Minor SWE-Bench inference config tweak (#2381)

* save infer logs to infer_logs

* set max budget for swebench eval

.dockerignore

@@ -0,0 +1,5 @@
+frontend/node_modules
+config.toml
+.envrc
+.env
+.git

.gitattributes

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

.github/.codecov.yml

@@ -0,0 +1,19 @@
+codecov:
+  notify:
+    wait_for_ci: true
+
+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
+
+ignore:
+  - "agenthub/SWE_agent/**" # SWE agent is deprecated

.github/ISSUE_TEMPLATE/bug_report.md

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

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -0,0 +1,75 @@
+name: Bug
+description: Report a problem with OpenDevin
+title: '[Bug]: '
+labels: ['bug']
+body:
+  - type: markdown
+    attributes:
+      value: Thank you for taking the time to fill out this bug report. We greatly appreciate your effort to complete this template fully. Please provide as much information as possible to help us understand and address the issue effectively.
+
+  - 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 troubleshooting document at https://opendevin.github.io/OpenDevin/modules/usage/troubleshooting
+        required: true
+      - label: I have checked the existing issues.
+        required: true
+
+  - type: textarea
+    id: bug-description
+    attributes:
+      label: Describe the bug
+      description: Provide a short description of the problem.
+    validations:
+      required: true
+
+  - type: textarea
+    id: current-version
+    attributes:
+      label: Current OpenDevin version
+      description: What version of OpenDevin are you using? If you're running in docker, tell us the tag you're using (e.g. ghcr.io/opendevin/opendevin:0.3.1).
+      render: bash
+    validations:
+      required: true
+
+  - type: textarea
+    id: config
+    attributes:
+      label: Installation and Configuration
+      description: Please provide any commands you ran and any configuration (redacting API keys)
+      render: bash
+    validations:
+      required: true
+
+  - type: textarea
+    id: model-agent
+    attributes:
+      label: Model and Agent
+      description: What model and agent are you using? You can see these settings in the UI by clicking the settings wheel.
+      placeholder: |
+        - Model:
+        - Agent:
+
+  - type: textarea
+    id: os-version
+    attributes:
+      label: Operating System
+      description: What Operating System are you using? Linux, Mac OS, WSL on Windows
+
+  - type: textarea
+    id: repro-steps
+    attributes:
+      label: Reproduction Steps
+      description: Please list the steps to reproduce the issue.
+      placeholder: |
+        1.
+        2.
+        3.
+
+  - type: textarea
+    id: additional-context
+    attributes:
+      label: Logs, Errors, Screenshots, and Additional Context
+      description: LLM logs will be stored in the `logs/llm/default` folder. Please add any additional context about the problem here.

.github/dependabot.yml

@@ -0,0 +1,15 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "pip" # See documentation for possible values
+    directory: "/" # Location of package manifests
+    schedule:
+      interval: "daily"
+  - package-ecosystem: "npm" # See documentation for possible values
+    directory: "/frontend" # Location of package manifests
+    schedule:
+      interval: "daily"

.github/workflows/deploy-docs.yml

@@ -0,0 +1,59 @@
+name: Deploy Docs to GitHub Pages
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  build:
+    name: Build Docusaurus
+    runs-on: ubuntu-latest
+    if: github.repository == 'OpenDevin/OpenDevin'
+    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: "3.11"
+
+      - 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:
+    name: Deploy to GitHub Pages
+    needs: build
+    if: github.ref == 'refs/heads/main' && github.repository == 'OpenDevin/OpenDevin'
+    # Grant GITHUB_TOKEN the permissions required to make a Pages deployment
+    permissions:
+      pages: write # to deploy to Pages
+      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 }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

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

@@ -0,0 +1,33 @@
+name: Run e2e test with dummy agent
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+on:
+  push:
+    branches:
+    - main
+  pull_request:
+
+env:
+  PERSIST_SANDBOX : "false"
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+      - name: Set up environment
+        run: |
+          curl -sSL https://install.python-poetry.org | python3 -
+          poetry install --without evaluation
+          poetry run playwright install --with-deps chromium
+          wget https://huggingface.co/BAAI/bge-small-en-v1.5/raw/main/1_Pooling/config.json -P /tmp/llama_index/models--BAAI--bge-small-en-v1.5/snapshots/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/1_Pooling/
+      - name: Run tests
+        run: |
+          poetry run python opendevin/core/main.py -t "do a flip" -m ollama/not-a-model -d ./workspace/ -c DummyAgent

.github/workflows/ghcr.yml

@@ -1,8 +1,16 @@
-name: Build and publish multi-arch container images
+name: Publish Docker Image
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
 
 on:
   push:
-    branches: [ main ]
+    branches:
+    - main
+    tags:
+      - '*'
+  pull_request:
   workflow_dispatch:
     inputs:
       reason:
@@ -13,12 +21,35 @@ on:
 jobs:
   ghcr_build_and_push:
     runs-on: ubuntu-latest
-    if: github.event_name == 'push' || github.event.inputs.reason != ''
+
+    permissions:
+      contents: read
+      packages: write
+
+    strategy:
+      matrix:
+        image: ["app", "sandbox"]
 
     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
 
@@ -26,34 +57,26 @@ jobs:
         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: Login to ghcr
+        uses: docker/login-action@v1
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
 
-      - name: Build and push multi-arch container images
+      - name: Build and push ${{ matrix.image }}
+        if: "!github.event.pull_request.head.repo.fork"
         run: |
-          # set env for fork repo
-          DOCKER_BUILD_ORG=$(echo "${{ github.repository }}" | tr '[A-Z]' '[a-z]' | cut -d '/' -f 1)
-          # Find directories containing Dockerfile but not containing .dockerfileignore
-          while IFS= read -r dockerfile_dir; do
-          
-            # Check if .dockerfileignore exists in the directory
-            if [ -f "$dockerfile_dir/.dockerfileignore" ]; then
-                echo "$dockerfile_dir/.dockerfileignore exists, skipping build and push"
-                continue
-            fi
-          
-            # Check if image was already exist in ghcr.io
-            pushd "$dockerfile_dir" > /dev/null
-            FULL_IMAGE=$(make get-full-image DOCKER_BUILD_ORG=$DOCKER_BUILD_ORG)
-            popd > /dev/null
-            EXISTS=$(docker manifest inspect "$FULL_IMAGE" > /dev/null 2>&1 && echo "true" || echo "false")
-            if [ "$EXISTS" == "true" ]; then
-              echo "Image $FULL_IMAGE already exists in ghcr.io, skipping build and push"
-              continue
-            fi
-          
-            # Build and push the image to ghcr.io
-            pushd "$dockerfile_dir" > /dev/null
-            make all DOCKER_BUILD_ORG=$DOCKER_BUILD_ORG
-            popd > /dev/null
-          done < <(find . -type f -name Dockerfile -exec dirname {} \; | sort -u)
+          ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} --push
+
+      - name: Build ${{ matrix.image }}
+        if: "github.event.pull_request.head.repo.fork"
+        run: |
+          ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }}
+
+  docker_build_success:
+    name: Docker Build Success
+    runs-on: ubuntu-latest
+    needs: ghcr_build_and_push
+    steps:
+    - run: echo Done!

.github/workflows/lint.yml

@@ -1,47 +1,50 @@
 name: Lint
 
-on: [push, pull_request]
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+on:
+  push:
+    branches:
+    - main
+  pull_request:
 
 jobs:
   lint-frontend:
+    name: Lint frontend
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-
-      - name: Install PNPM
-        uses: pnpm/action-setup@v2
-        with:
-          package_json_file: frontend/package.json
+      - uses: actions/checkout@v4
 
       - name: Install Node.js 20
-        uses: actions/setup-node@v2
+        uses: actions/setup-node@v4
         with:
           node-version: 20
-          cache: 'pnpm'
-          cache-dependency-path: 'frontend/pnpm-lock.yaml'
 
       - name: Install dependencies
         run: |
           cd frontend
-          pnpm install --frozen-lockfile
+          npm install --frozen-lockfile
 
       - name: Lint
         run: |
           cd frontend
-          pnpm run lint
+          npm run lint
 
   lint-python:
     name: Lint python
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
       - name: Set up python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
           python-version: 3.11
-      - name: Install dependencies
-        run: pip install ruff mypy
-      - name: Run ruff
-        run: ruff check --config dev_config/python/ruff.toml opendevin/ agenthub/
-      - name: Run mypy
-        run: mypy --install-types --non-interactive --config-file dev_config/python/mypy.ini opendevin/ agenthub/
+          cache: 'pip'
+      - name: Install pre-commit
+        run: pip install pre-commit==3.7.0
+      - name: Run pre-commit hooks
+        run: pre-commit run --files opendevin/**/* agenthub/**/* evaluation/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml

.github/workflows/review-pr.yml

@@ -0,0 +1,81 @@
+name: Use OpenDevin to Review Pull Request
+
+on:
+  pull_request:
+    types: [synchronize, labeled]
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  dogfood:
+    if: contains(github.event.pull_request.labels.*.name, 'review-this')
+    runs-on: ubuntu-latest
+    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
+        git config --global --add safe.directory $PWD
+
+    - name: Checkout Repository
+      uses: actions/checkout@v4
+      with:
+        ref: ${{ github.event.pull_request.base.ref }} # check out the target branch
+
+    - name: Download Diff
+      run: |
+        curl -O "${{ github.event.pull_request.diff_url }}" -L
+
+    - name: Write Task File
+      run: |
+        echo "Your coworker wants to apply a pull request to this project. Read and review ${{ github.event.pull_request.number }}.diff file. Create a review-${{ github.event.pull_request.number }}.txt and write your concise comments and suggestions there." > task.txt
+        echo "" >> task.txt
+        echo "Title" >> task.txt
+        echo "${{ github.event.pull_request.title }}" >> task.txt
+        echo "" >> task.txt
+        echo "Description" >> task.txt
+        echo "${{ github.event.pull_request.body }}" >> task.txt
+        echo "" >> task.txt
+        echo "Diff file is: ${{ github.event.pull_request.number }}.diff" >> task.txt
+
+    - name: Set up environment
+      run: |
+        curl -sSL https://install.python-poetry.org | python3 -
+        export PATH="/github/home/.local/bin:$PATH"
+        poetry install --without evaluation
+        poetry run playwright install --with-deps chromium
+
+    - name: Run OpenDevin
+      env:
+        LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        SANDBOX_TYPE: exec
+      run: |
+        # Append path to launch poetry
+        export PATH="/github/home/.local/bin:$PATH"
+        # Append path to correctly import package, note: must set pwd at first
+        export PYTHONPATH=$(pwd):$PYTHONPATH
+        WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE poetry run python ./opendevin/core/main.py -i 50 -f task.txt -d $GITHUB_WORKSPACE
+        rm task.txt
+
+    - name: Check if review file is non-empty
+      id: check_file
+      run: |
+        ls -la
+        if [[ -s review-${{ github.event.pull_request.number }}.txt ]]; then
+          echo "non_empty=true" >> $GITHUB_OUTPUT
+        fi
+      shell: bash
+
+    - name: Create PR review if file is non-empty
+      env:
+        GH_TOKEN: ${{ github.token }}
+      if: steps.check_file.outputs.non_empty == 'true'
+      run: |
+        gh pr review ${{ github.event.pull_request.number }} --comment --body-file "review-${{ github.event.pull_request.number }}.txt"

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

@@ -0,0 +1,104 @@
+name: Run Integration Tests
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+on:
+  push:
+    branches:
+      - main
+    paths-ignore:
+      - '**/*.md'
+      - 'frontend/**'
+      - 'docs/**'
+      - 'evaluation/**'
+  pull_request:
+
+env:
+  PERSIST_SANDBOX : "false"
+
+jobs:
+  integration-tests-on-linux:
+    name: Integration Tests on Linux
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11"]
+        sandbox: ["ssh", "exec", "local"]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'poetry'
+
+      - name: Install Python dependencies using Poetry
+        run: poetry install
+
+      - name: Build Environment
+        run: make build
+
+      - name: Run Integration Tests
+        env:
+          SANDBOX_TYPE: ${{ matrix.sandbox }}
+        run: |
+          TEST_IN_CI=true TEST_ONLY=true ./tests/integration/regenerate.sh
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+  integration-tests-on-mac:
+    name: Integration Tests on MacOS
+    runs-on: macos-13
+    if: contains(github.event.pull_request.title, 'mac') || contains(github.event.pull_request.title, 'Mac')
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11"]
+        sandbox: ["ssh"]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'poetry'
+
+      - name: Install Python dependencies using Poetry
+        run: poetry install
+
+      - name: Install & Start Docker
+        run: |
+          brew install colima docker
+          colima start
+
+          # For testcontainers to find the Colima socket
+          # https://github.com/abiosoft/colima/blob/main/docs/FAQ.md#cannot-connect-to-the-docker-daemon-at-unixvarrundockersock-is-the-docker-daemon-running
+          sudo ln -sf $HOME/.colima/default/docker.sock /var/run/docker.sock
+
+      - name: Build Environment
+        run: make build
+
+      - name: Run Integration Tests
+        env:
+          SANDBOX_TYPE: ${{ matrix.sandbox }}
+        run: |
+          TEST_IN_CI=true TEST_ONLY=true ./tests/integration/regenerate.sh
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

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

@@ -0,0 +1,129 @@
+name: Run Unit Tests
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+on:
+  push:
+    branches:
+      - main
+    paths-ignore:
+      - '**/*.md'
+      - 'frontend/**'
+      - 'docs/**'
+      - 'evaluation/**'
+  pull_request:
+
+env:
+  PERSIST_SANDBOX : "false"
+
+jobs:
+  test-on-macos:
+    name: Test on macOS
+    runs-on: macos-13
+    env:
+      INSTALL_DOCKER: "1" # Set to '0' to skip Docker installation
+    strategy:
+      matrix:
+        python-version: ["3.11"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "poetry"
+
+      - name: Install Python dependencies using Poetry
+        run: poetry install
+
+      - name: Install & Start Docker
+        if: env.INSTALL_DOCKER == '1'
+        run: |
+          brew install colima docker
+          colima start
+
+          # For testcontainers to find the Colima socket
+          # https://github.com/abiosoft/colima/blob/main/docs/FAQ.md#cannot-connect-to-the-docker-daemon-at-unixvarrundockersock-is-the-docker-daemon-running
+          sudo ln -sf $HOME/.colima/default/docker.sock /var/run/docker.sock
+
+      - name: Build Environment
+        run: make build
+
+      - name: Run Tests
+        run: poetry run pytest --forked --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox"
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+  test-on-linux:
+    name: Test on Linux
+    runs-on: ubuntu-latest
+    env:
+      INSTALL_DOCKER: "0" # Set to '0' to skip Docker installation
+    strategy:
+      matrix:
+        python-version: ["3.11"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "poetry"
+
+      - name: Install Python dependencies using Poetry
+        run: poetry install --without evaluation
+
+      - name: Build Environment
+        run: make build
+
+      - name: Run Tests
+        run: poetry run pytest --forked --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox"
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+  test-for-sandbox:
+    name: Test for Sandbox
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: "poetry"
+
+      - name: Install Python dependencies using Poetry
+        run: poetry install
+
+      - name: Build Environment
+        run: make build
+
+      - name: Run Integration Test for Sandbox
+        run: |
+          poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml -s ./tests/unit/test_sandbox.py
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

.github/workflows/solve-issue.yml

@@ -0,0 +1,122 @@
+name: Use OpenDevin to Resolve GitHub Issue
+
+on:
+  issues:
+    types: [labeled]
+
+permissions:
+  contents: write
+  pull-requests: write
+  issues: write
+
+jobs:
+  dogfood:
+    if: github.event.label.name == 'solve-this'
+    runs-on: ubuntu-latest
+    container:
+      image: ghcr.io/opendevin/opendevin
+      volumes:
+        - /var/run/docker.sock:/var/run/docker.sock
+
+    steps:
+    - name: install git, github cli
+      run: apt-get install -y git gh
+
+    - name: Checkout Repository
+      uses: actions/checkout@v4
+
+    - name: Write Task File
+      env:
+        ISSUE_TITLE: ${{ github.event.issue.title }}
+        ISSUE_BODY: ${{ github.event.issue.body }}
+      run: |
+        echo "TITLE:" > task.txt
+        echo "${ISSUE_TITLE}" >> task.txt
+        echo "" >> task.txt
+        echo "BODY:" >> task.txt
+        echo "${ISSUE_BODY}" >> task.txt
+    
+    - name: Set up environment
+      run: |
+        curl -sSL https://install.python-poetry.org | python3 -
+        export PATH="/github/home/.local/bin:$PATH"
+        poetry install --without evaluation
+        poetry run playwright install --with-deps chromium
+
+
+    - name: Run OpenDevin
+      env:
+        ISSUE_TITLE: ${{ github.event.issue.title }}
+        ISSUE_BODY: ${{ github.event.issue.body }}
+        LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        SANDBOX_TYPE: exec
+      run: |
+        # Append path to launch poetry
+        export PATH="/github/home/.local/bin:$PATH"
+        # Append path to correctly import package, note: must set pwd at first
+        export PYTHONPATH=$(pwd):$PYTHONPATH
+        WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE poetry run python ./opendevin/core/main.py -i 50 -f task.txt -d $GITHUB_WORKSPACE
+        rm task.txt
+
+    - name: Setup Git, Create Branch, and Commit Changes
+      run: |
+        # Setup Git configuration
+        git config --global --add safe.directory $PWD
+        git config --global user.name 'OpenDevin'
+        git config --global user.email 'OpenDevin@users.noreply.github.com'
+
+        # Create a unique branch name with a timestamp
+        BRANCH_NAME="fix/${{ github.event.issue.number }}-$(date +%Y%m%d%H%M%S)"
+
+        # Checkout new branch
+        git checkout -b $BRANCH_NAME
+
+        # Add all changes to staging, except task.txt
+        git add --all -- ':!task.txt'
+
+        # Commit the changes, if any
+        git commit -m "OpenDevin: Resolve Issue #${{ github.event.issue.number }}"
+        if [ $? -ne 0 ]; then
+          echo "No changes to commit."
+          exit 0
+        fi
+
+        # Push changes
+        git push --set-upstream origin $BRANCH_NAME
+
+    - name: Fetch Default Branch
+      env:
+        GH_TOKEN: ${{ github.token }}
+      run: |
+        # Fetch the default branch using gh cli
+        DEFAULT_BRANCH=$(gh repo view --json defaultBranchRef --jq .defaultBranchRef.name)
+        echo "Default branch is $DEFAULT_BRANCH"
+        echo "DEFAULT_BRANCH=$DEFAULT_BRANCH" >> $GITHUB_ENV
+
+    - name: Generate PR
+      env:
+        GH_TOKEN: ${{ github.token }}
+      run: |
+        # Create PR and capture URL
+        PR_URL=$(gh pr create \
+          --title "OpenDevin: Resolve Issue #2" \
+          --body "This PR was generated by OpenDevin to resolve issue #2" \
+          --repo "foragerr/OpenDevin" \
+          --head "${{ github.head_ref }}" \
+          --base "${{ env.DEFAULT_BRANCH }}" \
+          | grep -o 'https://github.com/[^ ]*')
+
+        # Extract PR number from URL
+        PR_NUMBER=$(echo "$PR_URL" | grep -o '[0-9]\+$')
+
+        # Set environment vars
+        echo "PR_URL=$PR_URL" >> $GITHUB_ENV
+        echo "PR_NUMBER=$PR_NUMBER" >> $GITHUB_ENV
+
+    - name: Post Comment
+      env:
+        GH_TOKEN: ${{ github.token }}
+      run: |
+        gh issue comment ${{ github.event.issue.number }} \
+          -b "OpenDevin raised [PR #${{ env.PR_NUMBER }}](${{ env.PR_URL }}) to resolve this issue."

.github/workflows/stale.yml

@@ -0,0 +1,29 @@
+name: 'Close stale issues'
+on:
+  schedule:
+    - cron: '30 1 * * *'
+
+jobs:
+  stale:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/stale@v9
+        with:
+          # Aggressively close issues that have been explicitly labeled `age-out`
+          any-of-labels: age-out
+          stale-issue-message: 'This issue is stale because it has been open for 7 days with no activity. Remove stale label or comment or this will be closed in 1 day.'
+          close-issue-message: 'This issue was closed because it has been stalled for over 7 days with no activity.'
+          stale-pr-message: 'This PR is stale because it has been open for 7 days with no activity. Remove stale label or comment or this will be closed in 1 days.'
+          close-pr-message: 'This PR was closed because it has been stalled for over 7 days with no activity.'
+          days-before-stale: 7
+          days-before-close: 1
+
+      - uses: actions/stale@v9
+        with:
+          # Be more lenient with other issues
+          stale-issue-message: 'This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
+          close-issue-message: 'This issue was closed because it has been stalled for over 30 days with no activity.'
+          stale-pr-message: 'This PR is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
+          close-pr-message: 'This PR was closed because it has been stalled for over 30 days with no activity.'
+          days-before-stale: 30
+          days-before-close: 7

.gitignore

@@ -57,7 +57,6 @@ cover/
 *.pot
 
 # Django stuff:
-*.log
 local_settings.py
 db.sqlite3
 db.sqlite3-journal
@@ -100,7 +99,7 @@ ipython_config.py
 #   This is especially recommended for binary packages to ensure reproducibility, and is more
 #   commonly ignored for libraries.
 #   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
+# poetry.lock
 
 # pdm
 #   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
@@ -127,7 +126,9 @@ env/
 venv/
 ENV/
 env.bak/
+.env.bak
 venv.bak/
+*venv/
 
 # Spyder project settings
 .spyderproject
@@ -160,9 +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
 
 # frontend
 
@@ -175,6 +181,8 @@ frontend/yarn.lock
 
 # testing
 frontend/coverage
+test_results*
+/_test_files_tmp/
 
 # production
 frontend/build
@@ -196,7 +204,10 @@ logs
 # agent
 .envrc
 /workspace
+/_test_workspace
 /debug
+cache
 
 # configuration
 config.toml
+config.toml.bak

CODE_OF_CONDUCT.md

@@ -0,0 +1,133 @@
+
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual
+identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the overall
+  community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or advances of
+  any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email address,
+  without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official email address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+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
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of
+actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or permanent
+ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior, harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the
+community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.1, available at
+[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
+
+Community Impact Guidelines were inspired by
+[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
+
+For answers to common questions about this code of conduct, see the FAQ at
+[https://www.contributor-covenant.org/faq][FAQ]. Translations are available at
+[https://www.contributor-covenant.org/translations][translations].
+
+[homepage]: https://www.contributor-covenant.org
+[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
+[Mozilla CoC]: https://github.com/mozilla/diversity
+[FAQ]: https://www.contributor-covenant.org/faq
+[translations]: https://www.contributor-covenant.org/translations

CONTRIBUTING.md

@@ -85,5 +85,6 @@ Please refer to the README in each module:
     - [mock server](./opendevin/mock/README.md)
 
 ## Tests
-TODO: make sure code pass the test before submit.
-
+Please navigate to `tests` folder to see existing test suites.
+At the moment, we have two kinds of tests: `unit` and `integration`. Please refer to the README for each test suite. These tests also run on CI to ensure quality of
+the project.

Development.md

@@ -0,0 +1,102 @@
+# Development Guide
+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)
+* [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
+
+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 3.11, nodejs, and poetry
+mamba install python=3.11
+mamba install conda-forge::nodejs
+mamba install conda-forge::poetry
+```
+
+### 2. Build and Setup The Environment
+
+- **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
+
+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 OpenDevin is tailored to your specific needs. Note that the model name will apply only when you run headless. If you use the UI, please set the model in the UI.
+   Set `persist_sandbox` to false if you want to use clean sandbox for each task. If `persist_sandbox` is set to true, you will need to set the `ssh_password` as well.
+
+**Note on Alternative Models:**
+Some alternative models may prove more challenging to tame than others. Fear not, brave adventurer! We shall soon unveil LLM-specific documentation to guide you on your quest. And if you've already mastered the art of wielding a model other than OpenAI's GPT, we encourage you to [share your setup instructions with us](https://github.com/OpenDevin/OpenDevin/issues/417).
+
+For a full list of the LM providers and models available, please consult the [litellm documentation](https://docs.litellm.ai/docs/providers).
+
+There is also [documentation for running with local models using ollama](./docs/documentation/LOCAL_LLM_GUIDE.md).
+
+### 4. Run the Application
+
+- **Run the Application:** Once the setup is complete, launching OpenDevin is as simple as running a single command. This command starts both the backend and frontend servers seamlessly, allowing you to interact with OpenDevin without any hassle.
+    ```bash
+    make run
+    ```
+
+### 5. Individual Server Startup
+
+- **Start the Backend Server:** If you prefer, you can start the backend server independently to focus on backend-related tasks or configurations.
+    ```bash
+    make start-backend
+    ```
+
+- **Start the Frontend Server:** Similarly, you can start the frontend server on its own to work on frontend-related components or interface enhancements.
+    ```bash
+    make start-frontend
+    ```
+
+### 6. LLM Debugging
+
+If you encounter any issues with the Language Model (LM) or you're simply curious, you can inspect the actual LLM prompts and responses. To do so, export DEBUG=1 in the environment and restart the backend. OpenDevin will then log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
+
+### 7. Help
+
+- **Get Some Help:** Need assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenDevin.
+    ```bash
+    make help
+    ```
+
+### 8. Testing
+
+#### Unit tests
+
+```bash
+poetry run pytest ./tests/unit/test_sandbox.py
+```
+
+#### Integration tests
+
+Please refer to [this README](./tests/integration/README.md) for details.
+
+### 9. Add or update dependency
+
+1. Add your dependency in `pyproject.toml` or use `poetry add xxx`
+2. Update the poetry.lock file via `poetry lock --no-update`

Makefile

@@ -1,3 +1,4 @@
+SHELL=/bin/bash
 # Makefile for OpenDevin project
 
 # Variables
@@ -6,92 +7,301 @@ BACKEND_PORT = 3000
 BACKEND_HOST = "127.0.0.1:$(BACKEND_PORT)"
 FRONTEND_PORT = 3001
 DEFAULT_WORKSPACE_DIR = "./workspace"
-DEFAULT_MODEL = "gpt-4-0125-preview"
+DEFAULT_MODEL = "gpt-4o"
 CONFIG_FILE = config.toml
+PRECOMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
+PYTHON_VERSION = 3.11
+
+# ANSI color codes
+GREEN=$(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)
 
 # Build
 build:
-	@echo "Building project..."
-	@echo "Pulling Docker image..."
-	@docker pull $(DOCKER_IMAGE)
-	@echo "Installing Python dependencies..."
-	@python -m pip install pipenv
-	@python -m pipenv install -v
-	@echo "Setting up frontend environment..."
-	@echo "Detect Node.js version..."
-	@cd frontend && node ./scripts/detect-node-version.js
-	@cd frontend && if [ -f node_modules/.package-lock.json ]; then \
-		echo "This project currently uses "pnpm" for dependency management. It has detected that dependencies were previously installed using "npm" and has automatically deleted the "node_modules" directory to prevent unnecessary conflicts."; \
-		rm -rf node_modules; \
+	@echo "$(GREEN)Building project...$(RESET)"
+	@$(MAKE) -s check-dependencies
+ifeq ($(INSTALL_DOCKER),)
+	@$(MAKE) -s pull-docker-image
+endif
+	@$(MAKE) -s install-python-dependencies
+	@$(MAKE) -s install-frontend-dependencies
+	@$(MAKE) -s install-precommit-hooks
+	@$(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 [ "$$(uname -r | grep -i microsoft)" ]; then \
+		echo "$(BLUE)Windows Subsystem for Linux detected.$(RESET)"; \
+	else \
+		echo "$(RED)Unsupported system detected. Please use macOS, Linux, or Windows Subsystem for Linux (WSL).$(RESET)"; \
+		exit 1; \
 	fi
-	@which corepack > /dev/null || (echo "Installing corepack..." && npm install -g corepack)
-	@cd frontend && corepack enable && pnpm install && pnpm run make-i18n
+
+check-python:
+	@echo "$(YELLOW)Checking Python installation...$(RESET)"
+	@if command -v python$(PYTHON_VERSION) > /dev/null; then \
+		echo "$(BLUE)$(shell python$(PYTHON_VERSION) --version) is already installed.$(RESET)"; \
+	else \
+		echo "$(RED)Python $(PYTHON_VERSION) is not installed. Please install Python $(PYTHON_VERSION) to continue.$(RESET)"; \
+		exit 1; \
+	fi
+
+check-npm:
+	@echo "$(YELLOW)Checking npm installation...$(RESET)"
+	@if command -v npm > /dev/null; then \
+		echo "$(BLUE)npm $(shell npm --version) is already installed.$(RESET)"; \
+	else \
+		echo "$(RED)npm is not installed. Please install Node.js to continue.$(RESET)"; \
+		exit 1; \
+	fi
+
+check-nodejs:
+	@echo "$(YELLOW)Checking Node.js installation...$(RESET)"
+	@if command -v node > /dev/null; then \
+		NODE_VERSION=$(shell node --version | sed -E 's/v//g'); \
+		IFS='.' read -r -a NODE_VERSION_ARRAY <<< "$$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...$(RESET)"
+	@if command -v docker > /dev/null; then \
+		echo "$(BLUE)$(shell docker --version) is already installed.$(RESET)"; \
+	else \
+		echo "$(RED)Docker is not installed. Please install Docker to continue.$(RESET)"; \
+		exit 1; \
+	fi
+
+check-poetry:
+	@echo "$(YELLOW)Checking Poetry installation...$(RESET)"
+	@if command -v poetry > /dev/null; then \
+		POETRY_VERSION=$(shell poetry --version 2>&1 | sed -E 's/Poetry \(version ([0-9]+\.[0-9]+\.[0-9]+)\)/\1/'); \
+		IFS='.' read -r -a POETRY_VERSION_ARRAY <<< "$$POETRY_VERSION"; \
+		if [ $${POETRY_VERSION_ARRAY[0]} -ge 1 ] && [ $${POETRY_VERSION_ARRAY[1]} -ge 8 ]; then \
+			echo "$(BLUE)$(shell poetry --version) is already installed.$(RESET)"; \
+		else \
+			echo "$(RED)Poetry 1.8 or later is required. You can install poetry by running the following command, then adding Poetry to your PATH:"; \
+			echo "$(RED) curl -sSL https://install.python-poetry.org | python$(PYTHON_VERSION) -$(RESET)"; \
+			echo "$(RED)More detail here: https://python-poetry.org/docs/#installing-with-the-official-installer$(RESET)"; \
+			exit 1; \
+		fi; \
+	else \
+		echo "$(RED)Poetry is not installed. You can install poetry by running the following command, then adding Poetry to your PATH:"; \
+		echo "$(RED) curl -sSL https://install.python-poetry.org | python$(PYTHON_VERSION) -$(RESET)"; \
+		echo "$(RED)More detail here: https://python-poetry.org/docs/#installing-with-the-official-installer$(RESET)"; \
+		exit 1; \
+	fi
+
+pull-docker-image:
+	@echo "$(YELLOW)Pulling Docker image...$(RESET)"
+	@docker pull $(DOCKER_IMAGE)
+	@echo "$(GREEN)Docker image pulled successfully.$(RESET)"
+
+install-python-dependencies:
+	@echo "$(GREEN)Installing Python dependencies...$(RESET)"
+	poetry env use python$(PYTHON_VERSION)
+	@if [ "$(shell uname)" = "Darwin" ]; then \
+		echo "$(BLUE)Installing chroma-hnswlib...$(RESET)"; \
+		export HNSWLIB_NO_NATIVE=1; \
+		poetry run pip install chroma-hnswlib; \
+	fi
+	@poetry install
+	@if [ -f "/etc/manjaro-release" ]; then \
+		echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
+		poetry run pip install playwright; \
+		poetry run playwright install chromium; \
+	else \
+		if [ ! -f cache/playwright_chromium_is_installed.txt ]; then \
+			echo "Running playwright install --with-deps chromium..."; \
+			poetry run playwright install --with-deps chromium; \
+			mkdir -p cache; \
+			touch cache/playwright_chromium_is_installed.txt; \
+		else \
+			echo "Setup already done. Skipping playwright installation."; \
+		fi \
+	fi
+	@echo "$(GREEN)Python dependencies installed successfully.$(RESET)"
+
+install-frontend-dependencies:
+	@echo "$(YELLOW)Setting up frontend environment...$(RESET)"
+	@echo "$(YELLOW)Detect Node.js version...$(RESET)"
+	@cd frontend && node ./scripts/detect-node-version.js
+	@cd frontend && \
+		echo "$(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.$(RESET)"
+
+install-precommit-hooks:
+	@echo "$(YELLOW)Installing pre-commit hooks...$(RESET)"
+	@git config --unset-all core.hooksPath || true
+	@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 opendevin/**/* agenthub/**/* evaluation/**/* --show-diff-on-failure --config $(PRECOMMIT_CONFIG_PATH)
+
+lint-frontend:
+	@echo "$(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
+
+build-frontend:
+	@echo "$(YELLOW)Building frontend...$(RESET)"
+	@cd frontend && npm run build
 
 # Start backend
 start-backend:
-	@echo "Starting backend..."
-	@python -m pipenv run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT)
+	@echo "$(YELLOW)Starting backend...$(RESET)"
+	@poetry run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT) --reload --reload-exclude "workspace/*"
 
 # Start frontend
 start-frontend:
-	@echo "Starting frontend..."
-	@cd frontend && BACKEND_HOST=$(BACKEND_HOST) FRONTEND_PORT=$(FRONTEND_PORT) npm run start
+	@echo "$(YELLOW)Starting frontend...$(RESET)"
+	@cd frontend && VITE_BACKEND_HOST=$(BACKEND_HOST) VITE_FRONTEND_PORT=$(FRONTEND_PORT) npm run start
 
 # Run the app
 run:
-	@echo "Running the app..."
-	@if [ "$(OS)" == "Windows_NT" ]; then \
-		echo "`make run` is not supported on Windows. Please run `make start-frontend` and `make start-backend` separately."; \
+	@echo "$(YELLOW)Running the app...$(RESET)"
+	@if [ "$(OS)" = "Windows_NT" ]; then \
+		echo "$(RED)`make run` is not supported on Windows. Please run `make start-frontend` and `make start-backend` separately.$(RESET)"; \
 		exit 1; \
 	fi
 	@mkdir -p logs
-	@rm -f logs/pipe
-	@mkfifo logs/pipe
-	@cat logs/pipe | (make start-backend) &
-	@echo 'test' | tee logs/pipe | (make start-frontend)
+	@echo "$(YELLOW)Starting backend server...$(RESET)"
+	@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.$(RESET)"
+	@cd frontend && echo "$(BLUE)Starting frontend with npm...$(RESET)" && npm run start -- --port $(FRONTEND_PORT)
+	@echo "$(GREEN)Application started successfully.$(RESET)"
 
 # Setup config.toml
 setup-config:
-	@echo "Setting up config.toml..."
-	@read -p "Enter your LLM Model name (see docs.litellm.ai/docs/providers for full list) [default: $(DEFAULT_MODEL)]: " llm_model; \
+	@echo "$(YELLOW)Setting up config.toml...$(RESET)"
+	@$(MAKE) setup-config-prompts
+	@mv $(CONFIG_FILE).tmp $(CONFIG_FILE)
+	@echo "$(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
+
+	@read -p "Do you want to persist the sandbox container? [true/false] [default: true]: " persist_sandbox; \
+	 persist_sandbox=$${persist_sandbox:-true}; \
+	 if [ "$$persist_sandbox" = "true" ]; then \
+		 read -p "Enter a password for the sandbox container: " ssh_password; \
+		 echo "ssh_password=\"$$ssh_password\"" >> $(CONFIG_FILE).tmp; \
+		 echo "persist_sandbox=$$persist_sandbox" >> $(CONFIG_FILE).tmp; \
+	 else \
+		echo "persist_sandbox=$$persist_sandbox" >> $(CONFIG_FILE).tmp; \
+	 fi
+
+	@echo "" >> $(CONFIG_FILE).tmp
+
+	@echo "[llm]" >> $(CONFIG_FILE).tmp
+	@read -p "Enter your LLM model name, used for running without UI. Set the model in the UI after you start the app. (see https://docs.litellm.ai/docs/providers for full list) [default: $(DEFAULT_MODEL)]: " llm_model; \
 	 llm_model=$${llm_model:-$(DEFAULT_MODEL)}; \
-	 echo "LLM_MODEL=\"$$llm_model\"" >> $(CONFIG_FILE).tmp
+	 echo "model=\"$$llm_model\"" >> $(CONFIG_FILE).tmp
 
-	@read -p "Enter your LLM API key: " llm_api_key; \
-	 echo "LLM_API_KEY=\"$$llm_api_key\"" >> $(CONFIG_FILE).tmp
+	@read -p "Enter your LLM api key: " llm_api_key; \
+	 echo "api_key=\"$$llm_api_key\"" >> $(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: " llm_base_url; \
-				echo "LLM_BASE_URL=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
+	@read -p "Enter your LLM base URL [mostly used for local LLMs, leave blank if not needed - example: http://localhost:5001/v1/]: " llm_base_url; \
+	 if [[ ! -z "$$llm_base_url" ]]; then echo "base_url=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; fi
+
+	@echo "Enter your LLM Embedding Model"; \
+		echo "Choices are:"; \
+		echo "  - openai"; \
+		echo "  - azureopenai"; \
+		echo "  - Embeddings available only with OllamaEmbedding:"; \
+		echo "    - llama2"; \
+		echo "    - mxbai-embed-large"; \
+		echo "    - nomic-embed-text"; \
+		echo "    - all-minilm"; \
+		echo "    - stable-code"; \
+		echo "  - Leave blank to default to 'BAAI/bge-small-en-v1.5' via huggingface"; \
+		read -p "> " llm_embedding_model; \
+		echo "embedding_model=\"$$llm_embedding_model\"" >> $(CONFIG_FILE).tmp; \
+		if [ "$$llm_embedding_model" = "llama2" ] || [ "$$llm_embedding_model" = "mxbai-embed-large" ] || [ "$$llm_embedding_model" = "nomic-embed-text" ] || [ "$$llm_embedding_model" = "all-minilm" ] || [ "$$llm_embedding_model" = "stable-code" ]; then \
+			read -p "Enter the local model URL for the embedding model (will set llm.embedding_base_url): " llm_embedding_base_url; \
+				echo "embedding_base_url=\"$$llm_embedding_base_url\"" >> $(CONFIG_FILE).tmp; \
 		elif [ "$$llm_embedding_model" = "azureopenai" ]; then \
-			read -p "Enter the Azure endpoint URL: " llm_base_url; \
-				echo "LLM_BASE_URL=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
-			read -p "Enter the Azure LLM Deployment Name: " llm_deployment_name; \
-				echo "LLM_DEPLOYMENT_NAME=\"$$llm_deployment_name\"" >> $(CONFIG_FILE).tmp; \
+			read -p "Enter the Azure endpoint URL (will overwrite llm.base_url): " llm_base_url; \
+				echo "base_url=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
+			read -p "Enter the Azure LLM Embedding Deployment Name: " llm_embedding_deployment_name; \
+				echo "embedding_deployment_name=\"$$llm_embedding_deployment_name\"" >> $(CONFIG_FILE).tmp; \
 			read -p "Enter the Azure API Version: " llm_api_version; \
-				echo "LLM_API_VERSION=\"$$llm_api_version\"" >> $(CONFIG_FILE).tmp; \
+				echo "api_version=\"$$llm_api_version\"" >> $(CONFIG_FILE).tmp; \
 		fi
 
-	@read -p "Enter your workspace directory [default: $(DEFAULT_WORKSPACE_DIR)]: " workspace_dir; \
-	 workspace_dir=$${workspace_dir:-$(DEFAULT_WORKSPACE_DIR)}; \
-	 echo "WORKSPACE_DIR=\"$$workspace_dir\"" >> $(CONFIG_FILE).tmp
 
-	@mv $(CONFIG_FILE).tmp $(CONFIG_FILE)
+# Clean up all caches
+clean:
+	@echo "$(YELLOW)Cleaning up caches...$(RESET)"
+	@rm -rf opendevin/.cache
+	@echo "$(GREEN)Caches cleaned up successfully.$(RESET)"
 
 # Help
 help:
-	@echo "Usage: make [target]"
+	@echo "$(BLUE)Usage: make [target]$(RESET)"
 	@echo "Targets:"
-	@echo "  build               - Build project, including environment setup and dependencies."
-	@echo "  start-backend       - Start the backend server for the OpenDevin project."
-	@echo "  start-frontend      - Start the frontend server for the OpenDevin project."
-	@echo "  run                 - Run the OpenDevin application, starting both backend and frontend servers."
+	@echo "  $(GREEN)build$(RESET)               - Build project, including environment setup and dependencies."
+	@echo "  $(GREEN)lint$(RESET)                - Run linters on the project."
+	@echo "  $(GREEN)setup-config$(RESET)        - Setup the configuration for OpenDevin by providing LLM API key,"
+	@echo "                        LLM Model name, and workspace directory."
+	@echo "  $(GREEN)start-backend$(RESET)       - Start the backend server for the OpenDevin project."
+	@echo "  $(GREEN)start-frontend$(RESET)      - Start the frontend server for the OpenDevin project."
+	@echo "  $(GREEN)run$(RESET)                 - Run the OpenDevin application, starting both backend and frontend servers."
 	@echo "                        Backend Log file will be stored in the 'logs' directory."
-	@echo "  setup-config        - Setup the configuration for OpenDevin by providing LLM API key, LLM Model name, and workspace directory."
-	@echo "  help                - Display this help message, providing information on available targets."
+	@echo "  $(GREEN)help$(RESET)                - Display this help message, providing information on available targets."
 
 # Phony targets
-.PHONY: install start-backend start-frontend run setup-config help
+.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

Pipfile

@@ -1,32 +0,0 @@
-[[source]]
-url = "https://pypi.org/simple"
-verify_ssl = true
-name = "pypi"
-
-[packages]
-datasets = "*"
-pandas = "*"
-litellm = "*"
-termcolor = "*"
-seaborn = "*"
-docker = "*"
-fastapi = "*"
-uvicorn = {extras = ["standard"], version = "*"}
-ruff = "*"
-mypy = "*"
-llama-index = "*"
-llama-index-vector-stores-chroma = "*"
-chromadb = "*"
-llama-index-embeddings-huggingface = "*"
-llama-index-embeddings-azure-openai = "*"
-llama-index-embeddings-ollama = "*"
-google-generativeai = "*"
-toml = "*"
-json_repair = "*"
-numpy = "*"
-playwright = "*"
-
-[dev-packages]
-
-[requires]
-python_version = "3.11"

Pipfile.torchidx

@@ -1,38 +0,0 @@
-[[source]]
-url = "https://pypi.org/simple"
-verify_ssl = true
-name = "pypi"
-
-[[source]]
-url = "https://download.pytorch.org/whl/cpu"
-verify_ssl = true
-name = "pytorch"
-
-[packages]
-torch = {version = "*", index = "pytorch"}
-datasets = "*"
-pandas = "*"
-litellm = "*"
-termcolor = "*"
-seaborn = "*"
-docker = "*"
-fastapi = "*"
-uvicorn = {extras = ["standard"], version = "*"}
-ruff = "*"
-mypy = "*"
-llama-index = "*"
-llama-index-vector-stores-chroma = "*"
-chromadb = "*"
-llama-index-embeddings-huggingface = "*"
-llama-index-embeddings-azure-openai = "*"
-llama-index-embeddings-ollama = "*"
-google-generativeai = "*"
-toml = "*"
-json_repair = "*"
-numpy = "*"
-playwright = "*"
-
-[dev-packages]
-
-[requires]
-python_version = "3.11"

README.md

@@ -1,4 +1,5 @@
 <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
@@ -7,8 +8,6 @@
 *** Thanks again! Now go create something AMAZING! :D
 -->
 
-
-
 <!-- PROJECT SHIELDS -->
 <!--
 *** I'm using markdown "reference style" links for readability.
@@ -19,228 +18,107 @@
 -->
 
 <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>
+  <a href="https://github.com/OpenDevin/OpenDevin/graphs/contributors"><img src="https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge&color=blue" alt="Contributors"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/network/members"><img src="https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge&color=blue" alt="Forks"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/stargazers"><img src="https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge&color=blue" alt="Stargazers"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/issues"><img src="https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge&color=blue" alt="Issues"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE"><img src="https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge&color=blue" alt="MIT License"></a>
+  <br/>
+  <a href="https://join.slack.com/t/opendevin/shared_invite/zt-2i1iqdag6-bVmvamiPA9EZUu7oCO6KhA"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
+  <a href="https://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>
+  <br/>
+  <a href="https://huggingface.co/spaces/OpenDevin/evaluation"><img src="https://img.shields.io/badge/SWE--bench%20Lite-25.0%25-green?style=for-the-badge" alt="SWE-bench "></a>
+  <a href="https://codecov.io/github/opendevin/opendevin?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/opendevin/opendevin?style=for-the-badge"></a>
 </div>
 
 <!-- PROJECT LOGO -->
 <div align="center">
-  <img src="./logo.png" alt="Logo" width="200" height="200">
+  <img src="./docs/static/img/logo.png" alt="Logo" width="200" height="200">
   <h1 align="center">OpenDevin: Code Less, Make More</h1>
+  <a href="https://opendevin.github.io/OpenDevin/"><img src="https://img.shields.io/badge/Documentation-OpenDevin-blue?logo=googledocs&logoColor=white&style=for-the-badge" alt="Check out the documentation"></a>
 </div>
+<hr>
 
+Welcome to OpenDevin, a platform for autonomous software engineers, powered by AI and LLMs.
 
+OpenDevin agents collaborate with human developers to write code, fix bugs, and ship features.
 
+![App screenshot](./docs/static/img/screenshot.png)
 
-<!-- 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>
+## ⚡ Getting Started
+The easiest way to run OpenDevin is inside a Docker container. It works best with the most recent version of Docker, `26.0.0`.
+You must be using Linux, Mac OS, or WSL on Windows.
 
-## 🎯 Mission
+To start OpenDevin in a docker container, run the following commands in your terminal:
 
-[Project Demo Video](https://github.com/OpenDevin/OpenDevin/assets/38853559/71a472cc-df34-430c-8b1d-4d7286c807c9)
+> [!WARNING]
+> When you run the following command, files in `./workspace` may be modified or deleted.
 
+```bash
+OPENDEVIN_WORKSPACE=$(pwd)/workspace
+docker run -it \
+    --pull=always \
+    -e SANDBOX_USER_ID=$(id -u) \
+    -e PERSIST_SANDBOX="true" \
+    -e SSH_PASSWORD="make something up here" \
+    -e WORKSPACE_MOUNT_PATH=$OPENDEVIN_WORKSPACE \
+    -v $OPENDEVIN_WORKSPACE:/opt/workspace_base \
+    -v /var/run/docker.sock:/var/run/docker.sock \
+    -p 3000:3000 \
+    --add-host host.docker.internal:host-gateway \
+    --name opendevin-app-$(date +%Y%m%d%H%M%S) \
+    ghcr.io/opendevin/opendevin:0.6
+```
 
-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.
+You'll find OpenDevin running at [http://localhost:3000](http://localhost:3000) with access to `./workspace`. To have OpenDevin operate on your code, place it in `./workspace`.
 
-<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>
+OpenDevin will only have access to this workspace folder. The rest of your system will not be affected as it runs in a secured docker sandbox.
 
-## 🤔 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.
+## 🚀 Documentation
 
-<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>
+To learn more about the project, and for tips on using OpenDevin,
+**check out our [documentation](https://opendevin.github.io/OpenDevin/)**.
 
-## 🐚 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>
-
-## 🚀 Get Started
-
-Getting started with the OpenDevin project is incredibly easy. Follow these simple steps to set up and run OpenDevin on your system:
-
-### 1. Requirements
-* Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)
-* [Docker](https://docs.docker.com/engine/install/)(For those on MacOS, make sure to allow the default Docker socket to be used from advanced settings!)
-* [Python](https://www.python.org/downloads/) >= 3.11
-* [NodeJS](https://nodejs.org/en/download/package-manager) >= 18.17.1
-
-### 2. Build and Setup The Environment
-
-- **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
-
-OpenDevin supports a diverse array of Language Models (LMs) through the powerful [litellm](https://docs.litellm.ai) library. By default, we've chosen the mighty GPT-4 from OpenAI as our go-to model, but the world is your oyster! You can unleash the potential of Anthropic's suave Claude, the enigmatic Llama, or any other LM that piques your interest.
-
-To configure the LM of your choice, follow these steps:
-
-1. **Using the Makefile: The Effortless Approach**
-   With a single command, you can have a smooth LM setup for your OpenDevin experience. Simply run:
-   ```bash
-   make setup-config
-   ```
-   This command will prompt you to enter the LLM API key and model name, ensuring that OpenDevin is tailored to your specific needs.
-
-2. **Manual Config: The Artisanal Touch**
-   If you're feeling particularly adventurous, you can manually update the `config.toml` file located in the project's root directory. Here, you'll find the `llm_api_key` and `llm_model_name` fields, where you can set the LM of your choosing.
-
-**Note on Alternative Models:**
-Some alternative models may prove more challenging to tame than others. Fear not, brave adventurer! We shall soon unveil LLM-specific documentation to guide you on your quest. And if you've already mastered the art of wielding a model other than OpenAI's GPT, we encourage you to [share your setup instructions with us](https://github.com/OpenDevin/OpenDevin/issues/417).
-
-For a full list of the LM providers and models available, please consult the [litellm documentation](https://docs.litellm.ai/docs/providers).
-
-### 4. Run the Application
-
-- **Run the Application:** Once the setup is complete, launching OpenDevin is as simple as running a single command. This command starts both the backend and frontend servers seamlessly, allowing you to interact with OpenDevin without any hassle.
-    ```bash
-    make run
-    ```
-
-### 5. Individual Server Startup
-
-- **Start the Backend Server:** If you prefer, you can start the backend server independently to focus on backend-related tasks or configurations.
-    ```bash
-    make start-backend
-    ```
-
-- **Start the Frontend Server:** Similarly, you can start the frontend server on its own to work on frontend-related components or interface enhancements.
-    ```bash
-    make start-frontend
-    ```
-
-### 6. Help
-
-- **Get Some Help:** Need assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenDevin.
-    ```bash
-    make help
-    ```
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
-
-## ⭐️ Research Strategy
-
-Achieving full replication of production-grade applications with LLMs is a complex endeavor. Our strategy involves:
-
-1. **Core Technical Research:** Focusing on foundational research to understand and improve the technical aspects of code generation and handling.
-2. **Specialist Abilities:** Enhancing the effectiveness of core components through data curation, training methods, and more.
-3. **Task Planning:** Developing capabilities for bug detection, codebase management, and optimization.
-4. **Evaluation:** Establishing comprehensive evaluation metrics to better understand and improve our models.
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
+There you'll find resources on how to use different LLM providers (like ollama and Anthropic's Claude),
+troubleshooting resources, and advanced configuration options.
 
 ## 🤝 How to Contribute
 
-OpenDevin is a community-driven project, and we welcome contributions from everyone. Whether you're a developer, a researcher, or simply enthusiastic about advancing the field of software engineering with AI, there are many ways to get involved:
+OpenDevin is a community-driven project, and we welcome contributions from everyone.
+Whether you're a developer, a researcher, or simply enthusiastic about advancing the field of
+software engineering with AI, there are many ways to get involved:
 
-- **Code Contributions:** Help us develop the core functionalities, frontend interface, or sandboxing solutions.
+- **Code Contributions:** Help us develop new agents, core functionality, the frontend and other interfaces, or sandboxing solutions.
 - **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in evaluating the models, or suggest improvements.
 - **Feedback and Testing:** Use the OpenDevin toolset, report bugs, suggest features, or provide feedback on usability.
 
-For details, please check [this document](./CONTRIBUTING.md).
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
+For details, please check [CONTRIBUTING.md](./CONTRIBUTING.md).
 
 ## 🤖 Join Our Community
 
-Join our Slack workspace by filling out the [form](https://forms.gle/758d5p6Ve8r2nxxq6). Stay updated on OpenDevin's progress, share ideas, and collaborate with fellow enthusiasts and experts. Let's simplify software engineering together!
+Whether you're a developer, a researcher, or simply enthusiastic about OpenDevin, we'd love to have you in our community.
+Let's make software engineering better together!
 
-🐚 **Code less, make more with OpenDevin.**
+- [Slack workspace](https://join.slack.com/t/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA) - Here we talk about research, architecture, and future development.
+- [Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
 
-[![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 ↑
+## 📈 Progress
+<p align="center">
+    <a href="https://www.swebench.com/lite.html">
+        <img src="/docs/static/img/results.png" alt="SWE-Bench Lite Score" width="500" height="auto">
     </a>
 </p>
 
+<p align="center">
+  <a href="https://star-history.com/#OpenDevin/OpenDevin&Date">
+    <img src="https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date" width="500" alt="Star History Chart">
+  </a>
+</p>
+
 ## 📜 License
 
 Distributed under the MIT License. See [`LICENSE`](./LICENSE) for more information.
 
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
-
 [contributors-shield]: https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge
 [contributors-url]: https://github.com/OpenDevin/OpenDevin/graphs/contributors
 [forks-shield]: https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge
@@ -251,3 +129,16 @@ Distributed under the MIT License. See [`LICENSE`](./LICENSE) for more informati
 [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
+
+## 📚 Cite
+
+```
+@misc{opendevin2024,
+  author       = {{OpenDevin Team}},
+  title        = {{OpenDevin: An Open Platform for AI Software Developers as Generalist Agents}},
+  year         = {2024},
+  version      = {v1.0},
+  howpublished = {\url{https://github.com/OpenDevin/OpenDevin}},
+  note         = {Accessed: ENTER THE DATE YOU ACCESSED THE PROJECT}
+}
+```

agenthub/README.md

@@ -2,71 +2,85 @@
 
 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.
+For example, `agenthub/codeact_agent`, etc.
 Contributors from different backgrounds and interests can choose to contribute to any (or all!) of these directions.
 
 ## Constructing an Agent
 
-The abstraction for an agent can be found [here](../opendevin/agent.py).
+The abstraction for an agent can be found [here](../opendevin/controller/agent.py).
 
 Agents are run inside of a loop. At each iteration, `agent.step()` is called with a
-[State](../opendevin/state.py) input, and the agent must output an [Action](../opendevin/action).
+[State](../opendevin/controller/state/state.py) input, and the agent must output an [Action](../opendevin/events/action).
 
 Every agent also has a `self.llm` which it can use to interact with the LLM configured by the user.
 See the [LiteLLM docs for `self.llm.completion`](https://docs.litellm.ai/docs/completion).
 
 ## State
+
 The `state` contains:
-* A history of actions taken by the agent, as well as any observations (e.g. file content, command output) from those actions
-* A list of actions/observations that have happened since the most recent step
-* A [`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`
+
+- A history of actions taken by the agent, as well as any observations (e.g. file content, command output) from those actions
+- A list of actions/observations that have happened since the most recent step
+- A [`root_task`](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/controller/state/task.py), which contains a plan of action
+  - The agent can add and modify subtasks through the `AddTaskAction` and `ModifyTaskAction`
 
 ## Actions
+
 Here is a list of available Actions, which can be returned by `agent.step()`:
-- [`CmdRunAction`](../opendevin/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
+
+- [`CmdRunAction`](../opendevin/events/action/commands.py) - Runs a command inside a sandboxed terminal
+- [`CmdKillAction`](../opendevin/events/action/commands.py) - Kills a background command
+- [`IPythonRunCellAction`](../opendevin/events/action/commands.py) - Execute a block of Python code interactively (in Jupyter notebook) and receives `CmdOutputObservation`. Requires setting up `jupyter` [plugin](../opendevin/runtime/plugins) as a requirement.
+- [`FileReadAction`](../opendevin/events/action/files.py) - Reads the content of a file
+- [`FileWriteAction`](../opendevin/events/action/files.py) - Writes new content to a file
+- [`BrowseURLAction`](../opendevin/events/action/browse.py) - Gets the content of a URL
+- [`AgentRecallAction`](../opendevin/events/action/agent.py) - Searches memory (e.g. a vector database)
+- [`AddTaskAction`](../opendevin/events/action/tasks.py) - Adds a subtask to the plan
+- [`ModifyTaskAction`](../opendevin/events/action/tasks.py) - Changes the state of a subtask.
+- [`AgentFinishAction`](../opendevin/events/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
+- [`AgentRejectAction`](../opendevin/events/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
+- [`AgentFinishAction`](../opendevin/events/action/agent.py) - Stops the control loop, allowing the user to enter a new task
+- [`MessageAction`](../opendevin/events/action/message.py) - Represents a message from an agent or the user
 
 You can use `action.to_dict()` and `action_from_dict` to serialize and deserialize actions.
 
 ## Observations
+
 There are also several types of Observations. These are typically available in the step following the corresponding Action.
 But they may also appear as a result of asynchronous events (e.g. a message from the user, 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)
+
+- [`CmdOutputObservation`](../opendevin/events/observation/commands.py)
+- [`BrowserOutputObservation`](../opendevin/events/observation/browse.py)
+- [`FileReadObservation`](../opendevin/events/observation/files.py)
+- [`FileWriteObservation`](../opendevin/events/observation/files.py)
+- [`AgentRecallObservation`](../opendevin/events/observation/recall.py)
+- [`ErrorObservation`](../opendevin/events/observation/error.py)
+- [`SuccessObservation`](../opendevin/events/observation/success.py)
 
 You can use `observation.to_dict()` and `observation_from_dict` to serialize and deserialize observations.
 
 ## Interface
+
 Every agent must implement the following methods:
 
 ### `step`
+
 ```
 def step(self, state: "State") -> "Action"
 ```
+
 `step` moves the agent forward one step towards its goal. This probably means
 sending a prompt to the LLM, then parsing the response into an `Action`.
 
 ### `search_memory`
+
 ```
-def search_memory(self, query: str) -> List[str]:
+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.
 

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

agenthub/SWE_agent/agent.py

@@ -0,0 +1,117 @@
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.events.action import (
+    Action,
+    FileReadAction,
+    FileWriteAction,
+    MessageAction,
+)
+from opendevin.events.serialization.event import event_to_memory
+from opendevin.llm.llm import LLM
+from opendevin.runtime.tools import RuntimeTool
+
+from .parser import parse_command
+from .prompts import (
+    CONTEXT_PROMPT,
+    MEMORY_FORMAT,
+    NO_ACTION,
+    STEP_PROMPT,
+    SYSTEM_MESSAGE,
+)
+
+
+class SWEAgent(Agent):
+    VERSION = '1.0'
+    DEPRECATED = True
+    """
+    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'
+    """
+    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
+
+    def __init__(self, llm: LLM):
+        super().__init__(llm)
+        self.memory_window = 4
+        self.max_retries = 2
+        self.cur_file: str = ''
+        self.cur_line: int = 0
+
+    def _think_act(self, messages: list[dict]) -> tuple[Action, str]:
+        resp = self.llm.do_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)
+        """
+        # retrieve short term memories from state.history, up to memory_window
+        memory_window = min(self.memory_window, len(state.history))
+        running_memory: list[str] = []
+        for prev_action, obs in state.history[-memory_window:]:
+            running_memory.append(
+                MEMORY_FORMAT(event_to_memory(prev_action), event_to_memory(obs))
+            )
+
+        goal = state.get_current_user_intent()
+
+        # always in the prompt if they exist: file and line
+        prompt = STEP_PROMPT(goal, self.cur_file, self.cur_line)
+
+        # prepare messages
+        msgs = [
+            {'content': SYSTEM_MESSAGE, 'role': 'system'},
+            {'content': prompt, 'role': 'user'},
+        ]
+
+        # insert memories
+        if len(running_memory) > 0:
+            context = CONTEXT_PROMPT(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)]))
+
+        # send it over
+        action, thought = self._think_act(messages=msgs)
+
+        # be robust with malformed responses
+        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 = MessageAction(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]
+        raise NotImplementedError('Search_memory not implemented currently')
+
+    def reset(self) -> None:
+        """Used to reset the agent"""
+        super().reset()

agenthub/SWE_agent/parser.py

@@ -0,0 +1,167 @@
+import re
+
+from opendevin.events.action import (
+    Action,
+    AgentFinishAction,
+    BrowseURLAction,
+    CmdRunAction,
+    FileReadAction,
+    FileWriteAction,
+    MessageAction,
+)
+
+from .prompts import COMMAND_USAGE, CUSTOM_DOCS
+
+# commands: exit, read, write, browse, kill, search_file, search_dir
+
+no_open_file_error = MessageAction(
+    '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 MessageAction(' '.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+)$'
+        valid = re.match(rex, command_string)
+        if valid:
+            start = int(valid.group(1))
+            end = start + 100
+            return FileReadAction(path, start, end, thoughts)
+        else:
+            return MessageAction(invalid_error(command_string, 'goto'))
+
+    elif 'edit' == cmd:
+        if not path:
+            return no_open_file_error
+        rex = r'^edit\s+(\d+)\s+(-?\d+)\s+(\S.*)$'
+        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 MessageAction(invalid_error(command_string, 'edit'))
+
+    elif 'read' == cmd:
+        rex = r'^read\s+(\S+)(?:\s+(\d+))?(?:\s+(-?\d+))?$'
+        valid = re.match(rex, command_string, re.DOTALL)
+        if valid:
+            file = valid.group(1)
+            start_str = valid.group(2)
+            end_str = valid.group(3)
+
+            start = 0 if not start_str else int(start_str)
+            end = -1 if not end_str else int(end_str)
+
+            return FileReadAction(file, start, end, thoughts)
+        else:
+            return MessageAction(invalid_error(command_string, 'read'))
+
+    elif 'write' == cmd:
+        rex = r'^write\s+(\S+)\s+(.*?)\s*(\d+)?\s*(-?\d+)?$'
+        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 MessageAction(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 MessageAction(
+                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 MessageAction(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 +1,208 @@
+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. Set end_line to -1 to denote the end of the file',
+    '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()])
+
+# from opendevin.parse_commands import parse_command_file
+# USE parse_command_file(filepath) to get the custom commands
+CUSTOM_DOCS = None
+
+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 are an autonomous coding agent, here to provide solutions for coding issues.
+You have been designed to assist 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] | None = None):
+    lines = []
+    restrict = [] if restrict is None else restrict
+    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

@@ -1,9 +1,46 @@
 from dotenv import load_dotenv
+
+from opendevin.controller.agent import Agent
+
+from .micro.agent import MicroAgent
+from .micro.registry import all_microagents
+
 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
 
-__all__ = ['monologue_agent', 'codeact_agent', 'planner_agent']
+from . import (  # noqa: E402
+    SWE_agent,
+    browsing_agent,
+    codeact_agent,
+    codeact_swe_agent,
+    delegator_agent,
+    dummy_agent,
+    monologue_agent,
+    planner_agent,
+)
+
+__all__ = [
+    'monologue_agent',
+    'codeact_agent',
+    'codeact_swe_agent',
+    'planner_agent',
+    'SWE_agent',
+    'delegator_agent',
+    'dummy_agent',
+    'browsing_agent',
+]
+
+for agent in all_microagents.values():
+    name = agent['name']
+    prompt = agent['prompt']
+
+    anon_class = type(
+        name,
+        (MicroAgent,),
+        {
+            'prompt': prompt,
+            'agent_definition': agent,
+        },
+    )
+
+    Agent.register(name, anon_class)

agenthub/browsing_agent/README.md

@@ -0,0 +1,16 @@
+# Browsing Agent Framework
+
+This folder implements the basic BrowserGym [demo agent](https://github.com/ServiceNow/BrowserGym/tree/main/demo_agent) that enables full-featured web browsing.
+
+
+## Test run
+
+Note that for browsing tasks, GPT-4 is usually a requirement to get reasonable results, due to the complexity of the web page structures.
+
+```
+poetry run python ./opendevin/core/main.py \
+           -i 10 \
+           -t "tell me the usa's president using google search" \
+           -c BrowsingAgent \
+           -m gpt-4o-2024-05-13
+```

agenthub/browsing_agent/__init__.py

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

agenthub/browsing_agent/browsing_agent.py

@@ -0,0 +1,247 @@
+import ast
+import os
+
+from browsergym.core.action.highlevel import HighLevelActionSet
+from browsergym.utils.obs import flatten_axtree_to_str
+
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.core.logger import opendevin_logger as logger
+from opendevin.events.action import (
+    Action,
+    AgentFinishAction,
+    BrowseInteractiveAction,
+    MessageAction,
+)
+from opendevin.events.event import EventSource
+from opendevin.events.observation import BrowserOutputObservation
+from opendevin.llm.llm import LLM
+from opendevin.runtime.plugins import (
+    PluginRequirement,
+)
+from opendevin.runtime.tools import RuntimeTool
+
+USE_NAV = (
+    os.environ.get('USE_NAV', 'true') == 'true'
+)  # only disable NAV actions when running webarena and miniwob benchmarks
+USE_CONCISE_ANSWER = (
+    os.environ.get('USE_CONCISE_ANSWER', 'false') == 'true'
+)  # only return concise answer when running webarena and miniwob benchmarks
+
+if not USE_NAV and USE_CONCISE_ANSWER:
+    EVAL_MODE = True  # disabled NAV actions and only return concise answer, for webarena and miniwob benchmarks\
+else:
+    EVAL_MODE = False
+
+
+class BrowsingAgent(Agent):
+    VERSION = '1.0'
+    """
+    An agent that interacts with the browser.
+    """
+
+    sandbox_plugins: list[PluginRequirement] = []
+    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
+
+    def __init__(
+        self,
+        llm: LLM,
+    ) -> None:
+        """
+        Initializes a new instance of the BrowsingAgent class.
+
+        Parameters:
+        - llm (LLM): The llm to be used by this agent
+        """
+        super().__init__(llm)
+        # define a configurable action space, with chat functionality, web navigation, and webpage grounding using accessibility tree and HTML.
+        # see https://github.com/ServiceNow/BrowserGym/blob/main/core/src/browsergym/core/action/highlevel.py for more details
+        action_subsets = ['chat', 'bid']
+        if USE_NAV:
+            action_subsets.append('nav')
+        self.action_space = HighLevelActionSet(
+            subsets=action_subsets,
+            strict=False,  # less strict on the parsing of the actions
+            multiaction=True,  # enable to agent to take multiple actions at once
+        )
+
+        self.reset()
+
+    def reset(self) -> None:
+        """
+        Resets the Browsing Agent.
+        """
+        super().reset()
+        self.cost_accumulator = 0
+        self.error_accumulator = 0
+
+    def parse_response(self, response: str) -> Action:
+        if '```' not in response:
+            # unexpected response format, message back to user
+            action_str = f'send_msg_to_user("""{response}""")'
+            return BrowseInteractiveAction(
+                browser_actions=action_str,
+                thought=response,
+                browsergym_send_msg_to_user=response,
+            )
+        thought = response.split('```')[0].strip()
+        action_str = response.split('```')[1].strip()
+        # handle send message to user function call in BrowserGym
+        msg_content = ''
+        for sub_action in action_str.split('\n'):
+            if 'send_msg_to_user(' in sub_action:
+                tree = ast.parse(sub_action)
+                args = tree.body[0].value.args  # type: ignore
+                msg_content = args[0].value
+
+        return BrowseInteractiveAction(
+            browser_actions=action_str,
+            thought=thought,
+            browsergym_send_msg_to_user=msg_content,
+        )
+
+    def step(self, state: State) -> Action:
+        """
+        Performs one step using the Browsing Agent.
+        This includes gathering information on previous steps and prompting the model to make a browsing command to execute.
+
+        Parameters:
+        - state (State): used to get updated info
+
+        Returns:
+        - BrowseInteractiveAction(browsergym_command) - BrowserGym commands to run
+        - MessageAction(content) - Message action to run (e.g. ask for clarification)
+        - AgentFinishAction() - end the interaction
+        """
+        goal = state.get_current_user_intent()
+        if goal is None:
+            goal = state.inputs['task']
+        messages = []
+        prev_actions = []
+        cur_axtree_txt = ''
+        error_prefix = ''
+        last_obs = None
+        last_action = None
+
+        if EVAL_MODE and len(state.history) == 1:
+            # for webarena and miniwob++ eval, we need to retrieve the initial observation already in browser env
+            # initialize and retrieve the first observation by issuing an noop OP
+            # For non-benchmark browsing, the browser env starts with a blank page, and the agent is expected to first navigate to desired websites
+            return BrowseInteractiveAction(browser_actions='noop()')
+
+        for prev_action, obs in state.history:
+            if isinstance(prev_action, BrowseInteractiveAction):
+                prev_actions.append(prev_action.browser_actions)
+                last_obs = obs
+                last_action = prev_action
+            elif (
+                isinstance(prev_action, MessageAction)
+                and prev_action.source == EventSource.AGENT
+            ):
+                # agent has responded, task finish.
+                return AgentFinishAction(outputs={'content': prev_action.content})
+
+        if EVAL_MODE:
+            prev_actions = prev_actions[1:]  # remove the first noop action
+
+        prev_action_str = '\n'.join(prev_actions)
+        # if the final BrowserInteractiveAction exec BrowserGym's send_msg_to_user,
+        # we should also send a message back to the user in OpenDevin and call it a day
+        if (
+            isinstance(last_action, BrowseInteractiveAction)
+            and last_action.browsergym_send_msg_to_user
+        ):
+            return MessageAction(last_action.browsergym_send_msg_to_user)
+
+        if isinstance(last_obs, BrowserOutputObservation):
+            if last_obs.error:
+                # add error recovery prompt prefix
+                error_prefix = f'IMPORTANT! Last action is incorrect:\n{last_obs.last_browser_action}\nThink again with the current observation of the page.\n'
+            try:
+                cur_axtree_txt = flatten_axtree_to_str(
+                    last_obs.axtree_object,
+                    extra_properties=last_obs.extra_element_properties,
+                    with_clickable=True,
+                    filter_visible_only=True,
+                )
+            except Exception as e:
+                logger.error(
+                    'Error when trying to process the accessibility tree: %s', e
+                )
+                return MessageAction('Error encountered when browsing.')
+
+        if error_prefix:
+            self.error_accumulator += 1
+            if self.error_accumulator > 5:
+                return MessageAction('Too many errors encountered. Task failed.')
+        system_msg = f"""\
+# Instructions
+Review the current state of the page and all other information to find the best
+possible next action to accomplish your goal. Your answer will be interpreted
+and executed by a program, make sure to follow the formatting instructions.
+
+# Goal:
+{goal}
+
+# Action Space
+{self.action_space.describe(with_long_description=False, with_examples=True)}
+"""
+
+        messages.append({'role': 'system', 'content': system_msg})
+
+        prompt = f"""\
+{error_prefix}
+
+# Current Accessibility Tree:
+{cur_axtree_txt}
+
+# Previous Actions
+{prev_action_str}
+
+Here is an example with chain of thought of a valid action when clicking on a button:
+"
+In order to accomplish my goal I need to click on the button with bid 12
+```click("12")```
+"
+""".strip()
+
+        if USE_CONCISE_ANSWER:
+            concise_instruction = """\
+
+Here is another example with chain of thought of a valid action when providing a concise answer to user:
+"
+In order to accomplish my goal I need to send the information asked back to the user. This page list the information of HP Inkjet Fax Machine, which is the product identified in the objective. Its price is $279.49. I will send a message back to user with the answer.
+```send_msg_to_user("$279.49")```
+"
+"""
+            prompt += concise_instruction
+        messages.append({'role': 'user', 'content': prompt})
+        response = self.llm.completion(
+            messages=messages,
+            temperature=0.0,
+            stop=[')```', ')\n```'],
+        )
+        self.log_cost(response)
+        action_resp = response['choices'][0]['message']['content'].strip()
+        if not action_resp.endswith('```'):
+            action_resp = action_resp + ')```'
+
+        logger.info(prompt)
+        logger.info(action_resp)
+        return self.parse_response(action_resp)
+
+    def search_memory(self, query: str) -> list[str]:
+        raise NotImplementedError('Implement this abstract method')
+
+    def log_cost(self, response):
+        # TODO: refactor to unified cost tracking
+        try:
+            cur_cost = self.llm.completion_cost(response)
+        except Exception:
+            cur_cost = 0
+        self.cost_accumulator += cur_cost
+        logger.info(
+            'Cost: %.2f USD | Accumulated Cost: %.2f USD',
+            cur_cost,
+            self.cost_accumulator,
+        )

agenthub/browsing_agent/prompt.py

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

agenthub/browsing_agent/utils.py

@@ -0,0 +1,160 @@
+import collections
+import re
+from warnings import warn
+
+import yaml
+
+
+def yaml_parser(message):
+    """Parse a yaml message for the retry function."""
+
+    # saves gpt-3.5 from some yaml parsing errors
+    message = re.sub(r':\s*\n(?=\S|\n)', ': ', message)
+
+    try:
+        value = yaml.safe_load(message)
+        valid = True
+        retry_message = ''
+    except yaml.YAMLError as e:
+        warn(str(e), stacklevel=2)
+        value = {}
+        valid = False
+        retry_message = "Your response is not a valid yaml. Please try again and be careful to the format. Don't add any apology or comment, just the answer."
+    return value, valid, retry_message
+
+
+def _compress_chunks(text, identifier, skip_list, split_regex='\n\n+'):
+    """Compress a string by replacing redundant chunks by identifiers. Chunks are defined by the split_regex."""
+    text_list = re.split(split_regex, text)
+    text_list = [chunk.strip() for chunk in text_list]
+    counter = collections.Counter(text_list)
+    def_dict = {}
+    id = 0
+
+    # Store items that occur more than once in a dictionary
+    for item, count in counter.items():
+        if count > 1 and item not in skip_list and len(item) > 10:
+            def_dict[f'{identifier}-{id}'] = item
+            id += 1
+
+    # Replace redundant items with their identifiers in the text
+    compressed_text = '\n'.join(text_list)
+    for key, value in def_dict.items():
+        compressed_text = compressed_text.replace(value, key)
+
+    return def_dict, compressed_text
+
+
+def compress_string(text):
+    """Compress a string by replacing redundant paragraphs and lines with identifiers."""
+
+    # Perform paragraph-level compression
+    def_dict, compressed_text = _compress_chunks(
+        text, identifier='§', skip_list=[], split_regex='\n\n+'
+    )
+
+    # Perform line-level compression, skipping any paragraph identifiers
+    line_dict, compressed_text = _compress_chunks(
+        compressed_text, '¶', list(def_dict.keys()), split_regex='\n+'
+    )
+    def_dict.update(line_dict)
+
+    # Create a definitions section
+    def_lines = ['<definitions>']
+    for key, value in def_dict.items():
+        def_lines.append(f'{key}:\n{value}')
+    def_lines.append('</definitions>')
+    definitions = '\n'.join(def_lines)
+
+    return definitions + '\n' + compressed_text
+
+
+def extract_html_tags(text, keys):
+    """Extract the content within HTML tags for a list of keys.
+
+    Parameters
+    ----------
+    text : str
+        The input string containing the HTML tags.
+    keys : list of str
+        The HTML tags to extract the content from.
+
+    Returns
+    -------
+    dict
+        A dictionary mapping each key to a list of subset in `text` that match the key.
+
+    Notes
+    -----
+    All text and keys will be converted to lowercase before matching.
+
+    """
+    content_dict = {}
+    # text = text.lower()
+    # keys = set([k.lower() for k in keys])
+    for key in keys:
+        pattern = f'<{key}>(.*?)</{key}>'
+        matches = re.findall(pattern, text, re.DOTALL)
+        if matches:
+            content_dict[key] = [match.strip() for match in matches]
+    return content_dict
+
+
+class ParseError(Exception):
+    pass
+
+
+def parse_html_tags_raise(text, keys=(), optional_keys=(), merge_multiple=False):
+    """A version of parse_html_tags that raises an exception if the parsing is not successful."""
+    content_dict, valid, retry_message = parse_html_tags(
+        text, keys, optional_keys, merge_multiple=merge_multiple
+    )
+    if not valid:
+        raise ParseError(retry_message)
+    return content_dict
+
+
+def parse_html_tags(text, keys=(), optional_keys=(), merge_multiple=False):
+    """Satisfy the parse api, extracts 1 match per key and validates that all keys are present
+
+    Parameters
+    ----------
+    text : str
+        The input string containing the HTML tags.
+    keys : list of str
+        The HTML tags to extract the content from.
+    optional_keys : list of str
+        The HTML tags to extract the content from, but are optional.
+
+    Returns
+    -------
+    dict
+        A dictionary mapping each key to subset of `text` that match the key.
+    bool
+        Whether the parsing was successful.
+    str
+        A message to be displayed to the agent if the parsing was not successful.
+    """
+    all_keys = tuple(keys) + tuple(optional_keys)
+    content_dict = extract_html_tags(text, all_keys)
+    retry_messages = []
+
+    for key in all_keys:
+        if key not in content_dict:
+            if key not in optional_keys:
+                retry_messages.append(f'Missing the key <{key}> in the answer.')
+        else:
+            val = content_dict[key]
+            content_dict[key] = val[0]
+            if len(val) > 1:
+                if not merge_multiple:
+                    retry_messages.append(
+                        f'Found multiple instances of the key {key}. You should have only one of them.'
+                    )
+                else:
+                    # merge the multiple instances
+                    content_dict[key] = '\n'.join(val)
+
+    valid = len(retry_messages) == 0
+    retry_message = '\n'.join(retry_messages)
+    return content_dict, valid, retry_message

agenthub/codeact_agent/README.md

@@ -1,21 +1,29 @@
-# CodeAct-based Agent Framework
+# CodeAct 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. 
+This folder implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.01030), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a unified **code** action space for both *simplicity* and *performance* (see paper for more details).
 
-A minimalistic example can be found at [research/codeact/examples/run_flask_server_with_bash.py](./examples/run_flask_server_with_bash.py):
+The conceptual idea is illustrated below. At each turn, the agent can:
 
-```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."
-```
+1. **Converse**: Communicate with humans in natural language to ask for clarification, confirmation, etc.
+2. **CodeAct**: Choose to perform the task by executing code
+   - Execute any valid Linux `bash` command
+   - Execute any valid `Python` code with [an interactive Python interpreter](https://ipython.org/). This is simulated through `bash` command, see plugin system below for more details.
 
+![image](https://github.com/OpenDevin/OpenDevin/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
 
-Example: prompts `gpt-4-0125-preview` to write a flask server, install `flask` library, and start the server.
+## Plugin System
 
-<img width="951" alt="image" src="https://github.com/OpenDevin/OpenDevin/assets/38853559/325c3115-a343-4cc5-a92b-f1e5d552a077">
+To make the CodeAct agent more powerful with only access to `bash` action space, CodeAct agent leverages OpenDevin's plugin system:
+- [Jupyter plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/jupyter): for IPython execution via bash command
+- [SWE-agent tool plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/swe_agent_commands): Powerful bash command line tools for software development tasks introduced by [swe-agent](https://github.com/princeton-nlp/swe-agent).
 
-<img width="957" alt="image" src="https://github.com/OpenDevin/OpenDevin/assets/38853559/68ad10c1-744a-4e9d-bb29-0f163d665a0a">
+## Demo
 
-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. 
+https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
 
-**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).
+*Example of CodeActAgent with `gpt-4-turbo-2024-04-09` performing a data science task (linear regression)*
+
+## Work-in-progress & Next step
+
+[] Support web-browsing
+[] Complete the workflow for CodeAct agent to submit Github PRs

agenthub/codeact_agent/__init__.py

@@ -1,4 +1,5 @@
-from opendevin.agent import Agent
+from opendevin.controller.agent import Agent
+
 from .codeact_agent import CodeActAgent
 
-Agent.register("CodeActAgent", CodeActAgent)
+Agent.register('CodeActAgent', CodeActAgent)

agenthub/codeact_agent/action_parser.py

@@ -0,0 +1,182 @@
+import re
+
+from opendevin.controller.action_parser import ActionParser, ResponseParser
+from opendevin.events.action import (
+    Action,
+    AgentDelegateAction,
+    AgentFinishAction,
+    CmdRunAction,
+    IPythonRunCellAction,
+    MessageAction,
+)
+
+
+class CodeActResponseParser(ResponseParser):
+    """
+    Parser action:
+        - CmdRunAction(command) - bash command to run
+        - IPythonRunCellAction(code) - IPython code to run
+        - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
+        - MessageAction(content) - Message action to run (e.g. ask for clarification)
+        - AgentFinishAction() - end the interaction
+    """
+
+    def __init__(
+        self,
+    ):
+        # Need pay attention to the item order in self.action_parsers
+        self.action_parsers = [
+            CodeActActionParserFinish(),
+            CodeActActionParserCmdRun(),
+            CodeActActionParserIPythonRunCell(),
+            CodeActActionParserAgentDelegate(),
+        ]
+        self.default_parser = CodeActActionParserMessage()
+
+    def parse(self, response: str) -> Action:
+        action_str = self.parse_response(response)
+        return self.parse_action(action_str)
+
+    def parse_response(self, response) -> str:
+        action = response.choices[0].message.content
+        for lang in ['bash', 'ipython', 'browse']:
+            if f'<execute_{lang}>' in action and f'</execute_{lang}>' not in action:
+                action += f'</execute_{lang}>'
+        return action
+
+    def parse_action(self, action_str: str) -> Action:
+        for action_parser in self.action_parsers:
+            if action_parser.check_condition(action_str):
+                return action_parser.parse(action_str)
+        return self.default_parser.parse(action_str)
+
+
+class CodeActActionParserFinish(ActionParser):
+    """
+    Parser action:
+        - AgentFinishAction() - end the interaction
+    """
+
+    def __init__(
+        self,
+    ):
+        self.finish_command = None
+
+    def check_condition(self, action_str: str) -> bool:
+        self.finish_command = re.search(r'<finish>.*</finish>', action_str, re.DOTALL)
+        return self.finish_command is not None
+
+    def parse(self, action_str: str) -> Action:
+        assert (
+            self.finish_command is not None
+        ), 'self.finish_command should not be None when parse is called'
+        thought = action_str.replace(self.finish_command.group(0), '').strip()
+        return AgentFinishAction(thought=thought)
+
+
+class CodeActActionParserCmdRun(ActionParser):
+    """
+    Parser action:
+        - CmdRunAction(command) - bash command to run
+        - AgentFinishAction() - end the interaction
+    """
+
+    def __init__(
+        self,
+    ):
+        self.bash_command = None
+
+    def check_condition(self, action_str: str) -> bool:
+        self.bash_command = re.search(
+            r'<execute_bash>(.*?)</execute_bash>', action_str, re.DOTALL
+        )
+        return self.bash_command is not None
+
+    def parse(self, action_str: str) -> Action:
+        assert (
+            self.bash_command is not None
+        ), 'self.bash_command should not be None when parse is called'
+        thought = action_str.replace(self.bash_command.group(0), '').strip()
+        # a command was found
+        command_group = self.bash_command.group(1).strip()
+        if command_group.strip() == 'exit':
+            return AgentFinishAction()
+        return CmdRunAction(command=command_group, thought=thought)
+
+
+class CodeActActionParserIPythonRunCell(ActionParser):
+    """
+    Parser action:
+        - IPythonRunCellAction(code) - IPython code to run
+    """
+
+    def __init__(
+        self,
+    ):
+        self.python_code = None
+        self.jupyter_kernel_init_code: str = 'from agentskills import *'
+
+    def check_condition(self, action_str: str) -> bool:
+        self.python_code = re.search(
+            r'<execute_ipython>(.*?)</execute_ipython>', action_str, re.DOTALL
+        )
+        return self.python_code is not None
+
+    def parse(self, action_str: str) -> Action:
+        assert (
+            self.python_code is not None
+        ), 'self.python_code should not be None when parse is called'
+        code_group = self.python_code.group(1).strip()
+        thought = action_str.replace(self.python_code.group(0), '').strip()
+        return IPythonRunCellAction(
+            code=code_group,
+            thought=thought,
+            kernel_init_code=self.jupyter_kernel_init_code,
+        )
+
+
+class CodeActActionParserAgentDelegate(ActionParser):
+    """
+    Parser action:
+        - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
+    """
+
+    def __init__(
+        self,
+    ):
+        self.agent_delegate = None
+
+    def check_condition(self, action_str: str) -> bool:
+        self.agent_delegate = re.search(
+            r'<execute_browse>(.*)</execute_browse>', action_str, re.DOTALL
+        )
+        return self.agent_delegate is not None
+
+    def parse(self, action_str: str) -> Action:
+        assert (
+            self.agent_delegate is not None
+        ), 'self.agent_delegate should not be None when parse is called'
+        thought = action_str.replace(self.agent_delegate.group(0), '').strip()
+        browse_actions = self.agent_delegate.group(1).strip()
+        task = f'{thought}. I should start with: {browse_actions}'
+        return AgentDelegateAction(agent='BrowsingAgent', inputs={'task': task})
+
+
+class CodeActActionParserMessage(ActionParser):
+    """
+    Parser action:
+        - MessageAction(content) - Message action to run (e.g. ask for clarification)
+    """
+
+    def __init__(
+        self,
+    ):
+        pass
+
+    def check_condition(self, action_str: str) -> bool:
+        # We assume the LLM is GOOD enough that when it returns pure natural language
+        # it wants to talk to the user
+        return True
+
+    def parse(self, action_str: str) -> Action:
+        return MessageAction(content=action_str, wait_for_response=True)

agenthub/codeact_agent/codeact_agent.py

@@ -1,58 +1,170 @@
-import re
-from typing import List, Mapping
-
-
-from opendevin.agent import Agent
-from opendevin.state import State
-from opendevin.action import (
+from agenthub.codeact_agent.action_parser import CodeActResponseParser
+from agenthub.codeact_agent.prompt import (
+    COMMAND_DOCS,
+    EXAMPLES,
+    GITHUB_MESSAGE,
+    SYSTEM_PREFIX,
+    SYSTEM_SUFFIX,
+)
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.events.action import (
     Action,
-    CmdRunAction,
-    AgentEchoAction,
     AgentFinishAction,
+    BrowseInteractiveAction,
+    CmdRunAction,
+    IPythonRunCellAction,
+    MessageAction,
 )
-from opendevin.observation import (
+from opendevin.events.observation import (
+    AgentDelegateObservation,
+    BrowserOutputObservation,
     CmdOutputObservation,
-    AgentMessageObservation,
+    IPythonRunCellObservation,
 )
-
 from opendevin.llm.llm import LLM
-
-SYSTEM_MESSAGE = """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>
-
-When you are done, execute "exit" to close the shell and end the conversation.
-"""
-
-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>."
+from opendevin.runtime.plugins import (
+    AgentSkillsRequirement,
+    JupyterRequirement,
+    PluginRequirement,
 )
+from opendevin.runtime.tools import RuntimeTool
+
+ENABLE_GITHUB = True
 
 
-def parse_response(response) -> str:
-    action = response.choices[0].message.content
-    if "<execute>" in action and "</execute>" not in action:
-        action += "</execute>"
-    return action
+def action_to_str(action: Action) -> str:
+    if isinstance(action, CmdRunAction):
+        return f'{action.thought}\n<execute_bash>\n{action.command}\n</execute_bash>'
+    elif isinstance(action, IPythonRunCellAction):
+        return f'{action.thought}\n<execute_ipython>\n{action.code}\n</execute_ipython>'
+    elif isinstance(action, BrowseInteractiveAction):
+        return f'{action.thought}\n<execute_browse>\n{action.browser_actions}\n</execute_browse>'
+    elif isinstance(action, MessageAction):
+        return action.content
+    return ''
+
+
+def get_action_message(action: Action) -> dict[str, str] | None:
+    if (
+        isinstance(action, BrowseInteractiveAction)
+        or isinstance(action, CmdRunAction)
+        or isinstance(action, IPythonRunCellAction)
+        or isinstance(action, MessageAction)
+    ):
+        return {
+            'role': 'user' if action.source == 'user' else 'assistant',
+            'content': action_to_str(action),
+        }
+    return None
+
+
+def get_observation_message(obs) -> dict[str, str] | None:
+    if isinstance(obs, CmdOutputObservation):
+        content = 'OBSERVATION:\n' + truncate_observation(obs.content)
+        content += (
+            f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]]'
+        )
+        return {'role': 'user', 'content': content}
+    elif isinstance(obs, IPythonRunCellObservation):
+        content = 'OBSERVATION:\n' + obs.content
+        # replace base64 images with a placeholder
+        splitted = content.split('\n')
+        for i, line in enumerate(splitted):
+            if '![image](data:image/png;base64,' in line:
+                splitted[i] = (
+                    '![image](data:image/png;base64, ...) already displayed to user'
+                )
+        content = '\n'.join(splitted)
+        content = truncate_observation(content)
+        return {'role': 'user', 'content': content}
+    elif isinstance(obs, BrowserOutputObservation):
+        content = 'OBSERVATION:\n' + truncate_observation(obs.content)
+        return {'role': 'user', 'content': content}
+    elif isinstance(obs, AgentDelegateObservation):
+        content = 'OBSERVATION:\n' + truncate_observation(str(obs.outputs))
+        return {'role': 'user', 'content': content}
+    return None
+
+
+def truncate_observation(observation: str, max_chars: int = 10_000) -> str:
+    """
+    Truncate the middle of the observation if it is too long.
+    """
+    if len(observation) <= max_chars:
+        return observation
+    half = max_chars // 2
+    return (
+        observation[:half]
+        + '\n[... Observation truncated due to length ...]\n'
+        + observation[-half:]
+    )
+
+
+# FIXME: We can tweak these two settings to create MicroAgents specialized toward different area
+def get_system_message() -> str:
+    if ENABLE_GITHUB:
+        return f'{SYSTEM_PREFIX}\n{GITHUB_MESSAGE}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
+    else:
+        return f'{SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
+
+
+def get_in_context_example() -> str:
+    return EXAMPLES
 
 
 class CodeActAgent(Agent):
+    VERSION = '1.6'
+    """
+    The Code Act Agent is a minimalist agent.
+    The agent works by passing the model a list of action-observation pairs and prompting the model to take the next step.
+
+    ### Overview
+
+    This agent implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.13463), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a unified **code** action space for both *simplicity* and *performance* (see paper for more details).
+
+    The conceptual idea is illustrated below. At each turn, the agent can:
+
+    1. **Converse**: Communicate with humans in natural language to ask for clarification, confirmation, etc.
+    2. **CodeAct**: Choose to perform the task by executing code
+    - Execute any valid Linux `bash` command
+    - Execute any valid `Python` code with [an interactive Python interpreter](https://ipython.org/). This is simulated through `bash` command, see plugin system below for more details.
+
+    ![image](https://github.com/OpenDevin/OpenDevin/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
+
+    ### Plugin System
+
+    To make the CodeAct agent more powerful with only access to `bash` action space, CodeAct agent leverages OpenDevin's plugin system:
+    - [Jupyter plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/jupyter): for IPython execution via bash command
+    - [SWE-agent tool plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/swe_agent_commands): Powerful bash command line tools for software development tasks introduced by [swe-agent](https://github.com/princeton-nlp/swe-agent).
+
+    ### Demo
+
+    https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
+
+    *Example of CodeActAgent with `gpt-4-turbo-2024-04-09` performing a data science task (linear regression)*
+
+    ### Work-in-progress & Next step
+
+    [] Support web-browsing
+    [] Complete the workflow for CodeAct agent to submit Github PRs
+
+    """
+
+    sandbox_plugins: list[PluginRequirement] = [
+        # NOTE: AgentSkillsRequirement need to go before JupyterRequirement, since
+        # AgentSkillsRequirement provides a lot of Python functions
+        # and it need to be initialized before Jupyter for Jupyter to use those functions.
+        AgentSkillsRequirement(),
+        JupyterRequirement(),
+    ]
+    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
+
+    system_message: str = get_system_message()
+    in_context_example: str = f"Here is an example of how you can interact with the environment for task solving:\n{get_in_context_example()}\n\nNOW, LET'S START!"
+
+    action_parser = CodeActResponseParser()
+
     def __init__(
         self,
         llm: LLM,
@@ -61,59 +173,67 @@ class CodeActAgent(Agent):
         Initializes a new instance of the CodeActAgent class.
 
         Parameters:
-        - instruction (str): The instruction for the agent to execute.
-        - max_steps (int): The maximum number of steps to run the agent.
+        - llm (LLM): The llm to be used by this agent
         """
         super().__init__(llm)
-        self.messages: List[Mapping[str, str]] = []
+        self.reset()
+
+    def reset(self) -> None:
+        """
+        Resets the CodeAct Agent.
+        """
+        super().reset()
 
     def step(self, state: State) -> Action:
-        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,
-            seed=42,
-        )
-        action_str: str = parse_response(response)
-        self.messages.append({"role": "assistant", "content": action_str})
+        """
+        Performs one step using the CodeAct Agent.
+        This includes gathering info on previous steps and prompting the model to make a command to execute.
 
-        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":
+        Parameters:
+        - state (State): used to get updated info and background commands
+
+        Returns:
+        - CmdRunAction(command) - bash command to run
+        - IPythonRunCellAction(code) - IPython code to run
+        - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
+        - MessageAction(content) - Message action to run (e.g. ask for clarification)
+        - AgentFinishAction() - end the interaction
+        """
+        messages: list[dict[str, str]] = [
+            {'role': 'system', 'content': self.system_message},
+            {'role': 'user', 'content': self.in_context_example},
+        ]
+
+        for prev_action, obs in state.history:
+            action_message = get_action_message(prev_action)
+            if action_message:
+                messages.append(action_message)
+
+            obs_message = get_observation_message(obs)
+            if obs_message:
+                messages.append(obs_message)
+
+        latest_user_message = [m for m in messages if m['role'] == 'user'][-1]
+        if latest_user_message:
+            if latest_user_message['content'].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
+            latest_user_message['content'] += (
+                f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task.'
+            )
 
+        response = self.llm.do_completion(
+            messages=messages,
+            stop=[
+                '</execute_ipython>',
+                '</execute_bash>',
+                '</execute_browse>',
+            ],
+            temperature=0.0,
+        )
+        state.num_of_chars += sum(
+            len(message['content']) for message in messages
+        ) + len(response.choices[0].message.content)
+        return self.action_parser.parse(response)
 
-    def search_memory(self, query: str) -> List[str]:
-        raise NotImplementedError("Implement this abstract method")
-
+    def search_memory(self, query: str) -> list[str]:
+        raise NotImplementedError('Implement this abstract method')

agenthub/codeact_agent/prompt.py

@@ -0,0 +1,255 @@
+from opendevin.runtime.plugins import AgentSkillsRequirement
+
+_AGENT_SKILLS_DOCS = AgentSkillsRequirement.documentation
+
+COMMAND_DOCS = (
+    '\nApart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:\n'
+    f'{_AGENT_SKILLS_DOCS}'
+    "Please note that THE `edit_file` and `append_file` FUNCTIONS REQUIRE PROPER INDENTATION. If the assistant would like to add the line '        print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run."
+)
+
+# ======= SYSTEM MESSAGE =======
+MINIMAL_SYSTEM_PREFIX = """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
+The assistant can use an interactive Python (Jupyter Notebook) environment, executing code with <execute_ipython>.
+<execute_ipython>
+print("Hello World!")
+</execute_ipython>
+The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
+
+For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
+Important, however: do not run interactive commands. You do not have access to stdin.
+Also, you need to handle commands that may run indefinitely and not return a result. For such cases, you should redirect the output to a file and run the command in the background to avoid blocking the execution.
+For example, to run a Python script that might run indefinitely without returning immediately, you can use the following format: <execute_bash> python3 app.py > server.log 2>&1 & </execute_bash>
+Also, if a command execution result saying like: Command: "npm start" timed out. Sending SIGINT to the process, you should also retry with running the command in the background.
+"""
+
+BROWSING_PREFIX = """The assistant can browse the Internet with <execute_browse> and </execute_browse>.
+For example, <execute_browse> Tell me the usa's president using google search </execute_browse>.
+Or <execute_browse> Tell me what is in http://example.com </execute_browse>.
+"""
+PIP_INSTALL_PREFIX = """The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them."""
+
+SYSTEM_PREFIX = MINIMAL_SYSTEM_PREFIX + BROWSING_PREFIX + PIP_INSTALL_PREFIX
+
+GITHUB_MESSAGE = """To interact with GitHub, use the $GITHUB_TOKEN environment variable.
+For example, to push a branch `my_branch` to the GitHub repo `owner/repo`:
+<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
+If $GITHUB_TOKEN is not set, ask the user to set it."""
+
+SYSTEM_SUFFIX = """Responses should be concise.
+The assistant should attempt fewer things at a time instead of putting too much commands OR code in one "execute" block.
+Include ONLY ONE <execute_ipython>, <execute_bash>, or <execute_browse> per response, unless the assistant is finished with the task or need more input or action from the user in order to proceed.
+IMPORTANT: Execute code using <execute_ipython>, <execute_bash>, or <execute_browse> whenever possible.
+"""
+
+
+# ======= EXAMPLE MESSAGE =======
+EXAMPLES = """
+--- START OF EXAMPLE ---
+
+USER: Create a list of numbers from 1 to 10, and display them in a web page at port 5000.
+
+ASSISTANT:
+Sure! Let me create a Python file `app.py`:
+<execute_ipython>
+create_file('app.py')
+</execute_ipython>
+
+USER:
+OBSERVATION:
+[File: /workspace/app.py (1 lines total)]
+1|
+[File app.py created.]
+
+ASSISTANT:
+Now I will write the Python code for starting a web server and save it to the file `app.py`:
+<execute_ipython>
+EDITED_CODE=\"\"\"from flask import Flask
+app = Flask(__name__)
+
+@app.route('/')
+def index():
+    numbers = list(range(1, 11))
+    return str(numbers)
+
+if __name__ == '__main__':
+    app.run(port=5000)\"\"\"
+edit_file('app.py', start=1, end=1, content=EDITED_CODE)
+</execute_ipython>
+
+USER:
+OBSERVATION:
+1|from flask import Flask
+2|app = Flask(__name__)
+3|
+4|@app.route('/')
+5|def index():
+6|    numbers = list(range(1, 11))
+7|    return str(numbers)
+8|
+9|if __name__ == '__main__':
+10|    app.run(port=5000)
+[File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
+
+ASSISTANT:
+I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you:
+<execute_bash>
+python3 app.py > server.log 2>&1 &
+</execute_bash>
+
+USER:
+OBSERVATION:
+[1] 121[1]+  Exit 1                  python3 app.py > server.log 2>&1
+
+ASSISTANT: Looks like the server is running with PID 121 then crashed. Let me check the server log:
+<execute_bash>
+cat server.log
+</execute_bash>
+
+USER:
+OBSERVATION:
+Traceback (most recent call last):
+  File "/workspace/app.py", line 2, in <module>
+    from flask import Flask
+ModuleNotFoundError: No module named 'flask'
+
+ASSISTANT:
+It seems that Flask is not installed. Let me install Flask for you:
+<execute_bash>
+pip install flask
+</execute_bash>
+
+USER:
+OBSERVATION:
+Defaulting to user installation because normal site-packages is not writeable
+Collecting flask
+  Using cached flask-3.0.3-py3-none-any.whl (101 kB)
+Collecting blinker>=1.6.2
+  Using cached blinker-1.7.0-py3-none-any.whl (13 kB)
+Collecting Werkzeug>=3.0.0
+  Using cached werkzeug-3.0.2-py3-none-any.whl (226 kB)
+Collecting click>=8.1.3
+  Using cached click-8.1.7-py3-none-any.whl (97 kB)
+Collecting itsdangerous>=2.1.2
+  Using cached itsdangerous-2.2.0-py3-none-any.whl (16 kB)
+Requirement already satisfied: Jinja2>=3.1.2 in /home/opendevin/.local/lib/python3.10/site-packages (from flask) (3.1.3)
+Requirement already satisfied: MarkupSafe>=2.0 in /home/opendevin/.local/lib/python3.10/site-packages (from Jinja2>=3.1.2->flask) (2.1.5)
+Installing collected packages: Werkzeug, itsdangerous, click, blinker, flask
+Successfully installed Werkzeug-3.0.2 blinker-1.7.0 click-8.1.7 flask-3.0.3 itsdangerous-2.2.0
+
+ASSISTANT:
+Now that Flask is installed, let me run the Python file again:
+<execute_bash>
+python3 app.py > server.log 2>&1 &
+</execute_bash>
+
+USER:
+OBSERVATION:
+[1] 124
+
+ASSISTANT:
+Let me check the server log again:
+<execute_bash>
+cat server.log
+</execute_bash>
+
+USER:
+OBSERVATION:
+* Serving Flask app 'app'
+ * Debug mode: off
+WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
+ * Running on http://127.0.0.1:5000
+Press CTRL+C to quit
+
+ASSISTANT:
+The server is running on port 5000 with PID 124. You can access the list of numbers by visiting http://127.0.0.1:5000. If you have any further questions, feel free to ask!
+
+USER: Now browse the newly started server's homepage and show me the content.
+
+ASSISTANT:
+Sure! Let me browse the server's homepage at http://127.0.0.1:5000:
+<execute_browse>
+Get the content on "http://127.0.0.1:5000"
+</execute_browse>
+
+USER:
+OBSERVATION:
+[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
+
+ASSISTANT:
+The content of the server's homepage is "[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]". If you have any further questions, feel free to ask!
+
+USER: Now kill the server, make it display the numbers in a table format.
+
+ASSISTANT:
+Sure! Let me stop the server first:
+<execute_bash>
+kill 124
+</execute_bash>
+
+USER:
+OBSERVATION:
+[1]+  Terminated              python3 app.py > server.log 2>&1
+
+ASSISTANT:
+The server has been stopped. Let me open the Python file and modify it.
+<execute_ipython>
+open_file('app.py')
+</execute_ipython>
+
+USER:
+[File: /workspace/app.py (10 lines total)]
+1|from flask import Flask
+2|app = Flask(__name__)
+3|
+4|@app.route('/')
+5|def index():
+6|    numbers = list(range(1, 11))
+7|    return str(numbers)
+8|
+9|if __name__ == '__main__':
+10|    app.run(port=5000)
+
+ASSISTANT:
+I should edit the file to display the numbers in a table format. I should include correct indentation. Let me update the file:
+<execute_ipython>
+edit_file('app.py', start=7, end=7, content="    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'")
+</execute_ipython>
+
+USER:
+Observation:
+[File: /workspace/app.py (10 lines total after edit)]
+1|from flask import Flask
+2|app = Flask(__name__)
+3|
+4|@app.route('/')
+5|def index():
+6|    numbers = list(range(1, 11))
+7|    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
+8|
+9|if __name__ == '__main__':
+10|    app.run(port=5000)
+[File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
+
+ASSISTANT:
+Running the updated file:
+<execute_bash>
+python3 app.py > server.log 2>&1 &
+</execute_bash>
+
+USER:
+Observation:
+[1] 126
+
+ASSISTANT:
+The server is running on port 5000 with PID 126. You can access the list of numbers in a table format by visiting http://127.0.0.1:5000. Let me know if you have any further requests!
+
+--- END OF EXAMPLE ---
+"""
+
+INVALID_INPUT_MESSAGE = (
+    "I don't understand your input. \n"
+    'For bash commands, use <execute_bash> YOUR_COMMAND </execute_bash>.\n'
+    'For Python code, use <execute_ipython> YOUR_CODE </execute_ipython>.\n'
+    'For browsing, use <execute_browse> YOUR_COMMAND </execute_browse>.\n'
+)

agenthub/codeact_swe_agent/README.md

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

agenthub/codeact_swe_agent/__init__.py

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

agenthub/codeact_swe_agent/codeact_swe_agent.py

@@ -0,0 +1,248 @@
+import re
+
+from agenthub.codeact_swe_agent.prompt import (
+    COMMAND_DOCS,
+    MINIMAL_SYSTEM_PREFIX,
+    SWE_EXAMPLE,
+    SYSTEM_SUFFIX,
+)
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.events.action import (
+    Action,
+    AgentFinishAction,
+    BrowseInteractiveAction,
+    CmdRunAction,
+    IPythonRunCellAction,
+    MessageAction,
+)
+from opendevin.events.observation import (
+    BrowserOutputObservation,
+    CmdOutputObservation,
+    IPythonRunCellObservation,
+)
+from opendevin.llm.llm import LLM
+from opendevin.runtime.plugins import (
+    AgentSkillsRequirement,
+    JupyterRequirement,
+    PluginRequirement,
+)
+from opendevin.runtime.tools import RuntimeTool
+
+
+def parse_response(response) -> str:
+    action = response.choices[0].message.content
+    for lang in ['bash', 'ipython', 'browse']:
+        if f'<execute_{lang}>' in action and f'</execute_{lang}>' not in action:
+            action += f'</execute_{lang}>'
+    return action
+
+
+def action_to_str(action: Action) -> str:
+    if isinstance(action, CmdRunAction):
+        return f'{action.thought}\n<execute_bash>\n{action.command}\n</execute_bash>'
+    elif isinstance(action, IPythonRunCellAction):
+        return f'{action.thought}\n<execute_ipython>\n{action.code}\n</execute_ipython>'
+    elif isinstance(action, BrowseInteractiveAction):
+        return f'{action.thought}\n<execute_browse>\n{action.browser_actions}\n</execute_browse>'
+    elif isinstance(action, MessageAction):
+        return action.content
+    return ''
+
+
+def get_action_message(action: Action) -> dict[str, str] | None:
+    if (
+        isinstance(action, BrowseInteractiveAction)
+        or isinstance(action, CmdRunAction)
+        or isinstance(action, IPythonRunCellAction)
+        or isinstance(action, MessageAction)
+    ):
+        return {
+            'role': 'user' if action.source == 'user' else 'assistant',
+            'content': action_to_str(action),
+        }
+    return None
+
+
+def get_observation_message(obs) -> dict[str, str] | None:
+    if isinstance(obs, CmdOutputObservation):
+        content = 'OBSERVATION:\n' + truncate_observation(obs.content)
+        content += (
+            f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]]'
+        )
+        return {'role': 'user', 'content': content}
+    elif isinstance(obs, IPythonRunCellObservation):
+        content = 'OBSERVATION:\n' + obs.content
+        # replace base64 images with a placeholder
+        splitted = content.split('\n')
+        for i, line in enumerate(splitted):
+            if '![image](data:image/png;base64,' in line:
+                splitted[i] = (
+                    '![image](data:image/png;base64, ...) already displayed to user'
+                )
+        content = '\n'.join(splitted)
+        content = truncate_observation(content)
+        return {'role': 'user', 'content': content}
+    elif isinstance(obs, BrowserOutputObservation):
+        content = 'OBSERVATION:\n' + truncate_observation(obs.content)
+        return {'role': 'user', 'content': content}
+    return None
+
+
+def truncate_observation(observation: str, max_chars: int = 10_000) -> str:
+    """
+    Truncate the middle of the observation if it is too long.
+    """
+    if len(observation) <= max_chars:
+        return observation
+    half = max_chars // 2
+    return (
+        observation[:half]
+        + '\n[... Observation truncated due to length ...]\n'
+        + observation[-half:]
+    )
+
+
+def get_system_message() -> str:
+    return f'{MINIMAL_SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
+
+
+def get_in_context_example() -> str:
+    return SWE_EXAMPLE
+
+
+class CodeActSWEAgent(Agent):
+    VERSION = '1.5'
+    """
+    This agent is an adaptation of the original [SWE Agent](https://swe-agent.com/) based on CodeAct 1.5 using the `agentskills` library of OpenDevin.
+
+    It is intended use is **solving Github issues**.
+
+    It removes web-browsing and Github capability from the original CodeAct agent to avoid confusion to the agent.
+    """
+
+    sandbox_plugins: list[PluginRequirement] = [
+        # NOTE: AgentSkillsRequirement need to go before JupyterRequirement, since
+        # AgentSkillsRequirement provides a lot of Python functions
+        # and it need to be initialized before Jupyter for Jupyter to use those functions.
+        AgentSkillsRequirement(),
+        JupyterRequirement(),
+    ]
+    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
+    jupyter_kernel_init_code: str = 'from agentskills import *'
+
+    system_message: str = get_system_message()
+    in_context_example: str = f"Here is an example of how you can interact with the environment for task solving:\n{get_in_context_example()}\n\nNOW, LET'S START!"
+
+    def __init__(
+        self,
+        llm: LLM,
+    ) -> None:
+        """
+        Initializes a new instance of the CodeActAgent class.
+
+        Parameters:
+        - llm (LLM): The llm to be used by this agent
+        """
+        super().__init__(llm)
+        self.reset()
+
+    def reset(self) -> None:
+        """
+        Resets the CodeAct Agent.
+        """
+        super().reset()
+
+    def step(self, state: State) -> Action:
+        """
+        Performs one step using the CodeAct Agent.
+        This includes gathering info on previous steps and prompting the model to make a command to execute.
+
+        Parameters:
+        - state (State): used to get updated info and background commands
+
+        Returns:
+        - CmdRunAction(command) - bash command to run
+        - IPythonRunCellAction(code) - IPython code to run
+        - BrowseInteractiveAction(browsergym_command) - BrowserGym commands to run
+        - MessageAction(content) - Message action to run (e.g. ask for clarification)
+        - AgentFinishAction() - end the interaction
+        """
+        messages: list[dict[str, str]] = [
+            {'role': 'system', 'content': self.system_message},
+            {'role': 'user', 'content': self.in_context_example},
+        ]
+
+        for prev_action, obs in state.history:
+            action_message = get_action_message(prev_action)
+            if action_message:
+                messages.append(action_message)
+
+            obs_message = get_observation_message(obs)
+            if obs_message:
+                messages.append(obs_message)
+
+        latest_user_message = [m for m in messages if m['role'] == 'user'][-1]
+        if latest_user_message:
+            if latest_user_message['content'].strip() == '/exit':
+                return AgentFinishAction()
+            latest_user_message['content'] += (
+                f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task.'
+            )
+
+        response = self.llm.do_completion(
+            messages=messages,
+            stop=[
+                '</execute_ipython>',
+                '</execute_bash>',
+                '</execute_browse>',
+            ],
+            temperature=0.0,
+        )
+
+        action_str: str = parse_response(response)
+        state.num_of_chars += sum(
+            len(message['content']) for message in messages
+        ) + len(action_str)
+
+        if finish_command := re.search(r'<finish>.*</finish>', action_str, re.DOTALL):
+            thought = action_str.replace(finish_command.group(0), '').strip()
+            return AgentFinishAction(thought=thought)
+        if bash_command := re.search(
+            r'<execute_bash>(.*?)</execute_bash>', action_str, re.DOTALL
+        ):
+            # remove the command from the action string to get thought
+            thought = action_str.replace(bash_command.group(0), '').strip()
+            # a command was found
+            command_group = bash_command.group(1).strip()
+
+            if command_group.strip() == 'exit':
+                return AgentFinishAction()
+            return CmdRunAction(command=command_group, thought=thought)
+        elif python_code := re.search(
+            r'<execute_ipython>(.*?)</execute_ipython>', action_str, re.DOTALL
+        ):
+            # a code block was found
+            code_group = python_code.group(1).strip()
+            thought = action_str.replace(python_code.group(0), '').strip()
+            return IPythonRunCellAction(
+                code=code_group,
+                thought=thought,
+                kernel_init_code=self.jupyter_kernel_init_code,
+            )
+        elif browse_command := re.search(
+            r'<execute_browse>(.*)</execute_browse>', action_str, re.DOTALL
+        ):
+            # BrowserGym actions was found
+            browse_actions = browse_command.group(1).strip()
+            thought = action_str.replace(browse_command.group(0), '').strip()
+            return BrowseInteractiveAction(
+                browser_actions=browse_actions, thought=thought
+            )
+        else:
+            # We assume the LLM is GOOD enough that when it returns pure natural language
+            # it want to talk to the user
+            return MessageAction(content=action_str, wait_for_response=True)
+
+    def search_memory(self, query: str) -> list[str]:
+        raise NotImplementedError('Implement this abstract method')

agenthub/codeact_swe_agent/prompt.py

@@ -0,0 +1,451 @@
+from opendevin.runtime.plugins import AgentSkillsRequirement
+
+_AGENT_SKILLS_DOCS = AgentSkillsRequirement.documentation
+
+COMMAND_DOCS = (
+    '\nApart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:\n'
+    f'{_AGENT_SKILLS_DOCS}'
+    "Please note that THE `edit_file` FUNCTION REQUIRES PROPER INDENTATION. If the assistant would like to add the line '        print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run."
+)
+
+# ======= SYSTEM MESSAGE =======
+MINIMAL_SYSTEM_PREFIX = """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
+The assistant can interact with an interactive Python (Jupyter Notebook) environment and receive the corresponding output when needed. The code should be enclosed using "<execute_ipython>" tag, for example:
+<execute_ipython>
+print("Hello World!")
+</execute_ipython>
+The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
+For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
+"""
+
+SYSTEM_SUFFIX = """The assistant's response should be concise.
+The assistant should include ONLY ONE <execute_ipython> or <execute_bash> or <execute_browse> in every one of the responses, unless the assistant is finished with the task or need more input or action from the user in order to proceed.
+IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> or <execute_browse> instead of providing it.
+"""
+
+SWE_EXAMPLE = """
+--- START OF EXAMPLE ---
+
+USER: We are currently solving the following issue within our repository. Here is the issue text:
+--- BEGIN ISSUE ---
+TimeDelta serialization precision
+Hi there!
+
+I just found quite strange behaviour of `TimeDelta` field serialization
+
+```python3
+from marshmallow.fields import TimeDelta
+from datetime import timedelta
+
+td_field = TimeDelta(precision="milliseconds")
+
+obj = dict()
+obj["td_field"] = timedelta(milliseconds=345)
+
+print(td_field.serialize("td_field", obj))
+```
+
+Output of this snippet is `344`, but it seems that `345` is correct.
+
+Looks like a rounding issue here: https://github.com/marshmallow-code/marshmallow/blob/dev/src/marshmallow/fields.py#L1474
+--- END ISSUE ---
+
+[Current directory: /workspace/marshmallow-code__marshmallow]
+
+ASSISTANT:
+Let's first start by reproducing the results of the issue. The issue includes some example code for reproduction, which we can use. We'll create a new file called `reproduce.py` and paste the example code into it.
+<execute_ipython>
+create_file('/workspace/marshmallow-code__marshmallow/reproduce.py')
+</execute_ipython>
+
+USER:
+OBSERVATION:
+[File: /workspace/marshmallow-code__marshmallow/reproduce.py (1 lines total)]
+1|
+[File /workspace/marshmallow-code__marshmallow/reproduce.py created.]
+
+ASSISTANT:
+Now let's paste in the example code from the issue.
+<execute_ipython>
+EDITED_CODE = \"\"\"from marshmallow.fields import TimeDelta
+from datetime import timedelta
+
+td_field = TimeDelta(precision="milliseconds")
+
+obj = dict()
+obj["td_field"] = timedelta(milliseconds=345)
+
+print(td_field.serialize("td_field", obj))
+\"\"\"
+edit_file(start=1, end=1, content=EDITED_CODE)
+</execute_ipython>
+
+USER:
+OBSERVATION:
+[File: /workspace/marshmallow-code__marshmallow/reproduce.py (9 lines total)]
+1|from marshmallow.fields import TimeDelta
+2|from datetime import timedelta
+3|
+4|td_field = TimeDelta(precision="milliseconds")
+5|
+6|obj = dict()
+7|obj["td_field"] = timedelta(milliseconds=345)
+8|
+9|print(td_field.serialize("td_field", obj))
+[File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
+
+ASSISTANT:
+Now let's run the code to see if we see the same output as the issue.
+<execute_bash>
+python reproduce.py
+</execute_bash>
+
+USER:
+OBSERVATION:
+344
+
+ASSISTANT:
+We are indeed seeing the same output as the issue. The issue suggests that we should look at line 1474 of the `fields.py` file to see if there is a rounding issue. Let's open the `fields.py` file and navigate to line 1474 to see the relevant code. First we should find the `fields.py` file in the repository. It is likely to be in the `src/marshmallow` directory, but we should check to be sure.
+<execute_bash>
+ls -F
+</execute_bash>
+
+USER:
+OBSERVATION:
+AUTHORS.rst
+CHANGELOG.rst
+CODE_OF_CONDUCT.md
+CONTRIBUTING.rst
+LICENSE
+MANIFEST.in
+NOTICE
+README.rst
+RELEASING.md
+azure-pipelines.yml
+docs/
+examples/
+performance/
+pyproject.toml
+reproduce.py
+setup.cfg
+setup.py
+src/
+tests/
+tox.ini
+
+ASSISTANT:
+It looks like the `src` directory is present, which suggests that the `fields.py` file is likely to be in the `src` directory. Let's use find_file to see where it is.
+<execute_ipython>
+find_file("fields.py", "/workspace/marshmallow-code__marshmallow/src")
+</execute_ipython>
+
+USER:
+OBSERVATION:
+[Found 1 matches for "fields.py" in /workspace/marshmallow-code__marshmallow/src]
+/workspace/marshmallow-code__marshmallow/src/marshmallow/fields.py
+
+ASSISTANT:
+It looks like the `fields.py` file is present in the `./src/marshmallow/` directory. The issue also points to a specific URL with line number 1474. We should navigate to that line in fields.py to see the relevant code for the `TimeDelta` serialization.
+<execute_ipython>
+open_file("/workspace/marshmallow-code__marshmallow/src/marshmallow/fields.py", 1474)
+</execute_ipython>
+
+USER:
+OBSERVATION:
+[File: /workspace/marshmallow-code__marshmallow/src/marshmallow/fields.py (1997 lines total)]
+(1458 more lines above)
+1459|            self.WEEKS,
+1460|        )
+1461|
+1462|        if precision not in units:
+1463|            msg = 'The precision must be {} or "{}".'.format(
+1464|                ", ".join([f'"{each}"' for each in units[:-1]]), units[-1]
+1465|            )
+1466|            raise ValueError(msg)
+1467|
+1468|        self.precision = precision
+1469|        super().__init__(**kwargs)
+1470|
+1471|    def _serialize(self, value, attr, obj, **kwargs):
+1472|        if value is None:
+1473|            return None
+1474|        base_unit = dt.timedelta(**{self.precision: 1})
+1475|        return int(value.total_seconds() / base_unit.total_seconds())
+1476|
+1477|    def _deserialize(self, value, attr, data, **kwargs):
+1478|        try:
+1479|            value = int(value)
+1480|        except (TypeError, ValueError) as error:
+1481|            raise self.make_error("invalid") from error
+1482|
+1483|        kwargs = {self.precision: value}
+1484|
+1485|        try:
+1486|            return dt.timedelta(**kwargs)
+1487|        except OverflowError as error:
+1488|            raise self.make_error("invalid") from error
+1489|
+1490|
+1491|class Mapping(Field):
+1492|    \"\"\"An abstract class for objects with key-value pairs.
+1493|
+1494|    :param keys: A field class or instance for dict keys.
+1495|    :param values: A field class or instance for dict values.
+1496|    :param kwargs: The same keyword arguments that :class:`Field` receives.
+1497|
+1498|    .. note::
+1499|        When the structure of nested data is not known, you may omit the
+1500|        `keys` and `values` arguments to prevent content validation.
+1501|
+1502|    .. versionadded:: 3.0.0rc4
+1503|    \"\"\"
+1504|
+1505|    mapping_type = dict
+1506|
+1507|    #: Default error messages.
+1508|    default_error_messages = {"invalid": "Not a valid mapping type."}
+1509|
+1510|    def __init__(
+1511|        self,
+1512|        keys: typing.Optional[typing.Union[Field, type]] = None,
+1513|        values: typing.Optional[typing.Union[Field, type]] = None,
+1514|        **kwargs,
+1515|    ):
+1516|        super().__init__(**kwargs)
+1517|        if keys is None:
+1518|            self.key_field = None
+1519|        else:
+1520|            try:
+1521|                self.key_field = resolve_field_instance(keys)
+1522|            except FieldInstanceResolutionError as error:
+1523|                raise ValueError(
+1524|                    '"keys" must be a subclass or instance of '
+1525|                    "marshmallow.base.FieldABC."
+1526|                ) from error
+1527|
+1528|        if values is None:
+1529|            self.value_field = None
+1530|        else:
+1531|            try:
+1532|                self.value_field = resolve_field_instance(values)
+1533|            except FieldInstanceResolutionError as error:
+1534|                raise ValueError(
+1535|                    '"values" must be a subclass or instance of '
+1536|                    "marshmallow.base.FieldABC."
+1537|                ) from error
+1538|            if isinstance(self.value_field, Nested):
+1539|                self.only = self.value_field.only
+1540|                self.exclude = self.value_field.exclude
+1541|
+1542|    def _bind_to_schema(self, field_name, schema):
+1543|        super()._bind_to_schema(field_name, schema)
+1544|        if self.value_field:
+1545|            self.value_field = copy.deepcopy(self.value_field)
+1546|            self.value_field._bind_to_schema(field_name, self)
+1547|        if isinstance(self.value_field, Nested):
+1548|            self.value_field.only = self.only
+1549|            self.value_field.exclude = self.exclude
+1550|        if self.key_field:
+1551|            self.key_field = copy.deepcopy(self.key_field)
+1552|            self.key_field._bind_to_schema(field_name, self)
+1553|
+1554|    def _serialize(self, value, attr, obj, **kwargs):
+1555|        if value is None:
+1556|            return None
+1557|        if not self.value_field and not self.key_field:
+1558|            return self.mapping_type(value)
+(439 more lines below)
+
+ASSISTANT:
+We are now looking at the relevant section of the `fields.py` file where the `TimeDelta` serialization occurs. The issue suggests that there is a rounding problem near line 1474. The current implementation uses integer division, which truncates the decimal part and can lead to incorrect rounding on line 1475. To fix this issue, we should ensure that the division results in a float, and then round the result to the nearest integer before converting it to an int. This should preserve the milliseconds precision as expected. Let's make the necessary edit to the code.
+<execute_ipython>
+edit_file(start=1475, end=1475, content="return int(round(value.total_seconds() / base_unit.total_seconds()))  # round to nearest int")
+</execute_ipython>
+
+USER:
+OBSERVATION:
+[Your proposed edit has introduced new syntax error(s). Please understand the errors and retry your edit command.]
+
+ERRORS:
+- E999 IndentationError: unexpected indent
+
+[This is how your edit would have looked if applied]
+-------------------------------------------------
+[File: /marshmallow-code__marshmallow/src/marshmallow/fields.py (1997 lines total)]
+(1468 more lines above)
+1469|        super().__init__(**kwargs)
+1470|
+1471|    def _serialize(self, value, attr, obj, **kwargs):
+1472|        if value is None:
+1473|            return None
+1474|        base_unit = dt.timedelta(**{self.precision: 1})
+1475|return int(round(value.total_seconds() / base_unit.total_seconds()))  # round to nearest int
+1476|
+1477|    def _deserialize(self, value, attr, data, **kwargs):
+1478|        try:
+1479|            value = int(value)
+(518 more lines below)
+-------------------------------------------------
+
+[This is the original code before your edit]
+-------------------------------------------------
+[File: /marshmallow-code__marshmallow/src/marshmallow/fields.py (1997 lines total)]
+(1469 more lines above)
+1470|
+1471|    def _serialize(self, value, attr, obj, **kwargs):
+1472|        if value is None:
+1473|            return None
+1474|        base_unit = dt.timedelta(**{self.precision: 1})
+1475|        return int(value.total_seconds() / base_unit.total_seconds())
+1476|
+1477|    def _deserialize(self, value, attr, data, **kwargs):
+1478|        try:
+1479|            value = int(value)
+1480|        except (TypeError, ValueError) as error:
+(517 more lines below)
+-------------------------------------------------
+Your changes have NOT been applied. Please fix your edit command and try again.
+You either need to 1) Specify the correct start/end line arguments or 2) Correct your edit code.
+DO NOT re-run the same failed edit command. Running it again will lead to the same error.
+
+ASSISTANT:
+My edit command did not use the proper indentation, I will fix my syntax in this follow up edit command.
+<execute_ipython>
+EDITED_CODE="        return int(round(value.total_seconds() / base_unit.total_seconds()))  # round to nearest int"
+edit_file(start=1475, end=1475, content=EDITED_CODE)
+</execute_ipython>
+
+USER:
+OBSERVATION:
+[File: /marshmallow-code__marshmallow/src/marshmallow/fields.py (1997 lines total)]
+(1424 more lines above)
+1425|
+1426|    :param precision: Influences how the integer is interpreted during
+1427|        (de)serialization. Must be 'days', 'seconds', 'microseconds',
+1428|        'milliseconds', 'minutes', 'hours' or 'weeks'.
+1429|    :param kwargs: The same keyword arguments that :class:`Field` receives.
+1430|
+1431|    .. versionchanged:: 2.0.0
+1432|        Always serializes to an integer value to avoid rounding errors.
+1433|        Add `precision` parameter.
+1434|    \"\"\"
+1435|
+1436|    DAYS = "days"
+1437|    SECONDS = "seconds"
+1438|    MICROSECONDS = "microseconds"
+1439|    MILLISECONDS = "milliseconds"
+1440|    MINUTES = "minutes"
+1441|    HOURS = "hours"
+1442|    WEEKS = "weeks"
+1443|
+1444|    #: Default error messages.
+1445|    default_error_messages = {
+1446|        "invalid": "Not a valid period of time.",
+1447|        "format": "{input!r} cannot be formatted as a timedelta.",
+1448|    }
+1449|
+1450|    def __init__(self, precision: str = SECONDS, **kwargs):
+1451|        precision = precision.lower()
+1452|        units = (
+1453|            self.DAYS,
+1454|            self.SECONDS,
+1455|            self.MICROSECONDS,
+1456|            self.MILLISECONDS,
+1457|            self.MINUTES,
+1458|            self.HOURS,
+1459|            self.WEEKS,
+1460|        )
+1461|
+1462|        if precision not in units:
+1463|            msg = 'The precision must be {} or "{}".'.format(
+1464|                ", ".join([f'"{each}"' for each in units[:-1]]), units[-1]
+1465|            )
+1466|            raise ValueError(msg)
+1467|
+1468|        self.precision = precision
+1469|        super().__init__(**kwargs)
+1470|
+1471|    def _serialize(self, value, attr, obj, **kwargs):
+1472|        if value is None:
+1473|            return None
+1474|        base_unit = dt.timedelta(**{self.precision: 1})
+1475|        return int(round(value.total_seconds() / base_unit.total_seconds()))  # round to nearest int
+1476|
+1477|    def _deserialize(self, value, attr, data, **kwargs):
+1478|        try:
+1479|            value = int(value)
+1480|        except (TypeError, ValueError) as error:
+1481|            raise self.make_error("invalid") from error
+1482|
+1483|        kwargs = {self.precision: value}
+1484|
+1485|        try:
+1486|            return dt.timedelta(**kwargs)
+1487|        except OverflowError as error:
+1488|            raise self.make_error("invalid") from error
+1489|
+1490|
+1491|class Mapping(Field):
+1492|    \"\"\"An abstract class for objects with key-value pairs.
+1493|
+1494|    :param keys: A field class or instance for dict keys.
+1495|    :param values: A field class or instance for dict values.
+1496|    :param kwargs: The same keyword arguments that :class:`Field` receives.
+1497|
+1498|    .. note::
+1499|        When the structure of nested data is not known, you may omit the
+1500|        `keys` and `values` arguments to prevent content validation.
+1501|
+1502|    .. versionadded:: 3.0.0rc4
+1503|    \"\"\"
+1504|
+1505|    mapping_type = dict
+1506|
+1507|    #: Default error messages.
+1508|    default_error_messages = {"invalid": "Not a valid mapping type."}
+1509|
+1510|    def __init__(
+1511|        self,
+1512|        keys: typing.Optional[typing.Union[Field, type]] = None,
+1513|        values: typing.Optional[typing.Union[Field, type]] = None,
+1514|        **kwargs,
+1515|    ):
+1516|        super().__init__(**kwargs)
+1517|        if keys is None:
+1518|            self.key_field = None
+1519|        else:
+1520|            try:
+1521|                self.key_field = resolve_field_instance(keys)
+1522|            except FieldInstanceResolutionError as error:
+1523|                raise ValueError(
+1524|                    '"keys" must be a subclass or instance of '
+(473 more lines below)
+[File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
+
+ASSISTANT:
+The code has been updated to use the `round` function, which should fix the rounding issue. Before submitting the changes, it would be prudent to run the reproduce.py code again to ensure that this change has the desired effect. I see that "Current directory" is still `/marshmallow-code__marshmallow`, so we can just run `reproduce.py` directly.
+<execute_bash>
+python reproduce.py
+</execute_bash>
+
+USER:
+OBSERVATION:
+345
+
+ASSISTANT:
+The output has changed from 344 to 345, which suggests that the rounding issue has been fixed. Let's remove the reproduce.py file since it is no longer needed.
+<execute_bash>
+rm reproduce.py
+</execute_bash>
+
+USER:
+OBSERVATION:
+
+ASSISTANT:
+rm doesn't have any output when it deletes successfully, so that must have worked. Now that we have fixed the issue, we can exit the current task.
+<execute_bash>
+exit
+</execute_bash>
+
+--- END OF EXAMPLE ---
+"""

agenthub/delegator_agent/__init__.py

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

agenthub/delegator_agent/agent.py

@@ -0,0 +1,86 @@
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.events.action import Action, AgentDelegateAction, AgentFinishAction
+from opendevin.events.observation import AgentDelegateObservation
+from opendevin.llm.llm import LLM
+
+
+class DelegatorAgent(Agent):
+    VERSION = '1.0'
+    """
+    The 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.
+    """
+
+    current_delegate: str = ''
+
+    def __init__(self, llm: LLM):
+        """
+        Initialize the Delegator Agent with an LLM
+
+        Parameters:
+        - llm (LLM): The llm to be used by this agent
+        """
+        super().__init__(llm)
+
+    def step(self, state: State) -> Action:
+        """
+        Checks to see if current step is completed, returns AgentFinishAction if True.
+        Otherwise, 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 self.current_delegate == '':
+            self.current_delegate = 'study'
+            task = state.get_current_user_intent()
+            return AgentDelegateAction(
+                agent='StudyRepoForTaskAgent', inputs={'task': task}
+            )
+
+        last_observation = state.history[-1][1]
+        if not isinstance(last_observation, AgentDelegateObservation):
+            raise Exception('Last observation is not an AgentDelegateObservation')
+
+        goal = state.get_current_user_intent()
+        if self.current_delegate == 'study':
+            self.current_delegate = 'coder'
+            return AgentDelegateAction(
+                agent='CoderAgent',
+                inputs={
+                    'task': goal,
+                    'summary': last_observation.outputs['summary'],
+                },
+            )
+        elif self.current_delegate == 'coder':
+            self.current_delegate = 'verifier'
+            return AgentDelegateAction(
+                agent='VerifierAgent',
+                inputs={
+                    'task': goal,
+                },
+            )
+        elif self.current_delegate == 'verifier':
+            if (
+                'completed' in last_observation.outputs
+                and last_observation.outputs['completed']
+            ):
+                return AgentFinishAction()
+            else:
+                self.current_delegate = 'coder'
+                return AgentDelegateAction(
+                    agent='CoderAgent',
+                    inputs={
+                        'task': goal,
+                        'summary': last_observation.outputs['summary'],
+                    },
+                )
+        else:
+            raise Exception('Invalid delegate state')
+
+    def search_memory(self, query: str) -> list[str]:
+        return []

agenthub/dummy_agent/__init__.py

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

agenthub/dummy_agent/agent.py

@@ -0,0 +1,175 @@
+import time
+from typing import TypedDict
+
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.events.action import (
+    Action,
+    AddTaskAction,
+    AgentFinishAction,
+    AgentRecallAction,
+    AgentRejectAction,
+    BrowseInteractiveAction,
+    BrowseURLAction,
+    CmdRunAction,
+    FileReadAction,
+    FileWriteAction,
+    MessageAction,
+    ModifyTaskAction,
+)
+from opendevin.events.observation import (
+    AgentRecallObservation,
+    CmdOutputObservation,
+    FileReadObservation,
+    FileWriteObservation,
+    NullObservation,
+    Observation,
+)
+from opendevin.events.serialization.event import event_to_dict
+from opendevin.llm.llm import LLM
+
+"""
+FIXME: There are a few problems this surfaced
+* FileWrites seem to add an unintended newline at the end of the file
+* command_id is sometimes a number, sometimes a string
+* Why isn't the output of the background command split between two steps?
+* Browser not working
+"""
+
+ActionObs = TypedDict(
+    'ActionObs', {'action': Action, 'observations': list[Observation]}
+)
+
+BACKGROUND_CMD = 'echo "This is in the background" && sleep .1 && echo "This too"'
+
+
+class DummyAgent(Agent):
+    VERSION = '1.0'
+    """
+    The DummyAgent is used for e2e testing. It just sends the same set of actions deterministically,
+    without making any LLM calls.
+    """
+
+    def __init__(self, llm: LLM):
+        super().__init__(llm)
+        self.steps: list[ActionObs] = [
+            {
+                'action': AddTaskAction(parent='0', goal='check the current directory'),
+                'observations': [NullObservation('')],
+            },
+            {
+                'action': AddTaskAction(parent='0.0', goal='run ls'),
+                'observations': [NullObservation('')],
+            },
+            {
+                'action': ModifyTaskAction(task_id='0.0', state='in_progress'),
+                'observations': [NullObservation('')],
+            },
+            {
+                'action': MessageAction('Time to get started!'),
+                'observations': [NullObservation('')],
+            },
+            {
+                'action': CmdRunAction(command='echo "foo"'),
+                'observations': [
+                    CmdOutputObservation('foo', command_id=-1, command='echo "foo"')
+                ],
+            },
+            {
+                'action': FileWriteAction(
+                    content='echo "Hello, World!"', path='hello.sh'
+                ),
+                'observations': [FileWriteObservation('', path='hello.sh')],
+            },
+            {
+                'action': FileReadAction(path='hello.sh'),
+                'observations': [
+                    FileReadObservation('echo "Hello, World!"\n', path='hello.sh')
+                ],
+            },
+            {
+                'action': CmdRunAction(command='bash hello.sh'),
+                'observations': [
+                    CmdOutputObservation(
+                        'Hello, World!', command_id=-1, command='bash hello.sh'
+                    )
+                ],
+            },
+            {
+                'action': CmdRunAction(command=BACKGROUND_CMD, background=True),
+                'observations': [
+                    CmdOutputObservation(
+                        'Background command started. To stop it, send a `kill` action with command_id 42',
+                        command_id='42',  # type: ignore[arg-type]
+                        command=BACKGROUND_CMD,
+                    ),
+                    CmdOutputObservation(
+                        'This is in the background\nThis too\n',
+                        command_id='42',  # type: ignore[arg-type]
+                        command=BACKGROUND_CMD,
+                    ),
+                ],
+            },
+            {
+                'action': AgentRecallAction(query='who am I?'),
+                'observations': [
+                    AgentRecallObservation('', memories=['I am a computer.']),
+                    # CmdOutputObservation('This too\n', command_id='42', command=BACKGROUND_CMD),
+                ],
+            },
+            {
+                'action': BrowseURLAction(url='https://google.com'),
+                'observations': [
+                    # BrowserOutputObservation('<html></html>', url='https://google.com', screenshot=""),
+                ],
+            },
+            {
+                'action': BrowseInteractiveAction(
+                    browser_actions='goto("https://google.com")'
+                ),
+                'observations': [
+                    # BrowserOutputObservation('<html></html>', url='https://google.com', screenshot=""),
+                ],
+            },
+            {
+                'action': AgentFinishAction(),
+                'observations': [],
+            },
+            {
+                'action': AgentRejectAction(),
+                'observations': [],
+            },
+        ]
+
+    def step(self, state: State) -> Action:
+        time.sleep(0.1)
+        if state.iteration > 0:
+            prev_step = self.steps[state.iteration - 1]
+            if 'observations' in prev_step:
+                expected_observations = prev_step['observations']
+                hist_start = len(state.history) - len(expected_observations)
+                for i in range(len(expected_observations)):
+                    hist_obs = event_to_dict(state.history[hist_start + i][1])
+                    expected_obs = event_to_dict(expected_observations[i])
+                    if (
+                        'command_id' in hist_obs['extras']
+                        and hist_obs['extras']['command_id'] != -1
+                    ):
+                        del hist_obs['extras']['command_id']
+                        hist_obs['content'] = ''
+                    if (
+                        'command_id' in expected_obs['extras']
+                        and expected_obs['extras']['command_id'] != -1
+                    ):
+                        del expected_obs['extras']['command_id']
+                        expected_obs['content'] = ''
+                    if hist_obs != expected_obs:
+                        print('\nactual', hist_obs)
+                        print('\nexpect', expected_obs)
+                    assert (
+                        hist_obs == expected_obs
+                    ), f'Expected observation {expected_obs}, got {hist_obs}'
+        return self.steps[state.iteration]['action']
+
+    def search_memory(self, query: str) -> list[str]:
+        return ['I am a computer.']

agenthub/micro/README.md

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

agenthub/micro/_instructions/actions/browse.md

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

agenthub/micro/_instructions/actions/delegate.md

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

agenthub/micro/_instructions/actions/finish.md

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

agenthub/micro/_instructions/actions/kill.md

@@ -0,0 +1,2 @@
+* `kill` - kills a background command
+  * `command_id` - the ID of the background command to kill

agenthub/micro/_instructions/actions/message.md

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

agenthub/micro/_instructions/actions/read.md

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

agenthub/micro/_instructions/actions/reject.md

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

agenthub/micro/_instructions/actions/run.md

@@ -0,0 +1,3 @@
+* `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.

agenthub/micro/_instructions/actions/write.md

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

agenthub/micro/_instructions/format/action.md

@@ -0,0 +1,5 @@
+Your response MUST be in JSON format. It must be an object, and it must contain two fields:
+* `action`, which is one of the actions specified here
+* `args`, which is a map of key-value pairs, specifying the arguments for that action
+
+You MUST NOT include any other text besides the JSON response

agenthub/micro/_instructions/history_truncated.md

@@ -0,0 +1,4 @@
+Here is a recent history of actions you've taken in service of this plan,
+as well as observations you've made. This only includes the MOST RECENT
+actions and observations--more may have happened before that.
+They are time-ordered, with your most recent action at the bottom.

agenthub/micro/agent.py

@@ -0,0 +1,74 @@
+from jinja2 import BaseLoader, Environment
+
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.core.utils import json
+from opendevin.events.action import Action
+from opendevin.events.serialization.action import action_from_dict
+from opendevin.events.serialization.event import event_to_memory
+from opendevin.llm.llm import LLM
+
+from .instructions import instructions
+from .registry import all_microagents
+
+
+def parse_response(orig_response: str) -> Action:
+    # attempt to load the JSON dict from the response
+    action_dict = json.loads(orig_response)
+
+    # load the action from the dict
+    return action_from_dict(action_dict)
+
+
+def to_json(obj, **kwargs):
+    """
+    Serialize an object to str format
+    """
+    return json.dumps(obj, **kwargs)
+
+
+def history_to_json(obj, **kwargs):
+    """
+    Serialize and simplify history to str format
+    """
+    if isinstance(obj, list):
+        # process history, make it simpler.
+        processed_history = []
+        for action, observation in obj:
+            processed_history.append(
+                (event_to_memory(action), event_to_memory(observation))
+            )
+        return json.dumps(processed_history, **kwargs)
+
+
+class MicroAgent(Agent):
+    VERSION = '1.0'
+    prompt = ''
+    agent_definition: dict = {}
+
+    def __init__(self, llm: LLM):
+        super().__init__(llm)
+        if 'name' not in self.agent_definition:
+            raise ValueError('Agent definition must contain a name')
+        self.prompt_template = Environment(loader=BaseLoader).from_string(self.prompt)
+        self.delegates = all_microagents.copy()
+        del self.delegates[self.agent_definition['name']]
+
+    def step(self, state: State) -> Action:
+        prompt = self.prompt_template.render(
+            state=state,
+            instructions=instructions,
+            to_json=to_json,
+            history_to_json=history_to_json,
+            delegates=self.delegates,
+            latest_user_message=state.get_current_user_intent(),
+        )
+        messages = [{'content': prompt, 'role': 'user'}]
+        resp = self.llm.do_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/micro/coder/agent.yaml

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

agenthub/micro/coder/prompt.md

@@ -0,0 +1,27 @@
+# Task
+You are a software engineer. You've inherited an existing codebase, which you
+need to modify to complete this task:
+
+{{ state.inputs.task }}
+
+{% if state.inputs.summary %}
+Here's a summary of the codebase, as it relates to this task:
+
+{{ state.inputs.summary }}
+{% endif %}
+
+## Available Actions
+{{ instructions.actions.run }}
+{{ instructions.actions.write }}
+{{ instructions.actions.read }}
+{{ instructions.actions.message }}
+{{ instructions.actions.finish }}
+
+Do NOT finish until you have completed the tasks.
+
+## History
+{{ instructions.history_truncated }}
+{{ history_to_json(state.history[-10:]) }}
+
+## Format
+{{ instructions.format.action }}

agenthub/micro/commit_writer/README.md

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

agenthub/micro/commit_writer/agent.yaml

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

agenthub/micro/commit_writer/prompt.md

@@ -0,0 +1,31 @@
+# Task
+You are a responsible software engineer and always write good commit messages.
+
+Please analyze the diff in the staging area, understand the context and content
+of the updates from the diff only. Identify key elements like:
+- Which files are affected?
+- What types of changes were made (e.g., new features, bug fixes, refactoring, documentation, testing)?
+
+Then you should generate a commit message that succinctly summarizes the staged
+changes. The commit message should include:
+- A summary line that clearly states the purpose of the changes.
+- Optionally, a detailed description if the changes are complex or need further explanation.
+
+You should find the diff using `git diff --cached`, compile a commit message,
+and call the `finish` action with `outputs.answer` set to the answer. If current
+repo is not a valid git repo, or there is no diff in the staging area, please call
+the `reject` action.
+
+## History
+{{ instructions.history_truncated }}
+{{ history_to_json(state.history[-10:]) }}
+
+If the last item in the history is an error, you should try to fix it.
+
+## Available Actions
+{{ instructions.actions.run }}
+{{ instructions.actions.reject }}
+{{ instructions.actions.finish }}
+
+## Format
+{{ instructions.format.action }}

agenthub/micro/instructions.py

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

agenthub/micro/manager/agent.yaml

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

agenthub/micro/manager/prompt.md

@@ -0,0 +1,40 @@
+# Task
+You are in charge of accomplishing the following task:
+{{ latest_user_message }}
+
+In order to accomplish this goal, you must delegate tasks to one or more agents, who
+can do the actual work. A description of each agent is provided below. You MUST
+select one of the delegates below to move towards accomplishing the task, and you MUST
+provide the correct inputs for the delegate you select.
+
+Note: the delegated agent either returns "finish" or "reject".
+- If the action is "finish", but the full task is not done yet, you should
+continue to delegate to one of the agents below to until the full task is finished.
+- If the action is "reject", it means the delegated agent is not capable of the
+task you send to. You should revisit the input you send to the delegate, and consider
+whether any other delegate would be able to solve the task. If you cannot find
+a proper delegate agent, or the delegate attempts keep failing, call the `reject`
+action.
+
+## Agents
+{% for name, details in delegates.items() %}
+### {{ name }}
+{{ details.description }}
+#### Inputs
+{{ to_json(details.inputs) }}
+{% endfor %}
+
+## History
+{{ instructions.history_truncated }}
+{{ history_to_json(state.history[-10:]) }}
+
+If the last item in the history is an error, you should try to fix it. If you
+cannot fix it, call the `reject` action.
+
+## Available Actions
+{{ instructions.actions.delegate }}
+{{ instructions.actions.finish }}
+{{ instructions.actions.reject }}
+
+## Format
+{{ instructions.format.action }}

agenthub/micro/math_agent/agent.yaml

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

agenthub/micro/math_agent/prompt.md

@@ -0,0 +1,23 @@
+# Task
+You are a brilliant mathematician and programmer. You've been given the following problem to solve:
+
+`{{ state.inputs.task }}`
+
+Please write a python script that solves this problem, and prints the answer to stdout.
+ONLY print the answer to stdout, nothing else.
+You should then run the python script with `python3`,
+and call the `finish` action with `outputs.answer` set to the answer.
+
+## History
+{{ instructions.history_truncated }}
+{{ history_to_json(state.history[-10:]) }}
+
+If the last item in the history is an error, you should try to fix it.
+
+## Available Actions
+{{ instructions.actions.write }}
+{{ instructions.actions.run }}
+{{ instructions.actions.finish }}
+
+## Format
+{{ instructions.format.action }}

agenthub/micro/postgres_agent/agent.yaml

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

agenthub/micro/postgres_agent/prompt.md

@@ -0,0 +1,24 @@
+# Task
+You are a database engineer. You are working on an existing Postgres project, and have been given
+the following task:
+
+{{ state.inputs.task }}
+
+You must:
+* Investigate the existing migrations to understand the current schema
+* Write a new migration to accomplish the task above
+* Test that the migrations work properly
+
+## Actions
+You may take any of the following actions:
+{{ instructions.actions.message }}
+{{ instructions.actions.read }}
+{{ instructions.actions.write }}
+{{ instructions.actions.run }}
+
+## History
+{{ instructions.history_truncated }}
+{{ history_to_json(state.history[-10:]) }}
+
+## Format
+{{ instructions.format.action }}

agenthub/micro/registry.py

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

agenthub/micro/repo_explorer/agent.yaml

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

agenthub/micro/repo_explorer/prompt.md

@@ -0,0 +1,26 @@
+# Task
+You are a software engineer. You've inherited an existing codebase, which you're
+learning about for the first time. Your goal is to produce a detailed summary
+of the codebase, including:
+* The overall purpose of the project
+* The directory structure
+* The main components of the codebase
+* How the components fit together
+
+## Available Actions
+{{ instructions.actions.run }}
+{{ instructions.actions.read }}
+{{ instructions.actions.message }}
+{{ instructions.actions.finish }}
+
+You should ONLY `run` commands that have no side-effects, like `ls` and `grep`.
+
+Do NOT finish until you have a complete understanding of the codebase.
+When you're done, put your summary into the output of the `finish` action.
+
+## History
+{{ instructions.history_truncated }}
+{{ history_to_json(state.history[-10:]) }}
+
+## Format
+{{ instructions.format.action }}

agenthub/micro/study_repo_for_task/agent.yaml

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

agenthub/micro/study_repo_for_task/prompt.md

@@ -0,0 +1,63 @@
+# Task
+You are a software architect. Your team has inherited an existing codebase, and
+need to finish a project:
+
+{{ state.inputs.task }}
+
+As an architect, you need to study the codebase to find all the information that
+might be helpful for your software engineering team.
+
+## Available Actions
+{{ instructions.actions.run }}
+{{ instructions.actions.read }}
+{{ instructions.actions.message }}
+{{ instructions.actions.finish }}
+
+You must ONLY `run` commands that have no side-effects, like `ls` and `grep`. You
+MUST NOT modify or write to any file.
+
+Do NOT finish until you have a complete understanding of which parts of the
+codebase are relevant to the project, including particular files, functions, and classes.
+When you're done, put your summary in `outputs.summary` in the `finish` action.
+Remember, your task is to explore and study the current repository, not actually
+implement the solution. If the codebase is empty, you should call the `finish` action.
+
+## History
+{{ instructions.history_truncated }}
+{{ history_to_json(state.history[-10:]) }}
+
+## Format
+{{ instructions.format.action }}
+
+## Examples
+
+Here is an example of how you can interact with the environment for task solving:
+
+--- START OF EXAMPLE ---
+
+USER: Can you create a list of numbers from 1 to 10, and create a web page to display them at port 5000?
+
+ASSISTANT:
+{
+  "action": "run",
+  "args": {
+    "command": "ls",
+    "background": false
+  }
+}
+
+USER:
+OBSERVATION:
+[]
+
+ASSISTANT:
+{
+  "action": "finish",
+  "args": {
+    "outputs": {
+      "summary": "The codebase appears to be empty. Engineers should start everything from scratch."
+    }
+  }
+}
+
+--- END OF EXAMPLE ---

agenthub/micro/typo_fixer_agent/agent.yaml

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

agenthub/micro/typo_fixer_agent/prompt.md

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

agenthub/micro/verifier/agent.yaml

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

agenthub/micro/verifier/prompt.md

@@ -0,0 +1,28 @@
+# Task
+You are a quality assurance engineer. Another engineer has made changes to the
+codebase which are supposed to solve this task:
+
+{{ state.inputs.task }}
+
+Note the changes might have already been applied in-line. You should focus on
+validating if the task is solved, nothing else.
+
+## Available Actions
+{{ instructions.actions.run }}
+{{ instructions.actions.read }}
+{{ instructions.actions.message }}
+{{ instructions.actions.finish }}
+
+You must ONLY `run` commands that have no side-effects, like `ls`, `grep`, and test scripts.
+
+Do NOT finish until you know whether the task is complete and correct.
+When you're done, add a `completed` boolean to the `outputs` of the `finish` action.
+If `completed` is `false`, you MUST also provide a `summary` in the `outputs` of the `finish` action
+explaining what the problem is.
+
+## History
+{{ instructions.history_truncated }}
+{{ history_to_json(state.history[-10:]) }}
+
+## Format
+{{ instructions.format.action }}

agenthub/monologue_agent/TODO.md

@@ -6,4 +6,3 @@ There's a lot of low-hanging fruit for this agent:
 * Improve memory condensing--condense earlier memories more aggressively
 * Limit the time that `run` can wait (in case agent runs an interactive command and it's hanging)
 * Figure out how to run background processes, e.g. `node server.js` to start a server
-

agenthub/monologue_agent/__init__.py

@@ -1,4 +1,5 @@
-from opendevin.agent import Agent
+from opendevin.controller.agent import Agent
+
 from .agent import MonologueAgent
 
-Agent.register("MonologueAgent", MonologueAgent)
+Agent.register('MonologueAgent', MonologueAgent)

agenthub/monologue_agent/agent.py

@@ -1,172 +1,240 @@
-from typing import List
-from opendevin.agent import Agent
-from opendevin.state import State
-from opendevin.llm.llm import LLM
-
-from opendevin.action import (
+import agenthub.monologue_agent.utils.prompts as prompts
+from agenthub.monologue_agent.utils.prompts import INITIAL_THOUGHTS
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.core.config import config
+from opendevin.core.exceptions import AgentNoInstructionError
+from opendevin.core.schema import ActionType
+from opendevin.events.action import (
     Action,
-    NullAction,
-    CmdRunAction,
-    FileWriteAction,
-    FileReadAction,
     AgentRecallAction,
     BrowseURLAction,
-    AgentThinkAction,
+    CmdRunAction,
+    FileReadAction,
+    FileWriteAction,
+    MessageAction,
+    NullAction,
 )
-
-from opendevin.observation import (
-    Observation,
-    NullObservation,
-    CmdOutputObservation,
-    FileReadObservation,
+from opendevin.events.observation import (
     AgentRecallObservation,
     BrowserOutputObservation,
+    CmdOutputObservation,
+    FileReadObservation,
+    NullObservation,
+    Observation,
 )
+from opendevin.events.serialization.event import event_to_memory
+from opendevin.llm.llm import LLM
+from opendevin.memory.condenser import MemoryCondenser
+from opendevin.runtime.tools import RuntimeTool
 
-import agenthub.monologue_agent.utils.prompts as prompts
-from agenthub.monologue_agent.utils.monologue import Monologue
-from agenthub.monologue_agent.utils.memory import LongTermMemory
+if config.agent.memory_enabled:
+    from opendevin.memory.memory import LongTermMemory
 
-MAX_MONOLOGUE_LENGTH = 20000
+MAX_TOKEN_COUNT_PADDING = 512
 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):
+    VERSION = '1.0'
+    """
+    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
+    initial_thoughts: list[dict[str, str]]
+    memory: 'LongTermMemory | None'
+    memory_condenser: MemoryCondenser
+    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
 
     def __init__(self, llm: LLM):
+        """
+        Initializes the Monologue Agent with an llm.
+
+        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):
-        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] + "..."
+    def _initialize(self, task: str):
+        """
+        Utilizes the INITIAL_THOUGHTS list to give the agent a context for its capabilities
+        and how to navigate the WORKSPACE_MOUNT_PATH_IN_SANDBOX in `config` (e.g., /workspace by default).
+        Short circuited to return when already initialized.
+        Will execute again when called after reset.
 
-        self.monologue.add_event(event)
-        self.memory.add_event(event)
-        if self.monologue.get_total_length() > MAX_MONOLOGUE_LENGTH:
-            self.monologue.condense(self.llm)
+        Parameters:
+        - task (str): The initial goal statement provided by the user
+
+        Raises:
+        - AgentNoInstructionError: If task is not provided
+        """
 
-    def _initialize(self, task):
         if self._initialized:
             return
 
-        if task is None or task == "":
-            raise ValueError("Instruction must be provided")
-        self.monologue = Monologue()
-        self.memory = LongTermMemory()
+        if task is None or task == '':
+            raise AgentNoInstructionError()
 
-        output_type = ""
+        self.initial_thoughts = []
+        if config.agent.memory_enabled:
+            self.memory = LongTermMemory()
+        else:
+            self.memory = None
+
+        self.memory_condenser = MemoryCondenser()
+
+        self._add_initial_thoughts(task)
+        self._initialized = True
+
+    def _add_initial_thoughts(self, task):
+        previous_action = ''
         for thought in INITIAL_THOUGHTS:
-            thought = thought.replace("$TASK", task)
-            if output_type != "":
-                observation: Observation = NullObservation(content="")
-                if output_type == "run":
-                    observation = CmdOutputObservation(content=thought, command_id=0, command="")
-                elif output_type == "read":
-                    observation = FileReadObservation(content=thought, path="")
-                elif output_type == "recall":
+            thought = thought.replace('$TASK', task)
+            if previous_action != '':
+                observation: Observation = NullObservation(content='')
+                if previous_action in {ActionType.RUN, ActionType.PUSH}:
+                    observation = CmdOutputObservation(
+                        content=thought, command_id=0, command=''
+                    )
+                elif previous_action == ActionType.READ:
+                    observation = FileReadObservation(content=thought, path='')
+                elif previous_action == ActionType.RECALL:
                     observation = AgentRecallObservation(content=thought, memories=[])
-                elif output_type == "browse":
-                    observation = BrowserOutputObservation(content=thought, url="", screenshot="")
-                self._add_event(observation.to_dict())
-                output_type = ""
+                elif previous_action == ActionType.BROWSE:
+                    observation = BrowserOutputObservation(
+                        content=thought, url='', screenshot=''
+                    )
+                self.initial_thoughts.append(event_to_memory(observation))
+                previous_action = ''
             else:
                 action: Action = NullAction()
-                if thought.startswith("RUN"):
-                    command = thought.split("RUN ")[1]
+                if thought.startswith('RUN'):
+                    command = thought.split('RUN ')[1]
                     action = CmdRunAction(command)
-                    output_type = "run"
-                elif thought.startswith("WRITE"):
-                    parts = thought.split("WRITE ")[1].split(" > ")
+                    previous_action = 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]
+                elif thought.startswith('READ'):
+                    path = thought.split('READ ')[1]
                     action = FileReadAction(path=path)
-                    output_type = "read"
-                elif thought.startswith("RECALL"):
-                    query = thought.split("RECALL ")[1]
+                    previous_action = ActionType.READ
+                elif thought.startswith('RECALL'):
+                    query = thought.split('RECALL ')[1]
                     action = AgentRecallAction(query=query)
-                    output_type = "recall"
-                elif thought.startswith("BROWSE"):
-                    url = thought.split("BROWSE ")[1]
+                    previous_action = ActionType.RECALL
+                elif thought.startswith('BROWSE'):
+                    url = thought.split('BROWSE ')[1]
                     action = BrowseURLAction(url=url)
-                    output_type = "browse"
+                    previous_action = ActionType.BROWSE
                 else:
-                    action = AgentThinkAction(thought=thought)
-                self._add_event(action.to_dict())
-        self._initialized = True
+                    action = MessageAction(thought)
+                self.initial_thoughts.append(event_to_memory(action))
 
     def step(self, state: State) -> Action:
-        self._initialize(state.plan.main_goal)
-        for prev_action, obs in state.updated_info:
-            self._add_event(prev_action.to_dict())
-            self._add_event(obs.to_dict())
+        """
+        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.
 
-        state.updated_info = []
+        Parameters:
+        - state (State): The current state based on previous steps taken
 
+        Returns:
+        - Action: The next action to take based on LLM response
+        """
+
+        goal = state.get_current_user_intent()
+        self._initialize(goal)
+
+        recent_events: list[dict[str, str]] = []
+
+        # add the events from state.history
+        for prev_action, obs in state.history:
+            if not isinstance(prev_action, NullAction):
+                recent_events.append(event_to_memory(prev_action))
+            if not isinstance(obs, NullObservation):
+                recent_events.append(self._truncate_output(event_to_memory(obs)))
+
+        # add the last messages to long term memory
+        if self.memory is not None and state.history and len(state.history) > 0:
+            self.memory.add_event(event_to_memory(state.history[-1][0]))
+            self.memory.add_event(
+                self._truncate_output(event_to_memory(state.history[-1][1]))
+            )
+
+        # the action prompt with initial thoughts and recent events
         prompt = prompts.get_request_action_prompt(
-            state.plan.main_goal,
-            self.monologue.get_thoughts(),
+            goal,
+            self.initial_thoughts,
+            recent_events,
             state.background_commands_obs,
         )
-        messages = [{"content": prompt,"role": "user"}]
-        resp = self.llm.completion(messages=messages)
+
+        messages: list[dict[str, str]] = [
+            {'role': 'user', 'content': prompt},
+        ]
+
+        # format all as a single message, a monologue
+        resp = self.llm.do_completion(messages=messages)
+
+        # get the next action from the response
         action_resp = resp['choices'][0]['message']['content']
+
+        # keep track of max_chars fallback option
+        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]:
+    def _truncate_output(
+        self, observation: dict, max_chars: int = MAX_OUTPUT_LENGTH
+    ) -> dict[str, str]:
+        """
+        Truncates the output of an observation to a maximum number of characters.
+
+        Parameters:
+        - output (str): The observation whose output to truncate
+        - max_chars (int): The maximum number of characters to allow
+
+        Returns:
+        - str: The truncated output
+        """
+        if (
+            'args' in observation
+            and 'output' in observation['args']
+            and len(observation['args']['output']) > max_chars
+        ):
+            output = observation['args']['output']
+            half = max_chars // 2
+            observation['args']['output'] = (
+                output[:half]
+                + '\n[... Output truncated due to length...]\n'
+                + output[-half:]
+            )
+        return observation
+
+    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
+        """
+        if self.memory is None:
+            return []
         return self.memory.search(query)
 
+    def reset(self) -> None:
+        super().reset()
+
+        # Reset the initial monologue and memory
+        self._initialized = False

agenthub/monologue_agent/utils/json.py

@@ -1,14 +0,0 @@
-import json
-from json_repair import repair_json
-
-def my_encoder(obj):
-    if hasattr(obj, "to_dict"):
-        return obj.to_dict()
-
-def dumps(obj, **kwargs):
-    return json.dumps(obj, default=my_encoder, **kwargs)
-
-def loads(s, **kwargs):
-    s_repaired = repair_json(s)
-    return json.loads(s_repaired, **kwargs)
-

agenthub/monologue_agent/utils/memory.py

@@ -1,79 +0,0 @@
-import chromadb
-from llama_index.core import Document
-from llama_index.core.retrievers import VectorIndexRetriever
-from llama_index.core import VectorStoreIndex
-from llama_index.vector_stores.chroma import ChromaVectorStore
-
-from opendevin import config
-from . import json
-
-embedding_strategy = config.get("LLM_EMBEDDING_MODEL")
-
-# TODO: More embeddings: https://docs.llamaindex.ai/en/stable/examples/embeddings/OpenAI/
-# There's probably a more programmatic way to do this.
-if embedding_strategy == "llama2":
-    from llama_index.embeddings.ollama import OllamaEmbedding
-    embed_model = OllamaEmbedding(
-        model_name="llama2",
-        base_url=config.get_or_error("LLM_BASE_URL"),
-        ollama_additional_kwargs={"mirostat": 0},
-    )
-elif embedding_strategy == "openai":
-    from llama_index.embeddings.openai import OpenAIEmbedding
-    embed_model = OpenAIEmbedding(
-        model="text-embedding-ada-002"
-    )
-elif embedding_strategy == "azureopenai":
-    from llama_index.embeddings.azure_openai import AzureOpenAIEmbedding  # Need to instruct to set these env variables in documentation
-    embed_model = AzureOpenAIEmbedding(
-        model="text-embedding-ada-002",
-        deployment_name=config.get_or_error("LLM_DEPLOYMENT_NAME"),
-        api_key=config.get_or_error("LLM_API_KEY"),
-        azure_endpoint=config.get_or_error("LLM_BASE_URL"),
-        api_version=config.get_or_error("LLM_API_VERSION"),
-    )
-else:
-    from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-    embed_model = HuggingFaceEmbedding(
-        model_name="BAAI/bge-small-en-v1.5"
-    )
-
-
-class LongTermMemory:
-    def __init__(self):
-        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):
-        id = ""
-        t = ""
-        if "action" in event:
-            t = "action"
-            id = event["action"]
-        elif "observation" in event:
-            t = "observation"
-            id = event["observation"]
-        doc = Document(
-            text=json.dumps(event),
-            doc_id=str(self.thought_idx),
-            extra_info={
-                "type": t,
-                "id": id,
-                "idx": self.thought_idx,
-            },
-        )
-        self.thought_idx += 1
-        self.index.insert(doc)
-
-    def search(self, query, k=10):
-        retriever = VectorIndexRetriever(
-            index=self.index,
-            similarity_top_k=k,
-        )
-        results = retriever.retrieve(query)
-        return [r.get_text() for r in results]
-
-

agenthub/monologue_agent/utils/monologue.py

@@ -1,40 +0,0 @@
-import traceback
-
-import agenthub.monologue_agent.utils.json as json
-import agenthub.monologue_agent.utils.prompts as prompts
-
-class Monologue:
-    def __init__(self):
-        self.thoughts = []
-
-    def add_event(self, t: dict):
-        if not isinstance(t, dict):
-            raise ValueError("Event must be a dictionary")
-        self.thoughts.append(t)
-
-    def get_thoughts(self):
-        return self.thoughts
-
-    def get_total_length(self):
-        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):
-        try:
-            prompt = prompts.get_summarize_monologue_prompt(self.thoughts)
-            messages = [{"content": prompt,"role": "user"}]
-            resp = llm.completion(messages=messages)
-            summary_resp = resp['choices'][0]['message']['content']
-            self.thoughts = prompts.parse_summary_response(strip_markdown(summary_resp))
-        except Exception as e:
-            traceback.print_exc()
-            raise RuntimeError(f"Error condensing thoughts: {e}")
-
-def strip_markdown(markdown_json):
-    # remove markdown code block
-    return markdown_json.replace('```json\n', '').replace('```', '').strip()

agenthub/monologue_agent/utils/prompts.py

@@ -1,30 +1,26 @@
-from typing import List
-
-from . import json
-
-from opendevin.action import (
-    action_from_dict,
+from opendevin.core.config import config
+from opendevin.core.utils import json
+from opendevin.events.action import (
     Action,
 )
-from opendevin.observation import (
+from opendevin.events.observation import (
     CmdOutputObservation,
 )
+from opendevin.events.serialization.action import action_from_dict
 
 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:
-```json
+
 %(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:
+What is your next single thought or action? Your response must be in JSON format.
+It must be a single 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
 
@@ -38,27 +34,36 @@ Here are the possible actions:
   * `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
+  * `command_id` - the ID of the background command to kill
 * `browse` - opens a web page. Arguments:
   * `url` - the URL to open
+* `push` - Push a branch from the current repo to github:
+  * `owner` - the owner of the repo to push to
+  * `repo` - the name of the repo to push to
+  * `branch` - the name of the branch to push
 * `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
+* `message` - make a plan, set a goal, record your thoughts, or ask for more input from the user. Arguments:
+  * `content` - the message to record
+  * `wait_for_response` - set to `true` to wait for the user to respond before proceeding
 * `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 MUST take time to think in between read, write, run, kill, browse, push, and recall actions--do this with the `message` action.
 You should never act twice in a row without thinking. But if your last several
-actions are all "think" actions, you should consider taking a different action.
+actions are all `message` 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.
+* you are logged in as %(user)s, but sudo will always work without a password.
+* all non-background commands will be forcibly stopped if they remain running for over %(timeout)s seconds.
+* your environment is Debian Linux. You can install software with `sudo apt-get`, but remember to use -y.
 * 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 &`)
+* don't run interactive text editors (e.g. `nano` or 'vim'), instead use the 'write' or 'read' action.
+* don't run gui applications (e.g. software IDEs (like vs code or codium), web browsers (like firefox or chromium), or other complex software packages). Use non-interactive cli applications, or special actions instead.
+* whenever an action fails, always send a `message` about why it may have happened before acting again.
 
-What is your next thought or action? Again, you must reply with JSON, and only with JSON.
+What is your next single thought or action? Again, you must reply with JSON, and only with JSON. You must respond with exactly one 'action' object.
 
 %(hint)s
 """
@@ -71,9 +76,9 @@ 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.
-```json
+
 %(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.
@@ -86,54 +91,155 @@ 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.
 """
 
+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 `pwd` and `ls` to orient myself.',
+]
 
-def get_summarize_monologue_prompt(thoughts):
+
+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] = [],
-):
-    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 = ""
+def get_request_action_prompt(
+    task: str,
+    thoughts: list[dict],
+    recent_events: list[dict],
+    background_commands_obs: list[CmdOutputObservation] | None = None,
+):
+    """
+    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 commands included
+    """
+
+    if background_commands_obs is None:
+        background_commands_obs = []
+
+    hint = ''
+    if len(recent_events) > 0:
+        latest_event = recent_events[-1]
+        if 'action' in latest_event:
+            if (
+                latest_event['action'] == 'message'
+                and 'source' in latest_event
+                and latest_event['source'] == 'agent'
+            ):
+                hint = (
+                    "You've been thinking a lot lately. Maybe it's time to take action?"
+                )
+            elif latest_event['action'] == 'error':
+                hint = 'Looks like that last command failed. Maybe you need to fix it, or try something else.'
+    else:
+        hint = "You're just getting started! What should you do first?"
+
+    bg_commands_message = ''
     if len(background_commands_obs) > 0:
-        bg_commands_message = "The following commands are running in the background:"
+        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."
-    latest_thought = thoughts[-1]
+            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 `command_id` above.'
+
+    user = 'opendevin' if config.run_as_devin else 'root'
+
+    monologue = thoughts + recent_events
 
     return ACTION_PROMPT % {
         'task': task,
-        'monologue': json.dumps(thoughts, indent=2),
+        'monologue': json.dumps(monologue, indent=2),
         'background_commands': bg_commands_message,
         'hint': hint,
+        'user': user,
+        'timeout': config.sandbox_timeout,
+        'WORKSPACE_MOUNT_PATH_IN_SANDBOX': config.workspace_mount_path_in_sandbox,
     }
 
-def parse_action_response(response: str) -> Action:
-    json_start = response.find("{")
-    json_end = response.rfind("}") + 1
-    response = response[json_start:json_end]
-    action_dict = json.loads(response)
+
+def parse_action_response(orig_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
+    """
+    # attempt to load the JSON dict from the response
+    action_dict = json.loads(orig_response)
+
     if 'content' in action_dict:
         # The LLM gets confused here. Might as well be robust
         action_dict['contents'] = action_dict.pop('content')
+
     return action_from_dict(action_dict)
 
-def parse_summary_response(response: str) -> List[dict]:
+
+def parse_summary_response(response: str) -> list[dict]:
+    """
+    Parses a summary of the monologue
+
+    Parameters:
+    - response (str): The response string to be parsed
+
+    Returns:
+    - list[dict]: The list of summaries output by the model
+    """
     parsed = json.loads(response)
     return parsed['new_monologue']

agenthub/planner_agent/__init__.py

@@ -1,4 +1,5 @@
-from opendevin.agent import Agent
+from opendevin.controller.agent import Agent
+
 from .agent import PlannerAgent
 
-Agent.register("PlannerAgent", PlannerAgent)
+Agent.register('PlannerAgent', PlannerAgent)

agenthub/planner_agent/agent.py

@@ -1,26 +1,55 @@
-from typing import List
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.events.action import Action, AgentFinishAction
+from opendevin.llm.llm import LLM
+from opendevin.runtime.tools import RuntimeTool
+
 from .prompt import get_prompt, 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):
+    VERSION = '1.0'
+    """
+    The planner agent utilizes a special prompting strategy to create long term plans for solving problems.
+    The agent is given its previous action-observation pairs, current task, and hint based on last action taken at every step.
+    """
+    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
+
     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:
-        if state.plan.task.state in ['completed', 'verified', 'abandoned']:
+        """
+        Checks to see if current step is completed, returns AgentFinishAction if True.
+        Otherwise, creates a plan prompt and sends to model for inference, returning the result as the next action.
+
+        Parameters:
+        - state (State): The current state given the previous actions and observations
+
+        Returns:
+        - AgentFinishAction: If the last state was 'completed', 'verified', or 'abandoned'
+        - Action: The next action to take based on llm response
+        """
+
+        if state.root_task.state in [
+            'completed',
+            'verified',
+            'abandoned',
+        ]:
             return AgentFinishAction()
-        prompt = get_prompt(state.plan, state.history)
-        messages = [{"content": prompt, "role": "user"}]
-        resp = self.llm.completion(messages=messages)
+        prompt = get_prompt(state)
+        messages = [{'content': prompt, 'role': 'user'}]
+        resp = self.llm.do_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]:
+    def search_memory(self, query: str) -> list[str]:
         return []
-

agenthub/planner_agent/prompt.py

@@ -1,43 +1,16 @@
-import json
-from typing import List, Tuple, Dict, Type
-
-from opendevin.controller.agent_controller import print_with_color
-from opendevin.plan import Plan
-from opendevin.action import Action, action_from_dict
-from opendevin.observation import Observation
-
-from opendevin.action import (
+from opendevin.controller.state.state import State
+from opendevin.core.logger import opendevin_logger as logger
+from opendevin.core.schema import ActionType
+from opendevin.core.utils import json
+from opendevin.events.action import (
+    Action,
     NullAction,
-    CmdRunAction,
-    CmdKillAction,
-    BrowseURLAction,
-    FileReadAction,
-    FileWriteAction,
-    AgentRecallAction,
-    AgentThinkAction,
-    AgentFinishAction,
-    AgentSummarizeAction,
-    AddTaskAction,
-    ModifyTaskAction,
 )
-
-from opendevin.observation import (
+from opendevin.events.observation import (
     NullObservation,
 )
-
-ACTION_TYPE_TO_CLASS: Dict[str, Type[Action]] = {
-    "run": CmdRunAction,
-    "kill": CmdKillAction,
-    "browse": BrowseURLAction,
-    "read": FileReadAction,
-    "write": FileWriteAction,
-    "recall": AgentRecallAction,
-    "think": AgentThinkAction,
-    "summarize": AgentSummarizeAction,
-    "finish": AgentFinishAction,
-    "add_task": AddTaskAction,
-    "modify_task": ModifyTaskAction,
-}
+from opendevin.events.serialization.action import action_from_dict
+from opendevin.events.serialization.event import event_to_memory
 
 HISTORY_SIZE = 10
 
@@ -53,9 +26,9 @@ You've been given the following task:
 ## 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:
-```json
+
 %(plan)s
-```
+
 
 %(plan_status)s
 
@@ -84,9 +57,9 @@ you MUST respond with the `finish` action.
 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.
-```json
+
 %(history)s
-```
+
 
 Your most recent action is at the bottom of that history.
 
@@ -106,98 +79,106 @@ It must be an object, and it must contain two fields:
   * `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
+  * `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
+* `message` - make a plan, set a goal, record your thoughts, or ask for more input from the user. Arguments:
+  * `content` - the message to record
+  * `wait_for_response` - set to `true` to wait for the user to respond before proceeding
 * `add_task` - add a task to your plan. Arguments:
-  * `parent` - the ID of the parent task
+  * `parent` - the ID of the parent task (leave empty if it should go at the top level)
   * `goal` - the goal of the task
   * `subtasks` - a list of subtasks, each of which is a map with a `goal` key.
 * `modify_task` - close a task. Arguments:
-  * `id` - the ID of the task to close
+  * `task_id` - the ID of the task to close
   * `state` - set to 'in_progress' to start the task, 'completed' to finish it, 'verified' to assert that it was successful, 'abandoned' to give up on it permanently, or `open` to stop working on it for now.
-* `finish` - if ALL of your tasks and subtasks have been verified or abanded, and you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.
+* `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 MUST take time to think in between read, write, run, kill, browse, and recall actions--do this with the `message` action.
 You should never act twice in a row without thinking. But if your last several
-actions are all `think` actions, you should consider taking a different action.
+actions are all `message` actions, you should consider taking a different action.
 
 What is your next thought or action? Again, you must reply with JSON, and only with JSON.
 
 %(hint)s
 """
 
-def get_prompt(plan: Plan, history: List[Tuple[Action, Observation]]):
-    plan_str = json.dumps(plan.task.to_dict(), indent=2)
-    sub_history = history[-HISTORY_SIZE:]
+
+def get_hint(latest_action_id: str) -> str:
+    """Returns action type hint based on given action_id"""
+
+    hints = {
+        '': "You haven't taken any actions yet. Start by using `ls` to check out what files you're working with.",
+        ActionType.RUN: 'You should think about the command you just ran, what output it gave, and how that affects your plan.',
+        ActionType.READ: 'You should think about the file you just read, what you learned from it, and how that affects your plan.',
+        ActionType.WRITE: 'You just changed a file. You should think about how it affects your plan.',
+        ActionType.BROWSE: 'You should think about the page you just visited, and what you learned from it.',
+        ActionType.MESSAGE: "Look at your last thought in the history above. What does it suggest? Don't think anymore--take action.",
+        ActionType.RECALL: 'You should think about the information you just recalled, and how it should affect your plan.',
+        ActionType.ADD_TASK: 'You should think about the next action to take.',
+        ActionType.MODIFY_TASK: 'You should think about the next action to take.',
+        ActionType.SUMMARIZE: '',
+        ActionType.FINISH: '',
+    }
+    return hints.get(latest_action_id, '')
+
+
+def get_prompt(state: State) -> str:
+    """
+    Gets the prompt for the planner agent.
+    Formatted with the most recent action-observation pairs, current task, and hint based on last action
+
+    Parameters:
+    - state (State): The state of the current agent
+
+    Returns:
+    - str: The formatted string prompt with historical values
+    """
+
+    plan_str = json.dumps(state.root_task.to_dict(), indent=2)
+    sub_history = state.history[-HISTORY_SIZE:]
     history_dicts = []
     latest_action: Action = NullAction()
     for action, observation in sub_history:
         if not isinstance(action, NullAction):
-            history_dicts.append(action.to_dict())
+            history_dicts.append(event_to_memory(action))
             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"]
+            observation_dict = event_to_memory(observation)
             history_dicts.append(observation_dict)
     history_str = json.dumps(history_dicts, indent=2)
-
-    hint = ""
-    current_task = plan.get_current_task()
+    current_task = state.root_task.get_current_task()
     if current_task is not None:
         plan_status = f"You're currently working on this task:\n{current_task.goal}."
         if len(current_task.subtasks) == 0:
             plan_status += "\nIf it's not achievable AND verifiable with a SINGLE action, you MUST break it down into subtasks NOW."
     else:
         plan_status = "You're not currently working on any tasks. Your next action MUST be to mark a task as in_progress."
-        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 == "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 == "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 == "write":
-            hint = "You just changed a file. You should think about how it affects your plan."
-        elif latest_action_id == "browse":
-            hint = "You should think about the page you just visited, and what you learned from it."
-        elif latest_action_id == "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 == "recall":
-            hint = "You should think about the information you just recalled, and how it should affect your plan."
-        elif latest_action_id == "add_task":
-            hint = "You should think about the next action to take."
-        elif latest_action_id == "modify_task":
-            hint = "You should think about the next action to take."
-        elif latest_action_id == "summarize":
-            hint = ""
-        elif latest_action_id == "finish":
-            hint = ""
-
-    print_with_color("HINT:\n" + hint, "INFO")
+    hint = get_hint(event_to_memory(latest_action).get('action', ''))
+    logger.info('HINT:\n' + hint, extra={'msg_type': 'DETAIL'})
+    task = state.get_current_user_intent()
     return prompt % {
-        'task': plan.main_goal,
+        'task': task,
         'plan': plan_str,
         'history': history_str,
         'hint': hint,
         'plan_status': plan_status,
     }
 
+
 def parse_response(response: str) -> Action:
-    json_start = response.find("{")
-    json_end = response.rfind("}") + 1
-    response = response[json_start:json_end]
+    """
+    Parses the model output to find a valid action to take
+
+    Parameters:
+    - response (str): A response from the model that potentially contains an Action.
+
+    Returns:
+    - Action: A valid next action to perform from model output
+    """
     action_dict = json.loads(response)
     if 'contents' in action_dict:
         # The LLM gets confused here. Might as well be robust
         action_dict['content'] = action_dict.pop('contents')
     action = action_from_dict(action_dict)
     return action
-

config.toml.template

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

containers/README.md

@@ -0,0 +1,11 @@
+# Docker Containers
+Each folder here contains a Dockerfile, and a config.sh describing how to build
+the image and where to push it. These are images are built and pushed in GitHub Actions
+by the `ghcr.yml` workflow.
+
+## Building Manually
+
+```
+docker build -f containers/app/Dockerfile -t opendevin .
+docker build -f containers/sandbox/Dockerfile -t sandbox .
+```

containers/app/Dockerfile

@@ -0,0 +1,82 @@
+ARG OPEN_DEVIN_BUILD_VERSION=dev
+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
+
+COPY ./frontend ./
+RUN npm run make-i18n && npm run build
+
+FROM python:3.12.3-slim as backend-builder
+
+WORKDIR /app
+ENV PYTHONPATH '/app'
+
+ENV POETRY_NO_INTERACTION=1 \
+    POETRY_VIRTUALENVS_IN_PROJECT=1 \
+    POETRY_VIRTUALENVS_CREATE=1 \
+    POETRY_CACHE_DIR=/tmp/poetry_cache
+
+RUN apt-get update -y \
+    && apt-get install -y curl make git build-essential \
+    && python3 -m pip install poetry==1.8.2  --break-system-packages
+
+COPY ./pyproject.toml ./poetry.lock ./
+RUN touch README.md
+RUN poetry install --without evaluation --no-root && rm -rf $POETRY_CACHE_DIR
+
+FROM python:3.12.3-slim as runtime
+
+WORKDIR /app
+
+ENV RUN_AS_DEVIN=true
+# A random number--we need this to be different from the user's UID on the host machine
+ENV OPENDEVIN_USER_ID=42420
+ENV USE_HOST_NETWORK=false
+ENV SSH_HOSTNAME=host.docker.internal
+ENV WORKSPACE_BASE=/opt/workspace_base
+ENV OPEN_DEVIN_BUILD_VERSION=$OPEN_DEVIN_BUILD_VERSION
+RUN mkdir -p $WORKSPACE_BASE
+
+RUN apt-get update -y \
+    && apt-get install -y curl ssh sudo
+
+RUN sed -i 's/^UID_MIN.*/UID_MIN 499/' /etc/login.defs # Default is 1000, but OSX is often 501
+RUN sed -i 's/^UID_MAX.*/UID_MAX 1000000/' /etc/login.defs # Default is 60000, but we've seen up to 200000
+
+RUN groupadd app
+RUN useradd -l -m -u $OPENDEVIN_USER_ID -s /bin/bash opendevin && \
+    usermod -aG app opendevin && \
+    usermod -aG sudo opendevin && \
+    echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
+RUN chown -R opendevin:app /app && chmod -R 770 /app
+RUN sudo chown -R opendevin:app $WORKSPACE_BASE && sudo chmod -R 770 $WORKSPACE_BASE
+USER opendevin
+
+ENV VIRTUAL_ENV=/app/.venv \
+    PATH="/app/.venv/bin:$PATH" \
+    PYTHONPATH='/app'
+
+COPY --chown=opendevin:app --chmod=770 --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
+RUN playwright install --with-deps chromium
+
+COPY --chown=opendevin:app --chmod=770 ./opendevin ./opendevin
+COPY --chown=opendevin:app --chmod=777 ./opendevin/runtime/plugins ./opendevin/runtime/plugins
+COPY --chown=opendevin:app --chmod=770 ./agenthub ./agenthub
+
+RUN python opendevin/core/download.py # No-op to download assets
+RUN chown -R opendevin:app /app/logs && chmod -R 770 /app/logs # This gets created by the download.py script
+
+
+COPY --chown=opendevin:app --chmod=770 --from=frontend-builder /app/dist ./frontend/dist
+COPY --chown=opendevin:app --chmod=770 ./containers/app/entrypoint.sh /app/entrypoint.sh
+
+USER root
+
+WORKDIR /app
+
+ENTRYPOINT ["/app/entrypoint.sh"]
+CMD ["uvicorn", "opendevin.server.listen:app", "--host", "0.0.0.0", "--port", "3000"]

containers/app/config.sh

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

containers/app/entrypoint.sh

@@ -0,0 +1,60 @@
+#!/bin/bash
+set -eo pipefail
+
+echo "Starting OpenDevin..."
+if [[ $NO_SETUP == "true" ]]; then
+  echo "Skipping setup, running as $(whoami)"
+  "$@"
+  exit 0
+fi
+
+if [ "$(id -u)" -ne 0 ]; then
+  echo "The OpenDevin entrypoint.sh must run as root"
+  exit 1
+fi
+
+if [ -z "$SANDBOX_USER_ID" ]; then
+  echo "SANDBOX_USER_ID is not set"
+  exit 1
+fi
+
+if [[ "$SANDBOX_USER_ID" -eq 0 ]]; then
+  echo "Running OpenDevin as root"
+  export RUN_AS_DEVIN=false
+  mkdir -p /root/.cache/ms-playwright/
+  mv /home/opendevin/.cache/ms-playwright/ /root/.cache/
+  "$@"
+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 $SANDBOX_USER_ID. Moving opendevin user."
+      incremented_id=$(($SANDBOX_USER_ID + 1))
+      usermod -u $incremented_id opendevin
+      if ! useradd -l -m -u $SANDBOX_USER_ID -s /bin/bash enduser; then
+        echo "Failed to create user enduser with id $SANDBOX_USER_ID for a second time. Exiting."
+        exit 1
+      fi
+    fi
+  fi
+  usermod -aG app enduser
+  # get the user group of /var/run/docker.sock and set opendevin to that group
+  DOCKER_SOCKET_GID=$(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/
+  mv /home/opendevin/.cache/ms-playwright/ /home/enduser/.cache/
+
+  usermod -aG $DOCKER_SOCKET_GID enduser
+  echo "Running as enduser"
+  su enduser /bin/bash -c "$*"
+fi

containers/build.sh

@@ -0,0 +1,67 @@
+#!/bin/bash
+set -eo pipefail
+
+image_name=$1
+org_name=$2
+push=0
+if [[ $3 == "--push" ]]; then
+  push=1
+fi
+
+echo -e "Building: $image_name"
+tags=()
+
+OPEN_DEVIN_BUILD_VERSION="dev"
+
+cache_tag_base="buildcache"
+cache_tag="$cache_tag_base"
+
+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 $minor_version)
+  fi
+  sanitized=$(echo $GITHUB_REF_NAME | sed 's/[^a-zA-Z0-9.-]\+/-/g')
+  OPEN_DEVIN_BUILD_VERSION=$sanitized
+  cache_tag+="-${sanitized}"
+  tags+=($sanitized)
+fi
+echo "Tags: ${tags[@]}"
+
+dir=./containers/$image_name
+if [ ! -f $dir/Dockerfile ]; then
+  echo "No Dockerfile found"
+  exit 1
+fi
+if [ ! -f $dir/config.sh ]; then
+  echo "No config.sh found for Dockerfile"
+  exit 1
+fi
+source $dir/config.sh
+if [[ -n "$org_name" ]]; then
+  DOCKER_ORG="$org_name"
+fi
+DOCKER_REPOSITORY=$DOCKER_REGISTRY/$DOCKER_ORG/$DOCKER_IMAGE
+DOCKER_REPOSITORY=${DOCKER_REPOSITORY,,} # lowercase
+echo "Repo: $DOCKER_REPOSITORY"
+echo "Base dir: $DOCKER_BASE_DIR"
+
+args=""
+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
+
+docker buildx build \
+  $args \
+  --build-arg OPEN_DEVIN_BUILD_VERSION=$OPEN_DEVIN_BUILD_VERSION \
+  --cache-from=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag \
+  --cache-from=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag_base-main \
+  --platform linux/amd64,linux/arm64 \
+  --provenance=false \
+  -f $dir/Dockerfile $DOCKER_BASE_DIR

containers/e2b-sandbox/Dockerfile

@@ -14,4 +14,6 @@ RUN apt-get update && apt-get install -y \
     python3-venv \
     python3-dev \
     build-essential \
+    openssh-server \
+    sudo \
     && rm -rf /var/lib/apt/lists/*