make start-frontend` and `make start-backend` separately.$(RESET)"; \
+		echo "$(RED) Windows is not supported, use WSL instead!$(RESET)"; \
 		exit 1; \
 	fi
 	@mkdir -p logs
 	@echo "$(YELLOW)Starting backend server...$(RESET)"
-	@poetry run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT) &
+	@poetry run uvicorn openhands.server.listen:app --host $(BACKEND_HOST) --port $(BACKEND_PORT) &
 	@echo "$(YELLOW)Waiting for the backend to start...$(RESET)"
 	@until nc -z localhost $(BACKEND_PORT); do sleep 0.1; done
 	@echo "$(GREEN)Backend started successfully.$(RESET)"
-	@cd frontend && echo "$(BLUE)Starting frontend with npm...$(RESET)" && npm run start -- --port $(FRONTEND_PORT)
+
+# Run the app (standard mode)
+run:
+	@echo "$(YELLOW)Running the app...$(RESET)"
+	@$(MAKE) -s _run_setup
+	@$(MAKE) -s start-frontend
 	@echo "$(GREEN)Application started successfully.$(RESET)"
 
+# Run the app (in docker)
+docker-run: WORKSPACE_BASE ?= $(PWD)/workspace
+docker-run:
+	@if [ -f /.dockerenv ]; then \
+		echo "Running inside a Docker container. Exiting..."; \
+		exit 0; \
+	else \
+		echo "$(YELLOW)Running the app in Docker $(OPTIONS)...$(RESET)"; \
+		export WORKSPACE_BASE=${WORKSPACE_BASE}; \
+		export SANDBOX_USER_ID=$(shell id -u); \
+		export DATE=$(shell date +%Y%m%d%H%M%S); \
+		docker compose up $(OPTIONS); \
+	fi
+
+
 # Setup config.toml
 setup-config:
 	@echo "$(YELLOW)Setting up config.toml...$(RESET)"
@@ -139,47 +305,67 @@ setup-config:
 	@echo "$(GREEN)Config.toml setup completed.$(RESET)"
 
 setup-config-prompts:
-	@read -p "Enter your LLM Model name (see https://docs.litellm.ai/docs/providers for full list) [default: $(DEFAULT_MODEL)]: " llm_model; \
-	 llm_model=$${llm_model:-$(DEFAULT_MODEL)}; \
-	 echo "LLM_MODEL=\"$$llm_model\"" > $(CONFIG_FILE).tmp
+	@echo "[core]" > $(CONFIG_FILE).tmp
 
-	@read -p "Enter your LLM API key: " llm_api_key; \
-	 echo "LLM_API_KEY=\"$$llm_api_key\"" >> $(CONFIG_FILE).tmp
-
-	@read -p "Enter your LLM Base URL [mostly used for local LLMs, leave blank if not needed - example: http://localhost:5001/v1/]: " llm_base_url; \
-	 if [[ ! -z "$$llm_base_url" ]]; then echo "LLM_BASE_URL=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; fi
-
-	@echo "Enter your LLM Embedding Model\nChoices are openai, azureopenai, llama2 or leave blank to default to 'BAAI/bge-small-en-v1.5' via huggingface"; \
-	 read -p "> " llm_embedding_model; \
-	 	echo "LLM_EMBEDDING_MODEL=\"$$llm_embedding_model\"" >> $(CONFIG_FILE).tmp; \
-		if [ "$$llm_embedding_model" = "llama2" ]; then \
-			read -p "Enter the local model URL (will overwrite LLM_BASE_URL): " llm_base_url; \
-				echo "LLM_BASE_URL=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
-		elif [ "$$llm_embedding_model" = "azureopenai" ]; then \
-			read -p "Enter the Azure endpoint URL (will overwrite LLM_BASE_URL): " llm_base_url; \
-				echo "LLM_BASE_URL=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
-			read -p "Enter the Azure LLM Deployment Name: " llm_deployment_name; \
-				echo "LLM_DEPLOYMENT_NAME=\"$$llm_deployment_name\"" >> $(CONFIG_FILE).tmp; \
-			read -p "Enter the Azure API Version: " llm_api_version; \
-				echo "LLM_API_VERSION=\"$$llm_api_version\"" >> $(CONFIG_FILE).tmp; \
-		fi
-
-	@read -p "Enter your workspace directory [default: $(DEFAULT_WORKSPACE_DIR)]: " workspace_dir; \
+	@read -p "Enter your workspace directory (as absolute path) [default: $(DEFAULT_WORKSPACE_DIR)]: " workspace_dir; \
 	 workspace_dir=$${workspace_dir:-$(DEFAULT_WORKSPACE_DIR)}; \
-	 echo "WORKSPACE_DIR=\"$$workspace_dir\"" >> $(CONFIG_FILE).tmp
+	 echo "workspace_base=\"$$workspace_dir\"" >> $(CONFIG_FILE).tmp
+
+	@echo "" >> $(CONFIG_FILE).tmp
+
+	@echo "[llm]" >> $(CONFIG_FILE).tmp
+	@read -p "Enter your LLM model name, used for running without UI. Set the model in the UI after you start the app. (see https://docs.litellm.ai/docs/providers for full list) [default: $(DEFAULT_MODEL)]: " llm_model; \
+	 llm_model=$${llm_model:-$(DEFAULT_MODEL)}; \
+	 echo "model=\"$$llm_model\"" >> $(CONFIG_FILE).tmp
+
+	@read -p "Enter your LLM api key: " llm_api_key; \
+	 echo "api_key=\"$$llm_api_key\"" >> $(CONFIG_FILE).tmp
+
+	@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.$(RESET)"
+
+openhands-cloud-run:
+	@$(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:
+	@if [ -f /.dockerenv ]; then \
+		echo "Running inside a Docker container. Exiting..."; \
+		exit 0; \
+	else \
+		echo "$(YELLOW)Build and run in Docker $(OPTIONS)...$(RESET)"; \
+		./containers/dev/dev.sh $(OPTIONS); \
+	fi
+
+# Clean up all caches
+clean:
+	@echo "$(YELLOW)Cleaning up caches...$(RESET)"
+	@rm -rf openhands/.cache
+	@echo "$(GREEN)Caches cleaned up successfully.$(RESET)"
 
 # Help
 help:
 	@echo "$(BLUE)Usage: make [target]$(RESET)"
 	@echo "Targets:"
 	@echo "  $(GREEN)build$(RESET)               - Build project, including environment setup and dependencies."
-	@echo "  $(GREEN)setup-config$(RESET)        - Setup the configuration for OpenDevin by providing LLM API key,"
+	@echo "  $(GREEN)lint$(RESET)                - Run linters on the project."
+	@echo "  $(GREEN)setup-config$(RESET)        - Setup the configuration for OpenHands by providing LLM API key,"
 	@echo "                        LLM Model name, and workspace directory."
-	@echo "  $(GREEN)start-backend$(RESET)       - Start the backend server for the OpenDevin project."
-	@echo "  $(GREEN)start-frontend$(RESET)      - Start the frontend server for the OpenDevin project."
-	@echo "  $(GREEN)run$(RESET)                 - Run the OpenDevin application, starting both backend and frontend servers."
+	@echo "  $(GREEN)start-backend$(RESET)       - Start the backend server for the OpenHands project."
+	@echo "  $(GREEN)start-frontend$(RESET)      - Start the frontend server for the OpenHands project."
+	@echo "  $(GREEN)run$(RESET)                 - Run the OpenHands application, starting both backend and frontend servers."
 	@echo "                        Backend Log file will be stored in the 'logs' directory."
+	@echo "  $(GREEN)docker-dev$(RESET)          - Build and run the OpenHands application in Docker."
+	@echo "  $(GREEN)docker-run$(RESET)          - Run the OpenHands application, starting both backend and frontend servers in Docker."
 	@echo "  $(GREEN)help$(RESET)                - Display this help message, providing information on available targets."
 
 # Phony targets
-.PHONY: build check-dependencies check-python check-npm check-docker check-poetry pull-docker-image install-python-dependencies install-frontend-dependencies install-precommit-hooks start-backend start-frontend run setup-config setup-config-prompts help
+.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

README.md

@@ -1,269 +1,86 @@
 <a name="readme-top"></a>
-<!--
-*** Thanks for checking out the Best-README-Template. If you have a suggestion
-*** that would make this better, please fork the repo and create a pull request
-*** or simply open an issue with the tag "enhancement".
-*** Don't forget to give the project a star!
-*** Thanks again! Now go create something AMAZING! :D
--->
-
-
-
-<!-- PROJECT SHIELDS -->
-<!--
-*** I'm using markdown "reference style" links for readability.
-*** Reference links are enclosed in brackets [ ] instead of parentheses ( ).
-*** See the bottom of this document for the declaration of the reference variables
-*** for contributors-url, forks-url, etc. This is an optional, concise syntax you may use.
-*** https://www.markdownguide.org/basic-syntax/#reference-style-links
--->
 
 <div align="center">
-  <a href="https://github.com/OpenDevin/OpenDevin/graphs/contributors"><img src="https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge" alt="Contributors"></a>
-  <a href="https://github.com/OpenDevin/OpenDevin/network/members"><img src="https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge" alt="Forks"></a>
-  <a href="https://github.com/OpenDevin/OpenDevin/stargazers"><img src="https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge" alt="Stargazers"></a>
-  <a href="https://github.com/OpenDevin/OpenDevin/issues"><img src="https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge" alt="Issues"></a>
-  <a href="https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE"><img src="https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge" alt="MIT License"></a>
-  </br>
-  <a href="https://join.slack.com/t/opendevin/shared_invite/zt-2etftj1dd-X1fDL2PYIVpsmJZkqEYANw"><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/mBuDGRzzES"><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>
-</div>
-
-<!-- PROJECT LOGO -->
-<div align="center">
-  <img src="./logo.png" alt="Logo" width="200" height="200">
-  <h1 align="center">OpenDevin: Code Less, Make More</h1>
+  <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>
 </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>
+  <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>
 
 
-<!-- TABLE OF CONTENTS -->
-<details>
-  <summary>🗂️ Table of Contents</summary>
-  <ol>
-    <li><a href="#-mission">🎯 Mission</a></li>
-    <li><a href="#-what-is-devin">🤔 What is Devin?</a></li>
-    <li><a href="#-why-opendevin">🐚 Why OpenDevin?</a></li>
-    <li><a href="#-project-status">🚧 Project Status</a></li>
-      <a href="#-get-started">🚀 Get Started</a>
-      <ul>
-        <li><a href="#1-requirements">1. Requirements</a></li>
-        <li><a href="#2-build-and-setup">2. Build and Setup</a></li>
-        <li><a href="#3-run-the-application">3. Run the Application</a></li>
-        <li><a href="#4-individual-server-startup">4. Individual Server Startup</a></li>
-        <li><a href="#5-help">5. Help</a></li>
-      </ul>
-    </li>
-    <li><a href="#%EF%B8%8F-research-strategy">⭐️ Research Strategy</a></li>
-    <li><a href="#-how-to-contribute">🤝 How to Contribute</a></li>
-    <li><a href="#-join-our-community">🤖 Join Our Community</a></li>
-    <li><a href="#%EF%B8%8F-built-with">🛠️ Built With</a></li>
-    <li><a href="#-license">📜 License</a></li>
-  </ol>
-</details>
+  <!-- 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>
 
-## 🎯 Mission
+</div>
 
-[Project Demo Video](https://github.com/OpenDevin/OpenDevin/assets/38853559/71a472cc-df34-430c-8b1d-4d7286c807c9)
+<hr>
 
+🙌 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).
 
-Welcome to OpenDevin, an open-source project aiming to replicate Devin, an autonomous AI software engineer who is capable of executing complex engineering tasks and collaborating actively with users on software development projects. This project aspires to replicate, enhance, and innovate upon Devin through the power of the open-source community.
+There are a few ways to work with OpenHands:
 
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
+### 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.
 
-## 🤔 What is Devin?
-Devin represents a cutting-edge autonomous agent designed to navigate the complexities of software engineering. It leverages a combination of tools such as a shell, code editor, and web browser, showcasing the untapped potential of LLMs in software development. Our goal is to explore and expand upon Devin's capabilities, identifying both its strengths and areas for improvement, to guide the progress of open code models.
+Define agents in code, then run them locally, or scale to 1000s of agents in the cloud.
 
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
+[Check out the docs](https://docs.openhands.dev/sdk) or [view the source](https://github.com/OpenHands/software-agent-sdk/)
 
-## 🐚 Why OpenDevin?
-The OpenDevin project is born out of a desire to replicate, enhance, and innovate beyond the original Devin model. By engaging the open-source community, we aim to tackle the challenges faced by Code LLMs in practical scenarios, producing works that significantly contribute to the community and pave the way for future advancements.
+### 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.
 
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
+[Check out the docs](https://docs.openhands.dev/openhands/usage/run-openhands/cli-mode) or [view the source](https://github.com/OpenHands/OpenHands-CLI)
 
-## 🚧 Project Status
+### 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.
 
-OpenDevin is currently a work in progress, but you can already run the alpha version to see the end-to-end system in action. The project team is actively working on the following key milestones:
+[Check out the docs](https://docs.openhands.dev/openhands/usage/run-openhands/local-setup) or view the source in this repo.
 
-- **UI**: Developing a user-friendly interface, including a chat interface, a shell demonstrating commands, and a web browser.
-- **Architecture**: Building a stable agent framework with a robust backend that can read, write, and run simple commands.
-- **Agent Capabilities**: Enhancing the agent's abilities to generate bash scripts, run tests, and perform other software engineering tasks.
-- **Evaluation**: Establishing a minimal evaluation pipeline that is consistent with Devin's evaluation criteria.
+### OpenHands Cloud
+This is a deployment of OpenHands GUI, running on hosted infrastructure.
 
-After completing the MVP, the team will focus on research in various areas, including foundation models, specialist capabilities, evaluation, and agent studies.
+You can try it with a free $10 credit by [signing in with your GitHub or GitLab account](https://app.all-hands.dev).
 
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
+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)
 
-## ⚠️ Caveats and Warnings
-* OpenDevin is still an alpha project. It is changing very quickly and is unstable. We are working on getting a stable release out in the coming weeks.
-* OpenDevin will issue many prompts to the LLM you configure. Most of these LLMs cost money--be sure to set spending limits and monitor usage.
-* OpenDevin runs `bash` commands within a Docker sandbox, so it should not affect your machine. But your workspace directory will be attached to that sandbox, and files in the directory may be modified or deleted.
-* Our default Agent is currently the MonologueAgent, which has limited capabilities, but is fairly stable. We're working on other Agent implementations, including [SWE Agent](https://swe-agent.com/). You can [read about our current set of agents here](./docs/documentation/Agents.md).
+### 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.
 
-## 🚀 Get Started
+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.
 
-Getting started with the OpenDevin project is incredibly easy. Follow these simple steps to set up and run OpenDevin on your system:
+Enterprise contracts also come with extended support and access to our research team.
 
-### 1. Requirements
-* Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)
-* [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/) >= 3.11
-* [NodeJS](https://nodejs.org/en/download/package-manager) >= 18.17.1
-* [Poetry](https://python-poetry.org/docs/#installing-with-the-official-installer) >= 1.8
+Learn more at [openhands.dev/enterprise](https://openhands.dev/enterprise)
 
-Make sure you have all these dependencies installed before moving on to `make build`.
+### Everything Else
 
-### 2. Build and Setup The Environment
+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!
 
-- **Build the Project:** Begin by building the project, which includes setting up the environment and installing dependencies. This step ensures that OpenDevin is ready to run smoothly on your system.
-    ```bash
-    make build
-    ```
+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).
 
-### 3. Configuring the Language Model
+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.
 
-OpenDevin supports a diverse array of Language Models (LMs) through the powerful [litellm](https://docs.litellm.ai) library. By default, we've chosen the mighty GPT-4 from OpenAI as our go-to model, but the world is your oyster! You can unleash the potential of Anthropic's suave Claude, the enigmatic Llama, or any other LM that piques your interest.
-
-To configure the LM of your choice, follow these steps:
-
-1. **Using the Makefile: The Effortless Approach**
-   With a single command, you can have a smooth LM setup for your OpenDevin experience. Simply run:
-   ```bash
-   make setup-config
-   ```
-   This command will prompt you to enter the LLM API key and model name, ensuring that OpenDevin is tailored to your specific needs.
-
-**Note on Alternative Models:**
-Some alternative models may prove more challenging to tame than others. Fear not, brave adventurer! We shall soon unveil LLM-specific documentation to guide you on your quest. And if you've already mastered the art of wielding a model other than OpenAI's GPT, we encourage you to [share your setup instructions with us](https://github.com/OpenDevin/OpenDevin/issues/417).
-
-For a full list of the LM providers and models available, please consult the [litellm documentation](https://docs.litellm.ai/docs/providers).
-
-There is also [documentation for running with local models using ollama](./docs/documentation/LOCAL_LLM_GUIDE.md).
-
-### 4. Run the Application
-
-- **Run the Application:** Once the setup is complete, launching OpenDevin is as simple as running a single command. This command starts both the backend and frontend servers seamlessly, allowing you to interact with OpenDevin without any hassle.
-    ```bash
-    make run
-    ```
-
-### 5. 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 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. Help
-
-- **Get Some Help:** Need assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenDevin.
-    ```bash
-    make help
-    ```
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
-
-## ⭐️ Research Strategy
-
-Achieving full replication of production-grade applications with LLMs is a complex endeavor. Our strategy involves:
-
-1. **Core Technical Research:** Focusing on foundational research to understand and improve the technical aspects of code generation and handling.
-2. **Specialist Abilities:** Enhancing the effectiveness of core components through data curation, training methods, and more.
-3. **Task Planning:** Developing capabilities for bug detection, codebase management, and optimization.
-4. **Evaluation:** Establishing comprehensive evaluation metrics to better understand and improve our models.
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
-
-## 🤝 How to Contribute
-
-OpenDevin is a community-driven project, and 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:
-
-- **Code Contributions:** Help us develop the core functionalities, frontend interface, or sandboxing solutions.
-- **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 OpenDevin toolset, report bugs, suggest features, or provide feedback on usability.
-
-For details, please check [this document](./CONTRIBUTING.md).
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
-
-## 🤖 Join Our Community
-
-Now we have both Slack workspace for the collaboration on building OpenDevin and Discord server for discussion about anything related, e.g., this project, LLM, agent, etc. 
-
-* [Slack workspace](https://join.slack.com/t/opendevin/shared_invite/zt-2etftj1dd-X1fDL2PYIVpsmJZkqEYANw)
-* [Discord server](https://discord.gg/mBuDGRzzES)
-
-If you would love to contribute, feel free to join our community (note that now there is no need to fill in the [form](https://forms.gle/758d5p6Ve8r2nxxq6)). Let's simplify software engineering together!
-
-🐚 **Code less, make more with OpenDevin.**
-
-[![Star History Chart](https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date)](https://star-history.com/#OpenDevin/OpenDevin&Date)
-
-## 🛠️ Built With
-
-OpenDevin is built using a combination of powerful frameworks and libraries, providing a robust foundation for its development. Here are the key technologies used in the project:
-
-![FastAPI](https://img.shields.io/badge/FastAPI-black?style=for-the-badge) ![uvicorn](https://img.shields.io/badge/uvicorn-black?style=for-the-badge) ![LiteLLM](https://img.shields.io/badge/LiteLLM-black?style=for-the-badge) ![Docker](https://img.shields.io/badge/Docker-black?style=for-the-badge) ![Ruff](https://img.shields.io/badge/Ruff-black?style=for-the-badge) ![MyPy](https://img.shields.io/badge/MyPy-black?style=for-the-badge) ![LlamaIndex](https://img.shields.io/badge/LlamaIndex-black?style=for-the-badge) ![React](https://img.shields.io/badge/React-black?style=for-the-badge)
-
-Please note that the selection of these technologies is in progress, and additional technologies may be added or existing ones may be removed as the project evolves. We strive to adopt the most suitable and efficient tools to enhance the capabilities of OpenDevin.
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
-
-## 📜 License
-
-Distributed under the MIT License. See [`LICENSE`](./LICENSE) for more information.
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
-
-[contributors-shield]: https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge
-[contributors-url]: https://github.com/OpenDevin/OpenDevin/graphs/contributors
-[forks-shield]: https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge
-[forks-url]: https://github.com/OpenDevin/OpenDevin/network/members
-[stars-shield]: https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge
-[stars-url]: https://github.com/OpenDevin/OpenDevin/stargazers
-[issues-shield]: https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge
-[issues-url]: https://github.com/OpenDevin/OpenDevin/issues
-[license-shield]: https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge
-[license-url]: https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE
+If you need help with anything, or just want to chat, [come find us on Slack](https://dub.sh/openhands).

agenthub/README.md

@@ -1,73 +0,0 @@
-# Agent Framework Research
-
-In this folder, there may exist multiple implementations of `Agent` that will be used by the framework.
-
-For example, `agenthub/monologue_agent`, `agenthub/metagpt_agent`, `agenthub/codeact_agent`, etc.
-Contributors from different backgrounds and interests can choose to contribute to any (or all!) of these directions.
-
-## Constructing an Agent
-
-The abstraction for an agent can be found [here](../opendevin/agent.py).
-
-Agents are run inside of a loop. At each iteration, `agent.step()` is called with a
-[State](../opendevin/state.py) input, and the agent must output an [Action](../opendevin/action).
-
-Every agent also has a `self.llm` which it can use to interact with the LLM configured by the user.
-See the [LiteLLM docs for `self.llm.completion`](https://docs.litellm.ai/docs/completion).
-
-## State
-The `state` contains:
-* A history of actions taken by the agent, as well as any observations (e.g. file content, command output) from those actions
-* A list of actions/observations that have happened since the most recent step
-* A [`plan`](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/plan.py), which contains the main goal
-  * The agent can add and modify subtasks through the `AddTaskAction` and `ModifyTaskAction`
-
-## Actions
-Here is a list of available Actions, which can be returned by `agent.step()`:
-- [`CmdRunAction`](../opendevin/action/bash.py) - Runs a command inside a sandboxed terminal
-- [`CmdKillAction`](../opendevin/action/bash.py) - Kills a background command
-- [`FileReadAction`](../opendevin/action/fileop.py) - Reads the content of a file
-- [`FileWriteAction`](../opendevin/action/fileop.py) - Writes new content to a file
-- [`BrowseURLAction`](../opendevin/action/browse.py) - Gets the content of a URL
-- [`AgentRecallAction`](../opendevin/action/agent.py) - Searches memory (e.g. a vector database)
-- [`AddTaskAction`](../opendevin/action/tasks.py) - Adds a subtask to the plan
-- [`ModifyTaskAction`](../opendevin/action/tasks.py) - Changes the state of a subtask
-- [`AgentThinkAction`](../opendevin/action/agent.py) - A no-op that allows the agent to add plaintext to the history (as well as the chat log)
-- [`AgentFinishAction`](../opendevin/action/agent.py) - Stops the control loop, allowing the user to enter a new task
-
-You can use `action.to_dict()` and `action_from_dict` to serialize and deserialize actions.
-
-## Observations
-There are also several types of Observations. These are typically available in the step following the corresponding Action.
-But they may also appear as a result of asynchronous events (e.g. a message from the user, logs from a command running
-in the background).
-
-Here is a list of available Observations:
-- [`CmdOutputObservation`](../opendevin/observation/run.py)
-- [`BrowserOutputObservation`](../opendevin/observation/browse.py)
-- [`FileReadObservation`](../opendevin/observation/files.py)
-- [`FileWriteObservation`](../opendevin/observation/files.py)
-- [`UserMessageObservation`](../opendevin/observation/)
-- [`AgentRecallObservation`](../opendevin/observation/recall.py)
-- [`AgentErrorObservation`](../opendevin/observation/error.py)
-
-You can use `observation.to_dict()` and `observation_from_dict` to serialize and deserialize observations.
-
-## Interface
-Every agent must implement the following methods:
-
-### `step`
-```
-def step(self, state: "State") -> "Action"
-```
-`step` moves the agent forward one step towards its goal. This probably means
-sending a prompt to the LLM, then parsing the response into an `Action`.
-
-### `search_memory`
-```
-def search_memory(self, query: str) -> List[str]:
-```
-`search_memory` should return a list of events that match the query. This will be used
-for the `recall` action.
-
-You can optionally just return `[]` for this method, meaning the agent has no long-term memory.

agenthub/__init__.py

@@ -1,11 +0,0 @@
-from dotenv import load_dotenv
-load_dotenv()
-
-# Import agents after environment variables are loaded
-from . import monologue_agent  # noqa: E402
-from . import codeact_agent  # noqa: E402
-from . import planner_agent  # noqa: E402
-from . import thinkact_agent  # noqa: E402
-
-__all__ = ['monologue_agent', 'codeact_agent',
-           'planner_agent', 'thinkact_agent']

agenthub/codeact_agent/README.md

@@ -1,21 +0,0 @@
-# CodeAct-based Agent Framework
-
-This folder implements the [CodeAct idea](https://arxiv.org/abs/2402.13463) that relies on LLM to autonomously perform actions in a Bash shell. It requires more from the LLM itself: LLM needs to be capable enough to do all the stuff autonomously, instead of stuck in an infinite loop. 
-
-A minimalistic example can be found at [research/codeact/examples/run_flask_server_with_bash.py](./examples/run_flask_server_with_bash.py):
-
-```bash
-mkdir workspace
-PYTHONPATH=`pwd`:$PYTHONPATH python3 opendevin/main.py -d ./workspace -c CodeActAgent -t "Please write a flask app that returns 'Hello, World\!' at the root URL, then start the app on port 5000. python3 has already been installed for you."
-```
-
-
-Example: prompts `gpt-4-0125-preview` to write a flask server, install `flask` library, and start the server.
-
-<img width="951" alt="image" src="https://github.com/OpenDevin/OpenDevin/assets/38853559/325c3115-a343-4cc5-a92b-f1e5d552a077">
-
-<img width="957" alt="image" src="https://github.com/OpenDevin/OpenDevin/assets/38853559/68ad10c1-744a-4e9d-bb29-0f163d665a0a">
-
-Most of the things are working as expected, except at the end, the model did not follow the instruction to stop the interaction by outputting `<execute> exit </execute>` as instructed. 
-
-**TODO**: This should be fixable by either (1) including a complete in-context example like [this](https://github.com/xingyaoww/mint-bench/blob/main/mint/tasks/in_context_examples/reasoning/with_tool.txt), OR (2) collect some interaction data like this and fine-tune a model (like [this](https://github.com/xingyaoww/code-act), a more complex route).

agenthub/codeact_agent/__init__.py

@@ -1,4 +0,0 @@
-from opendevin.agent import Agent
-from .codeact_agent import CodeActAgent
-
-Agent.register("CodeActAgent", CodeActAgent)

agenthub/codeact_agent/codeact_agent.py

@@ -1,152 +0,0 @@
-import re
-from typing import List, Mapping
-
-from opendevin.action import (
-    Action,
-    AgentEchoAction,
-    AgentFinishAction,
-    CmdRunAction,
-)
-from opendevin.agent import Agent
-from opendevin.llm.llm import LLM
-from opendevin.observation import (
-    AgentMessageObservation,
-    CmdOutputObservation,
-)
-from opendevin.parse_commands import parse_command_file
-from opendevin.state import State
-
-COMMAND_DOCS = parse_command_file()
-COMMAND_SEGMENT = (
-    f"""
-
-Apart from the standard bash commands, you can also use the following special commands:
-{COMMAND_DOCS}
-"""
-    if COMMAND_DOCS is not None
-    else ""
-)
-SYSTEM_MESSAGE = f"""You are a helpful assistant. You will be provided access (as root) to a bash shell to complete user-provided tasks.
-You will be able to execute commands in the bash shell, interact with the file system, install packages, and receive the output of your commands.
-
-DO NOT provide code in ```triple backticks```. Instead, you should execute bash command on behalf of the user by wrapping them with <execute> and </execute>.
-For example:
-
-You can list the files in the current directory by executing the following command:
-<execute>ls</execute>
-
-You can also install packages using pip:
-<execute> pip install numpy </execute>
-
-You can also write a block of code to a file:
-<execute>
-echo "import math
-print(math.pi)" > math.py
-</execute>
-{COMMAND_SEGMENT}
-
-When you are done, execute the following to close the shell and end the conversation:
-<execute>exit</execute> 
-"""
-
-INVALID_INPUT_MESSAGE = (
-    "I don't understand your input. \n"
-    "If you want to execute command, please use <execute> YOUR_COMMAND_HERE </execute>.\n"
-    "If you already completed the task, please exit the shell by generating: <execute> exit </execute>."
-)
-
-def parse_response(response) -> str:
-    action = response.choices[0].message.content
-    if "<execute>" in action and "</execute>" not in action:
-        action += "</execute>"
-    return action
-
-class CodeActAgent(Agent):
-    """
-    The Code Act Agent is a minimalist agent. 
-    The agent works by passing the model a list of action-observaiton pairs and prompting the model to take the next step.
-    """
-    
-    def __init__(
-        self,
-        llm: LLM,
-    ) -> None:
-        """
-        Initializes a new instance of the CodeActAgent class.
-
-        Parameters:
-        - llm (LLM): The llm to be used by this agent
-        """
-        super().__init__(llm)
-        self.messages: List[Mapping[str, str]] = []
-
-    def step(self, state: State) -> Action:
-        """
-        Performs one step using the Code Act Agent. 
-        This includes gathering info on previous steps and prompting the model to make a command to execute.
-
-        Parameters:
-        - state (State): used to get updated info and background commands
-
-        Returns:
-        - CmdRunAction(command) - command action to run
-        - AgentEchoAction(content=INVALID_INPUT_MESSAGE) - invalid command output
-
-        Raises:
-        - NotImplementedError - for actions other than CmdOutputObservation or AgentMessageObservation
-        """
-
-        if len(self.messages) == 0:
-            assert state.plan.main_goal, "Expecting instruction to be set"
-            self.messages = [
-                {"role": "system", "content": SYSTEM_MESSAGE},
-                {"role": "user", "content": state.plan.main_goal},
-            ]
-        updated_info = state.updated_info
-        if updated_info:
-            for prev_action, obs in updated_info:
-                assert isinstance(
-                    prev_action, (CmdRunAction, AgentEchoAction)
-                ), "Expecting CmdRunAction or AgentEchoAction for Action"
-                if isinstance(
-                    obs, AgentMessageObservation
-                ):  # warning message from itself
-                    self.messages.append({"role": "user", "content": obs.content})
-                elif isinstance(obs, CmdOutputObservation):
-                    content = "OBSERVATION:\n" + obs.content
-                    content += f"\n[Command {obs.command_id} finished with exit code {obs.exit_code}]]"
-                    self.messages.append({"role": "user", "content": content})
-                else:
-                    raise NotImplementedError(
-                        f"Unknown observation type: {obs.__class__}"
-                    )
-        response = self.llm.completion(
-            messages=self.messages,
-            stop=["</execute>"],
-            temperature=0.0
-        )
-        action_str: str = parse_response(response)
-        self.messages.append({"role": "assistant", "content": action_str})
-
-        command = re.search(r"<execute>(.*)</execute>", action_str, re.DOTALL)
-        if command is not None:
-            # a command was found
-            command_group = command.group(1)
-            if command_group.strip() == "exit":
-                return AgentFinishAction()
-            return CmdRunAction(command=command_group)
-            # # execute the code
-            # # TODO: does exit_code get loaded into Message?
-            # exit_code, observation = self.env.execute(command_group)
-            # self._history.append(Message(Role.ASSISTANT, observation))
-        else:
-            # we could provide a error message for the model to continue similar to
-            # https://github.com/xingyaoww/mint-bench/blob/main/mint/envs/general_env.py#L18-L23
-            # observation = INVALID_INPUT_MESSAGE
-            # self._history.append(Message(Role.ASSISTANT, observation))
-            return AgentEchoAction(
-                content=INVALID_INPUT_MESSAGE
-            )  # warning message to itself
-
-    def search_memory(self, query: str) -> List[str]:
-        raise NotImplementedError("Implement this abstract method")

agenthub/monologue_agent/.dockerignore

@@ -1,2 +0,0 @@
-.envrc
-workspace

agenthub/monologue_agent/README.md

@@ -1,8 +0,0 @@
-# LLM control loop
-This is currently a standalone utility. It will need to be integrated into OpenDevin's backend.
-
-## Usage
-```bash
-# Run this in project root
-./agenthub/monologue_agent/build-and-run.sh "write a bash script that prints 'hello world'"
-```

agenthub/monologue_agent/TODO.md

@@ -1,9 +0,0 @@
-# TODO
-There's a lot of low-hanging fruit for this agent:
-
-* Strip `<script>`, `<style>`, and other non-text tags from the HTML before sending it to the LLM
-* Keep track of the working directory when the agent uses `cd`
-* Improve memory condensing--condense earlier memories more aggressively
-* Limit the time that `run` can wait (in case agent runs an interactive command and it's hanging)
-* Figure out how to run background processes, e.g. `node server.js` to start a server
-

agenthub/monologue_agent/__init__.py

@@ -1,4 +0,0 @@
-from opendevin.agent import Agent
-from .agent import MonologueAgent
-
-Agent.register("MonologueAgent", MonologueAgent)

agenthub/monologue_agent/agent.py

@@ -1,235 +0,0 @@
-from typing import List
-from opendevin.agent import Agent
-from opendevin.state import State
-from opendevin.llm.llm import LLM
-from opendevin.schema import ActionType, ObservationType
-
-from opendevin.action import (
-    Action,
-    NullAction,
-    CmdRunAction,
-    FileWriteAction,
-    FileReadAction,
-    AgentRecallAction,
-    BrowseURLAction,
-    AgentThinkAction,
-)
-
-from opendevin.observation import (
-    Observation,
-    NullObservation,
-    CmdOutputObservation,
-    FileReadObservation,
-    AgentRecallObservation,
-    BrowserOutputObservation,
-)
-
-import agenthub.monologue_agent.utils.prompts as prompts
-from agenthub.monologue_agent.utils.monologue import Monologue
-from agenthub.monologue_agent.utils.memory import LongTermMemory
-
-MAX_MONOLOGUE_LENGTH = 20000
-MAX_OUTPUT_LENGTH = 5000
-
-INITIAL_THOUGHTS = [
-    'I exist!',
-    'Hmm...looks like I can type in a command line prompt',
-    'Looks like I have a web browser too!',
-    "Here's what I want to do: $TASK",
-    'How am I going to get there though?',
-    'It seems like I have some kind of short term memory.',
-    'Each of my thoughts seems to be stored in a JSON array.',
-    'It seems whatever I say next will be added as an object to the list.',
-    'But no one has perfect short-term memory. My list of thoughts will be summarized and condensed over time, losing information in the process.',
-    'Fortunately I have long term memory!',
-    'I can just perform a recall action, followed by the thing I want to remember. And then related thoughts just spill out!',
-    "Sometimes they're random thoughts that don't really have to do with what I wanted to remember. But usually they're exactly what I need!",
-    "Let's try it out!",
-    'RECALL what it is I want to do',
-    "Here's what I want to do: $TASK",
-    'How am I going to get there though?',
-    "Neat! And it looks like it's easy for me to use the command line too! I just have to perform a run action and include the command I want to run in the command argument. The command output just jumps into my head!",
-    'RUN echo "hello world"',
-    'hello world',
-    'Cool! I bet I can write files too using the write action.',
-    "WRITE 0 1 echo \"console.log('hello world')\" > test.js",
-    '',
-    "I just created test.js. I'll try and run it now.",
-    'RUN node test.js',
-    'hello world',
-    'It works!',
-    "I'm going to try reading it now using the read action.",
-    'READ test.js',
-    "console.log('hello world')",
-    'Nice! I can read files too!',
-    'And if I want to use the browser, I just need to use the browse action and include the url I want to visit in the url argument',
-    "Let's try that...",
-    'BROWSE google.com',
-    '<form><input type="text"></input><button type="submit"></button></form>',
-    'I can browse the web too!',
-    'And once I have completed my task, I can use the finish action to stop working.',
-    "But I should only use the finish action when I'm absolutely certain that I've completed my task and have tested my work.",
-    'Very cool. Now to accomplish my task.',
-    "I'll need a strategy. And as I make progress, I'll need to keep refining that strategy. I'll need to set goals, and break them into sub-goals.",
-    'In between actions, I must always take some time to think, strategize, and set new goals. I should never take two actions in a row.',
-    "OK so my task is to $TASK. I haven't made any progress yet. Where should I start?",
-    "It seems like there might be an existing project here. I should probably start by running `ls` to see what's here.",
-]
-
-
-class MonologueAgent(Agent):
-    """
-    The Monologue Agent utilizes long and short term memory to complete tasks.
-    Long term memory is stored as a LongTermMemory object and the model uses it to search for examples from the past.
-    Short term memory is stored as a Monologue object and the model can condense it as necessary.
-    """
-
-    _initialized = False
-
-    def __init__(self, llm: LLM):
-        """
-        Initializes the Monologue Agent with an llm, monologue, and memory.
-
-        Parameters:
-        - llm (LLM): The llm to be used by this agent
-        """
-        super().__init__(llm)
-        self.monologue = Monologue()
-        self.memory = LongTermMemory()
-
-    def _add_event(self, event: dict):
-        """
-        Adds a new event to the agent's monologue and memory.
-        Monologue automatically condenses when it gets too large.
-
-        Parameters:
-        - event (dict): The event that will be added to monologue and memory
-        """
-
-        if 'extras' in event and 'screenshot' in event['extras']:
-            del event['extras']['screenshot']
-        if (
-            'args' in event
-            and 'output' in event['args']
-            and len(event['args']['output']) > MAX_OUTPUT_LENGTH
-        ):
-            event['args']['output'] = (
-                event['args']['output'][:MAX_OUTPUT_LENGTH] + '...'
-            )
-
-        self.monologue.add_event(event)
-        self.memory.add_event(event)
-        if self.monologue.get_total_length() > MAX_MONOLOGUE_LENGTH:
-            self.monologue.condense(self.llm)
-
-    def _initialize(self, task: str):
-        """
-        Utilizes the INITIAL_THOUGHTS list to give the agent a context for it's capabilities and how to navigate the /workspace.
-        Short circuited to return when already initialized.
-
-        Parameters:
-        - task (str): The initial goal statement provided by the user
-
-        Raises:
-        - ValueError: If task is not provided
-        """
-
-        if self._initialized:
-            return
-
-        if task is None or task == '':
-            raise ValueError('Instruction must be provided')
-        self.monologue = Monologue()
-        self.memory = LongTermMemory()
-
-        output_type = ''
-        for thought in INITIAL_THOUGHTS:
-            thought = thought.replace('$TASK', task)
-            if output_type != '':
-                observation: Observation = NullObservation(content='')
-                if output_type == ObservationType.RUN:
-                    observation = CmdOutputObservation(
-                        content=thought, command_id=0, command=''
-                    )
-                elif output_type == ObservationType.READ:
-                    observation = FileReadObservation(content=thought, path='')
-                elif output_type == ObservationType.RECALL:
-                    observation = AgentRecallObservation(
-                        content=thought, memories=[])
-                elif output_type == ObservationType.BROWSE:
-                    observation = BrowserOutputObservation(
-                        content=thought, url='', screenshot=''
-                    )
-                self._add_event(observation.to_dict())
-                output_type = ''
-            else:
-                action: Action = NullAction()
-                if thought.startswith('RUN'):
-                    command = thought.split('RUN ')[1]
-                    action = CmdRunAction(command)
-                    output_type = ActionType.RUN
-                elif thought.startswith('WRITE'):
-                    parts = thought.split('WRITE ')[1].split(' > ')
-                    path = parts[1]
-                    start, end, content = parts[0].split(' ')
-                    start_ind, end_ind = int(start), int(end)
-                    action = FileWriteAction(
-                        path=path, start=start_ind, end=end_ind, content=content)
-                elif thought.startswith('READ'):
-                    path = thought.split('READ ')[1]
-                    action = FileReadAction(path=path)
-                    output_type = ActionType.READ
-                elif thought.startswith('RECALL'):
-                    query = thought.split('RECALL ')[1]
-                    action = AgentRecallAction(query=query)
-                    output_type = ActionType.RECALL
-                elif thought.startswith('BROWSE'):
-                    url = thought.split('BROWSE ')[1]
-                    action = BrowseURLAction(url=url)
-                    output_type = ActionType.BROWSE
-                else:
-                    action = AgentThinkAction(thought=thought)
-                self._add_event(action.to_dict())
-        self._initialized = True
-
-    def step(self, state: State) -> Action:
-        """
-        Modifies the current state by adding the most recent actions and observations, then prompts the model to think about it's next action to take using monologue, memory, and hint.
-
-        Parameters:
-        - state (State): The current state based on previous steps taken
-
-        Returns:
-        - Action: The next action to take based on LLM response
-        """
-        self._initialize(state.plan.main_goal)
-        for prev_action, obs in state.updated_info:
-            self._add_event(prev_action.to_dict())
-            self._add_event(obs.to_dict())
-
-        state.updated_info = []
-
-        prompt = prompts.get_request_action_prompt(
-            state.plan.main_goal,
-            self.monologue.get_thoughts(),
-            state.background_commands_obs,
-        )
-        messages = [{'content': prompt, 'role': 'user'}]
-        resp = self.llm.completion(messages=messages)
-        action_resp = resp['choices'][0]['message']['content']
-        action = prompts.parse_action_response(action_resp)
-        self.latest_action = action
-        return action
-
-    def search_memory(self, query: str) -> List[str]:
-        """
-        Uses VectorIndexRetriever to find related memories within the long term memory.
-        Uses search to produce top 10 results.
-
-        Parameters:
-        - query (str): The query that we want to find related memories for
-
-        Returns:
-        - List[str]: A list of top 10 text results that matched the query
-        """
-        return self.memory.search(query)

agenthub/monologue_agent/utils/json.py

@@ -1,35 +0,0 @@
-import json
-from json_repair import repair_json
-
-def my_encoder(obj):
-    """
-    Encodes objects as dictionaries
-
-    Parameters:
-    - obj (Object): An object that will be converted
-
-    Returns:
-    - dict: If the object can be converted it is returned in dict format
-    """
-    if hasattr(obj, "to_dict"):
-        return obj.to_dict()
-
-def dumps(obj, **kwargs):
-    """
-    Serialize an object to str format
-    """
-
-    return json.dumps(obj, default=my_encoder, **kwargs)
-
-def loads(s, **kwargs):
-    """
-    Create a JSON object from str
-    """
-    json_start = s.find("{")
-    json_end = s.rfind("}") + 1
-    if json_start == -1 or json_end == -1:
-        raise ValueError("Invalid response: no JSON found")
-    s = s[json_start:json_end]
-    s = repair_json(s)
-    return json.loads(s, **kwargs)
-

agenthub/monologue_agent/utils/memory.py

@@ -1,104 +0,0 @@
-import chromadb
-from llama_index.core import Document
-from llama_index.core.retrievers import VectorIndexRetriever
-from llama_index.core import VectorStoreIndex
-from llama_index.vector_stores.chroma import ChromaVectorStore
-
-from opendevin import config
-from . import json
-
-embedding_strategy = config.get("LLM_EMBEDDING_MODEL")
-
-# TODO: More embeddings: https://docs.llamaindex.ai/en/stable/examples/embeddings/OpenAI/
-# There's probably a more programmatic way to do this.
-if embedding_strategy == "llama2":
-    from llama_index.embeddings.ollama import OllamaEmbedding
-    embed_model = OllamaEmbedding(
-        model_name="llama2",
-        base_url=config.get_or_error("LLM_BASE_URL"),
-        ollama_additional_kwargs={"mirostat": 0},
-    )
-elif embedding_strategy == "openai":
-    from llama_index.embeddings.openai import OpenAIEmbedding
-    embed_model = OpenAIEmbedding(
-        model="text-embedding-ada-002",
-        api_key=config.get_or_error("LLM_API_KEY")
-    )
-elif embedding_strategy == "azureopenai":
-    from llama_index.embeddings.azure_openai import AzureOpenAIEmbedding  # Need to instruct to set these env variables in documentation
-    embed_model = AzureOpenAIEmbedding(
-        model="text-embedding-ada-002",
-        deployment_name=config.get_or_error("LLM_DEPLOYMENT_NAME"),
-        api_key=config.get_or_error("LLM_API_KEY"),
-        azure_endpoint=config.get_or_error("LLM_BASE_URL"),
-        api_version=config.get_or_error("LLM_API_VERSION"),
-    )
-else:
-    from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-    embed_model = HuggingFaceEmbedding(
-        model_name="BAAI/bge-small-en-v1.5"
-    )
-
-
-class LongTermMemory:
-    """
-    Responsible for storing information that the agent can call on later for better insights and context.
-    Uses chromadb to store and search through memories.
-    """
-
-    def __init__(self):
-        """
-        Initialize the chromadb and set up ChromaVectorStore for later use.
-        """
-        db = chromadb.Client()
-        self.collection = db.get_or_create_collection(name="memories")
-        vector_store = ChromaVectorStore(chroma_collection=self.collection)
-        self.index = VectorStoreIndex.from_vector_store(vector_store, embed_model=embed_model)
-        self.thought_idx = 0
-
-    def add_event(self, event: dict):
-        """
-        Adds a new event to the long term memory with a unique id.
-
-        Parameters:
-        - event (dict): The new event to be added to memory
-        """
-        id = ""
-        t = ""
-        if "action" in event:
-            t = "action"
-            id = event["action"]
-        elif "observation" in event:
-            t = "observation"
-            id = event["observation"]
-        doc = Document(
-            text=json.dumps(event),
-            doc_id=str(self.thought_idx),
-            extra_info={
-                "type": t,
-                "id": id,
-                "idx": self.thought_idx,
-            },
-        )
-        self.thought_idx += 1
-        self.index.insert(doc)
-
-    def search(self, query: str, k: int=10):
-        """
-        Searches through the current memory using VectorIndexRetriever
-
-        Parameters:
-        - query (str): A query to match search results to
-        - k (int): Number of top results to return
-
-        Returns:
-        - List[str]: List of top k results found in current memory
-        """
-        retriever = VectorIndexRetriever(
-            index=self.index,
-            similarity_top_k=k,
-        )
-        results = retriever.retrieve(query)
-        return [r.get_text() for r in results]
-
-

agenthub/monologue_agent/utils/monologue.py

@@ -1,79 +0,0 @@
-import traceback
-from opendevin.llm.llm import LLM
-import agenthub.monologue_agent.utils.json as json
-import agenthub.monologue_agent.utils.prompts as prompts
-
-class Monologue:
-    """
-    The monologue is a representation for the agent's internal monologue where it can think.
-    The agent has the capability of using this monologue for whatever it wants.
-    """
-
-    def __init__(self):
-        """
-        Initialize the empty list of thoughts
-        """
-        self.thoughts = []
-
-    def add_event(self, t: dict):
-        """
-        Adds an event to memory if it is a valid event.
-
-        Parameters:
-        - t (dict): The thought that we want to add to memory
-
-        Raises:
-        - ValueError: If t is not a dict
-        """
-        if not isinstance(t, dict):
-            raise ValueError("Event must be a dictionary")
-        self.thoughts.append(t)
-
-    def get_thoughts(self):
-        """
-        Get the current thoughts of the agent.
-
-        Returns:
-        - List: The list of thoughts that the agent has.
-        """
-        return self.thoughts
-
-    def get_total_length(self):
-        """
-        Gives the total number of characters in all thoughts
-
-        Returns:
-        - Int: Total number of chars in thoughts.
-        """
-        total_length = 0
-        for t in self.thoughts:
-            try:
-                total_length += len(json.dumps(t))
-            except TypeError as e:
-                print(f"Error serializing thought: {e}")
-        return total_length
-
-    def condense(self, llm: LLM):
-        """
-        Attempts to condense the monologue by using the llm
-
-        Parameters:
-        - llm (LLM): llm to be used for summarization
-
-        Raises:
-        - RunTimeError: When the condensing process fails for any reason
-        """
-        
-        try:
-            prompt = prompts.get_summarize_monologue_prompt(self.thoughts)
-            messages = [{"content": prompt,"role": "user"}]
-            resp = llm.completion(messages=messages)
-            summary_resp = resp['choices'][0]['message']['content']
-            self.thoughts = prompts.parse_summary_response(strip_markdown(summary_resp))
-        except Exception as e:
-            traceback.print_exc()
-            raise RuntimeError(f"Error condensing thoughts: {e}")
-
-def strip_markdown(markdown_json):
-    # remove markdown code block
-    return markdown_json.replace('```json\n', '').replace('```', '').strip()

agenthub/monologue_agent/utils/prompts.py

@@ -1,171 +0,0 @@
-from typing import List
-
-from . import json
-
-from opendevin.action import (
-    action_from_dict,
-    Action,
-)
-from opendevin.observation import (
-    CmdOutputObservation,
-)
-
-ACTION_PROMPT = """
-You're a thoughtful robot. Your main task is this:
-
-%(task)s
-
-Don't expand the scope of your task--just complete it as written.
-
-This is your internal monologue, in JSON format:
-
-%(monologue)s
-
-
-Your most recent thought is at the bottom of that monologue. Continue your train of thought.
-What is your next thought or action? Your response must be in JSON format.
-It must be an object, and it must contain two fields:
-* `action`, which is one of the actions below
-* `args`, which is a map of key-value pairs, specifying the arguments for that action
-
-Here are the possible actions:
-* `read` - reads the content of a file. Arguments:
-  * `path` - the path of the file to read
-* `write` - writes the content to a file. Arguments:
-  * `path` - the path of the file to write
-  * `content` - the content to write to the file
-* `run` - runs a command. Arguments:
-  * `command` - the command to run
-  * `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
-* `kill` - kills a background command
-  * `id` - the ID of the background command to kill
-* `browse` - opens a web page. Arguments:
-  * `url` - the URL to open
-* `recall` - recalls a past memory. Arguments:
-  * `query` - the query to search for
-* `think` - make a plan, set a goal, or record your thoughts. Arguments:
-  * `thought` - the thought to record
-* `finish` - if you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.
-
-%(background_commands)s
-
-You MUST take time to think in between read, write, run, browse, and recall actions.
-You should never act twice in a row without thinking. But if your last several
-actions are all "think" actions, you should consider taking a different action.
-
-Notes:
-* your environment is Debian Linux. You can install software with `apt`
-* your working directory will not change, even if you run `cd`. All commands will be run in the `/workspace` directory.
-* don't run interactive commands, or commands that don't return (e.g. `node server.js`). You may run commands in the background (e.g. `node server.js &`)
-
-What is your next thought or action? Again, you must reply with JSON, and only with JSON.
-
-%(hint)s
-"""
-
-MONOLOGUE_SUMMARY_PROMPT = """
-Below is the internal monologue of an automated LLM agent. Each
-thought is an item in a JSON array. The thoughts may be memories,
-actions taken by the agent, or outputs from those actions.
-Please return a new, smaller JSON array, which summarizes the
-internal monologue. You can summarize individual thoughts, and
-you can condense related thoughts together with a description
-of their content.
-
-%(monologue)s
-
-Make the summaries as pithy and informative as possible.
-Be specific about what happened and what was learned. The summary
-will be used as keywords for searching for the original memory.
-Be sure to preserve any key words or important information.
-
-Your response must be in JSON format. It must be an object with the
-key `new_monologue`, which is a JSON array containing the summarized monologue.
-Each entry in the array must have an `action` key, and an `args` key.
-The action key may be `summarize`, and `args.summary` should contain the summary.
-You can also use the same action and args from the source monologue.
-"""
-
-
-def get_summarize_monologue_prompt(thoughts: List[dict]):
-    """
-    Gets the prompt for summarizing the monologue
-
-    Returns: 
-    - str: A formatted string with the current monologue within the prompt
-    """
-    return MONOLOGUE_SUMMARY_PROMPT % {
-        'monologue': json.dumps({'old_monologue': thoughts}, indent=2),
-    }
-
-def get_request_action_prompt(
-        task: str,
-        thoughts: List[dict],
-        background_commands_obs: List[CmdOutputObservation] = [],
-):
-    """
-    Gets the action prompt formatted with appropriate values.
-
-    Parameters:
-    - task (str): The current task the agent is trying to accomplish
-    - thoughts (List[dict]): The agent's current thoughts
-    - background_commands_obs (List[CmdOutputObservation]): List of all observed background commands running
-
-    Returns:
-    - str: Formatted prompt string with hint, task, monologue, and background included
-    """
-
-    hint = ''
-    if len(thoughts) > 0:
-        latest_thought = thoughts[-1]
-        if "action" in latest_thought:
-            if latest_thought["action"] == 'think':
-                if latest_thought["args"]['thought'].startswith("OK so my task is"):
-                    hint = "You're just getting started! What should you do first?"
-                else:
-                    hint = "You've been thinking a lot lately. Maybe it's time to take action?"
-            elif latest_thought["action"] == 'error':
-                hint = "Looks like that last command failed. Maybe you need to fix it, or try something else."
-
-    bg_commands_message = ""
-    if len(background_commands_obs) > 0:
-        bg_commands_message = "The following commands are running in the background:"
-        for command_obs in background_commands_obs:
-            bg_commands_message += f"\n`{command_obs.command_id}`: {command_obs.command}"
-        bg_commands_message += "\nYou can end any process by sending a `kill` action with the numerical `id` above."
-        
-    return ACTION_PROMPT % {
-        'task': task,
-        'monologue': json.dumps(thoughts, indent=2),
-        'background_commands': bg_commands_message,
-        'hint': hint,
-    }
-
-def parse_action_response(response: str) -> Action:
-    """
-    Parses a string to find an action within it
-
-    Parameters:
-    - response (str): The string to be parsed
-
-    Returns:
-    - Action: The action that was found in the response string
-    """
-    action_dict = json.loads(response)
-    if 'content' in action_dict:
-        # The LLM gets confused here. Might as well be robust
-        action_dict['contents'] = action_dict.pop('content')
-    return action_from_dict(action_dict)
-
-def parse_summary_response(response: str) -> List[dict]:
-    """
-    Parses a summary of the monologue
-
-    Parameters:
-    - response (str): The response string to be parsed
-
-    Returns:
-    - List[dict]: The list of summaries output by the model
-    """
-    parsed = json.loads(response)
-    return parsed['new_monologue']

agenthub/planner_agent/__init__.py

@@ -1,4 +0,0 @@
-from opendevin.agent import Agent
-from .agent import PlannerAgent
-
-Agent.register("PlannerAgent", PlannerAgent)

agenthub/planner_agent/agent.py

@@ -1,49 +0,0 @@
-from typing import List
-from .prompt import get_prompt, parse_response
-
-from opendevin.agent import Agent
-from opendevin.action import AgentFinishAction
-from opendevin.llm.llm import LLM
-from opendevin.state import State
-from opendevin.action import Action
-
-class PlannerAgent(Agent):
-    """
-    The planner agent utilizes a special prompting strategy to create long term plans for solving problems.
-    The agent is given its previous action-observation pairs, current task, and hint based on last action taken at every step.
-    """
-
-    def __init__(self, llm: LLM):
-        """
-        Initialize the Planner Agent with an LLM
-
-        Parameters:
-        - llm (LLM): The llm to be used by this agent
-        """
-        super().__init__(llm)
-
-    def step(self, state: State) -> Action:
-        """
-        Checks to see if current step is completed, returns AgentFinishAction if True. 
-        Otherwise, creates a plan prompt and sends to model for inference, returning the result as the next action.
-
-        Parameters:
-        - state (State): The current state given the previous actions and observations
-
-        Returns:
-        - AgentFinishAction: If the last state was 'completed', 'verified', or 'abandoned'
-        - Action: The next action to take based on llm response
-        """
-
-        if state.plan.task.state in ['completed', 'verified', 'abandoned']:
-            return AgentFinishAction()
-        prompt = get_prompt(state.plan, state.history)
-        messages = [{"content": prompt, "role": "user"}]
-        resp = self.llm.completion(messages=messages)
-        action_resp = resp['choices'][0]['message']['content']
-        action = parse_response(action_resp)
-        return action
-
-    def search_memory(self, query: str) -> List[str]:
-        return []
-

agenthub/planner_agent/prompt.py

@@ -1,229 +0,0 @@
-import json
-from typing import List, Tuple, Dict, Type
-
-from opendevin.controller.agent_controller import print_with_color
-from opendevin.plan import Plan
-from opendevin.action import Action, action_from_dict
-from opendevin.observation import Observation
-from opendevin.schema import ActionType
-
-from opendevin.action import (
-    NullAction,
-    CmdRunAction,
-    CmdKillAction,
-    BrowseURLAction,
-    FileReadAction,
-    FileWriteAction,
-    AgentRecallAction,
-    AgentThinkAction,
-    AgentFinishAction,
-    AgentSummarizeAction,
-    AddTaskAction,
-    ModifyTaskAction,
-)
-
-from opendevin.observation import (
-    NullObservation,
-)
-
-ACTION_TYPE_TO_CLASS: Dict[str, Type[Action]] = {
-    ActionType.RUN: CmdRunAction,
-    ActionType.KILL: CmdKillAction,
-    ActionType.BROWSE: BrowseURLAction,
-    ActionType.READ: FileReadAction,
-    ActionType.WRITE: FileWriteAction,
-    ActionType.RECALL: AgentRecallAction,
-    ActionType.THINK: AgentThinkAction,
-    ActionType.SUMMARIZE: AgentSummarizeAction,
-    ActionType.FINISH: AgentFinishAction,
-    ActionType.ADD_TASK: AddTaskAction,
-    ActionType.MODIFY_TASK: ModifyTaskAction,
-}
-
-HISTORY_SIZE = 10
-
-prompt = """
-# Task
-You're a diligent software engineer AI. You can't see, draw, or interact with a
-browser, but you can read and write files, and you can run commands, and you can think.
-
-You've been given the following task:
-
-%(task)s
-
-## Plan
-As you complete this task, you're building a plan and keeping
-track of your progress. Here's a JSON representation of your plan:
-
-%(plan)s
-
-
-%(plan_status)s
-
-You're responsible for managing this plan and the status of tasks in
-it, by using the `add_task` and `modify_task` actions described below.
-
-If the History below contradicts the state of any of these tasks, you
-MUST modify the task using the `modify_task` action described below.
-
-Be sure NOT to duplicate any tasks. Do NOT use the `add_task` action for
-a task that's already represented. Every task must be represented only once.
-
-Tasks that are sequential MUST be siblings. They must be added in order
-to their parent task.
-
-If you mark a task as 'completed', 'verified', or 'abandoned',
-all non-abandoned subtasks will be marked the same way.
-So before closing a task this way, you MUST not only be sure that it has
-been completed successfully--you must ALSO be sure that all its subtasks
-are ready to be marked the same way.
-
-If, and only if, ALL tasks have already been marked verified,
-you MUST respond with the `finish` action.
-
-## History
-Here is a recent history of actions you've taken in service of this plan,
-as well as observations you've made. This only includes the MOST RECENT
-ten actions--more happened before that.
-
-%(history)s
-
-
-Your most recent action is at the bottom of that history.
-
-## Action
-What is your next thought or action? Your response must be in JSON format.
-
-It must be an object, and it must contain two fields:
-* `action`, which is one of the actions below
-* `args`, which is a map of key-value pairs, specifying the arguments for that action
-
-* `read` - reads the content of a file. Arguments:
-  * `path` - the path of the file to read
-* `write` - writes the content to a file. Arguments:
-  * `path` - the path of the file to write
-  * `content` - the content to write to the file
-* `run` - runs a command on the command line in a Linux shell. Arguments:
-  * `command` - the command to run
-  * `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
-* `kill` - kills a background command
-  * `id` - the ID of the background command to kill
-* `browse` - opens a web page. Arguments:
-  * `url` - the URL to open
-* `think` - make a plan, set a goal, or record your thoughts. Arguments:
-  * `thought` - the thought to record
-* `add_task` - add a task to your plan. Arguments:
-  * `parent` - the ID of the parent task
-  * `goal` - the goal of the task
-  * `subtasks` - a list of subtasks, each of which is a map with a `goal` key.
-* `modify_task` - close a task. Arguments:
-  * `id` - the ID of the task to close
-  * `state` - set to 'in_progress' to start the task, 'completed' to finish it, 'verified' to assert that it was successful, 'abandoned' to give up on it permanently, or `open` to stop working on it for now.
-* `finish` - if ALL of your tasks and subtasks have been verified or abandoned, and you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.
-
-You MUST take time to think in between read, write, run, browse, and recall actions.
-You should never act twice in a row without thinking. But if your last several
-actions are all `think` actions, you should consider taking a different action.
-
-What is your next thought or action? Again, you must reply with JSON, and only with JSON.
-
-%(hint)s
-"""
-
-
-def get_prompt(plan: Plan, history: List[Tuple[Action, Observation]]) -> str:
-    """
-    Gets the prompt for the planner agent.
-    Formatted with the most recent action-observation pairs, current task, and hint based on last action
-
-    Parameters:
-    - plan (Plan): The original plan outlined by the user with LLM defined tasks
-    - history (List[Tuple[Action, Observation]]): List of corresponding action-observation pairs
-
-    Returns:
-    - str: The formatted string prompt with historical values
-    """
-
-    plan_str = json.dumps(plan.task.to_dict(), indent=2)
-    sub_history = history[-HISTORY_SIZE:]
-    history_dicts = []
-    latest_action: Action = NullAction()
-    for action, observation in sub_history:
-        if not isinstance(action, NullAction):
-            history_dicts.append(action.to_dict())
-            latest_action = action
-        if not isinstance(observation, NullObservation):
-            observation_dict = observation.to_dict()
-            if (
-                "extras" in observation_dict
-                and "screenshot" in observation_dict["extras"]
-            ):
-                del observation_dict["extras"]["screenshot"]
-            history_dicts.append(observation_dict)
-    history_str = json.dumps(history_dicts, indent=2)
-
-    hint = ""
-    current_task = plan.get_current_task()
-    if current_task is not None:
-        plan_status = f"You're currently working on this task:\n{current_task.goal}."
-        if len(current_task.subtasks) == 0:
-            plan_status += "\nIf it's not achievable AND verifiable with a SINGLE action, you MUST break it down into subtasks NOW."
-    else:
-        plan_status = "You're not currently working on any tasks. Your next action MUST be to mark a task as in_progress."
-        hint = plan_status
-
-    latest_action_id = latest_action.to_dict()["action"]
-
-    if current_task is not None:
-        if latest_action_id == "":
-            hint = "You haven't taken any actions yet. Start by using `ls` to check out what files you're working with."
-        elif latest_action_id == ActionType.RUN:
-            hint = "You should think about the command you just ran, what output it gave, and how that affects your plan."
-        elif latest_action_id == ActionType.READ:
-            hint = "You should think about the file you just read, what you learned from it, and how that affects your plan."
-        elif latest_action_id == ActionType.WRITE:
-            hint = "You just changed a file. You should think about how it affects your plan."
-        elif latest_action_id == ActionType.BROWSE:
-            hint = "You should think about the page you just visited, and what you learned from it."
-        elif latest_action_id == ActionType.THINK:
-            hint = "Look at your last thought in the history above. What does it suggest? Don't think anymore--take action."
-        elif latest_action_id == ActionType.RECALL:
-            hint = "You should think about the information you just recalled, and how it should affect your plan."
-        elif latest_action_id == ActionType.ADD_TASK:
-            hint = "You should think about the next action to take."
-        elif latest_action_id == ActionType.MODIFY_TASK:
-            hint = "You should think about the next action to take."
-        elif latest_action_id == ActionType.SUMMARIZE:
-            hint = ""
-        elif latest_action_id == ActionType.FINISH:
-            hint = ""
-
-    print_with_color("HINT:\n" + hint, "INFO")
-    return prompt % {
-        "task": plan.main_goal,
-        "plan": plan_str,
-        "history": history_str,
-        "hint": hint,
-        "plan_status": plan_status,
-    }
-
-
-def parse_response(response: str) -> Action:
-    """
-    Parses the model output to find a valid action to take
-
-    Parameters:
-    - response (str): A response from the model that potentially contains an Action.
-
-    Returns:
-    - Action: A valid next action to perform from model output
-    """
-    json_start = response.find("{")
-    json_end = response.rfind("}") + 1
-    response = response[json_start:json_end]
-    action_dict = json.loads(response)
-    if "contents" in action_dict:
-        # The LLM gets confused here. Might as well be robust
-        action_dict["content"] = action_dict.pop("contents")
-    action = action_from_dict(action_dict)
-    return action

agenthub/thinkact_agent/__init__.py

@@ -1,4 +0,0 @@
-from opendevin.agent import Agent
-from .agent import ThinkActAgent
-
-Agent.register('ThinkActAgent', ThinkActAgent)

agenthub/thinkact_agent/agent.py

@@ -1,99 +0,0 @@
-from typing import List
-from opendevin.agent import Agent
-from opendevin.llm.llm import LLM
-from opendevin.state import State
-from opendevin.action import Action, AgentThinkAction
-from opendevin.observation import Observation
-
-from .parser import parse_command
-
-from .prompts import (
-    SYSTEM_MESSAGE,
-    STEP_PROMPT,
-    MEMORY_FORMAT,
-    NO_ACTION,
-    CONTEXT_PROMPT
-)
-
-# TODO: Add state management
-
-
-class ThinkActAgent(Agent):
-    """
-    An attempt to recreate swe_agent with output parsing, prompting style, and Application Computer Interface (ACI).
-
-    SWE-agent includes ACI functions like 'goto', 'search_for', 'edit', 'scroll', 'run'
-    """
-
-    def __init__(self, llm: LLM):
-        super().__init__(llm)
-        self.memory_window = 5
-        self.max_retries = 5
-        self.running_memory: List[str] = []
-
-    def _remember(self, action: Action, observation: Observation):
-        """Agent has a limited memory of the few steps implemented as a queue"""
-        memory = MEMORY_FORMAT(action.to_dict(), observation.to_dict())
-        self.running_memory.append(memory)
-
-    def _think_act(self, messages: List[dict]) -> tuple[Action, str]:
-        resp = self.llm.completion(
-            messages=messages,
-            temperature=0.0
-        )
-        action_resp = resp['choices'][0]['message']['content']
-        return parse_command(action_resp)
-
-    def step(self, state: State) -> Action:
-        """
-        SWE-Agent step:
-            1. Get context - past actions, custom commands, current step
-            2. Perform think-act - prompt model for action and reasoning
-            3. Catch errors - ensure model takes action (5 attempts max)
-        """
-        for prev_action, obs in state.updated_info:
-            self._remember(prev_action, obs)
-
-        prompt = STEP_PROMPT(
-            state.plan.main_goal,
-            state.working_dir,
-            state.file_name,
-            state.cur_line
-        )
-
-        context = CONTEXT_PROMPT(
-            self.running_memory,
-            self.memory_window
-        )
-
-        msgs = [
-            {'content': SYSTEM_MESSAGE, 'role': 'user'},
-            {'content': prompt, 'role': 'user'}
-        ]
-
-        if len(self.running_memory) > 0:
-            msgs.insert(0, context)
-
-        # print('\n\n\n'.join([m['content'] for m in msgs]))
-        action, thought = self._think_act(messages=msgs)
-
-        start_msg_len = len(msgs)
-        while not action and len(msgs) < self.max_retries + start_msg_len:
-            error = NO_ACTION(thought)
-            error_msg = {'content': error, 'role': 'user'}
-            msgs.append(error_msg)
-            action, thought = self._think_act(messages=msgs)
-
-        if not action:
-            action = AgentThinkAction(thought)
-
-        self.latest_action = action
-        return action
-
-    def search_memory(self, query: str) -> List[str]:
-        return [item for item in self.running_memory if query in item]
-
-    def reset(self) -> None:
-        """Used to reset the agent"""
-        self.running_memory = []
-        super().reset()

agenthub/thinkact_agent/parser.py

@@ -1,75 +0,0 @@
-from opendevin.action import (
-    Action,
-    AgentFinishAction,
-    CmdRunAction,
-    FileReadAction,
-    FileWriteAction,
-    BrowseURLAction,
-)
-
-# commands: exit, read, write, browse, kill, search_file, search_dir
-
-
-def get_action_from_string(command_string: str) -> Action | None:
-    """
-    Parses the command string to find which command the agent wants to run
-    Converts the command into a proper Action and returns
-    """
-    vars = command_string.split(' ')
-    cmd = vars[0]
-    args = [] if len(vars) == 1 else ' '.join(vars[1:])
-
-    # TODO: add exception handling for improper commands
-    if 'exit' == cmd:
-        return AgentFinishAction()
-
-    elif 'read' == cmd:
-        if len(args) == 1:
-            file = args[0]
-            start = 0
-        elif len(args) == 2:
-            file, start = args[0], int(args[1])
-        elif len(args) > 2:
-            file, start = args[0], int(args[1])
-        else:
-            return None
-
-        return FileReadAction(file, start)
-
-    elif 'write' == cmd:
-        assert len(args) >= 4, 'Not enough arguments for this command'
-        file = args[0]
-        start, end = [int(arg) for arg in args[1:3]]
-        content = ' '.join(args[3:])
-        return FileWriteAction(file, content, start, end)
-
-    elif 'browse' == cmd:
-        return BrowseURLAction(args[0].strip())
-
-    # TODO: need to integrate all of the custom commands
-
-    else:
-        return CmdRunAction(command_string)
-
-
-def parse_command(input_str: str):
-    """
-    Parses a given string and separates the command (enclosed in triple backticks) from any accompanying text.
-
-    Args:
-        input_str (str): The input string to be parsed.
-
-    Returns:
-        tuple: A tuple containing the command and the accompanying text (if any).
-    """
-    input_str = input_str.strip()
-    if '```' in input_str:
-        parts = input_str.split('```')
-        command_str = parts[1].strip()
-        action = get_action_from_string(command_str)
-        if action:
-            ind = 2 if len(parts) > 2 else 1
-            accompanying_text = ''.join(parts[:-ind]).strip()
-            return action, accompanying_text
-
-    return None, input_str  # used for retry

agenthub/thinkact_agent/plans.md

@@ -1,36 +0,0 @@
-# Things that need to be done for SWE-Agent
-
-## 1. Add in all of the following commands to ACI
-```
-'search_for': {
-    'params': '<keywords>',
-    'description': 'Will allow you to search your working directory for files and folders that match your <keyword>.',
-}
-
-'edit ': {
-    'params': '<filename>',
-    'description': 'This will allow you to modify files within your working directory. Usage: "edit example.txt" -> opens the example.txt file and shows the first 100 lines',
-},
-
-'goto': {
-    'params': '<line_num>',
-    'description': 'This will allow you to go through a file to any line. Usage: "Goto 124" -> returns lines 124-224 within current file',
-},
-
-'scroll_up': {
-    'params': '',
-    'description': 'When you are in a file you can see the 100 lines above your current view. Usage: "scroll_up" -> returns the 100 lines above what you were reading',
-},
-
-'scroll_down': {
-    'params': '',
-    'description': 'When you are in a file you can see the 100 lines below your current view. Usage: "scroll_down" -> returns the 100 lines below what you were reading',
-},
-
-'modify': {
-    'params': '<start_line>:<end_line> "<replacement>"',
-    'description': 'This will make changes to a file by deleting all lines from <start_line> to <end_line> and replacing them with <replacement>',
-}
-
-```
-## 2. Add linter to check code edits before modifying file

agenthub/thinkact_agent/prompts.py

@@ -1,158 +0,0 @@
-from opendevin.parse_commands import parse_command_file
-
-
-DEFAULT_COMMANDS = {
-    'exit': 'Executed when task is complete',
-    'read <file_name> [<start_line>]': 'shows a given file\'s contents starting from <start_line>, default start is 0',
-    'write <file> <changes> [<start_line>] [<end_line>]': 'modifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>',
-    'browse <url>': 'returns the text version of any url',
-    '<bash_command> <args>': 'Any bash command is valid (cd, ls, rm, grep, dir, mv, wget, git, zip, etc.) with their arguments included',
-}
-
-
-DEFAULT_COMMAND_STR = '\n'.join(
-    [k + ' - ' + v for k, v in DEFAULT_COMMANDS.items()])
-
-
-COMMAND_DOCS = parse_command_file()
-
-
-CUSTOM_COMMANDS = f"""
-Apart from the standard bash commands, you can also use the following special commands:
-{COMMAND_DOCS}
-"""
-
-
-COMMAND_SEGMENT = CUSTOM_COMMANDS if COMMAND_DOCS is not None else ''
-
-
-DOCUMENTATION = f"""
-Commands:
-{DEFAULT_COMMAND_STR}
-{COMMAND_SEGMENT}
-"""
-
-
-RESPONSE_FORMAT = '''
-This is the format of the response you will make in order to solve the current issue.
-You will be given multiple iterations to complete this task so break it into steps and solve them one by one.
-
-Your output must contain the following:
-- First, think about what your next action should be and plan it out. you will have a memory of your thoughts so you can use this to remember things for the next step.
-- Second, create a piece of code that will execute your next action based on the thoughts you have.
-    - The code MUST be surrounded in triple back ticks EXACTLY like this: ```\n<code>\n```
-
-This is a template using the format described above
-Items in <> are suggestions for you, fill them out based on the context of the problem you are solving.
-Format:
-    Thoughts:
-    <Provide clear and concise thoughts on the next steps to take, highlighting any important details or context that should be remembered.>
-    Action to execute:
-    ```
-    <command> <params>
-    ```
-
-Notes:
-- If you give more than one command as your output then only the last command in your output will be executed.
-- To execute multiple commands you should write them down in your thoughts so you can remember it on the next step and execute them then.
-- The only commands you are not capable of executing are interactive commands like `python` or `vim`.
-- When you have finished the task you should run the `exit` command so the system knows you have finished.
-- The write command requires proper indentation in the content section ex. `write hw.py def hello():\n    print(\'Hello World\')` this is how you would have to format your write command.
-    - The white spaces matter as the code changes will be added to the code so they must have proper syntax.
-'''
-
-
-SYSTEM_MESSAGE = f'''
-SYSTEM INFO:
-You are an autonomous coding agent, here to provide solutions for coding issues. I have been designed to assist you with a wide range of programming tasks, from code editing and debugging to testing and deployment. I have access to a variety of tools and commands that I can use to help you solve problems efficiently.
-{DOCUMENTATION}
-
-{RESPONSE_FORMAT}
-'''.strip()
-
-
-GENERAL_GUIDELINES = '''INSTRUCTIONS:
-Now, you're going to solve this issue on your own. You can use any bash commands or custom commands you wish to complete your task. Edit all the files you need to and run any checks or tests that you want.
-Remember, YOU CAN ONLY ENTER ONE COMMAND AT A TIME. You should always wait for feedback after every command.
-When you're satisfied with all of the changes you've made, you can indicate that you are done by running the exit command.
-Note however that you cannot use any interactive session commands (e.g. python, vim) in this environment, but you can write scripts and run them. E.g. you can write a python script and then run it with `python <script_name>.py`.
-
-NOTE ABOUT THE write COMMAND: Indentation really matters! When editing a file, make sure to insert appropriate indentation before each line!
-
-IMPORTANT TIPS:
-1. Reproduce the bug: Always start by trying to replicate the bug that the issue discusses. If the issue includes code for reproducing the bug, we recommend that you re-implement that in your environment and run it to ensure you can reproduce the bug. Then, start trying to fix it. When you think you've fixed the bug, re-run the bug reproduction script to make sure that the issue has indeed been resolved.
-
-   If the bug reproduction script does not print anything when it successfully runs, we recommend adding a print("Script completed successfully, no errors.") command at the end of the file, so that you can be sure the script ran fine all the way through.
-
-2. Try different commands: If you run a command and it doesn't work, try running a different command. A command that did not work once will not work the second time unless you modify it.
-
-3. Navigate large files: If you open a file and need to get to an area around a specific line that is not in the first 100 lines, say line 583, you would use the 'read' command like this: 'read <file> 583'. This is a much faster way to read through the file.
-
-4. Handle input files: If the bug reproduction script requires inputting/reading a specific file, such as 'buggy-input.png', and you'd like to understand how to input that file, conduct a search in the existing repository code to see whether someone else has already done that. Do this by running the command: 'search_dir "buggy-input.png"'. If that doesn't work, use the Linux 'find' command.
-
-5. Understand your context: Always make sure to look at the currently open file and the current working directory. The currently open file might be in a different directory than the working directory.
-
-6. Verify your edits: When editing files, it is easy to accidentally specify a wrong line number or to write code with incorrect indentation. Always check the code after you issue an edit to make sure that it reflects what you wanted to accomplish. If it didn't, issue another command to fix it.
-
-7. Thoroughly test your solution: After making any changes to fix a bug, be sure to thoroughly test your solution to ensure the bug has been resolved. Re-run the bug reproduction script and verify that the issue has been addressed.
-'''
-
-
-def NO_ACTION(latest): return f'''
-You did not include any action to take in your most recent output:
-
-===== Output ======
-{latest}
-==== End Output ===
-
-Remember these are the custom commands you can use:
-{DOCUMENTATION}
-
-Lets try that again, it is very important that you adhere to the output format
-This time, be sure to use the exact format below, replacing anything in <> with the appropriate value(s):
-{RESPONSE_FORMAT}
-
-It is crucial you use the format provided as the output will be parsed automatically.
-'''
-
-
-def file_info(dir: str, file: str, line: int):
-    res = 'Here is an overview of your current workspace:\n'
-    res += f'\t- Working Directory: {dir}'
-    if file:
-        res += f'\t- Open File: {file}, Lines {line}:{line+100}'
-    return res
-
-
-def STEP_PROMPT(task, dir, file, line_num): return f'''
-{GENERAL_GUIDELINES}
-
-You are currently trying to complete this task:
-{task}
-
-{file_info(dir, file, line_num)}
-
-Keep all of the guidelines above in mind when you are thinking and making code.
-Please come up with a thought and action based on your current task and latest steps.
-'''.strip()
-
-
-def MEMORY_FORMAT(act, obs): return f'''
-You performed this action:
-'{act}'
-
-The following happened as a result:
-{obs}
-'''.strip()
-
-
-def CONTEXT_PROMPT(memory, window):
-    res = f'These are your past {window} memories:\n'
-    window_size = window if len(memory) > window else len(memory)
-    cur_mems = memory[-window_size:]
-    res += '===== Memories =====\n'
-    for idx, mem in enumerate(cur_mems):
-        res += f'\nMemory {idx}:\n{mem}\n'
-    res += '======= End =======\n'
-    res += 'Use these memories to provide additional context to the problem you are solving.\n'
-    return res

build.sh

@@ -0,0 +1,4 @@
+#!/usr/bin/env bash
+set -e
+
+poetry build -v

config.template.toml

@@ -0,0 +1,536 @@
+###################### OpenHands Configuration Example ######################
+#
+# All settings have default values, so you only need to uncomment and
+# modify what you want to change
+# The fields within each section are sorted in alphabetical order.
+#
+##############################################################################
+
+#################################### Core ####################################
+# General core configurations
+##############################################################################
+[core]
+# API keys and configuration for core services
+
+# Base path for the workspace
+#workspace_base = "./workspace"
+
+# Cache directory path
+#cache_dir = "/tmp/cache"
+
+# Debugging enabled
+#debug = false
+
+# Disable color in terminal output
+#disable_color = 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
+#replay_trajectory_path = ""
+
+# File store path
+#file_store_path = "/tmp/file_store"
+
+# File store type
+#file_store = "memory"
+
+# 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
+
+# Path to mount the workspace in the sandbox
+#workspace_mount_path_in_sandbox = "/workspace"
+
+# Path to mount the workspace
+#workspace_mount_path = ""
+
+# Path to rewrite the workspace mount path to
+#workspace_mount_rewrite = ""
+
+# Run as openhands
+#run_as_openhands = true
+
+# Runtime environment
+#runtime = "docker"
+
+# Name of the default agent
+#default_agent = "CodeActAgent"
+
+# JWT secret for authentication
+#jwt_secret = ""
+
+# Restrict file types for file uploads
+#file_uploads_restrict_file_types = false
+
+# 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
+##############################################################################
+[llm]
+# AWS access key ID
+#aws_access_key_id = ""
+
+# AWS region name
+#aws_region_name = ""
+
+# AWS secret access key
+#aws_secret_access_key = ""
+
+# API key to use (For Headless / CLI only -  In Web this is overridden by Session Init)
+api_key = ""
+
+# API base URL (For Headless / CLI only -  In Web this is overridden by Session Init)
+#base_url = ""
+
+# 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
+
+# Cost per output token
+#output_cost_per_token = 0.0
+
+# Custom LLM provider
+#custom_llm_provider = ""
+
+# Maximum number of characters in an observation's content
+#max_message_chars = 10000
+
+# Maximum number of input tokens
+#max_input_tokens = 0
+
+# Maximum number of output tokens
+#max_output_tokens = 0
+
+# Model to use. (For Headless / CLI only -  In Web this is overridden by Session Init)
+model = "gpt-4o"
+
+# Number of retries to attempt when an operation fails with the LLM.
+# Increase this value to allow more attempts before giving up
+#num_retries = 8
+
+# Maximum wait time (in seconds) between retry attempts
+# This caps the exponential backoff to prevent excessively long
+#retry_max_wait = 120
+
+# Minimum wait time (in seconds) between retry attempts
+# This sets the initial delay before the first retry
+#retry_min_wait = 15
+
+# Multiplier for exponential backoff calculation
+# The wait time increases by this factor after each failed attempt
+# A value of 2.0 means each retry waits twice as long as the previous one
+#retry_multiplier = 2.0
+
+# Drop any unmapped (unsupported) params without causing an exception
+#drop_params = false
+
+# Modify params for litellm to do transformations like adding a default message, when a message is empty.
+# Note: this setting is global, unlike drop_params, it cannot be overridden in each call to litellm.
+#modify_params = true
+
+# Using the prompt caching feature if provided by the LLM and supported
+#caching_prompt = true
+
+# Base URL for the OLLAMA API
+#ollama_base_url = ""
+
+# Temperature for the API
+#temperature = 0.0
+
+# Timeout for the API
+#timeout = 0
+
+# Top p for the API
+#top_p = 1.0
+
+# If model is vision capable, this option allows to disable image processing (useful for cost reduction).
+#disable_vision = true
+
+# Custom tokenizer to use for token counting
+# https://docs.litellm.ai/docs/completion/token_usage
+#custom_tokenizer = ""
+
+# Whether to use native tool calling if supported by the model. Can be true, false, or None by default, which chooses the model's default behavior based on the evaluation.
+# ATTENTION: Based on evaluation, enabling native function calling may lead to worse results
+# in some scenarios. Use with caution and consider testing with your specific use case.
+# https://github.com/OpenHands/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 = ""
+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')
+# Use 'agent' for the default agent config
+# otherwise, group name must be `agent.<agent_name>` (case-sensitive), e.g.
+# agent.CodeActAgent
+##############################################################################
+[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 LLM draft editor is enabled
+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
+enable_jupyter = true
+
+# Whether the command tool is enabled
+enable_cmd = true
+
+# Whether the think tool is enabled
+enable_think = true
+
+# Whether the finish tool is enabled
+enable_finish = true
+
+# LLM config group to use
+#llm_config = 'your-llm-config-group'
+
+# Whether to use prompt extension (e.g., microagent, repo/runtime info) at all
+#enable_prompt_extensions = 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
+##############################################################################
+[sandbox]
+# Sandbox timeout in seconds
+#timeout = 120
+
+# Sandbox user ID
+#user_id = 1000
+
+# Container image to use for the sandbox
+#base_container_image = "nikolaik/python-nodejs:python3.12-nodejs22"
+
+# Use host network
+#use_host_network = false
+
+# Runtime extra build args
+#runtime_extra_build_args = ["--network=host", "--add-host=host.docker.internal:host-gateway"]
+
+# Enable auto linting after editing
+#enable_auto_lint = false
+
+# Whether to initialize plugins
+#initialize_plugins = true
+
+# Extra dependencies to install in the runtime image
+#runtime_extra_deps = ""
+
+# Environment variables to set at the launch of the runtime
+#runtime_startup_env_vars = {}
+
+# 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
+##############################################################################
+[security]
+
+# Enable confirmation mode (For Headless / CLI only -  In Web this is overridden by Session Init)
+#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
+
+########################### 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"

config.toml.template

@@ -1,4 +0,0 @@
-# This is a template. Run `cp config.toml.template config.toml` to use it.
-
-LLM_API_KEY="<YOUR OPENAI API KEY>"
-WORKSPACE_DIR="./workspace"

containers/README.md

@@ -0,0 +1,12 @@
+# Docker Containers
+
+Each folder here contains a Dockerfile, and a config.sh describing how to build
+the images and where to push them. These images are built and pushed in GitHub Actions
+by the `ghcr.yml` workflow.
+
+## Building Manually
+
+```bash
+docker build -f containers/app/Dockerfile -t openhands .
+docker build -f containers/sandbox/Dockerfile -t sandbox .
+```

containers/app/Dockerfile

@@ -0,0 +1,95 @@
+ARG OPENHANDS_BUILD_VERSION=dev
+FROM node:25.2-trixie-slim AS frontend-builder
+
+WORKDIR /app
+
+COPY frontend/package.json frontend/package-lock.json ./
+RUN npm ci
+
+COPY frontend ./
+RUN npm run build
+
+FROM python:3.13.7-slim-trixie AS base
+FROM base AS backend-builder
+
+WORKDIR /app
+ENV PYTHONPATH='/app'
+
+ENV POETRY_NO_INTERACTION=1 \
+    POETRY_VIRTUALENVS_IN_PROJECT=1 \
+    POETRY_VIRTUALENVS_CREATE=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
+
+COPY pyproject.toml poetry.lock ./
+RUN touch README.md
+RUN export POETRY_CACHE_DIR && poetry install --no-root && rm -rf $POETRY_CACHE_DIR
+
+FROM base AS openhands-app
+
+WORKDIR /app
+
+# re-declare for this section
+ARG OPENHANDS_BUILD_VERSION
+
+ENV RUN_AS_OPENHANDS=true
+# A random number--we need this to be different from the user's UID on the host machine
+ENV OPENHANDS_USER_ID=42420
+ENV SANDBOX_LOCAL_RUNTIME_URL=http://host.docker.internal
+ENV USE_HOST_NETWORK=false
+ENV WORKSPACE_BASE=/opt/workspace_base
+ENV OPENHANDS_BUILD_VERSION=$OPENHANDS_BUILD_VERSION
+ENV SANDBOX_USER_ID=0
+ENV FILE_STORE=local
+ENV FILE_STORE_PATH=/.openhands
+ENV INIT_GIT_IN_EMPTY_WORKSPACE=1
+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/*
+
+# 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 && \
+    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 $WORKSPACE_BASE
+USER openhands
+
+ENV VIRTUAL_ENV=/app/.venv \
+    PATH="/app/.venv/bin:$PATH" \
+    PYTHONPATH='/app'
+
+COPY --chown=openhands:openhands --chmod=770 --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
+
+COPY --chown=openhands: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 ./
+
+# 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 {} +
+
+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
+
+USER root
+
+WORKDIR /app
+
+ENTRYPOINT ["/app/entrypoint.sh"]
+CMD ["uvicorn", "openhands.server.listen:app", "--host", "0.0.0.0", "--port", "3000"]

containers/app/config.sh

@@ -0,0 +1,4 @@
+DOCKER_REGISTRY=ghcr.io
+DOCKER_ORG=openhands
+DOCKER_IMAGE=openhands
+DOCKER_BASE_DIR="."

containers/app/entrypoint.sh

@@ -0,0 +1,73 @@
+#!/bin/bash
+set -eo pipefail
+
+echo "Starting OpenHands..."
+if [[ $NO_SETUP == "true" ]]; then
+  echo "Skipping setup, running as $(whoami)"
+  "$@"
+  exit 0
+fi
+
+if [ "$(id -u)" -ne 0 ]; then
+  echo "The OpenHands entrypoint.sh must run as root"
+  exit 1
+fi
+
+if [ -z "$SANDBOX_USER_ID" ]; then
+  echo "SANDBOX_USER_ID is not set"
+  exit 1
+fi
+
+if [ -z "$WORKSPACE_MOUNT_PATH" ]; then
+  # This is set to /opt/workspace in the Dockerfile. But if the user isn't mounting, we want to unset it so that OpenHands doesn't mount at all
+  unset WORKSPACE_BASE
+fi
+
+if [[ "$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 [[ "$SANDBOX_USER_ID" -eq 0 ]]; then
+  echo "Running OpenHands as root"
+  export RUN_AS_OPENHANDS=false
+  "$@"
+else
+  echo "Setting up enduser with id $SANDBOX_USER_ID"
+  if id "enduser" &>/dev/null; then
+    echo "User enduser already exists. Skipping creation."
+  else
+    if ! useradd -l -m -u $SANDBOX_USER_ID -s /bin/bash enduser; then
+      echo "Failed to create user enduser with id $SANDBOX_USER_ID. Moving openhands user."
+      incremented_id=$(($SANDBOX_USER_ID + 1))
+      usermod -u $incremented_id openhands
+      if ! useradd -l -m -u $SANDBOX_USER_ID -s /bin/bash enduser; then
+        echo "Failed to create user enduser with id $SANDBOX_USER_ID for a second time. Exiting."
+        exit 1
+      fi
+    fi
+  fi
+  usermod -aG openhands enduser
+  # get the user group of /var/run/docker.sock and set openhands to that group
+  DOCKER_SOCKET_GID=$(stat -c '%g' /var/run/docker.sock)
+  echo "Docker socket group id: $DOCKER_SOCKET_GID"
+  if getent group $DOCKER_SOCKET_GID; then
+    echo "Group with id $DOCKER_SOCKET_GID already exists"
+  else
+    echo "Creating group with id $DOCKER_SOCKET_GID"
+    groupadd -g $DOCKER_SOCKET_GID docker
+  fi
+
+  mkdir -p /home/enduser/.cache/huggingface/hub/
+
+  usermod -aG $DOCKER_SOCKET_GID enduser
+  echo "Running as enduser"
+  su enduser /bin/bash -c "${*@Q}" # This magically runs any arguments passed to the script as a command
+fi

containers/build.sh

@@ -0,0 +1,182 @@
+#!/usr/bin/env bash
+set -eo pipefail
+
+# Initialize variables with default values
+image_name=""
+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 "  -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
+}
+
+# Parse command-line options
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        -i) image_name="$2"; shift 2 ;;
+        -o) org_name="$2"; shift 2 ;;
+        --push) push=1; shift ;;
+        --load) load=1; shift ;;
+        -t) tag_suffix="$2"; shift 2 ;;
+        --dry) dry_run=1; shift ;;
+        *) usage ;;
+    esac
+done
+# Check if required arguments are provided
+if [[ -z "$image_name" ]]; then
+    echo "Error: Image name is required."
+    usage
+fi
+
+echo "Building: $image_name"
+tags=()
+
+OPENHANDS_BUILD_VERSION="dev"
+
+cache_tag_base="buildcache"
+cache_tag="$cache_tag_base"
+
+if [[ -n $RELEVANT_SHA ]]; then
+  git_hash=$(git rev-parse --short "$RELEVANT_SHA")
+  tags+=("$git_hash")
+  tags+=("$RELEVANT_SHA")
+fi
+
+if [[ -n $GITHUB_REF_NAME ]]; then
+  # check if ref name is a version number
+  if [[ $GITHUB_REF_NAME =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+    major_version=$(echo "$GITHUB_REF_NAME" | cut -d. -f1)
+    minor_version=$(echo "$GITHUB_REF_NAME" | cut -d. -f1,2)
+    tags+=("$major_version" "$minor_version")
+    tags+=("latest")
+  fi
+  sanitized_ref_name=$(echo "$GITHUB_REF_NAME" | sed 's/[^a-zA-Z0-9.-]\+/-/g')
+  OPENHANDS_BUILD_VERSION=$sanitized_ref_name
+  sanitized_ref_name=$(echo "$sanitized_ref_name" | tr '[:upper:]' '[:lower:]') # lower case is required in tagging
+  tags+=("$sanitized_ref_name")
+  cache_tag+="-${sanitized_ref_name}"
+fi
+
+if [[ -n $tag_suffix ]]; then
+  cache_tag+="-${tag_suffix}"
+  for i in "${!tags[@]}"; do
+    tags[$i]="${tags[$i]}-$tag_suffix"
+  done
+fi
+
+echo "Tags: ${tags[@]}"
+
+if [[ "$image_name" == "openhands" ]]; then
+  dir="./containers/app"
+elif [[ "$image_name" == "runtime" ]]; then
+  dir="./containers/runtime"
+else
+  dir="./containers/$image_name"
+fi
+
+if [[ (! -f "$dir/Dockerfile") && "$image_name" != "runtime" ]]; then
+  # Allow runtime to be built without a Dockerfile
+  echo "No Dockerfile found"
+  exit 1
+fi
+if [[ ! -f "$dir/config.sh" ]]; then
+  echo "No config.sh found for Dockerfile"
+  exit 1
+fi
+
+source "$dir/config.sh"
+
+if [[ -n "$org_name" ]]; then
+  DOCKER_ORG="$org_name"
+fi
+
+# If $DOCKER_IMAGE_SOURCE_TAG is set, add it to the tags
+if [[ -n "$DOCKER_IMAGE_SOURCE_TAG" ]]; then
+  tags+=("$DOCKER_IMAGE_SOURCE_TAG")
+fi
+# If $DOCKER_IMAGE_TAG is set, add it to the tags
+if [[ -n "$DOCKER_IMAGE_TAG" ]]; then
+  tags+=("$DOCKER_IMAGE_TAG")
+fi
+
+DOCKER_REPOSITORY="$DOCKER_REGISTRY/$DOCKER_ORG/$DOCKER_IMAGE"
+DOCKER_REPOSITORY=${DOCKER_REPOSITORY,,} # lowercase
+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"
+fi
+
+if [[ $load -eq 1 ]]; then
+  args+=" --load"
+fi
+
+echo "Args: $args"
+
+# Modify the platform selection based on --load flag
+if [[ $load -eq 1 ]]; then
+  # When loading, build only for the current platform
+  platform=$(docker version -f '{{.Server.Os}}/{{.Server.Arch}}')
+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"
+
+docker buildx build \
+  $args \
+  --build-arg OPENHANDS_BUILD_VERSION="$OPENHANDS_BUILD_VERSION" \
+  --cache-from=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag \
+  --cache-from=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag_base-main \
+  --platform $platform \
+  --provenance=false \
+  -f "$dir/Dockerfile" \
+  "$DOCKER_BASE_DIR"
+
+# If load was requested, print the loaded images
+if [[ $load -eq 1 ]]; then
+  echo "Local images built:"
+  docker images "$DOCKER_REPOSITORY" --format "{{.Repository}}:{{.Tag}}"
+fi

containers/dev/Dockerfile

@@ -0,0 +1,127 @@
+# syntax=docker/dockerfile:1
+
+###
+FROM ubuntu:22.04 AS dind
+
+# https://docs.docker.com/engine/install/ubuntu/
+RUN apt-get update && apt-get install -y \
+	ca-certificates \
+	curl \
+	&& install -m 0755 -d /etc/apt/keyrings \
+	&& curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc \
+	&& chmod a+r /etc/apt/keyrings/docker.asc \
+	&& echo \
+		"deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
+		$(. /etc/os-release && echo "$VERSION_CODENAME") stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null
+
+RUN apt-get update && apt-get install -y \
+	docker-ce \
+	docker-ce-cli \
+	containerd.io \
+	docker-buildx-plugin \
+	docker-compose-plugin \
+	&& rm -rf /var/lib/apt/lists/* \
+	&& apt-get clean \
+	&& apt-get autoremove -y
+
+###
+FROM dind AS openhands
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+#
+RUN apt-get update && apt-get install -y \
+	bash \
+    build-essential \
+    curl \
+	git \
+	git-lfs \
+	software-properties-common \
+	make \
+    netcat \
+    sudo \
+	wget \
+	&& rm -rf /var/lib/apt/lists/* \
+	&& apt-get clean \
+	&& apt-get autoremove -y
+
+# https://github.com/cli/cli/blob/trunk/docs/install_linux.md
+RUN curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg | dd of=/usr/share/keyrings/githubcli-archive-keyring.gpg \
+	&& chmod go+r /usr/share/keyrings/githubcli-archive-keyring.gpg \
+	&& echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" | tee /etc/apt/sources.list.d/github-cli.list > /dev/null \
+	&& apt-get update && apt-get -y install \
+    gh \
+  && rm -rf /var/lib/apt/lists/* \
+  && apt-get clean \
+  && apt-get autoremove -y
+
+# Python 3.12
+RUN add-apt-repository ppa:deadsnakes/ppa \
+    && apt-get update \
+    && 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 - \
+    && apt-get install -y nodejs
+
+# Poetry >= 1.8
+RUN curl -fsSL https://install.python-poetry.org | python3.12 - \
+    && ln -s ~/.local/bin/poetry /usr/local/bin/poetry
+
+#
+RUN <<EOF
+#!/bin/bash
+printf "#!/bin/bash
+set +x
+uname -a
+docker --version
+gh --version | head -n 1
+git --version
+#
+python --version
+echo node `node --version`
+echo npm `npm --version`
+poetry --version
+netcat -h 2>&1 | head -n 1
+" > /version.sh
+chmod a+x /version.sh
+EOF
+
+###
+FROM openhands AS dev
+
+RUN apt-get update && apt-get install -y \
+	dnsutils \
+	file \
+	iproute2 \
+	jq \
+	lsof \
+	ripgrep \
+	silversearcher-ag \
+	vim \
+	&& rm -rf /var/lib/apt/lists/* \
+	&& 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 \
+  <<EOF
+#!/bin/bash
+make -s clean
+make -s check-dependencies
+make -s install-python-dependencies
+
+# NOTE
+# node_modules are .dockerignore-d therefore not mountable
+# make -s install-frontend-dependencies
+EOF
+
+#
+CMD ["bash"]

containers/dev/README.md

@@ -0,0 +1,57 @@
+# Develop in Docker
+
+> [!WARNING]
+> This way of running OpenHands is not officially supported. It is maintained by the community and may not work.
+
+Install [Docker](https://docs.docker.com/engine/install/) on your host machine and run:
+
+```bash
+make docker-dev
+# same as:
+cd ./containers/dev
+./dev.sh
+```
+
+It could take some time if you are running for the first time as Docker will pull all the  tools required for building OpenHands. The next time you run again, it should be instant.
+
+## Build and run
+
+If everything goes well, you should be inside a container after Docker finishes building the `openhands:dev` image similar to the following:
+
+```bash
+Build and run in Docker ...
+root@93fc0005fcd2:/app#
+```
+
+You may now proceed with the normal [build and run](../../Development.md) workflow as if you were on the host.
+
+## Make changes
+
+The source code on the host is mounted as `/app` inside docker. You may edit the files as usual either inside the Docker container or on your host with your favorite IDE/editors.
+
+The following are also mapped as readonly from your host:
+
+```yaml
+# host credentials
+- $HOME/.git-credentials:/root/.git-credentials:ro
+- $HOME/.gitconfig:/root/.gitconfig:ro
+- $HOME/.npmrc:/root/.npmrc:ro
+```
+
+## VSCode
+
+Alternatively, if you use VSCode, you could also [attach to the running container](https://code.visualstudio.com/docs/devcontainers/attach-container).
+
+See details for [developing in docker](https://code.visualstudio.com/docs/devcontainers/containers) or simply ask `OpenHands` ;-)
+
+## Rebuild dev image
+
+You could optionally pass additional options to the build script.
+
+```bash
+make docker-dev OPTIONS="--build"
+# or
+./containers/dev/dev.sh --build
+```
+
+See [docker compose run](https://docs.docker.com/reference/cli/docker/compose/run/) for more options.

containers/dev/compose.yml

@@ -0,0 +1,40 @@
+#
+services:
+  dev:
+    privileged: true
+    build:
+      context: ${OPENHANDS_WORKSPACE:-../../}
+      dockerfile: ./containers/dev/Dockerfile
+    image: openhands:dev
+    container_name: openhands-dev
+    environment:
+      - BACKEND_HOST=${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_USER_ID=${SANDBOX_USER_ID:-1234}
+      - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
+    ports:
+      - "3000:3000"
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock
+      - ${WORKSPACE_BASE:-$PWD/workspace}:/opt/workspace_base
+      # source code
+      - ${OPENHANDS_WORKSPACE:-../../}:/app
+      # host credentials
+      - $HOME/.git-credentials:/root/.git-credentials:ro
+      - $HOME/.gitconfig:/root/.gitconfig:ro
+      - $HOME/.npmrc:/root/.npmrc:ro
+      # cache
+      - cache-data:/root/.cache
+    pull_policy: never
+    stdin_open: true
+    tty: true
+
+##
+volumes:
+  cache-data:

containers/dev/dev.sh

@@ -0,0 +1,39 @@
+#!/usr/bin/env bash
+set -o pipefail
+
+function get_docker() {
+    echo "Docker is required to build and run OpenHands."
+    echo "https://docs.docker.com/get-started/get-docker/"
+    exit 1
+}
+
+function check_tools() {
+	command -v docker &>/dev/null || get_docker
+}
+
+function exit_if_indocker() {
+    if [ -f /.dockerenv ]; then
+        echo "Running inside a Docker container. Exiting..."
+        exit 1
+    fi
+}
+
+#
+exit_if_indocker
+
+check_tools
+
+##
+OPENHANDS_WORKSPACE=$(git rev-parse --show-toplevel)
+
+cd "$OPENHANDS_WORKSPACE/containers/dev/" || exit 1
+
+##
+export BACKEND_HOST="0.0.0.0"
+#
+export SANDBOX_USER_ID=$(id -u)
+export WORKSPACE_BASE=${WORKSPACE_BASE:-$OPENHANDS_WORKSPACE/workspace}
+
+docker compose run --rm --service-ports "$@" dev
+
+##

containers/runtime/README.md

@@ -0,0 +1,12 @@
+# Dynamically constructed Dockerfile
+
+This folder builds a runtime image (sandbox), which will use a dynamically generated `Dockerfile`
+that depends on the `base_image` **AND** a [Python source distribution](https://docs.python.org/3.10/distutils/sourcedist.html) that is based on the current commit of `openhands`.
+
+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 \
+    --base_image nikolaik/python-nodejs:python3.12-nodejs22 \
+    --build_folder containers/runtime
+```

containers/runtime/config.sh

@@ -0,0 +1,7 @@
+DOCKER_REGISTRY=ghcr.io
+DOCKER_ORG=openhands
+DOCKER_BASE_DIR="./containers/runtime"
+DOCKER_IMAGE=runtime
+# These variables will be appended by the runtime_build.py script
+# DOCKER_IMAGE_TAG=
+# DOCKER_IMAGE_SOURCE_TAG=

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

@@ -1,44 +1,65 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v3.2.0
+    rev: v5.0.0
     hooks:
       - id: trailing-whitespace
+        exclude: ^(docs/|modules/|python/|openhands-ui/|third_party/|enterprise/)
       - id: end-of-file-fixer
+        exclude: ^(docs/|modules/|python/|openhands-ui/|third_party/|enterprise/)
       - id: check-yaml
+        args: ["--allow-multiple-documents"]
       - id: debug-statements
-      - id: double-quote-string-fixer
 
-  - repo: https://github.com/hhatto/autopep8
-    rev: v2.1.0
-    hooks:
-      - id: autopep8
 
-  - repo: https://github.com/asottile/setup-cfg-fmt
-    rev: v2.5.0
+  - repo: local
     hooks:
-      - id: setup-cfg-fmt
-        always_run: true
+      - 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
+    hooks:
+      - id: pyproject-fmt
+  - repo: https://github.com/abravalheri/validate-pyproject
+    rev: v0.24.1
+    hooks:
+      - id: validate-pyproject
+
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.3.5
+    rev: v0.11.8
     hooks:
       # Run the linter.
       - id: ruff
-        entry: ruff check --config dev_config/python/ruff.toml opendevin/ agenthub/
-        types_or: [ python, pyi, jupyter ]
-        args: [ --fix ]
+        entry: ruff check --config dev_config/python/ruff.toml
+        types_or: [python, pyi, jupyter]
+        args: [--fix, --unsafe-fixes]
+        exclude: ^(third_party/|enterprise/)
       # Run the formatter.
       - id: ruff-format
-        entry: ruff check --config dev_config/python/ruff.toml opendevin/ agenthub/
-        types_or: [ python, pyi, jupyter ]
+        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: v1.9.0
+    rev: v1.15.0
     hooks:
       - id: mypy
-        additional_dependencies: [types-requests, types-setuptools, types-pyyaml, types-toml]
-        entry: mypy --config-file dev_config/python/mypy.ini opendevin/ agenthub/
+        additional_dependencies:
+          [
+            types-requests,
+            types-setuptools,
+            types-pyyaml,
+            types-toml,
+            types-docker,
+            types-Markdown,
+            pydantic,
+            lxml,
+          ]
+        # To see gaps add `--html-report mypy-report/`
+        entry: mypy --config-file dev_config/python/mypy.ini openhands/
         always_run: true
         pass_filenames: false

dev_config/python/mypy.ini

@@ -7,5 +7,10 @@ warn_unreachable = True
 warn_redundant_casts = True
 no_implicit_optional = True
 strict_optional = True
+disable_error_code = type-abstract
 
-exclude = agenthub/monologue_agent/regression
+# 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

@@ -1,3 +1,42 @@
-exclude = [
-    "agenthub/monologue_agent/regression/",
-]
+# Exclude third-party runtime directory from linting
+exclude = ["third_party/", "enterprise/"]
+
+[lint]
+select = [
+    "E",
+    "W",
+    "F",
+    "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 = [
+    "E501",
+    "B003",
+    "B007",
+    "B009",
+    "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]
+docstring-quotes = "double"
+inline-quotes = "single"
+
+[format]
+quote-style = "single"
+
+[lint.flake8-bugbear]
+extend-immutable-calls = ["Depends", "fastapi.Depends", "fastapi.params.Depends"]

docker-compose.yml

@@ -0,0 +1,24 @@
+
+services:
+  openhands:
+    build:
+      context: ./
+      dockerfile: ./containers/app/Dockerfile
+    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
+      - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
+    ports:
+      - "3000:3000"
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock
+      - ~/.openhands:/.openhands
+      - ${WORKSPACE_BASE:-$PWD/workspace}:/opt/workspace_base
+    pull_policy: build
+    stdin_open: true
+    tty: true

docs/architecture/Architecture.md

@@ -1,14 +0,0 @@
-
-# System Architecture Overview
-
-This is a high-level overview of the system architecture. The system is divided into two main components: the frontend and the backend. The frontend is responsible for handling user interactions and displaying the results. The backend is responsible for handling the business logic and executing the agents.
-
-![system_architecture.svg](system_architecture.svg)
-
-This Overview is simplified to show the main components and their interactions. For a more detailed view of the backend architecture, see the [Backend Architecture](#backend-architecture) section.
-
-# Backend Architecture
-
-*__Disclaimer__: The backend architecture is a work in progress and is subject to change. The following diagram shows the current architecture of the backend based on the commit that is shown in the footer of the diagram.*
-
-![backend_architecture.svg](backend_architecture.svg)

docs/architecture/README.md

@@ -1,23 +0,0 @@
-# Process for updating the backend architecture diagram
-The generation of the backend architecture diagram is partially automated. The diagram is generated from the type hints in the code using the py2puml tool. The diagram is then manually reviewed, adjusted and exported to PNG and SVG.
-
-## Prerequisites
-- Running python environment in which opendevin is executable (according to the instructions in the README.md file in the root of the repository)
-- [py2puml](https://github.com/lucsorel/py2puml) installed
-
-## Steps
-1. Autogenerate the diagram by running the following command from the root of the repository:  
-```py2puml opendevin opendevin > docs/architecture/backend_architecture.puml```
-
-2. Open the generated file in a PlantUML editor, e.g. Visual Studio Code with the PlantUML extension or [PlantText](https://www.planttext.com/)
-
-3. Review the generated PUML and make all necessary adjustments to the diagram (add missing parts, fix mistakes, improve positioning).  
-*py2puml creates the diagram based on the type hints in the code, so missing or incorrect type hints may result in an incomplete or incorrect diagram.*
-
-4. Review the diff between the new and the previous diagram and manually check if the changes are correct.  
-*Make sure not to remove parts that were manually added to the diagram in the past and are still relevant.*
-
-4. Add the commit hash of the commit that was used to generat the diagram to the diagram footer.
-
-5. Export the diagram as PNG and SVG files and replace the existing diagrams in the `docs/architecture` directory. This can be done with (e.g. [PlantText](https://www.planttext.com/))
-

docs/architecture/backend_architecture.puml

@@ -1,222 +0,0 @@
-@startuml opendevin
-!pragma useIntermediatePackages false
-
-class opendevin.action.agent.AgentEchoAction {
-  content: str
-  runnable: bool
-  action: str
-}
-class opendevin.action.agent.AgentFinishAction {
-  runnable: bool
-  action: str
-}
-class opendevin.observation.AgentMessageObservation {
-  role: str
-  observation: str
-}
-class opendevin.action.agent.AgentRecallAction {
-  query: str
-  action: str
-}
-class opendevin.observation.AgentRecallObservation {
-  memories: List[str]
-  role: str
-  observation: str
-}
-class opendevin.action.agent.AgentSummarizeAction {
-  summary: str
-  action: str
-}
-class opendevin.action.agent.AgentThinkAction {
-  thought: str
-  runnable: bool
-  action: str
-}
-class opendevin.action.base.ExecutableAction {
-}
-class opendevin.action.base.NotExecutableAction {
-}
-class opendevin.observation.Observation {
-  content: str
-}
-class opendevin.action.base.Action {
-}
-class opendevin.action.base.NullAction {
-  action: str
-}
-class opendevin.action.bash.CmdKillAction {
-  id: int
-  action: str
-}
-class opendevin.action.bash.CmdRunAction {
-  command: str
-  background: bool
-  action: str
-}
-class opendevin.action.browse.BrowseURLAction {
-  url: str
-  action: str
-}
-class opendevin.observation.BrowserOutputObservation {
-  url: str
-  status_code: int
-  error: bool
-  observation: str
-}
-class opendevin.action.fileop.FileReadAction {
-  path: str
-  action: str
-}
-class opendevin.observation.FileReadObservation {
-  path: str
-  observation: str
-}
-class opendevin.action.fileop.FileWriteAction {
-  path: str
-  contents: str
-  action: str
-}
-class opendevin.observation.FileWriteObservation {
-  path: str
-  observation: str
-}
-class opendevin.action.tasks.AddTaskAction {
-  parent: str
-  goal: str
-  subtasks: list
-  action: str
-}
-class opendevin.action.tasks.ModifyTaskAction {
-  id: str
-  state: str
-  action: str
-}
-abstract class opendevin.agent.Agent {
-  _registry: Dict[str, Type[Agent]] {static}
-  llm: LLM
-  _complete: None
-}
-class opendevin.llm.llm.LLM {
-  model: None
-  api_key: None
-  base_url: None
-  _debug_dir: None
-  _debug_idx: None
-  _debug_id: None
-  _completion: None
-}
-class opendevin.controller.agent_controller.AgentController {
-  agent: Agent
-  max_iterations: int
-  workdir: str
-  command_manager: CommandManager
-  state: State
-  plan: Plan
-  callbacks: List[Callable]
-}
-class opendevin.observation.AgentErrorObservation {
-  observation: str
-}
-class opendevin.controller.command_manager.CommandManager {
-  directory: None
-  shell: None
-}
-class opendevin.observation.NullObservation {
-  observation: str
-}
-class opendevin.plan.Plan {
-  main_goal: str {static}
-  task: Task {static}
-  main_goal: str
-  task: None
-}
-class opendevin.state.State {
-  plan: Plan
-  iteration: int
-  background_commands_obs: List[CmdOutputObservation]
-  history: List[Tuple[Action, Observation]]
-  updated_info: List[Tuple[Action, Observation]]
-}
-class opendevin.observation.CmdOutputObservation {
-  command_id: int
-  command: str
-  exit_code: int
-  observation: str
-}
-class opendevin.sandbox.sandbox.DockerInteractive {
-  background_commands: Dict[int, BackgroundCommand] {static}
-  instance_id: None
-  instance_id: None
-  workspace_dir: None
-  workspace_dir: None
-  workspace_dir: None
-  timeout: int
-  container_image: None
-  container_name: None
-}
-class opendevin.observation.UserMessageObservation {
-  role: str
-  observation: str
-}
-class opendevin.plan.Task {
-  id: str {static}
-  goal: str {static}
-  parent: Task | None {static}
-  subtasks: List[Task] {static}
-  id: None
-  id: None
-  parent: None
-  goal: str
-  subtasks: None
-}
-
-class opendevin.server.session.Session {
-  websocket: None
-  controller: Optional[AgentController]
-  agent: Optional[Agent]
-  agent_task: None
-}
-
-opendevin.action.base.ExecutableAction <|-- opendevin.action.agent.AgentEchoAction
-opendevin.action.base.NotExecutableAction <|-- opendevin.action.agent.AgentFinishAction
-opendevin.observation.Observation <|-- opendevin.observation.AgentMessageObservation
-opendevin.action.base.ExecutableAction <|-- opendevin.action.agent.AgentRecallAction
-opendevin.observation.Observation <|-- opendevin.observation.AgentRecallObservation
-opendevin.action.base.NotExecutableAction <|-- opendevin.action.agent.AgentSummarizeAction
-opendevin.action.base.NotExecutableAction <|-- opendevin.action.agent.AgentThinkAction
-opendevin.action.base.Action <|-- opendevin.action.base.ExecutableAction
-opendevin.action.base.Action <|-- opendevin.action.base.NotExecutableAction
-opendevin.action.base.NotExecutableAction <|-- opendevin.action.base.NullAction
-opendevin.action.base.ExecutableAction <|-- opendevin.action.bash.CmdKillAction
-opendevin.action.base.ExecutableAction <|-- opendevin.action.bash.CmdRunAction
-opendevin.action.base.ExecutableAction <|-- opendevin.action.browse.BrowseURLAction
-opendevin.observation.Observation <|-- opendevin.observation.BrowserOutputObservation
-opendevin.action.base.ExecutableAction <|-- opendevin.action.fileop.FileReadAction
-opendevin.observation.Observation <|-- opendevin.observation.FileReadObservation
-opendevin.action.base.ExecutableAction <|-- opendevin.action.fileop.FileWriteAction
-opendevin.observation.Observation <|-- opendevin.observation.FileWriteObservation
-opendevin.action.base.NotExecutableAction <|-- opendevin.action.tasks.AddTaskAction
-opendevin.action.base.NotExecutableAction <|-- opendevin.action.tasks.ModifyTaskAction
-opendevin.agent.Agent *-- opendevin.agent.Agent
-opendevin.agent.Agent *-- opendevin.llm.llm.LLM
-opendevin.controller.agent_controller.AgentController *-- opendevin.agent.Agent
-opendevin.observation.Observation <|-- opendevin.observation.AgentErrorObservation
-opendevin.observation.Observation <|-- opendevin.observation.NullObservation
-opendevin.plan.Plan *-- opendevin.plan.Task
-opendevin.state.State *-- opendevin.plan.Plan
-opendevin.state.State *-- opendevin.observation.CmdOutputObservation
-opendevin.state.State *-- opendevin.action.base.Action
-opendevin.state.State *-- opendevin.observation.Observation
-opendevin.observation.Observation <|-- opendevin.observation.CmdOutputObservation
-opendevin.sandbox.sandbox.DockerInteractive *-- opendevin.sandbox.sandbox.BackgroundCommand
-opendevin.observation.Observation <|-- opendevin.observation.UserMessageObservation
-opendevin.plan.Task *-- opendevin.plan.Task
-opendevin.server.session.Session *-- opendevin.controller.agent_controller.AgentController
-opendevin.server.session.Session *-- opendevin.agent.Agent
-opendevin.controller.agent_controller.AgentController -> opendevin.state.State
-opendevin.controller.agent_controller.AgentController -> opendevin.plan.Plan
-opendevin.controller.agent_controller.AgentController -> opendevin.controller.command_manager.CommandManager
-opendevin.controller.command_manager.CommandManager -> opendevin.sandbox.sandbox.DockerInteractive
-
-footer Based on f3fda42; Generated by //py2puml//
-@enduml