Add RuntimeManager to centralize runtime management

.devcontainer/README.MD

@@ -1 +0,0 @@
-The files in this directory configure a development container for GitHub Codespaces.

.devcontainer/devcontainer.json

@@ -1,15 +0,0 @@
-{
-	"name": "OpenDevin Codespaces",
-	"image": "mcr.microsoft.com/devcontainers/universal",
-	"customizations":{
-        "vscode":{
-            "extensions": [
-                "ms-python.python"
-            ]
-        }
-    },
-	"onCreateCommand": "sh ./.devcontainer/on_create.sh",
-	"postCreateCommand": "make build",
-	"postStartCommand": "USE_HOST_NETWORK=True nohup bash -c 'make run &'"
-
-}

.devcontainer/on_create.sh

@@ -1,8 +0,0 @@
-#!/usr/bin/env bash
-sudo apt update
-sudo apt install -y netcat
-sudo add-apt-repository -y ppa:deadsnakes/ppa
-sudo apt install -y python3.11
-curl -sSL https://install.python-poetry.org | python3.11 -
-# chromadb requires SQLite > 3.35 but SQLite in Python3.11.9 comes with 3.31.1
-sudo cp /opt/conda/lib/libsqlite3.so.0 /lib/x86_64-linux-gnu/libsqlite3.so.0

.dockerignore

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

.gitattributes

@@ -1 +0,0 @@
-*.ipynb linguist-vendored

.github/.codecov.yml

@@ -1,19 +0,0 @@
-codecov:
-  notify:
-    wait_for_ci: true
-    # our project is large, so 6 builds are typically uploaded. this waits till 5/6
-    # See https://docs.codecov.com/docs/notifications#section-preventing-notifications-until-after-n-builds
-    after_n_builds: 5
-
-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

.github/ISSUE_TEMPLATE/bug_template.yml

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

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,18 +0,0 @@
----
-name: Feature Request
-about: Suggest an idea for OpenDevin features
-title: ''
-labels: 'enhancement'
-assignees: ''
-
----
-
-**What problem or use case are you trying to solve?**
-
-**Describe the UX of the solution you'd like**
-
-**Do you have thoughts on the technical implementation?**
-
-**Describe alternatives you've considered**
-
-**Additional context**

.github/ISSUE_TEMPLATE/technical_proposal.md

@@ -1,18 +0,0 @@
----
-name: Technical Proposal
-about: Propose a new architecture or technology
-title: ''
-labels: 'proposal'
-assignees: ''
-
----
-
-**Summary**
-
-**Motivation**
-
-**Technical Design**
-
-**Alternatives to Consider**
-
-**Additional context**

.github/dependabot.yml

@@ -1,22 +0,0 @@
-# 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"
-    open-pull-requests-limit: 20
-  - package-ecosystem: "npm" # See documentation for possible values
-    directory: "/frontend" # Location of package manifests
-    schedule:
-      interval: "daily"
-    open-pull-requests-limit: 20
-  - package-ecosystem: "npm" # See documentation for possible values
-    directory: "/docs" # Location of package manifests
-    schedule:
-      interval: "daily"
-    open-pull-requests-limit: 20

.github/pull_request_template.md

@@ -1,11 +0,0 @@
-**What is the problem that this fixes or functionality that this introduces? Does it fix any open issues?**
-
-
-
----
-**Give a summary of what the PR does, explaining any non-trivial design decisions**
-
-
-
----
-**Other references**

.github/workflows/deploy-docs.yml

@@ -1,59 +0,0 @@
-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

@@ -1,42 +0,0 @@
-name: Run E2E test with dummy agent
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-
-on:
-  push:
-    branches:
-    - main
-  pull_request:
-
-env:
-  PERSIST_SANDBOX : "false"
-
-jobs:
-  test:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.11'
-      - name: Set up environment
-        run: |
-          curl -sSL https://install.python-poetry.org | python3 -
-          poetry install --without evaluation,llama-index
-          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: |
-          set -e
-          poetry run python opendevin/core/main.py -t "do a flip" -d ./workspace/ -c DummyAgent
-      - name: Check exit code
-        run: |
-          if [ $? -ne 0 ]; then
-            echo "Test failed"
-            exit 1
-          else
-            echo "Test passed"
-          fi

.github/workflows/ghcr.yml

@@ -1,481 +0,0 @@
-name: Build Publish and Test Runtime 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:
-        description: 'Reason for manual trigger'
-        required: true
-        default: ''
-
-jobs:
-  ghcr_build:
-    runs-on: ubuntu-latest
-
-    outputs:
-      tags: ${{ steps.capture-tags.outputs.tags }}
-
-    permissions:
-      contents: read
-      packages: write
-
-    strategy:
-      matrix:
-        image: ["sandbox", "opendevin"]
-        platform: ["amd64", "arm64"]
-
-    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
-
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Build and export image
-        id: build
-        run: ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} ${{ matrix.platform }}
-
-      - name: Capture tags
-        id: capture-tags
-        run: |
-          tags=$(cat tags.txt)
-          echo "tags=$tags"
-          echo "tags=$tags" >> $GITHUB_OUTPUT
-
-      - name: Upload Docker image as artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
-          path: /tmp/${{ matrix.image }}_image_${{ matrix.platform }}.tar
-
-  ghcr_build_runtime:
-    runs-on: ubuntu-latest
-
-    outputs:
-      tags: ${{ steps.capture-tags.outputs.tags }}
-
-    permissions:
-      contents: read
-      packages: write
-
-    strategy:
-      matrix:
-        image: ["od_runtime"]
-        base_image: ["ubuntu:22.04"]
-        platform: ["amd64", "arm64"]
-
-    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
-
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-
-      - 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: make install-python-dependencies
-
-      - name: Create source distribution and Dockerfile
-        run: poetry run python3 opendevin/runtime/utils/runtime_build.py --base_image ${{ matrix.base_image }} --build_folder containers/runtime
-
-      - name: Build and export image
-        id: build
-        run: ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} ${{ matrix.platform }}
-
-      - name: Capture tags
-        id: capture-tags
-        run: |
-          tags=$(cat tags.txt)
-          echo "tags=$tags"
-          echo "tags=$tags" >> $GITHUB_OUTPUT
-
-      - name: Upload Docker image as artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
-          path: /tmp/${{ matrix.image }}_image_${{ matrix.platform }}.tar
-
-  test_runtime:
-    name: Test Runtime
-    runs-on: ubuntu-latest
-    needs: [ghcr_build_runtime, ghcr_build]
-    env:
-      PERSIST_SANDBOX: "false"
-
-    strategy:
-      matrix:
-        runtime_type: ["eventstream", "server"]
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # when 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
-          swap-storage: true
-
-      - 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: make install-python-dependencies
-
-      - name: Download Runtime Docker image
-        if: matrix.runtime_type == 'eventstream'
-        uses: actions/download-artifact@v4
-        with:
-          name: od_runtime-docker-image-amd64
-          path: /tmp/
-
-      - name: Download Sandbox Docker image
-        if: matrix.runtime_type == 'server'
-        uses: actions/download-artifact@v4
-        with:
-          name: sandbox-docker-image-amd64
-          path: /tmp/
-
-      - name: Load Runtime image and run runtime tests
-        run: |
-          # Load the Docker image and capture the output
-          if [ "${{ matrix.runtime_type }}" == "eventstream" ]; then
-            output=$(docker load -i /tmp/od_runtime_image_amd64.tar)
-          else
-            output=$(docker load -i /tmp/sandbox_image_amd64.tar)
-          fi
-
-          # Extract the first image name from the output
-          image_name=$(echo "$output" | grep -oP 'Loaded image: \K.*' | head -n 1)
-
-          # Print the full name of the image
-          echo "Loaded Docker image: $image_name"
-
-          TEST_RUNTIME=${{ matrix.runtime_type }} SANDBOX_USER_ID=$(id -u) SANDBOX_CONTAINER_IMAGE=$image_name TEST_IN_CI=true poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml -s ./tests/unit/test_runtime.py
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
-  integration_tests_on_linux:
-    name: Integration Tests on Linux
-    runs-on: ubuntu-latest
-    needs: ghcr_build
-    env:
-      PERSIST_SANDBOX: "false"
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ["3.11"]
-        sandbox: ["ssh", "local"]
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
-
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-
-      - name: Download sandbox Docker image
-        uses: actions/download-artifact@v4
-        with:
-          name: sandbox-docker-image-amd64
-          path: /tmp/
-
-      - name: Load sandbox image and run integration tests
-        env:
-          SANDBOX_BOX_TYPE: ${{ matrix.sandbox }}
-        run: |
-          # Load the Docker image and capture the output
-          output=$(docker load -i /tmp/sandbox_image_amd64.tar)
-
-          # Extract the first image name from the output
-          image_name=$(echo "$output" | grep -oP 'Loaded image: \K.*' | head -n 1)
-
-          # Print the full name of the image
-          echo "Loaded Docker image: $image_name"
-
-          SANDBOX_CONTAINER_IMAGE=$image_name 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 }}
-
-
-  ghcr_push:
-    runs-on: ubuntu-latest
-    # don't push if integration tests or sandbox tests fail
-    needs: [ghcr_build, test_runtime, integration_tests_on_linux]
-    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
-
-    env:
-      tags: ${{ needs.ghcr_build.outputs.tags }}
-
-    permissions:
-      contents: read
-      packages: write
-
-    strategy:
-      matrix:
-        image: ["sandbox", "opendevin"]
-        platform: ["amd64", "arm64"]
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Login to GHCR
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Download Docker images
-        uses: actions/download-artifact@v4
-        with:
-          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
-          path: /tmp/${{ matrix.platform }}
-
-      - name: Load images and push to registry
-        run: |
-          mv /tmp/${{ matrix.platform }}/${{ matrix.image }}_image_${{ matrix.platform }}.tar .
-          loaded_image=$(docker load -i ${{ matrix.image }}_image_${{ matrix.platform }}.tar | grep "Loaded image:" | head -n 1 | awk '{print $3}')
-          echo "loaded image = $loaded_image"
-          tags=$(echo ${tags} | tr ' ' '\n')
-          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
-          echo "image name = $image_name"
-          for tag in $tags; do
-            echo "tag = $tag"
-            docker tag $loaded_image $image_name:${tag}_${{ matrix.platform }}
-            docker push $image_name:${tag}_${{ matrix.platform }}
-          done
-
-  ghcr_push_runtime:
-    runs-on: ubuntu-latest
-    # don't push if runtime tests fail
-    needs: [ghcr_build_runtime, test_runtime, integration_tests_on_linux]
-    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
-
-    env:
-      tags: ${{ needs.ghcr_build_runtime.outputs.tags }}
-
-    permissions:
-      contents: read
-      packages: write
-
-    strategy:
-      matrix:
-        image: ["od_runtime"]
-        platform: ["amd64", "arm64"]
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          tool-cache: true
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
-
-      - name: Login to GHCR
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Download Docker images
-        uses: actions/download-artifact@v4
-        with:
-          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
-          path: /tmp/${{ matrix.platform }}
-
-      - name: List downloaded files
-        run: |
-          ls -la /tmp/${{ matrix.platform }}
-          file /tmp/${{ matrix.platform }}/*
-
-      - name: Load images and push to registry
-        run: |
-          mv /tmp/${{ matrix.platform }}/${{ matrix.image }}_image_${{ matrix.platform }}.tar ./${{ matrix.image }}_image_${{ matrix.platform }}.tar
-          if ! loaded_image=$(docker load -i ${{ matrix.image }}_image_${{ matrix.platform }}.tar | grep "Loaded image:" | head -n 1 | awk '{print $3}'); then
-            echo "Failed to load Docker image"
-            exit 1
-          fi
-          echo "loaded image = $loaded_image"
-          tags=$(echo ${tags} | tr ' ' '\n')
-          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
-          echo "image name = $image_name"
-          for tag in $tags; do
-            echo "tag = $tag"
-            if [ -n "$image_name" ]; then
-              docker tag $loaded_image $image_name:${tag}_${{ matrix.platform }}
-              docker push $image_name:${tag}_${{ matrix.platform }}
-            else
-              echo "Skipping tag and push due to empty image_name"
-            fi
-          done
-
-  create_manifest:
-    runs-on: ubuntu-latest
-    needs: [ghcr_build, ghcr_push]
-    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
-
-    env:
-      tags: ${{ needs.ghcr_build.outputs.tags }}
-
-    strategy:
-      matrix:
-        image: ["sandbox", "opendevin"]
-
-    permissions:
-      contents: read
-      packages: write
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Login to GHCR
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Create and push multi-platform manifest
-        run: |
-          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
-          echo "image name = $image_name"
-          tags=$(echo ${tags} | tr ' ' '\n')
-          for tag in $tags; do
-            echo 'tag = $tag'
-            docker buildx imagetools create --tag $image_name:$tag \
-              $image_name:${tag}_amd64 \
-              $image_name:${tag}_arm64
-          done
-
-  create_manifest_runtime:
-    runs-on: ubuntu-latest
-    needs: [ghcr_build_runtime, ghcr_push_runtime]
-    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
-
-    env:
-      tags: ${{ needs.ghcr_build_runtime.outputs.tags }}
-
-    strategy:
-      matrix:
-        image: ["od_runtime"]
-
-    permissions:
-      contents: read
-      packages: write
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Login to GHCR
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Create and push multi-platform manifest
-        run: |
-          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
-          echo "image name = $image_name"
-          tags=$(echo ${tags} | tr ' ' '\n')
-          for tag in $tags; do
-            echo 'tag = $tag'
-            docker buildx imagetools create --tag $image_name:$tag \
-              $image_name:${tag}_amd64 \
-              $image_name:${tag}_arm64
-          done

.github/workflows/lint.yml

@@ -1,50 +0,0 @@
-name: Lint
-
-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
-
-      - name: Install Node.js 20
-        uses: actions/setup-node@v4
-        with:
-          node-version: 20
-
-      - name: Install dependencies
-        run: |
-          cd frontend
-          npm install --frozen-lockfile
-
-      - name: Lint
-        run: |
-          cd frontend
-          npm run lint
-
-  lint-python:
-    name: Lint python
-    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/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml

.github/workflows/review-pr.yml

@@ -1,85 +0,0 @@
-name: Use OpenDevin to Review Pull Request
-
-on:
-  pull_request:
-    types: [synchronize, labeled]
-
-permissions:
-  contents: write
-  pull-requests: write
-
-jobs:
-  dogfood:
-    if: contains(github.event.pull_request.labels.*.name, 'review-this')
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v4
-    - name: Set up Python
-      uses: actions/setup-python@v5
-      with:
-        python-version: '3.11'
-    - name: install git, github cli
-      run: |
-        sudo apt-get install -y git gh
-        git config --global --add safe.directory $PWD
-
-    - name: Checkout Repository
-      uses: actions/checkout@v4
-      with:
-        ref: ${{ github.event.pull_request.base.ref }} # check out the target branch
-
-    - name: Download Diff
-      run: |
-        curl -O "${{ github.event.pull_request.diff_url }}" -L
-
-    - name: Write Task File
-      run: |
-        echo "Your coworker wants to apply a pull request to this project." > task.txt
-        echo "Read and review ${{ github.event.pull_request.number }}.diff file. Create a review-${{ github.event.pull_request.number }}.txt and write your concise comments and suggestions there." >> task.txt
-        echo "Do not ask me for confirmation at any point." >> task.txt
-        echo "" >> task.txt
-        echo "Title" >> task.txt
-        echo "${{ github.event.pull_request.title }}" >> task.txt
-        echo "" >> task.txt
-        echo "Description" >> task.txt
-        echo "${{ github.event.pull_request.body }}" >> task.txt
-        echo "" >> task.txt
-        echo "Diff file is: ${{ github.event.pull_request.number }}.diff" >> task.txt
-
-    - name: Set up environment
-      run: |
-        curl -sSL https://install.python-poetry.org | python3 -
-        export PATH="/github/home/.local/bin:$PATH"
-        poetry install --without evaluation,llama-index
-        poetry run playwright install --with-deps chromium
-
-    - name: Run OpenDevin
-      env:
-        LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
-        LLM_MODEL: ${{ vars.LLM_MODEL }}
-        SANDBOX_BOX_TYPE: ssh
-      run: |
-        # Append path to launch poetry
-        export PATH="/github/home/.local/bin:$PATH"
-        # Append path to correctly import package, note: must set pwd at first
-        export PYTHONPATH=$(pwd):$PYTHONPATH
-        export WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE
-        export WORKSPACE_BASE=$GITHUB_WORKSPACE
-        echo -e "/exit\n" | poetry run python opendevin/core/main.py -i 50 -f task.txt
-        rm task.txt
-
-    - name: Check if review file is non-empty
-      id: check_file
-      run: |
-        ls -la
-        if [[ -s review-${{ github.event.pull_request.number }}.txt ]]; then
-          echo "non_empty=true" >> $GITHUB_OUTPUT
-        fi
-      shell: bash
-
-    - name: Create PR review if file is non-empty
-      env:
-        GH_TOKEN: ${{ github.token }}
-      if: steps.check_file.outputs.non_empty == 'true'
-      run: |
-        gh pr review ${{ github.event.pull_request.number }} --comment --body-file "review-${{ github.event.pull_request.number }}.txt"

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

@@ -1,167 +0,0 @@
-name: Run Unit Tests
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-
-on:
-  push:
-    branches:
-      - main
-    paths-ignore:
-      - '**/*.md'
-      - 'frontend/**'
-      - 'docs/**'
-      - 'evaluation/**'
-  pull_request:
-
-env:
-  PERSIST_SANDBOX : "false"
-
-jobs:
-  fe-test:
-    runs-on: ubuntu-latest
-
-    strategy:
-      matrix:
-        node-version: [20]
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Set up Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: ${{ matrix.node-version }}
-
-      - name: Install dependencies
-        working-directory: ./frontend
-        run: npm ci
-
-      - name: Run tests and collect coverage
-        working-directory: ./frontend
-        run: npm run test:coverage
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
-  test-on-macos:
-    name: Test on macOS
-    runs-on: macos-12
-    env:
-      INSTALL_DOCKER: "1" # Set to '0' to skip Docker installation
-    strategy:
-      matrix:
-        python-version: ["3.11"]
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation,llama-index
-
-      - name: Install & Start Docker
-        if: env.INSTALL_DOCKER == '1'
-        run: |
-          INSTANCE_NAME="colima-${GITHUB_RUN_ID}"
-
-          # Uninstall colima to upgrade to the latest version
-          if brew list colima &>/dev/null; then
-            brew uninstall colima
-            # unlinking colima dependency: go
-            brew uninstall go@1.21
-          fi
-          rm -rf ~/.colima ~/.lima
-          brew install --HEAD colima
-          brew install docker
-
-          start_colima() {
-            # Find a free port in the range 10000-20000
-            RANDOM_PORT=$((RANDOM % 10001 + 10000))
-
-            # Original line:
-            if ! colima start --network-address --arch x86_64 --cpu=1 --memory=1 --verbose --ssh-port $RANDOM_PORT; then
-              echo "Failed to start Colima."
-              return 1
-            fi
-            return 0
-          }
-
-          # Attempt to start Colima for 5 total attempts:
-          ATTEMPT_LIMIT=5
-          for ((i=1; i<=ATTEMPT_LIMIT; i++)); do
-
-            if start_colima; then
-              echo "Colima started successfully."
-              break
-            else
-              colima stop -f
-              sleep 10
-              colima delete -f
-              if [ $i -eq $ATTEMPT_LIMIT ]; then
-                exit 1
-              fi
-              sleep 10
-            fi
-          done
-
-          # For testcontainers to find the Colima socket
-          # https://github.com/abiosoft/colima/blob/main/docs/FAQ.md#cannot-connect-to-the-docker-daemon-at-unixvarrundockersock-is-the-docker-daemon-running
-          sudo ln -sf $HOME/.colima/default/docker.sock /var/run/docker.sock
-
-      - name: Build Environment
-        run: make build
-
-      - name: Run Tests
-        run: poetry run pytest --forked --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox.py and not test_runtime.py"
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-  test-on-linux:
-    name: Test on Linux
-    runs-on: ubuntu-latest
-    env:
-      INSTALL_DOCKER: "0" # Set to '0' to skip Docker installation
-    strategy:
-      matrix:
-        python-version: ["3.11"]
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation,llama-index
-
-      - name: Build Environment
-        run: make build
-
-      - name: Run Tests
-        run: poetry run pytest --forked --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox.py and not test_runtime.py"
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

.github/workflows/solve-issue.yml

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

.github/workflows/stale.yml

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

.github/workflows/update-pyproject-version.yml

@@ -1,48 +0,0 @@
-name: Update pyproject.toml Version and Tags
-
-on:
-  release:
-    types:
-      - published
-
-jobs:
-  update-pyproject-and-tags:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0  # Fetch all history for all branches and tags
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install toml
-
-      - name: Get release tag
-        id: get_release_tag
-        run: echo "RELEASE_TAG=${GITHUB_REF#refs/tags/}" >> $GITHUB_ENV
-
-      - name: Update pyproject.toml with release tag
-        run: |
-          python -c "
-          import toml
-          with open('pyproject.toml', 'r') as f:
-              data = toml.load(f)
-          data['tool']['poetry']['version'] = '${{ env.RELEASE_TAG }}'
-          with open('pyproject.toml', 'w') as f:
-              toml.dump(data, f)
-          "
-
-      - name: Commit and push pyproject.toml changes
-        uses: stefanzweifel/git-auto-commit-action@v4
-        with:
-          commit_message: "Update pyproject.toml version to ${{ env.RELEASE_TAG }}"
-          branch: main
-          file_pattern: pyproject.toml

.gitignore

@@ -1,226 +0,0 @@
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-./lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-requirements.txt
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-.python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-# poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/#use-with-ide
-.pdm.toml
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-.env.bak
-venv.bak/
-*venv/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-.idea/
-.vscode/
-.cursorignore
-
-# evaluation
-evaluation/evaluation_outputs
-evaluation/outputs
-evaluation/swe_bench/eval_workspace*
-evaluation/SWE-bench/data
-evaluation/webarena/scripts/webarena_env.sh
-
-# frontend
-
-# dependencies
-frontend/node_modules
-frontend/.pnp
-frontend/bun.lockb
-frontend/yarn.lock
-.pnp.js
-
-# testing
-frontend/coverage
-test_results*
-/_test_files_tmp/
-
-# production
-frontend/build
-frontend/dist
-
-# misc
-.DS_Store
-.env.local
-.env.development.local
-.env.test.local
-.env.production.local
-
-npm-debug.log*
-yarn-debug.log*
-yarn-error.log*
-
-logs
-
-# agent
-.envrc
-/workspace
-/_test_workspace
-/debug
-cache
-
-# configuration
-config.toml
-config.toml_
-config.toml.bak
-
-containers/agnostic_sandbox
-
-# swe-bench-eval
-image_build_logs
-run_instance_logs
-
-od_runtime_*.tar
-
-# docker build
-containers/runtime/Dockerfile
-containers/runtime/project.tar.gz

CODE_OF_CONDUCT.md

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

CONTRIBUTING.md

@@ -1,116 +0,0 @@
-# Contributing
-
-Thanks for your interest in contributing to OpenDevin! We welcome and appreciate contributions.
-
-## How Can I Contribute?
-
-There are many ways that you can contribute:
-
-1. **Download and use** OpenDevin, and send [issues](https://github.com/OpenDevin/OpenDevin/issues) when you encounter something that isn't working or a feature that you'd like to see.
-2. **Send feedback** after each session by [clicking the thumbs-up thumbs-down buttons](https://docs.all-hands.dev/modules/usage/feedback), so we can see where things are working and failing, and also build an open dataset for training code agents.
-3. **Improve the Codebase** by sending PRs (see details below). In particular, we have some [good first issue](https://github.com/OpenDevin/OpenDevin/labels/good%20first%20issue) issues that may be ones to start on.
-
-## Understanding OpenDevin's CodeBase
-
-To understand the codebase, please refer to the README in each module:
-- [frontend](./frontend/README.md)
-- [agenthub](./agenthub/README.md)
-- [evaluation](./evaluation/README.md)
-- [opendevin](./opendevin/README.md)
-    - [server](./opendevin/server/README.md)
-
-When you write code, it is also good to write tests. Please navigate to the `tests` folder to see existing test suites.
-At the moment, we have two kinds of tests: `unit` and `integration`. Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
-
-## Sending Pull Requests to OpenDevin
-
-### 1. Fork the Official Repository
-Fork the [OpenDevin repository](https://github.com/OpenDevin/OpenDevin) into your own account.
-Clone your own forked repository into your local environment:
-
-```shell
-git clone git@github.com:<YOUR-USERNAME>/OpenDevin.git
-```
-
-### 2. Configure Git
-
-Set the official repository as your [upstream](https://www.atlassian.com/git/tutorials/git-forks-and-upstreams) to synchronize with the latest update in the official repository.
-Add the original repository as upstream:
-
-```shell
-cd OpenDevin
-git remote add upstream git@github.com:OpenDevin/OpenDevin.git
-```
-
-Verify that the remote is set:
-
-```shell
-git remote -v
-```
-
-You should see both `origin` and `upstream` in the output.
-
-### 3. Synchronize with Official Repository
-Synchronize latest commit with official repository before coding:
-
-```shell
-git fetch upstream
-git checkout main
-git merge upstream/main
-git push origin main
-```
-
-### 4. Set up the Development Environment
-
-We have a separate doc [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md) that tells you how to set up a development workflow.
-
-### 5. Write Code and Commit It
-
-Once you have done this, you can write code, test it, and commit it to a branch (replace `my_branch` with an appropriate name):
-
-```shell
-git checkout -b my_branch
-git add .
-git commit
-git push origin my_branch
-```
-
-### 6. Open a Pull Request
-
-* On GitHub, go to the page of your forked repository, and create a Pull Request:
-   - Click on `Branches`
-   - Click on the `...` beside your branch and click on `New pull request`
-   - Set `base repository` to `OpenDevin/OpenDevin`
-   - Set `base` to `main`
-   - Click `Create pull request`
-
-The PR should appear in [OpenDevin PRs](https://github.com/OpenDevin/OpenDevin/pulls).
-
-Then the OpenDevin team will review your code.
-
-## PR Rules
-
-### 1. Pull Request title
-As described [here](https://github.com/commitizen/conventional-commit-types/blob/master/index.json), a valid PR title should begin with one of the following prefixes:
-
-- `feat`: A new feature
-- `fix`: A bug fix
-- `docs`: Documentation only changes
-- `style`: Changes that do not affect the meaning of the code (white space, formatting, missing semicolons, etc.)
-- `refactor`: A code change that neither fixes a bug nor adds a feature
-- `perf`: A code change that improves performance
-- `test`: Adding missing tests or correcting existing tests
-- `build`: Changes that affect the build system or external dependencies (example scopes: gulp, broccoli, npm)
-- `ci`: Changes to our CI configuration files and scripts (example scopes: Travis, Circle, BrowserStack, SauceLabs)
-- `chore`: Other changes that don't modify src or test files
-- `revert`: Reverts a previous commit
-
-For example, a PR title could be:
-- `refactor: modify package path`
-- `feat(frontend): xxxx`, where `(frontend)` means that this PR mainly focuses on the frontend component.
-
-You may also check out previous PRs in the [PR list](https://github.com/OpenDevin/OpenDevin/pulls).
-
-### 2. Pull Request description
-- If your PR is small (such as a typo fix), you can go brief.
-- If it contains a lot of changes, it's better to write more details.

Development.md

@@ -1,99 +0,0 @@
-# Development Guide
-This guide is for people working on OpenDevin and editing the source code.
-If you wish to contribute your changes, check out the [CONTRIBUTING.md](https://github.com/OpenDevin/OpenDevin/blob/main/CONTRIBUTING.md) on how to clone and setup the project initially before moving on.
-Otherwise, you can clone the OpenDevin project directly.
-
-## Start the server for development
-### 1. Requirements
-* Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)  [ Ubuntu <= 22.04]
-* [Docker](https://docs.docker.com/engine/install/) (For those on MacOS, make sure to allow the default Docker socket to be used from advanced settings!)
-* [Python](https://www.python.org/downloads/) = 3.11
-* [NodeJS](https://nodejs.org/en/download/package-manager) >= 18.17.1
-* [Poetry](https://python-poetry.org/docs/#installing-with-the-official-installer) >= 1.8
-* netcat => sudo apt-get install netcat
-
-Make sure you have all these dependencies installed before moving on to `make build`.
-
-#### Develop without sudo access
-If you want to develop without system admin/sudo access to upgrade/install `Python` and/or `NodeJs`, you can use `conda` or `mamba` to manage the packages for you:
-
-```bash
-# Download and install Mamba (a faster version of conda)
-curl -L -O "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"
-bash Miniforge3-$(uname)-$(uname -m).sh
-
-# Install Python 3.11, nodejs, and poetry
-mamba install python=3.11
-mamba install conda-forge::nodejs
-mamba install conda-forge::poetry
-```
-
-### 2. Build and Setup The Environment
-Begin by building the project which includes setting up the environment and installing dependencies. This step ensures that OpenDevin is ready to run on your system:
-
-```bash
-make build
-```
-
-### 3. Configuring the Language Model
-OpenDevin supports a diverse array of Language Models (LMs) through the powerful [litellm](https://docs.litellm.ai) library. By default, we've chosen the mighty GPT-4 from OpenAI as our go-to model, but the world is your oyster! You can unleash the potential of Anthropic's suave Claude, the enigmatic Llama, or any other LM that piques your interest.
-
-To configure the LM of your choice, run:
-
-   ```bash
-   make setup-config
-   ```
-
-   This command will prompt you to enter the LLM API key, model name, and other variables ensuring that OpenDevin is tailored to your specific needs. Note that the model name will apply only when you run headless. If you use the UI, please set the model in the UI.
-
-   Note: If you have previously run OpenDevin using the docker command, you may have already set some environmental variables in your terminal. The final configurations are set from highest to lowest priority:
-   Environment variables > config.toml variables > default variables
-
-**Note on Alternative Models:**
-Some alternative models may prove more challenging to tame than others. Fear not, brave adventurer! We shall soon unveil LLM-specific documentation to guide you on your quest.
-And if you've already mastered the art of wielding a model other than OpenAI's GPT, we encourage you to share your setup instructions with us by creating instructions and adding it [to our documentation](https://github.com/OpenDevin/OpenDevin/tree/main/docs/modules/usage/llms).
-
-For a full list of the LM providers and models available, please consult the [litellm documentation](https://docs.litellm.ai/docs/providers).
-
-### 4. Running the application
-#### Option A: Run the Full Application
-Once the setup is complete, launching OpenDevin is as simple as running a single command. This command starts both the backend and frontend servers seamlessly, allowing you to interact with OpenDevin:
-```bash
-make run
-```
-
-#### Option B: Individual Server Startup
-- **Start the Backend Server:** If you prefer, you can start the backend server independently to focus on backend-related tasks or configurations.
-    ```bash
-    make start-backend
-    ```
-
-- **Start the Frontend Server:** Similarly, you can start the frontend server on its own to work on frontend-related components or interface enhancements.
-    ```bash
-    make start-frontend
-    ```
-
-### 6. LLM Debugging
-If you encounter any issues with the Language Model (LM) or you're simply curious, you can inspect the actual LLM prompts and responses. To do so, export DEBUG=1 in the environment and restart the backend.
-OpenDevin will then log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
-
-### 7. Help
-Need assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenDevin.
-```bash
-make help
- ```
-
-### 8. Testing
-To run tests, refer to the following:
-#### Unit tests
-
-```bash
-poetry run pytest ./tests/unit/test_*.py
-```
-
-#### Integration tests
-Please refer to [this README](./tests/integration/README.md) for details.
-
-### 9. Add or update dependency
-1. Add your dependency in `pyproject.toml` or use `poetry add xxx`
-2. Update the poetry.lock file via `poetry lock --no-update`

ISSUE_TRIAGE.md

@@ -1,25 +0,0 @@
-# Issue Triage
-These are the procedures and guidelines on how issues are triaged in this repo by the maintainers.
-
-## General
-* Most issues must be tagged with **enhancement** or **bug**
-* Issues may be tagged with what it relates to (**backend**, **frontend**, **agent quality**, etc.)
-
-## Severity
-* **Low**: Minor issues, single user report
-* **Medium**: Affecting multiple users
-* **Critical**: Affecting all users or potential security issues
-
-## Effort
-* Issues may be estimated with effort required (**small effort**, **medium effort**, **large effort**)
-
-## Difficulty
-* Issues with low implementation difficulty may be tagged with **good first issue**
-
-## Not Enough Information
-* User is asked to provide more information (logs, how to reproduce, etc.) when the issue is not clear
-* If an issue is unclear and the author does not provide more information or respond to a request, the issue may be closed as **not planned** (Usually after a week)
-
-## Multiple Requests/Fixes in One Issue
-* These issues will be narrowed down to one request/fix so the issue is more easily tracked and fixed
-* Issues may be broken down into multiple issues if required

LICENSE

@@ -1,25 +0,0 @@
-The MIT License (MIT)
-=====================
-
-Copyright © 2023
-
-Permission is hereby granted, free of charge, to any person
-obtaining a copy of this software and associated documentation
-files (the “Software”), to deal in the Software without
-restriction, including without limitation the rights to use,
-copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the
-Software is furnished to do so, subject to the following
-conditions:
-
-The above copyright notice and this permission notice shall be
-included in all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND,
-EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
-OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
-HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
-WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
-FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
-OTHER DEALINGS IN THE SOFTWARE.

Makefile

@@ -1,319 +0,0 @@
-SHELL=/bin/bash
-# Makefile for OpenDevin project
-
-# Variables
-DOCKER_IMAGE = ghcr.io/opendevin/sandbox:main
-BACKEND_PORT = 3000
-BACKEND_HOST = "127.0.0.1:$(BACKEND_PORT)"
-FRONTEND_PORT = 3001
-DEFAULT_WORKSPACE_DIR = "./workspace"
-DEFAULT_MODEL = "gpt-4o"
-CONFIG_FILE = config.toml
-PRE_COMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
-PYTHON_VERSION = 3.11
-
-# ANSI color codes
-GREEN=$(shell tput -Txterm setaf 2)
-YELLOW=$(shell tput -Txterm setaf 3)
-RED=$(shell tput -Txterm setaf 1)
-BLUE=$(shell tput -Txterm setaf 6)
-RESET=$(shell tput -Txterm sgr0)
-
-# Build
-build:
-	@echo "$(GREEN)Building project...$(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-pre-commit-hooks
-	@$(MAKE) -s build-frontend
-	@echo "$(GREEN)Build completed successfully.$(RESET)"
-
-check-dependencies:
-	@echo "$(YELLOW)Checking dependencies...$(RESET)"
-	@$(MAKE) -s check-system
-	@$(MAKE) -s check-python
-	@$(MAKE) -s check-npm
-	@$(MAKE) -s check-nodejs
-ifeq ($(INSTALL_DOCKER),)
-	@$(MAKE) -s check-docker
-endif
-	@$(MAKE) -s check-poetry
-	@echo "$(GREEN)Dependencies checked successfully.$(RESET)"
-
-check-system:
-	@echo "$(YELLOW)Checking system...$(RESET)"
-	@if [ "$(shell uname)" = "Darwin" ]; then \
-		echo "$(BLUE)macOS detected.$(RESET)"; \
-	elif [ "$(shell uname)" = "Linux" ]; then \
-		if [ -f "/etc/manjaro-release" ]; then \
-			echo "$(BLUE)Manjaro Linux detected.$(RESET)"; \
-		else \
-			echo "$(BLUE)Linux detected.$(RESET)"; \
-		fi; \
-	elif [ "$$(uname -r | grep -i microsoft)" ]; then \
-		echo "$(BLUE)Windows Subsystem for Linux detected.$(RESET)"; \
-	else \
-		echo "$(RED)Unsupported system detected. Please use macOS, Linux, or Windows Subsystem for Linux (WSL).$(RESET)"; \
-		exit 1; \
-	fi
-
-check-python:
-	@echo "$(YELLOW)Checking Python installation...$(RESET)"
-	@if command -v python$(PYTHON_VERSION) > /dev/null; then \
-		echo "$(BLUE)$(shell python$(PYTHON_VERSION) --version) is already installed.$(RESET)"; \
-	else \
-		echo "$(RED)Python $(PYTHON_VERSION) is not installed. Please install Python $(PYTHON_VERSION) to continue.$(RESET)"; \
-		exit 1; \
-	fi
-
-check-npm:
-	@echo "$(YELLOW)Checking npm installation...$(RESET)"
-	@if command -v npm > /dev/null; then \
-		echo "$(BLUE)npm $(shell npm --version) is already installed.$(RESET)"; \
-	else \
-		echo "$(RED)npm is not installed. Please install Node.js to continue.$(RESET)"; \
-		exit 1; \
-	fi
-
-check-nodejs:
-	@echo "$(YELLOW)Checking Node.js installation...$(RESET)"
-	@if command -v node > /dev/null; then \
-		NODE_VERSION=$(shell node --version | sed -E 's/v//g'); \
-		IFS='.' read -r -a NODE_VERSION_ARRAY <<< "$$NODE_VERSION"; \
-		if [ "$${NODE_VERSION_ARRAY[0]}" -gt 18 ] || ([ "$${NODE_VERSION_ARRAY[0]}" -eq 18 ] && [ "$${NODE_VERSION_ARRAY[1]}" -gt 17 ]) || ([ "$${NODE_VERSION_ARRAY[0]}" -eq 18 ] && [ "$${NODE_VERSION_ARRAY[1]}" -eq 17 ] && [ "$${NODE_VERSION_ARRAY[2]}" -ge 1 ]); then \
-			echo "$(BLUE)Node.js $$NODE_VERSION is already installed.$(RESET)"; \
-		else \
-			echo "$(RED)Node.js 18.17.1 or later is required. Please install Node.js 18.17.1 or later to continue.$(RESET)"; \
-			exit 1; \
-		fi; \
-	else \
-		echo "$(RED)Node.js is not installed. Please install Node.js to continue.$(RESET)"; \
-		exit 1; \
-	fi
-
-check-docker:
-	@echo "$(YELLOW)Checking Docker installation...$(RESET)"
-	@if command -v docker > /dev/null; then \
-		echo "$(BLUE)$(shell docker --version) is already installed.$(RESET)"; \
-	else \
-		echo "$(RED)Docker is not installed. Please install Docker to continue.$(RESET)"; \
-		exit 1; \
-	fi
-
-check-poetry:
-	@echo "$(YELLOW)Checking Poetry installation...$(RESET)"
-	@if command -v poetry > /dev/null; then \
-		POETRY_VERSION=$(shell poetry --version 2>&1 | sed -E 's/Poetry \(version ([0-9]+\.[0-9]+\.[0-9]+)\)/\1/'); \
-		IFS='.' read -r -a POETRY_VERSION_ARRAY <<< "$$POETRY_VERSION"; \
-		if [ $${POETRY_VERSION_ARRAY[0]} -ge 1 ] && [ $${POETRY_VERSION_ARRAY[1]} -ge 8 ]; then \
-			echo "$(BLUE)$(shell poetry --version) is already installed.$(RESET)"; \
-		else \
-			echo "$(RED)Poetry 1.8 or later is required. You can install poetry by running the following command, then adding Poetry to your PATH:"; \
-			echo "$(RED) curl -sSL https://install.python-poetry.org | python$(PYTHON_VERSION) -$(RESET)"; \
-			echo "$(RED)More detail here: https://python-poetry.org/docs/#installing-with-the-official-installer$(RESET)"; \
-			exit 1; \
-		fi; \
-	else \
-		echo "$(RED)Poetry is not installed. You can install poetry by running the following command, then adding Poetry to your PATH:"; \
-		echo "$(RED) curl -sSL https://install.python-poetry.org | python$(PYTHON_VERSION) -$(RESET)"; \
-		echo "$(RED)More detail here: https://python-poetry.org/docs/#installing-with-the-official-installer$(RESET)"; \
-		exit 1; \
-	fi
-
-pull-docker-image:
-	@echo "$(YELLOW)Pulling Docker image...$(RESET)"
-	@docker pull $(DOCKER_IMAGE)
-	@echo "$(GREEN)Docker image pulled successfully.$(RESET)"
-
-install-python-dependencies:
-	@echo "$(GREEN)Installing Python dependencies...$(RESET)"
-	@if [ -z "${TZ}" ]; then \
-		echo "Defaulting TZ (timezone) to UTC"; \
-		export TZ="UTC"; \
-	fi
-	poetry env use python$(PYTHON_VERSION)
-	@if [ "$(shell uname)" = "Darwin" ]; then \
-		echo "$(BLUE)Installing chroma-hnswlib...$(RESET)"; \
-		export HNSWLIB_NO_NATIVE=1; \
-		poetry run pip install chroma-hnswlib; \
-	fi
-	@poetry install --without llama-index
-	@if [ -f "/etc/manjaro-release" ]; then \
-		echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
-		poetry run pip install playwright; \
-		poetry run playwright install chromium; \
-	else \
-		if [ ! -f cache/playwright_chromium_is_installed.txt ]; then \
-			echo "Running playwright install --with-deps chromium..."; \
-			poetry run playwright install --with-deps chromium; \
-			mkdir -p cache; \
-			touch cache/playwright_chromium_is_installed.txt; \
-		else \
-			echo "Setup already done. Skipping playwright installation."; \
-		fi \
-	fi
-	@echo "$(GREEN)Python dependencies installed successfully.$(RESET)"
-
-install-frontend-dependencies:
-	@echo "$(YELLOW)Setting up frontend environment...$(RESET)"
-	@echo "$(YELLOW)Detect Node.js version...$(RESET)"
-	@cd frontend && node ./scripts/detect-node-version.js
-	echo "$(BLUE)Installing frontend dependencies with npm...$(RESET)"
-	@cd frontend && npm install
-	@echo "$(GREEN)Frontend dependencies installed successfully.$(RESET)"
-
-install-pre-commit-hooks:
-	@echo "$(YELLOW)Installing pre-commit hooks...$(RESET)"
-	@git config --unset-all core.hooksPath || true
-	@poetry run pre-commit install --config $(PRE_COMMIT_CONFIG_PATH)
-	@echo "$(GREEN)Pre-commit hooks installed successfully.$(RESET)"
-
-lint-backend:
-	@echo "$(YELLOW)Running linters...$(RESET)"
-	@poetry run pre-commit run --files opendevin/**/* agenthub/**/* evaluation/**/* --show-diff-on-failure --config $(PRE_COMMIT_CONFIG_PATH)
-
-lint-frontend:
-	@echo "$(YELLOW)Running linters for frontend...$(RESET)"
-	@cd frontend && npm run lint
-
-lint:
-	@$(MAKE) -s lint-frontend
-	@$(MAKE) -s lint-backend
-
-test-frontend:
-	@echo "$(YELLOW)Running tests for frontend...$(RESET)"
-	@cd frontend && npm run test
-
-test:
-	@$(MAKE) -s test-frontend
-
-build-frontend:
-	@echo "$(YELLOW)Building frontend...$(RESET)"
-	@cd frontend && npm run build
-
-# Start backend
-start-backend:
-	@echo "$(YELLOW)Starting backend...$(RESET)"
-	@poetry run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT) --reload --reload-exclude "workspace/*"
-
-# Start frontend
-start-frontend:
-	@echo "$(YELLOW)Starting frontend...$(RESET)"
-	@cd frontend && VITE_BACKEND_HOST=$(BACKEND_HOST) VITE_FRONTEND_PORT=$(FRONTEND_PORT) npm run start
-
-# Common setup for running the app (non-callable)
-_run_setup:
-	@if [ "$(OS)" = "Windows_NT" ]; then \
-		echo "$(RED) Windows is not supported, use WSL instead!$(RESET)"; \
-		exit 1; \
-	fi
-	@mkdir -p logs
-	@echo "$(YELLOW)Starting backend server...$(RESET)"
-	@poetry run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT) &
-	@echo "$(YELLOW)Waiting for the backend to start...$(RESET)"
-	@until nc -z localhost $(BACKEND_PORT); do sleep 0.1; done
-	@echo "$(GREEN)Backend started successfully.$(RESET)"
-
-# Run the app (standard mode)
-run:
-	@echo "$(YELLOW)Running the app...$(RESET)"
-	@$(MAKE) -s _run_setup
-	@cd frontend && echo "$(BLUE)Starting frontend with npm...$(RESET)" && npm run start -- --port $(FRONTEND_PORT)
-	@echo "$(GREEN)Application started successfully.$(RESET)"
-
-# Run the app (WSL mode)
-run-wsl:
-	@echo "$(YELLOW)Running the app in WSL mode...$(RESET)"
-	@$(MAKE) -s _run_setup
-	@cd frontend && echo "$(BLUE)Starting frontend with npm (WSL mode)...$(RESET)" && npm run dev_wsl -- --port $(FRONTEND_PORT)
-	@echo "$(GREEN)Application started successfully in WSL mode.$(RESET)"
-
-# Setup config.toml
-setup-config:
-	@echo "$(YELLOW)Setting up config.toml...$(RESET)"
-	@$(MAKE) setup-config-prompts
-	@mv $(CONFIG_FILE).tmp $(CONFIG_FILE)
-	@echo "$(GREEN)Config.toml setup completed.$(RESET)"
-
-setup-config-prompts:
-	@echo "[core]" > $(CONFIG_FILE).tmp
-
-	@read -p "Enter your workspace directory (as absolute path) [default: $(DEFAULT_WORKSPACE_DIR)]: " workspace_dir; \
-	 workspace_dir=$${workspace_dir:-$(DEFAULT_WORKSPACE_DIR)}; \
-	 echo "workspace_base=\"$$workspace_dir\"" >> $(CONFIG_FILE).tmp
-
-	@read -p "Do you want to persist the sandbox container? [true/false] [default: false]: " persist_sandbox; \
-	 persist_sandbox=$${persist_sandbox:-false}; \
-	 if [ "$$persist_sandbox" = "true" ]; then \
-		 read -p "Enter a password for the sandbox container: " ssh_password; \
-		 echo "ssh_password=\"$$ssh_password\"" >> $(CONFIG_FILE).tmp; \
-		 echo "persist_sandbox=$$persist_sandbox" >> $(CONFIG_FILE).tmp; \
-	 else \
-		echo "persist_sandbox=$$persist_sandbox" >> $(CONFIG_FILE).tmp; \
-	 fi
-
-	@echo "" >> $(CONFIG_FILE).tmp
-
-	@echo "[llm]" >> $(CONFIG_FILE).tmp
-	@read -p "Enter your LLM model name, used for running without UI. Set the model in the UI after you start the app. (see https://docs.litellm.ai/docs/providers for full list) [default: $(DEFAULT_MODEL)]: " llm_model; \
-	 llm_model=$${llm_model:-$(DEFAULT_MODEL)}; \
-	 echo "model=\"$$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\"" >> $(CONFIG_FILE).tmp; \
-		fi
-
-
-# Clean up all caches
-clean:
-	@echo "$(YELLOW)Cleaning up caches...$(RESET)"
-	@rm -rf opendevin/.cache
-	@echo "$(GREEN)Caches cleaned up successfully.$(RESET)"
-
-# Help
-help:
-	@echo "$(BLUE)Usage: make [target]$(RESET)"
-	@echo "Targets:"
-	@echo "  $(GREEN)build$(RESET)               - Build project, including environment setup and dependencies."
-	@echo "  $(GREEN)lint$(RESET)                - Run linters on the project."
-	@echo "  $(GREEN)setup-config$(RESET)        - Setup the configuration for OpenDevin by providing LLM API key,"
-	@echo "                        LLM Model name, and workspace directory."
-	@echo "  $(GREEN)start-backend$(RESET)       - Start the backend server for the OpenDevin project."
-	@echo "  $(GREEN)start-frontend$(RESET)      - Start the frontend server for the OpenDevin project."
-	@echo "  $(GREEN)run$(RESET)                 - Run the OpenDevin application, starting both backend and frontend servers."
-	@echo "                        Backend Log file will be stored in the 'logs' directory."
-	@echo "  $(GREEN)help$(RESET)                - Display this help message, providing information on available targets."
-
-# Phony targets
-.PHONY: build check-dependencies check-python check-npm check-docker check-poetry pull-docker-image install-python-dependencies install-frontend-dependencies install-pre-commit-hooks lint start-backend start-frontend run run-wsl setup-config setup-config-prompts help

README.md

@@ -1,152 +0,0 @@
-<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&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>
-  <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="./docs/static/img/logo.png" alt="Logo" width="200" height="200">
-  <h1 align="center">OpenDevin: Code Less, Make More</h1>
-  <a href="https://docs.all-hands.dev/modules/usage/intro"><img src="https://img.shields.io/badge/Documentation-OpenDevin-blue?logo=googledocs&logoColor=white&style=for-the-badge" alt="Check out the documentation"></a>
-  <a href="https://arxiv.org/abs/2407.16741"><img src="https://img.shields.io/badge/Paper-%20on%20Arxiv-red?logo=arxiv&style=for-the-badge" alt="Paper on Arxiv"></a>
-  <br/>
-  <a href="https://huggingface.co/spaces/OpenDevin/evaluation"><img src="https://img.shields.io/badge/Evaluation-Benchmark%20on%20HF%20Space-green?logo=huggingface&style=for-the-badge" alt="Evaluation Benchmark"></a>
-</div>
-<hr>
-
-Welcome to OpenDevin, a platform for autonomous software engineers, powered by AI and LLMs.
-
-OpenDevin agents collaborate with human developers to write code, fix bugs, and ship features.
-
-![App screenshot](./docs/static/img/screenshot.png)
-
-## ⚡ Getting Started
-OpenDevin works best with Docker version 26.0.0+ (Docker Desktop 4.31.0+).
-You must be using Linux, Mac OS, or WSL on Windows.
-
-To start OpenDevin in a docker container, run the following commands in your terminal:
-
-> [!WARNING]
-> When you run the following command, files in `./workspace` may be modified or deleted.
-
-```bash
-WORKSPACE_BASE=$(pwd)/workspace
-docker run -it \
-    --pull=always \
-    -e SANDBOX_USER_ID=$(id -u) \
-    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
-    -v $WORKSPACE_BASE:/opt/workspace_base \
-    -v /var/run/docker.sock:/var/run/docker.sock \
-    -p 3000:3000 \
-    --add-host host.docker.internal:host-gateway \
-    --name opendevin-app-$(date +%Y%m%d%H%M%S) \
-    ghcr.io/opendevin/opendevin
-```
-
-> [!NOTE]
-> By default, this command pulls the `latest` tag, which represents the most recent release of OpenDevin. You have other options as well:
-> - For a specific release version, use `ghcr.io/opendevin/opendevin:<OpenDevin_version>` (replace <OpenDevin_version> with the desired version number).
-> - For the most up-to-date development version, use `ghcr.io/opendevin/opendevin:main`. This version may be **(unstable!)** and is recommended for testing or development purposes only.
->
-> Choose the tag that best suits your needs based on stability requirements and desired features.
-
-You'll find OpenDevin running at [http://localhost:3000](http://localhost:3000) with access to `./workspace`. To have OpenDevin operate on your code, place it in `./workspace`.
-OpenDevin will only have access to this workspace folder. The rest of your system will not be affected as it runs in a secured docker sandbox.
-
-Upon opening OpenDevin, you must select the appropriate `Model` and enter the `API Key` within the settings that should pop up automatically. These can be set at any time by selecting
-the `Settings` button (gear icon) in the UI. If the required `Model` does not exist in the list, you can manually enter it in the text box.
-
-For the development workflow, see [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md).
-
-Are you having trouble? Check out our [Troubleshooting Guide](https://docs.all-hands.dev/modules/usage/troubleshooting).
-
-## 🚀 Documentation
-
-To learn more about the project, and for tips on using OpenDevin,
-**check out our [documentation](https://docs.all-hands.dev/modules/usage/intro)**.
-
-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:
-
-- **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 [CONTRIBUTING.md](./CONTRIBUTING.md).
-
-## 🤖 Join Our Community
-
-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-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA) - Here we talk about research, architecture, and future development.
-- [Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
-
-## 📈 Progress
-
-<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.
-
-[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
-
-## 📚 Cite
-
-```
-@misc{opendevin,
-      title={{OpenDevin: An Open Platform for AI Software Developers as Generalist Agents}}, 
-      author={Xingyao Wang and Boxuan Li and Yufan Song and Frank F. Xu and Xiangru Tang and Mingchen Zhuge and Jiayi Pan and Yueqi Song and Bowen Li and Jaskirat Singh and Hoang H. Tran and Fuqiang Li and Ren Ma and Mingzhang Zheng and Bill Qian and Yanjun Shao and Niklas Muennighoff and Yizhe Zhang and Binyuan Hui and Junyang Lin and Robert Brennan and Hao Peng and Heng Ji and Graham Neubig},
-      year={2024},
-      eprint={2407.16741},
-      archivePrefix={arXiv},
-      primaryClass={cs.SE},
-      url={https://arxiv.org/abs/2407.16741}, 
-}
-```

__init__.py

@@ -0,0 +1,37 @@
+import os
+
+__package_name__ = 'openhands_ai'
+
+
+def get_version():
+    # Try getting the version from pyproject.toml
+    try:
+        root_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+        with open(os.path.join(root_dir, 'pyproject.toml'), 'r') as f:
+            for line in f:
+                if line.startswith('version ='):
+                    return line.split('=')[1].strip().strip('"')
+    except FileNotFoundError:
+        pass
+
+    try:
+        from importlib.metadata import PackageNotFoundError, version
+
+        return version(__package_name__)
+    except (ImportError, PackageNotFoundError):
+        pass
+
+    try:
+        from pkg_resources import DistributionNotFound, get_distribution
+
+        return get_distribution(__package_name__).version
+    except (ImportError, DistributionNotFound):
+        pass
+
+    return 'unknown'
+
+
+try:
+    __version__ = get_version()
+except Exception:
+    __version__ = 'unknown'

agenthub/README.md

@@ -1,72 +0,0 @@
-# Agent Hub
-
-In this folder, there may exist multiple implementations of `Agent` that will be used by the framework.
-
-For example, `agenthub/codeact_agent`, etc.
-Contributors from different backgrounds and interests can choose to contribute to any (or all!) of these directions.
-
-## Constructing an Agent
-
-The abstraction for an agent can be found [here](../opendevin/controller/agent.py).
-
-Agents are run inside of a loop. At each iteration, `agent.step()` is called with a
-[State](../opendevin/controller/state/state.py) input, and the agent must output an [Action](../opendevin/events/action).
-
-Every agent also has a `self.llm` which it can use to interact with the LLM configured by the user.
-See the [LiteLLM docs for `self.llm.completion`](https://docs.litellm.ai/docs/completion).
-
-## State
-
-The `state` contains:
-
-- A history of actions taken by the agent, as well as any observations (e.g. file content, command output) from those actions
-- A list of actions/observations that have happened since the most recent step
-- A [`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/events/action/commands.py) - Runs a command inside a sandboxed terminal
-- [`IPythonRunCellAction`](../opendevin/events/action/commands.py) - Execute a block of Python code interactively (in Jupyter notebook) and receives `CmdOutputObservation`. Requires setting up `jupyter` [plugin](../opendevin/runtime/plugins) as a requirement.
-- [`FileReadAction`](../opendevin/events/action/files.py) - Reads the content of a file
-- [`FileWriteAction`](../opendevin/events/action/files.py) - Writes new content to a file
-- [`BrowseURLAction`](../opendevin/events/action/browse.py) - Gets the content of a URL
-- [`AddTaskAction`](../opendevin/events/action/tasks.py) - Adds a subtask to the plan
-- [`ModifyTaskAction`](../opendevin/events/action/tasks.py) - Changes the state of a subtask.
-- [`AgentFinishAction`](../opendevin/events/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
-- [`AgentRejectAction`](../opendevin/events/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
-- [`AgentFinishAction`](../opendevin/events/action/agent.py) - Stops the control loop, allowing the user to enter a new task
-- [`MessageAction`](../opendevin/events/action/message.py) - Represents a message from an agent or the user
-
-You can use `action.to_dict()` and `action_from_dict` to serialize and deserialize actions.
-
-## Observations
-
-There are also several types of Observations. These are typically available in the step following the corresponding Action.
-But they may also appear as a result of asynchronous events (e.g. a message from the user).
-
-Here is a list of available Observations:
-
-- [`CmdOutputObservation`](../opendevin/events/observation/commands.py)
-- [`BrowserOutputObservation`](../opendevin/events/observation/browse.py)
-- [`FileReadObservation`](../opendevin/events/observation/files.py)
-- [`FileWriteObservation`](../opendevin/events/observation/files.py)
-- [`ErrorObservation`](../opendevin/events/observation/error.py)
-- [`SuccessObservation`](../opendevin/events/observation/success.py)
-
-You can use `observation.to_dict()` and `observation_from_dict` to serialize and deserialize observations.
-
-## Interface
-
-Every agent must implement the following methods:
-
-### `step`
-
-```
-def step(self, state: "State") -> "Action"
-```
-
-`step` moves the agent forward one step towards its goal. This probably means
-sending a prompt to the LLM, then parsing the response into an `Action`.

agenthub/__init__.py

@@ -1,17 +1,15 @@
 from dotenv import load_dotenv
 
-from opendevin.controller.agent import Agent
-
-from .micro.agent import MicroAgent
-from .micro.registry import all_microagents
+from openhands.agenthub.micro.agent import MicroAgent
+from openhands.agenthub.micro.registry import all_microagents
+from openhands.controller.agent import Agent
 
 load_dotenv()
 
 
-from . import (  # noqa: E402
+from openhands.agenthub import (  # noqa: E402
     browsing_agent,
     codeact_agent,
-    codeact_swe_agent,
     delegator_agent,
     dummy_agent,
     planner_agent,
@@ -19,7 +17,6 @@ from . import (  # noqa: E402
 
 __all__ = [
     'codeact_agent',
-    'codeact_swe_agent',
     'planner_agent',
     'delegator_agent',
     'dummy_agent',

agenthub/browsing_agent/README.md

@@ -1,16 +0,0 @@
-# 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

@@ -1,5 +1,4 @@
-from opendevin.controller.agent import Agent
-
-from .browsing_agent import BrowsingAgent
+from openhands.agenthub.browsing_agent.browsing_agent import BrowsingAgent
+from openhands.controller.agent import Agent
 
 Agent.register('BrowsingAgent', BrowsingAgent)

agenthub/browsing_agent/browsing_agent.py

@@ -3,24 +3,25 @@ import os
 from browsergym.core.action.highlevel import HighLevelActionSet
 from browsergym.utils.obs import flatten_axtree_to_str
 
-from agenthub.browsing_agent.response_parser import BrowsingResponseParser
-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 (
+from openhands.agenthub.browsing_agent.response_parser import BrowsingResponseParser
+from openhands.controller.agent import Agent
+from openhands.controller.state.state import State
+from openhands.core.config import AgentConfig
+from openhands.core.logger import openhands_logger as logger
+from openhands.core.message import Message, TextContent
+from openhands.events.action import (
     Action,
     AgentFinishAction,
     BrowseInteractiveAction,
     MessageAction,
 )
-from opendevin.events.event import EventSource
-from opendevin.events.observation import BrowserOutputObservation
-from opendevin.events.observation.observation import Observation
-from opendevin.llm.llm import LLM
-from opendevin.runtime.plugins import (
+from openhands.events.event import EventSource
+from openhands.events.observation import BrowserOutputObservation
+from openhands.events.observation.observation import Observation
+from openhands.llm.llm import LLM
+from openhands.runtime.plugins import (
     PluginRequirement,
 )
-from opendevin.runtime.tools import RuntimeTool
 
 USE_NAV = (
     os.environ.get('USE_NAV', 'true') == 'true'
@@ -64,10 +65,15 @@ In order to accomplish my goal I need to send the information asked back to the
 """
 
 
-def get_prompt(error_prefix: str, cur_axtree_txt: str, prev_action_str: str) -> str:
+def get_prompt(
+    error_prefix: str, cur_url: str, cur_axtree_txt: str, prev_action_str: str
+) -> str:
     prompt = f"""\
 {error_prefix}
 
+# Current Page URL:
+{cur_url}
+
 # Current Accessibility Tree:
 {cur_axtree_txt}
 
@@ -92,19 +98,19 @@ class BrowsingAgent(Agent):
     """
 
     sandbox_plugins: list[PluginRequirement] = []
-    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
     response_parser = BrowsingResponseParser()
 
     def __init__(
         self,
         llm: LLM,
+        config: AgentConfig,
     ) -> None:
         """Initializes a new instance of the BrowsingAgent class.
 
         Parameters:
         - llm (LLM): The llm to be used by this agent
         """
-        super().__init__(llm)
+        super().__init__(llm, config)
         # define a configurable action space, with chat functionality, web navigation, and webpage grounding using accessibility tree and HTML.
         # see https://github.com/ServiceNow/BrowserGym/blob/main/core/src/browsergym/core/action/highlevel.py for more details
         action_subsets = ['chat', 'bid']
@@ -136,20 +142,21 @@ class BrowsingAgent(Agent):
         - MessageAction(content) - Message action to run (e.g. ask for clarification)
         - AgentFinishAction() - end the interaction
         """
-        messages = []
+        messages: list[Message] = []
         prev_actions = []
+        cur_url = ''
         cur_axtree_txt = ''
         error_prefix = ''
         last_obs = None
         last_action = None
 
-        if EVAL_MODE and len(state.history.get_events_as_list()) == 1:
+        if EVAL_MODE and len(state.history) == 1:
             # for webarena and miniwob++ eval, we need to retrieve the initial observation already in browser env
             # initialize and retrieve the first observation by issuing an noop OP
             # For non-benchmark browsing, the browser env starts with a blank page, and the agent is expected to first navigate to desired websites
             return BrowseInteractiveAction(browser_actions='noop()')
 
-        for event in state.history.get_events():
+        for event in state.history:
             if isinstance(event, BrowseInteractiveAction):
                 prev_actions.append(event.browser_actions)
                 last_action = event
@@ -164,7 +171,7 @@ class BrowsingAgent(Agent):
 
         prev_action_str = '\n'.join(prev_actions)
         # if the final BrowserInteractiveAction exec BrowserGym's send_msg_to_user,
-        # we should also send a message back to the user in OpenDevin and call it a day
+        # we should also send a message back to the user in OpenHands and call it a day
         if (
             isinstance(last_action, BrowseInteractiveAction)
             and last_action.browsergym_send_msg_to_user
@@ -178,6 +185,9 @@ class BrowsingAgent(Agent):
                 self.error_accumulator += 1
                 if self.error_accumulator > 5:
                     return MessageAction('Too many errors encountered. Task failed.')
+
+            cur_url = last_obs.url
+
             try:
                 cur_axtree_txt = flatten_axtree_to_str(
                     last_obs.axtree_object,
@@ -191,21 +201,23 @@ class BrowsingAgent(Agent):
                 )
                 return MessageAction('Error encountered when browsing.')
 
-        if (goal := state.get_current_user_intent()) is None:
+        goal, _ = state.get_current_user_intent()
+
+        if goal is None:
             goal = state.inputs['task']
+
         system_msg = get_system_message(
             goal,
             self.action_space.describe(with_long_description=False, with_examples=True),
         )
 
-        messages.append({'role': 'system', 'content': system_msg})
+        messages.append(Message(role='system', content=[TextContent(text=system_msg)]))
+
+        prompt = get_prompt(error_prefix, cur_url, cur_axtree_txt, prev_action_str)
+        messages.append(Message(role='user', content=[TextContent(text=prompt)]))
 
-        prompt = get_prompt(error_prefix, cur_axtree_txt, prev_action_str)
-        messages.append({'role': 'user', 'content': prompt})
-        logger.debug(prompt)
         response = self.llm.completion(
-            messages=messages,
-            temperature=0.0,
+            messages=self.llm.format_messages_for_llm(messages),
             stop=[')```', ')\n```'],
         )
         return self.response_parser.parse(response)

agenthub/browsing_agent/prompt.py

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

agenthub/browsing_agent/response_parser.py

@@ -1,8 +1,9 @@
 import ast
+import re
 
-from opendevin.controller.action_parser import ActionParser, ResponseParser
-from opendevin.core.logger import opendevin_logger as logger
-from opendevin.events.action import (
+from openhands.controller.action_parser import ActionParser, ResponseParser
+from openhands.core.logger import openhands_logger as logger
+from openhands.events.action import (
     Action,
     BrowseInteractiveAction,
 )
@@ -24,9 +25,14 @@ class BrowsingResponseParser(ResponseParser):
         if action_str is None:
             return ''
         action_str = action_str.strip()
-        if not action_str.endswith('```'):
-            action_str = action_str + ')```'
-        logger.info(action_str)
+        # Ensure action_str ends with ')```'
+        if action_str:
+            if not action_str.endswith('```'):
+                if action_str.endswith(')'):
+                    action_str += '```'  # prevent duplicate ending paranthesis, e.g. send_msg_to_user('Done'))
+                else:
+                    action_str += ')```'  # expected format
+        logger.debug(action_str)
         return action_str
 
     def parse_action(self, action_str: str) -> Action:
@@ -72,17 +78,46 @@ class BrowsingActionParserBrowseInteractive(ActionParser):
         return True
 
     def parse(self, action_str: str) -> Action:
-        thought = action_str.split('```')[0].strip()
-        action_str = action_str.split('```')[1].strip()
+        # parse the action string into browser_actions and thought
+        # the LLM can return only one string, or both
+
+        # when both are returned, it looks like this:
+        ### Based on the current state of the page and the goal of finding out the president of the USA, the next action should involve searching for information related to the president.
+        ### To achieve this, we can navigate to a reliable source such as a search engine or a specific website that provides information about the current president of the USA.
+        ### Here is an example of a valid action to achieve this:
+        ### ```
+        ### goto('https://www.whitehouse.gov/about-the-white-house/presidents/'
+        # in practice, BrowsingResponseParser.parse_response also added )``` to the end of the string
+
+        # when the LLM returns only one string, it looks like this:
+        ### goto('https://www.whitehouse.gov/about-the-white-house/presidents/')
+        # and parse_response added )``` to the end of the string
+        parts = action_str.split('```')
+        browser_actions = (
+            parts[1].strip() if parts[1].strip() != '' else parts[0].strip()
+        )
+        thought = parts[0].strip() if parts[1].strip() != '' else ''
+
+        # if the LLM wants to talk to the user, we extract the message
         msg_content = ''
-        for sub_action in action_str.split('\n'):
+        for sub_action in browser_actions.split('\n'):
             if 'send_msg_to_user(' in sub_action:
-                tree = ast.parse(sub_action)
-                args = tree.body[0].value.args  # type: ignore
-                msg_content = args[0].value
+                try:
+                    tree = ast.parse(sub_action)
+                    args = tree.body[0].value.args  # type: ignore
+                    msg_content = args[0].value
+                except SyntaxError:
+                    logger.error(f'Error parsing action: {sub_action}')
+                    # the syntax was not correct, but we can still try to get the message
+                    # e.g. send_msg_to_user("Hello, world!") or send_msg_to_user('Hello, world!'
+                    match = re.search(r'send_msg_to_user\((["\'])(.*?)\1\)', sub_action)
+                    if match:
+                        msg_content = match.group(2)
+                    else:
+                        msg_content = ''
 
         return BrowseInteractiveAction(
-            browser_actions=action_str,
+            browser_actions=browser_actions,
             thought=thought,
             browsergym_send_msg_to_user=msg_content,
         )

agenthub/codeact_agent/README.md

@@ -1,29 +0,0 @@
-# CodeAct Agent Framework
-
-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).
-
-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

agenthub/codeact_agent/__init__.py

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

agenthub/codeact_agent/action_parser.py

@@ -1,177 +0,0 @@
-import re
-
-from opendevin.controller.action_parser import ActionParser, ResponseParser
-from opendevin.events.action import (
-    Action,
-    AgentDelegateAction,
-    AgentFinishAction,
-    CmdRunAction,
-    IPythonRunCellAction,
-    MessageAction,
-)
-
-
-class CodeActResponseParser(ResponseParser):
-    """Parser action:
-    - CmdRunAction(command) - bash command to run
-    - IPythonRunCellAction(code) - IPython code to run
-    - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
-    - MessageAction(content) - Message action to run (e.g. ask for clarification)
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(self):
-        # Need pay attention to the item order in self.action_parsers
-        super().__init__()
-        self.action_parsers = [
-            CodeActActionParserFinish(),
-            CodeActActionParserCmdRun(),
-            CodeActActionParserIPythonRunCell(),
-            CodeActActionParserAgentDelegate(),
-        ]
-        self.default_parser = CodeActActionParserMessage()
-
-    def parse(self, response) -> Action:
-        action_str = self.parse_response(response)
-        return self.parse_action(action_str)
-
-    def parse_response(self, response) -> str:
-        action = response.choices[0].message.content
-        if action is None:
-            return ''
-        for lang in ['bash', 'ipython', 'browse']:
-            if f'<execute_{lang}>' in action and f'</execute_{lang}>' not in action:
-                action += f'</execute_{lang}>'
-        return action
-
-    def parse_action(self, action_str: str) -> Action:
-        for action_parser in self.action_parsers:
-            if action_parser.check_condition(action_str):
-                return action_parser.parse(action_str)
-        return self.default_parser.parse(action_str)
-
-
-class CodeActActionParserFinish(ActionParser):
-    """Parser action:
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(
-        self,
-    ):
-        self.finish_command = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.finish_command = re.search(r'<finish>.*</finish>', action_str, re.DOTALL)
-        return self.finish_command is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.finish_command is not None
-        ), 'self.finish_command should not be None when parse is called'
-        thought = action_str.replace(self.finish_command.group(0), '').strip()
-        return AgentFinishAction(thought=thought)
-
-
-class CodeActActionParserCmdRun(ActionParser):
-    """Parser action:
-    - CmdRunAction(command) - bash command to run
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(
-        self,
-    ):
-        self.bash_command = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.bash_command = re.search(
-            r'<execute_bash>(.*?)</execute_bash>', action_str, re.DOTALL
-        )
-        return self.bash_command is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.bash_command is not None
-        ), 'self.bash_command should not be None when parse is called'
-        thought = action_str.replace(self.bash_command.group(0), '').strip()
-        # a command was found
-        command_group = self.bash_command.group(1).strip()
-        if command_group.strip() == 'exit':
-            return AgentFinishAction(thought=thought)
-        return CmdRunAction(command=command_group, thought=thought)
-
-
-class CodeActActionParserIPythonRunCell(ActionParser):
-    """Parser action:
-    - IPythonRunCellAction(code) - IPython code to run
-    """
-
-    def __init__(
-        self,
-    ):
-        self.python_code = None
-        self.jupyter_kernel_init_code: str = 'from agentskills import *'
-
-    def check_condition(self, action_str: str) -> bool:
-        self.python_code = re.search(
-            r'<execute_ipython>(.*?)</execute_ipython>', action_str, re.DOTALL
-        )
-        return self.python_code is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.python_code is not None
-        ), 'self.python_code should not be None when parse is called'
-        code_group = self.python_code.group(1).strip()
-        thought = action_str.replace(self.python_code.group(0), '').strip()
-        return IPythonRunCellAction(
-            code=code_group,
-            thought=thought,
-            kernel_init_code=self.jupyter_kernel_init_code,
-        )
-
-
-class CodeActActionParserAgentDelegate(ActionParser):
-    """Parser action:
-    - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
-    """
-
-    def __init__(
-        self,
-    ):
-        self.agent_delegate = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.agent_delegate = re.search(
-            r'<execute_browse>(.*)</execute_browse>', action_str, re.DOTALL
-        )
-        return self.agent_delegate is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.agent_delegate is not None
-        ), 'self.agent_delegate should not be None when parse is called'
-        thought = action_str.replace(self.agent_delegate.group(0), '').strip()
-        browse_actions = self.agent_delegate.group(1).strip()
-        task = f'{thought}. I should start with: {browse_actions}'
-        return AgentDelegateAction(agent='BrowsingAgent', inputs={'task': task})
-
-
-class CodeActActionParserMessage(ActionParser):
-    """Parser action:
-    - MessageAction(content) - Message action to run (e.g. ask for clarification)
-    """
-
-    def __init__(
-        self,
-    ):
-        pass
-
-    def check_condition(self, action_str: str) -> bool:
-        # We assume the LLM is GOOD enough that when it returns pure natural language
-        # it wants to talk to the user
-        return True
-
-    def parse(self, action_str: str) -> Action:
-        return MessageAction(content=action_str, wait_for_response=True)

agenthub/codeact_agent/codeact_agent.py

@@ -1,53 +1,48 @@
-from agenthub.codeact_agent.action_parser import CodeActResponseParser
-from agenthub.codeact_agent.prompt import (
-    COMMAND_DOCS,
-    EXAMPLES,
-    GITHUB_MESSAGE,
-    SYSTEM_PREFIX,
-    SYSTEM_SUFFIX,
-)
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.events.action import (
+import json
+import os
+from collections import deque
+
+from litellm import ModelResponse
+
+import openhands.agenthub.codeact_agent.function_calling as codeact_function_calling
+from openhands.controller.agent import Agent
+from openhands.controller.state.state import State
+from openhands.core.config import AgentConfig
+from openhands.core.logger import openhands_logger as logger
+from openhands.core.message import ImageContent, Message, TextContent
+from openhands.events.action import (
     Action,
     AgentDelegateAction,
     AgentFinishAction,
+    BrowseInteractiveAction,
+    BrowseURLAction,
     CmdRunAction,
+    FileEditAction,
     IPythonRunCellAction,
     MessageAction,
 )
-from opendevin.events.observation import (
+from openhands.events.observation import (
     AgentDelegateObservation,
+    BrowserOutputObservation,
     CmdOutputObservation,
+    FileEditObservation,
     IPythonRunCellObservation,
+    UserRejectObservation,
 )
-from opendevin.events.observation.observation import Observation
-from opendevin.events.serialization.event import truncate_content
-from opendevin.llm.llm import LLM
-from opendevin.runtime.plugins import (
+from openhands.events.observation.error import ErrorObservation
+from openhands.events.observation.observation import Observation
+from openhands.events.serialization.event import truncate_content
+from openhands.llm.llm import LLM
+from openhands.runtime.plugins import (
     AgentSkillsRequirement,
     JupyterRequirement,
     PluginRequirement,
 )
-from opendevin.runtime.tools import RuntimeTool
-
-ENABLE_GITHUB = True
-
-
-# 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
+from openhands.utils.prompt import PromptManager
 
 
 class CodeActAgent(Agent):
-    VERSION = '1.8'
+    VERSION = '2.2'
     """
     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.
@@ -63,24 +58,7 @@ class CodeActAgent(Agent):
     - 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
+    ![image](https://github.com/All-Hands-AI/OpenHands/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
 
     """
 
@@ -91,82 +69,264 @@ class CodeActAgent(Agent):
         AgentSkillsRequirement(),
         JupyterRequirement(),
     ]
-    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
-
-    system_message: str = get_system_message()
-    in_context_example: str = f"Here is an example of how you can interact with the environment for task solving:\n{get_in_context_example()}\n\nNOW, LET'S START!"
-
-    action_parser = CodeActResponseParser()
 
     def __init__(
         self,
         llm: LLM,
+        config: AgentConfig,
     ) -> None:
         """Initializes a new instance of the CodeActAgent class.
 
         Parameters:
         - llm (LLM): The llm to be used by this agent
         """
-        super().__init__(llm)
+        super().__init__(llm, config)
         self.reset()
 
-    def action_to_str(self, action: Action) -> str:
-        if isinstance(action, CmdRunAction):
-            return (
-                f'{action.thought}\n<execute_bash>\n{action.command}\n</execute_bash>'
+        self.mock_function_calling = False
+        if not self.llm.is_function_calling_active():
+            logger.info(
+                f'Function calling not enabled for model {self.llm.config.model}. '
+                'Mocking function calling via prompting.'
             )
-        elif isinstance(action, IPythonRunCellAction):
-            return f'{action.thought}\n<execute_ipython>\n{action.code}\n</execute_ipython>'
-        elif isinstance(action, AgentDelegateAction):
-            return f'{action.thought}\n<execute_browse>\n{action.inputs["task"]}\n</execute_browse>'
+            self.mock_function_calling = True
+
+        # Function calling mode
+        self.tools = codeact_function_calling.get_tools(
+            codeact_enable_browsing=self.config.codeact_enable_browsing,
+            codeact_enable_jupyter=self.config.codeact_enable_jupyter,
+            codeact_enable_llm_editor=self.config.codeact_enable_llm_editor,
+        )
+        logger.debug(
+            f'TOOLS loaded for CodeActAgent: {json.dumps(self.tools, indent=2)}'
+        )
+        self.prompt_manager = PromptManager(
+            microagent_dir=os.path.join(os.path.dirname(__file__), 'micro')
+            if self.config.use_microagents
+            else None,
+            prompt_dir=os.path.join(os.path.dirname(__file__), 'prompts'),
+            disabled_microagents=self.config.disabled_microagents,
+        )
+
+        self.pending_actions: deque[Action] = deque()
+
+    def get_action_message(
+        self,
+        action: Action,
+        pending_tool_call_action_messages: dict[str, Message],
+    ) -> list[Message]:
+        """Converts an action into a message format that can be sent to the LLM.
+
+        This method handles different types of actions and formats them appropriately:
+        1. For tool-based actions (AgentDelegate, CmdRun, IPythonRunCell, FileEdit) and agent-sourced AgentFinish:
+            - In function calling mode: Stores the LLM's response in pending_tool_call_action_messages
+            - In non-function calling mode: Creates a message with the action string
+        2. For MessageActions: Creates a message with the text content and optional image content
+
+        Args:
+            action (Action): The action to convert. Can be one of:
+                - CmdRunAction: For executing bash commands
+                - IPythonRunCellAction: For running IPython code
+                - FileEditAction: For editing files
+                - BrowseInteractiveAction: For browsing the web
+                - AgentFinishAction: For ending the interaction
+                - MessageAction: For sending messages
+            pending_tool_call_action_messages (dict[str, Message]): Dictionary mapping response IDs
+                to their corresponding messages. Used in function calling mode to track tool calls
+                that are waiting for their results.
+
+        Returns:
+            list[Message]: A list containing the formatted message(s) for the action.
+                May be empty if the action is handled as a tool call in function calling mode.
+
+        Note:
+            In function calling mode, tool-based actions are stored in pending_tool_call_action_messages
+            rather than being returned immediately. They will be processed later when all corresponding
+            tool call results are available.
+        """
+        # create a regular message from an event
+        if isinstance(
+            action,
+            (
+                AgentDelegateAction,
+                IPythonRunCellAction,
+                FileEditAction,
+                BrowseInteractiveAction,
+                BrowseURLAction,
+            ),
+        ) or (isinstance(action, CmdRunAction) and action.source == 'agent'):
+            tool_metadata = action.tool_call_metadata
+            assert tool_metadata is not None, (
+                'Tool call metadata should NOT be None when function calling is enabled. Action: '
+                + str(action)
+            )
+
+            llm_response: ModelResponse = tool_metadata.model_response
+            assistant_msg = llm_response.choices[0].message
+
+            # Add the LLM message (assistant) that initiated the tool calls
+            # (overwrites any previous message with the same response_id)
+            logger.debug(
+                f'Tool calls type: {type(assistant_msg.tool_calls)}, value: {assistant_msg.tool_calls}'
+            )
+            pending_tool_call_action_messages[llm_response.id] = Message(
+                role=assistant_msg.role,
+                # tool call content SHOULD BE a string
+                content=[TextContent(text=assistant_msg.content or '')]
+                if assistant_msg.content is not None
+                else [],
+                tool_calls=assistant_msg.tool_calls,
+            )
+            return []
+        elif isinstance(action, AgentFinishAction):
+            role = 'user' if action.source == 'user' else 'assistant'
+
+            # when agent finishes, it has tool_metadata
+            # which has already been executed, and it doesn't have a response
+            # when the user finishes (/exit), we don't have tool_metadata
+            tool_metadata = action.tool_call_metadata
+            if tool_metadata is not None:
+                # take the response message from the tool call
+                assistant_msg = tool_metadata.model_response.choices[0].message
+                content = assistant_msg.content or ''
+
+                # save content if any, to thought
+                if action.thought:
+                    if action.thought != content:
+                        action.thought += '\n' + content
+                else:
+                    action.thought = content
+
+                # remove the tool call metadata
+                action.tool_call_metadata = None
+            return [
+                Message(
+                    role=role,
+                    content=[TextContent(text=action.thought)],
+                )
+            ]
         elif isinstance(action, MessageAction):
-            return action.content
-        elif isinstance(action, AgentFinishAction) and action.source == 'agent':
-            return action.thought
-        return ''
+            role = 'user' if action.source == 'user' else 'assistant'
+            content = [TextContent(text=action.content or '')]
+            if self.llm.vision_is_active() and action.image_urls:
+                content.append(ImageContent(image_urls=action.image_urls))
+            return [
+                Message(
+                    role=role,
+                    content=content,
+                )
+            ]
+        elif isinstance(action, CmdRunAction) and action.source == 'user':
+            content = [
+                TextContent(text=f'User executed the command:\n{action.command}')
+            ]
+            return [
+                Message(
+                    role='user',
+                    content=content,
+                )
+            ]
+        return []
 
-    def get_action_message(self, action: Action) -> dict[str, str] | None:
-        if (
-            isinstance(action, AgentDelegateAction)
-            or isinstance(action, CmdRunAction)
-            or isinstance(action, IPythonRunCellAction)
-            or isinstance(action, MessageAction)
-            or (isinstance(action, AgentFinishAction) and action.source == 'agent')
-        ):
-            return {
-                'role': 'user' if action.source == 'user' else 'assistant',
-                'content': self.action_to_str(action),
-            }
-        return None
+    def get_observation_message(
+        self,
+        obs: Observation,
+        tool_call_id_to_message: dict[str, Message],
+    ) -> list[Message]:
+        """Converts an observation into a message format that can be sent to the LLM.
 
-    def get_observation_message(self, obs: Observation) -> dict[str, str] | None:
+        This method handles different types of observations and formats them appropriately:
+        - CmdOutputObservation: Formats command execution results with exit codes
+        - IPythonRunCellObservation: Formats IPython cell execution results, replacing base64 images
+        - FileEditObservation: Formats file editing results
+        - AgentDelegateObservation: Formats results from delegated agent tasks
+        - ErrorObservation: Formats error messages from failed actions
+        - UserRejectObservation: Formats user rejection messages
+
+        In function calling mode, observations with tool_call_metadata are stored in
+        tool_call_id_to_message for later processing instead of being returned immediately.
+
+        Args:
+            obs (Observation): The observation to convert
+            tool_call_id_to_message (dict[str, Message]): Dictionary mapping tool call IDs
+                to their corresponding messages (used in function calling mode)
+
+        Returns:
+            list[Message]: A list containing the formatted message(s) for the observation.
+                May be empty if the observation is handled as a tool response in function calling mode.
+
+        Raises:
+            ValueError: If the observation type is unknown
+        """
+        message: Message
         max_message_chars = self.llm.config.max_message_chars
         if isinstance(obs, CmdOutputObservation):
-            content = 'OBSERVATION:\n' + truncate_content(
-                obs.content, max_message_chars
-            )
-            content += (
-                f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]'
-            )
-            return {'role': 'user', 'content': content}
+            # if it doesn't have tool call metadata, it was triggered by a user action
+            if obs.tool_call_metadata is None:
+                text = truncate_content(
+                    f'\nObserved result of command executed by user:\n{obs.content}',
+                    max_message_chars,
+                )
+            else:
+                text = truncate_content(
+                    obs.content + obs.interpreter_details, max_message_chars
+                )
+            text += f'\n[Command finished with exit code {obs.exit_code}]'
+            message = Message(role='user', content=[TextContent(text=text)])
         elif isinstance(obs, IPythonRunCellObservation):
-            content = 'OBSERVATION:\n' + obs.content
+            text = obs.content
             # replace base64 images with a placeholder
-            splitted = content.split('\n')
+            splitted = text.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_content(content, max_message_chars)
-            return {'role': 'user', 'content': content}
-        elif isinstance(obs, AgentDelegateObservation):
-            content = 'OBSERVATION:\n' + truncate_content(
-                str(obs.outputs), max_message_chars
+            text = '\n'.join(splitted)
+            text = truncate_content(text, max_message_chars)
+            message = Message(role='user', content=[TextContent(text=text)])
+        elif isinstance(obs, FileEditObservation):
+            text = truncate_content(str(obs), max_message_chars)
+            message = Message(role='user', content=[TextContent(text=text)])
+        elif isinstance(obs, BrowserOutputObservation):
+            text = obs.get_agent_obs_text()
+            message = Message(
+                role='user',
+                content=[TextContent(text=text)],
             )
-            return {'role': 'user', 'content': content}
-        return None
+        elif isinstance(obs, AgentDelegateObservation):
+            text = truncate_content(
+                obs.outputs['content'] if 'content' in obs.outputs else '',
+                max_message_chars,
+            )
+            message = Message(role='user', content=[TextContent(text=text)])
+        elif isinstance(obs, ErrorObservation):
+            text = truncate_content(obs.content, max_message_chars)
+            text += '\n[Error occurred in processing last action]'
+            message = Message(role='user', content=[TextContent(text=text)])
+        elif isinstance(obs, UserRejectObservation):
+            text = 'OBSERVATION:\n' + truncate_content(obs.content, max_message_chars)
+            text += '\n[Last action has been rejected by the user]'
+            message = Message(role='user', content=[TextContent(text=text)])
+        else:
+            # If an observation message is not returned, it will cause an error
+            # when the LLM tries to return the next message
+            raise ValueError(f'Unknown observation type: {type(obs)}')
+
+        # Update the message as tool response properly
+        if (tool_call_metadata := obs.tool_call_metadata) is not None:
+            tool_call_id_to_message[tool_call_metadata.tool_call_id] = Message(
+                role='tool',
+                content=message.content,
+                tool_call_id=tool_call_metadata.tool_call_id,
+                name=tool_call_metadata.function_name,
+            )
+            # No need to return the observation message
+            # because it will be added by get_action_message when all the corresponding
+            # tool calls in the SAME request are processed
+            return []
+
+        return [message]
 
     def reset(self) -> None:
         """Resets the CodeAct Agent."""
@@ -186,60 +346,159 @@ class CodeActAgent(Agent):
         - MessageAction(content) - Message action to run (e.g. ask for clarification)
         - AgentFinishAction() - end the interaction
         """
+        # Continue with pending actions if any
+        if self.pending_actions:
+            return self.pending_actions.popleft()
+
         # if we're done, go back
-        latest_user_message = state.history.get_last_user_message()
-        if latest_user_message and latest_user_message.strip() == '/exit':
+        latest_user_message = state.get_last_user_message()
+        if latest_user_message and latest_user_message.content.strip() == '/exit':
             return AgentFinishAction()
 
         # prepare what we want to send to the LLM
-        messages: list[dict[str, str]] = self._get_messages(state)
+        messages = self._get_messages(state)
+        params: dict = {
+            'messages': self.llm.format_messages_for_llm(messages),
+        }
+        params['tools'] = self.tools
+        if self.mock_function_calling:
+            params['mock_function_calling'] = True
+        response = self.llm.completion(**params)
+        actions = codeact_function_calling.response_to_actions(response)
+        for action in actions:
+            self.pending_actions.append(action)
+        return self.pending_actions.popleft()
 
-        response = self.llm.completion(
-            messages=messages,
-            stop=[
-                '</execute_ipython>',
-                '</execute_bash>',
-                '</execute_browse>',
-            ],
-            temperature=0.0,
-        )
-        return self.action_parser.parse(response)
+    def _get_messages(self, state: State) -> list[Message]:
+        """Constructs the message history for the LLM conversation.
 
-    def _get_messages(self, state: State) -> list[dict[str, str]]:
-        messages = [
-            {'role': 'system', 'content': self.system_message},
-            {'role': 'user', 'content': self.in_context_example},
+        This method builds a structured conversation history by processing events from the state
+        and formatting them into messages that the LLM can understand. It handles both regular
+        message flow and function-calling scenarios.
+
+        The method performs the following steps:
+        1. Initializes with system prompt and optional initial user message
+        2. Processes events (Actions and Observations) into messages
+        3. Handles tool calls and their responses in function-calling mode
+        4. Manages message role alternation (user/assistant/tool)
+        5. Applies caching for specific LLM providers (e.g., Anthropic)
+        6. Adds environment reminders for non-function-calling mode
+
+        Args:
+            state (State): The current state object containing conversation history and other metadata
+
+        Returns:
+            list[Message]: A list of formatted messages ready for LLM consumption, including:
+                - System message with prompt
+                - Initial user message (if configured)
+                - Action messages (from both user and assistant)
+                - Observation messages (including tool responses)
+                - Environment reminders (in non-function-calling mode)
+
+        Note:
+            - In function-calling mode, tool calls and their responses are carefully tracked
+              to maintain proper conversation flow
+            - Messages from the same role are combined to prevent consecutive same-role messages
+            - For Anthropic models, specific messages are cached according to their documentation
+        """
+        if not self.prompt_manager:
+            raise Exception('Prompt Manager not instantiated.')
+
+        messages: list[Message] = [
+            Message(
+                role='system',
+                content=[
+                    TextContent(
+                        text=self.prompt_manager.get_system_message(),
+                        cache_prompt=self.llm.is_caching_prompt_active(),
+                    )
+                ],
+            )
         ]
+        example_message = self.prompt_manager.get_example_user_message()
+        if example_message:
+            messages.append(
+                Message(
+                    role='user',
+                    content=[TextContent(text=example_message)],
+                    cache_prompt=self.llm.is_caching_prompt_active(),
+                )
+            )
 
-        for event in state.history.get_events():
+        pending_tool_call_action_messages: dict[str, Message] = {}
+        tool_call_id_to_message: dict[str, Message] = {}
+        events = list(state.history)
+        for event in events:
             # create a regular message from an event
             if isinstance(event, Action):
-                message = self.get_action_message(event)
+                messages_to_add = self.get_action_message(
+                    action=event,
+                    pending_tool_call_action_messages=pending_tool_call_action_messages,
+                )
             elif isinstance(event, Observation):
-                message = self.get_observation_message(event)
+                messages_to_add = self.get_observation_message(
+                    obs=event,
+                    tool_call_id_to_message=tool_call_id_to_message,
+                )
             else:
                 raise ValueError(f'Unknown event type: {type(event)}')
 
-            # add regular message
-            if message:
-                # handle error if the message is the SAME role as the previous message
-                # litellm.exceptions.BadRequestError: litellm.BadRequestError: OpenAIException - Error code: 400 - {'detail': 'Only supports u/a/u/a/u...'}
-                # there should not have two consecutive messages from the same role
-                if messages and messages[-1]['role'] == message['role']:
-                    messages[-1]['content'] += '\n\n' + message['content']
-                else:
-                    messages.append(message)
+            # Check pending tool call action messages and see if they are complete
+            _response_ids_to_remove = []
+            for (
+                response_id,
+                pending_message,
+            ) in pending_tool_call_action_messages.items():
+                assert pending_message.tool_calls is not None, (
+                    'Tool calls should NOT be None when function calling is enabled & the message is considered pending tool call. '
+                    f'Pending message: {pending_message}'
+                )
+                if all(
+                    tool_call.id in tool_call_id_to_message
+                    for tool_call in pending_message.tool_calls
+                ):
+                    # If complete:
+                    # -- 1. Add the message that **initiated** the tool calls
+                    messages_to_add.append(pending_message)
+                    # -- 2. Add the tool calls **results***
+                    for tool_call in pending_message.tool_calls:
+                        messages_to_add.append(tool_call_id_to_message[tool_call.id])
+                        tool_call_id_to_message.pop(tool_call.id)
+                    _response_ids_to_remove.append(response_id)
+            # Cleanup the processed pending tool messages
+            for response_id in _response_ids_to_remove:
+                pending_tool_call_action_messages.pop(response_id)
 
-        # the latest user message is important:
-        # we want to remind the agent of the environment constraints
-        latest_user_message = next(
-            (m for m in reversed(messages) if m['role'] == 'user'), None
-        )
+            for message in messages_to_add:
+                if message:
+                    if message.role == 'user':
+                        self.prompt_manager.enhance_message(message)
+                    # handle error if the message is the SAME role as the previous message
+                    # litellm.exceptions.BadRequestError: litellm.BadRequestError: OpenAIException - Error code: 400 - {'detail': 'Only supports u/a/u/a/u...'}
+                    # there shouldn't be two consecutive messages from the same role
+                    # NOTE: we shouldn't combine tool messages because each of them has a different tool_call_id
+                    if (
+                        messages
+                        and messages[-1].role == message.role
+                        and message.role != 'tool'
+                    ):
+                        messages[-1].content.extend(message.content)
+                    else:
+                        messages.append(message)
 
-        # add a reminder to the prompt
-        if latest_user_message:
-            latest_user_message['content'] += (
-                f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task. When finished reply with <finish></finish>'
-            )
+        if self.llm.is_caching_prompt_active():
+            # NOTE: this is only needed for anthropic
+            # following logic here:
+            # https://github.com/anthropics/anthropic-quickstarts/blob/8f734fd08c425c6ec91ddd613af04ff87d70c5a0/computer-use-demo/computer_use_demo/loop.py#L241-L262
+            breakpoints_remaining = 3  # remaining 1 for system/tool
+            for message in reversed(messages):
+                if message.role == 'user' or message.role == 'tool':
+                    if breakpoints_remaining > 0:
+                        message.content[
+                            -1
+                        ].cache_prompt = True  # Last item inside the message content
+                        breakpoints_remaining -= 1
+                    else:
+                        break
 
         return messages

agenthub/codeact_agent/function_calling.py

@@ -0,0 +1,554 @@
+"""This file contains the function calling implementation for different actions.
+
+This is similar to the functionality of `CodeActResponseParser`.
+"""
+
+import json
+
+from browsergym.core.action.highlevel import HighLevelActionSet
+from litellm import (
+    ChatCompletionToolParam,
+    ChatCompletionToolParamFunctionChunk,
+    ModelResponse,
+)
+
+from openhands.core.exceptions import FunctionCallNotExistsError
+from openhands.core.logger import openhands_logger as logger
+from openhands.events.action import (
+    Action,
+    AgentDelegateAction,
+    AgentFinishAction,
+    BrowseInteractiveAction,
+    BrowseURLAction,
+    CmdRunAction,
+    FileEditAction,
+    IPythonRunCellAction,
+    MessageAction,
+)
+from openhands.events.tool import ToolCallMetadata
+
+_BASH_DESCRIPTION = """Execute a bash command in the terminal.
+* Long running commands: For commands that may run indefinitely, it should be run in the background and the output should be redirected to a file, e.g. command = `python3 app.py > server.log 2>&1 &`.
+* Interactive: If a bash command returns exit code `-1`, this means the process is not yet finished. The assistant must then send a second call to terminal with an empty `command` (which will retrieve any additional logs), or it can send additional text (set `command` to the text) to STDIN of the running process, or it can send command=`ctrl+c` to interrupt the process.
+* Timeout: If a command execution result says "Command timed out. Sending SIGINT to the process", the assistant should retry running the command in the background.
+"""
+
+CmdRunTool = ChatCompletionToolParam(
+    type='function',
+    function=ChatCompletionToolParamFunctionChunk(
+        name='execute_bash',
+        description=_BASH_DESCRIPTION,
+        parameters={
+            'type': 'object',
+            'properties': {
+                'command': {
+                    'type': 'string',
+                    'description': 'The bash command to execute. Can be empty to view additional logs when previous exit code is `-1`. Can be `ctrl+c` to interrupt the currently running process.',
+                },
+            },
+            'required': ['command'],
+        },
+    ),
+)
+
+_IPYTHON_DESCRIPTION = """Run a cell of Python code in an IPython environment.
+* The assistant should define variables and import packages before using them.
+* The variable defined in the IPython environment will not be available outside the IPython environment (e.g., in terminal).
+"""
+
+IPythonTool = ChatCompletionToolParam(
+    type='function',
+    function=ChatCompletionToolParamFunctionChunk(
+        name='execute_ipython_cell',
+        description=_IPYTHON_DESCRIPTION,
+        parameters={
+            'type': 'object',
+            'properties': {
+                'code': {
+                    'type': 'string',
+                    'description': 'The Python code to execute. Supports magic commands like %pip.',
+                },
+            },
+            'required': ['code'],
+        },
+    ),
+)
+
+_FILE_EDIT_DESCRIPTION = """Edit a file.
+* The assistant can edit files by specifying the file path and providing a draft of the new file content.
+* The draft content doesn't need to be exactly the same as the existing file; the assistant may skip unchanged lines using comments like `# unchanged` to indicate unchanged sections.
+* IMPORTANT: For large files (e.g., > 300 lines), specify the range of lines to edit using `start` and `end` (1-indexed, inclusive). The range should be smaller than 300 lines.
+* To append to a file, set both `start` and `end` to `-1`.
+* If the file doesn't exist, a new file will be created with the provided content.
+
+**Example 1: general edit for short files**
+For example, given an existing file `/path/to/file.py` that looks like this:
+(this is the end of the file)
+1|class MyClass:
+2|    def __init__(self):
+3|        self.x = 1
+4|        self.y = 2
+5|        self.z = 3
+6|
+7|print(MyClass().z)
+8|print(MyClass().x)
+(this is the end of the file)
+
+The assistant wants to edit the file to look like this:
+(this is the end of the file)
+1|class MyClass:
+2|    def __init__(self):
+3|        self.x = 1
+4|        self.y = 2
+5|
+6|print(MyClass().y)
+(this is the end of the file)
+
+The assistant may produce an edit action like this:
+path="/path/to/file.txt" start=1 end=-1
+content=```
+class MyClass:
+    def __init__(self):
+        # no changes before
+        self.y = 2
+        # self.z is removed
+
+# MyClass().z is removed
+print(MyClass().y)
+```
+
+**Example 2: append to file for short files**
+For example, given an existing file `/path/to/file.py` that looks like this:
+(this is the end of the file)
+1|class MyClass:
+2|    def __init__(self):
+3|        self.x = 1
+4|        self.y = 2
+5|        self.z = 3
+6|
+7|print(MyClass().z)
+8|print(MyClass().x)
+(this is the end of the file)
+
+To append the following lines to the file:
+```python
+print(MyClass().y)
+```
+
+The assistant may produce an edit action like this:
+path="/path/to/file.txt" start=-1 end=-1
+content=```
+print(MyClass().y)
+```
+
+**Example 3: edit for long files**
+
+Given an existing file `/path/to/file.py` that looks like this:
+(1000 more lines above)
+1001|class MyClass:
+1002|    def __init__(self):
+1003|        self.x = 1
+1004|        self.y = 2
+1005|        self.z = 3
+1006|
+1007|print(MyClass().z)
+1008|print(MyClass().x)
+(2000 more lines below)
+
+The assistant wants to edit the file to look like this:
+
+(1000 more lines above)
+1001|class MyClass:
+1002|    def __init__(self):
+1003|        self.x = 1
+1004|        self.y = 2
+1005|
+1006|print(MyClass().y)
+(2000 more lines below)
+
+The assistant may produce an edit action like this:
+path="/path/to/file.txt" start=1001 end=1008
+content=```
+class MyClass:
+    def __init__(self):
+        # no changes before
+        self.y = 2
+        # self.z is removed
+
+# MyClass().z is removed
+print(MyClass().y)
+```
+"""
+
+LLMBasedFileEditTool = ChatCompletionToolParam(
+    type='function',
+    function=ChatCompletionToolParamFunctionChunk(
+        name='edit_file',
+        description=_FILE_EDIT_DESCRIPTION,
+        parameters={
+            'type': 'object',
+            'properties': {
+                'path': {
+                    'type': 'string',
+                    'description': 'The absolute path to the file to be edited.',
+                },
+                'new_content_draft': {
+                    'type': 'string',
+                    'description': 'A draft of the new content for the file being edited. Note that the assistant may skip unchanged lines.',
+                },
+                'start': {
+                    'type': 'integer',
+                    'description': 'The starting line number for the edit (1-indexed, inclusive). Default is 1.',
+                },
+                'end': {
+                    'type': 'integer',
+                    'description': 'The ending line number for the edit (1-indexed, inclusive). Default is -1 (end of file).',
+                },
+            },
+            'required': ['path', 'content'],
+        },
+    ),
+)
+
+_STR_REPLACE_EDITOR_DESCRIPTION = """Custom editing tool for viewing, creating and editing files
+* State is persistent across command calls and discussions with the user
+* If `path` is a file, `view` displays the result of applying `cat -n`. If `path` is a directory, `view` lists non-hidden files and directories up to 2 levels deep
+* The `create` command cannot be used if the specified `path` already exists as a file
+* If a `command` generates a long output, it will be truncated and marked with `<response clipped>`
+* The `undo_edit` command will revert the last edit made to the file at `path`
+
+Notes for using the `str_replace` command:
+* The `old_str` parameter should match EXACTLY one or more consecutive lines from the original file. Be mindful of whitespaces!
+* If the `old_str` parameter is not unique in the file, the replacement will not be performed. Make sure to include enough context in `old_str` to make it unique
+* The `new_str` parameter should contain the edited lines that should replace the `old_str`
+"""
+
+StrReplaceEditorTool = ChatCompletionToolParam(
+    type='function',
+    function=ChatCompletionToolParamFunctionChunk(
+        name='str_replace_editor',
+        description=_STR_REPLACE_EDITOR_DESCRIPTION,
+        parameters={
+            'type': 'object',
+            'properties': {
+                'command': {
+                    'description': 'The commands to run. Allowed options are: `view`, `create`, `str_replace`, `insert`, `undo_edit`.',
+                    'enum': ['view', 'create', 'str_replace', 'insert', 'undo_edit'],
+                    'type': 'string',
+                },
+                'path': {
+                    'description': 'Absolute path to file or directory, e.g. `/workspace/file.py` or `/workspace`.',
+                    'type': 'string',
+                },
+                'file_text': {
+                    'description': 'Required parameter of `create` command, with the content of the file to be created.',
+                    'type': 'string',
+                },
+                'old_str': {
+                    'description': 'Required parameter of `str_replace` command containing the string in `path` to replace.',
+                    'type': 'string',
+                },
+                'new_str': {
+                    'description': 'Optional parameter of `str_replace` command containing the new string (if not given, no string will be added). Required parameter of `insert` command containing the string to insert.',
+                    'type': 'string',
+                },
+                'insert_line': {
+                    'description': 'Required parameter of `insert` command. The `new_str` will be inserted AFTER the line `insert_line` of `path`.',
+                    'type': 'integer',
+                },
+                'view_range': {
+                    'description': 'Optional parameter of `view` command when `path` points to a file. If none is given, the full file is shown. If provided, the file will be shown in the indicated line number range, e.g. [11, 12] will show lines 11 and 12. Indexing at 1 to start. Setting `[start_line, -1]` shows all lines from `start_line` to the end of the file.',
+                    'items': {'type': 'integer'},
+                    'type': 'array',
+                },
+            },
+            'required': ['command', 'path'],
+        },
+    ),
+)
+
+
+_WEB_DESCRIPTION = """Read (convert to markdown) content from a webpage. You should prefer using the `webpage_read` tool over the `browser` tool, but do use the `browser` tool if you need to interact with a webpage (e.g., click a button, fill out a form, etc.).
+
+You may use the `webpage_read` tool to read content from a webpage, and even search the webpage content using a Google search query (e.g., url=`https://www.google.com/search?q=YOUR_QUERY`).
+"""
+
+WebReadTool = ChatCompletionToolParam(
+    type='function',
+    function=ChatCompletionToolParamFunctionChunk(
+        name='web_read',
+        description=_WEB_DESCRIPTION,
+        parameters={
+            'type': 'object',
+            'properties': {
+                'url': {
+                    'type': 'string',
+                    'description': 'The URL of the webpage to read. You can also use a Google search query here (e.g., `https://www.google.com/search?q=YOUR_QUERY`).',
+                }
+            },
+            'required': ['url'],
+        },
+    ),
+)
+
+# from browsergym/core/action/highlevel.py
+_browser_action_space = HighLevelActionSet(
+    subsets=['bid', 'nav'],
+    strict=False,  # less strict on the parsing of the actions
+    multiaction=True,  # enable to agent to take multiple actions at once
+)
+
+
+_BROWSER_DESCRIPTION = """Interact with the browser using Python code. Use it ONLY when you need to interact with a webpage.
+
+See the description of "code" parameter for more details.
+
+Multiple actions can be provided at once, but will be executed sequentially without any feedback from the page.
+More than 2-3 actions usually leads to failure or unexpected behavior. Example:
+fill('a12', 'example with "quotes"')
+click('a51')
+click('48', button='middle', modifiers=['Shift'])
+"""
+
+_BROWSER_TOOL_DESCRIPTION = """
+The following 15 functions are available. Nothing else is supported.
+
+goto(url: str)
+    Description: Navigate to a url.
+    Examples:
+        goto('http://www.example.com')
+
+go_back()
+    Description: Navigate to the previous page in history.
+    Examples:
+        go_back()
+
+go_forward()
+    Description: Navigate to the next page in history.
+    Examples:
+        go_forward()
+
+noop(wait_ms: float = 1000)
+    Description: Do nothing, and optionally wait for the given time (in milliseconds).
+    You can use this to get the current page content and/or wait for the page to load.
+    Examples:
+        noop()
+
+        noop(500)
+
+scroll(delta_x: float, delta_y: float)
+    Description: Scroll horizontally and vertically. Amounts in pixels, positive for right or down scrolling, negative for left or up scrolling. Dispatches a wheel event.
+    Examples:
+        scroll(0, 200)
+
+        scroll(-50.2, -100.5)
+
+fill(bid: str, value: str)
+    Description: Fill out a form field. It focuses the element and triggers an input event with the entered text. It works for <input>, <textarea> and [contenteditable] elements.
+    Examples:
+        fill('237', 'example value')
+
+        fill('45', 'multi-line\nexample')
+
+        fill('a12', 'example with "quotes"')
+
+select_option(bid: str, options: str | list[str])
+    Description: Select one or multiple options in a <select> element. You can specify option value or label to select. Multiple options can be selected.
+    Examples:
+        select_option('a48', 'blue')
+
+        select_option('c48', ['red', 'green', 'blue'])
+
+click(bid: str, button: Literal['left', 'middle', 'right'] = 'left', modifiers: list[typing.Literal['Alt', 'Control', 'ControlOrMeta', 'Meta', 'Shift']] = [])
+    Description: Click an element.
+    Examples:
+        click('a51')
+
+        click('b22', button='right')
+
+        click('48', button='middle', modifiers=['Shift'])
+
+dblclick(bid: str, button: Literal['left', 'middle', 'right'] = 'left', modifiers: list[typing.Literal['Alt', 'Control', 'ControlOrMeta', 'Meta', 'Shift']] = [])
+    Description: Double click an element.
+    Examples:
+        dblclick('12')
+
+        dblclick('ca42', button='right')
+
+        dblclick('178', button='middle', modifiers=['Shift'])
+
+hover(bid: str)
+    Description: Hover over an element.
+    Examples:
+        hover('b8')
+
+press(bid: str, key_comb: str)
+    Description: Focus the matching element and press a combination of keys. It accepts the logical key names that are emitted in the keyboardEvent.key property of the keyboard events: Backquote, Minus, Equal, Backslash, Backspace, Tab, Delete, Escape, ArrowDown, End, Enter, Home, Insert, PageDown, PageUp, ArrowRight, ArrowUp, F1 - F12, Digit0 - Digit9, KeyA - KeyZ, etc. You can alternatively specify a single character you'd like to produce such as "a" or "#". Following modification shortcuts are also supported: Shift, Control, Alt, Meta, ShiftLeft, ControlOrMeta. ControlOrMeta resolves to Control on Windows and Linux and to Meta on macOS.
+    Examples:
+        press('88', 'Backspace')
+
+        press('a26', 'ControlOrMeta+a')
+
+        press('a61', 'Meta+Shift+t')
+
+focus(bid: str)
+    Description: Focus the matching element.
+    Examples:
+        focus('b455')
+
+clear(bid: str)
+    Description: Clear the input field.
+    Examples:
+        clear('996')
+
+drag_and_drop(from_bid: str, to_bid: str)
+    Description: Perform a drag & drop. Hover the element that will be dragged. Press left mouse button. Move mouse to the element that will receive the drop. Release left mouse button.
+    Examples:
+        drag_and_drop('56', '498')
+
+upload_file(bid: str, file: str | list[str])
+    Description: Click an element and wait for a "filechooser" event, then select one or multiple input files for upload. Relative file paths are resolved relative to the current working directory. An empty list clears the selected files.
+    Examples:
+        upload_file('572', '/home/user/my_receipt.pdf')
+
+        upload_file('63', ['/home/bob/Documents/image.jpg', '/home/bob/Documents/file.zip'])
+"""
+
+
+for _, action in _browser_action_space.action_set.items():
+    assert (
+        action.signature in _BROWSER_TOOL_DESCRIPTION
+    ), f'Browser description mismatch. Please double check if the BrowserGym updated their action space.\n\nAction: {action.signature}'
+    assert (
+        action.description in _BROWSER_TOOL_DESCRIPTION
+    ), f'Browser description mismatch. Please double check if the BrowserGym updated their action space.\n\nAction: {action.description}'
+
+BrowserTool = ChatCompletionToolParam(
+    type='function',
+    function=ChatCompletionToolParamFunctionChunk(
+        name='browser',
+        description=_BROWSER_DESCRIPTION,
+        parameters={
+            'type': 'object',
+            'properties': {
+                'code': {
+                    'type': 'string',
+                    'description': (
+                        'The Python code that interacts with the browser.\n'
+                        + _BROWSER_TOOL_DESCRIPTION
+                    ),
+                }
+            },
+            'required': ['code'],
+        },
+    ),
+)
+
+_FINISH_DESCRIPTION = """Finish the interaction when the task is complete OR if the assistant cannot proceed further with the task."""
+
+FinishTool = ChatCompletionToolParam(
+    type='function',
+    function=ChatCompletionToolParamFunctionChunk(
+        name='finish',
+        description=_FINISH_DESCRIPTION,
+    ),
+)
+
+
+def combine_thought(action: Action, thought: str) -> Action:
+    if not hasattr(action, 'thought'):
+        return action
+    if thought:
+        action.thought = thought
+    return action
+
+
+def response_to_actions(response: ModelResponse) -> list[Action]:
+    actions: list[Action] = []
+    assert len(response.choices) == 1, 'Only one choice is supported for now'
+    assistant_msg = response.choices[0].message
+    if assistant_msg.tool_calls:
+        # Check if there's assistant_msg.content. If so, add it to the thought
+        thought = ''
+        if isinstance(assistant_msg.content, str):
+            thought = assistant_msg.content
+        elif isinstance(assistant_msg.content, list):
+            for msg in assistant_msg.content:
+                if msg['type'] == 'text':
+                    thought += msg['text']
+
+        # Process each tool call to OpenHands action
+        for i, tool_call in enumerate(assistant_msg.tool_calls):
+            action: Action
+            try:
+                arguments = json.loads(tool_call.function.arguments)
+            except json.decoder.JSONDecodeError as e:
+                raise RuntimeError(
+                    f'Failed to parse tool call arguments: {tool_call.function.arguments}'
+                ) from e
+            if tool_call.function.name == 'execute_bash':
+                action = CmdRunAction(**arguments)
+            elif tool_call.function.name == 'execute_ipython_cell':
+                action = IPythonRunCellAction(**arguments)
+            elif tool_call.function.name == 'delegate_to_browsing_agent':
+                action = AgentDelegateAction(
+                    agent='BrowsingAgent',
+                    inputs=arguments,
+                )
+            elif tool_call.function.name == 'finish':
+                action = AgentFinishAction()
+            elif tool_call.function.name == 'edit_file':
+                action = FileEditAction(**arguments)
+            elif tool_call.function.name == 'str_replace_editor':
+                # We implement this in agent_skills, which can be used via Jupyter
+                # convert tool_call.function.arguments to kwargs that can be passed to file_editor
+                code = f'print(file_editor(**{arguments}))'
+                logger.debug(
+                    f'TOOL CALL: str_replace_editor -> file_editor with code: {code}'
+                )
+                action = IPythonRunCellAction(code=code, include_extra=False)
+            elif tool_call.function.name == 'browser':
+                action = BrowseInteractiveAction(browser_actions=arguments['code'])
+            elif tool_call.function.name == 'web_read':
+                action = BrowseURLAction(url=arguments['url'])
+            else:
+                raise FunctionCallNotExistsError(
+                    f'Tool {tool_call.function.name} is not registered. (arguments: {arguments}). Please check the tool name and retry with an existing tool.'
+                )
+
+            # We only add thought to the first action
+            if i == 0:
+                action = combine_thought(action, thought)
+            # Add metadata for tool calling
+            action.tool_call_metadata = ToolCallMetadata(
+                tool_call_id=tool_call.id,
+                function_name=tool_call.function.name,
+                model_response=response,
+                total_calls_in_response=len(assistant_msg.tool_calls),
+            )
+            actions.append(action)
+    else:
+        actions.append(
+            MessageAction(content=assistant_msg.content, wait_for_response=True)
+        )
+
+    assert len(actions) >= 1
+    return actions
+
+
+def get_tools(
+    codeact_enable_browsing: bool = False,
+    codeact_enable_llm_editor: bool = False,
+    codeact_enable_jupyter: bool = False,
+) -> list[ChatCompletionToolParam]:
+    tools = [CmdRunTool, FinishTool]
+    if codeact_enable_browsing:
+        tools.append(WebReadTool)
+        tools.append(BrowserTool)
+    if codeact_enable_jupyter:
+        tools.append(IPythonTool)
+    if codeact_enable_llm_editor:
+        tools.append(LLMBasedFileEditTool)
+    else:
+        tools.append(StrReplaceEditorTool)
+    return tools

agenthub/codeact_agent/prompt.py

@@ -1,275 +0,0 @@
-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_by_replace`, `append_file` and `insert_content_at_line` FUNCTIONS REQUIRE PROPER INDENTATION. If the assistant would like to add the line '        print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run."
-)
-
-# ======= SYSTEM MESSAGE =======
-MINIMAL_SYSTEM_PREFIX = """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
-The assistant can use an interactive Python (Jupyter Notebook) environment, executing code with <execute_ipython>.
-<execute_ipython>
-print("Hello World!")
-</execute_ipython>
-The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
-
-For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
-Important, however: do not run interactive commands. You do not have access to stdin.
-Also, you need to handle commands that may run indefinitely and not return a result. For such cases, you should redirect the output to a file and run the command in the background to avoid blocking the execution.
-For example, to run a Python script that might run indefinitely without returning immediately, you can use the following format: <execute_bash> python3 app.py > server.log 2>&1 & </execute_bash>
-Also, if a command execution result saying like: Command: "npm start" timed out. Sending SIGINT to the process, you should also retry with running the command in the background.
-"""
-
-BROWSING_PREFIX = """The assistant can browse the Internet with <execute_browse> and </execute_browse>.
-For example, <execute_browse> Tell me the usa's president using google search </execute_browse>.
-Or <execute_browse> Tell me what is in http://example.com </execute_browse>.
-"""
-PIP_INSTALL_PREFIX = """The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them."""
-
-SYSTEM_PREFIX = MINIMAL_SYSTEM_PREFIX + BROWSING_PREFIX + PIP_INSTALL_PREFIX
-
-GITHUB_MESSAGE = """To interact with GitHub, use the $GITHUB_TOKEN environment variable.
-For example, to push a branch `my_branch` to the GitHub repo `owner/repo`:
-<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
-If $GITHUB_TOKEN is not set, ask the user to set it."""
-
-SYSTEM_SUFFIX = """Responses should be concise.
-The assistant should attempt fewer things at a time instead of putting too many commands OR too much code in one "execute" block.
-Include ONLY ONE <execute_ipython>, <execute_bash>, or <execute_browse> per response, unless the assistant is finished with the task or needs more input or action from the user in order to proceed.
-If the assistant is finished with the task you MUST include <finish></finish> in your response.
-IMPORTANT: Execute code using <execute_ipython>, <execute_bash>, or <execute_browse> whenever possible.
-When handling files, try to use full paths and pwd to avoid errors.
-"""
-
-
-# ======= EXAMPLE MESSAGE =======
-EXAMPLES = """
---- START OF EXAMPLE ---
-
-USER: Create a list of numbers from 1 to 10, and display them in a web page at port 5000.
-
-ASSISTANT:
-Sure! Let me create a Python file `app.py`:
-<execute_ipython>
-create_file('app.py')
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[File: /workspace/app.py (1 lines total)]
-(this is the beginning of the file)
-1|
-(this is the end of the file)
-[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)\"\"\"
-
-insert_content_at_line(
-  'app.py',
-  1,
-  EDITED_CODE,
-)
-</execute_ipython>
-
-USER:
-OBSERVATION:
-(this is the beginning of the file)
-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)
-(this is the end of the file)
-[File updated (edited at line 1). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
-
-ASSISTANT:
-I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you:
-<execute_bash>
-python3 app.py > server.log 2>&1 &
-</execute_bash>
-
-USER:
-OBSERVATION:
-[1] 121[1]+  Exit 1                  python3 app.py > server.log 2>&1
-
-ASSISTANT: Looks like the server is running with PID 121 then crashed. Let me check the server log:
-<execute_bash>
-cat server.log
-</execute_bash>
-
-USER:
-OBSERVATION:
-Traceback (most recent call last):
-  File "/workspace/app.py", line 2, in <module>
-    from flask import Flask
-ModuleNotFoundError: No module named 'flask'
-
-ASSISTANT:
-It seems that Flask is not installed. Let me install Flask for you:
-<execute_bash>
-pip install flask
-</execute_bash>
-
-USER:
-OBSERVATION:
-Defaulting to user installation because normal site-packages is not writeable
-Collecting flask
-  Using cached flask-3.0.3-py3-none-any.whl (101 kB)
-Collecting blinker>=1.6.2
-  Using cached blinker-1.7.0-py3-none-any.whl (13 kB)
-Collecting Werkzeug>=3.0.0
-  Using cached werkzeug-3.0.2-py3-none-any.whl (226 kB)
-Collecting click>=8.1.3
-  Using cached click-8.1.7-py3-none-any.whl (97 kB)
-Collecting itsdangerous>=2.1.2
-  Using cached itsdangerous-2.2.0-py3-none-any.whl (16 kB)
-Requirement already satisfied: Jinja2>=3.1.2 in /home/opendevin/.local/lib/python3.10/site-packages (from flask) (3.1.3)
-Requirement already satisfied: MarkupSafe>=2.0 in /home/opendevin/.local/lib/python3.10/site-packages (from Jinja2>=3.1.2->flask) (2.1.5)
-Installing collected packages: Werkzeug, itsdangerous, click, blinker, flask
-Successfully installed Werkzeug-3.0.2 blinker-1.7.0 click-8.1.7 flask-3.0.3 itsdangerous-2.2.0
-
-ASSISTANT:
-Now that Flask is installed, let me run the Python file again:
-<execute_bash>
-python3 app.py > server.log 2>&1 &
-</execute_bash>
-
-USER:
-OBSERVATION:
-[1] 124
-
-ASSISTANT:
-Let me check the server log again:
-<execute_bash>
-cat server.log
-</execute_bash>
-
-USER:
-OBSERVATION:
-* Serving Flask app 'app'
- * Debug mode: off
-WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
- * Running on http://127.0.0.1:5000
-Press CTRL+C to quit
-
-ASSISTANT:
-The server is running on port 5000 with PID 124. You can access the list of numbers by visiting http://127.0.0.1:5000. If you have any further questions, feel free to ask!
-
-USER: Now browse the newly started server's homepage and show me the content.
-
-ASSISTANT:
-Sure! Let me browse the server's homepage at http://127.0.0.1:5000:
-<execute_browse>
-Get the content on "http://127.0.0.1:5000"
-</execute_browse>
-
-USER:
-OBSERVATION:
-[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
-
-ASSISTANT:
-The content of the server's homepage is "[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]". If you have any further questions, feel free to ask!
-
-USER: Now kill the server, make it display the numbers in a table format.
-
-ASSISTANT:
-Sure! Let me stop the server first:
-<execute_bash>
-kill 124
-</execute_bash>
-
-USER:
-OBSERVATION:
-[1]+  Terminated              python3 app.py > server.log 2>&1
-
-ASSISTANT:
-The server has been stopped. Let me open the Python file and modify it.
-<execute_ipython>
-open_file('app.py')
-</execute_ipython>
-
-USER:
-[File: /workspace/app.py (10 lines total)]
-(this is the beginning of the file)
-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)
-(this is the end of the file)
-
-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_by_replace(
-  'app.py',
-  to_replace="    return str(numbers)",
-  new_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)]
-(this is the beginning of the file)
-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)
-(this is the end of the file)
-[File updated (edited at line 7). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
-
-ASSISTANT:
-Running the updated file:
-<execute_bash>
-python3 app.py > server.log 2>&1 &
-</execute_bash>
-
-USER:
-Observation:
-[1] 126
-
-ASSISTANT:
-The server is running on port 5000 with PID 126. You can access the list of numbers in a table format by visiting http://127.0.0.1:5000. Let me know if you have any further requests!
-<finish></finish>
-
---- END OF EXAMPLE ---
-"""
-
-INVALID_INPUT_MESSAGE = (
-    "I don't understand your input. \n"
-    'For bash commands, use <execute_bash> YOUR_COMMAND </execute_bash>.\n'
-    'For Python code, use <execute_ipython> YOUR_CODE </execute_ipython>.\n'
-    'For browsing, use <execute_browse> YOUR_COMMAND </execute_browse>.\n'
-)

agenthub/codeact_agent/prompts/system_prompt.j2

@@ -0,0 +1,6 @@
+You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.
+<IMPORTANT>
+* If user provides a path, you should NOT assume it's relative to the current working directory. Instead, you should explore the file system to find the file before working on it.
+* When configuring git credentials, use "openhands" as the user.name and "openhands@all-hands.dev" as the user.email by default, unless explicitly instructed otherwise.
+* The assistant MUST NOT include comments in the code unless they are necessary to describe non-obvious behavior.
+</IMPORTANT>

agenthub/codeact_swe_agent/README.md

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

agenthub/codeact_swe_agent/__init__.py

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

agenthub/codeact_swe_agent/action_parser.py

@@ -1,110 +0,0 @@
-import re
-
-from opendevin.controller.action_parser import ActionParser
-from opendevin.events.action import (
-    Action,
-    AgentFinishAction,
-    CmdRunAction,
-    IPythonRunCellAction,
-    MessageAction,
-)
-
-
-class CodeActSWEActionParserFinish(ActionParser):
-    """Parser action:
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(
-        self,
-    ):
-        self.finish_command = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.finish_command = re.search(r'<finish>.*</finish>', action_str, re.DOTALL)
-        return self.finish_command is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.finish_command is not None
-        ), 'self.finish_command should not be None when parse is called'
-        thought = action_str.replace(self.finish_command.group(0), '').strip()
-        return AgentFinishAction(thought=thought)
-
-
-class CodeActSWEActionParserCmdRun(ActionParser):
-    """Parser action:
-    - CmdRunAction(command) - bash command to run
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(
-        self,
-    ):
-        self.bash_command = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.bash_command = re.search(
-            r'<execute_bash>(.*?)</execute_bash>', action_str, re.DOTALL
-        )
-        return self.bash_command is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.bash_command is not None
-        ), 'self.bash_command should not be None when parse is called'
-        thought = action_str.replace(self.bash_command.group(0), '').strip()
-        # a command was found
-        command_group = self.bash_command.group(1).strip()
-        if command_group.strip() == 'exit':
-            return AgentFinishAction()
-        return CmdRunAction(command=command_group, thought=thought)
-
-
-class CodeActSWEActionParserIPythonRunCell(ActionParser):
-    """Parser action:
-    - IPythonRunCellAction(code) - IPython code to run
-    """
-
-    def __init__(
-        self,
-    ):
-        self.python_code = None
-        self.jupyter_kernel_init_code: str = 'from agentskills import *'
-
-    def check_condition(self, action_str: str) -> bool:
-        self.python_code = re.search(
-            r'<execute_ipython>(.*?)</execute_ipython>', action_str, re.DOTALL
-        )
-        return self.python_code is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.python_code is not None
-        ), 'self.python_code should not be None when parse is called'
-        code_group = self.python_code.group(1).strip()
-        thought = action_str.replace(self.python_code.group(0), '').strip()
-        return IPythonRunCellAction(
-            code=code_group,
-            thought=thought,
-            kernel_init_code=self.jupyter_kernel_init_code,
-        )
-
-
-class CodeActSWEActionParserMessage(ActionParser):
-    """Parser action:
-    - MessageAction(content) - Message action to run (e.g. ask for clarification)
-    """
-
-    def __init__(
-        self,
-    ):
-        pass
-
-    def check_condition(self, action_str: str) -> bool:
-        # We assume the LLM is GOOD enough that when it returns pure natural language
-        # it wants to talk to the user
-        return True
-
-    def parse(self, action_str: str) -> Action:
-        return MessageAction(content=action_str, wait_for_response=True)

agenthub/codeact_swe_agent/codeact_swe_agent.py

@@ -1,196 +0,0 @@
-from agenthub.codeact_swe_agent.prompt import (
-    COMMAND_DOCS,
-    SWE_EXAMPLE,
-    SYSTEM_PREFIX,
-    SYSTEM_SUFFIX,
-)
-from agenthub.codeact_swe_agent.response_parser import CodeActSWEResponseParser
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.events.action import (
-    Action,
-    AgentFinishAction,
-    CmdRunAction,
-    IPythonRunCellAction,
-    MessageAction,
-)
-from opendevin.events.observation import (
-    CmdOutputObservation,
-    IPythonRunCellObservation,
-)
-from opendevin.events.observation.observation import Observation
-from opendevin.events.serialization.event import truncate_content
-from opendevin.llm.llm import LLM
-from opendevin.runtime.plugins import (
-    AgentSkillsRequirement,
-    JupyterRequirement,
-    PluginRequirement,
-)
-from opendevin.runtime.tools import RuntimeTool
-
-
-def get_system_message() -> str:
-    return f'{SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
-
-
-def get_in_context_example() -> str:
-    return SWE_EXAMPLE
-
-
-class CodeActSWEAgent(Agent):
-    VERSION = '1.6'
-    """
-    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 needs to be initialized before Jupyter for Jupyter to use those functions.
-        AgentSkillsRequirement(),
-        JupyterRequirement(),
-    ]
-    runtime_tools: list[RuntimeTool] = []
-
-    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!"
-
-    response_parser = CodeActSWEResponseParser()
-
-    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 action_to_str(self, 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, MessageAction):
-            return action.content
-        return ''
-
-    def get_action_message(self, action: Action) -> dict[str, str] | None:
-        if (
-            isinstance(action, CmdRunAction)
-            or isinstance(action, IPythonRunCellAction)
-            or isinstance(action, MessageAction)
-        ):
-            return {
-                'role': 'user' if action.source == 'user' else 'assistant',
-                'content': self.action_to_str(action),
-            }
-        return None
-
-    def get_observation_message(self, obs: Observation) -> dict[str, str] | None:
-        max_message_chars = self.llm.config.max_message_chars
-        if isinstance(obs, CmdOutputObservation):
-            content = 'OBSERVATION:\n' + truncate_content(
-                obs.content, max_message_chars
-            )
-            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_content(content, max_message_chars)
-            return {'role': 'user', 'content': content}
-        return None
-
-    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
-        - MessageAction(content) - Message action to run (e.g. ask for clarification)
-        - AgentFinishAction() - end the interaction
-        """
-        # if we're done, go back
-        latest_user_message = state.history.get_last_user_message()
-        if latest_user_message and latest_user_message.strip() == '/exit':
-            return AgentFinishAction()
-
-        # prepare what we want to send to the LLM
-        messages: list[dict[str, str]] = self._get_messages(state)
-
-        response = self.llm.completion(
-            messages=messages,
-            stop=[
-                '</execute_ipython>',
-                '</execute_bash>',
-            ],
-            temperature=0.0,
-        )
-
-        return self.response_parser.parse(response)
-
-    def _get_messages(self, state: State) -> list[dict[str, str]]:
-        messages = [
-            {'role': 'system', 'content': self.system_message},
-            {'role': 'user', 'content': self.in_context_example},
-        ]
-
-        for event in state.history.get_events():
-            # create a regular message from an event
-            if isinstance(event, Action):
-                message = self.get_action_message(event)
-            elif isinstance(event, Observation):
-                message = self.get_observation_message(event)
-            else:
-                raise ValueError(f'Unknown event type: {type(event)}')
-
-            # add regular message
-            if message:
-                # handle error if the message is the SAME role as the previous message
-                # litellm.exceptions.BadRequestError: litellm.BadRequestError: OpenAIException - Error code: 400 - {'detail': 'Only supports u/a/u/a/u...'}
-                # there should not have two consecutive messages from the same role
-                if messages and messages[-1]['role'] == message['role']:
-                    messages[-1]['content'] += '\n\n' + message['content']
-                else:
-                    messages.append(message)
-
-        # the latest user message is important:
-        # we want to remind the agent of the environment constraints
-        latest_user_message = next(
-            (m for m in reversed(messages) if m['role'] == 'user'), None
-        )
-
-        # add a reminder to the prompt
-        if latest_user_message:
-            latest_user_message['content'] += (
-                f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task.'
-            )
-
-        return messages

agenthub/codeact_swe_agent/prompt.py

@@ -1,455 +0,0 @@
-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>.
-"""
-
-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 + PIP_INSTALL_PREFIX
-
-SYSTEM_SUFFIX = """The assistant's response should be concise.
-The assistant should include ONLY ONE <execute_ipython> or <execute_bash> 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> 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/codeact_swe_agent/response_parser.py

@@ -1,46 +0,0 @@
-from agenthub.codeact_swe_agent.action_parser import (
-    CodeActSWEActionParserCmdRun,
-    CodeActSWEActionParserFinish,
-    CodeActSWEActionParserIPythonRunCell,
-    CodeActSWEActionParserMessage,
-)
-from opendevin.controller.action_parser import ResponseParser
-from opendevin.events.action import Action
-
-
-class CodeActSWEResponseParser(ResponseParser):
-    """Parser action:
-    - CmdRunAction(command) - bash command to run
-    - IPythonRunCellAction(code) - IPython code to run
-    - MessageAction(content) - Message action to run (e.g. ask for clarification)
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(self):
-        # Need pay attention to the item order in self.action_parsers
-        super().__init__()
-        self.action_parsers = [
-            CodeActSWEActionParserFinish(),
-            CodeActSWEActionParserCmdRun(),
-            CodeActSWEActionParserIPythonRunCell(),
-        ]
-        self.default_parser = CodeActSWEActionParserMessage()
-
-    def parse(self, response: str) -> Action:
-        action_str = self.parse_response(response)
-        return self.parse_action(action_str)
-
-    def parse_response(self, response) -> str:
-        action = response.choices[0].message.content
-        if action is None:
-            return ''
-        for lang in ['bash', 'ipython']:
-            if f'<execute_{lang}>' in action and f'</execute_{lang}>' not in action:
-                action += f'</execute_{lang}>'
-        return action
-
-    def parse_action(self, action_str: str) -> Action:
-        for action_parser in self.action_parsers:
-            if action_parser.check_condition(action_str):
-                return action_parser.parse(action_str)
-        return self.default_parser.parse(action_str)

agenthub/delegator_agent/__init__.py

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

agenthub/delegator_agent/agent.py

@@ -1,8 +1,9 @@
-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 openhands.controller.agent import Agent
+from openhands.controller.state.state import State
+from openhands.core.config import AgentConfig
+from openhands.events.action import Action, AgentDelegateAction, AgentFinishAction
+from openhands.events.observation import AgentDelegateObservation, Observation
+from openhands.llm.llm import LLM
 
 
 class DelegatorAgent(Agent):
@@ -13,13 +14,13 @@ class DelegatorAgent(Agent):
 
     current_delegate: str = ''
 
-    def __init__(self, llm: LLM):
+    def __init__(self, llm: LLM, config: AgentConfig):
         """Initialize the Delegator Agent with an LLM
 
         Parameters:
         - llm (LLM): The llm to be used by this agent
         """
-        super().__init__(llm)
+        super().__init__(llm, config)
 
     def step(self, state: State) -> Action:
         """Checks to see if current step is completed, returns AgentFinishAction if True.
@@ -34,18 +35,22 @@ class DelegatorAgent(Agent):
         """
         if self.current_delegate == '':
             self.current_delegate = 'study'
-            task = state.get_current_user_intent()
+            task, _ = state.get_current_user_intent()
             return AgentDelegateAction(
                 agent='StudyRepoForTaskAgent', inputs={'task': task}
             )
 
         # last observation in history should be from the delegate
-        last_observation = state.history.get_last_observation()
+        last_observation = None
+        for event in reversed(state.history):
+            if isinstance(event, Observation):
+                last_observation = event
+                break
 
         if not isinstance(last_observation, AgentDelegateObservation):
             raise Exception('Last observation is not an AgentDelegateObservation')
 
-        goal = state.get_current_user_intent()
+        goal, _ = state.get_current_user_intent()
         if self.current_delegate == 'study':
             self.current_delegate = 'coder'
             return AgentDelegateAction(

agenthub/dummy_agent/__init__.py

@@ -1,5 +1,4 @@
-from opendevin.controller.agent import Agent
-
-from .agent import DummyAgent
+from openhands.agenthub.dummy_agent.agent import DummyAgent
+from openhands.controller.agent import Agent
 
 Agent.register('DummyAgent', DummyAgent)

agenthub/dummy_agent/agent.py

@@ -1,9 +1,10 @@
 from typing import TypedDict, Union
 
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.core.schema import AgentState
-from opendevin.events.action import (
+from openhands.controller.agent import Agent
+from openhands.controller.state.state import State
+from openhands.core.config import AgentConfig
+from openhands.core.schema import AgentState
+from openhands.events.action import (
     Action,
     AddTaskAction,
     AgentFinishAction,
@@ -16,7 +17,7 @@ from opendevin.events.action import (
     MessageAction,
     ModifyTaskAction,
 )
-from opendevin.events.observation import (
+from openhands.events.observation import (
     AgentStateChangedObservation,
     CmdOutputObservation,
     FileReadObservation,
@@ -24,8 +25,8 @@ from opendevin.events.observation import (
     NullObservation,
     Observation,
 )
-from opendevin.events.serialization.event import event_to_dict
-from opendevin.llm.llm import LLM
+from openhands.events.serialization.event import event_to_dict
+from openhands.llm.llm import LLM
 
 """
 FIXME: There are a few problems this surfaced
@@ -45,8 +46,8 @@ class DummyAgent(Agent):
     without making any LLM calls.
     """
 
-    def __init__(self, llm: LLM):
-        super().__init__(llm)
+    def __init__(self, llm: LLM, config: AgentConfig):
+        super().__init__(llm, config)
         self.steps: list[ActionObs] = [
             {
                 'action': AddTaskAction(
@@ -163,7 +164,7 @@ class DummyAgent(Agent):
 
             if 'observations' in prev_step and prev_step['observations']:
                 expected_observations = prev_step['observations']
-                hist_events = state.history.get_last_events(len(expected_observations))
+                hist_events = state.history[-len(expected_observations) :]
 
                 if len(hist_events) < len(expected_observations):
                     print(
@@ -208,9 +209,3 @@ class DummyAgent(Agent):
                 f' Unable to perform interactive browsing: {action.browser_actions}'
             )
         return MessageAction(content=message)
-
-    async def get_working_directory(self, state: State) -> str:
-        # Implement this method to return the current working directory
-        # This might involve accessing state information or making an async call
-        # For now, we'll return a placeholder value
-        return './workspace'

agenthub/micro/README.md

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

agenthub/micro/_instructions/actions/browse.md

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

agenthub/micro/_instructions/actions/delegate.md

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

agenthub/micro/_instructions/actions/finish.md

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

agenthub/micro/_instructions/actions/message.md

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

agenthub/micro/_instructions/actions/read.md

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

agenthub/micro/_instructions/actions/reject.md

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

agenthub/micro/_instructions/actions/run.md

@@ -1,2 +0,0 @@
-* `run` - runs a command on the command line in a Linux shell. Arguments:
-  * `command` - the command to run

agenthub/micro/_instructions/actions/write.md

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

agenthub/micro/_instructions/format/action.md

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

agenthub/micro/_instructions/history_truncated.md

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

agenthub/micro/agent.py

@@ -1,16 +1,17 @@
 from jinja2 import BaseLoader, Environment
 
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.core.utils import json
-from opendevin.events.action import Action
-from opendevin.events.serialization.action import action_from_dict
-from opendevin.events.serialization.event import event_to_memory
-from opendevin.llm.llm import LLM
-from opendevin.memory.history import ShortTermHistory
-
-from .instructions import instructions
-from .registry import all_microagents
+from openhands.agenthub.micro.instructions import instructions
+from openhands.agenthub.micro.registry import all_microagents
+from openhands.controller.agent import Agent
+from openhands.controller.state.state import State
+from openhands.core.config import AgentConfig
+from openhands.core.message import ImageContent, Message, TextContent
+from openhands.core.utils import json
+from openhands.events.action import Action
+from openhands.events.event import Event
+from openhands.events.serialization.action import action_from_dict
+from openhands.events.serialization.event import event_to_memory
+from openhands.llm.llm import LLM
 
 
 def parse_response(orig_response: str) -> Action:
@@ -31,16 +32,14 @@ class MicroAgent(Agent):
     prompt = ''
     agent_definition: dict = {}
 
-    def history_to_json(
-        self, history: ShortTermHistory, max_events: int = 20, **kwargs
-    ):
+    def history_to_json(self, history: list[Event], max_events: int = 20, **kwargs):
         """
         Serialize and simplify history to str format
         """
         processed_history = []
         event_count = 0
 
-        for event in history.get_events(reverse=True):
+        for event in reversed(history):
             if event_count >= max_events:
                 break
             processed_history.append(
@@ -53,8 +52,8 @@ class MicroAgent(Agent):
 
         return json.dumps(processed_history, **kwargs)
 
-    def __init__(self, llm: LLM):
-        super().__init__(llm)
+    def __init__(self, llm: LLM, config: AgentConfig):
+        super().__init__(llm, config)
         if 'name' not in self.agent_definition:
             raise ValueError('Agent definition must contain a name')
         self.prompt_template = Environment(loader=BaseLoader).from_string(self.prompt)
@@ -62,16 +61,22 @@ class MicroAgent(Agent):
         del self.delegates[self.agent_definition['name']]
 
     def step(self, state: State) -> Action:
+        last_user_message, last_image_urls = state.get_current_user_intent()
         prompt = self.prompt_template.render(
             state=state,
             instructions=instructions,
             to_json=to_json,
             history_to_json=self.history_to_json,
             delegates=self.delegates,
-            latest_user_message=state.get_current_user_intent(),
+            latest_user_message=last_user_message,
+        )
+        content = [TextContent(text=prompt)]
+        if self.llm.vision_is_active() and last_image_urls:
+            content.append(ImageContent(image_urls=last_image_urls))
+        message = Message(role='user', content=content)
+        resp = self.llm.completion(
+            messages=self.llm.format_messages_for_llm(message),
         )
-        messages = [{'content': prompt, 'role': 'user'}]
-        resp = self.llm.completion(messages=messages)
         action_resp = resp['choices'][0]['message']['content']
         action = parse_response(action_resp)
         return action

agenthub/micro/coder/prompt.md

@@ -1,27 +0,0 @@
-# Task
-You are a software engineer. You've inherited an existing codebase, which you
-need to modify to complete this task:
-
-{{ state.inputs.task }}
-
-{% if state.inputs.summary %}
-Here's a summary of the codebase, as it relates to this task:
-
-{{ state.inputs.summary }}
-{% endif %}
-
-## Available Actions
-{{ instructions.actions.run }}
-{{ instructions.actions.write }}
-{{ instructions.actions.read }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-Do NOT finish until you have completed the tasks.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}

agenthub/micro/commit_writer/README.md

@@ -1,25 +0,0 @@
-## Introduction
-
-CommitWriterAgent can help write git commit message. Example:
-
-```bash
-WORKSPACE_MOUNT_PATH="`PWD`" SANDBOX_BOX_TYPE="ssh" \
-  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/prompt.md

@@ -1,33 +0,0 @@
-# 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 first use `git status` to check whether it's a valid git repo and there
-is diff in the staging area. If not, please call the `reject` action.
-
-If it is a valid git repo and there is diff in the staging area, you should find
-the diff using `git diff --cached`, compile a commit message, and call the `finish`
-action with `outputs.answer` set to the answer.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-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/manager/prompt.md

@@ -1,41 +0,0 @@
-# Task
-You are in charge of accomplishing the following task:
-{{ latest_user_message }}
-
-In order to accomplish this goal, you must delegate tasks to one or more agents, who
-can do the actual work. A description of each agent is provided below. You MUST
-select one of the delegates below to move towards accomplishing the task, and you MUST
-provide the correct inputs for the delegate you select.
-
-Note: the delegated agent either returns "finish" or "reject".
-- If the action is "finish", but the full task is not done yet, you should
-continue to delegate to one of the agents below to until the full task is finished.
-- If the action is "reject", it means the delegated agent is not capable of the
-task you send to. You should revisit the input you send to the delegate, and consider
-whether any other delegate would be able to solve the task. If you cannot find
-a proper delegate agent, or the delegate attempts keep failing, call the `reject`
-action. In `reason` attribute, make sure you include your attempts (e.g. what agent
-you have delegated to, and why they failed).
-
-## Agents
-{% for name, details in delegates.items() %}
-### {{ name }}
-{{ details.description }}
-#### Inputs
-{{ to_json(details.inputs) }}
-{% endfor %}
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-If the last item in the history is an error, you should try to fix it. If you
-cannot fix it, call the `reject` action.
-
-## Available Actions
-{{ instructions.actions.delegate }}
-{{ instructions.actions.finish }}
-{{ instructions.actions.reject }}
-
-## Format
-{{ instructions.format.action }}

agenthub/micro/math_agent/prompt.md

@@ -1,23 +0,0 @@
-# Task
-You are a brilliant mathematician and programmer. You've been given the following problem to solve:
-
-`{{ state.inputs.task }}`
-
-Please write a python script that solves this problem, and prints the answer to stdout.
-ONLY print the answer to stdout, nothing else.
-You should then run the python script with `python3`,
-and call the `finish` action with `outputs.answer` set to the answer.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-If the last item in the history is an error, you should try to fix it.
-
-## Available Actions
-{{ instructions.actions.write }}
-{{ instructions.actions.run }}
-{{ instructions.actions.finish }}
-
-## Format
-{{ instructions.format.action }}

agenthub/micro/postgres_agent/prompt.md

@@ -1,24 +0,0 @@
-# Task
-You are a database engineer. You are working on an existing Postgres project, and have been given
-the following task:
-
-{{ state.inputs.task }}
-
-You must:
-* Investigate the existing migrations to understand the current schema
-* Write a new migration to accomplish the task above
-* Test that the migrations work properly
-
-## Actions
-You may take any of the following actions:
-{{ instructions.actions.message }}
-{{ instructions.actions.read }}
-{{ instructions.actions.write }}
-{{ instructions.actions.run }}
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}

agenthub/micro/repo_explorer/prompt.md

@@ -1,26 +0,0 @@
-# Task
-You are a software engineer. You've inherited an existing codebase, which you're
-learning about for the first time. Your goal is to produce a detailed summary
-of the codebase, including:
-* The overall purpose of the project
-* The directory structure
-* The main components of the codebase
-* How the components fit together
-
-## Available Actions
-{{ instructions.actions.run }}
-{{ instructions.actions.read }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-You should ONLY `run` commands that have no side-effects, like `ls` and `grep`.
-
-Do NOT finish until you have a complete understanding of the codebase.
-When you're done, put your summary into the output of the `finish` action.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}

agenthub/micro/study_repo_for_task/prompt.md

@@ -1,62 +0,0 @@
-# Task
-You are a software architect. Your team has inherited an existing codebase, and
-need to finish a project:
-
-{{ state.inputs.task }}
-
-As an architect, you need to study the codebase to find all the information that
-might be helpful for your software engineering team.
-
-## Available Actions
-{{ instructions.actions.run }}
-{{ instructions.actions.read }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-You must ONLY `run` commands that have no side-effects, like `ls` and `grep`. You
-MUST NOT modify or write to any file.
-
-Do NOT finish until you have a complete understanding of which parts of the
-codebase are relevant to the project, including particular files, functions, and classes.
-When you're done, put your summary in `outputs.summary` in the `finish` action.
-Remember, your task is to explore and study the current repository, not actually
-implement the solution. If the codebase is empty, you should call the `finish` action.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}
-
-## Examples
-
-Here is an example of how you can interact with the environment for task solving:
-
---- START OF EXAMPLE ---
-
-USER: Can you create a list of numbers from 1 to 10, and create a web page to display them at port 5000?
-
-ASSISTANT:
-{
-  "action": "run",
-  "args": {
-    "command": "ls"
-  }
-}
-
-USER:
-OBSERVATION:
-[]
-
-ASSISTANT:
-{
-  "action": "finish",
-  "args": {
-    "outputs": {
-      "summary": "The codebase appears to be empty. Engineers should start everything from scratch."
-    }
-  }
-}
-
---- END OF EXAMPLE ---

agenthub/micro/typo_fixer_agent/prompt.md

@@ -1,54 +0,0 @@
-# Task
-You are a proofreader tasked with fixing typos in the files in your current working directory.
-
-{% if state.inputs.task %}
-Specifically, your task is:
-{{ state.inputs.task }}
-{% endif %}
-
-To achieve this goal, you should:
-
-1. Scan the files for typos
-2. Overwrite the files with the typos fixed
-3. Provide a summary of the typos fixed
-
-## Available Actions
-{{ instructions.actions.read }}
-{{ instructions.actions.write }}
-{{ instructions.actions.run }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-To complete this task:
-1. Use the `read` action to read the contents of the files in your current working directory. Make sure to provide the file path in the format `'./file_name.ext'`.
-2. Use the `message` action to analyze the contents and identify typos.
-3. Use the `write` action to create new versions of the files with the typos fixed.
-  - Overwrite the original files with the corrected content. Make sure to provide the file path in the format `'./file_name.ext'`.
-4. Use the `message` action to generate a summary of the typos fixed, including the original and fixed versions of each typo, and the file(s) they were found in.
-5. Use the `finish` action to return the summary in the `outputs.summary` field.
-
-Do NOT finish until you have fixed all the typos and generated a summary.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=10) }}
-
-## 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/prompt.md

@@ -1,28 +0,0 @@
-# Task
-You are a quality assurance engineer. Another engineer has made changes to the
-codebase which are supposed to solve this task:
-
-{{ state.inputs.task }}
-
-Note the changes might have already been applied in-line. You should focus on
-validating if the task is solved, nothing else.
-
-## Available Actions
-{{ instructions.actions.run }}
-{{ instructions.actions.read }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-You must ONLY `run` commands that have no side-effects, like `ls`, `grep`, and test scripts.
-
-Do NOT finish until you know whether the task is complete and correct.
-When you're done, add a `completed` boolean to the `outputs` of the `finish` action.
-If `completed` is `false`, you MUST also provide a `summary` in the `outputs` of the `finish` action
-explaining what the problem is.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}

agenthub/planner_agent/__init__.py

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

agenthub/planner_agent/agent.py

@@ -1,11 +1,11 @@
-from agenthub.planner_agent.response_parser import PlannerResponseParser
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.events.action import Action, AgentFinishAction
-from opendevin.llm.llm import LLM
-from opendevin.runtime.tools import RuntimeTool
-
-from .prompt import get_prompt
+from openhands.agenthub.planner_agent.prompt import get_prompt_and_images
+from openhands.agenthub.planner_agent.response_parser import PlannerResponseParser
+from openhands.controller.agent import Agent
+from openhands.controller.state.state import State
+from openhands.core.config import AgentConfig
+from openhands.core.message import ImageContent, Message, TextContent
+from openhands.events.action import Action, AgentFinishAction
+from openhands.llm.llm import LLM
 
 
 class PlannerAgent(Agent):
@@ -14,16 +14,15 @@ class PlannerAgent(Agent):
     The planner agent utilizes a special prompting strategy to create long term plans for solving problems.
     The agent is given its previous action-observation pairs, current task, and hint based on last action taken at every step.
     """
-    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
     response_parser = PlannerResponseParser()
 
-    def __init__(self, llm: LLM):
+    def __init__(self, llm: LLM, config: AgentConfig):
         """Initialize the Planner Agent with an LLM
 
         Parameters:
         - llm (LLM): The llm to be used by this agent
         """
-        super().__init__(llm)
+        super().__init__(llm, config)
 
     def step(self, state: State) -> Action:
         """Checks to see if current step is completed, returns AgentFinishAction if True.
@@ -42,7 +41,13 @@ class PlannerAgent(Agent):
             'abandoned',
         ]:
             return AgentFinishAction()
-        prompt = get_prompt(state, self.llm.config.max_message_chars)
-        messages = [{'content': prompt, 'role': 'user'}]
-        resp = self.llm.completion(messages=messages)
+
+        prompt, image_urls = get_prompt_and_images(
+            state, self.llm.config.max_message_chars
+        )
+        content = [TextContent(text=prompt)]
+        if self.llm.vision_is_active() and image_urls:
+            content.append(ImageContent(image_urls=image_urls))
+        message = Message(role='user', content=content)
+        resp = self.llm.completion(messages=self.llm.format_messages_for_llm(message))
         return self.response_parser.parse(resp)

agenthub/planner_agent/prompt.py

@@ -1,13 +1,13 @@
-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 (
+from openhands.controller.state.state import State
+from openhands.core.logger import openhands_logger as logger
+from openhands.core.schema import ActionType
+from openhands.core.utils import json
+from openhands.events.action import (
     Action,
     NullAction,
 )
-from opendevin.events.serialization.action import action_from_dict
-from opendevin.events.serialization.event import event_to_memory
+from openhands.events.serialization.action import action_from_dict
+from openhands.events.serialization.event import event_to_memory
 
 HISTORY_SIZE = 20
 
@@ -115,7 +115,9 @@ def get_hint(latest_action_id: str) -> str:
     return hints.get(latest_action_id, '')
 
 
-def get_prompt(state: State, max_message_chars: int) -> str:
+def get_prompt_and_images(
+    state: State, max_message_chars: int
+) -> tuple[str, list[str] | None]:
     """Gets the prompt for the planner agent.
 
     Formatted with the most recent action-observation pairs, current task, and hint based on last action
@@ -134,7 +136,7 @@ def get_prompt(state: State, max_message_chars: int) -> str:
     latest_action: Action = NullAction()
 
     # retrieve the latest HISTORY_SIZE events
-    for event_count, event in enumerate(state.history.get_events(reverse=True)):
+    for event_count, event in enumerate(reversed(state.history)):
         if event_count >= HISTORY_SIZE:
             break
         if latest_action == NullAction() and isinstance(event, Action):
@@ -158,19 +160,19 @@ def get_prompt(state: State, max_message_chars: int) -> str:
 
     # the hint, based on the last action
     hint = get_hint(event_to_memory(latest_action, max_message_chars).get('action', ''))
-    logger.info('HINT:\n' + hint, extra={'msg_type': 'DETAIL'})
+    logger.debug('HINT:\n' + hint, extra={'msg_type': 'DETAIL'})
 
     # the last relevant user message (the task)
-    task = state.get_current_user_intent()
+    message, image_urls = state.get_current_user_intent()
 
     # finally, fill in the prompt
     return prompt % {
-        'task': task,
+        'task': message,
         'plan': plan_str,
         'history': history_str,
         'hint': hint,
         'plan_status': plan_status,
-    }
+    }, image_urls
 
 
 def parse_response(response: str) -> Action:

agenthub/planner_agent/response_parser.py

@@ -1,9 +1,9 @@
-from opendevin.controller.action_parser import ResponseParser
-from opendevin.core.utils import json
-from opendevin.events.action import (
+from openhands.controller.action_parser import ResponseParser
+from openhands.core.utils import json
+from openhands.events.action import (
     Action,
 )
-from opendevin.events.serialization.action import action_from_dict
+from openhands.events.serialization.action import action_from_dict
 
 
 class PlannerResponseParser(ResponseParser):

config.template.toml

@@ -1,204 +0,0 @@
-###################### OpenDevin Configuration Example ######################
-#
-# All settings have default values, so you only need to uncomment and
-# modify what you want to change
-# The fields within each section are sorted in alphabetical order.
-#
-##############################################################################
-
-#################################### Core ####################################
-# General core configurations
-##############################################################################
-[core]
-# API key for E2B
-#e2b_api_key = ""
-
-# Base path for the workspace
-workspace_base = "./workspace"
-
-# Cache directory path
-#cache_dir = "/tmp/cache"
-
-# Debugging enabled
-#debug = false
-
-# Disable color in terminal output
-#disable_color = false
-
-# Enable saving and restoring the session when run from CLI
-#enable_cli_session = false
-
-# File store path
-#file_store_path = "/tmp/file_store"
-
-# File store type
-#file_store = "memory"
-
-# List of allowed file extensions for uploads
-#file_uploads_allowed_extensions = [".*"]
-
-# Maximum file size for uploads, in megabytes
-#file_uploads_max_file_size_mb = 0
-
-# Maximum budget per task, 0.0 means no limit
-#max_budget_per_task = 0.0
-
-# Maximum number of iterations
-#max_iterations = 100
-
-# Path to mount the workspace in the sandbox
-#workspace_mount_path_in_sandbox = "/workspace"
-
-# Path to mount the workspace
-#workspace_mount_path = ""
-
-# Path to rewrite the workspace mount path to
-#workspace_mount_rewrite = ""
-
-# Persist the sandbox
-persist_sandbox = false
-
-# Run as devin
-#run_as_devin = true
-
-# Runtime environment
-#runtime = "server"
-
-# SSH hostname for the sandbox
-#ssh_hostname = "localhost"
-
-# SSH password for the sandbox
-#ssh_password = ""
-
-# SSH port for the sandbox
-#ssh_port = 63710
-
-
-# Name of the default agent
-#default_agent = "CodeActAgent"
-
-#################################### LLM #####################################
-# Configuration for LLM models (group name starts with 'llm')
-# use 'llm' for the default LLM config
-##############################################################################
-[llm]
-# AWS access key ID
-#aws_access_key_id = ""
-
-# AWS region name
-#aws_region_name = ""
-
-# AWS secret access key
-#aws_secret_access_key = ""
-
-# API key to use
-api_key = "your-api-key"
-
-# API base URL
-#base_url = ""
-
-# API version
-#api_version = ""
-
-# Cost per input token
-#input_cost_per_token = 0.0
-
-# Cost per output token
-#output_cost_per_token = 0.0
-
-# Custom LLM provider
-#custom_llm_provider = ""
-
-# Embedding API base URL
-#embedding_base_url = ""
-
-# Embedding deployment name
-#embedding_deployment_name = ""
-
-# Embedding model to use
-embedding_model = ""
-
-# Maximum number of characters in an observation's content
-#max_message_chars = 10000
-
-# Maximum number of input tokens
-#max_input_tokens = 0
-
-# Maximum number of output tokens
-#max_output_tokens = 0
-
-# Model to use
-model = "gpt-4o"
-
-# Number of retries to attempt
-#num_retries = 5
-
-# Retry maximum wait time
-#retry_max_wait = 60
-
-# Retry minimum wait time
-#retry_min_wait = 3
-
-# Temperature for the API
-#temperature = 0.0
-
-# Timeout for the API
-#timeout = 0
-
-# Top p for the API
-#top_p = 0.5
-
-[llm.gpt3]
-# API key to use
-api_key = "your-api-key"
-
-# Model to use
-model = "gpt-3.5"
-
-#################################### Agent ###################################
-# Configuration for agents (group name starts with 'agent')
-# Use 'agent' for the default agent config
-# otherwise, group name must be `agent.<agent_name>` (case-sensitive), e.g.
-# agent.CodeActAgent
-##############################################################################
-[agent]
-# Memory enabled
-#memory_enabled = false
-
-# Memory maximum threads
-#memory_max_threads = 2
-
-# LLM config group to use
-#llm_config = 'llm'
-
-[agent.RepoExplorerAgent]
-# Example: use a cheaper model for RepoExplorerAgent to reduce cost, especially
-# useful when an agent doesn't demand high quality but uses a lot of tokens
-llm_config = 'gpt3'
-
-#################################### Sandbox ###################################
-# Configuration for the sandbox
-##############################################################################
-[sandbox]
-# Sandbox timeout in seconds
-#timeout = 120
-
-# Sandbox type (ssh, e2b, local)
-#box_type = "ssh"
-
-# Sandbox user ID
-#user_id = 1000
-
-# Container image to use for the sandbox
-#container_image = "ghcr.io/opendevin/sandbox:main"
-
-# Use host network
-#use_host_network = false
-
-# Enable auto linting after editing
-#enable_auto_lint = false
-
-#################################### Eval ####################################
-# Configuration for the evaluation, please refer to the specific evaluation
-# plugin for the available options
-##############################################################################

containers/README.md

@@ -1,12 +0,0 @@
-# Docker Containers
-
-Each folder here contains a Dockerfile, and a config.sh describing how to build
-the images and where to push them. These images are built and pushed in GitHub Actions
-by the `ghcr.yml` workflow.
-
-## Building Manually
-
-```bash
-docker build -f containers/app/Dockerfile -t opendevin .
-docker build -f containers/sandbox/Dockerfile -t sandbox .
-```

containers/app/Dockerfile

@@ -1,82 +0,0 @@
-ARG OPEN_DEVIN_BUILD_VERSION=dev
-FROM node:21.7.2-bookworm-slim AS frontend-builder
-
-WORKDIR /app
-
-COPY ./frontend/package.json frontend/package-lock.json ./
-RUN npm install -g npm@10.5.1
-RUN npm ci
-
-COPY ./frontend ./
-RUN npm run make-i18n && npm run build
-
-FROM python:3.12.3-slim AS backend-builder
-
-WORKDIR /app
-ENV PYTHONPATH='/app'
-
-ENV POETRY_NO_INTERACTION=1 \
-    POETRY_VIRTUALENVS_IN_PROJECT=1 \
-    POETRY_VIRTUALENVS_CREATE=1 \
-    POETRY_CACHE_DIR=/tmp/poetry_cache
-
-RUN apt-get update -y \
-    && apt-get install -y curl make git build-essential \
-    && python3 -m pip install poetry==1.8.2  --break-system-packages
-
-COPY ./pyproject.toml ./poetry.lock ./
-RUN touch README.md
-RUN export POETRY_CACHE_DIR && poetry install --without evaluation,llama-index --no-root && rm -rf $POETRY_CACHE_DIR
-
-FROM python:3.12.3-slim AS runtime
-
-WORKDIR /app
-
-ENV RUN_AS_DEVIN=true
-# A random number--we need this to be different from the user's UID on the host machine
-ENV OPENDEVIN_USER_ID=42420
-ENV USE_HOST_NETWORK=false
-ENV SSH_HOSTNAME=host.docker.internal
-ENV WORKSPACE_BASE=/opt/workspace_base
-ENV OPEN_DEVIN_BUILD_VERSION=$OPEN_DEVIN_BUILD_VERSION
-RUN mkdir -p $WORKSPACE_BASE
-
-RUN apt-get update -y \
-    && apt-get install -y curl ssh sudo
-
-RUN sed -i 's/^UID_MIN.*/UID_MIN 499/' /etc/login.defs # Default is 1000, but OSX is often 501
-RUN sed -i 's/^UID_MAX.*/UID_MAX 1000000/' /etc/login.defs # Default is 60000, but we've seen up to 200000
-
-RUN groupadd app
-RUN useradd -l -m -u $OPENDEVIN_USER_ID -s /bin/bash opendevin && \
-    usermod -aG app opendevin && \
-    usermod -aG sudo opendevin && \
-    echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
-RUN chown -R opendevin:app /app && chmod -R 770 /app
-RUN sudo chown -R opendevin:app $WORKSPACE_BASE && sudo chmod -R 770 $WORKSPACE_BASE
-USER opendevin
-
-ENV VIRTUAL_ENV=/app/.venv \
-    PATH="/app/.venv/bin:$PATH" \
-    PYTHONPATH='/app'
-
-COPY --chown=opendevin:app --chmod=770 --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
-RUN playwright install --with-deps chromium
-
-COPY --chown=opendevin:app --chmod=770 ./opendevin ./opendevin
-COPY --chown=opendevin:app --chmod=777 ./opendevin/runtime/plugins ./opendevin/runtime/plugins
-COPY --chown=opendevin:app --chmod=770 ./agenthub ./agenthub
-
-RUN python opendevin/core/download.py # No-op to download assets
-RUN chown -R opendevin:app /app/logs && chmod -R 770 /app/logs # This gets created by the download.py script
-
-
-COPY --chown=opendevin:app --chmod=770 --from=frontend-builder /app/dist ./frontend/dist
-COPY --chown=opendevin:app --chmod=770 ./containers/app/entrypoint.sh /app/entrypoint.sh
-
-USER root
-
-WORKDIR /app
-
-ENTRYPOINT ["/app/entrypoint.sh"]
-CMD ["uvicorn", "opendevin.server.listen:app", "--host", "0.0.0.0", "--port", "3000"]

containers/app/config.sh

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

containers/app/entrypoint.sh

@@ -1,64 +0,0 @@
-#!/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 [[ "$SANDBOX_USER_ID" -eq 0 ]]; then
-  echo "Running OpenDevin as root"
-  export RUN_AS_DEVIN=false
-  mkdir -p /root/.cache/ms-playwright/
-  if [ -d "/home/opendevin/.cache/ms-playwright/" ]; then
-    mv /home/opendevin/.cache/ms-playwright/ /root/.cache/
-  fi
-  "$@"
-else
-  echo "Setting up enduser with id $SANDBOX_USER_ID"
-  if id "enduser" &>/dev/null; then
-    echo "User enduser already exists. Skipping creation."
-  else
-    if ! useradd -l -m -u $SANDBOX_USER_ID -s /bin/bash enduser; then
-      echo "Failed to create user enduser with id $SANDBOX_USER_ID. Moving opendevin user."
-      incremented_id=$(($SANDBOX_USER_ID + 1))
-      usermod -u $incremented_id opendevin
-      if ! useradd -l -m -u $SANDBOX_USER_ID -s /bin/bash enduser; then
-        echo "Failed to create user enduser with id $SANDBOX_USER_ID for a second time. Exiting."
-        exit 1
-      fi
-    fi
-  fi
-  usermod -aG app enduser
-  # get the user group of /var/run/docker.sock and set opendevin to that group
-  DOCKER_SOCKET_GID=$(stat -c '%g' /var/run/docker.sock)
-  echo "Docker socket group id: $DOCKER_SOCKET_GID"
-  if getent group $DOCKER_SOCKET_GID; then
-    echo "Group with id $DOCKER_SOCKET_GID already exists"
-  else
-    echo "Creating group with id $DOCKER_SOCKET_GID"
-    groupadd -g $DOCKER_SOCKET_GID docker
-  fi
-
-  mkdir -p /home/enduser/.cache/huggingface/hub/
-  mkdir -p /home/enduser/.cache/ms-playwright/
-  if [ -d "/home/opendevin/.cache/ms-playwright/" ]; then
-    mv /home/opendevin/.cache/ms-playwright/ /home/enduser/.cache/
-  fi
-
-  usermod -aG $DOCKER_SOCKET_GID enduser
-  echo "Running as enduser"
-  su enduser /bin/bash -c "$*"
-fi

containers/build.sh

@@ -1,78 +0,0 @@
-#!/bin/bash
-set -eo pipefail
-
-image_name=$1
-org_name=$2
-platform=$3
-
-echo "Building: $image_name for platform: $platform"
-tags=()
-
-OPEN_DEVIN_BUILD_VERSION="dev"
-
-if [[ -n $GITHUB_REF_NAME ]]; then
-  # check if ref name is a version number
-  if [[ $GITHUB_REF_NAME =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
-    major_version=$(echo "$GITHUB_REF_NAME" | cut -d. -f1)
-    minor_version=$(echo "$GITHUB_REF_NAME" | cut -d. -f1,2)
-    tags+=("$major_version" "$minor_version")
-    tags+=("latest")
-  fi
-  sanitized=$(echo "$GITHUB_REF_NAME" | sed 's/[^a-zA-Z0-9.-]\+/-/g')
-  OPEN_DEVIN_BUILD_VERSION=$sanitized
-  tag=$(echo "$sanitized" | tr '[:upper:]' '[:lower:]') # lower case is required in tagging
-  tags+=("$tag")
-fi
-echo "Tags: ${tags[@]}"
-
-if [[ "$image_name" == "opendevin" ]]; then
-  dir="./containers/app"
-elif [[ "$image_name" == "od_runtime" ]]; then
-  dir="./containers/runtime"
-else
-  dir="./containers/$image_name"
-fi
-
-if [[ (! -f "$dir/Dockerfile") && "$image_name" != "od_runtime" ]]; then
-  # Allow runtime to be built without a Dockerfile
-  echo "No Dockerfile found"
-  exit 1
-fi
-if [[ ! -f "$dir/config.sh" ]]; then
-  echo "No config.sh found for Dockerfile"
-  exit 1
-fi
-
-source "$dir/config.sh"
-
-if [[ -n "$org_name" ]]; then
-  DOCKER_ORG="$org_name"
-fi
-
-# If $DOCKER_IMAGE_TAG is set, add it to the tags
-if [[ -n "$DOCKER_IMAGE_TAG" ]]; then
-  tags+=("$DOCKER_IMAGE_TAG")
-fi
-
-DOCKER_REPOSITORY="$DOCKER_REGISTRY/$DOCKER_ORG/$DOCKER_IMAGE"
-DOCKER_REPOSITORY=${DOCKER_REPOSITORY,,} # lowercase
-echo "Repo: $DOCKER_REPOSITORY"
-echo "Base dir: $DOCKER_BASE_DIR"
-
-args=""
-for tag in "${tags[@]}"; do
-  args+=" -t $DOCKER_REPOSITORY:$tag"
-done
-
-output_image="/tmp/${image_name}_image_${platform}.tar"
-
-docker buildx build \
-  $args \
-  --build-arg OPEN_DEVIN_BUILD_VERSION="$OPEN_DEVIN_BUILD_VERSION" \
-  --platform linux/$platform \
-  --provenance=false \
-  -f "$dir/Dockerfile" \
-  --output type=docker,dest="$output_image" \
-  "$DOCKER_BASE_DIR"
-
-echo "${tags[*]}" > tags.txt

containers/e2b-sandbox/Dockerfile

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

containers/e2b-sandbox/README.md

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

containers/e2b-sandbox/e2b.toml

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

containers/runtime/README.md

@@ -1,11 +0,0 @@
-# Dynamic constructed Dockerfile
-
-This folder builds runtime image (sandbox), which will use a `Dockerfile` that is dynamically generated depends on the `base_image` AND a [Python source distribution](https://docs.python.org/3.10/distutils/sourcedist.html) that's based on the current commit of `opendevin`.
-
-The following command will generate Dockerfile for `ubuntu:22.04` and the source distribution `.tar` into `containers/runtime`.
-
-```bash
-poetry run python3 opendevin/runtime/utils/runtime_build.py \
-    --base_image ubuntu:22.04 \
-    --build_folder containers/runtime
-```

containers/runtime/config.sh

@@ -1,8 +0,0 @@
-DOCKER_REGISTRY=ghcr.io
-DOCKER_ORG=opendevin
-DOCKER_BASE_DIR="./containers/runtime"
-# These two variables will be appended by the runtime_build.py script
-# DOCKER_IMAGE=
-# DOCKER_IMAGE_TAG=
-DOCKER_IMAGE=od_runtime
-DOCKER_IMAGE_TAG=od_v0.8.1_image_ubuntu_tag_22.04

containers/sandbox/Dockerfile

@@ -1,44 +0,0 @@
-FROM ubuntu:22.04
-
-# install basic packages
-RUN apt-get update && apt-get install -y \
-    curl \
-    wget \
-    git \
-    vim \
-    nano \
-    unzip \
-    zip \
-    python3 \
-    python3-pip \
-    python3-venv \
-    python3-dev \
-    build-essential \
-    openssh-server \
-    sudo \
-    gcc \
-    jq \
-    g++ \
-    make \
-    iproute2 \
-    && 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
-
-# ==== OpenDevin Runtime Client ====
-RUN mkdir -p /opendevin && mkdir -p /opendevin/logs && chmod 777 /opendevin/logs
-RUN wget --progress=bar:force -O Miniforge3.sh "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"
-RUN bash Miniforge3.sh -b -p /opendevin/miniforge3
-RUN chmod -R g+w /opendevin/miniforge3
-RUN bash -c ". /opendevin/miniforge3/etc/profile.d/conda.sh && conda config --set changeps1 False && conda config --append channels conda-forge"
-RUN echo "" > /opendevin/bash.bashrc
-RUN rm -f Miniforge3.sh
-
-# - agentskills dependencies
-RUN /opendevin/miniforge3/bin/pip install --upgrade pip
-RUN /opendevin/miniforge3/bin/pip install jupyterlab notebook jupyter_kernel_gateway flake8
-RUN /opendevin/miniforge3/bin/pip install python-docx PyPDF2 python-pptx pylatexenc openai
-RUN /opendevin/miniforge3/bin/pip install python-dotenv toml termcolor pydantic python-docx pyyaml docker pexpect tenacity e2b browsergym minio

containers/sandbox/config.sh

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

controller/__init__.py

@@ -0,0 +1,5 @@
+from openhands.controller.agent_controller import AgentController
+
+__all__ = [
+    'AgentController',
+]

controller/action_parser.py

@@ -1,6 +1,16 @@
 from abc import ABC, abstractmethod
 
-from opendevin.events.action import Action
+from openhands.events.action import Action
+
+
+class ActionParseError(Exception):
+    """Exception raised when the response from the LLM cannot be parsed into an action."""
+
+    def __init__(self, error: str):
+        self.error = error
+
+    def __str__(self):
+        return self.error
 
 
 class ResponseParser(ABC):

controller/agent.py

@@ -2,15 +2,16 @@ from abc import ABC, abstractmethod
 from typing import TYPE_CHECKING, Type
 
 if TYPE_CHECKING:
-    from opendevin.controller.state.state import State
-    from opendevin.events.action import Action
-from opendevin.core.exceptions import (
+    from openhands.controller.state.state import State
+    from openhands.core.config import AgentConfig
+    from openhands.events.action import Action
+from openhands.core.exceptions import (
     AgentAlreadyRegisteredError,
     AgentNotRegisteredError,
 )
-from opendevin.llm.llm import LLM
-from opendevin.runtime.plugins import PluginRequirement
-from opendevin.runtime.tools import RuntimeTool
+from openhands.llm.llm import LLM
+from openhands.runtime.plugins import PluginRequirement
+from openhands.utils.prompt import PromptManager
 
 
 class Agent(ABC):
@@ -24,14 +25,16 @@ class Agent(ABC):
 
     _registry: dict[str, Type['Agent']] = {}
     sandbox_plugins: list[PluginRequirement] = []
-    runtime_tools: list[RuntimeTool] = []
 
     def __init__(
         self,
         llm: LLM,
+        config: 'AgentConfig',
     ):
         self.llm = llm
+        self.config = config
         self._complete = False
+        self.prompt_manager: PromptManager | None = None
 
     @property
     def complete(self) -> bool:

controller/agent_controller.py

@@ -0,0 +1,955 @@
+import asyncio
+import copy
+import os
+import traceback
+from typing import Callable, ClassVar, Type
+
+import litellm
+from litellm.exceptions import BadRequestError, ContextWindowExceededError
+
+from openhands.controller.agent import Agent
+from openhands.controller.state.state import State, TrafficControlState
+from openhands.controller.stuck import StuckDetector
+from openhands.core.config import AgentConfig, LLMConfig
+from openhands.core.exceptions import (
+    FunctionCallNotExistsError,
+    FunctionCallValidationError,
+    LLMMalformedActionError,
+    LLMNoActionError,
+    LLMResponseError,
+)
+from openhands.core.logger import LOG_ALL_EVENTS
+from openhands.core.logger import openhands_logger as logger
+from openhands.core.schema import AgentState
+from openhands.events import EventSource, EventStream, EventStreamSubscriber
+from openhands.events.action import (
+    Action,
+    ActionConfirmationStatus,
+    AddTaskAction,
+    AgentDelegateAction,
+    AgentFinishAction,
+    AgentRejectAction,
+    ChangeAgentStateAction,
+    CmdRunAction,
+    IPythonRunCellAction,
+    MessageAction,
+    ModifyTaskAction,
+    NullAction,
+)
+from openhands.events.event import Event
+from openhands.events.observation import (
+    AgentDelegateObservation,
+    AgentStateChangedObservation,
+    ErrorObservation,
+    NullObservation,
+    Observation,
+)
+from openhands.events.serialization.event import truncate_content
+from openhands.llm.llm import LLM
+from openhands.utils.shutdown_listener import should_continue
+
+# note: RESUME is only available on web GUI
+TRAFFIC_CONTROL_REMINDER = (
+    "Please click on resume button if you'd like to continue, or start a new task."
+)
+
+
+class AgentController:
+    id: str
+    agent: Agent
+    max_iterations: int
+    event_stream: EventStream
+    state: State
+    confirmation_mode: bool
+    agent_to_llm_config: dict[str, LLMConfig]
+    agent_configs: dict[str, AgentConfig]
+    agent_task: asyncio.Future | None = None
+    parent: 'AgentController | None' = None
+    delegate: 'AgentController | None' = None
+    _pending_action: Action | None = None
+    _closed: bool = False
+    filter_out: ClassVar[tuple[type[Event], ...]] = (
+        NullAction,
+        NullObservation,
+        ChangeAgentStateAction,
+        AgentStateChangedObservation,
+    )
+
+    def __init__(
+        self,
+        agent: Agent,
+        event_stream: EventStream,
+        max_iterations: int,
+        max_budget_per_task: float | None = None,
+        agent_to_llm_config: dict[str, LLMConfig] | None = None,
+        agent_configs: dict[str, AgentConfig] | None = None,
+        sid: str = 'default',
+        confirmation_mode: bool = False,
+        initial_state: State | None = None,
+        is_delegate: bool = False,
+        headless_mode: bool = True,
+        status_callback: Callable | None = None,
+    ):
+        """Initializes a new instance of the AgentController class.
+
+        Args:
+            agent: The agent instance to control.
+            event_stream: The event stream to publish events to.
+            max_iterations: The maximum number of iterations the agent can run.
+            max_budget_per_task: The maximum budget (in USD) allowed per task, beyond which the agent will stop.
+            agent_to_llm_config: A dictionary mapping agent names to LLM configurations in the case that
+                we delegate to a different agent.
+            agent_configs: A dictionary mapping agent names to agent configurations in the case that
+                we delegate to a different agent.
+            sid: The session ID of the agent.
+            confirmation_mode: Whether to enable confirmation mode for agent actions.
+            initial_state: The initial state of the controller.
+            is_delegate: Whether this controller is a delegate.
+            headless_mode: Whether the agent is run in headless mode.
+            status_callback: Optional callback function to handle status updates.
+        """
+        self._step_lock = asyncio.Lock()
+        self.id = sid
+        self.agent = agent
+        self.headless_mode = headless_mode
+
+        # subscribe to the event stream
+        self.event_stream = event_stream
+        self.event_stream.subscribe(
+            EventStreamSubscriber.AGENT_CONTROLLER, self.on_event, self.id
+        )
+
+        # state from the previous session, state from a parent agent, or a fresh state
+        self.set_initial_state(
+            state=initial_state,
+            max_iterations=max_iterations,
+            confirmation_mode=confirmation_mode,
+        )
+        self.max_budget_per_task = max_budget_per_task
+        self.agent_to_llm_config = agent_to_llm_config if agent_to_llm_config else {}
+        self.agent_configs = agent_configs if agent_configs else {}
+        self._initial_max_iterations = max_iterations
+        self._initial_max_budget_per_task = max_budget_per_task
+
+        # stuck helper
+        self._stuck_detector = StuckDetector(self.state)
+        self.status_callback = status_callback
+
+    async def close(self) -> None:
+        """Closes the agent controller, canceling any ongoing tasks and unsubscribing from the event stream.
+
+        Note that it's fairly important that this closes properly, otherwise the state is incomplete.
+        """
+        await self.set_agent_state_to(AgentState.STOPPED)
+
+        # we made history, now is the time to rewrite it!
+        # the final state.history will be used by external scripts like evals, tests, etc.
+        # history will need to be complete WITH delegates events
+        # like the regular agent history, it does not include:
+        # - 'hidden' events, events with hidden=True
+        # - backend events (the default 'filtered out' types, types in self.filter_out)
+        start_id = self.state.start_id if self.state.start_id >= 0 else 0
+        end_id = (
+            self.state.end_id
+            if self.state.end_id >= 0
+            else self.event_stream.get_latest_event_id()
+        )
+        self.state.history = list(
+            self.event_stream.get_events(
+                start_id=start_id,
+                end_id=end_id,
+                reverse=False,
+                filter_out_type=self.filter_out,
+                filter_hidden=True,
+            )
+        )
+
+        # unsubscribe from the event stream
+        self.event_stream.unsubscribe(EventStreamSubscriber.AGENT_CONTROLLER, self.id)
+        self._closed = True
+
+    def log(self, level: str, message: str, extra: dict | None = None) -> None:
+        """Logs a message to the agent controller's logger.
+
+        Args:
+            level (str): The logging level to use (e.g., 'info', 'debug', 'error').
+            message (str): The message to log.
+            extra (dict | None, optional): Additional fields to include in the log. Defaults to None.
+        """
+        message = f'[Agent Controller {self.id}] {message}'
+        getattr(logger, level)(message, extra=extra, stacklevel=2)
+
+    def update_state_before_step(self):
+        self.state.iteration += 1
+        self.state.local_iteration += 1
+
+    async def update_state_after_step(self):
+        # update metrics especially for cost. Use deepcopy to avoid it being modified by agent._reset()
+        self.state.local_metrics = copy.deepcopy(self.agent.llm.metrics)
+
+    async def _react_to_exception(
+        self,
+        e: Exception,
+    ):
+        await self.set_agent_state_to(AgentState.ERROR)
+        if self.status_callback is not None:
+            err_id = ''
+            if isinstance(e, litellm.AuthenticationError):
+                err_id = 'STATUS$ERROR_LLM_AUTHENTICATION'
+            self.status_callback('error', err_id, str(e))
+
+    async def start_step_loop(self):
+        """The main loop for the agent's step-by-step execution."""
+        self.log('info', 'Starting step loop...')
+        while True:
+            if not self._is_awaiting_observation() and not should_continue():
+                break
+            if self._closed:
+                break
+            try:
+                await self._step()
+            except asyncio.CancelledError:
+                self.log('debug', 'AgentController task was cancelled')
+                break
+            except Exception as e:
+                traceback.print_exc()
+                self.log('error', f'Error while running the agent: {e}')
+                await self._react_to_exception(e)
+
+            await asyncio.sleep(0.1)
+
+    async def on_event(self, event: Event) -> None:
+        """Callback from the event stream. Notifies the controller of incoming events.
+
+        Args:
+            event (Event): The incoming event to process.
+        """
+        if hasattr(event, 'hidden') and event.hidden:
+            return
+
+        # if the event is not filtered out, add it to the history
+        if not any(isinstance(event, filter_type) for filter_type in self.filter_out):
+            self.state.history.append(event)
+
+        if isinstance(event, Action):
+            await self._handle_action(event)
+        elif isinstance(event, Observation):
+            await self._handle_observation(event)
+
+    async def _handle_action(self, action: Action) -> None:
+        """Handles actions from the event stream.
+
+        Args:
+            action (Action): The action to handle.
+        """
+        if isinstance(action, ChangeAgentStateAction):
+            await self.set_agent_state_to(action.agent_state)  # type: ignore
+        elif isinstance(action, MessageAction):
+            await self._handle_message_action(action)
+        elif isinstance(action, AgentDelegateAction):
+            await self.start_delegate(action)
+        elif isinstance(action, AddTaskAction):
+            self.state.root_task.add_subtask(
+                action.parent, action.goal, action.subtasks
+            )
+        elif isinstance(action, ModifyTaskAction):
+            self.state.root_task.set_subtask_state(action.task_id, action.state)
+        elif isinstance(action, AgentFinishAction):
+            self.state.outputs = action.outputs
+            self.state.metrics.merge(self.state.local_metrics)
+            await self.set_agent_state_to(AgentState.FINISHED)
+        elif isinstance(action, AgentRejectAction):
+            self.state.outputs = action.outputs
+            self.state.metrics.merge(self.state.local_metrics)
+            await self.set_agent_state_to(AgentState.REJECTED)
+
+    async def _handle_observation(self, observation: Observation) -> None:
+        """Handles observation from the event stream.
+
+        Args:
+            observation (observation): The observation to handle.
+        """
+        observation_to_print = copy.deepcopy(observation)
+        if len(observation_to_print.content) > self.agent.llm.config.max_message_chars:
+            observation_to_print.content = truncate_content(
+                observation_to_print.content, self.agent.llm.config.max_message_chars
+            )
+        # Use info level if LOG_ALL_EVENTS is set
+        log_level = 'info' if os.getenv('LOG_ALL_EVENTS') in ('true', '1') else 'debug'
+        self.log(
+            log_level, str(observation_to_print), extra={'msg_type': 'OBSERVATION'}
+        )
+
+        if observation.llm_metrics is not None:
+            self.agent.llm.metrics.merge(observation.llm_metrics)
+
+        if self._pending_action and self._pending_action.id == observation.cause:
+            if self.state.agent_state == AgentState.AWAITING_USER_CONFIRMATION:
+                return
+            self._pending_action = None
+            if self.state.agent_state == AgentState.USER_CONFIRMED:
+                await self.set_agent_state_to(AgentState.RUNNING)
+            if self.state.agent_state == AgentState.USER_REJECTED:
+                await self.set_agent_state_to(AgentState.AWAITING_USER_INPUT)
+            return
+        elif isinstance(observation, ErrorObservation):
+            if self.state.agent_state == AgentState.ERROR:
+                self.state.metrics.merge(self.state.local_metrics)
+
+    async def _handle_message_action(self, action: MessageAction) -> None:
+        """Handles message actions from the event stream.
+
+        Args:
+            action (MessageAction): The message action to handle.
+        """
+        if action.source == EventSource.USER:
+            # Use info level if LOG_ALL_EVENTS is set
+            log_level = (
+                'info' if os.getenv('LOG_ALL_EVENTS') in ('true', '1') else 'debug'
+            )
+            self.log(
+                log_level,
+                str(action),
+                extra={'msg_type': 'ACTION', 'event_source': EventSource.USER},
+            )
+            # Extend max iterations when the user sends a message (only in non-headless mode)
+            if self._initial_max_iterations is not None and not self.headless_mode:
+                self.state.max_iterations = (
+                    self.state.iteration + self._initial_max_iterations
+                )
+                if (
+                    self.state.traffic_control_state == TrafficControlState.THROTTLING
+                    or self.state.traffic_control_state == TrafficControlState.PAUSED
+                ):
+                    self.state.traffic_control_state = TrafficControlState.NORMAL
+                self.log(
+                    'debug',
+                    f'Extended max iterations to {self.state.max_iterations} after user message',
+                )
+            if self.get_agent_state() != AgentState.RUNNING:
+                await self.set_agent_state_to(AgentState.RUNNING)
+        elif action.source == EventSource.AGENT and action.wait_for_response:
+            await self.set_agent_state_to(AgentState.AWAITING_USER_INPUT)
+
+    def _reset(self) -> None:
+        """Resets the agent controller"""
+
+        self._pending_action = None
+        self.agent.reset()
+
+    async def set_agent_state_to(self, new_state: AgentState) -> None:
+        """Updates the agent's state and handles side effects. Can emit events to the event stream.
+
+        Args:
+            new_state (AgentState): The new state to set for the agent.
+        """
+        self.log(
+            'info',
+            f'Setting agent({self.agent.name}) state from {self.state.agent_state} to {new_state}',
+        )
+
+        if new_state == self.state.agent_state:
+            return
+
+        if new_state in (AgentState.STOPPED, AgentState.ERROR):
+            self._reset()
+        elif (
+            new_state == AgentState.RUNNING
+            and self.state.agent_state == AgentState.PAUSED
+            # TODO: do we really need both THROTTLING and PAUSED states, or can we clean up one of them completely?
+            and self.state.traffic_control_state == TrafficControlState.THROTTLING
+        ):
+            # user intends to interrupt traffic control and let the task resume temporarily
+            self.state.traffic_control_state = TrafficControlState.PAUSED
+            # User has chosen to deliberately continue - lets double the max iterations
+            if (
+                self.state.iteration is not None
+                and self.state.max_iterations is not None
+                and self._initial_max_iterations is not None
+                and not self.headless_mode
+            ):
+                if self.state.iteration >= self.state.max_iterations:
+                    self.state.max_iterations += self._initial_max_iterations
+
+            if (
+                self.state.metrics.accumulated_cost is not None
+                and self.max_budget_per_task is not None
+                and self._initial_max_budget_per_task is not None
+            ):
+                if self.state.metrics.accumulated_cost >= self.max_budget_per_task:
+                    self.max_budget_per_task += self._initial_max_budget_per_task
+        elif self._pending_action is not None and (
+            new_state in (AgentState.USER_CONFIRMED, AgentState.USER_REJECTED)
+        ):
+            if hasattr(self._pending_action, 'thought'):
+                self._pending_action.thought = ''  # type: ignore[union-attr]
+            if new_state == AgentState.USER_CONFIRMED:
+                confirmation_state = ActionConfirmationStatus.CONFIRMED
+            else:
+                confirmation_state = ActionConfirmationStatus.REJECTED
+            self._pending_action.confirmation_state = confirmation_state  # type: ignore[attr-defined]
+            self._pending_action._id = None  # type: ignore[attr-defined]
+            self.event_stream.add_event(self._pending_action, EventSource.AGENT)
+
+        self.state.agent_state = new_state
+        self.event_stream.add_event(
+            AgentStateChangedObservation('', self.state.agent_state),
+            EventSource.ENVIRONMENT,
+        )
+
+        if new_state == AgentState.INIT and self.state.resume_state:
+            await self.set_agent_state_to(self.state.resume_state)
+            self.state.resume_state = None
+
+    def get_agent_state(self) -> AgentState:
+        """Returns the current state of the agent.
+
+        Returns:
+            AgentState: The current state of the agent.
+        """
+        return self.state.agent_state
+
+    async def start_delegate(self, action: AgentDelegateAction) -> None:
+        """Start a delegate agent to handle a subtask.
+
+        OpenHands is a multi-agentic system. A `task` is a conversation between
+        OpenHands (the whole system) and the user, which might involve one or more inputs
+        from the user. It starts with an initial input (typically a task statement) from
+        the user, and ends with either an `AgentFinishAction` initiated by the agent, a
+        stop initiated by the user, or an error.
+
+        A `subtask` is a conversation between an agent and the user, or another agent. If a `task`
+        is conducted by a single agent, then it's also a `subtask`. Otherwise, a `task` consists of
+        multiple `subtasks`, each executed by one agent.
+
+        Args:
+            action (AgentDelegateAction): The action containing information about the delegate agent to start.
+        """
+        agent_cls: Type[Agent] = Agent.get_cls(action.agent)
+        agent_config = self.agent_configs.get(action.agent, self.agent.config)
+        llm_config = self.agent_to_llm_config.get(action.agent, self.agent.llm.config)
+        llm = LLM(config=llm_config)
+        delegate_agent = agent_cls(llm=llm, config=agent_config)
+        state = State(
+            inputs=action.inputs or {},
+            local_iteration=0,
+            iteration=self.state.iteration,
+            max_iterations=self.state.max_iterations,
+            delegate_level=self.state.delegate_level + 1,
+            # global metrics should be shared between parent and child
+            metrics=self.state.metrics,
+            # start on top of the stream
+            start_id=self.event_stream.get_latest_event_id() + 1,
+        )
+        self.log(
+            'debug',
+            f'start delegate, creating agent {delegate_agent.name} using LLM {llm}',
+        )
+
+        self.event_stream.unsubscribe(EventStreamSubscriber.AGENT_CONTROLLER, self.id)
+        self.delegate = AgentController(
+            sid=self.id + '-delegate',
+            agent=delegate_agent,
+            event_stream=self.event_stream,
+            max_iterations=self.state.max_iterations,
+            max_budget_per_task=self.max_budget_per_task,
+            agent_to_llm_config=self.agent_to_llm_config,
+            agent_configs=self.agent_configs,
+            initial_state=state,
+            is_delegate=True,
+            headless_mode=self.headless_mode,
+        )
+        await self.delegate.set_agent_state_to(AgentState.RUNNING)
+
+    async def _step(self) -> None:
+        """Executes a single step of the parent or delegate agent. Detects stuck agents and limits on the number of iterations and the task budget."""
+        if self.get_agent_state() != AgentState.RUNNING:
+            await asyncio.sleep(1)
+            return
+
+        if self._pending_action:
+            await asyncio.sleep(1)
+            return
+
+        if self.delegate is not None:
+            assert self.delegate != self
+            if self.delegate.get_agent_state() == AgentState.PAUSED:
+                # no need to check too often
+                await asyncio.sleep(1)
+            else:
+                await self._delegate_step()
+            return
+
+        self.log(
+            'info',
+            f'LEVEL {self.state.delegate_level} LOCAL STEP {self.state.local_iteration} GLOBAL STEP {self.state.iteration}',
+            extra={'msg_type': 'STEP'},
+        )
+
+        # check if agent hit the resources limit
+        stop_step = False
+        if self.state.iteration >= self.state.max_iterations:
+            stop_step = await self._handle_traffic_control(
+                'iteration', self.state.iteration, self.state.max_iterations
+            )
+        if self.max_budget_per_task is not None:
+            current_cost = self.state.metrics.accumulated_cost
+            if current_cost > self.max_budget_per_task:
+                stop_step = await self._handle_traffic_control(
+                    'budget', current_cost, self.max_budget_per_task
+                )
+        if stop_step:
+            return
+
+        if self._is_stuck():
+            await self._react_to_exception(RuntimeError('Agent got stuck in a loop'))
+            return
+
+        self.update_state_before_step()
+        action: Action = NullAction()
+        try:
+            action = self.agent.step(self.state)
+            if action is None:
+                raise LLMNoActionError('No action was returned')
+        except (
+            LLMMalformedActionError,
+            LLMNoActionError,
+            LLMResponseError,
+            FunctionCallValidationError,
+            FunctionCallNotExistsError,
+        ) as e:
+            self.event_stream.add_event(
+                ErrorObservation(
+                    content=str(e),
+                ),
+                EventSource.AGENT,
+            )
+            return
+        except (ContextWindowExceededError, BadRequestError) as e:
+            # FIXME: this is a hack until a litellm fix is confirmed
+            # Check if this is a nested context window error
+            error_str = str(e).lower()
+            if (
+                'contextwindowexceedederror' in error_str
+                or 'prompt is too long' in error_str
+                or isinstance(e, ContextWindowExceededError)
+            ):
+                # When context window is exceeded, keep roughly half of agent interactions
+                self.state.history = self._apply_conversation_window(self.state.history)
+
+                # Save the ID of the first event in our truncated history for future reloading
+                if self.state.history:
+                    self.state.start_id = self.state.history[0].id
+                # Don't add error event - let the agent retry with reduced context
+                return
+            raise
+
+        if action.runnable:
+            if self.state.confirmation_mode and (
+                type(action) is CmdRunAction or type(action) is IPythonRunCellAction
+            ):
+                action.confirmation_state = (
+                    ActionConfirmationStatus.AWAITING_CONFIRMATION
+                )
+            self._pending_action = action
+
+        if not isinstance(action, NullAction):
+            if (
+                hasattr(action, 'confirmation_state')
+                and action.confirmation_state
+                == ActionConfirmationStatus.AWAITING_CONFIRMATION
+            ):
+                await self.set_agent_state_to(AgentState.AWAITING_USER_CONFIRMATION)
+            self.event_stream.add_event(action, EventSource.AGENT)
+
+        await self.update_state_after_step()
+
+        log_level = 'info' if LOG_ALL_EVENTS else 'debug'
+        self.log(log_level, str(action), extra={'msg_type': 'ACTION'})
+
+    async def _delegate_step(self) -> None:
+        """Executes a single step of the delegate agent."""
+        await self.delegate._step()  # type: ignore[union-attr]
+        assert self.delegate is not None
+        delegate_state = self.delegate.get_agent_state()
+        self.log('debug', f'Delegate state: {delegate_state}')
+        if delegate_state == AgentState.ERROR:
+            # update iteration that shall be shared across agents
+            self.state.iteration = self.delegate.state.iteration
+
+            # emit AgentDelegateObservation to mark delegate termination due to error
+            delegate_outputs = (
+                self.delegate.state.outputs if self.delegate.state else {}
+            )
+            content = (
+                f'{self.delegate.agent.name} encountered an error during execution.'
+            )
+            obs = AgentDelegateObservation(outputs=delegate_outputs, content=content)
+            self.event_stream.add_event(obs, EventSource.AGENT)
+
+            # close the delegate upon error
+            await self.delegate.close()
+
+            # resubscribe parent when delegate is finished
+            self.event_stream.subscribe(
+                EventStreamSubscriber.AGENT_CONTROLLER, self.on_event, self.id
+            )
+            self.delegate = None
+            self.delegateAction = None
+
+        elif delegate_state in (AgentState.FINISHED, AgentState.REJECTED):
+            self.log('debug', 'Delegate agent has finished execution')
+            # retrieve delegate result
+            outputs = self.delegate.state.outputs if self.delegate.state else {}
+
+            # update iteration that shall be shared across agents
+            self.state.iteration = self.delegate.state.iteration
+
+            # close delegate controller: we must close the delegate controller before adding new events
+            await self.delegate.close()
+
+            # resubscribe parent when delegate is finished
+            self.event_stream.subscribe(
+                EventStreamSubscriber.AGENT_CONTROLLER, self.on_event, self.id
+            )
+
+            # update delegate result observation
+            # TODO: replace this with AI-generated summary (#2395)
+            formatted_output = ', '.join(
+                f'{key}: {value}' for key, value in outputs.items()
+            )
+            content = (
+                f'{self.delegate.agent.name} finishes task with {formatted_output}'
+            )
+            obs = AgentDelegateObservation(outputs=outputs, content=content)
+
+            # clean up delegate status
+            self.delegate = None
+            self.delegateAction = None
+            self.event_stream.add_event(obs, EventSource.AGENT)
+        return
+
+    async def _handle_traffic_control(
+        self, limit_type: str, current_value: float, max_value: float
+    ) -> bool:
+        """Handles agent state after hitting the traffic control limit.
+
+        Args:
+            limit_type (str): The type of limit that was hit.
+            current_value (float): The current value of the limit.
+            max_value (float): The maximum value of the limit.
+        """
+        stop_step = False
+        if self.state.traffic_control_state == TrafficControlState.PAUSED:
+            self.log(
+                'debug', 'Hitting traffic control, temporarily resume upon user request'
+            )
+            self.state.traffic_control_state = TrafficControlState.NORMAL
+        else:
+            self.state.traffic_control_state = TrafficControlState.THROTTLING
+            # Format values as integers for iterations, keep decimals for budget
+            if limit_type == 'iteration':
+                current_str = str(int(current_value))
+                max_str = str(int(max_value))
+            else:
+                current_str = f'{current_value:.2f}'
+                max_str = f'{max_value:.2f}'
+
+            if self.headless_mode:
+                e = RuntimeError(
+                    f'Agent reached maximum {limit_type} in headless mode. '
+                    f'Current {limit_type}: {current_str}, max {limit_type}: {max_str}'
+                )
+                await self._react_to_exception(e)
+            else:
+                e = RuntimeError(
+                    f'Agent reached maximum {limit_type}. '
+                    f'Current {limit_type}: {current_str}, max {limit_type}: {max_str}. '
+                )
+                # FIXME: this isn't really an exception--we should have a different path
+                await self._react_to_exception(e)
+            stop_step = True
+        return stop_step
+
+    def get_state(self) -> State:
+        """Returns the current running state object.
+
+        Returns:
+            State: The current state object.
+        """
+        return self.state
+
+    def set_initial_state(
+        self,
+        state: State | None,
+        max_iterations: int,
+        confirmation_mode: bool = False,
+    ) -> None:
+        """Sets the initial state for the agent, either from the previous session, or from a parent agent, or by creating a new one.
+
+        Args:
+            state: The state to initialize with, or None to create a new state.
+            max_iterations: The maximum number of iterations allowed for the task.
+            confirmation_mode: Whether to enable confirmation mode.
+        """
+        # state can come from:
+        # - the previous session, in which case it has history
+        # - from a parent agent, in which case it has no history
+        # - None / a new state
+        if state is None:
+            self.state = State(
+                inputs={},
+                max_iterations=max_iterations,
+                confirmation_mode=confirmation_mode,
+            )
+        else:
+            self.state = state
+
+            if self.state.start_id <= -1:
+                self.state.start_id = 0
+
+            self.log(
+                'debug',
+                f'AgentController {self.id} initializing history from event {self.state.start_id}',
+            )
+
+            self._init_history()
+
+    def _init_history(self) -> None:
+        """Initializes the agent's history from the event stream.
+
+        The history is a list of events that:
+        - Excludes events of types listed in self.filter_out
+        - Excludes events with hidden=True attribute
+        - For delegate events (between AgentDelegateAction and AgentDelegateObservation):
+            - Excludes all events between the action and observation
+            - Includes the delegate action and observation themselves
+
+        The history is loaded in two parts if truncation_id is set:
+        1. First user message from start_id onwards
+        2. Rest of history from truncation_id to the end
+
+        Otherwise loads normally from start_id.
+        """
+        # define range of events to fetch
+        # delegates start with a start_id and initially won't find any events
+        # otherwise we're restoring a previous session
+        start_id = self.state.start_id if self.state.start_id >= 0 else 0
+        end_id = (
+            self.state.end_id
+            if self.state.end_id >= 0
+            else self.event_stream.get_latest_event_id()
+        )
+
+        # sanity check
+        if start_id > end_id + 1:
+            self.log(
+                'warning',
+                f'start_id {start_id} is greater than end_id + 1 ({end_id + 1}). History will be empty.',
+            )
+            self.state.history = []
+            return
+
+        events: list[Event] = []
+
+        # If we have a truncation point, get first user message and then rest of history
+        if hasattr(self.state, 'truncation_id') and self.state.truncation_id > 0:
+            # Find first user message from stream
+            first_user_msg = next(
+                (
+                    e
+                    for e in self.event_stream.get_events(
+                        start_id=start_id,
+                        end_id=end_id,
+                        reverse=False,
+                        filter_out_type=self.filter_out,
+                        filter_hidden=True,
+                    )
+                    if isinstance(e, MessageAction) and e.source == EventSource.USER
+                ),
+                None,
+            )
+            if first_user_msg:
+                events.append(first_user_msg)
+
+            # the rest of the events are from the truncation point
+            start_id = self.state.truncation_id
+
+        # Get rest of history
+        events_to_add = list(
+            self.event_stream.get_events(
+                start_id=start_id,
+                end_id=end_id,
+                reverse=False,
+                filter_out_type=self.filter_out,
+                filter_hidden=True,
+            )
+        )
+        events.extend(events_to_add)
+
+        # Find all delegate action/observation pairs
+        delegate_ranges: list[tuple[int, int]] = []
+        delegate_action_ids: list[int] = []  # stack of unmatched delegate action IDs
+
+        for event in events:
+            if isinstance(event, AgentDelegateAction):
+                delegate_action_ids.append(event.id)
+                # Note: we can get agent=event.agent and task=event.inputs.get('task','')
+                # if we need to track these in the future
+
+            elif isinstance(event, AgentDelegateObservation):
+                # Match with most recent unmatched delegate action
+                if not delegate_action_ids:
+                    self.log(
+                        'warning',
+                        f'Found AgentDelegateObservation without matching action at id={event.id}',
+                    )
+                    continue
+
+                action_id = delegate_action_ids.pop()
+                delegate_ranges.append((action_id, event.id))
+
+        # Filter out events between delegate action/observation pairs
+        if delegate_ranges:
+            filtered_events: list[Event] = []
+            current_idx = 0
+
+            for start_id, end_id in sorted(delegate_ranges):
+                # Add events before delegate range
+                filtered_events.extend(
+                    event for event in events[current_idx:] if event.id < start_id
+                )
+
+                # Add delegate action and observation
+                filtered_events.extend(
+                    event for event in events if event.id in (start_id, end_id)
+                )
+
+                # Update index to after delegate range
+                current_idx = next(
+                    (i for i, e in enumerate(events) if e.id > end_id), len(events)
+                )
+
+            # Add any remaining events after last delegate range
+            filtered_events.extend(events[current_idx:])
+
+            self.state.history = filtered_events
+        else:
+            self.state.history = events
+
+        # make sure history is in sync
+        self.state.start_id = start_id
+
+    def _apply_conversation_window(self, events: list[Event]) -> list[Event]:
+        """Cuts history roughly in half when context window is exceeded, preserving action-observation pairs
+        and ensuring the first user message is always included.
+
+        The algorithm:
+        1. Cut history in half
+        2. Check first event in new history:
+           - If Observation: find and include its Action
+           - If MessageAction: ensure its related Action-Observation pair isn't split
+        3. Always include the first user message
+
+        Args:
+            events: List of events to filter
+
+        Returns:
+            Filtered list of events keeping newest half while preserving pairs
+        """
+        if not events:
+            return events
+
+        # Find first user message - we'll need to ensure it's included
+        first_user_msg = next(
+            (
+                e
+                for e in events
+                if isinstance(e, MessageAction) and e.source == EventSource.USER
+            ),
+            None,
+        )
+
+        # cut in half
+        mid_point = max(1, len(events) // 2)
+        kept_events = events[mid_point:]
+
+        # Handle first event in truncated history
+        if kept_events:
+            i = 0
+            while i < len(kept_events):
+                first_event = kept_events[i]
+                if isinstance(first_event, Observation) and first_event.cause:
+                    # Find its action and include it
+                    matching_action = next(
+                        (
+                            e
+                            for e in reversed(events[:mid_point])
+                            if isinstance(e, Action) and e.id == first_event.cause
+                        ),
+                        None,
+                    )
+                    if matching_action:
+                        kept_events = [matching_action] + kept_events
+                    else:
+                        self.log(
+                            'warning',
+                            f'Found Observation without matching Action at id={first_event.id}',
+                        )
+                        # drop this observation
+                        kept_events = kept_events[1:]
+                    break
+
+                elif isinstance(first_event, MessageAction) or (
+                    isinstance(first_event, Action)
+                    and first_event.source == EventSource.USER
+                ):
+                    # if it's a message action or a user action, keep it and continue to find the next event
+                    i += 1
+                    continue
+
+                else:
+                    # if it's an action with source == EventSource.AGENT, we're good
+                    break
+
+        # Save where to continue from in next reload
+        if kept_events:
+            self.state.truncation_id = kept_events[0].id
+
+        # Ensure first user message is included
+        if first_user_msg and first_user_msg not in kept_events:
+            kept_events = [first_user_msg] + kept_events
+
+        # start_id points to first user message
+        if first_user_msg:
+            self.state.start_id = first_user_msg.id
+
+        return kept_events
+
+    def _is_stuck(self) -> bool:
+        """Checks if the agent or its delegate is stuck in a loop.
+
+        Returns:
+            bool: True if the agent is stuck, False otherwise.
+        """
+        # check if delegate stuck
+        if self.delegate and self.delegate._is_stuck():
+            return True
+
+        return self._stuck_detector.is_stuck(self.headless_mode)
+
+    def __repr__(self):
+        return (
+            f'AgentController(id={self.id}, agent={self.agent!r}, '
+            f'event_stream={self.event_stream!r}, '
+            f'state={self.state!r}, agent_task={self.agent_task!r}, '
+            f'delegate={self.delegate!r}, _pending_action={self._pending_action!r})'
+        )
+
+    def _is_awaiting_observation(self):
+        events = self.event_stream.get_events(reverse=True)
+        for event in events:
+            if isinstance(event, AgentStateChangedObservation):
+                result = event.agent_state == AgentState.RUNNING
+                return result
+        return False

controller/state/state.py

@@ -0,0 +1,171 @@
+import base64
+import pickle
+from dataclasses import dataclass, field
+from enum import Enum
+from typing import Any
+
+from openhands.controller.state.task import RootTask
+from openhands.core.logger import openhands_logger as logger
+from openhands.core.schema import AgentState
+from openhands.events.action import (
+    MessageAction,
+)
+from openhands.events.action.agent import AgentFinishAction
+from openhands.events.event import Event, EventSource
+from openhands.llm.metrics import Metrics
+from openhands.storage.files import FileStore
+
+
+class TrafficControlState(str, Enum):
+    # default state, no rate limiting
+    NORMAL = 'normal'
+
+    # task paused due to traffic control
+    THROTTLING = 'throttling'
+
+    # traffic control is temporarily paused
+    PAUSED = 'paused'
+
+
+RESUMABLE_STATES = [
+    AgentState.RUNNING,
+    AgentState.PAUSED,
+    AgentState.AWAITING_USER_INPUT,
+    AgentState.FINISHED,
+]
+
+
+@dataclass
+class State:
+    """
+    Represents the running state of an agent in the OpenHands system, saving data of its operation and memory.
+
+    - Multi-agent/delegate state:
+      - store the task (conversation between the agent and the user)
+      - the subtask (conversation between an agent and the user or another agent)
+      - global and local iterations
+      - delegate levels for multi-agent interactions
+      - almost stuck state
+
+    - Running state of an agent:
+      - current agent state (e.g., LOADING, RUNNING, PAUSED)
+      - traffic control state for rate limiting
+      - confirmation mode
+      - the last error encountered
+
+    - Data for saving and restoring the agent:
+      - save to and restore from a session
+      - serialize with pickle and base64
+
+    - Save / restore data about message history
+      - start and end IDs for events in agent's history
+      - summaries and delegate summaries
+
+    - Metrics:
+      - global metrics for the current task
+      - local metrics for the current subtask
+
+    - Extra data:
+      - additional task-specific data
+    """
+
+    root_task: RootTask = field(default_factory=RootTask)
+    # global iteration for the current task
+    iteration: int = 0
+    # local iteration for the current subtask
+    local_iteration: int = 0
+    # max number of iterations for the current task
+    max_iterations: int = 100
+    confirmation_mode: bool = False
+    history: list[Event] = field(default_factory=list)
+    inputs: dict = field(default_factory=dict)
+    outputs: dict = field(default_factory=dict)
+    agent_state: AgentState = AgentState.LOADING
+    resume_state: AgentState | None = None
+    traffic_control_state: TrafficControlState = TrafficControlState.NORMAL
+    # global metrics for the current task
+    metrics: Metrics = field(default_factory=Metrics)
+    # local metrics for the current subtask
+    local_metrics: Metrics = field(default_factory=Metrics)
+    # root agent has level 0, and every delegate increases the level by one
+    delegate_level: int = 0
+    # start_id and end_id track the range of events in history
+    start_id: int = -1
+    end_id: int = -1
+    # truncation_id tracks where to load history after context window truncation
+    truncation_id: int = -1
+
+    delegates: dict[tuple[int, int], tuple[str, str]] = field(default_factory=dict)
+    # NOTE: This will never be used by the controller, but it can be used by different
+    # evaluation tasks to store extra data needed to track the progress/state of the task.
+    extra_data: dict[str, Any] = field(default_factory=dict)
+    last_error: str = ''
+
+    def save_to_session(self, sid: str, file_store: FileStore):
+        pickled = pickle.dumps(self)
+        logger.debug(f'Saving state to session {sid}:{self.agent_state}')
+        encoded = base64.b64encode(pickled).decode('utf-8')
+        try:
+            file_store.write(f'sessions/{sid}/agent_state.pkl', encoded)
+        except Exception as e:
+            logger.error(f'Failed to save state to session: {e}')
+            raise e
+
+    @staticmethod
+    def restore_from_session(sid: str, file_store: FileStore) -> 'State':
+        try:
+            encoded = file_store.read(f'sessions/{sid}/agent_state.pkl')
+            pickled = base64.b64decode(encoded)
+            state = pickle.loads(pickled)
+        except Exception as e:
+            logger.debug(f'Could not restore state from session: {e}')
+            raise e
+
+        # update state
+        if state.agent_state in RESUMABLE_STATES:
+            state.resume_state = state.agent_state
+        else:
+            state.resume_state = None
+
+        # first state after restore
+        state.agent_state = AgentState.LOADING
+        return state
+
+    def __getstate__(self):
+        # don't pickle history, it will be restored from the event stream
+        state = self.__dict__.copy()
+        state['history'] = []
+        return state
+
+    def __setstate__(self, state):
+        self.__dict__.update(state)
+
+        # make sure we always have the attribute history
+        if not hasattr(self, 'history'):
+            self.history = []
+
+    def get_current_user_intent(self) -> tuple[str | None, list[str] | None]:
+        """Returns the latest user message and image(if provided) that appears after a FinishAction, or the first (the task) if nothing was finished yet."""
+        last_user_message = None
+        last_user_message_image_urls: list[str] | None = []
+        for event in reversed(self.history):
+            if isinstance(event, MessageAction) and event.source == 'user':
+                last_user_message = event.content
+                last_user_message_image_urls = event.image_urls
+            elif isinstance(event, AgentFinishAction):
+                if last_user_message is not None:
+                    return last_user_message, None
+
+        return last_user_message, last_user_message_image_urls
+
+    def get_last_agent_message(self) -> MessageAction | None:
+        for event in reversed(self.history):
+            if isinstance(event, MessageAction) and event.source == EventSource.AGENT:
+                return event
+        return None
+
+    def get_last_user_message(self) -> MessageAction | None:
+        for event in reversed(self.history):
+            if isinstance(event, MessageAction) and event.source == EventSource.USER:
+                return event
+        return None

controller/state/task.py

@@ -1,8 +1,8 @@
-from opendevin.core.exceptions import (
+from openhands.core.exceptions import (
     LLMMalformedActionError,
     TaskInvalidStateError,
 )
-from opendevin.core.logger import opendevin_logger as logger
+from openhands.core.logger import openhands_logger as logger
 
 OPEN_STATE = 'open'
 COMPLETED_STATE = 'completed'