Update ghcr.yml (#1576)

* permissions mostly working

* fix browser

.gitattributes

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

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,41 +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
-```
-
-**My operating system**:
-
-<!-- tell us everything about your environment -->
-**My environment vars and other configuration** (be sure to redact API keys):
-```bash
-```
-
-**My model and agent** (you can see these settings in the UI):
-* Model:
-* Agent:
-
-**Commands I ran to install and run OpenDevin**:
-```
-```
-
-**Steps to Reproduce**:
-1.
-2.
-3.
-
-**Logs, error messages, and screenshots**:
-
-#### Additional Context

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -0,0 +1,69 @@
+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 Version
+      description: What version 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: 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: Please add any additional context about the problem here.

.github/workflows/build_run-tests.yml

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

.github/workflows/deploy-docs.yml

@@ -0,0 +1,58 @@
+name: Deploy Docs to GitHub Pages
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  build:
+    name: Build Docusaurus
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 18
+          cache: npm
+          cache-dependency-path: docs/package-lock.json
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - 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'
+    # 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 +1,30 @@
+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:
+
+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: Publish Docker Image
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
 on:
   push:
-    branches: [ '**' ]
+    branches:
+    - main
+    tags:
+      - '*'
+  pull_request:
   workflow_dispatch:
     inputs:
       reason:
@@ -13,7 +21,11 @@ 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", "evaluation", "sandbox"]
@@ -22,6 +34,22 @@ jobs:
       - 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
 
@@ -29,8 +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 ${{ matrix.image }}
-        run: ./containers/build.sh ${{ matrix.image }} --push
+        if: "!github.event.pull_request.head.repo.fork"
+        run: |
+          ./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

@@ -1,9 +1,18 @@
 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@v4
@@ -28,11 +37,21 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
       - name: Set up python
         uses: actions/setup-python@v5
         with:
           python-version: 3.11
+          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/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
+        if: github.ref != 'refs/heads/main'
+        run: |
+          git fetch https://github.com/OpenDevin/OpenDevin.git main:main && \
+          pre-commit run \
+            --files \
+            $(git diff --name-only $(git merge-base main $(git branch --show-current)) $(git branch --show-current) | tr '\n' ' ') \
+            --show-diff-on-failure \
+            --config ./dev_config/python/.pre-commit-config.yaml

.github/workflows/review-pr.yml

@@ -0,0 +1,69 @@
+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: Run OpenDevin
+      env:
+        LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        SANDBOX_TYPE: exec
+      run: |
+        WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE 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 +1,76 @@
+name: Run Integration Tests
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+on:
+  push:
+    branches:
+    - main
+  pull_request:
+
+jobs:
+  integration-tests:
+    name: Integration Tests
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11"]
+        agent: ["SWEAgent", "PlannerAgent", "MonologueAgent", "CodeActAgent"]
+        sandbox: ["ssh", "exec"]
+        include:
+          - agent: "MonologueAgent"
+            embedding-model: "local"
+          - agent: "MonologueAgent"
+            # sufficient to have one agent testing against local sandbox
+            sandbox: "local"
+            embedding-model: "local"
+          - agent: "SWEAgent"
+            embedding-model: "none"
+          - agent: "PlannerAgent"
+            embedding-model: "none"
+          - agent: "CodeActAgent"
+            embedding-model: "none"
+    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 Tests
+        env:
+          SANDBOX_TYPE: ${{ matrix.sandbox }}
+          AGENT: ${{ matrix.agent }}
+          MAX_ITERATIONS: 10
+          LLM_EMBEDDING_MODEL: ${{ matrix.embedding-model }}
+        run: |
+          rm -rf workspace
+          mkdir workspace
+          WORKSPACE_BASE="$GITHUB_WORKSPACE/workspace" \
+            WORKSPACE_MOUNT_PATH="$GITHUB_WORKSPACE/workspace" \
+            poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml \
+            -s ./tests/integration
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+  test_matrix_success:
+    name: All Integration Tests Passed
+    runs-on: ubuntu-latest
+    needs: [integration-tests]
+    steps:
+    - run: echo Done!

.github/workflows/run-tests.yml

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

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

@@ -0,0 +1,92 @@
+name: Run Unit Tests
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+on:
+  push:
+    branches:
+    - main
+  pull_request:
+
+jobs:
+  test-on-macos:
+    name: Test on macOS
+    runs-on: macos-13
+    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
+        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 --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit
+
+      - 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
+    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 --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+  test_matrix_success:
+    name: All Mac/Linux Tests Passed
+    runs-on: ubuntu-latest
+    needs: [test-on-macos, test-on-linux]
+    steps:
+    - run: echo Done!

.github/workflows/solve-issue.yml

@@ -10,8 +10,8 @@ permissions:
   issues: write
 
 jobs:
-  open-devin:
-    if: github.event.label.name == 'dogfood-this'
+  dogfood:
+    if: github.event.label.name == 'solve-this'
     runs-on: ubuntu-latest
     container:
       image: ghcr.io/opendevin/opendevin
@@ -43,7 +43,7 @@ jobs:
         LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
         SANDBOX_TYPE: exec
       run: |
-        python ./opendevin/main.py -d "./" -i 50 -f task.txt -d $GITHUB_WORKSPACE
+        WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE python ./opendevin/core/main.py -i 50 -f task.txt -d $GITHUB_WORKSPACE
         rm task.txt
 
     - name: Setup Git, Create Branch, and Commit Changes

.gitignore

@@ -57,7 +57,6 @@ cover/
 *.pot
 
 # Django stuff:
-*.log
 local_settings.py
 db.sqlite3
 db.sqlite3-journal

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

@@ -12,6 +12,20 @@ This guide is for people working on OpenDevin and editing the source code.
 
 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.
@@ -30,7 +44,7 @@ To configure the LM of your choice, follow these steps:
    ```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.
+   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.
 
 **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).
@@ -58,9 +72,25 @@ There is also [documentation for running with local models using ollama](./docs/
     make start-frontend
     ```
 
-### 6. Help
+### 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.

Makefile

@@ -1,3 +1,4 @@
+SHELL=/bin/bash
 # Makefile for OpenDevin project
 
 # Variables
@@ -11,11 +12,11 @@ CONFIG_FILE = config.toml
 PRECOMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
 
 # ANSI color codes
-GREEN=\033[0;32m
-YELLOW=\033[0;33m
-RED=\033[0;31m
-BLUE=\033[0;34m
-RESET=\033[0m
+GREEN=$(shell tput -Txterm setaf 2)
+YELLOW=$(shell tput -Txterm setaf 3)
+RED=$(shell tput -Txterm setaf 1)
+BLUE=$(shell tput -Txterm setaf 6)
+RESET=$(shell tput -Txterm sgr0)
 
 # Build
 build:
@@ -30,18 +31,33 @@ build:
 
 check-dependencies:
 	@echo "$(YELLOW)Checking dependencies...$(RESET)"
+	@$(MAKE) -s check-system
 	@$(MAKE) -s check-python
 	@$(MAKE) -s check-npm
+	@$(MAKE) -s check-nodejs
 	@$(MAKE) -s check-docker
 	@$(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 \
+		echo "$(BLUE)Linux detected.$(RESET)"; \
+	elif [ "$$(uname -r | grep -i microsoft)" ]; then \
+		echo "$(BLUE)Windows Subsystem for Linux detected.$(RESET)"; \
+	else \
+		echo "$(RED)Unsupported system detected. Please use macOS, Linux, or Windows Subsystem for Linux (WSL).$(RESET)"; \
+		exit 1; \
+	fi
+
 check-python:
 	@echo "$(YELLOW)Checking Python installation...$(RESET)"
-	@if command -v python3 > /dev/null; then \
-		echo "$(BLUE)$(shell python3 --version) is already installed.$(RESET)"; \
+	@if command -v python3.11 > /dev/null; then \
+		echo "$(BLUE)$(shell python3.11 --version) is already installed.$(RESET)"; \
 	else \
-		echo "$(RED)Python 3 is not installed. Please install Python 3 to continue.$(RESET)"; \
+		echo "$(RED)Python 3.11 is not installed. Please install Python 3.11 to continue.$(RESET)"; \
 		exit 1; \
 	fi
 
@@ -54,6 +70,22 @@ check-npm:
 		exit 1; \
 	fi
 
+check-nodejs:
+	@echo "$(YELLOW)Checking Node.js installation...$(RESET)"
+	@if command -v node > /dev/null; then \
+		NODE_VERSION=$(shell node --version | sed -E 's/v//g'); \
+		IFS='.' read -r -a NODE_VERSION_ARRAY <<< "$$NODE_VERSION"; \
+		if [ "$${NODE_VERSION_ARRAY[0]}" -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...$(RESET)"
 	@if command -v docker > /dev/null; then \
@@ -66,10 +98,19 @@ check-docker:
 check-poetry:
 	@echo "$(YELLOW)Checking Poetry installation...$(RESET)"
 	@if command -v poetry > /dev/null; then \
-		echo "$(BLUE)$(shell poetry --version) is already installed.$(RESET)"; \
+		POETRY_VERSION=$(shell poetry --version 2>&1 | sed -E 's/Poetry \(version ([0-9]+\.[0-9]+\.[0-9]+)\)/\1/'); \
+		IFS='.' read -r -a POETRY_VERSION_ARRAY <<< "$$POETRY_VERSION"; \
+		if [ $${POETRY_VERSION_ARRAY[0]} -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 "$(RED) curl -sSL https://install.python-poetry.org | python3 -$(RESET)"; \
+			echo "$(RED)More detail here: https://python-poetry.org/docs/#installing-with-the-official-installer$(RESET)"; \
+			exit 1; \
+		fi; \
 	else \
 		echo "$(RED)Poetry is not installed. You can install poetry by running the following command, then adding Poetry to your PATH:"; \
-		echo "$(RED) curl -sSL https://install.python-poetry.org | python3 -$(RESET)"; \
+		echo "$(RED) curl -sSL https://install.python-poetry.org | python3.11 -$(RESET)"; \
 		echo "$(RED)More detail here: https://python-poetry.org/docs/#installing-with-the-official-installer$(RESET)"; \
 		exit 1; \
 	fi
@@ -87,6 +128,7 @@ install-python-dependencies:
 		poetry run pip install chroma-hnswlib; \
 	fi
 	@poetry install --without evaluation
+	@poetry run playwright install --with-deps chromium
 	@echo "$(GREEN)Python dependencies installed successfully.$(RESET)"
 
 install-frontend-dependencies:
@@ -106,6 +148,25 @@ install-precommit-hooks:
 	@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 $$(git diff --name-only $$(git merge-base main $$(git branch --show-current)) $$(git branch --show-current) | tr '\n' ' ') --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
@@ -113,12 +174,12 @@ build-frontend:
 # Start backend
 start-backend:
 	@echo "$(YELLOW)Starting backend...$(RESET)"
-	@poetry run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT)
+	@poetry run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT) --reload --reload-exclude "workspace/*"
 
 # Start frontend
 start-frontend:
 	@echo "$(YELLOW)Starting frontend...$(RESET)"
-	@cd frontend && BACKEND_HOST=$(BACKEND_HOST) FRONTEND_PORT=$(FRONTEND_PORT) npm run start
+	@cd frontend && VITE_BACKEND_HOST=$(BACKEND_HOST) VITE_FRONTEND_PORT=$(FRONTEND_PORT) npm run start
 
 # Run the app
 run:
@@ -144,7 +205,7 @@ setup-config:
 	@echo "$(GREEN)Config.toml setup completed.$(RESET)"
 
 setup-config-prompts:
-	@read -p "Enter your LLM Model name (see https://docs.litellm.ai/docs/providers for full list) [default: $(DEFAULT_MODEL)]: " llm_model; \
+	@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
 
@@ -154,17 +215,27 @@ setup-config-prompts:
 	@read -p "Enter your LLM Base URL [mostly used for local LLMs, leave blank if not needed - example: http://localhost:5001/v1/]: " llm_base_url; \
 	 if [[ ! -z "$$llm_base_url" ]]; then echo "LLM_BASE_URL=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; fi
 
-	@echo "Enter your LLM Embedding Model\nChoices are openai, azureopenai, llama2 or leave blank to default to 'BAAI/bge-small-en-v1.5' via huggingface"; \
-	 read -p "> " llm_embedding_model; \
-	 	echo "LLM_EMBEDDING_MODEL=\"$$llm_embedding_model\"" >> $(CONFIG_FILE).tmp; \
-		if [ "$$llm_embedding_model" = "llama2" ]; then \
-			read -p "Enter the local model URL (will overwrite LLM_BASE_URL): " llm_base_url; \
-				echo "LLM_BASE_URL=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
+	@echo "Enter your LLM Embedding Model"; \
+		echo "Choices are:"; \
+		echo "  - openai"; \
+		echo "  - azureopenai"; \
+		echo "  - Embeddings available only with OllamaEmbedding:"; \
+		echo "    - llama2"; \
+		echo "    - mxbai-embed-large"; \
+		echo "    - nomic-embed-text"; \
+		echo "    - all-minilm"; \
+		echo "    - stable-code"; \
+		echo "  - Leave blank to default to 'BAAI/bge-small-en-v1.5' via huggingface"; \
+		read -p "> " llm_embedding_model; \
+		echo "LLM_EMBEDDING_MODEL=\"$$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" ] || [ "$$llm_embedding_model" = "stable-code" ]; then \
+			read -p "Enter the local model URL for the embedding model (will set LLM_EMBEDDING_BASE_URL): " llm_embedding_base_url; \
+				echo "LLM_EMBEDDING_BASE_URL=\"$$llm_embedding_base_url\"" >> $(CONFIG_FILE).tmp; \
 		elif [ "$$llm_embedding_model" = "azureopenai" ]; then \
 			read -p "Enter the Azure endpoint URL (will overwrite LLM_BASE_URL): " llm_base_url; \
 				echo "LLM_BASE_URL=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
-			read -p "Enter the Azure LLM Deployment Name: " llm_deployment_name; \
-				echo "LLM_DEPLOYMENT_NAME=\"$$llm_deployment_name\"" >> $(CONFIG_FILE).tmp; \
+			read -p "Enter the Azure LLM Embedding Deployment Name: " llm_embedding_deployment_name; \
+				echo "LLM_EMBEDDING_DEPLOYMENT_NAME=\"$$llm_embedding_deployment_name\"" >> $(CONFIG_FILE).tmp; \
 			read -p "Enter the Azure API Version: " llm_api_version; \
 				echo "LLM_API_VERSION=\"$$llm_api_version\"" >> $(CONFIG_FILE).tmp; \
 		fi
@@ -173,11 +244,18 @@ setup-config-prompts:
 	 workspace_dir=$${workspace_dir:-$(DEFAULT_WORKSPACE_DIR)}; \
 	 echo "WORKSPACE_BASE=\"$$workspace_dir\"" >> $(CONFIG_FILE).tmp
 
+# 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 "$(BLUE)Usage: make [target]$(RESET)"
 	@echo "Targets:"
 	@echo "  $(GREEN)build$(RESET)               - Build project, including environment setup and dependencies."
+	@echo "  $(GREEN)lint$(RESET)                - Run linters on the project."
 	@echo "  $(GREEN)setup-config$(RESET)        - Setup the configuration for OpenDevin by providing LLM API key,"
 	@echo "                        LLM Model name, and workspace directory."
 	@echo "  $(GREEN)start-backend$(RESET)       - Start the backend server for the OpenDevin project."
@@ -187,4 +265,4 @@ help:
 	@echo "  $(GREEN)help$(RESET)                - Display this help message, providing information on available targets."
 
 # Phony targets
-.PHONY: build check-dependencies check-python check-npm check-docker check-poetry pull-docker-image install-python-dependencies install-frontend-dependencies install-precommit-hooks start-backend start-frontend run setup-config setup-config-prompts help
+.PHONY: build check-dependencies check-python check-npm check-docker check-poetry pull-docker-image install-python-dependencies install-frontend-dependencies install-precommit-hooks lint start-backend start-frontend run setup-config setup-config-prompts help

README.md

@@ -1,4 +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.
@@ -25,156 +24,22 @@
   <a href="https://github.com/OpenDevin/OpenDevin/issues"><img src="https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge" alt="Issues"></a>
   <a href="https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE"><img src="https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge" alt="MIT License"></a>
   </br>
-  <a href="https://join.slack.com/t/opendevin/shared_invite/zt-2etftj1dd-X1fDL2PYIVpsmJZkqEYANw"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
-  <a href="https://discord.gg/mBuDGRzzES"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
+  <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>
 </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/Documenation-OpenDevin-blue?logo=googledocs&logoColor=white&style=for-the-badge" alt="Check out the documentation"></a>
 </div>
 
-
-
-
-<!-- TABLE OF CONTENTS -->
-<details>
-  <summary>🗂️ Table of Contents</summary>
-  <ol>
-    <li><a href="#-mission">🎯 Mission</a></li>
-    <li><a href="#-what-is-devin">🤔 What is Devin?</a></li>
-    <li><a href="#-why-opendevin">🐚 Why OpenDevin?</a></li>
-    <li><a href="#-project-status">🚧 Project Status</a></li>
-      <a href="#-get-started">🚀 Get Started</a>
-      <ul>
-        <li><a href="#1-requirements">1. Requirements</a></li>
-        <li><a href="#2-build-and-setup">2. Build and Setup</a></li>
-        <li><a href="#3-run-the-application">3. Run the Application</a></li>
-        <li><a href="#4-individual-server-startup">4. Individual Server Startup</a></li>
-        <li><a href="#5-help">5. Help</a></li>
-      </ul>
-    </li>
-    <li><a href="#%EF%B8%8F-research-strategy">⭐️ Research Strategy</a></li>
-    <li><a href="#-how-to-contribute">🤝 How to Contribute</a></li>
-    <li><a href="#-join-our-community">🤖 Join Our Community</a></li>
-    <li><a href="#%EF%B8%8F-built-with">🛠️ Built With</a></li>
-    <li><a href="#-license">📜 License</a></li>
-  </ol>
-</details>
-
 ## 🎯 Mission
 
-[Project Demo Video](https://github.com/OpenDevin/OpenDevin/assets/38853559/71a472cc-df34-430c-8b1d-4d7286c807c9)
-
-
 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.
 
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
-
-## 🤔 What is Devin?
-Devin represents a cutting-edge autonomous agent designed to navigate the complexities of software engineering. It leverages a combination of tools such as a shell, code editor, and web browser, showcasing the untapped potential of LLMs in software development. Our goal is to explore and expand upon Devin's capabilities, identifying both its strengths and areas for improvement, to guide the progress of open code models.
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
-
-## 🐚 Why OpenDevin?
-The OpenDevin project is born out of a desire to replicate, enhance, and innovate beyond the original Devin model. By engaging the open-source community, we aim to tackle the challenges faced by Code LLMs in practical scenarios, producing works that significantly contribute to the community and pave the way for future advancements.
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
-
-## 🚧 Project Status
-
-OpenDevin is currently a work in progress, but you can already run the alpha version to see the end-to-end system in action. The project team is actively working on the following key milestones:
-
-- **UI**: Developing a user-friendly interface, including a chat interface, a shell demonstrating commands, and a web browser.
-- **Architecture**: Building a stable agent framework with a robust backend that can read, write, and run simple commands.
-- **Agent Capabilities**: Enhancing the agent's abilities to generate bash scripts, run tests, and perform other software engineering tasks.
-- **Evaluation**: Establishing a minimal evaluation pipeline that is consistent with Devin's evaluation criteria.
-
-After completing the MVP, the team will focus on research in various areas, including foundation models, specialist capabilities, evaluation, and agent studies.
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
-
-## ⚠️ Caveats and Warnings
-* OpenDevin is still an alpha project. It is changing very quickly and is unstable. We are working on getting a stable release out in the coming weeks.
-* OpenDevin will issue many prompts to the LLM you configure. Most of these LLMs cost money--be sure to set spending limits and monitor usage.
-* OpenDevin runs `bash` commands within a Docker sandbox, so it should not affect your machine. But your workspace directory will be attached to that sandbox, and files in the directory may be modified or deleted.
-* Our default Agent is currently the MonologueAgent, which has limited capabilities, but is fairly stable. We're working on other Agent implementations, including [SWE Agent](https://swe-agent.com/). You can [read about our current set of agents here](./docs/documentation/Agents.md).
-
-## 🚀 Get Started
-
-Getting started with the OpenDevin project is incredibly easy. Follow these simple steps to set up and run OpenDevin on your system:
-
-The easiest way to run OpenDevin is inside a Docker container.
-You can run:
-```bash
-# Your OpenAI API key, or any other LLM API key
-export LLM_API_KEY="sk-..."
-
-# The directory you want OpenDevin to modify. MUST be an absolute path!
-export WORKSPACE_DIR=$(pwd)/workspace
-
-docker run \
-    -e LLM_API_KEY \
-    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_DIR \
-    -v $WORKSPACE_DIR:/opt/workspace_base \
-    -v /var/run/docker.sock:/var/run/docker.sock \
-    -p 3000:3000 \
-    ghcr.io/opendevin/opendevin:latest
-```
-Replace `$(pwd)/workspace` with the path to the code you want OpenDevin to work with.
-
-You can find opendevin running at `http://localhost:3000`.
-
-See [Development.md](Development.md) for instructions on running OpenDevin without Docker.
-
-## 🤖 LLM Backends
-OpenDevin can work with any LLM backend.
-For a full list of the LM providers and models available, please consult the
-[litellm documentation](https://docs.litellm.ai/docs/providers).
-
-The `LLM_MODEL` environment variable controls which model is used in programmatic interactions,
-but choosing a model in the OpenDevin UI will override this setting.
-
-The following environment variables might be necessary for some LLMs:
-* `LLM_API_KEY`
-* `LLM_BASE_URL`
-* `LLM_EMBEDDING_MODEL`
-* `LLM_DEPLOYMENT_NAME`
-* `LLM_API_VERSION`
-
-**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).
-
-There is also [documentation for running with local models using ollama](./docs/documentation/LOCAL_LLM_GUIDE.md).
-
-## ⭐️ 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.
+To learn more and to use OpenDevin, check out our [documentation](https://opendevin.github.io/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;">
@@ -202,8 +67,8 @@ For details, please check [this document](./CONTRIBUTING.md).
 
 Now we have both Slack workspace for the collaboration on building OpenDevin and Discord server for discussion about anything related, e.g., this project, LLM, agent, etc.
 
-* [Slack workspace](https://join.slack.com/t/opendevin/shared_invite/zt-2etftj1dd-X1fDL2PYIVpsmJZkqEYANw)
-* [Discord server](https://discord.gg/mBuDGRzzES)
+- [Slack workspace](https://join.slack.com/t/opendevin/shared_invite/zt-2ggtwn3k5-PvAA2LUmqGHVZ~XzGq~ILw)
+- [Discord server](https://discord.gg/ESHStjSjD4)
 
 If you would love to contribute, feel free to join our community (note that now there is no need to fill in the [form](https://forms.gle/758d5p6Ve8r2nxxq6)). Let's simplify software engineering together!
 
@@ -211,14 +76,6 @@ If you would love to contribute, feel free to join our community (note that now
 
 [![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 ↑

agenthub/README.md

@@ -26,6 +26,7 @@ The `state` contains:
 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
+- [`IPythonRunCellAction`](../opendevin/action/bash.py) - Execute a block of Python code interactively (in Jupyter notebook) and receives `CmdOutputObservation`. Requires setting up `jupyter` [plugin](../opendevin/sandbox/plugins) as a requirement.
 - [`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
@@ -33,6 +34,7 @@ Here is a list of available Actions, which can be returned by `agent.step()`:
 - [`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)
+- [`AgentTalkAction`](../opendevin/action/agent.py) - A no-op that allows the agent to add plaintext to the history and talk to the user.
 - [`AgentFinishAction`](../opendevin/action/agent.py) - Stops the control loop, allowing the user to enter a new task
 
 You can use `action.to_dict()` and `action_from_dict` to serialize and deserialize actions.

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 +1,108 @@
+from typing import List
+
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.events.action import (
+    Action,
+    AgentThinkAction,
+    FileReadAction,
+    FileWriteAction,
+)
+from opendevin.events.observation import Observation
+from opendevin.llm.llm import LLM
+
+from .parser import parse_command
+from .prompts import (
+    CONTEXT_PROMPT,
+    MEMORY_FORMAT,
+    NO_ACTION,
+    STEP_PROMPT,
+    SYSTEM_MESSAGE,
+)
+
+
+class SWEAgent(Agent):
+    """
+    An attempt to recreate swe_agent with output parsing, prompting style, and Application Computer Interface (ACI).
+
+    SWE-agent includes ACI functions like 'goto', 'search_for', 'edit', 'scroll', 'run'
+    """
+
+    def __init__(self, llm: LLM):
+        super().__init__(llm)
+        self.memory_window = 4
+        self.max_retries = 2
+        self.running_memory: List[str] = []
+        self.cur_file: str = ''
+        self.cur_line: int = 0
+
+    def _remember(self, action: Action, observation: Observation) -> None:
+        """Agent has a limited memory of the few steps implemented as a queue"""
+        memory = MEMORY_FORMAT(action.to_memory(), observation.to_memory())
+        self.running_memory.append(memory)
+
+    def _think_act(self, messages: List[dict]) -> tuple[Action, str]:
+        resp = self.llm.completion(
+            messages=messages,
+            temperature=0.05,
+        )
+        action_resp = resp['choices'][0]['message']['content']
+        print(f"\033[1m\033[91m{resp['usage']}\033[0m")
+        print(
+            '\n==== RAW OUTPUT ====',
+            f'\033[96m{action_resp}\033[0m',
+            '==== END RAW ====\n',
+            sep='\n',
+        )
+        return parse_command(action_resp, self.cur_file, self.cur_line)
+
+    def _update(self, action: Action) -> None:
+        if isinstance(action, (FileReadAction, FileWriteAction)):
+            self.cur_file = action.path
+            self.cur_line = action.start
+
+    def step(self, state: State) -> Action:
+        """
+        SWE-Agent step:
+            1. Get context - past actions, custom commands, current step
+            2. Perform think-act - prompt model for action and reasoning
+            3. Catch errors - ensure model takes action (5 attempts max)
+        """
+        for prev_action, obs in state.updated_info:
+            self._remember(prev_action, obs)
+
+        prompt = STEP_PROMPT(state.plan.main_goal, self.cur_file, self.cur_line)
+
+        msgs = [
+            {'content': SYSTEM_MESSAGE, 'role': 'system'},
+            {'content': prompt, 'role': 'user'},
+        ]
+
+        if len(self.running_memory) > 0:
+            context = CONTEXT_PROMPT(self.running_memory, self.memory_window)
+            msgs.insert(1, {'content': context, 'role': 'user'})
+        # clrs = [''] * (len(msgs)-2) + ['\033[0;36m', '\033[0;35m']
+        # print('\n\n'.join([c+m['content']+'\033[0m' for c, m in zip(clrs, msgs)]))
+        action, thought = self._think_act(messages=msgs)
+
+        start_msg_len = len(msgs)
+        while not action and len(msgs) < self.max_retries + start_msg_len:
+            error = NO_ACTION(thought)
+            error_msg = {'content': error, 'role': 'user'}
+            msgs.append(error_msg)
+            action, thought = self._think_act(messages=msgs)
+
+        if not action:
+            action = AgentThinkAction(thought)
+
+        self._update(action)
+        self.latest_action = action
+        return action
+
+    def search_memory(self, query: str) -> List[str]:
+        return [item for item in self.running_memory if query in item]
+
+    def reset(self) -> None:
+        """Used to reset the agent"""
+        self.running_memory = []
+        super().reset()

agenthub/SWE_agent/parser.py

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

agenthub/SWE_agent/prompts.py

@@ -0,0 +1,206 @@
+
+DEFAULT_COMMANDS_DICT = {
+    'exit': 'Executed when task is complete',
+    'read <file_name> [<start_line>] [<end_line>]': "Shows a given file's contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. By default the whole file will be read.",
+    'write <file> <changes> [<start_line>] [<end_line>]': 'Modifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>. Default start_line = 0 and end_line = -1. Calling this with no line args will replace the whole file.',
+    'browse <url>': 'Returns the text version of any url, this can be useful to look up documentation or finding issues on github',
+    'scroll_up': 'Takes no arguments. This will scroll up and show you the 100 lines above your current lines',
+    'scroll_down': 'Takes no arguments. This will scroll down and show you the 100 lines below your current lines',
+    'edit <start_line> <end_line> <changes>': 'This will modify lines in the currently open file. use start_line and end_line to designate which lines to change and then write the multiline changes',
+    'goto <line_num>': 'This will take you directly to a line and show you the 100 lines below it.',
+    '<bash_command> <args>': 'You can use any bash command you need (cd, ls, rm, grep, dir, mv, wget, git, zip, etc.) with their arguments included',
+    'pip install <package>': 'You can use this to import python packages. Make sure you include the correct package name when using this command.',
+    'ls': 'Use the ls command to view all the files in your current directory, this is a good starting point.',
+    'NOT ALLOWED': 'You cannot use interactive commands like python or node'
+}
+
+COMMAND_USAGE = {
+    'exit': 'Usage:\n```\nexit\n```\nExecuted when task is complete',
+    'read': "Args:\n<file_name> [<start_line>] [<end_line>]\nUsage:\n```\nread file.py\n```\nor\n```\nread example.py <start_line> <end_line>\n```\nShows a given file's contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. by default the whole file will be read.",
+    'write': 'Args:\n<file> <changes> [<start_line>] [<end_line>]\nUsage:\n```\nwrite "def main():\n    print("This is line one")" 0 2\n```\nModifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>. Default start_line = 0 and end_line = -1. Calling this with no line args will replace the whole file.',
+    'edit': 'Args:\n<start_line> <end_line> <changes>\nUsage:\n```\nedit 0 1 import pandas as pd\n```\nThis will modify the current file you are in with the changes you make between the line numbers you designate',
+    'goto': 'Args:\n<line_num>\nUsage:\n```\ngoto <line_num>\n```\nThis will show you the 100 lines below and including the line you specify within your current file.',
+    'scroll_up': 'Usage:\n```\nscroll_up\n```\nThis will return the 100 lines above where you are currently at',
+    'scroll_down': 'Usage:\n```\nscroll_down\n```\nThis will return the 100 line below where you are currently at',
+    'browse': 'Args:\n<url>\nUsage:\n```\nbrowse https://github.com/OpenDevin/OpenDevin\n```\nThis will fetch the Text elements from the given url and show them to you.',
+}
+
+DEFAULT_COMMANDS = '\n'.join(
+    [k + ' - ' + v for k, v in DEFAULT_COMMANDS_DICT.items()])
+
+# 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 am an autonomous coding agent, here to provide solutions for coding issues.
+You have been designed to assist you with a wide range of programming tasks, from code editing and debugging to testing and deployment.
+You have access to a variety of tools and commands that you can use to help you solve problems efficiently.
+
+{GENERAL_GUIDELINES}
+
+{DOCUMENTATION}
+""".strip()
+
+
+def NO_ACTION(latest): return f"""
+You did not include any action to take in your most recent output:
+
+===== Output ======
+{latest}
+==== End Output ===
+
+Remember these are the custom commands you can use:
+{DOCUMENTATION}
+
+Lets try that again, it is very important that you adhere to the output format
+This time, be sure to use the exact format below, replacing anything in <> with the appropriate value(s):
+{RESPONSE_FORMAT}
+
+It is crucial you use the format provided as the output will be parsed automatically.
+"""
+
+
+def file_info(file: str, line: int):
+    if file:
+        return f"""CURRENT WORKSPACE:
+    Open File: {file} on line {line}
+    You can use these commands with the current file:
+    Navigation: `scroll_up`, `scroll_down`, and `goto <line>`
+    Modification: `edit <start_line> <end_line> <changes>`
+    """
+
+
+def STEP_PROMPT(task, file, line_num): return f"""
+{RESPONSE_FORMAT}
+You are currently trying to complete this task:
+{task}
+
+{file_info(file, line_num)}
+
+Keep all of the guidelines above in mind when you are thinking and making code.
+Please come up with a thought and action based on your current task and latest steps.
+Make sure that you do not repeat the same actions, there will not be any changes in result if you do not changes anything.
+Be very strict about the formatting that you use and make sure you follow the guidelines.
+NEVER output multiple commands. ONLY take ONE STEP at a time.
+When you have completed your task run the "exit" command.
+Begin with your thought about the next step and then come up with an action to perform your thought.
+""".strip()
+
+
+def unpack_dict(data: dict, restrict: list[str] = []):
+    lines = []
+    for key, value in data.items():
+        if key in restrict:
+            continue
+        elif isinstance(value, dict):
+            nested_str = unpack_dict(value, restrict).replace('\n', '\n  ')
+            val = f'{key}:' + '\n  ' + f'{nested_str}'
+            lines.append(val)
+        else:
+            lines.append(f'{key}: {value}')
+    return '\n'.join(lines)
+
+
+def MEMORY_FORMAT(act, obs): return f"""
+Previous Action:
+{unpack_dict(act, ["content"])}
+
+Output from Action:
+{unpack_dict(obs)}
+""".strip()
+
+
+def CONTEXT_PROMPT(memory, window):
+    res = f'These are your past {window} actions:\n'
+    window_size = window if len(memory) > window else len(memory)
+    cur_mems = memory[-window_size:]
+    res += '===== Previous Actions =====\n'
+    for idx, mem in enumerate(cur_mems):
+        res += f'\nMemory {idx}:\n{mem}\n'
+    res += '======= End Actions =======\n'
+    res += 'Use these memories to provide additional context to the problem you are solving.\nRemember that you have already completed these steps so you do not need to perform them again.'
+    return res

agenthub/__init__.py

@@ -1,9 +1,42 @@
 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,
+    codeact_agent,
+    delegator_agent,
+    dummy_agent,
+    monologue_agent,
+    planner_agent,
+)
+
+__all__ = [
+    'monologue_agent',
+    'codeact_agent',
+    'planner_agent',
+    'SWE_agent',
+    'delegator_agent',
+    'dummy_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/codeact_agent/README.md

@@ -1,23 +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/2402.13463), [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).
 
-**NOTE: This agent is still highly experimental and under active development to reach the capability described in the original paper & [repo](https://github.com/xingyaoww/code-act).**
+The conceptual idea is illustrated below. At each turn, the agent can:
 
-<video src="https://github.com/xingyaoww/code-act/assets/38853559/62c80ada-62ce-447e-811c-fc801dd4beac"> </video>
-*Demo of the expected capability - work-in-progress.*
+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.
 
-```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."
-```
+![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)

agenthub/codeact_agent/codeact_agent.py

@@ -1,74 +1,109 @@
 import re
 from typing import List, Mapping
 
-from opendevin.action import (
+from agenthub.codeact_agent.prompt import EXAMPLES, SYSTEM_MESSAGE
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.events.action import (
     Action,
     AgentEchoAction,
     AgentFinishAction,
+    AgentTalkAction,
     CmdRunAction,
+    IPythonRunCellAction,
+    NullAction,
 )
-from opendevin.agent import Agent
-from opendevin.llm.llm import LLM
-from opendevin.observation import (
+from opendevin.events.observation import (
     AgentMessageObservation,
     CmdOutputObservation,
+    IPythonRunCellObservation,
+    UserMessageObservation,
 )
-from opendevin.parse_commands import parse_command_file
-from opendevin.state import State
-
-COMMAND_DOCS = parse_command_file()
-COMMAND_SEGMENT = (
-    f"""
-
-Apart from the standard bash commands, you can also use the following special commands:
-{COMMAND_DOCS}
-"""
-    if COMMAND_DOCS is not None
-    else ''
-)
-SYSTEM_MESSAGE = f"""You are a helpful assistant. You will be provided access (as root) to a bash shell to complete user-provided tasks.
-You will be able to execute commands in the bash shell, interact with the file system, install packages, and receive the output of your commands.
-
-DO NOT provide code in ```triple backticks```. Instead, you should execute bash command on behalf of the user by wrapping them with <execute> and </execute>.
-For example:
-
-You can list the files in the current directory by executing the following command:
-<execute>ls</execute>
-
-You can also install packages using pip:
-<execute> pip install numpy </execute>
-
-You can also write a block of code to a file:
-<execute>
-echo "import math
-print(math.pi)" > math.py
-</execute>
-{COMMAND_SEGMENT}
-
-When you are done, execute the following to close the shell and end the conversation:
-<execute>exit</execute>
-"""
-
-INVALID_INPUT_MESSAGE = (
-    "I don't understand your input. \n"
-    'If you want to execute command, please use <execute> YOUR_COMMAND_HERE </execute>.\n'
-    'If you already completed the task, please exit the shell by generating: <execute> exit </execute>.'
+from opendevin.llm.llm import LLM
+from opendevin.runtime.plugins import (
+    JupyterRequirement,
+    PluginRequirement,
+    SWEAgentCommandsRequirement,
 )
 
 
 def parse_response(response) -> str:
     action = response.choices[0].message.content
-    if '<execute>' in action and '</execute>' not in action:
-        action += '</execute>'
+    for lang in ['bash', 'ipython']:
+        if f'<execute_{lang}>' in action and f'</execute_{lang}>' not in action:
+            action += f'</execute_{lang}>'
     return action
 
 
+def truncate_observation(observation: str, max_chars: int = 5000) -> 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:]
+    )
+
+
 class CodeActAgent(Agent):
     """
     The Code Act Agent is a minimalist agent.
     The agent works by passing the model a list of action-observation pairs and prompting the model to take the next step.
+
+    ### 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] = [
+        JupyterRequirement(),
+        SWEAgentCommandsRequirement(),
+    ]
+    SUPPORTED_ACTIONS = (
+        CmdRunAction,
+        IPythonRunCellAction,
+        AgentEchoAction,
+        AgentTalkAction,
+        NullAction,
+    )
+    SUPPORTED_OBSERVATIONS = (
+        AgentMessageObservation,
+        UserMessageObservation,
+        CmdOutputObservation,
+        IPythonRunCellObservation,
+    )
+
     def __init__(
         self,
         llm: LLM,
@@ -84,74 +119,106 @@ class CodeActAgent(Agent):
 
     def step(self, state: State) -> Action:
         """
-        Performs one step using the Code Act Agent.
+        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) - command action to run
-        - AgentEchoAction(content=INVALID_INPUT_MESSAGE) - invalid command output
-
-        Raises:
-        - NotImplementedError - for actions other than CmdOutputObservation or AgentMessageObservation
+        - CmdRunAction(command) - bash command to run
+        - IPythonRunCellAction(code) - IPython code to run
+        - AgentTalkAction(content) - Talk action to run (e.g. ask for clarification)
+        - AgentFinishAction() - end the interaction
         """
 
         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},
+                {
+                    'role': 'user',
+                    'content': (
+                        f'Here is an example of how you can interact with the environment for task solving:\n{EXAMPLES}\n\n'
+                        f"NOW, LET'S START!\n\n{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})
+                    prev_action, self.SUPPORTED_ACTIONS
+                ), f'{prev_action.__class__} is not supported (supported: {self.SUPPORTED_ACTIONS})'
+                # prev_action is already added to self.messages when returned
+
+                # handle observations
+                assert isinstance(
+                    obs, self.SUPPORTED_OBSERVATIONS
+                ), f'{obs.__class__} is not supported (supported: {self.SUPPORTED_OBSERVATIONS})'
+                if isinstance(obs, (AgentMessageObservation, UserMessageObservation)):
+                    self.messages.append({'role': 'user', 'content': obs.content})
+
+                    # User wants to exit
+                    if obs.content.strip() == '/exit':
+                        return AgentFinishAction()
                 elif isinstance(obs, CmdOutputObservation):
-                    content = 'OBSERVATION:\n' + obs.content
+                    content = 'OBSERVATION:\n' + truncate_observation(obs.content)
                     content += f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]]'
                     self.messages.append({'role': 'user', 'content': content})
+
+                elif isinstance(obs, IPythonRunCellObservation):
+                    content = 'OBSERVATION:\n' + obs.content
+                    # replace base64 images with a placeholder
+                    splited = content.split('\n')
+                    for i, line in enumerate(splited):
+                        if '![image](data:image/png;base64,' in line:
+                            splited[i] = (
+                                '![image](data:image/png;base64, ...) already displayed to user'
+                            )
+                    content = '\n'.join(splited)
+                    content = truncate_observation(content)
+                    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
+            stop=[
+                '</execute_ipython>',
+                '</execute_bash>',
+            ],
+            temperature=0.0,
         )
         action_str: str = parse_response(response)
-        state.num_of_chars += sum(len(message['content'])
-                                  for message in self.messages) + len(action_str)
+        state.num_of_chars += sum(
+            len(message['content']) for message in self.messages
+        ) + len(action_str)
         self.messages.append({'role': 'assistant', 'content': action_str})
 
-        command = re.search(r'<execute>(.*)</execute>', action_str, re.DOTALL)
-        if command is not None:
+        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 = command.group(1)
+            command_group = bash_command.group(1).strip()
             if command_group.strip() == 'exit':
                 return AgentFinishAction()
-            return CmdRunAction(command=command_group)
-            # # execute the code
-            # # TODO: does exit_code get loaded into Message?
-            # exit_code, observation = self.env.execute(command_group)
-            # self._history.append(Message(Role.ASSISTANT, observation))
+            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)
         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
+            # We assume the LLM is GOOD enough that when it returns pure natural language
+            # it want to talk to the user
+            return AgentTalkAction(content=action_str)
 
     def search_memory(self, query: str) -> List[str]:
         raise NotImplementedError('Implement this abstract method')

agenthub/codeact_agent/prompt.py

@@ -0,0 +1,226 @@
+from opendevin.runtime.plugins import SWEAgentCommandsRequirement
+
+_SWEAGENT_BASH_DOCS = '\n'.join(
+    filter(
+        lambda x: not x.startswith('submit'),
+        SWEAgentCommandsRequirement.documentation.split('\n'),
+    )
+)
+# _SWEAGENT_BASH_DOCS content below:
+"""
+open <path> [<line_number>] - opens the file at the given path in the editor. If line_number is provided, the window will be move to include that line
+goto <line_number> - moves the window to show <line_number>
+scroll_down - moves the window down {WINDOW} lines
+scroll_up - moves the window down {WINDOW} lines
+create <filename> - creates and opens a new file with the given name
+search_dir <search_term> [<dir>] - searches for search_term in all files in dir. If dir is not provided, searches in the current directory
+search_file <search_term> [<file>] - searches for search_term in file. If file is not provided, searches in the current open file
+find_file <file_name> [<dir>] - finds all files with the given name in dir. If dir is not provided, searches in the current directory
+edit <start_line>:<end_line>
+<replacement_text>
+end_of_edit - replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing the same command a second time will just lead to the same error message again.
+"""
+
+_COMMAND_DOCS = (
+    '\nApart from the standard bash commands, you can also use the following special commands in <execute_bash> environment:\n'
+    f'{_SWEAGENT_BASH_DOCS}'
+    "Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. If you'd like to add the line '        print(x)' you 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 = f"""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>.
+The assistant should attempt fewer things at a time instead of putting too much commands OR code in one "execute" block.
+The assistant can install Python packages through bash by <execute_bash> pip install [package needed] </execute_bash> and should always import packages and define variables before starting to use them.
+The assistant should stop <execute> and provide an answer when they have already obtained the answer from the execution result.
+
+{_COMMAND_DOCS}
+
+The assistant's response should be concise, but do express their thoughts.
+Try to include one of <execute_ipython> or <execute_bash> in each of your responses, unless it is a direct answer to a question OR a message to the user.
+IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
+"""
+
+EXAMPLES = """
+--- 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:
+Sure! Let me write the Python code for starting a web server and save it to a file `app.py`:
+<execute_ipython>
+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)
+'''
+with open('app.py', 'w') as f:
+    f.write(CODE)
+</execute_ipython>
+
+USER:
+Observation:
+[Code executed successfully with no output]
+
+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 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_bash>
+open app.py
+</execute_bash>
+
+USER:
+[File: /workspace/app.py (11 lines total)]
+1:
+2:from flask import Flask
+3:app = Flask(__name__)
+4:
+5:@app.route('/')
+6:def index():
+7:    numbers = list(range(1, 11))
+8:    return str(numbers)
+9:
+10:if __name__ == '__main__':
+11:    app.run(port=5000)
+
+ASSISTANT:
+I should edit the file to display the numbers in a table format. Let me do that for you:
+
+<execute_bash>
+edit 8:8 <<EOF
+    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
+EOF
+</execute_bash>
+
+USER:
+Observation:
+[File: /workspace/app.py (11 lines total)]
+1:
+2:from flask import Flask
+3:app = Flask(__name__)
+4:
+5:@app.route('/')
+6:def index():
+7:    numbers = list(range(1, 11))
+8:    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
+9:
+10:if __name__ == '__main__':
+11:    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:
+The file has been updated. Let me run the Python file again with the new changes:
+<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. Free free to let me know if you have any further requests!
+
+--- END OF EXAMPLE ---
+"""
+
+INVALID_INPUT_MESSAGE = (
+    "I don't understand your input. \n"
+    'If you want to execute a bash command, please use <execute_bash> YOUR_COMMAND_HERE </execute_bash>.\n'
+    'If you want to execute a block of Python code, please use <execute_ipython> YOUR_COMMAND_HERE </execute_ipython>.\n'
+)

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 +1,85 @@
+from typing import List
+
+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):
+    """
+    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'
+            return AgentDelegateAction(
+                agent='StudyRepoForTaskAgent', inputs={'task': state.plan.main_goal}
+            )
+
+        lastObservation = state.history[-1][1]
+        if not isinstance(lastObservation, AgentDelegateObservation):
+            raise Exception('Last observation is not an AgentDelegateObservation')
+
+        if self.current_delegate == 'study':
+            self.current_delegate = 'coder'
+            return AgentDelegateAction(
+                agent='Coder',
+                inputs={
+                    'task': state.plan.main_goal,
+                    'summary': lastObservation.outputs['summary'],
+                },
+            )
+        elif self.current_delegate == 'coder':
+            self.current_delegate = 'verifier'
+            return AgentDelegateAction(
+                agent='Verifier',
+                inputs={
+                    'task': state.plan.main_goal,
+                },
+            )
+        elif self.current_delegate == 'verifier':
+            if (
+                'completed' in lastObservation.outputs
+                and lastObservation.outputs['completed']
+            ):
+                return AgentFinishAction()
+            else:
+                self.current_delegate = 'coder'
+                return AgentDelegateAction(
+                    agent='Coder',
+                    inputs={
+                        'task': state.plan.main_goal,
+                        'summary': lastObservation.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 +1,159 @@
+import time
+from typing import List, TypedDict
+
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.events.action import (
+    Action,
+    AddTaskAction,
+    AgentFinishAction,
+    AgentRecallAction,
+    AgentThinkAction,
+    BrowseURLAction,
+    CmdRunAction,
+    FileReadAction,
+    FileWriteAction,
+    ModifyTaskAction,
+)
+from opendevin.events.observation import (
+    AgentRecallObservation,
+    CmdOutputObservation,
+    FileReadObservation,
+    FileWriteObservation,
+    NullObservation,
+    Observation,
+)
+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):
+    """
+    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(id='0.0', state='in_progress'),
+                'observations': [NullObservation('')],
+            },
+            {
+                'action': AgentThinkAction(thought='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 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': AgentFinishAction(),
+                '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 = state.history[hist_start + i][1].to_dict()
+                    expected_obs = expected_observations[i].to_dict()
+                    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 +1,14 @@
+## 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.

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 and have tested your work, 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
+  * `id` - the ID of the background command to kill

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/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/think.md

@@ -0,0 +1,2 @@
+* `think` - make a plan, set a goal, or record your thoughts. Arguments:
+  * `thought` - the thought to record

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 +1,107 @@
+import copy
+import json
+from typing import Dict, List
+
+from jinja2 import BaseLoader, Environment
+
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.core.exceptions import LLMOutputError
+from opendevin.events.action import Action, action_from_dict
+from opendevin.llm.llm import LLM
+
+from .instructions import instructions
+from .registry import all_microagents
+
+
+def parse_response(orig_response: str) -> Action:
+    json_start = orig_response.find('{')
+    json_end = orig_response.rfind('}') + 1
+    response = orig_response[json_start:json_end]
+    try:
+        action_dict = json.loads(response)
+    except json.JSONDecodeError as e:
+        raise LLMOutputError(
+            'Invalid JSON in response. Please make sure the response is a valid JSON object'
+        ) from e
+    action = action_from_dict(action_dict)
+    return action
+
+
+def my_encoder(obj):
+    """
+    Encodes objects as dictionaries
+
+    Parameters:
+    - obj (Object): An object that will be converted
+
+    Returns:
+    - dict: If the object can be converted it is returned in dict format
+    """
+    if hasattr(obj, 'to_dict'):
+        return obj.to_dict()
+
+
+def _remove_fields(obj, fields: set[str]):
+    """
+    Remove fields from an object
+
+    Parameters:
+    - obj (Object): The object to remove fields from
+    - fields (set[str]): A set of field names to remove from the object
+    """
+    if isinstance(obj, dict):
+        for field in fields:
+            if field in obj:
+                del obj[field]
+        for _, value in obj.items():
+            _remove_fields(value, fields)
+    elif isinstance(obj, list) or isinstance(obj, tuple):
+        for item in obj:
+            _remove_fields(item, fields)
+    elif hasattr(obj, '__dataclass_fields__'):
+        for field in fields:
+            if field in obj.__dataclass_fields__:
+                setattr(obj, field, None)
+        for value in obj.__dict__.values():
+            _remove_fields(value, fields)
+
+
+def to_json(obj, **kwargs):
+    """
+    Serialize an object to str format
+    """
+    # Remove things like screenshots that shouldn't be in a prompt
+    sanitized_obj = copy.deepcopy(obj)
+    _remove_fields(sanitized_obj, {'screenshot'})
+    return json.dumps(sanitized_obj, default=my_encoder, **kwargs)
+
+
+class MicroAgent(Agent):
+    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,
+            delegates=self.delegates,
+        )
+        messages = [{'content': prompt, 'role': 'user'}]
+        resp = self.llm.completion(messages=messages)
+        action_resp = resp['choices'][0]['message']['content']
+        state.num_of_chars += len(prompt) + len(action_resp)
+        action = parse_response(action_resp)
+        return action
+
+    def search_memory(self, query: str) -> List[str]:
+        return []

agenthub/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
+  codebase_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.plan.main_goal }}
+
+{% 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.think }}
+{{ instructions.actions.finish }}
+
+Do NOT finish until you have completed the tasks.
+
+## History
+{{ instructions.history_truncated }}
+{{ 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"
+generates: Action
+inputs: {}
+outputs:
+  answer: string

agenthub/micro/commit_writer/prompt.md

@@ -0,0 +1,28 @@
+# 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.
+
+## History
+{{ instructions.history_truncated }}
+{{ 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.finish }}
+
+## Format
+{{ instructions.format.action }}

agenthub/micro/instructions.py

@@ -0,0 +1,20 @@
+import os
+from typing import Dict
+
+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
+    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 +1,6 @@
+name: ManagerAgent
+description: Delegates tasks to microagents based on their area of expertise
+generates: Action
+inputs:
+  task: string
+outputs: {}

agenthub/micro/manager/prompt.md

@@ -0,0 +1,27 @@
+# Task
+You are in charge of accomplishing the following task:
+{{ state.plan.main_goal }}
+
+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.
+
+## Agents
+{% for name, details in delegates.items() %}
+### {{ name }}
+{{ details.description }}
+#### Inputs
+{{ to_json(details.inputs) }}
+{% endfor %}
+
+## History
+{{ instructions.history_truncated }}
+{{ to_json(state.history[-10:]) }}
+
+## Available Actions
+{{ instructions.actions.delegate }}
+{{ instructions.actions.finish }}
+
+## Format
+{{ instructions.format.action }}

agenthub/micro/math_agent/agent.yaml

@@ -0,0 +1,25 @@
+name: MathAgent
+description: "Solves simple and complex math problems using python"
+generates: Action
+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.plan.main_goal }}
+
+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 }}
+{{ 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 +1,6 @@
+name: PostgresAgent
+description: Writes and maintains PostgreSQL migrations
+generates: Action
+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.plan.main_goal }}
+
+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.think }}
+{{ instructions.actions.read }}
+{{ instructions.actions.write }}
+{{ instructions.actions.run }}
+
+## History
+{{ instructions.history_truncated }}
+{{ to_json(state.history[-10:]) }}
+
+## Format
+{{ instructions.format.action }}

agenthub/micro/registry.py

@@ -0,0 +1,25 @@
+import os
+
+import yaml
+
+all_microagents = {}
+
+for dir in os.listdir(os.path.dirname(__file__)):
+    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.think }}
+{{ 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 }}
+{{ 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 +1,25 @@
+# Task
+You are a software engineer. You've inherited an existing codebase, which you're
+learning about for the first time. You need to study the codebase to find all
+the information needed to complete this task:
+
+{{ state.plan.main_goal }}
+
+## Available Actions
+{{ instructions.actions.run }}
+{{ instructions.actions.read }}
+{{ instructions.actions.think }}
+{{ instructions.actions.finish }}
+
+You must ONLY `run` commands that have no side-effects, like `ls` and `grep`.
+
+Do NOT finish until you have a complete understanding of which parts of the
+codebase are relevant to the task, including particular files, functions, and classes.
+When you're done, put your summary in `outputs.summary` in the `finish` action.
+
+## History
+{{ instructions.history_truncated }}
+{{ to_json(state.history[-10:]) }}
+
+## Format
+{{ instructions.format.action }}

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 +1,27 @@
+# Task
+You are a quality assurance engineer. Another engineer has made changes to the
+codebase which are supposed to solve this task:
+
+{{ state.plan.main_goal }}
+
+Your goal is to verify that the changes are correct and bug-free.
+
+## Available Actions
+{{ instructions.actions.run }}
+{{ instructions.actions.read }}
+{{ instructions.actions.think }}
+{{ 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 }}
+{{ to_json(state.history[-10:]) }}
+
+## Format
+{{ instructions.format.action }}

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)

agenthub/monologue_agent/agent.py

@@ -1,33 +1,36 @@
 from typing import List
-from opendevin.agent import Agent
-from opendevin.state import State
-from opendevin.llm.llm import LLM
-from opendevin.schema import ActionType, ObservationType
-from opendevin.exceptions import AgentNoInstructionError
-
-from opendevin.action import (
-    Action,
-    NullAction,
-    CmdRunAction,
-    FileWriteAction,
-    FileReadAction,
-    AgentRecallAction,
-    BrowseURLAction,
-    AgentThinkAction,
-)
-
-from opendevin.observation import (
-    Observation,
-    NullObservation,
-    CmdOutputObservation,
-    FileReadObservation,
-    AgentRecallObservation,
-    BrowserOutputObservation,
-)
 
 import agenthub.monologue_agent.utils.prompts as prompts
 from agenthub.monologue_agent.utils.monologue import Monologue
-from agenthub.monologue_agent.utils.memory import LongTermMemory
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.core import config
+from opendevin.core.exceptions import AgentNoInstructionError
+from opendevin.core.schema import ActionType
+from opendevin.core.schema.config import ConfigType
+from opendevin.events.action import (
+    Action,
+    AgentRecallAction,
+    AgentThinkAction,
+    BrowseURLAction,
+    CmdRunAction,
+    FileReadAction,
+    FileWriteAction,
+    GitHubPushAction,
+    NullAction,
+)
+from opendevin.events.observation import (
+    AgentRecallObservation,
+    BrowserOutputObservation,
+    CmdOutputObservation,
+    FileReadObservation,
+    NullObservation,
+    Observation,
+)
+from opendevin.llm.llm import LLM
+
+if config.get(ConfigType.AGENT_MEMORY_ENABLED):
+    from agenthub.monologue_agent.utils.memory import LongTermMemory
 
 MAX_MONOLOGUE_LENGTH = 20000
 MAX_OUTPUT_LENGTH = 5000
@@ -53,7 +56,7 @@ INITIAL_THOUGHTS = [
     '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",
+    'WRITE echo "console.log(\'hello world\')" > test.js',
     '',
     "I just created test.js. I'll try and run it now.",
     'RUN node test.js',
@@ -68,13 +71,17 @@ INITIAL_THOUGHTS = [
     'BROWSE google.com',
     '<form><input type="text"></input><button type="submit"></button></form>',
     'I can browse the web too!',
+    'If I have done some work and I want to push it to github, I can do that also!',
+    "Let's do it.",
+    'PUSH owner/repo branch',
+    'The repo was successfully pushed to https://github.com/owner/repo/branch',
     '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.",
+    'It seems like there might be an existing project here. I should probably start by running `pwd` and `ls` to orient myself.',
 ]
 
 
@@ -86,6 +93,8 @@ class MonologueAgent(Agent):
     """
 
     _initialized = False
+    monologue: Monologue
+    memory: 'LongTermMemory | None'
 
     def __init__(self, llm: LLM):
         """
@@ -95,8 +104,6 @@ class MonologueAgent(Agent):
         - 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):
         """
@@ -119,14 +126,17 @@ class MonologueAgent(Agent):
             )
 
         self.monologue.add_event(event)
-        self.memory.add_event(event)
+        if self.memory is not None:
+            self.memory.add_event(event)
         if self.monologue.get_total_length() > MAX_MONOLOGUE_LENGTH:
             self.monologue.condense(self.llm)
 
     def _initialize(self, task: str):
         """
-        Utilizes the INITIAL_THOUGHTS list to give the agent a context for it's capabilities and how to navigate the /workspace.
-        Short circuted to return when already initialized.
+        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.
 
         Parameters:
         - task (str): The initial goal statement provided by the user
@@ -140,35 +150,42 @@ class MonologueAgent(Agent):
 
         if task is None or task == '':
             raise AgentNoInstructionError()
-        self.monologue = Monologue()
-        self.memory = LongTermMemory()
 
-        output_type = ''
+        self.monologue = Monologue()
+        if config.get(ConfigType.AGENT_MEMORY_ENABLED):
+            self.memory = LongTermMemory()
+        else:
+            self.memory = None
+
+        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 != '':
+            if previous_action != '':
                 observation: Observation = NullObservation(content='')
-                if output_type == ObservationType.RUN:
+                if previous_action in {ActionType.RUN, ActionType.PUSH}:
                     observation = CmdOutputObservation(
                         content=thought, command_id=0, command=''
                     )
-                elif output_type == ObservationType.READ:
+                elif previous_action == ActionType.READ:
                     observation = FileReadObservation(content=thought, path='')
-                elif output_type == ObservationType.RECALL:
-                    observation = AgentRecallObservation(
-                        content=thought, memories=[])
-                elif output_type == ObservationType.BROWSE:
+                elif previous_action == ActionType.RECALL:
+                    observation = AgentRecallObservation(content=thought, memories=[])
+                elif previous_action == ActionType.BROWSE:
                     observation = BrowserOutputObservation(
                         content=thought, url='', screenshot=''
                     )
-                self._add_event(observation.to_dict())
-                output_type = ''
+                self._add_event(observation.to_memory())
+                previous_action = ''
             else:
                 action: Action = NullAction()
                 if thought.startswith('RUN'):
                     command = thought.split('RUN ')[1]
                     action = CmdRunAction(command)
-                    output_type = ActionType.RUN
+                    previous_action = ActionType.RUN
                 elif thought.startswith('WRITE'):
                     parts = thought.split('WRITE ')[1].split(' > ')
                     path = parts[1]
@@ -177,19 +194,23 @@ class MonologueAgent(Agent):
                 elif thought.startswith('READ'):
                     path = thought.split('READ ')[1]
                     action = FileReadAction(path=path)
-                    output_type = ActionType.READ
+                    previous_action = ActionType.READ
                 elif thought.startswith('RECALL'):
                     query = thought.split('RECALL ')[1]
                     action = AgentRecallAction(query=query)
-                    output_type = ActionType.RECALL
+                    previous_action = ActionType.RECALL
                 elif thought.startswith('BROWSE'):
                     url = thought.split('BROWSE ')[1]
                     action = BrowseURLAction(url=url)
-                    output_type = ActionType.BROWSE
+                    previous_action = ActionType.BROWSE
+                elif thought.startswith('PUSH'):
+                    owner_repo, branch = thought.split('PUSH ')[1].split(' ')
+                    owner, repo = owner_repo.split('/')
+                    action = GitHubPushAction(owner=owner, repo=repo, branch=branch)
+                    previous_action = ActionType.PUSH
                 else:
                     action = AgentThinkAction(thought=thought)
-                self._add_event(action.to_dict())
-        self._initialized = True
+                self._add_event(action.to_memory())
 
     def step(self, state: State) -> Action:
         """
@@ -203,8 +224,8 @@ class MonologueAgent(Agent):
         """
         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())
+            self._add_event(prev_action.to_memory())
+            self._add_event(obs.to_memory())
 
         state.updated_info = []
 
@@ -232,4 +253,12 @@ class MonologueAgent(Agent):
         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

@@ -1,4 +1,5 @@
 import json
+
 from json_repair import repair_json
 
 

agenthub/monologue_agent/utils/memory.py

@@ -1,44 +1,115 @@
-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
+import threading
+
+import chromadb
+import llama_index.embeddings.openai.base as llama_openai
+from llama_index.core import Document, VectorStoreIndex
+from llama_index.core.retrievers import VectorIndexRetriever
+from llama_index.vector_stores.chroma import ChromaVectorStore
+from openai._exceptions import APIConnectionError, InternalServerError, RateLimitError
+from tenacity import (
+    retry,
+    retry_if_exception_type,
+    stop_after_attempt,
+    wait_random_exponential,
+)
+
+from opendevin.core import config
+from opendevin.core.logger import opendevin_logger as logger
+from opendevin.core.schema.config import ConfigType
 
-from opendevin import config
 from . import json
 
-embedding_strategy = config.get('LLM_EMBEDDING_MODEL')
+num_retries = config.get(ConfigType.LLM_NUM_RETRIES)
+retry_min_wait = config.get(ConfigType.LLM_RETRY_MIN_WAIT)
+retry_max_wait = config.get(ConfigType.LLM_RETRY_MAX_WAIT)
+
+# llama-index includes a retry decorator around openai.get_embeddings() function
+# it is initialized with hard-coded values and errors
+# this non-customizable behavior is creating issues when it's retrying faster than providers' rate limits
+# this block attempts to banish it and replace it with our decorator, to allow users to set their own limits
+
+if hasattr(llama_openai.get_embeddings, '__wrapped__'):
+    original_get_embeddings = llama_openai.get_embeddings.__wrapped__
+else:
+    logger.warning('Cannot set custom retry limits.')  # warn
+    num_retries = 1
+    original_get_embeddings = llama_openai.get_embeddings
+
+
+def attempt_on_error(retry_state):
+    logger.error(
+        f'{retry_state.outcome.exception()}. Attempt #{retry_state.attempt_number} | You can customize these settings in the configuration.',
+        exc_info=False,
+    )
+    return True
+
+
+@retry(
+    reraise=True,
+    stop=stop_after_attempt(num_retries),
+    wait=wait_random_exponential(min=retry_min_wait, max=retry_max_wait),
+    retry=retry_if_exception_type(
+        (RateLimitError, APIConnectionError, InternalServerError)
+    ),
+    after=attempt_on_error,
+)
+def wrapper_get_embeddings(*args, **kwargs):
+    return original_get_embeddings(*args, **kwargs)
+
+
+llama_openai.get_embeddings = wrapper_get_embeddings
+
+embedding_strategy = config.get(ConfigType.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':
+supported_ollama_embed_models = [
+    'llama2',
+    'mxbai-embed-large',
+    'nomic-embed-text',
+    'all-minilm',
+    'stable-code',
+]
+if embedding_strategy in supported_ollama_embed_models:
     from llama_index.embeddings.ollama import OllamaEmbedding
+
     embed_model = OllamaEmbedding(
-        model_name='llama2',
-        base_url=config.get('LLM_BASE_URL', required=True),
+        model_name=embedding_strategy,
+        base_url=config.get(ConfigType.LLM_EMBEDDING_BASE_URL, required=True),
         ollama_additional_kwargs={'mirostat': 0},
     )
 elif embedding_strategy == 'openai':
     from llama_index.embeddings.openai import OpenAIEmbedding
+
     embed_model = OpenAIEmbedding(
         model='text-embedding-ada-002',
-        api_key=config.get('LLM_API_KEY', required=True)
+        api_key=config.get(ConfigType.LLM_API_KEY, required=True),
     )
 elif embedding_strategy == 'azureopenai':
     # Need to instruct to set these env variables in documentation
     from llama_index.embeddings.azure_openai import AzureOpenAIEmbedding
+
     embed_model = AzureOpenAIEmbedding(
         model='text-embedding-ada-002',
-        deployment_name=config.get('LLM_DEPLOYMENT_NAME', required=True),
-        api_key=config.get('LLM_API_KEY', required=True),
-        azure_endpoint=config.get('LLM_BASE_URL', required=True),
-        api_version=config.get('LLM_API_VERSION', required=True),
+        deployment_name=config.get(
+            ConfigType.LLM_EMBEDDING_DEPLOYMENT_NAME, required=True
+        ),
+        api_key=config.get(ConfigType.LLM_API_KEY, required=True),
+        azure_endpoint=config.get(ConfigType.LLM_BASE_URL, required=True),
+        api_version=config.get(ConfigType.LLM_API_VERSION, required=True),
     )
+elif (embedding_strategy is not None) and (embedding_strategy.lower() == 'none'):
+    # TODO: this works but is not elegant enough. The incentive is when
+    # monologue agent is not used, there is no reason we need to initialize an
+    # embedding model
+    embed_model = None
 else:
     from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-    embed_model = HuggingFaceEmbedding(
-        model_name='BAAI/bge-small-en-v1.5'
-    )
+
+    embed_model = HuggingFaceEmbedding(model_name='BAAI/bge-small-en-v1.5')
+
+
+sema = threading.Semaphore(value=config.get(ConfigType.AGENT_MEMORY_MAX_THREADS))
 
 
 class LongTermMemory:
@@ -55,8 +126,10 @@ class LongTermMemory:
         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)
+            vector_store, embed_model=embed_model
+        )
         self.thought_idx = 0
+        self._add_threads = []
 
     def add_event(self, event: dict):
         """
@@ -83,7 +156,14 @@ class LongTermMemory:
             },
         )
         self.thought_idx += 1
-        self.index.insert(doc)
+        logger.debug('Adding %s event to memory: %d', t, self.thought_idx)
+        thread = threading.Thread(target=self._add_doc, args=(doc,))
+        self._add_threads.append(thread)
+        thread.start()  # We add the doc concurrently so we don't have to wait ~500ms for the insert
+
+    def _add_doc(self, doc):
+        with sema:
+            self.index.insert(doc)
 
     def search(self, query: str, k: int = 10):
         """

agenthub/monologue_agent/utils/monologue.py

@@ -1,9 +1,8 @@
-import traceback
-
-from opendevin.llm.llm import LLM
-from opendevin.exceptions import AgentEventTypeError
 import agenthub.monologue_agent.utils.json as json
 import agenthub.monologue_agent.utils.prompts as prompts
+from opendevin.core.exceptions import AgentEventTypeError
+from opendevin.core.logger import opendevin_logger as logger
+from opendevin.llm.llm import LLM
 
 
 class Monologue:
@@ -53,7 +52,7 @@ class Monologue:
             try:
                 total_length += len(json.dumps(t))
             except TypeError as e:
-                print(f'Error serializing thought: {e}')
+                logger.error('Error serializing thought: %s', str(e), exc_info=False)
         return total_length
 
     def condense(self, llm: LLM):
@@ -64,7 +63,7 @@ class Monologue:
         - llm (LLM): llm to be used for summarization
 
         Raises:
-        - RunTimeError: When the condensing process fails for any reason
+        - Exception: the same exception as it got from the llm or processing the response
         """
 
         try:
@@ -74,5 +73,7 @@ class Monologue:
             summary_resp = resp['choices'][0]['message']['content']
             self.thoughts = prompts.parse_summary_response(summary_resp)
         except Exception as e:
-            traceback.print_exc()
-            raise RuntimeError(f'Error condensing thoughts: {e}')
+            logger.error('Error condensing thoughts: %s', str(e), exc_info=False)
+
+            # TODO If the llm fails with ContextWindowExceededError, we can try to condense the monologue chunk by chunk
+            raise

agenthub/monologue_agent/utils/prompts.py

@@ -1,18 +1,19 @@
+import re
+from json import JSONDecodeError
 from typing import List
 
-from . import json
-from json import JSONDecodeError
-
-import re
-
-from opendevin.action import (
-    action_from_dict,
+from opendevin.core import config
+from opendevin.core.exceptions import LLMOutputError
+from opendevin.core.schema.config import ConfigType
+from opendevin.events.action import (
     Action,
+    action_from_dict,
 )
-from opendevin.observation import (
+from opendevin.events.observation import (
     CmdOutputObservation,
 )
-from opendevin.exceptions import LLMOutputError
+
+from . import json
 
 ACTION_PROMPT = """
 You're a thoughtful robot. Your main task is this:
@@ -26,8 +27,8 @@ This is your internal monologue, in JSON format:
 
 
 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
 
@@ -44,6 +45,10 @@ Here are the possible actions:
   * `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:
@@ -52,16 +57,20 @@ Here are the possible actions:
 
 %(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, browse, push, and recall actions.
 You should never act twice in a row without thinking. But if your last several
 actions are all "think" actions, you should consider taking a different action.
 
 Notes:
-* your environment is Debian Linux. You can install software with `apt`
-* your working directory will not change, even if you run `cd`. All commands will be run in the `/workspace` directory.
+* 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 `think` 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
 """
@@ -140,11 +149,18 @@ def get_request_action_prompt(
             )
         bg_commands_message += '\nYou can end any process by sending a `kill` action with the numerical `id` above.'
 
+    user = 'opendevin' if config.get(ConfigType.RUN_AS_DEVIN) else 'root'
+
     return ACTION_PROMPT % {
         'task': task,
         'monologue': json.dumps(thoughts, indent=2),
         'background_commands': bg_commands_message,
         'hint': hint,
+        'user': user,
+        'timeout': config.get(ConfigType.SANDBOX_TIMEOUT),
+        'WORKSPACE_MOUNT_PATH_IN_SANDBOX': config.get(
+            ConfigType.WORKSPACE_MOUNT_PATH_IN_SANDBOX
+        ),
     }
 
 
@@ -164,16 +180,26 @@ def parse_action_response(response: str) -> Action:
         # Find response-looking json in the output and use the more promising one. Helps with weak llms
         response_json_matches = re.finditer(
             r"""{\s*\"action\":\s?\"(\w+)\"(?:,?|,\s*\"args\":\s?{((?:.|\s)*?)})\s*}""",
-            response)  # Find all response-looking strings
+            response,
+        )  # Find all response-looking strings
 
         def rank(match):
-            return len(match[2]) if match[1] == 'think' else 130  # Crudely rank multiple responses by length
+            return (
+                len(match[2]) if match[1] == 'think' else 130
+            )  # Crudely rank multiple responses by length
+
         try:
-            action_dict = json.loads(max(response_json_matches, key=rank)[0])  # Use the highest ranked response
-        except ValueError as e:
+            action_dict = json.loads(
+                max(response_json_matches, key=rank)[0]
+            )  # Use the highest ranked response
+        except (ValueError, JSONDecodeError):
             raise LLMOutputError(
-                "Output from the LLM isn't properly formatted. The model may be misconfigured."
-            ) from e
+                'Invalid JSON, the response must be well-formed JSON as specified in the prompt.'
+            )
+    except (ValueError, TypeError):
+        raise LLMOutputError(
+            'Invalid JSON, the response must be well-formed JSON as specified in the prompt.'
+        )
     if 'content' in action_dict:
         # The LLM gets confused here. Might as well be robust
         action_dict['contents'] = action_dict.pop('content')

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)

agenthub/planner_agent/agent.py

@@ -1,11 +1,11 @@
 from typing import List
-from .prompt import get_prompt, parse_response
 
-from opendevin.agent import Agent
-from opendevin.action import AgentFinishAction
+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.state import State
-from opendevin.action import Action
+
+from .prompt import get_prompt, parse_response
 
 
 class PlannerAgent(Agent):

agenthub/planner_agent/prompt.py

@@ -1,29 +1,28 @@
 import json
-from typing import List, Tuple, Dict, Type
+from typing import Dict, List, Tuple, Type
 
-from opendevin.controller.agent_controller import print_with_color
-from opendevin.plan import Plan
-from opendevin.action import Action, action_from_dict
-from opendevin.observation import Observation
-from opendevin.schema import ActionType
-
-from opendevin.action import (
-    NullAction,
-    CmdRunAction,
-    CmdKillAction,
+from opendevin.controller.state.plan import Plan
+from opendevin.core.logger import opendevin_logger as logger
+from opendevin.core.schema import ActionType
+from opendevin.events.action import (
+    Action,
+    AddTaskAction,
+    AgentFinishAction,
+    AgentRecallAction,
+    AgentSummarizeAction,
+    AgentThinkAction,
     BrowseURLAction,
+    CmdKillAction,
+    CmdRunAction,
     FileReadAction,
     FileWriteAction,
-    AgentRecallAction,
-    AgentThinkAction,
-    AgentFinishAction,
-    AgentSummarizeAction,
-    AddTaskAction,
     ModifyTaskAction,
+    NullAction,
+    action_from_dict,
 )
-
-from opendevin.observation import (
+from opendevin.events.observation import (
     NullObservation,
+    Observation,
 )
 
 ACTION_TYPE_TO_CLASS: Dict[str, Type[Action]] = {
@@ -131,6 +130,25 @@ What is your next thought or action? Again, you must reply with JSON, and only w
 """
 
 
+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.THINK: "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(plan: Plan, history: List[Tuple[Action, Observation]]) -> str:
     """
     Gets the prompt for the planner agent.
@@ -150,10 +168,10 @@ def get_prompt(plan: Plan, history: List[Tuple[Action, Observation]]) -> str:
     latest_action: Action = NullAction()
     for action, observation in sub_history:
         if not isinstance(action, NullAction):
-            history_dicts.append(action.to_dict())
+            history_dicts.append(action.to_memory())
             latest_action = action
         if not isinstance(observation, NullObservation):
-            observation_dict = observation.to_dict()
+            observation_dict = observation.to_memory()
             if (
                 'extras' in observation_dict
                 and 'screenshot' in observation_dict['extras']
@@ -161,8 +179,6 @@ def get_prompt(plan: Plan, history: List[Tuple[Action, Observation]]) -> str:
                 del observation_dict['extras']['screenshot']
             history_dicts.append(observation_dict)
     history_str = json.dumps(history_dicts, indent=2)
-
-    hint = ''
     current_task = plan.get_current_task()
     if current_task is not None:
         plan_status = f"You're currently working on this task:\n{current_task.goal}."
@@ -170,35 +186,8 @@ def get_prompt(plan: Plan, history: List[Tuple[Action, Observation]]) -> str:
             plan_status += "\nIf it's not achievable AND verifiable with a SINGLE action, you MUST break it down into subtasks NOW."
     else:
         plan_status = "You're not currently working on any tasks. Your next action MUST be to mark a task as in_progress."
-        hint = plan_status
-
-    latest_action_id = latest_action.to_dict()['action']
-
-    if current_task is not None:
-        if latest_action_id == '':
-            hint = "You haven't taken any actions yet. Start by using `ls` to check out what files you're working with."
-        elif latest_action_id == ActionType.RUN:
-            hint = 'You should think about the command you just ran, what output it gave, and how that affects your plan.'
-        elif latest_action_id == ActionType.READ:
-            hint = 'You should think about the file you just read, what you learned from it, and how that affects your plan.'
-        elif latest_action_id == ActionType.WRITE:
-            hint = 'You just changed a file. You should think about how it affects your plan.'
-        elif latest_action_id == ActionType.BROWSE:
-            hint = 'You should think about the page you just visited, and what you learned from it.'
-        elif latest_action_id == ActionType.THINK:
-            hint = "Look at your last thought in the history above. What does it suggest? Don't think anymore--take action."
-        elif latest_action_id == ActionType.RECALL:
-            hint = 'You should think about the information you just recalled, and how it should affect your plan.'
-        elif latest_action_id == ActionType.ADD_TASK:
-            hint = 'You should think about the next action to take.'
-        elif latest_action_id == ActionType.MODIFY_TASK:
-            hint = 'You should think about the next action to take.'
-        elif latest_action_id == ActionType.SUMMARIZE:
-            hint = ''
-        elif latest_action_id == ActionType.FINISH:
-            hint = ''
-
-    print_with_color('HINT:\n' + hint, 'INFO')
+    hint = get_hint(latest_action.to_dict()['action'])
+    logger.info('HINT:\n' + hint, extra={'msg_type': 'INFO'})
     return prompt % {
         'task': plan.main_goal,
         'plan': plan_str,

containers/README.md

@@ -0,0 +1,13 @@
+# 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 .
+docker build -f containers/evaluation/Dockerfile -t evaluation evaluation/SWE-bench/
+
+```

containers/app/Dockerfile

@@ -1,9 +1,11 @@
+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
+RUN npm install -g npm@10.5.1
+RUN npm ci
 
 COPY ./frontend ./
 RUN npm run make-i18n && npm run build
@@ -30,25 +32,44 @@ FROM python:3.12-slim as runtime
 
 WORKDIR /app
 
-ENV RUN_AS_DEVIN=false
+ENV RUN_AS_DEVIN=true
+ENV OPENDEVIN_USER_ID=1000
 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
+    && 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 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
+USER opendevin
 
 ENV VIRTUAL_ENV=/app/.venv \
     PATH="/app/.venv/bin:$PATH" \
     PYTHONPATH='/app'
 
-COPY --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
+COPY --chown=opendevin:app --chmod=770 --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
+RUN playwright install --with-deps chromium
 
-COPY ./opendevin ./opendevin
-COPY ./agenthub ./agenthub
-RUN python opendevin/download.py # No-op to download assets
+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
 
-COPY --from=frontend-builder /app/dist ./frontend/dist
+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
 
-CMD ["uvicorn", "opendevin.server.listen:app", "--host", "0.0.0.0", "--port", "3000"]
+
+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
+CMD ["/app/entrypoint.sh"]

containers/app/config.sh

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

containers/app/entrypoint.sh

@@ -0,0 +1,26 @@
+#!/bin/bash
+# check user is root
+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
+
+# change uid of opendevin user to match the host user
+# but the group id is not changed, so the user can still access everything under /app
+useradd -l -m -u $SANDBOX_USER_ID -s /bin/bash enduser
+usermod -aG app enduser
+mkdir -p /home/enduser/.cache/ms-playwright/
+mv /home/opendevin/.cache/ms-playwright/ /home/enduser/.cache/
+
+# get the user group of /var/run/docker.sock and set opendevin to that group
+DOCKER_SOCKET_GID=$(stat -c '%g' /var/run/docker.sock)
+echo "Docker socket group id: $DOCKER_SOCKET_GID"
+usermod -aG $DOCKER_SOCKET_GID enduser
+
+# switch to the user and start the server
+su enduser -c "cd /app && uvicorn opendevin.server.listen:app --host 0.0.0.0 --port 3000"

containers/build.sh

@@ -2,21 +2,30 @@
 set -eo pipefail
 
 image_name=$1
+org_name=$2
 push=0
-if [[ $2 == "--push" ]]; then
+if [[ $3 == "--push" ]]; then
   push=1
 fi
 
 echo -e "Building: $image_name"
-tags=(latest)
+tags=()
+
+OPEN_DEVIN_BUILD_VERSION="dev"
+
+cache_tag_base="buildcache"
+cache_tag="$cache_tag_base"
+
 if [[ -n $GITHUB_REF_NAME ]]; then
   # check if ref name is a version number
-  if [[ $GITHUB_REF_NAME =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+  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[@]}"
@@ -31,18 +40,28 @@ if [ ! -f $dir/config.sh ]; then
   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"
-#docker pull $DOCKER_REPOSITORY:main || true # try to get any cached layers
+
 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

@@ -0,0 +1,19 @@
+FROM ubuntu:22.04
+
+# install basic packages
+RUN apt-get update && apt-get install -y \
+    curl \
+    wget \
+    git \
+    vim \
+    nano \
+    unzip \
+    zip \
+    python3 \
+    python3-pip \
+    python3-venv \
+    python3-dev \
+    build-essential \
+    openssh-server \
+    sudo \
+    && rm -rf /var/lib/apt/lists/*

containers/e2b-sandbox/README.md

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

containers/e2b-sandbox/e2b.toml

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

containers/evaluation/config.sh

@@ -1,2 +1,4 @@
-DOCKER_REPOSITORY=ghcr.io/opendevin/eval-swe-bench
+DOCKER_REGISTRY=ghcr.io
+DOCKER_ORG=opendevin
+DOCKER_IMAGE=eval-swe-bench
 DOCKER_BASE_DIR=evaluation/SWE-bench

containers/sandbox/Dockerfile

@@ -16,6 +16,18 @@ RUN apt-get update && apt-get install -y \
     build-essential \
     openssh-server \
     sudo \
+    bash \
+    gcc \
+    jq \
+    g++ \
+    make \
     && rm -rf /var/lib/apt/lists/*
 
-RUN service ssh start
+RUN mkdir -p -m0755 /var/run/sshd
+
+# symlink python3 to python
+RUN ln -s /usr/bin/python3 /usr/bin/python
+
+# install basic dependencies for CodeActAgent
+RUN pip3 install --upgrade pip
+RUN pip3 install jupyterlab notebook jupyter_kernel_gateway flake8

containers/sandbox/config.sh

@@ -1,2 +1,4 @@
-DOCKER_REPOSITORY=ghcr.io/opendevin/sandbox
+DOCKER_REGISTRY=ghcr.io
+DOCKER_ORG=opendevin
+DOCKER_IMAGE=sandbox
 DOCKER_BASE_DIR="."

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

@@ -1,44 +1,43 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v3.2.0
+    rev: v4.5.0
     hooks:
       - id: trailing-whitespace
+        exclude: docs/modules/python
       - id: end-of-file-fixer
+        exclude: docs/modules/python
       - id: check-yaml
       - id: debug-statements
-      - id: double-quote-string-fixer
 
-  - repo: https://github.com/hhatto/autopep8
-    rev: v2.1.0
+  - repo: https://github.com/tox-dev/pyproject-fmt
+    rev: 1.7.0
     hooks:
-      - id: autopep8
-
-  - repo: https://github.com/asottile/setup-cfg-fmt
-    rev: v2.5.0
+      - id: pyproject-fmt
+  - repo: https://github.com/abravalheri/validate-pyproject
+    rev: v0.16
     hooks:
-      - id: setup-cfg-fmt
-        always_run: true
-        pass_filenames: false
+      - id: validate-pyproject
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.3.7
+    rev: v0.4.1
     hooks:
       # Run the linter.
       - id: ruff
-        entry: ruff check --config dev_config/python/ruff.toml opendevin/ agenthub/
-        types_or: [ python, pyi, jupyter ]
-        args: [ --fix ]
+        entry: ruff check --config dev_config/python/ruff.toml
+        types_or: [python, pyi, jupyter]
+        args: [--fix]
       # Run the formatter.
       - id: ruff-format
-        entry: ruff check --config dev_config/python/ruff.toml opendevin/ agenthub/
-        types_or: [ python, pyi, jupyter ]
+        entry: ruff format --config dev_config/python/ruff.toml
+        types_or: [python, pyi, jupyter]
 
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.9.0
     hooks:
       - id: mypy
-        additional_dependencies: [types-requests, types-setuptools, types-pyyaml, types-toml]
+        additional_dependencies:
+          [types-requests, types-setuptools, types-pyyaml, types-toml]
         entry: mypy --config-file dev_config/python/mypy.ini opendevin/ agenthub/
         always_run: true
         pass_filenames: false

dev_config/python/ruff.toml

@@ -1,3 +1,23 @@
 exclude = [
     "agenthub/monologue_agent/regression/",
-]
+]
+
+[lint]
+select = [
+    "E",
+    "W",
+    "F",
+    "I",
+    "Q",
+]
+
+ignore = [
+    "E501",
+]
+
+[lint.flake8-quotes]
+docstring-quotes = "double"
+inline-quotes = "single"
+
+[format]
+quote-style = "single"

docs/.gitignore

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

docs/README.md

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

docs/architecture/Architecture.md

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

docs/architecture/README.md

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

docs/babel.config.js

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

docs/documentation/Agents.md

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

docs/documentation/LOCAL_LLM_GUIDE.md

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

docs/docusaurus.config.ts

@@ -0,0 +1,128 @@
+import type * as Preset from "@docusaurus/preset-classic";
+import type { Config } from "@docusaurus/types";
+import { themes as prismThemes } from "prism-react-renderer";
+
+const config: Config = {
+  title: "OpenDevin",
+  tagline: "Code Less, Make More",
+  favicon: "img/logo.png",
+
+  // Set the production url of your site here
+  url: "https://OpenDevin.github.io",
+  baseUrl: "/OpenDevin/",
+
+  // GitHub pages deployment config.
+  organizationName: "OpenDevin",
+  projectName: "OpenDevin",
+  trailingSlash: false,
+
+  onBrokenLinks: "throw",
+  onBrokenMarkdownLinks: "warn",
+
+  // Even if you don't use internationalization, you can use this field to set
+  // useful metadata like html lang. For example, if your site is Chinese, you
+  // may want to replace "en" with "zh-Hans".
+  i18n: {
+    defaultLocale: "en",
+    locales: ["en"],
+  },
+
+  presets: [
+    [
+      "classic",
+      {
+        docs: {
+          path: "modules",
+          routeBasePath: "modules",
+          sidebarPath: "./sidebars.ts",
+          exclude: [
+            // '**/_*.{js,jsx,ts,tsx,md,mdx}',
+            // '**/_*/**',
+            "**/*.test.{js,jsx,ts,tsx}",
+            "**/__tests__/**",
+          ],
+        },
+        blog: {
+          showReadingTime: true,
+        },
+        theme: {
+          customCss: "./src/css/custom.css",
+        },
+      } satisfies Preset.Options,
+    ],
+  ],
+
+  themeConfig: {
+    image: "img/docusaurus.png",
+    navbar: {
+      title: "OpenDevin",
+      logo: {
+        alt: "OpenDevin",
+        src: "img/logo.png",
+      },
+      items: [
+        {
+          type: "docSidebar",
+          sidebarId: "docsSidebar",
+          position: "left",
+          label: "Docs",
+        },
+        {
+          type: "docSidebar",
+          sidebarId: "apiSidebar",
+          position: "left",
+          label: "Codebase",
+        },
+        { to: "/faq", label: "FAQ", position: "left" },
+        {
+          href: "https://github.com/OpenDevin/OpenDevin",
+          label: "GitHub",
+          position: "right",
+        },
+      ],
+    },
+    footer: {
+      style: "dark",
+      links: [
+        {
+          title: "OpenDevin",
+          items: [
+            {
+              label: "Docs",
+              to: "/modules/usage/intro",
+            },
+          ],
+        },
+        {
+          title: "Community",
+          items: [
+            {
+              label: "Slack",
+              href: "https://join.slack.com/t/opendevin/shared_invite/zt-2ggtwn3k5-PvAA2LUmqGHVZ~XzGq~ILw"
+            },
+            {
+              label: "Discord",
+              href: "https://discord.gg/ESHStjSjD4",
+            },
+          ],
+        },
+        {
+          title: "More",
+          items: [
+            {
+              label: "GitHub",
+              href: "https://github.com/OpenDevin/OpenDevin",
+            },
+          ],
+        },
+      ],
+      copyright: `Copyright © ${new Date().getFullYear()} OpenDevin`,
+    },
+    prism: {
+      theme: prismThemes.oneLight,
+      darkTheme: prismThemes.oneDark,
+    },
+  } satisfies Preset.ThemeConfig,
+};
+
+export default config;

docs/modules/python/python.md

@@ -0,0 +1,3 @@
+# Python Docs
+
+Docs will appear here after deployment.

docs/modules/python/sidebar.json

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

docs/modules/usage/about.md

@@ -0,0 +1,53 @@
+---
+sidebar_position: 6
+---
+
+# 📚 Misc
+
+## ⭐️ 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.
+
+## 🚧 Default Agent
+
+- Our default Agent is currently the MonologueAgent, which has limited capabilities, but is fairly stable. We're working on other Agent implementations, including [SWE Agent](https://swe-agent.com/). You can [read about our current set of agents here](./agents).
+
+## 🤝 How to Contribute
+
+OpenDevin is a community-driven project, and we welcome contributions from everyone. Whether you're a developer, a researcher, or simply enthusiastic about advancing the field of software engineering with AI, there are many ways to get involved:
+
+- **Code Contributions:** Help us develop the core functionalities, frontend interface, or sandboxing solutions.
+- **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in evaluating the models, or suggest improvements.
+- **Feedback and Testing:** Use the OpenDevin toolset, report bugs, suggest features, or provide feedback on usability.
+
+For details, please check [this document](https://github.com/OpenDevin/OpenDevin/blob/main/CONTRIBUTING.md).
+
+## 🤖 Join Our Community
+
+Now we have both Slack workspace for the collaboration on building OpenDevin and Discord server for discussion about anything related, e.g., this project, LLM, agent, etc.
+
+- [Slack workspace](https://join.slack.com/t/opendevin/shared_invite/zt-2ggtwn3k5-PvAA2LUmqGHVZ~XzGq~ILw)
+- [Discord server](https://discord.gg/ESHStjSjD4)
+
+If you would love to contribute, feel free to join our community (note that now there is no need to fill in the [form](https://forms.gle/758d5p6Ve8r2nxxq6)). Let's simplify software engineering together!
+
+🐚 **Code less, make more with OpenDevin.**
+
+[![Star History Chart](https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date)](https://star-history.com/#OpenDevin/OpenDevin&Date)
+
+## 🛠️ Built With
+
+OpenDevin is built using a combination of powerful frameworks and libraries, providing a robust foundation for its development. Here are the key technologies used in the project:
+
+![FastAPI](https://img.shields.io/badge/FastAPI-black?style=for-the-badge) ![uvicorn](https://img.shields.io/badge/uvicorn-black?style=for-the-badge) ![LiteLLM](https://img.shields.io/badge/LiteLLM-black?style=for-the-badge) ![Docker](https://img.shields.io/badge/Docker-black?style=for-the-badge) ![Ruff](https://img.shields.io/badge/Ruff-black?style=for-the-badge) ![MyPy](https://img.shields.io/badge/MyPy-black?style=for-the-badge) ![LlamaIndex](https://img.shields.io/badge/LlamaIndex-black?style=for-the-badge) ![React](https://img.shields.io/badge/React-black?style=for-the-badge)
+
+Please note that the selection of these technologies is in progress, and additional technologies may be added or existing ones may be removed as the project evolves. We strive to adopt the most suitable and efficient tools to enhance the capabilities of OpenDevin.
+
+## 📜 License
+
+Distributed under the MIT License. See [our license](https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE) for more information.

docs/modules/usage/agents.md

@@ -0,0 +1,142 @@
+---
+sidebar_position: 3
+---
+
+# 🧠 Agents and Capabilities
+
+## CodeAct Agent
+
+### Description
+
+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)*
+
+
+### Actions
+
+`Action`,
+`CmdRunAction`,
+`IPythonRunCellAction`,
+`AgentEchoAction`,
+`AgentFinishAction`,
+`AgentTalkAction`
+
+### Observations
+
+`CmdOutputObservation`,
+`IPythonRunCellObservation`,
+`AgentMessageObservation`,
+`UserMessageObservation`
+
+### Methods
+
+| Method          | Description                                                                                                                                                                                                                                             |
+| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `__init__`      | Initializes an agent with `llm` and a list of messages `List[Mapping[str, str]]`                                                                                                                                                                        |
+| `step`          | Performs one step using the CodeAct Agent. This includes gathering info on previous steps and prompting the model to make a command to execute. |
+| `search_memory` | Not yet implemented                                                                                                                                                                                                                                     |
+
+### Work-in-progress & Next step
+
+[] Support web-browsing
+[] Complete the workflow for CodeAct agent to submit Github PRs
+
+
+## Monologue Agent
+
+### Description
+
+The Monologue Agent utilizes long and short term memory to complete tasks.
+Long term memory is stored as a LongTermMemory object and the model uses it to search for examples from the past.
+Short term memory is stored as a Monologue object and the model can condense it as necessary.
+
+### Actions
+
+`Action`,
+`NullAction`,
+`CmdRunAction`,
+`FileWriteAction`,
+`FileReadAction`,
+`AgentRecallAction`,
+`BrowseURLAction`,
+`GithubPushAction`,
+`AgentThinkAction`
+
+### Observations
+
+`Observation`,
+`NullObservation`,
+`CmdOutputObservation`,
+`FileReadObservation`,
+`AgentRecallObservation`,
+`BrowserOutputObservation`
+
+### Methods
+
+| Method          | Description                                                                                                                                   |
+| --------------- | --------------------------------------------------------------------------------------------------------------------------------------------- |
+| `__init__`      | Initializes the agent with a long term memory, and an internal monologue                                                                      |
+| `_add_event`    | Appends events to the monologue of the agent and condenses with summary automatically if the monologue is too long                            |
+| `_initialize`   | Utilizes the `INITIAL_THOUGHTS` list to give the agent a context for its capabilities and how to navigate the `/workspace`                    |
+| `step`          | Modifies the current state by adding the most recent actions and observations, then prompts the model to think about its next action to take. |
+| `search_memory` | Uses `VectorIndexRetriever` to find related memories within the long term memory.                                                             |
+
+## Planner Agent
+
+### Description
+
+The planner agent utilizes a special prompting strategy to create long term plans for solving problems.
+The agent is given its previous action-observation pairs, current task, and hint based on last action taken at every step.
+
+### Actions
+
+`NullAction`,
+`CmdRunAction`,
+`CmdKillAction`,
+`BrowseURLAction`,
+`GithubPushAction`,
+`FileReadAction`,
+`FileWriteAction`,
+`AgentRecallAction`,
+`AgentThinkAction`,
+`AgentFinishAction`,
+`AgentSummarizeAction`,
+`AddTaskAction`,
+`ModifyTaskAction`,
+
+### Observations
+
+`Observation`,
+`NullObservation`,
+`CmdOutputObservation`,
+`FileReadObservation`,
+`AgentRecallObservation`,
+`BrowserOutputObservation`
+
+### Methods
+
+| Method          | Description                                                                                                                                                                               |
+| --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `__init__`      | Initializes an agent with `llm`                                                                                                                                                           |
+| `step`          | Checks to see if current step is completed, returns `AgentFinishAction` if True. Otherwise, creates a plan prompt and sends to model for inference, adding the result as the next action. |
+| `search_memory` | Not yet implemented                                                                                                                                                                       |

docs/modules/usage/architecture.mdx

@@ -0,0 +1,51 @@
+---
+sidebar_position: 4
+---
+
+# 🏛️ System Architecture Overview
+
+This is a high-level overview of the system architecture. The system is divided into two main components: the frontend and the backend. The frontend is responsible for handling user interactions and displaying the results. The backend is responsible for handling the business logic and executing the agents.
+
+![system_architecture.svg](/img/system_architecture.svg)
+
+This Overview is simplified to show the main components and their interactions. For a more detailed view of the backend architecture, see the [Backend Architecture](#backend-architecture) section.
+
+# Backend Architecture
+
+_**Disclaimer**: The backend architecture is a work in progress and is subject to change. The following diagram shows the current architecture of the backend based on the commit that is shown in the footer of the diagram._
+
+![backend_architecture.svg](/img/backend_architecture.svg)
+
+<details>
+  <summary>Updating this Diagram</summary>
+  <div>
+    The generation of the backend architecture diagram is partially automated.
+    The diagram is generated from the type hints in the code using the py2puml
+    tool. The diagram is then manually reviewed, adjusted and exported to PNG
+    and SVG.
+
+    ## Prerequisites
+
+    - Running python environment in which opendevin is executable
+    (according to the instructions in the README.md file in the root of the repository)
+    - [py2puml](https://github.com/lucsorel/py2puml) installed
+
+## Steps
+
+1.  Autogenerate the diagram by running the following command from the root of the repository:
+    `py2puml opendevin opendevin > docs/architecture/backend_architecture.puml`
+
+2.  Open the generated file in a PlantUML editor, e.g. Visual Studio Code with the PlantUML extension or [PlantText](https://www.planttext.com/)
+
+3.  Review the generated PUML and make all necessary adjustments to the diagram (add missing parts, fix mistakes, improve positioning).
+    _py2puml creates the diagram based on the type hints in the code, so missing or incorrect type hints may result in an incomplete or incorrect diagram._
+
+4.  Review the diff between the new and the previous diagram and manually check if the changes are correct.
+    _Make sure not to remove parts that were manually added to the diagram in the past and are still relevant._
+
+5.  Add the commit hash of the commit that was used to generate the diagram to the diagram footer.
+
+6.  Export the diagram as PNG and SVG files and replace the existing diagrams in the `docs/architecture` directory. This can be done with (e.g. [PlantText](https://www.planttext.com/))
+
+  </div>
+</details>