feat: make use of the partial file tree fetching implemented in the backend

.gitattributes

@@ -1 +1 @@
-*.ipynb linguist-vendored
+*.ipynb linguist-vendored

.github/.codecov.yml

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

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,41 @@
+---
+name: Bug Report
+about: Report a problem with OpenDevin
+title: ''
+labels: 'bug'
+assignees: ''
+
+---
+<!-- You MUST fill out this template. We will close issues that don't include enough information to reproduce -->
+#### Describe the bug
+<!-- a short description of the problem -->
+
+#### Setup and configuration
+**Current version**:
+<!-- run `git log -n 1` to see this -->
+```bash
+```
+
+**My operating system**:
+
+<!-- tell us everything about your environment -->
+**My environment vars and other configuration** (be sure to redact API keys):
+```bash
+```
+
+**My model and agent** (you can see these settings in the UI):
+* Model:
+* Agent:
+
+**Commands I ran to install and run OpenDevin**:
+```
+```
+
+**Steps to Reproduce**:
+1.
+2.
+3.
+
+**Logs, error messages, and screenshots**:
+
+#### Additional Context

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -1,61 +0,0 @@
-name: Bug
-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. 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?
-      description: Please check if an issue already exists for the bug you encountered.
-      options:
-      - label: I have checked the existing issues.
-        required: true
-
-  - type: textarea
-    id: bug-description
-    attributes:
-      label: Describe the bug and reproduction steps
-      description: Provide a description of the issue along with any reproduction steps.
-    validations:
-      required: true
-
-  - type: dropdown
-    id: installation
-    attributes:
-      label: OpenHands Installation
-      description: How are you running OpenHands?
-      options:
-        - Docker command in README
-        - Development workflow
-        - app.all-hands.dev
-        - Other
-      default: 0
-
-  - type: input
-    id: openhands-version
-    attributes:
-      label: OpenHands Version
-      description: What version of OpenHands are you using?
-      placeholder: ex. 0.9.8, main, etc.
-
-  - type: dropdown
-    id: os
-    attributes:
-      label: Operating System
-      options:
-        - MacOS
-        - Linux
-        - WSL on Windows
-
-  - type: textarea
-    id: additional-context
-    attributes:
-      label: Logs, Errors, Screenshots, and Additional Context
-      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 OpenHands features
+about: Suggest an idea for OpenDevin features
 title: ''
 labels: 'enhancement'
 assignees: ''

.github/ISSUE_TEMPLATE/question.md

@@ -0,0 +1,16 @@
+---
+name: Question
+about: Use this template to ask a question regarding the project.
+title: ''
+labels: question
+assignees: ''
+
+---
+
+## Describe your question
+
+<!--A clear and concise description of what you want to know.-->
+
+## Additional context
+
+<!--Add any other context about the question here, like what you've tried so far.-->

.github/dependabot.yml

@@ -1,77 +0,0 @@
-version: 2
-updates:
-  - package-ecosystem: "pip"
-    directory: "/"
-    schedule:
-      interval: "daily"
-    open-pull-requests-limit: 1
-    groups:
-      # put packages in their own group if they have a history of breaking the build or needing to be reverted
-      pre-commit:
-        patterns:
-          - "pre-commit"
-      llama:
-        patterns:
-          - "llama*"
-      chromadb:
-        patterns:
-          - "chromadb"
-      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: 1
-    groups:
-      docusaurus:
-        patterns:
-          - "*docusaurus*"
-      eslint:
-        patterns:
-          - "*eslint*"
-      security-all:
-        applies-to: "security-updates"
-        patterns:
-          - "*"
-      version-all:
-        applies-to: "version-updates"
-        patterns:
-          - "*"
-
-  - package-ecosystem: "npm"
-    directory: "/docs"
-    schedule:
-      interval: "weekly"
-      day: "wednesday"
-    open-pull-requests-limit: 1
-    groups:
-      docusaurus:
-        patterns:
-          - "*docusaurus*"
-      eslint:
-        patterns:
-          - "*eslint*"
-      security-all:
-        applies-to: "security-updates"
-        patterns:
-          - "*"
-      version-all:
-        applies-to: "version-updates"
-        patterns:
-          - "*"
-
-  - package-ecosystem: "github-actions"
-    directory: "/"
-    schedule:
-      interval: "weekly"

.github/pull_request_template.md

@@ -1,11 +0,0 @@
-**End-user friendly description of the problem this fixes or functionality that this introduces**
-
-- [ ] Include this change in the Release Notes. If checked, you must provide an **end-user friendly** description for your change below
-
----
-**Give a summary of what the PR does, explaining any non-trivial design decisions**
-
-
-
----
-**Link of any specific issues this addresses**

.github/workflows/build_run-tests.yml

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

.github/workflows/clean-up.yml

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

.github/workflows/deploy-docs.yml

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

.github/workflows/dogfood.yml

@@ -0,0 +1,109 @@
+name: Use OpenDevin to Resolve GitHub Issue
+
+on:
+  issues:
+    types: [labeled]
+
+permissions:
+  contents: write
+  pull-requests: write
+  issues: write
+
+jobs:
+  open-devin:
+    if: github.event.label.name == 'dogfood-this'
+    runs-on: ubuntu-latest
+    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: Run OpenDevin
+      env:
+        ISSUE_TITLE: ${{ github.event.issue.title }}
+        ISSUE_BODY: ${{ github.event.issue.body }}
+        LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        SANDBOX_TYPE: exec
+      run: |
+        python ./opendevin/main.py -d "./" -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/dummy-agent-test.yml

@@ -1,61 +0,0 @@
-# Workflow that uses the DummyAgent to run a simple task
-name: Run E2E test with dummy agent
-
-# Always run on "main"
-# Always run on PRs
-on:
-  push:
-    branches:
-    - main
-  pull_request:
-
-# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  test:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-      - name: Install poetry via pipx
-        run: pipx install poetry
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.12'
-          cache: 'poetry'
-      - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation,llama-index
-      - name: Build Environment
-        run: make build
-      - name: Run tests
-        run: |
-          set -e
-          SANDBOX_FORCE_REBUILD_RUNTIME=True poetry run python3 openhands/core/main.py -t "do a flip" -d ./workspace/ -c DummyAgent
-      - name: Check exit code
-        run: |
-          if [ $? -ne 0 ]; then
-            echo "Test failed"
-            exit 1
-          else
-            echo "Test passed"
-          fi

.github/workflows/eval-runner.yml

@@ -1,137 +0,0 @@
-name: Run SWE-Bench Evaluation
-
-on:
-  pull_request:
-    types: [labeled]
-  workflow_dispatch:
-    inputs:
-      reason:
-        description: "Reason for manual trigger"
-        required: true
-        default: ""
-
-env:
-  N_PROCESSES: 32 # Global configuration for number of parallel processes for evaluation
-
-jobs:
-  run-evaluation:
-    if: github.event.label.name == 'eval-this' || github.event_name != 'pull_request'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: "read"
-      id-token: "write"
-      pull-requests: "write"
-      issues: "write"
-    strategy:
-      matrix:
-        python-version: ["3.12"]
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-
-      - name: Comment on PR if 'eval-this' label is present
-        if: github.event_name == 'pull_request' && github.event.label.name == 'eval-this'
-        uses: KeisukeYamashita/create-comment@v1
-        with:
-          unique: false
-          comment: |
-            Hi! I started running the evaluation on your PR. You will receive a comment with the results shortly.
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install
-
-      - name: Configure config.toml for evaluation
-        env:
-          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_LLM_API_KEY }}
-        run: |
-          echo "[llm.eval]" > config.toml
-          echo "model = \"deepseek/deepseek-chat\"" >> config.toml
-          echo "api_key = \"$DEEPSEEK_API_KEY\"" >> config.toml
-          echo "temperature = 0.0" >> config.toml
-
-      - name: Run SWE-Bench evaluation
-        env:
-          ALLHANDS_API_KEY: ${{ secrets.ALLHANDS_EVAL_RUNTIME_API_KEY }}
-          RUNTIME: remote
-          SANDBOX_REMOTE_RUNTIME_API_URL: https://runtime.eval.all-hands.dev
-          EVAL_DOCKER_IMAGE_PREFIX: us-central1-docker.pkg.dev/evaluation-092424/swe-bench-images
-
-        run: |
-          poetry run ./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.eval HEAD CodeActAgent 300 30 $N_PROCESSES "princeton-nlp/SWE-bench_Lite" test
-          OUTPUT_FOLDER=$(find evaluation/evaluation_outputs/outputs/princeton-nlp__SWE-bench_Lite-test/CodeActAgent -name "deepseek-chat_maxiter_50_N_*-no-hint-run_1" -type d | head -n 1)
-          echo "OUTPUT_FOLDER for SWE-bench evaluation: $OUTPUT_FOLDER"
-          poetry run ./evaluation/benchmarks/swe_bench/scripts/eval_infer_remote.sh $OUTPUT_FOLDER/output.jsonl $N_PROCESSES "princeton-nlp/SWE-bench_Lite" test
-
-          poetry run ./evaluation/benchmarks/swe_bench/scripts/eval/summarize_outputs.py $OUTPUT_FOLDER/output.jsonl > summarize_outputs.log 2>&1
-          echo "SWEBENCH_REPORT<<EOF" >> $GITHUB_ENV
-          cat summarize_outputs.log >> $GITHUB_ENV
-          echo "EOF" >> $GITHUB_ENV
-
-      - name: Create tar.gz of evaluation outputs
-        run: |
-          TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
-          tar -czvf evaluation_outputs_${TIMESTAMP}.tar.gz evaluation/evaluation_outputs/outputs
-
-      - name: Upload evaluation results as artifact
-        uses: actions/upload-artifact@v4
-        id: upload_results_artifact
-        with:
-          name: evaluation-outputs
-          path: evaluation_outputs_*.tar.gz
-
-      - name: Get artifact URL
-        run: echo "ARTIFACT_URL=${{ steps.upload_results_artifact.outputs.artifact-url }}" >> $GITHUB_ENV
-
-      - name: Authenticate to Google Cloud
-        uses: 'google-github-actions/auth@v2'
-        with:
-          credentials_json: ${{ secrets.GCP_RESEARCH_OBJECT_CREATOR_SA_KEY }}
-
-      - name: Set timestamp and trigger reason
-        run: |
-          echo "TIMESTAMP=$(date +'%Y-%m-%d-%H-%M')" >> $GITHUB_ENV
-          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
-            echo "TRIGGER_REASON=pr-${{ github.event.pull_request.number }}" >> $GITHUB_ENV
-          elif [[ "${{ github.event_name }}" == "schedule" ]]; then
-            echo "TRIGGER_REASON=schedule" >> $GITHUB_ENV
-          else
-            echo "TRIGGER_REASON=manual-${{ github.event.inputs.reason }}" >> $GITHUB_ENV
-          fi
-
-      - name: Upload evaluation results to Google Cloud Storage
-        uses: 'google-github-actions/upload-cloud-storage@v2'
-        with:
-          path: 'evaluation/evaluation_outputs/outputs'
-          destination: 'openhands-oss-eval-results/${{ env.TIMESTAMP }}-${{ env.TRIGGER_REASON }}'
-
-      - name: Comment with evaluation results and artifact link
-        id: create_comment
-        uses: KeisukeYamashita/create-comment@v1
-        with:
-          number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || 4504 }}
-          unique: false
-          comment: |
-              Trigger by: ${{ github.event_name == 'pull_request' && format('Pull Request (eval-this label on PR #{0})', github.event.pull_request.number) || github.event_name == 'schedule' && 'Daily Schedule' || format('Manual Trigger: {0}', github.event.inputs.reason) }}
-              Commit: ${{ github.sha }}
-              **SWE-Bench Evaluation Report**
-              ${{ env.SWEBENCH_REPORT }}
-              ---
-              You can download the full evaluation outputs [here](${{ env.ARTIFACT_URL }}).
-
-      - name: Post to a Slack channel
-        id: slack
-        uses: slackapi/slack-github-action@v2.0.0
-        with:
-          channel-id: 'C07SVQSCR6F'
-          slack-message: "*Evaluation Trigger:* ${{ github.event_name == 'pull_request' && format('Pull Request (eval-this label on PR #{0})', github.event.pull_request.number) || github.event_name == 'schedule' && 'Daily Schedule' || format('Manual Trigger: {0}', github.event.inputs.reason) }}\n\nLink to summary: [here](https://github.com/${{ github.repository }}/issues/${{ github.event_name == 'pull_request' && github.event.pull_request.number || 4504 }}#issuecomment-${{ steps.create_comment.outputs.comment-id }})"
-        env:
-          SLACK_BOT_TOKEN: ${{ secrets.EVAL_NOTIF_SLACK_BOT_TOKEN }}

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

@@ -1,48 +0,0 @@
-# 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: ubuntu-latest
-    strategy:
-      matrix:
-        node-version: [20, 22]
-      fail-fast: true
-    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 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

@@ -1,445 +0,0 @@
-# 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:
-  BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST: nikolaik/python-nodejs:python3.12-nodejs22
-  RELEVANT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
-
-jobs:
-  # Builds the OpenHands Docker images
-  ghcr_build_app:
-    name: Build App Image
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    outputs:
-      hash_from_app_image: ${{ steps.get_hash_in_app_image.outputs.hash_from_app_image }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # 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@v3.0.0
-        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: Build and push app image
-        if: "!github.event.pull_request.head.repo.fork"
-        run: |
-          ./containers/build.sh -i openhands -o ${{ github.repository_owner }} --push
-      - name: Build app image
-        if: "github.event.pull_request.head.repo.fork"
-        run: |
-          ./containers/build.sh -i openhands -o ${{ github.repository_owner }} --load
-      - name: Get hash in App Image
-        id: get_hash_in_app_image
-        run: |
-          # Lowercase the repository owner
-          export REPO_OWNER=${{ github.repository_owner }}
-          REPO_OWNER=$(echo $REPO_OWNER | tr '[:upper:]' '[:lower:]')
-          # Run the build script in the app image
-          docker run -e SANDBOX_USER_ID=0 -v /var/run/docker.sock:/var/run/docker.sock ghcr.io/${REPO_OWNER}/openhands:${{ env.RELEVANT_SHA }} /bin/bash -c "mkdir -p containers/runtime; python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild" 2>&1 | tee docker-outputs.txt
-          # Get the hash from the build script
-          hash_from_app_image=$(cat docker-outputs.txt | grep "Hash for docker build directory" | awk -F "): " '{print $2}' | uniq | head -n1)
-          echo "hash_from_app_image=$hash_from_app_image" >> $GITHUB_OUTPUT
-          echo "Hash from app image: $hash_from_app_image"
-
-  # Builds the runtime Docker images
-  ghcr_build_runtime:
-    name: Build Image
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    strategy:
-      matrix:
-        base_image:
-          - image: 'nikolaik/python-nodejs:python3.12-nodejs22'
-            tag: nikolaik
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # 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@v3.0.0
-        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: actions/setup-python@v5
-        with:
-          python-version: '3.12'
-      - name: Cache Poetry dependencies
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/pypoetry
-            ~/.virtualenvs
-          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-poetry-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-      - 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: Build and push runtime image ${{ matrix.base_image.image }}
-        if: github.event.pull_request.head.repo.fork != true
-        run: |
-          ./containers/build.sh -i runtime -o ${{ github.repository_owner }} --push -t ${{ matrix.base_image.tag }}
-      # Forked repos can't push to GHCR, so we need to upload the image as an artifact
-      - name: Build runtime image ${{ matrix.base_image.image }} for fork
-        if: github.event.pull_request.head.repo.fork
-        uses: docker/build-push-action@v6
-        with:
-          tags: ghcr.io/all-hands-ai/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
-          outputs: type=docker,dest=/tmp/runtime-${{ matrix.base_image.tag }}.tar
-          context: containers/runtime
-      - name: Upload runtime image for fork
-        if: github.event.pull_request.head.repo.fork
-        uses: actions/upload-artifact@v4
-        with:
-          name: runtime-${{ matrix.base_image.tag }}
-          path: /tmp/runtime-${{ matrix.base_image.tag }}.tar
-
-  verify_hash_equivalence_in_runtime_and_app:
-    name: Verify Hash Equivalence in Runtime and Docker images
-    runs-on: ubuntu-latest
-    needs: [ghcr_build_runtime, ghcr_build_app]
-    strategy:
-      fail-fast: false
-      matrix:
-        base_image: ['nikolaik']
-    steps:
-      - uses: actions/checkout@v4
-      - name: Cache Poetry dependencies
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/pypoetry
-            ~/.virtualenvs
-          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-poetry-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.12'
-      - name: Install poetry via pipx
-        run: pipx install poetry
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-      - name: 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 }}" = "${{ env.hash_from_code }}" ]; then
-            echo "Hashes match!"
-          else
-            echo "Hashes do not match!"
-            exit 1
-          fi
-
-  # Run unit tests with the EventStream runtime Docker images as root
-  test_runtime_root:
-    name: RT Unit Tests (Root)
-    needs: [ghcr_build_runtime]
-    runs-on: ubuntu-latest
-    strategy:
-      fail-fast: false
-      matrix:
-        base_image: ['nikolaik']
-    steps:
-      - uses: actions/checkout@v4
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-      # Forked repos can't push to GHCR, so we need to download the image as an artifact
-      - name: Download runtime image for fork
-        if: github.event.pull_request.head.repo.fork
-        uses: actions/download-artifact@v4
-        with:
-          name: runtime-${{ matrix.base_image }}
-          path: /tmp
-      - name: Load runtime image for fork
-        if: github.event.pull_request.head.repo.fork
-        run: |
-          docker load --input /tmp/runtime-${{ matrix.base_image }}.tar
-      - name: Cache Poetry dependencies
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/pypoetry
-            ~/.virtualenvs
-          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-poetry-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.12'
-      - name: Install poetry via pipx
-        run: pipx install poetry
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-      - name: Run runtime tests
-        run: |
-          # We install pytest-xdist in order to run tests across CPUs
-          poetry run pip install pytest-xdist
-
-          # Install to be able to retry on failures for flaky tests
-          poetry run pip install pytest-rerunfailures
-
-          image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
-          image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
-
-          TEST_RUNTIME=eventstream \
-          SANDBOX_USER_ID=$(id -u) \
-          SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
-          TEST_IN_CI=true \
-          RUN_AS_OPENHANDS=false \
-          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v5
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
-  # Run unit tests with the EventStream runtime Docker images as openhands user
-  test_runtime_oh:
-    name: RT Unit Tests (openhands)
-    runs-on: ubuntu-latest
-    needs: [ghcr_build_runtime]
-    strategy:
-      matrix:
-        base_image: ['nikolaik']
-    steps:
-      - uses: actions/checkout@v4
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-      # Forked repos can't push to GHCR, so we need to download the image as an artifact
-      - name: Download runtime image for fork
-        if: github.event.pull_request.head.repo.fork
-        uses: actions/download-artifact@v4
-        with:
-          name: runtime-${{ matrix.base_image }}
-          path: /tmp
-      - name: Load runtime image for fork
-        if: github.event.pull_request.head.repo.fork
-        run: |
-          docker load --input /tmp/runtime-${{ matrix.base_image }}.tar
-      - name: Cache Poetry dependencies
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/pypoetry
-            ~/.virtualenvs
-          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-poetry-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.12'
-      - name: Install poetry via pipx
-        run: pipx install poetry
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-      - name: Run runtime tests
-        run: |
-          # We install pytest-xdist in order to run tests across CPUs
-          poetry run pip install pytest-xdist
-
-          # Install to be able to retry on failures for flaky tests
-          poetry run pip install pytest-rerunfailures
-
-          image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
-          image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
-
-          TEST_RUNTIME=eventstream \
-          SANDBOX_USER_ID=$(id -u) \
-          SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
-          TEST_IN_CI=true \
-          RUN_AS_OPENHANDS=true \
-          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v5
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
-  # The two following jobs (named identically) are to check whether all the runtime tests have passed as the
-  # "All Runtime Tests Passed" is a required job for PRs to merge
-  # 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: ubuntu-latest
-    needs: [test_runtime_root, test_runtime_oh, verify_hash_equivalence_in_runtime_and_app]
-    steps:
-      - name: All tests passed
-        run: echo "All runtime tests have passed successfully!"
-
-  runtime_tests_check_fail:
-    name: All Runtime Tests Passed
-    if: ${{ cancelled() || contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled') }}
-    runs-on: ubuntu-latest
-    needs: [test_runtime_root, test_runtime_oh, verify_hash_equivalence_in_runtime_and_app]
-    steps:
-      - name: Some tests failed
-        run: |
-          echo "Some runtime tests failed or were cancelled"
-          exit 1
-  update_pr_description:
-    name: Update PR Description
-    if: github.event_name == 'pull_request' && !github.event.pull_request.head.repo.fork && github.actor != 'dependabot[bot]'
-    needs: [ghcr_build_runtime]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Get short SHA
-        id: short_sha
-        run: echo "SHORT_SHA=$(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

@@ -0,0 +1,35 @@
+name: Publish Docker Image
+
+on:
+  push:
+  workflow_dispatch:
+    inputs:
+      reason:
+        description: 'Reason for manual trigger'
+        required: true
+        default: ''
+
+jobs:
+  ghcr_build_and_push:
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' || github.event.inputs.reason != ''
+    strategy:
+      matrix:
+        image: ["app", "evaluation", "sandbox"]
+
+    steps:
+      - name: checkout
+        uses: actions/checkout@v4
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log-in to ghcr.io
+        run: echo "${{ secrets.GITHUB_TOKEN }}" | docker login ghcr.io -u ${{ github.actor }} --password-stdin
+
+      - name: Build and push ${{ matrix.image }}
+        run: ./containers/build.sh ${{ matrix.image }} --push

.github/workflows/integration-runner.yml

@@ -1,158 +0,0 @@
-name: Run Integration Tests
-
-on:
-  pull_request:
-    types: [labeled]
-  workflow_dispatch:
-    inputs:
-      reason:
-        description: 'Reason for manual trigger'
-        required: true
-        default: ''
-  schedule:
-    - cron: '30 22 * * *'  # Runs at 10:30pm UTC every day
-
-env:
-  N_PROCESSES: 10 # Global configuration for number of parallel processes for evaluation
-
-jobs:
-  run-integration-tests:
-    if: github.event.label.name == 'integration-test' || github.event_name == 'workflow_dispatch' || github.event_name == 'schedule'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: "read"
-      id-token: "write"
-      pull-requests: "write"
-      issues: "write"
-    strategy:
-      matrix:
-        python-version: ["3.12"]
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-
-      - name: Comment on PR if 'integration-test' label is present
-        if: github.event_name == 'pull_request' && github.event.label.name == 'integration-test'
-        uses: KeisukeYamashita/create-comment@v1
-        with:
-          unique: false
-          comment: |
-            Hi! I started running the integration tests on your PR. You will receive a comment with the results shortly.
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation,llama-index
-
-      - name: Configure config.toml for testing with Haiku
-        env:
-          LLM_MODEL: "litellm_proxy/claude-3-5-haiku-20241022"
-          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
-          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-        run: |
-          echo "[llm.eval]" > config.toml
-          echo "model = \"$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 '' $N_PROCESSES '' 'haiku_run'
-
-          # get integration tests report
-          REPORT_FILE_HAIKU=$(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: ${{ secrets.LLM_BASE_URL }}
-        run: |
-          echo "[llm.eval]" > config.toml
-          echo "model = \"$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 '' $N_PROCESSES '' 'deepseek_run'
-
-          # get integration tests report
-          REPORT_FILE_DEEPSEEK=$(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" >> $GITHUB_ENV
-
-      - name: Create archive of evaluation outputs
-        run: |
-          TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
-          cd evaluation/evaluation_outputs/outputs  # Change to the outputs directory
-          tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/*  # Only include the actual result directories
-
-      - name: Upload evaluation results as artifact
-        uses: actions/upload-artifact@v4
-        id: upload_results_artifact
-        with:
-          name: integration-test-outputs-${{ 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:
-              ${{ env.INTEGRATION_TEST_REPORT_DEEPSEEK }}
-              ---
-              Download testing outputs (includes both Haiku and DeepSeek results): [Download](${{ steps.upload_results_artifact.outputs.artifact-url }})

.github/workflows/lint-fix.yml

@@ -1,91 +0,0 @@
-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: ubuntu-latest
-    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: actions/setup-node@v4
-        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: ubuntu-latest
-    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: actions/setup-python@v5
-        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

@@ -1,55 +1,38 @@
-# Workflow that runs lint on the frontend and python code
 name: Lint
 
-# 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
+on: [push, pull_request]
 
 jobs:
-  # Run lint on the frontend code
   lint-frontend:
-    name: Lint frontend
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
+
       - name: Install Node.js 20
         uses: actions/setup-node@v4
         with:
           node-version: 20
+
       - name: Install dependencies
         run: |
           cd frontend
           npm install --frozen-lockfile
-      - name: Lint and TypeScript compilation
+
+      - name: Lint
         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
     steps:
       - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
       - name: Set up python
         uses: actions/setup-python@v5
         with:
-          python-version: 3.12
-          cache: 'pip'
+          python-version: 3.11
       - name: Install pre-commit
         run: pip install pre-commit==3.7.0
       - name: Run pre-commit hooks
-        run: pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
+        run: pre-commit run --files opendevin/**/* agenthub/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml

.github/workflows/openhands-resolver.yml

@@ -1,393 +0,0 @@
-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"
-      LLM_MODEL:
-        required: false
-        type: string
-        default: "anthropic/claude-3-5-sonnet-20241022"
-      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 $2}' | tr -d '()')
-          echo "openhands-ai==${OPENHANDS_VERSION}" >> requirements.txt
-          cat 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('requirements.txt') }}
-          restore-keys: |
-            ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }}
-
-      - name: Check required environment variables
-        env:
-          LLM_MODEL: ${{ secrets.LLM_MODEL || inputs.LLM_MODEL }}
-          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
-          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-          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
-        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" >> $GITHUB_ENV
-          # Handle pull request review events
-          elif [ -n "${{ github.event.review.body }}" ]; then
-            echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
-            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
-          # Handle issue comment events that reference a PR
-          elif [ -n "${{ 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" >> $GITHUB_ENV
-          fi
-
-          if [ -n "${{ github.event.review.body }}" ]; then
-            echo "COMMENT_ID=${{ github.event.review.id || 'None' }}" >> $GITHUB_ENV
-          else
-            echo "COMMENT_ID=${{ github.event.comment.id || 'None' }}" >> $GITHUB_ENV
-          fi
-
-          echo "MAX_ITERATIONS=${{ inputs.max_iterations || 50 }}" >> $GITHUB_ENV
-          echo "SANDBOX_ENV_GITHUB_TOKEN=${{ secrets.PAT_TOKEN || github.token }}" >> $GITHUB_ENV
-          echo "SANDBOX_ENV_BASE_CONTAINER_IMAGE=${{ inputs.base_container_image }}" >> $GITHUB_ENV
-
-          # Set branch variables
-          echo "TARGET_BRANCH=${{ inputs.target_branch }}" >> $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
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const commentBody = `${{ github.event.comment.body || '' }}`.trim();
-            const reviewBody = `${{ github.event.review.body || '' }}`.trim();
-            const labelName = `${{ github.event.label.name || '' }}`.trim();
-            const eventName = `${{ github.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");
-
-            // 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 requirements.txt");
-            }
-
-      - name: Attempt to resolve issue
-        env:
-          GITHUB_TOKEN: ${{ secrets.PAT_TOKEN || github.token }}
-          GITHUB_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 }}
-          PYTHONPATH: ""
-        run: |
-          cd /tmp && python -m openhands.resolver.resolve_issue \
-            --repo ${{ github.repository }} \
-            --issue-number ${{ env.ISSUE_NUMBER }} \
-            --issue-type ${{ env.ISSUE_TYPE }} \
-            --max-iterations ${{ env.MAX_ITERATIONS }} \
-            --comment-id ${{ env.COMMENT_ID }}
-
-      - 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' }}
-          LLM_MODEL: ${{ secrets.LLM_MODEL || inputs.LLM_MODEL }}
-          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
-          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-          PYTHONPATH: ""
-        run: |
-          if [ "${{ steps.check_result.outputs.RESOLUTION_SUCCESS }}" == "true" ]; then
-            cd /tmp && python -m openhands.resolver.send_pull_request \
-              --issue-number ${{ env.ISSUE_NUMBER }} \
-              --pr-type draft \
-              --reviewer ${{ github.actor }} | tee pr_result.txt && \
-              grep "draft created" pr_result.txt | sed 's/.*\///g' > pr_number.txt
-          else
-            cd /tmp && python -m openhands.resolver.send_pull_request \
-              --issue-number ${{ env.ISSUE_NUMBER }} \
-              --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' }}
-        with:
-          github-token: ${{ secrets.PAT_TOKEN || github.token }}
-          script: |
-            const fs = require('fs');
-            const issueNumber = ${{ env.ISSUE_NUMBER }};
-            let logContent = '';
-
-            try {
-              logContent = fs.readFileSync('/tmp/pr_result.txt', 'utf8').trim();
-            } catch (error) {
-              console.error('Error reading pr_result.txt file:', error);
-            }
-
-            const noChangesMessage = `No changes to commit for issue #${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' }}
-        with:
-          github-token: ${{ secrets.PAT_TOKEN || github.token }}
-          script: |
-            const fs = require('fs');
-            const path = require('path');
-            const issueNumber = ${{ env.ISSUE_NUMBER }};
-            const success = ${{ steps.check_result.outputs.RESOLUTION_SUCCESS }};
-
-            let prNumber = '';
-            let branchName = '';
-            let resultExplanation = '';
-
-            try {
-              if (success) {
-                prNumber = fs.readFileSync('/tmp/pr_number.txt', 'utf8').trim();
-              } else {
-                branchName = fs.readFileSync('/tmp/branch_name.txt', 'utf8').trim();
-              }
-            } catch (error) {
-              console.error('Error reading file:', error);
-            }
-
-
-            try {
-              if (!success){
-                // Read result_explanation from JSON file for failed resolution
-                const outputFilePath = path.resolve('/tmp/output/output.jsonl');
-                if (fs.existsSync(outputFilePath)) {
-                  const outputContent = fs.readFileSync(outputFilePath, 'utf8');
-                  const jsonLines = outputContent.split('\n').filter(line => line.trim() !== '');
-
-                  if (jsonLines.length > 0) {
-                    // First entry in JSON lines has the key 'result_explanation'
-                    const firstEntry = JSON.parse(jsonLines[0]);
-                    resultExplanation = firstEntry.result_explanation || '';
-                  }
-                }
-              }
-            } catch (error){
-              console.error('Error reading file:', error);
-            }
-
-            // Check "success" log from resolver output
-            if (success && prNumber) {
-              github.rest.issues.createComment({
-                issue_number: issueNumber,
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                body: `A potential fix has been generated and a draft PR #${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
-        with:
-          github-token: ${{ secrets.PAT_TOKEN || github.token }}
-          script: |
-            const issueNumber = ${{ env.ISSUE_NUMBER }};
-
-            github.rest.issues.createComment({
-              issue_number: issueNumber,
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              body: `The workflow to fix this issue encountered an error. Please check the [workflow logs](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}) for more information.`
-            });

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

@@ -1,96 +0,0 @@
-# Workflow that runs python unit tests on mac
-name: Run Python Unit Tests Mac
-
-# This job is flaky so only run it nightly
-on:
-  schedule:
-    - cron: '0 0 * * *'
-
-jobs:
-  # Run python unit tests on macOS
-  test-on-macos:
-    name: Python Unit Tests on macOS
-    runs-on: macos-14
-    env:
-      INSTALL_DOCKER: '1' # Set to '0' to skip Docker installation
-    strategy:
-      matrix:
-        python-version: ['3.12']
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-      - name: Cache Poetry dependencies
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/pypoetry
-            ~/.virtualenvs
-          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-poetry-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-      - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation,llama-index
-      - name: Install & Start Docker
-        if: env.INSTALL_DOCKER == '1'
-        run: |
-          INSTANCE_NAME="colima-${GITHUB_RUN_ID}"
-
-          # Uninstall colima to upgrade to the latest version
-          if brew list colima &>/dev/null; then
-            brew uninstall colima
-            # unlinking colima dependency: go
-            brew uninstall go@1.21
-          fi
-          rm -rf ~/.colima ~/.lima
-          brew install --HEAD colima
-          brew install docker
-
-          start_colima() {
-            # Find a free port in the range 10000-20000
-            RANDOM_PORT=$((RANDOM % 10001 + 10000))
-
-            # Original line:
-            if ! colima start --network-address --arch x86_64 --cpu=1 --memory=1 --verbose --ssh-port $RANDOM_PORT; then
-              echo "Failed to start Colima."
-              return 1
-            fi
-            return 0
-          }
-
-          # Attempt to start Colima for 5 total attempts:
-          ATTEMPT_LIMIT=5
-          for ((i=1; i<=ATTEMPT_LIMIT; i++)); do
-
-            if start_colima; then
-              echo "Colima started successfully."
-              break
-            else
-              colima stop -f
-              sleep 10
-              colima delete -f
-              if [ $i -eq $ATTEMPT_LIMIT ]; then
-                exit 1
-              fi
-              sleep 10
-            fi
-          done
-
-          # For testcontainers to find the Colima socket
-          # https://github.com/abiosoft/colima/blob/main/docs/FAQ.md#cannot-connect-to-the-docker-daemon-at-unixvarrundockersock-is-the-docker-daemon-running
-          sudo ln -sf $HOME/.colima/default/docker.sock /var/run/docker.sock
-      - name: Build Environment
-        run: make build
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-      - name: Run Tests
-        run: poetry run pytest --forked --cov=openhands --cov-report=xml ./tests/unit --ignore=tests/unit/test_memory.py
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v5
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

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

@@ -1,49 +0,0 @@
-# Workflow that runs python unit tests
-name: Run Python Unit Tests
-
-# The jobs in this workflow are required, so they must run at all times
-# * Always run on "main"
-# * Always run on PRs
-on:
-  push:
-    branches:
-      - main
-  pull_request:
-
-# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  # Run python unit tests on Linux
-  test-on-linux:
-    name: Python Unit Tests on Linux
-    runs-on: ubuntu-latest
-    env:
-      INSTALL_DOCKER: '0' # Set to '0' to skip Docker installation
-    strategy:
-      matrix:
-        python-version: ['3.12']
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-      - name: Install poetry via pipx
-        run: pipx install poetry
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
-      - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation,llama-index
-      - name: Build Environment
-        run: make build
-      - name: Run Tests
-        run: poetry run pytest --forked -n auto --cov=openhands --cov-report=xml -svv ./tests/unit --ignore=tests/unit/test_memory.py
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v5
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

.github/workflows/pypi-release.yml

@@ -1,31 +0,0 @@
-# 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: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
-        with:
-          python-version: 3.12
-      - name: Install Poetry
-        uses: snok/install-poetry@v1.4.1
-        with:
-          virtualenvs-in-project: true
-          virtualenvs-path: ~/.virtualenvs
-      - name: Install Poetry Dependencies
-        run: poetry install --no-interaction --no-root
-      - name: Build poetry project
-        run: ./build.sh
-      - name: publish
-        run: poetry publish -u __token__ -p ${{ secrets.PYPI_TOKEN }}

.github/workflows/run-eval.yml

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

.github/workflows/run-tests.yml

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

.github/workflows/stale.yml

@@ -1,7 +1,4 @@
-# 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 * * *'
@@ -12,10 +9,21 @@ jobs:
     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.'
-          stale-pr-message: 'This PR is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
-          days-before-stale: 30
-          exempt-issue-labels: 'tracked'
           close-issue-message: 'This issue was closed because it has been stalled for over 30 days with no activity.'
+          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
           days-before-close: 7

.gitignore

@@ -57,6 +57,7 @@ cover/
 *.pot
 
 # Django stuff:
+*.log
 local_settings.py
 db.sqlite3
 db.sqlite3-journal
@@ -121,13 +122,11 @@ celerybeat.pid
 
 # Environments
 .env
-frontend/.env
 .venv
 env/
 venv/
 ENV/
 env.bak/
-.env.bak
 venv.bak/
 *venv/
 
@@ -162,27 +161,14 @@ cython_debug/
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 .idea/
 .vscode/
-.cursorignore
 
 # evaluation
-evaluation/evaluation_outputs
-evaluation/outputs
-evaluation/swe_bench/eval_workspace*
 evaluation/SWE-bench/data
-evaluation/webarena/scripts/webarena_env.sh
-evaluation/bird/data
-evaluation/gaia/data
-evaluation/gorilla/data
-evaluation/toolqa/data
-evaluation/scienceagentbench/benchmark
-evaluation/commit0_bench/repos
-
-# openhands resolver
-output/
 
 # frontend
 
 # dependencies
+frontend/node_modules
 frontend/.pnp
 frontend/bun.lockb
 frontend/yarn.lock
@@ -190,8 +176,6 @@ frontend/yarn.lock
 
 # testing
 frontend/coverage
-test_results*
-/_test_files_tmp/
 
 # production
 frontend/build
@@ -213,23 +197,8 @@ logs
 # agent
 .envrc
 /workspace
-/_test_workspace
 /debug
 cache
 
 # configuration
 config.toml
-config.toml_
-config.toml.bak
-
-# swe-bench-eval
-image_build_logs
-run_instance_logs
-
-runtime_*.tar
-
-# docker build
-containers/runtime/Dockerfile
-containers/runtime/project.tar.gz
-containers/runtime/code
-**/node_modules/

.nvmrc

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

.openhands/microagents/repo.md

@@ -1,41 +0,0 @@
----
-name: repo
-agent: CodeAct
----
-This repository contains the code for OpenHands, an automated AI software engineer. It has a Python backend
-(in the `openhands` directory) and React frontend (in the `frontend` directory).
-
-## General Setup:
-To set up the entire repo, including frontend and backend, run `make build`.
-You don't need to do this unless the user asks you to, or if you're trying to run the entire application.
-
-Before pushing any changes, you should ensure that any lint errors or simple test errors have been fixed.
-
-* If you've made changes to the backend, you should run `pre-commit run --all-files --config ./dev_config/python/.pre-commit-config.yaml`
-* If you've made changes to the frontend, you should run `cd frontend && npm run lint:fix && npm run build ; cd ..`
-
-If either command fails, it may have automatically fixed some issues. You should fix any issues that weren't automatically fixed,
-then re-run the command to ensure it passes.
-
-## Repository Structure
-Backend:
-- Located in the `openhands` directory
-- Testing:
-  - All tests are in `tests/unit/test_*.py`
-  - To test new code, run `poetry run pytest tests/unit/test_xxx.py` where `xxx` is the appropriate file for the current functionality
-  - Write all tests with pytest
-
-Frontend:
-- Located in the `frontend` directory
-- Prerequisites: A recent version of NodeJS / NPM
-- Setup: Run `npm install` in the frontend directory
-- Testing:
-  - Run tests: `npm run test`
-  - To run specific tests: `npm run test -- -t "TestName"`
-- Building:
-  - Build for production: `npm run build`
-- Environment Variables:
-  - Set in `frontend/.env` or as environment variables
-  - Available variables: VITE_BACKEND_HOST, VITE_USE_TLS, VITE_INSECURE_SKIP_VERIFY, VITE_FRONTEND_PORT
-- Internationalization:
-  - Generate i18n declaration file: `npm run make-i18n`

COMMUNITY.md

@@ -1,43 +0,0 @@
-# 🙌 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

@@ -1,82 +1,63 @@
 # Contributing
 
-Thanks for your interest in contributing to OpenHands! We welcome and appreciate contributions.
+Thanks for your interest in contributing to OpenDevin! We welcome and appreciate contributions.
+To report bugs, create a [GitHub issue](https://github.com/OpenDevin/OpenDevin/issues/new/choose).
 
-## Understanding OpenHands's CodeBase
+## Contribution Guide
+### 1. Fork the Official Repository
 
-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)
+Fork [OpenDevin repository](https://github.com/OpenDevin/OpenDevin) into your own account.
+Clone your own forked repository into your local environment.
 
-## Setting up your development environment
+```shell
+git clone git@github.com:<YOUR-USERNAME>/OpenDevin.git
+```
 
-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.
+### 2. Configure Git
 
-## How can I contribute?
+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
 
-There are many ways that you can contribute:
+```shell
+cd OpenDevin
+git remote add upstream git@github.com:OpenDevin/OpenDevin.git
+```
 
-1. **Download and use** OpenHands, and send [issues](https://github.com/All-Hands-AI/OpenHands/issues) when you encounter something that isn't working or a feature that you'd like to see.
-2. **Send feedback** after each session by [clicking the thumbs-up thumbs-down buttons](https://docs.all-hands.dev/modules/usage/feedback), so we can see where things are working and failing, and also build an open dataset for training code agents.
-3. **Improve the Codebase** by sending [PRs](#sending-pull-requests-to-openhands) (see details below). In particular, we have some [good first issues](https://github.com/All-Hands-AI/OpenHands/labels/good%20first%20issue) that may be ones to start on.
+Verify that the remote is set.
+```shell
+git remote -v
+```
+You should see both `origin` and `upstream` in the output.
 
-## What can I build?
-Here are a few ways you can help improve the codebase.
+### 3. Synchronize with Official Repository
+Synchronize latest commit with official repository before coding.
 
-#### 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.
+```shell
+git fetch upstream
+git checkout main
+git merge upstream/main
+git push origin main
+```
 
-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.
+### 4. Create a New Branch And Open a Pull Request
+After you finish implementation, open forked repository. The source branch is your new branch, and the target branch is `OpenDevin/OpenDevin` `main` branch. Then PR should appears in [OpenDevin PRs](https://github.com/OpenDevin/OpenDevin/pulls).
 
-#### 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)
+Then OpenDevin team will review your code.
 
-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.
+## PR Rules
 
-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.
+### 1. Pull Request title
 
-#### Adding a new agent
-You may want to experiment with building new types of agents. You can add an agent to [`openhands/agenthub`](./openhands/agenthub)
-to help expand the capabilities of OpenHands.
-
-#### Adding a new runtime
-The agent needs a place to run code and commands. When you run OpenHands on your laptop, it uses a Docker container
-to do this by default. But there are other ways of creating a sandbox for the agent.
-
-If you work for a company that provides a cloud-based runtime, you could help us add support for that runtime
-by implementing the [interface specified here](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/base.py).
-
-#### Testing
-When you write code, it is also good to write tests. Please navigate to the [`./tests`](./tests) folder to see existing test suites.
-At the moment, we have two kinds of tests: [`unit`](./tests/unit) and [`integration`](./evaluation/integration_tests). Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
-
-## Sending Pull Requests to OpenHands
-
-You'll need to fork our repository to send us a Pull Request. You can learn more
-about how to fork a GitHub repo and open a PR with your changes in [this article](https://medium.com/swlh/forks-and-pull-requests-how-to-contribute-to-github-repos-8843fac34ce8)
-
-### Pull Request title
-As described [here](https://github.com/commitizen/conventional-commit-types/blob/master/index.json), a valid PR title should begin with one of the following prefixes:
+As described in [here](https://github.com/commitizen/conventional-commit-types/blob/master/index.json), a valid PR title should begin with one of the following prefixes:
 
 - `feat`: A new feature
 - `fix`: A bug fix
-- `docs`: Documentation only changes
-- `style`: Changes that do not affect the meaning of the code (white space, formatting, missing semicolons, etc.)
+- `doc`: Documentation only changes
 - `refactor`: A code change that neither fixes a bug nor adds a feature
+- `style`: A refactoring that improves code style
 - `perf`: A code change that improves performance
 - `test`: Adding missing tests or correcting existing tests
-- `build`: Changes that affect the build system or external dependencies (example scopes: gulp, broccoli, npm)
-- `ci`: Changes to our CI configuration files and scripts (example scopes: Travis, Circle, BrowserStack, SauceLabs)
+- `ci`: Changes to CI configuration files and scripts (example scopes: `.github`, `ci` (Buildkite))
 - `chore`: Other changes that don't modify src or test files
 - `revert`: Reverts a previous commit
 
@@ -84,40 +65,25 @@ 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/All-Hands-AI/OpenHands/pulls).
+You may also check out previous PRs in the [PR list](https://github.com/OpenDevin/OpenDevin/pulls).
+
+As described in [here](https://github.com/OpenDevin/OpenDevin/labels), we create several labels. Every PR should be tagged with the corresponding labels.
+
+### 2. Pull Request description
 
-### Pull Request description
 - If your PR is small (such as a typo fix), you can go brief.
-- If it contains a lot of changes, it's better to write more details.
+- If it is large and you have changed a lot, 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
+## How to begin
+Please refer to the README in each module:
+- [frontend](./frontend/README.md)
+- [agenthub](./agenthub/README.md)
+- [evaluation](./evaluation/README.md)
+- [opendevin](./opendevin/README.md)
+    - [server](./opendevin/server/README.md)
+    - [mock server](./opendevin/mock/README.md)
 
-### Opening Issues
+## Tests
+TODO: make sure code pass the test before submit.
 
-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 [PRs](https://github.com/All-Hands-AI/OpenHands/pulls), 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

@@ -1,312 +0,0 @@
-# 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
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [yyyy] [name of copyright owner]
-
-
-
-### Non-Open Source Reference Implementations:
-
-#### [MultiPL-E](https://github.com/nuprl/MultiPL-E)
-   - License: BSD 3-Clause License with Machine Learning Restriction
-
-BSD 3-Clause License with Machine Learning Restriction
-
-Copyright (c) 2022, Northeastern University, Oberlin College, Roblox Inc,
-Stevens Institute of Technology, University of Massachusetts Amherst, and
-Wellesley College.
-
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
-1. Redistributions of source code must retain the above copyright notice, this
-   list of conditions and the following disclaimer.
-
-2. Redistributions in binary form must reproduce the above copyright notice,
-   this list of conditions and the following disclaimer in the documentation
-   and/or other materials provided with the distribution.
-
-3. Neither the name of the copyright holder nor the names of its
-   contributors may be used to endorse or promote products derived from
-   this software without specific prior written permission.
-
-4.  The contents of this repository may not be used as training data for any
-    machine learning model, including but not limited to neural networks.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
-FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

CodeOfConduct.md

@@ -61,7 +61,7 @@ representative at an online or offline event.
 
 Instances of abusive, harassing, or otherwise unacceptable behavior may be
 reported to the community leaders responsible for enforcement at
-contact@all-hands.dev
+contact@rbren.io
 All complaints will be reviewed and investigated promptly and fairly.
 
 All community leaders are obligated to respect the privacy and security of the

Development.md

@@ -1,69 +1,53 @@
 # Development Guide
-This guide is for people working on OpenHands and editing the source code.
-If you wish to contribute your changes, check out the [CONTRIBUTING.md](https://github.com/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.
+This guide is for people working on OpenDevin and editing the source code.
 
 ## Start the server for development
+
 ### 1. Requirements
-* Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)  [Ubuntu <= 22.04]
-* [Docker](https://docs.docker.com/engine/install/) (For those on MacOS, make sure to allow the default Docker socket to be used from advanced settings!)
-* [Python](https://www.python.org/downloads/) = 3.12
+* Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)
+* [Docker](https://docs.docker.com/engine/install/)(For those on MacOS, make sure to allow the default Docker socket to be used from advanced settings!)
+* [Python](https://www.python.org/downloads/) >= 3.11
 * [NodeJS](https://nodejs.org/en/download/package-manager) >= 18.17.1
 * [Poetry](https://python-poetry.org/docs/#installing-with-the-official-installer) >= 1.8
-* 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
-# Download and install Mamba (a faster version of conda)
-curl -L -O "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"
-bash Miniforge3-$(uname)-$(uname -m).sh
-
-# Install Python 3.12, nodejs, and poetry
-mamba install python=3.12
-mamba install conda-forge::nodejs
-mamba install conda-forge::poetry
-```
-
 ### 2. Build and Setup The Environment
-Begin by building the project which includes setting up the environment and installing dependencies. This step ensures that OpenHands is ready to run on your system:
 
-```bash
-make build
-```
+- **Build the Project:** Begin by building the project, which includes setting up the environment and installing dependencies. This step ensures that OpenDevin is ready to run smoothly on your system.
+    ```bash
+    make build
+    ```
 
 ### 3. Configuring the Language Model
-OpenHands supports a diverse array of Language Models (LMs) through the powerful [litellm](https://docs.litellm.ai) library.
-By default, we've chosen Claude Sonnet 3.5 as our go-to model, but the world is your oyster! You can unleash the
-potential of any other LM that piques your interest.
 
-To configure the LM of your choice, run:
+OpenDevin supports a diverse array of Language Models (LMs) through the powerful [litellm](https://docs.litellm.ai) library. By default, we've chosen the mighty GPT-4 from OpenAI as our go-to model, but the world is your oyster! You can unleash the potential of Anthropic's suave Claude, the enigmatic Llama, or any other LM that piques your interest.
 
+To configure the LM of your choice, follow these steps:
+
+1. **Using the Makefile: The Effortless Approach**
+   With a single command, you can have a smooth LM setup for your OpenDevin experience. Simply run:
    ```bash
    make setup-config
    ```
-
-   This command will prompt you to enter the LLM API key, model name, and other variables ensuring that OpenHands is tailored to your specific needs. Note that the model name will apply only when you run headless. If you use the UI, please set the model in the UI.
-
-   Note: If you have previously run OpenHands using the docker command, you may have already set some environmental variables in your terminal. The final configurations are set from highest to lowest priority:
-   Environment variables > config.toml variables > default variables
+   This command will prompt you to enter the LLM API key and model name, ensuring that OpenDevin is tailored to your specific needs.
 
 **Note on Alternative Models:**
-See [our documentation](https://docs.all-hands.dev/modules/usage/llms) for recommended models.
+Some alternative models may prove more challenging to tame than others. Fear not, brave adventurer! We shall soon unveil LLM-specific documentation to guide you on your quest. And if you've already mastered the art of wielding a model other than OpenAI's GPT, we encourage you to [share your setup instructions with us](https://github.com/OpenDevin/OpenDevin/issues/417).
 
-### 4. Running the application
-#### Option A: Run the Full Application
-Once the setup is complete, launching OpenHands is as simple as running a single command. This command starts both the backend and frontend servers seamlessly, allowing you to interact with OpenHands:
-```bash
-make run
-```
+For a full list of the LM providers and models available, please consult the [litellm documentation](https://docs.litellm.ai/docs/providers).
+
+There is also [documentation for running with local models using ollama](./docs/documentation/LOCAL_LLM_GUIDE.md).
+
+### 4. Run the Application
+
+- **Run the Application:** Once the setup is complete, launching OpenDevin is as simple as running a single command. This command starts both the backend and frontend servers seamlessly, allowing you to interact with OpenDevin without any hassle.
+    ```bash
+    make run
+    ```
+
+### 5. Individual Server Startup
 
-#### 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
@@ -75,54 +59,12 @@ make run
     ```
 
 ### 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.
-OpenHands 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, 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.
 
 ### 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 OpenHands.
-```bash
-make help
- ```
 
-### 8. Testing
-To run tests, refer to the following:
-#### Unit tests
-
-```bash
-poetry run pytest ./tests/unit/test_*.py
-```
-
-### 9. Add or update dependency
-1. Add your dependency in `pyproject.toml` or use `poetry add xxx`
-2. Update the poetry.lock file via `poetry lock --no-update`
-
-### 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:0.17-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.
+- **Get Some Help:** Need assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenDevin.
+    ```bash
+    make help
+    ```

ISSUE_TRIAGE.md

@@ -1,25 +0,0 @@
-# Issue Triage
-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.)
-
-## Severity
-* **Low**: Minor issues or affecting single user.
-* **Medium**: Affecting multiple users.
-* **Critical**: Affecting all users or potential security issues.
-
-## Effort
-* Issues may be estimated with effort required (**small effort**, **medium effort**, **large effort**)
-
-## Difficulty
-* Issues 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).
-
-## 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.

MANIFEST.in

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

Makefile

@@ -1,69 +1,47 @@
-SHELL=/bin/bash
-# Makefile for OpenHands project
+# Makefile for OpenDevin project
 
 # Variables
-BACKEND_HOST ?= "127.0.0.1"
+DOCKER_IMAGE = ghcr.io/opendevin/sandbox
 BACKEND_PORT = 3000
-BACKEND_HOST_PORT = "$(BACKEND_HOST):$(BACKEND_PORT)"
+BACKEND_HOST = "127.0.0.1:$(BACKEND_PORT)"
 FRONTEND_PORT = 3001
 DEFAULT_WORKSPACE_DIR = "./workspace"
-DEFAULT_MODEL = "gpt-4o"
+DEFAULT_MODEL = "gpt-3.5-turbo-1106"
 CONFIG_FILE = config.toml
-PRE_COMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
-PYTHON_VERSION = 3.12
+PRECOMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
 
 # ANSI color codes
-GREEN=$(shell tput -Txterm setaf 2)
-YELLOW=$(shell tput -Txterm setaf 3)
-RED=$(shell tput -Txterm setaf 1)
-BLUE=$(shell tput -Txterm setaf 6)
-RESET=$(shell tput -Txterm sgr0)
+GREEN=\033[0;32m
+YELLOW=\033[0;33m
+RED=\033[0;31m
+BLUE=\033[0;34m
+RESET=\033[0m
 
 # Build
 build:
 	@echo "$(GREEN)Building project...$(RESET)"
 	@$(MAKE) -s check-dependencies
+	@$(MAKE) -s pull-docker-image
 	@$(MAKE) -s install-python-dependencies
 	@$(MAKE) -s install-frontend-dependencies
-	@$(MAKE) -s install-pre-commit-hooks
+	@$(MAKE) -s install-precommit-hooks
 	@$(MAKE) -s build-frontend
 	@echo "$(GREEN)Build completed successfully.$(RESET)"
 
 check-dependencies:
 	@echo "$(YELLOW)Checking dependencies...$(RESET)"
-	@$(MAKE) -s check-system
 	@$(MAKE) -s check-python
 	@$(MAKE) -s check-npm
-	@$(MAKE) -s check-nodejs
-ifeq ($(INSTALL_DOCKER),)
 	@$(MAKE) -s check-docker
-endif
 	@$(MAKE) -s check-poetry
 	@echo "$(GREEN)Dependencies checked successfully.$(RESET)"
 
-check-system:
-	@echo "$(YELLOW)Checking system...$(RESET)"
-	@if [ "$(shell uname)" = "Darwin" ]; then \
-		echo "$(BLUE)macOS detected.$(RESET)"; \
-	elif [ "$(shell uname)" = "Linux" ]; then \
-		if [ -f "/etc/manjaro-release" ]; then \
-			echo "$(BLUE)Manjaro Linux detected.$(RESET)"; \
-		else \
-			echo "$(BLUE)Linux detected.$(RESET)"; \
-		fi; \
-	elif [ "$$(uname -r | grep -i microsoft)" ]; then \
-		echo "$(BLUE)Windows Subsystem for Linux detected.$(RESET)"; \
-	else \
-		echo "$(RED)Unsupported system detected. Please use macOS, Linux, or Windows Subsystem for Linux (WSL).$(RESET)"; \
-		exit 1; \
-	fi
-
 check-python:
 	@echo "$(YELLOW)Checking Python installation...$(RESET)"
-	@if command -v python$(PYTHON_VERSION) > /dev/null; then \
-		echo "$(BLUE)$(shell python$(PYTHON_VERSION) --version) is already installed.$(RESET)"; \
+	@if command -v python3.11 > /dev/null; then \
+		echo "$(BLUE)$(shell python3.11 --version) is already installed.$(RESET)"; \
 	else \
-		echo "$(RED)Python $(PYTHON_VERSION) is not installed. Please install Python $(PYTHON_VERSION) to continue.$(RESET)"; \
+		echo "$(RED)Python 3.11 is not installed. Please install Python 3.11 to continue.$(RESET)"; \
 		exit 1; \
 	fi
 
@@ -76,22 +54,6 @@ check-npm:
 		exit 1; \
 	fi
 
-check-nodejs:
-	@echo "$(YELLOW)Checking Node.js installation...$(RESET)"
-	@if command -v node > /dev/null; then \
-		NODE_VERSION=$(shell node --version | sed -E 's/v//g'); \
-		IFS='.' read -r -a NODE_VERSION_ARRAY <<< "$$NODE_VERSION"; \
-		if [ "$${NODE_VERSION_ARRAY[0]}" -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 ] && [ "$${NODE_VERSION_ARRAY[2]}" -ge 1 ]); then \
-			echo "$(BLUE)Node.js $$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.$(RESET)"; \
-			exit 1; \
-		fi; \
-	else \
-		echo "$(RED)Node.js is not installed. Please install Node.js to continue.$(RESET)"; \
-		exit 1; \
-	fi
-
 check-docker:
 	@echo "$(YELLOW)Checking Docker installation...$(RESET)"
 	@if command -v docker > /dev/null; then \
@@ -104,84 +66,49 @@ check-docker:
 check-poetry:
 	@echo "$(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 \
-			echo "$(BLUE)$(shell poetry --version) is already installed.$(RESET)"; \
-		else \
-			echo "$(RED)Poetry 1.8 or later is required. You can install poetry by running the following command, then adding Poetry to your PATH:"; \
-			echo "$(RED) curl -sSL https://install.python-poetry.org | python$(PYTHON_VERSION) -$(RESET)"; \
-			echo "$(RED)More detail here: https://python-poetry.org/docs/#installing-with-the-official-installer$(RESET)"; \
-			exit 1; \
-		fi; \
+		echo "$(BLUE)$(shell poetry --version) is already installed.$(RESET)"; \
 	else \
 		echo "$(RED)Poetry is not installed. You can install poetry by running the following command, then adding Poetry to your PATH:"; \
-		echo "$(RED) curl -sSL https://install.python-poetry.org | python$(PYTHON_VERSION) -$(RESET)"; \
+		echo "$(RED) curl -sSL https://install.python-poetry.org | python3.11 -$(RESET)"; \
 		echo "$(RED)More detail here: https://python-poetry.org/docs/#installing-with-the-official-installer$(RESET)"; \
 		exit 1; \
 	fi
 
+pull-docker-image:
+	@echo "$(YELLOW)Pulling Docker image...$(RESET)"
+	@docker pull $(DOCKER_IMAGE)
+	@echo "$(GREEN)Docker image pulled successfully.$(RESET)"
+
 install-python-dependencies:
 	@echo "$(GREEN)Installing Python dependencies...$(RESET)"
-	@if [ -z "${TZ}" ]; then \
-		echo "Defaulting TZ (timezone) to UTC"; \
-		export TZ="UTC"; \
-	fi
-	poetry env use python$(PYTHON_VERSION)
 	@if [ "$(shell uname)" = "Darwin" ]; then \
-		echo "$(BLUE)Installing chroma-hnswlib...$(RESET)"; \
+		echo "$(BLUE)Installing `chroma-hnswlib`...$(RESET)"; \
 		export HNSWLIB_NO_NATIVE=1; \
 		poetry run pip install chroma-hnswlib; \
 	fi
-	@poetry install --without llama-index
-	@if [ -f "/etc/manjaro-release" ]; then \
-		echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
-		poetry run pip install playwright; \
-		poetry run playwright install chromium; \
-	else \
-		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
+	@poetry install --without evaluation
 	@echo "$(GREEN)Python dependencies installed successfully.$(RESET)"
 
 install-frontend-dependencies:
 	@echo "$(YELLOW)Setting up frontend environment...$(RESET)"
 	@echo "$(YELLOW)Detect Node.js version...$(RESET)"
 	@cd frontend && node ./scripts/detect-node-version.js
-	echo "$(BLUE)Installing frontend dependencies with npm...$(RESET)"
-	@cd frontend && npm install
+	@cd frontend && \
+		echo "$(BLUE)Installing frontend dependencies with npm...$(RESET)" && \
+		npm install && \
+		echo "$(BLUE)Running make-i18n with npm...$(RESET)" && \
+		npm run make-i18n
 	@echo "$(GREEN)Frontend dependencies installed successfully.$(RESET)"
 
-install-pre-commit-hooks:
+install-precommit-hooks:
 	@echo "$(YELLOW)Installing pre-commit hooks...$(RESET)"
 	@git config --unset-all core.hooksPath || true
-	@poetry run pre-commit install --config $(PRE_COMMIT_CONFIG_PATH)
+	@poetry run pre-commit install --config $(PRECOMMIT_CONFIG_PATH)
 	@echo "$(GREEN)Pre-commit hooks installed successfully.$(RESET)"
 
-lint-backend:
-	@echo "$(YELLOW)Running linters...$(RESET)"
-	@poetry run pre-commit run --files openhands/**/* agenthub/**/* evaluation/**/* --show-diff-on-failure --config $(PRE_COMMIT_CONFIG_PATH)
-
-lint-frontend:
-	@echo "$(YELLOW)Running linters for frontend...$(RESET)"
-	@cd frontend && npm run lint
-
 lint:
-	@$(MAKE) -s lint-frontend
-	@$(MAKE) -s lint-backend
-
-test-frontend:
-	@echo "$(YELLOW)Running tests for frontend...$(RESET)"
-	@cd frontend && npm run test
-
-test:
-	@$(MAKE) -s test-frontend
+	@echo "$(YELLOW)Running linters...$(RESET)"
+	@poetry run pre-commit run --files opendevin/**/* agenthub/**/* --show-diff-on-failure --config $(PRECOMMIT_CONFIG_PATH)
 
 build-frontend:
 	@echo "$(YELLOW)Building frontend...$(RESET)"
@@ -190,54 +117,29 @@ build-frontend:
 # Start backend
 start-backend:
 	@echo "$(YELLOW)Starting backend...$(RESET)"
-	@poetry run uvicorn openhands.server.listen:app --host $(BACKEND_HOST) --port $(BACKEND_PORT) --reload --reload-exclude "$(shell pwd)/workspace"
+	@poetry run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT)
 
 # Start frontend
 start-frontend:
 	@echo "$(YELLOW)Starting frontend...$(RESET)"
-	@cd frontend && VITE_BACKEND_HOST=$(BACKEND_HOST_PORT) VITE_FRONTEND_PORT=$(FRONTEND_PORT) npm run dev -- --port $(FRONTEND_PORT) --host $(BACKEND_HOST)
+	@cd frontend && BACKEND_HOST=$(BACKEND_HOST) FRONTEND_PORT=$(FRONTEND_PORT) npm run start
 
-# Common setup for running the app (non-callable)
-_run_setup:
+# Run the app
+run:
+	@echo "$(YELLOW)Running the app...$(RESET)"
 	@if [ "$(OS)" = "Windows_NT" ]; then \
-		echo "$(RED) Windows is not supported, use WSL instead!$(RESET)"; \
+		echo "$(RED)`make run` is not supported on Windows. Please run `make start-frontend` and `make start-backend` separately.$(RESET)"; \
 		exit 1; \
 	fi
 	@mkdir -p logs
 	@echo "$(YELLOW)Starting backend server...$(RESET)"
-	@poetry run uvicorn openhands.server.listen:app --host $(BACKEND_HOST) --port $(BACKEND_PORT) &
+	@poetry run uvicorn opendevin.server.listen:app --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.$(RESET)"
-
-# Run the app (standard mode)
-run:
-	@echo "$(YELLOW)Running the app...$(RESET)"
-	@$(MAKE) -s _run_setup
-	@$(MAKE) -s start-frontend
+	@cd frontend && echo "$(BLUE)Starting frontend with npm...$(RESET)" && npm run start -- --port $(FRONTEND_PORT)
 	@echo "$(GREEN)Application started successfully.$(RESET)"
 
-# Run the app (in docker)
-docker-run: WORKSPACE_BASE ?= $(PWD)/workspace
-docker-run:
-	@if [ -f /.dockerenv ]; then \
-		echo "Running inside a Docker container. Exiting..."; \
-		exit 0; \
-	else \
-		echo "$(YELLOW)Running the app in Docker $(OPTIONS)...$(RESET)"; \
-		export WORKSPACE_BASE=${WORKSPACE_BASE}; \
-		export SANDBOX_USER_ID=$(shell id -u); \
-		export DATE=$(shell date +%Y%m%d%H%M%S); \
-		docker compose up $(OPTIONS); \
-	fi
-
-# Run the app (WSL mode)
-run-wsl:
-	@echo "$(YELLOW)Running the app in WSL mode...$(RESET)"
-	@$(MAKE) -s _run_setup
-	@cd frontend && echo "$(BLUE)Starting frontend with npm (WSL mode)...$(RESET)" && npm run dev_wsl -- --port $(FRONTEND_PORT)
-	@echo "$(GREEN)Application started successfully in WSL mode.$(RESET)"
-
 # Setup config.toml
 setup-config:
 	@echo "$(YELLOW)Setting up config.toml...$(RESET)"
@@ -246,70 +148,34 @@ setup-config:
 	@echo "$(GREEN)Config.toml setup completed.$(RESET)"
 
 setup-config-prompts:
-	@echo "[core]" > $(CONFIG_FILE).tmp
-
-	@read -p "Enter your workspace directory (as absolute path) [default: $(DEFAULT_WORKSPACE_DIR)]: " workspace_dir; \
-	 workspace_dir=$${workspace_dir:-$(DEFAULT_WORKSPACE_DIR)}; \
-	 echo "workspace_base=\"$$workspace_dir\"" >> $(CONFIG_FILE).tmp
-
-	@echo "" >> $(CONFIG_FILE).tmp
-
-	@echo "[llm]" >> $(CONFIG_FILE).tmp
-	@read -p "Enter your LLM model name, used for running without UI. Set the model in the UI after you start the app. (see https://docs.litellm.ai/docs/providers for full list) [default: $(DEFAULT_MODEL)]: " llm_model; \
+	@read -p "Enter your LLM Model name (see https://docs.litellm.ai/docs/providers for full list) [default: $(DEFAULT_MODEL)]: " llm_model; \
 	 llm_model=$${llm_model:-$(DEFAULT_MODEL)}; \
-	 echo "model=\"$$llm_model\"" >> $(CONFIG_FILE).tmp
+	 echo "LLM_MODEL=\"$$llm_model\"" > $(CONFIG_FILE).tmp
 
-	@read -p "Enter your LLM api key: " llm_api_key; \
-	 echo "api_key=\"$$llm_api_key\"" >> $(CONFIG_FILE).tmp
+	@read -p "Enter your LLM API key: " llm_api_key; \
+	 echo "LLM_API_KEY=\"$$llm_api_key\"" >> $(CONFIG_FILE).tmp
 
-	@read -p "Enter your LLM base URL [mostly used for local LLMs, leave blank if not needed - example: http://localhost:5001/v1/]: " llm_base_url; \
-	 if [[ ! -z "$$llm_base_url" ]]; then echo "base_url=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; fi
+	@read -p "Enter your LLM Base URL [mostly used for local LLMs, leave blank if not needed - example: http://localhost:5001/v1/]: " llm_base_url; \
+	 if [[ ! -z "$$llm_base_url" ]]; then echo "LLM_BASE_URL=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; fi
 
-	@echo "Enter your LLM Embedding Model"; \
-		echo "Choices are:"; \
-		echo "  - openai"; \
-		echo "  - azureopenai"; \
-		echo "  - Embeddings available only with OllamaEmbedding:"; \
-		echo "    - llama2"; \
-		echo "    - mxbai-embed-large"; \
-		echo "    - nomic-embed-text"; \
-		echo "    - all-minilm"; \
-		echo "    - stable-code"; \
-		echo "    - bge-m3"; \
-		echo "    - bge-large"; \
-		echo "    - paraphrase-multilingual"; \
-		echo "    - snowflake-arctic-embed"; \
-		echo "  - Leave blank to default to 'BAAI/bge-small-en-v1.5' via huggingface"; \
-		read -p "> " llm_embedding_model; \
-		echo "embedding_model=\"$$llm_embedding_model\"" >> $(CONFIG_FILE).tmp; \
-		if [ "$$llm_embedding_model" = "llama2" ] || [ "$$llm_embedding_model" = "mxbai-embed-large" ] || [ "$$llm_embedding_model" = "nomic-embed-text" ] || [ "$$llm_embedding_model" = "all-minilm" ] || [ "$$llm_embedding_model" = "stable-code" ]; then \
-			read -p "Enter the local model URL for the embedding model (will set llm.embedding_base_url): " llm_embedding_base_url; \
-				echo "embedding_base_url=\"$$llm_embedding_base_url\"" >> $(CONFIG_FILE).tmp; \
+	@echo "Enter your LLM Embedding Model\nChoices are openai, azureopenai, llama2 or leave blank to default to 'BAAI/bge-small-en-v1.5' via huggingface"; \
+	 read -p "> " llm_embedding_model; \
+	 	echo "LLM_EMBEDDING_MODEL=\"$$llm_embedding_model\"" >> $(CONFIG_FILE).tmp; \
+		if [ "$$llm_embedding_model" = "llama2" ]; then \
+			read -p "Enter the local model URL (will overwrite LLM_BASE_URL): " llm_base_url; \
+				echo "LLM_BASE_URL=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
 		elif [ "$$llm_embedding_model" = "azureopenai" ]; then \
-			read -p "Enter the Azure endpoint URL (will overwrite llm.base_url): " llm_base_url; \
-				echo "base_url=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
-			read -p "Enter the Azure LLM Embedding Deployment Name: " llm_embedding_deployment_name; \
-				echo "embedding_deployment_name=\"$$llm_embedding_deployment_name\"" >> $(CONFIG_FILE).tmp; \
+			read -p "Enter the Azure endpoint URL (will overwrite LLM_BASE_URL): " llm_base_url; \
+				echo "LLM_BASE_URL=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
+			read -p "Enter the Azure LLM Deployment Name: " llm_deployment_name; \
+				echo "LLM_DEPLOYMENT_NAME=\"$$llm_deployment_name\"" >> $(CONFIG_FILE).tmp; \
 			read -p "Enter the Azure API Version: " llm_api_version; \
-				echo "api_version=\"$$llm_api_version\"" >> $(CONFIG_FILE).tmp; \
+				echo "LLM_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...$(RESET)"
-	@rm -rf openhands/.cache
-	@echo "$(GREEN)Caches cleaned up successfully.$(RESET)"
+	@read -p "Enter your workspace directory [default: $(DEFAULT_WORKSPACE_DIR)]: " workspace_dir; \
+	 workspace_dir=$${workspace_dir:-$(DEFAULT_WORKSPACE_DIR)}; \
+	 echo "WORKSPACE_BASE=\"$$workspace_dir\"" >> $(CONFIG_FILE).tmp
 
 # Help
 help:
@@ -317,16 +183,13 @@ 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 OpenHands by providing LLM API key,"
+	@echo "  $(GREEN)setup-config$(RESET)        - Setup the configuration for OpenDevin by providing LLM API key,"
 	@echo "                        LLM Model name, and workspace directory."
-	@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 "  $(GREEN)start-backend$(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 "                        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 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
+.PHONY: build check-dependencies check-python check-npm check-docker check-poetry pull-docker-image install-python-dependencies install-frontend-dependencies install-precommit-hooks lint start-backend start-frontend run setup-config setup-config-prompts help

README.md

@@ -1,137 +1,247 @@
+[English](README.md) | [中文](docs/README-zh.md)
+
 <a name="readme-top"></a>
+<!--
+*** Thanks for checking out the Best-README-Template. If you have a suggestion
+*** that would make this better, please fork the repo and create a pull request
+*** or simply open an issue with the tag "enhancement".
+*** Don't forget to give the project a star!
+*** Thanks again! Now go create something AMAZING! :D
+-->
+
+
+
+<!-- PROJECT SHIELDS -->
+<!--
+*** I'm using markdown "reference style" links for readability.
+*** Reference links are enclosed in brackets [ ] instead of parentheses ( ).
+*** See the bottom of this document for the declaration of the reference variables
+*** for contributors-url, forks-url, etc. This is an optional, concise syntax you may use.
+*** https://www.markdownguide.org/basic-syntax/#reference-style-links
+-->
 
 <div align="center">
-  <img src="./docs/static/img/logo.png" alt="Logo" width="200">
-  <h1 align="center">OpenHands: Code Less, Make More</h1>
+  <a href="https://github.com/OpenDevin/OpenDevin/graphs/contributors"><img src="https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge" alt="Contributors"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/network/members"><img src="https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge" alt="Forks"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/stargazers"><img src="https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge" alt="Stargazers"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/issues"><img src="https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge" alt="Issues"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE"><img src="https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge" alt="MIT License"></a>
+  </br>
+  <a href="https://join.slack.com/t/opendevin/shared_invite/zt-2etftj1dd-X1fDL2PYIVpsmJZkqEYANw"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
+  <a href="https://discord.gg/mBuDGRzzES"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
+</div>
+
+<!-- PROJECT LOGO -->
+<div align="center">
+  <img src="./logo.png" alt="Logo" width="200" height="200">
+  <h1 align="center">OpenDevin: Code Less, Make More</h1>
 </div>
 
 
-<div align="center">
-  <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/openhands-ai/shared_invite/zt-2wkh4pklz-w~h_DVDtEe9H5kyQlcNxVw"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
-  <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
-  <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="Credits"></a>
-  <br/>
-  <a href="https://docs.all-hands.dev/modules/usage/getting-started"><img src="https://img.shields.io/badge/Documentation-000?logo=googledocs&logoColor=FFE165&style=for-the-badge" alt="Check out the documentation"></a>
-  <a href="https://arxiv.org/abs/2407.16741"><img src="https://img.shields.io/badge/Paper%20on%20Arxiv-000?logoColor=FFE165&logo=arxiv&style=for-the-badge" alt="Paper on Arxiv"></a>
-  <a href="https://huggingface.co/spaces/OpenHands/evaluation"><img src="https://img.shields.io/badge/Benchmark%20score-000?logoColor=FFE165&logo=huggingface&style=for-the-badge" alt="Evaluation Benchmark Score"></a>
-  <hr>
-</div>
 
-Welcome to OpenHands (formerly OpenDevin), a platform for software development agents powered by AI.
 
-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.
+<!-- TABLE OF CONTENTS -->
+<details>
+  <summary>🗂️ Table of Contents</summary>
+  <ol>
+    <li><a href="#-mission">🎯 Mission</a></li>
+    <li><a href="#-what-is-devin">🤔 What is Devin?</a></li>
+    <li><a href="#-why-opendevin">🐚 Why OpenDevin?</a></li>
+    <li><a href="#-project-status">🚧 Project Status</a></li>
+      <a href="#-get-started">🚀 Get Started</a>
+      <ul>
+        <li><a href="#1-requirements">1. Requirements</a></li>
+        <li><a href="#2-build-and-setup">2. Build and Setup</a></li>
+        <li><a href="#3-run-the-application">3. Run the Application</a></li>
+        <li><a href="#4-individual-server-startup">4. Individual Server Startup</a></li>
+        <li><a href="#5-help">5. Help</a></li>
+      </ul>
+    </li>
+    <li><a href="#%EF%B8%8F-research-strategy">⭐️ Research Strategy</a></li>
+    <li><a href="#-how-to-contribute">🤝 How to Contribute</a></li>
+    <li><a href="#-join-our-community">🤖 Join Our Community</a></li>
+    <li><a href="#%EF%B8%8F-built-with">🛠️ Built With</a></li>
+    <li><a href="#-license">📜 License</a></li>
+  </ol>
+</details>
 
-Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or jump to the [Quick Start](#-quick-start).
+## 🎯 Mission
 
-> [!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.
+[Project Demo Video](https://github.com/OpenDevin/OpenDevin/assets/38853559/71a472cc-df34-430c-8b1d-4d7286c807c9)
 
-![App screenshot](./docs/static/img/screenshot.png)
 
-## ⚡ Quick Start
+Welcome to OpenDevin, an open-source project aiming to replicate Devin, an autonomous AI software engineer who is capable of executing complex engineering tasks and collaborating actively with users on software development projects. This project aspires to replicate, enhance, and innovate upon Devin through the power of the open-source community.
 
-The easiest way to run OpenHands is in Docker.
-See the [Installation](https://docs.all-hands.dev/modules/usage/installation) guide for
-system requirements and more information.
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
 
+## 🤔 What is Devin?
+Devin represents a cutting-edge autonomous agent designed to navigate the complexities of software engineering. It leverages a combination of tools such as a shell, code editor, and web browser, showcasing the untapped potential of LLMs in software development. Our goal is to explore and expand upon Devin's capabilities, identifying both its strengths and areas for improvement, to guide the progress of open code models.
+
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
+
+## 🐚 Why OpenDevin?
+The OpenDevin project is born out of a desire to replicate, enhance, and innovate beyond the original Devin model. By engaging the open-source community, we aim to tackle the challenges faced by Code LLMs in practical scenarios, producing works that significantly contribute to the community and pave the way for future advancements.
+
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
+
+## 🚧 Project Status
+
+OpenDevin is currently a work in progress, but you can already run the alpha version to see the end-to-end system in action. The project team is actively working on the following key milestones:
+
+- **UI**: Developing a user-friendly interface, including a chat interface, a shell demonstrating commands, and a web browser.
+- **Architecture**: Building a stable agent framework with a robust backend that can read, write, and run simple commands.
+- **Agent Capabilities**: Enhancing the agent's abilities to generate bash scripts, run tests, and perform other software engineering tasks.
+- **Evaluation**: Establishing a minimal evaluation pipeline that is consistent with Devin's evaluation criteria.
+
+After completing the MVP, the team will focus on research in various areas, including foundation models, specialist capabilities, evaluation, and agent studies.
+
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
+
+## ⚠️ Caveats and Warnings
+* OpenDevin is still an alpha project. It is changing very quickly and is unstable. We are working on getting a stable release out in the coming weeks.
+* OpenDevin will issue many prompts to the LLM you configure. Most of these LLMs cost money--be sure to set spending limits and monitor usage.
+* OpenDevin runs `bash` commands within a Docker sandbox, so it should not affect your machine. But your workspace directory will be attached to that sandbox, and files in the directory may be modified or deleted.
+* Our default Agent is currently the MonologueAgent, which has limited capabilities, but is fairly stable. We're working on other Agent implementations, including [SWE Agent](https://swe-agent.com/). You can [read about our current set of agents here](./docs/documentation/Agents.md).
+
+## 🚀 Get Started
+The easiest way to run OpenDevin is inside a Docker container.
+
+To start the app, run these commands, replacing `$(pwd)/workspace` with the path to the code you want OpenDevin to work with.
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik
+# Your OpenAI API key, or any other LLM API key
+export LLM_API_KEY="sk-..."
 
-docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
-    -e LOG_ALL_EVENTS=true \
+# The directory you want OpenDevin to modify. MUST be an absolute path!
+export WORKSPACE_DIR=$(pwd)/workspace
+
+docker run \
+    -e LLM_API_KEY \
+    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_DIR \
+    -v $WORKSPACE_DIR:/opt/workspace_base \
     -v /var/run/docker.sock:/var/run/docker.sock \
-    -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
-    --add-host host.docker.internal:host-gateway \
-    --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.17
+    ghcr.io/opendevin/opendevin:0.3.1
 ```
+You'll find opendevin running at `http://localhost:3000`.
 
-You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
+If you want to use the (unstable!) bleeding edge, you can use `ghcr.io/opendevin/opendevin:main` as the image.
 
-Finally, you'll need a model provider and API key.
-[Anthropic's Claude 3.5 Sonnet](https://www.anthropic.com/api) (`anthropic/claude-3-5-sonnet-20241022`)
-works best, but you have [many options](https://docs.all-hands.dev/modules/usage/llms).
+See [Development.md](Development.md) for instructions on running OpenDevin without Docker.
 
----
+## 🤖 LLM Backends
+OpenDevin can work with any LLM backend.
+For a full list of the LM providers and models available, please consult the
+[litellm documentation](https://docs.litellm.ai/docs/providers).
 
-You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes),
-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://github.com/All-Hands-AI/OpenHands/blob/main/openhands/resolver/README.md).
+The `LLM_MODEL` environment variable controls which model is used in programmatic interactions,
+but choosing a model in the OpenDevin UI will override this setting.
 
-Visit [Installation](https://docs.all-hands.dev/modules/usage/installation) for more information and setup instructions.
+The following environment variables might be necessary for some LLMs:
+* `LLM_API_KEY`
+* `LLM_BASE_URL`
+* `LLM_EMBEDDING_MODEL`
+* `LLM_DEPLOYMENT_NAME`
+* `LLM_API_VERSION`
 
-> [!CAUTION]
-> OpenHands is meant to be run by a single user on their local workstation.
-> It is not appropriate for multi-tenant deployments, where multiple users share the same instance--there is no built-in isolation or scalability.
->
-> If you're interested in running OpenHands in a multi-tenant environment, please
-> [get in touch with us](https://docs.google.com/forms/d/e/1FAIpQLSet3VbGaz8z32gW9Wm-Grl4jpt5WgMXPgJ4EDPVmCETCBpJtQ/viewform)
-> for advanced deployment options.
+**Note on Alternative Models:**
+Some alternative models may prove more challenging to tame than others.
+Fear not, brave adventurer! We shall soon unveil LLM-specific documentation to guide you on your quest.
+And if you've already mastered the art of wielding a model other than OpenAI's GPT,
+we encourage you to [share your setup instructions with us](https://github.com/OpenDevin/OpenDevin/issues/417).
 
-If you want to modify the OpenHands source code, check out [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
+There is also [documentation for running with local models using ollama](./docs/documentation/LOCAL_LLM_GUIDE.md).
 
-Having issues? The [Troubleshooting Guide](https://docs.all-hands.dev/modules/usage/troubleshooting) can help.
+## ⭐️ Research Strategy
 
-## 📖 Documentation
+Achieving full replication of production-grade applications with LLMs is a complex endeavor. Our strategy involves:
 
-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)**.
+1. **Core Technical Research:** Focusing on foundational research to understand and improve the technical aspects of code generation and handling.
+2. **Specialist Abilities:** Enhancing the effectiveness of core components through data curation, training methods, and more.
+3. **Task Planning:** Developing capabilities for bug detection, codebase management, and optimization.
+4. **Evaluation:** Establishing comprehensive evaluation metrics to better understand and improve our models.
 
-There you'll find resources on how to use different LLM providers,
-troubleshooting resources, and advanced configuration options.
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
 
-## 🤝 How to Join the Community
+## 🤝 How to Contribute
 
-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:
+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:
 
-- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-2wkh4pklz-w~h_DVDtEe9H5kyQlcNxVw) - 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.
+- **Code Contributions:** Help us develop the core functionalities, frontend interface, or sandboxing solutions.
+- **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in evaluating the models, or suggest improvements.
+- **Feedback and Testing:** Use the OpenDevin toolset, report bugs, suggest features, or provide feedback on usability.
 
-See more about the community in [COMMUNITY.md](./COMMUNITY.md) or find details on contributing in [CONTRIBUTING.md](./CONTRIBUTING.md).
+For details, please check [this document](./CONTRIBUTING.md).
 
-## 📈 Progress
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
 
-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).
+## 🤖 Join Our Community
 
-<p align="center">
-  <a href="https://star-history.com/#All-Hands-AI/OpenHands&Date">
-    <img src="https://api.star-history.com/svg?repos=All-Hands-AI/OpenHands&type=Date" width="500" alt="Star History Chart">
-  </a>
+Now we have both Slack workspace for the collaboration on building OpenDevin and Discord server for discussion about anything related, e.g., this project, LLM, agent, etc.
+
+* [Slack workspace](https://join.slack.com/t/opendevin/shared_invite/zt-2etftj1dd-X1fDL2PYIVpsmJZkqEYANw)
+* [Discord server](https://discord.gg/mBuDGRzzES)
+
+If you would love to contribute, feel free to join our community (note that now there is no need to fill in the [form](https://forms.gle/758d5p6Ve8r2nxxq6)). Let's simplify software engineering together!
+
+🐚 **Code less, make more with OpenDevin.**
+
+[![Star History Chart](https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date)](https://star-history.com/#OpenDevin/OpenDevin&Date)
+
+## 🛠️ Built With
+
+OpenDevin is built using a combination of powerful frameworks and libraries, providing a robust foundation for its development. Here are the key technologies used in the project:
+
+![FastAPI](https://img.shields.io/badge/FastAPI-black?style=for-the-badge) ![uvicorn](https://img.shields.io/badge/uvicorn-black?style=for-the-badge) ![LiteLLM](https://img.shields.io/badge/LiteLLM-black?style=for-the-badge) ![Docker](https://img.shields.io/badge/Docker-black?style=for-the-badge) ![Ruff](https://img.shields.io/badge/Ruff-black?style=for-the-badge) ![MyPy](https://img.shields.io/badge/MyPy-black?style=for-the-badge) ![LlamaIndex](https://img.shields.io/badge/LlamaIndex-black?style=for-the-badge) ![React](https://img.shields.io/badge/React-black?style=for-the-badge)
+
+Please note that the selection of these technologies is in progress, and additional technologies may be added or existing ones may be removed as the project evolves. We strive to adopt the most suitable and efficient tools to enhance the capabilities of OpenDevin.
+
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
 </p>
 
 ## 📜 License
 
 Distributed under the MIT License. See [`LICENSE`](./LICENSE) for more information.
 
-## 🙏 Acknowledgements
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
 
-OpenHands is built by a large number of contributors, and every contribution is greatly appreciated! We also build upon other open source projects, and we are deeply thankful for their work.
-
-For a list of open source projects and licenses used in OpenHands, please see our [CREDITS.md](./CREDITS.md) file.
-
-## 📚 Cite
-
-```
-@misc{openhands,
-      title={{OpenHands: An Open Platform for AI Software Developers as Generalist Agents}},
-      author={Xingyao Wang and Boxuan Li and Yufan Song and Frank F. Xu and Xiangru Tang and Mingchen Zhuge and Jiayi Pan and Yueqi Song and Bowen Li and Jaskirat Singh and Hoang H. Tran and Fuqiang Li and Ren Ma and Mingzhang Zheng and Bill Qian and Yanjun Shao and Niklas Muennighoff and Yizhe Zhang and Binyuan Hui and Junyang Lin and Robert Brennan and Hao Peng and Heng Ji and Graham Neubig},
-      year={2024},
-      eprint={2407.16741},
-      archivePrefix={arXiv},
-      primaryClass={cs.SE},
-      url={https://arxiv.org/abs/2407.16741},
-}
-```
+[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

agenthub/README.md

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

agenthub/SWE_agent/Examples.md

@@ -0,0 +1,405 @@
+# GPT-4 Examples:
+
+### Notes:
+- The final result is not completed as I only gave it 10 steps, but shows very promising use of the tools.
+- This whole run costs: $0.35 using gpt-4-turbo
+  - Input Tokens: 29,734
+  - Completion Tokens: 1,636
+
+Interesting things:
+1. Using comments as an initial placeholder for the next move and then having that output in memory is a very cool behavior.
+2. It makes very small iterative changes due to the prompting.
+3. A lot of the logic for the game is present but not put together well
+4. There are a lot of odd quirks with the code that it has written.
+5. Some odd agent behavior with putting random lines of code in random places?
+6. The structure of the feedback loop needs some improvement so the agent can see the changes it has made better in context.
+7. Might be beneficial to add in some line numbers so the model knows what lines it is looking at.
+
+
+```
+==============
+STEP 0
+
+PLAN:
+Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
+Usage(completion_tokens=91, prompt_tokens=2047, total_tokens=2138)
+
+==== RAW OUTPUT ====
+Thoughts:
+To start implementing Conway's Game of Life in Python using the pygame library, I first need to set up a Python script file where I can write the code. I'll create a new Python file named `game_of_life.py`. This file will serve as the base for writing the game logic and using pygame functionalities.
+
+Action:
+"""
+write game_of_life.py # This is a placeholder for the game of life implementation using pygame.
+"""
+
+==== END RAW ====
+
+
+ACTION:
+FileWriteAction(path='game_of_life.py', content='# This is a placeholder for the game of life implementation using pygame.', start=0, end=-1, thoughts="Thoughts:\nTo start implementing Conway's Game of Life in Python using the pygame library, I first need to set up a Python script file where I can write the code. I'll create a new Python file named `game_of_life.py`. This file will serve as the base for writing the game logic and using pygame functionalities.\n\nAction:", action=<ActionType.WRITE: 'write'>)
+
+OBSERVATION:
+WRITE OPERATION:
+You have written to "game_of_life.py" on these lines: 0:-1.
+
+
+==============
+STEP 1
+
+PLAN:
+Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
+Usage(completion_tokens=101, prompt_tokens=2351, total_tokens=2452)
+
+==== RAW OUTPUT ====
+Thoughts:
+The placeholder for the game of life implementation using pygame has been set up in the file `game_of_life.py`. The next step is to start implementing the basic structure of the game. This includes importing necessary libraries, initializing the pygame module, setting up the display window, and defining the main game loop. I will begin by importing pygame and initializing it, which are the foundational steps for any pygame application.
+
+Action:
+"""
+edit 0 0 import pygame
+
+pygame.init()
+"""
+
+==== END RAW ====
+
+
+ACTION:
+FileWriteAction(path='game_of_life.py', content='import pygame\n\npygame.init()', start=0, end=0, thoughts='Thoughts:\nThe placeholder for the game of life implementation using pygame has been set up in the file `game_of_life.py`. The next step is to start implementing the basic structure of the game. This includes importing necessary libraries, initializing the pygame module, setting up the display window, and defining the main game loop. I will begin by importing pygame and initializing it, which are the foundational steps for any pygame application.\n\nAction:', action=<ActionType.WRITE: 'write'>)
+
+OBSERVATION:
+WRITE OPERATION:
+You have written to "game_of_life.py" on these lines: 0:0.
+
+
+==============
+STEP 2
+
+PLAN:
+Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
+Usage(completion_tokens=123, prompt_tokens=2552, total_tokens=2675)
+
+==== RAW OUTPUT ====
+Thoughts:
+Previously, I initialized pygame in the `game_of_life.py` file. The next step is to set up the display window for the game. This involves defining the size of the window and setting the title. This is crucial as it provides the visual interface for the game. I will also add a comment to indicate that this is the setup for the display window.
+
+Action:
+"""
+edit 2 2
+# Setup the display window
+screen_size = (800, 600)
+screen = pygame.display.set_mode(screen_size)
+pygame.display.set_caption("Conway's Game of Life")
+"""
+==== END RAW ====
+
+
+ACTION:
+FileWriteAction(path='game_of_life.py', content='# Setup the display window\nscreen_size = (800, 600)\nscreen = pygame.display.set_mode(screen_size)\npygame.display.set_caption("Conway\'s Game of Life")', start=2, end=2, thoughts='Thoughts:\nPreviously, I initialized pygame in the `game_of_life.py` file. The next step is to set up the display window for the game. This involves defining the size of the window and setting the title. This is crucial as it provides the visual interface for the game. I will also add a comment to indicate that this is the setup for the display window.\n\nAction:', action=<ActionType.WRITE: 'write'>)
+
+OBSERVATION:
+WRITE OPERATION:
+You have written to "game_of_life.py" on these lines: 2:2.
+
+
+==============
+STEP 3
+
+PLAN:
+Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
+Usage(completion_tokens=144, prompt_tokens=2777, total_tokens=2921)
+
+==== RAW OUTPUT ====
+Thoughts:
+So far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame and setting up the display window. The next step is to define the main game loop where the game's logic will be continuously updated and rendered. This loop will handle events, update the game state, and redraw the screen. I will start by defining the main loop structure and a basic event handling mechanism to allow for quitting the game when the user presses the close button.
+
+Action:
+"""
+edit 5 5 # Main game loop
+running = True
+while running:
+    for event in pygame.event.get():
+        if event.type == pygame.QUIT:
+            running = False
+"""
+
+==== END RAW ====
+
+
+ACTION:
+FileWriteAction(path='game_of_life.py', content='# Main game loop\nrunning = True\nwhile running:\n    for event in pygame.event.get():\n        if event.type == pygame.QUIT:\n            running = False', start=5, end=5, thoughts="Thoughts:\nSo far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame and setting up the display window. The next step is to define the main game loop where the game's logic will be continuously updated and rendered. This loop will handle events, update the game state, and redraw the screen. I will start by defining the main loop structure and a basic event handling mechanism to allow for quitting the game when the user presses the close button.\n\nAction:", action=<ActionType.WRITE: 'write'>)
+
+OBSERVATION:
+WRITE OPERATION:
+You have written to "game_of_life.py" on these lines: 5:5.
+
+
+==============
+STEP 4
+
+PLAN:
+Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
+Usage(completion_tokens=222, prompt_tokens=3022, total_tokens=3244)
+
+==== RAW OUTPUT ====
+Thoughts:
+So far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, and defining the main game loop. The next step is to implement the logic for Conway's Game of Life. This involves creating a grid to represent the game state, initializing it with a random pattern, and defining the rules for cell survival, birth, and death. I will start by defining the grid size and initializing the grid with random states.
+
+Action:
+"""
+edit 7 7 # Define grid size and initialize grid
+grid_size = (50, 50)  # Grid size as a tuple (rows, columns)
+grid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]  # Initialize grid with zeros
+import random
+for y in range(grid_size[0]):
+    for x in range(grid_size[1]):
+        grid[y][x] = random.randint(0, 1)  # Randomly assign cells as alive (1) or dead (0)
+"""
+==== END RAW ====
+
+
+ACTION:
+FileWriteAction(path='game_of_life.py', content='# Define grid size and initialize grid\ngrid_size = (50, 50)  # Grid size as a tuple (rows, columns)\ngrid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]  # Initialize grid with zeros\nimport random\nfor y in range(grid_size[0]):\n    for x in range(grid_size[1]):\n        grid[y][x] = random.randint(0, 1)  # Randomly assign cells as alive (1) or dead (0)', start=7, end=7, thoughts="Thoughts:\nSo far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, and defining the main game loop. The next step is to implement the logic for Conway's Game of Life. This involves creating a grid to represent the game state, initializing it with a random pattern, and defining the rules for cell survival, birth, and death. I will start by defining the grid size and initializing the grid with random states.\n\nAction:", action=<ActionType.WRITE: 'write'>)
+
+OBSERVATION:
+WRITE OPERATION:
+You have written to "game_of_life.py" on these lines: 7:7.
+
+
+==============
+STEP 5
+
+PLAN:
+Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
+Usage(completion_tokens=234, prompt_tokens=3158, total_tokens=3392)
+
+==== RAW OUTPUT ====
+Thoughts:
+So far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, and initializing the grid with random states. The next step is to implement the rules for Conway's Game of Life. This involves checking each cell's neighbors to determine its next state based on the number of alive neighbors. I will start by defining a function to count the alive neighbors for a given cell.
+
+Action:
+"""
+edit 9 9 def count_alive_neighbors(grid, x, y):
+    directions = [(-1, -1), (-1, 0), (-1, 1), (0, -1), (0, 1), (1, -1), (1, 0), (1, 1)]
+    count = 0
+    for dx, dy in directions:
+        nx, ny = x + dx, y + dy
+        if 0 <= nx < grid_size[1] and 0 <= ny < grid_size[0]:
+            count += grid[ny][nx]
+    return count
+"""
+
+==== END RAW ====
+
+
+ACTION:
+FileWriteAction(path='game_of_life.py', content='def count_alive_neighbors(grid, x, y):\n    directions = [(-1, -1), (-1, 0), (-1, 1), (0, -1), (0, 1), (1, -1), (1, 0), (1, 1)]\n    count = 0\n    for dx, dy in directions:\n        nx, ny = x + dx, y + dy\n        if 0 <= nx < grid_size[1] and 0 <= ny < grid_size[0]:\n            count += grid[ny][nx]\n    return count', start=9, end=9, thoughts="Thoughts:\nSo far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, and initializing the grid with random states. The next step is to implement the rules for Conway's Game of Life. This involves checking each cell's neighbors to determine its next state based on the number of alive neighbors. I will start by defining a function to count the alive neighbors for a given cell.\n\nAction:", action=<ActionType.WRITE: 'write'>)
+
+OBSERVATION:
+WRITE OPERATION:
+You have written to "game_of_life.py" on these lines: 9:9.
+
+
+==============
+STEP 6
+
+PLAN:
+Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
+Usage(completion_tokens=257, prompt_tokens=3290, total_tokens=3547)
+
+==== RAW OUTPUT ====
+Thoughts:
+So far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating a function to count alive neighbors. The next step is to implement the rules for Conway's Game of Life. This involves updating the grid state based on the number of alive neighbors each cell has. I will define a function `update_grid` that applies the rules of the game to update the grid for the next generation.
+
+Action:
+"""
+write game_of_life.py def update_grid(grid):
+    new_grid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]
+    for y in range(grid_size[0]):
+        for x in range(grid_size[1]):
+            alive_neighbors = count_alive_neighbors(grid, x, y)
+            if grid[y][x] == 1 and (alive_neighbors == 2 or alive_neighbors == 3):
+                new_grid[y][x] = 1
+            elif grid[y][x] == 0 and alive_neighbors == 3:
+                new_grid[y][x] = 1
+    return new_grid
+ 11
+ 11
+"""
+==== END RAW ====
+
+
+ACTION:
+FileWriteAction(path='game_of_life.py', content='def update_grid(grid):\n    new_grid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]\n    for y in range(grid_size[0]):\n        for x in range(grid_size[1]):\n            alive_neighbors = count_alive_neighbors(grid, x, y)\n            if grid[y][x] == 1 and (alive_neighbors == 2 or alive_neighbors == 3):\n                new_grid[y][x] = 1\n            elif grid[y][x] == 0 and alive_neighbors == 3:\n                new_grid[y][x] = 1\n    return new_grid', start=11, end=11, thoughts="Thoughts:\nSo far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating a function to count alive neighbors. The next step is to implement the rules for Conway's Game of Life. This involves updating the grid state based on the number of alive neighbors each cell has. I will define a function `update_grid` that applies the rules of the game to update the grid for the next generation.\n\nAction:", action=<ActionType.WRITE: 'write'>)
+
+OBSERVATION:
+WRITE OPERATION:
+You have written to "game_of_life.py" on these lines: 11:11.
+
+
+==============
+STEP 7
+
+PLAN:
+Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
+Usage(completion_tokens=124, prompt_tokens=3416, total_tokens=3540)
+
+==== RAW OUTPUT ====
+Thoughts:
+So far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating functions to count alive neighbors and update the grid. The next step is to integrate the `update_grid` function into the main game loop to continuously update the state of the grid based on the game rules. This will allow the game to evolve over time, showing different generations of the cell population.
+
+Action:
+"""
+edit 6 6
+    grid = update_grid(grid)
+"""
+==== END RAW ====
+
+
+ACTION:
+FileWriteAction(path='game_of_life.py', content='grid = update_grid(grid)', start=6, end=6, thoughts="Thoughts:\nSo far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating functions to count alive neighbors and update the grid. The next step is to integrate the `update_grid` function into the main game loop to continuously update the state of the grid based on the game rules. This will allow the game to evolve over time, showing different generations of the cell population.\n\nAction:", action=<ActionType.WRITE: 'write'>)
+
+OBSERVATION:
+WRITE OPERATION:
+You have written to "game_of_life.py" on these lines: 6:6.
+
+
+==============
+STEP 8
+
+PLAN:
+Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
+Usage(completion_tokens=166, prompt_tokens=3393, total_tokens=3559)
+
+==== RAW OUTPUT ====
+Thoughts:
+So far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating functions to count alive neighbors and update the grid. The next step is to integrate the `update_grid` function into the main game loop to continuously update the state of the grid based on the game rules. This will allow the game to evolve over time, showing different generations of the cell population. I need to ensure that the `update_grid` function is called within the main game loop and that the display is updated accordingly. I will start by checking the current content of the main game loop to see where to integrate the `update_grid` function.
+
+Action:
+"""
+goto 6
+"""
+==== END RAW ====
+
+
+ACTION:
+FileReadAction(path='game_of_life.py', start=6, end=106, thoughts="Thoughts:\nSo far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating functions to count alive neighbors and update the grid. The next step is to integrate the `update_grid` function into the main game loop to continuously update the state of the grid based on the game rules. This will allow the game to evolve over time, showing different generations of the cell population. I need to ensure that the `update_grid` function is called within the main game loop and that the display is updated accordingly. I will start by checking the current content of the main game loop to see where to integrate the `update_grid` function.\n\nAction:", action=<ActionType.READ: 'read'>)
+
+OBSERVATION:
+grid = update_grid(grid)
+running = True
+# Define grid size and initialize grid
+grid_size = (50, 50)  # Grid size as a tuple (rows, columns)
+def count_alive_neighbors(grid, x, y):
+    directions = [(-1, -1), (-1, 0), (-1, 1), (0, -1), (0, 1), (1, -1), (1, 0), (1, 1)]
+def update_grid(grid):
+    new_grid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]
+    for y in range(grid_size[0]):
+        for x in range(grid_size[1]):
+            alive_neighbors = count_alive_neighbors(grid, x, y)
+            if grid[y][x] == 1 and (alive_neighbors == 2 or alive_neighbors == 3):
+                new_grid[y][x] = 1
+            elif grid[y][x] == 0 and alive_neighbors == 3:
+                new_grid[y][x] = 1
+    return new_grid
+    count = 0
+    for dx, dy in directions:
+        nx, ny = x + dx, y + dy
+        if 0 <= nx < grid_size[1] and 0 <= ny < grid_size[0]:
+            count += grid[ny][nx]
+    return count
+grid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]  # Initialize grid with zeros
+import random
+for y in range(grid_size[0]):
+    for x in range(grid_size[1]):
+        grid[y][x] = random.randint(0, 1)  # Randomly assign cells as alive (1) or dead (0)
+while running:
+    for event in pygame.event.get():
+        if event.type == pygame.QUIT:
+            running = False
+pygame.display.set_caption("Conway's Game of Life")
+pygame.init()
+
+
+
+==============
+STEP 9
+
+PLAN:
+Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
+Usage(completion_tokens=174, prompt_tokens=3728, total_tokens=3902)
+
+==== RAW OUTPUT ====
+Thoughts:
+From the previous actions, it seems that the basic structure for Conway's Game of Life using pygame has been set up, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating functions to count alive neighbors and update the grid. The next step is to ensure that the game loop properly updates the grid and refreshes the display to show the new state of the grid in each iteration. This involves calling `pygame.display.update()` to update the entire screen and using `pygame.time.Clock()` to control the frame rate. I will start by adding these necessary updates to the game loop.
+
+Action:
+"""
+edit 95 95
+    pygame.display.update()
+    clock = pygame.time.Clock()
+    clock.tick(10)  # Control the frame rate (10 frames per second)
+"""
+
+==== END RAW ====
+
+
+ACTION:
+FileWriteAction(path='game_of_life.py', content='pygame.display.update()\n    clock = pygame.time.Clock()\n    clock.tick(10)  # Control the frame rate (10 frames per second)', start=95, end=95, thoughts="Thoughts:\nFrom the previous actions, it seems that the basic structure for Conway's Game of Life using pygame has been set up, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating functions to count alive neighbors and update the grid. The next step is to ensure that the game loop properly updates the grid and refreshes the display to show the new state of the grid in each iteration. This involves calling `pygame.display.update()` to update the entire screen and using `pygame.time.Clock()` to control the frame rate. I will start by adding these necessary updates to the game loop.\n\nAction:", action=<ActionType.WRITE: 'write'>)
+
+OBSERVATION:
+WRITE OPERATION:
+You have written to "game_of_life.py" on these lines: 95:95.
+16:43:55 - opendevin:INFO: agent_controller.py:125 - Exited before finishing the task.
+
+
+```
+
+## Result:
+
+```
+import pygame
+
+# Setup the display window
+screen_size = (800, 600)
+screen = pygame.display.set_mode(screen_size)
+# Main game loop
+grid = update_grid(grid)
+running = True
+# Define grid size and initialize grid
+grid_size = (50, 50)  # Grid size as a tuple (rows, columns)
+def count_alive_neighbors(grid, x, y):
+    directions = [(-1, -1), (-1, 0), (-1, 1), (0, -1), (0, 1), (1, -1), (1, 0), (1, 1)]
+def update_grid(grid):
+    new_grid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]
+    for y in range(grid_size[0]):
+        for x in range(grid_size[1]):
+            alive_neighbors = count_alive_neighbors(grid, x, y)
+            if grid[y][x] == 1 and (alive_neighbors == 2 or alive_neighbors == 3):
+                new_grid[y][x] = 1
+            elif grid[y][x] == 0 and alive_neighbors == 3:
+                new_grid[y][x] = 1
+    return new_grid
+    count = 0
+    for dx, dy in directions:
+        nx, ny = x + dx, y + dy
+        if 0 <= nx < grid_size[1] and 0 <= ny < grid_size[0]:
+            count += grid[ny][nx]
+    return count
+grid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]  # Initialize grid with zeros
+import random
+for y in range(grid_size[0]):
+    for x in range(grid_size[1]):
+        grid[y][x] = random.randint(0, 1)  # Randomly assign cells as alive (1) or dead (0)
+while running:
+    for event in pygame.event.get():
+        if event.type == pygame.QUIT:
+            running = False
+pygame.display.set_caption("Conway's Game of Life")
+pygame.init()
+# This is a placeholder for the game of life implementation using pygame.pygame.display.update()
+    clock = pygame.time.Clock()
+    clock.tick(10)  # Control the frame rate (10 frames per second)
+
+```

agenthub/SWE_agent/__init__.py

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

agenthub/SWE_agent/agent.py

@@ -0,0 +1,112 @@
+from typing import List
+from opendevin.agent import Agent
+from opendevin.llm.llm import LLM
+from opendevin.state import State
+from opendevin.action import (
+    Action,
+    AgentThinkAction,
+    FileReadAction,
+    FileWriteAction,
+)
+from opendevin.observation import Observation
+
+from .parser import parse_command
+
+from .prompts import (
+    SYSTEM_MESSAGE,
+    STEP_PROMPT,
+    MEMORY_FORMAT,
+    NO_ACTION,
+    CONTEXT_PROMPT
+)
+
+
+class SWEAgent(Agent):
+    """
+    An attempt to recreate swe_agent with output parsing, prompting style, and Application Computer Interface (ACI).
+
+    SWE-agent includes ACI functions like 'goto', 'search_for', 'edit', 'scroll', 'run'
+    """
+
+    def __init__(self, llm: LLM):
+        super().__init__(llm)
+        self.memory_window = 4
+        self.max_retries = 2
+        self.running_memory: List[str] = []
+        self.cur_file: str = ''
+        self.cur_line: int = 0
+
+    def _remember(self, action: Action, observation: Observation) -> None:
+        """Agent has a limited memory of the few steps implemented as a queue"""
+        memory = MEMORY_FORMAT(action.to_dict(), observation.to_dict())
+        self.running_memory.append(memory)
+
+    def _think_act(self, messages: List[dict]) -> tuple[Action, str]:
+        resp = self.llm.completion(
+            messages=messages,
+            temperature=0.05,
+        )
+        action_resp = resp['choices'][0]['message']['content']
+        print(f"\033[1m\033[91m{resp['usage']}\033[0m")
+        print('\n==== RAW OUTPUT ====',
+              f'\033[96m{action_resp}\033[0m',
+              '==== END RAW ====\n', sep='\n')
+        return parse_command(action_resp, self.cur_file, self.cur_line)
+
+    def _update(self, action: Action) -> None:
+        if isinstance(action, (FileReadAction, FileWriteAction)):
+            self.cur_file = action.path
+            self.cur_line = action.start
+
+    def step(self, state: State) -> Action:
+        """
+        SWE-Agent step:
+            1. Get context - past actions, custom commands, current step
+            2. Perform think-act - prompt model for action and reasoning
+            3. Catch errors - ensure model takes action (5 attempts max)
+        """
+        for prev_action, obs in state.updated_info:
+            self._remember(prev_action, obs)
+
+        prompt = STEP_PROMPT(
+            state.plan.main_goal,
+            self.cur_file,
+            self.cur_line
+        )
+
+        msgs = [
+            {'content': SYSTEM_MESSAGE, 'role': 'user'},
+            {'content': prompt, 'role': 'user'}
+        ]
+
+        if len(self.running_memory) > 0:
+            context = CONTEXT_PROMPT(
+                self.running_memory,
+                self.memory_window
+            )
+            msgs.insert(1, {'content': context, 'role': 'user'})
+        # clrs = [''] * (len(msgs)-2) + ['\033[0;36m', '\033[0;35m']
+        # print('\n\n'.join([c+m['content']+'\033[0m' for c, m in zip(clrs, msgs)]))
+        action, thought = self._think_act(messages=msgs)
+
+        start_msg_len = len(msgs)
+        while not action and len(msgs) < self.max_retries + start_msg_len:
+            error = NO_ACTION(thought)
+            error_msg = {'content': error, 'role': 'user'}
+            msgs.append(error_msg)
+            action, thought = self._think_act(messages=msgs)
+
+        if not action:
+            action = AgentThinkAction(thought)
+
+        self._update(action)
+        self.latest_action = action
+        return action
+
+    def search_memory(self, query: str) -> List[str]:
+        return [item for item in self.running_memory if query in item]
+
+    def reset(self) -> None:
+        """Used to reset the agent"""
+        self.running_memory = []
+        super().reset()

agenthub/SWE_agent/parser.py

@@ -0,0 +1,164 @@
+from opendevin.action import (
+    Action,
+    AgentFinishAction,
+    CmdRunAction,
+    FileReadAction,
+    FileWriteAction,
+    BrowseURLAction,
+    AgentEchoAction,
+    AgentThinkAction,
+)
+
+import re
+
+from .prompts import CUSTOM_DOCS, COMMAND_USAGE
+
+# commands: exit, read, write, browse, kill, search_file, search_dir
+
+no_open_file_error = AgentEchoAction(
+    'You are not currently in a file. You can use the read command to open a file and then use goto to navigate through it.')
+
+
+def invalid_error(cmd, docs):
+    return f'''ERROR:
+Invalid command structure for
+```
+{cmd}
+```
+You may have caused this error by having multiple commands within your command block.
+If so, try again by running only one of the commands:
+
+Try again using this format:
+{COMMAND_USAGE[docs]}
+'''
+
+
+def get_action_from_string(command_string: str, path: str, line: int, thoughts: str = '') -> Action | None:
+    """
+    Parses the command string to find which command the agent wants to run
+    Converts the command into a proper Action and returns
+    """
+    vars = command_string.split(' ')
+    cmd = vars[0]
+    args = [] if len(vars) == 1 else vars[1:]
+
+    if 'exit' == cmd:
+        return AgentFinishAction()
+
+    elif 'think' == cmd:
+        return AgentThinkAction(' '.join(args))
+
+    elif 'scroll_up' == cmd:
+        if not path:
+            return no_open_file_error
+        return FileReadAction(path, line + 100, line + 200, thoughts)
+
+    elif 'scroll_down' == cmd:
+        if not path:
+            return no_open_file_error
+        return FileReadAction(path, line - 100, line, thoughts)
+
+    elif 'goto' == cmd:
+        if not path:
+            return no_open_file_error
+        rex = r'^goto\s+(\d+)$'
+        valid = re.match(rex, command_string)
+        if valid:
+            start = int(valid.group(1))
+            end = start + 100
+            return FileReadAction(path, start, end, thoughts)
+        else:
+            return AgentEchoAction(invalid_error(command_string, 'goto'))
+
+    elif 'edit' == cmd:
+        if not path:
+            return no_open_file_error
+        rex = r'^edit\s+(\d+)\s+(-?\d+)\s+(\S.*)$'
+        valid = re.match(rex, command_string, re.DOTALL)
+        if valid:
+            start = int(valid.group(1))
+            end = int(valid.group(2))
+            change = valid.group(3)
+            if '"' == change[-1] and '"' == change[0]:
+                change = change[1:-1]
+            return FileWriteAction(path, change, start, end, thoughts)
+        else:
+            return AgentEchoAction(invalid_error(command_string, 'edit'))
+
+    elif 'read' == cmd:
+        rex = r'^read\s+(\S+)(?:\s+(\d+))?(?:\s+(-?\d+))?$'
+        valid = re.match(rex, command_string, re.DOTALL)
+        if valid:
+            file = valid.group(1)
+            start_str = valid.group(2)
+            end_str = valid.group(3)
+
+            start = 0 if not start_str else int(start_str)
+            end = -1 if not end_str else int(end_str)
+
+            return FileReadAction(file, start, end, thoughts)
+        else:
+            return AgentEchoAction(invalid_error(command_string, 'read'))
+
+    elif 'write' == cmd:
+        rex = r'^write\s+(\S+)\s+(.*?)\s*(\d+)?\s*(-?\d+)?$'
+        valid = re.match(rex, command_string, re.DOTALL)
+
+        if valid:
+            file = valid.group(1)
+            content = valid.group(2)
+            start_str = valid.group(3)
+            end_str = valid.group(4)
+
+            start = 0 if not start_str else int(start_str)
+            end = -1 if not end_str else int(end_str)
+
+            if '"' == content[-1] and '"' == content[0]:
+                content = content[1:-1]
+
+            return FileWriteAction(file, content, start, end, thoughts)
+        else:
+            return AgentEchoAction(invalid_error(command_string, 'write'))
+
+    elif 'browse' == cmd:
+        return BrowseURLAction(args[0].strip())
+
+    elif cmd in ['search_file', 'search_dir', 'find_file']:
+        rex = r'^(search_file|search_dir|find_file)\s+(\S+)(?:\s+(\S+))?$'
+        valid = re.match(rex, command_string, re.DOTALL)
+        if valid:
+            return CmdRunAction(command_string)
+        else:
+            return AgentEchoAction(f'Invalid command structure for\n ```\n{command_string}\n```.\nTry again using this format:\n{CUSTOM_DOCS}')
+    else:
+        # check bash command
+        obs = str(CmdRunAction(f'type {cmd}'))
+        if obs.split(':')[-1].strip() == 'not found':
+            # echo not found error for llm
+            return AgentEchoAction(content=obs)
+        else:
+            # run valid command
+            return CmdRunAction(command_string)
+
+
+def parse_command(input_str: str, path: str, line: int):
+    """
+    Parses a given string and separates the command (enclosed in triple backticks) from any accompanying text.
+
+    Args:
+        input_str (str): The input string to be parsed.
+
+    Returns:
+        tuple: A tuple containing the command and the accompanying text (if any).
+    """
+    input_str = input_str.strip()
+    if '```' in input_str:
+        parts = input_str.split('```')
+        command_str = parts[1].strip()
+        ind = 2 if len(parts) > 2 else 1
+        accompanying_text = ''.join(parts[:-ind]).strip()
+        action = get_action_from_string(
+            command_str, path, line, accompanying_text)
+        if action:
+            return action, accompanying_text
+    return None, input_str  # used for retry

agenthub/SWE_agent/prompts.py

@@ -0,0 +1,205 @@
+from opendevin.parse_commands import parse_command_file
+
+DEFAULT_COMMANDS_DICT = {
+    'exit': 'Executed when task is complete',
+    'read <file_name> [<start_line>] [<end_line>]': 'Shows a given file\'s contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. By default the whole file will be read.',
+    'write <file> <changes> [<start_line>] [<end_line>]': 'Modifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>. Default start_line = 0 and end_line = -1. Calling this with no line args will replace the whole file.',
+    'browse <url>': 'Returns the text version of any url, this can be useful to look up documentation or finding issues on github',
+    'scroll_up': 'Takes no arguments. This will scroll up and show you the 100 lines above your current lines',
+    'scroll_down': 'Takes no arguments. This will scroll down and show you the 100 lines below your current lines',
+    'edit <start_line> <end_line> <changes>': 'This will modify lines in the currently open file. use start_line and end_line to designate which lines to change and then write the multiline changes',
+    'goto <line_num>': 'This will take you directly to a line and show you the 100 lines below it.',
+    '<bash_command> <args>': 'You can use any bash command you need (cd, ls, rm, grep, dir, mv, wget, git, zip, etc.) with their arguments included',
+    'pip install <package>': 'You can use this to import python packages. Make sure you include the correct package name when using this command.',
+    'ls': 'Use the ls command to view all the files in your current directory, this is a good starting point.',
+    'NOT ALLOWED': 'You cannot use interactive commands like python or node'
+}
+
+COMMAND_USAGE = {
+    'exit': 'Usage:\n```\nexit\n```\nExecuted when task is complete',
+    'read': 'Args:\n<file_name> [<start_line>] [<end_line>]\nUsage:\n```\nread file.py\n```\nor\n```\nread example.py <start_line> <end_line>\n```\nShows a given file\'s contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. by default the whole file will be read.',
+    'write': 'Args:\n<file> <changes> [<start_line>] [<end_line>]\nUsage:\n```\nwrite "def main():\n    print("This is line one")" 0 2\n```\nModifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>. Default start_line = 0 and end_line = -1. Calling this with no line args will replace the whole file.',
+    'edit': 'Args:\n<start_line> <end_line> <changes>\nUsage:\n```\nedit 0 1 import pandas as pd\n```\nThis will modify the current file you are in with the changes you make between the line numbers you designate',
+    'goto': 'Args:\n<line_num>\nUsage:\n```\ngoto <line_num>\n```\nThis will show you the 100 lines below and including the line you specify within your current file.',
+    'scroll_up': 'Usage:\n```\nscroll_up\n```\nThis will return the 100 lines above where you are currently at',
+    'scroll_down': 'Usage:\n```\nscroll_down\n```\nThis will return the 100 line below where you are currently at',
+    'browse': 'Args:\n<url>\nUsage:\n```\nbrowse https://github.com/OpenDevin/OpenDevin\n```\nThis will fetch the Text elements from the given url and show them to you.',
+}
+
+DEFAULT_COMMANDS = '\n'.join(
+    [k + ' - ' + v for k, v in DEFAULT_COMMANDS_DICT.items()])
+
+CUSTOM_DOCS = parse_command_file()
+
+CUSTOM_COMMANDS = f"""Custom bash commands:
+{CUSTOM_DOCS}
+"""
+
+DOCUMENTATION = f"""DOCUMENTATION:
+It is recommend that you use the commands provided for interacting with files and your directory because they have been specially built for you.
+They will make it much easier for you to look at files and make changes. Using these commands will help you be better at your task.
+You can open an file by using either the read or write operations.
+- If a file already exists you should read it before making any changes. Use the `edit` command to make changes once you have read it.
+- If you are creating a new file use the write command. Use the `edit` command to make changes once you have created the new file.
+
+Commands:
+{DEFAULT_COMMANDS}
+{CUSTOM_COMMANDS}
+
+The following commands require an open file to be used: edit, scroll_up, scroll_down, goto
+To modify the current file use 'edit'. To move through the current file use 'goto' or 'scroll_up'/'scroll_down'
+when using write and edit do not surround the code with any "" just write the code.
+"""
+
+GENERAL_GUIDELINES = '''INSTRUCTIONS:
+Now, you're going to solve this issue on your own. You can use any bash commands or custom commands you wish to complete your task. Edit all the files you need to and run any checks or tests that you want.
+Remember, YOU CAN ONLY ENTER ONE COMMAND AT A TIME. You should always wait for feedback after every command.
+When you're satisfied with all of the changes you've made, you can indicate that you are done by running the exit command.
+Note however that you cannot use any interactive session commands (e.g. python, vim, node) in this environment, but you can write scripts and run them. E.g. you can write a python script and then run it with `python <script_name>.py`.
+
+NOTE ABOUT THE write COMMAND: Indentation really matters! When editing a file, make sure to insert appropriate indentation before each line!
+
+IMPORTANT TIPS:
+1. Reproduce the bug: Always start by trying to replicate the bug that the issue discusses. If the issue includes code for reproducing the bug, we recommend that you re-implement that in your environment and run it to ensure you can reproduce the bug. Then, start trying to fix it. When you think you've fixed the bug, re-run the bug reproduction script to make sure that the issue has indeed been resolved.
+   If the bug reproduction script does not print anything when it successfully runs, we recommend adding a print("Script completed successfully, no errors.") command at the end of the file, so that you can be sure the script ran fine all the way through.
+2. Try different commands: If you run a command and it doesn't work, try running a different command. A command that did not work once will not work the second time unless you modify it.
+3. Navigate large files: If you open a file and need to get to an area around a specific line that is not in the first 100 lines, say line 583, you would use the 'read' command like this: 'read <file> 583'. This is a much faster way to read through the file.
+4. Handle input files: If the bug reproduction script requires inputting/reading a specific file, such as 'buggy-input.png', and you'd like to understand how to input that file, conduct a search in the existing repository code to see whether someone else has already done that. Do this by running the command: 'search_dir "buggy-input.png"'. If that doesn't work, use the Linux 'find' command.
+5. Understand your context: Always make sure to look at the currently open file and the current working directory. The currently open file might be in a different directory than the working directory.
+6. Verify your edits: When editing files, it is easy to accidentally specify a wrong line number or to write code with incorrect indentation. Always check the code after you issue an edit to make sure that it reflects what you wanted to accomplish. If it didn't, issue another command to fix it.
+7. Thoroughly test your solution: After making any changes to fix a bug, be sure to thoroughly test your solution to ensure the bug has been resolved. Re-run the bug reproduction script and verify that the issue has been addressed.
+'''
+
+RESPONSE_FORMAT = '''RESPONSE FORMAT:
+This is the format of the response you will make in order to solve the current issue.
+You will be given multiple iterations to complete this task so break it into steps and solve them one by one.
+
+Your output must contain the following:
+- First, thoughts about what your next action should be and plan it out.
+    - You will have a memory of your thoughts so you can use this to remember things for the next step.
+    - Use your thoughts to think about what you are currently doing, what you have done on prior steps and how that relates to solving the problem.
+- Second, create a piece of code that will execute your next action based on the thoughts you have.
+    - Remember that you can only have one action for each thought, do not include multiple actions.
+
+Your code MUST be surrounded in triple back ticks EXACTLY like this:
+```
+<code>
+```
+
+Notes:
+- Adhere to the format so that the program loop continues smoothly, it is very important to only give one command per output.
+- DO NOT give more than one command within the triple backticks. This will just throw an error and nothing will happen as a result.
+- Do not give multiple code blocks, if you do only the second one will be captured and run, this might give an error if the first one was necessary.
+- To execute multiple commands you should write them down in your thoughts section so you can remember it on the next step and execute them then.
+- The only commands you are not capable of executing are interactive commands like `python` or `node` by themselves.
+- If you think that you have completed the task that has been given to you based on your previous actions and outputs then use ``` exit ``` as the command to let the system know that you are done.
+- DO NOT make any copies of your previous memories those will be provided to you at each step, making copies just wastes time and energy. Think smarter not harder.
+- The write and edit commands requires proper indentation in the content section ex. `write hw.py def hello():\n    print(\'Hello World\')` this is how you would have to format your write command.
+    - The white spaces matter as the code changes will be added to the code so they must have proper syntax.
+
+This is a template using the format described above
+Items in <> are suggestions for you, fill them out based on the context of the problem you are solving.
+
+[ FORMAT ]
+Thoughts:
+<Provide clear and concise thoughts on the next step to take, highlighting any important details or context that should be remembered.>
+<You can use multiple lines to express your thoughts>
+
+Action:
+```
+<command> <params>
+```
+[ END FORMAT ]
+
+Do not provide anything extra just your thought and action.
+'''
+
+SYSTEM_MESSAGE = f'''SYSTEM INFO:
+You am an autonomous coding agent, here to provide solutions for coding issues.
+You have been designed to assist you with a wide range of programming tasks, from code editing and debugging to testing and deployment.
+You have access to a variety of tools and commands that you can use to help you solve problems efficiently.
+
+{GENERAL_GUIDELINES}
+
+{DOCUMENTATION}
+'''.strip()
+
+
+def NO_ACTION(latest): return f'''
+You did not include any action to take in your most recent output:
+
+===== Output ======
+{latest}
+==== End Output ===
+
+Remember these are the custom commands you can use:
+{DOCUMENTATION}
+
+Lets try that again, it is very important that you adhere to the output format
+This time, be sure to use the exact format below, replacing anything in <> with the appropriate value(s):
+{RESPONSE_FORMAT}
+
+It is crucial you use the format provided as the output will be parsed automatically.
+'''
+
+
+def file_info(file: str, line: int):
+    if file:
+        return f'''CURRENT WORKSPACE:
+    Open File: {file} on line {line}
+    You can use these commands with the current file:
+    Navigation: `scroll_up`, `scroll_down`, and `goto <line>`
+    Modification: `edit <start_line> <end_line> <changes>`
+    '''
+
+
+def STEP_PROMPT(task, file, line_num): return f'''
+{RESPONSE_FORMAT}
+You are currently trying to complete this task:
+{task}
+
+{file_info(file, line_num)}
+
+Keep all of the guidelines above in mind when you are thinking and making code.
+Please come up with a thought and action based on your current task and latest steps.
+Make sure that you do not repeat the same actions, there will not be any changes in result if you do not changes anything.
+Be very strict about the formatting that you use and make sure you follow the guidelines.
+NEVER output multiple commands. ONLY take ONE STEP at a time.
+When you have completed your task run the "exit" command.
+Begin with your thought about the next step and then come up with an action to perform your thought.
+'''.strip()
+
+
+def unpack_dict(data: dict, restrict: list[str] = []):
+    lines = []
+    for key, value in data.items():
+        if key in restrict:
+            continue
+        elif isinstance(value, dict):
+            nested_str = unpack_dict(value, restrict).replace('\n', '\n  ')
+            val = f'{key}:' + '\n  ' + f'{nested_str}'
+            lines.append(val)
+        else:
+            lines.append(f'{key}: {value}')
+    return '\n'.join(lines)
+
+
+def MEMORY_FORMAT(act, obs): return f'''
+Previous Action:
+{unpack_dict(act, ["content"])}
+
+Output from Action:
+{unpack_dict(obs)}
+'''.strip()
+
+
+def CONTEXT_PROMPT(memory, window):
+    res = f'These are your past {window} actions:\n'
+    window_size = window if len(memory) > window else len(memory)
+    cur_mems = memory[-window_size:]
+    res += '===== Previous Actions =====\n'
+    for idx, mem in enumerate(cur_mems):
+        res += f'\nMemory {idx}:\n{mem}\n'
+    res += '======= End Actions =======\n'
+    res += 'Use these memories to provide additional context to the problem you are solving.\nRemember that you have already completed these steps so you do not need to perform them again.'
+    return res

agenthub/__init__.py

@@ -0,0 +1,12 @@
+
+from dotenv import load_dotenv
+load_dotenv()
+
+# Import agents after environment variables are loaded
+from . import monologue_agent  # noqa: E402
+from . import codeact_agent  # noqa: E402
+from . import planner_agent  # noqa: E402
+from . import SWE_agent      # noqa: E402
+
+__all__ = ['monologue_agent', 'codeact_agent',
+           'planner_agent', 'SWE_agent']

agenthub/codeact_agent/README.md

@@ -0,0 +1,23 @@
+# CodeAct-based Agent Framework
+
+This folder implements the [CodeAct idea](https://arxiv.org/abs/2402.13463) that relies on LLM to autonomously perform actions in a Bash shell. It requires more from the LLM itself: LLM needs to be capable enough to do all the stuff autonomously, instead of stuck in an infinite loop.
+
+**NOTE: This agent is still highly experimental and under active development to reach the capability described in the original paper & [repo](https://github.com/xingyaoww/code-act).**
+
+<video src="https://github.com/xingyaoww/code-act/assets/38853559/62c80ada-62ce-447e-811c-fc801dd4beac"> </video>
+*Demo of the expected capability - work-in-progress.*
+
+```bash
+mkdir workspace
+PYTHONPATH=`pwd`:$PYTHONPATH python3 opendevin/main.py -d ./workspace -c CodeActAgent -t "Please write a flask app that returns 'Hello, World\!' at the root URL, then start the app on port 5000. python3 has already been installed for you."
+```
+
+Example: prompts `gpt-4-0125-preview` to write a flask server, install `flask` library, and start the server.
+
+<img width="951" alt="image" src="https://github.com/OpenDevin/OpenDevin/assets/38853559/325c3115-a343-4cc5-a92b-f1e5d552a077">
+
+<img width="957" alt="image" src="https://github.com/OpenDevin/OpenDevin/assets/38853559/68ad10c1-744a-4e9d-bb29-0f163d665a0a">
+
+Most of the things are working as expected, except at the end, the model did not follow the instruction to stop the interaction by outputting `<execute> exit </execute>` as instructed.
+
+**TODO**: This should be fixable by either (1) including a complete in-context example like [this](https://github.com/xingyaoww/mint-bench/blob/main/mint/tasks/in_context_examples/reasoning/with_tool.txt), OR (2) collect some interaction data like this and fine-tune a model (like [this](https://github.com/xingyaoww/code-act), a more complex route).

agenthub/codeact_agent/__init__.py

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

agenthub/codeact_agent/codeact_agent.py

@@ -0,0 +1,157 @@
+import re
+from typing import List, Mapping
+
+from opendevin.action import (
+    Action,
+    AgentEchoAction,
+    AgentFinishAction,
+    CmdRunAction,
+)
+from opendevin.agent import Agent
+from opendevin.llm.llm import LLM
+from opendevin.observation import (
+    AgentMessageObservation,
+    CmdOutputObservation,
+)
+from opendevin.parse_commands import parse_command_file
+from opendevin.state import State
+
+COMMAND_DOCS = parse_command_file()
+COMMAND_SEGMENT = (
+    f"""
+
+Apart from the standard bash commands, you can also use the following special commands:
+{COMMAND_DOCS}
+"""
+    if COMMAND_DOCS is not None
+    else ''
+)
+SYSTEM_MESSAGE = f"""You are a helpful assistant. You will be provided access (as root) to a bash shell to complete user-provided tasks.
+You will be able to execute commands in the bash shell, interact with the file system, install packages, and receive the output of your commands.
+
+DO NOT provide code in ```triple backticks```. Instead, you should execute bash command on behalf of the user by wrapping them with <execute> and </execute>.
+For example:
+
+You can list the files in the current directory by executing the following command:
+<execute>ls</execute>
+
+You can also install packages using pip:
+<execute> pip install numpy </execute>
+
+You can also write a block of code to a file:
+<execute>
+echo "import math
+print(math.pi)" > math.py
+</execute>
+{COMMAND_SEGMENT}
+
+When you are done, execute the following to close the shell and end the conversation:
+<execute>exit</execute>
+"""
+
+INVALID_INPUT_MESSAGE = (
+    "I don't understand your input. \n"
+    'If you want to execute command, please use <execute> YOUR_COMMAND_HERE </execute>.\n'
+    'If you already completed the task, please exit the shell by generating: <execute> exit </execute>.'
+)
+
+
+def parse_response(response) -> str:
+    action = response.choices[0].message.content
+    if '<execute>' in action and '</execute>' not in action:
+        action += '</execute>'
+    return action
+
+
+class CodeActAgent(Agent):
+    """
+    The Code Act Agent is a minimalist agent.
+    The agent works by passing the model a list of action-observation pairs and prompting the model to take the next step.
+    """
+
+    def __init__(
+        self,
+        llm: LLM,
+    ) -> None:
+        """
+        Initializes a new instance of the CodeActAgent class.
+
+        Parameters:
+        - llm (LLM): The llm to be used by this agent
+        """
+        super().__init__(llm)
+        self.messages: List[Mapping[str, str]] = []
+
+    def step(self, state: State) -> Action:
+        """
+        Performs one step using the Code Act Agent.
+        This includes gathering info on previous steps and prompting the model to make a command to execute.
+
+        Parameters:
+        - state (State): used to get updated info and background commands
+
+        Returns:
+        - CmdRunAction(command) - command action to run
+        - AgentEchoAction(content=INVALID_INPUT_MESSAGE) - invalid command output
+
+        Raises:
+        - NotImplementedError - for actions other than CmdOutputObservation or AgentMessageObservation
+        """
+
+        if len(self.messages) == 0:
+            assert state.plan.main_goal, 'Expecting instruction to be set'
+            self.messages = [
+                {'role': 'system', 'content': SYSTEM_MESSAGE},
+                {'role': 'user', 'content': state.plan.main_goal},
+            ]
+        updated_info = state.updated_info
+        if updated_info:
+            for prev_action, obs in updated_info:
+                assert isinstance(
+                    prev_action, (CmdRunAction, AgentEchoAction)
+                ), 'Expecting CmdRunAction or AgentEchoAction for Action'
+                if isinstance(
+                    obs, AgentMessageObservation
+                ):  # warning message from itself
+                    self.messages.append(
+                        {'role': 'user', 'content': obs.content})
+                elif isinstance(obs, CmdOutputObservation):
+                    content = 'OBSERVATION:\n' + obs.content
+                    content += f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]]'
+                    self.messages.append({'role': 'user', 'content': content})
+                else:
+                    raise NotImplementedError(
+                        f'Unknown observation type: {obs.__class__}'
+                    )
+        response = self.llm.completion(
+            messages=self.messages,
+            stop=['</execute>'],
+            temperature=0.0
+        )
+        action_str: str = parse_response(response)
+        state.num_of_chars += sum(len(message['content'])
+                                  for message in self.messages) + len(action_str)
+        self.messages.append({'role': 'assistant', 'content': action_str})
+
+        command = re.search(r'<execute>(.*)</execute>', action_str, re.DOTALL)
+        if command is not None:
+            # a command was found
+            command_group = command.group(1)
+            if command_group.strip() == 'exit':
+                return AgentFinishAction()
+            return CmdRunAction(command=command_group)
+            # # execute the code
+            # # TODO: does exit_code get loaded into Message?
+            # exit_code, observation = self.env.execute(command_group)
+            # self._history.append(Message(Role.ASSISTANT, observation))
+        else:
+            # we could provide a error message for the model to continue similar to
+            # https://github.com/xingyaoww/mint-bench/blob/main/mint/envs/general_env.py#L18-L23
+            # observation = INVALID_INPUT_MESSAGE
+            # self._history.append(Message(Role.ASSISTANT, observation))
+            return AgentEchoAction(
+                content=INVALID_INPUT_MESSAGE
+            )  # warning message to itself
+
+    def search_memory(self, query: str) -> List[str]:
+        raise NotImplementedError('Implement this abstract method')

agenthub/monologue_agent/.dockerignore

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

agenthub/monologue_agent/README.md

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

agenthub/monologue_agent/TODO.md

@@ -0,0 +1,8 @@
+# TODO
+There's a lot of low-hanging fruit for this agent:
+
+* Strip `<script>`, `<style>`, and other non-text tags from the HTML before sending it to the LLM
+* Keep track of the working directory when the agent uses `cd`
+* Improve memory condensing--condense earlier memories more aggressively
+* Limit the time that `run` can wait (in case agent runs an interactive command and it's hanging)
+* Figure out how to run background processes, e.g. `node server.js` to start a server

agenthub/monologue_agent/__init__.py

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

agenthub/monologue_agent/agent.py

@@ -0,0 +1,239 @@
+from typing import List
+from opendevin.agent import Agent
+from opendevin.state import State
+from opendevin.llm.llm import LLM
+from opendevin.schema import ActionType, ObservationType
+from opendevin.exceptions import AgentNoInstructionError
+
+from opendevin.action import (
+    Action,
+    NullAction,
+    CmdRunAction,
+    FileWriteAction,
+    FileReadAction,
+    AgentRecallAction,
+    BrowseURLAction,
+    AgentThinkAction,
+)
+
+from opendevin.observation import (
+    Observation,
+    NullObservation,
+    CmdOutputObservation,
+    FileReadObservation,
+    AgentRecallObservation,
+    BrowserOutputObservation,
+)
+
+import agenthub.monologue_agent.utils.prompts as prompts
+from agenthub.monologue_agent.utils.monologue import Monologue
+from agenthub.monologue_agent.utils.memory import LongTermMemory
+
+MAX_MONOLOGUE_LENGTH = 20000
+MAX_OUTPUT_LENGTH = 5000
+
+INITIAL_THOUGHTS = [
+    'I exist!',
+    'Hmm...looks like I can type in a command line prompt',
+    'Looks like I have a web browser too!',
+    "Here's what I want to do: $TASK",
+    'How am I going to get there though?',
+    'It seems like I have some kind of short term memory.',
+    'Each of my thoughts seems to be stored in a JSON array.',
+    'It seems whatever I say next will be added as an object to the list.',
+    'But no one has perfect short-term memory. My list of thoughts will be summarized and condensed over time, losing information in the process.',
+    'Fortunately I have long term memory!',
+    'I can just perform a recall action, followed by the thing I want to remember. And then related thoughts just spill out!',
+    "Sometimes they're random thoughts that don't really have to do with what I wanted to remember. But usually they're exactly what I need!",
+    "Let's try it out!",
+    'RECALL what it is I want to do',
+    "Here's what I want to do: $TASK",
+    'How am I going to get there though?',
+    "Neat! And it looks like it's easy for me to use the command line too! I just have to perform a run action and include the command I want to run in the command argument. The command output just jumps into my head!",
+    'RUN echo "hello world"',
+    'hello world',
+    'Cool! I bet I can write files too using the write action.',
+    "WRITE echo \"console.log('hello world')\" > test.js",
+    '',
+    "I just created test.js. I'll try and run it now.",
+    'RUN node test.js',
+    'hello world',
+    'It works!',
+    "I'm going to try reading it now using the read action.",
+    'READ test.js',
+    "console.log('hello world')",
+    'Nice! I can read files too!',
+    'And if I want to use the browser, I just need to use the browse action and include the url I want to visit in the url argument',
+    "Let's try that...",
+    'BROWSE google.com',
+    '<form><input type="text"></input><button type="submit"></button></form>',
+    'I can browse the web too!',
+    'And once I have completed my task, I can use the finish action to stop working.',
+    "But I should only use the finish action when I'm absolutely certain that I've completed my task and have tested my work.",
+    'Very cool. Now to accomplish my task.',
+    "I'll need a strategy. And as I make progress, I'll need to keep refining that strategy. I'll need to set goals, and break them into sub-goals.",
+    'In between actions, I must always take some time to think, strategize, and set new goals. I should never take two actions in a row.',
+    "OK so my task is to $TASK. I haven't made any progress yet. Where should I start?",
+    "It seems like there might be an existing project here. I should probably start by running `ls` to see what's here.",
+]
+
+
+class MonologueAgent(Agent):
+    """
+    The Monologue Agent utilizes long and short term memory to complete tasks.
+    Long term memory is stored as a LongTermMemory object and the model uses it to search for examples from the past.
+    Short term memory is stored as a Monologue object and the model can condense it as necessary.
+    """
+
+    _initialized = False
+
+    def __init__(self, llm: LLM):
+        """
+        Initializes the Monologue Agent with an llm, monologue, and memory.
+
+        Parameters:
+        - llm (LLM): The llm to be used by this agent
+        """
+        super().__init__(llm)
+        self.monologue = Monologue()
+        self.memory = LongTermMemory()
+
+    def _add_event(self, event: dict):
+        """
+        Adds a new event to the agent's monologue and memory.
+        Monologue automatically condenses when it gets too large.
+
+        Parameters:
+        - event (dict): The event that will be added to monologue and memory
+        """
+
+        if 'extras' in event and 'screenshot' in event['extras']:
+            del event['extras']['screenshot']
+        if (
+            'args' in event
+            and 'output' in event['args']
+            and len(event['args']['output']) > MAX_OUTPUT_LENGTH
+        ):
+            event['args']['output'] = (
+                event['args']['output'][:MAX_OUTPUT_LENGTH] + '...'
+            )
+
+        self.monologue.add_event(event)
+        self.memory.add_event(event)
+        if self.monologue.get_total_length() > MAX_MONOLOGUE_LENGTH:
+            self.monologue.condense(self.llm)
+
+    def _initialize(self, task: str):
+        """
+        Utilizes the INITIAL_THOUGHTS list to give the agent a context for it's capabilities and how to navigate the /workspace.
+        Short circuited to return when already initialized.
+
+        Parameters:
+        - task (str): The initial goal statement provided by the user
+
+        Raises:
+        - AgentNoInstructionError: If task is not provided
+        """
+
+        if self._initialized:
+            return
+
+        if task is None or task == '':
+            raise AgentNoInstructionError()
+        self.monologue = Monologue()
+        self.memory = LongTermMemory()
+
+        output_type = ''
+        for thought in INITIAL_THOUGHTS:
+            thought = thought.replace('$TASK', task)
+            if output_type != '':
+                observation: Observation = NullObservation(content='')
+                if output_type == ObservationType.RUN:
+                    observation = CmdOutputObservation(
+                        content=thought, command_id=0, command=''
+                    )
+                elif output_type == ObservationType.READ:
+                    observation = FileReadObservation(content=thought, path='')
+                elif output_type == ObservationType.RECALL:
+                    observation = AgentRecallObservation(
+                        content=thought, memories=[])
+                elif output_type == ObservationType.BROWSE:
+                    observation = BrowserOutputObservation(
+                        content=thought, url='', screenshot=''
+                    )
+                self._add_event(observation.to_dict())
+                output_type = ''
+            else:
+                action: Action = NullAction()
+                if thought.startswith('RUN'):
+                    command = thought.split('RUN ')[1]
+                    action = CmdRunAction(command)
+                    output_type = ActionType.RUN
+                elif thought.startswith('WRITE'):
+                    parts = thought.split('WRITE ')[1].split(' > ')
+                    path = parts[1]
+                    content = parts[0]
+                    action = FileWriteAction(path=path, content=content)
+                elif thought.startswith('READ'):
+                    path = thought.split('READ ')[1]
+                    action = FileReadAction(path=path)
+                    output_type = ActionType.READ
+                elif thought.startswith('RECALL'):
+                    query = thought.split('RECALL ')[1]
+                    action = AgentRecallAction(query=query)
+                    output_type = ActionType.RECALL
+                elif thought.startswith('BROWSE'):
+                    url = thought.split('BROWSE ')[1]
+                    action = BrowseURLAction(url=url)
+                    output_type = ActionType.BROWSE
+                else:
+                    action = AgentThinkAction(thought=thought)
+                self._add_event(action.to_memory())
+        self._initialized = True
+
+    def step(self, state: State) -> Action:
+        """
+        Modifies the current state by adding the most recent actions and observations, then prompts the model to think about it's next action to take using monologue, memory, and hint.
+
+        Parameters:
+        - state (State): The current state based on previous steps taken
+
+        Returns:
+        - Action: The next action to take based on LLM response
+        """
+        self._initialize(state.plan.main_goal)
+        for prev_action, obs in state.updated_info:
+            self._add_event(prev_action.to_memory())
+            self._add_event(obs.to_dict())
+
+        state.updated_info = []
+
+        prompt = prompts.get_request_action_prompt(
+            state.plan.main_goal,
+            self.monologue.get_thoughts(),
+            state.background_commands_obs,
+        )
+        messages = [{'content': prompt, 'role': 'user'}]
+        resp = self.llm.completion(messages=messages)
+        action_resp = resp['choices'][0]['message']['content']
+        state.num_of_chars += len(prompt) + len(action_resp)
+        action = prompts.parse_action_response(action_resp)
+        self.latest_action = action
+        return action
+
+    def search_memory(self, query: str) -> List[str]:
+        """
+        Uses VectorIndexRetriever to find related memories within the long term memory.
+        Uses search to produce top 10 results.
+
+        Parameters:
+        - query (str): The query that we want to find related memories for
+
+        Returns:
+        - List[str]: A list of top 10 text results that matched the query
+        """
+        return self.memory.search(query)
+
+    def reset(self) -> None:
+        super().reset()
+        self.monologue = Monologue()

agenthub/monologue_agent/utils/json.py

@@ -0,0 +1,37 @@
+import json
+from json_repair import repair_json
+
+
+def my_encoder(obj):
+    """
+    Encodes objects as dictionaries
+
+    Parameters:
+    - obj (Object): An object that will be converted
+
+    Returns:
+    - dict: If the object can be converted it is returned in dict format
+    """
+    if hasattr(obj, 'to_dict'):
+        return obj.to_dict()
+
+
+def dumps(obj, **kwargs):
+    """
+    Serialize an object to str format
+    """
+
+    return json.dumps(obj, default=my_encoder, **kwargs)
+
+
+def loads(s, **kwargs):
+    """
+    Create a JSON object from str
+    """
+    json_start = s.find('{')
+    json_end = s.rfind('}') + 1
+    if json_start == -1 or json_end == -1:
+        raise ValueError('Invalid response: no JSON found')
+    s = s[json_start:json_end]
+    s = repair_json(s)
+    return json.loads(s, **kwargs)

agenthub/monologue_agent/utils/memory.py

@@ -0,0 +1,112 @@
+from threading import Thread
+
+import chromadb
+from llama_index.core import Document
+from llama_index.core.retrievers import VectorIndexRetriever
+from llama_index.core import VectorStoreIndex
+from llama_index.vector_stores.chroma import ChromaVectorStore
+
+from opendevin import config
+from opendevin.logger import opendevin_logger as logger
+from . import json
+
+embedding_strategy = config.get('LLM_EMBEDDING_MODEL')
+
+# TODO: More embeddings: https://docs.llamaindex.ai/en/stable/examples/embeddings/OpenAI/
+# There's probably a more programmatic way to do this.
+if embedding_strategy == 'llama2':
+    from llama_index.embeddings.ollama import OllamaEmbedding
+    embed_model = OllamaEmbedding(
+        model_name='llama2',
+        base_url=config.get('LLM_BASE_URL', required=True),
+        ollama_additional_kwargs={'mirostat': 0},
+    )
+elif embedding_strategy == 'openai':
+    from llama_index.embeddings.openai import OpenAIEmbedding
+    embed_model = OpenAIEmbedding(
+        model='text-embedding-ada-002',
+        api_key=config.get('LLM_API_KEY', required=True)
+    )
+elif embedding_strategy == 'azureopenai':
+    # Need to instruct to set these env variables in documentation
+    from llama_index.embeddings.azure_openai import AzureOpenAIEmbedding
+    embed_model = AzureOpenAIEmbedding(
+        model='text-embedding-ada-002',
+        deployment_name=config.get('LLM_DEPLOYMENT_NAME', required=True),
+        api_key=config.get('LLM_API_KEY', required=True),
+        azure_endpoint=config.get('LLM_BASE_URL', required=True),
+        api_version=config.get('LLM_API_VERSION', required=True),
+    )
+else:
+    from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+    embed_model = HuggingFaceEmbedding(
+        model_name='BAAI/bge-small-en-v1.5'
+    )
+
+
+class LongTermMemory:
+    """
+    Responsible for storing information that the agent can call on later for better insights and context.
+    Uses chromadb to store and search through memories.
+    """
+
+    def __init__(self):
+        """
+        Initialize the chromadb and set up ChromaVectorStore for later use.
+        """
+        db = chromadb.Client()
+        self.collection = db.get_or_create_collection(name='memories')
+        vector_store = ChromaVectorStore(chroma_collection=self.collection)
+        self.index = VectorStoreIndex.from_vector_store(
+            vector_store, embed_model=embed_model)
+        self.thought_idx = 0
+
+    def add_event(self, event: dict):
+        """
+        Adds a new event to the long term memory with a unique id.
+
+        Parameters:
+        - event (dict): The new event to be added to memory
+        """
+        id = ''
+        t = ''
+        if 'action' in event:
+            t = 'action'
+            id = event['action']
+        elif 'observation' in event:
+            t = 'observation'
+            id = event['observation']
+        doc = Document(
+            text=json.dumps(event),
+            doc_id=str(self.thought_idx),
+            extra_info={
+                'type': t,
+                'id': id,
+                'idx': self.thought_idx,
+            },
+        )
+        self.thought_idx += 1
+        logger.debug('Adding %s event to memory: %d', t, self.thought_idx)
+        thread = Thread(target=self._add_doc, args=(doc,))
+        thread.start()  # We add the doc concurrently so we don't have to wait ~500ms for the insert
+
+    def _add_doc(self, doc):
+        self.index.insert(doc)
+
+    def search(self, query: str, k: int = 10):
+        """
+        Searches through the current memory using VectorIndexRetriever
+
+        Parameters:
+        - query (str): A query to match search results to
+        - k (int): Number of top results to return
+
+        Returns:
+        - List[str]: List of top k results found in current memory
+        """
+        retriever = VectorIndexRetriever(
+            index=self.index,
+            similarity_top_k=k,
+        )
+        results = retriever.retrieve(query)
+        return [r.get_text() for r in results]

agenthub/monologue_agent/utils/monologue.py

@@ -0,0 +1,78 @@
+import traceback
+
+from opendevin.llm.llm import LLM
+from opendevin.exceptions import AgentEventTypeError
+import agenthub.monologue_agent.utils.json as json
+import agenthub.monologue_agent.utils.prompts as prompts
+
+
+class Monologue:
+    """
+    The monologue is a representation for the agent's internal monologue where it can think.
+    The agent has the capability of using this monologue for whatever it wants.
+    """
+
+    def __init__(self):
+        """
+        Initialize the empty list of thoughts
+        """
+        self.thoughts = []
+
+    def add_event(self, t: dict):
+        """
+        Adds an event to memory if it is a valid event.
+
+        Parameters:
+        - t (dict): The thought that we want to add to memory
+
+        Raises:
+        - AgentEventTypeError: If t is not a dict
+        """
+        if not isinstance(t, dict):
+            raise AgentEventTypeError()
+        self.thoughts.append(t)
+
+    def get_thoughts(self):
+        """
+        Get the current thoughts of the agent.
+
+        Returns:
+        - List: The list of thoughts that the agent has.
+        """
+        return self.thoughts
+
+    def get_total_length(self):
+        """
+        Gives the total number of characters in all thoughts
+
+        Returns:
+        - Int: Total number of chars in thoughts.
+        """
+        total_length = 0
+        for t in self.thoughts:
+            try:
+                total_length += len(json.dumps(t))
+            except TypeError as e:
+                print(f'Error serializing thought: {e}')
+        return total_length
+
+    def condense(self, llm: LLM):
+        """
+        Attempts to condense the monologue by using the llm
+
+        Parameters:
+        - llm (LLM): llm to be used for summarization
+
+        Raises:
+        - RunTimeError: When the condensing process fails for any reason
+        """
+
+        try:
+            prompt = prompts.get_summarize_monologue_prompt(self.thoughts)
+            messages = [{'content': prompt, 'role': 'user'}]
+            resp = llm.completion(messages=messages)
+            summary_resp = resp['choices'][0]['message']['content']
+            self.thoughts = prompts.parse_summary_response(summary_resp)
+        except Exception as e:
+            traceback.print_exc()
+            raise RuntimeError(f'Error condensing thoughts: {e}')

agenthub/monologue_agent/utils/prompts.py

@@ -0,0 +1,194 @@
+from typing import List
+
+from . import json
+from json import JSONDecodeError
+
+import re
+
+from opendevin.action import (
+    action_from_dict,
+    Action,
+)
+from opendevin.observation import (
+    CmdOutputObservation,
+)
+from opendevin.exceptions import LLMOutputError
+
+ACTION_PROMPT = """
+You're a thoughtful robot. Your main task is this:
+%(task)s
+
+Don't expand the scope of your task--just complete it as written.
+
+This is your internal monologue, in JSON format:
+
+%(monologue)s
+
+
+Your most recent thought is at the bottom of that monologue. Continue your train of thought.
+What is your next thought or action? Your response must be in JSON format.
+It must be an object, and it must contain two fields:
+* `action`, which is one of the actions below
+* `args`, which is a map of key-value pairs, specifying the arguments for that action
+
+Here are the possible actions:
+* `read` - reads the content of a file. Arguments:
+  * `path` - the path of the file to read
+* `write` - writes the content to a file. Arguments:
+  * `path` - the path of the file to write
+  * `content` - the content to write to the file
+* `run` - runs a command. Arguments:
+  * `command` - the command to run
+  * `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
+* `kill` - kills a background command
+  * `id` - the ID of the background command to kill
+* `browse` - opens a web page. Arguments:
+  * `url` - the URL to open
+* `recall` - recalls a past memory. Arguments:
+  * `query` - the query to search for
+* `think` - make a plan, set a goal, or record your thoughts. Arguments:
+  * `thought` - the thought to record
+* `finish` - if you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.
+
+%(background_commands)s
+
+You MUST take time to think in between read, write, run, browse, and recall actions.
+You should never act twice in a row without thinking. But if your last several
+actions are all "think" actions, you should consider taking a different action.
+
+Notes:
+* your environment is Debian Linux. You can install software with `apt`
+* your working directory will not change, even if you run `cd`. All commands will be run in the `/workspace` directory.
+* don't run interactive commands, or commands that don't return (e.g. `node server.js`). You may run commands in the background (e.g. `node server.js &`)
+
+What is your next thought or action? Again, you must reply with JSON, and only with JSON.
+
+%(hint)s
+"""
+
+MONOLOGUE_SUMMARY_PROMPT = """
+Below is the internal monologue of an automated LLM agent. Each
+thought is an item in a JSON array. The thoughts may be memories,
+actions taken by the agent, or outputs from those actions.
+Please return a new, smaller JSON array, which summarizes the
+internal monologue. You can summarize individual thoughts, and
+you can condense related thoughts together with a description
+of their content.
+
+%(monologue)s
+
+Make the summaries as pithy and informative as possible.
+Be specific about what happened and what was learned. The summary
+will be used as keywords for searching for the original memory.
+Be sure to preserve any key words or important information.
+
+Your response must be in JSON format. It must be an object with the
+key `new_monologue`, which is a JSON array containing the summarized monologue.
+Each entry in the array must have an `action` key, and an `args` key.
+The action key may be `summarize`, and `args.summary` should contain the summary.
+You can also use the same action and args from the source monologue.
+"""
+
+
+def get_summarize_monologue_prompt(thoughts: List[dict]):
+    """
+    Gets the prompt for summarizing the monologue
+
+    Returns:
+    - str: A formatted string with the current monologue within the prompt
+    """
+    return MONOLOGUE_SUMMARY_PROMPT % {
+        'monologue': json.dumps({'old_monologue': thoughts}, indent=2),
+    }
+
+
+def get_request_action_prompt(
+    task: str,
+    thoughts: List[dict],
+    background_commands_obs: List[CmdOutputObservation] = [],
+):
+    """
+    Gets the action prompt formatted with appropriate values.
+
+    Parameters:
+    - task (str): The current task the agent is trying to accomplish
+    - thoughts (List[dict]): The agent's current thoughts
+    - background_commands_obs (List[CmdOutputObservation]): List of all observed background commands running
+
+    Returns:
+    - str: Formatted prompt string with hint, task, monologue, and background included
+    """
+
+    hint = ''
+    if len(thoughts) > 0:
+        latest_thought = thoughts[-1]
+        if 'action' in latest_thought:
+            if latest_thought['action'] == 'think':
+                if latest_thought['args']['thought'].startswith('OK so my task is'):
+                    hint = "You're just getting started! What should you do first?"
+                else:
+                    hint = "You've been thinking a lot lately. Maybe it's time to take action?"
+            elif latest_thought['action'] == 'error':
+                hint = 'Looks like that last command failed. Maybe you need to fix it, or try something else.'
+
+    bg_commands_message = ''
+    if len(background_commands_obs) > 0:
+        bg_commands_message = 'The following commands are running in the background:'
+        for command_obs in background_commands_obs:
+            bg_commands_message += (
+                f'\n`{command_obs.command_id}`: {command_obs.command}'
+            )
+        bg_commands_message += '\nYou can end any process by sending a `kill` action with the numerical `id` above.'
+
+    return ACTION_PROMPT % {
+        'task': task,
+        'monologue': json.dumps(thoughts, indent=2),
+        'background_commands': bg_commands_message,
+        'hint': hint,
+    }
+
+
+def parse_action_response(response: str) -> Action:
+    """
+    Parses a string to find an action within it
+
+    Parameters:
+    - response (str): The string to be parsed
+
+    Returns:
+    - Action: The action that was found in the response string
+    """
+    try:
+        action_dict = json.loads(response)
+    except JSONDecodeError:
+        # Find response-looking json in the output and use the more promising one. Helps with weak llms
+        response_json_matches = re.finditer(
+            r"""{\s*\"action\":\s?\"(\w+)\"(?:,?|,\s*\"args\":\s?{((?:.|\s)*?)})\s*}""",
+            response)  # Find all response-looking strings
+
+        def rank(match):
+            return len(match[2]) if match[1] == 'think' else 130  # Crudely rank multiple responses by length
+        try:
+            action_dict = json.loads(max(response_json_matches, key=rank)[0])  # Use the highest ranked response
+        except ValueError as e:
+            raise LLMOutputError(
+                "Output from the LLM isn't properly formatted. The model may be misconfigured."
+            ) from e
+    if 'content' in action_dict:
+        # The LLM gets confused here. Might as well be robust
+        action_dict['contents'] = action_dict.pop('content')
+    return action_from_dict(action_dict)
+
+
+def parse_summary_response(response: str) -> List[dict]:
+    """
+    Parses a summary of the monologue
+
+    Parameters:
+    - response (str): The response string to be parsed
+
+    Returns:
+    - List[dict]: The list of summaries output by the model
+    """
+    parsed = json.loads(response)
+    return parsed['new_monologue']

agenthub/planner_agent/__init__.py

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

agenthub/planner_agent/agent.py

@@ -0,0 +1,50 @@
+from typing import List
+from .prompt import get_prompt, parse_response
+
+from opendevin.agent import Agent
+from opendevin.action import AgentFinishAction
+from opendevin.llm.llm import LLM
+from opendevin.state import State
+from opendevin.action import Action
+
+
+class PlannerAgent(Agent):
+    """
+    The planner agent utilizes a special prompting strategy to create long term plans for solving problems.
+    The agent is given its previous action-observation pairs, current task, and hint based on last action taken at every step.
+    """
+
+    def __init__(self, llm: LLM):
+        """
+        Initialize the Planner Agent with an LLM
+
+        Parameters:
+        - llm (LLM): The llm to be used by this agent
+        """
+        super().__init__(llm)
+
+    def step(self, state: State) -> Action:
+        """
+        Checks to see if current step is completed, returns AgentFinishAction if True.
+        Otherwise, creates a plan prompt and sends to model for inference, returning the result as the next action.
+
+        Parameters:
+        - state (State): The current state given the previous actions and observations
+
+        Returns:
+        - AgentFinishAction: If the last state was 'completed', 'verified', or 'abandoned'
+        - Action: The next action to take based on llm response
+        """
+
+        if state.plan.task.state in ['completed', 'verified', 'abandoned']:
+            return AgentFinishAction()
+        prompt = get_prompt(state.plan, state.history)
+        messages = [{'content': prompt, 'role': 'user'}]
+        resp = self.llm.completion(messages=messages)
+        action_resp = resp['choices'][0]['message']['content']
+        state.num_of_chars += len(prompt) + len(action_resp)
+        action = parse_response(action_resp)
+        return action
+
+    def search_memory(self, query: str) -> List[str]:
+        return []

agenthub/planner_agent/prompt.py

@@ -0,0 +1,228 @@
+import json
+from typing import List, Tuple, Dict, Type
+from opendevin.plan import Plan
+from opendevin.action import Action, action_from_dict
+from opendevin.observation import Observation
+from opendevin.schema import ActionType
+from opendevin.logger import opendevin_logger as logger
+
+from opendevin.action import (
+    NullAction,
+    CmdRunAction,
+    CmdKillAction,
+    BrowseURLAction,
+    FileReadAction,
+    FileWriteAction,
+    AgentRecallAction,
+    AgentThinkAction,
+    AgentFinishAction,
+    AgentSummarizeAction,
+    AddTaskAction,
+    ModifyTaskAction,
+)
+
+from opendevin.observation import (
+    NullObservation,
+)
+
+ACTION_TYPE_TO_CLASS: Dict[str, Type[Action]] = {
+    ActionType.RUN: CmdRunAction,
+    ActionType.KILL: CmdKillAction,
+    ActionType.BROWSE: BrowseURLAction,
+    ActionType.READ: FileReadAction,
+    ActionType.WRITE: FileWriteAction,
+    ActionType.RECALL: AgentRecallAction,
+    ActionType.THINK: AgentThinkAction,
+    ActionType.SUMMARIZE: AgentSummarizeAction,
+    ActionType.FINISH: AgentFinishAction,
+    ActionType.ADD_TASK: AddTaskAction,
+    ActionType.MODIFY_TASK: ModifyTaskAction,
+}
+
+HISTORY_SIZE = 10
+
+prompt = """
+# Task
+You're a diligent software engineer AI. You can't see, draw, or interact with a
+browser, but you can read and write files, and you can run commands, and you can think.
+
+You've been given the following task:
+
+%(task)s
+
+## Plan
+As you complete this task, you're building a plan and keeping
+track of your progress. Here's a JSON representation of your plan:
+
+%(plan)s
+
+
+%(plan_status)s
+
+You're responsible for managing this plan and the status of tasks in
+it, by using the `add_task` and `modify_task` actions described below.
+
+If the History below contradicts the state of any of these tasks, you
+MUST modify the task using the `modify_task` action described below.
+
+Be sure NOT to duplicate any tasks. Do NOT use the `add_task` action for
+a task that's already represented. Every task must be represented only once.
+
+Tasks that are sequential MUST be siblings. They must be added in order
+to their parent task.
+
+If you mark a task as 'completed', 'verified', or 'abandoned',
+all non-abandoned subtasks will be marked the same way.
+So before closing a task this way, you MUST not only be sure that it has
+been completed successfully--you must ALSO be sure that all its subtasks
+are ready to be marked the same way.
+
+If, and only if, ALL tasks have already been marked verified,
+you MUST respond with the `finish` action.
+
+## History
+Here is a recent history of actions you've taken in service of this plan,
+as well as observations you've made. This only includes the MOST RECENT
+ten actions--more happened before that.
+
+%(history)s
+
+
+Your most recent action is at the bottom of that history.
+
+## Action
+What is your next thought or action? Your response must be in JSON format.
+
+It must be an object, and it must contain two fields:
+* `action`, which is one of the actions below
+* `args`, which is a map of key-value pairs, specifying the arguments for that action
+
+* `read` - reads the content of a file. Arguments:
+  * `path` - the path of the file to read
+* `write` - writes the content to a file. Arguments:
+  * `path` - the path of the file to write
+  * `content` - the content to write to the file
+* `run` - runs a command on the command line in a Linux shell. Arguments:
+  * `command` - the command to run
+  * `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
+* `kill` - kills a background command
+  * `id` - the ID of the background command to kill
+* `browse` - opens a web page. Arguments:
+  * `url` - the URL to open
+* `think` - make a plan, set a goal, or record your thoughts. Arguments:
+  * `thought` - the thought to record
+* `add_task` - add a task to your plan. Arguments:
+  * `parent` - the ID of the parent task
+  * `goal` - the goal of the task
+  * `subtasks` - a list of subtasks, each of which is a map with a `goal` key.
+* `modify_task` - close a task. Arguments:
+  * `id` - the ID of the task to close
+  * `state` - set to 'in_progress' to start the task, 'completed' to finish it, 'verified' to assert that it was successful, 'abandoned' to give up on it permanently, or `open` to stop working on it for now.
+* `finish` - if ALL of your tasks and subtasks have been verified or abandoned, and you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.
+
+You MUST take time to think in between read, write, run, browse, and recall actions.
+You should never act twice in a row without thinking. But if your last several
+actions are all `think` actions, you should consider taking a different action.
+
+What is your next thought or action? Again, you must reply with JSON, and only with JSON.
+
+%(hint)s
+"""
+
+
+def get_prompt(plan: Plan, history: List[Tuple[Action, Observation]]) -> str:
+    """
+    Gets the prompt for the planner agent.
+    Formatted with the most recent action-observation pairs, current task, and hint based on last action
+
+    Parameters:
+    - plan (Plan): The original plan outlined by the user with LLM defined tasks
+    - history (List[Tuple[Action, Observation]]): List of corresponding action-observation pairs
+
+    Returns:
+    - str: The formatted string prompt with historical values
+    """
+
+    plan_str = json.dumps(plan.task.to_dict(), indent=2)
+    sub_history = history[-HISTORY_SIZE:]
+    history_dicts = []
+    latest_action: Action = NullAction()
+    for action, observation in sub_history:
+        if not isinstance(action, NullAction):
+            history_dicts.append(action.to_memory())
+            latest_action = action
+        if not isinstance(observation, NullObservation):
+            observation_dict = observation.to_dict()
+            if (
+                'extras' in observation_dict
+                and 'screenshot' in observation_dict['extras']
+            ):
+                del observation_dict['extras']['screenshot']
+            history_dicts.append(observation_dict)
+    history_str = json.dumps(history_dicts, indent=2)
+
+    hint = ''
+    current_task = plan.get_current_task()
+    if current_task is not None:
+        plan_status = f"You're currently working on this task:\n{current_task.goal}."
+        if len(current_task.subtasks) == 0:
+            plan_status += "\nIf it's not achievable AND verifiable with a SINGLE action, you MUST break it down into subtasks NOW."
+    else:
+        plan_status = "You're not currently working on any tasks. Your next action MUST be to mark a task as in_progress."
+        hint = plan_status
+
+    latest_action_id = latest_action.to_dict()['action']
+
+    if current_task is not None:
+        if latest_action_id == '':
+            hint = "You haven't taken any actions yet. Start by using `ls` to check out what files you're working with."
+        elif latest_action_id == ActionType.RUN:
+            hint = 'You should think about the command you just ran, what output it gave, and how that affects your plan.'
+        elif latest_action_id == ActionType.READ:
+            hint = 'You should think about the file you just read, what you learned from it, and how that affects your plan.'
+        elif latest_action_id == ActionType.WRITE:
+            hint = 'You just changed a file. You should think about how it affects your plan.'
+        elif latest_action_id == ActionType.BROWSE:
+            hint = 'You should think about the page you just visited, and what you learned from it.'
+        elif latest_action_id == ActionType.THINK:
+            hint = "Look at your last thought in the history above. What does it suggest? Don't think anymore--take action."
+        elif latest_action_id == ActionType.RECALL:
+            hint = 'You should think about the information you just recalled, and how it should affect your plan.'
+        elif latest_action_id == ActionType.ADD_TASK:
+            hint = 'You should think about the next action to take.'
+        elif latest_action_id == ActionType.MODIFY_TASK:
+            hint = 'You should think about the next action to take.'
+        elif latest_action_id == ActionType.SUMMARIZE:
+            hint = ''
+        elif latest_action_id == ActionType.FINISH:
+            hint = ''
+
+    logger.info('HINT:\n' + hint, extra={'msg_type': 'INFO'})
+    return prompt % {
+        'task': plan.main_goal,
+        'plan': plan_str,
+        'history': history_str,
+        'hint': hint,
+        'plan_status': plan_status,
+    }
+
+
+def parse_response(response: str) -> Action:
+    """
+    Parses the model output to find a valid action to take
+
+    Parameters:
+    - response (str): A response from the model that potentially contains an Action.
+
+    Returns:
+    - Action: A valid next action to perform from model output
+    """
+    json_start = response.find('{')
+    json_end = response.rfind('}') + 1
+    response = response[json_start:json_end]
+    action_dict = json.loads(response)
+    if 'contents' in action_dict:
+        # The LLM gets confused here. Might as well be robust
+        action_dict['content'] = action_dict.pop('contents')
+    action = action_from_dict(action_dict)
+    return action

build.sh

@@ -1,5 +0,0 @@
-#!/bin/bash
-set -e
-
-cp pyproject.toml poetry.lock openhands
-poetry build -v

compose.yml

@@ -1,22 +0,0 @@
-#
-services:
-  openhands:
-    build:
-      context: ./
-      dockerfile: ./containers/app/Dockerfile
-    image: openhands:latest
-    container_name: openhands-app-${DATE:-}
-    environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.17-nikolaik}
-      - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
-      - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
-    ports:
-      - "3000:3000"
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock
-      - ${WORKSPACE_BASE:-$PWD/workspace}:/opt/workspace_base
-    pull_policy: build
-    stdin_open: true
-    tty: true

config.template.toml

@@ -1,260 +0,0 @@
-###################### OpenHands Configuration Example ######################
-#
-# All settings have default values, so you only need to uncomment and
-# modify what you want to change
-# The fields within each section are sorted in alphabetical order.
-#
-##############################################################################
-
-#################################### Core ####################################
-# General core configurations
-##############################################################################
-[core]
-# API key for E2B
-#e2b_api_key = ""
-
-# API key for Modal
-#modal_api_token_id = ""
-#modal_api_token_secret = ""
-
-# Base path for the workspace
-workspace_base = "./workspace"
-
-# Cache directory path
-#cache_dir = "/tmp/cache"
-
-# Debugging enabled
-#debug = false
-
-# Disable color in terminal output
-#disable_color = false
-
-# Enable saving and restoring the session when run from CLI
-#enable_cli_session = false
-
-# Path to store trajectories, can be a folder or a file
-# If it's a folder, the session id will be used as the file name
-#trajectories_path="./trajectories"
-
-# File store path
-#file_store_path = "/tmp/file_store"
-
-# File store type
-#file_store = "memory"
-
-# List of allowed file extensions for uploads
-#file_uploads_allowed_extensions = [".*"]
-
-# Maximum file size for uploads, in megabytes
-#file_uploads_max_file_size_mb = 0
-
-# Maximum budget per task, 0.0 means no limit
-#max_budget_per_task = 0.0
-
-# Maximum number of iterations
-#max_iterations = 100
-
-# Path to mount the workspace in the sandbox
-#workspace_mount_path_in_sandbox = "/workspace"
-
-# Path to mount the workspace
-#workspace_mount_path = ""
-
-# Path to rewrite the workspace mount path to
-#workspace_mount_rewrite = ""
-
-# Run as openhands
-#run_as_openhands = true
-
-# Runtime environment
-#runtime = "eventstream"
-
-# Name of the default agent
-#default_agent = "CodeActAgent"
-
-# JWT secret for authentication
-#jwt_secret = ""
-
-# Restrict file types for file uploads
-#file_uploads_restrict_file_types = false
-
-# List of allowed file extensions for uploads
-#file_uploads_allowed_extensions = [".*"]
-
-#################################### LLM #####################################
-# Configuration for LLM models (group name starts with 'llm')
-# use 'llm' for the default LLM config
-##############################################################################
-[llm]
-# AWS access key ID
-#aws_access_key_id = ""
-
-# AWS region name
-#aws_region_name = ""
-
-# AWS secret access key
-#aws_secret_access_key = ""
-
-# API key to use (For Headless / CLI only -  In Web this is overridden by Session Init)
-api_key = "your-api-key"
-
-# API base URL (For Headless / CLI only -  In Web this is overridden by Session Init)
-#base_url = ""
-
-# API version
-#api_version = ""
-
-# Cost per input token
-#input_cost_per_token = 0.0
-
-# Cost per output token
-#output_cost_per_token = 0.0
-
-# Custom LLM provider
-#custom_llm_provider = ""
-
-# Embedding API base URL
-#embedding_base_url = ""
-
-# Embedding deployment name
-#embedding_deployment_name = ""
-
-# Embedding model to use
-embedding_model = "local"
-
-# Maximum number of characters in an observation's content
-#max_message_chars = 10000
-
-# Maximum number of input tokens
-#max_input_tokens = 0
-
-# Maximum number of output tokens
-#max_output_tokens = 0
-
-# Model to use. (For Headless / CLI only -  In Web this is overridden by Session Init)
-model = "gpt-4o"
-
-# Number of retries to attempt when an operation fails with the LLM.
-# Increase this value to allow more attempts before giving up
-#num_retries = 8
-
-# Maximum wait time (in seconds) between retry attempts
-# This caps the exponential backoff to prevent excessively long
-#retry_max_wait = 120
-
-# Minimum wait time (in seconds) between retry attempts
-# This sets the initial delay before the first retry
-#retry_min_wait = 15
-
-# Multiplier for exponential backoff calculation
-# The wait time increases by this factor after each failed attempt
-# A value of 2.0 means each retry waits twice as long as the previous one
-#retry_multiplier = 2.0
-
-# Drop any unmapped (unsupported) params without causing an exception
-#drop_params = false
-
-# Modify params for litellm to do transformations like adding a default message, when a message is empty.
-# Note: this setting is global, unlike drop_params, it cannot be overridden in each call to litellm.
-#modify_params = true
-
-# Using the prompt caching feature if provided by the LLM and supported
-#caching_prompt = true
-
-# Base URL for the OLLAMA API
-#ollama_base_url = ""
-
-# Temperature for the API
-#temperature = 0.0
-
-# Timeout for the API
-#timeout = 0
-
-# Top p for the API
-#top_p = 1.0
-
-# If model is vision capable, this option allows to disable image processing (useful for cost reduction).
-#disable_vision = true
-
-# Custom tokenizer to use for token counting
-# https://docs.litellm.ai/docs/completion/token_usage
-#custom_tokenizer = ""
-
-[llm.gpt4o-mini]
-api_key = "your-api-key"
-model = "gpt-4o"
-
-
-#################################### Agent ###################################
-# Configuration for agents (group name starts with 'agent')
-# Use 'agent' for the default agent config
-# otherwise, group name must be `agent.<agent_name>` (case-sensitive), e.g.
-# agent.CodeActAgent
-##############################################################################
-[agent]
-# Name of the micro agent to use for this agent
-#micro_agent_name = ""
-
-# Memory enabled
-#memory_enabled = false
-
-# Memory maximum threads
-#memory_max_threads = 3
-
-# LLM config group to use
-#llm_config = 'your-llm-config-group'
-
-[agent.RepoExplorerAgent]
-# Example: use a cheaper model for RepoExplorerAgent to reduce cost, especially
-# useful when an agent doesn't demand high quality but uses a lot of tokens
-llm_config = 'gpt3'
-
-#################################### Sandbox ###################################
-# Configuration for the sandbox
-##############################################################################
-[sandbox]
-# Sandbox timeout in seconds
-#timeout = 120
-
-# Sandbox user ID
-#user_id = 1000
-
-# Container image to use for the sandbox
-#base_container_image = "nikolaik/python-nodejs:python3.12-nodejs22"
-
-# Use host network
-#use_host_network = false
-
-# runtime extra build args
-#runtime_extra_build_args = ["--network=host", "--add-host=host.docker.internal:host-gateway"]
-
-# Enable auto linting after editing
-#enable_auto_lint = false
-
-# Whether to initialize plugins
-#initialize_plugins = true
-
-# Extra dependencies to install in the runtime image
-#runtime_extra_deps = ""
-
-# Environment variables to set at the launch of the runtime
-#runtime_startup_env_vars = {}
-
-# BrowserGym environment to use for evaluation
-#browsergym_eval_env = ""
-
-#################################### Security ###################################
-# Configuration for security features
-##############################################################################
-[security]
-
-# Enable confirmation mode (For Headless / CLI only -  In Web this is overridden by Session Init)
-#confirmation_mode = false
-
-# The security analyzer to use (For Headless / CLI only -  In Web this is overridden by Session Init)
-#security_analyzer = ""
-
-#################################### Eval ####################################
-# Configuration for the evaluation, please refer to the specific evaluation
-# plugin for the available options
-##############################################################################

containers/README.md

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

containers/app/Dockerfile

@@ -1,19 +1,17 @@
-ARG OPENHANDS_BUILD_VERSION=dev
-FROM node:21.7.2-bookworm-slim AS frontend-builder
+FROM node:21.7.2-bookworm-slim as frontend-builder
 
 WORKDIR /app
 
 COPY ./frontend/package.json frontend/package-lock.json ./
-RUN npm install -g npm@10.5.1
-RUN npm ci
+RUN npm install
 
 COPY ./frontend ./
-RUN npm run build
+RUN npm run make-i18n && npm run build
 
-FROM python:3.12.3-slim AS backend-builder
+FROM python:3.12-slim as backend-builder
 
 WORKDIR /app
-ENV PYTHONPATH='/app'
+ENV PYTHONPATH '/app'
 
 ENV POETRY_NO_INTERACTION=1 \
     POETRY_VIRTUALENVS_IN_PROJECT=1 \
@@ -26,72 +24,31 @@ RUN apt-get update -y \
 
 COPY ./pyproject.toml ./poetry.lock ./
 RUN touch README.md
-RUN export POETRY_CACHE_DIR && poetry install --without evaluation,llama-index --no-root && rm -rf $POETRY_CACHE_DIR
+RUN poetry install --without evaluation --no-root && rm -rf $POETRY_CACHE_DIR
 
-FROM python:3.12.3-slim AS openhands-app
+FROM python:3.12-slim as runtime
 
 WORKDIR /app
 
-ARG OPENHANDS_BUILD_VERSION #re-declare for this section
-
-ENV RUN_AS_OPENHANDS=true
-# A random number--we need this to be different from the user's UID on the host machine
-ENV OPENHANDS_USER_ID=42420
-ENV SANDBOX_LOCAL_RUNTIME_URL=http://host.docker.internal
+ENV RUN_AS_DEVIN=false
 ENV USE_HOST_NETWORK=false
+ENV SSH_HOSTNAME=host.docker.internal
 ENV WORKSPACE_BASE=/opt/workspace_base
-ENV OPENHANDS_BUILD_VERSION=$OPENHANDS_BUILD_VERSION
-ENV SANDBOX_USER_ID=0
-ENV FILE_STORE=local
-ENV FILE_STORE_PATH=/.openhands-state
-RUN mkdir -p $FILE_STORE_PATH
 RUN mkdir -p $WORKSPACE_BASE
 
 RUN apt-get update -y \
-    && apt-get install -y curl ssh sudo
-
-# Default is 1000, but OSX is often 501
-RUN sed -i 's/^UID_MIN.*/UID_MIN 499/' /etc/login.defs
-# Default is 60000, but we've seen up to 200000
-RUN sed -i 's/^UID_MAX.*/UID_MAX 1000000/' /etc/login.defs
-
-RUN groupadd app
-RUN useradd -l -m -u $OPENHANDS_USER_ID -s /bin/bash openhands && \
-    usermod -aG app openhands && \
-    usermod -aG sudo openhands && \
-    echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
-RUN chown -R openhands:app /app && chmod -R 770 /app
-RUN sudo chown -R openhands:app $WORKSPACE_BASE && sudo chmod -R 770 $WORKSPACE_BASE
-USER openhands
+    && apt-get install -y curl ssh
 
 ENV VIRTUAL_ENV=/app/.venv \
     PATH="/app/.venv/bin:$PATH" \
     PYTHONPATH='/app'
 
-COPY --chown=openhands:app --chmod=770 --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
-RUN playwright install --with-deps chromium
+COPY --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
 
-COPY --chown=openhands:app --chmod=770 ./openhands ./openhands
-COPY --chown=openhands:app --chmod=777 ./openhands/runtime/plugins ./openhands/runtime/plugins
-COPY --chown=openhands:app --chmod=770 ./openhands/agenthub ./openhands/agenthub
-COPY --chown=openhands:app ./pyproject.toml ./pyproject.toml
-COPY --chown=openhands:app ./poetry.lock ./poetry.lock
-COPY --chown=openhands:app ./README.md ./README.md
-COPY --chown=openhands:app ./MANIFEST.in ./MANIFEST.in
-COPY --chown=openhands:app ./LICENSE ./LICENSE
+COPY ./opendevin ./opendevin
+COPY ./agenthub ./agenthub
+RUN python opendevin/download.py # No-op to download assets
 
-# This is run as "openhands" user, and will create __pycache__ with openhands:openhands ownership
-RUN python openhands/core/download.py # No-op to download assets
-# Add this line to set group ownership of all files/directories not already in "app" group
-# openhands:openhands -> openhands:app
-RUN find /app \! -group app -exec chgrp app {} +
+COPY --from=frontend-builder /app/dist ./frontend/dist
 
-COPY --chown=openhands:app --chmod=770 --from=frontend-builder /app/build ./frontend/build
-COPY --chown=openhands:app --chmod=770 ./containers/app/entrypoint.sh /app/entrypoint.sh
-
-USER root
-
-WORKDIR /app
-
-ENTRYPOINT ["/app/entrypoint.sh"]
-CMD ["uvicorn", "openhands.server.listen:app", "--host", "0.0.0.0", "--port", "3000"]
+CMD ["uvicorn", "opendevin.server.listen:app", "--host", "0.0.0.0", "--port", "3000"]

containers/app/config.sh

@@ -1,4 +1,2 @@
-DOCKER_REGISTRY=ghcr.io
-DOCKER_ORG=all-hands-ai
-DOCKER_IMAGE=openhands
+DOCKER_REPOSITORY=ghcr.io/opendevin/opendevin
 DOCKER_BASE_DIR="."

containers/app/entrypoint.sh

@@ -1,69 +0,0 @@
-#!/bin/bash
-set -eo pipefail
-
-echo "Starting OpenHands..."
-if [[ $NO_SETUP == "true" ]]; then
-  echo "Skipping setup, running as $(whoami)"
-  "$@"
-  exit 0
-fi
-
-if [ "$(id -u)" -ne 0 ]; then
-  echo "The OpenHands entrypoint.sh must run as root"
-  exit 1
-fi
-
-if [ -z "$SANDBOX_USER_ID" ]; then
-  echo "SANDBOX_USER_ID is not set"
-  exit 1
-fi
-
-if [ -z "$WORKSPACE_MOUNT_PATH" ]; then
-  # This is set to /opt/workspace in the Dockerfile. But if the user isn't mounting, we want to unset it so that OpenHands doesn't mount at all
-  unset WORKSPACE_BASE
-fi
-
-if [[ "$SANDBOX_USER_ID" -eq 0 ]]; then
-  echo "Running OpenHands as root"
-  export RUN_AS_OPENHANDS=false
-  mkdir -p /root/.cache/ms-playwright/
-  if [ -d "/home/openhands/.cache/ms-playwright/" ]; then
-    mv /home/openhands/.cache/ms-playwright/ /root/.cache/
-  fi
-  "$@"
-else
-  echo "Setting up enduser with id $SANDBOX_USER_ID"
-  if id "enduser" &>/dev/null; then
-    echo "User enduser already exists. Skipping creation."
-  else
-    if ! useradd -l -m -u $SANDBOX_USER_ID -s /bin/bash enduser; then
-      echo "Failed to create user enduser with id $SANDBOX_USER_ID. Moving openhands user."
-      incremented_id=$(($SANDBOX_USER_ID + 1))
-      usermod -u $incremented_id openhands
-      if ! useradd -l -m -u $SANDBOX_USER_ID -s /bin/bash enduser; then
-        echo "Failed to create user enduser with id $SANDBOX_USER_ID for a second time. Exiting."
-        exit 1
-      fi
-    fi
-  fi
-  usermod -aG app enduser
-  # get the user group of /var/run/docker.sock and set openhands to that group
-  DOCKER_SOCKET_GID=$(stat -c '%g' /var/run/docker.sock)
-  echo "Docker socket group id: $DOCKER_SOCKET_GID"
-  if getent group $DOCKER_SOCKET_GID; then
-    echo "Group with id $DOCKER_SOCKET_GID already exists"
-  else
-    echo "Creating group with id $DOCKER_SOCKET_GID"
-    groupadd -g $DOCKER_SOCKET_GID docker
-  fi
-
-  mkdir -p /home/enduser/.cache/huggingface/hub/
-  mkdir -p /home/enduser/.cache/ms-playwright/
-  if [ -d "/home/openhands/.cache/ms-playwright/" ]; then
-    mv /home/openhands/.cache/ms-playwright/ /home/enduser/.cache/
-  fi
-
-  usermod -aG $DOCKER_SOCKET_GID enduser
-  echo "Running as enduser"
-  su enduser /bin/bash -c "${*@Q}" # This magically runs any arguments passed to the script as a command
-fi

containers/build.sh

@@ -1,156 +1,48 @@
 #!/bin/bash
 set -eo pipefail
 
-# Initialize variables with default values
-image_name=""
-org_name=""
+image_name=$1
 push=0
-load=0
-tag_suffix=""
-
-# Function to display usage information
-usage() {
-    echo "Usage: $0 -i <image_name> [-o <org_name>] [--push] [--load] [-t <tag_suffix>]"
-    echo "  -i: Image name (required)"
-    echo "  -o: Organization name"
-    echo "  --push: Push the image"
-    echo "  --load: Load the image"
-    echo "  -t: Tag suffix"
-    exit 1
-}
-
-# Parse command-line options
-while [[ $# -gt 0 ]]; do
-    case $1 in
-        -i) image_name="$2"; shift 2 ;;
-        -o) org_name="$2"; shift 2 ;;
-        --push) push=1; shift ;;
-        --load) load=1; shift ;;
-        -t) tag_suffix="$2"; shift 2 ;;
-        *) usage ;;
-    esac
-done
-# Check if required arguments are provided
-if [[ -z "$image_name" ]]; then
-    echo "Error: Image name is required."
-    usage
-fi
-
-echo "Building: $image_name"
-tags=()
-
-OPENHANDS_BUILD_VERSION="dev"
-
-cache_tag_base="buildcache"
-cache_tag="$cache_tag_base"
-
-if [[ -n $RELEVANT_SHA ]]; then
-  git_hash=$(git rev-parse --short "$RELEVANT_SHA")
-  tags+=("$git_hash")
-  tags+=("$RELEVANT_SHA")
+if [[ $2 == "--push" ]]; then
+  push=1
 fi
 
+echo -e "Building: $image_name"
+tags=(latest)
 if [[ -n $GITHUB_REF_NAME ]]; then
   # check if ref name is a version number
-  if [[ $GITHUB_REF_NAME =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
-    major_version=$(echo "$GITHUB_REF_NAME" | cut -d. -f1)
-    minor_version=$(echo "$GITHUB_REF_NAME" | cut -d. -f1,2)
-    tags+=("$major_version" "$minor_version")
-    tags+=("latest")
+  if [[ $GITHUB_REF_NAME =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+    major_version=$(echo $GITHUB_REF_NAME | cut -d. -f1)
+    minor_version=$(echo $GITHUB_REF_NAME | cut -d. -f1,2)
+    tags+=($major_version $minor_version)
   fi
-  sanitized_ref_name=$(echo "$GITHUB_REF_NAME" | sed 's/[^a-zA-Z0-9.-]\+/-/g')
-  OPENHANDS_BUILD_VERSION=$sanitized_ref_name
-  sanitized_ref_name=$(echo "$sanitized_ref_name" | tr '[:upper:]' '[:lower:]') # lower case is required in tagging
-  tags+=("$sanitized_ref_name")
-  cache_tag+="-${sanitized_ref_name}"
+  sanitized=$(echo $GITHUB_REF_NAME | sed 's/[^a-zA-Z0-9.-]\+/-/g')
+  tags+=($sanitized)
 fi
-
-if [[ -n $tag_suffix ]]; then
-  cache_tag+="-${tag_suffix}"
-  for i in "${!tags[@]}"; do
-    tags[$i]="${tags[$i]}-$tag_suffix"
-  done
-fi
-
 echo "Tags: ${tags[@]}"
 
-if [[ "$image_name" == "openhands" ]]; then
-  dir="./containers/app"
-elif [[ "$image_name" == "runtime" ]]; then
-  dir="./containers/runtime"
-else
-  dir="./containers/$image_name"
-fi
-
-if [[ (! -f "$dir/Dockerfile") && "$image_name" != "runtime" ]]; then
-  # Allow runtime to be built without a Dockerfile
+dir=./containers/$image_name
+if [ ! -f $dir/Dockerfile ]; then
   echo "No Dockerfile found"
   exit 1
 fi
-if [[ ! -f "$dir/config.sh" ]]; then
+if [ ! -f $dir/config.sh ]; then
   echo "No config.sh found for Dockerfile"
   exit 1
 fi
-
-source "$dir/config.sh"
-
-if [[ -n "$org_name" ]]; then
-  DOCKER_ORG="$org_name"
-fi
-
-# If $DOCKER_IMAGE_SOURCE_TAG is set, add it to the tags
-if [[ -n "$DOCKER_IMAGE_SOURCE_TAG" ]]; then
-  tags+=("$DOCKER_IMAGE_SOURCE_TAG")
-fi
-# If $DOCKER_IMAGE_TAG is set, add it to the tags
-if [[ -n "$DOCKER_IMAGE_TAG" ]]; then
-  tags+=("$DOCKER_IMAGE_TAG")
-fi
-
-DOCKER_REPOSITORY="$DOCKER_REGISTRY/$DOCKER_ORG/$DOCKER_IMAGE"
-DOCKER_REPOSITORY=${DOCKER_REPOSITORY,,} # lowercase
+source $dir/config.sh
 echo "Repo: $DOCKER_REPOSITORY"
 echo "Base dir: $DOCKER_BASE_DIR"
-
+#docker pull $DOCKER_REPOSITORY:main || true # try to get any cached layers
 args=""
-for tag in "${tags[@]}"; do
+for tag in ${tags[@]}; do
   args+=" -t $DOCKER_REPOSITORY:$tag"
 done
-
 if [[ $push -eq 1 ]]; then
   args+=" --push"
-  args+=" --cache-to=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag,mode=max"
 fi
 
-if [[ $load -eq 1 ]]; then
-  args+=" --load"
-fi
-
-echo "Args: $args"
-
-# Modify the platform selection based on --load flag
-if [[ $load -eq 1 ]]; then
-  # When loading, build only for the current platform
-  platform=$(docker version -f '{{.Server.Os}}/{{.Server.Arch}}')
-else
-  # For push or without load, build for multiple platforms
-  platform="linux/amd64,linux/arm64"
-fi
-
-echo "Building for platform(s): $platform"
-
 docker buildx build \
   $args \
-  --build-arg OPENHANDS_BUILD_VERSION="$OPENHANDS_BUILD_VERSION" \
-  --cache-from=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag \
-  --cache-from=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag_base-main \
-  --platform $platform \
-  --provenance=false \
-  -f "$dir/Dockerfile" \
-  "$DOCKER_BASE_DIR"
-
-# If load was requested, print the loaded images
-if [[ $load -eq 1 ]]; then
-  echo "Local images built:"
-  docker images "$DOCKER_REPOSITORY" --format "{{.Repository}}:{{.Tag}}"
-fi
+  --platform linux/amd64,linux/arm64 \
+  -f $dir/Dockerfile $DOCKER_BASE_DIR

containers/dev/Dockerfile

@@ -1,124 +0,0 @@
-# syntax=docker/dockerfile:1
-
-###
-FROM ubuntu:22.04 AS dind
-
-# https://docs.docker.com/engine/install/ubuntu/
-RUN apt-get update && apt-get install -y \
-	ca-certificates \
-	curl \
-	&& install -m 0755 -d /etc/apt/keyrings \
-	&& curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc \
-	&& chmod a+r /etc/apt/keyrings/docker.asc \
-	&& echo \
-		"deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
-		$(. /etc/os-release && echo "$VERSION_CODENAME") stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null
-
-RUN apt-get update && apt-get install -y \
-	docker-ce \
-	docker-ce-cli \
-	containerd.io \
-	docker-buildx-plugin \
-	docker-compose-plugin \
-	&& rm -rf /var/lib/apt/lists/* \
-	&& apt-get clean \
-	&& apt-get autoremove -y
-
-###
-FROM dind AS openhands
-
-ENV DEBIAN_FRONTEND=noninteractive
-
-#
-RUN apt-get update && apt-get install -y \
-	bash \
-    build-essential \
-    curl \
-	git \
-	git-lfs \
-	software-properties-common \
-	make \
-    netcat \
-    sudo \
-	wget \
-	&& rm -rf /var/lib/apt/lists/* \
-	&& apt-get clean \
-	&& apt-get autoremove -y
-
-# https://github.com/cli/cli/blob/trunk/docs/install_linux.md
-RUN curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg | dd of=/usr/share/keyrings/githubcli-archive-keyring.gpg \
-	&& chmod go+r /usr/share/keyrings/githubcli-archive-keyring.gpg \
-	&& echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" | tee /etc/apt/sources.list.d/github-cli.list > /dev/null \
-	&& apt-get update && apt-get -y install \
-    gh \
-  && rm -rf /var/lib/apt/lists/* \
-  && apt-get clean \
-  && apt-get autoremove -y
-
-# Python 3.12
-RUN add-apt-repository ppa:deadsnakes/ppa \
-    && apt-get update \
-    && apt-get install -y python3.12 python3.12-venv python3.12-dev python3-pip \
-    && ln -s /usr/bin/python3.12 /usr/bin/python
-
-# NodeJS >= 18.17.1
-RUN curl -fsSL https://deb.nodesource.com/setup_18.x | bash - \
-    && apt-get install -y nodejs
-
-# Poetry >= 1.8
-RUN curl -fsSL https://install.python-poetry.org | python3.12 - \
-    && ln -s ~/.local/bin/poetry /usr/local/bin/poetry
-
-#
-RUN <<EOF
-#!/bin/bash
-printf "#!/bin/bash
-set +x
-uname -a
-docker --version
-gh --version | head -n 1
-git --version
-#
-python --version
-echo node `node --version`
-echo npm `npm --version`
-poetry --version
-netcat -h 2>&1 | head -n 1
-" > /version.sh
-chmod a+x /version.sh
-EOF
-
-###
-FROM openhands AS dev
-
-RUN apt-get update && apt-get install -y \
-	dnsutils \
-	file \
-	iproute2 \
-	jq \
-	lsof \
-	ripgrep \
-	silversearcher-ag \
-	vim \
-	&& rm -rf /var/lib/apt/lists/* \
-	&& apt-get clean \
-	&& apt-get autoremove -y
-
-WORKDIR /app
-
-# cache build dependencies
-RUN \
-  --mount=type=bind,source=./,target=/app/ \
-  <<EOF
-#!/bin/bash
-make -s clean
-make -s check-dependencies
-make -s install-python-dependencies
-
-# NOTE
-# node_modules are .dockerignore-d therefore not mountable
-# make -s install-frontend-dependencies
-EOF
-
-#
-CMD ["bash"]

containers/dev/README.md

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

containers/dev/compose.yml

@@ -1,38 +0,0 @@
-#
-services:
-  dev:
-    privileged: true
-    build:
-      context: ${OPENHANDS_WORKSPACE:-../../}
-      dockerfile: ./containers/dev/Dockerfile
-    image: openhands:dev
-    container_name: openhands-dev
-    environment:
-      - BACKEND_HOST=${BACKEND_HOST:-"0.0.0.0"}
-      - SANDBOX_API_HOSTNAME=host.docker.internal
-      #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.17-nikolaik}
-      - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
-      - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
-    ports:
-      - "3000:3000"
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock
-      - ${WORKSPACE_BASE:-$PWD/workspace}:/opt/workspace_base
-      # source code
-      - ${OPENHANDS_WORKSPACE:-../../}:/app
-      # host credentials
-      - $HOME/.git-credentials:/root/.git-credentials:ro
-      - $HOME/.gitconfig:/root/.gitconfig:ro
-      - $HOME/.npmrc:/root/.npmrc:ro
-      # cache
-      - cache-data:/root/.cache
-    pull_policy: never
-    stdin_open: true
-    tty: true
-
-##
-volumes:
-  cache-data:

containers/dev/dev.sh

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

containers/e2b-sandbox/README.md

@@ -1,15 +0,0 @@
-# How to build custom E2B sandbox for OpenHands
-
-[E2B](https://e2b.dev) is an [open-source](https://github.com/e2b-dev/e2b) secure cloud environment (sandbox) made for running AI-generated code and agents. E2B offers [Python](https://pypi.org/project/e2b/) and [JS/TS](https://www.npmjs.com/package/e2b) SDK to spawn and control these sandboxes.
-
-
-1. Install the CLI with NPM.
-    ```sh
-    npm install -g @e2b/cli@latest
-    ```
-    Full CLI API is [here](https://e2b.dev/docs/cli/installation).
-
-1. Build the sandbox
-  ```sh
-  e2b template build --dockerfile ./Dockerfile --name "openhands"
-  ```

containers/e2b-sandbox/e2b.toml

@@ -1,14 +0,0 @@
-# This is a config for E2B sandbox template.
-# You can use 'template_id' (785n69crgahmz0lkdw9h) or 'template_name (openhands) from this config to spawn a sandbox:
-
-# Python SDK
-# from e2b import Sandbox
-# sandbox = Sandbox(template='openhands')
-
-# JS SDK
-# import { Sandbox } from 'e2b'
-# const sandbox = await Sandbox.create({ template: 'openhands' })
-
-dockerfile = "Dockerfile"
-template_name = "openhands"
-template_id = "785n69crgahmz0lkdw9h"

containers/evaluation/Dockerfile

@@ -0,0 +1,41 @@
+FROM ubuntu:20.04
+
+# https://github.com/princeton-nlp/SWE-bench/issues/15#issuecomment-1815392192
+RUN apt-get update && \
+    apt-get install -y bash gcc git jq wget && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+RUN git config --global user.email "swebench@pnlp.org"
+RUN git config --global user.name "swebench"
+
+RUN apt update && apt install -y build-essential
+
+# Create new user
+RUN useradd -ms /bin/bash swe-bench
+USER swe-bench
+WORKDIR /home/swe-bench
+
+# Setup Conda
+ENV PATH="/home/swe-bench/miniconda3/bin:${PATH}"
+ARG PATH="/home/swe-bench/miniconda3/bin:${PATH}"
+RUN wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-`uname -m`.sh -O miniconda.sh \
+    && mkdir ~/.conda \
+    && bash miniconda.sh -b \
+    && rm -f miniconda.sh
+RUN conda --version
+
+# Setup SWE-Bench Env
+COPY environment.yml .
+RUN conda env create -f environment.yml
+
+# Add commands
+COPY ./commands.sh .
+RUN . ./commands.sh
+
+# Some missing packages
+RUN pip install datasets python-dotenv gitpython
+
+RUN conda init bash
+
+CMD ["/bin/bash"]

containers/evaluation/config.sh

@@ -0,0 +1,2 @@
+DOCKER_REPOSITORY=ghcr.io/opendevin/eval-swe-bench
+DOCKER_BASE_DIR=evaluation/SWE-bench

containers/runtime/README.md

@@ -1,12 +0,0 @@
-# Dynamically constructed Dockerfile
-
-This folder builds a runtime image (sandbox), which will use a dynamically generated `Dockerfile`
-that depends on the `base_image` **AND** a [Python source distribution](https://docs.python.org/3.10/distutils/sourcedist.html) that is based on the current commit of `openhands`.
-
-The following command will generate a `Dockerfile` file for `nikolaik/python-nodejs:python3.12-nodejs22` (the default base image), an updated `config.sh` and the runtime source distribution files/folders into `containers/runtime`:
-
-```bash
-poetry run python3 openhands/runtime/utils/runtime_build.py \
-    --base_image nikolaik/python-nodejs:python3.12-nodejs22 \
-    --build_folder containers/runtime
-```

containers/runtime/config.sh

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

containers/sandbox/Dockerfile

@@ -17,3 +17,5 @@ RUN apt-get update && apt-get install -y \
     openssh-server \
     sudo \
     && rm -rf /var/lib/apt/lists/*
+
+RUN service ssh start

containers/sandbox/config.sh

@@ -0,0 +1,2 @@
+DOCKER_REPOSITORY=ghcr.io/opendevin/sandbox
+DOCKER_BASE_DIR="."

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

@@ -3,41 +3,49 @@ repos:
     rev: v4.5.0
     hooks:
       - id: trailing-whitespace
-        exclude: docs/modules/python
       - id: end-of-file-fixer
-        exclude: docs/modules/python
       - id: check-yaml
       - id: debug-statements
 
-  - repo: https://github.com/tox-dev/pyproject-fmt
-    rev: 1.7.0
+  - repo: https://github.com/PyCQA/flake8
+    rev: 7.0.0
     hooks:
-      - id: pyproject-fmt
-  - repo: https://github.com/abravalheri/validate-pyproject
-    rev: v0.16
+      - id: flake8
+        args: ['--select=Q000']  # Q000 is the error code for single quote enforcement
+        additional_dependencies:
+          - flake8-quotes
+
+  - repo: https://github.com/hhatto/autopep8
+    rev: v2.1.0
     hooks:
-      - id: validate-pyproject
+      - id: autopep8
+
+  - repo: https://github.com/asottile/setup-cfg-fmt
+    rev: v2.5.0
+    hooks:
+      - id: setup-cfg-fmt
+        always_run: true
+        pass_filenames: false
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.4.1
+    rev: v0.3.7
     hooks:
       # Run the linter.
       - id: ruff
-        entry: ruff check --config dev_config/python/ruff.toml
-        types_or: [python, pyi, jupyter]
-        args: [--fix]
+        entry: ruff check --config dev_config/python/ruff.toml opendevin/ agenthub/
+        types_or: [ python, pyi, jupyter ]
+        args: [ --fix ]
       # Run the formatter.
       - id: ruff-format
-        entry: ruff format --config dev_config/python/ruff.toml
-        types_or: [python, pyi, jupyter]
+        entry: ruff check --config dev_config/python/ruff.toml opendevin/ agenthub/
+        types_or: [ python, pyi, jupyter ]
 
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.9.0
     hooks:
       - id: mypy
-        additional_dependencies:
-          [types-requests, types-setuptools, types-pyyaml, types-toml]
-        entry: mypy --config-file dev_config/python/mypy.ini openhands/
+        additional_dependencies: [types-requests, types-setuptools, types-pyyaml, types-toml]
+        entry: mypy --config-file dev_config/python/mypy.ini opendevin/ agenthub/
         always_run: true
         pass_filenames: false

dev_config/python/mypy.ini

@@ -7,3 +7,5 @@ warn_unreachable = True
 warn_redundant_casts = True
 no_implicit_optional = True
 strict_optional = True
+
+exclude = agenthub/monologue_agent/regression

dev_config/python/ruff.toml

@@ -1,26 +1,3 @@
-[lint]
-select = [
-    "E",
-    "W",
-    "F",
-    "I",
-    "Q",
-    "B",
-]
-
-ignore = [
-    "E501",
-    "B003",
-    "B007",
-    "B009",
-    "B010",
-    "B904",
-    "B018",
-]
-
-[lint.flake8-quotes]
-docstring-quotes = "double"
-inline-quotes = "single"
-
-[format]
-quote-style = "single"
+exclude = [
+    "agenthub/monologue_agent/regression/",
+]

docs/.gitignore

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

docs/README-zh.md

@@ -0,0 +1,251 @@
+> 警告：此说明文件可能已过时。应将 README.md 视为真实的来源。如果您注意到差异，请打开一个拉取请求以更新此说明文件。
+
+[English](../README.md) | [中文](README-zh.md)
+
+<a name="readme-top"></a>
+<!--
+*** Thanks for checking out the Best-README-Template. If you have a suggestion
+*** that would make this better, please fork the repo and create a pull request
+*** or simply open an issue with the tag "enhancement".
+*** Don't forget to give the project a star!
+*** Thanks again! Now go create something AMAZING! :D
+-->
+
+
+
+<!-- PROJECT SHIELDS -->
+<!--
+*** I'm using markdown "reference style" links for readability.
+*** Reference links are enclosed in brackets [ ] instead of parentheses ( ).
+*** See the bottom of this document for the declaration of the reference variables
+*** for contributors-url, forks-url, etc. This is an optional, concise syntax you may use.
+*** https://www.markdownguide.org/basic-syntax/#reference-style-links
+-->
+
+<div align="center">
+  <a href="https://github.com/OpenDevin/OpenDevin/graphs/contributors"><img src="https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge" alt="Contributors"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/network/members"><img src="https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge" alt="Forks"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/stargazers"><img src="https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge" alt="Stargazers"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/issues"><img src="https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge" alt="Issues"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE"><img src="https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge" alt="MIT License"></a>
+  </br>
+  <a href="https://join.slack.com/t/opendevin/shared_invite/zt-2etftj1dd-X1fDL2PYIVpsmJZkqEYANw"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
+  <a href="https://discord.gg/mBuDGRzzES"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
+</div>
+
+<!-- PROJECT LOGO -->
+<div align="center">
+  <img src="../logo.png" alt="Logo" width="200" height="200">
+  <h1 align="center">OpenDevin：少写代码，多创作</h1>
+</div>
+
+
+
+
+<!-- TABLE OF CONTENTS -->
+<details>
+  <summary>🗂️ Table of Contents</summary>
+  <ol>
+    <li><a href="#-mission">🎯 Mission</a></li>
+    <li><a href="#-what-is-devin">🤔 What is Devin?</a></li>
+    <li><a href="#-why-opendevin">🐚 Why OpenDevin?</a></li>
+    <li><a href="#-project-status">🚧 Project Status</a></li>
+      <a href="#-get-started">🚀 Get Started</a>
+      <ul>
+        <li><a href="#1-requirements">1. Requirements</a></li>
+        <li><a href="#2-build-and-setup">2. Build and Setup</a></li>
+        <li><a href="#3-run-the-application">3. Run the Application</a></li>
+        <li><a href="#4-individual-server-startup">4. Individual Server Startup</a></li>
+        <li><a href="#5-help">5. Help</a></li>
+      </ul>
+    </li>
+    <li><a href="#%EF%B8%8F-research-strategy">⭐️ Research Strategy</a></li>
+    <li><a href="#-how-to-contribute">🤝 How to Contribute</a></li>
+    <li><a href="#-join-our-community">🤖 Join Our Community</a></li>
+    <li><a href="#%EF%B8%8F-built-with">🛠️ Built With</a></li>
+    <li><a href="#-license">📜 License</a></li>
+  </ol>
+</details>
+
+## 🎯 使命
+
+[Project Demo Video](https://github.com/OpenDevin/OpenDevin/assets/38853559/71a472cc-df34-430c-8b1d-4d7286c807c9)
+
+
+欢迎来到 OpenDevin，一个开源项目，旨在复制 Devin，一款自主的 AI 软件工程师，能够执行复杂的工程任务，并与用户积极合作，共同进行软件开发项目。该项目立志通过开源社区的力量复制、增强和创新 Devin。
+
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
+
+## 🤔 Devin 是什么？
+Devin 代表着一种尖端的自主代理程序，旨在应对软件工程的复杂性。它利用诸如 shell、代码编辑器和 Web 浏览器等工具的组合，展示了在软件开发中利用 LLMs（大型语言模型）的未开发潜力。我们的目标是探索和拓展 Devin 的能力，找出其优势和改进空间，以指导开源代码模型的进展。
+
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
+
+## 🐚 为什么选择 OpenDevin？
+OpenDevin 项目源于对复制、增强和超越原始 Devin 模型的愿望。通过与开源社区的互动，我们旨在解决 Code LLMs 在实际场景中面临的挑战，创作出对社区有重大贡献并为未来进步铺平道路的作品。
+
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
+
+## 🚧 项目状态
+
+OpenDevin 目前仍在进行中，但您已经可以运行 alpha 版本来查看端到端系统的运行情况。项目团队正在积极努力实现以下关键里程碑：
+
+- **用户界面（UI）**：开发用户友好的界面，包括聊天界面、演示命令的 shell 和 Web 浏览器。
+- **架构**：构建一个稳定的代理框架，具有强大的后端，可以读取、写入和运行简单的命令。
+- **代理能力**：增强代理的能力，以生成 bash 脚本、运行测试和执行其他软件工程任务。
+- **评估**：建立一个与 Devin 评估标准一致的最小评估流水线。
+
+在完成 MVP 后，团队将专注于各个领域的研究，包括基础模型、专家能力、评估和代理研究。
+
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
+
+## ⚠️ 注意事项和警告
+* OpenDevin 仍然是一个 alpha 项目。它变化很快且不稳定。我们正在努力在未来几周发布稳定版本。
+* OpenDevin 会向您配置的 LLM 发出许多提示。大多数 LLM 都需要花费金钱，请务必设置花费限制并监控使用情况。
+* OpenDevin 在 Docker 沙箱中运行 `bash` 命令，因此不应影响您的计算机。但您的工作区目录将附加到该沙箱，并且目录中的文件可能会被修改或删除。
+* 我们默认的代理目前是 MonologueAgent，具有有限的功能，但相当稳定。我们正在开发其他代理实现，包括 [SWE 代理](https://swe-agent.com/)。您可以[在这里阅读我们当前的代理集合](./docs/documentation/Agents.md)。
+
+## 🚀 开始
+
+开始使用 OpenDevin 项目非常简单。按照以下简单步骤在您的系统上设置和运行 OpenDevin：
+
+运行 OpenDevin 最简单的方法是在 Docker 容器中。
+您可以运行：
+```bash
+# 您的 OpenAI API 密钥，或任何其他 LLM API 密钥
+export LLM_API_KEY="sk-..."
+
+# 您想要 OpenDevin 修改的目录。必须是绝对路径！
+export WORKSPACE_DIR=$(pwd)/workspace
+
+docker run \
+    -e LLM_API_KEY \
+    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_DIR \
+    -v $WORKSPACE_DIR:/opt/workspace_base \
+    -v /var/run/docker.sock:/var/run/docker.sock \
+    -p 3000:3000 \
+    ghcr.io/opendevin/opendevin:latest
+```
+将 `$(pwd)/workspace` 替换为您希望 OpenDevin 使用的代码路径。
+
+您可以在 `http://localhost:3000` 找到正在运行的 OpenDevin。
+
+请参阅[Development.md](Development.md)以获取在没有 Docker 的情况下运行 OpenDevin 的说明。
+
+## 🤖 LLM 后端
+OpenDevin 可以与任何 LLM 后端配合使用。
+要获取提供的 LM 提供商和模型的完整列表，请参阅
+[litellm 文档](https://docs.litellm.ai/docs/providers)。
+
+`LLM_MODEL` 环境变量控制在编程交互中使用哪个模型，
+但在 OpenDevin UI 中选择模型将覆盖此设置。
+
+对于某些 LLM，可能需要以下环境变量：
+* `LLM_API_KEY`
+* `LLM_BASE_URL`
+* `LLM_EMBEDDING_MODEL`
+* `LLM_DEPLOYMENT_NAME`
+* `LLM_API_VERSION`
+
+**关于替代模型的说明：**
+某些替代模型可能比其他模型更具挑战性。
+不要害怕，勇敢的冒险家！我们将很快公布 LLM 特定的文档，指导您完成您的探险。
+如果您已经掌握了除 OpenAI 的 GPT 之外的模型使用技巧，
+我们鼓励您[与我们分享您的设置说明](https://github.com/OpenDevin/OpenDevin/issues/417)。
+
+还有[使用 ollama 运行本地模型的文档](./docs/documentation/LOCAL_LLM_GUIDE.md)。
+
+## ⭐️ 研究策略
+
+利用 LLMs 实现生产级应用程序的完全复制是一个复杂的任务。我们的策略包括：
+
+1. **核心技术研究：** 专注于基础研究，以了解和改进代码生成和处理的技术方面。
+2. **专业能力：** 通过数据整理、训练方法等手段增强核心组件的效能。
+3. **任务规划：** 开发能力，用于错误检测、代码库管理和优化。
+4. **评估：** 建立全面的评估指标，以更好地了解和改进我们的模型。
+
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
+
+## 🤝 如何贡献
+
+OpenDevin 是一个社区驱动的项目，我们欢迎所有人的贡献。无论您是开发人员、研究人员，还是对利用人工智能推动软件工程领域发展充满热情的人，都有许多参与方式：
+
+- **代码贡献：** 帮助我们开发核心功能、前端界面或沙盒解决方案。
+- **研究和评估：** 为我们对软件工程中的 LLMs 的理解做出贡献，参与评估模型，或提出改进意见。
+- **反馈和测试：** 使用 OpenDevin 工具集，报告错误，提出功能建议，或就可用性提供反馈。
+
+详情请查看[此文档](./CONTRIBUTING.md)。
+
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
+
+## 🤖 加入我们的社区
+
+现在我们既有 Slack 工作空间用于协作构建 OpenDevin，也有 Discord 服务器用于讨论与项目、LLM、Agent 等相关的任何事情。
+
+* [Slack 工作空间](https://join.slack.com/t/opendevin/shared_invite/zt-2etftj1dd-X1fDL2PYIVpsmJZkqEYANw)
+* [Discord 服务器](https://discord.gg/mBuDGRzzES)
+
+如果你愿意贡献，欢迎加入我们的社区（请注意，现在无需填写[表格](https://forms.gle/758d5p6Ve8r2nxxq6)）。让我们一起简化软件工程！
+
+🐚 **少写代码，用OpenDevin创造更多。**
+
+[![Star History Chart](https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date)](https://star-history.com/#OpenDevin/OpenDevin&Date)
+
+## 🛠️ 技术栈
+
+OpenDevin 使用了一系列强大的框架和库的组合，为其开发提供了坚实的基础。以下是项目中使用的关键技术：
+
+![FastAPI](https://img.shields.io/badge/FastAPI-black?style=for-the-badge) ![uvicorn](https://img.shields.io/badge/uvicorn-black?style=for-the-badge) ![LiteLLM](https://img.shields.io/badge/LiteLLM-black?style=for-the-badge) ![Docker](https://img.shields.io/badge/Docker-black?style=for-the-badge) ![Ruff](https://img.shields.io/badge/Ruff-black?style=for-the-badge) ![MyPy](https://img.shields.io/badge/MyPy-black?style=for-the-badge) ![LlamaIndex](https://img.shields.io/badge/LlamaIndex-black?style=for-the-badge) ![React](https://img.shields.io/badge/React-black?style=for-the-badge)
+
+请注意，这些技术的选择正在进行中，随着项目的发展，可能会添加其他技术或移除现有技术。我们致力于采用最合适和最有效的工具，以增强 OpenDevin 的功能。
+
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
+
+## 📜 许可证
+
+根据 MIT 许可证分发。有关更多信息，请参阅 [`LICENSE`](./LICENSE)。
+
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>
+
+[contributors-shield]: https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge
+[contributors-url]: https://github.com/OpenDevin/OpenDevin/graphs/contributors
+[forks-shield]: https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge
+[forks-url]: https://github.com/OpenDevin/OpenDevin/network/members
+[stars-shield]: https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge
+[stars-url]: https://github.com/OpenDevin/OpenDevin/stargazers
+[issues-shield]: https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge
+[issues-url]: https://github.com/OpenDevin/OpenDevin/issues
+[license-shield]: https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge
+[license-url]: https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE

docs/README.md

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

docs/architecture/Architecture.md

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

docs/architecture/README.md

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

docs/architecture/backend_architecture.puml

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

docs/architecture/system_architecture.puml

@@ -2,13 +2,13 @@
 
 
 node frontend as frontend{
-
+    
     component App
 
     package components{
-
+        
         component Terminal
-
+        
         component ChatInterface
 
         component BannerSettings
@@ -37,8 +37,8 @@ node frontend as frontend{
 
     Terminal -[hidden]u-> ChatInterface
     ChatInterface -[hidden]u-> BannerSettings
-
-
+    
+    
 
     interface "HTTP (:3001)" as HTTP
     HTTP - App
@@ -50,13 +50,13 @@ node backend{
         component Server
 
         'defined in server/server.py, port is defined at startup with uvicorn
-        interface "Client WS\n(:3000/ws)" as client_socket
+        interface "Client WS\n(:3000/ws)" as client_socket 
         client_socket - Server
 
-
+        
     }
-    node AgentController{
-
+    node AgentController{        
+        
     }
     Server -d-> AgentController
 }

docs/babel.config.js

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

docs/documentation/AZURE_LLM_GUIDE.md

@@ -0,0 +1,31 @@
+# Azure OpenAI LLM Guide
+
+# 1. Completion
+
+OpenDevin uses LiteLLM for completion calls. You can find their documentation on Azure [here](https://docs.litellm.ai/docs/providers/azure)
+
+## azure openai configs
+
+When running the OpenDevin Docker image, you'll need to set the following environment variables using `-e`:
+```
+LLM_BASE_URL="<azure-api-base-url>"          # e.g. "https://openai-gpt-4-test-v-1.openai.azure.com/"
+LLM_API_KEY="<azure-api-key>"
+LLM_MODEL="azure/<your-gpt-deployment-name>"
+AZURE_API_VERSION = "<api-version>"          # e.g. "2024-02-15-preview"
+```
+
+# 2. Embeddings
+
+OpenDevin uses llama-index for embeddings. You can find their documentation on Azure [here](https://docs.llamaindex.ai/en/stable/api_reference/embeddings/azure_openai/)
+
+## azure openai configs
+
+The model used for Azure OpenAI embeddings is "text-embedding-ada-002".
+You need the correct deployment name for this model in your Azure account.
+
+When running OpenDevin in Docker, set the following environment variables using `-e`:
+```
+LLM_EMBEDDING_MODEL="azureopenai"
+DEPLOYMENT_NAME = "<your-embedding-deployment-name>"        # e.g. "TextEmbedding...<etc>"
+LLM_API_VERSION = "<api-version>"         # e.g. "2024-02-15-preview"
+```

docs/documentation/Agents.md

@@ -0,0 +1,96 @@
+# Agents and Capabilities
+
+## Monologue Agent:
+
+### Description:
+The Monologue Agent utilizes long and short term memory to complete tasks.
+Long term memory is stored as a LongTermMemory object and the model uses it to search for examples from the past.
+Short term memory is stored as a Monologue object and the model can condense it as necessary.
+
+### Actions:
+`Action`,
+`NullAction`,
+`CmdRunAction`,
+`FileWriteAction`,
+`FileReadAction`,
+`AgentRecallAction`,
+`BrowseURLAction`,
+`AgentThinkAction`
+
+### Observations:
+`Observation`,
+`NullObservation`,
+`CmdOutputObservation`,
+`FileReadObservation`,
+`AgentRecallObservation`,
+`BrowserOutputObservation`
+
+
+### Methods:
+`__init__`: Initializes the agent with a long term memory, and an internal monologue
+
+`_add_event`: Appends events to the monologue of the agent and condenses with summary automatically if the monologue is too long
+
+`_initialize`: Utilizes the `INITIAL_THOUGHTS` list to give the agent a context for its capabilities and how to navigate the `/workspace`
+
+`step`: Modifies the current state by adding the most rescent actions and observations, then prompts the model to think about its next action to take. 
+
+`search_memory`: Uses `VectorIndexRetriever` to find related memories within the long term memory.
+
+## Planner Agent:
+
+### Description:
+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.
+
+### Actions:
+`NullAction`,
+`CmdRunAction`,
+`CmdKillAction`,
+`BrowseURLAction`,
+`FileReadAction`,
+`FileWriteAction`,
+`AgentRecallAction`,
+`AgentThinkAction`,
+`AgentFinishAction`,
+`AgentSummarizeAction`,
+`AddTaskAction`,
+`ModifyTaskAction`,
+
+
+### Observations:
+`Observation`,
+`NullObservation`,
+`CmdOutputObservation`,
+`FileReadObservation`,
+`AgentRecallObservation`,
+`BrowserOutputObservation`
+
+### Methods:
+`__init__`: Initializes an agent with `llm`
+
+`step`: Checks to see if current step is completed, returns `AgentFinishAction` if True. Otherwise, creates a plan prompt and sends to model for inference, adding the result as the next action.
+
+`search_memory`: Not yet implemented
+
+## CodeAct Agent:
+
+### Description:
+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.
+
+### Actions:
+`Action`,
+`CmdRunAction`,
+`AgentEchoAction`,
+`AgentFinishAction`,
+
+### Observations:
+`CmdOutputObservation`,
+`AgentMessageObservation`,
+
+### Methods:
+`__init__`: Initializes an agent with `llm` and a list of messages `List[Mapping[str, str]]`
+
+`step`: First, gets messages from state and then compiles them into a list for context. Next, pass the context list with the prompt to get the next command to execute. Finally, Execute command if valid, else return `AgentEchoAction(INVALID_INPUT_MESSAGE)` 
+
+`search_memory`: Not yet implemented

docs/documentation/LOCAL_LLM_GUIDE.md

@@ -0,0 +1,108 @@
+# Local LLM Guide with Ollama server
+
+## 0. Install Ollama:
+run the following command in a conda env with CUDA etc.
+
+Linux:
+```
+curl -fsSL https://ollama.com/install.sh | sh
+```
+Windows or macOS:
+
+- Download from [here](https://ollama.com/download/)
+
+## 1. Install Models:
+Ollama model names can be found [here](https://ollama.com/library) (See example below)
+
+![alt text](images/ollama.png)
+
+Once you have found the model you want to use copy the command and run it in your conda env.
+
+Example of llama2 q4 quantized:
+```
+conda activate <env_name>
+ollama run llama2:13b-chat-q4_K_M
+```
+
+you can check which models you have downloaded like this:
+```
+~$ ollama list
+NAME                            ID              SIZE    MODIFIED
+llama2:latest                   78e26419b446    3.8 GB  6 weeks ago
+mistral:7b-instruct-v0.2-q4_K_M eb14864c7427    4.4 GB  2 weeks ago
+starcoder2:latest               f67ae0f64584    1.7 GB  19 hours ago
+```
+## 2. Run Ollama in CLI:
+This command starts up the ollama server that is on port `11434`
+
+This will show the requests in CLI
+```
+conda activate <env_name>
+ollama serve
+```
+or
+
+This will run with no output in the background
+```
+sudo systemctl start ollama
+```
+
+If you see something like this:
+```
+Error: listen tcp 127.0.0.1:11434: bind: address already in use
+```
+This is not an error it just means the server is already running
+
+To stop the server use:
+```
+sudo systemctl stop ollama
+```
+
+For more info go [here](https://github.com/ollama/ollama/blob/main/docs/faq.md)
+
+## 3. Start OpenDevin
+
+Use the instructions in [README.md](/README.md) to start OpenDevin using Docker.
+When running `docker run`, add the following environment variables using `-e`:
+
+```
+LLM_API_KEY="ollama"
+LLM_MODEL="ollama/<model_name>"
+LLM_EMBEDDING_MODEL="local"
+LLM_BASE_URL="http://localhost:<port_number>"
+WORKSPACE_DIR="./workspace"
+```
+Notes:
+- The API key should be set to `"ollama"`
+- The base url needs to be `localhost`
+- By default ollama port is `11434` unless you set it
+- `model_name` needs to be the entire model name
+    - Example: `LLM_MODEL="ollama/llama2:13b-chat-q4_K_M"`
+
+You should now be able to connect to `http://localhost:3001/` with your local model running!
+
+
+## Additional Notes for WSL2 Users:
+
+1. If you encounter the following error during setup: `Exception: Failed to create opendevin user in sandbox: b'useradd: UID 0 is not unique\n'`
+You can resolve it by running:
+    ```
+    export SANDBOX_USER_ID=1000
+    ```
+
+2. If you face issues running Poetry even after installing it during the build process, you may need to add its binary path to your environment:
+    ```
+    export PATH="$HOME/.local/bin:$PATH"
+    ```
+
+3. If you experiencing issues related to networking, such as `NoneType object has no attribute 'request'` when executing `make run`, you may need to configure your WSL2 networking settings. Follow these steps:
+   - Open or create the `.wslconfig` file located at `C:\Users\%username%\.wslconfig` on your Windows host machine.
+   - Add the following configuration to the `.wslconfig` file:
+        ```
+        [wsl2]
+        networkingMode=mirrored
+        localhostForwarding=true
+        ```
+   - Save the `.wslconfig` file.
+   - Restart WSL2 completely by exiting any running WSL2 instances and executing the command `wsl --shutdown` in your command prompt or terminal.
+   - After restarting WSL, attempt to execute `make run` again. The networking issue should be resolved.