Fix duplicate LLM_BASE_URL entry in config.toml and enable different ollama embeddings (#1437)

Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>

.gitattributes

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

.github/workflows/deploy-docs.yml

@@ -0,0 +1,55 @@
+name: Deploy Docs to GitHub Pages
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  build:
+    name: Build Docusaurus
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: docs
+    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: Install dependencies
+        run: npm ci
+      - name: Build website
+        run: npm run build
+
+      - name: Upload Build Artifact
+        if: github.ref == 'refs/heads/main'
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: docs/build
+
+  deploy:
+    name: Deploy to GitHub Pages
+    needs: build
+    if: github.ref == 'refs/heads/main'
+    # Grant GITHUB_TOKEN the permissions required to make a Pages deployment
+    permissions:
+      pages: write # to deploy to Pages
+      id-token: write # to verify the deployment originates from an appropriate source
+    # Deploy to the github-pages environment
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

.github/workflows/ghcr.yml

@@ -2,6 +2,9 @@ name: Publish Docker Image
 
 on:
   push:
+    branches:
+    - main
+  pull_request:
   workflow_dispatch:
     inputs:
       reason:
@@ -12,7 +15,11 @@ 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"]
@@ -28,13 +35,29 @@ jobs:
         id: buildx
         uses: docker/setup-buildx-action@v3
 
-      - name: Log-in to ghcr.io
-        run: echo "${{ secrets.GITHUB_TOKEN }}" | docker login ghcr.io -u ${{ github.actor }} --password-stdin
+      - name: Login to ghcr
+        uses: docker/login-action@v1
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Delete huge unnecessary tools folder
         run: rm -rf /opt/hostedtoolcache
 
       - name: Build and push ${{ matrix.image }}
+        if: github.event.pull_request.head.repo.full_name == github.repository
         run: |
-          ORG_NAME=$(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.full_name != github.repository
+        run: |
+          ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }}
+
+  docker_build_success:
+    name: Docker Build Success
+    runs-on: ubuntu-latest
+    needs: ghcr_build_and_push
+    steps:
+    - run: echo Done!

.github/workflows/lint.yml

@@ -1,9 +1,14 @@
 name: Lint
 
-on: [push, pull_request]
+on:
+  push:
+    branches:
+    - main
+  pull_request:
 
 jobs:
   lint-frontend:
+    name: Lint frontend
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
@@ -32,7 +37,12 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: 3.11
+          cache: 'pip'
       - name: Install pre-commit
         run: pip install pre-commit==3.7.0
       - name: Run pre-commit hooks
-        run: pre-commit run --files opendevin/**/* agenthub/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
+        run: |
+          pre-commit run \
+            --all-files \
+            --show-diff-on-failure \
+            --config ./dev_config/python/.pre-commit-config.yaml

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

@@ -1,63 +1,52 @@
 name: Run Integration Tests
 
-on: [push, pull_request]
+on:
+  push:
+    branches:
+    - main
+  pull_request:
 
 jobs:
-  on-linux:
+  integration-tests:
+    name: Integration Tests
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
+        python-version: ["3.11"]
+        agent: ["SWEAgent", "PlannerAgent", "MonologueAgent", "CodeActAgent"]
+        sandbox: ["ssh", "exec"]
         include:
-          - 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"
+          - 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"
+          - agent: "MonologueAgent"
+            # sufficient to have one agent testing against local sandbox
+            sandbox: "local"
             embedding-model: "local"
-            sandbox: "exec"
-          - name: CodeActAgent-py311-exec
-            python-version: "3.11"
-            agent: "CodeActAgent"
+          - agent: "SWEAgent"
+            embedding-model: "none"
+          - agent: "PlannerAgent"
+            embedding-model: "none"
+          - agent: "CodeActAgent"
             embedding-model: "none"
-            sandbox: "exec"
     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: ${{ matrix.sandbox }}
@@ -67,4 +56,17 @@ jobs:
         run: |
           rm -rf workspace
           mkdir workspace
-          WORKSPACE_BASE="$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
+    needs: [integration-tests]
+    steps:
+    - run: echo Done!

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

@@ -1,9 +1,14 @@
 name: Run Unit Tests
 
-on: [push, pull_request]
+on:
+  push:
+    branches:
+    - main
+  pull_request:
 
 jobs:
-  on-macos:
+  test-on-macos:
+    name: Test on macOS
     runs-on: macos-13
     strategy:
       matrix:
@@ -11,23 +16,35 @@ 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
+
       - name: Build Environment
         run: make build
+
       - name: Run Tests
-        run: poetry run pytest ./tests/unit
-  on-linux:
+        run: poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+  test-on-linux:
+    name: Test on Linux
     runs-on: ubuntu-latest
     strategy:
       matrix:
@@ -35,13 +52,31 @@ 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
+        run: poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+  test_matrix_success:
+    name: All Mac/Linux Tests Passed
+    runs-on: ubuntu-latest
+    needs: [test-on-macos, test-on-linux]
+    steps:
+    - run: echo Done!

Makefile

@@ -128,6 +128,7 @@ install-python-dependencies:
 		poetry run pip install chroma-hnswlib; \
 	fi
 	@poetry install --without evaluation
+	@poetry run playwright install --with-deps chromium
 	@echo "$(GREEN)Python dependencies installed successfully.$(RESET)"
 
 install-frontend-dependencies:
@@ -149,7 +150,7 @@ install-precommit-hooks:
 
 lint:
 	@echo "$(YELLOW)Running linters...$(RESET)"
-	@poetry run pre-commit run --files opendevin/**/* agenthub/**/* --show-diff-on-failure --config $(PRECOMMIT_CONFIG_PATH)
+	@poetry run pre-commit run --all-files --show-diff-on-failure --config $(PRECOMMIT_CONFIG_PATH)
 
 build-frontend:
 	@echo "$(YELLOW)Building frontend...$(RESET)"
@@ -158,7 +159,7 @@ build-frontend:
 # Start backend
 start-backend:
 	@echo "$(YELLOW)Starting backend...$(RESET)"
-	@poetry run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT) --reload --reload-dir opendevin --reload-dir agenthub --reload-dir evaluation
+	@poetry run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT) --reload --reload-exclude workspace/*
 
 # Start frontend
 start-frontend:
@@ -189,7 +190,7 @@ setup-config:
 	@echo "$(GREEN)Config.toml setup completed.$(RESET)"
 
 setup-config-prompts:
-	@read -p "Enter your LLM Model name (see https://docs.litellm.ai/docs/providers for full list) [default: $(DEFAULT_MODEL)]: " llm_model; \
+	@read -p "Enter your LLM Model name, used for running without UI. Set the model in the UI after you start the app. (see https://docs.litellm.ai/docs/providers for full list) [default: $(DEFAULT_MODEL)]: " llm_model; \
 	 llm_model=$${llm_model:-$(DEFAULT_MODEL)}; \
 	 echo "LLM_MODEL=\"$$llm_model\"" > $(CONFIG_FILE).tmp
 
@@ -199,12 +200,22 @@ 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; \

README.md

@@ -1,5 +1,3 @@
-[English](README.md) | [中文](docs/README-zh.md)
-
 <a name="readme-top"></a>
 
 <!--
@@ -32,168 +30,15 @@
 
 <!-- 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:0.3.1
-```
-
-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;">
@@ -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 ↑

agenthub/SWE_agent/__init__.py

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

agenthub/SWE_agent/agent.py

@@ -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 (
     Action,
     AgentThinkAction,
     FileReadAction,
     FileWriteAction,
 )
+from opendevin.agent import Agent
+from opendevin.llm.llm import LLM
 from opendevin.observation import Observation
+from opendevin.state import State
 
 from .parser import parse_command
-
 from .prompts import (
-    SYSTEM_MESSAGE,
-    STEP_PROMPT,
+    CONTEXT_PROMPT,
     MEMORY_FORMAT,
     NO_ACTION,
-    CONTEXT_PROMPT
+    STEP_PROMPT,
+    SYSTEM_MESSAGE,
 )
 
 

agenthub/SWE_agent/parser.py

@@ -1,17 +1,17 @@
+import re
+
 from opendevin.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
 
@@ -20,7 +20,7 @@ no_open_file_error = AgentEchoAction(
 
 
 def invalid_error(cmd, docs):
-    return f'''ERROR:
+    return f"""ERROR:
 Invalid command structure for
 ```
 {cmd}
@@ -30,7 +30,7 @@ If so, try again by running only one of the commands:
 
 Try again using this format:
 {COMMAND_USAGE[docs]}
-'''
+"""
 
 
 def get_action_from_string(command_string: str, path: str, line: int, thoughts: str = '') -> Action | None:

agenthub/SWE_agent/prompts.py

@@ -1,7 +1,7 @@
 
 DEFAULT_COMMANDS_DICT = {
     'exit': 'Executed when task is complete',
-    'read <file_name> [<start_line>] [<end_line>]': 'Shows a given file\'s contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. By default the whole file will be read.',
+    'read <file_name> [<start_line>] [<end_line>]': "Shows a given file's contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. By default the whole file will be read.",
     'write <file> <changes> [<start_line>] [<end_line>]': 'Modifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>. Default start_line = 0 and end_line = -1. Calling this with no line args will replace the whole file.',
     'browse <url>': 'Returns the text version of any url, this can be useful to look up documentation or finding issues on github',
     'scroll_up': 'Takes no arguments. This will scroll up and show you the 100 lines above your current lines',
@@ -16,7 +16,7 @@ DEFAULT_COMMANDS_DICT = {
 
 COMMAND_USAGE = {
     'exit': 'Usage:\n```\nexit\n```\nExecuted when task is complete',
-    'read': 'Args:\n<file_name> [<start_line>] [<end_line>]\nUsage:\n```\nread file.py\n```\nor\n```\nread example.py <start_line> <end_line>\n```\nShows a given file\'s contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. by default the whole file will be read.',
+    'read': "Args:\n<file_name> [<start_line>] [<end_line>]\nUsage:\n```\nread file.py\n```\nor\n```\nread example.py <start_line> <end_line>\n```\nShows a given file's contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. by default the whole file will be read.",
     'write': 'Args:\n<file> <changes> [<start_line>] [<end_line>]\nUsage:\n```\nwrite "def main():\n    print("This is line one")" 0 2\n```\nModifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>. Default start_line = 0 and end_line = -1. Calling this with no line args will replace the whole file.',
     'edit': 'Args:\n<start_line> <end_line> <changes>\nUsage:\n```\nedit 0 1 import pandas as pd\n```\nThis will modify the current file you are in with the changes you make between the line numbers you designate',
     'goto': 'Args:\n<line_num>\nUsage:\n```\ngoto <line_num>\n```\nThis will show you the 100 lines below and including the line you specify within your current file.',
@@ -52,7 +52,7 @@ To modify the current file use 'edit'. To move through the current file use 'got
 when using write and edit do not surround the code with any "" just write the code.
 """
 
-GENERAL_GUIDELINES = '''INSTRUCTIONS:
+GENERAL_GUIDELINES = """INSTRUCTIONS:
 Now, you're going to solve this issue on your own. You can use any bash commands or custom commands you wish to complete your task. Edit all the files you need to and run any checks or tests that you want.
 Remember, YOU CAN ONLY ENTER ONE COMMAND AT A TIME. You should always wait for feedback after every command.
 When you're satisfied with all of the changes you've made, you can indicate that you are done by running the exit command.
@@ -69,9 +69,9 @@ IMPORTANT TIPS:
 5. Understand your context: Always make sure to look at the currently open file and the current working directory. The currently open file might be in a different directory than the working directory.
 6. Verify your edits: When editing files, it is easy to accidentally specify a wrong line number or to write code with incorrect indentation. Always check the code after you issue an edit to make sure that it reflects what you wanted to accomplish. If it didn't, issue another command to fix it.
 7. Thoroughly test your solution: After making any changes to fix a bug, be sure to thoroughly test your solution to ensure the bug has been resolved. Re-run the bug reproduction script and verify that the issue has been addressed.
-'''
+"""
 
-RESPONSE_FORMAT = '''RESPONSE FORMAT:
+RESPONSE_FORMAT = """RESPONSE FORMAT:
 This is the format of the response you will make in order to solve the current issue.
 You will be given multiple iterations to complete this task so break it into steps and solve them one by one.
 
@@ -113,9 +113,9 @@ Action:
 [ END FORMAT ]
 
 Do not provide anything extra just your thought and action.
-'''
+"""
 
-SYSTEM_MESSAGE = f'''SYSTEM INFO:
+SYSTEM_MESSAGE = f"""SYSTEM INFO:
 You am an autonomous coding agent, here to provide solutions for coding issues.
 You have been designed to assist you with a wide range of programming tasks, from code editing and debugging to testing and deployment.
 You have access to a variety of tools and commands that you can use to help you solve problems efficiently.
@@ -123,10 +123,10 @@ You have access to a variety of tools and commands that you can use to help you
 {GENERAL_GUIDELINES}
 
 {DOCUMENTATION}
-'''.strip()
+""".strip()
 
 
-def NO_ACTION(latest): return f'''
+def NO_ACTION(latest): return f"""
 You did not include any action to take in your most recent output:
 
 ===== Output ======
@@ -141,20 +141,20 @@ This time, be sure to use the exact format below, replacing anything in <> with
 {RESPONSE_FORMAT}
 
 It is crucial you use the format provided as the output will be parsed automatically.
-'''
+"""
 
 
 def file_info(file: str, line: int):
     if file:
-        return f'''CURRENT WORKSPACE:
+        return f"""CURRENT WORKSPACE:
     Open File: {file} on line {line}
     You can use these commands with the current file:
     Navigation: `scroll_up`, `scroll_down`, and `goto <line>`
     Modification: `edit <start_line> <end_line> <changes>`
-    '''
+    """
 
 
-def STEP_PROMPT(task, file, line_num): return f'''
+def STEP_PROMPT(task, file, line_num): return f"""
 {RESPONSE_FORMAT}
 You are currently trying to complete this task:
 {task}
@@ -168,7 +168,7 @@ Be very strict about the formatting that you use and make sure you follow the gu
 NEVER output multiple commands. ONLY take ONE STEP at a time.
 When you have completed your task run the "exit" command.
 Begin with your thought about the next step and then come up with an action to perform your thought.
-'''.strip()
+""".strip()
 
 
 def unpack_dict(data: dict, restrict: list[str] = []):
@@ -185,13 +185,13 @@ def unpack_dict(data: dict, restrict: list[str] = []):
     return '\n'.join(lines)
 
 
-def MEMORY_FORMAT(act, obs): return f'''
+def MEMORY_FORMAT(act, obs): return f"""
 Previous Action:
 {unpack_dict(act, ["content"])}
 
 Output from Action:
 {unpack_dict(obs)}
-'''.strip()
+""".strip()
 
 
 def CONTEXT_PROMPT(memory, window):

agenthub/__init__.py

@@ -1,17 +1,21 @@
-from .micro.registry import all_microagents
-from .micro.agent import MicroAgent
+from dotenv import load_dotenv
+
 from opendevin.agent import Agent
 
-from dotenv import load_dotenv
+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,
+    monologue_agent,
+    planner_agent,
+)
 
 __all__ = ['monologue_agent', 'codeact_agent',
            'planner_agent', 'SWE_agent', 'delegator_agent']

agenthub/codeact_agent/__init__.py

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

agenthub/codeact_agent/codeact_agent.py

@@ -13,8 +13,8 @@ from opendevin.observation import (
     AgentMessageObservation,
     CmdOutputObservation,
 )
+from opendevin.sandbox.plugins import JupyterRequirement, PluginRequirement
 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.

agenthub/delegator_agent/__init__.py

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

agenthub/delegator_agent/agent.py

@@ -1,11 +1,10 @@
 from typing import List
 
+from opendevin.action import Action, AgentDelegateAction, AgentFinishAction
 from opendevin.agent import Agent
-from opendevin.action import AgentFinishAction, AgentDelegateAction
-from opendevin.observation import AgentDelegateObservation
 from opendevin.llm.llm import LLM
+from opendevin.observation import AgentDelegateObservation
 from opendevin.state import State
-from opendevin.action import Action
 
 
 class DelegatorAgent(Agent):

agenthub/dummy_agent/agent.py

@@ -0,0 +1,23 @@
+"""Module for a Dummy agent."""
+
+from typing import List
+
+from opendevin.action import Action
+from opendevin.action.base import NullAction
+from opendevin.agent import Agent
+from opendevin.controller.agent_controller import AgentController
+from opendevin.observation.base import NullObservation, Observation
+from opendevin.state import State
+
+
+class DummyAgent(Agent):
+    """A dummy agent that does nothing but can be used in testing."""
+
+    async def run(self, controller: AgentController) -> Observation:
+        return NullObservation('')
+
+    def step(self, state: State) -> Action:
+        return NullAction('')
+
+    def search_memory(self, query: str) -> List[str]:
+        return []

agenthub/micro/agent.py

@@ -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.action import Action, action_from_dict
 from opendevin.agent import Agent
+from opendevin.exceptions import LLMOutputError
 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
@@ -56,14 +56,9 @@ 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(

agenthub/micro/coder/agent.yaml

@@ -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: {}

agenthub/micro/instructions.py

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

agenthub/micro/manager/agent.yaml

@@ -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: {}

agenthub/micro/math_agent/agent.yaml

@@ -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"

agenthub/micro/postgres_agent/agent.yaml

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

agenthub/micro/registry.py

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

agenthub/micro/repo_explorer/agent.yaml

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

agenthub/micro/study_repo_for_task/agent.yaml

@@ -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

agenthub/micro/verifier/agent.yaml

@@ -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

agenthub/monologue_agent/__init__.py

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

agenthub/monologue_agent/agent.py

@@ -1,33 +1,36 @@
 from typing import List
-from opendevin.agent import Agent
-from opendevin.state import State
-from opendevin.llm.llm import LLM
-from opendevin.schema import ActionType, ObservationType
-from opendevin.exceptions import AgentNoInstructionError
-
-from opendevin.action import (
-    Action,
-    NullAction,
-    CmdRunAction,
-    FileWriteAction,
-    FileReadAction,
-    AgentRecallAction,
-    BrowseURLAction,
-    AgentThinkAction,
-)
-
-from opendevin.observation import (
-    Observation,
-    NullObservation,
-    CmdOutputObservation,
-    FileReadObservation,
-    AgentRecallObservation,
-    BrowserOutputObservation,
-)
 
 import agenthub.monologue_agent.utils.prompts as prompts
 from agenthub.monologue_agent.utils.monologue import Monologue
-from agenthub.monologue_agent.utils.memory import LongTermMemory
+from opendevin import config
+from opendevin.action import (
+    Action,
+    AgentRecallAction,
+    AgentThinkAction,
+    BrowseURLAction,
+    CmdRunAction,
+    FileReadAction,
+    FileWriteAction,
+    GitHubPushAction,
+    NullAction,
+)
+from opendevin.agent import Agent
+from opendevin.exceptions import AgentNoInstructionError
+from opendevin.llm.llm import LLM
+from opendevin.observation import (
+    AgentRecallObservation,
+    BrowserOutputObservation,
+    CmdOutputObservation,
+    FileReadObservation,
+    NullObservation,
+    Observation,
+)
+from opendevin.schema import ActionType
+from opendevin.schema.config import ConfigType
+from opendevin.state import State
+
+if config.get(ConfigType.AGENT_MEMORY_ENABLED):
+    from agenthub.monologue_agent.utils.memory import LongTermMemory
 
 MAX_MONOLOGUE_LENGTH = 20000
 MAX_OUTPUT_LENGTH = 5000
@@ -68,13 +71,17 @@ INITIAL_THOUGHTS = [
     'BROWSE google.com',
     '<form><input type="text"></input><button type="submit"></button></form>',
     'I can browse the web too!',
+    'If I have done some work and I want to push it to github, I can do that also!',
+    "Let's do it.",
+    'PUSH owner/repo branch',
+    'The repo was successfully pushed to https://github.com/owner/repo/branch',
     'And once I have completed my task, I can use the finish action to stop working.',
     "But I should only use the finish action when I'm absolutely certain that I've completed my task and have tested my work.",
     'Very cool. Now to accomplish my task.',
     "I'll need a strategy. And as I make progress, I'll need to keep refining that strategy. I'll need to set goals, and break them into sub-goals.",
     'In between actions, I must always take some time to think, strategize, and set new goals. I should never take two actions in a row.',
     "OK so my task is to $TASK. I haven't made any progress yet. Where should I start?",
-    "It seems like there might be an existing project here. I should probably start by running `ls` to see what's here.",
+    'It seems like there might be an existing project here. I should probably start by running `pwd` and `ls` to orient myself.',
 ]
 
 
@@ -86,6 +93,8 @@ class MonologueAgent(Agent):
     """
 
     _initialized = False
+    monologue: Monologue
+    memory: 'LongTermMemory | None'
 
     def __init__(self, llm: LLM):
         """
@@ -95,8 +104,6 @@ class MonologueAgent(Agent):
         - llm (LLM): The llm to be used by this agent
         """
         super().__init__(llm)
-        self.monologue = Monologue()
-        self.memory = LongTermMemory()
 
     def _add_event(self, event: dict):
         """
@@ -119,7 +126,8 @@ class MonologueAgent(Agent):
             )
 
         self.monologue.add_event(event)
-        self.memory.add_event(event)
+        if self.memory is not None:
+            self.memory.add_event(event)
         if self.monologue.get_total_length() > MAX_MONOLOGUE_LENGTH:
             self.monologue.condense(self.llm)
 
@@ -141,35 +149,39 @@ class MonologueAgent(Agent):
 
         if task is None or task == '':
             raise AgentNoInstructionError()
-        self.monologue = Monologue()
-        self.memory = LongTermMemory()
 
-        output_type = ''
+        self.monologue = Monologue()
+        if config.get(ConfigType.AGENT_MEMORY_ENABLED):
+            self.memory = LongTermMemory()
+        else:
+            self.memory = None
+
+        previous_action = ''
         for thought in INITIAL_THOUGHTS:
             thought = thought.replace('$TASK', task)
-            if output_type != '':
+            if previous_action != '':
                 observation: Observation = NullObservation(content='')
-                if output_type == ObservationType.RUN:
+                if previous_action in {ActionType.RUN, ActionType.PUSH}:
                     observation = CmdOutputObservation(
                         content=thought, command_id=0, command=''
                     )
-                elif output_type == ObservationType.READ:
+                elif previous_action == ActionType.READ:
                     observation = FileReadObservation(content=thought, path='')
-                elif output_type == ObservationType.RECALL:
+                elif previous_action == ActionType.RECALL:
                     observation = AgentRecallObservation(
                         content=thought, memories=[])
-                elif output_type == ObservationType.BROWSE:
+                elif previous_action == ActionType.BROWSE:
                     observation = BrowserOutputObservation(
                         content=thought, url='', screenshot=''
                     )
                 self._add_event(observation.to_memory())
-                output_type = ''
+                previous_action = ''
             else:
                 action: Action = NullAction()
                 if thought.startswith('RUN'):
                     command = thought.split('RUN ')[1]
                     action = CmdRunAction(command)
-                    output_type = ActionType.RUN
+                    previous_action = ActionType.RUN
                 elif thought.startswith('WRITE'):
                     parts = thought.split('WRITE ')[1].split(' > ')
                     path = parts[1]
@@ -178,15 +190,20 @@ class MonologueAgent(Agent):
                 elif thought.startswith('READ'):
                     path = thought.split('READ ')[1]
                     action = FileReadAction(path=path)
-                    output_type = ActionType.READ
+                    previous_action = ActionType.READ
                 elif thought.startswith('RECALL'):
                     query = thought.split('RECALL ')[1]
                     action = AgentRecallAction(query=query)
-                    output_type = ActionType.RECALL
+                    previous_action = ActionType.RECALL
                 elif thought.startswith('BROWSE'):
                     url = thought.split('BROWSE ')[1]
                     action = BrowseURLAction(url=url)
-                    output_type = ActionType.BROWSE
+                    previous_action = ActionType.BROWSE
+                elif thought.startswith('PUSH'):
+                    owner_repo, branch = thought.split('PUSH ')[1].split(' ')
+                    owner, repo = owner_repo.split('/')
+                    action = GitHubPushAction(owner=owner, repo=repo, branch=branch)
+                    previous_action = ActionType.PUSH
                 else:
                     action = AgentThinkAction(thought=thought)
                 self._add_event(action.to_memory())
@@ -233,8 +250,14 @@ class MonologueAgent(Agent):
         Returns:
         - List[str]: A list of top 10 text results that matched the query
         """
+        if self.memory is None:
+            return []
         return self.memory.search(query)
 
     def reset(self) -> None:
         super().reset()
         self.monologue = Monologue()
+        if config.get(ConfigType.AGENT_MEMORY_ENABLED):
+            self.memory = LongTermMemory()
+        else:
+            self.memory = None

agenthub/monologue_agent/utils/json.py

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

agenthub/monologue_agent/utils/memory.py

@@ -1,21 +1,27 @@
-import llama_index.embeddings.openai.base as llama_openai
-from threading import Thread
+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 import config
 from opendevin.logger import opendevin_logger as logger
+from opendevin.schema.config import ConfigType
+
 from . import json
 
-num_retries = config.get('LLM_NUM_RETRIES')
-retry_min_wait = config.get('LLM_RETRY_MIN_WAIT')
-retry_max_wait = config.get('LLM_RETRY_MAX_WAIT')
+num_retries = config.get(ConfigType.LLM_NUM_RETRIES)
+retry_min_wait = config.get(ConfigType.LLM_RETRY_MIN_WAIT)
+retry_max_wait = config.get(ConfigType.LLM_RETRY_MAX_WAIT)
 
 # llama-index includes a retry decorator around openai.get_embeddings() function
 # it is initialized with hard-coded values and errors
@@ -46,32 +52,33 @@ def wrapper_get_embeddings(*args, **kwargs):
 
 llama_openai.get_embeddings = wrapper_get_embeddings
 
-embedding_strategy = config.get('LLM_EMBEDDING_MODEL')
+embedding_strategy = config.get(ConfigType.LLM_EMBEDDING_MODEL)
 
 # TODO: More embeddings: https://docs.llamaindex.ai/en/stable/examples/embeddings/OpenAI/
 # There's probably a more programmatic way to do this.
-if embedding_strategy == 'llama2':
+supported_ollama_embed_models = ['llama2', 'mxbai-embed-large', 'nomic-embed-text', 'all-minilm', 'stable-code']
+if embedding_strategy in supported_ollama_embed_models:
     from llama_index.embeddings.ollama import OllamaEmbedding
     embed_model = OllamaEmbedding(
-        model_name='llama2',
-        base_url=config.get('LLM_BASE_URL', required=True),
+        model_name=embedding_strategy,
+        base_url=config.get(ConfigType.LLM_EMBEDDING_BASE_URL, required=True),
         ollama_additional_kwargs={'mirostat': 0},
     )
 elif embedding_strategy == 'openai':
     from llama_index.embeddings.openai import OpenAIEmbedding
     embed_model = OpenAIEmbedding(
         model='text-embedding-ada-002',
-        api_key=config.get('LLM_API_KEY', required=True)
+        api_key=config.get(ConfigType.LLM_API_KEY, required=True)
     )
 elif embedding_strategy == 'azureopenai':
     # Need to instruct to set these env variables in documentation
     from llama_index.embeddings.azure_openai import AzureOpenAIEmbedding
     embed_model = AzureOpenAIEmbedding(
         model='text-embedding-ada-002',
-        deployment_name=config.get('LLM_EMBEDDING_DEPLOYMENT_NAME', required=True),
-        api_key=config.get('LLM_API_KEY', required=True),
-        azure_endpoint=config.get('LLM_BASE_URL', required=True),
-        api_version=config.get('LLM_API_VERSION', required=True),
+        deployment_name=config.get(ConfigType.LLM_EMBEDDING_DEPLOYMENT_NAME, required=True),
+        api_key=config.get(ConfigType.LLM_API_KEY, required=True),
+        azure_endpoint=config.get(ConfigType.LLM_BASE_URL, required=True),
+        api_version=config.get(ConfigType.LLM_API_VERSION, required=True),
     )
 elif (embedding_strategy is not None) and (embedding_strategy.lower() == 'none'):
     # TODO: this works but is not elegant enough. The incentive is when
@@ -85,6 +92,9 @@ else:
     )
 
 
+sema = threading.Semaphore(value=config.get(ConfigType.AGENT_MEMORY_MAX_THREADS))
+
+
 class LongTermMemory:
     """
     Responsible for storing information that the agent can call on later for better insights and context.
@@ -101,6 +111,7 @@ class LongTermMemory:
         self.index = VectorStoreIndex.from_vector_store(
             vector_store, embed_model=embed_model)
         self.thought_idx = 0
+        self._add_threads = []
 
     def add_event(self, event: dict):
         """
@@ -128,11 +139,13 @@ class LongTermMemory:
         )
         self.thought_idx += 1
         logger.debug('Adding %s event to memory: %d', t, self.thought_idx)
-        thread = Thread(target=self._add_doc, args=(doc,))
+        thread = threading.Thread(target=self._add_doc, args=(doc,))
+        self._add_threads.append(thread)
         thread.start()  # We add the doc concurrently so we don't have to wait ~500ms for the insert
 
     def _add_doc(self, doc):
-        self.index.insert(doc)
+        with sema:
+            self.index.insert(doc)
 
     def search(self, query: str, k: int = 10):
         """

agenthub/monologue_agent/utils/monologue.py

@@ -1,8 +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.exceptions import AgentEventTypeError
+from opendevin.llm.llm import LLM
 from opendevin.logger import opendevin_logger as logger
 
 

agenthub/monologue_agent/utils/prompts.py

@@ -1,19 +1,19 @@
+import re
+from json import JSONDecodeError
 from typing import List
 
-from . import json
-from json import JSONDecodeError
-
-import re
-
+from opendevin import config
 from opendevin.action import (
-    action_from_dict,
     Action,
+    action_from_dict,
 )
+from opendevin.exceptions import LLMOutputError
 from opendevin.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:
@@ -27,8 +27,8 @@ This is your internal monologue, in JSON format:
 
 
 Your most recent thought is at the bottom of that monologue. Continue your train of thought.
-What is your next thought or action? Your response must be in JSON format.
-It must be an object, and it must contain two fields:
+What is your next single thought or action? Your response must be in JSON format.
+It must be a single object, and it must contain two fields:
 * `action`, which is one of the actions below
 * `args`, which is a map of key-value pairs, specifying the arguments for that action
 
@@ -45,6 +45,10 @@ Here are the possible actions:
   * `id` - the ID of the background command to kill
 * `browse` - opens a web page. Arguments:
   * `url` - the URL to open
+* `push` - Push a branch from the current repo to github:
+  * `owner` - the owner of the repo to push to
+  * `repo` - the name of the repo to push to
+  * `branch` - the name of the branch to push
 * `recall` - recalls a past memory. Arguments:
   * `query` - the query to search for
 * `think` - make a plan, set a goal, or record your thoughts. Arguments:
@@ -53,16 +57,20 @@ Here are the possible actions:
 
 %(background_commands)s
 
-You MUST take time to think in between read, write, run, browse, and recall actions.
+You MUST take time to think in between read, write, run, browse, push, and recall actions.
 You should never act twice in a row without thinking. But if your last several
 actions are all "think" actions, you should consider taking a different action.
 
 Notes:
-* your environment is Debian Linux. You can install software with `apt`
-* your working directory will not change, even if you run `cd`. All commands will be run in the `%(WORKSPACE_MOUNT_PATH_IN_SANDBOX)s` directory.
+* you are logged in as %(user)s, but sudo will always work without a password.
+* all non-background commands will be forcibly stopped if they remain running for over %(timeout)s seconds.
+* your environment is Debian Linux. You can install software with `sudo apt-get`, but remember to use -y.
 * don't run interactive commands, or commands that don't return (e.g. `node server.js`). You may run commands in the background (e.g. `node server.js &`)
+* don't run interactive text editors (e.g. `nano` or 'vim'), instead use the 'write' or 'read' action.
+* don't run gui applications (e.g. software IDEs (like vs code or codium), web browsers (like firefox or chromium), or other complex software packages). Use non-interactive cli applications, or special actions instead.
+* whenever an action fails, always `think` about why it may have happened before acting again.
 
-What is your next thought or action? Again, you must reply with JSON, and only with JSON.
+What is your next single thought or action? Again, you must reply with JSON, and only with JSON. You must respond with exactly one 'action' object.
 
 %(hint)s
 """
@@ -141,12 +149,16 @@ def get_request_action_prompt(
             )
         bg_commands_message += '\nYou can end any process by sending a `kill` action with the numerical `id` above.'
 
+    user = 'opendevin' if config.get(ConfigType.RUN_AS_DEVIN) else 'root'
+
     return ACTION_PROMPT % {
         'task': task,
         'monologue': json.dumps(thoughts, indent=2),
         'background_commands': bg_commands_message,
         'hint': hint,
-        'WORKSPACE_MOUNT_PATH_IN_SANDBOX': config.get('WORKSPACE_MOUNT_PATH_IN_SANDBOX'),
+        'user': user,
+        'timeout': config.get(ConfigType.SANDBOX_TIMEOUT),
+        'WORKSPACE_MOUNT_PATH_IN_SANDBOX': config.get(ConfigType.WORKSPACE_MOUNT_PATH_IN_SANDBOX),
     }
 
 
@@ -176,7 +188,7 @@ def parse_action_response(response: str) -> Action:
             raise LLMOutputError(
                 'Invalid JSON, the response must be well-formed JSON as specified in the prompt.'
             )
-    except ValueError:
+    except (ValueError, TypeError):
         raise LLMOutputError(
             'Invalid JSON, the response must be well-formed JSON as specified in the prompt.'
         )

agenthub/planner_agent/__init__.py

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

agenthub/planner_agent/agent.py

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

agenthub/planner_agent/prompt.py

@@ -1,29 +1,29 @@
 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,
+    Action,
+    AddTaskAction,
+    AgentFinishAction,
+    AgentRecallAction,
+    AgentSummarizeAction,
+    AgentThinkAction,
     BrowseURLAction,
+    CmdKillAction,
+    CmdRunAction,
     FileReadAction,
     FileWriteAction,
-    AgentRecallAction,
-    AgentThinkAction,
-    AgentFinishAction,
-    AgentSummarizeAction,
-    AddTaskAction,
     ModifyTaskAction,
+    NullAction,
+    action_from_dict,
 )
-
+from opendevin.logger import opendevin_logger as logger
 from opendevin.observation import (
     NullObservation,
+    Observation,
 )
+from opendevin.plan import Plan
+from opendevin.schema import ActionType
 
 ACTION_TYPE_TO_CLASS: Dict[str, Type[Action]] = {
     ActionType.RUN: CmdRunAction,
@@ -134,12 +134,12 @@ def get_hint(latest_action_id: str) -> str:
     """ Returns action type hint based on given action_id """
 
     hints = {
-        '': 'You haven\'t taken any actions yet. Start by using `ls` to check out what files you\'re working with.',
+        '': "You haven't taken any actions yet. Start by using `ls` to check out what files you're working with.",
         ActionType.RUN: 'You should think about the command you just ran, what output it gave, and how that affects your plan.',
         ActionType.READ: 'You should think about the file you just read, what you learned from it, and how that affects your plan.',
         ActionType.WRITE: 'You just changed a file. You should think about how it affects your plan.',
         ActionType.BROWSE: 'You should think about the page you just visited, and what you learned from it.',
-        ActionType.THINK: 'Look at your last thought in the history above. What does it suggest? Don\'t think anymore--take action.',
+        ActionType.THINK: "Look at your last thought in the history above. What does it suggest? Don't think anymore--take action.",
         ActionType.RECALL: 'You should think about the information you just recalled, and how it should affect your plan.',
         ActionType.ADD_TASK: 'You should think about the next action to take.',
         ActionType.MODIFY_TASK: 'You should think about the next action to take.',

containers/app/Dockerfile

@@ -33,7 +33,7 @@ FROM python:3.12-slim as runtime
 WORKDIR /app
 
 ENV RUN_AS_DEVIN=false
-ENV USE_HOST_NETWORK=true
+ENV USE_HOST_NETWORK=false
 ENV SSH_HOSTNAME=host.docker.internal
 ENV WORKSPACE_BASE=/opt/workspace_base
 ENV OPEN_DEVIN_BUILD_VERSION=$OPEN_DEVIN_BUILD_VERSION

containers/build.sh

@@ -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 \

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

@@ -3,29 +3,20 @@ 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/PyCQA/flake8
-    rev: 7.0.0
+  - repo: https://github.com/tox-dev/pyproject-fmt
+    rev: 1.7.0
     hooks:
-      - id: flake8
-        args: ['--select=Q000']  # Q000 is the error code for single quote enforcement
-        additional_dependencies:
-          - flake8-quotes
-
-  - repo: https://github.com/hhatto/autopep8
-    rev: v2.1.0
+      - id: pyproject-fmt
+  - repo: https://github.com/abravalheri/validate-pyproject
+    rev: v0.16
     hooks:
-      - id: autopep8
-
-  - repo: https://github.com/asottile/setup-cfg-fmt
-    rev: v2.5.0
-    hooks:
-      - id: setup-cfg-fmt
-        always_run: true
-        pass_filenames: false
+      - id: validate-pyproject
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
@@ -34,18 +25,24 @@ repos:
       # Run the linter.
       - id: ruff
         entry: ruff check --config dev_config/python/ruff.toml opendevin/ agenthub/
-        types_or: [ python, pyi, jupyter ]
-        args: [ --fix ]
+        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 ]
+        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
+
+  - repo: https://github.com/NiklasRosenstein/pydoc-markdown
+    rev: develop
+    hooks:
+      - id: pydoc-markdown

dev_config/python/ruff.toml

@@ -1,3 +1,21 @@
 exclude = [
     "agenthub/monologue_agent/regression/",
-]
+]
+
+[lint]
+select = [
+    "E",
+    "W",
+    "F",
+    "I",
+    "Q",
+]
+
+ignore = [
+    "E501",
+]
+
+flake8-quotes = {inline-quotes = "single"}
+
+[format]
+quote-style = "single"

docs/.gitignore

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

docs/Agents.md

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

docs/README-zh.md

@@ -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

docs/README.md

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

docs/architecture/Architecture.md

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

docs/architecture/README.md

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

docs/babel.config.js

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

docs/docusaurus.config.ts

@@ -0,0 +1,128 @@
+import type * as Preset from "@docusaurus/preset-classic";
+import type { Config } from "@docusaurus/types";
+import { themes as prismThemes } from "prism-react-renderer";
+
+const config: Config = {
+  title: "OpenDevin",
+  tagline: "Code Less, Make More",
+  favicon: "img/logo.png",
+
+  // Set the production url of your site here
+  url: "https://OpenDevin.github.io",
+  baseUrl: "/OpenDevin/",
+
+  // GitHub pages deployment config.
+  organizationName: "OpenDevin",
+  projectName: "OpenDevin",
+  trailingSlash: false,
+
+  onBrokenLinks: "throw",
+  onBrokenMarkdownLinks: "warn",
+
+  // Even if you don't use internationalization, you can use this field to set
+  // useful metadata like html lang. For example, if your site is Chinese, you
+  // may want to replace "en" with "zh-Hans".
+  i18n: {
+    defaultLocale: "en",
+    locales: ["en"],
+  },
+
+  presets: [
+    [
+      "classic",
+      {
+        docs: {
+          path: "modules",
+          routeBasePath: "modules",
+          sidebarPath: "./sidebars.ts",
+          exclude: [
+            // '**/_*.{js,jsx,ts,tsx,md,mdx}',
+            // '**/_*/**',
+            "**/*.test.{js,jsx,ts,tsx}",
+            "**/__tests__/**",
+          ],
+        },
+        blog: {
+          showReadingTime: true,
+        },
+        theme: {
+          customCss: "./src/css/custom.css",
+        },
+      } satisfies Preset.Options,
+    ],
+  ],
+
+  themeConfig: {
+    image: "img/docusaurus.png",
+    navbar: {
+      title: "OpenDevin",
+      logo: {
+        alt: "OpenDevin",
+        src: "img/logo.png",
+      },
+      items: [
+        {
+          type: "docSidebar",
+          sidebarId: "docsSidebar",
+          position: "left",
+          label: "Docs",
+        },
+        {
+          type: "docSidebar",
+          sidebarId: "apiSidebar",
+          position: "left",
+          label: "Codebase",
+        },
+        { to: "/faq", label: "FAQ", position: "left" },
+        {
+          href: "https://github.com/OpenDevin/OpenDevin",
+          label: "GitHub",
+          position: "right",
+        },
+      ],
+    },
+    footer: {
+      style: "dark",
+      links: [
+        {
+          title: "OpenDevin",
+          items: [
+            {
+              label: "Docs",
+              to: "/modules/usage/intro",
+            },
+          ],
+        },
+        {
+          title: "Community",
+          items: [
+            {
+              label: "Slack",
+              href: "https://join.slack.com/t/opendevin/shared_invite/zt-2etftj1dd-X1fDL2PYIVpsmJZkqEYANw",
+            },
+            {
+              label: "Discord",
+              href: "https://discord.gg/mBuDGRzzES",
+            },
+          ],
+        },
+        {
+          title: "More",
+          items: [
+            {
+              label: "GitHub",
+              href: "https://github.com/OpenDevin/OpenDevin",
+            },
+          ],
+        },
+      ],
+      copyright: `Copyright © ${new Date().getFullYear()} OpenDevin`,
+    },
+    prism: {
+      theme: prismThemes.oneLight,
+      darkTheme: prismThemes.oneDark,
+    },
+  } satisfies Preset.ThemeConfig,
+};
+
+export default config;

docs/modules/python/agenthub/SWE_agent/agent.md

@@ -0,0 +1,34 @@
+---
+sidebar_label: agent
+title: agenthub.SWE_agent.agent
+---
+
+## SWEAgent Objects
+
+```python
+class SWEAgent(Agent)
+```
+
+An attempt to recreate swe_agent with output parsing, prompting style, and Application Computer Interface (ACI).
+
+SWE-agent includes ACI functions like 'goto', 'search_for', 'edit', 'scroll', 'run'
+
+#### step
+
+```python
+def step(state: State) -> Action
+```
+
+SWE-Agent step:
+    1. Get context - past actions, custom commands, current step
+    2. Perform think-act - prompt model for action and reasoning
+    3. Catch errors - ensure model takes action (5 attempts max)
+
+#### reset
+
+```python
+def reset() -> None
+```
+
+Used to reset the agent
+

docs/modules/python/agenthub/SWE_agent/parser.md

@@ -0,0 +1,34 @@
+---
+sidebar_label: parser
+title: agenthub.SWE_agent.parser
+---
+
+#### get\_action\_from\_string
+
+```python
+def get_action_from_string(command_string: str,
+                           path: str,
+                           line: int,
+                           thoughts: str = '') -> Action | None
+```
+
+Parses the command string to find which command the agent wants to run
+Converts the command into a proper Action and returns
+
+#### parse\_command
+
+```python
+def parse_command(input_str: str, path: str, line: int)
+```
+
+Parses a given string and separates the command (enclosed in triple backticks) from any accompanying text.
+
+**Arguments**:
+
+- `input_str` _str_ - The input string to be parsed.
+  
+
+**Returns**:
+
+- `tuple` - A tuple containing the command and the accompanying text (if any).
+

docs/modules/python/agenthub/codeact_agent/codeact_agent.md

@@ -0,0 +1,50 @@
+---
+sidebar_label: codeact_agent
+title: agenthub.codeact_agent.codeact_agent
+---
+
+## CodeActAgent Objects
+
+```python
+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.
+
+#### \_\_init\_\_
+
+```python
+def __init__(llm: LLM) -> None
+```
+
+Initializes a new instance of the CodeActAgent class.
+
+**Arguments**:
+
+  - llm (LLM): The llm to be used by this agent
+
+#### step
+
+```python
+def step(state: State) -> Action
+```
+
+Performs one step using the Code Act Agent.
+This includes gathering info on previous steps and prompting the model to make a command to execute.
+
+**Arguments**:
+
+  - 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
+

docs/modules/python/agenthub/delegator_agent/agent.md

@@ -0,0 +1,45 @@
+---
+sidebar_label: agent
+title: agenthub.delegator_agent.agent
+---
+
+## DelegatorAgent Objects
+
+```python
+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.
+
+#### \_\_init\_\_
+
+```python
+def __init__(llm: LLM)
+```
+
+Initialize the Delegator Agent with an LLM
+
+**Arguments**:
+
+  - llm (LLM): The llm to be used by this agent
+
+#### step
+
+```python
+def step(state: State) -> Action
+```
+
+Checks to see if current step is completed, returns AgentFinishAction if True.
+Otherwise, creates a plan prompt and sends to model for inference, returning the result as the next action.
+
+**Arguments**:
+
+  - state (State): The current state given the previous actions and observations
+  
+
+**Returns**:
+
+  - AgentFinishAction: If the last state was 'completed', 'verified', or 'abandoned'
+  - Action: The next action to take based on llm response
+

docs/modules/python/agenthub/dummy_agent/agent.md

@@ -0,0 +1,15 @@
+---
+sidebar_label: agent
+title: agenthub.dummy_agent.agent
+---
+
+Module for a Dummy agent.
+
+## DummyAgent Objects
+
+```python
+class DummyAgent(Agent)
+```
+
+A dummy agent that does nothing but can be used in testing.
+

docs/modules/python/agenthub/micro/agent.md

@@ -0,0 +1,30 @@
+---
+sidebar_label: agent
+title: agenthub.micro.agent
+---
+
+#### my\_encoder
+
+```python
+def my_encoder(obj)
+```
+
+Encodes objects as dictionaries
+
+**Arguments**:
+
+  - obj (Object): An object that will be converted
+  
+
+**Returns**:
+
+  - dict: If the object can be converted it is returned in dict format
+
+#### to\_json
+
+```python
+def to_json(obj, **kwargs)
+```
+
+Serialize an object to str format
+

docs/modules/python/agenthub/monologue_agent/agent.md

@@ -0,0 +1,62 @@
+---
+sidebar_label: agent
+title: agenthub.monologue_agent.agent
+---
+
+## MonologueAgent Objects
+
+```python
+class MonologueAgent(Agent)
+```
+
+The Monologue Agent utilizes long and short term memory to complete tasks.
+Long term memory is stored as a LongTermMemory object and the model uses it to search for examples from the past.
+Short term memory is stored as a Monologue object and the model can condense it as necessary.
+
+#### \_\_init\_\_
+
+```python
+def __init__(llm: LLM)
+```
+
+Initializes the Monologue Agent with an llm, monologue, and memory.
+
+**Arguments**:
+
+  - llm (LLM): The llm to be used by this agent
+
+#### step
+
+```python
+def step(state: State) -> Action
+```
+
+Modifies the current state by adding the most recent actions and observations, then prompts the model to think about it's next action to take using monologue, memory, and hint.
+
+**Arguments**:
+
+  - state (State): The current state based on previous steps taken
+  
+
+**Returns**:
+
+  - Action: The next action to take based on LLM response
+
+#### search\_memory
+
+```python
+def search_memory(query: str) -> List[str]
+```
+
+Uses VectorIndexRetriever to find related memories within the long term memory.
+Uses search to produce top 10 results.
+
+**Arguments**:
+
+  - query (str): The query that we want to find related memories for
+  
+
+**Returns**:
+
+  - List[str]: A list of top 10 text results that matched the query
+

docs/modules/python/agenthub/monologue_agent/utils/json.md

@@ -0,0 +1,38 @@
+---
+sidebar_label: json
+title: agenthub.monologue_agent.utils.json
+---
+
+#### my\_encoder
+
+```python
+def my_encoder(obj)
+```
+
+Encodes objects as dictionaries
+
+**Arguments**:
+
+  - obj (Object): An object that will be converted
+  
+
+**Returns**:
+
+  - dict: If the object can be converted it is returned in dict format
+
+#### dumps
+
+```python
+def dumps(obj, **kwargs)
+```
+
+Serialize an object to str format
+
+#### loads
+
+```python
+def loads(s, **kwargs)
+```
+
+Create a JSON object from str
+

docs/modules/python/agenthub/monologue_agent/utils/memory.md

@@ -0,0 +1,52 @@
+---
+sidebar_label: memory
+title: agenthub.monologue_agent.utils.memory
+---
+
+## LongTermMemory Objects
+
+```python
+class LongTermMemory()
+```
+
+Responsible for storing information that the agent can call on later for better insights and context.
+Uses chromadb to store and search through memories.
+
+#### \_\_init\_\_
+
+```python
+def __init__()
+```
+
+Initialize the chromadb and set up ChromaVectorStore for later use.
+
+#### add\_event
+
+```python
+def add_event(event: dict)
+```
+
+Adds a new event to the long term memory with a unique id.
+
+**Arguments**:
+
+  - event (dict): The new event to be added to memory
+
+#### search
+
+```python
+def search(query: str, k: int = 10)
+```
+
+Searches through the current memory using VectorIndexRetriever
+
+**Arguments**:
+
+  - query (str): A query to match search results to
+  - k (int): Number of top results to return
+  
+
+**Returns**:
+
+  - List[str]: List of top k results found in current memory
+

docs/modules/python/agenthub/monologue_agent/utils/monologue.md

@@ -0,0 +1,80 @@
+---
+sidebar_label: monologue
+title: agenthub.monologue_agent.utils.monologue
+---
+
+## Monologue Objects
+
+```python
+class Monologue()
+```
+
+The monologue is a representation for the agent's internal monologue where it can think.
+The agent has the capability of using this monologue for whatever it wants.
+
+#### \_\_init\_\_
+
+```python
+def __init__()
+```
+
+Initialize the empty list of thoughts
+
+#### add\_event
+
+```python
+def add_event(t: dict)
+```
+
+Adds an event to memory if it is a valid event.
+
+**Arguments**:
+
+  - t (dict): The thought that we want to add to memory
+  
+
+**Raises**:
+
+  - AgentEventTypeError: If t is not a dict
+
+#### get\_thoughts
+
+```python
+def get_thoughts()
+```
+
+Get the current thoughts of the agent.
+
+**Returns**:
+
+  - List: The list of thoughts that the agent has.
+
+#### get\_total\_length
+
+```python
+def get_total_length()
+```
+
+Gives the total number of characters in all thoughts
+
+**Returns**:
+
+  - Int: Total number of chars in thoughts.
+
+#### condense
+
+```python
+def condense(llm: LLM)
+```
+
+Attempts to condense the monologue by using the llm
+
+**Arguments**:
+
+  - llm (LLM): llm to be used for summarization
+  
+
+**Raises**:
+
+  - Exception: the same exception as it got from the llm or processing the response
+

docs/modules/python/agenthub/monologue_agent/utils/prompts.md

@@ -0,0 +1,73 @@
+---
+sidebar_label: prompts
+title: agenthub.monologue_agent.utils.prompts
+---
+
+#### get\_summarize\_monologue\_prompt
+
+```python
+def get_summarize_monologue_prompt(thoughts: List[dict])
+```
+
+Gets the prompt for summarizing the monologue
+
+**Returns**:
+
+  - str: A formatted string with the current monologue within the prompt
+
+#### get\_request\_action\_prompt
+
+```python
+def get_request_action_prompt(
+        task: str,
+        thoughts: List[dict],
+        background_commands_obs: List[CmdOutputObservation] = [])
+```
+
+Gets the action prompt formatted with appropriate values.
+
+**Arguments**:
+
+  - task (str): The current task the agent is trying to accomplish
+  - thoughts (List[dict]): The agent's current thoughts
+  - background_commands_obs (List[CmdOutputObservation]): List of all observed background commands running
+  
+
+**Returns**:
+
+  - str: Formatted prompt string with hint, task, monologue, and background included
+
+#### parse\_action\_response
+
+```python
+def parse_action_response(response: str) -> Action
+```
+
+Parses a string to find an action within it
+
+**Arguments**:
+
+  - response (str): The string to be parsed
+  
+
+**Returns**:
+
+  - Action: The action that was found in the response string
+
+#### parse\_summary\_response
+
+```python
+def parse_summary_response(response: str) -> List[dict]
+```
+
+Parses a summary of the monologue
+
+**Arguments**:
+
+  - response (str): The response string to be parsed
+  
+
+**Returns**:
+
+  - List[dict]: The list of summaries output by the model
+

docs/modules/python/agenthub/planner_agent/agent.md

@@ -0,0 +1,45 @@
+---
+sidebar_label: agent
+title: agenthub.planner_agent.agent
+---
+
+## PlannerAgent Objects
+
+```python
+class PlannerAgent(Agent)
+```
+
+The planner agent utilizes a special prompting strategy to create long term plans for solving problems.
+The agent is given its previous action-observation pairs, current task, and hint based on last action taken at every step.
+
+#### \_\_init\_\_
+
+```python
+def __init__(llm: LLM)
+```
+
+Initialize the Planner Agent with an LLM
+
+**Arguments**:
+
+  - llm (LLM): The llm to be used by this agent
+
+#### step
+
+```python
+def step(state: State) -> Action
+```
+
+Checks to see if current step is completed, returns AgentFinishAction if True.
+Otherwise, creates a plan prompt and sends to model for inference, returning the result as the next action.
+
+**Arguments**:
+
+  - state (State): The current state given the previous actions and observations
+  
+
+**Returns**:
+
+  - AgentFinishAction: If the last state was 'completed', 'verified', or 'abandoned'
+  - Action: The next action to take based on llm response
+

docs/modules/python/agenthub/planner_agent/prompt.md

@@ -0,0 +1,49 @@
+---
+sidebar_label: prompt
+title: agenthub.planner_agent.prompt
+---
+
+#### get\_hint
+
+```python
+def get_hint(latest_action_id: str) -> str
+```
+
+Returns action type hint based on given action_id
+
+#### get\_prompt
+
+```python
+def get_prompt(plan: Plan, history: List[Tuple[Action, Observation]]) -> str
+```
+
+Gets the prompt for the planner agent.
+Formatted with the most recent action-observation pairs, current task, and hint based on last action
+
+**Arguments**:
+
+  - plan (Plan): The original plan outlined by the user with LLM defined tasks
+  - history (List[Tuple[Action, Observation]]): List of corresponding action-observation pairs
+  
+
+**Returns**:
+
+  - str: The formatted string prompt with historical values
+
+#### parse\_response
+
+```python
+def parse_response(response: str) -> Action
+```
+
+Parses the model output to find a valid action to take
+
+**Arguments**:
+
+  - response (str): A response from the model that potentially contains an Action.
+  
+
+**Returns**:
+
+  - Action: A valid next action to perform from model output
+

docs/modules/python/opendevin/action/__init__.md

@@ -0,0 +1,9 @@
+---
+sidebar_label: action
+title: opendevin.action
+---
+
+#### ACTION\_TYPE\_TO\_CLASS
+
+type: ignore[attr-defined]
+

docs/modules/python/opendevin/action/base.md

@@ -0,0 +1,14 @@
+---
+sidebar_label: base
+title: opendevin.action.base
+---
+
+## NullAction Objects
+
+```python
+@dataclass
+class NullAction(NotExecutableAction)
+```
+
+An action that does nothing.
+

docs/modules/python/opendevin/action/fileop.md

@@ -0,0 +1,16 @@
+---
+sidebar_label: fileop
+title: opendevin.action.fileop
+---
+
+## FileReadAction Objects
+
+```python
+@dataclass
+class FileReadAction(ExecutableAction)
+```
+
+Reads a file from a given path.
+Can be set to read specific lines using start and end
+Default lines 0:-1 (whole file)
+

docs/modules/python/opendevin/action/github.md

@@ -0,0 +1,46 @@
+---
+sidebar_label: github
+title: opendevin.action.github
+---
+
+## GitHubPushAction Objects
+
+```python
+@dataclass
+class GitHubPushAction(ExecutableAction)
+```
+
+This pushes the current branch to github.
+
+To use this, you need to set the GITHUB_TOKEN environment variable.
+The agent will return a message with a URL that you can click to make a pull
+request.
+
+**Attributes**:
+
+- `owner` - The owner of the source repo
+- `repo` - The name of the source repo
+- `branch` - The branch to push
+- `action` - The action identifier
+
+## GitHubSendPRAction Objects
+
+```python
+@dataclass
+class GitHubSendPRAction(ExecutableAction)
+```
+
+An action to send a github PR.
+
+To use this, you need to set the GITHUB_TOKEN environment variable.
+
+**Attributes**:
+
+- `owner` - The owner of the source repo
+- `repo` - The name of the source repo
+- `title` - The title of the PR
+- `head` - The branch to send the PR from
+- `head_repo` - The repo to send the PR from
+- `base` - The branch to send the PR to
+- `body` - The body of the PR
+

docs/modules/python/opendevin/action/tasks.md

@@ -0,0 +1,14 @@
+---
+sidebar_label: tasks
+title: opendevin.action.tasks
+---
+
+## TaskStateChangedAction Objects
+
+```python
+@dataclass
+class TaskStateChangedAction(NotExecutableAction)
+```
+
+Fake action, just to notify the client that a task state has changed.
+

docs/modules/python/opendevin/agent.md

@@ -0,0 +1,121 @@
+---
+sidebar_label: agent
+title: opendevin.agent
+---
+
+## Agent Objects
+
+```python
+class Agent(ABC)
+```
+
+This abstract base class is an general interface for an agent dedicated to
+executing a specific instruction and allowing human interaction with the
+agent during execution.
+It tracks the execution status and maintains a history of interactions.
+
+#### complete
+
+```python
+@property
+def complete() -> bool
+```
+
+Indicates whether the current instruction execution is complete.
+
+**Returns**:
+
+  - complete (bool): True if execution is complete; False otherwise.
+
+#### step
+
+```python
+@abstractmethod
+def step(state: 'State') -> 'Action'
+```
+
+Starts the execution of the assigned instruction. This method should
+be implemented by subclasses to define the specific execution logic.
+
+#### search\_memory
+
+```python
+@abstractmethod
+def search_memory(query: str) -> List[str]
+```
+
+Searches the agent's memory for information relevant to the given query.
+
+**Arguments**:
+
+  - query (str): The query to search for in the agent's memory.
+  
+
+**Returns**:
+
+  - response (str): The response to the query.
+
+#### reset
+
+```python
+def reset() -> None
+```
+
+Resets the agent's execution status and clears the history. This method can be used
+to prepare the agent for restarting the instruction or cleaning up before destruction.
+
+#### register
+
+```python
+@classmethod
+def register(cls, name: str, agent_cls: Type['Agent'])
+```
+
+Registers an agent class in the registry.
+
+**Arguments**:
+
+  - name (str): The name to register the class under.
+  - agent_cls (Type['Agent']): The class to register.
+  
+
+**Raises**:
+
+  - AgentAlreadyRegisteredError: If name already registered
+
+#### get\_cls
+
+```python
+@classmethod
+def get_cls(cls, name: str) -> Type['Agent']
+```
+
+Retrieves an agent class from the registry.
+
+**Arguments**:
+
+  - name (str): The name of the class to retrieve
+  
+
+**Returns**:
+
+  - agent_cls (Type['Agent']): The class registered under the specified name.
+  
+
+**Raises**:
+
+  - AgentNotRegisteredError: If name not registered
+
+#### list\_agents
+
+```python
+@classmethod
+def list_agents(cls) -> list[str]
+```
+
+Retrieves the list of all agent names from the registry.
+
+**Raises**:
+
+  - AgentNotRegisteredError: If no agent is registered
+

docs/modules/python/opendevin/config.md

@@ -0,0 +1,13 @@
+---
+sidebar_label: config
+title: opendevin.config
+---
+
+#### get
+
+```python
+def get(key: ConfigType, required: bool = False)
+```
+
+Get a key from the environment variables or config.toml or default configs.
+

docs/modules/python/opendevin/controller/agent_controller.md

@@ -0,0 +1,36 @@
+---
+sidebar_label: agent_controller
+title: opendevin.controller.agent_controller
+---
+
+## AgentController Objects
+
+```python
+class AgentController()
+```
+
+#### setup\_task
+
+```python
+async def setup_task(task: str, inputs: dict = {})
+```
+
+Sets up the agent controller with a task.
+
+#### start
+
+```python
+async def start(task: str)
+```
+
+Starts the agent controller with a task.
+If task already run before, it will continue from the last step.
+
+#### get\_task\_state
+
+```python
+def get_task_state()
+```
+
+Returns the current state of the agent task.
+

docs/modules/python/opendevin/files.md

@@ -0,0 +1,40 @@
+---
+sidebar_label: files
+title: opendevin.files
+---
+
+## WorkspaceFile Objects
+
+```python
+class WorkspaceFile()
+```
+
+#### to\_dict
+
+```python
+def to_dict() -> Dict[str, Any]
+```
+
+Converts the File object to a dictionary.
+
+**Returns**:
+
+  The dictionary representation of the File object.
+
+#### get\_folder\_structure
+
+```python
+def get_folder_structure(workdir: Path) -> WorkspaceFile
+```
+
+Gets the folder structure of a directory.
+
+**Arguments**:
+
+- `workdir` - The directory path.
+  
+
+**Returns**:
+
+  The folder structure.
+

docs/modules/python/opendevin/llm/llm.md

@@ -0,0 +1,56 @@
+---
+sidebar_label: llm
+title: opendevin.llm.llm
+---
+
+## LLM Objects
+
+```python
+class LLM()
+```
+
+The LLM class represents a Language Model instance.
+
+#### \_\_init\_\_
+
+```python
+def __init__(model=DEFAULT_MODEL_NAME,
+             api_key=DEFAULT_API_KEY,
+             base_url=DEFAULT_BASE_URL,
+             api_version=DEFAULT_API_VERSION,
+             num_retries=LLM_NUM_RETRIES,
+             retry_min_wait=LLM_RETRY_MIN_WAIT,
+             retry_max_wait=LLM_RETRY_MAX_WAIT,
+             llm_timeout=LLM_TIMEOUT,
+             llm_max_return_tokens=LLM_MAX_RETURN_TOKENS)
+```
+
+**Arguments**:
+
+- `model` _str, optional_ - The name of the language model. Defaults to LLM_MODEL.
+- `api_key` _str, optional_ - The API key for accessing the language model. Defaults to LLM_API_KEY.
+- `base_url` _str, optional_ - The base URL for the language model API. Defaults to LLM_BASE_URL. Not necessary for OpenAI.
+- `api_version` _str, optional_ - The version of the API to use. Defaults to LLM_API_VERSION. Not necessary for OpenAI.
+- `num_retries` _int, optional_ - The number of retries for API calls. Defaults to LLM_NUM_RETRIES.
+- `retry_min_wait` _int, optional_ - The minimum time to wait between retries in seconds. Defaults to LLM_RETRY_MIN_TIME.
+- `retry_max_wait` _int, optional_ - The maximum time to wait between retries in seconds. Defaults to LLM_RETRY_MAX_TIME.
+- `llm_timeout` _int, optional_ - The maximum time to wait for a response in seconds. Defaults to LLM_TIMEOUT.
+- `llm_max_return_tokens` _int, optional_ - The maximum number of tokens to return. Defaults to LLM_MAX_RETURN_TOKENS.
+  
+
+**Attributes**:
+
+- `model_name` _str_ - The name of the language model.
+- `api_key` _str_ - The API key for accessing the language model.
+- `base_url` _str_ - The base URL for the language model API.
+- `api_version` _str_ - The version of the API to use.
+
+#### completion
+
+```python
+@property
+def completion()
+```
+
+Decorator for the litellm completion function.
+

docs/modules/python/opendevin/logger.md

@@ -0,0 +1,92 @@
+---
+sidebar_label: logger
+title: opendevin.logger
+---
+
+#### get\_console\_handler
+
+```python
+def get_console_handler()
+```
+
+Returns a console handler for logging.
+
+#### get\_file\_handler
+
+```python
+def get_file_handler()
+```
+
+Returns a file handler for logging.
+
+#### log\_uncaught\_exceptions
+
+```python
+def log_uncaught_exceptions(ex_cls, ex, tb)
+```
+
+Logs uncaught exceptions along with the traceback.
+
+**Arguments**:
+
+- `ex_cls` _type_ - The type of the exception.
+- `ex` _Exception_ - The exception instance.
+- `tb` _traceback_ - The traceback object.
+  
+
+**Returns**:
+
+  None
+
+## LlmFileHandler Objects
+
+```python
+class LlmFileHandler(logging.FileHandler)
+```
+
+__LLM prompt and response logging__
+
+
+#### \_\_init\_\_
+
+```python
+def __init__(filename, mode='a', encoding='utf-8', delay=False)
+```
+
+Initializes an instance of LlmFileHandler.
+
+**Arguments**:
+
+- `filename` _str_ - The name of the log file.
+- `mode` _str, optional_ - The file mode. Defaults to 'a'.
+- `encoding` _str, optional_ - The file encoding. Defaults to None.
+- `delay` _bool, optional_ - Whether to delay file opening. Defaults to False.
+
+#### emit
+
+```python
+def emit(record)
+```
+
+Emits a log record.
+
+**Arguments**:
+
+- `record` _logging.LogRecord_ - The log record to emit.
+
+#### get\_llm\_prompt\_file\_handler
+
+```python
+def get_llm_prompt_file_handler()
+```
+
+Returns a file handler for LLM prompt logging.
+
+#### get\_llm\_response\_file\_handler
+
+```python
+def get_llm_response_file_handler()
+```
+
+Returns a file handler for LLM response logging.
+

docs/modules/python/opendevin/main.md

@@ -0,0 +1,29 @@
+---
+sidebar_label: main
+title: opendevin.main
+---
+
+#### read\_task\_from\_file
+
+```python
+def read_task_from_file(file_path: str) -> str
+```
+
+Read task from the specified file.
+
+#### read\_task\_from\_stdin
+
+```python
+def read_task_from_stdin() -> str
+```
+
+Read task from stdin.
+
+#### main
+
+```python
+async def main(task_str: str = '')
+```
+
+Main coroutine to run the agent controller with task input flexibility.
+

docs/modules/python/opendevin/observation/__init__.md

@@ -0,0 +1,9 @@
+---
+sidebar_label: observation
+title: opendevin.observation
+---
+
+#### OBSERVATION\_TYPE\_TO\_CLASS
+
+type: ignore[attr-defined]
+

docs/modules/python/opendevin/observation/base.md

@@ -0,0 +1,49 @@
+---
+sidebar_label: base
+title: opendevin.observation.base
+---
+
+## Observation Objects
+
+```python
+@dataclass
+class Observation()
+```
+
+This data class represents an observation of the environment.
+
+#### to\_dict
+
+```python
+def to_dict() -> dict
+```
+
+Converts the observation to a dictionary and adds user message.
+
+#### to\_memory
+
+```python
+def to_memory() -> dict
+```
+
+Converts the observation to a dictionary.
+
+#### message
+
+```python
+@property
+def message() -> str
+```
+
+Returns a message describing the observation.
+
+## NullObservation Objects
+
+```python
+@dataclass
+class NullObservation(Observation)
+```
+
+This data class represents a null observation.
+This is used when the produced action is NOT executable.
+

docs/modules/python/opendevin/observation/browse.md

@@ -0,0 +1,14 @@
+---
+sidebar_label: browse
+title: opendevin.observation.browse
+---
+
+## BrowserOutputObservation Objects
+
+```python
+@dataclass
+class BrowserOutputObservation(Observation)
+```
+
+This data class represents the output of a browser.
+

docs/modules/python/opendevin/observation/delegate.md

@@ -0,0 +1,15 @@
+---
+sidebar_label: delegate
+title: opendevin.observation.delegate
+---
+
+## AgentDelegateObservation Objects
+
+```python
+@dataclass
+class AgentDelegateObservation(Observation)
+```
+
+This data class represents a delegate observation.
+This is used when the produced action is NOT executable.
+

docs/modules/python/opendevin/observation/error.md

@@ -0,0 +1,14 @@
+---
+sidebar_label: error
+title: opendevin.observation.error
+---
+
+## AgentErrorObservation Objects
+
+```python
+@dataclass
+class AgentErrorObservation(Observation)
+```
+
+This data class represents an error encountered by the agent.
+

docs/modules/python/opendevin/observation/files.md

@@ -0,0 +1,23 @@
+---
+sidebar_label: files
+title: opendevin.observation.files
+---
+
+## FileReadObservation Objects
+
+```python
+@dataclass
+class FileReadObservation(Observation)
+```
+
+This data class represents the content of a file.
+
+## FileWriteObservation Objects
+
+```python
+@dataclass
+class FileWriteObservation(Observation)
+```
+
+This data class represents a file write operation
+

docs/modules/python/opendevin/observation/message.md

@@ -0,0 +1,23 @@
+---
+sidebar_label: message
+title: opendevin.observation.message
+---
+
+## UserMessageObservation Objects
+
+```python
+@dataclass
+class UserMessageObservation(Observation)
+```
+
+This data class represents a message sent by the user.
+
+## AgentMessageObservation Objects
+
+```python
+@dataclass
+class AgentMessageObservation(Observation)
+```
+
+This data class represents a message sent by the agent.
+

docs/modules/python/opendevin/observation/recall.md

@@ -0,0 +1,14 @@
+---
+sidebar_label: recall
+title: opendevin.observation.recall
+---
+
+## AgentRecallObservation Objects
+
+```python
+@dataclass
+class AgentRecallObservation(Observation)
+```
+
+This data class represents a list of memories recalled by the agent.
+

docs/modules/python/opendevin/observation/run.md

@@ -0,0 +1,14 @@
+---
+sidebar_label: run
+title: opendevin.observation.run
+---
+
+## CmdOutputObservation Objects
+
+```python
+@dataclass
+class CmdOutputObservation(Observation)
+```
+
+This data class represents the output of a command.
+

docs/modules/python/opendevin/plan.md

@@ -0,0 +1,182 @@
+---
+sidebar_label: plan
+title: opendevin.plan
+---
+
+## Task Objects
+
+```python
+class Task()
+```
+
+#### \_\_init\_\_
+
+```python
+def __init__(parent: 'Task | None',
+             goal: str,
+             state: str = OPEN_STATE,
+             subtasks: List = [])
+```
+
+Initializes a new instance of the Task class.
+
+**Arguments**:
+
+- `parent` - The parent task, or None if it is the root task.
+- `goal` - The goal of the task.
+- `state` - The initial state of the task.
+- `subtasks` - A list of subtasks associated with this task.
+
+#### to\_string
+
+```python
+def to_string(indent='')
+```
+
+Returns a string representation of the task and its subtasks.
+
+**Arguments**:
+
+- `indent` - The indentation string for formatting the output.
+  
+
+**Returns**:
+
+  A string representation of the task and its subtasks.
+
+#### to\_dict
+
+```python
+def to_dict()
+```
+
+Returns a dictionary representation of the task.
+
+**Returns**:
+
+  A dictionary containing the task's attributes.
+
+#### set\_state
+
+```python
+def set_state(state)
+```
+
+Sets the state of the task and its subtasks.
+
+Args:            state: The new state of the task.
+
+**Raises**:
+
+- `PlanInvalidStateError` - If the provided state is invalid.
+
+#### get\_current\_task
+
+```python
+def get_current_task() -> 'Task | None'
+```
+
+Retrieves the current task in progress.
+
+**Returns**:
+
+  The current task in progress, or None if no task is in progress.
+
+## Plan Objects
+
+```python
+class Plan()
+```
+
+Represents a plan consisting of tasks.
+
+**Attributes**:
+
+- `main_goal` - The main goal of the plan.
+- `task` - The root task of the plan.
+
+#### \_\_init\_\_
+
+```python
+def __init__(task: str)
+```
+
+Initializes a new instance of the Plan class.
+
+**Arguments**:
+
+- `task` - The main goal of the plan.
+
+#### \_\_str\_\_
+
+```python
+def __str__()
+```
+
+Returns a string representation of the plan.
+
+**Returns**:
+
+  A string representation of the plan.
+
+#### get\_task\_by\_id
+
+```python
+def get_task_by_id(id: str) -> Task
+```
+
+Retrieves a task by its ID.
+
+**Arguments**:
+
+- `id` - The ID of the task.
+  
+
+**Returns**:
+
+  The task with the specified ID.
+  
+
+**Raises**:
+
+- `ValueError` - If the provided task ID is invalid or does not exist.
+
+#### add\_subtask
+
+```python
+def add_subtask(parent_id: str, goal: str, subtasks: List = [])
+```
+
+Adds a subtask to a parent task.
+
+**Arguments**:
+
+- `parent_id` - The ID of the parent task.
+- `goal` - The goal of the subtask.
+- `subtasks` - A list of subtasks associated with the new subtask.
+
+#### set\_subtask\_state
+
+```python
+def set_subtask_state(id: str, state: str)
+```
+
+Sets the state of a subtask.
+
+**Arguments**:
+
+- `id` - The ID of the subtask.
+- `state` - The new state of the subtask.
+
+#### get\_current\_task
+
+```python
+def get_current_task()
+```
+
+Retrieves the current task in progress.
+
+**Returns**:
+
+  The current task in progress, or None if no task is in progress.
+

docs/modules/python/opendevin/sandbox/e2b/sandbox.md

@@ -0,0 +1,19 @@
+---
+sidebar_label: sandbox
+title: opendevin.sandbox.e2b.sandbox
+---
+
+## E2BBox Objects
+
+```python
+class E2BBox(Sandbox)
+```
+
+#### copy\_to
+
+```python
+def copy_to(host_src: str, sandbox_dest: str, recursive: bool = False)
+```
+
+Copies a local file or directory to the sandbox.
+

docs/modules/python/opendevin/sandbox/plugins/jupyter/__init__.md

@@ -0,0 +1,16 @@
+---
+sidebar_label: jupyter
+title: opendevin.sandbox.plugins.jupyter
+---
+
+## JupyterRequirement Objects
+
+```python
+@dataclass
+class JupyterRequirement(PluginRequirement)
+```
+
+#### host\_src
+
+The directory of this file (sandbox/plugins/jupyter)
+

docs/modules/python/opendevin/sandbox/plugins/mixin.md

@@ -0,0 +1,21 @@
+---
+sidebar_label: mixin
+title: opendevin.sandbox.plugins.mixin
+---
+
+## PluginMixin Objects
+
+```python
+class PluginMixin()
+```
+
+Mixin for Sandbox to support plugins.
+
+#### init\_plugins
+
+```python
+def init_plugins(requirements: List[PluginRequirement])
+```
+
+Load a plugin into the sandbox.
+

docs/modules/python/opendevin/sandbox/plugins/requirement.md

@@ -0,0 +1,14 @@
+---
+sidebar_label: requirement
+title: opendevin.sandbox.plugins.requirement
+---
+
+## PluginRequirement Objects
+
+```python
+@dataclass
+class PluginRequirement()
+```
+
+Requirement for a plugin.
+

docs/modules/python/opendevin/schema/action.md

@@ -0,0 +1,76 @@
+---
+sidebar_label: action
+title: opendevin.schema.action
+---
+
+## ActionTypeSchema Objects
+
+```python
+class ActionTypeSchema(BaseModel)
+```
+
+#### INIT
+
+Initializes the agent. Only sent by client.
+
+#### START
+
+Starts a new development task. Only sent by the client.
+
+#### READ
+
+Reads the content of a file.
+
+#### WRITE
+
+Writes the content to a file.
+
+#### RUN
+
+Runs a command.
+
+#### KILL
+
+Kills a background command.
+
+#### BROWSE
+
+Opens a web page.
+
+#### RECALL
+
+Searches long-term memory
+
+#### THINK
+
+Allows the agent to make a plan, set a goal, or record thoughts
+
+#### DELEGATE
+
+Delegates a task to another agent.
+
+#### FINISH
+
+If you're absolutely certain that you've completed your task and have tested your work,
+use the finish action to stop working.
+
+#### PAUSE
+
+Pauses the task.
+
+#### RESUME
+
+Resumes the task.
+
+#### STOP
+
+Stops the task. Must send a start action to restart a new task.
+
+#### PUSH
+
+Push a branch to github.
+
+#### SEND\_PR
+
+Send a PR to github.
+

docs/modules/python/opendevin/schema/observation.md

@@ -0,0 +1,35 @@
+---
+sidebar_label: observation
+title: opendevin.schema.observation
+---
+
+## ObservationTypeSchema Objects
+
+```python
+class ObservationTypeSchema(BaseModel)
+```
+
+#### READ
+
+The content of a file
+
+#### BROWSE
+
+The HTML content of a URL
+
+#### RUN
+
+The output of a command
+
+#### RECALL
+
+The result of a search
+
+#### CHAT
+
+A message from the user
+
+#### DELEGATE
+
+The result of a task delegated to another agent
+

docs/modules/python/opendevin/schema/task.md

@@ -0,0 +1,57 @@
+---
+sidebar_label: task
+title: opendevin.schema.task
+---
+
+## TaskState Objects
+
+```python
+class TaskState(str, Enum)
+```
+
+#### INIT
+
+Initial state of the task.
+
+#### RUNNING
+
+The task is running.
+
+#### PAUSED
+
+The task is paused.
+
+#### STOPPED
+
+The task is stopped.
+
+#### FINISHED
+
+The task is finished.
+
+#### ERROR
+
+An error occurred during the task.
+
+## TaskStateAction Objects
+
+```python
+class TaskStateAction(str, Enum)
+```
+
+#### START
+
+Starts the task.
+
+#### PAUSE
+
+Pauses the task.
+
+#### RESUME
+
+Resumes the task.
+
+#### STOP
+
+Stops the task.
+

docs/modules/python/opendevin/server/agent/agent.md

@@ -0,0 +1,132 @@
+---
+sidebar_label: agent
+title: opendevin.server.agent.agent
+---
+
+## AgentUnit Objects
+
+```python
+class AgentUnit()
+```
+
+Represents a session with an agent.
+
+**Attributes**:
+
+- `controller` - The AgentController instance for controlling the agent.
+- `agent_task` - The task representing the agent's execution.
+
+#### \_\_init\_\_
+
+```python
+def __init__(sid)
+```
+
+Initializes a new instance of the Session class.
+
+#### send\_error
+
+```python
+async def send_error(message)
+```
+
+Sends an error message to the client.
+
+**Arguments**:
+
+- `message` - The error message to send.
+
+#### send\_message
+
+```python
+async def send_message(message)
+```
+
+Sends a message to the client.
+
+**Arguments**:
+
+- `message` - The message to send.
+
+#### send
+
+```python
+async def send(data)
+```
+
+Sends data to the client.
+
+**Arguments**:
+
+- `data` - The data to send.
+
+#### dispatch
+
+```python
+async def dispatch(action: str | None, data: dict)
+```
+
+Dispatches actions to the agent from the client.
+
+#### get\_arg\_or\_default
+
+```python
+def get_arg_or_default(_args: dict, key: ConfigType) -> str
+```
+
+Gets an argument from the args dictionary or the default value.
+
+**Arguments**:
+
+- `_args` - The args dictionary.
+- `key` - The key to get.
+  
+
+**Returns**:
+
+  The value of the key or the default value.
+
+#### create\_controller
+
+```python
+async def create_controller(start_event: dict)
+```
+
+Creates an AgentController instance.
+
+**Arguments**:
+
+- `start_event` - The start event data (optional).
+
+#### start\_task
+
+```python
+async def start_task(start_event)
+```
+
+Starts a task for the agent.
+
+**Arguments**:
+
+- `start_event` - The start event data.
+
+#### set\_task\_state
+
+```python
+async def set_task_state(new_state_action: TaskStateAction)
+```
+
+Sets the state of the agent task.
+
+#### on\_agent\_event
+
+```python
+async def on_agent_event(event: Observation | Action)
+```
+
+Callback function for agent events.
+
+**Arguments**:
+
+- `event` - The agent event (Observation or Action).
+

docs/modules/python/opendevin/server/agent/manager.md

@@ -0,0 +1,31 @@
+---
+sidebar_label: manager
+title: opendevin.server.agent.manager
+---
+
+## AgentManager Objects
+
+```python
+class AgentManager()
+```
+
+#### register\_agent
+
+```python
+def register_agent(sid: str)
+```
+
+Registers a new agent.
+
+**Arguments**:
+
+- `sid` - The session ID of the agent.
+
+#### dispatch
+
+```python
+async def dispatch(sid: str, action: str | None, data: dict)
+```
+
+Dispatches actions to the agent from the client.
+

docs/modules/python/opendevin/server/auth/auth.md

@@ -0,0 +1,30 @@
+---
+sidebar_label: auth
+title: opendevin.server.auth.auth
+---
+
+#### get\_sid\_from\_token
+
+```python
+def get_sid_from_token(token: str) -> str
+```
+
+Retrieves the session id from a JWT token.
+
+**Arguments**:
+
+- `token` _str_ - The JWT token from which the session id is to be extracted.
+  
+
+**Returns**:
+
+- `str` - The session id if found and valid, otherwise an empty string.
+
+#### sign\_token
+
+```python
+def sign_token(payload: Dict[str, object]) -> str
+```
+
+Signs a JWT token.
+

docs/modules/python/opendevin/server/listen.md

@@ -0,0 +1,34 @@
+---
+sidebar_label: listen
+title: opendevin.server.listen
+---
+
+#### get\_litellm\_models
+
+```python
+@app.get('/api/litellm-models')
+async def get_litellm_models()
+```
+
+Get all models supported by LiteLLM.
+
+#### get\_agents
+
+```python
+@app.get('/api/agents')
+async def get_agents()
+```
+
+Get all agents supported by LiteLLM.
+
+#### get\_token
+
+```python
+@app.get('/api/auth')
+async def get_token(
+        credentials: HTTPAuthorizationCredentials = Depends(security_scheme))
+```
+
+Generate a JWT for authentication when starting a WebSocket connection. This endpoint checks if valid credentials
+are provided and uses them to get a session ID. If no valid credentials are provided, it generates a new session ID.
+

docs/modules/python/opendevin/server/session/manager.md

@@ -0,0 +1,35 @@
+---
+sidebar_label: manager
+title: opendevin.server.session.manager
+---
+
+## SessionManager Objects
+
+```python
+class SessionManager()
+```
+
+#### send
+
+```python
+async def send(sid: str, data: Dict[str, object]) -> bool
+```
+
+Sends data to the client.
+
+#### send\_error
+
+```python
+async def send_error(sid: str, message: str) -> bool
+```
+
+Sends an error message to the client.
+
+#### send\_message
+
+```python
+async def send_message(sid: str, message: str) -> bool
+```
+
+Sends a message to the client.
+

docs/modules/python/opendevin/server/session/msg_stack.md

@@ -0,0 +1,15 @@
+---
+sidebar_label: msg_stack
+title: opendevin.server.session.msg_stack
+---
+
+## Message Objects
+
+```python
+class Message()
+```
+
+#### role
+
+"user"| "assistant"
+