add section for gitlab in docs

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

.devcontainer/README.MD

@@ -1 +0,0 @@
-The files in this directory configure a development container for GitHub Codespaces.

.devcontainer/devcontainer.json

@@ -1,15 +0,0 @@
-{
-	"name": "OpenDevin Codespaces",
-	"image": "mcr.microsoft.com/devcontainers/universal",
-	"customizations":{
-        "vscode":{
-            "extensions": [
-                "ms-python.python"
-            ]
-        }
-    },
-	"onCreateCommand": "sh ./.devcontainer/on_create.sh",
-	"postCreateCommand": "make build",
-	"postStartCommand": "USE_HOST_NETWORK=True nohup bash -c 'make run &'"
-
-}

.devcontainer/on_create.sh

@@ -1,8 +0,0 @@
-#!/usr/bin/env bash
-sudo apt update
-sudo apt install -y netcat
-sudo add-apt-repository -y ppa:deadsnakes/ppa
-sudo apt install -y python3.11
-curl -sSL https://install.python-poetry.org | python3.11 -
-# chromadb requires SQLite > 3.35 but SQLite in Python3.11.9 comes with 3.31.1
-sudo cp /opt/conda/lib/libsqlite3.so.0 /lib/x86_64-linux-gnu/libsqlite3.so.0

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -1,75 +1,63 @@
 name: Bug
-description: Report a problem with OpenDevin
+description: Report a problem with OpenHands
 title: '[Bug]: '
 labels: ['bug']
 body:
   - type: markdown
     attributes:
-      value: Thank you for taking the time to fill out this bug report. We greatly appreciate your effort to complete this template fully. Please provide as much information as possible to help us understand and address the issue effectively.
+      value: Thank you for taking the time to fill out this bug report. Please provide as much information as possible
+       to help us understand and address the issue effectively.
 
   - type: checkboxes
     attributes:
-      label: Is there an existing issue for the same bug?
+      label: Is there an existing issue for the same bug? (If one exists, thumbs up or comment on the issue instead).
       description: Please check if an issue already exists for the bug you encountered.
       options:
-      - label: I have checked the troubleshooting document at https://docs.all-hands.dev/modules/usage/troubleshooting
-        required: true
       - label: I have checked the existing issues.
         required: true
 
   - type: textarea
     id: bug-description
     attributes:
-      label: Describe the bug
-      description: Provide a short description of the problem.
+      label: Describe the bug and reproduction steps
+      description: Provide a description of the issue along with any reproduction steps.
     validations:
       required: true
 
-  - type: textarea
-    id: current-version
+  - type: dropdown
+    id: installation
     attributes:
-      label: Current OpenDevin version
-      description: What version of OpenDevin are you using? If you're running in docker, tell us the tag you're using (e.g. ghcr.io/opendevin/opendevin:0.3.1).
-      render: bash
-    validations:
-      required: true
+      label: OpenHands Installation
+      description: How are you running OpenHands?
+      options:
+        - Docker command in README
+        - GitHub resolver
+        - Development workflow
+        - app.all-hands.dev
+        - Other
+      default: 0
 
-  - type: textarea
-    id: config
+  - type: input
+    id: openhands-version
     attributes:
-      label: Installation and Configuration
-      description: Please provide any commands you ran and any configuration (redacting API keys)
-      render: bash
-    validations:
-      required: true
+      label: OpenHands Version
+      description: What version of OpenHands are you using?
+      placeholder: ex. 0.9.8, main, etc.
 
-  - type: textarea
-    id: model-agent
-    attributes:
-      label: Model and Agent
-      description: What model and agent are you using? You can see these settings in the UI by clicking the settings wheel.
-      placeholder: |
-        - Model:
-        - Agent:
-
-  - type: textarea
-    id: os-version
+  - type: dropdown
+    id: os
     attributes:
       label: Operating System
-      description: What Operating System are you using? Linux, Mac OS, WSL on Windows
-
-  - type: textarea
-    id: repro-steps
-    attributes:
-      label: Reproduction Steps
-      description: Please list the steps to reproduce the issue.
-      placeholder: |
-        1.
-        2.
-        3.
+      options:
+        - MacOS
+        - Linux
+        - WSL on Windows
 
   - type: textarea
     id: additional-context
     attributes:
       label: Logs, Errors, Screenshots, and Additional Context
-      description: If you want to share the chat history you can click the thumbs-down (👎) button above the input field and you will get a shareable link (you can also click thumbs up when things are going well of course!). LLM logs will be stored in the `logs/llm/default` folder. Please add any additional context about the problem here.
+      description: Please provide any additional information you think might help. If you want to share the chat history
+        you can click the thumbs-down (👎) button above the input field and you will get a shareable link
+        (you can also click thumbs up when things are going well of course!). LLM logs will be stored in the
+        `logs/llm/default` folder. Please add any additional context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,6 +1,6 @@
 ---
-name: Feature Request
-about: Suggest an idea for OpenDevin features
+name: Feature Request or Enhancement
+about: Suggest an idea for an OpenHands feature or enhancement
 title: ''
 labels: 'enhancement'
 assignees: ''
@@ -9,10 +9,9 @@ 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**
+**Describe the UX or technical implementation you have in mind**
 
 **Additional context**
+
+
+### If you find this feature request or enhancement useful, make sure to add a 👍 to the issue

.github/ISSUE_TEMPLATE/technical_proposal.md

@@ -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

@@ -1,22 +1,71 @@
-# To get started with Dependabot version updates, you'll need to specify which
-# package ecosystems to update and where the package manifests are located.
-# Please see the documentation for all configuration options:
-# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
-
 version: 2
 updates:
-  - package-ecosystem: "pip" # See documentation for possible values
-    directory: "/" # Location of package manifests
+  - package-ecosystem: "pip"
+    directory: "/"
     schedule:
       interval: "daily"
-    open-pull-requests-limit: 20
-  - package-ecosystem: "npm" # See documentation for possible values
-    directory: "/frontend" # Location of package manifests
+    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*"
+      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: 20
-  - package-ecosystem: "npm" # See documentation for possible values
-    directory: "/docs" # Location of package manifests
+    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: "daily"
-    open-pull-requests-limit: 20
+      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"

.github/pull_request_template.md

@@ -1,11 +1,12 @@
-**What is the problem that this fixes or functionality that this introduces? Does it fix any open issues?**
+- [ ] This change is worth documenting at https://docs.all-hands.dev/
+- [ ] Include this change in the Release Notes. If checked, you **must** provide an **end-user friendly** description for your change below
 
+**End-user friendly description of the problem this fixes or functionality that this introduces.**
 
 
 ---
-**Give a summary of what the PR does, explaining any non-trivial design decisions**
-
+**Give a summary of what the PR does, explaining any non-trivial design decisions.**
 
 
 ---
-**Other references**
+**Link of any specific issues this addresses.**

.github/scripts/check_version_consistency.py

@@ -0,0 +1,74 @@
+#!/usr/bin/env python3
+import os
+import re
+import sys
+from typing import Set, Tuple
+
+
+def find_version_references(directory: str) -> Tuple[Set[str], Set[str]]:
+    openhands_versions = set()
+    runtime_versions = set()
+
+    version_pattern_openhands = re.compile(r'openhands:(\d{1})\.(\d{2})')
+    version_pattern_runtime = re.compile(r'runtime:(\d{1})\.(\d{2})')
+
+    for root, _, files in os.walk(directory):
+        # Skip .git directory and docs/build directory
+        if '.git' in root or 'docs/build' in root:
+            continue
+
+        for file in files:
+            if file.endswith(
+                ('.md', '.yml', '.yaml', '.txt', '.html', '.py', '.js', '.ts')
+            ):
+                file_path = os.path.join(root, file)
+                try:
+                    with open(file_path, 'r', encoding='utf-8') as f:
+                        content = f.read()
+
+                        # Find all openhands version references
+                        matches = version_pattern_openhands.findall(content)
+                        if matches:
+                            print(f'Found openhands version {matches} in {file_path}')
+                            openhands_versions.update(matches)
+
+                        # Find all runtime version references
+                        matches = version_pattern_runtime.findall(content)
+                        if matches:
+                            print(f'Found runtime version {matches} in {file_path}')
+                            runtime_versions.update(matches)
+                except Exception as e:
+                    print(f'Error reading {file_path}: {e}', file=sys.stderr)
+
+    return openhands_versions, runtime_versions
+
+
+def main():
+    repo_root = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '..'))
+    print(f'Checking version consistency in {repo_root}')
+    openhands_versions, runtime_versions = find_version_references(repo_root)
+
+    print(f'Found openhands versions: {sorted(openhands_versions)}')
+    print(f'Found runtime versions: {sorted(runtime_versions)}')
+
+    exit_code = 0
+
+    if len(openhands_versions) > 1:
+        print('Error: Multiple openhands versions found:', file=sys.stderr)
+        print('Found versions:', sorted(openhands_versions), file=sys.stderr)
+        exit_code = 1
+    elif len(openhands_versions) == 0:
+        print('Warning: No openhands version references found', file=sys.stderr)
+
+    if len(runtime_versions) > 1:
+        print('Error: Multiple runtime versions found:', file=sys.stderr)
+        print('Found versions:', sorted(runtime_versions), file=sys.stderr)
+        exit_code = 1
+    elif len(runtime_versions) == 0:
+        print('Warning: No runtime version references found', file=sys.stderr)
+
+    sys.exit(exit_code)
+
+
+if __name__ == '__main__':
+    main()

.github/workflows/clean-up.yml

@@ -0,0 +1,69 @@
+# Workflow that cleans up outdated and old workflows to prevent out of disk issues
+name: Delete old workflow runs
+
+# This workflow is currently only triggered manually
+on:
+  workflow_dispatch:
+    inputs:
+      days:
+        description: 'Days-worth of runs to keep for each workflow'
+        required: true
+        default: '30'
+      minimum_runs:
+        description: 'Minimum runs to keep for each workflow'
+        required: true
+        default: '10'
+      delete_workflow_pattern:
+        description: 'Name or filename of the workflow (if not set, all workflows are targeted)'
+        required: false
+      delete_workflow_by_state_pattern:
+        description: 'Filter workflows by state: active, deleted, disabled_fork, disabled_inactivity, disabled_manually'
+        required: true
+        default: "ALL"
+        type: choice
+        options:
+          - "ALL"
+          - active
+          - deleted
+          - disabled_inactivity
+          - disabled_manually
+      delete_run_by_conclusion_pattern:
+        description: 'Remove runs based on conclusion: action_required, cancelled, failure, skipped, success'
+        required: true
+        default: 'ALL'
+        type: choice
+        options:
+          - 'ALL'
+          - 'Unsuccessful: action_required,cancelled,failure,skipped'
+          - action_required
+          - cancelled
+          - failure
+          - skipped
+          - success
+      dry_run:
+        description: 'Logs simulated changes, no deletions are performed'
+        required: false
+
+jobs:
+  del_runs:
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    permissions:
+      actions: write
+      contents: read
+    steps:
+      - name: Delete workflow runs
+        uses: Mattraks/delete-workflow-runs@v2
+        with:
+          token: ${{ github.token }}
+          repository: ${{ github.repository }}
+          retain_days: ${{ github.event.inputs.days }}
+          keep_minimum_runs: ${{ github.event.inputs.minimum_runs }}
+          delete_workflow_pattern: ${{ github.event.inputs.delete_workflow_pattern }}
+          delete_workflow_by_state_pattern: ${{ github.event.inputs.delete_workflow_by_state_pattern }}
+          delete_run_by_conclusion_pattern: >-
+            ${{
+              startsWith(github.event.inputs.delete_run_by_conclusion_pattern, 'Unsuccessful:')
+              && 'action_required,cancelled,failure,skipped'
+              || github.event.inputs.delete_run_by_conclusion_pattern
+            }}
+          dry_run: ${{ github.event.inputs.dry_run }}

.github/workflows/deploy-docs.yml

@@ -1,49 +1,63 @@
+# Workflow that builds and deploys the documentation website
 name: Deploy Docs to GitHub Pages
 
+# * Always run on "main"
+# * Run on PRs that target the "main" branch and have changes in the "docs" folder or this workflow
 on:
   push:
     branches:
       - main
   pull_request:
+    paths:
+      - 'docs/**'
+      - '.github/workflows/deploy-docs.yml'
     branches:
       - main
 
+# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
+concurrency:
+  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
+  cancel-in-progress: true
+
 jobs:
+  # Build the documentation website
   build:
+    if: github.repository == 'All-Hands-AI/OpenHands'
     name: Build Docusaurus
-    runs-on: ubuntu-latest
-    if: github.repository == 'OpenDevin/OpenDevin'
+    runs-on: blacksmith-4vcpu-ubuntu-2204
     steps:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
-      - uses: actions/setup-node@v4
+      - uses: useblacksmith/setup-node@v5
         with:
           node-version: 18
           cache: npm
           cache-dependency-path: docs/package-lock.json
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: useblacksmith/setup-python@v6
         with:
-          python-version: "3.11"
-
-      - name: Generate Python Docs
-        run: rm -rf docs/modules/python && pip install pydoc-markdown && pydoc-markdown
+          python-version: '3.12'
       - name: Install dependencies
         run: cd docs && npm ci
       - name: Build website
         run: cd docs && npm run build
-
       - name: Upload Build Artifact
         if: github.ref == 'refs/heads/main'
         uses: actions/upload-pages-artifact@v3
         with:
           path: docs/build
 
+  # Deploy the documentation website
   deploy:
+    if: github.ref == 'refs/heads/main' && github.repository == 'All-Hands-AI/OpenHands'
     name: Deploy to GitHub Pages
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    # This job only runs on "main" so only run one of these jobs at a time
+    # otherwise it will fail if one is already running
+    concurrency:
+      group: ${{ github.workflow }}-${{ github.ref }}
     needs: build
-    if: github.ref == 'refs/heads/main' && github.repository == 'OpenDevin/OpenDevin'
     # Grant GITHUB_TOKEN the permissions required to make a Pages deployment
     permissions:
       pages: write # to deploy to Pages
@@ -52,7 +66,6 @@ jobs:
     environment:
       name: github-pages
       url: ${{ steps.deployment.outputs.page_url }}
-    runs-on: ubuntu-latest
     steps:
       - name: Deploy to GitHub Pages
         id: deployment

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

@@ -1,42 +0,0 @@
-name: Run E2E test with dummy agent
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-
-on:
-  push:
-    branches:
-    - main
-  pull_request:
-
-env:
-  PERSIST_SANDBOX : "false"
-
-jobs:
-  test:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.11'
-      - name: Set up environment
-        run: |
-          curl -sSL https://install.python-poetry.org | python3 -
-          poetry install --without evaluation,llama-index
-          poetry run playwright install --with-deps chromium
-          wget https://huggingface.co/BAAI/bge-small-en-v1.5/raw/main/1_Pooling/config.json -P /tmp/llama_index/models--BAAI--bge-small-en-v1.5/snapshots/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/1_Pooling/
-      - name: Run tests
-        run: |
-          set -e
-          poetry run python opendevin/core/main.py -t "do a flip" -d ./workspace/ -c DummyAgent
-      - name: Check exit code
-        run: |
-          if [ $? -ne 0 ]; then
-            echo "Test failed"
-            exit 1
-          else
-            echo "Test passed"
-          fi

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

@@ -0,0 +1,48 @@
+# 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: [20, 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 make-i18n && tsc
+      - name: Run tests and collect coverage
+        working-directory: ./frontend
+        run: npm run test:coverage
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

.github/workflows/ghcr-build.yml

@@ -0,0 +1,456 @@
+# 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: ${{ steps.define-base-images.outputs.base_image }}
+    steps:
+      - name: Define base images
+        shell: bash
+        id: define-base-images
+        run: |
+          # Only build nikolaik on PRs, otherwise build both nikolaik and ubuntu.
+          if [[ "$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
+    permissions:
+      contents: read
+      packages: write
+    outputs:
+      # Since this job uses outputs it cannot use matrix
+      hash_from_app_image: ${{ steps.get_hash_in_app_image.outputs.hash_from_app_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@v3.6.0
+        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
+      - name: Build app image
+        if: "github.event.pull_request.head.repo.fork"
+        run: |
+          ./containers/build.sh -i openhands -o ${{ env.REPO_OWNER }} --load
+      - name: Get hash in App Image
+        id: get_hash_in_app_image
+        run: |
+          # Run the build script in the app image
+          docker run -e SANDBOX_USER_ID=0 -v /var/run/docker.sock:/var/run/docker.sock ghcr.io/${{ env.REPO_OWNER }}/openhands:${{ env.RELEVANT_SHA }} /bin/bash -c "mkdir -p containers/runtime; python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild" 2>&1 | tee docker-outputs.txt
+          # Get the hash from the build script
+          hash_from_app_image=$(cat docker-outputs.txt | grep "Hash for docker build directory" | awk -F "): " '{print $2}' | uniq | head -n1)
+          echo "hash_from_app_image=$hash_from_app_image" >> $GITHUB_OUTPUT
+          echo "Hash from app image: $hash_from_app_image"
+
+  # Builds the runtime Docker images
+  ghcr_build_runtime:
+    name: Build Image
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    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@v3.6.0
+        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: Set up Python
+        uses: useblacksmith/setup-python@v6
+        with:
+          python-version: '3.12'
+      - name: Cache Poetry dependencies
+        uses: useblacksmith/cache@v5
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          # This is the one that saves the cache, the others set 'lookup-only: true'
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+      - name: Install poetry via pipx
+        run: pipx install 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 openhands/runtime/utils/runtime_build.py --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 }}
+          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@v4
+        with:
+          name: runtime-src-${{ matrix.base_image.tag }}
+          path: containers/runtime
+
+  verify_hash_equivalence_in_runtime_and_app:
+    name: Verify Hash Equivalence in Runtime and Docker images
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    needs: [ghcr_build_runtime, ghcr_build_app]
+    strategy:
+      fail-fast: false
+      matrix:
+        base_image: ['nikolaik']
+    env:
+      BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST: nikolaik/python-nodejs:python3.12-nodejs22
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.pull_request.head.sha }}
+      - name: Cache Poetry dependencies
+        uses: useblacksmith/cache@v5
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          lookup-only: true
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+      - name: Set up Python
+        uses: useblacksmith/setup-python@v6
+        with:
+          python-version: '3.12'
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies POETRY_GROUP=main INSTALL_PLAYWRIGHT=0
+      - name: Get hash in App Image
+        run: |
+          echo "Hash from app image: ${{ needs.ghcr_build_app.outputs.hash_from_app_image }}"
+          echo "hash_from_app_image=${{ needs.ghcr_build_app.outputs.hash_from_app_image }}" >> $GITHUB_ENV
+
+      - name: Get hash using code (development mode)
+        run: |
+          mkdir -p containers/runtime
+          poetry run python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild > output.txt 2>&1
+          hash_from_code=$(cat output.txt | grep "Hash for docker build directory" | awk -F "): " '{print $2}' | uniq | head -n1)
+          echo "hash_from_code=$hash_from_code" >> $GITHUB_ENV
+
+      - name: Compare hashes
+        run: |
+          echo "Hash from App Image: ${{ env.hash_from_app_image }}"
+          echo "Hash from Code: ${{ env.hash_from_code }}"
+          if [ "${{ env.hash_from_app_image }}" = "${{ env.hash_from_code }}" ]; then
+            echo "Hashes match!"
+          else
+            echo "Hashes do not match!"
+            exit 1
+          fi
+
+  # Run unit tests with the Docker runtime Docker images as root
+  test_runtime_root:
+    name: RT Unit Tests (Root)
+    needs: [ghcr_build_runtime, define-matrix]
+    runs-on: blacksmith-8vcpu-ubuntu-2204
+    strategy:
+      fail-fast: false
+      matrix:
+        base_image: ${{ fromJson(needs.define-matrix.outputs.base_image) }}
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Download runtime source for fork
+        if: github.event.pull_request.head.repo.fork
+        uses: actions/download-artifact@v4
+        with:
+          name: runtime-src-${{ matrix.base_image.tag }}
+          path: containers/runtime
+      - name: Lowercase Repository Owner
+        run: |
+          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
+      # Forked repos can't push to GHCR, so we need to rebuild using cache
+      - name: Build runtime image ${{ matrix.base_image.image }} for fork
+        if: github.event.pull_request.head.repo.fork
+        uses: useblacksmith/build-push-action@v1
+        with:
+          load: true
+          tags: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+          context: containers/runtime
+      - name: Cache Poetry dependencies
+        uses: useblacksmith/cache@v5
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          lookup-only: true
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+      - name: Set up Python
+        uses: useblacksmith/setup-python@v6
+        with:
+          python-version: '3.12'
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies POETRY_GROUP=main,test,runtime INSTALL_PLAYWRIGHT=0
+      - name: Run docker runtime tests
+        run: |
+          # We install pytest-xdist in order to run tests across CPUs
+          poetry run pip install pytest-xdist
+
+          # Install to be able to retry on failures for flaky tests
+          poetry run pip install pytest-rerunfailures
+
+          image_name=ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+
+          # Setting RUN_AS_OPENHANDS to false means use root.
+          # That should mean SANDBOX_USER_ID is ignored but some tests do not check for RUN_AS_OPENHANDS.
+
+          TEST_RUNTIME=docker \
+          SANDBOX_USER_ID=$(id -u) \
+          SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
+          TEST_IN_CI=true \
+          RUN_AS_OPENHANDS=false \
+          poetry run pytest -n 7 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py --durations=10
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+  # Run unit tests with the Docker runtime Docker images as openhands user
+  test_runtime_oh:
+    name: RT Unit Tests (openhands)
+    runs-on: blacksmith-8vcpu-ubuntu-2204
+    needs: [ghcr_build_runtime, define-matrix]
+    strategy:
+      matrix:
+        base_image: ${{ fromJson(needs.define-matrix.outputs.base_image) }}
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Download runtime source for fork
+        if: github.event.pull_request.head.repo.fork
+        uses: actions/download-artifact@v4
+        with:
+          name: runtime-src-${{ matrix.base_image.tag }}
+          path: containers/runtime
+      - name: Lowercase Repository Owner
+        run: |
+          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
+      # Forked repos can't push to GHCR, so we need to rebuild using cache
+      - name: Build runtime image ${{ matrix.base_image.image }} for fork
+        if: github.event.pull_request.head.repo.fork
+        uses: useblacksmith/build-push-action@v1
+        with:
+          load: true
+          tags: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+          context: containers/runtime
+      - name: Cache Poetry dependencies
+        uses: useblacksmith/cache@v5
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          lookup-only: true
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+      - name: Set up Python
+        uses: useblacksmith/setup-python@v6
+        with:
+          python-version: '3.12'
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies POETRY_GROUP=main,test,runtime INSTALL_PLAYWRIGHT=0
+      - name: Run runtime tests
+        run: |
+          # We install pytest-xdist in order to run tests across CPUs
+          poetry run pip install pytest-xdist
+
+          # Install to be able to retry on failures for flaky tests
+          poetry run pip install pytest-rerunfailures
+
+          image_name=ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+
+          TEST_RUNTIME=docker \
+          SANDBOX_USER_ID=$(id -u) \
+          SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
+          TEST_IN_CI=true \
+          RUN_AS_OPENHANDS=true \
+          poetry run pytest -n 7 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py --durations=10
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+  # The two following jobs (named identically) are to check whether all the runtime tests have passed as the
+  # "All Runtime Tests Passed" is a required job for PRs to merge
+  # Due to this bug: https://github.com/actions/runner/issues/2566, we want to create a job that runs when the
+  # prerequisites have been cancelled or failed so merging is disallowed, otherwise Github considers "skipped" as "success"
+  runtime_tests_check_success:
+    name: All Runtime Tests Passed
+    if: ${{ !cancelled() && !contains(needs.*.result, 'failure') && !contains(needs.*.result, 'cancelled') }}
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    needs: [test_runtime_root, test_runtime_oh, verify_hash_equivalence_in_runtime_and_app]
+    steps:
+      - name: All tests passed
+        run: echo "All runtime tests have passed successfully!"
+
+  runtime_tests_check_fail:
+    name: All Runtime Tests Passed
+    if: ${{ cancelled() || contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled') }}
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    needs: [test_runtime_root, test_runtime_oh, verify_hash_equivalence_in_runtime_and_app]
+    steps:
+      - name: Some tests failed
+        run: |
+          echo "Some runtime tests failed or were cancelled"
+          exit 1
+  update_pr_description:
+    name: Update PR Description
+    if: github.event_name == 'pull_request' && !github.event.pull_request.head.repo.fork && github.actor != 'dependabot[bot]'
+    needs: [ghcr_build_runtime]
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Get short SHA
+        id: short_sha
+        run: echo "SHORT_SHA=$(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: ${{ steps.short_sha.outputs.SHORT_SHA }}
+        run: |
+          echo "updating PR description"
+          DOCKER_RUN_COMMAND="docker run -it --rm \
+            -p 3000:3000 \
+            -v /var/run/docker.sock:/var/run/docker.sock \
+            --add-host host.docker.internal:host-gateway \
+            -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:$SHORT_SHA-nikolaik \
+            --name openhands-app-$SHORT_SHA \
+            docker.all-hands.dev/all-hands-ai/openhands:$SHORT_SHA"
+
+          PR_BODY=$(gh pr view $PR_NUMBER --json body --jq .body)
+
+          if echo "$PR_BODY" | grep -q "To run this PR locally, use the following command:"; then
+            UPDATED_PR_BODY=$(echo "${PR_BODY}" | sed -E "s|docker run -it --rm.*|$DOCKER_RUN_COMMAND|")
+          else
+            UPDATED_PR_BODY="${PR_BODY}
+
+          ---
+
+          To run this PR locally, use the following command:
+          \`\`\`
+          $DOCKER_RUN_COMMAND
+          \`\`\`"
+          fi
+
+          echo "updated body: $UPDATED_PR_BODY"
+          gh pr edit $PR_NUMBER --body "$UPDATED_PR_BODY"

.github/workflows/ghcr.yml

@@ -1,481 +0,0 @@
-name: Build Publish and Test Runtime Image
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-
-on:
-  push:
-    branches:
-      - main
-    tags:
-      - '*'
-  pull_request:
-  workflow_dispatch:
-    inputs:
-      reason:
-        description: 'Reason for manual trigger'
-        required: true
-        default: ''
-
-jobs:
-  ghcr_build:
-    runs-on: ubuntu-latest
-
-    outputs:
-      tags: ${{ steps.capture-tags.outputs.tags }}
-
-    permissions:
-      contents: read
-      packages: write
-
-    strategy:
-      matrix:
-        image: ["sandbox", "opendevin"]
-        platform: ["amd64", "arm64"]
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Build and export image
-        id: build
-        run: ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} ${{ matrix.platform }}
-
-      - name: Capture tags
-        id: capture-tags
-        run: |
-          tags=$(cat tags.txt)
-          echo "tags=$tags"
-          echo "tags=$tags" >> $GITHUB_OUTPUT
-
-      - name: Upload Docker image as artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
-          path: /tmp/${{ matrix.image }}_image_${{ matrix.platform }}.tar
-
-  ghcr_build_runtime:
-    runs-on: ubuntu-latest
-
-    outputs:
-      tags: ${{ steps.capture-tags.outputs.tags }}
-
-    permissions:
-      contents: read
-      packages: write
-
-    strategy:
-      matrix:
-        image: ["od_runtime"]
-        base_image: ["ubuntu:22.04"]
-        platform: ["amd64", "arm64"]
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
-      - 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: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-          cache: "poetry"
-
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-
-      - name: Create source distribution and Dockerfile
-        run: poetry run python3 opendevin/runtime/utils/runtime_build.py --base_image ${{ matrix.base_image }} --build_folder containers/runtime
-
-      - name: Build and export image
-        id: build
-        run: ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} ${{ matrix.platform }}
-
-      - name: Capture tags
-        id: capture-tags
-        run: |
-          tags=$(cat tags.txt)
-          echo "tags=$tags"
-          echo "tags=$tags" >> $GITHUB_OUTPUT
-
-      - name: Upload Docker image as artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
-          path: /tmp/${{ matrix.image }}_image_${{ matrix.platform }}.tar
-
-  test_runtime:
-    name: Test Runtime
-    runs-on: ubuntu-latest
-    needs: [ghcr_build_runtime, ghcr_build]
-    env:
-      PERSIST_SANDBOX: "false"
-
-    strategy:
-      matrix:
-        runtime_type: ["eventstream", "server"]
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # when set to "true" but frees about 6 GB
-          tool-cache: true
-
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          swap-storage: true
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-          cache: "poetry"
-
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-
-      - name: Download Runtime Docker image
-        if: matrix.runtime_type == 'eventstream'
-        uses: actions/download-artifact@v4
-        with:
-          name: od_runtime-docker-image-amd64
-          path: /tmp/
-
-      - name: Download Sandbox Docker image
-        if: matrix.runtime_type == 'server'
-        uses: actions/download-artifact@v4
-        with:
-          name: sandbox-docker-image-amd64
-          path: /tmp/
-
-      - name: Load Runtime image and run runtime tests
-        run: |
-          # Load the Docker image and capture the output
-          if [ "${{ matrix.runtime_type }}" == "eventstream" ]; then
-            output=$(docker load -i /tmp/od_runtime_image_amd64.tar)
-          else
-            output=$(docker load -i /tmp/sandbox_image_amd64.tar)
-          fi
-
-          # Extract the first image name from the output
-          image_name=$(echo "$output" | grep -oP 'Loaded image: \K.*' | head -n 1)
-
-          # Print the full name of the image
-          echo "Loaded Docker image: $image_name"
-
-          TEST_RUNTIME=${{ matrix.runtime_type }} SANDBOX_USER_ID=$(id -u) SANDBOX_CONTAINER_IMAGE=$image_name TEST_IN_CI=true poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml -s ./tests/unit/test_runtime.py
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
-  integration_tests_on_linux:
-    name: Integration Tests on Linux
-    runs-on: ubuntu-latest
-    needs: ghcr_build
-    env:
-      PERSIST_SANDBOX: "false"
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ["3.11"]
-        sandbox: ["ssh", "local"]
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
-
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-
-      - name: Download sandbox Docker image
-        uses: actions/download-artifact@v4
-        with:
-          name: sandbox-docker-image-amd64
-          path: /tmp/
-
-      - name: Load sandbox image and run integration tests
-        env:
-          SANDBOX_BOX_TYPE: ${{ matrix.sandbox }}
-        run: |
-          # Load the Docker image and capture the output
-          output=$(docker load -i /tmp/sandbox_image_amd64.tar)
-
-          # Extract the first image name from the output
-          image_name=$(echo "$output" | grep -oP 'Loaded image: \K.*' | head -n 1)
-
-          # Print the full name of the image
-          echo "Loaded Docker image: $image_name"
-
-          SANDBOX_CONTAINER_IMAGE=$image_name TEST_IN_CI=true TEST_ONLY=true ./tests/integration/regenerate.sh
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
-
-  ghcr_push:
-    runs-on: ubuntu-latest
-    # don't push if integration tests or sandbox tests fail
-    needs: [ghcr_build, test_runtime, integration_tests_on_linux]
-    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
-
-    env:
-      tags: ${{ needs.ghcr_build.outputs.tags }}
-
-    permissions:
-      contents: read
-      packages: write
-
-    strategy:
-      matrix:
-        image: ["sandbox", "opendevin"]
-        platform: ["amd64", "arm64"]
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Login to GHCR
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Download Docker images
-        uses: actions/download-artifact@v4
-        with:
-          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
-          path: /tmp/${{ matrix.platform }}
-
-      - name: Load images and push to registry
-        run: |
-          mv /tmp/${{ matrix.platform }}/${{ matrix.image }}_image_${{ matrix.platform }}.tar .
-          loaded_image=$(docker load -i ${{ matrix.image }}_image_${{ matrix.platform }}.tar | grep "Loaded image:" | head -n 1 | awk '{print $3}')
-          echo "loaded image = $loaded_image"
-          tags=$(echo ${tags} | tr ' ' '\n')
-          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
-          echo "image name = $image_name"
-          for tag in $tags; do
-            echo "tag = $tag"
-            docker tag $loaded_image $image_name:${tag}_${{ matrix.platform }}
-            docker push $image_name:${tag}_${{ matrix.platform }}
-          done
-
-  ghcr_push_runtime:
-    runs-on: ubuntu-latest
-    # don't push if runtime tests fail
-    needs: [ghcr_build_runtime, test_runtime, integration_tests_on_linux]
-    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
-
-    env:
-      tags: ${{ needs.ghcr_build_runtime.outputs.tags }}
-
-    permissions:
-      contents: read
-      packages: write
-
-    strategy:
-      matrix:
-        image: ["od_runtime"]
-        platform: ["amd64", "arm64"]
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          tool-cache: true
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
-
-      - name: Login to GHCR
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Download Docker images
-        uses: actions/download-artifact@v4
-        with:
-          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
-          path: /tmp/${{ matrix.platform }}
-
-      - name: List downloaded files
-        run: |
-          ls -la /tmp/${{ matrix.platform }}
-          file /tmp/${{ matrix.platform }}/*
-
-      - name: Load images and push to registry
-        run: |
-          mv /tmp/${{ matrix.platform }}/${{ matrix.image }}_image_${{ matrix.platform }}.tar ./${{ matrix.image }}_image_${{ matrix.platform }}.tar
-          if ! loaded_image=$(docker load -i ${{ matrix.image }}_image_${{ matrix.platform }}.tar | grep "Loaded image:" | head -n 1 | awk '{print $3}'); then
-            echo "Failed to load Docker image"
-            exit 1
-          fi
-          echo "loaded image = $loaded_image"
-          tags=$(echo ${tags} | tr ' ' '\n')
-          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
-          echo "image name = $image_name"
-          for tag in $tags; do
-            echo "tag = $tag"
-            if [ -n "$image_name" ]; then
-              docker tag $loaded_image $image_name:${tag}_${{ matrix.platform }}
-              docker push $image_name:${tag}_${{ matrix.platform }}
-            else
-              echo "Skipping tag and push due to empty image_name"
-            fi
-          done
-
-  create_manifest:
-    runs-on: ubuntu-latest
-    needs: [ghcr_build, ghcr_push]
-    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
-
-    env:
-      tags: ${{ needs.ghcr_build.outputs.tags }}
-
-    strategy:
-      matrix:
-        image: ["sandbox", "opendevin"]
-
-    permissions:
-      contents: read
-      packages: write
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Login to GHCR
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Create and push multi-platform manifest
-        run: |
-          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
-          echo "image name = $image_name"
-          tags=$(echo ${tags} | tr ' ' '\n')
-          for tag in $tags; do
-            echo 'tag = $tag'
-            docker buildx imagetools create --tag $image_name:$tag \
-              $image_name:${tag}_amd64 \
-              $image_name:${tag}_arm64
-          done
-
-  create_manifest_runtime:
-    runs-on: ubuntu-latest
-    needs: [ghcr_build_runtime, ghcr_push_runtime]
-    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
-
-    env:
-      tags: ${{ needs.ghcr_build_runtime.outputs.tags }}
-
-    strategy:
-      matrix:
-        image: ["od_runtime"]
-
-    permissions:
-      contents: read
-      packages: write
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Login to GHCR
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Create and push multi-platform manifest
-        run: |
-          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
-          echo "image name = $image_name"
-          tags=$(echo ${tags} | tr ' ' '\n')
-          for tag in $tags; do
-            echo 'tag = $tag'
-            docker buildx imagetools create --tag $image_name:$tag \
-              $image_name:${tag}_amd64 \
-              $image_name:${tag}_arm64
-          done

.github/workflows/integration-runner.yml

@@ -0,0 +1,199 @@
+name: Run Integration Tests
+
+on:
+  pull_request:
+    types: [labeled]
+  workflow_dispatch:
+    inputs:
+      reason:
+        description: 'Reason for manual trigger'
+        required: true
+        default: ''
+  schedule:
+    - cron: '30 22 * * *'  # Runs at 10:30pm UTC every day
+
+env:
+  N_PROCESSES: 10 # Global configuration for number of parallel processes for evaluation
+
+jobs:
+  run-integration-tests:
+    if: github.event.label.name == 'integration-test' || github.event_name == 'workflow_dispatch' || github.event_name == 'schedule'
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    permissions:
+      contents: "read"
+      id-token: "write"
+      pull-requests: "write"
+      issues: "write"
+    strategy:
+      matrix:
+        python-version: ["3.12"]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: useblacksmith/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "poetry"
+
+      - name: Setup Node.js
+        uses: useblacksmith/setup-node@v5
+        with:
+          node-version: '22.x'
+
+      - name: Comment on PR if 'integration-test' label is present
+        if: github.event_name == 'pull_request' && github.event.label.name == 'integration-test'
+        uses: KeisukeYamashita/create-comment@v1
+        with:
+          unique: false
+          comment: |
+            Hi! I started running the integration tests on your PR. You will receive a comment with the results shortly.
+
+      - name: Install Python dependencies using Poetry
+        run: poetry install --without evaluation
+
+      - name: Configure config.toml for testing with Haiku
+        env:
+          LLM_MODEL: "litellm_proxy/claude-3-5-haiku-20241022"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 10
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+
+      - name: Build environment
+        run: make build
+
+      - name: Run integration test evaluation for Haiku
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' 10 $N_PROCESSES '' 'haiku_run'
+
+          # get integration tests report
+          REPORT_FILE_HAIKU=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/*haiku*_maxiter_10_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE: $REPORT_FILE_HAIKU"
+          echo "INTEGRATION_TEST_REPORT_HAIKU<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_HAIKU >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      - name: Wait a little bit
+        run: sleep 10
+
+      - name: Configure config.toml for testing with DeepSeek
+        env:
+          LLM_MODEL: "litellm_proxy/deepseek-chat"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 10
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+
+      - name: Run integration test evaluation for DeepSeek
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' 10 $N_PROCESSES '' 'deepseek_run'
+
+          # get integration tests report
+          REPORT_FILE_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/deepseek*_maxiter_10_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE: $REPORT_FILE_DEEPSEEK"
+          echo "INTEGRATION_TEST_REPORT_DEEPSEEK<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_DEEPSEEK >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      # -------------------------------------------------------------
+      # Run VisualBrowsingAgent tests for DeepSeek, limited to t05 and t06
+      - name: Wait a little bit (again)
+        run: sleep 5
+
+      - name: Configure config.toml for testing VisualBrowsingAgent (DeepSeek)
+        env:
+          LLM_MODEL: "litellm_proxy/deepseek-chat"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 15
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+      - name: Run integration test evaluation for VisualBrowsingAgent (DeepSeek)
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD VisualBrowsingAgent '' 15 $N_PROCESSES "t05_simple_browsing,t06_github_pr_browsing.py" 'visualbrowsing_deepseek_run'
+
+          # Find and export the visual browsing agent test results
+          REPORT_FILE_VISUALBROWSING_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/VisualBrowsingAgent/deepseek*_maxiter_15_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE_VISUALBROWSING_DEEPSEEK: $REPORT_FILE_VISUALBROWSING_DEEPSEEK"
+          echo "INTEGRATION_TEST_REPORT_VISUALBROWSING_DEEPSEEK<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_VISUALBROWSING_DEEPSEEK >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      - name: Create archive of evaluation outputs
+        run: |
+          TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
+          cd evaluation/evaluation_outputs/outputs  # Change to the outputs directory
+          tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/* integration_tests/VisualBrowsingAgent/* # Only include the actual result directories
+
+      - name: Upload evaluation results as artifact
+        uses: actions/upload-artifact@v4
+        id: upload_results_artifact
+        with:
+          name: integration-test-outputs-${{ github.run_id }}-${{ github.run_attempt }}
+          path: integration_tests_*.tar.gz
+
+      - name: Get artifact URLs
+        run: |
+          echo "ARTIFACT_URL=${{ steps.upload_results_artifact.outputs.artifact-url }}" >> $GITHUB_ENV
+
+      - name: Set timestamp and trigger reason
+        run: |
+          echo "TIMESTAMP=$(date +'%Y-%m-%d-%H-%M')" >> $GITHUB_ENV
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            echo "TRIGGER_REASON=pr-${{ github.event.pull_request.number }}" >> $GITHUB_ENV
+          elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
+            echo "TRIGGER_REASON=manual-${{ github.event.inputs.reason }}" >> $GITHUB_ENV
+          else
+            echo "TRIGGER_REASON=nightly-scheduled" >> $GITHUB_ENV
+          fi
+
+      - name: Comment with results and artifact link
+        id: create_comment
+        uses: KeisukeYamashita/create-comment@v1
+        with:
+          # if triggered by PR, use PR number, otherwise use 5318 as fallback issue number for manual triggers
+          number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || 5318 }}
+          unique: false
+          comment: |
+              Trigger by: ${{ github.event_name == 'pull_request' && format('Pull Request (integration-test label on PR #{0})', github.event.pull_request.number) || (github.event_name == 'workflow_dispatch' && format('Manual Trigger: {0}', github.event.inputs.reason)) || 'Nightly Scheduled Run' }}
+              Commit: ${{ github.sha }}
+              **Integration Tests Report (Haiku)**
+              Haiku LLM Test Results:
+              ${{ env.INTEGRATION_TEST_REPORT_HAIKU }}
+              ---
+              **Integration Tests Report (DeepSeek)**
+              DeepSeek LLM Test Results:
+              ${{ env.INTEGRATION_TEST_REPORT_DEEPSEEK }}
+              ---
+              **Integration Tests Report VisualBrowsing (DeepSeek)**
+              ${{ env.INTEGRATION_TEST_REPORT_VISUALBROWSING_DEEPSEEK }}
+              ---
+              Download testing outputs (includes both Haiku and DeepSeek results): [Download](${{ steps.upload_results_artifact.outputs.artifact-url }})

.github/workflows/lint-fix.yml

@@ -0,0 +1,91 @@
+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 20
+        uses: useblacksmith/setup-node@v5
+        with:
+          node-version: 20
+      - name: Install frontend dependencies
+        run: |
+          cd frontend
+          npm install --frozen-lockfile
+      - 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"
+          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 --files openhands/**/* evaluation/**/* tests/**/* || 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"
+          git push

.github/workflows/lint.yml

@@ -1,50 +1,68 @@
+# Workflow that runs lint on the frontend and python code
 name: Lint
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-
+# 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:
     name: Lint frontend
-    runs-on: ubuntu-latest
+    runs-on: blacksmith-4vcpu-ubuntu-2204
     steps:
       - uses: actions/checkout@v4
-
       - name: Install Node.js 20
-        uses: actions/setup-node@v4
+        uses: useblacksmith/setup-node@v5
         with:
           node-version: 20
-
       - name: Install dependencies
         run: |
           cd frontend
           npm install --frozen-lockfile
-
-      - name: Lint
+      - name: Lint and TypeScript compilation
         run: |
           cd frontend
           npm run lint
+          npm run make-i18n && tsc
 
+  # 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
         with:
           fetch-depth: 0
       - name: Set up python
-        uses: actions/setup-python@v5
+        uses: useblacksmith/setup-python@v6
         with:
-          python-version: 3.11
+          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 --files opendevin/**/* agenthub/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
+        run: pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
+
+  # Check version consistency across documentation
+  check-version-consistency:
+    name: Check version consistency
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up python
+        uses: useblacksmith/setup-python@v6
+        with:
+          python-version: 3.12
+      - name: Run version consistency check
+        run: .github/scripts/check_version_consistency.py

.github/workflows/openhands-resolver.yml

@@ -0,0 +1,426 @@
+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-3-7-sonnet-20250219"
+      LLM_API_VERSION:
+        required: false
+        type: string
+        default: ""
+      base_container_image:
+        required: false
+        type: string
+        default: ""
+        description: "Custom sandbox env"
+    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: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - 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@v4
+        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/All-Hands-AI/OpenHands) started fixing the ${issueType}! You can monitor the progress [here](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}).`
+            });
+
+      - name: Install OpenHands
+        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("python -m pip install --upgrade pip");
+              await exec.exec("pip install git+https://github.com/all-hands-ai/openhands.git");
+            } else {
+              console.log("Installing from requirements.txt...");
+              await exec.exec("python -m pip install --upgrade pip");
+              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@v4
+        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-unit-tests.yml

@@ -0,0 +1,55 @@
+# Workflow that runs python unit tests
+name: Run Python Unit Tests
+
+# The jobs in this workflow are required, so they must run at all times
+# * Always run on "main"
+# * Always run on PRs
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
+concurrency:
+  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  # Run python unit tests on Linux
+  test-on-linux:
+    name: Python Unit Tests on Linux
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    env:
+      INSTALL_DOCKER: '0' # Set to '0' to skip Docker installation
+    strategy:
+      matrix:
+        python-version: ['3.12']
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Install tmux
+        run: sudo apt-get update && sudo apt-get install -y tmux
+      - name: 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 --without evaluation
+      - name: Build Environment
+        run: make build
+      - name: Run Tests
+        run: poetry run pytest --forked -n auto --cov=openhands --cov-report=xml -svv ./tests/unit
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

.github/workflows/pypi-release.yml

@@ -0,0 +1,31 @@
+# Publishes the OpenHands PyPi package
+name: Publish PyPi Package
+
+# Triggered manually
+on:
+  workflow_dispatch:
+    inputs:
+      reason:
+        description: 'Reason for manual trigger'
+        required: true
+        default: ''
+
+jobs:
+  release:
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    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/review-pr.yml

@@ -1,85 +0,0 @@
-name: Use OpenDevin to Review Pull Request
-
-on:
-  pull_request:
-    types: [synchronize, labeled]
-
-permissions:
-  contents: write
-  pull-requests: write
-
-jobs:
-  dogfood:
-    if: contains(github.event.pull_request.labels.*.name, 'review-this')
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v4
-    - name: Set up Python
-      uses: actions/setup-python@v5
-      with:
-        python-version: '3.11'
-    - name: install git, github cli
-      run: |
-        sudo apt-get install -y git gh
-        git config --global --add safe.directory $PWD
-
-    - name: Checkout Repository
-      uses: actions/checkout@v4
-      with:
-        ref: ${{ github.event.pull_request.base.ref }} # check out the target branch
-
-    - name: Download Diff
-      run: |
-        curl -O "${{ github.event.pull_request.diff_url }}" -L
-
-    - name: Write Task File
-      run: |
-        echo "Your coworker wants to apply a pull request to this project." > task.txt
-        echo "Read and review ${{ github.event.pull_request.number }}.diff file. Create a review-${{ github.event.pull_request.number }}.txt and write your concise comments and suggestions there." >> task.txt
-        echo "Do not ask me for confirmation at any point." >> task.txt
-        echo "" >> task.txt
-        echo "Title" >> task.txt
-        echo "${{ github.event.pull_request.title }}" >> task.txt
-        echo "" >> task.txt
-        echo "Description" >> task.txt
-        echo "${{ github.event.pull_request.body }}" >> task.txt
-        echo "" >> task.txt
-        echo "Diff file is: ${{ github.event.pull_request.number }}.diff" >> task.txt
-
-    - name: Set up environment
-      run: |
-        curl -sSL https://install.python-poetry.org | python3 -
-        export PATH="/github/home/.local/bin:$PATH"
-        poetry install --without evaluation,llama-index
-        poetry run playwright install --with-deps chromium
-
-    - name: Run OpenDevin
-      env:
-        LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
-        LLM_MODEL: ${{ vars.LLM_MODEL }}
-        SANDBOX_BOX_TYPE: ssh
-      run: |
-        # Append path to launch poetry
-        export PATH="/github/home/.local/bin:$PATH"
-        # Append path to correctly import package, note: must set pwd at first
-        export PYTHONPATH=$(pwd):$PYTHONPATH
-        export WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE
-        export WORKSPACE_BASE=$GITHUB_WORKSPACE
-        echo -e "/exit\n" | poetry run python opendevin/core/main.py -i 50 -f task.txt
-        rm task.txt
-
-    - name: Check if review file is non-empty
-      id: check_file
-      run: |
-        ls -la
-        if [[ -s review-${{ github.event.pull_request.number }}.txt ]]; then
-          echo "non_empty=true" >> $GITHUB_OUTPUT
-        fi
-      shell: bash
-
-    - name: Create PR review if file is non-empty
-      env:
-        GH_TOKEN: ${{ github.token }}
-      if: steps.check_file.outputs.non_empty == 'true'
-      run: |
-        gh pr review ${{ github.event.pull_request.number }} --comment --body-file "review-${{ github.event.pull_request.number }}.txt"

.github/workflows/run-eval.yml

@@ -0,0 +1,54 @@
+# Run evaluation on a PR
+name: Run Eval
+
+# Runs when a PR is labeled with one of the "run-eval-" labels
+on:
+  pull_request:
+    types: [labeled]
+
+jobs:
+  trigger-job:
+    name: Trigger remote eval job
+    if: ${{ github.event.label.name == 'run-eval-xs' || github.event.label.name == 'run-eval-s' || github.event.label.name == 'run-eval-m' }}
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+
+    steps:
+      - name: Checkout PR branch
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.head_ref }}
+
+      - name: Trigger remote job
+        env:
+          PR_BRANCH: ${{ github.head_ref }}
+        run: |
+          REPO_URL="https://github.com/${{ github.repository }}"
+          echo "Repository URL: $REPO_URL"
+          echo "PR Branch: $PR_BRANCH"
+
+          if [[ "${{ github.event.label.name }}" == "run-eval-xs" ]]; then
+            EVAL_INSTANCES="1"
+          elif [[ "${{ github.event.label.name }}" == "run-eval-s" ]]; then
+            EVAL_INSTANCES="5"
+          elif [[ "${{ github.event.label.name }}" == "run-eval-m" ]]; then
+            EVAL_INSTANCES="30"
+          fi
+
+          curl -X POST \
+            -H "Authorization: Bearer ${{ secrets.PAT_TOKEN }}" \
+            -H "Accept: application/vnd.github+json" \
+            -d "{\"ref\": \"main\", \"inputs\": {\"github-repo\": \"${REPO_URL}\", \"github-branch\": \"${PR_BRANCH}\", \"pr-number\": \"${{ github.event.pull_request.number }}\", \"eval-instances\": \"${EVAL_INSTANCES}\"}}" \
+            https://api.github.com/repos/All-Hands-AI/evaluation/actions/workflows/create-branch.yml/dispatches
+
+          # Send Slack message
+          PR_URL="https://github.com/${{ github.repository }}/pull/${{ github.event.pull_request.number }}"
+          slack_text="PR $PR_URL has triggered evaluation on $EVAL_INSTANCES instances..."
+          curl -X POST -H 'Content-type: application/json' --data '{"text":"'"$slack_text"'"}' \
+            https://hooks.slack.com/services/${{ secrets.SLACK_TOKEN }}
+
+      - name: Comment on PR
+        uses: KeisukeYamashita/create-comment@v1
+        with:
+          unique: false
+          comment: |
+            Running evaluation on the PR. Once eval is done, the results will be posted.

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

@@ -1,167 +0,0 @@
-name: Run Unit Tests
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-
-on:
-  push:
-    branches:
-      - main
-    paths-ignore:
-      - '**/*.md'
-      - 'frontend/**'
-      - 'docs/**'
-      - 'evaluation/**'
-  pull_request:
-
-env:
-  PERSIST_SANDBOX : "false"
-
-jobs:
-  fe-test:
-    runs-on: ubuntu-latest
-
-    strategy:
-      matrix:
-        node-version: [20]
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Set up Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: ${{ matrix.node-version }}
-
-      - name: Install dependencies
-        working-directory: ./frontend
-        run: npm ci
-
-      - name: Run tests and collect coverage
-        working-directory: ./frontend
-        run: npm run test:coverage
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
-  test-on-macos:
-    name: Test on macOS
-    runs-on: macos-12
-    env:
-      INSTALL_DOCKER: "1" # Set to '0' to skip Docker installation
-    strategy:
-      matrix:
-        python-version: ["3.11"]
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation,llama-index
-
-      - name: Install & Start Docker
-        if: env.INSTALL_DOCKER == '1'
-        run: |
-          INSTANCE_NAME="colima-${GITHUB_RUN_ID}"
-
-          # Uninstall colima to upgrade to the latest version
-          if brew list colima &>/dev/null; then
-            brew uninstall colima
-            # unlinking colima dependency: go
-            brew uninstall go@1.21
-          fi
-          rm -rf ~/.colima ~/.lima
-          brew install --HEAD colima
-          brew install docker
-
-          start_colima() {
-            # Find a free port in the range 10000-20000
-            RANDOM_PORT=$((RANDOM % 10001 + 10000))
-
-            # Original line:
-            if ! colima start --network-address --arch x86_64 --cpu=1 --memory=1 --verbose --ssh-port $RANDOM_PORT; then
-              echo "Failed to start Colima."
-              return 1
-            fi
-            return 0
-          }
-
-          # Attempt to start Colima for 5 total attempts:
-          ATTEMPT_LIMIT=5
-          for ((i=1; i<=ATTEMPT_LIMIT; i++)); do
-
-            if start_colima; then
-              echo "Colima started successfully."
-              break
-            else
-              colima stop -f
-              sleep 10
-              colima delete -f
-              if [ $i -eq $ATTEMPT_LIMIT ]; then
-                exit 1
-              fi
-              sleep 10
-            fi
-          done
-
-          # For testcontainers to find the Colima socket
-          # https://github.com/abiosoft/colima/blob/main/docs/FAQ.md#cannot-connect-to-the-docker-daemon-at-unixvarrundockersock-is-the-docker-daemon-running
-          sudo ln -sf $HOME/.colima/default/docker.sock /var/run/docker.sock
-
-      - name: Build Environment
-        run: make build
-
-      - name: Run Tests
-        run: poetry run pytest --forked --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox.py and not test_runtime.py"
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-  test-on-linux:
-    name: Test on Linux
-    runs-on: ubuntu-latest
-    env:
-      INSTALL_DOCKER: "0" # Set to '0' to skip Docker installation
-    strategy:
-      matrix:
-        python-version: ["3.11"]
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation,llama-index
-
-      - name: Build Environment
-        run: make build
-
-      - name: Run Tests
-        run: poetry run pytest --forked --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox.py and not test_runtime.py"
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

.github/workflows/solve-issue.yml

@@ -1,122 +0,0 @@
-name: Use OpenDevin to Resolve GitHub Issue
-
-on:
-  issues:
-    types: [labeled]
-
-permissions:
-  contents: write
-  pull-requests: write
-  issues: write
-
-jobs:
-  dogfood:
-    if: github.event.label.name == 'solve-this'
-    runs-on: ubuntu-latest
-    container:
-      image: ghcr.io/opendevin/opendevin
-      volumes:
-        - /var/run/docker.sock:/var/run/docker.sock
-
-    steps:
-    - name: install git, github cli
-      run: apt-get install -y git gh
-
-    - name: Checkout Repository
-      uses: actions/checkout@v4
-
-    - 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 "${ISSUE_BODY}" >> task.txt
-
-    - name: Set up environment
-      run: |
-        curl -sSL https://install.python-poetry.org | python3 -
-        export PATH="/github/home/.local/bin:$PATH"
-        poetry install --without evaluation,llama-index
-        poetry run playwright install --with-deps chromium
-
-
-    - name: Run OpenDevin
-      env:
-        ISSUE_TITLE: ${{ github.event.issue.title }}
-        ISSUE_BODY: ${{ github.event.issue.body }}
-        LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-        SANDBOX_BOX_TYPE: ssh
-      run: |
-        # Append path to launch poetry
-        export PATH="/github/home/.local/bin:$PATH"
-        # Append path to correctly import package, note: must set pwd at first
-        export PYTHONPATH=$(pwd):$PYTHONPATH
-        WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE poetry run python ./opendevin/core/main.py -i 50 -f task.txt -d $GITHUB_WORKSPACE
-        rm task.txt
-
-    - name: Setup Git, Create Branch, and Commit Changes
-      run: |
-        # Setup Git configuration
-        git config --global --add safe.directory $PWD
-        git config --global user.name 'OpenDevin'
-        git config --global user.email 'OpenDevin@users.noreply.github.com'
-
-        # Create a unique branch name with a timestamp
-        BRANCH_NAME="fix/${{ 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: 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/stale.yml

@@ -1,29 +1,22 @@
+# 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: ubuntu-latest
+    runs-on: blacksmith-4vcpu-ubuntu-2204
     steps:
       - uses: actions/stale@v9
         with:
-          # Aggressively close issues that have been explicitly labeled `age-out`
-          any-of-labels: age-out
-          stale-issue-message: 'This issue is stale because it has been open for 7 days with no activity. Remove stale label or comment or this will be closed in 1 day.'
-          close-issue-message: 'This issue was closed because it has been stalled for over 7 days with no activity.'
-          stale-pr-message: 'This PR is stale because it has been open for 7 days with no activity. Remove stale label or comment or this will be closed in 1 days.'
-          close-pr-message: 'This PR was closed because it has been stalled for over 7 days with no activity.'
-          days-before-stale: 7
-          days-before-close: 1
-
-      - uses: actions/stale@v9
-        with:
-          # Be more lenient with other issues
           stale-issue-message: 'This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
-          close-issue-message: 'This issue was closed because it has been stalled for over 30 days with no activity.'
           stale-pr-message: 'This PR is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
-          close-pr-message: 'This PR was closed because it has been stalled for over 30 days with no activity.'
           days-before-stale: 30
+          exempt-issue-labels: 'tracked'
+          close-issue-message: 'This issue was closed because it has been stalled for over 30 days with no activity.'
+          close-pr-message: 'This PR was closed because it has been stalled for over 30 days with no activity.'
           days-before-close: 7
+          operations-per-run: 150

.github/workflows/update-pyproject-version.yml

@@ -1,48 +0,0 @@
-name: Update pyproject.toml Version and Tags
-
-on:
-  release:
-    types:
-      - published
-
-jobs:
-  update-pyproject-and-tags:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0  # Fetch all history for all branches and tags
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install toml
-
-      - name: Get release tag
-        id: get_release_tag
-        run: echo "RELEASE_TAG=${GITHUB_REF#refs/tags/}" >> $GITHUB_ENV
-
-      - name: Update pyproject.toml with release tag
-        run: |
-          python -c "
-          import toml
-          with open('pyproject.toml', 'r') as f:
-              data = toml.load(f)
-          data['tool']['poetry']['version'] = '${{ env.RELEASE_TAG }}'
-          with open('pyproject.toml', 'w') as f:
-              toml.dump(data, f)
-          "
-
-      - name: Commit and push pyproject.toml changes
-        uses: stefanzweifel/git-auto-commit-action@v4
-        with:
-          commit_message: "Update pyproject.toml version to ${{ env.RELEASE_TAG }}"
-          branch: main
-          file_pattern: pyproject.toml

.gitignore

@@ -121,6 +121,7 @@ celerybeat.pid
 
 # Environments
 .env
+frontend/.env
 .venv
 env/
 venv/
@@ -169,11 +170,19 @@ 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
@@ -213,14 +222,14 @@ config.toml
 config.toml_
 config.toml.bak
 
-containers/agnostic_sandbox
-
 # swe-bench-eval
 image_build_logs
 run_instance_logs
 
-od_runtime_*.tar
+runtime_*.tar
 
 # docker build
 containers/runtime/Dockerfile
 containers/runtime/project.tar.gz
+containers/runtime/code
+**/node_modules/

.nvmrc

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

.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.
+
+#### Repository Microagent
+A type of microagent that provides repository-specific context and guidelines, stored in the `.openhands/microagents/` directory.
+
+### Prompt
+Components for managing and processing prompts.
+
+#### Prompt Caching
+A system for caching and reusing common prompts to improve performance.
+
+#### Prompt Manager
+A component that handles the loading, processing, and management of prompts used by agents, including microagents.
+
+#### Response Parsing
+The process of interpreting and structuring responses from language models and tools.
+
+### Runtime
+The execution environment where agents perform their tasks, which can be local, remote, or containerized.
+
+#### Action Execution Server
+A REST API that receives agent actions (e.g. bash commands, python code, browsing actions), executes them in the runtime environment, and returns the results.
+
+#### Action Execution Client
+A component that handles the execution of actions in the runtime environment, managing the communication between the agent and the runtime.
+
+#### Docker Runtime
+A containerized runtime environment that provides isolation and reproducibility for agent operations.
+
+#### E2B Runtime
+A specialized runtime environment built on E2B for secure and isolated code execution.
+
+#### Local Runtime
+A runtime environment that executes on the local machine, suitable for development and testing.
+
+#### Modal Runtime
+A runtime environment built on Modal for scalable and distributed agent operations.
+
+#### Remote Runtime
+A sandboxed environment that executes code and commands remotely, providing isolation and security for agent operations.
+
+#### Runtime Builder
+A component that builds a Docker image for the Action Execution Server based on a user-specified base image.
+
+### Security
+Security-related components and features.
+
+#### Security Analyzer
+A component that checks agent actions for potential security risks.

.openhands/microagents/repo.md

@@ -0,0 +1,73 @@
+---
+name: repo
+type: repo
+agent: CodeActAgent
+---
+This repository contains the code for OpenHands, an automated AI software engineer. It has a Python backend
+(in the `openhands` directory) and React frontend (in the `frontend` directory).
+
+## General Setup:
+To set up the entire repo, including frontend and backend, run `make build`.
+You don't need to do this unless the user asks you to, or if you're trying to run the entire application.
+
+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 --all-files --config ./dev_config/python/.pre-commit-config.yaml`
+* If you've made changes to the frontend, you should run `cd frontend && npm run lint:fix && npm run build ; cd ..`
+
+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
+
+## 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`
+
+
+## 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.
+
+### 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

.openhands/setup.sh

@@ -0,0 +1,5 @@
+#! /bin/bash
+
+echo "Setting up the environment..."
+
+python -m pip install pre-commit

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"

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@all-hands.dev
+contact@all-hands.dev.
 All complaints will be reviewed and investigated promptly and fairly.
 
 All community leaders are obligated to respect the privacy and security of the
@@ -113,6 +113,20 @@ individual, or aggression toward or disparagement of classes of individuals.
 **Consequence**: A permanent ban from any sort of public interaction within the
 community.
 
+### Slack and Discord Etiquettes
+
+These Slack and Discord etiquette guidelines are designed to foster an inclusive, respectful, and productive environment for all community members. By following these best practices, we ensure effective communication and collaboration while minimizing disruptions. Let’s work together to build a supportive and welcoming community!
+
+- Communicate respectfully and professionally, avoiding sarcasm or harsh language, and remember that tone can be difficult to interpret in text.
+- Use threads for specific discussions to keep channels organized and easier to follow.
+- Tag others only when their input is critical or urgent, and use @here, @channel or @everyone sparingly to minimize disruptions.
+- Be patient, as open-source contributors and maintainers often have other commitments and may need time to respond.
+- Post questions or discussions in the most relevant channel (e.g., for [slack - #general](https://app.slack.com/client/T06P212QSEA/C06P5NCGSFP) for general topics, [slack - #questions](https://openhands-ai.slack.com/archives/C06U8UTKSAD) for queries/questions, [discord - #general](https://discord.com/channels/1222935860639563850/1222935861386018885)).
+- When asking for help or raising issues, include necessary details like links, screenshots, or clear explanations to provide context.
+- Keep discussions in public channels whenever possible to allow others to benefit from the conversation, unless the matter is sensitive or private.
+- Always adhere to [our standards](https://github.com/All-Hands-AI/OpenHands/blob/main/CODE_OF_CONDUCT.md#our-standards) to ensure a welcoming and collaborative environment.
+- If you choose to mute a channel, consider setting up alerts for topics that still interest you to stay engaged. For Slack, Go to Settings → Notifications → My Keywords to add specific keywords that will notify you when mentioned. For example, if you're here for discussions about LLMs, mute the channel if it’s too busy, but set notifications to alert you only when “LLMs” appears in messages. Also for Discord, go to the channel notifications and choose the option that best describes your need.
+
 ## Attribution
 
 This Code of Conduct is adapted from the [Contributor Covenant][homepage],

COMMUNITY.md

@@ -0,0 +1,43 @@
+# 🙌 The OpenHands Community
+
+The OpenHands community is built around the belief that (1) AI and AI agents are going to fundamentally change the way
+we build software, and (2) if this is true, we should do everything we can to make sure that the benefits provided by
+such powerful technology are accessible to everyone.
+
+If this resonates with you, we'd love to have you join us in our quest!
+
+## 🤝 How to Join
+
+Check out our [How to Join the Community section.](https://github.com/All-Hands-AI/OpenHands?tab=readme-ov-file#-how-to-join-the-community)
+
+## 💪 Becoming a Contributor
+
+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 new core functionality, improve our agents, improve the frontend and other
+interfaces, or anything else that would help make OpenHands better.
+- **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in
+evaluating the models, or suggest improvements.
+- **Feedback and Testing:** Use the OpenHands toolset, report bugs, suggest features, or provide feedback on usability.
+
+For details, please check [CONTRIBUTING.md](./CONTRIBUTING.md).
+
+## Code of Conduct
+
+We have a [Code of Conduct](./CODE_OF_CONDUCT.md) that we expect all contributors to adhere to.
+Long story short, we are aiming for an open, welcoming, diverse, inclusive, and healthy community.
+All contributors are expected to contribute to building this sort of community.
+
+## 🛠️ Becoming a Maintainer
+
+For contributors who have made significant and sustained contributions to the project, there is a possibility of joining
+the maintainer team. The process for this is as follows:
+
+1. Any contributor who has made sustained and high-quality contributions to the codebase can be nominated by any
+maintainer. If you feel that you may qualify you can reach out to any of the maintainers that have reviewed your PRs and ask if you can be nominated.
+2. Once a maintainer nominates a new maintainer, there will be a discussion period among the maintainers for at least 3 days.
+3. If no concerns are raised the nomination will be accepted by acclamation, and if concerns are raised there will be a discussion and possible vote.
+
+Note that just making many PRs does not immediately imply that you will become a maintainer. We will be looking
+at sustained high-quality contributions over a period of time, as well as good teamwork and adherence to our [Code of Conduct](./CODE_OF_CONDUCT.md).

CONTRIBUTING.md

@@ -1,96 +1,71 @@
 # Contributing
 
-Thanks for your interest in contributing to OpenDevin! We welcome and appreciate contributions.
+Thanks for your interest in contributing to OpenHands! We welcome and appreciate contributions.
+
+## Understanding OpenHands's CodeBase
+
+To understand the codebase, please refer to the README in each module:
+- [frontend](./frontend/README.md)
+- [evaluation](./evaluation/README.md)
+- [openhands](./openhands/README.md)
+   - [agenthub](./openhands/agenthub/README.md)
+   - [server](./openhands/server/README.md)
+
+## Setting up Your Development Environment
+
+We have a separate doc [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) that tells you how to set up a development workflow.
 
 ## How Can I Contribute?
 
 There are many ways that you can contribute:
 
-1. **Download and use** OpenDevin, and send [issues](https://github.com/OpenDevin/OpenDevin/issues) when you encounter something that isn't working or a feature that you'd like to see.
+1. **Download and use** OpenHands, and send [issues](https://github.com/All-Hands-AI/OpenHands/issues) when you encounter something that isn't working or a feature that you'd like to see.
 2. **Send feedback** after each session by [clicking the thumbs-up thumbs-down buttons](https://docs.all-hands.dev/modules/usage/feedback), so we can see where things are working and failing, and also build an open dataset for training code agents.
-3. **Improve the Codebase** by sending PRs (see details below). In particular, we have some [good first issue](https://github.com/OpenDevin/OpenDevin/labels/good%20first%20issue) issues that may be ones to start on.
+3. **Improve the Codebase** by sending [PRs](#sending-pull-requests-to-openhands) (see details below). In particular, we have some [good first issues](https://github.com/All-Hands-AI/OpenHands/labels/good%20first%20issue) that may be ones to start on.
 
-## Understanding OpenDevin's CodeBase
+## What Can I Build?
+Here are a few ways you can help improve the codebase.
 
-To understand the codebase, 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)
+#### UI/UX
+We're always looking to improve the look and feel of the application. If you've got a small fix
+for something that's bugging you, feel free to open up a PR that changes the [`./frontend`](./frontend) directory.
 
-When you write code, it is also good to write tests. Please navigate to the `tests` folder to see existing test suites.
-At the moment, we have two kinds of tests: `unit` and `integration`. Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
+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 #frontend channel in our Slack
+to gather consensus from our design team first.
 
-## Sending Pull Requests to OpenDevin
+#### Improving the agent
+Our main agent is the CodeAct agent. You can [see its prompts here](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/agenthub/codeact_agent).
 
-### 1. Fork the Official Repository
-Fork the [OpenDevin repository](https://github.com/OpenDevin/OpenDevin) into your own account.
-Clone your own forked repository into your local environment:
+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.
 
-```shell
-git clone git@github.com:<YOUR-USERNAME>/OpenDevin.git
-```
+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.
 
-### 2. Configure Git
+#### 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.
 
-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:
+#### 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.
 
-```shell
-cd OpenDevin
-git remote add upstream git@github.com:OpenDevin/OpenDevin.git
-```
+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/All-Hands-AI/OpenHands/blob/main/openhands/runtime/base.py).
 
-Verify that the remote is set:
+#### 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 two kinds of tests: [`unit`](./tests/unit) and [`integration`](./evaluation/integration_tests). Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
 
-```shell
-git remote -v
-```
+## Sending Pull Requests to OpenHands
 
-You should see both `origin` and `upstream` in the output.
+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).
 
-### 3. Synchronize with Official Repository
-Synchronize latest commit with official repository before coding:
-
-```shell
-git fetch upstream
-git checkout main
-git merge upstream/main
-git push origin main
-```
-
-### 4. Set up the Development Environment
-
-We have a separate doc [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md) that tells you how to set up a development workflow.
-
-### 5. Write Code and Commit It
-
-Once you have done this, you can write code, test it, and commit it to a branch (replace `my_branch` with an appropriate name):
-
-```shell
-git checkout -b my_branch
-git add .
-git commit
-git push origin my_branch
-```
-
-### 6. Open a Pull Request
-
-* On GitHub, go to the page of your forked repository, and create a Pull Request:
-   - Click on `Branches`
-   - Click on the `...` beside your branch and click on `New pull request`
-   - Set `base repository` to `OpenDevin/OpenDevin`
-   - Set `base` to `main`
-   - Click `Create pull request`
-
-The PR should appear in [OpenDevin PRs](https://github.com/OpenDevin/OpenDevin/pulls).
-
-Then the OpenDevin team will review your code.
-
-## PR Rules
-
-### 1. Pull Request title
+### Pull Request title
 As described [here](https://github.com/commitizen/conventional-commit-types/blob/master/index.json), a valid PR title should begin with one of the following prefixes:
 
 - `feat`: A new feature
@@ -109,8 +84,40 @@ 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/All-Hands-AI/OpenHands/pulls).
 
-### 2. Pull Request description
+### Pull Request description
 - If your PR is small (such as a typo fix), you can go brief.
 - If it contains a lot of changes, it's better to write more details.
+
+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 Make Effective Contributions
+
+### Opening Issues
+
+If you notice any bugs or have any feature requests please open them via the [issues page](https://github.com/All-Hands-AI/OpenHands/issues). We will triage based on how critical the bug is or how potentially useful the improvement is, discuss, and implement the ones that the community has interest/effort for.
+
+Further, if you see an issue you like, please leave a "thumbs-up" or a comment, which will help us prioritize.
+
+### 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

@@ -1,3 +1,82 @@
+# Credits
+
+## Contributors
+
+We would like to thank all the [contributors](https://github.com/All-Hands-AI/OpenHands/graphs/contributors) who have helped make OpenHands possible. We greatly appreciate your dedication and hard work.
+
+## Open Source Projects
+
+OpenHands includes and adapts the following open source projects. We are grateful for their contributions to the open source community:
+
+#### [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/All-Hands-AI/OpenHands/tree/main/openhands/runtime/plugins/agent_skills/utils/aider)
+
+#### [BrowserGym](https://github.com/ServiceNow/BrowserGym)
+   - License: Apache License 2.0
+   - Description: Adapted in implementing the browsing agent
+
+
+### Reference Implementations for Evaluation Benchmarks
+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
@@ -189,14 +268,45 @@
 
    Copyright [yyyy] [name of copyright owner]
 
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
 
-       http://www.apache.org/licenses/LICENSE-2.0
 
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.
+### 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

@@ -1,20 +1,26 @@
 # Development Guide
-This guide is for people working on OpenDevin and editing the source code.
-If you wish to contribute your changes, check out the [CONTRIBUTING.md](https://github.com/OpenDevin/OpenDevin/blob/main/CONTRIBUTING.md) on how to clone and setup the project initially before moving on.
-Otherwise, you can clone the OpenDevin project directly.
 
-## Start the server for development
+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/All-Hands-AI/OpenHands/blob/main/CONTRIBUTING.md) on how to clone and setup the project initially before moving on.
+Otherwise, you can clone the OpenHands project directly.
+
+## Start the Server for Development
+
 ### 1. Requirements
-* Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)  [ Ubuntu <= 22.04]
-* [Docker](https://docs.docker.com/engine/install/) (For those on MacOS, make sure to allow the default Docker socket to be used from advanced settings!)
-* [Python](https://www.python.org/downloads/) = 3.11
-* [NodeJS](https://nodejs.org/en/download/package-manager) >= 18.17.1
-* [Poetry](https://python-poetry.org/docs/#installing-with-the-official-installer) >= 1.8
-* netcat => sudo apt-get install netcat
+
+- 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`
+  - WSL: netcat => `sudo apt-get install netcat`
 
 Make sure you have all these dependencies installed before moving on to `make build`.
 
 #### 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
@@ -22,78 +28,136 @@ If you want to develop without system admin/sudo access to upgrade/install `Pyth
 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 3.11, nodejs, and poetry
-mamba install python=3.11
+# 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 OpenDevin is ready to run on your system:
+
+Begin by building the project which includes setting up the environment and installing dependencies. This step ensures that OpenHands is ready to run on your system:
 
 ```bash
 make build
 ```
 
 ### 3. Configuring the Language Model
-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.
+
+OpenHands supports a diverse array of Language Models (LMs) through the powerful [litellm](https://docs.litellm.ai) library.
+By default, we've chosen Claude Sonnet 3.5 as our go-to model, but the world is your oyster! You can unleash the
+potential of any other LM that piques your interest.
 
 To configure the LM of your choice, run:
 
-   ```bash
-   make setup-config
-   ```
+```bash
+make setup-config
+```
 
-   This command will prompt you to enter the LLM API key, model name, and other variables ensuring that OpenDevin is tailored to your specific needs. Note that the model name will apply only when you run headless. If you use the UI, please set the model in the UI.
+This command will prompt you to enter the LLM API key, model name, and other variables ensuring that OpenHands is tailored to your specific needs. Note that the model name will apply only when you run headless. If you use the UI, please set the model in the UI.
 
-   Note: If you have previously run OpenDevin using the docker command, you may have already set some environmental variables in your terminal. The final configurations are set from highest to lowest priority:
-   Environment variables > config.toml variables > default variables
+Note: If you have previously run OpenHands using the docker command, you may have already set some environmental variables in your terminal. The final configurations are set from highest to lowest priority:
+Environment variables > config.toml variables > default variables
 
 **Note on Alternative Models:**
-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 by creating instructions and adding it [to our documentation](https://github.com/OpenDevin/OpenDevin/tree/main/docs/modules/usage/llms).
-
-For a full list of the LM providers and models available, please consult the [litellm documentation](https://docs.litellm.ai/docs/providers).
+See [our documentation](https://docs.all-hands.dev/modules/usage/llms) for recommended models.
 
 ### 4. Running the application
+
 #### Option A: Run the Full Application
-Once the setup is complete, 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:
+
+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
-    ```
+
+  ```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
-    ```
+  ```bash
+  make start-frontend
+  ```
 
 ### 6. LLM Debugging
-If you encounter any issues with the Language Model (LM) or you're simply curious, you can inspect the actual LLM prompts and responses. To do so, export DEBUG=1 in the environment and restart the backend.
-OpenDevin will then log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
+
+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 assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenDevin.
+
+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
 ```
 
-#### Integration tests
-Please refer to [this README](./tests/integration/README.md) for details.
-
 ### 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`
+
+1. Add your dependency in `pyproject.toml` or use `poetry add xxx`.
+2. Update the poetry.lock file via `poetry lock --no-update`.
+
+### 9. Use existing Docker image
+
+To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker container image by
+setting the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
+
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.34-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
+- [/docs/DOC_STYLE_GUIDE.md](./docs/DOC_STYLE_GUIDE.md): Standards for writing and maintaining project documentation
+- [/openhands/README.md](./openhands/README.md): Details about the backend Python implementation
+- [/frontend/README.md](./frontend/README.md): Frontend React application setup and development guide
+- [/containers/README.md](./containers/README.md): Information about Docker containers and deployment
+- [/tests/unit/README.md](./tests/unit/README.md): Guide to writing and running unit tests
+- [/evaluation/README.md](./evaluation/README.md): Documentation for the evaluation framework and benchmarks
+- [/microagents/README.md](./microagents/README.md): Information about the microagents architecture and implementation
+- [/openhands/server/README.md](./openhands/server/README.md): Server implementation details and API documentation
+- [/openhands/runtime/README.md](./openhands/runtime/README.md): Documentation for the runtime environment and execution model

ISSUE_TRIAGE.md

@@ -2,24 +2,31 @@
 These are the procedures and guidelines on how issues are triaged in this repo by the maintainers.
 
 ## General
-* Most issues must be tagged with **enhancement** or **bug**
-* Issues may be tagged with what it relates to (**backend**, **frontend**, **agent quality**, etc.)
+* All issues must be tagged with **enhancement**, **bug** or **troubleshooting/help**.
+* Issues may be tagged with what it relates to (**agent quality**, **frontend**, **resolver**, etc.).
 
 ## Severity
-* **Low**: Minor issues, single user report
-* **Medium**: Affecting multiple users
-* **Critical**: Affecting all users or potential security issues
+* **Low**: Minor issues or affecting single user.
+* **Medium**: Affecting multiple users.
+* **High**: High visibility issues or affecting many users.
+* **Critical**: Affecting all users or potential security issues.
 
 ## Effort
-* Issues may be estimated with effort required (**small effort**, **medium effort**, **large effort**)
+* Issues may be estimated with effort required (**small effort**, **medium effort**, **large effort**).
 
 ## Difficulty
-* Issues with low implementation difficulty may be tagged with **good first issue**
+* Issues with low implementation difficulty may be tagged with **good first issue**.
 
 ## Not Enough Information
-* User is asked to provide more information (logs, how to reproduce, etc.) when the issue is not clear
-* If an issue is unclear and the author does not provide more information or respond to a request, the issue may be closed as **not planned** (Usually after a week)
+* 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
+* 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 30 days are automatically marked as **Stale**.
+* If issues marked as **Stale** continue to have no activity for 7 more days, they will automatically be closed as not planned.
+* Issues may be reopened by maintainers if deemed important.

MANIFEST.in

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

Makefile

@@ -1,16 +1,16 @@
-SHELL=/bin/bash
-# Makefile for OpenDevin project
+SHELL=/usr/bin/env bash
+# Makefile for OpenHands project
 
 # Variables
-DOCKER_IMAGE = ghcr.io/opendevin/sandbox:main
+BACKEND_HOST ?= "127.0.0.1"
 BACKEND_PORT = 3000
-BACKEND_HOST = "127.0.0.1:$(BACKEND_PORT)"
+BACKEND_HOST_PORT = "$(BACKEND_HOST):$(BACKEND_PORT)"
 FRONTEND_PORT = 3001
 DEFAULT_WORKSPACE_DIR = "./workspace"
 DEFAULT_MODEL = "gpt-4o"
 CONFIG_FILE = config.toml
 PRE_COMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
-PYTHON_VERSION = 3.11
+PYTHON_VERSION = 3.12
 
 # ANSI color codes
 GREEN=$(shell tput -Txterm setaf 2)
@@ -23,9 +23,6 @@ RESET=$(shell tput -Txterm sgr0)
 build:
 	@echo "$(GREEN)Building project...$(RESET)"
 	@$(MAKE) -s check-dependencies
-ifeq ($(INSTALL_DOCKER),)
-	@$(MAKE) -s pull-docker-image
-endif
 	@$(MAKE) -s install-python-dependencies
 	@$(MAKE) -s install-frontend-dependencies
 	@$(MAKE) -s install-pre-commit-hooks
@@ -42,6 +39,7 @@ ifeq ($(INSTALL_DOCKER),)
 	@$(MAKE) -s check-docker
 endif
 	@$(MAKE) -s check-poetry
+	@$(MAKE) -s check-tmux
 	@echo "$(GREEN)Dependencies checked successfully.$(RESET)"
 
 check-system:
@@ -84,10 +82,10 @@ check-nodejs:
 	@if command -v node > /dev/null; then \
 		NODE_VERSION=$(shell node --version | sed -E 's/v//g'); \
 		IFS='.' read -r -a NODE_VERSION_ARRAY <<< "$$NODE_VERSION"; \
-		if [ "$${NODE_VERSION_ARRAY[0]}" -gt 18 ] || ([ "$${NODE_VERSION_ARRAY[0]}" -eq 18 ] && [ "$${NODE_VERSION_ARRAY[1]}" -gt 17 ]) || ([ "$${NODE_VERSION_ARRAY[0]}" -eq 18 ] && [ "$${NODE_VERSION_ARRAY[1]}" -eq 17 ] && [ "$${NODE_VERSION_ARRAY[2]}" -ge 1 ]); then \
+		if [ "$${NODE_VERSION_ARRAY[0]}" -ge 22 ]; then \
 			echo "$(BLUE)Node.js $$NODE_VERSION is already installed.$(RESET)"; \
 		else \
-			echo "$(RED)Node.js 18.17.1 or later is required. Please install Node.js 18.17.1 or later to continue.$(RESET)"; \
+			echo "$(RED)Node.js 22.x or later is required. Please install Node.js 22.x or later to continue.$(RESET)"; \
 			exit 1; \
 		fi; \
 	else \
@@ -104,12 +102,24 @@ 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...$(RESET)"
 	@if command -v poetry > /dev/null; then \
 		POETRY_VERSION=$(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]} -ge 1 ] && [ $${POETRY_VERSION_ARRAY[1]} -ge 8 ]; then \
+		if [ $${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:"; \
@@ -124,11 +134,6 @@ check-poetry:
 		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 \
@@ -141,20 +146,29 @@ install-python-dependencies:
 		export HNSWLIB_NO_NATIVE=1; \
 		poetry run pip install chroma-hnswlib; \
 	fi
-	@poetry install --without llama-index
-	@if [ -f "/etc/manjaro-release" ]; then \
-		echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
-		poetry run pip install playwright; \
-		poetry run playwright install chromium; \
+	@if [ -n "${POETRY_GROUP}" ]; then \
+		echo "Installing only POETRY_GROUP=${POETRY_GROUP}"; \
+		poetry install --only $${POETRY_GROUP}; \
 	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; \
+		poetry install; \
+	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 \
-			echo "Setup already done. Skipping playwright installation."; \
+			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)"
 
@@ -174,7 +188,7 @@ install-pre-commit-hooks:
 
 lint-backend:
 	@echo "$(YELLOW)Running linters...$(RESET)"
-	@poetry run pre-commit run --files opendevin/**/* agenthub/**/* evaluation/**/* --show-diff-on-failure --config $(PRE_COMMIT_CONFIG_PATH)
+	@poetry run pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config $(PRE_COMMIT_CONFIG_PATH)
 
 lint-frontend:
 	@echo "$(YELLOW)Running linters for frontend...$(RESET)"
@@ -193,17 +207,24 @@ test:
 
 build-frontend:
 	@echo "$(YELLOW)Building frontend...$(RESET)"
-	@cd frontend && npm run build
+	@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) --reload --reload-exclude "workspace/*"
+	@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 && VITE_BACKEND_HOST=$(BACKEND_HOST) VITE_FRONTEND_PORT=$(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)
 
 # Common setup for running the app (non-callable)
 _run_setup:
@@ -213,7 +234,7 @@ _run_setup:
 	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.$(RESET)"
@@ -222,15 +243,23 @@ _run_setup:
 run:
 	@echo "$(YELLOW)Running the app...$(RESET)"
 	@$(MAKE) -s _run_setup
-	@cd frontend && echo "$(BLUE)Starting frontend with npm...$(RESET)" && npm run start -- --port $(FRONTEND_PORT)
+	@$(MAKE) -s start-frontend
 	@echo "$(GREEN)Application started successfully.$(RESET)"
 
-# Run the app (WSL mode)
-run-wsl:
-	@echo "$(YELLOW)Running the app in WSL mode...$(RESET)"
-	@$(MAKE) -s _run_setup
-	@cd frontend && echo "$(BLUE)Starting frontend with npm (WSL mode)...$(RESET)" && npm run dev_wsl -- --port $(FRONTEND_PORT)
-	@echo "$(GREEN)Application started successfully in WSL mode.$(RESET)"
+# 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:
@@ -246,16 +275,6 @@ setup-config-prompts:
 	 workspace_dir=$${workspace_dir:-$(DEFAULT_WORKSPACE_DIR)}; \
 	 echo "workspace_base=\"$$workspace_dir\"" >> $(CONFIG_FILE).tmp
 
-	@read -p "Do you want to persist the sandbox container? [true/false] [default: false]: " persist_sandbox; \
-	 persist_sandbox=$${persist_sandbox:-false}; \
-	 if [ "$$persist_sandbox" = "true" ]; then \
-		 read -p "Enter a password for the sandbox container: " ssh_password; \
-		 echo "ssh_password=\"$$ssh_password\"" >> $(CONFIG_FILE).tmp; \
-		 echo "persist_sandbox=$$persist_sandbox" >> $(CONFIG_FILE).tmp; \
-	 else \
-		echo "persist_sandbox=$$persist_sandbox" >> $(CONFIG_FILE).tmp; \
-	 fi
-
 	@echo "" >> $(CONFIG_FILE).tmp
 
 	@echo "[llm]" >> $(CONFIG_FILE).tmp
@@ -269,36 +288,21 @@ setup-config-prompts:
 	@read -p "Enter your LLM base URL [mostly used for local LLMs, leave blank if not needed - example: http://localhost:5001/v1/]: " llm_base_url; \
 	 if [[ ! -z "$$llm_base_url" ]]; then echo "base_url=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; fi
 
-	@echo "Enter your LLM Embedding Model"; \
-		echo "Choices are:"; \
-		echo "  - openai"; \
-		echo "  - azureopenai"; \
-		echo "  - Embeddings available only with OllamaEmbedding:"; \
-		echo "    - llama2"; \
-		echo "    - mxbai-embed-large"; \
-		echo "    - nomic-embed-text"; \
-		echo "    - all-minilm"; \
-		echo "    - stable-code"; \
-		echo "  - Leave blank to default to 'BAAI/bge-small-en-v1.5' via huggingface"; \
-		read -p "> " llm_embedding_model; \
-		echo "embedding_model=\"$$llm_embedding_model\"" >> $(CONFIG_FILE).tmp; \
-		if [ "$$llm_embedding_model" = "llama2" ] || [ "$$llm_embedding_model" = "mxbai-embed-large" ] || [ "$$llm_embedding_model" = "nomic-embed-text" ] || [ "$$llm_embedding_model" = "all-minilm" ] || [ "$$llm_embedding_model" = "stable-code" ]; then \
-			read -p "Enter the local model URL for the embedding model (will set llm.embedding_base_url): " llm_embedding_base_url; \
-				echo "embedding_base_url=\"$$llm_embedding_base_url\"" >> $(CONFIG_FILE).tmp; \
-		elif [ "$$llm_embedding_model" = "azureopenai" ]; then \
-			read -p "Enter the Azure endpoint URL (will overwrite llm.base_url): " llm_base_url; \
-				echo "base_url=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
-			read -p "Enter the Azure LLM Embedding Deployment Name: " llm_embedding_deployment_name; \
-				echo "embedding_deployment_name=\"$$llm_embedding_deployment_name\"" >> $(CONFIG_FILE).tmp; \
-			read -p "Enter the Azure API Version: " llm_api_version; \
-				echo "api_version=\"$$llm_api_version\"" >> $(CONFIG_FILE).tmp; \
-		fi
 
+# 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 opendevin/.cache
+	@rm -rf openhands/.cache
 	@echo "$(GREEN)Caches cleaned up successfully.$(RESET)"
 
 # Help
@@ -307,13 +311,16 @@ help:
 	@echo "Targets:"
 	@echo "  $(GREEN)build$(RESET)               - Build project, including environment setup and dependencies."
 	@echo "  $(GREEN)lint$(RESET)                - Run linters on the project."
-	@echo "  $(GREEN)setup-config$(RESET)        - Setup the configuration for OpenDevin by providing LLM API key,"
+	@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-pre-commit-hooks lint start-backend start-frontend run run-wsl setup-config setup-config-prompts help
+.PHONY: build check-dependencies check-python check-npm check-docker check-poetry install-python-dependencies install-frontend-dependencies install-pre-commit-hooks lint start-backend start-frontend run run-wsl setup-config setup-config-prompts help
+.PHONY: docker-dev docker-run

README.md

@@ -1,124 +1,123 @@
 <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
--->
+<div align="center">
+  <img src="./docs/static/img/logo.png" alt="Logo" width="200">
+  <h1 align="center">OpenHands: Code Less, Make More</h1>
+</div>
 
-<!-- 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&color=blue" 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&color=blue" 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&color=blue" 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&color=blue" 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&color=blue" alt="MIT License"></a>
+  <a href="https://github.com/All-Hands-AI/OpenHands/graphs/contributors"><img src="https://img.shields.io/github/contributors/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="Contributors"></a>
+  <a href="https://github.com/All-Hands-AI/OpenHands/stargazers"><img src="https://img.shields.io/github/stars/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="Stargazers"></a>
+  <a href="https://codecov.io/github/All-Hands-AI/OpenHands?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/All-Hands-AI/OpenHands?style=for-the-badge&color=blue"></a>
+  <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/github/license/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="MIT License"></a>
   <br/>
-  <a href="https://join.slack.com/t/opendevin/shared_invite/zt-2i1iqdag6-bVmvamiPA9EZUu7oCO6KhA"><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://join.slack.com/t/openhands-ai/shared_invite/zt-2ngejmfw6-9gW4APWOC9XUp1n~SiQ6iw"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
   <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
-  <a href="https://codecov.io/github/opendevin/opendevin?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/opendevin/opendevin?style=for-the-badge"></a>
-</div>
-
-<!-- PROJECT LOGO -->
-<div align="center">
-  <img src="./docs/static/img/logo.png" alt="Logo" width="200" height="200">
-  <h1 align="center">OpenDevin: Code Less, Make More</h1>
-  <a href="https://docs.all-hands.dev/modules/usage/intro"><img src="https://img.shields.io/badge/Documentation-OpenDevin-blue?logo=googledocs&logoColor=white&style=for-the-badge" alt="Check out the documentation"></a>
-  <a href="https://arxiv.org/abs/2407.16741"><img src="https://img.shields.io/badge/Paper-%20on%20Arxiv-red?logo=arxiv&style=for-the-badge" alt="Paper on Arxiv"></a>
+  <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="Credits"></a>
   <br/>
-  <a href="https://huggingface.co/spaces/OpenDevin/evaluation"><img src="https://img.shields.io/badge/Evaluation-Benchmark%20on%20HF%20Space-green?logo=huggingface&style=for-the-badge" alt="Evaluation Benchmark"></a>
+  <a href="https://docs.all-hands.dev/modules/usage/getting-started"><img src="https://img.shields.io/badge/Documentation-000?logo=googledocs&logoColor=FFE165&style=for-the-badge" alt="Check out the documentation"></a>
+  <a href="https://arxiv.org/abs/2407.16741"><img src="https://img.shields.io/badge/Paper%20on%20Arxiv-000?logoColor=FFE165&logo=arxiv&style=for-the-badge" alt="Paper on Arxiv"></a>
+  <a href="https://docs.google.com/spreadsheets/d/1wOUdFCMyY6Nt0AIqF705KN4JKOWgeI4wUGUP60krXXs/edit?gid=0#gid=0"><img src="https://img.shields.io/badge/Benchmark%20score-000?logoColor=FFE165&logo=huggingface&style=for-the-badge" alt="Evaluation Benchmark Score"></a>
+  <hr>
 </div>
-<hr>
 
-Welcome to OpenDevin, a platform for autonomous software engineers, powered by AI and LLMs.
+Welcome to OpenHands (formerly OpenDevin), a platform for software development agents powered by AI.
 
-OpenDevin agents collaborate with human developers to write code, fix bugs, and ship features.
+OpenHands agents can do anything a human developer can: modify code, run commands, browse the web,
+call APIs, and yes—even copy code snippets from StackOverflow.
+
+Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or [sign up for OpenHands Cloud](https://app.all-hands.dev) to get started.
+
+> [!IMPORTANT]
+> Using OpenHands for work? We'd love to chat! Fill out
+> [this short form](https://docs.google.com/forms/d/e/1FAIpQLSet3VbGaz8z32gW9Wm-Grl4jpt5WgMXPgJ4EDPVmCETCBpJtQ/viewform)
+> to join our Design Partner program, where you'll get early access to commercial features and the opportunity to provide input on our product roadmap.
 
 ![App screenshot](./docs/static/img/screenshot.png)
 
-## ⚡ Getting Started
-OpenDevin works best with Docker version 26.0.0+ (Docker Desktop 4.31.0+).
-You must be using Linux, Mac OS, or WSL on Windows.
+## ☁️ OpenHands Cloud
+The easiest way to get started with OpenHands is on [OpenHands Cloud](https://app.all-hands.dev),
+which comes with $50 in free credits for new users.
 
-To start OpenDevin in a docker container, run the following commands in your terminal:
+## 💻 Running OpenHands Locally
+
+OpenHands can also run on your local system using Docker.
+See the [Running OpenHands](https://docs.all-hands.dev/modules/usage/installation) guide for
+system requirements and more information.
 
 > [!WARNING]
-> When you run the following command, files in `./workspace` may be modified or deleted.
+> On a public network? See our [Hardened Docker Installation Guide](https://docs.all-hands.dev/modules/usage/runtimes/docker#hardened-docker-installation)
+> to secure your deployment by restricting network binding and implementing additional security measures.
+
 
 ```bash
-WORKSPACE_BASE=$(pwd)/workspace
-docker run -it \
-    --pull=always \
-    -e SANDBOX_USER_ID=$(id -u) \
-    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
-    -v $WORKSPACE_BASE:/opt/workspace_base \
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
+
+docker run -it --rm --pull=always \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
+    -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
-    --name opendevin-app-$(date +%Y%m%d%H%M%S) \
-    ghcr.io/opendevin/opendevin
+    --name openhands-app \
+    docker.all-hands.dev/all-hands-ai/openhands:0.34
 ```
 
-> [!NOTE]
-> By default, this command pulls the `latest` tag, which represents the most recent release of OpenDevin. You have other options as well:
-> - For a specific release version, use `ghcr.io/opendevin/opendevin:<OpenDevin_version>` (replace <OpenDevin_version> with the desired version number).
-> - For the most up-to-date development version, use `ghcr.io/opendevin/opendevin:main`. This version may be **(unstable!)** and is recommended for testing or development purposes only.
+You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
+
+When you open the application, you'll be asked to choose an LLM provider and add an API key.
+[Anthropic's Claude 3.5 Sonnet](https://www.anthropic.com/api) (`anthropic/claude-3-5-sonnet-20241022`)
+works best, but you have [many options](https://docs.all-hands.dev/modules/usage/llms).
+
+## 💡 Other ways to run OpenHands
+
+> [!CAUTION]
+> OpenHands is meant to be run by a single user on their local workstation.
+> It is not appropriate for multi-tenant deployments where multiple users share the same instance. There is no built-in authentication, isolation, or scalability.
 >
-> Choose the tag that best suits your needs based on stability requirements and desired features.
+> If you're interested in running OpenHands in a multi-tenant environment, please
+> [get in touch with us](https://docs.google.com/forms/d/e/1FAIpQLSet3VbGaz8z32gW9Wm-Grl4jpt5WgMXPgJ4EDPVmCETCBpJtQ/viewform)
+> for advanced deployment options.
 
-You'll find OpenDevin running at [http://localhost:3000](http://localhost:3000) with access to `./workspace`. To have OpenDevin operate on your code, place it in `./workspace`.
-OpenDevin will only have access to this workspace folder. The rest of your system will not be affected as it runs in a secured docker sandbox.
+You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes/docker#connecting-to-your-filesystem),
+run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
+interact with it via a [friendly CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode),
+or run it on tagged issues with [a github action](https://docs.all-hands.dev/modules/usage/how-to/github-action).
 
-Upon opening OpenDevin, you must select the appropriate `Model` and enter the `API Key` within the settings that should pop up automatically. These can be set at any time by selecting
-the `Settings` button (gear icon) in the UI. If the required `Model` does not exist in the list, you can manually enter it in the text box.
+Visit [Running OpenHands](https://docs.all-hands.dev/modules/usage/installation) for more information and setup instructions.
 
-For the development workflow, see [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md).
+If you want to modify the OpenHands source code, check out [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
 
-Are you having trouble? Check out our [Troubleshooting Guide](https://docs.all-hands.dev/modules/usage/troubleshooting).
+Having issues? The [Troubleshooting Guide](https://docs.all-hands.dev/modules/usage/troubleshooting) can help.
 
-## 🚀 Documentation
+## 📖 Documentation
 
-To learn more about the project, and for tips on using OpenDevin,
-**check out our [documentation](https://docs.all-hands.dev/modules/usage/intro)**.
+To learn more about the project, and for tips on using OpenHands,
+check out our [documentation](https://docs.all-hands.dev/modules/usage/getting-started).
 
-There you'll find resources on how to use different LLM providers (like ollama and Anthropic's Claude),
+There you'll find resources on how to use different LLM providers,
 troubleshooting resources, and advanced configuration options.
 
-## 🤝 How to Contribute
+## 🤝 How to Join the Community
 
-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:
+OpenHands is a community-driven project, and we welcome contributions from everyone. We do most of our communication
+through Slack, so this is the best place to start, but we also are happy to have you contact us on Discord or Github:
 
-- **Code Contributions:** Help us develop new agents, core functionality, the frontend and other interfaces, 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.
+- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-2ngejmfw6-9gW4APWOC9XUp1n~SiQ6iw) - Here we talk about research, architecture, and future development.
+- [Join our Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
+- [Read or post Github Issues](https://github.com/All-Hands-AI/OpenHands/issues) - Check out the issues we're working on, or add your own ideas.
 
-For details, please check [CONTRIBUTING.md](./CONTRIBUTING.md).
-
-## 🤖 Join Our Community
-
-Whether you're a developer, a researcher, or simply enthusiastic about OpenDevin, we'd love to have you in our community.
-Let's make software engineering better together!
-
-- [Slack workspace](https://join.slack.com/t/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA) - Here we talk about research, architecture, and future development.
-- [Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
+See more about the community in [COMMUNITY.md](./COMMUNITY.md) or find details on contributing in [CONTRIBUTING.md](./CONTRIBUTING.md).
 
 ## 📈 Progress
 
+See the monthly OpenHands roadmap [here](https://github.com/orgs/All-Hands-AI/projects/1) (updated at the maintainer's meeting at the end of each month).
+
 <p align="center">
-  <a href="https://star-history.com/#OpenDevin/OpenDevin&Date">
-    <img src="https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date" width="500" alt="Star History Chart">
+  <a href="https://star-history.com/#All-Hands-AI/OpenHands&Date">
+    <img src="https://api.star-history.com/svg?repos=All-Hands-AI/OpenHands&type=Date" width="500" alt="Star History Chart">
   </a>
 </p>
 
@@ -126,27 +125,22 @@ Let's make software engineering better together!
 
 Distributed under the MIT License. See [`LICENSE`](./LICENSE) for more information.
 
-[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
+## 🙏 Acknowledgements
+
+OpenHands is built by a large number of contributors, and every contribution is greatly appreciated! We also build upon other open source projects, and we are deeply thankful for their work.
+
+For a list of open source projects and licenses used in OpenHands, please see our [CREDITS.md](./CREDITS.md) file.
 
 ## 📚 Cite
 
 ```
-@misc{opendevin,
-      title={{OpenDevin: An Open Platform for AI Software Developers as Generalist Agents}}, 
+@misc{openhands,
+      title={{OpenHands: An Open Platform for AI Software Developers as Generalist Agents}},
       author={Xingyao Wang and Boxuan Li and Yufan Song and Frank F. Xu and Xiangru Tang and Mingchen Zhuge and Jiayi Pan and Yueqi Song and Bowen Li and Jaskirat Singh and Hoang H. Tran and Fuqiang Li and Ren Ma and Mingzhang Zheng and Bill Qian and Yanjun Shao and Niklas Muennighoff and Yizhe Zhang and Binyuan Hui and Junyang Lin and Robert Brennan and Hao Peng and Heng Ji and Graham Neubig},
       year={2024},
       eprint={2407.16741},
       archivePrefix={arXiv},
       primaryClass={cs.SE},
-      url={https://arxiv.org/abs/2407.16741}, 
+      url={https://arxiv.org/abs/2407.16741},
 }
 ```

agenthub/README.md

@@ -1,72 +0,0 @@
-# Agent Hub
-
-In this folder, there may exist multiple implementations of `Agent` that will be used by the framework.
-
-For example, `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/controller/agent.py).
-
-Agents are run inside of a loop. At each iteration, `agent.step()` is called with a
-[State](../opendevin/controller/state/state.py) input, and the agent must output an [Action](../opendevin/events/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 [`root_task`](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/controller/state/task.py), which contains a plan of action
-  - 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/events/action/commands.py) - Runs a command inside a sandboxed terminal
-- [`IPythonRunCellAction`](../opendevin/events/action/commands.py) - Execute a block of Python code interactively (in Jupyter notebook) and receives `CmdOutputObservation`. Requires setting up `jupyter` [plugin](../opendevin/runtime/plugins) as a requirement.
-- [`FileReadAction`](../opendevin/events/action/files.py) - Reads the content of a file
-- [`FileWriteAction`](../opendevin/events/action/files.py) - Writes new content to a file
-- [`BrowseURLAction`](../opendevin/events/action/browse.py) - Gets the content of a URL
-- [`AddTaskAction`](../opendevin/events/action/tasks.py) - Adds a subtask to the plan
-- [`ModifyTaskAction`](../opendevin/events/action/tasks.py) - Changes the state of a subtask.
-- [`AgentFinishAction`](../opendevin/events/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
-- [`AgentRejectAction`](../opendevin/events/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
-- [`AgentFinishAction`](../opendevin/events/action/agent.py) - Stops the control loop, allowing the user to enter a new task
-- [`MessageAction`](../opendevin/events/action/message.py) - Represents a message from an agent or the user
-
-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).
-
-Here is a list of available Observations:
-
-- [`CmdOutputObservation`](../opendevin/events/observation/commands.py)
-- [`BrowserOutputObservation`](../opendevin/events/observation/browse.py)
-- [`FileReadObservation`](../opendevin/events/observation/files.py)
-- [`FileWriteObservation`](../opendevin/events/observation/files.py)
-- [`ErrorObservation`](../opendevin/events/observation/error.py)
-- [`SuccessObservation`](../opendevin/events/observation/success.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`.

agenthub/__init__.py

@@ -1,42 +0,0 @@
-from dotenv import load_dotenv
-
-from opendevin.controller.agent import Agent
-
-from .micro.agent import MicroAgent
-from .micro.registry import all_microagents
-
-load_dotenv()
-
-
-from . import (  # noqa: E402
-    browsing_agent,
-    codeact_agent,
-    codeact_swe_agent,
-    delegator_agent,
-    dummy_agent,
-    planner_agent,
-)
-
-__all__ = [
-    'codeact_agent',
-    'codeact_swe_agent',
-    'planner_agent',
-    'delegator_agent',
-    'dummy_agent',
-    'browsing_agent',
-]
-
-for agent in all_microagents.values():
-    name = agent['name']
-    prompt = agent['prompt']
-
-    anon_class = type(
-        name,
-        (MicroAgent,),
-        {
-            'prompt': prompt,
-            'agent_definition': agent,
-        },
-    )
-
-    Agent.register(name, anon_class)

agenthub/browsing_agent/__init__.py

@@ -1,5 +0,0 @@
-from opendevin.controller.agent import Agent
-
-from .browsing_agent import BrowsingAgent
-
-Agent.register('BrowsingAgent', BrowsingAgent)

agenthub/browsing_agent/prompt.py

@@ -1,787 +0,0 @@
-import abc
-import difflib
-import logging
-import platform
-from copy import deepcopy
-from dataclasses import asdict, dataclass
-from textwrap import dedent
-from typing import Literal, Union
-from warnings import warn
-
-from browsergym.core.action.base import AbstractActionSet
-from browsergym.core.action.highlevel import HighLevelActionSet
-from browsergym.core.action.python import PythonActionSet
-
-from opendevin.runtime.browser.browser_env import BrowserEnv
-
-from .utils import (
-    ParseError,
-    parse_html_tags_raise,
-)
-
-
-@dataclass
-class Flags:
-    use_html: bool = True
-    use_ax_tree: bool = False
-    drop_ax_tree_first: bool = True  # This flag is no longer active TODO delete
-    use_thinking: bool = False
-    use_error_logs: bool = False
-    use_past_error_logs: bool = False
-    use_history: bool = False
-    use_action_history: bool = False
-    use_memory: bool = False
-    use_diff: bool = False
-    html_type: str = 'pruned_html'
-    use_concrete_example: bool = True
-    use_abstract_example: bool = False
-    multi_actions: bool = False
-    action_space: Literal[
-        'python', 'bid', 'coord', 'bid+coord', 'bid+nav', 'coord+nav', 'bid+coord+nav'
-    ] = 'bid'
-    is_strict: bool = False
-    # This flag will be automatically disabled `if not chat_model_args.has_vision()`
-    use_screenshot: bool = True
-    enable_chat: bool = False
-    max_prompt_tokens: int = 100_000
-    extract_visible_tag: bool = False
-    extract_coords: Literal['False', 'center', 'box'] = 'False'
-    extract_visible_elements_only: bool = False
-    demo_mode: Literal['off', 'default', 'only_visible_elements'] = 'off'
-
-    def copy(self):
-        return deepcopy(self)
-
-    def asdict(self):
-        """Helper for JSON serializble requirement."""
-        return asdict(self)
-
-    @classmethod
-    def from_dict(self, flags_dict):
-        """Helper for JSON serializble requirement."""
-        if isinstance(flags_dict, Flags):
-            return flags_dict
-
-        if not isinstance(flags_dict, dict):
-            raise ValueError(
-                f'Unregcognized type for flags_dict of type {type(flags_dict)}.'
-            )
-        return Flags(**flags_dict)
-
-
-class PromptElement:
-    """Base class for all prompt elements. Prompt elements can be hidden.
-
-    Prompt elements are used to build the prompt. Use flags to control which
-    prompt elements are visible. We use class attributes as a convenient way
-    to implement static prompts, but feel free to override them with instance
-    attributes or @property decorator.
-    """
-
-    _prompt = ''
-    _abstract_ex = ''
-    _concrete_ex = ''
-
-    def __init__(self, visible: bool = True) -> None:
-        """Prompt element that can be hidden.
-
-        Parameters
-        ----------
-        visible : bool, optional
-            Whether the prompt element should be visible, by default True. Can
-            be a callable that returns a bool. This is useful when a specific
-            flag changes during a shrink iteration.
-        """
-        self._visible = visible
-
-    @property
-    def prompt(self):
-        """Avoid overriding this method. Override _prompt instead."""
-        return self._hide(self._prompt)
-
-    @property
-    def abstract_ex(self):
-        """Useful when this prompt element is requesting an answer from the llm.
-        Provide an abstract example of the answer here. See Memory for an
-        example.
-
-        Avoid overriding this method. Override _abstract_ex instead
-        """
-        return self._hide(self._abstract_ex)
-
-    @property
-    def concrete_ex(self):
-        """Useful when this prompt element is requesting an answer from the llm.
-        Provide a concrete example of the answer here. See Memory for an
-        example.
-
-        Avoid overriding this method. Override _concrete_ex instead
-        """
-        return self._hide(self._concrete_ex)
-
-    @property
-    def is_visible(self):
-        """Handle the case where visible is a callable."""
-        visible = self._visible
-        if callable(visible):
-            visible = visible()
-        return visible
-
-    def _hide(self, value):
-        """Return value if visible is True, else return empty string."""
-        if self.is_visible:
-            return value
-        else:
-            return ''
-
-    def _parse_answer(self, text_answer) -> dict:
-        if self.is_visible:
-            return self._parse_answer(text_answer)
-        else:
-            return {}
-
-
-class Shrinkable(PromptElement, abc.ABC):
-    @abc.abstractmethod
-    def shrink(self) -> None:
-        """Implement shrinking of this prompt element.
-
-        You need to recursively call all shrinkable elements that are part of
-        this prompt. You can also implement a shrinking strategy for this prompt.
-        Shrinking is can be called multiple times to progressively shrink the
-        prompt until it fits max_tokens. Default max shrink iterations is 20.
-        """
-        pass
-
-
-class Truncater(Shrinkable):
-    """A prompt element that can be truncated to fit the context length of the LLM.
-    Of course, it will be great that we never have to use the functionality here to `shrink()` the prompt.
-    Extend this class for prompt elements that can be truncated. Usually long observations such as AxTree or HTML.
-    """
-
-    def __init__(self, visible, shrink_speed=0.3, start_truncate_iteration=10):
-        super().__init__(visible=visible)
-        self.shrink_speed = shrink_speed  # the percentage shrunk in each iteration
-        self.start_truncate_iteration = (
-            start_truncate_iteration  # the iteration to start truncating
-        )
-        self.shrink_calls = 0
-        self.deleted_lines = 0
-
-    def shrink(self) -> None:
-        if self.is_visible and self.shrink_calls >= self.start_truncate_iteration:
-            # remove the fraction of _prompt
-            lines = self._prompt.splitlines()
-            new_line_count = int(len(lines) * (1 - self.shrink_speed))
-            self.deleted_lines += len(lines) - new_line_count
-            self._prompt = '\n'.join(lines[:new_line_count])
-            self._prompt += (
-                f'\n... Deleted {self.deleted_lines} lines to reduce prompt size.'
-            )
-
-        self.shrink_calls += 1
-
-
-def fit_tokens(
-    shrinkable: Shrinkable,
-    max_prompt_chars=None,
-    max_iterations=20,
-):
-    """Shrink a prompt element until it fits max_tokens.
-
-    Parameters
-    ----------
-    shrinkable : Shrinkable
-        The prompt element to shrink.
-    max_prompt_chars : int
-        The maximum number of chars allowed.
-    max_iterations : int, optional
-        The maximum number of shrink iterations, by default 20.
-    model_name : str, optional
-        The name of the model used when tokenizing.
-
-    Returns:
-    -------
-    str : the prompt after shrinking.
-    """
-    if max_prompt_chars is None:
-        return shrinkable.prompt
-
-    for _ in range(max_iterations):
-        prompt = shrinkable.prompt
-        if isinstance(prompt, str):
-            prompt_str = prompt
-        elif isinstance(prompt, list):
-            prompt_str = '\n'.join([p['text'] for p in prompt if p['type'] == 'text'])
-        else:
-            raise ValueError(f'Unrecognized type for prompt: {type(prompt)}')
-        n_chars = len(prompt_str)
-        if n_chars <= max_prompt_chars:
-            return prompt
-        shrinkable.shrink()
-
-    logging.info(
-        dedent(
-            f"""\
-            After {max_iterations} shrink iterations, the prompt is still
-            {len(prompt_str)} chars (greater than {max_prompt_chars}). Returning the prompt as is."""
-        )
-    )
-    return prompt
-
-
-class HTML(Truncater):
-    def __init__(self, html, visible: bool = True, prefix='') -> None:
-        super().__init__(visible=visible, start_truncate_iteration=5)
-        self._prompt = f'\n{prefix}HTML:\n{html}\n'
-
-
-class AXTree(Truncater):
-    def __init__(
-        self, ax_tree, visible: bool = True, coord_type=None, prefix=''
-    ) -> None:
-        super().__init__(visible=visible, start_truncate_iteration=10)
-        if coord_type == 'center':
-            coord_note = """\
-Note: center coordinates are provided in parenthesis and are
-  relative to the top left corner of the page.\n\n"""
-        elif coord_type == 'box':
-            coord_note = """\
-Note: bounding box of each object are provided in parenthesis and are
-  relative to the top left corner of the page.\n\n"""
-        else:
-            coord_note = ''
-        self._prompt = f'\n{prefix}AXTree:\n{coord_note}{ax_tree}\n'
-
-
-class Error(PromptElement):
-    def __init__(self, error, visible: bool = True, prefix='') -> None:
-        super().__init__(visible=visible)
-        self._prompt = f'\n{prefix}Error from previous action:\n{error}\n'
-
-
-class Observation(Shrinkable):
-    """Observation of the current step.
-
-    Contains the html, the accessibility tree and the error logs.
-    """
-
-    def __init__(self, obs, flags: Flags) -> None:
-        super().__init__()
-        self.flags = flags
-        self.obs = obs
-        self.html = HTML(obs[flags.html_type], visible=flags.use_html, prefix='## ')
-        self.ax_tree = AXTree(
-            obs['axtree_txt'],
-            visible=flags.use_ax_tree,
-            coord_type=flags.extract_coords,
-            prefix='## ',
-        )
-        self.error = Error(
-            obs['last_action_error'],
-            visible=flags.use_error_logs and obs['last_action_error'],
-            prefix='## ',
-        )
-
-    def shrink(self):
-        self.ax_tree.shrink()
-        self.html.shrink()
-
-    @property
-    def _prompt(self) -> str:  # type: ignore
-        return f'\n# Observation of current step:\n{self.html.prompt}{self.ax_tree.prompt}{self.error.prompt}\n\n'
-
-    def add_screenshot(self, prompt):
-        if self.flags.use_screenshot:
-            if isinstance(prompt, str):
-                prompt = [{'type': 'text', 'text': prompt}]
-            img_url = BrowserEnv.image_to_jpg_base64_url(
-                self.obs['screenshot'], add_data_prefix=True
-            )
-            prompt.append({'type': 'image_url', 'image_url': img_url})
-
-        return prompt
-
-
-class MacNote(PromptElement):
-    def __init__(self) -> None:
-        super().__init__(visible=platform.system() == 'Darwin')
-        self._prompt = '\nNote: you are on mac so you should use Meta instead of Control for Control+C etc.\n'
-
-
-class BeCautious(PromptElement):
-    def __init__(self, visible: bool = True) -> None:
-        super().__init__(visible=visible)
-        self._prompt = """\
-\nBe very cautious. Avoid submitting anything before verifying the effect of your
-actions. Take the time to explore the effect of safe actions first. For example
-you can fill a few elements of a form, but don't click submit before verifying
-that everything was filled correctly.\n"""
-
-
-class GoalInstructions(PromptElement):
-    def __init__(self, goal, visible: bool = True) -> None:
-        super().__init__(visible)
-        self._prompt = f"""\
-# Instructions
-Review the current state of the page and all other information to find the best
-possible next action to accomplish your goal. Your answer will be interpreted
-and executed by a program, make sure to follow the formatting instructions.
-
-## Goal:
-{goal}
-"""
-
-
-class ChatInstructions(PromptElement):
-    def __init__(self, chat_messages, visible: bool = True) -> None:
-        super().__init__(visible)
-        self._prompt = """\
-# Instructions
-
-You are a UI Assistant, your goal is to help the user perform tasks using a web browser. You can
-communicate with the user via a chat, in which the user gives you instructions and in which you
-can send back messages. You have access to a web browser that both you and the user can see,
-and with which only you can interact via specific commands.
-
-Review the instructions from the user, the current state of the page and all other information
-to find the best possible next action to accomplish your goal. Your answer will be interpreted
-and executed by a program, make sure to follow the formatting instructions.
-
-## Chat messages:
-
-"""
-        self._prompt += '\n'.join(
-            [
-                f"""\
- - [{msg['role']}] {msg['message']}"""
-                for msg in chat_messages
-            ]
-        )
-
-
-class SystemPrompt(PromptElement):
-    _prompt = """\
-You are an agent trying to solve a web task based on the content of the page and
-a user instructions. You can interact with the page and explore. Each time you
-submit an action it will be sent to the browser and you will receive a new page."""
-
-
-class MainPrompt(Shrinkable):
-    def __init__(
-        self,
-        obs_history,
-        actions,
-        memories,
-        thoughts,
-        flags: Flags,
-    ) -> None:
-        super().__init__()
-        self.flags = flags
-        self.history = History(obs_history, actions, memories, thoughts, flags)
-        if self.flags.enable_chat:
-            self.instructions: Union[ChatInstructions, GoalInstructions] = (
-                ChatInstructions(obs_history[-1]['chat_messages'])
-            )
-        else:
-            if (
-                'chat_messages' in obs_history[-1]
-                and sum(
-                    [msg['role'] == 'user' for msg in obs_history[-1]['chat_messages']]
-                )
-                > 1
-            ):
-                logging.warning(
-                    'Agent is in goal mode, but multiple user messages are present in the chat. Consider switching to `enable_chat=True`.'
-                )
-            self.instructions = GoalInstructions(obs_history[-1]['goal'])
-
-        self.obs = Observation(obs_history[-1], self.flags)
-        self.action_space = ActionSpace(self.flags)
-
-        self.think = Think(visible=flags.use_thinking)
-        self.memory = Memory(visible=flags.use_memory)
-
-    @property
-    def _prompt(self) -> str:  # type: ignore
-        prompt = f"""\
-{self.instructions.prompt}\
-{self.obs.prompt}\
-{self.history.prompt}\
-{self.action_space.prompt}\
-{self.think.prompt}\
-{self.memory.prompt}\
-"""
-
-        if self.flags.use_abstract_example:
-            prompt += f"""
-# Abstract Example
-
-Here is an abstract version of the answer with description of the content of
-each tag. Make sure you follow this structure, but replace the content with your
-answer:
-{self.think.abstract_ex}\
-{self.memory.abstract_ex}\
-{self.action_space.abstract_ex}\
-"""
-
-        if self.flags.use_concrete_example:
-            prompt += f"""
-# Concrete Example
-
-Here is a concrete example of how to format your answer.
-Make sure to follow the template with proper tags:
-{self.think.concrete_ex}\
-{self.memory.concrete_ex}\
-{self.action_space.concrete_ex}\
-"""
-        return self.obs.add_screenshot(prompt)
-
-    def shrink(self):
-        self.history.shrink()
-        self.obs.shrink()
-
-    def _parse_answer(self, text_answer):
-        ans_dict = {}
-        ans_dict.update(self.think._parse_answer(text_answer))
-        ans_dict.update(self.memory._parse_answer(text_answer))
-        ans_dict.update(self.action_space._parse_answer(text_answer))
-        return ans_dict
-
-
-class ActionSpace(PromptElement):
-    def __init__(self, flags: Flags) -> None:
-        super().__init__()
-        self.flags = flags
-        self.action_space = _get_action_space(flags)
-
-        self._prompt = (
-            f'# Action space:\n{self.action_space.describe()}{MacNote().prompt}\n'
-        )
-        self._abstract_ex = f"""
-<action>
-{self.action_space.example_action(abstract=True)}
-</action>
-"""
-        self._concrete_ex = f"""
-<action>
-{self.action_space.example_action(abstract=False)}
-</action>
-"""
-
-    def _parse_answer(self, text_answer):
-        ans_dict = parse_html_tags_raise(
-            text_answer, keys=['action'], merge_multiple=True
-        )
-
-        try:
-            # just check if action can be mapped to python code but keep action as is
-            # the environment will be responsible for mapping it to python
-            self.action_space.to_python_code(ans_dict['action'])
-        except Exception as e:
-            raise ParseError(
-                f'Error while parsing action\n: {e}\n'
-                'Make sure your answer is restricted to the allowed actions.'
-            )
-
-        return ans_dict
-
-
-def _get_action_space(flags: Flags) -> AbstractActionSet:
-    match flags.action_space:
-        case 'python':
-            action_space = PythonActionSet(strict=flags.is_strict)
-            if flags.multi_actions:
-                warn(
-                    f'Flag action_space={repr(flags.action_space)} incompatible with multi_actions={repr(flags.multi_actions)}.',
-                    stacklevel=2,
-                )
-            if flags.demo_mode != 'off':
-                warn(
-                    f'Flag action_space={repr(flags.action_space)} incompatible with demo_mode={repr(flags.demo_mode)}.',
-                    stacklevel=2,
-                )
-            return action_space
-        case 'bid':
-            action_subsets = ['chat', 'bid']
-        case 'coord':
-            action_subsets = ['chat', 'coord']
-        case 'bid+coord':
-            action_subsets = ['chat', 'bid', 'coord']
-        case 'bid+nav':
-            action_subsets = ['chat', 'bid', 'nav']
-        case 'coord+nav':
-            action_subsets = ['chat', 'coord', 'nav']
-        case 'bid+coord+nav':
-            action_subsets = ['chat', 'bid', 'coord', 'nav']
-        case _:
-            raise NotImplementedError(
-                f'Unknown action_space {repr(flags.action_space)}'
-            )
-
-    action_space = HighLevelActionSet(
-        subsets=action_subsets,
-        multiaction=flags.multi_actions,
-        strict=flags.is_strict,
-        demo_mode=flags.demo_mode,
-    )
-
-    return action_space
-
-
-class Memory(PromptElement):
-    _prompt = ''  # provided in the abstract and concrete examples
-
-    _abstract_ex = """
-<memory>
-Write down anything you need to remember for next steps. You will be presented
-with the list of previous memories and past actions.
-</memory>
-"""
-
-    _concrete_ex = """
-<memory>
-I clicked on bid 32 to activate tab 2. The accessibility tree should mention
-focusable for elements of the form at next step.
-</memory>
-"""
-
-    def _parse_answer(self, text_answer):
-        return parse_html_tags_raise(
-            text_answer, optional_keys=['memory'], merge_multiple=True
-        )
-
-
-class Think(PromptElement):
-    _prompt = ''
-
-    _abstract_ex = """
-<think>
-Think step by step. If you need to make calculations such as coordinates, write them here. Describe the effect
-that your previous action had on the current content of the page.
-</think>
-"""
-    _concrete_ex = """
-<think>
-My memory says that I filled the first name and last name, but I can't see any
-content in the form. I need to explore different ways to fill the form. Perhaps
-the form is not visible yet or some fields are disabled. I need to replan.
-</think>
-"""
-
-    def _parse_answer(self, text_answer):
-        return parse_html_tags_raise(
-            text_answer, optional_keys=['think'], merge_multiple=True
-        )
-
-
-def diff(previous, new):
-    """Return a string showing the difference between original and new.
-
-    If the difference is above diff_threshold, return the diff string.
-    """
-    if previous == new:
-        return 'Identical', []
-
-    if len(previous) == 0 or previous is None:
-        return 'previous is empty', []
-
-    diff_gen = difflib.ndiff(previous.splitlines(), new.splitlines())
-
-    diff_lines = []
-    plus_count = 0
-    minus_count = 0
-    for line in diff_gen:
-        if line.strip().startswith('+'):
-            diff_lines.append(line)
-            plus_count += 1
-        elif line.strip().startswith('-'):
-            diff_lines.append(line)
-            minus_count += 1
-        else:
-            continue
-
-    header = f'{plus_count} lines added and {minus_count} lines removed:'
-
-    return header, diff_lines
-
-
-class Diff(Shrinkable):
-    def __init__(
-        self, previous, new, prefix='', max_line_diff=20, shrink_speed=2, visible=True
-    ) -> None:
-        super().__init__(visible=visible)
-        self.max_line_diff = max_line_diff
-        self.header, self.diff_lines = diff(previous, new)
-        self.shrink_speed = shrink_speed
-        self.prefix = prefix
-
-    def shrink(self):
-        self.max_line_diff -= self.shrink_speed
-        self.max_line_diff = max(1, self.max_line_diff)
-
-    @property
-    def _prompt(self) -> str:  # type: ignore
-        diff_str = '\n'.join(self.diff_lines[: self.max_line_diff])
-        if len(self.diff_lines) > self.max_line_diff:
-            original_count = len(self.diff_lines)
-            diff_str = f'{diff_str}\nDiff truncated, {original_count - self.max_line_diff} changes now shown.'
-        return f'{self.prefix}{self.header}\n{diff_str}\n'
-
-
-class HistoryStep(Shrinkable):
-    def __init__(
-        self, previous_obs, current_obs, action, memory, flags: Flags, shrink_speed=1
-    ) -> None:
-        super().__init__()
-        self.html_diff = Diff(
-            previous_obs[flags.html_type],
-            current_obs[flags.html_type],
-            prefix='\n### HTML diff:\n',
-            shrink_speed=shrink_speed,
-            visible=lambda: flags.use_html and flags.use_diff,
-        )
-        self.ax_tree_diff = Diff(
-            previous_obs['axtree_txt'],
-            current_obs['axtree_txt'],
-            prefix='\n### Accessibility tree diff:\n',
-            shrink_speed=shrink_speed,
-            visible=lambda: flags.use_ax_tree and flags.use_diff,
-        )
-        self.error = Error(
-            current_obs['last_action_error'],
-            visible=(
-                flags.use_error_logs
-                and current_obs['last_action_error']
-                and flags.use_past_error_logs
-            ),
-            prefix='### ',
-        )
-        self.shrink_speed = shrink_speed
-        self.action = action
-        self.memory = memory
-        self.flags = flags
-
-    def shrink(self):
-        super().shrink()
-        self.html_diff.shrink()
-        self.ax_tree_diff.shrink()
-
-    @property
-    def _prompt(self) -> str:  # type: ignore
-        prompt = ''
-
-        if self.flags.use_action_history:
-            prompt += f'\n### Action:\n{self.action}\n'
-
-        prompt += (
-            f'{self.error.prompt}{self.html_diff.prompt}{self.ax_tree_diff.prompt}'
-        )
-
-        if self.flags.use_memory and self.memory is not None:
-            prompt += f'\n### Memory:\n{self.memory}\n'
-
-        return prompt
-
-
-class History(Shrinkable):
-    def __init__(
-        self, history_obs, actions, memories, thoughts, flags: Flags, shrink_speed=1
-    ) -> None:
-        super().__init__(visible=flags.use_history)
-        assert len(history_obs) == len(actions) + 1
-        assert len(history_obs) == len(memories) + 1
-
-        self.shrink_speed = shrink_speed
-        self.history_steps: list[HistoryStep] = []
-
-        for i in range(1, len(history_obs)):
-            self.history_steps.append(
-                HistoryStep(
-                    history_obs[i - 1],
-                    history_obs[i],
-                    actions[i - 1],
-                    memories[i - 1],
-                    flags,
-                )
-            )
-
-    def shrink(self):
-        """Shrink individual steps"""
-        # TODO set the shrink speed of older steps to be higher
-        super().shrink()
-        for step in self.history_steps:
-            step.shrink()
-
-    @property
-    def _prompt(self):
-        prompts = ['# History of interaction with the task:\n']
-        for i, step in enumerate(self.history_steps):
-            prompts.append(f'## step {i}')
-            prompts.append(step.prompt)
-        return '\n'.join(prompts) + '\n'
-
-
-if __name__ == '__main__':
-    html_template = """
-    <html>
-    <body>
-    <div>
-    Hello World.
-    Step {}.
-    </div>
-    </body>
-    </html>
-    """
-
-    OBS_HISTORY = [
-        {
-            'goal': 'do this and that',
-            'pruned_html': html_template.format(1),
-            'axtree_txt': '[1] Click me',
-            'last_action_error': '',
-        },
-        {
-            'goal': 'do this and that',
-            'pruned_html': html_template.format(2),
-            'axtree_txt': '[1] Click me',
-            'last_action_error': '',
-        },
-        {
-            'goal': 'do this and that',
-            'pruned_html': html_template.format(3),
-            'axtree_txt': '[1] Click me',
-            'last_action_error': 'Hey, there is an error now',
-        },
-    ]
-    ACTIONS = ["click('41')", "click('42')"]
-    MEMORIES = ['memory A', 'memory B']
-    THOUGHTS = ['thought A', 'thought B']
-
-    flags = Flags(
-        use_html=True,
-        use_ax_tree=True,
-        use_thinking=True,
-        use_error_logs=True,
-        use_past_error_logs=True,
-        use_history=True,
-        use_action_history=True,
-        use_memory=True,
-        use_diff=True,
-        html_type='pruned_html',
-        use_concrete_example=True,
-        use_abstract_example=True,
-        use_screenshot=False,
-        multi_actions=True,
-    )
-
-    print(
-        MainPrompt(
-            obs_history=OBS_HISTORY,
-            actions=ACTIONS,
-            memories=MEMORIES,
-            thoughts=THOUGHTS,
-            flags=flags,
-        ).prompt
-    )

agenthub/browsing_agent/response_parser.py

@@ -1,88 +0,0 @@
-import ast
-
-from opendevin.controller.action_parser import ActionParser, ResponseParser
-from opendevin.core.logger import opendevin_logger as logger
-from opendevin.events.action import (
-    Action,
-    BrowseInteractiveAction,
-)
-
-
-class BrowsingResponseParser(ResponseParser):
-    def __init__(self):
-        # Need to pay attention to the item order in self.action_parsers
-        super().__init__()
-        self.action_parsers = [BrowsingActionParserMessage()]
-        self.default_parser = BrowsingActionParserBrowseInteractive()
-
-    def parse(self, response: str) -> Action:
-        action_str = self.parse_response(response)
-        return self.parse_action(action_str)
-
-    def parse_response(self, response) -> str:
-        action_str = response['choices'][0]['message']['content']
-        if action_str is None:
-            return ''
-        action_str = action_str.strip()
-        if not action_str.endswith('```'):
-            action_str = action_str + ')```'
-        logger.info(action_str)
-        return action_str
-
-    def parse_action(self, action_str: str) -> Action:
-        for action_parser in self.action_parsers:
-            if action_parser.check_condition(action_str):
-                return action_parser.parse(action_str)
-        return self.default_parser.parse(action_str)
-
-
-class BrowsingActionParserMessage(ActionParser):
-    """Parser action:
-    - BrowseInteractiveAction(browser_actions) - unexpected response format, message back to user
-    """
-
-    def __init__(
-        self,
-    ):
-        pass
-
-    def check_condition(self, action_str: str) -> bool:
-        return '```' not in action_str
-
-    def parse(self, action_str: str) -> Action:
-        msg = f'send_msg_to_user("""{action_str}""")'
-        return BrowseInteractiveAction(
-            browser_actions=msg,
-            thought=action_str,
-            browsergym_send_msg_to_user=action_str,
-        )
-
-
-class BrowsingActionParserBrowseInteractive(ActionParser):
-    """Parser action:
-    - BrowseInteractiveAction(browser_actions) - handle send message to user function call in BrowserGym
-    """
-
-    def __init__(
-        self,
-    ):
-        pass
-
-    def check_condition(self, action_str: str) -> bool:
-        return True
-
-    def parse(self, action_str: str) -> Action:
-        thought = action_str.split('```')[0].strip()
-        action_str = action_str.split('```')[1].strip()
-        msg_content = ''
-        for sub_action in action_str.split('\n'):
-            if 'send_msg_to_user(' in sub_action:
-                tree = ast.parse(sub_action)
-                args = tree.body[0].value.args  # type: ignore
-                msg_content = args[0].value
-
-        return BrowseInteractiveAction(
-            browser_actions=action_str,
-            thought=thought,
-            browsergym_send_msg_to_user=msg_content,
-        )

agenthub/codeact_agent/README.md

@@ -1,29 +0,0 @@
-# CodeAct Agent Framework
-
-This folder implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.01030), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a unified **code** action space for both *simplicity* and *performance* (see paper for more details).
-
-The conceptual idea is illustrated below. At each turn, the agent can:
-
-1. **Converse**: Communicate with humans in natural language to ask for clarification, confirmation, etc.
-2. **CodeAct**: Choose to perform the task by executing code
-   - Execute any valid Linux `bash` command
-   - Execute any valid `Python` code with [an interactive Python interpreter](https://ipython.org/). This is simulated through `bash` command, see plugin system below for more details.
-
-![image](https://github.com/OpenDevin/OpenDevin/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
-
-## Plugin System
-
-To make the CodeAct agent more powerful with only access to `bash` action space, CodeAct agent leverages OpenDevin's plugin system:
-- [Jupyter plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/jupyter): for IPython execution via bash command
-- [SWE-agent tool plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/swe_agent_commands): Powerful bash command line tools for software development tasks introduced by [swe-agent](https://github.com/princeton-nlp/swe-agent).
-
-## Demo
-
-https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
-
-*Example of CodeActAgent with `gpt-4-turbo-2024-04-09` performing a data science task (linear regression)*
-
-## Work-in-progress & Next step
-
-[] Support web-browsing
-[] Complete the workflow for CodeAct agent to submit Github PRs

agenthub/codeact_agent/__init__.py

@@ -1,5 +0,0 @@
-from opendevin.controller.agent import Agent
-
-from .codeact_agent import CodeActAgent
-
-Agent.register('CodeActAgent', CodeActAgent)

agenthub/codeact_agent/action_parser.py

@@ -1,177 +0,0 @@
-import re
-
-from opendevin.controller.action_parser import ActionParser, ResponseParser
-from opendevin.events.action import (
-    Action,
-    AgentDelegateAction,
-    AgentFinishAction,
-    CmdRunAction,
-    IPythonRunCellAction,
-    MessageAction,
-)
-
-
-class CodeActResponseParser(ResponseParser):
-    """Parser action:
-    - CmdRunAction(command) - bash command to run
-    - IPythonRunCellAction(code) - IPython code to run
-    - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
-    - MessageAction(content) - Message action to run (e.g. ask for clarification)
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(self):
-        # Need pay attention to the item order in self.action_parsers
-        super().__init__()
-        self.action_parsers = [
-            CodeActActionParserFinish(),
-            CodeActActionParserCmdRun(),
-            CodeActActionParserIPythonRunCell(),
-            CodeActActionParserAgentDelegate(),
-        ]
-        self.default_parser = CodeActActionParserMessage()
-
-    def parse(self, response) -> Action:
-        action_str = self.parse_response(response)
-        return self.parse_action(action_str)
-
-    def parse_response(self, response) -> str:
-        action = response.choices[0].message.content
-        if action is None:
-            return ''
-        for lang in ['bash', 'ipython', 'browse']:
-            if f'<execute_{lang}>' in action and f'</execute_{lang}>' not in action:
-                action += f'</execute_{lang}>'
-        return action
-
-    def parse_action(self, action_str: str) -> Action:
-        for action_parser in self.action_parsers:
-            if action_parser.check_condition(action_str):
-                return action_parser.parse(action_str)
-        return self.default_parser.parse(action_str)
-
-
-class CodeActActionParserFinish(ActionParser):
-    """Parser action:
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(
-        self,
-    ):
-        self.finish_command = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.finish_command = re.search(r'<finish>.*</finish>', action_str, re.DOTALL)
-        return self.finish_command is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.finish_command is not None
-        ), 'self.finish_command should not be None when parse is called'
-        thought = action_str.replace(self.finish_command.group(0), '').strip()
-        return AgentFinishAction(thought=thought)
-
-
-class CodeActActionParserCmdRun(ActionParser):
-    """Parser action:
-    - CmdRunAction(command) - bash command to run
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(
-        self,
-    ):
-        self.bash_command = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.bash_command = re.search(
-            r'<execute_bash>(.*?)</execute_bash>', action_str, re.DOTALL
-        )
-        return self.bash_command is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.bash_command is not None
-        ), 'self.bash_command should not be None when parse is called'
-        thought = action_str.replace(self.bash_command.group(0), '').strip()
-        # a command was found
-        command_group = self.bash_command.group(1).strip()
-        if command_group.strip() == 'exit':
-            return AgentFinishAction(thought=thought)
-        return CmdRunAction(command=command_group, thought=thought)
-
-
-class CodeActActionParserIPythonRunCell(ActionParser):
-    """Parser action:
-    - IPythonRunCellAction(code) - IPython code to run
-    """
-
-    def __init__(
-        self,
-    ):
-        self.python_code = None
-        self.jupyter_kernel_init_code: str = 'from agentskills import *'
-
-    def check_condition(self, action_str: str) -> bool:
-        self.python_code = re.search(
-            r'<execute_ipython>(.*?)</execute_ipython>', action_str, re.DOTALL
-        )
-        return self.python_code is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.python_code is not None
-        ), 'self.python_code should not be None when parse is called'
-        code_group = self.python_code.group(1).strip()
-        thought = action_str.replace(self.python_code.group(0), '').strip()
-        return IPythonRunCellAction(
-            code=code_group,
-            thought=thought,
-            kernel_init_code=self.jupyter_kernel_init_code,
-        )
-
-
-class CodeActActionParserAgentDelegate(ActionParser):
-    """Parser action:
-    - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
-    """
-
-    def __init__(
-        self,
-    ):
-        self.agent_delegate = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.agent_delegate = re.search(
-            r'<execute_browse>(.*)</execute_browse>', action_str, re.DOTALL
-        )
-        return self.agent_delegate is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.agent_delegate is not None
-        ), 'self.agent_delegate should not be None when parse is called'
-        thought = action_str.replace(self.agent_delegate.group(0), '').strip()
-        browse_actions = self.agent_delegate.group(1).strip()
-        task = f'{thought}. I should start with: {browse_actions}'
-        return AgentDelegateAction(agent='BrowsingAgent', inputs={'task': task})
-
-
-class CodeActActionParserMessage(ActionParser):
-    """Parser action:
-    - MessageAction(content) - Message action to run (e.g. ask for clarification)
-    """
-
-    def __init__(
-        self,
-    ):
-        pass
-
-    def check_condition(self, action_str: str) -> bool:
-        # We assume the LLM is GOOD enough that when it returns pure natural language
-        # it wants to talk to the user
-        return True
-
-    def parse(self, action_str: str) -> Action:
-        return MessageAction(content=action_str, wait_for_response=True)

agenthub/codeact_agent/codeact_agent.py

@@ -1,245 +0,0 @@
-from agenthub.codeact_agent.action_parser import CodeActResponseParser
-from agenthub.codeact_agent.prompt import (
-    COMMAND_DOCS,
-    EXAMPLES,
-    GITHUB_MESSAGE,
-    SYSTEM_PREFIX,
-    SYSTEM_SUFFIX,
-)
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.events.action import (
-    Action,
-    AgentDelegateAction,
-    AgentFinishAction,
-    CmdRunAction,
-    IPythonRunCellAction,
-    MessageAction,
-)
-from opendevin.events.observation import (
-    AgentDelegateObservation,
-    CmdOutputObservation,
-    IPythonRunCellObservation,
-)
-from opendevin.events.observation.observation import Observation
-from opendevin.events.serialization.event import truncate_content
-from opendevin.llm.llm import LLM
-from opendevin.runtime.plugins import (
-    AgentSkillsRequirement,
-    JupyterRequirement,
-    PluginRequirement,
-)
-from opendevin.runtime.tools import RuntimeTool
-
-ENABLE_GITHUB = True
-
-
-# FIXME: We can tweak these two settings to create MicroAgents specialized toward different area
-def get_system_message() -> str:
-    if ENABLE_GITHUB:
-        return f'{SYSTEM_PREFIX}\n{GITHUB_MESSAGE}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
-    else:
-        return f'{SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
-
-
-def get_in_context_example() -> str:
-    return EXAMPLES
-
-
-class CodeActAgent(Agent):
-    VERSION = '1.8'
-    """
-    The Code Act Agent is a minimalist agent.
-    The agent works by passing the model a list of action-observation pairs and prompting the model to take the next step.
-
-    ### Overview
-
-    This agent implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.01030), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a unified **code** action space for both *simplicity* and *performance* (see paper for more details).
-
-    The conceptual idea is illustrated below. At each turn, the agent can:
-
-    1. **Converse**: Communicate with humans in natural language to ask for clarification, confirmation, etc.
-    2. **CodeAct**: Choose to perform the task by executing code
-    - Execute any valid Linux `bash` command
-    - Execute any valid `Python` code with [an interactive Python interpreter](https://ipython.org/). This is simulated through `bash` command, see plugin system below for more details.
-
-    ![image](https://github.com/OpenDevin/OpenDevin/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
-
-    ### Plugin System
-
-    To make the CodeAct agent more powerful with only access to `bash` action space, CodeAct agent leverages OpenDevin's plugin system:
-    - [Jupyter plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/jupyter): for IPython execution via bash command
-    - [SWE-agent tool plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/swe_agent_commands): Powerful bash command line tools for software development tasks introduced by [swe-agent](https://github.com/princeton-nlp/swe-agent).
-
-    ### Demo
-
-    https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
-
-    *Example of CodeActAgent with `gpt-4-turbo-2024-04-09` performing a data science task (linear regression)*
-
-    ### Work-in-progress & Next step
-
-    [] Support web-browsing
-    [] Complete the workflow for CodeAct agent to submit Github PRs
-
-    """
-
-    sandbox_plugins: list[PluginRequirement] = [
-        # NOTE: AgentSkillsRequirement need to go before JupyterRequirement, since
-        # AgentSkillsRequirement provides a lot of Python functions,
-        # and it needs to be initialized before Jupyter for Jupyter to use those functions.
-        AgentSkillsRequirement(),
-        JupyterRequirement(),
-    ]
-    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
-
-    system_message: str = get_system_message()
-    in_context_example: str = f"Here is an example of how you can interact with the environment for task solving:\n{get_in_context_example()}\n\nNOW, LET'S START!"
-
-    action_parser = CodeActResponseParser()
-
-    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.reset()
-
-    def action_to_str(self, action: Action) -> str:
-        if isinstance(action, CmdRunAction):
-            return (
-                f'{action.thought}\n<execute_bash>\n{action.command}\n</execute_bash>'
-            )
-        elif isinstance(action, IPythonRunCellAction):
-            return f'{action.thought}\n<execute_ipython>\n{action.code}\n</execute_ipython>'
-        elif isinstance(action, AgentDelegateAction):
-            return f'{action.thought}\n<execute_browse>\n{action.inputs["task"]}\n</execute_browse>'
-        elif isinstance(action, MessageAction):
-            return action.content
-        elif isinstance(action, AgentFinishAction) and action.source == 'agent':
-            return action.thought
-        return ''
-
-    def get_action_message(self, action: Action) -> dict[str, str] | None:
-        if (
-            isinstance(action, AgentDelegateAction)
-            or isinstance(action, CmdRunAction)
-            or isinstance(action, IPythonRunCellAction)
-            or isinstance(action, MessageAction)
-            or (isinstance(action, AgentFinishAction) and action.source == 'agent')
-        ):
-            return {
-                'role': 'user' if action.source == 'user' else 'assistant',
-                'content': self.action_to_str(action),
-            }
-        return None
-
-    def get_observation_message(self, obs: Observation) -> dict[str, str] | None:
-        max_message_chars = self.llm.config.max_message_chars
-        if isinstance(obs, CmdOutputObservation):
-            content = 'OBSERVATION:\n' + truncate_content(
-                obs.content, max_message_chars
-            )
-            content += (
-                f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]'
-            )
-            return {'role': 'user', 'content': content}
-        elif isinstance(obs, IPythonRunCellObservation):
-            content = 'OBSERVATION:\n' + obs.content
-            # replace base64 images with a placeholder
-            splitted = content.split('\n')
-            for i, line in enumerate(splitted):
-                if '![image](data:image/png;base64,' in line:
-                    splitted[i] = (
-                        '![image](data:image/png;base64, ...) already displayed to user'
-                    )
-            content = '\n'.join(splitted)
-            content = truncate_content(content, max_message_chars)
-            return {'role': 'user', 'content': content}
-        elif isinstance(obs, AgentDelegateObservation):
-            content = 'OBSERVATION:\n' + truncate_content(
-                str(obs.outputs), max_message_chars
-            )
-            return {'role': 'user', 'content': content}
-        return None
-
-    def reset(self) -> None:
-        """Resets the CodeAct Agent."""
-        super().reset()
-
-    def step(self, state: State) -> Action:
-        """Performs one step using the CodeAct 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
-
-        Returns:
-        - CmdRunAction(command) - bash command to run
-        - IPythonRunCellAction(code) - IPython code to run
-        - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
-        - MessageAction(content) - Message action to run (e.g. ask for clarification)
-        - AgentFinishAction() - end the interaction
-        """
-        # if we're done, go back
-        latest_user_message = state.history.get_last_user_message()
-        if latest_user_message and latest_user_message.strip() == '/exit':
-            return AgentFinishAction()
-
-        # prepare what we want to send to the LLM
-        messages: list[dict[str, str]] = self._get_messages(state)
-
-        response = self.llm.completion(
-            messages=messages,
-            stop=[
-                '</execute_ipython>',
-                '</execute_bash>',
-                '</execute_browse>',
-            ],
-            temperature=0.0,
-        )
-        return self.action_parser.parse(response)
-
-    def _get_messages(self, state: State) -> list[dict[str, str]]:
-        messages = [
-            {'role': 'system', 'content': self.system_message},
-            {'role': 'user', 'content': self.in_context_example},
-        ]
-
-        for event in state.history.get_events():
-            # create a regular message from an event
-            if isinstance(event, Action):
-                message = self.get_action_message(event)
-            elif isinstance(event, Observation):
-                message = self.get_observation_message(event)
-            else:
-                raise ValueError(f'Unknown event type: {type(event)}')
-
-            # add regular message
-            if message:
-                # handle error if the message is the SAME role as the previous message
-                # litellm.exceptions.BadRequestError: litellm.BadRequestError: OpenAIException - Error code: 400 - {'detail': 'Only supports u/a/u/a/u...'}
-                # there should not have two consecutive messages from the same role
-                if messages and messages[-1]['role'] == message['role']:
-                    messages[-1]['content'] += '\n\n' + message['content']
-                else:
-                    messages.append(message)
-
-        # the latest user message is important:
-        # we want to remind the agent of the environment constraints
-        latest_user_message = next(
-            (m for m in reversed(messages) if m['role'] == 'user'), None
-        )
-
-        # add a reminder to the prompt
-        if latest_user_message:
-            latest_user_message['content'] += (
-                f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task. When finished reply with <finish></finish>'
-            )
-
-        return messages

agenthub/codeact_agent/prompt.py

@@ -1,275 +0,0 @@
-from opendevin.runtime.plugins import AgentSkillsRequirement
-
-_AGENT_SKILLS_DOCS = AgentSkillsRequirement.documentation
-
-COMMAND_DOCS = (
-    '\nApart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:\n'
-    f'{_AGENT_SKILLS_DOCS}'
-    "Please note that THE `edit_file_by_replace`, `append_file` and `insert_content_at_line` FUNCTIONS REQUIRE PROPER INDENTATION. If the assistant would like to add the line '        print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run."
-)
-
-# ======= SYSTEM MESSAGE =======
-MINIMAL_SYSTEM_PREFIX = """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
-The assistant can use an interactive Python (Jupyter Notebook) environment, executing code with <execute_ipython>.
-<execute_ipython>
-print("Hello World!")
-</execute_ipython>
-The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
-
-For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
-Important, however: do not run interactive commands. You do not have access to stdin.
-Also, you need to handle commands that may run indefinitely and not return a result. For such cases, you should redirect the output to a file and run the command in the background to avoid blocking the execution.
-For example, to run a Python script that might run indefinitely without returning immediately, you can use the following format: <execute_bash> python3 app.py > server.log 2>&1 & </execute_bash>
-Also, if a command execution result saying like: Command: "npm start" timed out. Sending SIGINT to the process, you should also retry with running the command in the background.
-"""
-
-BROWSING_PREFIX = """The assistant can browse the Internet with <execute_browse> and </execute_browse>.
-For example, <execute_browse> Tell me the usa's president using google search </execute_browse>.
-Or <execute_browse> Tell me what is in http://example.com </execute_browse>.
-"""
-PIP_INSTALL_PREFIX = """The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them."""
-
-SYSTEM_PREFIX = MINIMAL_SYSTEM_PREFIX + BROWSING_PREFIX + PIP_INSTALL_PREFIX
-
-GITHUB_MESSAGE = """To interact with GitHub, use the $GITHUB_TOKEN environment variable.
-For example, to push a branch `my_branch` to the GitHub repo `owner/repo`:
-<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
-If $GITHUB_TOKEN is not set, ask the user to set it."""
-
-SYSTEM_SUFFIX = """Responses should be concise.
-The assistant should attempt fewer things at a time instead of putting too many commands OR too much code in one "execute" block.
-Include ONLY ONE <execute_ipython>, <execute_bash>, or <execute_browse> per response, unless the assistant is finished with the task or needs more input or action from the user in order to proceed.
-If the assistant is finished with the task you MUST include <finish></finish> in your response.
-IMPORTANT: Execute code using <execute_ipython>, <execute_bash>, or <execute_browse> whenever possible.
-When handling files, try to use full paths and pwd to avoid errors.
-"""
-
-
-# ======= EXAMPLE MESSAGE =======
-EXAMPLES = """
---- START OF EXAMPLE ---
-
-USER: Create a list of numbers from 1 to 10, and display them in a web page at port 5000.
-
-ASSISTANT:
-Sure! Let me create a Python file `app.py`:
-<execute_ipython>
-create_file('app.py')
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[File: /workspace/app.py (1 lines total)]
-(this is the beginning of the file)
-1|
-(this is the end of the file)
-[File app.py created.]
-
-ASSISTANT:
-Now I will write the Python code for starting a web server and save it to the file `app.py`:
-<execute_ipython>
-EDITED_CODE=\"\"\"from flask import Flask
-app = Flask(__name__)
-
-@app.route('/')
-def index():
-    numbers = list(range(1, 11))
-    return str(numbers)
-
-if __name__ == '__main__':
-    app.run(port=5000)\"\"\"
-
-insert_content_at_line(
-  'app.py',
-  1,
-  EDITED_CODE,
-)
-</execute_ipython>
-
-USER:
-OBSERVATION:
-(this is the beginning of the file)
-1|from flask import Flask
-2|app = Flask(__name__)
-3|
-4|@app.route('/')
-5|def index():
-6|    numbers = list(range(1, 11))
-7|    return str(numbers)
-8|
-9|if __name__ == '__main__':
-10|    app.run(port=5000)
-(this is the end of the file)
-[File updated (edited at line 1). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
-
-ASSISTANT:
-I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you:
-<execute_bash>
-python3 app.py > server.log 2>&1 &
-</execute_bash>
-
-USER:
-OBSERVATION:
-[1] 121[1]+  Exit 1                  python3 app.py > server.log 2>&1
-
-ASSISTANT: Looks like the server is running with PID 121 then crashed. Let me check the server log:
-<execute_bash>
-cat server.log
-</execute_bash>
-
-USER:
-OBSERVATION:
-Traceback (most recent call last):
-  File "/workspace/app.py", line 2, in <module>
-    from flask import Flask
-ModuleNotFoundError: No module named 'flask'
-
-ASSISTANT:
-It seems that Flask is not installed. Let me install Flask for you:
-<execute_bash>
-pip install flask
-</execute_bash>
-
-USER:
-OBSERVATION:
-Defaulting to user installation because normal site-packages is not writeable
-Collecting flask
-  Using cached flask-3.0.3-py3-none-any.whl (101 kB)
-Collecting blinker>=1.6.2
-  Using cached blinker-1.7.0-py3-none-any.whl (13 kB)
-Collecting Werkzeug>=3.0.0
-  Using cached werkzeug-3.0.2-py3-none-any.whl (226 kB)
-Collecting click>=8.1.3
-  Using cached click-8.1.7-py3-none-any.whl (97 kB)
-Collecting itsdangerous>=2.1.2
-  Using cached itsdangerous-2.2.0-py3-none-any.whl (16 kB)
-Requirement already satisfied: Jinja2>=3.1.2 in /home/opendevin/.local/lib/python3.10/site-packages (from flask) (3.1.3)
-Requirement already satisfied: MarkupSafe>=2.0 in /home/opendevin/.local/lib/python3.10/site-packages (from Jinja2>=3.1.2->flask) (2.1.5)
-Installing collected packages: Werkzeug, itsdangerous, click, blinker, flask
-Successfully installed Werkzeug-3.0.2 blinker-1.7.0 click-8.1.7 flask-3.0.3 itsdangerous-2.2.0
-
-ASSISTANT:
-Now that Flask is installed, let me run the Python file again:
-<execute_bash>
-python3 app.py > server.log 2>&1 &
-</execute_bash>
-
-USER:
-OBSERVATION:
-[1] 124
-
-ASSISTANT:
-Let me check the server log again:
-<execute_bash>
-cat server.log
-</execute_bash>
-
-USER:
-OBSERVATION:
-* Serving Flask app 'app'
- * Debug mode: off
-WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
- * Running on http://127.0.0.1:5000
-Press CTRL+C to quit
-
-ASSISTANT:
-The server is running on port 5000 with PID 124. You can access the list of numbers by visiting http://127.0.0.1:5000. If you have any further questions, feel free to ask!
-
-USER: Now browse the newly started server's homepage and show me the content.
-
-ASSISTANT:
-Sure! Let me browse the server's homepage at http://127.0.0.1:5000:
-<execute_browse>
-Get the content on "http://127.0.0.1:5000"
-</execute_browse>
-
-USER:
-OBSERVATION:
-[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
-
-ASSISTANT:
-The content of the server's homepage is "[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]". If you have any further questions, feel free to ask!
-
-USER: Now kill the server, make it display the numbers in a table format.
-
-ASSISTANT:
-Sure! Let me stop the server first:
-<execute_bash>
-kill 124
-</execute_bash>
-
-USER:
-OBSERVATION:
-[1]+  Terminated              python3 app.py > server.log 2>&1
-
-ASSISTANT:
-The server has been stopped. Let me open the Python file and modify it.
-<execute_ipython>
-open_file('app.py')
-</execute_ipython>
-
-USER:
-[File: /workspace/app.py (10 lines total)]
-(this is the beginning of the file)
-1|from flask import Flask
-2|app = Flask(__name__)
-3|
-4|@app.route('/')
-5|def index():
-6|    numbers = list(range(1, 11))
-7|    return str(numbers)
-8|
-9|if __name__ == '__main__':
-10|    app.run(port=5000)
-(this is the end of the file)
-
-ASSISTANT:
-I should edit the file to display the numbers in a table format. I should include correct indentation. Let me update the file:
-<execute_ipython>
-edit_file_by_replace(
-  'app.py',
-  to_replace="    return str(numbers)",
-  new_content="    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'",
-)
-</execute_ipython>
-
-USER:
-Observation:
-[File: /workspace/app.py (10 lines total after edit)]
-(this is the beginning of the file)
-1|from flask import Flask
-2|app = Flask(__name__)
-3|
-4|@app.route('/')
-5|def index():
-6|    numbers = list(range(1, 11))
-7|    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
-8|
-9|if __name__ == '__main__':
-10|    app.run(port=5000)
-(this is the end of the file)
-[File updated (edited at line 7). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
-
-ASSISTANT:
-Running the updated file:
-<execute_bash>
-python3 app.py > server.log 2>&1 &
-</execute_bash>
-
-USER:
-Observation:
-[1] 126
-
-ASSISTANT:
-The server is running on port 5000 with PID 126. You can access the list of numbers in a table format by visiting http://127.0.0.1:5000. Let me know if you have any further requests!
-<finish></finish>
-
---- END OF EXAMPLE ---
-"""
-
-INVALID_INPUT_MESSAGE = (
-    "I don't understand your input. \n"
-    'For bash commands, use <execute_bash> YOUR_COMMAND </execute_bash>.\n'
-    'For Python code, use <execute_ipython> YOUR_CODE </execute_ipython>.\n'
-    'For browsing, use <execute_browse> YOUR_COMMAND </execute_browse>.\n'
-)

agenthub/codeact_swe_agent/README.md

@@ -1,7 +0,0 @@
-# CodeAct (SWE Edit Specialized)
-
-This agent is an adaptation of the original [SWE Agent](https://swe-agent.com/) based on CodeAct using the `agentskills` library of OpenDevin.
-
-Its intended use is **solving GitHub issues**.
-
-It removes web-browsing and GitHub capability from the original CodeAct agent to avoid confusion to the agent.

agenthub/codeact_swe_agent/__init__.py

@@ -1,5 +0,0 @@
-from opendevin.controller.agent import Agent
-
-from .codeact_swe_agent import CodeActSWEAgent
-
-Agent.register('CodeActSWEAgent', CodeActSWEAgent)

agenthub/codeact_swe_agent/action_parser.py

@@ -1,110 +0,0 @@
-import re
-
-from opendevin.controller.action_parser import ActionParser
-from opendevin.events.action import (
-    Action,
-    AgentFinishAction,
-    CmdRunAction,
-    IPythonRunCellAction,
-    MessageAction,
-)
-
-
-class CodeActSWEActionParserFinish(ActionParser):
-    """Parser action:
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(
-        self,
-    ):
-        self.finish_command = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.finish_command = re.search(r'<finish>.*</finish>', action_str, re.DOTALL)
-        return self.finish_command is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.finish_command is not None
-        ), 'self.finish_command should not be None when parse is called'
-        thought = action_str.replace(self.finish_command.group(0), '').strip()
-        return AgentFinishAction(thought=thought)
-
-
-class CodeActSWEActionParserCmdRun(ActionParser):
-    """Parser action:
-    - CmdRunAction(command) - bash command to run
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(
-        self,
-    ):
-        self.bash_command = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.bash_command = re.search(
-            r'<execute_bash>(.*?)</execute_bash>', action_str, re.DOTALL
-        )
-        return self.bash_command is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.bash_command is not None
-        ), 'self.bash_command should not be None when parse is called'
-        thought = action_str.replace(self.bash_command.group(0), '').strip()
-        # a command was found
-        command_group = self.bash_command.group(1).strip()
-        if command_group.strip() == 'exit':
-            return AgentFinishAction()
-        return CmdRunAction(command=command_group, thought=thought)
-
-
-class CodeActSWEActionParserIPythonRunCell(ActionParser):
-    """Parser action:
-    - IPythonRunCellAction(code) - IPython code to run
-    """
-
-    def __init__(
-        self,
-    ):
-        self.python_code = None
-        self.jupyter_kernel_init_code: str = 'from agentskills import *'
-
-    def check_condition(self, action_str: str) -> bool:
-        self.python_code = re.search(
-            r'<execute_ipython>(.*?)</execute_ipython>', action_str, re.DOTALL
-        )
-        return self.python_code is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.python_code is not None
-        ), 'self.python_code should not be None when parse is called'
-        code_group = self.python_code.group(1).strip()
-        thought = action_str.replace(self.python_code.group(0), '').strip()
-        return IPythonRunCellAction(
-            code=code_group,
-            thought=thought,
-            kernel_init_code=self.jupyter_kernel_init_code,
-        )
-
-
-class CodeActSWEActionParserMessage(ActionParser):
-    """Parser action:
-    - MessageAction(content) - Message action to run (e.g. ask for clarification)
-    """
-
-    def __init__(
-        self,
-    ):
-        pass
-
-    def check_condition(self, action_str: str) -> bool:
-        # We assume the LLM is GOOD enough that when it returns pure natural language
-        # it wants to talk to the user
-        return True
-
-    def parse(self, action_str: str) -> Action:
-        return MessageAction(content=action_str, wait_for_response=True)

agenthub/codeact_swe_agent/codeact_swe_agent.py

@@ -1,196 +0,0 @@
-from agenthub.codeact_swe_agent.prompt import (
-    COMMAND_DOCS,
-    SWE_EXAMPLE,
-    SYSTEM_PREFIX,
-    SYSTEM_SUFFIX,
-)
-from agenthub.codeact_swe_agent.response_parser import CodeActSWEResponseParser
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.events.action import (
-    Action,
-    AgentFinishAction,
-    CmdRunAction,
-    IPythonRunCellAction,
-    MessageAction,
-)
-from opendevin.events.observation import (
-    CmdOutputObservation,
-    IPythonRunCellObservation,
-)
-from opendevin.events.observation.observation import Observation
-from opendevin.events.serialization.event import truncate_content
-from opendevin.llm.llm import LLM
-from opendevin.runtime.plugins import (
-    AgentSkillsRequirement,
-    JupyterRequirement,
-    PluginRequirement,
-)
-from opendevin.runtime.tools import RuntimeTool
-
-
-def get_system_message() -> str:
-    return f'{SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
-
-
-def get_in_context_example() -> str:
-    return SWE_EXAMPLE
-
-
-class CodeActSWEAgent(Agent):
-    VERSION = '1.6'
-    """
-    This agent is an adaptation of the original [SWE Agent](https://swe-agent.com/) based on CodeAct 1.5 using the `agentskills` library of OpenDevin.
-
-    It is intended use is **solving Github issues**.
-
-    It removes web-browsing and Github capability from the original CodeAct agent to avoid confusion to the agent.
-    """
-
-    sandbox_plugins: list[PluginRequirement] = [
-        # NOTE: AgentSkillsRequirement need to go before JupyterRequirement, since
-        # AgentSkillsRequirement provides a lot of Python functions,
-        # and it needs to be initialized before Jupyter for Jupyter to use those functions.
-        AgentSkillsRequirement(),
-        JupyterRequirement(),
-    ]
-    runtime_tools: list[RuntimeTool] = []
-
-    system_message: str = get_system_message()
-    in_context_example: str = f"Here is an example of how you can interact with the environment for task solving:\n{get_in_context_example()}\n\nNOW, LET'S START!"
-
-    response_parser = CodeActSWEResponseParser()
-
-    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.reset()
-
-    def action_to_str(self, action: Action) -> str:
-        if isinstance(action, CmdRunAction):
-            return (
-                f'{action.thought}\n<execute_bash>\n{action.command}\n</execute_bash>'
-            )
-        elif isinstance(action, IPythonRunCellAction):
-            return f'{action.thought}\n<execute_ipython>\n{action.code}\n</execute_ipython>'
-        elif isinstance(action, MessageAction):
-            return action.content
-        return ''
-
-    def get_action_message(self, action: Action) -> dict[str, str] | None:
-        if (
-            isinstance(action, CmdRunAction)
-            or isinstance(action, IPythonRunCellAction)
-            or isinstance(action, MessageAction)
-        ):
-            return {
-                'role': 'user' if action.source == 'user' else 'assistant',
-                'content': self.action_to_str(action),
-            }
-        return None
-
-    def get_observation_message(self, obs: Observation) -> dict[str, str] | None:
-        max_message_chars = self.llm.config.max_message_chars
-        if isinstance(obs, CmdOutputObservation):
-            content = 'OBSERVATION:\n' + truncate_content(
-                obs.content, max_message_chars
-            )
-            content += (
-                f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]'
-            )
-            return {'role': 'user', 'content': content}
-        elif isinstance(obs, IPythonRunCellObservation):
-            content = 'OBSERVATION:\n' + obs.content
-            # replace base64 images with a placeholder
-            splitted = content.split('\n')
-            for i, line in enumerate(splitted):
-                if '![image](data:image/png;base64,' in line:
-                    splitted[i] = (
-                        '![image](data:image/png;base64, ...) already displayed to user'
-                    )
-            content = '\n'.join(splitted)
-            content = truncate_content(content, max_message_chars)
-            return {'role': 'user', 'content': content}
-        return None
-
-    def reset(self) -> None:
-        """Resets the CodeAct Agent."""
-        super().reset()
-
-    def step(self, state: State) -> Action:
-        """Performs one step using the CodeAct 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) - bash command to run
-        - IPythonRunCellAction(code) - IPython code to run
-        - MessageAction(content) - Message action to run (e.g. ask for clarification)
-        - AgentFinishAction() - end the interaction
-        """
-        # if we're done, go back
-        latest_user_message = state.history.get_last_user_message()
-        if latest_user_message and latest_user_message.strip() == '/exit':
-            return AgentFinishAction()
-
-        # prepare what we want to send to the LLM
-        messages: list[dict[str, str]] = self._get_messages(state)
-
-        response = self.llm.completion(
-            messages=messages,
-            stop=[
-                '</execute_ipython>',
-                '</execute_bash>',
-            ],
-            temperature=0.0,
-        )
-
-        return self.response_parser.parse(response)
-
-    def _get_messages(self, state: State) -> list[dict[str, str]]:
-        messages = [
-            {'role': 'system', 'content': self.system_message},
-            {'role': 'user', 'content': self.in_context_example},
-        ]
-
-        for event in state.history.get_events():
-            # create a regular message from an event
-            if isinstance(event, Action):
-                message = self.get_action_message(event)
-            elif isinstance(event, Observation):
-                message = self.get_observation_message(event)
-            else:
-                raise ValueError(f'Unknown event type: {type(event)}')
-
-            # add regular message
-            if message:
-                # handle error if the message is the SAME role as the previous message
-                # litellm.exceptions.BadRequestError: litellm.BadRequestError: OpenAIException - Error code: 400 - {'detail': 'Only supports u/a/u/a/u...'}
-                # there should not have two consecutive messages from the same role
-                if messages and messages[-1]['role'] == message['role']:
-                    messages[-1]['content'] += '\n\n' + message['content']
-                else:
-                    messages.append(message)
-
-        # the latest user message is important:
-        # we want to remind the agent of the environment constraints
-        latest_user_message = next(
-            (m for m in reversed(messages) if m['role'] == 'user'), None
-        )
-
-        # add a reminder to the prompt
-        if latest_user_message:
-            latest_user_message['content'] += (
-                f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task.'
-            )
-
-        return messages

agenthub/codeact_swe_agent/prompt.py

@@ -1,455 +0,0 @@
-from opendevin.runtime.plugins import AgentSkillsRequirement
-
-_AGENT_SKILLS_DOCS = AgentSkillsRequirement.documentation
-
-COMMAND_DOCS = (
-    '\nApart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:\n'
-    f'{_AGENT_SKILLS_DOCS}'
-    "Please note that THE `edit_file` FUNCTION REQUIRES PROPER INDENTATION. If the assistant would like to add the line '        print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run."
-)
-
-# ======= SYSTEM MESSAGE =======
-MINIMAL_SYSTEM_PREFIX = """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
-The assistant can interact with an interactive Python (Jupyter Notebook) environment and receive the corresponding output when needed. The code should be enclosed using "<execute_ipython>" tag, for example:
-<execute_ipython>
-print("Hello World!")
-</execute_ipython>
-The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
-For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
-"""
-
-PIP_INSTALL_PREFIX = """The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them."""
-
-SYSTEM_PREFIX = MINIMAL_SYSTEM_PREFIX + PIP_INSTALL_PREFIX
-
-SYSTEM_SUFFIX = """The assistant's response should be concise.
-The assistant should include ONLY ONE <execute_ipython> or <execute_bash> in every one of the responses, unless the assistant is finished with the task or need more input or action from the user in order to proceed.
-IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
-"""
-
-SWE_EXAMPLE = """
---- START OF EXAMPLE ---
-
-USER: We are currently solving the following issue within our repository. Here is the issue text:
---- BEGIN ISSUE ---
-TimeDelta serialization precision
-Hi there!
-
-I just found quite strange behaviour of `TimeDelta` field serialization
-
-```python3
-from marshmallow.fields import TimeDelta
-from datetime import timedelta
-
-td_field = TimeDelta(precision="milliseconds")
-
-obj = dict()
-obj["td_field"] = timedelta(milliseconds=345)
-
-print(td_field.serialize("td_field", obj))
-```
-
-Output of this snippet is `344`, but it seems that `345` is correct.
-
-Looks like a rounding issue here: https://github.com/marshmallow-code/marshmallow/blob/dev/src/marshmallow/fields.py#L1474
---- END ISSUE ---
-
-[Current directory: /workspace/marshmallow-code__marshmallow]
-
-ASSISTANT:
-Let's first start by reproducing the results of the issue. The issue includes some example code for reproduction, which we can use. We'll create a new file called `reproduce.py` and paste the example code into it.
-<execute_ipython>
-create_file('/workspace/marshmallow-code__marshmallow/reproduce.py')
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[File: /workspace/marshmallow-code__marshmallow/reproduce.py (1 lines total)]
-1|
-[File /workspace/marshmallow-code__marshmallow/reproduce.py created.]
-
-ASSISTANT:
-Now let's paste in the example code from the issue.
-<execute_ipython>
-EDITED_CODE = \"\"\"from marshmallow.fields import TimeDelta
-from datetime import timedelta
-
-td_field = TimeDelta(precision="milliseconds")
-
-obj = dict()
-obj["td_field"] = timedelta(milliseconds=345)
-
-print(td_field.serialize("td_field", obj))
-\"\"\"
-edit_file(start=1, end=1, content=EDITED_CODE)
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[File: /workspace/marshmallow-code__marshmallow/reproduce.py (9 lines total)]
-1|from marshmallow.fields import TimeDelta
-2|from datetime import timedelta
-3|
-4|td_field = TimeDelta(precision="milliseconds")
-5|
-6|obj = dict()
-7|obj["td_field"] = timedelta(milliseconds=345)
-8|
-9|print(td_field.serialize("td_field", obj))
-[File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
-
-ASSISTANT:
-Now let's run the code to see if we see the same output as the issue.
-<execute_bash>
-python reproduce.py
-</execute_bash>
-
-USER:
-OBSERVATION:
-344
-
-ASSISTANT:
-We are indeed seeing the same output as the issue. The issue suggests that we should look at line 1474 of the `fields.py` file to see if there is a rounding issue. Let's open the `fields.py` file and navigate to line 1474 to see the relevant code. First we should find the `fields.py` file in the repository. It is likely to be in the `src/marshmallow` directory, but we should check to be sure.
-<execute_bash>
-ls -F
-</execute_bash>
-
-USER:
-OBSERVATION:
-AUTHORS.rst
-CHANGELOG.rst
-CODE_OF_CONDUCT.md
-CONTRIBUTING.rst
-LICENSE
-MANIFEST.in
-NOTICE
-README.rst
-RELEASING.md
-azure-pipelines.yml
-docs/
-examples/
-performance/
-pyproject.toml
-reproduce.py
-setup.cfg
-setup.py
-src/
-tests/
-tox.ini
-
-ASSISTANT:
-It looks like the `src` directory is present, which suggests that the `fields.py` file is likely to be in the `src` directory. Let's use find_file to see where it is.
-<execute_ipython>
-find_file("fields.py", "/workspace/marshmallow-code__marshmallow/src")
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[Found 1 matches for "fields.py" in /workspace/marshmallow-code__marshmallow/src]
-/workspace/marshmallow-code__marshmallow/src/marshmallow/fields.py
-
-ASSISTANT:
-It looks like the `fields.py` file is present in the `./src/marshmallow/` directory. The issue also points to a specific URL with line number 1474. We should navigate to that line in fields.py to see the relevant code for the `TimeDelta` serialization.
-<execute_ipython>
-open_file("/workspace/marshmallow-code__marshmallow/src/marshmallow/fields.py", 1474)
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[File: /workspace/marshmallow-code__marshmallow/src/marshmallow/fields.py (1997 lines total)]
-(1458 more lines above)
-1459|            self.WEEKS,
-1460|        )
-1461|
-1462|        if precision not in units:
-1463|            msg = 'The precision must be {} or "{}".'.format(
-1464|                ", ".join([f'"{each}"' for each in units[:-1]]), units[-1]
-1465|            )
-1466|            raise ValueError(msg)
-1467|
-1468|        self.precision = precision
-1469|        super().__init__(**kwargs)
-1470|
-1471|    def _serialize(self, value, attr, obj, **kwargs):
-1472|        if value is None:
-1473|            return None
-1474|        base_unit = dt.timedelta(**{self.precision: 1})
-1475|        return int(value.total_seconds() / base_unit.total_seconds())
-1476|
-1477|    def _deserialize(self, value, attr, data, **kwargs):
-1478|        try:
-1479|            value = int(value)
-1480|        except (TypeError, ValueError) as error:
-1481|            raise self.make_error("invalid") from error
-1482|
-1483|        kwargs = {self.precision: value}
-1484|
-1485|        try:
-1486|            return dt.timedelta(**kwargs)
-1487|        except OverflowError as error:
-1488|            raise self.make_error("invalid") from error
-1489|
-1490|
-1491|class Mapping(Field):
-1492|    \"\"\"An abstract class for objects with key-value pairs.
-1493|
-1494|    :param keys: A field class or instance for dict keys.
-1495|    :param values: A field class or instance for dict values.
-1496|    :param kwargs: The same keyword arguments that :class:`Field` receives.
-1497|
-1498|    .. note::
-1499|        When the structure of nested data is not known, you may omit the
-1500|        `keys` and `values` arguments to prevent content validation.
-1501|
-1502|    .. versionadded:: 3.0.0rc4
-1503|    \"\"\"
-1504|
-1505|    mapping_type = dict
-1506|
-1507|    #: Default error messages.
-1508|    default_error_messages = {"invalid": "Not a valid mapping type."}
-1509|
-1510|    def __init__(
-1511|        self,
-1512|        keys: typing.Optional[typing.Union[Field, type]] = None,
-1513|        values: typing.Optional[typing.Union[Field, type]] = None,
-1514|        **kwargs,
-1515|    ):
-1516|        super().__init__(**kwargs)
-1517|        if keys is None:
-1518|            self.key_field = None
-1519|        else:
-1520|            try:
-1521|                self.key_field = resolve_field_instance(keys)
-1522|            except FieldInstanceResolutionError as error:
-1523|                raise ValueError(
-1524|                    '"keys" must be a subclass or instance of '
-1525|                    "marshmallow.base.FieldABC."
-1526|                ) from error
-1527|
-1528|        if values is None:
-1529|            self.value_field = None
-1530|        else:
-1531|            try:
-1532|                self.value_field = resolve_field_instance(values)
-1533|            except FieldInstanceResolutionError as error:
-1534|                raise ValueError(
-1535|                    '"values" must be a subclass or instance of '
-1536|                    "marshmallow.base.FieldABC."
-1537|                ) from error
-1538|            if isinstance(self.value_field, Nested):
-1539|                self.only = self.value_field.only
-1540|                self.exclude = self.value_field.exclude
-1541|
-1542|    def _bind_to_schema(self, field_name, schema):
-1543|        super()._bind_to_schema(field_name, schema)
-1544|        if self.value_field:
-1545|            self.value_field = copy.deepcopy(self.value_field)
-1546|            self.value_field._bind_to_schema(field_name, self)
-1547|        if isinstance(self.value_field, Nested):
-1548|            self.value_field.only = self.only
-1549|            self.value_field.exclude = self.exclude
-1550|        if self.key_field:
-1551|            self.key_field = copy.deepcopy(self.key_field)
-1552|            self.key_field._bind_to_schema(field_name, self)
-1553|
-1554|    def _serialize(self, value, attr, obj, **kwargs):
-1555|        if value is None:
-1556|            return None
-1557|        if not self.value_field and not self.key_field:
-1558|            return self.mapping_type(value)
-(439 more lines below)
-
-ASSISTANT:
-We are now looking at the relevant section of the `fields.py` file where the `TimeDelta` serialization occurs. The issue suggests that there is a rounding problem near line 1474. The current implementation uses integer division, which truncates the decimal part and can lead to incorrect rounding on line 1475. To fix this issue, we should ensure that the division results in a float, and then round the result to the nearest integer before converting it to an int. This should preserve the milliseconds precision as expected. Let's make the necessary edit to the code.
-<execute_ipython>
-edit_file(start=1475, end=1475, content="return int(round(value.total_seconds() / base_unit.total_seconds()))  # round to nearest int")
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[Your proposed edit has introduced new syntax error(s). Please understand the errors and retry your edit command.]
-
-ERRORS:
-- E999 IndentationError: unexpected indent
-
-[This is how your edit would have looked if applied]
--------------------------------------------------
-[File: /marshmallow-code__marshmallow/src/marshmallow/fields.py (1997 lines total)]
-(1468 more lines above)
-1469|        super().__init__(**kwargs)
-1470|
-1471|    def _serialize(self, value, attr, obj, **kwargs):
-1472|        if value is None:
-1473|            return None
-1474|        base_unit = dt.timedelta(**{self.precision: 1})
-1475|return int(round(value.total_seconds() / base_unit.total_seconds()))  # round to nearest int
-1476|
-1477|    def _deserialize(self, value, attr, data, **kwargs):
-1478|        try:
-1479|            value = int(value)
-(518 more lines below)
--------------------------------------------------
-
-[This is the original code before your edit]
--------------------------------------------------
-[File: /marshmallow-code__marshmallow/src/marshmallow/fields.py (1997 lines total)]
-(1469 more lines above)
-1470|
-1471|    def _serialize(self, value, attr, obj, **kwargs):
-1472|        if value is None:
-1473|            return None
-1474|        base_unit = dt.timedelta(**{self.precision: 1})
-1475|        return int(value.total_seconds() / base_unit.total_seconds())
-1476|
-1477|    def _deserialize(self, value, attr, data, **kwargs):
-1478|        try:
-1479|            value = int(value)
-1480|        except (TypeError, ValueError) as error:
-(517 more lines below)
--------------------------------------------------
-Your changes have NOT been applied. Please fix your edit command and try again.
-You either need to 1) Specify the correct start/end line arguments or 2) Correct your edit code.
-DO NOT re-run the same failed edit command. Running it again will lead to the same error.
-
-ASSISTANT:
-My edit command did not use the proper indentation, I will fix my syntax in this follow up edit command.
-<execute_ipython>
-EDITED_CODE="        return int(round(value.total_seconds() / base_unit.total_seconds()))  # round to nearest int"
-edit_file(start=1475, end=1475, content=EDITED_CODE)
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[File: /marshmallow-code__marshmallow/src/marshmallow/fields.py (1997 lines total)]
-(1424 more lines above)
-1425|
-1426|    :param precision: Influences how the integer is interpreted during
-1427|        (de)serialization. Must be 'days', 'seconds', 'microseconds',
-1428|        'milliseconds', 'minutes', 'hours' or 'weeks'.
-1429|    :param kwargs: The same keyword arguments that :class:`Field` receives.
-1430|
-1431|    .. versionchanged:: 2.0.0
-1432|        Always serializes to an integer value to avoid rounding errors.
-1433|        Add `precision` parameter.
-1434|    \"\"\"
-1435|
-1436|    DAYS = "days"
-1437|    SECONDS = "seconds"
-1438|    MICROSECONDS = "microseconds"
-1439|    MILLISECONDS = "milliseconds"
-1440|    MINUTES = "minutes"
-1441|    HOURS = "hours"
-1442|    WEEKS = "weeks"
-1443|
-1444|    #: Default error messages.
-1445|    default_error_messages = {
-1446|        "invalid": "Not a valid period of time.",
-1447|        "format": "{input!r} cannot be formatted as a timedelta.",
-1448|    }
-1449|
-1450|    def __init__(self, precision: str = SECONDS, **kwargs):
-1451|        precision = precision.lower()
-1452|        units = (
-1453|            self.DAYS,
-1454|            self.SECONDS,
-1455|            self.MICROSECONDS,
-1456|            self.MILLISECONDS,
-1457|            self.MINUTES,
-1458|            self.HOURS,
-1459|            self.WEEKS,
-1460|        )
-1461|
-1462|        if precision not in units:
-1463|            msg = 'The precision must be {} or "{}".'.format(
-1464|                ", ".join([f'"{each}"' for each in units[:-1]]), units[-1]
-1465|            )
-1466|            raise ValueError(msg)
-1467|
-1468|        self.precision = precision
-1469|        super().__init__(**kwargs)
-1470|
-1471|    def _serialize(self, value, attr, obj, **kwargs):
-1472|        if value is None:
-1473|            return None
-1474|        base_unit = dt.timedelta(**{self.precision: 1})
-1475|        return int(round(value.total_seconds() / base_unit.total_seconds()))  # round to nearest int
-1476|
-1477|    def _deserialize(self, value, attr, data, **kwargs):
-1478|        try:
-1479|            value = int(value)
-1480|        except (TypeError, ValueError) as error:
-1481|            raise self.make_error("invalid") from error
-1482|
-1483|        kwargs = {self.precision: value}
-1484|
-1485|        try:
-1486|            return dt.timedelta(**kwargs)
-1487|        except OverflowError as error:
-1488|            raise self.make_error("invalid") from error
-1489|
-1490|
-1491|class Mapping(Field):
-1492|    \"\"\"An abstract class for objects with key-value pairs.
-1493|
-1494|    :param keys: A field class or instance for dict keys.
-1495|    :param values: A field class or instance for dict values.
-1496|    :param kwargs: The same keyword arguments that :class:`Field` receives.
-1497|
-1498|    .. note::
-1499|        When the structure of nested data is not known, you may omit the
-1500|        `keys` and `values` arguments to prevent content validation.
-1501|
-1502|    .. versionadded:: 3.0.0rc4
-1503|    \"\"\"
-1504|
-1505|    mapping_type = dict
-1506|
-1507|    #: Default error messages.
-1508|    default_error_messages = {"invalid": "Not a valid mapping type."}
-1509|
-1510|    def __init__(
-1511|        self,
-1512|        keys: typing.Optional[typing.Union[Field, type]] = None,
-1513|        values: typing.Optional[typing.Union[Field, type]] = None,
-1514|        **kwargs,
-1515|    ):
-1516|        super().__init__(**kwargs)
-1517|        if keys is None:
-1518|            self.key_field = None
-1519|        else:
-1520|            try:
-1521|                self.key_field = resolve_field_instance(keys)
-1522|            except FieldInstanceResolutionError as error:
-1523|                raise ValueError(
-1524|                    '"keys" must be a subclass or instance of '
-(473 more lines below)
-[File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
-
-ASSISTANT:
-The code has been updated to use the `round` function, which should fix the rounding issue. Before submitting the changes, it would be prudent to run the reproduce.py code again to ensure that this change has the desired effect. I see that "Current directory" is still `/marshmallow-code__marshmallow`, so we can just run `reproduce.py` directly.
-<execute_bash>
-python reproduce.py
-</execute_bash>
-
-USER:
-OBSERVATION:
-345
-
-ASSISTANT:
-The output has changed from 344 to 345, which suggests that the rounding issue has been fixed. Let's remove the reproduce.py file since it is no longer needed.
-<execute_bash>
-rm reproduce.py
-</execute_bash>
-
-USER:
-OBSERVATION:
-
-ASSISTANT:
-rm doesn't have any output when it deletes successfully, so that must have worked. Now that we have fixed the issue, we can exit the current task.
-<execute_bash>
-exit
-</execute_bash>
-
---- END OF EXAMPLE ---
-"""

agenthub/codeact_swe_agent/response_parser.py

@@ -1,46 +0,0 @@
-from agenthub.codeact_swe_agent.action_parser import (
-    CodeActSWEActionParserCmdRun,
-    CodeActSWEActionParserFinish,
-    CodeActSWEActionParserIPythonRunCell,
-    CodeActSWEActionParserMessage,
-)
-from opendevin.controller.action_parser import ResponseParser
-from opendevin.events.action import Action
-
-
-class CodeActSWEResponseParser(ResponseParser):
-    """Parser action:
-    - CmdRunAction(command) - bash command to run
-    - IPythonRunCellAction(code) - IPython code to run
-    - MessageAction(content) - Message action to run (e.g. ask for clarification)
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(self):
-        # Need pay attention to the item order in self.action_parsers
-        super().__init__()
-        self.action_parsers = [
-            CodeActSWEActionParserFinish(),
-            CodeActSWEActionParserCmdRun(),
-            CodeActSWEActionParserIPythonRunCell(),
-        ]
-        self.default_parser = CodeActSWEActionParserMessage()
-
-    def parse(self, response: str) -> Action:
-        action_str = self.parse_response(response)
-        return self.parse_action(action_str)
-
-    def parse_response(self, response) -> str:
-        action = response.choices[0].message.content
-        if action is None:
-            return ''
-        for lang in ['bash', 'ipython']:
-            if f'<execute_{lang}>' in action and f'</execute_{lang}>' not in action:
-                action += f'</execute_{lang}>'
-        return action
-
-    def parse_action(self, action_str: str) -> Action:
-        for action_parser in self.action_parsers:
-            if action_parser.check_condition(action_str):
-                return action_parser.parse(action_str)
-        return self.default_parser.parse(action_str)

agenthub/delegator_agent/__init__.py

@@ -1,5 +0,0 @@
-from opendevin.controller.agent import Agent
-
-from .agent import DelegatorAgent
-
-Agent.register('DelegatorAgent', DelegatorAgent)

agenthub/delegator_agent/agent.py

@@ -1,82 +0,0 @@
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.events.action import Action, AgentDelegateAction, AgentFinishAction
-from opendevin.events.observation import AgentDelegateObservation
-from opendevin.llm.llm import LLM
-
-
-class DelegatorAgent(Agent):
-    VERSION = '1.0'
-    """
-    The Delegator Agent is responsible for delegating tasks to other agents based on the current task.
-    """
-
-    current_delegate: str = ''
-
-    def __init__(self, llm: LLM):
-        """Initialize the Delegator 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, delegates the task to the next agent in the pipeline.
-
-        Parameters:
-        - state (State): The current state given the previous actions and observations
-
-        Returns:
-        - AgentFinishAction: If the last state was 'completed', 'verified', or 'abandoned'
-        - AgentDelegateAction: The next agent to delegate the task to
-        """
-        if self.current_delegate == '':
-            self.current_delegate = 'study'
-            task = state.get_current_user_intent()
-            return AgentDelegateAction(
-                agent='StudyRepoForTaskAgent', inputs={'task': task}
-            )
-
-        # last observation in history should be from the delegate
-        last_observation = state.history.get_last_observation()
-
-        if not isinstance(last_observation, AgentDelegateObservation):
-            raise Exception('Last observation is not an AgentDelegateObservation')
-
-        goal = state.get_current_user_intent()
-        if self.current_delegate == 'study':
-            self.current_delegate = 'coder'
-            return AgentDelegateAction(
-                agent='CoderAgent',
-                inputs={
-                    'task': goal,
-                    'summary': last_observation.outputs['summary'],
-                },
-            )
-        elif self.current_delegate == 'coder':
-            self.current_delegate = 'verifier'
-            return AgentDelegateAction(
-                agent='VerifierAgent',
-                inputs={
-                    'task': goal,
-                },
-            )
-        elif self.current_delegate == 'verifier':
-            if (
-                'completed' in last_observation.outputs
-                and last_observation.outputs['completed']
-            ):
-                return AgentFinishAction()
-            else:
-                self.current_delegate = 'coder'
-                return AgentDelegateAction(
-                    agent='CoderAgent',
-                    inputs={
-                        'task': goal,
-                        'summary': last_observation.outputs['summary'],
-                    },
-                )
-        else:
-            raise Exception('Invalid delegate state')

agenthub/dummy_agent/__init__.py

@@ -1,5 +0,0 @@
-from opendevin.controller.agent import Agent
-
-from .agent import DummyAgent
-
-Agent.register('DummyAgent', DummyAgent)

agenthub/dummy_agent/agent.py

@@ -1,216 +0,0 @@
-from typing import TypedDict, Union
-
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.core.schema import AgentState
-from opendevin.events.action import (
-    Action,
-    AddTaskAction,
-    AgentFinishAction,
-    AgentRejectAction,
-    BrowseInteractiveAction,
-    BrowseURLAction,
-    CmdRunAction,
-    FileReadAction,
-    FileWriteAction,
-    MessageAction,
-    ModifyTaskAction,
-)
-from opendevin.events.observation import (
-    AgentStateChangedObservation,
-    CmdOutputObservation,
-    FileReadObservation,
-    FileWriteObservation,
-    NullObservation,
-    Observation,
-)
-from opendevin.events.serialization.event import event_to_dict
-from opendevin.llm.llm import LLM
-
-"""
-FIXME: There are a few problems this surfaced
-* FileWrites seem to add an unintended newline at the end of the file
-* Browser not working
-"""
-
-ActionObs = TypedDict(
-    'ActionObs', {'action': Action, 'observations': list[Observation]}
-)
-
-
-class DummyAgent(Agent):
-    VERSION = '1.0'
-    """
-    The DummyAgent is used for e2e testing. It just sends the same set of actions deterministically,
-    without making any LLM calls.
-    """
-
-    def __init__(self, llm: LLM):
-        super().__init__(llm)
-        self.steps: list[ActionObs] = [
-            {
-                'action': AddTaskAction(
-                    parent='None', goal='check the current directory'
-                ),
-                'observations': [],
-            },
-            {
-                'action': AddTaskAction(parent='0', goal='run ls'),
-                'observations': [],
-            },
-            {
-                'action': ModifyTaskAction(task_id='0', state='in_progress'),
-                'observations': [],
-            },
-            {
-                'action': MessageAction('Time to get started!'),
-                'observations': [],
-            },
-            {
-                'action': CmdRunAction(command='echo "foo"'),
-                'observations': [
-                    CmdOutputObservation(
-                        'foo', command_id=-1, command='echo "foo"', exit_code=0
-                    )
-                ],
-            },
-            {
-                'action': FileWriteAction(
-                    content='echo "Hello, World!"', path='hello.sh'
-                ),
-                'observations': [
-                    FileWriteObservation(
-                        content='echo "Hello, World!"', path='hello.sh'
-                    )
-                ],
-            },
-            {
-                'action': FileReadAction(path='hello.sh'),
-                'observations': [
-                    FileReadObservation('echo "Hello, World!"\n', path='hello.sh')
-                ],
-            },
-            {
-                'action': CmdRunAction(command='bash hello.sh'),
-                'observations': [
-                    CmdOutputObservation(
-                        'bash: hello.sh: No such file or directory',
-                        command_id=-1,
-                        command='bash workspace/hello.sh',
-                        exit_code=127,
-                    )
-                ],
-            },
-            {
-                'action': BrowseURLAction(url='https://google.com'),
-                'observations': [
-                    # BrowserOutputObservation('<html><body>Simulated Google page</body></html>',url='https://google.com',screenshot=''),
-                ],
-            },
-            {
-                'action': BrowseInteractiveAction(
-                    browser_actions='goto("https://google.com")'
-                ),
-                'observations': [
-                    # BrowserOutputObservation('<html><body>Simulated Google page after interaction</body></html>',url='https://google.com',screenshot=''),
-                ],
-            },
-            {
-                'action': AgentRejectAction(),
-                'observations': [NullObservation('')],
-            },
-            {
-                'action': AgentFinishAction(
-                    outputs={}, thought='Task completed', action='finish'
-                ),
-                'observations': [AgentStateChangedObservation('', AgentState.FINISHED)],
-            },
-        ]
-
-    def step(self, state: State) -> Action:
-        if state.iteration >= len(self.steps):
-            return AgentFinishAction()
-
-        current_step = self.steps[state.iteration]
-        action = current_step['action']
-
-        # If the action is AddTaskAction or ModifyTaskAction, update the parent ID or task_id
-        if isinstance(action, AddTaskAction):
-            if action.parent == 'None':
-                action.parent = ''  # Root task has no parent
-            elif action.parent == '0':
-                action.parent = state.root_task.id
-            elif action.parent.startswith('0.'):
-                action.parent = f'{state.root_task.id}{action.parent[1:]}'
-        elif isinstance(action, ModifyTaskAction):
-            if action.task_id == '0':
-                action.task_id = state.root_task.id
-            elif action.task_id.startswith('0.'):
-                action.task_id = f'{state.root_task.id}{action.task_id[1:]}'
-            # Ensure the task_id doesn't start with a dot
-            if action.task_id.startswith('.'):
-                action.task_id = action.task_id[1:]
-        elif isinstance(action, (BrowseURLAction, BrowseInteractiveAction)):
-            try:
-                return self.simulate_browser_action(action)
-            except (
-                Exception
-            ):  # This could be a specific exception for browser unavailability
-                return self.handle_browser_unavailable(action)
-
-        if state.iteration > 0:
-            prev_step = self.steps[state.iteration - 1]
-
-            if 'observations' in prev_step and prev_step['observations']:
-                expected_observations = prev_step['observations']
-                hist_events = state.history.get_last_events(len(expected_observations))
-
-                if len(hist_events) < len(expected_observations):
-                    print(
-                        f'Warning: Expected {len(expected_observations)} observations, but got {len(hist_events)}'
-                    )
-
-                for i in range(min(len(expected_observations), len(hist_events))):
-                    hist_obs = event_to_dict(hist_events[i])
-                    expected_obs = event_to_dict(expected_observations[i])
-
-                    # Remove dynamic fields for comparison
-                    for obs in [hist_obs, expected_obs]:
-                        obs.pop('id', None)
-                        obs.pop('timestamp', None)
-                        obs.pop('cause', None)
-                        obs.pop('source', None)
-                        if 'extras' in obs:
-                            obs['extras'].pop('command_id', None)
-
-                    if hist_obs != expected_obs:
-                        print(
-                            f'Warning: Observation mismatch. Expected {expected_obs}, got {hist_obs}'
-                        )
-
-        return action
-
-    def simulate_browser_action(
-        self, action: Union[BrowseURLAction, BrowseInteractiveAction]
-    ) -> Action:
-        # Instead of simulating, we'll reject the browser action
-        return self.handle_browser_unavailable(action)
-
-    def handle_browser_unavailable(
-        self, action: Union[BrowseURLAction, BrowseInteractiveAction]
-    ) -> Action:
-        # Create a message action to inform that browsing is not available
-        message = 'Browser actions are not available in the DummyAgent environment.'
-        if isinstance(action, BrowseURLAction):
-            message += f' Unable to browse URL: {action.url}'
-        elif isinstance(action, BrowseInteractiveAction):
-            message += (
-                f' Unable to perform interactive browsing: {action.browser_actions}'
-            )
-        return MessageAction(content=message)
-
-    async def get_working_directory(self, state: State) -> str:
-        # Implement this method to return the current working directory
-        # This might involve accessing state information or making an async call
-        # For now, we'll return a placeholder value
-        return './workspace'

agenthub/micro/README.md

@@ -1,17 +0,0 @@
-## Introduction
-
-This package contains definitions of micro-agents. A micro-agent is defined
-in the following structure:
-
-```
-[AgentName]
-├── agent.yaml
-└── prompt.md
-```
-
-Note that `prompt.md` could use jinja2 template syntax. During runtime, `prompt.md`
-is loaded and rendered, and used together with `agent.yaml` to initialize a
-micro-agent.
-
-Micro-agents can be used independently. You can also use `ManagerAgent` which knows
-how to coordinate the agents and collaboratively finish a task.

agenthub/micro/_instructions/actions/browse.md

@@ -1,2 +0,0 @@
-* `browse` - opens a web page. Arguments:
-  * `url` - the URL to open

agenthub/micro/_instructions/actions/delegate.md

@@ -1,3 +0,0 @@
-* `delegate` - send a task to another agent from the list provided. Arguments:
-  * `agent` - the agent to which the task is delegated. MUST match a name in the list of agents provided.
-  * `inputs` - a dictionary of input parameters to the agent, as specified in the list

agenthub/micro/_instructions/actions/finish.md

@@ -1,2 +0,0 @@
-* `finish` - if you're absolutely certain that you've completed your task, use the finish action to stop working. Arguments:
-  * `outputs` - a dictionary representing the outputs of your task, if any

agenthub/micro/_instructions/actions/message.md

@@ -1,3 +0,0 @@
-* `message` - make a plan, set a goal, record your thoughts, or ask for more input from the user. Arguments:
-  * `content` - the thought to record
-  * `wait_for_response` - set to `true` to wait for the user to respond before proceeding

agenthub/micro/_instructions/actions/read.md

@@ -1,2 +0,0 @@
-* `read` - reads the content of a file. Arguments:
-  * `path` - the path of the file to read

agenthub/micro/_instructions/actions/reject.md

@@ -1,2 +0,0 @@
-* `reject` - reject the task. Arguments:
-  * `outputs` - a dictionary with only a `reason` attribute

agenthub/micro/_instructions/actions/run.md

@@ -1,2 +0,0 @@
-* `run` - runs a command on the command line in a Linux shell. Arguments:
-  * `command` - the command to run

agenthub/micro/_instructions/actions/write.md

@@ -1,3 +0,0 @@
-* `write` - writes the content to a file. Arguments:
-  * `path` - the path of the file to write
-  * `content` - the content to write to the file

agenthub/micro/_instructions/format/action.md

@@ -1,5 +0,0 @@
-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 specified here
-* `args`, which is a map of key-value pairs, specifying the arguments for that action
-
-You MUST NOT include any other text besides the JSON response

agenthub/micro/_instructions/history_truncated.md

@@ -1,4 +0,0 @@
-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
-actions and observations--more may have happened before that.
-They are time-ordered, with your most recent action at the bottom.

agenthub/micro/agent.py

@@ -1,77 +0,0 @@
-from jinja2 import BaseLoader, Environment
-
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.core.utils import json
-from opendevin.events.action import Action
-from opendevin.events.serialization.action import action_from_dict
-from opendevin.events.serialization.event import event_to_memory
-from opendevin.llm.llm import LLM
-from opendevin.memory.history import ShortTermHistory
-
-from .instructions import instructions
-from .registry import all_microagents
-
-
-def parse_response(orig_response: str) -> Action:
-    # attempt to load the JSON dict from the response
-    action_dict = json.loads(orig_response)
-
-    # load the action from the dict
-    return action_from_dict(action_dict)
-
-
-def to_json(obj, **kwargs):
-    """Serialize an object to str format"""
-    return json.dumps(obj, **kwargs)
-
-
-class MicroAgent(Agent):
-    VERSION = '1.0'
-    prompt = ''
-    agent_definition: dict = {}
-
-    def history_to_json(
-        self, history: ShortTermHistory, max_events: int = 20, **kwargs
-    ):
-        """
-        Serialize and simplify history to str format
-        """
-        processed_history = []
-        event_count = 0
-
-        for event in history.get_events(reverse=True):
-            if event_count >= max_events:
-                break
-            processed_history.append(
-                event_to_memory(event, self.llm.config.max_message_chars)
-            )
-            event_count += 1
-
-        # history is in reverse order, let's fix it
-        processed_history.reverse()
-
-        return json.dumps(processed_history, **kwargs)
-
-    def __init__(self, llm: LLM):
-        super().__init__(llm)
-        if 'name' not in self.agent_definition:
-            raise ValueError('Agent definition must contain a name')
-        self.prompt_template = Environment(loader=BaseLoader).from_string(self.prompt)
-        self.delegates = all_microagents.copy()
-        del self.delegates[self.agent_definition['name']]
-
-    def step(self, state: State) -> Action:
-        prompt = self.prompt_template.render(
-            state=state,
-            instructions=instructions,
-            to_json=to_json,
-            history_to_json=self.history_to_json,
-            delegates=self.delegates,
-            latest_user_message=state.get_current_user_intent(),
-        )
-        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

agenthub/micro/coder/agent.yaml

@@ -1,6 +0,0 @@
-name: CoderAgent
-description: Given a particular task, and a detailed description of the codebase, accomplishes the task
-inputs:
-  task: string
-  summary: string
-outputs: {}

agenthub/micro/coder/prompt.md

@@ -1,27 +0,0 @@
-# Task
-You are a software engineer. You've inherited an existing codebase, which you
-need to modify to complete this task:
-
-{{ state.inputs.task }}
-
-{% if state.inputs.summary %}
-Here's a summary of the codebase, as it relates to this task:
-
-{{ state.inputs.summary }}
-{% endif %}
-
-## Available Actions
-{{ instructions.actions.run }}
-{{ instructions.actions.write }}
-{{ instructions.actions.read }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-Do NOT finish until you have completed the tasks.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}

agenthub/micro/commit_writer/README.md

@@ -1,25 +0,0 @@
-## Introduction
-
-CommitWriterAgent can help write git commit message. Example:
-
-```bash
-WORKSPACE_MOUNT_PATH="`PWD`" SANDBOX_BOX_TYPE="ssh" \
-  poetry run python opendevin/core/main.py -t "dummy task" -c CommitWriterAgent -d ./
-```
-
-This agent is special in the sense that it doesn't need a task. Once called,
-it attempts to read all diff in the git staging area and write a good commit
-message.
-
-## Future work
-
-### Feedback loop
-
-The commit message could be (optionally) shown to the customer or
-other agents, so that CommitWriterAgent could gather feedback to further
-improve the commit message.
-
-### Task rejection
-
-When the agent cannot compile a commit message (e.g. not git repository), it
-should reject the task with an explanation.

agenthub/micro/commit_writer/agent.yaml

@@ -1,6 +0,0 @@
-name: CommitWriterAgent
-description: "Write a git commit message for files in the git staging area"
-inputs: {}
-outputs:
-  answer: string
-  reason: string

agenthub/micro/commit_writer/prompt.md

@@ -1,33 +0,0 @@
-# Task
-You are a responsible software engineer and always write good commit messages.
-
-Please analyze the diff in the staging area, understand the context and content
-of the updates from the diff only. Identify key elements like:
-- Which files are affected?
-- What types of changes were made (e.g., new features, bug fixes, refactoring, documentation, testing)?
-
-Then you should generate a commit message that succinctly summarizes the staged
-changes. The commit message should include:
-- A summary line that clearly states the purpose of the changes.
-- Optionally, a detailed description if the changes are complex or need further explanation.
-
-You should first use `git status` to check whether it's a valid git repo and there
-is diff in the staging area. If not, please call the `reject` action.
-
-If it is a valid git repo and there is diff in the staging area, you should find
-the diff using `git diff --cached`, compile a commit message, and call the `finish`
-action with `outputs.answer` set to the answer.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-If the last item in the history is an error, you should try to fix it.
-
-## Available Actions
-{{ instructions.actions.run }}
-{{ instructions.actions.reject }}
-{{ instructions.actions.finish }}
-
-## Format
-{{ instructions.format.action }}

agenthub/micro/instructions.py

@@ -1,22 +0,0 @@
-import os
-
-instructions: dict = {}
-
-base_dir = os.path.dirname(os.path.abspath(__file__)) + '/_instructions'
-for root, dirs, files in os.walk(base_dir):
-    if len(files) == 0:
-        continue
-    if root == base_dir:
-        obj = instructions
-    else:
-        rel_base = os.path.relpath(root, base_dir)
-        keys = rel_base.split('/')
-        obj = instructions
-        for key in keys:
-            if key not in obj:
-                obj[key] = {}
-            obj = obj[key]
-    for file in files:
-        without_ext = os.path.splitext(file)[0]
-        with open(os.path.join(root, file), 'r') as f:
-            obj[without_ext] = f.read()

agenthub/micro/manager/agent.yaml

@@ -1,8 +0,0 @@
-name: ManagerAgent
-description: Delegates tasks to microagents based on their area of expertise
-generates: Action
-inputs:
-  task: string
-outputs:
-  summary: string # if finished
-  reason: string # if rejected

agenthub/micro/manager/prompt.md

@@ -1,41 +0,0 @@
-# Task
-You are in charge of accomplishing the following task:
-{{ latest_user_message }}
-
-In order to accomplish this goal, you must delegate tasks to one or more agents, who
-can do the actual work. A description of each agent is provided below. You MUST
-select one of the delegates below to move towards accomplishing the task, and you MUST
-provide the correct inputs for the delegate you select.
-
-Note: the delegated agent either returns "finish" or "reject".
-- If the action is "finish", but the full task is not done yet, you should
-continue to delegate to one of the agents below to until the full task is finished.
-- If the action is "reject", it means the delegated agent is not capable of the
-task you send to. You should revisit the input you send to the delegate, and consider
-whether any other delegate would be able to solve the task. If you cannot find
-a proper delegate agent, or the delegate attempts keep failing, call the `reject`
-action. In `reason` attribute, make sure you include your attempts (e.g. what agent
-you have delegated to, and why they failed).
-
-## Agents
-{% for name, details in delegates.items() %}
-### {{ name }}
-{{ details.description }}
-#### Inputs
-{{ to_json(details.inputs) }}
-{% endfor %}
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-If the last item in the history is an error, you should try to fix it. If you
-cannot fix it, call the `reject` action.
-
-## Available Actions
-{{ instructions.actions.delegate }}
-{{ instructions.actions.finish }}
-{{ instructions.actions.reject }}
-
-## Format
-{{ instructions.format.action }}

agenthub/micro/math_agent/agent.yaml

@@ -1,24 +0,0 @@
-name: MathAgent
-description: "Solves simple and complex math problems using python"
-container: python:3.12.3-bookworm
-inputs:
-  task: string
-outputs:
-  answer: string
-examples:
-  - inputs:
-      task: "What is 2 + 2?"
-    outputs:
-      answer: "4"
-  - inputs:
-      task: "What is the area of a circle with radius 7.324 inches?"
-    output:
-      answer: "168.518 square inches"
-  - inputs:
-      task: "What day of the week is 2099-01-01?"
-    outputs:
-      answer: "Saturday"
-  - inputs:
-      task: "What is the integral of sin(x^2) evaluated from -1 to 1?"
-    outputs:
-      answer: "0.603848"

agenthub/micro/math_agent/prompt.md

@@ -1,23 +0,0 @@
-# Task
-You are a brilliant mathematician and programmer. You've been given the following problem to solve:
-
-`{{ state.inputs.task }}`
-
-Please write a python script that solves this problem, and prints the answer to stdout.
-ONLY print the answer to stdout, nothing else.
-You should then run the python script with `python3`,
-and call the `finish` action with `outputs.answer` set to the answer.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-If the last item in the history is an error, you should try to fix it.
-
-## Available Actions
-{{ instructions.actions.write }}
-{{ instructions.actions.run }}
-{{ instructions.actions.finish }}
-
-## Format
-{{ instructions.format.action }}

agenthub/micro/postgres_agent/agent.yaml

@@ -1,5 +0,0 @@
-name: PostgresAgent
-description: Writes and maintains PostgreSQL migrations
-inputs:
-  task: string
-outputs: {}

agenthub/micro/postgres_agent/prompt.md

@@ -1,24 +0,0 @@
-# Task
-You are a database engineer. You are working on an existing Postgres project, and have been given
-the following task:
-
-{{ state.inputs.task }}
-
-You must:
-* Investigate the existing migrations to understand the current schema
-* Write a new migration to accomplish the task above
-* Test that the migrations work properly
-
-## Actions
-You may take any of the following actions:
-{{ instructions.actions.message }}
-{{ instructions.actions.read }}
-{{ instructions.actions.write }}
-{{ instructions.actions.run }}
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}

agenthub/micro/registry.py

@@ -1,27 +0,0 @@
-import os
-
-import yaml
-
-all_microagents = {}
-
-# Get the list of directories and sort them to preserve determinism
-dirs = sorted(os.listdir(os.path.dirname(__file__)))
-
-for dir in dirs:
-    base = os.path.dirname(__file__) + '/' + dir
-    if os.path.isfile(base):
-        continue
-    if dir.startswith('_'):
-        continue
-    promptFile = base + '/prompt.md'
-    agentFile = base + '/agent.yaml'
-    if not os.path.isfile(promptFile) or not os.path.isfile(agentFile):
-        raise Exception(f'Missing prompt or agent file in {base}. Please create them.')
-    with open(promptFile, 'r') as f:
-        prompt = f.read()
-    with open(agentFile, 'r') as f:
-        agent = yaml.safe_load(f)
-    if 'name' not in agent:
-        raise Exception(f'Missing name in {agentFile}')
-    agent['prompt'] = prompt
-    all_microagents[agent['name']] = agent

agenthub/micro/repo_explorer/agent.yaml

@@ -1,5 +0,0 @@
-name: RepoExplorerAgent
-description: Generates a detailed summary of an existing codebase
-inputs: {}
-outputs:
-  summary: string

agenthub/micro/repo_explorer/prompt.md

@@ -1,26 +0,0 @@
-# Task
-You are a software engineer. You've inherited an existing codebase, which you're
-learning about for the first time. Your goal is to produce a detailed summary
-of the codebase, including:
-* The overall purpose of the project
-* The directory structure
-* The main components of the codebase
-* How the components fit together
-
-## Available Actions
-{{ instructions.actions.run }}
-{{ instructions.actions.read }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-You should ONLY `run` commands that have no side-effects, like `ls` and `grep`.
-
-Do NOT finish until you have a complete understanding of the codebase.
-When you're done, put your summary into the output of the `finish` action.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}

agenthub/micro/study_repo_for_task/agent.yaml

@@ -1,6 +0,0 @@
-name: StudyRepoForTaskAgent
-description: Given a particular task, finds and describes all relevant parts of the codebase
-inputs:
-  task: string
-outputs:
-  summary: string

agenthub/micro/study_repo_for_task/prompt.md

@@ -1,62 +0,0 @@
-# Task
-You are a software architect. Your team has inherited an existing codebase, and
-need to finish a project:
-
-{{ state.inputs.task }}
-
-As an architect, you need to study the codebase to find all the information that
-might be helpful for your software engineering team.
-
-## Available Actions
-{{ instructions.actions.run }}
-{{ instructions.actions.read }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-You must ONLY `run` commands that have no side-effects, like `ls` and `grep`. You
-MUST NOT modify or write to any file.
-
-Do NOT finish until you have a complete understanding of which parts of the
-codebase are relevant to the project, including particular files, functions, and classes.
-When you're done, put your summary in `outputs.summary` in the `finish` action.
-Remember, your task is to explore and study the current repository, not actually
-implement the solution. If the codebase is empty, you should call the `finish` action.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}
-
-## Examples
-
-Here is an example of how you can interact with the environment for task solving:
-
---- START OF EXAMPLE ---
-
-USER: Can you create a list of numbers from 1 to 10, and create a web page to display them at port 5000?
-
-ASSISTANT:
-{
-  "action": "run",
-  "args": {
-    "command": "ls"
-  }
-}
-
-USER:
-OBSERVATION:
-[]
-
-ASSISTANT:
-{
-  "action": "finish",
-  "args": {
-    "outputs": {
-      "summary": "The codebase appears to be empty. Engineers should start everything from scratch."
-    }
-  }
-}
-
---- END OF EXAMPLE ---

agenthub/micro/typo_fixer_agent/agent.yaml

@@ -1,6 +0,0 @@
-name: TypoFixerAgent
-description: Fixes typos in files in the current working directory
-inputs:
-  task: string
-outputs:
-  summary: string

agenthub/micro/typo_fixer_agent/prompt.md

@@ -1,54 +0,0 @@
-# Task
-You are a proofreader tasked with fixing typos in the files in your current working directory.
-
-{% if state.inputs.task %}
-Specifically, your task is:
-{{ state.inputs.task }}
-{% endif %}
-
-To achieve this goal, you should:
-
-1. Scan the files for typos
-2. Overwrite the files with the typos fixed
-3. Provide a summary of the typos fixed
-
-## Available Actions
-{{ instructions.actions.read }}
-{{ instructions.actions.write }}
-{{ instructions.actions.run }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-To complete this task:
-1. Use the `read` action to read the contents of the files in your current working directory. Make sure to provide the file path in the format `'./file_name.ext'`.
-2. Use the `message` action to analyze the contents and identify typos.
-3. Use the `write` action to create new versions of the files with the typos fixed.
-  - Overwrite the original files with the corrected content. Make sure to provide the file path in the format `'./file_name.ext'`.
-4. Use the `message` action to generate a summary of the typos fixed, including the original and fixed versions of each typo, and the file(s) they were found in.
-5. Use the `finish` action to return the summary in the `outputs.summary` field.
-
-Do NOT finish until you have fixed all the typos and generated a summary.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=10) }}
-
-## Format
-{{ instructions.format.action }}
-
-For example, if you want to use the read action to read the contents of a file named example.txt, your response should look like this:
-{
-  "action": "read",
-  "args": {
-    "path": "./example.txt"
-  }
-}
-
-Similarly, if you want to use the write action to write content to a file named output.txt, your response should look like this:
-{
-  "action": "write",
-  "args": {
-    "path": "./output.txt",
-    "content": "This is the content to be written to the file."
-  }
-}

agenthub/micro/verifier/agent.yaml

@@ -1,7 +0,0 @@
-name: VerifierAgent
-description: Given a particular task, verifies that the task has been completed
-inputs:
-  task: string
-outputs:
-  completed: boolean
-  summary: string

agenthub/micro/verifier/prompt.md

@@ -1,28 +0,0 @@
-# Task
-You are a quality assurance engineer. Another engineer has made changes to the
-codebase which are supposed to solve this task:
-
-{{ state.inputs.task }}
-
-Note the changes might have already been applied in-line. You should focus on
-validating if the task is solved, nothing else.
-
-## Available Actions
-{{ instructions.actions.run }}
-{{ instructions.actions.read }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-You must ONLY `run` commands that have no side-effects, like `ls`, `grep`, and test scripts.
-
-Do NOT finish until you know whether the task is complete and correct.
-When you're done, add a `completed` boolean to the `outputs` of the `finish` action.
-If `completed` is `false`, you MUST also provide a `summary` in the `outputs` of the `finish` action
-explaining what the problem is.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}

agenthub/planner_agent/__init__.py

@@ -1,5 +0,0 @@
-from opendevin.controller.agent import Agent
-
-from .agent import PlannerAgent
-
-Agent.register('PlannerAgent', PlannerAgent)

agenthub/planner_agent/agent.py

@@ -1,48 +0,0 @@
-from agenthub.planner_agent.response_parser import PlannerResponseParser
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.events.action import Action, AgentFinishAction
-from opendevin.llm.llm import LLM
-from opendevin.runtime.tools import RuntimeTool
-
-from .prompt import get_prompt
-
-
-class PlannerAgent(Agent):
-    VERSION = '1.0'
-    """
-    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.
-    """
-    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
-    response_parser = PlannerResponseParser()
-
-    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.root_task.state in [
-            'completed',
-            'verified',
-            'abandoned',
-        ]:
-            return AgentFinishAction()
-        prompt = get_prompt(state, self.llm.config.max_message_chars)
-        messages = [{'content': prompt, 'role': 'user'}]
-        resp = self.llm.completion(messages=messages)
-        return self.response_parser.parse(resp)

agenthub/planner_agent/prompt.py

@@ -1,189 +0,0 @@
-from opendevin.controller.state.state import State
-from opendevin.core.logger import opendevin_logger as logger
-from opendevin.core.schema import ActionType
-from opendevin.core.utils import json
-from opendevin.events.action import (
-    Action,
-    NullAction,
-)
-from opendevin.events.serialization.action import action_from_dict
-from opendevin.events.serialization.event import event_to_memory
-
-HISTORY_SIZE = 20
-
-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
-* `browse` - opens a web page. Arguments:
-  * `url` - the URL to open
-* `message` - make a plan, set a goal, record your thoughts, or ask for more input from the user. Arguments:
-  * `content` - the message to record
-  * `wait_for_response` - set to `true` to wait for the user to respond before proceeding
-* `add_task` - add a task to your plan. Arguments:
-  * `parent` - the ID of the parent task (leave empty if it should go at the top level)
-  * `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:
-  * `task_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, and browse actions--do this with the `message` action.
-You should never act twice in a row without thinking. But if your last several
-actions are all `message` 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_hint(latest_action_id: str) -> str:
-    """Returns action type hint based on given action_id"""
-    hints = {
-        '': "You haven't taken any actions yet. Start by using `ls` to check out what files you're working with.",
-        ActionType.RUN: 'You should think about the command you just ran, what output it gave, and how that affects your plan.',
-        ActionType.READ: 'You should think about the file you just read, what you learned from it, and how that affects your plan.',
-        ActionType.WRITE: 'You just changed a file. You should think about how it affects your plan.',
-        ActionType.BROWSE: 'You should think about the page you just visited, and what you learned from it.',
-        ActionType.MESSAGE: "Look at your last thought in the history above. What does it suggest? Don't think anymore--take action.",
-        ActionType.ADD_TASK: 'You should think about the next action to take.',
-        ActionType.MODIFY_TASK: 'You should think about the next action to take.',
-        ActionType.SUMMARIZE: '',
-        ActionType.FINISH: '',
-    }
-    return hints.get(latest_action_id, '')
-
-
-def get_prompt(state: State, max_message_chars: int) -> 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:
-    - state (State): The state of the current agent
-
-    Returns:
-    - str: The formatted string prompt with historical values
-    """
-    # the plan
-    plan_str = json.dumps(state.root_task.to_dict(), indent=2)
-
-    # the history
-    history_dicts = []
-    latest_action: Action = NullAction()
-
-    # retrieve the latest HISTORY_SIZE events
-    for event_count, event in enumerate(state.history.get_events(reverse=True)):
-        if event_count >= HISTORY_SIZE:
-            break
-        if latest_action == NullAction() and isinstance(event, Action):
-            latest_action = event
-        history_dicts.append(event_to_memory(event, max_message_chars))
-
-    # history_dicts is in reverse order, lets fix it
-    history_dicts.reverse()
-
-    # and get it as a JSON string
-    history_str = json.dumps(history_dicts, indent=2)
-
-    # the plan status
-    current_task = state.root_task.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."
-
-    # the hint, based on the last action
-    hint = get_hint(event_to_memory(latest_action, max_message_chars).get('action', ''))
-    logger.info('HINT:\n' + hint, extra={'msg_type': 'DETAIL'})
-
-    # the last relevant user message (the task)
-    task = state.get_current_user_intent()
-
-    # finally, fill in the prompt
-    return prompt % {
-        'task': task,
-        '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
-    """
-    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/planner_agent/response_parser.py

@@ -1,37 +0,0 @@
-from opendevin.controller.action_parser import ResponseParser
-from opendevin.core.utils import json
-from opendevin.events.action import (
-    Action,
-)
-from opendevin.events.serialization.action import action_from_dict
-
-
-class PlannerResponseParser(ResponseParser):
-    def __init__(self):
-        super().__init__()
-
-    def parse(self, response: str) -> Action:
-        action_str = self.parse_response(response)
-        return self.parse_action(action_str)
-
-    def parse_response(self, response) -> str:
-        # get the next action from the response
-        return response['choices'][0]['message']['content']
-
-    def parse_action(self, action_str: 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
-        """
-        # attempt to load the JSON dict from the response
-        action_dict = json.loads(action_str)
-
-        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)

build.sh

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