github/OpenHands
1
0
Fork 0
mirror of https://github.com/OpenHands/OpenHands.git synced 2026-03-22 13:47:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '3886c5121745befb5d999e93825ec2e265863931' into bl-xw/swe-bench

Browse Source
This commit is contained in:
Xingyao Wang
2024-05-03 13:54:55 +08:00
parent c16af4c588 3886c51217
commit af4e9910c4
296 changed files with 22896 additions and 2763 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.github/ISSUE_TEMPLATE/bug_template.yml vendored
View File

@@ -12,7 +12,7 @@ body:
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://github.com/OpenDevin/OpenDevin/blob/main/docs/guides/Troubleshooting.md
- 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

58
.github/workflows/deploy-docs.yml vendored Normal file
View File

@@ -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

30
.github/workflows/dummy-agent-test.yml vendored Normal file
View File

@@ -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

49
.github/workflows/ghcr.yml vendored
View File

@@ -1,7 +1,14 @@
name: Publish Docker Image
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
on:
push:
branches:
- main
pull_request:
workflow_dispatch:
inputs:
reason:
@@ -12,7 +19,11 @@ on:
jobs:
ghcr_build_and_push:
runs-on: ubuntu-latest
if: github.event_name == 'push' || github.event.inputs.reason != ''
permissions:
contents: read
packages: write
strategy:
matrix:
image: ["app", "evaluation", "sandbox"]
@@ -21,6 +32,22 @@ jobs:
- name: checkout
uses: actions/checkout@v4
- name: Free Disk Space (Ubuntu)
uses: jlumbroso/free-disk-space@main
with:
# this might remove tools that are actually needed,
# if set to "true" but frees about 6 GB
tool-cache: true
# all of these default to true, but feel free to set to
# "false" if necessary for your workflow
android: true
dotnet: true
haskell: true
large-packages: true
docker-images: false
swap-storage: true
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
@@ -28,16 +55,22 @@ jobs:
id: buildx
uses: docker/setup-buildx-action@v3
- name: Log-in to ghcr.io
run: echo "${{ secrets.GITHUB_TOKEN }}" | docker login ghcr.io -u ${{ github.actor }} --password-stdin
- name: Delete huge unnecessary tools folder
run: rm -rf /opt/hostedtoolcache
- 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 ${{ matrix.image }}
if: "!github.event.pull_request.head.repo.fork"
run: |
ORG_NAME=$(echo "${{ github.repository }}" | tr '[A-Z]' '[a-z]' | cut -d '/' -f 1)
./containers/build.sh ${{ matrix.image }} $ORG_NAME --push
./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

12
.github/workflows/lint.yml vendored
View File

@@ -1,5 +1,9 @@
name: Lint
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
on:
push:
branches:
@@ -33,15 +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
if: github.ref != 'refs/heads/main'
run: |
git fetch https://github.com/OpenDevin/OpenDevin.git main:main && \
pre-commit run \
--all-files \
--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

2
.github/workflows/review-pr.yml vendored
View File

@@ -49,7 +49,7 @@ jobs:
LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
SANDBOX_TYPE: exec
run: |
WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE python ./opendevin/main.py -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: Check if review file is non-empty

88
.github/workflows/run-integration-tests.yml vendored
View File

@@ -1,5 +1,9 @@
name: Run Integration Tests
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
on:
push:
branches:
@@ -11,64 +15,42 @@ jobs:
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:
- name: SWEAgent-py311-ssh
python-version: "3.11"
agent: "SWEAgent"
embedding-model: "none"
sandbox: "ssh"
- name: PlannerAgent-py311-ssh
python-version: "3.11"
agent: "PlannerAgent"
embedding-model: "none"
sandbox: "ssh"
- name: MonologueAgent-py311-ssh
python-version: "3.11"
agent: "MonologueAgent"
embedding-model: "local"
sandbox: "ssh"
- name: CodeActAgent-py311-ssh
python-version: "3.11"
agent: "CodeActAgent"
embedding-model: "none"
sandbox: "ssh"
- name: SWEAgent-py311-exec
python-version: "3.11"
agent: "SWEAgent"
embedding-model: "none"
sandbox: "exec"
- name: PlannerAgent-py311-exec
python-version: "3.11"
agent: "PlannerAgent"
embedding-model: "none"
sandbox: "exec"
- name: MonologueAgent-py311-exec
python-version: "3.11"
agent: "MonologueAgent"
embedding-model: "local"
sandbox: "exec"
- name: CodeActAgent-py311-exec
python-version: "3.11"
agent: "CodeActAgent"
embedding-model: "none"
sandbox: "exec"
- name: MonologueAgent-py311-local
python-version: "3.11"
agent: "MonologueAgent"
- 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: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v2
- name: Install poetry via pipx
run: pipx install poetry
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install Poetry
run: curl -sSL https://install.python-poetry.org | python3 -
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: ${{ matrix.sandbox }}
@@ -78,8 +60,14 @@ jobs:
run: |
rm -rf workspace
mkdir workspace
WORKSPACE_BASE="$GITHUB_WORKSPACE/workspace" WORKSPACE_MOUNT_PATH="$GITHUB_WORKSPACE/workspace" poetry run pytest -s ./tests/integration
WORKSPACE_BASE="$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

56
.github/workflows/run-unit-tests.yml vendored
View File

@@ -1,5 +1,9 @@
name: Run Unit Tests
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
on:
push:
branches:
@@ -16,22 +20,38 @@ jobs:
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@v2
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
- name: Install and configure Poetry
uses: snok/install-poetry@v1
with:
version: latest
# 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 ./tests/unit
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
@@ -41,17 +61,29 @@ jobs:
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v2
- name: Install poetry via pipx
run: pipx install poetry
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install Poetry
run: curl -sSL https://install.python-poetry.org | python3 -
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 ./tests/unit
- 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

2
.github/workflows/solve-issue.yml vendored
View File

@@ -43,7 +43,7 @@ jobs:
LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
SANDBOX_TYPE: exec
run: |
WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE python ./opendevin/main.py -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

12
Development.md
View File

@@ -82,3 +82,15 @@ If you encounter any issues with the Language Model (LM) or you're simply curiou
```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.

36
Makefile
View File

@@ -148,9 +148,17 @@ install-precommit-hooks:
@poetry run pre-commit install --config $(PRECOMMIT_CONFIG_PATH)
@echo "$(GREEN)Pre-commit hooks installed successfully.$(RESET)"
lint:
lint-backend:
@echo "$(YELLOW)Running linters...$(RESET)"
@poetry run pre-commit run --all-files --show-diff-on-failure --config $(PRECOMMIT_CONFIG_PATH)
@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
@$(MAKE) -s lint-backend
build-frontend:
@echo "$(YELLOW)Building frontend...$(RESET)"
@@ -159,7 +167,7 @@ build-frontend:
# Start backend
start-backend:
@echo "$(YELLOW)Starting backend...$(RESET)"
@poetry run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT) --reload --reload-exclude workspace/*
@poetry run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT) --reload --reload-exclude "workspace/*"
# Start frontend
start-frontend:
@@ -200,12 +208,22 @@ 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; \

175
README.md
View File

@@ -1,5 +1,3 @@
[English](README.md) | [中文](docs/README-zh.md)
<a name="readme-top"></a>
<!--
@@ -26,174 +24,21 @@
<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-2ggtwn3k5-PvAA2LUmqGHVZ~XzGq~ILw"><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>
</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/Agents.md).
## 🚀 Get Started
The easiest way to run OpenDevin is inside a Docker container.
To start the app, run these commands, replacing `$(pwd)/workspace` with the path to the code you want OpenDevin to work with.
```bash
# Your OpenAI API key, or any other LLM API key
export LLM_API_KEY="sk-..."
# The directory you want OpenDevin to modify. MUST be an absolute path!
export WORKSPACE_BASE=$(pwd)/workspace
docker run \
-e LLM_API_KEY \
-e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
-v $WORKSPACE_BASE:/opt/workspace_base \
-v /var/run/docker.sock:/var/run/docker.sock \
-p 3000:3000 \
--add-host host.docker.internal=host-gateway \
ghcr.io/opendevin/opendevin:0.4.0
```
You'll find opendevin running at `http://localhost:3000`.
If you want to use the (unstable!) bleeding edge, you can use `ghcr.io/opendevin/opendevin:main` as the image.
See [Development.md](Development.md) for instructions on running OpenDevin without Docker.
Having trouble? Check out our [Troubleshooting Guide](./docs/guides/Troubleshooting.md).
## 🤖 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 when using the OpenDevin UI, you'll need to choose your model in the settings window (the gear
wheel on the bottom left).
The following environment variables might be necessary for some LLMs:
- `LLM_API_KEY`
- `LLM_BASE_URL`
- `LLM_EMBEDDING_MODEL`
- `LLM_EMBEDDING_DEPLOYMENT_NAME`
- `LLM_API_VERSION`
We have a few guides for running OpenDevin with specific model providers:
- [ollama](./docs/guides/LocalLLMs.md)
- [Azure](./docs/guides/AzureLLMs.md)
If you're using another provider, we encourage you to open a PR to share your setup!
**Note on Alternative Models:**
The best models are GPT-4 and Claude 3. Current local and open source models are
not nearly as powerful. When using an alternative model,
you may see long wait times between messages,
poor responses, or errors about malformed JSON. OpenDevin
can only be as powerful as the models driving it--fortunately folks on our team
are actively working on building better open source models!
**Note on API retries and rate limits:**
Some LLMs have rate limits and may require retries. OpenDevin will automatically retry requests if it receives a 429 error or API connection error.
You can set LLM_NUM_RETRIES, LLM_RETRY_MIN_WAIT, LLM_RETRY_MAX_WAIT environment variables to control the number of retries and the time between retries.
By default, LLM_NUM_RETRIES is 5 and LLM_RETRY_MIN_WAIT, LLM_RETRY_MAX_WAIT are 3 seconds and respectively 60 seconds.
## ⭐️ 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;">
@@ -221,8 +66,8 @@ 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!
@@ -230,14 +75,6 @@ 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 ↑

2
agenthub/README.md
View File

@@ -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.

3
agenthub/SWE_agent/__init__.py
View File

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

40
agenthub/SWE_agent/agent.py
View File

@@ -1,23 +1,23 @@
from typing import List
from opendevin.agent import Agent
from opendevin.llm.llm import LLM
from opendevin.state import State
from opendevin.action import (
from opendevin.controller.agent import Agent
from opendevin.controller.state.state import State
from opendevin.events.action import (
Action,
AgentThinkAction,
FileReadAction,
FileWriteAction,
)
from opendevin.observation import Observation
from opendevin.events.observation import Observation
from opendevin.llm.llm import LLM
from .parser import parse_command
from .prompts import (
SYSTEM_MESSAGE,
STEP_PROMPT,
CONTEXT_PROMPT,
MEMORY_FORMAT,
NO_ACTION,
CONTEXT_PROMPT
STEP_PROMPT,
SYSTEM_MESSAGE,
)
@@ -48,9 +48,12 @@ class SWEAgent(Agent):
)
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')
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:
@@ -68,22 +71,15 @@ class SWEAgent(Agent):
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
)
prompt = STEP_PROMPT(state.plan.main_goal, self.cur_file, self.cur_line)
msgs = [
{'content': SYSTEM_MESSAGE, 'role': 'system'},
{'content': prompt, 'role': 'user'}
{'content': prompt, 'role': 'user'},
]
if len(self.running_memory) > 0:
context = CONTEXT_PROMPT(
self.running_memory,
self.memory_window
)
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)]))

14
agenthub/SWE_agent/parser.py
View File

@@ -1,17 +1,17 @@
from opendevin.action import (
import re
from opendevin.events.action import (
Action,
AgentEchoAction,
AgentFinishAction,
AgentThinkAction,
BrowseURLAction,
CmdRunAction,
FileReadAction,
FileWriteAction,
BrowseURLAction,
AgentEchoAction,
AgentThinkAction,
)
import re
from .prompts import CUSTOM_DOCS, COMMAND_USAGE
from .prompts import COMMAND_USAGE, CUSTOM_DOCS
# commands: exit, read, write, browse, kill, search_file, search_dir

46
agenthub/__init__.py
View File

@@ -1,28 +1,42 @@
from .micro.registry import all_microagents
from .micro.agent import MicroAgent
from opendevin.agent import Agent
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
from . import SWE_agent # noqa: E402
from . import delegator_agent # noqa: E402
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']
__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,
})
anon_class = type(
name,
(MicroAgent,),
{
'prompt': prompt,
'agent_definition': agent,
},
)
Agent.register(name, anon_class)

34
agenthub/codeact_agent/README.md
View File

@@ -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

3
agenthub/codeact_agent/__init__.py
View File

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

216
agenthub/codeact_agent/codeact_agent.py
View File

@@ -1,64 +1,108 @@
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.state import State
from opendevin.sandbox.plugins import PluginRequirement, JupyterRequirement
SYSTEM_MESSAGE = """You are a helpful assistant. You will be provided access (as root) to a bash shell to complete user-provided tasks.
You will be able to execute commands in the bash shell, interact with the file system, install packages, and receive the output of your commands.
DO NOT provide code in ```triple backticks```. Instead, you should execute bash command on behalf of the user by wrapping them with <execute> and </execute>.
For example:
You can list the files in the current directory by executing the following command:
<execute>ls</execute>
You can also install packages using pip:
<execute> pip install numpy </execute>
You can also write a block of code to a file:
<execute>
echo "import math
print(math.pi)" > math.py
</execute>
When you are done, execute 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()]
sandbox_plugins: List[PluginRequirement] = [
JupyterRequirement(),
SWEAgentCommandsRequirement(),
]
SUPPORTED_ACTIONS = (
CmdRunAction,
IPythonRunCellAction,
AgentEchoAction,
AgentTalkAction,
NullAction,
)
SUPPORTED_OBSERVATIONS = (
AgentMessageObservation,
UserMessageObservation,
CmdOutputObservation,
IPythonRunCellObservation,
)
def __init__(
self,
@@ -75,74 +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')

226
agenthub/codeact_agent/prompt.py Normal file
View File

@@ -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'
)

3
agenthub/delegator_agent/__init__.py
View File

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

52
agenthub/delegator_agent/agent.py
View File

@@ -1,11 +1,10 @@
from typing import List
from opendevin.agent import Agent
from opendevin.action import AgentFinishAction, AgentDelegateAction
from opendevin.observation import AgentDelegateObservation
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
from opendevin.state import State
from opendevin.action import Action
class DelegatorAgent(Agent):
@@ -13,6 +12,7 @@ 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):
@@ -38,9 +38,9 @@ class DelegatorAgent(Agent):
"""
if self.current_delegate == '':
self.current_delegate = 'study'
return AgentDelegateAction(agent='StudyRepoForTaskAgent', inputs={
'task': state.plan.main_goal
})
return AgentDelegateAction(
agent='StudyRepoForTaskAgent', inputs={'task': state.plan.main_goal}
)
lastObservation = state.history[-1][1]
if not isinstance(lastObservation, AgentDelegateObservation):
@@ -48,24 +48,36 @@ class DelegatorAgent(Agent):
if self.current_delegate == 'study':
self.current_delegate = 'coder'
return AgentDelegateAction(agent='Coder', inputs={
'task': state.plan.main_goal,
'summary': lastObservation.outputs['summary'],
})
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,
})
return AgentDelegateAction(
agent='Verifier',
inputs={
'task': state.plan.main_goal,
},
)
elif self.current_delegate == 'verifier':
if 'completed' in lastObservation.outputs and lastObservation.outputs['completed']:
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'],
})
return AgentDelegateAction(
agent='Coder',
inputs={
'task': state.plan.main_goal,
'summary': lastObservation.outputs['summary'],
},
)
else:
raise Exception('Invalid delegate state')

5
agenthub/dummy_agent/__init__.py
View File

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

164
agenthub/dummy_agent/agent.py
View File

@@ -1,21 +1,159 @@
"""Module for a Dummy agent."""
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"'
from opendevin.action.base import NullAction
from opendevin.state import State
from opendevin.action import Action
from typing import List
from opendevin.agent import Agent
from opendevin.controller.agent_controller import AgentController
from opendevin.observation.base import NullObservation, Observation
class DummyAgent(Agent):
"""A dummy agent that does nothing but can be used in testing."""
"""
The DummyAgent is used for e2e testing. It just sends the same set of actions deterministically,
without making any LLM calls.
"""
async def run(self, controller: AgentController) -> Observation:
return NullObservation('')
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:
return NullAction('')
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 []
return ['I am a computer.']

14
agenthub/micro/README.md Normal file
View File

@@ -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.

4
agenthub/micro/_instructions/actions/add_task.md
View File

@@ -1,4 +0,0 @@
* `add_task` - add a task to your plan. Arguments:
* `parent` - the ID of the parent task
* `goal` - the goal of the task
* `subtasks` - a list of subtasks, each of which is a map with a `goal` key.

2
agenthub/micro/_instructions/actions/finish.md
View File

@@ -1,2 +1,2 @@
* `finish` - if ALL of your tasks and subtasks have been verified or abandoned, and you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working. Arguments:
* `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

3
agenthub/micro/_instructions/actions/modify_task.md
View File

@@ -1,3 +0,0 @@
* `modify_task` - close a task. Arguments:
* `id` - the ID of the task to close
* `state` - set to 'in_progress' to start the task, 'completed' to finish it, 'verified' to assert that it was successful, 'abandoned' to give up on it permanently, or `open` to stop working on it for now.

22
agenthub/micro/agent.py
View File

@@ -1,13 +1,13 @@
import json
from typing import List, Dict
from typing import Dict, List
from jinja2 import Environment, BaseLoader
from jinja2 import BaseLoader, Environment
from opendevin.agent import Agent
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 opendevin.state import State
from opendevin.action import Action, action_from_dict
from opendevin.exceptions import LLMOutputError
from .instructions import instructions
from .registry import all_microagents
@@ -56,21 +56,17 @@ class MicroAgent(Agent):
super().__init__(llm)
if 'name' not in self.agent_definition:
raise ValueError('Agent definition must contain a name')
self.name = self.agent_definition['name']
self.description = self.agent_definition['description'] if 'description' in self.agent_definition else ''
self.inputs = self.agent_definition['inputs'] if 'inputs' in self.agent_definition else []
self.outputs = self.agent_definition['outputs'] if 'outputs' in self.agent_definition else []
self.examples = self.agent_definition['examples'] if 'examples' in self.agent_definition else []
self.prompt_template = Environment(loader=BaseLoader).from_string(self.prompt)
self.delegates = all_microagents.copy()
del self.delegates[self.name]
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)
delegates=self.delegates,
)
messages = [{'content': prompt, 'role': 'user'}]
resp = self.llm.completion(messages=messages)
action_resp = resp['choices'][0]['message']['content']

8
agenthub/micro/coder/agent.yaml
View File

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

2
agenthub/micro/coder/prompt.md
View File

@@ -4,9 +4,11 @@ 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 }}

25
agenthub/micro/commit_writer/README.md Normal file
View File

@@ -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.

6
agenthub/micro/commit_writer/agent.yaml Normal file
View File

@@ -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

28
agenthub/micro/commit_writer/prompt.md Normal file
View File

@@ -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 }}

2
agenthub/micro/instructions.py
View File

@@ -1,5 +1,5 @@
from typing import Dict
import os
from typing import Dict
instructions: Dict = {}

3
agenthub/micro/manager/agent.yaml
View File

@@ -1,5 +1,6 @@
name: Manager
name: ManagerAgent
description: Delegates tasks to microagents based on their area of expertise
generates: Action
inputs:
task: string
outputs: {}

14
agenthub/micro/math_agent/agent.yaml
View File

@@ -7,19 +7,19 @@ inputs:
outputs:
answer: string
examples:
- input:
- inputs:
task: "What is 2 + 2?"
output:
outputs:
answer: "4"
- input:
- inputs:
task: "What is the area of a circle with radius 7.324 inches?"
output:
answer: "168.518 square inches"
- input:
- inputs:
task: "What day of the week is 2099-01-01?"
output:
outputs:
answer: "Saturday"
- input:
- inputs:
task: "What is the integral of sin(x^2) evaluated from -1 to 1?"
output:
outputs:
answer: "0.603848"

4
agenthub/micro/postgres_agent/agent.yaml
View File

@@ -2,5 +2,5 @@ name: PostgresAgent
description: Writes and maintains PostgreSQL migrations
generates: Action
inputs:
- task: string
outputs: []
task: string
outputs: {}

1
agenthub/micro/registry.py
View File

@@ -1,4 +1,5 @@
import os
import yaml
all_microagents = {}

6
agenthub/micro/repo_explorer/agent.yaml
View File

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

4
agenthub/micro/study_repo_for_task/agent.yaml
View File

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

2
agenthub/micro/study_repo_for_task/prompt.md
View File

@@ -14,7 +14,7 @@ the information needed to complete this task:
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, function, functions, and classes.
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

8
agenthub/micro/verifier/agent.yaml
View File

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

3
agenthub/monologue_agent/__init__.py
View File

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

74
agenthub/monologue_agent/agent.py
View File

@@ -1,35 +1,34 @@
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
from opendevin.exceptions import AgentNoInstructionError
from opendevin.schema.config import ConfigType
from opendevin import config
from opendevin.action import (
Action,
NullAction,
CmdRunAction,
FileWriteAction,
FileReadAction,
AgentRecallAction,
BrowseURLAction,
GitHubPushAction,
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 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
@@ -57,7 +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',
@@ -137,6 +136,7 @@ class MonologueAgent(Agent):
Utilizes the INITIAL_THOUGHTS list to give the agent a context for it's 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
@@ -157,6 +157,10 @@ class MonologueAgent(Agent):
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)
@@ -169,8 +173,7 @@ class MonologueAgent(Agent):
elif previous_action == ActionType.READ:
observation = FileReadObservation(content=thought, path='')
elif previous_action == ActionType.RECALL:
observation = AgentRecallObservation(
content=thought, memories=[])
observation = AgentRecallObservation(content=thought, memories=[])
elif previous_action == ActionType.BROWSE:
observation = BrowserOutputObservation(
content=thought, url='', screenshot=''
@@ -208,7 +211,6 @@ class MonologueAgent(Agent):
else:
action = AgentThinkAction(thought=thought)
self._add_event(action.to_memory())
self._initialized = True
def step(self, state: State) -> Action:
"""
@@ -257,8 +259,6 @@ class MonologueAgent(Agent):
def reset(self) -> None:
super().reset()
self.monologue = Monologue()
if config.get(ConfigType.AGENT_MEMORY_ENABLED):
self.memory = LongTermMemory()
else:
self.memory = None
# Reset the initial monologue and memory
self._initialized = False

1
agenthub/monologue_agent/utils/json.py
View File

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

70
agenthub/monologue_agent/utils/memory.py
View File

@@ -1,17 +1,22 @@
import llama_index.embeddings.openai.base as llama_openai
import threading
import chromadb
from llama_index.core import Document
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.core import VectorStoreIndex
from llama_index.vector_stores.chroma import ChromaVectorStore
from tenacity import retry, retry_if_exception_type, stop_after_attempt, wait_random_exponential
from openai._exceptions import APIConnectionError, RateLimitError, InternalServerError
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 opendevin.logger import opendevin_logger as logger
from opendevin.schema.config import ConfigType
from . import json
num_retries = config.get(ConfigType.LLM_NUM_RETRIES)
@@ -32,15 +37,22 @@ else:
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)
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)
@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)
@@ -51,25 +63,37 @@ 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(ConfigType.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(ConfigType.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(ConfigType.LLM_EMBEDDING_DEPLOYMENT_NAME, 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),
@@ -81,9 +105,8 @@ elif (embedding_strategy is not None) and (embedding_strategy.lower() == 'none')
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))
@@ -103,7 +126,8 @@ 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 = []

7
agenthub/monologue_agent/utils/monologue.py
View File

@@ -1,9 +1,8 @@
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.logger import opendevin_logger as logger
from opendevin.core.exceptions import AgentEventTypeError
from opendevin.core.logger import opendevin_logger as logger
from opendevin.llm.llm import LLM
class Monologue:

37
agenthub/monologue_agent/utils/prompts.py
View File

@@ -1,20 +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 opendevin import config
from opendevin.schema.config import ConfigType
from . import json
ACTION_PROMPT = """
You're a thoughtful robot. Your main task is this:
@@ -159,7 +158,9 @@ def get_request_action_prompt(
'hint': hint,
'user': user,
'timeout': config.get(ConfigType.SANDBOX_TIMEOUT),
'WORKSPACE_MOUNT_PATH_IN_SANDBOX': config.get(ConfigType.WORKSPACE_MOUNT_PATH_IN_SANDBOX),
'WORKSPACE_MOUNT_PATH_IN_SANDBOX': config.get(
ConfigType.WORKSPACE_MOUNT_PATH_IN_SANDBOX
),
}
@@ -179,12 +180,18 @@ 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
action_dict = json.loads(
max(response_json_matches, key=rank)[0]
) # Use the highest ranked response
except (ValueError, JSONDecodeError):
raise LLMOutputError(
'Invalid JSON, the response must be well-formed JSON as specified in the prompt.'

3
agenthub/planner_agent/__init__.py
View File

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

10
agenthub/planner_agent/agent.py
View File

@@ -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):

36
agenthub/planner_agent/prompt.py
View File

@@ -1,28 +1,28 @@
import json
from typing import List, Tuple, Dict, Type
from opendevin.plan import Plan
from opendevin.action import Action, action_from_dict
from opendevin.observation import Observation
from opendevin.schema import ActionType
from opendevin.logger import opendevin_logger as logger
from typing import Dict, List, Tuple, Type
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]] = {
@@ -131,7 +131,7 @@ 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 """
"""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.",

31
containers/app/Dockerfile
View File

@@ -5,7 +5,7 @@ WORKDIR /app
COPY ./frontend/package.json frontend/package-lock.json ./
RUN npm install -g npm@10.5.1
RUN npm install
RUN npm ci
COPY ./frontend ./
RUN npm run make-i18n && npm run build
@@ -32,7 +32,8 @@ FROM python:3.12-slim as runtime
WORKDIR /app
ENV RUN_AS_DEVIN=false
ENV RUN_AS_DEVIN=true
ENV SANDBOX_USER_ID=1000
ENV USE_HOST_NETWORK=false
ENV SSH_HOSTNAME=host.docker.internal
ENV WORKSPACE_BASE=/opt/workspace_base
@@ -40,19 +41,31 @@ 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 useradd -l -m -u $SANDBOX_USER_ID -s /bin/bash opendevin && \
usermod -aG sudo opendevin && \
echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
RUN chown -R opendevin:opendevin /app
USER opendevin
ENV VIRTUAL_ENV=/app/.venv \
PATH="/app/.venv/bin:$PATH" \
PYTHONPATH='/app'
COPY --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
COPY --chown=opendevin --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
USER root
RUN chown -R opendevin:opendevin ${VIRTUAL_ENV}
USER opendevin
COPY ./opendevin ./opendevin
COPY ./agenthub ./agenthub
RUN python opendevin/download.py # No-op to download assets
COPY --chown=opendevin ./opendevin ./opendevin
COPY --chown=opendevin ./agenthub ./agenthub
RUN python opendevin/core/download.py # No-op to download assets
RUN playwright install --with-deps chromium
COPY --from=frontend-builder /app/dist ./frontend/dist
COPY --chown=opendevin --from=frontend-builder /app/dist ./frontend/dist
CMD ["uvicorn", "opendevin.server.listen:app", "--host", "0.0.0.0", "--port", "3000"]
COPY --chown=opendevin ./containers/app/entrypoint.sh /app/entrypoint.sh
USER root
CMD ["/app/entrypoint.sh"]

23
containers/app/entrypoint.sh Executable file
View File

@@ -0,0 +1,23 @@
#!/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
usermod -u $SANDBOX_USER_ID opendevin
# get the user group of /var/run/docker.sock and set opendevin to that group
DOCKER_SOCKET_GID=$(stat -c '%g' /var/run/docker.sock)
echo "Docker socket group id: $DOCKER_SOCKET_GID"
usermod -aG $DOCKER_SOCKET_GID opendevin
# switch to the user and start the server
su opendevin -c "cd /app && uvicorn opendevin.server.listen:app --host 0.0.0.0 --port 3000"

3
containers/build.sh
View File

@@ -44,6 +44,7 @@ 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"
@@ -53,12 +54,12 @@ for tag in ${tags[@]}; do
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-to=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag,mode=max \
--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 \

4
containers/sandbox/Dockerfile
View File

@@ -27,3 +27,7 @@ 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

29
dev_config/python/.pre-commit-config.yaml
View File

@@ -3,36 +3,41 @@ repos:
rev: v4.5.0
hooks:
- id: trailing-whitespace
exclude: docs/modules/python
- id: end-of-file-fixer
exclude: docs/modules/python
- id: check-yaml
- id: debug-statements
- repo: https://github.com/asottile/setup-cfg-fmt
rev: v2.5.0
- repo: https://github.com/tox-dev/pyproject-fmt
rev: 1.7.0
hooks:
- id: setup-cfg-fmt
always_run: true
pass_filenames: false
- id: pyproject-fmt
- repo: https://github.com/abravalheri/validate-pyproject
rev: v0.16
hooks:
- 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

5
dev_config/python/ruff.toml
View File

@@ -7,6 +7,7 @@ select = [
"E",
"W",
"F",
"I",
"Q",
]
@@ -14,7 +15,9 @@ ignore = [
"E501",
]
flake8-quotes = {inline-quotes = "single"}
[lint.flake8-quotes]
docstring-quotes = "double"
inline-quotes = "single"
[format]
quote-style = "single"

20
docs/.gitignore vendored Normal file
View File

@@ -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*

98
docs/Agents.md
View File

@@ -1,98 +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`,
`GithubPushAction`,
`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 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:
`__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

253
docs/README-zh.md
View File

@@ -1,253 +0,0 @@
> 警告：此说明文件可能已过时。应将 README.md 视为真实的来源。如果您注意到差异，请打开一个拉取请求以更新此说明文件。
[English](../README.md) | [中文](README-zh.md)
<a name="readme-top"></a>
<!--
*** Thanks for checking out the Best-README-Template. If you have a suggestion
*** that would make this better, please fork the repo and create a pull request
*** or simply open an issue with the tag "enhancement".
*** Don't forget to give the project a star!
*** Thanks again! Now go create something AMAZING! :D
-->
<!-- PROJECT SHIELDS -->
<!--
*** I'm using markdown "reference style" links for readability.
*** Reference links are enclosed in brackets [ ] instead of parentheses ( ).
*** See the bottom of this document for the declaration of the reference variables
*** for contributors-url, forks-url, etc. This is an optional, concise syntax you may use.
*** https://www.markdownguide.org/basic-syntax/#reference-style-links
-->
<div align="center">
<a href="https://github.com/OpenDevin/OpenDevin/graphs/contributors"><img src="https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge" alt="Contributors"></a>
<a href="https://github.com/OpenDevin/OpenDevin/network/members"><img src="https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge" alt="Forks"></a>
<a href="https://github.com/OpenDevin/OpenDevin/stargazers"><img src="https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge" alt="Stargazers"></a>
<a href="https://github.com/OpenDevin/OpenDevin/issues"><img src="https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge" alt="Issues"></a>
<a href="https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE"><img src="https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge" alt="MIT License"></a>
</br>
<a href="https://join.slack.com/t/opendevin/shared_invite/zt-2etftj1dd-X1fDL2PYIVpsmJZkqEYANw"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
<a href="https://discord.gg/mBuDGRzzES"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
</div>
<!-- PROJECT LOGO -->
<div align="center">
<img src="../logo.png" alt="Logo" width="200" height="200">
<h1 align="center">OpenDevin：少写代码，多创作</h1>
</div>
<!-- TABLE OF CONTENTS -->
<details>
<summary>🗂️ Table of Contents</summary>
<ol>
<li><a href="#-mission">🎯 Mission</a></li>
<li><a href="#-what-is-devin">🤔 What is Devin?</a></li>
<li><a href="#-why-opendevin">🐚 Why OpenDevin?</a></li>
<li><a href="#-project-status">🚧 Project Status</a></li>
<a href="#-get-started">🚀 Get Started</a>
<ul>
<li><a href="#1-requirements">1. Requirements</a></li>
<li><a href="#2-build-and-setup">2. Build and Setup</a></li>
<li><a href="#3-run-the-application">3. Run the Application</a></li>
<li><a href="#4-individual-server-startup">4. Individual Server Startup</a></li>
<li><a href="#5-help">5. Help</a></li>
</ul>
</li>
<li><a href="#%EF%B8%8F-research-strategy">⭐️ Research Strategy</a></li>
<li><a href="#-how-to-contribute">🤝 How to Contribute</a></li>
<li><a href="#-join-our-community">🤖 Join Our Community</a></li>
<li><a href="#%EF%B8%8F-built-with">🛠️ Built With</a></li>
<li><a href="#-license">📜 License</a></li>
</ol>
</details>
## 🎯 使命
[Project Demo Video](https://github.com/OpenDevin/OpenDevin/assets/38853559/71a472cc-df34-430c-8b1d-4d7286c807c9)
欢迎来到 OpenDevin，一个开源项目，旨在复制 Devin，一款自主的 AI 软件工程师，能够执行复杂的工程任务，并与用户积极合作，共同进行软件开发项目。该项目立志通过开源社区的力量复制、增强和创新 Devin。
<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
<a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
↑ Back to Top ↑
</a>
</p>
## 🤔 Devin 是什么？
Devin 代表着一种尖端的自主代理程序，旨在应对软件工程的复杂性。它利用诸如 shell、代码编辑器和 Web 浏览器等工具的组合，展示了在软件开发中利用 LLMs（大型语言模型）的未开发潜力。我们的目标是探索和拓展 Devin 的能力，找出其优势和改进空间，以指导开源代码模型的进展。
<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
<a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
↑ Back to Top ↑
</a>
</p>
## 🐚 为什么选择 OpenDevin？
OpenDevin 项目源于对复制、增强和超越原始 Devin 模型的愿望。通过与开源社区的互动，我们旨在解决 Code LLMs 在实际场景中面临的挑战，创作出对社区有重大贡献并为未来进步铺平道路的作品。
<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
<a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
↑ Back to Top ↑
</a>
</p>
## 🚧 项目状态
OpenDevin 目前仍在进行中，但您已经可以运行 alpha 版本来查看端到端系统的运行情况。项目团队正在积极努力实现以下关键里程碑：
- **用户界面（UI）**：开发用户友好的界面，包括聊天界面、演示命令的 shell 和 Web 浏览器。
- **架构**：构建一个稳定的代理框架，具有强大的后端，可以读取、写入和运行简单的命令。
- **代理能力**：增强代理的能力，以生成 bash 脚本、运行测试和执行其他软件工程任务。
- **评估**：建立一个与 Devin 评估标准一致的最小评估流水线。
在完成 MVP 后，团队将专注于各个领域的研究，包括基础模型、专家能力、评估和代理研究。
<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
<a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
↑ Back to Top ↑
</a>
</p>
## ⚠️ 注意事项和警告
- OpenDevin 仍然是一个 alpha 项目。它变化很快且不稳定。我们正在努力在未来几周发布稳定版本。
- OpenDevin 会向您配置的 LLM 发出许多提示。大多数 LLM 都需要花费金钱，请务必设置花费限制并监控使用情况。
- OpenDevin 在 Docker 沙箱中运行 `bash` 命令，因此不应影响您的计算机。但您的工作区目录将附加到该沙箱，并且目录中的文件可能会被修改或删除。
- 我们默认的代理目前是 MonologueAgent，具有有限的功能，但相当稳定。我们正在开发其他代理实现，包括 [SWE 代理](https://swe-agent.com/)。您可以[在这里阅读我们当前的代理集合](./docs/documentation/Agents.md)。
## 🚀 开始
开始使用 OpenDevin 项目非常简单。按照以下简单步骤在您的系统上设置和运行 OpenDevin：
运行 OpenDevin 最简单的方法是在 Docker 容器中。
您可以运行：
```bash
# 您的 OpenAI API 密钥，或任何其他 LLM API 密钥
export LLM_API_KEY="sk-..."
# 您想要 OpenDevin 修改的目录。必须是绝对路径！
export WORKSPACE_BASE=$(pwd)/workspace
docker run \
-e LLM_API_KEY \
-e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
-v $WORKSPACE_BASE:/opt/workspace_base \
-v /var/run/docker.sock:/var/run/docker.sock \
-p 3000:3000 \
ghcr.io/opendevin/opendevin:latest
```
将 `$(pwd)/workspace` 替换为您希望 OpenDevin 使用的代码路径。
您可以在 `http://localhost:3000` 找到正在运行的 OpenDevin。
请参阅[Development.md](Development.md)以获取在没有 Docker 的情况下运行 OpenDevin 的说明。
## 🤖 LLM 后端
OpenDevin 可以与任何 LLM 后端配合使用。
要获取提供的 LM 提供商和模型的完整列表，请参阅
[litellm 文档](https://docs.litellm.ai/docs/providers)。
`LLM_MODEL` 环境变量控制在编程交互中使用哪个模型，
但在 OpenDevin UI 中选择模型将覆盖此设置。
对于某些 LLM，可能需要以下环境变量：
- `LLM_API_KEY`
- `LLM_BASE_URL`
- `LLM_EMBEDDING_MODEL`
- `LLM_EMBEDDING_DEPLOYMENT_NAME`
- `LLM_API_VERSION`
**关于替代模型的说明：**
某些替代模型可能比其他模型更具挑战性。
不要害怕，勇敢的冒险家！我们将很快公布 LLM 特定的文档，指导您完成您的探险。
如果您已经掌握了除 OpenAI 的 GPT 之外的模型使用技巧，
我们鼓励您[与我们分享您的设置说明](https://github.com/OpenDevin/OpenDevin/issues/417)。
还有[使用 ollama 运行本地模型的文档](./docs/documentation/LOCAL_LLM_GUIDE.md)。
## ⭐️ 研究策略
利用 LLMs 实现生产级应用程序的完全复制是一个复杂的任务。我们的策略包括：
1. **核心技术研究：** 专注于基础研究，以了解和改进代码生成和处理的技术方面。
2. **专业能力：** 通过数据整理、训练方法等手段增强核心组件的效能。
3. **任务规划：** 开发能力，用于错误检测、代码库管理和优化。
4. **评估：** 建立全面的评估指标，以更好地了解和改进我们的模型。
<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
<a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
↑ Back to Top ↑
</a>
</p>
## 🤝 如何贡献
OpenDevin 是一个社区驱动的项目，我们欢迎所有人的贡献。无论您是开发人员、研究人员，还是对利用人工智能推动软件工程领域发展充满热情的人，都有许多参与方式：
- **代码贡献：** 帮助我们开发核心功能、前端界面或沙盒解决方案。
- **研究和评估：** 为我们对软件工程中的 LLMs 的理解做出贡献，参与评估模型，或提出改进意见。
- **反馈和测试：** 使用 OpenDevin 工具集，报告错误，提出功能建议，或就可用性提供反馈。
详情请查看[此文档](./CONTRIBUTING.md)。
<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
<a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
↑ Back to Top ↑
</a>
</p>
## 🤖 加入我们的社区
现在我们既有 Slack 工作空间用于协作构建 OpenDevin，也有 Discord 服务器用于讨论与项目、LLM、Agent 等相关的任何事情。
- [Slack 工作空间](https://join.slack.com/t/opendevin/shared_invite/zt-2etftj1dd-X1fDL2PYIVpsmJZkqEYANw)
- [Discord 服务器](https://discord.gg/mBuDGRzzES)
如果你愿意贡献，欢迎加入我们的社区（请注意，现在无需填写[表格](https://forms.gle/758d5p6Ve8r2nxxq6)）。让我们一起简化软件工程！
🐚 **少写代码，用 OpenDevin 创造更多。**
[![Star History Chart](https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date)](https://star-history.com/#OpenDevin/OpenDevin&Date)
## 🛠️ 技术栈
OpenDevin 使用了一系列强大的框架和库的组合，为其开发提供了坚实的基础。以下是项目中使用的关键技术：
![FastAPI](https://img.shields.io/badge/FastAPI-black?style=for-the-badge) ![uvicorn](https://img.shields.io/badge/uvicorn-black?style=for-the-badge) ![LiteLLM](https://img.shields.io/badge/LiteLLM-black?style=for-the-badge) ![Docker](https://img.shields.io/badge/Docker-black?style=for-the-badge) ![Ruff](https://img.shields.io/badge/Ruff-black?style=for-the-badge) ![MyPy](https://img.shields.io/badge/MyPy-black?style=for-the-badge) ![LlamaIndex](https://img.shields.io/badge/LlamaIndex-black?style=for-the-badge) ![React](https://img.shields.io/badge/React-black?style=for-the-badge)
请注意，这些技术的选择正在进行中，随着项目的发展，可能会添加其他技术或移除现有技术。我们致力于采用最合适和最有效的工具，以增强 OpenDevin 的功能。
<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
<a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
↑ Back to Top ↑
</a>
</p>
## 📜 许可证
根据 MIT 许可证分发。有关更多信息，请参阅 [`LICENSE`](./LICENSE)。
<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
<a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
↑ Back to Top ↑
</a>
</p>
[contributors-shield]: https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge
[contributors-url]: https://github.com/OpenDevin/OpenDevin/graphs/contributors
[forks-shield]: https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge
[forks-url]: https://github.com/OpenDevin/OpenDevin/network/members
[stars-shield]: https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge
[stars-url]: https://github.com/OpenDevin/OpenDevin/stargazers
[issues-shield]: https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge
[issues-url]: https://github.com/OpenDevin/OpenDevin/issues
[license-shield]: https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge
[license-url]: https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE

41
docs/README.md Normal file
View File

@@ -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.

14
docs/architecture/Architecture.md
View File

@@ -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)

22
docs/architecture/README.md
View File

@@ -1,22 +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/))

3
docs/babel.config.js Normal file
View File

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

128
docs/docusaurus.config.ts Normal file
View File

@@ -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;

73
docs/guides/Troubleshooting.md
View File

@@ -1,73 +0,0 @@
# Troubleshooting
> If you're running on Windows and having trouble, check out our [guide for Windows users](./Windows.md)
There are some error messages that get reported over and over by users.
We'll try and make the install process easier, and to make these error messages
better in the future. But for now, you can look for your error message below,
and see if there are any workaround.
For each of these error messages **there is an existing issue**. Please do not
open an new issue--just comment there.
If you find more information or a workaround for one of these issues, please
open a PR to add details to this file.
## Unable to connect to docker
https://github.com/OpenDevin/OpenDevin/issues/1226
### Symptoms
```
Error creating controller. Please check Docker is running using docker ps
```
```
docker.errors.DockerException: Error while fetching server API version: ('Connection aborted.', FileNotFoundError(2, 'No such file or directory'))
```
### Details
OpenDevin uses a docker container to do its work safely, without potentially breaking your machine.
### Workarounds
* Run `docker ps` to ensure that docker is running
* Make sure you don't need `sudo` to run docker [see here](https://www.baeldung.com/linux/docker-run-without-sudo)
## Unable to connect to SSH box
https://github.com/OpenDevin/OpenDevin/issues/1156
### Symptoms
```
self.shell = DockerSSHBox(
...
pexpect.pxssh.ExceptionPxssh: Could not establish connection to host
```
### Details
By default, OpenDevin connects to a running container using SSH. On some machines,
especially Windows, this seems to fail.
### Workarounds
* Restart your computer (sometimes works?)
* Be sure to have the latest versions of WSL and Docker
* Try [this reinstallation guide](https://github.com/OpenDevin/OpenDevin/issues/1156#issuecomment-2064549427)
* Set `-e SANDBOX_TYPE=exec` to switch to the ExecBox docker container
## Unable to connect to LLM
https://github.com/OpenDevin/OpenDevin/issues/1208
### Symptoms
```
File "/app/.venv/lib/python3.12/site-packages/openai/_exceptions.py", line 81, in __init__
super().__init__(message, response.request, body=body)
^^^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'request'
```
### Details
This usually happens with local LLM setups, when OpenDevin can't connect to the LLM server.
See our guide for [local LLMs](./LocalLLMs.md) for more information.
### Workarounds
* Check your `LLM_BASE_URL`
* Check that ollama is running OK
* Make sure you're using `--add-host host.docker.internal=host-gateway` when running in docker

BIN
docs/guides/images/ollama.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 39 KiB

3
docs/modules/python/python.md Normal file
View File

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

5
docs/modules/python/sidebar.json Normal file
View File

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

53
docs/modules/usage/about.md Normal file
View File

@@ -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.

142
docs/modules/usage/agents.md Normal file
View File

@@ -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&#x27;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 &amp; 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 |

51
docs/modules/usage/architecture.mdx Normal file
View File

@@ -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>

114
docs/modules/usage/intro.mdx Normal file
View File

@@ -0,0 +1,114 @@
---
sidebar_position: 1
---
# 💻 OpenDevin
OpenDevin is an **autonomous AI software engineer** capable of executing complex engineering tasks and collaborating actively with users on software development projects.
This project is fully open-source, so you can use and modify it however you like.
:::tip
Explore the codebase of OpenDevin on [GitHub](https://github.com/OpenDevin/OpenDevin) or join one of our communities!
<a href="https://github.com/OpenDevin/OpenDevin/graphs/contributors">
<img
src="https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge"
alt="Contributors"
/>
</a>
<a href="https://github.com/OpenDevin/OpenDevin/network/members">
<img
src="https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge"
alt="Forks"
/>
</a>
<a href="https://github.com/OpenDevin/OpenDevin/stargazers">
<img
src="https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge"
alt="Stargazers"
/>
</a>
<a href="https://github.com/OpenDevin/OpenDevin/issues">
<img
src="https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge"
alt="Issues"
/>
</a>
<br></br>
<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></br>
<a href="https://join.slack.com/t/opendevin/shared_invite/zt-2ggtwn3k5-PvAA2LUmqGHVZ~XzGq~ILw">
<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>
:::
## 🛠️ Getting Started
The easiest way to run OpenDevin is inside a Docker container.
To start the app, run these commands, replacing `$(pwd)/workspace` with the path to the code you want OpenDevin to work with.
```
# Your OpenAI API key, or any other LLM API key
export LLM_API_KEY="sk-..."
```
```
# The directory you want OpenDevin to modify.
# MUST be an absolute path!
export WORKSPACE_BASE=$(pwd)/workspace
```
:::warning
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.
:::
```
docker run \
-e LLM_API_KEY \
-e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
-v $WORKSPACE_BASE:/opt/workspace_base \
-v /var/run/docker.sock:/var/run/docker.sock \
-p 3000:3000 \
--add-host host.docker.internal=host-gateway \
ghcr.io/opendevin/opendevin:0.4.0
```
You'll find opendevin running at [http://localhost:3000](http://localhost:3000).
:::tip
If you want to use the **(unstable!)** bleeding edge, you can use `ghcr.io/opendevin/opendevin:main` as the image (last line).
:::
See Development.md for instructions on running OpenDevin without Docker.
Having trouble? Check out our Troubleshooting Guide.
:::warning
OpenDevin is currently a work in progress, but you can already run the alpha version to see the end-to-end system in action.
:::
[contributors-shield]: https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge
[contributors-url]: https://github.com/OpenDevin/OpenDevin/graphs/contributors
[forks-shield]: https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge
[forks-url]: https://github.com/OpenDevin/OpenDevin/network/members
[stars-shield]: https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge
[stars-url]: https://github.com/OpenDevin/OpenDevin/stargazers
[issues-shield]: https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge
[issues-url]: https://github.com/OpenDevin/OpenDevin/issues
[license-shield]: https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge
[license-url]: https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE

16
docs/guides/AzureLLMs.md → docs/modules/usage/llms/azureLLMs.md
View File

@@ -1,12 +1,13 @@
# Azure OpenAI LLM Guide
# Azure OpenAI LLM
# 1. Completion
## Completion
OpenDevin uses LiteLLM for completion calls. You can find their documentation on Azure [here](https://docs.litellm.ai/docs/providers/azure)
## azure openai configs
### Azure openai configs
When running the OpenDevin Docker image, you'll need to set the following environment variables using `-e`:
```
LLM_BASE_URL="<azure-api-base-url>" # e.g. "https://openai-gpt-4-test-v-1.openai.azure.com/"
LLM_API_KEY="<azure-api-key>"
@@ -14,20 +15,21 @@ LLM_MODEL="azure/<your-gpt-deployment-name>"
LLM_API_VERSION = "<api-version>" # e.g. "2024-02-15-preview"
```
## Important Note:
:::note
You can find your ChatGPT deployment name on the deployments page in Azure. It could be the same with the chat model name (e.g. 'GPT4-1106-preview'), by default or initially set, but it doesn't have to be the same. Run opendevin, and when you load it in the browser, go to Settings and set model as above: "azure/&lt;your-actual-gpt-deployment-name&gt;". If it's not in the list, enter your own text and save it.
:::
# 2. Embeddings
## Embeddings
OpenDevin uses llama-index for embeddings. You can find their documentation on Azure [here](https://docs.llamaindex.ai/en/stable/api_reference/embeddings/azure_openai/)
## azure openai configs
### Azure openai configs
The model used for Azure OpenAI embeddings is "text-embedding-ada-002".
You need the correct deployment name for this model in your Azure account.
When running OpenDevin in Docker, set the following environment variables using `-e`:
```
LLM_EMBEDDING_MODEL="azureopenai"
LLM_EMBEDDING_DEPLOYMENT_NAME = "<your-embedding-deployment-name>" # e.g. "TextEmbedding...<etc>"

12
docs/guides/GoogleLLMs.md → docs/modules/usage/llms/googleLLMs.md
View File

@@ -1,23 +1,25 @@
# Google Gemini/Vertex LLM Guide
# Google Gemini/Vertex LLM
# 1. Completion
## Completion
OpenDevin uses LiteLLM for completion calls. The following resources are relevant for using OpenDevin with Google's LLMs
- [Gemini - Google AI Studio](https://docs.litellm.ai/docs/providers/gemini)
- [VertexAI - Google Cloud Platform](https://docs.litellm.ai/docs/providers/vertex)
## Gemini - Google AI Studio Configs
### Gemini - Google AI Studio Configs
To use Gemini through Google AI Studio when running the OpenDevin Docker image, you'll need to set the following environment variables using `-e`:
```
GEMINI_API_KEY="<your-google-api-key>"
LLM_MODEL="gemini/gemini-1.5-pro"
```
## Vertex AI - Google Cloud Platform Configs
### Vertex AI - Google Cloud Platform Configs
To use Vertex AI through Google Cloud Platform when running the OpenDevin Docker image, you'll need to set the following environment variables using `-e`:
```
GOOGLE_APPLICATION_CREDENTIALS="<json-dump-of-gcp-service-account-json>"
VERTEXAI_PROJECT="<your-gcp-project-id>"

47
docs/modules/usage/llms/llms.md Normal file
View File

@@ -0,0 +1,47 @@
---
sidebar_position: 2
---
# 🤖 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).
:::warning
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.
:::
The `LLM_MODEL` environment variable controls which model is used in programmatic interactions.
But when using the OpenDevin UI, you'll need to choose your model in the settings window (the gear
wheel on the bottom left).
The following environment variables might be necessary for some LLMs:
- `LLM_API_KEY`
- `LLM_BASE_URL`
- `LLM_EMBEDDING_MODEL`
- `LLM_EMBEDDING_DEPLOYMENT_NAME`
- `LLM_API_VERSION`
We have a few guides for running OpenDevin with specific model providers:
- [ollama](llms/localLLMs)
- [Azure](llms/azureLLMs)
If you're using another provider, we encourage you to open a PR to share your setup!
## Note on Alternative Models
The best models are GPT-4 and Claude 3. Current local and open source models are
not nearly as powerful. When using an alternative model,
you may see long wait times between messages,
poor responses, or errors about malformed JSON. OpenDevin
can only be as powerful as the models driving it--fortunately folks on our team
are actively working on building better open source models!
## API retries and rate limits
Some LLMs have rate limits and may require retries. OpenDevin will automatically retry requests if it receives a 429 error or API connection error.
You can set `LLM_NUM_RETRIES`, `LLM_RETRY_MIN_WAIT`, `LLM_RETRY_MAX_WAIT` environment variables to control the number of retries and the time between retries.
By default, `LLM_NUM_RETRIES` is 5 and `LLM_RETRY_MIN_WAIT`, `LLM_RETRY_MAX_WAIT` are 3 seconds and respectively 60 seconds.

23
docs/guides/LocalLLMs.md → docs/modules/usage/llms/localLLMs.md
View File

@@ -1,11 +1,11 @@
# Local LLM Guide with Ollama server
# Local LLM with Ollama
Ensure that you have the Ollama server up and running.
For detailed startup instructions, refer to the [here](https://github.com/ollama/ollama)
This guide assumes you've started ollama with `ollama serve`. If you're running ollama differently (e.g. inside docker), the instructions might need to be modified. Please note that if you're running wsl the default ollama configuration blocks requests from docker containers. See [here](#4-configuring-the-ollama-service-wsl).
## 1. Pull Models
## Pull Models
Ollama model names can be found [here](https://ollama.com/library). For a small example, you can use
the `codellama:7b` model. Bigger models will generally perform better.
@@ -24,10 +24,11 @@ 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. Start OpenDevin
## Start OpenDevin
### 2.1 Docker
Use the instructions in [README.md](/README.md) to start OpenDevin using Docker.
### Docker
Use the instructions [here](../intro) to start OpenDevin using Docker.
But when running `docker run`, you'll need to add a few more arguments:
```bash
@@ -55,8 +56,9 @@ docker run \
You should now be able to connect to `http://localhost:3000/`
### 2.2 Build from Source
Use the instructions in [Development.md](/Development.md) to build OpenDevin.
### Build from Source
Use the instructions in [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md) to build OpenDevin.
Make sure `config.toml` is there by running `make setup-config` which will create one for you. In `config.toml`, enter the followings:
```
@@ -67,11 +69,12 @@ LLM_BASE_URL="http://localhost:11434"
WORKSPACE_BASE="./workspace"
WORKSPACE_DIR="$(pwd)/workspace"
```
Replace `LLM_MODEL` of your choice if you need to.
Done! Now you can start Devin by: `make run` without Docker. You now should be able to connect to `http://localhost:3000/`
## 3. Select your Model
## Select your Model
In the OpenDevin UI, click on the Settings wheel in the bottom-left corner.
Then in the `Model` input, enter `ollama/codellama:7b`, or the name of the model you pulled earlier.
@@ -79,7 +82,7 @@ If it doesn’t show up in a dropdown, that’s fine, just type it in. Click Sav
And now you're ready to go!
## 4. Configuring the ollama service (WSL)
## Configuring the ollama service (WSL)
The default configuration for ollama in wsl only serves localhost. This means you can't reach it from a docker container. eg. it wont work with OpenDevin. First let's test that ollama is running correctly.
@@ -98,7 +101,7 @@ docker exec [CONTAINER ID] curl http://host.docker.internal:11434/api/generate -
#ex. docker exec cd9cc82f7a11 curl http://host.docker.internal:11434/api/generate -d '{"model":"codellama","prompt":"hi"}'
```
### Fixing it
## Fixing it
Now let's make it work, edit /etc/systemd/system/ollama.service with sudo priviledges. (Path may vary depending on linux flavor)

135
docs/modules/usage/troubleshooting/troubleshooting.md Normal file
View File

@@ -0,0 +1,135 @@
---
sidebar_position: 5
---
# 🚧 Troubleshooting
There are some error messages that get reported over and over by users.
We'll try and make the install process easier, and to make these error messages
better in the future. But for now, you can look for your error message below,
and see if there are any workaround.
For each of these error messages **there is an existing issue**. Please do not
open an new issue--just comment there.
If you find more information or a workaround for one of these issues, please
open a PR to add details to this file.
:::tip
If you're running on Windows and having trouble, check out our [guide for Windows users](troubleshooting/windows)
:::
## Unable to connect to docker
[GitHub Issue](https://github.com/OpenDevin/OpenDevin/issues/1226)
### Symptoms
```
Error creating controller. Please check Docker is running and visit `https://opendevin.github.io/OpenDevin/modules/usage/troubleshooting` for more debugging information.
```
```
docker.errors.DockerException: Error while fetching server API version: ('Connection aborted.', FileNotFoundError(2, 'No such file or directory'))
```
### Details
OpenDevin uses a docker container to do its work safely, without potentially breaking your machine.
### Workarounds
* Run `docker ps` to ensure that docker is running
* Make sure you don't need `sudo` to run docker [see here](https://www.baeldung.com/linux/docker-run-without-sudo)
* If you are on a mac, check the [permissions requirements](https://docs.docker.com/desktop/mac/permission-requirements/) and in particular consider enabling the "Allow the default Docker socket to be used" under "Settings > Advanced" in Docker Desktop.
## Unable to connect to SSH box
[GitHub Issue](https://github.com/OpenDevin/OpenDevin/issues/1156)
### Symptoms
```
self.shell = DockerSSHBox(
...
pexpect.pxssh.ExceptionPxssh: Could not establish connection to host
```
### Details
By default, OpenDevin connects to a running container using SSH. On some machines,
especially Windows, this seems to fail.
### Workarounds
- Restart your computer (sometimes works?)
- Be sure to have the latest versions of WSL and Docker
- Try [this reinstallation guide](https://github.com/OpenDevin/OpenDevin/issues/1156#issuecomment-2064549427)
- Set `-e SANDBOX_TYPE=exec` to switch to the ExecBox docker container
## Unable to connect to LLM
[GitHub Issue](https://github.com/OpenDevin/OpenDevin/issues/1208)
### Symptoms
```
File "/app/.venv/lib/python3.12/site-packages/openai/_exceptions.py", line 81, in __init__
super().__init__(message, response.request, body=body)
^^^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'request'
```
### Details
[GitHub Issues](https://github.com/OpenDevin/OpenDevin/issues?q=is%3Aissue+is%3Aopen+404)
This usually happens with local LLM setups, when OpenDevin can't connect to the LLM server.
See our guide for [local LLMs](llms/localLLMs) for more information.
### Workarounds
- Check your `LLM_BASE_URL`
- Check that ollama is running OK
- Make sure you're using `--add-host host.docker.internal=host-gateway` when running in docker
## 404 Resource not found
### Symptoms
```
Traceback (most recent call last):
File "/app/.venv/lib/python3.12/site-packages/litellm/llms/openai.py", line 414, in completion
raise e
File "/app/.venv/lib/python3.12/site-packages/litellm/llms/openai.py", line 373, in completion
response = openai_client.chat.completions.create(**data, timeout=timeout) # type: ignore
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/openai/_utils/_utils.py", line 277, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/openai/resources/chat/completions.py", line 579, in create
return self._post(
^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1232, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 921, in request
return self._request(
^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1012, in _request
raise self._make_status_error_from_response(err.response) from None
openai.NotFoundError: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
```
### Details
This happens when LiteLLM (our library for connecting to different LLM providers) can't find
the API you're trying to connect to. Most often this happens for Azure or ollama users.
### Workarounds
- Check that you've set `LLM_BASE_URL` properly
- Check that model is set properly, based on the [LiteLLM docs](https://docs.litellm.ai/docs/providers)
- If you're running inside the UI, be sure to set the `model` in the settings modal
- If you're running headless (via main.py) be sure to set `LLM_MODEL` in your env/config
- Make sure you've followed any special instructions for your LLM provider
- [ollama](/OpenDevin/modules/usage/llms/localLLMs)
- [Azure](/OpenDevin/modules/usage/llms/azureLLMs)
- [Google](/OpenDevin/modules/usage/llms/googleLLMs)
- Make sure your API key is correct
- See if you can connect to the LLM using `curl`
- Try [connecting via LiteLLM directly](https://github.com/BerriAI/litellm) to test your setup

17
docs/guides/Windows.md → docs/modules/usage/troubleshooting/windows.md
View File

@@ -1,31 +1,36 @@
# Notes for Windows and WSL Users
OpenDevin only supports Windows via [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
Please be sure to run all commands inside your WSL terminal.
## Troubleshooting
### Failed to create opendevin user
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
```
` export SANDBOX_USER_ID=1000
`
### Poetry Installation
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"
```
` export PATH="$HOME/.local/bin:$PATH"
`
### NoneType object has no attribute 'request'
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.

15363
docs/package-lock.json generated Normal file
View File

File diff suppressed because it is too large Load Diff

51
docs/package.json Normal file
View File

@@ -0,0 +1,51 @@
{
"name": "docs",
"version": "0.0.0",
"private": true,
"scripts": {
"docusaurus": "docusaurus",
"start": "docusaurus start",
"build": "docusaurus build",
"swizzle": "docusaurus swizzle",
"deploy": "docusaurus deploy",
"clear": "docusaurus clear",
"serve": "docusaurus serve",
"write-translations": "docusaurus write-translations",
"write-heading-ids": "docusaurus write-heading-ids",
"typecheck": "tsc"
},
"dependencies": {
"@docusaurus/core": "3.2.1",
"@docusaurus/preset-classic": "3.2.1",
"@mdx-js/react": "^3.0.0",
"autoprefixer": "^10.4.19",
"clsx": "^2.0.0",
"postcss": "^8.4.38",
"prism-react-renderer": "^2.3.0",
"react": "^18.0.0",
"react-dom": "^18.0.0",
"react-use": "^17.5.0",
"tailwindcss": "^3.4.3"
},
"devDependencies": {
"@docusaurus/module-type-aliases": "3.2.1",
"@docusaurus/tsconfig": "3.2.1",
"@docusaurus/types": "3.2.1",
"typescript": "~5.2.2"
},
"browserslist": {
"production": [
">0.5%",
"not dead",
"not op_mini all"
],
"development": [
"last 3 chrome version",
"last 3 firefox version",
"last 5 safari version"
]
},
"engines": {
"node": ">=18.0"
}
}

8
docs/sidebars.ts Normal file
View File

@@ -0,0 +1,8 @@
import type { SidebarsConfig } from "@docusaurus/plugin-content-docs";
const sidebars: SidebarsConfig = {
docsSidebar: [{ type: "autogenerated", dirName: "usage" }],
apiSidebar: [require("./modules/python/sidebar.json")],
};
export default sidebars;

47
docs/src/components/Code/Code.tsx Normal file
View File

@@ -0,0 +1,47 @@
import Link from "@docusaurus/Link";
import { Header } from "@site/src/pages";
import { CodeBlock } from "./CodeBlock";
import styles from "./styles.module.css";
export function Code() {
const keyCode = `# Your OpenAI API key, or any other LLM API key
export LLM_API_KEY="sk-..."`;
const workspaceCode = `# The directory you want OpenDevin to modify. MUST be an absolute path!
export WORKSPACE_BASE=$(pwd)/workspace`;
const dockerCode = `docker run \\
-e LLM_API_KEY \\
-e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \\
-v $WORKSPACE_BASE:/opt/workspace_base \\
-v /var/run/docker.sock:/var/run/docker.sock \\
-p 3000:3000 \\
--add-host host.docker.internal=host-gateway \\
ghcr.io/opendevin/opendevin:0.3.1`;
return (
<div className={styles.container}>
<div className={styles.innerContainer}>
<div className={styles.header}>
<Header
title="Getting Started"
summary="Getting Started"
description="Get started using OpenDevin in just a few lines of code"
></Header>
<div className={styles.buttons}>
<Link
className="button button--secondary button--lg"
to="/modules/usage/intro"
>
Learn More
</Link>
</div>
</div>
<br />
<CodeBlock language="python" code={keyCode} />
<CodeBlock language="python" code={workspaceCode} />
<CodeBlock language="python" code={dockerCode} />
</div>
</div>
);
}

63
docs/src/components/Code/CodeBlock.tsx Normal file
View File

@@ -0,0 +1,63 @@
import { useColorMode } from "@docusaurus/theme-common";
import { Highlight, themes } from "prism-react-renderer";
import { useCopyToClipboard } from "react-use";
interface CodeBlockProps {
language: string;
code: string;
}
export function CodeBlock({ language, code }: CodeBlockProps) {
const [state, copyToClipboard] = useCopyToClipboard();
const { isDarkTheme } = useColorMode();
const copyCode = () => {
copyToClipboard(code);
};
return (
<div
style={{
position: "relative",
}}
>
<Highlight
theme={isDarkTheme ? themes.vsLight : themes.vsDark}
code={code}
language={language}
>
{({ style, tokens, getLineProps, getTokenProps }) => (
<pre style={style}>
{tokens.map((line, i) => (
<div key={i} {...getLineProps({ line })}>
<span
style={{
display: "inline-block",
width: "3em",
color: "var(--gray)",
}}
>
{i + 1}
</span>
{line.map((token, key) => (
<span key={key} {...getTokenProps({ token })} />
))}
</div>
))}
</pre>
)}
</Highlight>
<button
className="button button--secondary"
style={{
position: "absolute",
top: "10px",
right: "10px",
}}
onClick={copyCode}
>
{state.value ? "Copied!" : "Copy"}
</button>
</div>
);
}

26
docs/src/components/Code/styles.module.css Normal file
View File

@@ -0,0 +1,26 @@
.container {
display: flex;
flex-direction: column;
padding-top: 25px;
padding-bottom: 25px;
width: 100%;
}
.innerContainer {
padding: 50px;
width: 100%;
max-width: 1300px;
padding-top: 30px;
margin: auto;
}
.header {
display: flex;
justify-content: space-between;
}
@media (max-width: 768px) {
.header {
flex-direction: column;
}
}

25
docs/src/components/Demo/Demo.tsx Normal file
View File

@@ -0,0 +1,25 @@
import React from "react";
import styles from "./index.module.css";
export function Demo() {
const videoRef = React.useRef<HTMLVideoElement>(null);
return (
<div
style={{ paddingBottom: "30px", paddingTop: "20px", textAlign: "center" }}
>
<video
playsInline
autoPlay={true}
loop
className={styles.demo}
muted
onMouseOver={() => (videoRef.current.controls = true)}
onMouseOut={() => (videoRef.current.controls = false)}
ref={videoRef}
>
<source src="img/teaser.mp4" type="video/mp4"></source>
</video>
</div>
);
}

7
docs/src/components/Demo/index.module.css Normal file
View File

@@ -0,0 +1,7 @@
.demo {
width: 100%;
padding: 30px;
max-width: 800px;
text-align: center;
border-radius: 40px;
}

28
docs/src/components/HomepageHeader/HomepageHeader.tsx Normal file
View File

@@ -0,0 +1,28 @@
import Link from "@docusaurus/Link";
import useDocusaurusContext from "@docusaurus/useDocusaurusContext";
import Heading from "@theme/Heading";
import { Demo } from "../Demo/Demo";
import styles from "./index.module.css";
export function HomepageHeader() {
const { siteConfig } = useDocusaurusContext();
return (
<div className={styles.headerContainer}>
<div className={styles.header}>
<Heading as="h1" className="hero__title">
{siteConfig.title}
</Heading>
<p className="hero__subtitle">{siteConfig.tagline}</p>
<div className={styles.buttons}>
<Link
className="button button--secondary button--lg"
to="/modules/usage/intro"
>
Get Started
</Link>
</div>
</div>{" "}
<Demo />
</div>
);
}

37
docs/src/components/HomepageHeader/index.module.css Normal file
View File

@@ -0,0 +1,37 @@
.headerContainer {
background: radial-gradient(circle, var(--secondary), var(--secondary-light));
background-size: 200% 200%;
animation: gradientAnimation 10s linear infinite;
display: flex;
justify-content: center;
}
@media only screen and (max-width: 600px) {
.headerContainer {
flex-direction: column;
}
}
@keyframes gradientAnimation {
0% {
background-position: left center;
}
50% {
background-position: right center;
}
100% {
background-position: left center;
}
}
.header {
max-width: 1300px;
color: white;
display: flex;
margin-left: 100px;
margin-right: 100px;
flex-direction: column;
align-items: center;
justify-content: center;
overflow: hidden;
padding: 70px 30px 30px;
}

19
docs/src/components/Welcome/Welcome.tsx Normal file
View File

@@ -0,0 +1,19 @@
import styles from "./styles.module.css";
export function Welcome() {
return (
<div className={styles.container}>
<div className={styles.innerContainer}>
<img src="img/logo.png" className={styles.sidebarImage} />
<p className={styles.welcomeText}>
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>
</div>
</div>
);
}

27
docs/src/components/Welcome/styles.module.css Normal file
View File

@@ -0,0 +1,27 @@
.container {
display: flex;
flex-direction: column;
padding-top: 25px;
padding-bottom: 25px;
width: 100%;
}
.innerContainer {
padding: 50px;
width: 100%;
max-width: 1300px;
padding-top: 30px;
margin: auto;
display: flex;
align-items: center;
}
.sidebarImage {
max-width: 400px;
padding-right: 30px;
}
.welcomeText {
text-align: justify;
font-size: larger;
}

36
docs/src/css/custom.css Normal file
View File

@@ -0,0 +1,36 @@
/**
* Any CSS included here will be global. The classic template
* bundles Infima by default. Infima is a CSS framework designed to
* work well for content-centric websites.
*/
/* You can override the default Infima variables here. */
:root {
--ifm-color-primary: #4465db;
--ifm-code-font-size: 95%;
--docusaurus-highlighted-code-line-bg: rgba(0, 0, 0, 0.1);
--secondary: #171717;
--secondary-dark: #0a0a0a;
--secondary-light: #737373;
}
/* For readability concerns, you should choose a lighter palette in dark mode. */
[data-theme="dark"] {
--ifm-color-primary: #4465db;
--docusaurus-highlighted-code-line-bg: rgba(0, 0, 0, 0.3);
--secondary: #737373;
--secondary-dark: #171717;
--secondary-light: #d4d4d4;
}
.footer--dark {
background-image: linear-gradient(
140deg,
var(--secondary) 20%,
var(--secondary-light) 100%
);
}
.a {
text-decoration: underline;
}

56
docs/src/pages/faq.tsx Normal file
View File

@@ -0,0 +1,56 @@
import Layout from "@theme/Layout";
export default function FAQ() {
return (
<Layout title="FAQ" description="Frequently Asked Questions">
<div
id="faq"
style={{
maxWidth: "900px",
margin: "0px auto",
padding: "40px",
textAlign: "justify",
}}
>
<h1 style={{ fontSize: "3rem" }}>Frequently Asked Questions</h1>
<h2 style={{ fontSize: "2rem" }}>Support</h2>
<h3>How can I report an issue with OpenDevin?</h3>
<p>
Please file a bug on{" "}
<a href="https://github.com/OpenDevin/OpenDevin/issues">GitHub</a> if
you notice a problem that likely affects others.
If you're having trouble installing, or have general questions, reach out on{" "}
<a href="https://discord.gg/mBuDGRzzES">Discord</a> or{" "}
<a href="https://join.slack.com/t/opendevin/shared_invite/zt-2ggtwn3k5-PvAA2LUmqGHVZ~XzGq~ILw">Slack</a>.
</p>
<h2 style={{ fontSize: "2rem" }}>General</h2>
<h3>What is Devin?</h3>
<p>
<span style={{ fontWeight: "600", color: "var(--logo)" }}>Devin</span>{" "}
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>
<h3>Why OpenDevin?</h3>
<p>
The{" "}
<span style={{ fontWeight: "600", color: "var(--logo)" }}>
OpenDevin
</span>{" "}
project is born out of a desire to replicate, enhance, and innovate
beyond the original Devin model. By engaging the{" "}
<a href="https://github.com/OpenDevin/OpenDevin">
open-source community
</a>
, 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>
</div>
</Layout>
);
}

23
docs/src/pages/index.module.css Normal file
View File

@@ -0,0 +1,23 @@
/**
* CSS files with the .module.css suffix will be treated as CSS modules
* and scoped locally.
*/
.heroBanner {
padding: 4rem 0;
text-align: center;
position: relative;
overflow: hidden;
}
@media screen and (max-width: 996px) {
.heroBanner {
padding: 2rem;
}
}
.buttons {
display: flex;
align-items: center;
justify-content: center;
}

33
docs/src/pages/index.tsx Normal file
View File

@@ -0,0 +1,33 @@
import useDocusaurusContext from "@docusaurus/useDocusaurusContext";
import Layout from "@theme/Layout";
import { Code } from "../components/Code/Code";
import { HomepageHeader } from "../components/HomepageHeader/HomepageHeader";
import { Welcome } from "../components/Welcome/Welcome";
export function Header({ title, summary, description }): JSX.Element {
return (
<div>
<h2 style={{ fontSize: "40px" }}>{summary}</h2>
<h3 className="headerDescription">{description}</h3>
</div>
);
}
export default function Home(): JSX.Element {
const { siteConfig } = useDocusaurusContext();
return (
<Layout
title={`Hello from ${siteConfig.title}`}
description="AI-powered code generation for software engineering."
>
<div>
<HomepageHeader />
<div>
<Welcome />
<Code />
</div>
</div>
</Layout>
);
}

0
docs/static/.nojekyll vendored Normal file
View File

0
docs/architecture/backend_architecture.png → docs/static/img/backend_architecture.png vendored
View File

Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 267 KiB

After

Width:  |  Height:  |  Size: 267 KiB

0
docs/architecture/backend_architecture.puml → docs/static/img/backend_architecture.puml vendored
View File

Some files were not shown because too many files have changed in this diff Show More