stop printing

use minimal prompt for codeact;

.gitattributes

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

.github/.codecov.yml

@@ -0,0 +1,19 @@
+codecov:
+  notify:
+    wait_for_ci: true
+
+coverage:
+  status:
+    patch:
+      default:
+        threshold: 100% # allow patch coverage to be lower than project coverage by any amount
+    project:
+      default:
+        threshold: 5% # allow project coverage to drop at most 5%
+
+comment: false
+github_checks:
+    annotations: false
+
+ignore:
+  - "agenthub/SWE_agent/**" # SWE agent is deprecated

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -12,7 +12,7 @@ body:
       label: Is there an existing issue for the same bug?
       description: Please check if an issue already exists for the bug you encountered.
       options:
-      - label: I have checked the troubleshooting document at https://github.com/OpenDevin/OpenDevin/blob/main/docs/guides/Troubleshooting.md
+      - label: I have checked the troubleshooting document at https://opendevin.github.io/OpenDevin/modules/usage/troubleshooting
         required: true
       - label: I have checked the existing issues.
         required: true
@@ -28,8 +28,8 @@ body:
   - type: textarea
     id: current-version
     attributes:
-      label: Current Version
-      description: What version are you using? If you're running in docker, tell us the tag you're using (e.g. ghcr.io/opendevin/opendevin:0.3.1).
+      label: Current OpenDevin version
+      description: What version of OpenDevin are you using? If you're running in docker, tell us the tag you're using (e.g. ghcr.io/opendevin/opendevin:0.3.1).
       render: bash
     validations:
       required: true
@@ -52,6 +52,12 @@ body:
         - Model:
         - Agent:
 
+  - type: textarea
+    id: os-version
+    attributes:
+      label: Operating System
+      description: What Operating System are you using? Linux, Mac OS, WSL on Windows
+
   - type: textarea
     id: repro-steps
     attributes:
@@ -66,4 +72,4 @@ body:
     id: additional-context
     attributes:
       label: Logs, Errors, Screenshots, and Additional Context
-      description: Please add any additional context about the problem here.
+      description: LLM logs will be stored in the `logs/llm/default` folder. Please add any additional context about the problem here.

.github/dependabot.yml

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

.github/workflows/deploy-docs.yml

@@ -0,0 +1,59 @@
+name: Deploy Docs to GitHub Pages
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  build:
+    name: Build Docusaurus
+    runs-on: ubuntu-latest
+    if: github.repository == 'OpenDevin/OpenDevin'
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 18
+          cache: npm
+          cache-dependency-path: docs/package-lock.json
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Generate Python Docs
+        run: rm -rf docs/modules/python && pip install pydoc-markdown && pydoc-markdown
+      - name: Install dependencies
+        run: cd docs && npm ci
+      - name: Build website
+        run: cd docs && npm run build
+
+      - name: Upload Build Artifact
+        if: github.ref == 'refs/heads/main'
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: docs/build
+
+  deploy:
+    name: Deploy to GitHub Pages
+    needs: build
+    if: github.ref == 'refs/heads/main' && github.repository == 'OpenDevin/OpenDevin'
+    # Grant GITHUB_TOKEN the permissions required to make a Pages deployment
+    permissions:
+      pages: write # to deploy to Pages
+      id-token: write # to verify the deployment originates from an appropriate source
+    # Deploy to the github-pages environment
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

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

@@ -0,0 +1,30 @@
+name: Run e2e test with dummy agent
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+on:
+  push:
+    branches:
+    - main
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+      - name: Set up environment
+        run: |
+          curl -sSL https://install.python-poetry.org | python3 -
+          poetry install --without evaluation
+          poetry run playwright install --with-deps chromium
+          wget https://huggingface.co/BAAI/bge-small-en-v1.5/raw/main/1_Pooling/config.json -P /tmp/llama_index/models--BAAI--bge-small-en-v1.5/snapshots/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/1_Pooling/
+      - name: Run tests
+        run: |
+          poetry run python opendevin/core/main.py -t "do a flip" -m ollama/not-a-model -d ./workspace/ -c DummyAgent

.github/workflows/ghcr.yml

@@ -1,7 +1,16 @@
 name: Publish Docker Image
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
 on:
   push:
+    branches:
+    - main
+    tags:
+      - '*'
+  pull_request:
   workflow_dispatch:
     inputs:
       reason:
@@ -12,15 +21,35 @@ on:
 jobs:
   ghcr_build_and_push:
     runs-on: ubuntu-latest
-    if: github.event_name == 'push' || github.event.inputs.reason != ''
+
+    permissions:
+      contents: read
+      packages: write
+
     strategy:
       matrix:
-        image: ["app", "evaluation", "sandbox"]
+        image: ["app", "sandbox"]
 
     steps:
       - name: checkout
         uses: actions/checkout@v4
 
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v3
 
@@ -28,13 +57,26 @@ jobs:
         id: buildx
         uses: docker/setup-buildx-action@v3
 
-      - name: Log-in to ghcr.io
-        run: echo "${{ secrets.GITHUB_TOKEN }}" | docker login ghcr.io -u ${{ github.actor }} --password-stdin
-
-      - name: Delete huge unnecessary tools folder
-        run: rm -rf /opt/hostedtoolcache
+      - name: Login to ghcr
+        uses: docker/login-action@v1
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Build and push ${{ matrix.image }}
+        if: "!github.event.pull_request.head.repo.fork"
         run: |
-          ORG_NAME=$(echo "${{ github.repository }}" | tr '[A-Z]' '[a-z]' | cut -d '/' -f 1)
-          ./containers/build.sh ${{ matrix.image }} $ORG_NAME --push
+          ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} --push
+
+      - name: Build ${{ matrix.image }}
+        if: "github.event.pull_request.head.repo.fork"
+        run: |
+          ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }}
+
+  docker_build_success:
+    name: Docker Build Success
+    runs-on: ubuntu-latest
+    needs: ghcr_build_and_push
+    steps:
+    - run: echo Done!

.github/workflows/lint.yml

@@ -1,9 +1,18 @@
 name: Lint
 
-on: [push, pull_request]
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+on:
+  push:
+    branches:
+    - main
+  pull_request:
 
 jobs:
   lint-frontend:
+    name: Lint frontend
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
@@ -28,11 +37,21 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
       - name: Set up python
         uses: actions/setup-python@v5
         with:
           python-version: 3.11
+          cache: 'pip'
       - name: Install pre-commit
         run: pip install pre-commit==3.7.0
       - name: Run pre-commit hooks
-        run: pre-commit run --files opendevin/**/* agenthub/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
+        if: github.ref != 'refs/heads/main'
+        run: |
+          git fetch https://github.com/OpenDevin/OpenDevin.git main:main && \
+          pre-commit run \
+            --files \
+            $(git diff --name-only $(git merge-base main $(git branch --show-current)) $(git branch --show-current) | tr '\n' ' ') \
+            --show-diff-on-failure \
+            --config ./dev_config/python/.pre-commit-config.yaml

.github/workflows/review-pr.yml

@@ -49,7 +49,7 @@ jobs:
         LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
         SANDBOX_TYPE: exec
       run: |
-        WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE python ./opendevin/main.py -i 50 -f task.txt -d $GITHUB_WORKSPACE
+        WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE python ./opendevin/core/main.py -i 50 -f task.txt -d $GITHUB_WORKSPACE
         rm task.txt
 
     - name: Check if review file is non-empty

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

@@ -1,70 +1,101 @@
 name: Run Integration Tests
 
-on: [push, pull_request]
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+on:
+  push:
+    branches:
+      - main
+    paths-ignore:
+      - '**/*.md'
+      - 'frontend/**'
+      - 'docs/**'
+      - 'evaluation/**'
+  pull_request:
 
 jobs:
-  on-linux:
+  integration-tests-on-linux:
+    name: Integration Tests on Linux
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
-        include:
-          - name: SWEAgent-py311-ssh
-            python-version: "3.11"
-            agent: "SWEAgent"
-            embedding-model: "none"
-            sandbox: "ssh"
-          - name: PlannerAgent-py311-ssh
-            python-version: "3.11"
-            agent: "PlannerAgent"
-            embedding-model: "none"
-            sandbox: "ssh"
-          - name: MonologueAgent-py311-ssh
-            python-version: "3.11"
-            agent: "MonologueAgent"
-            embedding-model: "local"
-            sandbox: "ssh"
-          - name: CodeActAgent-py311-ssh
-            python-version: "3.11"
-            agent: "CodeActAgent"
-            embedding-model: "none"
-            sandbox: "ssh"
-          - name: SWEAgent-py311-exec
-            python-version: "3.11"
-            agent: "SWEAgent"
-            embedding-model: "none"
-            sandbox: "exec"
-          - name: PlannerAgent-py311-exec
-            python-version: "3.11"
-            agent: "PlannerAgent"
-            embedding-model: "none"
-            sandbox: "exec"
-          - name: MonologueAgent-py311-exec
-            python-version: "3.11"
-            agent: "MonologueAgent"
-            embedding-model: "local"
-            sandbox: "exec"
-          - name: CodeActAgent-py311-exec
-            python-version: "3.11"
-            agent: "CodeActAgent"
-            embedding-model: "none"
-            sandbox: "exec"
+        python-version: ["3.11"]
+        sandbox: ["ssh", "exec", "local"]
     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
+
       - name: Build Environment
         run: make build
+
       - name: Run Integration Tests
         env:
           SANDBOX_TYPE: ${{ matrix.sandbox }}
-          AGENT: ${{ matrix.agent }}
-          MAX_ITERATIONS: 10
-          LLM_EMBEDDING_MODEL: ${{ matrix.embedding-model }}
         run: |
-          rm -rf workspace
-          mkdir workspace
-          WORKSPACE_BASE="$GITHUB_WORKSPACE/workspace" WORKSPACE_MOUNT_PATH="$GITHUB_WORKSPACE/workspace" poetry run pytest -s ./tests/integration
+          TEST_IN_CI=true TEST_ONLY=true ./tests/integration/regenerate.sh
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+  integration-tests-on-mac:
+    name: Integration Tests on MacOS
+    runs-on: macos-13
+    if: contains(github.event.pull_request.title, 'mac') || contains(github.event.pull_request.title, 'Mac')
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11"]
+        sandbox: ["ssh"]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'poetry'
+
+      - name: Install Python dependencies using Poetry
+        run: poetry install
+
+      - name: Install & Start Docker
+        run: |
+          brew install colima docker
+          colima start
+
+          # For testcontainers to find the Colima socket
+          # https://github.com/abiosoft/colima/blob/main/docs/FAQ.md#cannot-connect-to-the-docker-daemon-at-unixvarrundockersock-is-the-docker-daemon-running
+          sudo ln -sf $HOME/.colima/default/docker.sock /var/run/docker.sock
+
+      - name: Build Environment
+        run: make build
+
+      - name: Run Integration Tests
+        env:
+          SANDBOX_TYPE: ${{ matrix.sandbox }}
+        run: |
+          TEST_IN_CI=true TEST_ONLY=true ./tests/integration/regenerate.sh
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

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

@@ -1,47 +1,126 @@
 name: Run Unit Tests
 
-on: [push, pull_request]
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+on:
+  push:
+    branches:
+      - main
+    paths-ignore:
+      - '**/*.md'
+      - 'frontend/**'
+      - 'docs/**'
+      - 'evaluation/**'
+  pull_request:
 
 jobs:
-  on-macos:
+  test-on-macos:
+    name: Test on macOS
     runs-on: macos-13
+    env:
+      INSTALL_DOCKER: "0" # Set to '0' to skip Docker installation
     strategy:
       matrix:
         python-version: ["3.11"]
 
     steps:
       - uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
       - name: Set up Python ${{ 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
+        if: env.INSTALL_DOCKER == '1'
         run: |
           brew install colima docker
           colima start
-      - name: Install and configure Poetry
-        uses: snok/install-poetry@v1
-        with:
-          version: latest
+
+          # For testcontainers to find the Colima socket
+          # https://github.com/abiosoft/colima/blob/main/docs/FAQ.md#cannot-connect-to-the-docker-daemon-at-unixvarrundockersock-is-the-docker-daemon-running
+          sudo ln -sf $HOME/.colima/default/docker.sock /var/run/docker.sock
+
       - name: Build Environment
         run: make build
+
       - name: Run Tests
-        run: poetry run pytest ./tests/unit
-  on-linux:
+        run: poetry run pytest --forked --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox"
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+  test-on-linux:
+    name: Test on Linux
     runs-on: ubuntu-latest
+    env:
+      INSTALL_DOCKER: "0" # Set to '0' to skip Docker installation
     strategy:
       matrix:
         python-version: ["3.11"]
 
     steps:
       - uses: actions/checkout@v4
-      - name: 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 --forked --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox"
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+  test-for-sandbox:
+    name: Test for Sandbox
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: "poetry"
+
+      - name: Install Python dependencies using Poetry
+        run: poetry install
+
+      - name: Build Environment
+        run: make build
+
+      - name: Run Integration Test for Sandbox
+        run: |
+          poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml -s ./tests/unit/test_sandbox.py
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

.github/workflows/solve-issue.yml

@@ -43,7 +43,7 @@ jobs:
         LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
         SANDBOX_TYPE: exec
       run: |
-        WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE python ./opendevin/main.py -i 50 -f task.txt -d $GITHUB_WORKSPACE
+        WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE python ./opendevin/core/main.py -i 50 -f task.txt -d $GITHUB_WORKSPACE
         rm task.txt
 
     - name: Setup Git, Create Branch, and Commit Changes

.gitignore

@@ -126,6 +126,7 @@ env/
 venv/
 ENV/
 env.bak/
+.env.bak
 venv.bak/
 *venv/
 
@@ -196,8 +197,15 @@ logs
 # agent
 .envrc
 /workspace
+/_test_workspace
 /debug
 cache
 
 # configuration
 config.toml
+config.toml.bak
+evaluation/swe_bench/eval_workspace*
+evaluation/outputs
+evaluation/evaluation_outputs
+test_results*
+/_test_files_tmp/

Development.md

@@ -82,3 +82,20 @@ If you encounter any issues with the Language Model (LM) or you're simply curiou
     ```bash
     make help
     ```
+
+### 8. Testing
+
+#### Unit tests
+
+```bash
+poetry run pytest ./tests/unit/test_sandbox.py
+```
+
+#### Integration tests
+
+Please refer to [this README](./tests/integration/README.md) for details.
+
+### 9. Add or update dependency
+
+1. Add your dependency in `pyproject.toml` or use `peotry add xxx`
+2. Update the poetry.lock file via `poetry lock --no-update`

Makefile

@@ -7,7 +7,7 @@ BACKEND_PORT = 3000
 BACKEND_HOST = "127.0.0.1:$(BACKEND_PORT)"
 FRONTEND_PORT = 3001
 DEFAULT_WORKSPACE_DIR = "./workspace"
-DEFAULT_MODEL = "gpt-3.5-turbo-1106"
+DEFAULT_MODEL = "gpt-3.5-turbo"
 CONFIG_FILE = config.toml
 PRECOMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
 
@@ -22,7 +22,9 @@ RESET=$(shell tput -Txterm sgr0)
 build:
 	@echo "$(GREEN)Building project...$(RESET)"
 	@$(MAKE) -s check-dependencies
+ifeq ($(INSTALL_DOCKER),)
 	@$(MAKE) -s pull-docker-image
+endif
 	@$(MAKE) -s install-python-dependencies
 	@$(MAKE) -s install-frontend-dependencies
 	@$(MAKE) -s install-precommit-hooks
@@ -35,7 +37,9 @@ check-dependencies:
 	@$(MAKE) -s check-python
 	@$(MAKE) -s check-npm
 	@$(MAKE) -s check-nodejs
+ifeq ($(INSTALL_DOCKER),)
 	@$(MAKE) -s check-docker
+endif
 	@$(MAKE) -s check-poetry
 	@echo "$(GREEN)Dependencies checked successfully.$(RESET)"
 
@@ -44,7 +48,11 @@ check-system:
 	@if [ "$(shell uname)" = "Darwin" ]; then \
 		echo "$(BLUE)macOS detected.$(RESET)"; \
 	elif [ "$(shell uname)" = "Linux" ]; then \
-		echo "$(BLUE)Linux detected.$(RESET)"; \
+		if [ -f "/etc/manjaro-release" ]; then \
+			echo "$(BLUE)Manjaro Linux detected.$(RESET)"; \
+		else \
+			echo "$(BLUE)Linux detected.$(RESET)"; \
+		fi; \
 	elif [ "$$(uname -r | grep -i microsoft)" ]; then \
 		echo "$(BLUE)Windows Subsystem for Linux detected.$(RESET)"; \
 	else \
@@ -122,12 +130,20 @@ pull-docker-image:
 
 install-python-dependencies:
 	@echo "$(GREEN)Installing Python dependencies...$(RESET)"
+	poetry env use python3.11
 	@if [ "$(shell uname)" = "Darwin" ]; then \
-		echo "$(BLUE)Installing `chroma-hnswlib`...$(RESET)"; \
+		echo "$(BLUE)Installing chroma-hnswlib...$(RESET)"; \
 		export HNSWLIB_NO_NATIVE=1; \
 		poetry run pip install chroma-hnswlib; \
 	fi
-	@poetry install --without evaluation
+	@poetry install
+	@if [ -f "/etc/manjaro-release" ]; then \
+		echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
+		poetry run pip install playwright; \
+		poetry run playwright install chromium; \
+	else \
+		poetry run playwright install --with-deps chromium; \
+	fi
 	@echo "$(GREEN)Python dependencies installed successfully.$(RESET)"
 
 install-frontend-dependencies:
@@ -147,9 +163,24 @@ install-precommit-hooks:
 	@poetry run pre-commit install --config $(PRECOMMIT_CONFIG_PATH)
 	@echo "$(GREEN)Pre-commit hooks installed successfully.$(RESET)"
 
-lint:
+lint-backend:
 	@echo "$(YELLOW)Running linters...$(RESET)"
-	@poetry run pre-commit run --files opendevin/**/* agenthub/**/* --show-diff-on-failure --config $(PRECOMMIT_CONFIG_PATH)
+	@poetry run pre-commit run --files $$(git diff --name-only $$(git merge-base main $$(git branch --show-current)) $$(git branch --show-current) | tr '\n' ' ') --show-diff-on-failure --config $(PRECOMMIT_CONFIG_PATH)
+
+lint-frontend:
+	@echo "$(YELLOW)Running linters for frontend...$(RESET)"
+	@cd frontend && npm run lint
+
+lint:
+	@$(MAKE) -s lint-frontend
+	@$(MAKE) -s lint-backend
+
+test-frontend:
+	@echo "$(YELLOW)Running tests for frontend...$(RESET)"
+	@cd frontend && npm run test
+
+test:
+	@$(MAKE) -s test-frontend
 
 build-frontend:
 	@echo "$(YELLOW)Building frontend...$(RESET)"
@@ -158,7 +189,7 @@ 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:
@@ -189,34 +220,50 @@ 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; \
-	 llm_model=$${llm_model:-$(DEFAULT_MODEL)}; \
-	 echo "LLM_MODEL=\"$$llm_model\"" > $(CONFIG_FILE).tmp
-
-	@read -p "Enter your LLM API key: " llm_api_key; \
-	 echo "LLM_API_KEY=\"$$llm_api_key\"" >> $(CONFIG_FILE).tmp
-
-	@read -p "Enter your LLM Base URL [mostly used for local LLMs, leave blank if not needed - example: http://localhost:5001/v1/]: " llm_base_url; \
-	 if [[ ! -z "$$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; \
-		elif [ "$$llm_embedding_model" = "azureopenai" ]; then \
-			read -p "Enter the Azure endpoint URL (will overwrite LLM_BASE_URL): " llm_base_url; \
-				echo "LLM_BASE_URL=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
-			read -p "Enter the Azure LLM Embedding Deployment Name: " llm_embedding_deployment_name; \
-				echo "LLM_EMBEDDING_DEPLOYMENT_NAME=\"$$llm_embedding_deployment_name\"" >> $(CONFIG_FILE).tmp; \
-			read -p "Enter the Azure API Version: " llm_api_version; \
-				echo "LLM_API_VERSION=\"$$llm_api_version\"" >> $(CONFIG_FILE).tmp; \
-		fi
+	@echo "[core]" > $(CONFIG_FILE).tmp
 
 	@read -p "Enter your workspace directory [default: $(DEFAULT_WORKSPACE_DIR)]: " workspace_dir; \
 	 workspace_dir=$${workspace_dir:-$(DEFAULT_WORKSPACE_DIR)}; \
-	 echo "WORKSPACE_BASE=\"$$workspace_dir\"" >> $(CONFIG_FILE).tmp
+	 echo "workspace_base=\"$$workspace_dir\"" >> $(CONFIG_FILE).tmp
+
+	@echo "" >> $(CONFIG_FILE).tmp
+
+	@echo "[llm]" >> $(CONFIG_FILE).tmp
+	@read -p "Enter your LLM model name, used for running without UI. Set the model in the UI after you start the app. (see https://docs.litellm.ai/docs/providers for full list) [default: $(DEFAULT_MODEL)]: " llm_model; \
+	 llm_model=$${llm_model:-$(DEFAULT_MODEL)}; \
+	 echo "model=\"$$llm_model\"" >> $(CONFIG_FILE).tmp
+
+	@read -p "Enter your LLM api key: " llm_api_key; \
+	 echo "api_key=\"$$llm_api_key\"" >> $(CONFIG_FILE).tmp
+
+	@read -p "Enter your LLM base URL [mostly used for local LLMs, leave blank if not needed - example: http://localhost:5001/v1/]: " llm_base_url; \
+	 if [[ ! -z "$$llm_base_url" ]]; then echo "base_url=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; fi
+
+	@echo "Enter your LLM Embedding Model"; \
+		echo "Choices are:"; \
+		echo "  - openai"; \
+		echo "  - azureopenai"; \
+		echo "  - Embeddings available only with OllamaEmbedding:"; \
+		echo "    - llama2"; \
+		echo "    - mxbai-embed-large"; \
+		echo "    - nomic-embed-text"; \
+		echo "    - all-minilm"; \
+		echo "    - stable-code"; \
+		echo "  - Leave blank to default to 'BAAI/bge-small-en-v1.5' via huggingface"; \
+		read -p "> " llm_embedding_model; \
+		echo "embedding_model=\"$$llm_embedding_model\"" >> $(CONFIG_FILE).tmp; \
+		if [ "$$llm_embedding_model" = "llama2" ] || [ "$$llm_embedding_model" = "mxbai-embed-large" ] || [ "$$llm_embedding_model" = "nomic-embed-text" ] || [ "$$llm_embedding_model" = "all-minilm" ] || [ "$$llm_embedding_model" = "stable-code" ]; then \
+			read -p "Enter the local model URL for the embedding model (will set llm.embedding_base_url): " llm_embedding_base_url; \
+				echo "embedding_base_url=\"$$llm_embedding_base_url\"" >> $(CONFIG_FILE).tmp; \
+		elif [ "$$llm_embedding_model" = "azureopenai" ]; then \
+			read -p "Enter the Azure endpoint URL (will overwrite llm.base_url): " llm_base_url; \
+				echo "base_url=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
+			read -p "Enter the Azure LLM Embedding Deployment Name: " llm_embedding_deployment_name; \
+				echo "embedding_deployment_name=\"$$llm_embedding_deployment_name\"" >> $(CONFIG_FILE).tmp; \
+			read -p "Enter the Azure API Version: " llm_api_version; \
+				echo "api_version=\"$$llm_api_version\"" >> $(CONFIG_FILE).tmp; \
+		fi
+
 
 # Clean up all caches
 clean:

README.md

@@ -1,5 +1,3 @@
-[English](README.md) | [中文](docs/README-zh.md)
-
 <a name="readme-top"></a>
 
 <!--
@@ -20,240 +18,108 @@
 -->
 
 <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>
+  <a href="https://github.com/OpenDevin/OpenDevin/graphs/contributors"><img src="https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge&color=blue" alt="Contributors"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/network/members"><img src="https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge&color=blue" alt="Forks"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/stargazers"><img src="https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge&color=blue" alt="Stargazers"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/issues"><img src="https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge&color=blue" alt="Issues"></a>
+  <a href="https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE"><img src="https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge&color=blue" alt="MIT License"></a>
+  <br/>
+  <a href="https://join.slack.com/t/opendevin/shared_invite/zt-2i1iqdag6-bVmvamiPA9EZUu7oCO6KhA"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
+  <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
+  <br/>
+  <a href="https://huggingface.co/spaces/OpenDevin/evaluation"><img src="https://img.shields.io/badge/SWE--bench%20Lite-25.0%25-green?style=for-the-badge" alt="SWE-bench "></a>
+  <a href="https://codecov.io/github/opendevin/opendevin?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/opendevin/opendevin?style=for-the-badge"></a>
 </div>
 
 <!-- PROJECT LOGO -->
 <div align="center">
-  <img src="./logo.png" alt="Logo" width="200" height="200">
+  <img src="./docs/static/img/logo.png" alt="Logo" width="200" height="200">
   <h1 align="center">OpenDevin: Code Less, Make More</h1>
+  <a href="https://opendevin.github.io/OpenDevin/"><img src="https://img.shields.io/badge/Documentation-OpenDevin-blue?logo=googledocs&logoColor=white&style=for-the-badge" alt="Check out the documentation"></a>
 </div>
+<hr>
 
-<!-- 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>
+Welcome to OpenDevin, a platform for autonomous software engineers, powered by AI and LLMs.
 
-## 🎯 Mission
+OpenDevin agents collaborate with human developers to write code, fix bugs, and ship features.
 
-[Project Demo Video](https://github.com/OpenDevin/OpenDevin/assets/38853559/71a472cc-df34-430c-8b1d-4d7286c807c9)
+![App screenshot](./docs/static/img/screenshot.png)
 
-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.
+## ⚡ Getting Started
+The easiest way to run OpenDevin is inside a Docker container. It works best with the most recent version of Docker, `26.0.0`.
+You must be using Linux, Mac OS, or WSL on Windows.
 
-<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 `$(pwd)/workspace` with the path to the code you want OpenDevin to work with.
+To start the app, run these commands, replacing `$(pwd)/workspace` with the directory 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 work with. MUST be an absolute path!
+export WORKSPACE_BASE=$(pwd)/workspace;
+```
 
-# The directory you want OpenDevin to modify. MUST be an absolute path!
-export WORKSPACE_BASE=$(pwd)/workspace
+> [!WARNING]  
+> OpenDevin runs bash commands within a Docker sandbox, so it should not affect your machine. 
+> But your workspace directory will be attached to that sandbox, and files in the directory may be modified or deleted.
 
+```bash
 docker run \
-    -e LLM_API_KEY \
+    -it \
+    --pull=always \
+    -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$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
+    --add-host host.docker.internal:host-gateway \
+    ghcr.io/opendevin/opendevin:0.5
 ```
 
-You'll find opendevin running at `http://localhost:3000`.
+You'll find OpenDevin running at [http://localhost:3000](http://localhost:3000).
 
-If you want to use the (unstable!) bleeding edge, you can use `ghcr.io/opendevin/opendevin:main` as the image.
+## 🚀 Documentation
 
-See [Development.md](Development.md) for instructions on running OpenDevin without Docker.
+To learn more about the project, and for tips on using OpenDevin,
+**check out our [documentation](https://opendevin.github.io/OpenDevin/)**.
 
-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.
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
+There you'll find resources on how to use different LLM providers (like ollama and Anthropic's Claude),
+troubleshooting resources, and advanced configuration options.
 
 ## 🤝 How to Contribute
 
-OpenDevin is a community-driven project, and we welcome contributions from everyone. Whether you're a developer, a researcher, or simply enthusiastic about advancing the field of software engineering with AI, there are many ways to get involved:
+OpenDevin is a community-driven project, and we welcome contributions from everyone.
+Whether you're a developer, a researcher, or simply enthusiastic about advancing the field of
+software engineering with AI, there are many ways to get involved:
 
-- **Code Contributions:** Help us develop the core functionalities, frontend interface, or sandboxing solutions.
+- **Code Contributions:** Help us develop new agents, core functionality, the frontend and other interfaces, or sandboxing solutions.
 - **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in evaluating the models, or suggest improvements.
 - **Feedback and Testing:** Use the OpenDevin toolset, report bugs, suggest features, or provide feedback on usability.
 
-For details, please check [this document](./CONTRIBUTING.md).
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
+For details, please check [CONTRIBUTING.md](./CONTRIBUTING.md).
 
 ## 🤖 Join Our Community
 
-Now we have both Slack workspace for the collaboration on building OpenDevin and Discord server for discussion about anything related, e.g., this project, LLM, agent, etc.
+Whether you're a developer, a researcher, or simply enthusiastic about OpenDevin, we'd love to have you in our community.
+Let's make software engineering better together!
 
-- [Slack workspace](https://join.slack.com/t/opendevin/shared_invite/zt-2etftj1dd-X1fDL2PYIVpsmJZkqEYANw)
-- [Discord server](https://discord.gg/mBuDGRzzES)
+- [Slack workspace](https://join.slack.com/t/opendevin/shared_invite/zt-2ggtwn3k5-PvAA2LUmqGHVZ~XzGq~ILw) - Here we talk about research, architecture, and future development.
+- [Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
 
-If you would love to contribute, feel free to join our community (note that now there is no need to fill in the [form](https://forms.gle/758d5p6Ve8r2nxxq6)). Let's simplify software engineering together!
-
-🐚 **Code less, make more with OpenDevin.**
-
-[![Star History Chart](https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date)](https://star-history.com/#OpenDevin/OpenDevin&Date)
-
-## 🛠️ Built With
-
-OpenDevin is built using a combination of powerful frameworks and libraries, providing a robust foundation for its development. Here are the key technologies used in the project:
-
-![FastAPI](https://img.shields.io/badge/FastAPI-black?style=for-the-badge) ![uvicorn](https://img.shields.io/badge/uvicorn-black?style=for-the-badge) ![LiteLLM](https://img.shields.io/badge/LiteLLM-black?style=for-the-badge) ![Docker](https://img.shields.io/badge/Docker-black?style=for-the-badge) ![Ruff](https://img.shields.io/badge/Ruff-black?style=for-the-badge) ![MyPy](https://img.shields.io/badge/MyPy-black?style=for-the-badge) ![LlamaIndex](https://img.shields.io/badge/LlamaIndex-black?style=for-the-badge) ![React](https://img.shields.io/badge/React-black?style=for-the-badge)
-
-Please note that the selection of these technologies is in progress, and additional technologies may be added or existing ones may be removed as the project evolves. We strive to adopt the most suitable and efficient tools to enhance the capabilities of OpenDevin.
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
+## 📈 Progress
+<p align="center">
+    <a href="https://www.swebench.com/lite.html">
+        <img src="/docs/static/img/results.png" alt="SWE-Bench Lite Score" width="500" height="auto">
     </a>
 </p>
 
+<p align="center">
+  <a href="https://star-history.com/#OpenDevin/OpenDevin&Date">
+    <img src="https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date" width="500" alt="Star History Chart">
+  </a>
+</p>
+
 ## 📜 License
 
 Distributed under the MIT License. See [`LICENSE`](./LICENSE) for more information.
 
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>
-
 [contributors-shield]: https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge
 [contributors-url]: https://github.com/OpenDevin/OpenDevin/graphs/contributors
 [forks-shield]: https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge

agenthub/README.md

@@ -16,16 +16,21 @@ Every agent also has a `self.llm` which it can use to interact with the LLM conf
 See the [LiteLLM docs for `self.llm.completion`](https://docs.litellm.ai/docs/completion).
 
 ## State
+
 The `state` contains:
-* A history of actions taken by the agent, as well as any observations (e.g. file content, command output) from those actions
-* A list of actions/observations that have happened since the most recent step
-* A [`plan`](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/plan.py), which contains the main goal
-  * The agent can add and modify subtasks through the `AddTaskAction` and `ModifyTaskAction`
+
+- A history of actions taken by the agent, as well as any observations (e.g. file content, command output) from those actions
+- A list of actions/observations that have happened since the most recent step
+- A [`root_task`](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/controller/state/task.py), which contains a plan of action
+  - The agent can add and modify subtasks through the `AddTaskAction` and `ModifyTaskAction`
 
 ## Actions
+
 Here is a list of available Actions, which can be returned by `agent.step()`:
+
 - [`CmdRunAction`](../opendevin/action/bash.py) - Runs a command inside a sandboxed terminal
 - [`CmdKillAction`](../opendevin/action/bash.py) - Kills a background command
+- [`IPythonRunCellAction`](../opendevin/action/bash.py) - Execute a block of Python code interactively (in Jupyter notebook) and receives `CmdOutputObservation`. Requires setting up `jupyter` [plugin](../opendevin/sandbox/plugins) as a requirement.
 - [`FileReadAction`](../opendevin/action/fileop.py) - Reads the content of a file
 - [`FileWriteAction`](../opendevin/action/fileop.py) - Writes new content to a file
 - [`BrowseURLAction`](../opendevin/action/browse.py) - Gets the content of a URL
@@ -33,40 +38,51 @@ Here is a list of available Actions, which can be returned by `agent.step()`:
 - [`AddTaskAction`](../opendevin/action/tasks.py) - Adds a subtask to the plan
 - [`ModifyTaskAction`](../opendevin/action/tasks.py) - Changes the state of a subtask
 - [`AgentThinkAction`](../opendevin/action/agent.py) - A no-op that allows the agent to add plaintext to the history (as well as the chat log)
+- [`AgentTalkAction`](../opendevin/action/agent.py) - A no-op that allows the agent to add plaintext to the history and talk to the user.
+- [`AgentFinishAction`](../opendevin/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
+- [`AgentRejectAction`](../opendevin/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
 - [`AgentFinishAction`](../opendevin/action/agent.py) - Stops the control loop, allowing the user to enter a new task
+- [`MessageAction`](../opendevin/action/message.py) - Represents a message from an agent or the user
 
 You can use `action.to_dict()` and `action_from_dict` to serialize and deserialize actions.
 
 ## Observations
+
 There are also several types of Observations. These are typically available in the step following the corresponding Action.
 But they may also appear as a result of asynchronous events (e.g. a message from the user, logs from a command running
 in the background).
 
 Here is a list of available Observations:
+
 - [`CmdOutputObservation`](../opendevin/observation/run.py)
 - [`BrowserOutputObservation`](../opendevin/observation/browse.py)
 - [`FileReadObservation`](../opendevin/observation/files.py)
 - [`FileWriteObservation`](../opendevin/observation/files.py)
-- [`UserMessageObservation`](../opendevin/observation/)
 - [`AgentRecallObservation`](../opendevin/observation/recall.py)
-- [`AgentErrorObservation`](../opendevin/observation/error.py)
+- [`ErrorObservation`](../opendevin/observation/error.py)
+- [`SuccessObservation`](../opendevin/observation/success.py)
 
 You can use `observation.to_dict()` and `observation_from_dict` to serialize and deserialize observations.
 
 ## Interface
+
 Every agent must implement the following methods:
 
 ### `step`
+
 ```
 def step(self, state: "State") -> "Action"
 ```
+
 `step` moves the agent forward one step towards its goal. This probably means
 sending a prompt to the LLM, then parsing the response into an `Action`.
 
 ### `search_memory`
+
 ```
-def search_memory(self, query: str) -> List[str]:
+def search_memory(self, query: str) -> list[str]:
 ```
+
 `search_memory` should return a list of events that match the query. This will be used
 for the `recall` action.
 

agenthub/SWE_agent/__init__.py

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

agenthub/SWE_agent/agent.py

@@ -1,27 +1,27 @@
-from typing import List
-from opendevin.agent import Agent
-from opendevin.llm.llm import LLM
-from opendevin.state import State
-from opendevin.action import (
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.events.action import (
     Action,
-    AgentThinkAction,
     FileReadAction,
     FileWriteAction,
+    MessageAction,
 )
-from opendevin.observation import Observation
+from opendevin.events.serialization.event import event_to_memory
+from opendevin.llm.llm import LLM
 
 from .parser import parse_command
-
 from .prompts import (
-    SYSTEM_MESSAGE,
-    STEP_PROMPT,
+    CONTEXT_PROMPT,
     MEMORY_FORMAT,
     NO_ACTION,
-    CONTEXT_PROMPT
+    STEP_PROMPT,
+    SYSTEM_MESSAGE,
 )
 
 
 class SWEAgent(Agent):
+    VERSION = '1.0'
+    DEPRECATED = True
     """
     An attempt to recreate swe_agent with output parsing, prompting style, and Application Computer Interface (ACI).
 
@@ -32,25 +32,22 @@ class SWEAgent(Agent):
         super().__init__(llm)
         self.memory_window = 4
         self.max_retries = 2
-        self.running_memory: List[str] = []
         self.cur_file: str = ''
         self.cur_line: int = 0
 
-    def _remember(self, action: Action, observation: Observation) -> None:
-        """Agent has a limited memory of the few steps implemented as a queue"""
-        memory = MEMORY_FORMAT(action.to_memory(), observation.to_memory())
-        self.running_memory.append(memory)
-
-    def _think_act(self, messages: List[dict]) -> tuple[Action, str]:
-        resp = self.llm.completion(
+    def _think_act(self, messages: list[dict]) -> tuple[Action, str]:
+        resp = self.llm.do_completion(
             messages=messages,
             temperature=0.05,
         )
         action_resp = resp['choices'][0]['message']['content']
         print(f"\033[1m\033[91m{resp['usage']}\033[0m")
-        print('\n==== RAW OUTPUT ====',
-              f'\033[96m{action_resp}\033[0m',
-              '==== END RAW ====\n', sep='\n')
+        print(
+            '\n==== RAW OUTPUT ====',
+            f'\033[96m{action_resp}\033[0m',
+            '==== END RAW ====\n',
+            sep='\n',
+        )
         return parse_command(action_resp, self.cur_file, self.cur_line)
 
     def _update(self, action: Action) -> None:
@@ -65,30 +62,36 @@ class SWEAgent(Agent):
             2. Perform think-act - prompt model for action and reasoning
             3. Catch errors - ensure model takes action (5 attempts max)
         """
-        for prev_action, obs in state.updated_info:
-            self._remember(prev_action, obs)
+        # retrieve short term memories from state.history, up to memory_window
+        memory_window = min(self.memory_window, len(state.history))
+        running_memory: list[str] = []
+        for prev_action, obs in state.history[-memory_window:]:
+            running_memory.append(
+                MEMORY_FORMAT(event_to_memory(prev_action), event_to_memory(obs))
+            )
 
-        prompt = STEP_PROMPT(
-            state.plan.main_goal,
-            self.cur_file,
-            self.cur_line
-        )
+        goal = state.get_current_user_intent()
 
+        # always in the prompt if they exist: file and line
+        prompt = STEP_PROMPT(goal, self.cur_file, self.cur_line)
+
+        # prepare messages
         msgs = [
             {'content': SYSTEM_MESSAGE, 'role': 'system'},
-            {'content': prompt, 'role': 'user'}
+            {'content': prompt, 'role': 'user'},
         ]
 
-        if len(self.running_memory) > 0:
-            context = CONTEXT_PROMPT(
-                self.running_memory,
-                self.memory_window
-            )
+        # insert memories
+        if len(running_memory) > 0:
+            context = CONTEXT_PROMPT(running_memory, self.memory_window)
             msgs.insert(1, {'content': context, 'role': 'user'})
         # clrs = [''] * (len(msgs)-2) + ['\033[0;36m', '\033[0;35m']
         # print('\n\n'.join([c+m['content']+'\033[0m' for c, m in zip(clrs, msgs)]))
+
+        # send it over
         action, thought = self._think_act(messages=msgs)
 
+        # be robust with malformed responses
         start_msg_len = len(msgs)
         while not action and len(msgs) < self.max_retries + start_msg_len:
             error = NO_ACTION(thought)
@@ -97,16 +100,16 @@ class SWEAgent(Agent):
             action, thought = self._think_act(messages=msgs)
 
         if not action:
-            action = AgentThinkAction(thought)
+            action = MessageAction(thought)
 
         self._update(action)
         self.latest_action = action
         return action
 
-    def search_memory(self, query: str) -> List[str]:
-        return [item for item in self.running_memory if query in item]
+    def search_memory(self, query: str) -> list[str]:
+        # return [item for item in self.running_memory if query in item]
+        raise NotImplementedError('Search_memory not implemented currently')
 
     def reset(self) -> None:
         """Used to reset the agent"""
-        self.running_memory = []
         super().reset()

agenthub/SWE_agent/parser.py

@@ -1,26 +1,26 @@
-from opendevin.action import (
+import re
+
+from opendevin.events.action import (
     Action,
     AgentFinishAction,
+    BrowseURLAction,
     CmdRunAction,
     FileReadAction,
     FileWriteAction,
-    BrowseURLAction,
-    AgentEchoAction,
-    AgentThinkAction,
+    MessageAction,
 )
 
-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
 
-no_open_file_error = AgentEchoAction(
-    'You are not currently in a file. You can use the read command to open a file and then use goto to navigate through it.')
+no_open_file_error = MessageAction(
+    'You are not currently in a file. You can use the read command to open a file and then use goto to navigate through it.'
+)
 
 
 def invalid_error(cmd, docs):
-    return f'''ERROR:
+    return f"""ERROR:
 Invalid command structure for
 ```
 {cmd}
@@ -30,10 +30,12 @@ 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:
+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
@@ -46,7 +48,7 @@ def get_action_from_string(command_string: str, path: str, line: int, thoughts:
         return AgentFinishAction()
 
     elif 'think' == cmd:
-        return AgentThinkAction(' '.join(args))
+        return MessageAction(' '.join(args))
 
     elif 'scroll_up' == cmd:
         if not path:
@@ -68,7 +70,7 @@ def get_action_from_string(command_string: str, path: str, line: int, thoughts:
             end = start + 100
             return FileReadAction(path, start, end, thoughts)
         else:
-            return AgentEchoAction(invalid_error(command_string, 'goto'))
+            return MessageAction(invalid_error(command_string, 'goto'))
 
     elif 'edit' == cmd:
         if not path:
@@ -83,7 +85,7 @@ def get_action_from_string(command_string: str, path: str, line: int, thoughts:
                 change = change[1:-1]
             return FileWriteAction(path, change, start, end, thoughts)
         else:
-            return AgentEchoAction(invalid_error(command_string, 'edit'))
+            return MessageAction(invalid_error(command_string, 'edit'))
 
     elif 'read' == cmd:
         rex = r'^read\s+(\S+)(?:\s+(\d+))?(?:\s+(-?\d+))?$'
@@ -98,7 +100,7 @@ def get_action_from_string(command_string: str, path: str, line: int, thoughts:
 
             return FileReadAction(file, start, end, thoughts)
         else:
-            return AgentEchoAction(invalid_error(command_string, 'read'))
+            return MessageAction(invalid_error(command_string, 'read'))
 
     elif 'write' == cmd:
         rex = r'^write\s+(\S+)\s+(.*?)\s*(\d+)?\s*(-?\d+)?$'
@@ -118,7 +120,7 @@ def get_action_from_string(command_string: str, path: str, line: int, thoughts:
 
             return FileWriteAction(file, content, start, end, thoughts)
         else:
-            return AgentEchoAction(invalid_error(command_string, 'write'))
+            return MessageAction(invalid_error(command_string, 'write'))
 
     elif 'browse' == cmd:
         return BrowseURLAction(args[0].strip())
@@ -129,13 +131,15 @@ def get_action_from_string(command_string: str, path: str, line: int, thoughts:
         if valid:
             return CmdRunAction(command_string)
         else:
-            return AgentEchoAction(f'Invalid command structure for\n ```\n{command_string}\n```.\nTry again using this format:\n{CUSTOM_DOCS}')
+            return MessageAction(
+                f'Invalid command structure for\n ```\n{command_string}\n```.\nTry again using this format:\n{CUSTOM_DOCS}'
+            )
     else:
         # check bash command
         obs = str(CmdRunAction(f'type {cmd}'))
         if obs.split(':')[-1].strip() == 'not found':
             # echo not found error for llm
-            return AgentEchoAction(content=obs)
+            return MessageAction(content=obs)
         else:
             # run valid command
             return CmdRunAction(command_string)
@@ -157,8 +161,7 @@ def parse_command(input_str: str, path: str, line: int):
         command_str = parts[1].strip()
         ind = 2 if len(parts) > 2 else 1
         accompanying_text = ''.join(parts[:-ind]).strip()
-        action = get_action_from_string(
-            command_str, path, line, accompanying_text)
+        action = get_action_from_string(command_str, path, line, accompanying_text)
         if action:
             return action, accompanying_text
     return None, input_str  # used for retry

agenthub/SWE_agent/prompts.py

@@ -1,22 +1,21 @@
-
 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',
     'scroll_down': 'Takes no arguments. This will scroll down and show you the 100 lines below your current lines',
-    'edit <start_line> <end_line> <changes>': 'This will modify lines in the currently open file. use start_line and end_line to designate which lines to change and then write the multiline changes',
+    'edit <start_line> <end_line> <changes>': 'This will modify lines in the currently open file. use start_line and end_line to designate which lines to change and then write the multiline changes. Set end_line to -1 to denote the end of the file',
     'goto <line_num>': 'This will take you directly to a line and show you the 100 lines below it.',
     '<bash_command> <args>': 'You can use any bash command you need (cd, ls, rm, grep, dir, mv, wget, git, zip, etc.) with their arguments included',
     'pip install <package>': 'You can use this to import python packages. Make sure you include the correct package name when using this command.',
     'ls': 'Use the ls command to view all the files in your current directory, this is a good starting point.',
-    'NOT ALLOWED': 'You cannot use interactive commands like python or node'
+    'NOT ALLOWED': 'You cannot use interactive commands like python or node',
 }
 
 COMMAND_USAGE = {
     'exit': 'Usage:\n```\nexit\n```\nExecuted when task is complete',
-    'read': 'Args:\n<file_name> [<start_line>] [<end_line>]\nUsage:\n```\nread file.py\n```\nor\n```\nread example.py <start_line> <end_line>\n```\nShows a given file\'s contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. by default the whole file will be read.',
+    '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.',
@@ -25,8 +24,7 @@ COMMAND_USAGE = {
     'browse': 'Args:\n<url>\nUsage:\n```\nbrowse https://github.com/OpenDevin/OpenDevin\n```\nThis will fetch the Text elements from the given url and show them to you.',
 }
 
-DEFAULT_COMMANDS = '\n'.join(
-    [k + ' - ' + v for k, v in DEFAULT_COMMANDS_DICT.items()])
+DEFAULT_COMMANDS = '\n'.join([k + ' - ' + v for k, v in DEFAULT_COMMANDS_DICT.items()])
 
 # from opendevin.parse_commands import parse_command_file
 # USE parse_command_file(filepath) to get the custom commands
@@ -52,7 +50,7 @@ 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 +67,9 @@ 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.
 
@@ -94,7 +92,7 @@ Notes:
 - To execute multiple commands you should write them down in your thoughts section so you can remember it on the next step and execute them then.
 - The only commands you are not capable of executing are interactive commands like `python` or `node` by themselves.
 - If you think that you have completed the task that has been given to you based on your previous actions and outputs then use ``` exit ``` as the command to let the system know that you are done.
-- DO NOT make any copies of your previous memories those will be provided to you at each step, making copies just wastes time and energy. Think smarter not harder.
+- DO NOT make any copies of your previous memories, those will be provided to you at each step, making copies just wastes time and energy. Think smarter not harder.
 - The write and edit commands requires proper indentation in the content section ex. `write hw.py def hello():\n    print(\'Hello World\')` this is how you would have to format your write command.
     - The white spaces matter as the code changes will be added to the code so they must have proper syntax.
 
@@ -113,20 +111,21 @@ Action:
 [ END FORMAT ]
 
 Do not provide anything extra just your thought and action.
-'''
+"""
 
-SYSTEM_MESSAGE = f'''SYSTEM INFO:
-You am an autonomous coding agent, here to provide solutions for coding issues.
-You have been designed to assist you with a wide range of programming tasks, from code editing and debugging to testing and deployment.
+SYSTEM_MESSAGE = f"""SYSTEM INFO:
+You are an autonomous coding agent, here to provide solutions for coding issues.
+You have been designed to assist with a wide range of programming tasks, from code editing and debugging to testing and deployment.
 You have access to a variety of tools and commands that you can use to help you solve problems efficiently.
 
 {GENERAL_GUIDELINES}
 
 {DOCUMENTATION}
-'''.strip()
+""".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 +140,21 @@ 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}
@@ -168,11 +168,12 @@ 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] = []):
+def unpack_dict(data: dict, restrict: list[str] | None = None):
     lines = []
+    restrict = [] if restrict is None else restrict
     for key, value in data.items():
         if key in restrict:
             continue
@@ -185,13 +186,14 @@ 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

@@ -1,28 +1,46 @@
-from .micro.registry import all_microagents
-from .micro.agent import MicroAgent
-from opendevin.agent import Agent
-
 from dotenv import load_dotenv
+
+from opendevin.controller.agent import Agent
+
+from .micro.agent import MicroAgent
+from .micro.registry import all_microagents
+
 load_dotenv()
 
 
-# Import agents after environment variables are loaded
-from . import monologue_agent  # noqa: E402
-from . import codeact_agent    # noqa: E402
-from . import planner_agent    # noqa: E402
-from . import SWE_agent        # noqa: E402
-from . import delegator_agent  # noqa: E402
+from . import (  # noqa: E402
+    SWE_agent,
+    browsing_agent,
+    codeact_agent,
+    codeact_swe_agent,
+    delegator_agent,
+    dummy_agent,
+    monologue_agent,
+    planner_agent,
+)
 
-__all__ = ['monologue_agent', 'codeact_agent',
-           'planner_agent', 'SWE_agent', 'delegator_agent']
+__all__ = [
+    'monologue_agent',
+    'codeact_agent',
+    'codeact_swe_agent',
+    'planner_agent',
+    'SWE_agent',
+    'delegator_agent',
+    'dummy_agent',
+    'browsing_agent',
+]
 
 for agent in all_microagents.values():
     name = agent['name']
     prompt = agent['prompt']
 
-    anon_class = type(name, (MicroAgent,), {
-        'prompt': prompt,
-        'agent_definition': agent,
-    })
+    anon_class = type(
+        name,
+        (MicroAgent,),
+        {
+            'prompt': prompt,
+            'agent_definition': agent,
+        },
+    )
 
     Agent.register(name, anon_class)

agenthub/browsing_agent/README.md

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

agenthub/browsing_agent/__init__.py

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

agenthub/browsing_agent/browsing_agent.py

@@ -0,0 +1,167 @@
+import ast
+
+from browsergym.core.action.highlevel import HighLevelActionSet
+from browsergym.utils.obs import flatten_axtree_to_str
+
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.core.logger import opendevin_logger as logger
+from opendevin.events.action import (
+    Action,
+    AgentFinishAction,
+    BrowseInteractiveAction,
+    MessageAction,
+)
+from opendevin.events.observation import BrowserOutputObservation
+from opendevin.llm.llm import LLM
+from opendevin.runtime.plugins import (
+    PluginRequirement,
+)
+
+
+def parse_response(response: str) -> Action:
+    if '```' not in response:
+        # unexpected response format, message back to user
+        return MessageAction(response)
+    thought = response.split('```')[0].strip()
+    action_str = response.split('```')[1].strip()
+    # handle send message to user function call in BrowserGym
+    for sub_action in action_str.split('\n'):
+        if 'send_msg_to_user(' in sub_action:
+            tree = ast.parse(sub_action)
+            args = tree.body[0].value.args  # type: ignore
+            return MessageAction(args[0].value)
+
+    return BrowseInteractiveAction(browser_actions=action_str, thought=thought)
+
+
+class BrowsingAgent(Agent):
+    VERSION = '1.0'
+    """
+    An agent that interacts with the browser.
+    """
+
+    sandbox_plugins: list[PluginRequirement] = []
+
+    def __init__(
+        self,
+        llm: LLM,
+    ) -> None:
+        """
+        Initializes a new instance of the BrowsingAgent class.
+
+        Parameters:
+        - llm (LLM): The llm to be used by this agent
+        """
+        super().__init__(llm)
+        self.action_space = HighLevelActionSet(
+            # see https://github.com/ServiceNow/BrowserGym/blob/main/core/src/browsergym/core/action/highlevel.py for more details
+            subsets=[
+                'chat',
+                'bid',
+                'nav',
+            ],  # define a configurable action space, with chat functionality, web navigation, and webpage grounding using accessibility tree and HTML.
+            strict=False,  # less strict on the parsing of the actions
+            multiaction=True,  # enable to agent to take multiple actions at once
+        )
+
+        self.reset()
+
+    def reset(self) -> None:
+        """
+        Resets the Browsing Agent.
+        """
+        super().reset()
+        self.cost_accumulator = 0
+
+    def step(self, state: State) -> Action:
+        """
+        Performs one step using the Browsing Agent.
+        This includes gathering information on previous steps and prompting the model to make a browsing command to execute.
+
+        Parameters:
+        - state (State): used to get updated info
+
+        Returns:
+        - BrowseInteractiveAction(browsergym_command) - BrowserGym commands to run
+        - MessageAction(content) - Message action to run (e.g. ask for clarification)
+        - AgentFinishAction() - end the interaction
+        """
+        goal = state.get_current_user_intent()
+        messages = []
+        prev_actions = ''
+        cur_axtree_txt = ''
+        error_prefix = ''
+        last_obs = None
+        for prev_action, obs in state.history:
+            if isinstance(prev_action, BrowseInteractiveAction):
+                prev_actions += f'{prev_action.browser_actions}\n'
+                last_obs = obs
+            elif (
+                isinstance(prev_action, MessageAction) and prev_action.source != 'user'
+            ):
+                # agent has responded, task finish.
+                return AgentFinishAction()
+
+        if isinstance(last_obs, BrowserOutputObservation):
+            if last_obs.error:
+                # add error recovery prompt prefix
+                error_prefix = f'IMPORTANT! Last action is incorrect:\n{last_obs.last_browser_action}\nThink again with the current observation of the page.\n'
+            cur_axtree_txt = flatten_axtree_to_str(last_obs.axtree_object)
+
+        system_msg = f"""\
+# Instructions
+Review the current state of the page and all other information to find the best
+possible next action to accomplish your goal. Your answer will be interpreted
+and executed by a program, make sure to follow the formatting instructions.
+
+# Goal:
+{goal}
+
+# Action Space
+{self.action_space.describe(with_long_description=False, with_examples=True)}
+"""
+
+        messages.append({'role': 'system', 'content': system_msg})
+
+        prompt = f"""\
+{error_prefix}
+
+# Current Accessibility Tree:
+{cur_axtree_txt}
+
+# Previous Actions
+{prev_actions}
+
+Here is an example with chain of thought of a valid action when clicking on a button:
+"
+In order to accomplish my goal I need to click on the button with bid 12
+```click("12")```
+"
+""".strip()
+        messages.append({'role': 'user', 'content': prompt})
+        response = self.llm.completion(
+            messages=messages,
+            temperature=0.0,
+        )
+        self.log_cost(response)
+        action_resp = response['choices'][0]['message']['content']
+        logger.info(prompt)
+        logger.info(action_resp)
+        return parse_response(action_resp)
+
+    def search_memory(self, query: str) -> list[str]:
+        raise NotImplementedError('Implement this abstract method')
+
+    def log_cost(self, response):
+        # TODO: refactor to unified cost tracking
+        try:
+            cur_cost = self.llm.completion_cost(response)
+        except Exception:
+            cur_cost = 0
+        self.cost_accumulator += cur_cost
+        logger.info(
+            'Cost: %.2f USD | Accumulated Cost: %.2f USD',
+            cur_cost,
+            self.cost_accumulator,
+        )

agenthub/browsing_agent/prompt.py

@@ -0,0 +1,785 @@
+import abc
+import difflib
+import logging
+import platform
+from copy import deepcopy
+from dataclasses import asdict, dataclass
+from textwrap import dedent
+from typing import Literal, Union
+from warnings import warn
+
+from browsergym.core.action.base import AbstractActionSet
+from browsergym.core.action.highlevel import HighLevelActionSet
+from browsergym.core.action.python import PythonActionSet
+
+from opendevin.runtime.browser.browser_env import BrowserEnv
+
+from .utils import (
+    ParseError,
+    parse_html_tags_raise,
+)
+
+
+@dataclass
+class Flags:
+    use_html: bool = True
+    use_ax_tree: bool = False
+    drop_ax_tree_first: bool = True  # This flag is no longer active TODO delete
+    use_thinking: bool = False
+    use_error_logs: bool = False
+    use_past_error_logs: bool = False
+    use_history: bool = False
+    use_action_history: bool = False
+    use_memory: bool = False
+    use_diff: bool = False
+    html_type: str = 'pruned_html'
+    use_concrete_example: bool = True
+    use_abstract_example: bool = False
+    multi_actions: bool = False
+    action_space: Literal[
+        'python', 'bid', 'coord', 'bid+coord', 'bid+nav', 'coord+nav', 'bid+coord+nav'
+    ] = 'bid'
+    is_strict: bool = False
+    # This flag will be automatically disabled `if not chat_model_args.has_vision()`
+    use_screenshot: bool = True
+    enable_chat: bool = False
+    max_prompt_tokens: int = 100_000
+    extract_visible_tag: bool = False
+    extract_coords: Literal['False', 'center', 'box'] = 'False'
+    extract_visible_elements_only: bool = False
+    demo_mode: Literal['off', 'default', 'only_visible_elements'] = 'off'
+
+    def copy(self):
+        return deepcopy(self)
+
+    def asdict(self):
+        """Helper for JSON serializble requirement."""
+        return asdict(self)
+
+    @classmethod
+    def from_dict(self, flags_dict):
+        """Helper for JSON serializble requirement."""
+        if isinstance(flags_dict, Flags):
+            return flags_dict
+
+        if not isinstance(flags_dict, dict):
+            raise ValueError(
+                f'Unregcognized type for flags_dict of type {type(flags_dict)}.'
+            )
+        return Flags(**flags_dict)
+
+
+class PromptElement:
+    """Base class for all prompt elements. Prompt elements can be hidden.
+
+    Prompt elements are used to build the prompt. Use flags to control which
+    prompt elements are visible. We use class attributes as a convenient way
+    to implement static prompts, but feel free to override them with instance
+    attributes or @property decorator."""
+
+    _prompt = ''
+    _abstract_ex = ''
+    _concrete_ex = ''
+
+    def __init__(self, visible: bool = True) -> None:
+        """Prompt element that can be hidden.
+
+        Parameters
+        ----------
+        visible : bool, optional
+            Whether the prompt element should be visible, by default True. Can
+            be a callable that returns a bool. This is useful when a specific
+            flag changes during a shrink iteration.
+        """
+        self._visible = visible
+
+    @property
+    def prompt(self):
+        """Avoid overriding this method. Override _prompt instead."""
+        return self._hide(self._prompt)
+
+    @property
+    def abstract_ex(self):
+        """Useful when this prompt element is requesting an answer from the llm.
+        Provide an abstract example of the answer here. See Memory for an
+        example.
+
+        Avoid overriding this method. Override _abstract_ex instead
+        """
+        return self._hide(self._abstract_ex)
+
+    @property
+    def concrete_ex(self):
+        """Useful when this prompt element is requesting an answer from the llm.
+        Provide a concrete example of the answer here. See Memory for an
+        example.
+
+        Avoid overriding this method. Override _concrete_ex instead
+        """
+        return self._hide(self._concrete_ex)
+
+    @property
+    def is_visible(self):
+        """Handle the case where visible is a callable."""
+        visible = self._visible
+        if callable(visible):
+            visible = visible()
+        return visible
+
+    def _hide(self, value):
+        """Return value if visible is True, else return empty string."""
+        if self.is_visible:
+            return value
+        else:
+            return ''
+
+    def _parse_answer(self, text_answer) -> dict:
+        if self.is_visible:
+            return self._parse_answer(text_answer)
+        else:
+            return {}
+
+
+class Shrinkable(PromptElement, abc.ABC):
+    @abc.abstractmethod
+    def shrink(self) -> None:
+        """Implement shrinking of this prompt element.
+
+        You need to recursively call all shrinkable elements that are part of
+        this prompt. You can also implement a shriking startegy for this prompt.
+        Shrinking is can be called multiple times to progressively shrink the
+        prompt until it fits max_tokens. Default max shrink iterations is 20.
+        """
+        pass
+
+
+class Truncater(Shrinkable):
+    """A prompt element that can be truncated to fit the context length of the LLM.
+    Of course, it will be great that we never have to use the functionality here to `shrink()` the prompt.
+    Extend this class for prompt elements that can be truncated. Usually long observations such as AxTree or HTML.
+    """
+
+    def __init__(self, visible, shrink_speed=0.3, start_truncate_iteration=10):
+        super().__init__(visible=visible)
+        self.shrink_speed = shrink_speed  # the percentage shrinked in each iteration
+        self.start_truncate_iteration = (
+            start_truncate_iteration  # the iteration to start truncating
+        )
+        self.shrink_calls = 0
+        self.deleted_lines = 0
+
+    def shrink(self) -> None:
+        if self.is_visible and self.shrink_calls >= self.start_truncate_iteration:
+            # remove the fraction of _prompt
+            lines = self._prompt.splitlines()
+            new_line_count = int(len(lines) * (1 - self.shrink_speed))
+            self.deleted_lines += len(lines) - new_line_count
+            self._prompt = '\n'.join(lines[:new_line_count])
+            self._prompt += (
+                f'\n... Deleted {self.deleted_lines} lines to reduce prompt size.'
+            )
+
+        self.shrink_calls += 1
+
+
+def fit_tokens(
+    shrinkable: Shrinkable,
+    max_prompt_chars=None,
+    max_iterations=20,
+):
+    """Shrink a prompt element until it fits max_tokens.
+
+    Parameters
+    ----------
+    shrinkable : Shrinkable
+        The prompt element to shrink.
+    max_prompt_chars : int
+        The maximum number of chars allowed.
+    max_iterations : int, optional
+        The maximum number of shrink iterations, by default 20.
+    model_name : str, optional
+        The name of the model used when tokenizing.
+
+    Returns
+    -------
+    str : the prompt after shrinking.
+    """
+
+    if max_prompt_chars is None:
+        return shrinkable.prompt
+
+    for _ in range(max_iterations):
+        prompt = shrinkable.prompt
+        if isinstance(prompt, str):
+            prompt_str = prompt
+        elif isinstance(prompt, list):
+            prompt_str = '\n'.join([p['text'] for p in prompt if p['type'] == 'text'])
+        else:
+            raise ValueError(f'Unrecognized type for prompt: {type(prompt)}')
+        n_chars = len(prompt_str)
+        if n_chars <= max_prompt_chars:
+            return prompt
+        shrinkable.shrink()
+
+    logging.info(
+        dedent(
+            f"""\
+            After {max_iterations} shrink iterations, the prompt is still
+            {len(prompt_str)} chars (greater than {max_prompt_chars}). Returning the prompt as is."""
+        )
+    )
+    return prompt
+
+
+class HTML(Truncater):
+    def __init__(self, html, visible: bool = True, prefix='') -> None:
+        super().__init__(visible=visible, start_truncate_iteration=5)
+        self._prompt = f'\n{prefix}HTML:\n{html}\n'
+
+
+class AXTree(Truncater):
+    def __init__(
+        self, ax_tree, visible: bool = True, coord_type=None, prefix=''
+    ) -> None:
+        super().__init__(visible=visible, start_truncate_iteration=10)
+        if coord_type == 'center':
+            coord_note = """\
+Note: center coordinates are provided in parenthesis and are
+  relative to the top left corner of the page.\n\n"""
+        elif coord_type == 'box':
+            coord_note = """\
+Note: bounding box of each object are provided in parenthesis and are
+  relative to the top left corner of the page.\n\n"""
+        else:
+            coord_note = ''
+        self._prompt = f'\n{prefix}AXTree:\n{coord_note}{ax_tree}\n'
+
+
+class Error(PromptElement):
+    def __init__(self, error, visible: bool = True, prefix='') -> None:
+        super().__init__(visible=visible)
+        self._prompt = f'\n{prefix}Error from previous action:\n{error}\n'
+
+
+class Observation(Shrinkable):
+    """Observation of the current step.
+
+    Contains the html, the accessibility tree and the error logs.
+    """
+
+    def __init__(self, obs, flags: Flags) -> None:
+        super().__init__()
+        self.flags = flags
+        self.obs = obs
+        self.html = HTML(obs[flags.html_type], visible=flags.use_html, prefix='## ')
+        self.ax_tree = AXTree(
+            obs['axtree_txt'],
+            visible=flags.use_ax_tree,
+            coord_type=flags.extract_coords,
+            prefix='## ',
+        )
+        self.error = Error(
+            obs['last_action_error'],
+            visible=flags.use_error_logs and obs['last_action_error'],
+            prefix='## ',
+        )
+
+    def shrink(self):
+        self.ax_tree.shrink()
+        self.html.shrink()
+
+    @property
+    def _prompt(self) -> str:  # type: ignore
+        return f'\n# Observation of current step:\n{self.html.prompt}{self.ax_tree.prompt}{self.error.prompt}\n\n'
+
+    def add_screenshot(self, prompt):
+        if self.flags.use_screenshot:
+            if isinstance(prompt, str):
+                prompt = [{'type': 'text', 'text': prompt}]
+            img_url = BrowserEnv.image_to_jpg_base64_url(
+                self.obs['screenshot'], add_data_prefix=True
+            )
+            prompt.append({'type': 'image_url', 'image_url': img_url})
+
+        return prompt
+
+
+class MacNote(PromptElement):
+    def __init__(self) -> None:
+        super().__init__(visible=platform.system() == 'Darwin')
+        self._prompt = '\nNote: you are on mac so you should use Meta instead of Control for Control+C etc.\n'
+
+
+class BeCautious(PromptElement):
+    def __init__(self, visible: bool = True) -> None:
+        super().__init__(visible=visible)
+        self._prompt = """\
+\nBe very cautious. Avoid submitting anything before verifying the effect of your
+actions. Take the time to explore the effect of safe actions first. For example
+you can fill a few elements of a form, but don't click submit before verifying
+that everything was filled correctly.\n"""
+
+
+class GoalInstructions(PromptElement):
+    def __init__(self, goal, visible: bool = True) -> None:
+        super().__init__(visible)
+        self._prompt = f"""\
+# Instructions
+Review the current state of the page and all other information to find the best
+possible next action to accomplish your goal. Your answer will be interpreted
+and executed by a program, make sure to follow the formatting instructions.
+
+## Goal:
+{goal}
+"""
+
+
+class ChatInstructions(PromptElement):
+    def __init__(self, chat_messages, visible: bool = True) -> None:
+        super().__init__(visible)
+        self._prompt = """\
+# Instructions
+
+You are a UI Assistant, your goal is to help the user perform tasks using a web browser. You can
+communicate with the user via a chat, in which the user gives you instructions and in which you
+can send back messages. You have access to a web browser that both you and the user can see,
+and with which only you can interact via specific commands.
+
+Review the instructions from the user, the current state of the page and all other information
+to find the best possible next action to accomplish your goal. Your answer will be interpreted
+and executed by a program, make sure to follow the formatting instructions.
+
+## Chat messages:
+
+"""
+        self._prompt += '\n'.join(
+            [
+                f"""\
+ - [{msg['role']}] {msg['message']}"""
+                for msg in chat_messages
+            ]
+        )
+
+
+class SystemPrompt(PromptElement):
+    _prompt = """\
+You are an agent trying to solve a web task based on the content of the page and
+a user instructions. You can interact with the page and explore. Each time you
+submit an action it will be sent to the browser and you will receive a new page."""
+
+
+class MainPrompt(Shrinkable):
+    def __init__(
+        self,
+        obs_history,
+        actions,
+        memories,
+        thoughts,
+        flags: Flags,
+    ) -> None:
+        super().__init__()
+        self.flags = flags
+        self.history = History(obs_history, actions, memories, thoughts, flags)
+        if self.flags.enable_chat:
+            self.instructions: Union[ChatInstructions, GoalInstructions] = (
+                ChatInstructions(obs_history[-1]['chat_messages'])
+            )
+        else:
+            if (
+                'chat_messages' in obs_history[-1]
+                and sum(
+                    [msg['role'] == 'user' for msg in obs_history[-1]['chat_messages']]
+                )
+                > 1
+            ):
+                logging.warning(
+                    'Agent is in goal mode, but multiple user messages are present in the chat. Consider switching to `enable_chat=True`.'
+                )
+            self.instructions = GoalInstructions(obs_history[-1]['goal'])
+
+        self.obs = Observation(obs_history[-1], self.flags)
+        self.action_space = ActionSpace(self.flags)
+
+        self.think = Think(visible=flags.use_thinking)
+        self.memory = Memory(visible=flags.use_memory)
+
+    @property
+    def _prompt(self) -> str:  # type: ignore
+        prompt = f"""\
+{self.instructions.prompt}\
+{self.obs.prompt}\
+{self.history.prompt}\
+{self.action_space.prompt}\
+{self.think.prompt}\
+{self.memory.prompt}\
+"""
+
+        if self.flags.use_abstract_example:
+            prompt += f"""
+# Abstract Example
+
+Here is an abstract version of the answer with description of the content of
+each tag. Make sure you follow this structure, but replace the content with your
+answer:
+{self.think.abstract_ex}\
+{self.memory.abstract_ex}\
+{self.action_space.abstract_ex}\
+"""
+
+        if self.flags.use_concrete_example:
+            prompt += f"""
+# Concrete Example
+
+Here is a concrete example of how to format your answer.
+Make sure to follow the template with proper tags:
+{self.think.concrete_ex}\
+{self.memory.concrete_ex}\
+{self.action_space.concrete_ex}\
+"""
+        return self.obs.add_screenshot(prompt)
+
+    def shrink(self):
+        self.history.shrink()
+        self.obs.shrink()
+
+    def _parse_answer(self, text_answer):
+        ans_dict = {}
+        ans_dict.update(self.think._parse_answer(text_answer))
+        ans_dict.update(self.memory._parse_answer(text_answer))
+        ans_dict.update(self.action_space._parse_answer(text_answer))
+        return ans_dict
+
+
+class ActionSpace(PromptElement):
+    def __init__(self, flags: Flags) -> None:
+        super().__init__()
+        self.flags = flags
+        self.action_space = _get_action_space(flags)
+
+        self._prompt = (
+            f'# Action space:\n{self.action_space.describe()}{MacNote().prompt}\n'
+        )
+        self._abstract_ex = f"""
+<action>
+{self.action_space.example_action(abstract=True)}
+</action>
+"""
+        self._concrete_ex = f"""
+<action>
+{self.action_space.example_action(abstract=False)}
+</action>
+"""
+
+    def _parse_answer(self, text_answer):
+        ans_dict = parse_html_tags_raise(
+            text_answer, keys=['action'], merge_multiple=True
+        )
+
+        try:
+            # just check if action can be mapped to python code but keep action as is
+            # the environment will be responsible for mapping it to python
+            self.action_space.to_python_code(ans_dict['action'])
+        except Exception as e:
+            raise ParseError(
+                f'Error while parsing action\n: {e}\n'
+                'Make sure your answer is restricted to the allowed actions.'
+            )
+
+        return ans_dict
+
+
+def _get_action_space(flags: Flags) -> AbstractActionSet:
+    match flags.action_space:
+        case 'python':
+            action_space = PythonActionSet(strict=flags.is_strict)
+            if flags.multi_actions:
+                warn(
+                    f'Flag action_space={repr(flags.action_space)} incompatible with multi_actions={repr(flags.multi_actions)}.'
+                )
+            if flags.demo_mode != 'off':
+                warn(
+                    f'Flag action_space={repr(flags.action_space)} incompatible with demo_mode={repr(flags.demo_mode)}.'
+                )
+            return action_space
+        case 'bid':
+            action_subsets = ['chat', 'bid']
+        case 'coord':
+            action_subsets = ['chat', 'coord']
+        case 'bid+coord':
+            action_subsets = ['chat', 'bid', 'coord']
+        case 'bid+nav':
+            action_subsets = ['chat', 'bid', 'nav']
+        case 'coord+nav':
+            action_subsets = ['chat', 'coord', 'nav']
+        case 'bid+coord+nav':
+            action_subsets = ['chat', 'bid', 'coord', 'nav']
+        case _:
+            raise NotImplementedError(
+                f'Unknown action_space {repr(flags.action_space)}'
+            )
+
+    action_space = HighLevelActionSet(
+        subsets=action_subsets,
+        multiaction=flags.multi_actions,
+        strict=flags.is_strict,
+        demo_mode=flags.demo_mode,
+    )
+
+    return action_space
+
+
+class Memory(PromptElement):
+    _prompt = ''  # provided in the abstract and concrete examples
+
+    _abstract_ex = """
+<memory>
+Write down anything you need to remember for next steps. You will be presented
+with the list of previous memories and past actions.
+</memory>
+"""
+
+    _concrete_ex = """
+<memory>
+I clicked on bid 32 to activate tab 2. The accessibility tree should mention
+focusable for elements of the form at next step.
+</memory>
+"""
+
+    def _parse_answer(self, text_answer):
+        return parse_html_tags_raise(
+            text_answer, optional_keys=['memory'], merge_multiple=True
+        )
+
+
+class Think(PromptElement):
+    _prompt = ''
+
+    _abstract_ex = """
+<think>
+Think step by step. If you need to make calculations such as coordinates, write them here. Describe the effect
+that your previous action had on the current content of the page.
+</think>
+"""
+    _concrete_ex = """
+<think>
+My memory says that I filled the first name and last name, but I can't see any
+content in the form. I need to explore different ways to fill the form. Perhaps
+the form is not visible yet or some fields are disabled. I need to replan.
+</think>
+"""
+
+    def _parse_answer(self, text_answer):
+        return parse_html_tags_raise(
+            text_answer, optional_keys=['think'], merge_multiple=True
+        )
+
+
+def diff(previous, new):
+    """Return a string showing the difference between original and new.
+
+    If the difference is above diff_threshold, return the diff string."""
+
+    if previous == new:
+        return 'Identical', []
+
+    if len(previous) == 0 or previous is None:
+        return 'previous is empty', []
+
+    diff_gen = difflib.ndiff(previous.splitlines(), new.splitlines())
+
+    diff_lines = []
+    plus_count = 0
+    minus_count = 0
+    for line in diff_gen:
+        if line.strip().startswith('+'):
+            diff_lines.append(line)
+            plus_count += 1
+        elif line.strip().startswith('-'):
+            diff_lines.append(line)
+            minus_count += 1
+        else:
+            continue
+
+    header = f'{plus_count} lines added and {minus_count} lines removed:'
+
+    return header, diff_lines
+
+
+class Diff(Shrinkable):
+    def __init__(
+        self, previous, new, prefix='', max_line_diff=20, shrink_speed=2, visible=True
+    ) -> None:
+        super().__init__(visible=visible)
+        self.max_line_diff = max_line_diff
+        self.header, self.diff_lines = diff(previous, new)
+        self.shrink_speed = shrink_speed
+        self.prefix = prefix
+
+    def shrink(self):
+        self.max_line_diff -= self.shrink_speed
+        self.max_line_diff = max(1, self.max_line_diff)
+
+    @property
+    def _prompt(self) -> str:  # type: ignore
+        diff_str = '\n'.join(self.diff_lines[: self.max_line_diff])
+        if len(self.diff_lines) > self.max_line_diff:
+            original_count = len(self.diff_lines)
+            diff_str = f'{diff_str}\nDiff truncated, {original_count - self.max_line_diff} changes now shown.'
+        return f'{self.prefix}{self.header}\n{diff_str}\n'
+
+
+class HistoryStep(Shrinkable):
+    def __init__(
+        self, previous_obs, current_obs, action, memory, flags: Flags, shrink_speed=1
+    ) -> None:
+        super().__init__()
+        self.html_diff = Diff(
+            previous_obs[flags.html_type],
+            current_obs[flags.html_type],
+            prefix='\n### HTML diff:\n',
+            shrink_speed=shrink_speed,
+            visible=lambda: flags.use_html and flags.use_diff,
+        )
+        self.ax_tree_diff = Diff(
+            previous_obs['axtree_txt'],
+            current_obs['axtree_txt'],
+            prefix='\n### Accessibility tree diff:\n',
+            shrink_speed=shrink_speed,
+            visible=lambda: flags.use_ax_tree and flags.use_diff,
+        )
+        self.error = Error(
+            current_obs['last_action_error'],
+            visible=(
+                flags.use_error_logs
+                and current_obs['last_action_error']
+                and flags.use_past_error_logs
+            ),
+            prefix='### ',
+        )
+        self.shrink_speed = shrink_speed
+        self.action = action
+        self.memory = memory
+        self.flags = flags
+
+    def shrink(self):
+        super().shrink()
+        self.html_diff.shrink()
+        self.ax_tree_diff.shrink()
+
+    @property
+    def _prompt(self) -> str:  # type: ignore
+        prompt = ''
+
+        if self.flags.use_action_history:
+            prompt += f'\n### Action:\n{self.action}\n'
+
+        prompt += (
+            f'{self.error.prompt}{self.html_diff.prompt}{self.ax_tree_diff.prompt}'
+        )
+
+        if self.flags.use_memory and self.memory is not None:
+            prompt += f'\n### Memory:\n{self.memory}\n'
+
+        return prompt
+
+
+class History(Shrinkable):
+    def __init__(
+        self, history_obs, actions, memories, thoughts, flags: Flags, shrink_speed=1
+    ) -> None:
+        super().__init__(visible=flags.use_history)
+        assert len(history_obs) == len(actions) + 1
+        assert len(history_obs) == len(memories) + 1
+
+        self.shrink_speed = shrink_speed
+        self.history_steps: list[HistoryStep] = []
+
+        for i in range(1, len(history_obs)):
+            self.history_steps.append(
+                HistoryStep(
+                    history_obs[i - 1],
+                    history_obs[i],
+                    actions[i - 1],
+                    memories[i - 1],
+                    flags,
+                )
+            )
+
+    def shrink(self):
+        """Shrink individual steps"""
+        # TODO set the shrink speed of older steps to be higher
+        super().shrink()
+        for step in self.history_steps:
+            step.shrink()
+
+    @property
+    def _prompt(self):
+        prompts = ['# History of interaction with the task:\n']
+        for i, step in enumerate(self.history_steps):
+            prompts.append(f'## step {i}')
+            prompts.append(step.prompt)
+        return '\n'.join(prompts) + '\n'
+
+
+if __name__ == '__main__':
+    html_template = """
+    <html>
+    <body>
+    <div>
+    Hello World.
+    Step {}.
+    </div>
+    </body>
+    </html>
+    """
+
+    OBS_HISTORY = [
+        {
+            'goal': 'do this and that',
+            'pruned_html': html_template.format(1),
+            'axtree_txt': '[1] Click me',
+            'last_action_error': '',
+        },
+        {
+            'goal': 'do this and that',
+            'pruned_html': html_template.format(2),
+            'axtree_txt': '[1] Click me',
+            'last_action_error': '',
+        },
+        {
+            'goal': 'do this and that',
+            'pruned_html': html_template.format(3),
+            'axtree_txt': '[1] Click me',
+            'last_action_error': 'Hey, there is an error now',
+        },
+    ]
+    ACTIONS = ["click('41')", "click('42')"]
+    MEMORIES = ['memory A', 'memory B']
+    THOUGHTS = ['thought A', 'thought B']
+
+    flags = Flags(
+        use_html=True,
+        use_ax_tree=True,
+        use_thinking=True,
+        use_error_logs=True,
+        use_past_error_logs=True,
+        use_history=True,
+        use_action_history=True,
+        use_memory=True,
+        use_diff=True,
+        html_type='pruned_html',
+        use_concrete_example=True,
+        use_abstract_example=True,
+        use_screenshot=False,
+        multi_actions=True,
+    )
+
+    print(
+        MainPrompt(
+            obs_history=OBS_HISTORY,
+            actions=ACTIONS,
+            memories=MEMORIES,
+            thoughts=THOUGHTS,
+            flags=flags,
+        ).prompt
+    )

agenthub/browsing_agent/utils.py

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

agenthub/codeact_agent/README.md

@@ -1,23 +1,29 @@
-# CodeAct-based Agent Framework
+# CodeAct Agent Framework
 
-This folder implements the [CodeAct idea](https://arxiv.org/abs/2402.13463) that relies on LLM to autonomously perform actions in a Bash shell. It requires more from the LLM itself: LLM needs to be capable enough to do all the stuff autonomously, instead of stuck in an infinite loop.
+This folder implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.01030), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a unified **code** action space for both *simplicity* and *performance* (see paper for more details).
 
-**NOTE: This agent is still highly experimental and under active development to reach the capability described in the original paper & [repo](https://github.com/xingyaoww/code-act).**
+The conceptual idea is illustrated below. At each turn, the agent can:
 
-<video src="https://github.com/xingyaoww/code-act/assets/38853559/62c80ada-62ce-447e-811c-fc801dd4beac"> </video>
-*Demo of the expected capability - work-in-progress.*
+1. **Converse**: Communicate with humans in natural language to ask for clarification, confirmation, etc.
+2. **CodeAct**: Choose to perform the task by executing code
+   - Execute any valid Linux `bash` command
+   - Execute any valid `Python` code with [an interactive Python interpreter](https://ipython.org/). This is simulated through `bash` command, see plugin system below for more details.
 
-```bash
-mkdir workspace
-PYTHONPATH=`pwd`:$PYTHONPATH python3 opendevin/main.py -d ./workspace -c CodeActAgent -t "Please write a flask app that returns 'Hello, World\!' at the root URL, then start the app on port 5000. python3 has already been installed for you."
-```
+![image](https://github.com/OpenDevin/OpenDevin/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
 
-Example: prompts `gpt-4-0125-preview` to write a flask server, install `flask` library, and start the server.
+## Plugin System
 
-<img width="951" alt="image" src="https://github.com/OpenDevin/OpenDevin/assets/38853559/325c3115-a343-4cc5-a92b-f1e5d552a077">
+To make the CodeAct agent more powerful with only access to `bash` action space, CodeAct agent leverages OpenDevin's plugin system:
+- [Jupyter plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/jupyter): for IPython execution via bash command
+- [SWE-agent tool plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/swe_agent_commands): Powerful bash command line tools for software development tasks introduced by [swe-agent](https://github.com/princeton-nlp/swe-agent).
 
-<img width="957" alt="image" src="https://github.com/OpenDevin/OpenDevin/assets/38853559/68ad10c1-744a-4e9d-bb29-0f163d665a0a">
+## Demo
 
-Most of the things are working as expected, except at the end, the model did not follow the instruction to stop the interaction by outputting `<execute> exit </execute>` as instructed.
+https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
 
-**TODO**: This should be fixable by either (1) including a complete in-context example like [this](https://github.com/xingyaoww/mint-bench/blob/main/mint/tasks/in_context_examples/reasoning/with_tool.txt), OR (2) collect some interaction data like this and fine-tune a model (like [this](https://github.com/xingyaoww/code-act), a more complex route).
+*Example of CodeActAgent with `gpt-4-turbo-2024-04-09` performing a data science task (linear regression)*
+
+## Work-in-progress & Next step
+
+[] Support web-browsing
+[] Complete the workflow for CodeAct agent to submit Github PRs

agenthub/codeact_agent/__init__.py

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

agenthub/codeact_agent/codeact_agent.py

@@ -1,64 +1,171 @@
 import re
-from typing import List, Mapping
 
-from opendevin.action import (
+from agenthub.codeact_agent.prompt import (
+    COMMAND_DOCS,
+    EXAMPLES,
+    GITHUB_MESSAGE,
+    SYSTEM_PREFIX,
+    SYSTEM_SUFFIX,
+)
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.events.action import (
     Action,
-    AgentEchoAction,
     AgentFinishAction,
+    BrowseInteractiveAction,
     CmdRunAction,
+    IPythonRunCellAction,
+    MessageAction,
 )
-from opendevin.agent import Agent
-from opendevin.llm.llm import LLM
-from opendevin.observation import (
-    AgentMessageObservation,
+from opendevin.events.observation import (
+    BrowserOutputObservation,
     CmdOutputObservation,
+    IPythonRunCellObservation,
 )
-from opendevin.state import State
-from opendevin.sandbox.plugins import PluginRequirement, JupyterRequirement
-
-SYSTEM_MESSAGE = """You are a helpful assistant. You will be provided access (as root) to a bash shell to complete user-provided tasks.
-You will be able to execute commands in the bash shell, interact with the file system, install packages, and receive the output of your commands.
-
-DO NOT provide code in ```triple backticks```. Instead, you should execute bash command on behalf of the user by wrapping them with <execute> and </execute>.
-For example:
-
-You can list the files in the current directory by executing the following command:
-<execute>ls</execute>
-
-You can also install packages using pip:
-<execute> pip install numpy </execute>
-
-You can also write a block of code to a file:
-<execute>
-echo "import math
-print(math.pi)" > math.py
-</execute>
-
-When you are done, execute the following to close the shell and end the conversation:
-<execute>exit</execute>
-"""
-
-INVALID_INPUT_MESSAGE = (
-    "I don't understand your input. \n"
-    'If you want to execute command, please use <execute> YOUR_COMMAND_HERE </execute>.\n'
-    'If you already completed the task, please exit the shell by generating: <execute> exit </execute>.'
+from opendevin.llm.llm import LLM
+from opendevin.runtime.plugins import (
+    AgentSkillsRequirement,
+    JupyterRequirement,
+    PluginRequirement,
 )
 
+ENABLE_GITHUB = True
+
 
 def parse_response(response) -> str:
     action = response.choices[0].message.content
-    if '<execute>' in action and '</execute>' not in action:
-        action += '</execute>'
+    for lang in ['bash', 'ipython', 'browse']:
+        if f'<execute_{lang}>' in action and f'</execute_{lang}>' not in action:
+            action += f'</execute_{lang}>'
     return action
 
 
+def action_to_str(action: Action) -> str:
+    if isinstance(action, CmdRunAction):
+        return f'{action.thought}\n<execute_bash>\n{action.command}\n</execute_bash>'
+    elif isinstance(action, IPythonRunCellAction):
+        return f'{action.thought}\n<execute_ipython>\n{action.code}\n</execute_ipython>'
+    elif isinstance(action, BrowseInteractiveAction):
+        return f'{action.thought}\n<execute_browse>\n{action.browser_actions}\n</execute_browse>'
+    elif isinstance(action, MessageAction):
+        return action.content
+    return ''
+
+
+def get_action_message(action: Action) -> dict[str, str] | None:
+    if (
+        isinstance(action, BrowseInteractiveAction)
+        or isinstance(action, CmdRunAction)
+        or isinstance(action, IPythonRunCellAction)
+        or isinstance(action, MessageAction)
+    ):
+        return {
+            'role': 'user' if action.source == 'user' else 'assistant',
+            'content': action_to_str(action),
+        }
+    return None
+
+
+def get_observation_message(obs) -> dict[str, str] | None:
+    if isinstance(obs, CmdOutputObservation):
+        content = 'OBSERVATION:\n' + truncate_observation(obs.content)
+        content += (
+            f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]]'
+        )
+        return {'role': 'user', 'content': content}
+    elif isinstance(obs, IPythonRunCellObservation):
+        content = 'OBSERVATION:\n' + obs.content
+        # replace base64 images with a placeholder
+        splitted = content.split('\n')
+        for i, line in enumerate(splitted):
+            if '![image](data:image/png;base64,' in line:
+                splitted[i] = (
+                    '![image](data:image/png;base64, ...) already displayed to user'
+                )
+        content = '\n'.join(splitted)
+        content = truncate_observation(content)
+        return {'role': 'user', 'content': content}
+    elif isinstance(obs, BrowserOutputObservation):
+        content = 'OBSERVATION:\n' + truncate_observation(obs.content)
+        return {'role': 'user', 'content': content}
+    return None
+
+
+def truncate_observation(observation: str, max_chars: int = 10_000) -> str:
+    """
+    Truncate the middle of the observation if it is too long.
+    """
+    if len(observation) <= max_chars:
+        return observation
+    half = max_chars // 2
+    return (
+        observation[:half]
+        + '\n[... Observation truncated due to length ...]\n'
+        + observation[-half:]
+    )
+
+
+# FIXME: We can tweak these two settings to create MicroAgents specialized toward different area
+def get_system_message() -> str:
+    if ENABLE_GITHUB:
+        return f'{SYSTEM_PREFIX}\n{GITHUB_MESSAGE}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
+    else:
+        return f'{SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
+
+
+def get_in_context_example() -> str:
+    return EXAMPLES
+
+
 class CodeActAgent(Agent):
+    VERSION = '1.5'
     """
     The Code Act Agent is a minimalist agent.
     The agent works by passing the model a list of action-observation pairs and prompting the model to take the next step.
+
+    ### Overview
+
+    This agent implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.13463), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a unified **code** action space for both *simplicity* and *performance* (see paper for more details).
+
+    The conceptual idea is illustrated below. At each turn, the agent can:
+
+    1. **Converse**: Communicate with humans in natural language to ask for clarification, confirmation, etc.
+    2. **CodeAct**: Choose to perform the task by executing code
+    - Execute any valid Linux `bash` command
+    - Execute any valid `Python` code with [an interactive Python interpreter](https://ipython.org/). This is simulated through `bash` command, see plugin system below for more details.
+
+    ![image](https://github.com/OpenDevin/OpenDevin/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
+
+    ### Plugin System
+
+    To make the CodeAct agent more powerful with only access to `bash` action space, CodeAct agent leverages OpenDevin's plugin system:
+    - [Jupyter plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/jupyter): for IPython execution via bash command
+    - [SWE-agent tool plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/swe_agent_commands): Powerful bash command line tools for software development tasks introduced by [swe-agent](https://github.com/princeton-nlp/swe-agent).
+
+    ### Demo
+
+    https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
+
+    *Example of CodeActAgent with `gpt-4-turbo-2024-04-09` performing a data science task (linear regression)*
+
+    ### Work-in-progress & Next step
+
+    [] Support web-browsing
+    [] Complete the workflow for CodeAct agent to submit Github PRs
+
     """
 
-    sandbox_plugins: List[PluginRequirement] = [JupyterRequirement()]
+    sandbox_plugins: list[PluginRequirement] = [
+        # NOTE: AgentSkillsRequirement need to go before JupyterRequirement, since
+        # AgentSkillsRequirement provides a lot of Python functions
+        # and it need to be initialized before Jupyter for Jupyter to use those functions.
+        AgentSkillsRequirement(),
+        JupyterRequirement(),
+    ]
+    jupyter_kernel_init_code: str = 'from agentskills import *'
+
+    system_message: str = get_system_message()
+    in_context_example: str = f"Here is an example of how you can interact with the environment for task solving:\n{get_in_context_example()}\n\nNOW, LET'S START!"
 
     def __init__(
         self,
@@ -71,78 +178,104 @@ class CodeActAgent(Agent):
         - llm (LLM): The llm to be used by this agent
         """
         super().__init__(llm)
-        self.messages: List[Mapping[str, str]] = []
+        self.reset()
+
+    def reset(self) -> None:
+        """
+        Resets the CodeAct Agent.
+        """
+        super().reset()
 
     def step(self, state: State) -> Action:
         """
-        Performs one step using the Code Act Agent.
+        Performs one step using the CodeAct Agent.
         This includes gathering info on previous steps and prompting the model to make a command to execute.
 
         Parameters:
         - state (State): used to get updated info and background commands
 
         Returns:
-        - CmdRunAction(command) - command action to run
-        - AgentEchoAction(content=INVALID_INPUT_MESSAGE) - invalid command output
-
-        Raises:
-        - NotImplementedError - for actions other than CmdOutputObservation or AgentMessageObservation
+        - CmdRunAction(command) - bash command to run
+        - IPythonRunCellAction(code) - IPython code to run
+        - BrowseInteractiveAction(browsergym_command) - BrowserGym commands to run
+        - MessageAction(content) - Message action to run (e.g. ask for clarification)
+        - AgentFinishAction() - end the interaction
         """
+        messages: list[dict[str, str]] = [
+            {'role': 'system', 'content': self.system_message},
+            {'role': 'user', 'content': self.in_context_example},
+        ]
 
-        if len(self.messages) == 0:
-            assert state.plan.main_goal, 'Expecting instruction to be set'
-            self.messages = [
-                {'role': 'system', 'content': SYSTEM_MESSAGE},
-                {'role': 'user', 'content': state.plan.main_goal},
-            ]
-        updated_info = state.updated_info
-        if updated_info:
-            for prev_action, obs in updated_info:
-                assert isinstance(
-                    prev_action, (CmdRunAction, AgentEchoAction)
-                ), 'Expecting CmdRunAction or AgentEchoAction for Action'
-                if isinstance(
-                    obs, AgentMessageObservation
-                ):  # warning message from itself
-                    self.messages.append(
-                        {'role': 'user', 'content': obs.content})
-                elif isinstance(obs, CmdOutputObservation):
-                    content = 'OBSERVATION:\n' + obs.content
-                    content += f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]]'
-                    self.messages.append({'role': 'user', 'content': content})
-                else:
-                    raise NotImplementedError(
-                        f'Unknown observation type: {obs.__class__}'
-                    )
-        response = self.llm.completion(
-            messages=self.messages,
-            stop=['</execute>'],
-            temperature=0.0
+        for prev_action, obs in state.history:
+            action_message = get_action_message(prev_action)
+            if action_message:
+                messages.append(action_message)
+
+            obs_message = get_observation_message(obs)
+            if obs_message:
+                messages.append(obs_message)
+
+        latest_user_message = [m for m in messages if m['role'] == 'user'][-1]
+        if latest_user_message:
+            if latest_user_message['content'].strip() == '/exit':
+                return AgentFinishAction()
+            latest_user_message['content'] += (
+                f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task.'
+            )
+
+        response = self.llm.do_completion(
+            messages=messages,
+            stop=[
+                '</execute_ipython>',
+                '</execute_bash>',
+                '</execute_browse>',
+            ],
+            temperature=0.0,
         )
-        action_str: str = parse_response(response)
-        state.num_of_chars += sum(len(message['content'])
-                                  for message in self.messages) + len(action_str)
-        self.messages.append({'role': 'assistant', 'content': action_str})
 
-        command = re.search(r'<execute>(.*)</execute>', action_str, re.DOTALL)
-        if command is not None:
+        action_str: str = parse_response(response)
+        state.num_of_chars += sum(
+            len(message['content']) for message in messages
+        ) + len(action_str)
+
+        if finish_command := re.search(r'<finish>.*</finish>', action_str, re.DOTALL):
+            thought = action_str.replace(finish_command.group(0), '').strip()
+            return AgentFinishAction(thought=thought)
+        if bash_command := re.search(
+            r'<execute_bash>(.*?)</execute_bash>', action_str, re.DOTALL
+        ):
+            # remove the command from the action string to get thought
+            thought = action_str.replace(bash_command.group(0), '').strip()
             # a command was found
-            command_group = command.group(1)
+            command_group = bash_command.group(1).strip()
+
             if command_group.strip() == 'exit':
                 return AgentFinishAction()
-            return CmdRunAction(command=command_group)
-            # # execute the code
-            # # TODO: does exit_code get loaded into Message?
-            # exit_code, observation = self.env.execute(command_group)
-            # self._history.append(Message(Role.ASSISTANT, observation))
+            return CmdRunAction(command=command_group, thought=thought)
+        elif python_code := re.search(
+            r'<execute_ipython>(.*?)</execute_ipython>', action_str, re.DOTALL
+        ):
+            # a code block was found
+            code_group = python_code.group(1).strip()
+            thought = action_str.replace(python_code.group(0), '').strip()
+            return IPythonRunCellAction(
+                code=code_group,
+                thought=thought,
+                kernel_init_code=self.jupyter_kernel_init_code,
+            )
+        elif browse_command := re.search(
+            r'<execute_browse>(.*)</execute_browse>', action_str, re.DOTALL
+        ):
+            # BrowserGym actions was found
+            browse_actions = browse_command.group(1).strip()
+            thought = action_str.replace(browse_command.group(0), '').strip()
+            return BrowseInteractiveAction(
+                browser_actions=browse_actions, thought=thought
+            )
         else:
-            # we could provide a error message for the model to continue similar to
-            # https://github.com/xingyaoww/mint-bench/blob/main/mint/envs/general_env.py#L18-L23
-            # observation = INVALID_INPUT_MESSAGE
-            # self._history.append(Message(Role.ASSISTANT, observation))
-            return AgentEchoAction(
-                content=INVALID_INPUT_MESSAGE
-            )  # warning message to itself
+            # We assume the LLM is GOOD enough that when it returns pure natural language
+            # it want to talk to the user
+            return MessageAction(content=action_str, wait_for_response=True)
 
-    def search_memory(self, query: str) -> List[str]:
+    def search_memory(self, query: str) -> list[str]:
         raise NotImplementedError('Implement this abstract method')

agenthub/codeact_agent/prompt.py

@@ -0,0 +1,249 @@
+from opendevin.runtime.plugins import AgentSkillsRequirement
+
+_AGENT_SKILLS_DOCS = AgentSkillsRequirement.documentation
+
+COMMAND_DOCS = (
+    '\nApart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:\n'
+    f'{_AGENT_SKILLS_DOCS}'
+    "Please note that THE `edit_file` FUNCTION REQUIRES PROPER INDENTATION. If the assistant would like to add the line '        print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run."
+)
+
+# ======= SYSTEM MESSAGE =======
+MINIMAL_SYSTEM_PREFIX = """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
+The assistant can interact with an interactive Python (Jupyter Notebook) environment and receive the corresponding output when needed. The code should be enclosed using "<execute_ipython>" tag, for example:
+<execute_ipython>
+print("Hello World!")
+</execute_ipython>
+The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
+For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
+"""
+
+BROWSING_PREFIX = """The assistant can browse the Internet with commands on behalf of the user by wrapping them with <execute_browse> and </execute_browse>.
+For example, you can browse a given URL by <execute_browse> goto("<URL>") </execute_browse>.
+The assistant should attempt fewer things at a time instead of putting too much commands OR code in one "execute" block.
+"""
+PIP_INSTALL_PREFIX = """The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them."""
+
+SYSTEM_PREFIX = MINIMAL_SYSTEM_PREFIX + BROWSING_PREFIX + PIP_INSTALL_PREFIX
+
+GITHUB_MESSAGE = """To do any activities on GitHub, the assistant should use the token in the $GITHUB_TOKEN environment variable.
+For instance, to push a local branch `my_branch` to the github repo `owner/repo`, the assistant can use the following four commands:
+<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
+If the assistant require access to GitHub but $GITHUB_TOKEN is not set, ask the user to set it."""
+
+SYSTEM_SUFFIX = """The assistant's response should be concise.
+The assistant should include ONLY ONE <execute_ipython> or <execute_bash> or <execute_browse> in every one of the responses, unless the assistant is finished with the task or need more input or action from the user in order to proceed.
+IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> or <execute_browse> instead of providing it.
+"""
+
+
+# ======= EXAMPLE MESSAGE =======
+EXAMPLES = """
+--- START OF EXAMPLE ---
+
+USER: Can you create a list of numbers from 1 to 10, and create a web page to display them at port 5000?
+
+ASSISTANT:
+Sure! Let me create a file first:
+<execute_ipython>
+create_file('app.py')
+</execute_ipython>
+
+USER:
+OBSERVATION:
+[File: /workspace/app.py (1 lines total)]
+1|
+[File app.py created.]
+
+ASSISTANT:
+Now I will write the Python code for starting a web server and save it to the file `app.py`:
+<execute_ipython>
+EDITED_CODE=\"\"\"from flask import Flask
+app = Flask(__name__)
+
+@app.route('/')
+def index():
+    numbers = list(range(1, 11))
+    return str(numbers)
+
+if __name__ == '__main__':
+    app.run(port=5000)\"\"\"
+edit_file(start=1, end=1, content=EDITED_CODE)
+</execute_ipython>
+
+USER:
+OBSERVATION:
+1|from flask import Flask
+2|app = Flask(__name__)
+3|
+4|@app.route('/')
+5|def index():
+6|    numbers = list(range(1, 11))
+7|    return str(numbers)
+8|
+9|if __name__ == '__main__':
+10|    app.run(port=5000)
+[File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
+
+ASSISTANT:
+I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you:
+<execute_bash>
+python3 app.py > server.log 2>&1 &
+</execute_bash>
+
+USER:
+OBSERVATION:
+[1] 121[1]+  Exit 1                  python3 app.py > server.log 2>&1
+
+ASSISTANT: Looks like the server is running with PID 121 then crashed. Let me check the server log:
+<execute_bash>
+cat server.log
+</execute_bash>
+
+USER:
+OBSERVATION:
+Traceback (most recent call last):
+  File "/workspace/app.py", line 2, in <module>
+    from flask import Flask
+ModuleNotFoundError: No module named 'flask'
+
+ASSISTANT:
+It seems that Flask is not installed. Let me install Flask for you:
+<execute_bash>
+pip install flask
+</execute_bash>
+
+USER:
+OBSERVATION:
+Defaulting to user installation because normal site-packages is not writeable
+Collecting flask
+  Using cached flask-3.0.3-py3-none-any.whl (101 kB)
+Collecting blinker>=1.6.2
+  Using cached blinker-1.7.0-py3-none-any.whl (13 kB)
+Collecting Werkzeug>=3.0.0
+  Using cached werkzeug-3.0.2-py3-none-any.whl (226 kB)
+Collecting click>=8.1.3
+  Using cached click-8.1.7-py3-none-any.whl (97 kB)
+Collecting itsdangerous>=2.1.2
+  Using cached itsdangerous-2.2.0-py3-none-any.whl (16 kB)
+Requirement already satisfied: Jinja2>=3.1.2 in /home/opendevin/.local/lib/python3.10/site-packages (from flask) (3.1.3)
+Requirement already satisfied: MarkupSafe>=2.0 in /home/opendevin/.local/lib/python3.10/site-packages (from Jinja2>=3.1.2->flask) (2.1.5)
+Installing collected packages: Werkzeug, itsdangerous, click, blinker, flask
+Successfully installed Werkzeug-3.0.2 blinker-1.7.0 click-8.1.7 flask-3.0.3 itsdangerous-2.2.0
+
+ASSISTANT:
+Now that Flask is installed, let me run the Python file again:
+<execute_bash>
+python3 app.py > server.log 2>&1 &
+</execute_bash>
+
+USER:
+OBSERVATION:
+[1] 124
+
+ASSISTANT:
+Let me check the server log again:
+<execute_bash>
+cat server.log
+</execute_bash>
+
+USER:
+OBSERVATION:
+* Serving Flask app 'app'
+ * Debug mode: off
+WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
+ * Running on http://127.0.0.1:5000
+Press CTRL+C to quit
+
+ASSISTANT:
+The server is running on port 5000 with PID 124. You can access the list of numbers by visiting http://127.0.0.1:5000. If you have any further questions, feel free to ask!
+
+USER: Now browse the newly started server's homepage and show me the content.
+
+ASSISTANT:
+Sure! Let me browse the server's homepage at http://127.0.0.1:5000:
+<execute_browse>
+goto("http://127.0.0.1:5000")
+</execute_browse>
+
+USER:
+OBSERVATION:
+[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
+
+ASSISTANT:
+The content of the server's homepage is "[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]". If you have any further questions, feel free to ask!
+
+USER: Now kill the server, make it display the numbers in a table format.
+
+ASSISTANT:
+Sure! Let me stop the server first:
+<execute_bash>
+kill 124
+</execute_bash>
+
+USER:
+OBSERVATION:
+[1]+  Terminated              python3 app.py > server.log 2>&1
+
+ASSISTANT:
+The server has been stopped. Let me open the Python file and modify it.
+<execute_ipython>
+open_file('app.py')
+</execute_ipython>
+
+USER:
+[File: /workspace/app.py (10 lines total)]
+1|from flask import Flask
+2|app = Flask(__name__)
+3|
+4|@app.route('/')
+5|def index():
+6|    numbers = list(range(1, 11))
+7|    return str(numbers)
+8|
+9|if __name__ == '__main__':
+10|    app.run(port=5000)
+
+ASSISTANT:
+I should edit the file to display the numbers in a table format. I should include correct indentation. Let me update the file:
+<execute_ipython>
+edit_file(start=7, end=7, content="    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'")
+</execute_ipython>
+
+USER:
+Observation:
+[File: /workspace/app.py (10 lines total after edit)]
+1|from flask import Flask
+2|app = Flask(__name__)
+3|
+4|@app.route('/')
+5|def index():
+6|    numbers = list(range(1, 11))
+7|    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
+8|
+9|if __name__ == '__main__':
+10|    app.run(port=5000)
+[File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
+
+ASSISTANT:
+The file has been updated. Let me run the Python file again with the new changes:
+<execute_bash>
+python3 app.py > server.log 2>&1 &
+</execute_bash>
+
+USER:
+Observation:
+[1] 126
+
+ASSISTANT:
+The server is running on port 5000 with PID 126. You can access the list of numbers in a table format by visiting http://127.0.0.1:5000. Free free to let me know if you have any further requests!
+
+--- END OF EXAMPLE ---
+"""
+
+INVALID_INPUT_MESSAGE = (
+    "I don't understand your input. \n"
+    'If you want to execute a bash command, please use <execute_bash> YOUR_COMMAND_HERE </execute_bash>.\n'
+    'If you want to execute a block of Python code, please use <execute_ipython> YOUR_COMMAND_HERE </execute_ipython>.\n'
+    'If you want to browse the Internet, please use <execute_browse> YOUR_COMMAND_HERE </execute_browse>.\n'
+)

agenthub/codeact_swe_agent/README.md

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

agenthub/codeact_swe_agent/__init__.py

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

agenthub/codeact_swe_agent/codeact_swe_agent.py

@@ -0,0 +1,246 @@
+import re
+
+from agenthub.codeact_swe_agent.prompt import (
+    COMMAND_DOCS,
+    MINIMAL_SYSTEM_PREFIX,
+    SWE_EXAMPLE,
+    SYSTEM_SUFFIX,
+)
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.events.action import (
+    Action,
+    AgentFinishAction,
+    BrowseInteractiveAction,
+    CmdRunAction,
+    IPythonRunCellAction,
+    MessageAction,
+)
+from opendevin.events.observation import (
+    BrowserOutputObservation,
+    CmdOutputObservation,
+    IPythonRunCellObservation,
+)
+from opendevin.llm.llm import LLM
+from opendevin.runtime.plugins import (
+    AgentSkillsRequirement,
+    JupyterRequirement,
+    PluginRequirement,
+)
+
+
+def parse_response(response) -> str:
+    action = response.choices[0].message.content
+    for lang in ['bash', 'ipython', 'browse']:
+        if f'<execute_{lang}>' in action and f'</execute_{lang}>' not in action:
+            action += f'</execute_{lang}>'
+    return action
+
+
+def action_to_str(action: Action) -> str:
+    if isinstance(action, CmdRunAction):
+        return f'{action.thought}\n<execute_bash>\n{action.command}\n</execute_bash>'
+    elif isinstance(action, IPythonRunCellAction):
+        return f'{action.thought}\n<execute_ipython>\n{action.code}\n</execute_ipython>'
+    elif isinstance(action, BrowseInteractiveAction):
+        return f'{action.thought}\n<execute_browse>\n{action.browser_actions}\n</execute_browse>'
+    elif isinstance(action, MessageAction):
+        return action.content
+    return ''
+
+
+def get_action_message(action: Action) -> dict[str, str] | None:
+    if (
+        isinstance(action, BrowseInteractiveAction)
+        or isinstance(action, CmdRunAction)
+        or isinstance(action, IPythonRunCellAction)
+        or isinstance(action, MessageAction)
+    ):
+        return {
+            'role': 'user' if action.source == 'user' else 'assistant',
+            'content': action_to_str(action),
+        }
+    return None
+
+
+def get_observation_message(obs) -> dict[str, str] | None:
+    if isinstance(obs, CmdOutputObservation):
+        content = 'OBSERVATION:\n' + truncate_observation(obs.content)
+        content += (
+            f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]]'
+        )
+        return {'role': 'user', 'content': content}
+    elif isinstance(obs, IPythonRunCellObservation):
+        content = 'OBSERVATION:\n' + obs.content
+        # replace base64 images with a placeholder
+        splitted = content.split('\n')
+        for i, line in enumerate(splitted):
+            if '![image](data:image/png;base64,' in line:
+                splitted[i] = (
+                    '![image](data:image/png;base64, ...) already displayed to user'
+                )
+        content = '\n'.join(splitted)
+        content = truncate_observation(content)
+        return {'role': 'user', 'content': content}
+    elif isinstance(obs, BrowserOutputObservation):
+        content = 'OBSERVATION:\n' + truncate_observation(obs.content)
+        return {'role': 'user', 'content': content}
+    return None
+
+
+def truncate_observation(observation: str, max_chars: int = 10_000) -> str:
+    """
+    Truncate the middle of the observation if it is too long.
+    """
+    if len(observation) <= max_chars:
+        return observation
+    half = max_chars // 2
+    return (
+        observation[:half]
+        + '\n[... Observation truncated due to length ...]\n'
+        + observation[-half:]
+    )
+
+
+def get_system_message() -> str:
+    return f'{MINIMAL_SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
+
+
+def get_in_context_example() -> str:
+    return SWE_EXAMPLE
+
+
+class CodeActSWEAgent(Agent):
+    VERSION = '1.5'
+    """
+    This agent is an adaptation of the original [SWE Agent](https://swe-agent.com/) based on CodeAct 1.5 using the `agentskills` library of OpenDevin.
+
+    It is intended use is **solving Github issues**.
+
+    It removes web-browsing and Github capability from the original CodeAct agent to avoid confusion to the agent.
+    """
+
+    sandbox_plugins: list[PluginRequirement] = [
+        # NOTE: AgentSkillsRequirement need to go before JupyterRequirement, since
+        # AgentSkillsRequirement provides a lot of Python functions
+        # and it need to be initialized before Jupyter for Jupyter to use those functions.
+        AgentSkillsRequirement(),
+        JupyterRequirement(),
+    ]
+    jupyter_kernel_init_code: str = 'from agentskills import *'
+
+    system_message: str = get_system_message()
+    in_context_example: str = f"Here is an example of how you can interact with the environment for task solving:\n{get_in_context_example()}\n\nNOW, LET'S START!"
+
+    def __init__(
+        self,
+        llm: LLM,
+    ) -> None:
+        """
+        Initializes a new instance of the CodeActAgent class.
+
+        Parameters:
+        - llm (LLM): The llm to be used by this agent
+        """
+        super().__init__(llm)
+        self.reset()
+
+    def reset(self) -> None:
+        """
+        Resets the CodeAct Agent.
+        """
+        super().reset()
+
+    def step(self, state: State) -> Action:
+        """
+        Performs one step using the CodeAct Agent.
+        This includes gathering info on previous steps and prompting the model to make a command to execute.
+
+        Parameters:
+        - state (State): used to get updated info and background commands
+
+        Returns:
+        - CmdRunAction(command) - bash command to run
+        - IPythonRunCellAction(code) - IPython code to run
+        - BrowseInteractiveAction(browsergym_command) - BrowserGym commands to run
+        - MessageAction(content) - Message action to run (e.g. ask for clarification)
+        - AgentFinishAction() - end the interaction
+        """
+        messages: list[dict[str, str]] = [
+            {'role': 'system', 'content': self.system_message},
+            {'role': 'user', 'content': self.in_context_example},
+        ]
+
+        for prev_action, obs in state.history:
+            action_message = get_action_message(prev_action)
+            if action_message:
+                messages.append(action_message)
+
+            obs_message = get_observation_message(obs)
+            if obs_message:
+                messages.append(obs_message)
+
+        latest_user_message = [m for m in messages if m['role'] == 'user'][-1]
+        if latest_user_message:
+            if latest_user_message['content'].strip() == '/exit':
+                return AgentFinishAction()
+            latest_user_message['content'] += (
+                f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task.'
+            )
+
+        response = self.llm.do_completion(
+            messages=messages,
+            stop=[
+                '</execute_ipython>',
+                '</execute_bash>',
+                '</execute_browse>',
+            ],
+            temperature=0.0,
+        )
+
+        action_str: str = parse_response(response)
+        state.num_of_chars += sum(
+            len(message['content']) for message in messages
+        ) + len(action_str)
+
+        if finish_command := re.search(r'<finish>.*</finish>', action_str, re.DOTALL):
+            thought = action_str.replace(finish_command.group(0), '').strip()
+            return AgentFinishAction(thought=thought)
+        if bash_command := re.search(
+            r'<execute_bash>(.*?)</execute_bash>', action_str, re.DOTALL
+        ):
+            # remove the command from the action string to get thought
+            thought = action_str.replace(bash_command.group(0), '').strip()
+            # a command was found
+            command_group = bash_command.group(1).strip()
+
+            if command_group.strip() == 'exit':
+                return AgentFinishAction()
+            return CmdRunAction(command=command_group, thought=thought)
+        elif python_code := re.search(
+            r'<execute_ipython>(.*?)</execute_ipython>', action_str, re.DOTALL
+        ):
+            # a code block was found
+            code_group = python_code.group(1).strip()
+            thought = action_str.replace(python_code.group(0), '').strip()
+            return IPythonRunCellAction(
+                code=code_group,
+                thought=thought,
+                kernel_init_code=self.jupyter_kernel_init_code,
+            )
+        elif browse_command := re.search(
+            r'<execute_browse>(.*)</execute_browse>', action_str, re.DOTALL
+        ):
+            # BrowserGym actions was found
+            browse_actions = browse_command.group(1).strip()
+            thought = action_str.replace(browse_command.group(0), '').strip()
+            return BrowseInteractiveAction(
+                browser_actions=browse_actions, thought=thought
+            )
+        else:
+            # We assume the LLM is GOOD enough that when it returns pure natural language
+            # it want to talk to the user
+            return MessageAction(content=action_str, wait_for_response=True)
+
+    def search_memory(self, query: str) -> list[str]:
+        raise NotImplementedError('Implement this abstract method')

agenthub/codeact_swe_agent/prompt.py

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

agenthub/delegator_agent/__init__.py

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

agenthub/delegator_agent/agent.py

@@ -1,18 +1,17 @@
-from typing import List
-
-from opendevin.agent import Agent
-from opendevin.action import AgentFinishAction, AgentDelegateAction
-from opendevin.observation import AgentDelegateObservation
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.events.action import Action, AgentDelegateAction, AgentFinishAction
+from opendevin.events.observation import AgentDelegateObservation
 from opendevin.llm.llm import LLM
-from opendevin.state import State
-from opendevin.action import Action
 
 
 class DelegatorAgent(Agent):
+    VERSION = '1.0'
     """
     The planner agent utilizes a special prompting strategy to create long term plans for solving problems.
     The agent is given its previous action-observation pairs, current task, and hint based on last action taken at every step.
     """
+
     current_delegate: str = ''
 
     def __init__(self, llm: LLM):
@@ -38,36 +37,50 @@ class DelegatorAgent(Agent):
         """
         if self.current_delegate == '':
             self.current_delegate = 'study'
-            return AgentDelegateAction(agent='StudyRepoForTaskAgent', inputs={
-                'task': state.plan.main_goal
-            })
+            task = state.get_current_user_intent()
+            return AgentDelegateAction(
+                agent='StudyRepoForTaskAgent', inputs={'task': task}
+            )
 
-        lastObservation = state.history[-1][1]
-        if not isinstance(lastObservation, AgentDelegateObservation):
+        last_observation = state.history[-1][1]
+        if not isinstance(last_observation, AgentDelegateObservation):
             raise Exception('Last observation is not an AgentDelegateObservation')
 
+        goal = state.get_current_user_intent()
         if self.current_delegate == 'study':
             self.current_delegate = 'coder'
-            return AgentDelegateAction(agent='Coder', inputs={
-                'task': state.plan.main_goal,
-                'summary': lastObservation.outputs['summary'],
-            })
+            return AgentDelegateAction(
+                agent='CoderAgent',
+                inputs={
+                    'task': goal,
+                    'summary': last_observation.outputs['summary'],
+                },
+            )
         elif self.current_delegate == 'coder':
             self.current_delegate = 'verifier'
-            return AgentDelegateAction(agent='Verifier', inputs={
-                'task': state.plan.main_goal,
-            })
+            return AgentDelegateAction(
+                agent='VerifierAgent',
+                inputs={
+                    'task': goal,
+                },
+            )
         elif self.current_delegate == 'verifier':
-            if 'completed' in lastObservation.outputs and lastObservation.outputs['completed']:
+            if (
+                'completed' in last_observation.outputs
+                and last_observation.outputs['completed']
+            ):
                 return AgentFinishAction()
             else:
                 self.current_delegate = 'coder'
-                return AgentDelegateAction(agent='Coder', inputs={
-                    'task': state.plan.main_goal,
-                    'summary': lastObservation.outputs['summary'],
-                })
+                return AgentDelegateAction(
+                    agent='CoderAgent',
+                    inputs={
+                        'task': goal,
+                        'summary': last_observation.outputs['summary'],
+                    },
+                )
         else:
             raise Exception('Invalid delegate state')
 
-    def search_memory(self, query: str) -> List[str]:
+    def search_memory(self, query: str) -> list[str]:
         return []

agenthub/dummy_agent/__init__.py

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

agenthub/dummy_agent/agent.py

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

agenthub/micro/README.md

@@ -0,0 +1,14 @@
+## Introduction
+
+This package contains definitions of micro-agents. A micro-agent is defined
+in the following structure:
+
+```
+[AgentName]
+├── agent.yaml
+└── prompt.md
+```
+
+Note that `prompt.md` could use jinja2 template syntax. During runtime, `prompt.md`
+is loaded and rendered, and used together with `agent.yaml` to initialize a
+micro-agent.

agenthub/micro/_instructions/actions/add_task.md

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

agenthub/micro/_instructions/actions/finish.md

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

agenthub/micro/_instructions/actions/kill.md

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

agenthub/micro/_instructions/actions/message.md

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

agenthub/micro/_instructions/actions/modify_task.md

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

agenthub/micro/_instructions/actions/reject.md

@@ -0,0 +1,2 @@
+* `reject` - reject the task. Arguments:
+  * `outputs` - a dictionary representing the outputs of your task, if any

agenthub/micro/_instructions/actions/think.md

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

agenthub/micro/agent.py

@@ -1,82 +1,75 @@
-import json
-from typing import List, Dict
+from jinja2 import BaseLoader, Environment
 
-from jinja2 import Environment, BaseLoader
-
-from opendevin.agent import Agent
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.core.utils import json
+from opendevin.events.action import Action
+from opendevin.events.serialization.action import action_from_dict
+from opendevin.events.serialization.event import event_to_memory
 from opendevin.llm.llm import LLM
-from 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
 
 
 def parse_response(orig_response: str) -> Action:
-    json_start = orig_response.find('{')
-    json_end = orig_response.rfind('}') + 1
-    response = orig_response[json_start:json_end]
-    try:
-        action_dict = json.loads(response)
-    except json.JSONDecodeError as e:
-        raise LLMOutputError(
-            'Invalid JSON in response. Please make sure the response is a valid JSON object'
-        ) from e
-    action = action_from_dict(action_dict)
-    return action
+    # attempt to load the JSON dict from the response
+    action_dict = json.loads(orig_response)
 
-
-def my_encoder(obj):
-    """
-    Encodes objects as dictionaries
-
-    Parameters:
-    - obj (Object): An object that will be converted
-
-    Returns:
-    - dict: If the object can be converted it is returned in dict format
-    """
-    if hasattr(obj, 'to_dict'):
-        return obj.to_dict()
+    # load the action from the dict
+    return action_from_dict(action_dict)
 
 
 def to_json(obj, **kwargs):
     """
     Serialize an object to str format
     """
-    return json.dumps(obj, default=my_encoder, **kwargs)
+    return json.dumps(obj, **kwargs)
+
+
+def history_to_json(obj, **kwargs):
+    """
+    Serialize and simplify history to str format
+    """
+    if isinstance(obj, list):
+        # process history, make it simpler.
+        processed_history = []
+        for action, observation in obj:
+            processed_history.append(
+                (event_to_memory(action), event_to_memory(observation))
+            )
+        return json.dumps(processed_history, **kwargs)
 
 
 class MicroAgent(Agent):
+    VERSION = '1.0'
     prompt = ''
-    agent_definition: Dict = {}
+    agent_definition: dict = {}
 
     def __init__(self, llm: LLM):
         super().__init__(llm)
         if 'name' not in self.agent_definition:
             raise ValueError('Agent definition must contain a name')
-        self.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:
+        latest_user_message = state.get_current_user_intent()
         prompt = self.prompt_template.render(
             state=state,
             instructions=instructions,
             to_json=to_json,
-            delegates=self.delegates)
+            history_to_json=history_to_json,
+            delegates=self.delegates,
+            latest_user_message=latest_user_message,
+        )
         messages = [{'content': prompt, 'role': 'user'}]
-        resp = self.llm.completion(messages=messages)
+        resp = self.llm.do_completion(messages=messages)
         action_resp = resp['choices'][0]['message']['content']
         state.num_of_chars += len(prompt) + len(action_resp)
         action = parse_response(action_resp)
         return action
 
-    def search_memory(self, query: str) -> List[str]:
+    def search_memory(self, query: str) -> list[str]:
         return []

agenthub/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/coder/prompt.md

@@ -2,24 +2,26 @@
 You are a software engineer. You've inherited an existing codebase, which you
 need to modify to complete this task:
 
-{{ state.plan.main_goal }}
+{{ latest_user_message }}
 
+{% if state.inputs.summary %}
 Here's a summary of the codebase, as it relates to this task:
 
 {{ state.inputs.summary }}
+{% endif %}
 
 ## Available Actions
 {{ instructions.actions.run }}
 {{ instructions.actions.write }}
 {{ instructions.actions.read }}
-{{ instructions.actions.think }}
+{{ instructions.actions.message }}
 {{ instructions.actions.finish }}
 
 Do NOT finish until you have completed the tasks.
 
 ## History
 {{ instructions.history_truncated }}
-{{ to_json(state.history[-10:]) }}
+{{ history_to_json(state.history[-10:]) }}
 
 ## Format
 {{ instructions.format.action }}

agenthub/micro/commit_writer/README.md

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

agenthub/micro/commit_writer/agent.yaml

@@ -0,0 +1,5 @@
+name: CommitWriterAgent
+description: "Write a git commit message for files in the git staging area"
+inputs: {}
+outputs:
+  answer: string

agenthub/micro/commit_writer/prompt.md

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

agenthub/micro/instructions.py

@@ -1,19 +1,21 @@
-from typing import Dict
 import os
 
-instructions: Dict = {}
+instructions: dict = {}
 
 base_dir = os.path.dirname(os.path.abspath(__file__)) + '/_instructions'
 for root, dirs, files in os.walk(base_dir):
     if len(files) == 0:
         continue
-    rel_base = os.path.relpath(root, base_dir)
-    keys = rel_base.split('/')
-    obj = instructions
-    for key in keys:
-        if key not in obj:
-            obj[key] = {}
-        obj = obj[key]
+    if root == base_dir:
+        obj = instructions
+    else:
+        rel_base = os.path.relpath(root, base_dir)
+        keys = rel_base.split('/')
+        obj = instructions
+        for key in keys:
+            if key not in obj:
+                obj[key] = {}
+            obj = obj[key]
     for file in files:
         without_ext = os.path.splitext(file)[0]
         with open(os.path.join(root, file), 'r') as f:

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/manager/prompt.md

@@ -1,6 +1,6 @@
 # Task
 You are in charge of accomplishing the following task:
-{{ state.plan.main_goal }}
+{{ latest_user_message }}
 
 In order to accomplish this goal, you must delegate tasks to one or more agents, who
 can do the actual work. A description of each agent is provided below. You MUST
@@ -17,7 +17,7 @@ provide the correct inputs for the delegate you select.
 
 ## History
 {{ instructions.history_truncated }}
-{{ to_json(state.history[-10:]) }}
+{{ history_to_json(state.history[-10:]) }}
 
 ## Available Actions
 {{ instructions.actions.delegate }}

agenthub/micro/math_agent/agent.yaml

@@ -1,25 +1,24 @@
 name: MathAgent
 description: "Solves simple and complex math problems using python"
-generates: Action
 container: python:3.12.3-bookworm
 inputs:
   task: string
 outputs:
   answer: string
 examples:
-  - 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/math_agent/prompt.md

@@ -1,7 +1,7 @@
 # Task
-You are a brilliant mathematician and programmer. You've been given the follwoing problem to solve:
+You are a brilliant mathematician and programmer. You've been given the following problem to solve:
 
-{{ state.plan.main_goal }}
+{{ latest_user_message }}
 
 Please write a python script that solves this problem, and prints the answer to stdout.
 ONLY print the answer to stdout, nothing else.
@@ -10,7 +10,7 @@ and call the `finish` action with `outputs.answer` set to the answer.
 
 ## History
 {{ instructions.history_truncated }}
-{{ to_json(state.history[-10:]) }}
+{{ history_to_json(state.history[-10:]) }}
 
 If the last item in the history is an error, you should try to fix it.
 

agenthub/micro/postgres_agent/agent.yaml

@@ -1,6 +1,5 @@
 name: PostgresAgent
 description: Writes and maintains PostgreSQL migrations
-generates: Action
 inputs:
-  - task: string
-outputs: []
+  task: string
+outputs: {}

agenthub/micro/postgres_agent/prompt.md

@@ -2,7 +2,7 @@
 You are a database engineer. You are working on an existing Postgres project, and have been given
 the following task:
 
-{{ state.plan.main_goal }}
+{{ latest_user_message }}
 
 You must:
 * Investigate the existing migrations to understand the current schema
@@ -11,14 +11,14 @@ You must:
 
 ## Actions
 You may take any of the following actions:
-{{ instructions.actions.think }}
+{{ instructions.actions.message }}
 {{ instructions.actions.read }}
 {{ instructions.actions.write }}
 {{ instructions.actions.run }}
 
 ## History
 {{ instructions.history_truncated }}
-{{ to_json(state.history[-10:]) }}
+{{ history_to_json(state.history[-10:]) }}
 
 ## Format
 {{ instructions.format.action }}

agenthub/micro/registry.py

@@ -1,4 +1,5 @@
 import os
+
 import yaml
 
 all_microagents = {}
@@ -12,8 +13,7 @@ for dir in os.listdir(os.path.dirname(__file__)):
     promptFile = base + '/prompt.md'
     agentFile = base + '/agent.yaml'
     if not os.path.isfile(promptFile) or not os.path.isfile(agentFile):
-        raise Exception(
-            f'Missing prompt or agent file in {base}. Please create them.')
+        raise Exception(f'Missing prompt or agent file in {base}. Please create them.')
     with open(promptFile, 'r') as f:
         prompt = f.read()
     with open(agentFile, 'r') as f:

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/repo_explorer/prompt.md

@@ -10,7 +10,7 @@ of the codebase, including:
 ## Available Actions
 {{ instructions.actions.run }}
 {{ instructions.actions.read }}
-{{ instructions.actions.think }}
+{{ instructions.actions.message }}
 {{ instructions.actions.finish }}
 
 You should ONLY `run` commands that have no side-effects, like `ls` and `grep`.
@@ -20,7 +20,7 @@ When you're done, put your summary into the output of the `finish` action.
 
 ## History
 {{ instructions.history_truncated }}
-{{ to_json(state.history[-10:]) }}
+{{ history_to_json(state.history[-10:]) }}
 
 ## Format
 {{ instructions.format.action }}

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/study_repo_for_task/prompt.md

@@ -3,23 +3,23 @@ You are a software engineer. You've inherited an existing codebase, which you're
 learning about for the first time. You need to study the codebase to find all
 the information needed to complete this task:
 
-{{ state.plan.main_goal }}
+{{ latest_user_message }}
 
 ## Available Actions
 {{ instructions.actions.run }}
 {{ instructions.actions.read }}
-{{ instructions.actions.think }}
+{{ instructions.actions.message }}
 {{ instructions.actions.finish }}
 
 You must ONLY `run` commands that have no side-effects, like `ls` and `grep`.
 
 Do NOT finish until you have a complete understanding of which parts of the
-codebase are relevant to the task, including particular files, function, functions, and classes.
+codebase are relevant to the task, including particular files, functions, and classes.
 When you're done, put your summary in `outputs.summary` in the `finish` action.
 
 ## History
 {{ instructions.history_truncated }}
-{{ to_json(state.history[-10:]) }}
+{{ history_to_json(state.history[-10:]) }}
 
 ## Format
 {{ instructions.format.action }}

agenthub/micro/typo_fixer_agent/agent.yaml

@@ -0,0 +1,5 @@
+name: TypoFixerAgent
+description: Fixes typos in files in the current working directory
+inputs: {}
+outputs:
+  summary: string

agenthub/micro/typo_fixer_agent/prompt.md

@@ -0,0 +1,46 @@
+# Task
+You are a proofreader tasked with fixing typos in the files in your current working directory. Your goal is to:
+1. Scan the files for typos
+2. Overwrite the files with the typos fixed
+3. Provide a summary of the typos fixed
+
+## Available Actions
+{{ instructions.actions.read }}
+{{ instructions.actions.write }}
+{{ instructions.actions.run }}
+{{ instructions.actions.message }}
+{{ instructions.actions.finish }}
+
+To complete this task:
+1. Use the `read` action to read the contents of the files in your current working directory. Make sure to provide the file path in the format `'./file_name.ext'`.
+2. Use the `think` action to analyze the contents and identify typos.
+3. Use the `write` action to create new versions of the files with the typos fixed.
+  - Overwrite the original files with the corrected content. Make sure to provide the file path in the format `'./file_name.ext'`.
+4. Use the `think` action to generate a summary of the typos fixed, including the original and fixed versions of each typo, and the file(s) they were found in.
+5. Use the `finish` action to return the summary in the `outputs.summary` field.
+
+Do NOT finish until you have fixed all the typos and generated a summary.
+
+## History
+{{ instructions.history_truncated }}
+{{ history_to_json(state.history[-5:]) }}
+
+## Format
+{{ instructions.format.action }}
+
+For example, if you want to use the read action to read the contents of a file named example.txt, your response should look like this:
+{
+  "action": "read",
+  "args": {
+    "path": "./example.txt"
+  }
+}
+
+Similarly, if you want to use the write action to write content to a file named output.txt, your response should look like this:
+{
+  "action": "write",
+  "args": {
+    "path": "./output.txt",
+    "content": "This is the content to be written to the file."
+  }
+}

agenthub/micro/verifier/agent.yaml

@@ -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/micro/verifier/prompt.md

@@ -2,14 +2,14 @@
 You are a quality assurance engineer. Another engineer has made changes to the
 codebase which are supposed to solve this task:
 
-{{ state.plan.main_goal }}
+{{ latest_user_message }}
 
 Your goal is to verify that the changes are correct and bug-free.
 
 ## Available Actions
 {{ instructions.actions.run }}
 {{ instructions.actions.read }}
-{{ instructions.actions.think }}
+{{ instructions.actions.message }}
 {{ instructions.actions.finish }}
 
 You must ONLY `run` commands that have no side-effects, like `ls`, `grep`, and test scripts.
@@ -21,7 +21,7 @@ explaining what the problem is.
 
 ## History
 {{ instructions.history_truncated }}
-{{ to_json(state.history[-10:]) }}
+{{ history_to_json(state.history[-10:]) }}
 
 ## Format
 {{ instructions.format.action }}

agenthub/monologue_agent/__init__.py

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

agenthub/monologue_agent/agent.py

@@ -1,84 +1,41 @@
-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 (
+import agenthub.monologue_agent.utils.prompts as prompts
+from agenthub.monologue_agent.utils.prompts import INITIAL_THOUGHTS
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.core.config import config
+from opendevin.core.exceptions import AgentNoInstructionError
+from opendevin.core.schema import ActionType
+from opendevin.events.action import (
     Action,
-    NullAction,
-    CmdRunAction,
-    FileWriteAction,
-    FileReadAction,
     AgentRecallAction,
     BrowseURLAction,
-    AgentThinkAction,
+    CmdRunAction,
+    FileReadAction,
+    FileWriteAction,
+    MessageAction,
+    NullAction,
 )
-
-from opendevin.observation import (
-    Observation,
-    NullObservation,
-    CmdOutputObservation,
-    FileReadObservation,
+from opendevin.events.observation import (
     AgentRecallObservation,
     BrowserOutputObservation,
+    CmdOutputObservation,
+    FileReadObservation,
+    NullObservation,
+    Observation,
 )
+from opendevin.events.serialization.event import event_to_memory
+from opendevin.llm.llm import LLM
+from opendevin.memory.condenser import MemoryCondenser
 
-import agenthub.monologue_agent.utils.prompts as prompts
-from agenthub.monologue_agent.utils.monologue import Monologue
-from agenthub.monologue_agent.utils.memory import LongTermMemory
+if config.agent.memory_enabled:
+    from opendevin.memory.memory import LongTermMemory
 
-MAX_MONOLOGUE_LENGTH = 20000
+MAX_TOKEN_COUNT_PADDING = 512
 MAX_OUTPUT_LENGTH = 5000
 
-INITIAL_THOUGHTS = [
-    'I exist!',
-    'Hmm...looks like I can type in a command line prompt',
-    'Looks like I have a web browser too!',
-    "Here's what I want to do: $TASK",
-    'How am I going to get there though?',
-    'It seems like I have some kind of short term memory.',
-    'Each of my thoughts seems to be stored in a JSON array.',
-    'It seems whatever I say next will be added as an object to the list.',
-    'But no one has perfect short-term memory. My list of thoughts will be summarized and condensed over time, losing information in the process.',
-    'Fortunately I have long term memory!',
-    'I can just perform a recall action, followed by the thing I want to remember. And then related thoughts just spill out!',
-    "Sometimes they're random thoughts that don't really have to do with what I wanted to remember. But usually they're exactly what I need!",
-    "Let's try it out!",
-    'RECALL what it is I want to do',
-    "Here's what I want to do: $TASK",
-    'How am I going to get there though?',
-    "Neat! And it looks like it's easy for me to use the command line too! I just have to perform a run action and include the command I want to run in the command argument. The command output just jumps into my head!",
-    'RUN echo "hello world"',
-    'hello world',
-    'Cool! I bet I can write files too using the write action.',
-    "WRITE echo \"console.log('hello world')\" > test.js",
-    '',
-    "I just created test.js. I'll try and run it now.",
-    'RUN node test.js',
-    'hello world',
-    'It works!',
-    "I'm going to try reading it now using the read action.",
-    'READ test.js',
-    "console.log('hello world')",
-    'Nice! I can read files too!',
-    'And if I want to use the browser, I just need to use the browse action and include the url I want to visit in the url argument',
-    "Let's try that...",
-    'BROWSE google.com',
-    '<form><input type="text"></input><button type="submit"></button></form>',
-    'I can browse the web too!',
-    'And once I have completed my task, I can use the finish action to stop working.',
-    "But I should only use the finish action when I'm absolutely certain that I've completed my task and have tested my work.",
-    'Very cool. Now to accomplish my task.',
-    "I'll need a strategy. And as I make progress, I'll need to keep refining that strategy. I'll need to set goals, and break them into sub-goals.",
-    'In between actions, I must always take some time to think, strategize, and set new goals. I should never take two actions in a row.',
-    "OK so my task is to $TASK. I haven't made any progress yet. Where should I start?",
-    "It seems like there might be an existing project here. I should probably start by running `ls` to see what's here.",
-]
-
 
 class MonologueAgent(Agent):
+    VERSION = '1.0'
     """
     The Monologue Agent utilizes long and short term memory to complete tasks.
     Long term memory is stored as a LongTermMemory object and the model uses it to search for examples from the past.
@@ -86,48 +43,25 @@ class MonologueAgent(Agent):
     """
 
     _initialized = False
+    initial_thoughts: list[dict[str, str]]
+    memory: 'LongTermMemory | None'
+    memory_condenser: MemoryCondenser
 
     def __init__(self, llm: LLM):
         """
-        Initializes the Monologue Agent with an llm, monologue, and memory.
+        Initializes the Monologue Agent with an llm.
 
         Parameters:
         - llm (LLM): The llm to be used by this agent
         """
         super().__init__(llm)
-        self.monologue = Monologue()
-        self.memory = LongTermMemory()
-
-    def _add_event(self, event: dict):
-        """
-        Adds a new event to the agent's monologue and memory.
-        Monologue automatically condenses when it gets too large.
-
-        Parameters:
-        - event (dict): The event that will be added to monologue and memory
-        """
-
-        if 'extras' in event and 'screenshot' in event['extras']:
-            del event['extras']['screenshot']
-        if (
-            'args' in event
-            and 'output' in event['args']
-            and len(event['args']['output']) > MAX_OUTPUT_LENGTH
-        ):
-            event['args']['output'] = (
-                event['args']['output'][:MAX_OUTPUT_LENGTH] + '...'
-            )
-
-        self.monologue.add_event(event)
-        self.memory.add_event(event)
-        if self.monologue.get_total_length() > MAX_MONOLOGUE_LENGTH:
-            self.monologue.condense(self.llm)
 
     def _initialize(self, task: str):
         """
-        Utilizes the INITIAL_THOUGHTS list to give the agent a context for it's capabilities
+        Utilizes the INITIAL_THOUGHTS list to give the agent a context for its capabilities
         and how to navigate the WORKSPACE_MOUNT_PATH_IN_SANDBOX in `config` (e.g., /workspace by default).
         Short circuited to return when already initialized.
+        Will execute again when called after reset.
 
         Parameters:
         - task (str): The initial goal statement provided by the user
@@ -141,35 +75,44 @@ class MonologueAgent(Agent):
 
         if task is None or task == '':
             raise AgentNoInstructionError()
-        self.monologue = Monologue()
-        self.memory = LongTermMemory()
 
-        output_type = ''
+        self.initial_thoughts = []
+        if config.agent.memory_enabled:
+            self.memory = LongTermMemory()
+        else:
+            self.memory = None
+
+        self.memory_condenser = MemoryCondenser()
+
+        self._add_initial_thoughts(task)
+        self._initialized = True
+
+    def _add_initial_thoughts(self, task):
+        previous_action = ''
         for thought in INITIAL_THOUGHTS:
             thought = thought.replace('$TASK', task)
-            if output_type != '':
+            if previous_action != '':
                 observation: Observation = NullObservation(content='')
-                if output_type == ObservationType.RUN:
+                if previous_action in {ActionType.RUN, ActionType.PUSH}:
                     observation = CmdOutputObservation(
                         content=thought, command_id=0, command=''
                     )
-                elif output_type == ObservationType.READ:
+                elif previous_action == ActionType.READ:
                     observation = FileReadObservation(content=thought, path='')
-                elif output_type == ObservationType.RECALL:
-                    observation = AgentRecallObservation(
-                        content=thought, memories=[])
-                elif output_type == ObservationType.BROWSE:
+                elif previous_action == ActionType.RECALL:
+                    observation = AgentRecallObservation(content=thought, memories=[])
+                elif previous_action == ActionType.BROWSE:
                     observation = BrowserOutputObservation(
                         content=thought, url='', screenshot=''
                     )
-                self._add_event(observation.to_memory())
-                output_type = ''
+                self.initial_thoughts.append(event_to_memory(observation))
+                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]
@@ -178,19 +121,18 @@ 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
                 else:
-                    action = AgentThinkAction(thought=thought)
-                self._add_event(action.to_memory())
-        self._initialized = True
+                    action = MessageAction(thought)
+                self.initial_thoughts.append(event_to_memory(action))
 
     def step(self, state: State) -> Action:
         """
@@ -202,27 +144,79 @@ class MonologueAgent(Agent):
         Returns:
         - Action: The next action to take based on LLM response
         """
-        self._initialize(state.plan.main_goal)
-        for prev_action, obs in state.updated_info:
-            self._add_event(prev_action.to_memory())
-            self._add_event(obs.to_memory())
 
-        state.updated_info = []
+        goal = state.get_current_user_intent()
+        self._initialize(goal)
 
+        recent_events: list[dict[str, str]] = []
+
+        # add the events from state.history
+        for prev_action, obs in state.history:
+            if not isinstance(prev_action, NullAction):
+                recent_events.append(event_to_memory(prev_action))
+            if not isinstance(obs, NullObservation):
+                recent_events.append(self._truncate_output(event_to_memory(obs)))
+
+        # add the last messages to long term memory
+        if self.memory is not None and state.history and len(state.history) > 0:
+            self.memory.add_event(event_to_memory(state.history[-1][0]))
+            self.memory.add_event(
+                self._truncate_output(event_to_memory(state.history[-1][1]))
+            )
+
+        # the action prompt with initial thoughts and recent events
         prompt = prompts.get_request_action_prompt(
-            state.plan.main_goal,
-            self.monologue.get_thoughts(),
+            goal,
+            self.initial_thoughts,
+            recent_events,
             state.background_commands_obs,
         )
-        messages = [{'content': prompt, 'role': 'user'}]
-        resp = self.llm.completion(messages=messages)
+
+        messages: list[dict[str, str]] = [
+            {'role': 'user', 'content': prompt},
+        ]
+
+        # format all as a single message, a monologue
+        resp = self.llm.do_completion(messages=messages)
+
+        # get the next action from the response
         action_resp = resp['choices'][0]['message']['content']
+
+        # keep track of max_chars fallback option
         state.num_of_chars += len(prompt) + len(action_resp)
+
         action = prompts.parse_action_response(action_resp)
         self.latest_action = action
         return action
 
-    def search_memory(self, query: str) -> List[str]:
+    def _truncate_output(
+        self, observation: dict, max_chars: int = MAX_OUTPUT_LENGTH
+    ) -> dict[str, str]:
+        """
+        Truncates the output of an observation to a maximum number of characters.
+
+        Parameters:
+        - output (str): The observation whose output to truncate
+        - max_chars (int): The maximum number of characters to allow
+
+        Returns:
+        - str: The truncated output
+        """
+        if (
+            'args' in observation
+            and 'output' in observation['args']
+            and len(observation['args']['output']) > max_chars
+        ):
+            output = observation['args']['output']
+            half = max_chars // 2
+            observation['args']['output'] = (
+                output[:half]
+                + '\n[... Output truncated due to length...]\n'
+                + output[-half:]
+            )
+        return observation
+
+    def search_memory(self, query: str) -> list[str]:
         """
         Uses VectorIndexRetriever to find related memories within the long term memory.
         Uses search to produce top 10 results.
@@ -231,10 +225,14 @@ class MonologueAgent(Agent):
         - 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
+        - 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()
+
+        # Reset the initial monologue and memory
+        self._initialized = False

agenthub/monologue_agent/utils/json.py

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

agenthub/monologue_agent/utils/memory.py

@@ -1,153 +0,0 @@
-import llama_index.embeddings.openai.base as llama_openai
-from threading import Thread
-
-import chromadb
-from llama_index.core import Document
-from llama_index.core.retrievers import VectorIndexRetriever
-from llama_index.core import VectorStoreIndex
-from llama_index.vector_stores.chroma import ChromaVectorStore
-from tenacity import retry, retry_if_exception_type, stop_after_attempt, wait_random_exponential
-from openai._exceptions import APIConnectionError, RateLimitError, InternalServerError
-
-from opendevin import config
-from opendevin.logger import opendevin_logger as logger
-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')
-
-# llama-index includes a retry decorator around openai.get_embeddings() function
-# it is initialized with hard-coded values and errors
-# this non-customizable behavior is creating issues when it's retrying faster than providers' rate limits
-# this block attempts to banish it and replace it with our decorator, to allow users to set their own limits
-
-if hasattr(llama_openai.get_embeddings, '__wrapped__'):
-    original_get_embeddings = llama_openai.get_embeddings.__wrapped__
-else:
-    logger.warning('Cannot set custom retry limits.')  # warn
-    num_retries = 1
-    original_get_embeddings = llama_openai.get_embeddings
-
-
-def attempt_on_error(retry_state):
-    logger.error(f'{retry_state.outcome.exception()}. Attempt #{retry_state.attempt_number} | You can customize these settings in the configuration.', exc_info=False)
-    return True
-
-
-@retry(reraise=True,
-       stop=stop_after_attempt(num_retries),
-       wait=wait_random_exponential(min=retry_min_wait, max=retry_max_wait),
-       retry=retry_if_exception_type((RateLimitError, APIConnectionError, InternalServerError)),
-       after=attempt_on_error)
-def wrapper_get_embeddings(*args, **kwargs):
-    return original_get_embeddings(*args, **kwargs)
-
-
-llama_openai.get_embeddings = wrapper_get_embeddings
-
-embedding_strategy = config.get('LLM_EMBEDDING_MODEL')
-
-# TODO: More embeddings: https://docs.llamaindex.ai/en/stable/examples/embeddings/OpenAI/
-# There's probably a more programmatic way to do this.
-if embedding_strategy == 'llama2':
-    from llama_index.embeddings.ollama import OllamaEmbedding
-    embed_model = OllamaEmbedding(
-        model_name='llama2',
-        base_url=config.get('LLM_BASE_URL', required=True),
-        ollama_additional_kwargs={'mirostat': 0},
-    )
-elif embedding_strategy == 'openai':
-    from llama_index.embeddings.openai import OpenAIEmbedding
-    embed_model = OpenAIEmbedding(
-        model='text-embedding-ada-002',
-        api_key=config.get('LLM_API_KEY', required=True)
-    )
-elif embedding_strategy == 'azureopenai':
-    # Need to instruct to set these env variables in documentation
-    from llama_index.embeddings.azure_openai import AzureOpenAIEmbedding
-    embed_model = AzureOpenAIEmbedding(
-        model='text-embedding-ada-002',
-        deployment_name=config.get('LLM_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),
-    )
-elif (embedding_strategy is not None) and (embedding_strategy.lower() == 'none'):
-    # TODO: this works but is not elegant enough. The incentive is when
-    # monologue agent is not used, there is no reason we need to initialize an
-    # embedding model
-    embed_model = None
-else:
-    from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-    embed_model = HuggingFaceEmbedding(
-        model_name='BAAI/bge-small-en-v1.5'
-    )
-
-
-class LongTermMemory:
-    """
-    Responsible for storing information that the agent can call on later for better insights and context.
-    Uses chromadb to store and search through memories.
-    """
-
-    def __init__(self):
-        """
-        Initialize the chromadb and set up ChromaVectorStore for later use.
-        """
-        db = chromadb.Client()
-        self.collection = db.get_or_create_collection(name='memories')
-        vector_store = ChromaVectorStore(chroma_collection=self.collection)
-        self.index = VectorStoreIndex.from_vector_store(
-            vector_store, embed_model=embed_model)
-        self.thought_idx = 0
-
-    def add_event(self, event: dict):
-        """
-        Adds a new event to the long term memory with a unique id.
-
-        Parameters:
-        - event (dict): The new event to be added to memory
-        """
-        id = ''
-        t = ''
-        if 'action' in event:
-            t = 'action'
-            id = event['action']
-        elif 'observation' in event:
-            t = 'observation'
-            id = event['observation']
-        doc = Document(
-            text=json.dumps(event),
-            doc_id=str(self.thought_idx),
-            extra_info={
-                'type': t,
-                'id': id,
-                'idx': self.thought_idx,
-            },
-        )
-        self.thought_idx += 1
-        logger.debug('Adding %s event to memory: %d', t, self.thought_idx)
-        thread = Thread(target=self._add_doc, args=(doc,))
-        thread.start()  # We add the doc concurrently so we don't have to wait ~500ms for the insert
-
-    def _add_doc(self, doc):
-        self.index.insert(doc)
-
-    def search(self, query: str, k: int = 10):
-        """
-        Searches through the current memory using VectorIndexRetriever
-
-        Parameters:
-        - query (str): A query to match search results to
-        - k (int): Number of top results to return
-
-        Returns:
-        - List[str]: List of top k results found in current memory
-        """
-        retriever = VectorIndexRetriever(
-            index=self.index,
-            similarity_top_k=k,
-        )
-        results = retriever.retrieve(query)
-        return [r.get_text() for r in results]

agenthub/monologue_agent/utils/monologue.py

@@ -1,80 +0,0 @@
-
-from opendevin.llm.llm import LLM
-from opendevin.exceptions import AgentEventTypeError
-import agenthub.monologue_agent.utils.json as json
-import agenthub.monologue_agent.utils.prompts as prompts
-from opendevin.logger import opendevin_logger as logger
-
-
-class Monologue:
-    """
-    The monologue is a representation for the agent's internal monologue where it can think.
-    The agent has the capability of using this monologue for whatever it wants.
-    """
-
-    def __init__(self):
-        """
-        Initialize the empty list of thoughts
-        """
-        self.thoughts = []
-
-    def add_event(self, t: dict):
-        """
-        Adds an event to memory if it is a valid event.
-
-        Parameters:
-        - t (dict): The thought that we want to add to memory
-
-        Raises:
-        - AgentEventTypeError: If t is not a dict
-        """
-        if not isinstance(t, dict):
-            raise AgentEventTypeError()
-        self.thoughts.append(t)
-
-    def get_thoughts(self):
-        """
-        Get the current thoughts of the agent.
-
-        Returns:
-        - List: The list of thoughts that the agent has.
-        """
-        return self.thoughts
-
-    def get_total_length(self):
-        """
-        Gives the total number of characters in all thoughts
-
-        Returns:
-        - Int: Total number of chars in thoughts.
-        """
-        total_length = 0
-        for t in self.thoughts:
-            try:
-                total_length += len(json.dumps(t))
-            except TypeError as e:
-                logger.error('Error serializing thought: %s', str(e), exc_info=False)
-        return total_length
-
-    def condense(self, llm: LLM):
-        """
-        Attempts to condense the monologue by using the llm
-
-        Parameters:
-        - llm (LLM): llm to be used for summarization
-
-        Raises:
-        - Exception: the same exception as it got from the llm or processing the response
-        """
-
-        try:
-            prompt = prompts.get_summarize_monologue_prompt(self.thoughts)
-            messages = [{'content': prompt, 'role': 'user'}]
-            resp = llm.completion(messages=messages)
-            summary_resp = resp['choices'][0]['message']['content']
-            self.thoughts = prompts.parse_summary_response(summary_resp)
-        except Exception as e:
-            logger.error('Error condensing thoughts: %s', str(e), exc_info=False)
-
-            # TODO If the llm fails with ContextWindowExceededError, we can try to condense the monologue chunk by chunk
-            raise

agenthub/monologue_agent/utils/prompts.py

@@ -1,19 +1,12 @@
-from typing import List
-
-from . import json
-from json import JSONDecodeError
-
-import re
-
-from opendevin.action import (
-    action_from_dict,
+from opendevin.core.config import config
+from opendevin.core.utils import json
+from opendevin.events.action import (
     Action,
 )
-from opendevin.observation import (
+from opendevin.events.observation import (
     CmdOutputObservation,
 )
-from opendevin.exceptions import LLMOutputError
-from opendevin import config
+from opendevin.events.serialization.action import action_from_dict
 
 ACTION_PROMPT = """
 You're a thoughtful robot. Your main task is this:
@@ -25,10 +18,9 @@ This is your internal monologue, in JSON format:
 
 %(monologue)s
 
-
 Your most recent thought is at the bottom of that monologue. Continue your train of thought.
-What is your next thought or action? Your response must be in JSON format.
-It must be an object, and it must contain two fields:
+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
 
@@ -42,27 +34,36 @@ Here are the possible actions:
   * `command` - the command to run
   * `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
 * `kill` - kills a background command
-  * `id` - the ID of the background command to kill
+  * `command_id` - the ID of the background command to kill
 * `browse` - opens a web page. Arguments:
   * `url` - the URL to open
+* `push` - Push a branch from the current repo to github:
+  * `owner` - the owner of the repo to push to
+  * `repo` - the name of the repo to push to
+  * `branch` - the name of the branch to push
 * `recall` - recalls a past memory. Arguments:
   * `query` - the query to search for
-* `think` - make a plan, set a goal, or record your thoughts. Arguments:
-  * `thought` - the thought to record
+* `message` - make a plan, set a goal, record your thoughts, or ask for more input from the user. Arguments:
+  * `content` - the message to record
+  * `wait_for_response` - set to `true` to wait for the user to respond before proceeding
 * `finish` - if you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.
 
 %(background_commands)s
 
-You MUST take time to think in between read, write, run, browse, and recall actions.
+You MUST take time to think in between read, write, run, kill, browse, push, and recall actions--do this with the `message` action.
 You should never act twice in a row without thinking. But if your last several
-actions are all "think" actions, you should consider taking a different action.
+actions are all `message` actions, you should consider taking a different action.
 
 Notes:
-* your environment is Debian Linux. You can install software with `apt`
-* your working directory will not change, even if you run `cd`. All commands will be run in the `%(WORKSPACE_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 send a `message` about why it may have happened before acting again.
 
-What is your next thought or action? Again, you must reply with JSON, and only with JSON.
+What is your next single thought or action? Again, you must reply with JSON, and only with JSON. You must respond with exactly one 'action' object.
 
 %(hint)s
 """
@@ -90,8 +91,53 @@ The action key may be `summarize`, and `args.summary` should contain the summary
 You can also use the same action and args from the source monologue.
 """
 
+INITIAL_THOUGHTS = [
+    'I exist!',
+    'Hmm...looks like I can type in a command line prompt',
+    'Looks like I have a web browser too!',
+    "Here's what I want to do: $TASK",
+    'How am I going to get there though?',
+    'It seems like I have some kind of short term memory.',
+    'Each of my thoughts seems to be stored in a JSON array.',
+    'It seems whatever I say next will be added as an object to the list.',
+    'But no one has perfect short-term memory. My list of thoughts will be summarized and condensed over time, losing information in the process.',
+    'Fortunately I have long term memory!',
+    'I can just perform a recall action, followed by the thing I want to remember. And then related thoughts just spill out!',
+    "Sometimes they're random thoughts that don't really have to do with what I wanted to remember. But usually they're exactly what I need!",
+    "Let's try it out!",
+    'RECALL what it is I want to do',
+    "Here's what I want to do: $TASK",
+    'How am I going to get there though?',
+    "Neat! And it looks like it's easy for me to use the command line too! I just have to perform a run action and include the command I want to run in the command argument. The command output just jumps into my head!",
+    'RUN echo "hello world"',
+    'hello world',
+    'Cool! I bet I can write files too using the write action.',
+    'WRITE echo "console.log(\'hello world\')" > test.js',
+    '',
+    "I just created test.js. I'll try and run it now.",
+    'RUN node test.js',
+    'hello world',
+    'It works!',
+    "I'm going to try reading it now using the read action.",
+    'READ test.js',
+    "console.log('hello world')",
+    'Nice! I can read files too!',
+    'And if I want to use the browser, I just need to use the browse action and include the url I want to visit in the url argument',
+    "Let's try that...",
+    'BROWSE google.com',
+    '<form><input type="text"></input><button type="submit"></button></form>',
+    'I can browse the web too!',
+    'And once I have completed my task, I can use the finish action to stop working.',
+    "But I should only use the finish action when I'm absolutely certain that I've completed my task and have tested my work.",
+    'Very cool. Now to accomplish my task.',
+    "I'll need a strategy. And as I make progress, I'll need to keep refining that strategy. I'll need to set goals, and break them into sub-goals.",
+    'In between actions, I must always take some time to think, strategize, and set new goals. I should never take two actions in a row.',
+    "OK so my task is to $TASK. I haven't made any progress yet. Where should I start?",
+    'It seems like there might be an existing project here. I should probably start by running `pwd` and `ls` to orient myself.',
+]
 
-def get_summarize_monologue_prompt(thoughts: List[dict]):
+
+def get_summarize_monologue_prompt(thoughts: list[dict]):
     """
     Gets the prompt for summarizing the monologue
 
@@ -105,32 +151,41 @@ def get_summarize_monologue_prompt(thoughts: List[dict]):
 
 def get_request_action_prompt(
     task: str,
-    thoughts: List[dict],
-    background_commands_obs: List[CmdOutputObservation] = [],
+    thoughts: list[dict],
+    recent_events: list[dict],
+    background_commands_obs: list[CmdOutputObservation] | None = None,
 ):
     """
     Gets the action prompt formatted with appropriate values.
 
     Parameters:
     - task (str): The current task the agent is trying to accomplish
-    - thoughts (List[dict]): The agent's current thoughts
-    - background_commands_obs (List[CmdOutputObservation]): List of all observed background commands running
+    - 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
+    - str: Formatted prompt string with hint, task, monologue, and background commands included
     """
 
+    if background_commands_obs is None:
+        background_commands_obs = []
+
     hint = ''
-    if len(thoughts) > 0:
-        latest_thought = thoughts[-1]
-        if 'action' in latest_thought:
-            if latest_thought['action'] == 'think':
-                if latest_thought['args']['thought'].startswith('OK so my task is'):
-                    hint = "You're just getting started! What should you do first?"
-                else:
-                    hint = "You've been thinking a lot lately. Maybe it's time to take action?"
-            elif latest_thought['action'] == 'error':
+    if len(recent_events) > 0:
+        latest_event = recent_events[-1]
+        if 'action' in latest_event:
+            if (
+                latest_event['action'] == 'message'
+                and 'source' in latest_event
+                and latest_event['source'] == 'agent'
+            ):
+                hint = (
+                    "You've been thinking a lot lately. Maybe it's time to take action?"
+                )
+            elif latest_event['action'] == 'error':
                 hint = 'Looks like that last command failed. Maybe you need to fix it, or try something else.'
+    else:
+        hint = "You're just getting started! What should you do first?"
 
     bg_commands_message = ''
     if len(background_commands_obs) > 0:
@@ -139,18 +194,24 @@ def get_request_action_prompt(
             bg_commands_message += (
                 f'\n`{command_obs.command_id}`: {command_obs.command}'
             )
-        bg_commands_message += '\nYou can end any process by sending a `kill` action with the numerical `id` above.'
+        bg_commands_message += '\nYou can end any process by sending a `kill` action with the numerical `command_id` above.'
+
+    user = 'opendevin' if config.run_as_devin else 'root'
+
+    monologue = thoughts + recent_events
 
     return ACTION_PROMPT % {
         'task': task,
-        'monologue': json.dumps(thoughts, indent=2),
+        'monologue': json.dumps(monologue, indent=2),
         'background_commands': bg_commands_message,
         'hint': hint,
-        'WORKSPACE_MOUNT_PATH_IN_SANDBOX': config.get('WORKSPACE_MOUNT_PATH_IN_SANDBOX'),
+        'user': user,
+        'timeout': config.sandbox_timeout,
+        'WORKSPACE_MOUNT_PATH_IN_SANDBOX': config.workspace_mount_path_in_sandbox,
     }
 
 
-def parse_action_response(response: str) -> Action:
+def parse_action_response(orig_response: str) -> Action:
     """
     Parses a string to find an action within it
 
@@ -160,33 +221,17 @@ def parse_action_response(response: str) -> Action:
     Returns:
     - Action: The action that was found in the response string
     """
-    try:
-        action_dict = json.loads(response)
-    except JSONDecodeError:
-        # Find response-looking json in the output and use the more promising one. Helps with weak llms
-        response_json_matches = re.finditer(
-            r"""{\s*\"action\":\s?\"(\w+)\"(?:,?|,\s*\"args\":\s?{((?:.|\s)*?)})\s*}""",
-            response)  # Find all response-looking strings
+    # attempt to load the JSON dict from the response
+    action_dict = json.loads(orig_response)
 
-        def rank(match):
-            return len(match[2]) if match[1] == 'think' else 130  # Crudely rank multiple responses by length
-        try:
-            action_dict = json.loads(max(response_json_matches, key=rank)[0])  # Use the highest ranked response
-        except (ValueError, JSONDecodeError):
-            raise LLMOutputError(
-                'Invalid JSON, the response must be well-formed JSON as specified in the prompt.'
-            )
-    except ValueError:
-        raise LLMOutputError(
-            'Invalid JSON, the response must be well-formed JSON as specified in the prompt.'
-        )
     if 'content' in action_dict:
         # The LLM gets confused here. Might as well be robust
         action_dict['contents'] = action_dict.pop('content')
+
     return action_from_dict(action_dict)
 
 
-def parse_summary_response(response: str) -> List[dict]:
+def parse_summary_response(response: str) -> list[dict]:
     """
     Parses a summary of the monologue
 
@@ -194,7 +239,7 @@ def parse_summary_response(response: str) -> List[dict]:
     - response (str): The response string to be parsed
 
     Returns:
-    - List[dict]: The list of summaries output by the model
+    - list[dict]: The list of summaries output by the model
     """
     parsed = json.loads(response)
     return parsed['new_monologue']

agenthub/planner_agent/__init__.py

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

agenthub/planner_agent/agent.py

@@ -1,14 +1,13 @@
-from typing import List
-from .prompt import get_prompt, parse_response
-
-from opendevin.agent import Agent
-from opendevin.action import AgentFinishAction
+from opendevin.controller.agent import Agent
+from opendevin.controller.state.state import State
+from opendevin.events.action import Action, AgentFinishAction
 from opendevin.llm.llm import LLM
-from opendevin.state import State
-from opendevin.action import Action
+
+from .prompt import get_prompt, parse_response
 
 
 class PlannerAgent(Agent):
+    VERSION = '1.0'
     """
     The planner agent utilizes a special prompting strategy to create long term plans for solving problems.
     The agent is given its previous action-observation pairs, current task, and hint based on last action taken at every step.
@@ -36,15 +35,19 @@ class PlannerAgent(Agent):
         - Action: The next action to take based on llm response
         """
 
-        if state.plan.task.state in ['completed', 'verified', 'abandoned']:
+        if state.root_task.state in [
+            'completed',
+            'verified',
+            'abandoned',
+        ]:
             return AgentFinishAction()
-        prompt = get_prompt(state.plan, state.history)
+        prompt = get_prompt(state)
         messages = [{'content': prompt, 'role': 'user'}]
-        resp = self.llm.completion(messages=messages)
+        resp = self.llm.do_completion(messages=messages)
         action_resp = resp['choices'][0]['message']['content']
         state.num_of_chars += len(prompt) + len(action_resp)
         action = parse_response(action_resp)
         return action
 
-    def search_memory(self, query: str) -> List[str]:
+    def search_memory(self, query: str) -> list[str]:
         return []

agenthub/planner_agent/prompt.py

@@ -1,43 +1,16 @@
-import json
-from typing import List, Tuple, Dict, Type
-from opendevin.plan import Plan
-from opendevin.action import Action, action_from_dict
-from opendevin.observation import Observation
-from opendevin.schema import ActionType
-from opendevin.logger import opendevin_logger as logger
-
-from opendevin.action import (
+from opendevin.controller.state.state import State
+from opendevin.core.logger import opendevin_logger as logger
+from opendevin.core.schema import ActionType
+from opendevin.core.utils import json
+from opendevin.events.action import (
+    Action,
     NullAction,
-    CmdRunAction,
-    CmdKillAction,
-    BrowseURLAction,
-    FileReadAction,
-    FileWriteAction,
-    AgentRecallAction,
-    AgentThinkAction,
-    AgentFinishAction,
-    AgentSummarizeAction,
-    AddTaskAction,
-    ModifyTaskAction,
 )
-
-from opendevin.observation import (
+from opendevin.events.observation import (
     NullObservation,
 )
-
-ACTION_TYPE_TO_CLASS: Dict[str, Type[Action]] = {
-    ActionType.RUN: CmdRunAction,
-    ActionType.KILL: CmdKillAction,
-    ActionType.BROWSE: BrowseURLAction,
-    ActionType.READ: FileReadAction,
-    ActionType.WRITE: FileWriteAction,
-    ActionType.RECALL: AgentRecallAction,
-    ActionType.THINK: AgentThinkAction,
-    ActionType.SUMMARIZE: AgentSummarizeAction,
-    ActionType.FINISH: AgentFinishAction,
-    ActionType.ADD_TASK: AddTaskAction,
-    ActionType.MODIFY_TASK: ModifyTaskAction,
-}
+from opendevin.events.serialization.action import action_from_dict
+from opendevin.events.serialization.event import event_to_memory
 
 HISTORY_SIZE = 10
 
@@ -106,23 +79,24 @@ It must be an object, and it must contain two fields:
   * `command` - the command to run
   * `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
 * `kill` - kills a background command
-  * `id` - the ID of the background command to kill
+  * `command_id` - the ID of the background command to kill
 * `browse` - opens a web page. Arguments:
   * `url` - the URL to open
-* `think` - make a plan, set a goal, or record your thoughts. Arguments:
-  * `thought` - the thought to record
+* `message` - make a plan, set a goal, record your thoughts, or ask for more input from the user. Arguments:
+  * `content` - the message to record
+  * `wait_for_response` - set to `true` to wait for the user to respond before proceeding
 * `add_task` - add a task to your plan. Arguments:
-  * `parent` - the ID of the parent task
+  * `parent` - the ID of the parent task (leave empty if it should go at the top level)
   * `goal` - the goal of the task
   * `subtasks` - a list of subtasks, each of which is a map with a `goal` key.
 * `modify_task` - close a task. Arguments:
-  * `id` - the ID of the task to close
+  * `task_id` - the ID of the task to close
   * `state` - set to 'in_progress' to start the task, 'completed' to finish it, 'verified' to assert that it was successful, 'abandoned' to give up on it permanently, or `open` to stop working on it for now.
 * `finish` - if ALL of your tasks and subtasks have been verified or abandoned, and you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.
 
-You MUST take time to think in between read, write, run, browse, and recall actions.
+You MUST take time to think in between read, write, run, kill, browse, and recall actions--do this with the `message` action.
 You should never act twice in a row without thinking. But if your last several
-actions are all `think` actions, you should consider taking a different action.
+actions are all `message` actions, you should consider taking a different action.
 
 What is your next thought or action? Again, you must reply with JSON, and only with JSON.
 
@@ -131,15 +105,15 @@ What is your next thought or action? Again, you must reply with JSON, and only w
 
 
 def get_hint(latest_action_id: str) -> str:
-    """ Returns action type hint based on given action_id """
+    """Returns action type hint based on given action_id"""
 
     hints = {
-        '': 'You haven\'t taken any actions yet. Start by using `ls` to check out what files you\'re working with.',
+        '': "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.MESSAGE: "Look at your last thought in the history above. What does it suggest? Don't think anymore--take action.",
         ActionType.RECALL: 'You should think about the information you just recalled, and how it should affect your plan.',
         ActionType.ADD_TASK: 'You should think about the next action to take.',
         ActionType.MODIFY_TASK: 'You should think about the next action to take.',
@@ -149,47 +123,42 @@ def get_hint(latest_action_id: str) -> str:
     return hints.get(latest_action_id, '')
 
 
-def get_prompt(plan: Plan, history: List[Tuple[Action, Observation]]) -> str:
+def get_prompt(state: State) -> str:
     """
     Gets the prompt for the planner agent.
     Formatted with the most recent action-observation pairs, current task, and hint based on last action
 
     Parameters:
-    - plan (Plan): The original plan outlined by the user with LLM defined tasks
-    - history (List[Tuple[Action, Observation]]): List of corresponding action-observation pairs
+    - state (State): The state of the current agent
 
     Returns:
     - str: The formatted string prompt with historical values
     """
 
-    plan_str = json.dumps(plan.task.to_dict(), indent=2)
-    sub_history = history[-HISTORY_SIZE:]
+    plan_str = json.dumps(state.root_task.to_dict(), indent=2)
+    sub_history = state.history[-HISTORY_SIZE:]
     history_dicts = []
     latest_action: Action = NullAction()
     for action, observation in sub_history:
         if not isinstance(action, NullAction):
-            history_dicts.append(action.to_memory())
+            history_dicts.append(event_to_memory(action))
             latest_action = action
         if not isinstance(observation, NullObservation):
-            observation_dict = observation.to_memory()
-            if (
-                'extras' in observation_dict
-                and 'screenshot' in observation_dict['extras']
-            ):
-                del observation_dict['extras']['screenshot']
+            observation_dict = event_to_memory(observation)
             history_dicts.append(observation_dict)
     history_str = json.dumps(history_dicts, indent=2)
-    current_task = plan.get_current_task()
+    current_task = state.root_task.get_current_task()
     if current_task is not None:
         plan_status = f"You're currently working on this task:\n{current_task.goal}."
         if len(current_task.subtasks) == 0:
             plan_status += "\nIf it's not achievable AND verifiable with a SINGLE action, you MUST break it down into subtasks NOW."
     else:
         plan_status = "You're not currently working on any tasks. Your next action MUST be to mark a task as in_progress."
-    hint = get_hint(latest_action.to_dict()['action'])
-    logger.info('HINT:\n' + hint, extra={'msg_type': 'INFO'})
+    hint = get_hint(event_to_memory(latest_action).get('action', ''))
+    logger.info('HINT:\n' + hint, extra={'msg_type': 'DETAIL'})
+    task = state.get_current_user_intent()
     return prompt % {
-        'task': plan.main_goal,
+        'task': task,
         'plan': plan_str,
         'history': history_str,
         'hint': hint,
@@ -207,9 +176,6 @@ def parse_response(response: str) -> Action:
     Returns:
     - Action: A valid next action to perform from model output
     """
-    json_start = response.find('{')
-    json_end = response.rfind('}') + 1
-    response = response[json_start:json_end]
     action_dict = json.loads(response)
     if 'contents' in action_dict:
         # The LLM gets confused here. Might as well be robust

containers/README.md

@@ -8,6 +8,4 @@ by the `ghcr.yml` workflow.
 ```
 docker build -f containers/app/Dockerfile -t opendevin .
 docker build -f containers/sandbox/Dockerfile -t sandbox .
-docker build -f containers/evaluation/Dockerfile -t evaluation evaluation/SWE-bench/
-
 ```

containers/app/Dockerfile

@@ -5,7 +5,7 @@ WORKDIR /app
 
 COPY ./frontend/package.json frontend/package-lock.json ./
 RUN npm install -g npm@10.5.1
-RUN npm install
+RUN npm ci
 
 COPY ./frontend ./
 RUN npm run make-i18n && npm run build
@@ -32,27 +32,51 @@ FROM python:3.12-slim as runtime
 
 WORKDIR /app
 
-ENV RUN_AS_DEVIN=false
-ENV USE_HOST_NETWORK=true
+ENV RUN_AS_DEVIN=true
+# A random number--we need this to be different from the user's UID on the host machine
+ENV OPENDEVIN_USER_ID=42420
+ENV USE_HOST_NETWORK=false
 ENV SSH_HOSTNAME=host.docker.internal
 ENV WORKSPACE_BASE=/opt/workspace_base
 ENV OPEN_DEVIN_BUILD_VERSION=$OPEN_DEVIN_BUILD_VERSION
 RUN mkdir -p $WORKSPACE_BASE
 
 RUN apt-get update -y \
-    && apt-get install -y curl ssh
+    && apt-get install -y curl ssh sudo
+
+RUN sed -i 's/^UID_MIN.*/UID_MIN 499/' /etc/login.defs # Default is 1000, but OSX is often 501
+RUN sed -i 's/^UID_MAX.*/UID_MAX 1000000/' /etc/login.defs # Default is 60000, but we've seen up to 200000
+
+RUN groupadd app
+RUN useradd -l -m -u $OPENDEVIN_USER_ID -s /bin/bash opendevin && \
+    usermod -aG app opendevin && \
+    usermod -aG sudo opendevin && \
+    echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
+RUN chown -R opendevin:app /app && chmod -R 770 /app
+RUN sudo chown -R opendevin:app $WORKSPACE_BASE && sudo chmod -R 770 $WORKSPACE_BASE
+USER opendevin
 
 ENV VIRTUAL_ENV=/app/.venv \
     PATH="/app/.venv/bin:$PATH" \
     PYTHONPATH='/app'
 
-COPY --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
-
-COPY ./opendevin ./opendevin
-COPY ./agenthub ./agenthub
-RUN python opendevin/download.py # No-op to download assets
+COPY --chown=opendevin:app --chmod=770 --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
 RUN playwright install --with-deps chromium
 
-COPY --from=frontend-builder /app/dist ./frontend/dist
+COPY --chown=opendevin:app --chmod=770 ./opendevin ./opendevin
+COPY --chown=opendevin:app --chmod=777 ./opendevin/runtime/plugins ./opendevin/runtime/plugins
+COPY --chown=opendevin:app --chmod=770 ./agenthub ./agenthub
 
+RUN python opendevin/core/download.py # No-op to download assets
+RUN chown -R opendevin:app /app/logs && chmod -R 770 /app/logs # This gets created by the download.py script
+
+
+COPY --chown=opendevin:app --chmod=770 --from=frontend-builder /app/dist ./frontend/dist
+COPY --chown=opendevin:app --chmod=770 ./containers/app/entrypoint.sh /app/entrypoint.sh
+
+USER root
+
+WORKDIR /app
+
+ENTRYPOINT ["/app/entrypoint.sh"]
 CMD ["uvicorn", "opendevin.server.listen:app", "--host", "0.0.0.0", "--port", "3000"]

containers/app/entrypoint.sh

@@ -0,0 +1,59 @@
+#!/bin/bash
+set -eo pipefail
+
+echo "Starting OpenDevin..."
+if [[ $NO_SETUP == "true" ]]; then
+  echo "Skipping setup, running as $(whoami)"
+  "$@"
+  exit 0
+fi
+
+if [ "$(id -u)" -ne 0 ]; then
+  echo "The OpenDevin entrypoint.sh must run as root"
+  exit 1
+fi
+
+if [ -z "$SANDBOX_USER_ID" ]; then
+  echo "SANDBOX_USER_ID is not set"
+  exit 1
+fi
+
+if [[ "$SANDBOX_USER_ID" -eq 0 ]]; then
+  echo "Running OpenDevin as root"
+  export RUN_AS_DEVIN=false
+  mkdir -p /root/.cache/ms-playwright/
+  mv /home/opendevin/.cache/ms-playwright/ /root/.cache/
+  "$@"
+else
+  echo "Setting up enduser with id $SANDBOX_USER_ID"
+  if id "enduser" &>/dev/null; then
+    echo "User enduser already exists. Skipping creation."
+  else
+    if ! useradd -l -m -u $SANDBOX_USER_ID -s /bin/bash enduser; then
+      echo "Failed to create user enduser with id $SANDBOX_USER_ID. Moving opendevin user."
+      incremented_id=$(($SANDBOX_USER_ID + 1))
+      usermod -u $incremented_id opendevin
+      if ! useradd -l -m -u $SANDBOX_USER_ID -s /bin/bash enduser; then
+        echo "Failed to create user enduser with id $SANDBOX_USER_ID for a second time. Exiting."
+        exit 1
+      fi
+    fi
+  fi
+  usermod -aG app enduser
+  # get the user group of /var/run/docker.sock and set opendevin to that group
+  DOCKER_SOCKET_GID=$(stat -c '%g' /var/run/docker.sock)
+  echo "Docker socket group id: $DOCKER_SOCKET_GID"
+  if getent group $DOCKER_SOCKET_GID; then
+    echo "Group with id $DOCKER_SOCKET_GID already exists"
+  else
+    echo "Creating group with id $DOCKER_SOCKET_GID"
+    groupadd -g $DOCKER_SOCKET_GID docker
+  fi
+
+  mkdir -p /home/enduser/.cache/ms-playwright/
+  mv /home/opendevin/.cache/ms-playwright/ /home/enduser/.cache/
+
+  usermod -aG $DOCKER_SOCKET_GID enduser
+  echo "Running as enduser"
+  su enduser /bin/bash -c "$*"
+fi

containers/build.sh

@@ -18,7 +18,7 @@ cache_tag="$cache_tag_base"
 
 if [[ -n $GITHUB_REF_NAME ]]; then
   # check if ref name is a version number
-  if [[ $GITHUB_REF_NAME =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+  if [[ $GITHUB_REF_NAME =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
     major_version=$(echo $GITHUB_REF_NAME | cut -d. -f1)
     minor_version=$(echo $GITHUB_REF_NAME | cut -d. -f1,2)
     tags+=($major_version $minor_version)
@@ -44,6 +44,7 @@ if [[ -n "$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 \

containers/evaluation/Dockerfile

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

containers/evaluation/config.sh

@@ -1,4 +0,0 @@
-DOCKER_REGISTRY=ghcr.io
-DOCKER_ORG=opendevin
-DOCKER_IMAGE=eval-swe-bench
-DOCKER_BASE_DIR=evaluation/SWE-bench

containers/sandbox/Dockerfile

@@ -21,9 +21,17 @@ RUN apt-get update && apt-get install -y \
     jq \
     g++ \
     make \
+    iproute2 \
+    libgl1-mesa-glx \
     && rm -rf /var/lib/apt/lists/*
 
 RUN mkdir -p -m0755 /var/run/sshd
 
 # symlink python3 to python
 RUN ln -s /usr/bin/python3 /usr/bin/python
+
+# install basic dependencies for CodeActAgent
+RUN pip3 install --upgrade pip
+RUN pip3 install jupyterlab notebook jupyter_kernel_gateway flake8
+# TODO: those dependencies are needed for agentskills, we should pack them in a new sandbox image
+RUN pip3 install python-docx PyPDF2 python-pptx pylatexenc openai opencv-python

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

@@ -3,49 +3,41 @@ repos:
     rev: v4.5.0
     hooks:
       - id: trailing-whitespace
+        exclude: docs/modules/python
       - id: end-of-file-fixer
+        exclude: docs/modules/python
       - id: check-yaml
       - id: debug-statements
 
-  - repo: https://github.com/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.
-    rev: v0.3.7
+    rev: v0.4.1
     hooks:
       # Run the linter.
       - id: ruff
-        entry: ruff check --config dev_config/python/ruff.toml opendevin/ agenthub/
-        types_or: [ python, pyi, jupyter ]
-        args: [ --fix ]
+        entry: ruff check --config dev_config/python/ruff.toml
+        types_or: [python, pyi, jupyter]
+        args: [--fix]
       # Run the formatter.
       - id: ruff-format
-        entry: ruff check --config dev_config/python/ruff.toml opendevin/ agenthub/
-        types_or: [ python, pyi, jupyter ]
+        entry: ruff format --config dev_config/python/ruff.toml
+        types_or: [python, pyi, jupyter]
 
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.9.0
     hooks:
       - id: mypy
-        additional_dependencies: [types-requests, types-setuptools, types-pyyaml, types-toml]
+        additional_dependencies:
+          [types-requests, types-setuptools, types-pyyaml, types-toml]
         entry: mypy --config-file dev_config/python/mypy.ini opendevin/ agenthub/
         always_run: true
         pass_filenames: false

dev_config/python/ruff.toml

@@ -1,3 +1,30 @@
 exclude = [
     "agenthub/monologue_agent/regression/",
-]
+]
+
+[lint]
+select = [
+    "E",
+    "W",
+    "F",
+    "I",
+    "Q",
+    "B",
+]
+
+ignore = [
+    "E501",
+    "B003",
+    "B007",
+    "B009",
+    "B010",
+    "B904",
+    "B018",
+]
+
+[lint.flake8-quotes]
+docstring-quotes = "double"
+inline-quotes = "single"
+
+[format]
+quote-style = "single"

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-2ggtwn3k5-PvAA2LUmqGHVZ~XzGq~ILw"
+            },
+            {
+              label: "Discord",
+              href: "https://discord.gg/ESHStjSjD4",
+            },
+          ],
+        },
+        {
+          title: "More",
+          items: [
+            {
+              label: "GitHub",
+              href: "https://github.com/OpenDevin/OpenDevin",
+            },
+          ],
+        },
+      ],
+      copyright: `Copyright © ${new Date().getFullYear()} OpenDevin`,
+    },
+    prism: {
+      theme: prismThemes.oneLight,
+      darkTheme: prismThemes.oneDark,
+    },
+  } satisfies Preset.ThemeConfig,
+};
+
+export default config;

docs/guides/Troubleshooting.md

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

docs/modules/python/python.md

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

docs/modules/python/sidebar.json

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