ghcr: Fix local built image name in tests (#2686)

* ghcr: Fix local built image name in tests

* Push to registry when tagged

* Fix push and experiment

* Remove debug

.github/.codecov.yml

@@ -1,14 +1,22 @@
 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: 10% # allow patch coverage to be lower than project coverage by at most 10%
+        threshold: 100% # allow patch coverage to be lower than project coverage by any amount
     project:
       default:
         threshold: 5% # allow project coverage to drop at most 5%
 
 comment: false
+github_checks:
+    annotations: false
+
+ignore:
+  - "agenthub/SWE_agent/**" # SWE agent is deprecated

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -28,8 +28,8 @@ body:
   - type: textarea
     id: current-version
     attributes:
-      label: Current Version
-      description: What version are you using? If you're running in docker, tell us the tag you're using (e.g. ghcr.io/opendevin/opendevin:0.3.1).
+      label: Current OpenDevin version
+      description: What version of OpenDevin are you using? If you're running in docker, tell us the tag you're using (e.g. ghcr.io/opendevin/opendevin:0.3.1).
       render: bash
     validations:
       required: true
@@ -52,6 +52,12 @@ body:
         - Model:
         - Agent:
 
+  - type: textarea
+    id: os-version
+    attributes:
+      label: Operating System
+      description: What Operating System are you using? Linux, Mac OS, WSL on Windows
+
   - type: textarea
     id: repro-steps
     attributes:

.github/ISSUE_TEMPLATE/question.md

@@ -1,16 +0,0 @@
----
-name: Question
-about: Use this template to ask a question regarding the project.
-title: ''
-labels: question
-assignees: ''
-
----
-
-## Describe your question
-
-<!--A clear and concise description of what you want to know.-->
-
-## Additional context
-
-<!--Add any other context about the question here, like what you've tried so far.-->

.github/dependabot.yml

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

.github/pull_request_template.md

@@ -0,0 +1,5 @@
+**What is the problem that this fixes or functionality that this introduces? Does it fix any open issues?**
+
+**Give a brief summary of what the PR does, explaining any non-trivial design decisions**
+
+**Other references**

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

@@ -10,6 +10,9 @@ on:
     - main
   pull_request:
 
+env:
+  PERSIST_SANDBOX : "false"
+
 jobs:
   test:
     runs-on: ubuntu-latest

.github/workflows/ghcr.yml

@@ -1,4 +1,4 @@
-name: Publish Docker Image
+name: Build Publish and Test Docker Image
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -7,7 +7,7 @@ concurrency:
 on:
   push:
     branches:
-    - main
+      - main
     tags:
       - '*'
   pull_request:
@@ -19,19 +19,23 @@ on:
         default: ''
 
 jobs:
-  ghcr_build_and_push:
+  ghcr_build:
     runs-on: ubuntu-latest
 
+    outputs:
+      tags: ${{ steps.capture-tags.outputs.tags }}
+
     permissions:
       contents: read
       packages: write
 
     strategy:
       matrix:
-        image: ["app", "sandbox"]
+        image: ["sandbox", "opendevin"]
+        platform: ["amd64", "arm64"]
 
     steps:
-      - name: checkout
+      - name: Checkout
         uses: actions/checkout@v4
 
       - name: Free Disk Space (Ubuntu)
@@ -40,7 +44,6 @@ jobs:
           # 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
@@ -57,26 +60,212 @@ jobs:
         id: buildx
         uses: docker/setup-buildx-action@v3
 
-      - name: Login to ghcr
-        uses: docker/login-action@v1
+      - 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-for-sandbox:
+    name: Test for Sandbox
+    runs-on: ubuntu-latest
+    needs: ghcr_build
+    env:
+      PERSIST_SANDBOX: "false"
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: "poetry"
+
+      - name: Install Python dependencies using Poetry
+        run: 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 sandbox tests
+        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 poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml -s ./tests/unit/test_sandbox.py
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+  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", "exec", "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_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, integration-tests-on-linux, test-for-sandbox]
+    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: Build and push ${{ matrix.image }}
-        if: "!github.event.pull_request.head.repo.fork"
-        run: |
-          ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} --push
+      - name: Download Docker images
+        uses: actions/download-artifact@v4
+        with:
+          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
+          path: /tmp/${{ matrix.platform }}
 
-      - name: Build ${{ matrix.image }}
-        if: "github.event.pull_request.head.repo.fork"
+      - name: Load images and push to registry
         run: |
-          ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }}
+          mv /tmp/${{ 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
 
+  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
+
+  # FIXME: an admin needs to mark this as non-mandatory, and then we can remove it
   docker_build_success:
     name: Docker Build Success
     runs-on: ubuntu-latest
-    needs: ghcr_build_and_push
+    needs: ghcr_build
     steps:
     - run: echo Done!

.github/workflows/lint.yml

@@ -47,11 +47,4 @@ jobs:
       - name: Install pre-commit
         run: pip install pre-commit==3.7.0
       - name: Run pre-commit hooks
-        if: github.ref != 'refs/heads/main'
-        run: |
-          git fetch https://github.com/OpenDevin/OpenDevin.git main:main && \
-          pre-commit run \
-            --files \
-            $(git diff --name-only $(git merge-base main $(git branch --show-current)) $(git branch --show-current) | tr '\n' ' ') \
-            --show-diff-on-failure \
-            --config ./dev_config/python/.pre-commit-config.yaml
+        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

@@ -44,12 +44,24 @@ jobs:
         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
+        poetry run playwright install --with-deps chromium
+
     - name: Run OpenDevin
       env:
         LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
         SANDBOX_TYPE: exec
       run: |
-        WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE python ./opendevin/core/main.py -i 50 -f task.txt -d $GITHUB_WORKSPACE
+        # Append path to launch poetry
+        export PATH="/github/home/.local/bin:$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: Check if review file is non-empty

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

@@ -1,76 +0,0 @@
-name: Run Integration Tests
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-
-on:
-  push:
-    branches:
-    - main
-  pull_request:
-
-jobs:
-  integration-tests:
-    name: Integration Tests
-    runs-on: ubuntu-latest
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ["3.11"]
-        agent: ["SWEAgent", "PlannerAgent", "MonologueAgent", "CodeActAgent"]
-        sandbox: ["ssh", "exec"]
-        include:
-          - agent: "MonologueAgent"
-            embedding-model: "local"
-          - agent: "MonologueAgent"
-            # sufficient to have one agent testing against local sandbox
-            sandbox: "local"
-            embedding-model: "local"
-          - agent: "SWEAgent"
-            embedding-model: "none"
-          - agent: "PlannerAgent"
-            embedding-model: "none"
-          - agent: "CodeActAgent"
-            embedding-model: "none"
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.11'
-          cache: 'poetry'
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install
-
-      - name: Build Environment
-        run: make build
-
-      - name: Run Integration Tests
-        env:
-          SANDBOX_TYPE: ${{ matrix.sandbox }}
-          AGENT: ${{ matrix.agent }}
-          MAX_ITERATIONS: 10
-          LLM_EMBEDDING_MODEL: ${{ matrix.embedding-model }}
-        run: |
-          rm -rf workspace
-          mkdir workspace
-          WORKSPACE_BASE="$GITHUB_WORKSPACE/workspace" \
-            WORKSPACE_MOUNT_PATH="$GITHUB_WORKSPACE/workspace" \
-            poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml \
-            -s ./tests/integration
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-  test_matrix_success:
-    name: All Integration Tests Passed
-    runs-on: ubuntu-latest
-    needs: [integration-tests]
-    steps:
-    - run: echo Done!

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

@@ -7,15 +7,23 @@ concurrency:
 on:
   push:
     branches:
-    - main
+      - main
+    paths-ignore:
+      - '**/*.md'
+      - 'frontend/**'
+      - 'docs/**'
+      - 'evaluation/**'
   pull_request:
 
+env:
+  PERSIST_SANDBOX : "false"
+
 jobs:
   test-on-macos:
     name: Test on macOS
-    runs-on: macos-13
+    runs-on: macos-12
     env:
-      INSTALL_DOCKER: '0'  # Set to '0' to skip Docker installation
+      INSTALL_DOCKER: "1" # Set to '0' to skip Docker installation
     strategy:
       matrix:
         python-version: ["3.11"]
@@ -30,7 +38,7 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
+          cache: "poetry"
 
       - name: Install Python dependencies using Poetry
         run: poetry install
@@ -38,8 +46,17 @@ jobs:
       - name: Install & Start Docker
         if: env.INSTALL_DOCKER == '1'
         run: |
-          brew install colima docker
-          colima start
+          # 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 services start colima
+          brew install docker
+          colima start  --network-address --arch x86_64
 
           # 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
@@ -49,7 +66,7 @@ jobs:
         run: make build
 
       - name: Run Tests
-        run: poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox"
+        run: poetry run pytest --forked --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox"
 
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4
@@ -59,7 +76,7 @@ jobs:
     name: Test on Linux
     runs-on: ubuntu-latest
     env:
-      INSTALL_DOCKER: '0'  # Set to '0' to skip Docker installation
+      INSTALL_DOCKER: "0" # Set to '0' to skip Docker installation
     strategy:
       matrix:
         python-version: ["3.11"]
@@ -74,7 +91,7 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
+          cache: "poetry"
 
       - name: Install Python dependencies using Poetry
         run: poetry install --without evaluation
@@ -83,45 +100,9 @@ jobs:
         run: make build
 
       - name: Run Tests
-        run: poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox"
+        run: poetry run pytest --forked --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox"
 
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
-  test-for-sandbox:
-    name: Test for Sandbox
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.11'
-          cache: 'poetry'
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install
-
-      - name: Build Environment
-        run: make build
-
-      - name: Run Integration Test for Sandbox
-        run: |
-          poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml -s ./tests/unit/test_sandbox.py
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-  test_matrix_success:
-    name: All Mac/Linux Tests Passed
-    runs-on: ubuntu-latest
-    needs: [test-on-macos, test-on-linux, test-for-sandbox]
-    steps:
-    - run: echo Done!

.github/workflows/solve-issue.yml

@@ -35,15 +35,28 @@ jobs:
         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
+        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: ${{ secrets.OPENAI_API_KEY }}
         SANDBOX_TYPE: exec
       run: |
-        WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE python ./opendevin/core/main.py -i 50 -f task.txt -d $GITHUB_WORKSPACE
+        # Append path to launch poetry
+        export PATH="/github/home/.local/bin:$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

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

@@ -0,0 +1,48 @@
+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

@@ -126,6 +126,7 @@ env/
 venv/
 ENV/
 env.bak/
+.env.bak
 venv.bak/
 *venv/
 
@@ -160,9 +161,14 @@ cython_debug/
 #  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
 
@@ -175,6 +181,8 @@ frontend/yarn.lock
 
 # testing
 frontend/coverage
+test_results*
+/_test_files_tmp/
 
 # production
 frontend/build
@@ -202,8 +210,6 @@ cache
 
 # configuration
 config.toml
-evaluation/swe_bench/eval_workspace
-evaluation/outputs
-evaluation/evaluation_outputs
-test_results*
-/_test_files_tmp/
+config.toml.bak
+
+containers/agnostic_sandbox

CONTRIBUTING.md

@@ -1,13 +1,32 @@
 # Contributing
 
-Thanks for your interest in contributing to OpenDevin! We welcome and appreciate contributions.
-To report bugs, create a [GitHub issue](https://github.com/OpenDevin/OpenDevin/issues/new/choose).
+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://opendevin.github.io/OpenDevin/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
+
+In order 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
 
-## Contribution Guide
 ### 1. Fork the Official Repository
-
-Fork [OpenDevin repository](https://github.com/OpenDevin/OpenDevin) into your own account.
-Clone your own forked repository into your local environment.
+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
@@ -16,21 +35,23 @@ 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
+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.
+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.
+Synchronize latest commit with official repository before coding:
 
 ```shell
 git fetch upstream
@@ -39,25 +60,48 @@ git merge upstream/main
 git push origin main
 ```
 
-### 4. Create a New Branch And Open a Pull Request
-After you finish implementation, open forked repository. The source branch is your new branch, and the target branch is `OpenDevin/OpenDevin` `main` branch. Then PR should appears in [OpenDevin PRs](https://github.com/OpenDevin/OpenDevin/pulls).
+### 4. Set up the Development Environment
 
-Then OpenDevin team will review your code.
+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 in [here](https://github.com/commitizen/conventional-commit-types/blob/master/index.json), a valid PR title should begin with one of the following prefixes:
+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
-- `doc`: Documentation only changes
+- `docs`: Documentation only changes
+- `style`: Changes that do not affect the meaning of the code (white-space, formatting, missing semi-colons, etc)
 - `refactor`: A code change that neither fixes a bug nor adds a feature
-- `style`: A refactoring that improves code style
 - `perf`: A code change that improves performance
 - `test`: Adding missing tests or correcting existing tests
-- `ci`: Changes to CI configuration files and scripts (example scopes: `.github`, `ci` (Buildkite))
+- `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
 
@@ -67,24 +111,9 @@ For example, a PR title could be:
 
 You may also check out previous PRs in the [PR list](https://github.com/OpenDevin/OpenDevin/pulls).
 
-As described in [here](https://github.com/OpenDevin/OpenDevin/labels), we create several labels. Every PR should be tagged with the corresponding labels.
+As described [here](https://github.com/OpenDevin/OpenDevin/labels), we have created several labels. Every PR should be tagged with the corresponding labels.
 
 ### 2. Pull Request description
-
 - If your PR is small (such as a typo fix), you can go brief.
-- If it is large and you have changed a lot, it's better to write more details.
+- If it contains a lot of changes, it's better to write more details.
 
-
-## How to begin
-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)
-    - [mock server](./opendevin/mock/README.md)
-
-## Tests
-Please navigate to `tests` folder to see existing test suites.
-At the moment, we have two kinds of tests: `unit` and `integration`. Please refer to the README for each test suite. These tests also run on CI to ensure quality of
-the project.

Development.md

@@ -1,12 +1,13 @@
 # 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)
-* [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
+* 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
 
@@ -27,41 +28,40 @@ 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:
 
-- **Build the Project:** Begin by building the project, which includes setting up the environment and installing dependencies. This step ensures that OpenDevin is ready to run smoothly on your system.
-    ```bash
-    make build
-    ```
+```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, follow these steps:
-
-1. **Using the Makefile: The Effortless Approach**
-   With a single command, you can have a smooth LM setup for your OpenDevin experience. Simply run:
+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](https://github.com/OpenDevin/OpenDevin/issues/417).
+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).
 
-There is also [documentation for running with local models using ollama](./docs/documentation/LOCAL_LLM_GUIDE.md).
-
-### 4. Run the Application
-
-- **Run the 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 without any hassle.
-    ```bash
-    make run
-    ```
-
-### 5. Individual Server Startup
+### 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
@@ -73,18 +73,16 @@ There is also [documentation for running with local models using ollama](./docs/
     ```
 
 ### 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.
+If you encounter any issues with the Language Model (LM) or you're simply curious, you can inspect the actual LLM prompts and responses. To do so, export DEBUG=1 in the environment and restart the backend.
+OpenDevin will then log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
 
 ### 7. Help
-
-- **Get Some Help:** Need assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenDevin.
-    ```bash
-    make help
-    ```
+Need assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenDevin.
+```bash
+make help
+ ```
 
 ### 8. Testing
-
 #### Unit tests
 
 ```bash
@@ -92,5 +90,8 @@ poetry run pytest ./tests/unit/test_sandbox.py
 ```
 
 #### Integration tests
-
 Please refer to [this README](./tests/integration/README.md) for details.
+
+### 9. Add or update dependency
+1. Add your dependency in `pyproject.toml` or use `poetry add xxx`
+2. Update the poetry.lock file via `poetry lock --no-update`

Makefile

@@ -2,14 +2,15 @@ SHELL=/bin/bash
 # Makefile for OpenDevin project
 
 # Variables
-DOCKER_IMAGE = ghcr.io/opendevin/sandbox
+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-3.5-turbo"
+DEFAULT_MODEL = "gpt-4o"
 CONFIG_FILE = config.toml
 PRECOMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
+PYTHON_VERSION = 3.11
 
 # ANSI color codes
 GREEN=$(shell tput -Txterm setaf 2)
@@ -62,10 +63,10 @@ check-system:
 
 check-python:
 	@echo "$(YELLOW)Checking Python installation...$(RESET)"
-	@if command -v python3.11 > /dev/null; then \
-		echo "$(BLUE)$(shell python3.11 --version) is already installed.$(RESET)"; \
+	@if command -v python$(PYTHON_VERSION) > /dev/null; then \
+		echo "$(BLUE)$(shell python$(PYTHON_VERSION) --version) is already installed.$(RESET)"; \
 	else \
-		echo "$(RED)Python 3.11 is not installed. Please install Python 3.11 to continue.$(RESET)"; \
+		echo "$(RED)Python $(PYTHON_VERSION) is not installed. Please install Python $(PYTHON_VERSION) to continue.$(RESET)"; \
 		exit 1; \
 	fi
 
@@ -112,13 +113,13 @@ check-poetry:
 			echo "$(BLUE)$(shell poetry --version) is already installed.$(RESET)"; \
 		else \
 			echo "$(RED)Poetry 1.8 or later is required. You can install poetry by running the following command, then adding Poetry to your PATH:"; \
-			echo "$(RED) curl -sSL https://install.python-poetry.org | python3 -$(RESET)"; \
+			echo "$(RED) curl -sSL https://install.python-poetry.org | python$(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 "$(RED) curl -sSL https://install.python-poetry.org | python3.11 -$(RESET)"; \
+		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
@@ -130,8 +131,13 @@ pull-docker-image:
 
 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`...$(RESET)"; \
+		echo "$(BLUE)Installing chroma-hnswlib...$(RESET)"; \
 		export HNSWLIB_NO_NATIVE=1; \
 		poetry run pip install chroma-hnswlib; \
 	fi
@@ -141,7 +147,14 @@ install-python-dependencies:
 		poetry run pip install playwright; \
 		poetry run playwright install chromium; \
 	else \
-		poetry run playwright install --with-deps chromium; \
+		if [ ! -f cache/playwright_chromium_is_installed.txt ]; then \
+			echo "Running playwright install --with-deps chromium..."; \
+			poetry run playwright install --with-deps chromium; \
+			mkdir -p cache; \
+			touch cache/playwright_chromium_is_installed.txt; \
+		else \
+			echo "Setup already done. Skipping playwright installation."; \
+		fi \
 	fi
 	@echo "$(GREEN)Python dependencies installed successfully.$(RESET)"
 
@@ -164,7 +177,7 @@ install-precommit-hooks:
 
 lint-backend:
 	@echo "$(YELLOW)Running linters...$(RESET)"
-	@poetry run pre-commit run --files $$(git diff --name-only $$(git merge-base main $$(git branch --show-current)) $$(git branch --show-current) | tr '\n' ' ') --show-diff-on-failure --config $(PRECOMMIT_CONFIG_PATH)
+	@poetry run pre-commit run --files opendevin/**/* agenthub/**/* evaluation/**/* --show-diff-on-failure --config $(PRECOMMIT_CONFIG_PATH)
 
 lint-frontend:
 	@echo "$(YELLOW)Running linters for frontend...$(RESET)"
@@ -221,10 +234,20 @@ setup-config:
 setup-config-prompts:
 	@echo "[core]" > $(CONFIG_FILE).tmp
 
-	@read -p "Enter your workspace directory [default: $(DEFAULT_WORKSPACE_DIR)]: " workspace_dir; \
+	@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

README.md

@@ -26,15 +26,15 @@
   <br/>
   <a href="https://join.slack.com/t/opendevin/shared_invite/zt-2i1iqdag6-bVmvamiPA9EZUu7oCO6KhA"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
   <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
-  <br/>
-  <a href="https://xwang.dev/blog/2024/opendevin-codeact-1.0-swebench/"><img src="https://img.shields.io/badge/SWE--bench%20Lite-21.0%25-green?style=for-the-badge" alt="SWE-bench "></a>
+  <a href="https://codecov.io/github/opendevin/opendevin?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/opendevin/opendevin?style=for-the-badge"></a>
 </div>
 
 <!-- PROJECT LOGO -->
 <div align="center">
   <img src="./docs/static/img/logo.png" alt="Logo" width="200" height="200">
   <h1 align="center">OpenDevin: Code Less, Make More</h1>
-  <a href="https://opendevin.github.io/OpenDevin/"><img src="https://img.shields.io/badge/Documenation-OpenDevin-blue?logo=googledocs&logoColor=white&style=for-the-badge" alt="Check out the documentation"></a>
+  <a href="https://opendevin.github.io/OpenDevin/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://huggingface.co/spaces/OpenDevin/evaluation"><img src="https://img.shields.io/badge/Evaluation-Benchmark%20on%20HF%20Space-green?style=for-the-badge" alt="Evaluation Benchmark"></a>
 </div>
 <hr>
 
@@ -44,16 +44,18 @@ OpenDevin agents collaborate with human developers to write code, fix bugs, and
 
 ![App screenshot](./docs/static/img/screenshot.png)
 
-## ⚡ Quick Start
-You can run OpenDevin with Docker. It works best with the most recent
-version of Docker, `26.0.0`.
+## ⚡ Getting Started
+The easiest way to run OpenDevin is inside a Docker container. It works best with the most recent version of Docker, `26.0.0`.
+You must be using Linux, Mac OS, or WSL on Windows.
+
+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
-#The directory you want OpenDevin to modify. MUST be an absolute path!
-export WORKSPACE_BASE=$(pwd)/workspace;
-
-docker run \
-    -it \
+WORKSPACE_BASE=$(pwd)/workspace
+docker run -it \
     --pull=always \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
@@ -61,13 +63,18 @@ docker run \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
-    ghcr.io/opendevin/opendevin:0.5
+    --name opendevin-app-$(date +%Y%m%d%H%M%S) \
+    ghcr.io/opendevin/opendevin:0.6.2
 ```
 
+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.
+
 ## 🚀 Documentation
 
 To learn more about the project, and for tips on using OpenDevin,
-**check out our [documentation](https://opendevin.github.io/OpenDevin/)**.
+**check out our [documentation](https://opendevin.github.io/OpenDevin/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.
@@ -89,15 +96,10 @@ For details, please check [CONTRIBUTING.md](./CONTRIBUTING.md).
 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-2ggtwn3k5-PvAA2LUmqGHVZ~XzGq~ILw) - Here we talk about research, architecture, and future development.
+- [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://www.swebench.com/lite.html">
-        <img src="/docs/static/img/results.png" alt="SWE-Bench Lite Score" width="500" height="auto">
-    </a>
-</p>
 
 <p align="center">
   <a href="https://star-history.com/#OpenDevin/OpenDevin&Date">
@@ -119,3 +121,16 @@ Distributed under the MIT License. See [`LICENSE`](./LICENSE) for more informati
 [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{opendevin2024,
+  author       = {{OpenDevin Team}},
+  title        = {{OpenDevin: An Open Platform for AI Software Developers as Generalist Agents}},
+  year         = {2024},
+  version      = {v1.0},
+  howpublished = {\url{https://github.com/OpenDevin/OpenDevin}},
+  note         = {Accessed: ENTER THE DATE YOU ACCESSED THE PROJECT}
+}
+```

agenthub/README.md

@@ -2,15 +2,15 @@
 
 In this folder, there may exist multiple implementations of `Agent` that will be used by the framework.
 
-For example, `agenthub/monologue_agent`, `agenthub/metagpt_agent`, `agenthub/codeact_agent`, etc.
+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/agent.py).
+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/state.py) input, and the agent must output an [Action](../opendevin/action).
+[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).
@@ -28,21 +28,19 @@ The `state` contains:
 
 Here is a list of available Actions, which can be returned by `agent.step()`:
 
-- [`CmdRunAction`](../opendevin/action/bash.py) - Runs a command inside a sandboxed terminal
-- [`CmdKillAction`](../opendevin/action/bash.py) - Kills a background command
-- [`IPythonRunCellAction`](../opendevin/action/bash.py) - Execute a block of Python code interactively (in Jupyter notebook) and receives `CmdOutputObservation`. Requires setting up `jupyter` [plugin](../opendevin/sandbox/plugins) as a requirement.
-- [`FileReadAction`](../opendevin/action/fileop.py) - Reads the content of a file
-- [`FileWriteAction`](../opendevin/action/fileop.py) - Writes new content to a file
-- [`BrowseURLAction`](../opendevin/action/browse.py) - Gets the content of a URL
-- [`AgentRecallAction`](../opendevin/action/agent.py) - Searches memory (e.g. a vector database)
-- [`AddTaskAction`](../opendevin/action/tasks.py) - Adds a subtask to the plan
-- [`ModifyTaskAction`](../opendevin/action/tasks.py) - Changes the state of a subtask
-- [`AgentThinkAction`](../opendevin/action/agent.py) - A no-op that allows the agent to add plaintext to the history (as well as the chat log)
-- [`AgentTalkAction`](../opendevin/action/agent.py) - A no-op that allows the agent to add plaintext to the history and talk to the user.
-- [`AgentFinishAction`](../opendevin/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
-- [`AgentRejectAction`](../opendevin/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
-- [`AgentFinishAction`](../opendevin/action/agent.py) - Stops the control loop, allowing the user to enter a new task
-- [`MessageAction`](../opendevin/action/message.py) - Represents a message from an agent or the user
+- [`CmdRunAction`](../opendevin/events/action/commands.py) - Runs a command inside a sandboxed terminal
+- [`CmdKillAction`](../opendevin/events/action/commands.py) - Kills a background command
+- [`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
+- [`AgentRecallAction`](../opendevin/events/action/agent.py) - Searches memory (e.g. a vector database)
+- [`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.
 
@@ -54,13 +52,13 @@ in the background).
 
 Here is a list of available Observations:
 
-- [`CmdOutputObservation`](../opendevin/observation/run.py)
-- [`BrowserOutputObservation`](../opendevin/observation/browse.py)
-- [`FileReadObservation`](../opendevin/observation/files.py)
-- [`FileWriteObservation`](../opendevin/observation/files.py)
-- [`AgentRecallObservation`](../opendevin/observation/recall.py)
-- [`ErrorObservation`](../opendevin/observation/error.py)
-- [`SuccessObservation`](../opendevin/observation/success.py)
+- [`CmdOutputObservation`](../opendevin/events/observation/commands.py)
+- [`BrowserOutputObservation`](../opendevin/events/observation/browse.py)
+- [`FileReadObservation`](../opendevin/events/observation/files.py)
+- [`FileWriteObservation`](../opendevin/events/observation/files.py)
+- [`AgentRecallObservation`](../opendevin/events/observation/recall.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.
 

agenthub/SWE_agent/agent.py

@@ -6,9 +6,9 @@ from opendevin.events.action import (
     FileWriteAction,
     MessageAction,
 )
-from opendevin.events.observation import Observation
 from opendevin.events.serialization.event import event_to_memory
 from opendevin.llm.llm import LLM
+from opendevin.runtime.tools import RuntimeTool
 
 from .parser import parse_command
 from .prompts import (
@@ -21,25 +21,22 @@ from .prompts import (
 
 
 class SWEAgent(Agent):
+    VERSION = '1.0'
+    DEPRECATED = True
     """
     An attempt to recreate swe_agent with output parsing, prompting style, and Application Computer Interface (ACI).
 
     SWE-agent includes ACI functions like 'goto', 'search_for', 'edit', 'scroll', 'run'
     """
+    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
 
     def __init__(self, llm: LLM):
         super().__init__(llm)
         self.memory_window = 4
         self.max_retries = 2
-        self.running_memory: list[str] = []
         self.cur_file: str = ''
         self.cur_line: int = 0
 
-    def _remember(self, action: Action, observation: Observation) -> None:
-        """Agent has a limited memory of the few steps implemented as a queue"""
-        memory = MEMORY_FORMAT(event_to_memory(action), event_to_memory(observation))
-        self.running_memory.append(memory)
-
     def _think_act(self, messages: list[dict]) -> tuple[Action, str]:
         resp = self.llm.completion(
             messages=messages,
@@ -67,24 +64,36 @@ class SWEAgent(Agent):
             2. Perform think-act - prompt model for action and reasoning
             3. Catch errors - ensure model takes action (5 attempts max)
         """
-        for prev_action, obs in state.updated_info:
-            self._remember(prev_action, obs)
+        # retrieve short term memories from state.history, up to memory_window
+        memory_window = min(self.memory_window, len(state.history))
+        running_memory: list[str] = []
+        for prev_action, obs in state.history[-memory_window:]:
+            running_memory.append(
+                MEMORY_FORMAT(event_to_memory(prev_action), event_to_memory(obs))
+            )
 
         goal = state.get_current_user_intent()
+
+        # always in the prompt if they exist: file and line
         prompt = STEP_PROMPT(goal, self.cur_file, self.cur_line)
 
+        # prepare messages
         msgs = [
             {'content': SYSTEM_MESSAGE, 'role': 'system'},
             {'content': prompt, 'role': 'user'},
         ]
 
-        if len(self.running_memory) > 0:
-            context = CONTEXT_PROMPT(self.running_memory, self.memory_window)
+        # insert memories
+        if len(running_memory) > 0:
+            context = CONTEXT_PROMPT(running_memory, self.memory_window)
             msgs.insert(1, {'content': context, 'role': 'user'})
         # clrs = [''] * (len(msgs)-2) + ['\033[0;36m', '\033[0;35m']
         # print('\n\n'.join([c+m['content']+'\033[0m' for c, m in zip(clrs, msgs)]))
+
+        # send it over
         action, thought = self._think_act(messages=msgs)
 
+        # be robust with malformed responses
         start_msg_len = len(msgs)
         while not action and len(msgs) < self.max_retries + start_msg_len:
             error = NO_ACTION(thought)
@@ -100,9 +109,9 @@ class SWEAgent(Agent):
         return action
 
     def search_memory(self, query: str) -> list[str]:
-        return [item for item in self.running_memory if query in item]
+        # return [item for item in self.running_memory if query in item]
+        raise NotImplementedError('Search_memory not implemented currently')
 
     def reset(self) -> None:
         """Used to reset the agent"""
-        self.running_memory = []
         super().reset()

agenthub/SWE_agent/prompts.py

@@ -92,7 +92,7 @@ Notes:
 - To execute multiple commands you should write them down in your thoughts section so you can remember it on the next step and execute them then.
 - The only commands you are not capable of executing are interactive commands like `python` or `node` by themselves.
 - If you think that you have completed the task that has been given to you based on your previous actions and outputs then use ``` exit ``` as the command to let the system know that you are done.
-- DO NOT make any copies of your previous memories those will be provided to you at each step, making copies just wastes time and energy. Think smarter not harder.
+- DO NOT make any copies of your previous memories, those will be provided to you at each step, making copies just wastes time and energy. Think smarter not harder.
 - The write and edit commands requires proper indentation in the content section ex. `write hw.py def hello():\n    print(\'Hello World\')` this is how you would have to format your write command.
     - The white spaces matter as the code changes will be added to the code so they must have proper syntax.
 
@@ -114,8 +114,8 @@ Do not provide anything extra just your thought and action.
 """
 
 SYSTEM_MESSAGE = f"""SYSTEM INFO:
-You am an autonomous coding agent, here to provide solutions for coding issues.
-You have been designed to assist you with a wide range of programming tasks, from code editing and debugging to testing and deployment.
+You are an autonomous coding agent, here to provide solutions for coding issues.
+You have been designed to assist with a wide range of programming tasks, from code editing and debugging to testing and deployment.
 You have access to a variety of tools and commands that you can use to help you solve problems efficiently.
 
 {GENERAL_GUIDELINES}
@@ -171,8 +171,9 @@ Begin with your thought about the next step and then come up with an action to p
 """.strip()
 
 
-def unpack_dict(data: dict, restrict: list[str] = []):
+def unpack_dict(data: dict, restrict: list[str] | None = None):
     lines = []
+    restrict = [] if restrict is None else restrict
     for key, value in data.items():
         if key in restrict:
             continue

agenthub/__init__.py

@@ -10,7 +10,9 @@ load_dotenv()
 
 from . import (  # noqa: E402
     SWE_agent,
+    browsing_agent,
     codeact_agent,
+    codeact_swe_agent,
     delegator_agent,
     dummy_agent,
     monologue_agent,
@@ -20,10 +22,12 @@ from . import (  # noqa: E402
 __all__ = [
     'monologue_agent',
     'codeact_agent',
+    'codeact_swe_agent',
     'planner_agent',
     'SWE_agent',
     'delegator_agent',
     'dummy_agent',
+    'browsing_agent',
 ]
 
 for agent in all_microagents.values():

agenthub/browsing_agent/README.md

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

agenthub/browsing_agent/__init__.py

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

agenthub/browsing_agent/browsing_agent.py

@@ -0,0 +1,219 @@
+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 (
+    Action,
+    AgentFinishAction,
+    BrowseInteractiveAction,
+    MessageAction,
+)
+from opendevin.events.event import EventSource
+from opendevin.events.observation import BrowserOutputObservation
+from opendevin.llm.llm import LLM
+from opendevin.runtime.plugins import (
+    PluginRequirement,
+)
+from opendevin.runtime.tools import RuntimeTool
+
+USE_NAV = (
+    os.environ.get('USE_NAV', 'true') == 'true'
+)  # only disable NAV actions when running webarena and miniwob benchmarks
+USE_CONCISE_ANSWER = (
+    os.environ.get('USE_CONCISE_ANSWER', 'false') == 'true'
+)  # only return concise answer when running webarena and miniwob benchmarks
+
+if not USE_NAV and USE_CONCISE_ANSWER:
+    EVAL_MODE = True  # disabled NAV actions and only return concise answer, for webarena and miniwob benchmarks\
+else:
+    EVAL_MODE = False
+
+
+def get_error_prefix(last_browser_action: str) -> str:
+    return f'IMPORTANT! Last action is incorrect:\n{last_browser_action}\nThink again with the current observation of the page.\n'
+
+
+def get_system_message(goal: str, action_space: str) -> str:
+    return f"""\
+# Instructions
+Review the current state of the page and all other information to find the best
+possible next action to accomplish your goal. Your answer will be interpreted
+and executed by a program, make sure to follow the formatting instructions.
+
+# Goal:
+{goal}
+
+# Action Space
+{action_space}
+"""
+
+
+CONCISE_INSTRUCTION = """\
+
+Here is another example with chain of thought of a valid action when providing a concise answer to user:
+"
+In order to accomplish my goal I need to send the information asked back to the user. This page list the information of HP Inkjet Fax Machine, which is the product identified in the objective. Its price is $279.49. I will send a message back to user with the answer.
+```send_msg_to_user("$279.49")```
+"
+"""
+
+
+def get_prompt(error_prefix: str, cur_axtree_txt: str, prev_action_str: str) -> str:
+    prompt = f"""\
+{error_prefix}
+
+# Current Accessibility Tree:
+{cur_axtree_txt}
+
+# Previous Actions
+{prev_action_str}
+
+Here is an example with chain of thought of a valid action when clicking on a button:
+"
+In order to accomplish my goal I need to click on the button with bid 12
+```click("12")```
+"
+""".strip()
+    if USE_CONCISE_ANSWER:
+        prompt += CONCISE_INSTRUCTION
+    return prompt
+
+
+class BrowsingAgent(Agent):
+    VERSION = '1.0'
+    """
+    An agent that interacts with the browser.
+    """
+
+    sandbox_plugins: list[PluginRequirement] = []
+    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
+    response_parser = BrowsingResponseParser()
+
+    def __init__(
+        self,
+        llm: LLM,
+    ) -> None:
+        """
+        Initializes a new instance of the BrowsingAgent class.
+
+        Parameters:
+        - llm (LLM): The llm to be used by this agent
+        """
+        super().__init__(llm)
+        # 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']
+        if USE_NAV:
+            action_subsets.append('nav')
+        self.action_space = HighLevelActionSet(
+            subsets=action_subsets,
+            strict=False,  # less strict on the parsing of the actions
+            multiaction=True,  # enable to agent to take multiple actions at once
+        )
+
+        self.reset()
+
+    def reset(self) -> None:
+        """
+        Resets the Browsing Agent.
+        """
+        super().reset()
+        self.cost_accumulator = 0
+        self.error_accumulator = 0
+
+    def step(self, state: State) -> Action:
+        """
+        Performs one step using the Browsing Agent.
+        This includes gathering information on previous steps and prompting the model to make a browsing command to execute.
+
+        Parameters:
+        - state (State): used to get updated info
+
+        Returns:
+        - BrowseInteractiveAction(browsergym_command) - BrowserGym commands to run
+        - MessageAction(content) - Message action to run (e.g. ask for clarification)
+        - AgentFinishAction() - end the interaction
+        """
+        messages = []
+        prev_actions = []
+        cur_axtree_txt = ''
+        error_prefix = ''
+        last_obs = None
+        last_action = None
+
+        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 prev_action, obs in state.history:
+            if isinstance(prev_action, BrowseInteractiveAction):
+                prev_actions.append(prev_action.browser_actions)
+                last_obs = obs
+                last_action = prev_action
+            elif (
+                isinstance(prev_action, MessageAction)
+                and prev_action.source == EventSource.AGENT
+            ):
+                # agent has responded, task finish.
+                return AgentFinishAction(outputs={'content': prev_action.content})
+
+        if EVAL_MODE:
+            prev_actions = prev_actions[1:]  # remove the first noop action
+
+        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
+        if (
+            isinstance(last_action, BrowseInteractiveAction)
+            and last_action.browsergym_send_msg_to_user
+        ):
+            return MessageAction(last_action.browsergym_send_msg_to_user)
+
+        if isinstance(last_obs, BrowserOutputObservation):
+            if last_obs.error:
+                # add error recovery prompt prefix
+                error_prefix = get_error_prefix(last_obs.last_browser_action)
+                self.error_accumulator += 1
+                if self.error_accumulator > 5:
+                    return MessageAction('Too many errors encountered. Task failed.')
+            try:
+                cur_axtree_txt = flatten_axtree_to_str(
+                    last_obs.axtree_object,
+                    extra_properties=last_obs.extra_element_properties,
+                    with_clickable=True,
+                    filter_visible_only=True,
+                )
+            except Exception as e:
+                logger.error(
+                    'Error when trying to process the accessibility tree: %s', e
+                )
+                return MessageAction('Error encountered when browsing.')
+
+        if (goal := state.get_current_user_intent()) 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})
+
+        prompt = get_prompt(error_prefix, cur_axtree_txt, prev_action_str)
+        messages.append({'role': 'user', 'content': prompt})
+        logger.info(prompt)
+        response = self.llm.completion(
+            messages=messages,
+            temperature=0.0,
+            stop=[')```', ')\n```'],
+        )
+        return self.response_parser.parse(response)
+
+    def search_memory(self, query: str) -> list[str]:
+        raise NotImplementedError('Implement this abstract method')

agenthub/browsing_agent/prompt.py

@@ -0,0 +1,787 @@
+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

@@ -0,0 +1,88 @@
+import ast
+
+from opendevin.controller.action_parser import ActionParser, ResponseParser
+from opendevin.core.logger import opendevin_logger as logger
+from opendevin.events.action import (
+    Action,
+    BrowseInteractiveAction,
+)
+
+
+class BrowsingResponseParser(ResponseParser):
+    def __init__(
+        self,
+    ):
+        # Need to pay attention to the item order in self.action_parsers
+        self.action_parsers = [BrowsingActionParserMessage()]
+        self.default_parser = BrowsingActionParserBrowseInteractive()
+
+    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_str = response['choices'][0]['message']['content'].strip()
+        if not action_str.endswith('```'):
+            action_str = action_str + ')```'
+        logger.info(action_str)
+        return action_str
+
+    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 BrowsingActionParserMessage(ActionParser):
+    """
+    Parser action:
+        - BrowseInteractiveAction(browser_actions) - unexpected response format, message back to user
+    """
+
+    def __init__(
+        self,
+    ):
+        pass
+
+    def check_condition(self, action_str: str) -> bool:
+        return '```' not in action_str
+
+    def parse(self, action_str: str) -> Action:
+        msg = f'send_msg_to_user("""{action_str}""")'
+        return BrowseInteractiveAction(
+            browser_actions=msg,
+            thought=action_str,
+            browsergym_send_msg_to_user=action_str,
+        )
+
+
+class BrowsingActionParserBrowseInteractive(ActionParser):
+    """
+    Parser action:
+        - BrowseInteractiveAction(browser_actions) - handle send message to user function call in BrowserGym
+    """
+
+    def __init__(
+        self,
+    ):
+        pass
+
+    def check_condition(self, action_str: str) -> bool:
+        return True
+
+    def parse(self, action_str: str) -> Action:
+        thought = action_str.split('```')[0].strip()
+        action_str = action_str.split('```')[1].strip()
+        msg_content = ''
+        for sub_action in action_str.split('\n'):
+            if 'send_msg_to_user(' in sub_action:
+                tree = ast.parse(sub_action)
+                args = tree.body[0].value.args  # type: ignore
+                msg_content = args[0].value
+
+        return BrowseInteractiveAction(
+            browser_actions=action_str,
+            thought=thought,
+            browsergym_send_msg_to_user=msg_content,
+        )

agenthub/browsing_agent/utils.py

@@ -0,0 +1,160 @@
+import collections
+import re
+from warnings import warn
+
+import yaml
+
+
+def yaml_parser(message):
+    """Parse a yaml message for the retry function."""
+
+    # saves gpt-3.5 from some yaml parsing errors
+    message = re.sub(r':\s*\n(?=\S|\n)', ': ', message)
+
+    try:
+        value = yaml.safe_load(message)
+        valid = True
+        retry_message = ''
+    except yaml.YAMLError as e:
+        warn(str(e), stacklevel=2)
+        value = {}
+        valid = False
+        retry_message = "Your response is not a valid yaml. Please try again and be careful to the format. Don't add any apology or comment, just the answer."
+    return value, valid, retry_message
+
+
+def _compress_chunks(text, identifier, skip_list, split_regex='\n\n+'):
+    """Compress a string by replacing redundant chunks by identifiers. Chunks are defined by the split_regex."""
+    text_list = re.split(split_regex, text)
+    text_list = [chunk.strip() for chunk in text_list]
+    counter = collections.Counter(text_list)
+    def_dict = {}
+    id = 0
+
+    # Store items that occur more than once in a dictionary
+    for item, count in counter.items():
+        if count > 1 and item not in skip_list and len(item) > 10:
+            def_dict[f'{identifier}-{id}'] = item
+            id += 1
+
+    # Replace redundant items with their identifiers in the text
+    compressed_text = '\n'.join(text_list)
+    for key, value in def_dict.items():
+        compressed_text = compressed_text.replace(value, key)
+
+    return def_dict, compressed_text
+
+
+def compress_string(text):
+    """Compress a string by replacing redundant paragraphs and lines with identifiers."""
+
+    # Perform paragraph-level compression
+    def_dict, compressed_text = _compress_chunks(
+        text, identifier='§', skip_list=[], split_regex='\n\n+'
+    )
+
+    # Perform line-level compression, skipping any paragraph identifiers
+    line_dict, compressed_text = _compress_chunks(
+        compressed_text, '¶', list(def_dict.keys()), split_regex='\n+'
+    )
+    def_dict.update(line_dict)
+
+    # Create a definitions section
+    def_lines = ['<definitions>']
+    for key, value in def_dict.items():
+        def_lines.append(f'{key}:\n{value}')
+    def_lines.append('</definitions>')
+    definitions = '\n'.join(def_lines)
+
+    return definitions + '\n' + compressed_text
+
+
+def extract_html_tags(text, keys):
+    """Extract the content within HTML tags for a list of keys.
+
+    Parameters
+    ----------
+    text : str
+        The input string containing the HTML tags.
+    keys : list of str
+        The HTML tags to extract the content from.
+
+    Returns
+    -------
+    dict
+        A dictionary mapping each key to a list of subset in `text` that match the key.
+
+    Notes
+    -----
+    All text and keys will be converted to lowercase before matching.
+
+    """
+    content_dict = {}
+    # text = text.lower()
+    # keys = set([k.lower() for k in keys])
+    for key in keys:
+        pattern = f'<{key}>(.*?)</{key}>'
+        matches = re.findall(pattern, text, re.DOTALL)
+        if matches:
+            content_dict[key] = [match.strip() for match in matches]
+    return content_dict
+
+
+class ParseError(Exception):
+    pass
+
+
+def parse_html_tags_raise(text, keys=(), optional_keys=(), merge_multiple=False):
+    """A version of parse_html_tags that raises an exception if the parsing is not successful."""
+    content_dict, valid, retry_message = parse_html_tags(
+        text, keys, optional_keys, merge_multiple=merge_multiple
+    )
+    if not valid:
+        raise ParseError(retry_message)
+    return content_dict
+
+
+def parse_html_tags(text, keys=(), optional_keys=(), merge_multiple=False):
+    """Satisfy the parse api, extracts 1 match per key and validates that all keys are present
+
+    Parameters
+    ----------
+    text : str
+        The input string containing the HTML tags.
+    keys : list of str
+        The HTML tags to extract the content from.
+    optional_keys : list of str
+        The HTML tags to extract the content from, but are optional.
+
+    Returns
+    -------
+    dict
+        A dictionary mapping each key to subset of `text` that match the key.
+    bool
+        Whether the parsing was successful.
+    str
+        A message to be displayed to the agent if the parsing was not successful.
+    """
+    all_keys = tuple(keys) + tuple(optional_keys)
+    content_dict = extract_html_tags(text, all_keys)
+    retry_messages = []
+
+    for key in all_keys:
+        if key not in content_dict:
+            if key not in optional_keys:
+                retry_messages.append(f'Missing the key <{key}> in the answer.')
+        else:
+            val = content_dict[key]
+            content_dict[key] = val[0]
+            if len(val) > 1:
+                if not merge_multiple:
+                    retry_messages.append(
+                        f'Found multiple instances of the key {key}. You should have only one of them.'
+                    )
+                else:
+                    # merge the multiple instances
+                    content_dict[key] = '\n'.join(val)
+
+    valid = len(retry_messages) == 0
+    retry_message = '\n'.join(retry_messages)
+    return content_dict, valid, retry_message

agenthub/codeact_agent/README.md

@@ -1,6 +1,6 @@
 # CodeAct Agent Framework
 
-This folder implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.13463), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a unified **code** action space for both *simplicity* and *performance* (see paper for more details).
+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:
 

agenthub/codeact_agent/action_parser.py

@@ -0,0 +1,182 @@
+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
+        self.action_parsers = [
+            CodeActActionParserFinish(),
+            CodeActActionParserCmdRun(),
+            CodeActActionParserIPythonRunCell(),
+            CodeActActionParserAgentDelegate(),
+        ]
+        self.default_parser = CodeActActionParserMessage()
+
+    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
+        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()
+        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

@@ -1,5 +1,4 @@
-import re
-
+from agenthub.codeact_agent.action_parser import CodeActResponseParser
 from agenthub.codeact_agent.prompt import (
     COMMAND_DOCS,
     EXAMPLES,
@@ -9,36 +8,79 @@ from agenthub.codeact_agent.prompt import (
 )
 from opendevin.controller.agent import Agent
 from opendevin.controller.state.state import State
-from opendevin.core.logger import opendevin_logger as logger
 from opendevin.events.action import (
     Action,
+    AgentDelegateAction,
     AgentFinishAction,
-    BrowseInteractiveAction,
     CmdRunAction,
     IPythonRunCellAction,
     MessageAction,
 )
 from opendevin.events.observation import (
-    BrowserOutputObservation,
+    AgentDelegateObservation,
     CmdOutputObservation,
     IPythonRunCellObservation,
 )
 from opendevin.llm.llm import LLM
 from opendevin.runtime.plugins import (
+    AgentSkillsRequirement,
     JupyterRequirement,
     PluginRequirement,
-    SWEAgentCommandsRequirement,
 )
+from opendevin.runtime.tools import RuntimeTool
 
 ENABLE_GITHUB = True
 
 
-def parse_response(response) -> str:
-    action = response.choices[0].message.content
-    for lang in ['bash', 'ipython', 'browse']:
-        if f'<execute_{lang}>' in action and f'</execute_{lang}>' not in action:
-            action += f'</execute_{lang}>'
-    return action
+def action_to_str(action: Action) -> str:
+    if isinstance(action, CmdRunAction):
+        return f'{action.thought}\n<execute_bash>\n{action.command}\n</execute_bash>'
+    elif isinstance(action, IPythonRunCellAction):
+        return f'{action.thought}\n<execute_ipython>\n{action.code}\n</execute_ipython>'
+    elif isinstance(action, AgentDelegateAction):
+        return f'{action.thought}\n<execute_browse>\n{action.inputs["task"]}\n</execute_browse>'
+    elif isinstance(action, MessageAction):
+        return action.content
+    return ''
+
+
+def get_action_message(action: Action) -> dict[str, str] | None:
+    if (
+        isinstance(action, AgentDelegateAction)
+        or isinstance(action, CmdRunAction)
+        or isinstance(action, IPythonRunCellAction)
+        or isinstance(action, MessageAction)
+    ):
+        return {
+            'role': 'user' if action.source == 'user' else 'assistant',
+            'content': action_to_str(action),
+        }
+    return None
+
+
+def get_observation_message(obs) -> dict[str, str] | None:
+    if isinstance(obs, CmdOutputObservation):
+        content = 'OBSERVATION:\n' + truncate_observation(obs.content)
+        content += (
+            f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]'
+        )
+        return {'role': 'user', 'content': content}
+    elif isinstance(obs, IPythonRunCellObservation):
+        content = 'OBSERVATION:\n' + obs.content
+        # replace base64 images with a placeholder
+        splitted = content.split('\n')
+        for i, line in enumerate(splitted):
+            if '![image](data:image/png;base64,' in line:
+                splitted[i] = (
+                    '![image](data:image/png;base64, ...) already displayed to user'
+                )
+        content = '\n'.join(splitted)
+        content = truncate_observation(content)
+        return {'role': 'user', 'content': content}
+    elif isinstance(obs, AgentDelegateObservation):
+        content = 'OBSERVATION:\n' + truncate_observation(str(obs.outputs))
+        return {'role': 'user', 'content': content}
+    return None
 
 
 def truncate_observation(observation: str, max_chars: int = 10_000) -> str:
@@ -55,39 +97,20 @@ def truncate_observation(observation: str, max_chars: int = 10_000) -> str:
     )
 
 
-def swe_agent_edit_hack(bash_command: str) -> str:
-    """
-    Hack to handle the SWE-agent edit command. The vanilla edit command will hang the SSHBox.
+# 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}'
 
-    REPLACE THIS:
-    edit 683:693
-            try:
-                return list(urlsplit(url))
-            except ValueError:
-                raise ValidationError(self.error_messages['invalid'], code='invalid')
-    end_of_edit
 
-    WITH THIS:
-    edit 683:693 <<EOF
-            try:
-                return list(urlsplit(url))
-            except ValueError:
-                raise ValidationError(self.error_messages['invalid'], code='invalid')
-    EOF
-    """
-    if 'edit' in bash_command:
-        # edit\s(\d+):(\d+)([\s\S]*)end_of_edit
-        # replace
-        bash_command = re.sub(
-            r'edit\s(\d+):(\d+)([\s\S]*?)end_of_edit',
-            r'edit \1:\2 <<EOF\3EOF',
-            bash_command,
-        )
-    return bash_command
+def get_in_context_example() -> str:
+    return EXAMPLES
 
 
 class CodeActAgent(Agent):
-    VERSION = '1.3'
+    VERSION = '1.6'
     """
     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.
@@ -125,15 +148,18 @@ class CodeActAgent(Agent):
     """
 
     sandbox_plugins: list[PluginRequirement] = [
+        # NOTE: AgentSkillsRequirement need to go before JupyterRequirement, since
+        # AgentSkillsRequirement provides a lot of Python functions
+        # and it need to be initialized before Jupyter for Jupyter to use those functions.
+        AgentSkillsRequirement(),
         JupyterRequirement(),
-        SWEAgentCommandsRequirement(),
     ]
+    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
 
-    system_message: str = (
-        f'{SYSTEM_PREFIX}\n{GITHUB_MESSAGE}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
-        if ENABLE_GITHUB
-        else f'{SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
-    )
+    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,
@@ -153,14 +179,6 @@ class CodeActAgent(Agent):
         Resets the CodeAct Agent.
         """
         super().reset()
-        self.messages: list[dict[str, str]] = [
-            {'role': 'system', 'content': self.system_message},
-            {
-                'role': 'user',
-                'content': f"Here is an example of how you can interact with the environment for task solving:\n{EXAMPLES}\n\nNOW, LET'S START!",
-            },
-        ]
-        self.cost_accumulator = 0
 
     def step(self, state: State) -> Action:
         """
@@ -173,53 +191,34 @@ class CodeActAgent(Agent):
         Returns:
         - CmdRunAction(command) - bash command to run
         - IPythonRunCellAction(code) - IPython code to run
-        - BrowseInteractiveAction(browsergym_command) - BrowserGym commands 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
         """
+        messages: list[dict[str, str]] = [
+            {'role': 'system', 'content': self.system_message},
+            {'role': 'user', 'content': self.in_context_example},
+        ]
 
-        updated_info = state.updated_info
-        if updated_info:
-            for prev_action, obs in updated_info:
-                if (
-                    isinstance(prev_action, MessageAction)
-                    and prev_action.source == 'user'
-                ):
-                    self.messages.append(
-                        {'role': 'user', 'content': prev_action.content}
-                    )
-                    if prev_action.content.strip() == '/exit':
-                        # User wants to exit
-                        return AgentFinishAction()
+        for prev_action, obs in state.history:
+            action_message = get_action_message(prev_action)
+            if action_message:
+                messages.append(action_message)
 
-                if isinstance(obs, CmdOutputObservation):
-                    content = 'OBSERVATION:\n' + truncate_observation(obs.content)
-                    content += f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]]'
-                    self.messages.append({'role': 'user', 'content': content})
-                elif isinstance(obs, IPythonRunCellObservation):
-                    content = 'OBSERVATION:\n' + obs.content
-                    # replace base64 images with a placeholder
-                    splitted = content.split('\n')
-                    for i, line in enumerate(splitted):
-                        if '![image](data:image/png;base64,' in line:
-                            splitted[i] = (
-                                '![image](data:image/png;base64, ...) already displayed to user'
-                            )
-                    content = '\n'.join(splitted)
-                    content = truncate_observation(content)
-                    self.messages.append({'role': 'user', 'content': content})
-                elif isinstance(obs, BrowserOutputObservation):
-                    content = 'OBSERVATION:\n' + truncate_observation(obs.content)
-                    self.messages.append({'role': 'user', 'content': content})
+            obs_message = get_observation_message(obs)
+            if obs_message:
+                messages.append(obs_message)
 
-        latest_user_message = [m for m in self.messages if m['role'] == 'user'][-1]
+        latest_user_message = [m for m in messages if m['role'] == 'user'][-1]
         if latest_user_message:
+            if latest_user_message['content'].strip() == '/exit':
+                return AgentFinishAction()
             latest_user_message['content'] += (
                 f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task.'
             )
 
         response = self.llm.completion(
-            messages=self.messages,
+            messages=messages,
             stop=[
                 '</execute_ipython>',
                 '</execute_bash>',
@@ -227,62 +226,10 @@ class CodeActAgent(Agent):
             ],
             temperature=0.0,
         )
-
-        self.log_cost(response)
-
-        action_str: str = parse_response(response)
         state.num_of_chars += sum(
-            len(message['content']) for message in self.messages
-        ) + len(action_str)
-        self.messages.append({'role': 'assistant', 'content': action_str})
-
-        if finish_command := re.search(r'<finish>.*</finish>', action_str, re.DOTALL):
-            thought = action_str.replace(finish_command.group(0), '').strip()
-            return AgentFinishAction(thought=thought)
-        if bash_command := re.search(
-            r'<execute_bash>(.*)</execute_bash>', action_str, re.DOTALL
-        ):
-            # remove the command from the action string to get thought
-            thought = action_str.replace(bash_command.group(0), '').strip()
-            # a command was found
-            command_group = bash_command.group(1).strip()
-            command_group = swe_agent_edit_hack(command_group)
-
-            if command_group.strip() == 'exit':
-                return AgentFinishAction()
-            return CmdRunAction(command=command_group, thought=thought)
-        elif python_code := re.search(
-            r'<execute_ipython>(.*)</execute_ipython>', action_str, re.DOTALL
-        ):
-            # a code block was found
-            code_group = python_code.group(1).strip()
-            thought = action_str.replace(python_code.group(0), '').strip()
-            return IPythonRunCellAction(code=code_group, thought=thought)
-        elif browse_command := re.search(
-            r'<execute_browse>(.*)</execute_browse>', action_str, re.DOTALL
-        ):
-            # BrowserGym actions was found
-            browse_actions = browse_command.group(1).strip()
-            thought = action_str.replace(browse_command.group(0), '').strip()
-            return BrowseInteractiveAction(
-                browser_actions=browse_actions, thought=thought
-            )
-        else:
-            # We assume the LLM is GOOD enough that when it returns pure natural language
-            # it want to talk to the user
-            return MessageAction(content=action_str, wait_for_response=True)
+            len(message['content']) for message in messages
+        ) + len(response.choices[0].message.content)
+        return self.action_parser.parse(response)
 
     def search_memory(self, query: str) -> list[str]:
         raise NotImplementedError('Implement this abstract method')
-
-    def log_cost(self, response):
-        try:
-            cur_cost = self.llm.completion_cost(response)
-        except Exception:
-            cur_cost = 0
-        self.cost_accumulator += cur_cost
-        logger.info(
-            'Cost: %.2f USD | Accumulated Cost: %.2f USD',
-            cur_cost,
-            self.cost_accumulator,
-        )

agenthub/codeact_agent/prompt.py

@@ -1,70 +1,71 @@
-from opendevin.runtime.plugins import SWEAgentCommandsRequirement
+from opendevin.runtime.plugins import AgentSkillsRequirement
 
-_SWEAGENT_BASH_DOCS = '\n'.join(
-    filter(
-        lambda x: not x.startswith('submit'),
-        SWEAgentCommandsRequirement.documentation.split('\n'),
-    )
-)
-# _SWEAGENT_BASH_DOCS content below:
-"""
-open <path> [<line_number>] - opens the file at the given path in the editor. If line_number is provided, the window will be move to include that line
-goto <line_number> - moves the window to show <line_number>
-scroll_down - moves the window down {WINDOW} lines
-scroll_up - moves the window down {WINDOW} lines
-create <filename> - creates and opens a new file with the given name
-search_dir <search_term> [<dir>] - searches for search_term in all files in dir. If dir is not provided, searches in the current directory
-search_file <search_term> [<file>] - searches for search_term in file. If file is not provided, searches in the current open file
-find_file <file_name> [<dir>] - finds all files with the given name in dir. If dir is not provided, searches in the current directory
-edit <start_line>:<end_line>
-<replacement_text>
-end_of_edit - replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing the same command a second time will just lead to the same error message again. Remember, the file must be open before editing.
-"""
+_AGENT_SKILLS_DOCS = AgentSkillsRequirement.documentation
 
 COMMAND_DOCS = (
-    '\nApart from the standard bash commands, you can also use the following special commands in <execute_bash> environment:\n'
-    f'{_SWEAGENT_BASH_DOCS}'
-    "Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. If you'd like to add the line '        print(x)' you must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run."
+    '\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` and `append_file` 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_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:
+# ======= 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>.
-The assistant can browse the Internet with commands on behalf of the user by wrapping them with <execute_browse> and </execute_browse>.
-For example, you can browse a given URL by <execute_browse> goto("<URL>") </execute_browse>.
-The assistant should attempt fewer things at a time instead of putting too much commands OR code in one "execute" block.
-The assistant can install Python packages through bash by <execute_bash> pip install [package needed] </execute_bash> and should always import packages and define variables before starting to use them.
-The assistant should stop <execute> and provide an answer when they have already obtained the answer from the execution result.
-If the assistant encounters an import error in IPython for a newly installed package, they should try to restart the kernel and import the package again. IPython kernel can be re-started by:
-<execute_ipython>
-import IPython
-IPython.Application.instance().kernel.do_shutdown(True)  # Restart the kernel
-</execute_ipython>"""
-
-GITHUB_MESSAGE = """To do any activities on GitHub, you should use the token in the $GITHUB_TOKEN environment variable.
-For instance, to push a local branch `my_branch` to the github repo `owner/repo`, you can use the following four commands:
-<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
-If you require access to GitHub but $GITHUB_TOKEN is not set, ask the user to set it for you."""
-
-SYSTEM_SUFFIX = """The assistant's response should be concise.
-You should include <execute_ipython> or <execute_bash> or <execute_browse> in every one of your responses, unless you are finished with the task or need more input or action from the user in order to proceed.
-IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> or <execute_browse> instead of providing it.
+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.
+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: Can you create a list of numbers from 1 to 10, and create a web page to display them at port 5000?
+USER: Create a list of numbers from 1 to 10, and display them in a web page at port 5000.
 
 ASSISTANT:
-Sure! Let me write the Python code for starting a web server and save it to a file `app.py`:
+Sure! Let me create a Python file `app.py`:
 <execute_ipython>
-CODE='''
-from flask import Flask
+create_file('app.py')
+</execute_ipython>
+
+USER:
+OBSERVATION:
+[File: /workspace/app.py (1 lines total)]
+1|
+[File app.py created.]
+
+ASSISTANT:
+Now I will write the Python code for starting a web server and save it to the file `app.py`:
+<execute_ipython>
+EDITED_CODE=\"\"\"from flask import Flask
 app = Flask(__name__)
 
 @app.route('/')
@@ -73,15 +74,23 @@ def index():
     return str(numbers)
 
 if __name__ == '__main__':
-    app.run(port=5000)
-'''
-with open('app.py', 'w') as f:
-    f.write(CODE)
+    app.run(port=5000)\"\"\"
+edit_file('app.py', start=1, end=1, content=EDITED_CODE)
 </execute_ipython>
 
 USER:
-Observation:
-[Code executed successfully with no output]
+OBSERVATION:
+1|from flask import Flask
+2|app = Flask(__name__)
+3|
+4|@app.route('/')
+5|def index():
+6|    numbers = list(range(1, 11))
+7|    return str(numbers)
+8|
+9|if __name__ == '__main__':
+10|    app.run(port=5000)
+[File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
 
 ASSISTANT:
 I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you:
@@ -90,7 +99,7 @@ python3 app.py > server.log 2>&1 &
 </execute_bash>
 
 USER:
-Observation:
+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:
@@ -99,7 +108,7 @@ cat server.log
 </execute_bash>
 
 USER:
-Observation:
+OBSERVATION:
 Traceback (most recent call last):
   File "/workspace/app.py", line 2, in <module>
     from flask import Flask
@@ -112,7 +121,7 @@ pip install flask
 </execute_bash>
 
 USER:
-Observation:
+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)
@@ -136,7 +145,7 @@ python3 app.py > server.log 2>&1 &
 </execute_bash>
 
 USER:
-Observation:
+OBSERVATION:
 [1] 124
 
 ASSISTANT:
@@ -146,7 +155,7 @@ cat server.log
 </execute_bash>
 
 USER:
-Observation:
+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.
@@ -161,11 +170,11 @@ USER: Now browse the newly started server's homepage and show me the content.
 ASSISTANT:
 Sure! Let me browse the server's homepage at http://127.0.0.1:5000:
 <execute_browse>
-goto("http://127.0.0.1:5000")
+Get the content on "http://127.0.0.1:5000"
 </execute_browse>
 
 USER:
-Observation:
+OBSERVATION:
 [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
 
 ASSISTANT:
@@ -180,55 +189,51 @@ kill 124
 </execute_bash>
 
 USER:
-Observation:
+OBSERVATION:
 [1]+  Terminated              python3 app.py > server.log 2>&1
 
 ASSISTANT:
 The server has been stopped. Let me open the Python file and modify it.
-<execute_bash>
-open app.py
-</execute_bash>
+<execute_ipython>
+open_file('app.py')
+</execute_ipython>
 
 USER:
-[File: /workspace/app.py (11 lines total)]
-1:
-2:from flask import Flask
-3:app = Flask(__name__)
-4:
-5:@app.route('/')
-6:def index():
-7:    numbers = list(range(1, 11))
-8:    return str(numbers)
-9:
-10:if __name__ == '__main__':
-11:    app.run(port=5000)
+[File: /workspace/app.py (10 lines total)]
+1|from flask import Flask
+2|app = Flask(__name__)
+3|
+4|@app.route('/')
+5|def index():
+6|    numbers = list(range(1, 11))
+7|    return str(numbers)
+8|
+9|if __name__ == '__main__':
+10|    app.run(port=5000)
 
 ASSISTANT:
 I should edit the file to display the numbers in a table format. I should include correct indentation. Let me update the file:
-<execute_bash>
-edit 8:8
-    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
-end_of_edit
-</execute_bash>
+<execute_ipython>
+edit_file('app.py', start=7, end=7, content="    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'")
+</execute_ipython>
 
 USER:
 Observation:
-[File: /workspace/app.py (11 lines total)]
-1:
-2:from flask import Flask
-3:app = Flask(__name__)
-4:
-5:@app.route('/')
-6:def index():
-7:    numbers = list(range(1, 11))
-8:    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
-9:
-10:if __name__ == '__main__':
-11:    app.run(port=5000)
-File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.
+[File: /workspace/app.py (10 lines total after edit)]
+1|from flask import Flask
+2|app = Flask(__name__)
+3|
+4|@app.route('/')
+5|def index():
+6|    numbers = list(range(1, 11))
+7|    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
+8|
+9|if __name__ == '__main__':
+10|    app.run(port=5000)
+[File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
 
 ASSISTANT:
-The file has been updated. Let me run the Python file again with the new changes:
+Running the updated file:
 <execute_bash>
 python3 app.py > server.log 2>&1 &
 </execute_bash>
@@ -238,14 +243,14 @@ Observation:
 [1] 126
 
 ASSISTANT:
-The server is running on port 5000 with PID 126. You can access the list of numbers in a table format by visiting http://127.0.0.1:5000. Free free to let me know if you have any further requests!
+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!
 
 --- END OF EXAMPLE ---
 """
 
 INVALID_INPUT_MESSAGE = (
     "I don't understand your input. \n"
-    'If you want to execute a bash command, please use <execute_bash> YOUR_COMMAND_HERE </execute_bash>.\n'
-    'If you want to execute a block of Python code, please use <execute_ipython> YOUR_COMMAND_HERE </execute_ipython>.\n'
-    'If you want to browse the Internet, please use <execute_browse> YOUR_COMMAND_HERE </execute_browse>.\n'
+    '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_swe_agent/README.md

@@ -0,0 +1,7 @@
+# CodeAct (SWE Edit Specialized)
+
+This agent is an adaptation of the original [SWE Agent](https://swe-agent.com/) based on CodeAct using the `agentskills` library of OpenDevin.
+
+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

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

agenthub/codeact_swe_agent/action_parser.py

@@ -0,0 +1,114 @@
+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

@@ -0,0 +1,191 @@
+from agenthub.codeact_swe_agent.prompt import (
+    COMMAND_DOCS,
+    MINIMAL_SYSTEM_PREFIX,
+    SWE_EXAMPLE,
+    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.llm.llm import LLM
+from opendevin.runtime.plugins import (
+    AgentSkillsRequirement,
+    JupyterRequirement,
+    PluginRequirement,
+)
+from opendevin.runtime.tools import RuntimeTool
+
+
+def action_to_str(action: Action) -> str:
+    if isinstance(action, CmdRunAction):
+        return f'{action.thought}\n<execute_bash>\n{action.command}\n</execute_bash>'
+    elif isinstance(action, IPythonRunCellAction):
+        return f'{action.thought}\n<execute_ipython>\n{action.code}\n</execute_ipython>'
+    elif isinstance(action, MessageAction):
+        return action.content
+    return ''
+
+
+def get_action_message(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': action_to_str(action),
+        }
+    return None
+
+
+def get_observation_message(obs) -> dict[str, str] | None:
+    if isinstance(obs, CmdOutputObservation):
+        content = 'OBSERVATION:\n' + truncate_observation(obs.content)
+        content += (
+            f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]'
+        )
+        return {'role': 'user', 'content': content}
+    elif isinstance(obs, IPythonRunCellObservation):
+        content = 'OBSERVATION:\n' + obs.content
+        # replace base64 images with a placeholder
+        splitted = content.split('\n')
+        for i, line in enumerate(splitted):
+            if '![image](data:image/png;base64,' in line:
+                splitted[i] = (
+                    '![image](data:image/png;base64, ...) already displayed to user'
+                )
+        content = '\n'.join(splitted)
+        content = truncate_observation(content)
+        return {'role': 'user', 'content': content}
+    return None
+
+
+def truncate_observation(observation: str, max_chars: int = 10_000) -> str:
+    """
+    Truncate the middle of the observation if it is too long.
+    """
+    if len(observation) <= max_chars:
+        return observation
+    half = max_chars // 2
+    return (
+        observation[:half]
+        + '\n[... Observation truncated due to length ...]\n'
+        + observation[-half:]
+    )
+
+
+def get_system_message() -> str:
+    return f'{MINIMAL_SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
+
+
+def get_in_context_example() -> str:
+    return SWE_EXAMPLE
+
+
+class CodeActSWEAgent(Agent):
+    VERSION = '1.5'
+    """
+    This agent is an adaptation of the original [SWE Agent](https://swe-agent.com/) based on CodeAct 1.5 using the `agentskills` library of OpenDevin.
+
+    It is intended use is **solving Github issues**.
+
+    It removes web-browsing and Github capability from the original CodeAct agent to avoid confusion to the agent.
+    """
+
+    sandbox_plugins: list[PluginRequirement] = [
+        # NOTE: AgentSkillsRequirement need to go before JupyterRequirement, since
+        # AgentSkillsRequirement provides a lot of Python functions
+        # and it need to be initialized before Jupyter for Jupyter to use those functions.
+        AgentSkillsRequirement(),
+        JupyterRequirement(),
+    ]
+    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 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
+        """
+        messages: list[dict[str, str]] = [
+            {'role': 'system', 'content': self.system_message},
+            {'role': 'user', 'content': self.in_context_example},
+        ]
+
+        for prev_action, obs in state.history:
+            action_message = get_action_message(prev_action)
+            if action_message:
+                messages.append(action_message)
+
+            obs_message = get_observation_message(obs)
+            if obs_message:
+                messages.append(obs_message)
+
+        latest_user_message = [m for m in messages if m['role'] == 'user'][-1]
+        if latest_user_message:
+            if latest_user_message['content'].strip() == '/exit':
+                return AgentFinishAction()
+            latest_user_message['content'] += (
+                f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task.'
+            )
+
+        response = self.llm.completion(
+            messages=messages,
+            stop=[
+                '</execute_ipython>',
+                '</execute_bash>',
+            ],
+            temperature=0.0,
+        )
+        state.num_of_chars += sum(
+            len(message['content']) for message in messages
+        ) + len(response.choices[0].message.content)
+
+        return self.response_parser.parse(response)
+
+    def search_memory(self, query: str) -> list[str]:
+        raise NotImplementedError('Implement this abstract method')

agenthub/codeact_swe_agent/prompt.py

@@ -0,0 +1,451 @@
+from opendevin.runtime.plugins import AgentSkillsRequirement
+
+_AGENT_SKILLS_DOCS = AgentSkillsRequirement.documentation
+
+COMMAND_DOCS = (
+    '\nApart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:\n'
+    f'{_AGENT_SKILLS_DOCS}'
+    "Please note that THE `edit_file` FUNCTION REQUIRES PROPER INDENTATION. If the assistant would like to add the line '        print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run."
+)
+
+# ======= SYSTEM MESSAGE =======
+MINIMAL_SYSTEM_PREFIX = """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
+The assistant can interact with an interactive Python (Jupyter Notebook) environment and receive the corresponding output when needed. The code should be enclosed using "<execute_ipython>" tag, for example:
+<execute_ipython>
+print("Hello World!")
+</execute_ipython>
+The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
+For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
+"""
+
+SYSTEM_SUFFIX = """The assistant's response should be concise.
+The assistant should include ONLY ONE <execute_ipython> or <execute_bash> 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

@@ -0,0 +1,46 @@
+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
+        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
+        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/agent.py

@@ -6,9 +6,9 @@ from opendevin.llm.llm import LLM
 
 
 class DelegatorAgent(Agent):
+    VERSION = '1.0'
     """
-    The planner agent utilizes a special prompting strategy to create long term plans for solving problems.
-    The agent is given its previous action-observation pairs, current task, and hint based on last action taken at every step.
+    The Delegator Agent is responsible for delegating tasks to other agents based on the current task.
     """
 
     current_delegate: str = ''
@@ -25,14 +25,14 @@ class DelegatorAgent(Agent):
     def step(self, state: State) -> Action:
         """
         Checks to see if current step is completed, returns AgentFinishAction if True.
-        Otherwise, creates a plan prompt and sends to model for inference, returning the result as the next action.
+        Otherwise, delegates the task to the next agent in the pipeline.
 
         Parameters:
         - state (State): The current state given the previous actions and observations
 
         Returns:
         - AgentFinishAction: If the last state was 'completed', 'verified', or 'abandoned'
-        - Action: The next action to take based on llm response
+        - AgentDelegateAction: The next agent to delegate the task to
         """
         if self.current_delegate == '':
             self.current_delegate = 'study'

agenthub/dummy_agent/agent.py

@@ -9,6 +9,7 @@ from opendevin.events.action import (
     AgentFinishAction,
     AgentRecallAction,
     AgentRejectAction,
+    BrowseInteractiveAction,
     BrowseURLAction,
     CmdRunAction,
     FileReadAction,
@@ -30,7 +31,6 @@ from opendevin.llm.llm import LLM
 """
 FIXME: There are a few problems this surfaced
 * FileWrites seem to add an unintended newline at the end of the file
-* command_id is sometimes a number, sometimes a string
 * Why isn't the output of the background command split between two steps?
 * Browser not working
 """
@@ -43,6 +43,7 @@ BACKGROUND_CMD = 'echo "This is in the background" && sleep .1 && echo "This too
 
 
 class DummyAgent(Agent):
+    VERSION = '1.0'
     """
     The DummyAgent is used for e2e testing. It just sends the same set of actions deterministically,
     without making any LLM calls.
@@ -98,12 +99,12 @@ class DummyAgent(Agent):
                 'observations': [
                     CmdOutputObservation(
                         'Background command started. To stop it, send a `kill` action with command_id 42',
-                        command_id='42',  # type: ignore[arg-type]
+                        command_id=42,
                         command=BACKGROUND_CMD,
                     ),
                     CmdOutputObservation(
                         'This is in the background\nThis too\n',
-                        command_id='42',  # type: ignore[arg-type]
+                        command_id=42,
                         command=BACKGROUND_CMD,
                     ),
                 ],
@@ -112,7 +113,7 @@ class DummyAgent(Agent):
                 'action': AgentRecallAction(query='who am I?'),
                 'observations': [
                     AgentRecallObservation('', memories=['I am a computer.']),
-                    # CmdOutputObservation('This too\n', command_id='42', command=BACKGROUND_CMD),
+                    # CmdOutputObservation('This too\n', command_id=42, command=BACKGROUND_CMD),
                 ],
             },
             {
@@ -121,6 +122,14 @@ class DummyAgent(Agent):
                     # BrowserOutputObservation('<html></html>', url='https://google.com', screenshot=""),
                 ],
             },
+            {
+                'action': BrowseInteractiveAction(
+                    browser_actions='goto("https://google.com")'
+                ),
+                'observations': [
+                    # BrowserOutputObservation('<html></html>', url='https://google.com', screenshot=""),
+                ],
+            },
             {
                 'action': AgentFinishAction(),
                 'observations': [],

agenthub/micro/README.md

@@ -12,3 +12,6 @@ in the following structure:
 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/finish.md

@@ -1,2 +1,2 @@
-* `finish` - if you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working. Arguments:
+* `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/reject.md

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

agenthub/micro/agent.py

@@ -35,11 +35,14 @@ def history_to_json(obj, **kwargs):
         # process history, make it simpler.
         processed_history = []
         for action, observation in obj:
-            processed_history.append((event_to_memory(action), event_to_memory(observation)))
+            processed_history.append(
+                (event_to_memory(action), event_to_memory(observation))
+            )
         return json.dumps(processed_history, **kwargs)
 
 
 class MicroAgent(Agent):
+    VERSION = '1.0'
     prompt = ''
     agent_definition: dict = {}
 
@@ -52,14 +55,13 @@ class MicroAgent(Agent):
         del self.delegates[self.agent_definition['name']]
 
     def step(self, state: State) -> Action:
-        latest_user_message = state.get_current_user_intent()
         prompt = self.prompt_template.render(
             state=state,
             instructions=instructions,
             to_json=to_json,
             history_to_json=history_to_json,
             delegates=self.delegates,
-            latest_user_message=latest_user_message,
+            latest_user_message=state.get_current_user_intent(),
         )
         messages = [{'content': prompt, 'role': 'user'}]
         resp = self.llm.completion(messages=messages)

agenthub/micro/coder/agent.yaml

@@ -2,5 +2,5 @@ name: CoderAgent
 description: Given a particular task, and a detailed description of the codebase, accomplishes the task
 inputs:
   task: string
-  codebase_summary: string
+  summary: string
 outputs: {}

agenthub/micro/coder/prompt.md

@@ -2,7 +2,7 @@
 You are a software engineer. You've inherited an existing codebase, which you
 need to modify to complete this task:
 
-{{ latest_user_message }}
+{{ state.inputs.task }}
 
 {% if state.inputs.summary %}
 Here's a summary of the codebase, as it relates to this task:

agenthub/micro/commit_writer/agent.yaml

@@ -3,3 +3,4 @@ description: "Write a git commit message for files in the git staging area"
 inputs: {}
 outputs:
   answer: string
+  reason: string

agenthub/micro/commit_writer/prompt.md

@@ -11,10 +11,12 @@ changes. The commit message should include:
 - A summary line that clearly states the purpose of the changes.
 - Optionally, a detailed description if the changes are complex or need further explanation.
 
-You should find the diff using `git diff --cached`, compile a commit message,
-and call the `finish` action with `outputs.answer` set to the answer. If current
-repo is not a valid git repo, or there is no diff in the staging area, please call
-the `reject` action with `outputs.answer` set to the reason.
+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 }}

agenthub/micro/manager/agent.yaml

@@ -3,4 +3,6 @@ description: Delegates tasks to microagents based on their area of expertise
 generates: Action
 inputs:
   task: string
-outputs: {}
+outputs:
+  summary: string # if finished
+  reason: string # if rejected

agenthub/micro/manager/prompt.md

@@ -7,6 +7,16 @@ 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 }}
@@ -19,9 +29,13 @@ provide the correct inputs for the delegate you select.
 {{ instructions.history_truncated }}
 {{ history_to_json(state.history[-10:]) }}
 
+If the last item in the history is an error, you should try to fix it. 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

@@ -1,7 +1,7 @@
 # Task
 You are a brilliant mathematician and programmer. You've been given the following problem to solve:
 
-{{ latest_user_message }}
+`{{ 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.

agenthub/micro/postgres_agent/prompt.md

@@ -2,7 +2,7 @@
 You are a database engineer. You are working on an existing Postgres project, and have been given
 the following task:
 
-{{ latest_user_message }}
+{{ state.inputs.task }}
 
 You must:
 * Investigate the existing migrations to understand the current schema

agenthub/micro/registry.py

@@ -4,7 +4,10 @@ import yaml
 
 all_microagents = {}
 
-for dir in os.listdir(os.path.dirname(__file__)):
+# Get the list of directories and sort them to preserve determinism
+dirs = sorted(os.listdir(os.path.dirname(__file__)))
+
+for dir in dirs:
     base = os.path.dirname(__file__) + '/' + dir
     if os.path.isfile(base):
         continue
@@ -13,8 +16,7 @@ for dir in os.listdir(os.path.dirname(__file__)):
     promptFile = base + '/prompt.md'
     agentFile = base + '/agent.yaml'
     if not os.path.isfile(promptFile) or not os.path.isfile(agentFile):
-        raise Exception(
-            f'Missing prompt or agent file in {base}. Please create them.')
+        raise Exception(f'Missing prompt or agent file in {base}. Please create them.')
     with open(promptFile, 'r') as f:
         prompt = f.read()
     with open(agentFile, 'r') as f:

agenthub/micro/study_repo_for_task/prompt.md

@@ -1,9 +1,11 @@
 # Task
-You are a software engineer. You've inherited an existing codebase, which you're
-learning about for the first time. You need to study the codebase to find all
-the information needed to complete this task:
+You are a software architect. Your team has inherited an existing codebase, and
+need to finish a project:
 
-{{ latest_user_message }}
+{{ 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 }}
@@ -11,11 +13,14 @@ the information needed to complete this task:
 {{ instructions.actions.message }}
 {{ instructions.actions.finish }}
 
-You must ONLY `run` commands that have no side-effects, like `ls` and `grep`.
+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 task, including particular files, functions, and classes.
+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 }}
@@ -23,3 +28,36 @@ When you're done, put your summary in `outputs.summary` in the `finish` action.
 
 ## 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",
+    "background": false
+  }
+}
+
+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/agent.yaml

@@ -1,5 +1,6 @@
 name: TypoFixerAgent
 description: Fixes typos in files in the current working directory
-inputs: {}
+inputs:
+  task: string
 outputs:
   summary: string

agenthub/micro/typo_fixer_agent/prompt.md

@@ -1,5 +1,13 @@
 # Task
-You are a proofreader tasked with fixing typos in the files in your current working directory. Your goal is to:
+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
@@ -13,10 +21,10 @@ You are a proofreader tasked with fixing typos in the files in your current work
 
 To complete this task:
 1. Use the `read` action to read the contents of the files in your current working directory. Make sure to provide the file path in the format `'./file_name.ext'`.
-2. Use the `think` action to analyze the contents and identify typos.
+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 `think` action to generate a summary of the typos fixed, including the original and fixed versions of each typo, and the file(s) they were found in.
+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.

agenthub/micro/verifier/prompt.md

@@ -2,9 +2,10 @@
 You are a quality assurance engineer. Another engineer has made changes to the
 codebase which are supposed to solve this task:
 
-{{ latest_user_message }}
+{{ state.inputs.task }}
 
-Your goal is to verify that the changes are correct and bug-free.
+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 }}

agenthub/monologue_agent/agent.py

@@ -1,4 +1,6 @@
 import agenthub.monologue_agent.utils.prompts as prompts
+from agenthub.monologue_agent.response_parser import MonologueResponseParser
+from agenthub.monologue_agent.utils.prompts import INITIAL_THOUGHTS
 from opendevin.controller.agent import Agent
 from opendevin.controller.state.state import State
 from opendevin.core.config import config
@@ -25,7 +27,7 @@ from opendevin.events.observation import (
 from opendevin.events.serialization.event import event_to_memory
 from opendevin.llm.llm import LLM
 from opendevin.memory.condenser import MemoryCondenser
-from opendevin.memory.history import ShortTermHistory
+from opendevin.runtime.tools import RuntimeTool
 
 if config.agent.memory_enabled:
     from opendevin.memory.memory import LongTermMemory
@@ -33,53 +35,9 @@ if config.agent.memory_enabled:
 MAX_TOKEN_COUNT_PADDING = 512
 MAX_OUTPUT_LENGTH = 5000
 
-INITIAL_THOUGHTS = [
-    'I exist!',
-    'Hmm...looks like I can type in a command line prompt',
-    'Looks like I have a web browser too!',
-    "Here's what I want to do: $TASK",
-    'How am I going to get there though?',
-    'It seems like I have some kind of short term memory.',
-    'Each of my thoughts seems to be stored in a JSON array.',
-    'It seems whatever I say next will be added as an object to the list.',
-    'But no one has perfect short-term memory. My list of thoughts will be summarized and condensed over time, losing information in the process.',
-    'Fortunately I have long term memory!',
-    'I can just perform a recall action, followed by the thing I want to remember. And then related thoughts just spill out!',
-    "Sometimes they're random thoughts that don't really have to do with what I wanted to remember. But usually they're exactly what I need!",
-    "Let's try it out!",
-    'RECALL what it is I want to do',
-    "Here's what I want to do: $TASK",
-    'How am I going to get there though?',
-    "Neat! And it looks like it's easy for me to use the command line too! I just have to perform a run action and include the command I want to run in the command argument. The command output just jumps into my head!",
-    'RUN echo "hello world"',
-    'hello world',
-    'Cool! I bet I can write files too using the write action.',
-    'WRITE echo "console.log(\'hello world\')" > test.js',
-    '',
-    "I just created test.js. I'll try and run it now.",
-    'RUN node test.js',
-    'hello world',
-    'It works!',
-    "I'm going to try reading it now using the read action.",
-    'READ test.js',
-    "console.log('hello world')",
-    'Nice! I can read files too!',
-    'And if I want to use the browser, I just need to use the browse action and include the url I want to visit in the url argument',
-    "Let's try that...",
-    'BROWSE google.com',
-    '<form><input type="text"></input><button type="submit"></button></form>',
-    'I can browse the web too!',
-    'And once I have completed my task, I can use the finish action to stop working.',
-    "But I should only use the finish action when I'm absolutely certain that I've completed my task and have tested my work.",
-    'Very cool. Now to accomplish my task.',
-    "I'll need a strategy. And as I make progress, I'll need to keep refining that strategy. I'll need to set goals, and break them into sub-goals.",
-    'In between actions, I must always take some time to think, strategize, and set new goals. I should never take two actions in a row.',
-    "OK so my task is to $TASK. I haven't made any progress yet. Where should I start?",
-    'It seems like there might be an existing project here. I should probably start by running `pwd` and `ls` to orient myself.',
-]
-
 
 class MonologueAgent(Agent):
+    VERSION = '1.0'
     """
     The Monologue Agent utilizes long and short term memory to complete tasks.
     Long term memory is stored as a LongTermMemory object and the model uses it to search for examples from the past.
@@ -87,57 +45,21 @@ class MonologueAgent(Agent):
     """
 
     _initialized = False
-    monologue: ShortTermHistory
+    initial_thoughts: list[dict[str, str]]
     memory: 'LongTermMemory | None'
     memory_condenser: MemoryCondenser
+    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
+    response_parser = MonologueResponseParser()
 
     def __init__(self, llm: LLM):
         """
-        Initializes the Monologue Agent with an llm, monologue, and memory.
+        Initializes the Monologue Agent with an llm.
 
         Parameters:
         - llm (LLM): The llm to be used by this agent
         """
         super().__init__(llm)
 
-    def _add_event(self, event_dict: dict):
-        """
-        Adds a new event to the agent's monologue and memory.
-        Monologue automatically condenses when it gets too large.
-
-        Parameters:
-        - event (dict): The event that will be added to monologue and memory
-        """
-
-        if (
-            'args' in event_dict
-            and 'output' in event_dict['args']
-            and len(event_dict['args']['output']) > MAX_OUTPUT_LENGTH
-        ):
-            event_dict['args']['output'] = (
-                event_dict['args']['output'][:MAX_OUTPUT_LENGTH] + '...'
-            )
-
-        self.monologue.add_event(event_dict)
-        if self.memory is not None:
-            self.memory.add_event(event_dict)
-
-        # Test monologue token length
-        prompt = prompts.get_request_action_prompt(
-            '',
-            self.monologue.get_events(),
-            [],
-        )
-        messages = [{'content': prompt, 'role': 'user'}]
-        token_count = self.llm.get_token_count(messages)
-
-        if token_count + MAX_TOKEN_COUNT_PADDING > self.llm.max_input_tokens:
-            prompt = prompts.get_summarize_monologue_prompt(self.monologue.events)
-            summary_response = self.memory_condenser.condense(
-                summarize_prompt=prompt, llm=self.llm
-            )
-            self.monologue.events = prompts.parse_summary_response(summary_response)
-
     def _initialize(self, task: str):
         """
         Utilizes the INITIAL_THOUGHTS list to give the agent a context for its capabilities
@@ -158,7 +80,7 @@ class MonologueAgent(Agent):
         if task is None or task == '':
             raise AgentNoInstructionError()
 
-        self.monologue = ShortTermHistory()
+        self.initial_thoughts = []
         if config.agent.memory_enabled:
             self.memory = LongTermMemory()
         else:
@@ -187,7 +109,7 @@ class MonologueAgent(Agent):
                     observation = BrowserOutputObservation(
                         content=thought, url='', screenshot=''
                     )
-                self._add_event(event_to_memory(observation))
+                self.initial_thoughts.append(event_to_memory(observation))
                 previous_action = ''
             else:
                 action: Action = NullAction()
@@ -214,7 +136,7 @@ class MonologueAgent(Agent):
                     previous_action = ActionType.BROWSE
                 else:
                     action = MessageAction(thought)
-                self._add_event(event_to_memory(action))
+                self.initial_thoughts.append(event_to_memory(action))
 
     def step(self, state: State) -> Action:
         """
@@ -229,25 +151,74 @@ class MonologueAgent(Agent):
 
         goal = state.get_current_user_intent()
         self._initialize(goal)
-        for prev_action, obs in state.updated_info:
-            self._add_event(event_to_memory(prev_action))
-            self._add_event(event_to_memory(obs))
 
-        state.updated_info = []
+        recent_events: list[dict[str, str]] = []
 
+        # add the events from state.history
+        for prev_action, obs in state.history:
+            if not isinstance(prev_action, NullAction):
+                recent_events.append(event_to_memory(prev_action))
+            if not isinstance(obs, NullObservation):
+                recent_events.append(self._truncate_output(event_to_memory(obs)))
+
+        # add the last messages to long term memory
+        if self.memory is not None and state.history and len(state.history) > 0:
+            self.memory.add_event(event_to_memory(state.history[-1][0]))
+            self.memory.add_event(
+                self._truncate_output(event_to_memory(state.history[-1][1]))
+            )
+
+        # the action prompt with initial thoughts and recent events
         prompt = prompts.get_request_action_prompt(
             goal,
-            self.monologue.get_events(),
+            self.initial_thoughts,
+            recent_events,
             state.background_commands_obs,
         )
-        messages = [{'content': prompt, 'role': 'user'}]
+
+        messages: list[dict[str, str]] = [
+            {'role': 'user', 'content': prompt},
+        ]
+
+        # format all as a single message, a monologue
         resp = self.llm.completion(messages=messages)
-        action_resp = resp['choices'][0]['message']['content']
-        state.num_of_chars += len(prompt) + len(action_resp)
-        action = prompts.parse_action_response(action_resp)
+
+        # keep track of max_chars fallback option
+        state.num_of_chars += len(prompt) + len(
+            resp['choices'][0]['message']['content']
+        )
+
+        action = self.response_parser.parse(resp)
         self.latest_action = action
         return action
 
+    def _truncate_output(
+        self, observation: dict, max_chars: int = MAX_OUTPUT_LENGTH
+    ) -> dict[str, str]:
+        """
+        Truncates the output of an observation to a maximum number of characters.
+
+        Parameters:
+        - output (str): The observation whose output to truncate
+        - max_chars (int): The maximum number of characters to allow
+
+        Returns:
+        - str: The truncated output
+        """
+        if (
+            'args' in observation
+            and 'output' in observation['args']
+            and len(observation['args']['output']) > max_chars
+        ):
+            output = observation['args']['output']
+            half = max_chars // 2
+            observation['args']['output'] = (
+                output[:half]
+                + '\n[... Output truncated due to length...]\n'
+                + output[-half:]
+            )
+        return observation
+
     def search_memory(self, query: str) -> list[str]:
         """
         Uses VectorIndexRetriever to find related memories within the long term memory.

agenthub/monologue_agent/response_parser.py

@@ -0,0 +1,40 @@
+from opendevin.controller.action_parser import ResponseParser
+from opendevin.core.utils import json
+from opendevin.events.action import (
+    Action,
+)
+from opendevin.events.serialization.action import action_from_dict
+
+
+class MonologueResponseParser(ResponseParser):
+    def __init__(
+        self,
+    ):
+        pass
+
+    def parse(self, response: str) -> Action:
+        action_str = self.parse_response(response)
+        return self.parse_action(action_str)
+
+    def parse_response(self, response) -> str:
+        # get the next action from the response
+        return response['choices'][0]['message']['content']
+
+    def parse_action(self, action_str: str) -> Action:
+        """
+        Parses a string to find an action within it
+
+        Parameters:
+        - response (str): The string to be parsed
+
+        Returns:
+        - Action: The action that was found in the response string
+        """
+        # attempt to load the JSON dict from the response
+        action_dict = json.loads(action_str)
+
+        if 'content' in action_dict:
+            # The LLM gets confused here. Might as well be robust
+            action_dict['contents'] = action_dict.pop('content')
+
+        return action_from_dict(action_dict)

agenthub/monologue_agent/utils/prompts.py

@@ -1,13 +1,13 @@
 from opendevin.core.config import config
 from opendevin.core.utils import json
-from opendevin.events.action import (
-    Action,
-)
 from opendevin.events.observation import (
     CmdOutputObservation,
 )
-from opendevin.events.serialization.action import action_from_dict
+from opendevin.events.action import (
+    Action,
+)
 
+from opendevin.events.serialization.action import action_from_dict
 ACTION_PROMPT = """
 You're a thoughtful robot. Your main task is this:
 %(task)s
@@ -18,7 +18,6 @@ This is your internal monologue, in JSON format:
 
 %(monologue)s
 
-
 Your most recent thought is at the bottom of that monologue. Continue your train of thought.
 What is your next single thought or action? Your response must be in JSON format.
 It must be a single object, and it must contain two fields:
@@ -51,7 +50,7 @@ Here are the possible actions:
 
 %(background_commands)s
 
-You MUST take time to think in between read, write, run, browse, push, and recall actions--do this with the `message` action.
+You MUST take time to think in between read, write, run, kill, browse, push, and recall actions--do this with the `message` action.
 You should never act twice in a row without thinking. But if your last several
 actions are all `message` actions, you should consider taking a different action.
 
@@ -92,6 +91,51 @@ The action key may be `summarize`, and `args.summary` should contain the summary
 You can also use the same action and args from the source monologue.
 """
 
+INITIAL_THOUGHTS = [
+    'I exist!',
+    'Hmm...looks like I can type in a command line prompt',
+    'Looks like I have a web browser too!',
+    "Here's what I want to do: $TASK",
+    'How am I going to get there though?',
+    'It seems like I have some kind of short term memory.',
+    'Each of my thoughts seems to be stored in a JSON array.',
+    'It seems whatever I say next will be added as an object to the list.',
+    'But no one has perfect short-term memory. My list of thoughts will be summarized and condensed over time, losing information in the process.',
+    'Fortunately I have long term memory!',
+    'I can just perform a recall action, followed by the thing I want to remember. And then related thoughts just spill out!',
+    "Sometimes they're random thoughts that don't really have to do with what I wanted to remember. But usually they're exactly what I need!",
+    "Let's try it out!",
+    'RECALL what it is I want to do',
+    "Here's what I want to do: $TASK",
+    'How am I going to get there though?',
+    "Neat! And it looks like it's easy for me to use the command line too! I just have to perform a run action and include the command I want to run in the command argument. The command output just jumps into my head!",
+    'RUN echo "hello world"',
+    'hello world',
+    'Cool! I bet I can write files too using the write action.',
+    'WRITE echo "console.log(\'hello world\')" > test.js',
+    '',
+    "I just created test.js. I'll try and run it now.",
+    'RUN node test.js',
+    'hello world',
+    'It works!',
+    "I'm going to try reading it now using the read action.",
+    'READ test.js',
+    "console.log('hello world')",
+    'Nice! I can read files too!',
+    'And if I want to use the browser, I just need to use the browse action and include the url I want to visit in the url argument',
+    "Let's try that...",
+    'BROWSE google.com',
+    '<form><input type="text"></input><button type="submit"></button></form>',
+    'I can browse the web too!',
+    'And once I have completed my task, I can use the finish action to stop working.',
+    "But I should only use the finish action when I'm absolutely certain that I've completed my task and have tested my work.",
+    'Very cool. Now to accomplish my task.',
+    "I'll need a strategy. And as I make progress, I'll need to keep refining that strategy. I'll need to set goals, and break them into sub-goals.",
+    'In between actions, I must always take some time to think, strategize, and set new goals. I should never take two actions in a row.',
+    "OK so my task is to $TASK. I haven't made any progress yet. Where should I start?",
+    'It seems like there might be an existing project here. I should probably start by running `pwd` and `ls` to orient myself.',
+]
+
 
 def get_summarize_monologue_prompt(thoughts: list[dict]):
     """
@@ -108,7 +152,8 @@ def get_summarize_monologue_prompt(thoughts: list[dict]):
 def get_request_action_prompt(
     task: str,
     thoughts: list[dict],
-    background_commands_obs: list[CmdOutputObservation] = [],
+    recent_events: list[dict],
+    background_commands_obs: list[CmdOutputObservation] | None = None,
 ):
     """
     Gets the action prompt formatted with appropriate values.
@@ -119,20 +164,28 @@ def get_request_action_prompt(
     - background_commands_obs (list[CmdOutputObservation]): list of all observed background commands running
 
     Returns:
-    - str: Formatted prompt string with hint, task, monologue, and background included
+    - str: Formatted prompt string with hint, task, monologue, and background commands included
     """
 
+    if background_commands_obs is None:
+        background_commands_obs = []
+
     hint = ''
-    if len(thoughts) > 0:
-        latest_thought = thoughts[-1]
-        if 'action' in latest_thought:
-            if latest_thought['action'] == 'message':
-                if latest_thought['args']['content'].startswith('OK so my task is'):
-                    hint = "You're just getting started! What should you do first?"
-                else:
-                    hint = "You've been thinking a lot lately. Maybe it's time to take action?"
-            elif latest_thought['action'] == 'error':
+    if len(recent_events) > 0:
+        latest_event = recent_events[-1]
+        if 'action' in latest_event:
+            if (
+                latest_event['action'] == 'message'
+                and 'source' in latest_event
+                and latest_event['source'] == 'agent'
+            ):
+                hint = (
+                    "You've been thinking a lot lately. Maybe it's time to take action?"
+                )
+            elif latest_event['action'] == 'error':
                 hint = 'Looks like that last command failed. Maybe you need to fix it, or try something else.'
+    else:
+        hint = "You're just getting started! What should you do first?"
 
     bg_commands_message = ''
     if len(background_commands_obs) > 0:
@@ -145,9 +198,11 @@ def get_request_action_prompt(
 
     user = 'opendevin' if config.run_as_devin else 'root'
 
+    monologue = thoughts + recent_events
+
     return ACTION_PROMPT % {
         'task': task,
-        'monologue': json.dumps(thoughts, indent=2),
+        'monologue': json.dumps(monologue, indent=2),
         'background_commands': bg_commands_message,
         'hint': hint,
         'user': user,
@@ -187,4 +242,4 @@ def parse_summary_response(response: str) -> list[dict]:
     - list[dict]: The list of summaries output by the model
     """
     parsed = json.loads(response)
-    return parsed['new_monologue']
+    return parsed['new_monologue']

agenthub/planner_agent/agent.py

@@ -1,16 +1,21 @@
+from agenthub.monologue_agent.response_parser import MonologueResponseParser
 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, parse_response
+from .prompt import get_prompt
 
 
 class PlannerAgent(Agent):
+    VERSION = '1.0'
     """
     The planner agent utilizes a special prompting strategy to create long term plans for solving problems.
     The agent is given its previous action-observation pairs, current task, and hint based on last action taken at every step.
     """
+    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
+    response_parser = MonologueResponseParser()
 
     def __init__(self, llm: LLM):
         """
@@ -43,10 +48,10 @@ class PlannerAgent(Agent):
         prompt = get_prompt(state)
         messages = [{'content': prompt, 'role': 'user'}]
         resp = self.llm.completion(messages=messages)
-        action_resp = resp['choices'][0]['message']['content']
-        state.num_of_chars += len(prompt) + len(action_resp)
-        action = parse_response(action_resp)
-        return action
+        state.num_of_chars += len(prompt) + len(
+            resp['choices'][0]['message']['content']
+        )
+        return self.response_parser.parse(resp)
 
     def search_memory(self, query: str) -> list[str]:
         return []

agenthub/planner_agent/prompt.py

@@ -94,7 +94,7 @@ It must be an object, and it must contain two fields:
   * `state` - set to 'in_progress' to start the task, 'completed' to finish it, 'verified' to assert that it was successful, 'abandoned' to give up on it permanently, or `open` to stop working on it for now.
 * `finish` - if ALL of your tasks and subtasks have been verified or abandoned, and you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.
 
-You MUST take time to think in between read, write, run, browse, and recall actions--do this with the `message` action.
+You MUST take time to think in between read, write, run, kill, browse, and recall actions--do this with the `message` action.
 You should never act twice in a row without thinking. But if your last several
 actions are all `message` actions, you should consider taking a different action.
 
@@ -155,7 +155,7 @@ def get_prompt(state: State) -> str:
     else:
         plan_status = "You're not currently working on any tasks. Your next action MUST be to mark a task as in_progress."
     hint = get_hint(event_to_memory(latest_action).get('action', ''))
-    logger.info('HINT:\n' + hint, extra={'msg_type': 'INFO'})
+    logger.info('HINT:\n' + hint, extra={'msg_type': 'DETAIL'})
     task = state.get_current_user_intent()
     return prompt % {
         'task': task,
@@ -169,10 +169,8 @@ def get_prompt(state: State) -> str:
 def parse_response(response: str) -> Action:
     """
     Parses the model output to find a valid action to take
-
     Parameters:
     - response (str): A response from the model that potentially contains an Action.
-
     Returns:
     - Action: A valid next action to perform from model output
     """

containers/README.md

@@ -1,11 +1,12 @@
 # Docker Containers
+
 Each folder here contains a Dockerfile, and a config.sh describing how to build
-the image and where to push it. These are images are built and pushed in GitHub Actions
+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

@@ -10,7 +10,7 @@ RUN npm ci
 COPY ./frontend ./
 RUN npm run make-i18n && npm run build
 
-FROM python:3.12-slim as backend-builder
+FROM python:3.12.3-slim as backend-builder
 
 WORKDIR /app
 ENV PYTHONPATH '/app'
@@ -28,7 +28,7 @@ COPY ./pyproject.toml ./poetry.lock ./
 RUN touch README.md
 RUN poetry install --without evaluation --no-root && rm -rf $POETRY_CACHE_DIR
 
-FROM python:3.12-slim as runtime
+FROM python:3.12.3-slim as runtime
 
 WORKDIR /app
 
@@ -53,6 +53,7 @@ RUN useradd -l -m -u $OPENDEVIN_USER_ID -s /bin/bash 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 \

containers/app/entrypoint.sh

@@ -26,13 +26,17 @@ if [[ "$SANDBOX_USER_ID" -eq 0 ]]; then
   "$@"
 else
   echo "Setting up enduser with id $SANDBOX_USER_ID"
-  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 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 for a second time. Exiting."
-      exit 1
+      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
@@ -46,6 +50,7 @@ else
     groupadd -g $DOCKER_SOCKET_GID docker
   fi
 
+  mkdir -p /home/enduser/.cache/huggingface/hub/
   mkdir -p /home/enduser/.cache/ms-playwright/
   mv /home/opendevin/.cache/ms-playwright/ /home/enduser/.cache/
 

containers/build.sh

@@ -3,65 +3,67 @@ set -eo pipefail
 
 image_name=$1
 org_name=$2
-push=0
-if [[ $3 == "--push" ]]; then
-  push=1
-fi
+platform=$3
 
-echo -e "Building: $image_name"
+echo "Building: $image_name for platform: $platform"
 tags=()
 
 OPEN_DEVIN_BUILD_VERSION="dev"
 
-cache_tag_base="buildcache"
-cache_tag="$cache_tag_base"
-
 if [[ -n $GITHUB_REF_NAME ]]; then
   # check if ref name is a version number
   if [[ $GITHUB_REF_NAME =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
-    major_version=$(echo $GITHUB_REF_NAME | cut -d. -f1)
-    minor_version=$(echo $GITHUB_REF_NAME | cut -d. -f1,2)
-    tags+=($major_version $minor_version)
+    major_version=$(echo "$GITHUB_REF_NAME" | cut -d. -f1)
+    minor_version=$(echo "$GITHUB_REF_NAME" | cut -d. -f1,2)
+    tags+=("$major_version" "$minor_version")
   fi
-  sanitized=$(echo $GITHUB_REF_NAME | sed 's/[^a-zA-Z0-9.-]\+/-/g')
+  sanitized=$(echo "$GITHUB_REF_NAME" | sed 's/[^a-zA-Z0-9.-]\+/-/g')
   OPEN_DEVIN_BUILD_VERSION=$sanitized
-  cache_tag+="-${sanitized}"
-  tags+=($sanitized)
+  tag=$(echo "$sanitized" | tr '[:upper:]' '[:lower:]') # lower case is required in tagging
+  tags+=("$tag")
 fi
 echo "Tags: ${tags[@]}"
 
-dir=./containers/$image_name
-if [ ! -f $dir/Dockerfile ]; then
+if [[ "$image_name" == "opendevin" ]]; then
+  dir="./containers/app"
+else
+  dir="./containers/$image_name"
+fi
+
+if [[ ! -f "$dir/Dockerfile" ]]; then
   echo "No Dockerfile found"
   exit 1
 fi
-if [ ! -f $dir/config.sh ]; then
+if [[ ! -f "$dir/config.sh" ]]; then
   echo "No config.sh found for Dockerfile"
   exit 1
 fi
-source $dir/config.sh
+
+source "$dir/config.sh"
+
 if [[ -n "$org_name" ]]; then
   DOCKER_ORG="$org_name"
 fi
-DOCKER_REPOSITORY=$DOCKER_REGISTRY/$DOCKER_ORG/$DOCKER_IMAGE
+
+DOCKER_REPOSITORY="$DOCKER_REGISTRY/$DOCKER_ORG/$DOCKER_IMAGE"
 DOCKER_REPOSITORY=${DOCKER_REPOSITORY,,} # lowercase
 echo "Repo: $DOCKER_REPOSITORY"
 echo "Base dir: $DOCKER_BASE_DIR"
 
 args=""
-for tag in ${tags[@]}; do
+for tag in "${tags[@]}"; do
   args+=" -t $DOCKER_REPOSITORY:$tag"
 done
-if [[ $push -eq 1 ]]; then
-  args+=" --push"
-  args+=" --cache-to=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag,mode=max"
-fi
+
+output_image="/tmp/${image_name}_image_${platform}.tar"
 
 docker buildx build \
   $args \
-  --build-arg OPEN_DEVIN_BUILD_VERSION=$OPEN_DEVIN_BUILD_VERSION \
-  --cache-from=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag \
-  --cache-from=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag_base-main \
-  --platform linux/amd64,linux/arm64 \
+  --build-arg OPEN_DEVIN_BUILD_VERSION="$OPEN_DEVIN_BUILD_VERSION" \
+  --platform linux/$platform \
   --provenance=false \
-  -f $dir/Dockerfile $DOCKER_BASE_DIR
+  -f "$dir/Dockerfile" \
+  --output type=docker,dest="$output_image" \
+  "$DOCKER_BASE_DIR"
+
+echo "${tags[*]}" > tags.txt

containers/sandbox/Dockerfile

@@ -21,6 +21,8 @@ RUN apt-get update && apt-get install -y \
     jq \
     g++ \
     make \
+    iproute2 \
+    libgl1-mesa-glx \
     && rm -rf /var/lib/apt/lists/*
 
 RUN mkdir -p -m0755 /var/run/sshd
@@ -28,6 +30,16 @@ RUN mkdir -p -m0755 /var/run/sshd
 # symlink python3 to python
 RUN ln -s /usr/bin/python3 /usr/bin/python
 
-# install basic dependencies for CodeActAgent
-RUN pip3 install --upgrade pip
-RUN pip3 install jupyterlab notebook jupyter_kernel_gateway flake8
+# ==== OpenDevin Runtime Client ====
+RUN mkdir -p /opendevin && mkdir -p /opendevin/logs && chmod 777 /opendevin/logs
+RUN wget "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"
+RUN bash Miniforge3-$(uname)-$(uname -m).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 "export PATH=/opendevin/miniforge3/bin:$PATH" >> ~/.bashrc
+RUN echo "export PATH=/opendevin/miniforge3/bin:$PATH" >> /opendevin/bash.bashrc
+
+# - 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 opencv-python

dev_config/python/ruff.toml

@@ -9,10 +9,17 @@ select = [
     "F",
     "I",
     "Q",
+    "B",
 ]
 
 ignore = [
     "E501",
+    "B003",
+    "B007",
+    "B009",
+    "B010",
+    "B904",
+    "B018",
 ]
 
 [lint.flake8-quotes]

docs/docusaurus.config.ts

@@ -8,8 +8,8 @@ const config: Config = {
   favicon: "img/logo.png",
 
   // Set the production url of your site here
-  url: "https://OpenDevin.github.io",
-  baseUrl: "/OpenDevin/",
+  url: "https://docs.all-hands.dev",
+  baseUrl: "/",
 
   // GitHub pages deployment config.
   organizationName: "OpenDevin",
@@ -23,8 +23,13 @@ const config: Config = {
   // useful metadata like html lang. For example, if your site is Chinese, you
   // may want to replace "en" with "zh-Hans".
   i18n: {
-    defaultLocale: "en",
-    locales: ["en"],
+    defaultLocale: 'en',
+    locales: ['en', 'fr', 'zh-Hans'],
+    localeConfigs: {
+      en: {
+        htmlLang: 'en-GB',
+      },
+    },
   },
 
   presets: [
@@ -51,7 +56,6 @@ const config: Config = {
       } satisfies Preset.Options,
     ],
   ],
-
   themeConfig: {
     image: "img/docusaurus.png",
     navbar: {
@@ -79,44 +83,11 @@ const config: Config = {
           label: "GitHub",
           position: "right",
         },
-      ],
-    },
-    footer: {
-      style: "dark",
-      links: [
         {
-          title: "OpenDevin",
-          items: [
-            {
-              label: "Docs",
-              to: "/modules/usage/intro",
-            },
-          ],
-        },
-        {
-          title: "Community",
-          items: [
-            {
-              label: "Slack",
-              href: "https://join.slack.com/t/opendevin/shared_invite/zt-2ggtwn3k5-PvAA2LUmqGHVZ~XzGq~ILw"
-            },
-            {
-              label: "Discord",
-              href: "https://discord.gg/ESHStjSjD4",
-            },
-          ],
-        },
-        {
-          title: "More",
-          items: [
-            {
-              label: "GitHub",
-              href: "https://github.com/OpenDevin/OpenDevin",
-            },
-          ],
+          type: 'localeDropdown',
+          position: 'left',
         },
       ],
-      copyright: `Copyright © ${new Date().getFullYear()} OpenDevin`,
     },
     prism: {
       theme: prismThemes.oneLight,

docs/i18n/fr/code.json

@@ -0,0 +1,406 @@
+{
+  "footer.title": {
+    "message": "OpenDevin"
+  },
+  "footer.docs": {
+    "message": "Docs"
+  },
+  "footer.community": {
+    "message": "Community"
+  },
+  "footer.copyright": {
+    "message": "Copyright © {year} OpenDevin"
+  },
+  "faq.title": {
+    "message": "Frequently Asked Questions",
+    "description": "FAQ Title"
+  },
+  "faq.description": {
+    "message": "Frequently Asked Questions"
+  },
+  "faq.section.title.1": {
+    "message": "What is OpenDevin?",
+    "description": "First Section Title"
+  },
+  "faq.section.highlight": {
+    "message": "OpenDevin",
+    "description": "Highlight Text"
+  },
+  "faq.section.description.1": {
+    "message": "is an autonomous software engineer that can solve software engineering and web-browsing tasks end-to-end. It can perform data science queries, such as \"Find the number of pull requests to the OpenDevin repository in the last month,\" and software engineering tasks, such as \"Please add tests to this file and verify that all the tests pass. If they don't fix the file.\"",
+    "description": "Description for OpenDevin"
+  },
+  "faq.section.description.2": {
+    "message": "At the same time, OpenDevin is a platform and community for agent developers to test out and evaluate new agents.",
+    "description": "Further Description for OpenDevin"
+  },
+  "faq.section.title.2": {
+    "message": "Support",
+    "description": "Support Section Title"
+  },
+  "faq.section.support.answer": {
+    "message": "Please file a bug on {githubLink} if you notice a problem that likely affects others. If you're having trouble installing, or have general questions, reach out on {discordLink} or {slackLink}.",
+    "description": "Support Answer"
+  },
+  "faq.section.title.3": {
+    "message": "How to fix a GitHub issue with OpenDevin?",
+    "description": "GitHub Issue Section Title"
+  },
+  "faq.section.github.steps.intro": {
+    "message": "To fix an issue on GitHub using OpenDevin, send a prompt to OpenDevin asking it to follow steps like the following:",
+    "description": "GitHub Steps Introduction"
+  },
+  "faq.section.github.step1": {
+    "message": "Read the issue https://github.com/OpenDevin/OpenDevin/issues/1611",
+    "description": "GitHub Step 1"
+  },
+  "faq.section.github.step2": {
+    "message": "Clone the repository and check out a new branch",
+    "description": "GitHub Step 2"
+  },
+  "faq.section.github.step3": {
+    "message": "Based on the instructions in the issue description, modify files to fix the issue",
+    "description": "GitHub Step 3"
+  },
+  "faq.section.github.step4": {
+    "message": "Push the resulting output to GitHub using the GITHUB_TOKEN environment variable",
+    "description": "GitHub Step 4"
+  },
+  "faq.section.github.step5": {
+    "message": "Tell me the link that I need to go to to send a pull request",
+    "description": "GitHub Step 5"
+  },
+  "faq.section.github.steps.preRun": {
+    "message": "Before you run OpenDevin, you can do:",
+    "description": "GitHub Steps Pre-Run"
+  },
+  "faq.section.github.steps.tokenInfo": {
+    "message": "where XXX is a GitHub token that you created that has permissions to push to the OpenDevin repo. If you don’t have write permission to the OpenDevin repo, you might need to change that to:",
+    "description": "GitHub Steps Token Info"
+  },
+  "faq.section.github.steps.usernameInfo": {
+    "message": "where USERNAME is your GitHub username.",
+    "description": "GitHub Steps Username Info"
+  },
+  "faq.section.title.4": {
+    "message": "How is OpenDevin different from Devin?",
+    "description": "Devin Section Title"
+  },
+  "faq.section.devin.linkText": {
+    "message": "Devin",
+    "description": "Devin Link Text"
+  },
+  "faq.section.devin.description": {
+    "message": "is a commercial product by Cognition Inc., that served as the initial inspiration for OpenDevin. They both aim to do a good job at solving software engineering tasks, but OpenDevin you can download, use, and modify, while Devin you can only use through the Cognition site. In addition, OpenDevin has evolved beyond the initial inspiration, and now serves as a community-driven ecosystem for agent development in general, and we'd love to have you join and",
+    "description": "Devin Description"
+  },
+  "faq.section.devin.contribute": {
+    "message": "contribute",
+    "description": "Contribute Link"
+  },
+  "faq.section.title.5": {
+    "message": "How is OpenDevin different from ChatGPT?",
+    "description": "ChatGPT Section Title"
+  },
+  "faq.section.chatgpt.description": {
+    "message": "ChatGPT you can access online, it does not interface with local files, and its ability to execute code is limited. So it can write code, but it is not easy to test or execute it.",
+    "description": "ChatGPT Description"
+  },
+  "homepage.description": {
+    "message": "AI-powered code generation for software engineering.",
+    "description": "The homepage description"
+  },
+  "homepage.getStarted": {
+    "message": "Get Started"
+  },
+  "welcome.message": {
+    "message": "Welcome to OpenDevin, an open-source autonomous AI software engineer that is capable of executing complex engineering tasks and collaborating actively with users on software development projects."
+  },
+  "theme.ErrorPageContent.title": {
+    "message": "Cette page a planté.",
+    "description": "The title of the fallback page when the page crashed"
+  },
+  "theme.BackToTopButton.buttonAriaLabel": {
+    "message": "Retour au début de la page",
+    "description": "The ARIA label for the back to top button"
+  },
+  "theme.blog.archive.title": {
+    "message": "Archive",
+    "description": "The page & hero title of the blog archive page"
+  },
+  "theme.blog.archive.description": {
+    "message": "Archive",
+    "description": "The page & hero description of the blog archive page"
+  },
+  "theme.blog.paginator.navAriaLabel": {
+    "message": "Pagination de la liste des articles du blog",
+    "description": "The ARIA label for the blog pagination"
+  },
+  "theme.blog.paginator.newerEntries": {
+    "message": "Nouvelles entrées",
+    "description": "The label used to navigate to the newer blog posts page (previous page)"
+  },
+  "theme.blog.paginator.olderEntries": {
+    "message": "Anciennes entrées",
+    "description": "The label used to navigate to the older blog posts page (next page)"
+  },
+  "theme.blog.post.paginator.navAriaLabel": {
+    "message": "Pagination des articles du blog",
+    "description": "The ARIA label for the blog posts pagination"
+  },
+  "theme.blog.post.paginator.newerPost": {
+    "message": "Article plus récent",
+    "description": "The blog post button label to navigate to the newer/previous post"
+  },
+  "theme.blog.post.paginator.olderPost": {
+    "message": "Article plus ancien",
+    "description": "The blog post button label to navigate to the older/next post"
+  },
+  "theme.blog.post.plurals": {
+    "message": "Un article|{count} articles",
+    "description": "Pluralized label for \"{count} posts\". Use as much plural forms (separated by \"|\") as your language support (see https://www.unicode.org/cldr/cldr-aux/charts/34/supplemental/language_plural_rules.html)"
+  },
+  "theme.blog.tagTitle": {
+    "message": "{nPosts} tagués avec « {tagName} »",
+    "description": "The title of the page for a blog tag"
+  },
+  "theme.tags.tagsPageLink": {
+    "message": "Voir tous les tags",
+    "description": "The label of the link targeting the tag list page"
+  },
+  "theme.colorToggle.ariaLabel": {
+    "message": "Basculer entre le mode sombre et clair (actuellement {mode})",
+    "description": "The ARIA label for the navbar color mode toggle"
+  },
+  "theme.colorToggle.ariaLabel.mode.dark": {
+    "message": "mode sombre",
+    "description": "The name for the dark color mode"
+  },
+  "theme.colorToggle.ariaLabel.mode.light": {
+    "message": "mode clair",
+    "description": "The name for the light color mode"
+  },
+  "theme.docs.breadcrumbs.navAriaLabel": {
+    "message": "Fil d'Ariane",
+    "description": "The ARIA label for the breadcrumbs"
+  },
+  "theme.docs.DocCard.categoryDescription.plurals": {
+    "message": "1 élément|{count} éléments",
+    "description": "The default description for a category card in the generated index about how many items this category includes"
+  },
+  "theme.docs.paginator.navAriaLabel": {
+    "message": "Pages de documentation",
+    "description": "The ARIA label for the docs pagination"
+  },
+  "theme.docs.paginator.previous": {
+    "message": "Précédent",
+    "description": "The label used to navigate to the previous doc"
+  },
+  "theme.docs.paginator.next": {
+    "message": "Suivant",
+    "description": "The label used to navigate to the next doc"
+  },
+  "theme.docs.tagDocListPageTitle.nDocsTagged": {
+    "message": "Un document tagué|{count} documents tagués",
+    "description": "Pluralized label for \"{count} docs tagged\". Use as much plural forms (separated by \"|\") as your language support (see https://www.unicode.org/cldr/cldr-aux/charts/34/supplemental/language_plural_rules.html)"
+  },
+  "theme.docs.tagDocListPageTitle": {
+    "message": "{nDocsTagged} avec \"{tagName}\"",
+    "description": "The title of the page for a docs tag"
+  },
+  "theme.docs.versionBadge.label": {
+    "message": "Version: {versionLabel}"
+  },
+  "theme.docs.versions.unreleasedVersionLabel": {
+    "message": "Ceci est la documentation de la prochaine version {versionLabel} de {siteTitle}.",
+    "description": "The label used to tell the user that he's browsing an unreleased doc version"
+  },
+  "theme.docs.versions.unmaintainedVersionLabel": {
+    "message": "Ceci est la documentation de {siteTitle} {versionLabel}, qui n'est plus activement maintenue.",
+    "description": "The label used to tell the user that he's browsing an unmaintained doc version"
+  },
+  "theme.docs.versions.latestVersionSuggestionLabel": {
+    "message": "Pour une documentation à jour, consultez la {latestVersionLink} ({versionLabel}).",
+    "description": "The label used to tell the user to check the latest version"
+  },
+  "theme.docs.versions.latestVersionLinkLabel": {
+    "message": "dernière version",
+    "description": "The label used for the latest version suggestion link label"
+  },
+  "theme.common.editThisPage": {
+    "message": "Éditer cette page",
+    "description": "The link label to edit the current page"
+  },
+  "theme.common.headingLinkTitle": {
+    "message": "Lien direct vers {heading}",
+    "description": "Title for link to heading"
+  },
+  "theme.lastUpdated.atDate": {
+    "message": " le {date}",
+    "description": "The words used to describe on which date a page has been last updated"
+  },
+  "theme.lastUpdated.byUser": {
+    "message": " par {user}",
+    "description": "The words used to describe by who the page has been last updated"
+  },
+  "theme.lastUpdated.lastUpdatedAtBy": {
+    "message": "Dernière mise à jour{atDate}{byUser}",
+    "description": "The sentence used to display when a page has been last updated, and by who"
+  },
+  "theme.navbar.mobileVersionsDropdown.label": {
+    "message": "Versions",
+    "description": "The label for the navbar versions dropdown on mobile view"
+  },
+  "theme.NotFound.title": {
+    "message": "Page introuvable",
+    "description": "The title of the 404 page"
+  },
+  "theme.tags.tagsListLabel": {
+    "message": "Tags :",
+    "description": "The label alongside a tag list"
+  },
+  "theme.admonition.caution": {
+    "message": "attention",
+    "description": "The default label used for the Caution admonition (:::caution)"
+  },
+  "theme.admonition.danger": {
+    "message": "danger",
+    "description": "The default label used for the Danger admonition (:::danger)"
+  },
+  "theme.admonition.info": {
+    "message": "info",
+    "description": "The default label used for the Info admonition (:::info)"
+  },
+  "theme.admonition.note": {
+    "message": "remarque",
+    "description": "The default label used for the Note admonition (:::note)"
+  },
+  "theme.admonition.tip": {
+    "message": "astuce",
+    "description": "The default label used for the Tip admonition (:::tip)"
+  },
+  "theme.admonition.warning": {
+    "message": "attention",
+    "description": "The default label used for the Warning admonition (:::warning)"
+  },
+  "theme.AnnouncementBar.closeButtonAriaLabel": {
+    "message": "Fermer",
+    "description": "The ARIA label for close button of announcement bar"
+  },
+  "theme.blog.sidebar.navAriaLabel": {
+    "message": "Navigation article de blog récent",
+    "description": "The ARIA label for recent posts in the blog sidebar"
+  },
+  "theme.CodeBlock.copied": {
+    "message": "Copié",
+    "description": "The copied button label on code blocks"
+  },
+  "theme.CodeBlock.copyButtonAriaLabel": {
+    "message": "Copier le code",
+    "description": "The ARIA label for copy code blocks button"
+  },
+  "theme.CodeBlock.copy": {
+    "message": "Copier",
+    "description": "The copy button label on code blocks"
+  },
+  "theme.CodeBlock.wordWrapToggle": {
+    "message": "Activer/désactiver le retour à la ligne",
+    "description": "The title attribute for toggle word wrapping button of code block lines"
+  },
+  "theme.DocSidebarItem.expandCategoryAriaLabel": {
+    "message": "Développer la catégorie '{label}' de la barre latérale",
+    "description": "The ARIA label to expand the sidebar category"
+  },
+  "theme.DocSidebarItem.collapseCategoryAriaLabel": {
+    "message": "Réduire la catégorie '{label}' de la barre latérale",
+    "description": "The ARIA label to collapse the sidebar category"
+  },
+  "theme.NavBar.navAriaLabel": {
+    "message": "Main",
+    "description": "The ARIA label for the main navigation"
+  },
+  "theme.navbar.mobileLanguageDropdown.label": {
+    "message": "Langues",
+    "description": "The label for the mobile language switcher dropdown"
+  },
+  "theme.NotFound.p1": {
+    "message": "Nous n'avons pas trouvé ce que vous recherchez.",
+    "description": "The first paragraph of the 404 page"
+  },
+  "theme.NotFound.p2": {
+    "message": "Veuillez contacter le propriétaire du site qui vous a lié à l'URL d'origine et leur faire savoir que leur lien est cassé.",
+    "description": "The 2nd paragraph of the 404 page"
+  },
+  "theme.TOCCollapsible.toggleButtonLabel": {
+    "message": "Sur cette page",
+    "description": "The label used by the button on the collapsible TOC component"
+  },
+  "theme.blog.post.readMore": {
+    "message": "Lire plus",
+    "description": "The label used in blog post item excerpts to link to full blog posts"
+  },
+  "theme.blog.post.readMoreLabel": {
+    "message": "En savoir plus sur {title}",
+    "description": "The ARIA label for the link to full blog posts from excerpts"
+  },
+  "theme.blog.post.readingTime.plurals": {
+    "message": "Une minute de lecture|{readingTime} minutes de lecture",
+    "description": "Pluralized label for \"{readingTime} min read\". Use as much plural forms (separated by \"|\") as your language support (see https://www.unicode.org/cldr/cldr-aux/charts/34/supplemental/language_plural_rules.html)"
+  },
+  "theme.docs.breadcrumbs.home": {
+    "message": "Page d'accueil",
+    "description": "The ARIA label for the home page in the breadcrumbs"
+  },
+  "theme.docs.sidebar.collapseButtonTitle": {
+    "message": "Réduire le menu latéral",
+    "description": "The title attribute for collapse button of doc sidebar"
+  },
+  "theme.docs.sidebar.collapseButtonAriaLabel": {
+    "message": "Réduire le menu latéral",
+    "description": "The title attribute for collapse button of doc sidebar"
+  },
+  "theme.docs.sidebar.navAriaLabel": {
+    "message": "Docs sidebar",
+    "description": "The ARIA label for the sidebar navigation"
+  },
+  "theme.docs.sidebar.closeSidebarButtonAriaLabel": {
+    "message": "Fermer la barre de navigation",
+    "description": "The ARIA label for close button of mobile sidebar"
+  },
+  "theme.navbar.mobileSidebarSecondaryMenu.backButtonLabel": {
+    "message": "← Retour au menu principal",
+    "description": "The label of the back button to return to main menu, inside the mobile navbar sidebar secondary menu (notably used to display the docs sidebar)"
+  },
+  "theme.docs.sidebar.toggleSidebarButtonAriaLabel": {
+    "message": "Ouvrir/fermer la barre de navigation",
+    "description": "The ARIA label for hamburger menu button of mobile navigation"
+  },
+  "theme.docs.sidebar.expandButtonTitle": {
+    "message": "Déplier le menu latéral",
+    "description": "The ARIA label and title attribute for expand button of doc sidebar"
+  },
+  "theme.docs.sidebar.expandButtonAriaLabel": {
+    "message": "Déplier le menu latéral",
+    "description": "The ARIA label and title attribute for expand button of doc sidebar"
+  },
+  "theme.ErrorPageContent.tryAgain": {
+    "message": "Réessayer",
+    "description": "The label of the button to try again rendering when the React error boundary captures an error"
+  },
+  "theme.common.skipToMainContent": {
+    "message": "Aller au contenu principal",
+    "description": "The skip to content label used for accessibility, allowing to rapidly navigate to main content with keyboard tab/enter navigation"
+  },
+  "theme.tags.tagsPageTitle": {
+    "message": "Tags",
+    "description": "The title of the tag list page"
+  },
+  "theme.unlistedContent.title": {
+    "message": "Page non répertoriée",
+    "description": "The unlisted content banner title"
+  },
+  "theme.unlistedContent.message": {
+    "message": "Cette page n'est pas répertoriée. Les moteurs de recherche ne l'indexeront pas, et seuls les utilisateurs ayant un lien direct peuvent y accéder.",
+    "description": "The unlisted content banner message"
+  }
+}

docs/i18n/fr/docusaurus-plugin-content-blog/options.json

@@ -0,0 +1,14 @@
+{
+  "title": {
+    "message": "Blog",
+    "description": "The title for the blog used in SEO"
+  },
+  "description": {
+    "message": "Blog",
+    "description": "The description for the blog used in SEO"
+  },
+  "sidebar.title": {
+    "message": "Articles récents",
+    "description": "The label for the left sidebar"
+  }
+}

docs/i18n/fr/docusaurus-plugin-content-docs/current.json

@@ -0,0 +1,18 @@
+{
+  "version.label": {
+    "message": "Next",
+    "description": "The label for version current"
+  },
+  "sidebar.docsSidebar.category.🤖 Backends LLM": {
+    "message": "🤖 Backends LLM",
+    "description": "The label for category 🤖 Backends LLM in sidebar docsSidebar"
+  },
+  "sidebar.docsSidebar.category.🚧 Dépannage": {
+    "message": "🚧 Dépannage",
+    "description": "The label for category 🚧 Dépannage in sidebar docsSidebar"
+  },
+  "sidebar.apiSidebar.category.Backend": {
+    "message": "Backend",
+    "description": "The label for category Backend in sidebar apiSidebar"
+  }
+}

docs/i18n/fr/docusaurus-plugin-content-docs/current/python/python.md

@@ -0,0 +1,3 @@
+# Documentation Python
+
+Les documents apparaîtront ici après le déploiement.

docs/i18n/fr/docusaurus-plugin-content-docs/current/python/sidebar.json

@@ -0,0 +1,7 @@
+```json
+{
+  "items": ["python/python"],
+  "label": "Backend",
+  "type": "categorie"
+}
+```

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/about.md

@@ -0,0 +1,53 @@
+---
+sidebar_position: 7
+---
+
+# 📚 Divers {#misc}
+
+## ⭐️ Stratégie de Recherche {#research-strategy}
+
+La réalisation d'une réplication complète des applications de production avec les LLM est une entreprise complexe. Notre stratégie implique :
+
+1. **Recherche Technique de Base :** Se concentrer sur la recherche fondamentale pour comprendre et améliorer les aspects techniques de la génération et de la gestion de code.
+2. **Compétences Spécialisées :** Améliorer l'efficacité des composants de base grâce à la curation des données, aux méthodes de formation, et plus encore.
+3. **Planification des Tâches :** Développer des capacités pour la détection de bogues, la gestion du code source et l'optimisation.
+4. **Évaluation :** Établir des métriques d'évaluation complètes pour mieux comprendre et améliorer nos modèles.
+
+## 🚧 Agent Par Défaut {#default-agent}
+
+- Notre agent par défaut est actuellement le CodeActAgent, capable de générer du code et de gérer des fichiers. Nous travaillons sur d'autres implémentations d'agents, y compris [SWE Agent](https://swe-agent.com/). Vous pouvez [lire à propos de notre ensemble actuel d'agents ici](./agents).
+
+## 🤝 Comment Contribuer {#how-to-contribute}
+
+OpenDevin est un projet communautaire, et nous accueillons les contributions de tout le monde. Que vous soyez développeur, chercheur, ou simplement enthousiaste à l'idée de faire progresser le domaine de l'ingénierie logicielle avec l'IA, il existe de nombreuses façons de vous impliquer :
+
+- **Contributions de Code :** Aidez-nous à développer les fonctionnalités de base, l'interface frontend ou les solutions de sandboxing.
+- **Recherche et Évaluation :** Contribuez à notre compréhension des LLM en ingénierie logicielle, participez à l'évaluation des modèles ou suggérez des améliorations.
+- **Retour d'Information et Tests :** Utilisez l'ensemble d'outils OpenDevin, signalez des bogues, suggérez des fonctionnalités ou fournissez des retours sur l'ergonomie.
+
+Pour plus de détails, veuillez consulter [ce document](https://github.com/OpenDevin/OpenDevin/blob/main/CONTRIBUTING.md).
+
+## 🤖 Rejoignez Notre Communauté {#join-our-community}
+
+Nous avons maintenant à la fois un espace de travail Slack pour la collaboration sur la construction d'OpenDevin et un serveur Discord pour discuter de tout ce qui est lié, par exemple, à ce projet, aux LLM, aux agents, etc.
+
+- [Espace de travail Slack](https://join.slack.com/t/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA)
+- [Serveur Discord](https://discord.gg/ESHStjSjD4)
+
+Si vous souhaitez contribuer, n'hésitez pas à rejoindre notre communauté. Simplifions l'ingénierie logicielle ensemble !
+
+🐚 **Codez moins, créez plus avec OpenDevin.**
+
+[![Star History Chart](https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date)](https://star-history.com/#OpenDevin/OpenDevin&Date)
+
+## 🛠️ Construit Avec {#built-with}
+
+OpenDevin est construit en utilisant une combinaison de cadres et de bibliothèques puissants, offrant une base robuste pour son développement. Voici les technologies clés utilisées dans le projet :
+
+![FastAPI](https://img.shields.io/badge/FastAPI-black?style=for-the-badge) ![uvicorn](https://img.shields.io/badge/uvicorn-black?style=for-the-badge) ![LiteLLM](https://img.shields.io/badge/LiteLLM-black?style=for-the-badge) ![Docker](https://img.shields.io/badge/Docker-black?style=for-the-badge) ![Ruff](https://img.shields.io/badge/Ruff-black?style=for-the-badge) ![MyPy](https://img.shields.io/badge/MyPy-black?style=for-the-badge) ![LlamaIndex](https://img.shields.io/badge/LlamaIndex-black?style=for-the-badge) ![React](https://img.shields.io/badge/React-black?style=for-the-badge)
+
+Veuillez noter que la sélection de ces technologies est en cours, et que des technologies supplémentaires peuvent être ajoutées ou des existantes supprimées au fur et à mesure de l'évolution du projet. Nous nous efforçons d'adopter les outils les plus adaptés et efficaces pour améliorer les capacités d'OpenDevin.
+
+## 📜 Licence {#license}
+
+Distribué sous la licence MIT. Voir [notre licence](https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE) pour plus d'informations.

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/agents.md

@@ -0,0 +1,142 @@
+---
+sidebar_position: 3
+---
+
+# 🧠 Agents et Capacités
+
+## Agent CodeAct
+
+### Description
+
+Cet agent implémente l'idée CodeAct ([article](https://arxiv.org/abs/2402.01030), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) qui consolide les **act**ions des agents LLM en un espace d'action **code** unifié pour à la fois la _simplicité_ et la _performance_ (voir article pour plus de détails).
+
+L'idée conceptuelle est illustrée ci-dessous. À chaque tour, l'agent peut :
+
+1. **Converse** : Communiquer avec les humains en langage naturel pour demander des clarifications, des confirmations, etc.
+2. **CodeAct** : Choisir d'accomplir la tâche en exécutant du code
+
+- Exécuter toute commande `bash` Linux valide
+- Exécuter tout code `Python` valide avec [un interpréteur Python interactif](https://ipython.org/). Cela est simulé à travers la commande `bash`, voir le système de plugin ci-dessous pour plus de détails.
+
+![image](https://github.com/OpenDevin/OpenDevin/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
+
+### Système de Plugin
+
+Pour rendre l'agent CodeAct plus puissant avec seulement l'accès à l'espace d'action `bash`, l'agent CodeAct exploite le système de plugins d'OpenDevin:
+
+- [Plugin Jupyter](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/jupyter) : pour l'exécution d'IPython via la commande bash
+- [Plugin outil agent SWE](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/swe_agent_commands) : Outils de ligne de commande bash puissants pour les tâches de développement logiciel introduits par [swe-agent](https://github.com/princeton-nlp/swe-agent).
+
+### Démonstration
+
+https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
+
+_Exemple de CodeActAgent avec `gpt-4-turbo-2024-04-09` effectuant une tâche de science des données (régression linéaire)_
+
+### Actions
+
+`Action`,
+`CmdRunAction`,
+`IPythonRunCellAction`,
+`AgentEchoAction`,
+`AgentFinishAction`,
+`AgentTalkAction`
+
+### Observations
+
+`CmdOutputObservation`,
+`IPythonRunCellObservation`,
+`AgentMessageObservation`,
+`UserMessageObservation`
+
+### Méthodes
+
+| Méthode          | Description                                                                                                                                     |
+| ---------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- |
+| `__init__`       | Initialise un agent avec `llm` et une liste de messages `list[Mapping[str, str]]`                                                                |
+| `step`           | Effectue une étape en utilisant l'agent CodeAct. Cela inclut la collecte d'informations sur les étapes précédentes et invite le modèle à exécuter une commande. |
+| `search_memory`  | Pas encore implémenté                                                                                                                             |
+
+### En cours de réalisation & prochaine étape
+
+[] Support de la navigation sur le web
+[] Compléter le workflow pour l'agent CodeAct afin de soumettre des PRs Github
+
+## Agent Monologue
+
+### Description
+
+L'agent Monologue utilise la mémoire à long terme et à court terme pour accomplir des tâches.
+La mémoire à long terme est stockée en tant qu'objet LongTermMemory et le modèle l'utilise pour rechercher des exemples du passé.
+La mémoire à court terme est stockée en tant qu'objet Monologue et le modèle peut la condenser si nécessaire.
+
+### Actions
+
+`Action`,
+`NullAction`,
+`CmdRunAction`,
+`FileWriteAction`,
+`FileReadAction`,
+`AgentRecallAction`,
+`BrowseURLAction`,
+`GithubPushAction`,
+`AgentThinkAction`
+
+### Observations
+
+`Observation`,
+`NullObservation`,
+`CmdOutputObservation`,
+`FileReadObservation`,
+`AgentRecallObservation`,
+`BrowserOutputObservation`
+
+### Méthodes
+
+| Méthode         | Description                                                                                                                                   |
+| --------------- | --------------------------------------------------------------------------------------------------------------------------------------------- |
+| `__init__`      | Initialise l'agent avec une mémoire à long terme et un monologue interne                                                                      |
+| `_add_event`    | Ajoute des événements au monologue de l'agent et condense avec un résumé automatiquement si le monologue est trop long                            |
+| `_initialize`   | Utilise la liste `INITIAL_THOUGHTS` pour donner à l'agent un contexte pour ses capacités et comment naviguer dans le `/workspace`                    |
+| `step`          | Modifie l'état actuel en ajoutant les actions et observations les plus récentes, puis invite le modèle à réfléchir à la prochaine action à entreprendre. |
+| `search_memory` | Utilise `VectorIndexRetriever` pour trouver des souvenirs liés à la mémoire à long terme.                                                             |
+
+## Agent Planificateur
+
+### Description
+
+L'agent planificateur utilise une stratégie d'incitation spéciale pour créer des plans à long terme pour résoudre les problèmes.
+L'agent reçoit ses paires action-observation précédentes, la tâche actuelle, et un indice basé sur la dernière action effectuée à chaque étape.
+
+### Actions
+
+`NullAction`,
+`CmdRunAction`,
+`CmdKillAction`,
+`BrowseURLAction`,
+`GithubPushAction`,
+`FileReadAction`,
+`FileWriteAction`,
+`AgentRecallAction`,
+`AgentThinkAction`,
+`AgentFinishAction`,
+`AgentSummarizeAction`,
+`AddTaskAction`,
+`ModifyTaskAction`,
+
+### Observations
+
+`Observation`,
+`NullObservation`,
+`CmdOutputObservation`,
+`FileReadObservation`,
+`AgentRecallObservation`,
+`BrowserOutputObservation`
+
+### Méthodes
+
+| Méthode          | Description                                                                                                                                                                               |
+| ---------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `__init__`       | Initialise un agent avec `llm`                                                                                                                                                           |
+| `step`           | Vérifie si l'étape actuelle est terminée, retourne `AgentFinishAction` si oui. Sinon, crée une incitation de planification et l'envoie au modèle pour inférence, en ajoutant le résultat comme prochaine action. |
+| `search_memory`  | Pas encore implémenté                                                                                                                                                                       |

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/architecture.mdx

@@ -0,0 +1,50 @@
+---
+sidebar_position: 4
+---
+
+# 🏛️ Aperçu de l'Architecture Système
+
+Voici un aperçu de haut niveau de l'architecture du système. Le système est divisé en deux composants principaux : le frontend et le backend. Le frontend est responsable de la gestion des interactions avec l'utilisateur et de l'affichage des résultats. Le backend est responsable de la gestion de la logique métier et de l'exécution des agents.
+
+![system_architecture.svg](/img/system_architecture.svg)
+
+Cet aperçu est simplifié pour montrer les principaux composants et leurs interactions. Pour une vue plus détaillée de l'architecture du backend, consultez la section [Architecture du Backend](#backend-architecture-fr).
+
+# Architecture du Backend {#backend-architecture-fr}
+
+_**Avertissement**: L'architecture du backend est en cours de développement et est sujette à modifications. Le schéma suivant montre l'architecture actuelle du backend basée sur le commit indiqué dans le pied de page du schéma._
+
+![backend_architecture.svg](/img/backend_architecture.svg)
+
+<details>
+  <summary>Mise à jour de ce Schéma</summary>
+  <div>
+    La génération du schéma d'architecture du backend est partiellement automatisée.
+    Le schéma est généré à partir des annotations de type dans le code en utilisant l'outil py2puml.
+    Le schéma est ensuite revu manuellement, ajusté et exporté en PNG et SVG.
+
+    ## Prérequis
+
+    - Un environnement Python dans lequel opendevin est exécutable
+    (selon les instructions du fichier README.md à la racine du dépôt)
+    - [py2puml](https://github.com/lucsorel/py2puml) installé
+
+## Étapes
+
+1.  Générez automatiquement le schéma en exécutant la commande suivante depuis la racine du dépôt :
+    `py2puml opendevin opendevin > docs/architecture/backend_architecture.puml`
+
+2.  Ouvrez le fichier généré dans un éditeur PlantUML, par exemple Visual Studio Code avec l'extension PlantUML ou [PlantText](https://www.planttext.com/)
+
+3.  Révisez le PUML généré et apportez toutes les modifications nécessaires au schéma (ajoutez les parties manquantes, corrigez les erreurs, améliorez l'agencement).
+    _py2puml crée le schéma à partir des annotations de type dans le code, donc les annotations de type manquantes ou incorrectes peuvent entraîner un schéma incomplet ou incorrect._
+
+4.  Examinez la différence entre le nouveau schéma et le précédent et vérifiez manuellement si les modifications sont correctes.
+    _Assurez-vous de ne pas supprimer les parties ajoutées manuellement au schéma par le passé et qui sont toujours pertinentes._
+
+5.  Ajoutez le hash du commit qui a été utilisé pour générer le schéma dans le pied de page du schéma.
+
+6.  Exporte le schéma sous forme de fichiers PNG et SVG et remplacez les schémas existants dans le répertoire `docs/architecture`. Cela peut être fait avec (par exemple [PlantText](https://www.planttext.com/))
+
+  </div>
+</details>

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/feedback.md

@@ -0,0 +1,18 @@
+---
+sidebar_position: 6
+---
+
+# ✅ Fournir des Commentaires
+
+Lorsque vous utilisez OpenDevin, vous rencontrerez sans aucun doute des cas où les choses fonctionnent bien et d'autres où elles ne fonctionnent pas. Nous vous encourageons à fournir des commentaires lorsque vous utilisez OpenDevin pour aider l'équipe de développement et, peut-être plus important encore, créer un corpus ouvert d'exemples de formation pour les agents de codage -- Partagez-OpenDevin !
+
+## 📝 Comment Fournir des Commentaires
+
+Fournir des commentaires est simple ! Lorsque vous utilisez OpenDevin, vous pouvez appuyer sur le bouton de pouce vers le haut ou vers le bas à n'importe quel moment de votre interaction. Vous serez invité à fournir votre adresse email (par exemple, afin que nous puissions vous contacter si nous voulons poser des questions de suivi), et vous pouvez choisir si vous souhaitez fournir des commentaires publiquement ou en privé.
+
+<iframe width="560" height="315" src="https://www.youtube.com/embed/5rFx-StMVV0?si=svo7xzp6LhGK_GXr" title="Lecteur vidéo YouTube" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
+
+## 📜 Licence de Données et Confidentialité
+
+* Les données **publiques** seront distribuées sous la licence MIT, comme OpenDevin lui-même, et pourront être utilisées par la communauté pour former et tester des modèles. Évidemment, les commentaires que vous pouvez rendre publics seront plus précieux pour la communauté dans son ensemble, donc lorsque vous ne traitez pas d'informations sensibles, nous vous encourageons à choisir cette option !
+* Les données **privées** ne seront partagées qu'avec l'équipe OpenDevin dans le but d'améliorer OpenDevin.

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/intro.mdx

@@ -0,0 +1,111 @@
+---
+sidebar_position: 1
+---
+
+# 💻 OpenDevin
+
+OpenDevin est un **ingénieur logiciel IA autonome** capable d'exécuter des tâches d'ingénierie complexes et de collaborer activement avec les utilisateurs sur des projets de développement logiciel.
+Ce projet est entièrement open-source, vous pouvez donc l'utiliser et le modifier comme bon vous semble.
+
+:::tip
+Explorez le code source d'OpenDevin sur [GitHub](https://github.com/OpenDevin/OpenDevin) ou rejoignez l'une de nos communautés !
+
+<a href="https://github.com/OpenDevin/OpenDevin/graphs/contributors">
+  <img
+    src="https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge"
+    alt="Contributors"
+  />
+</a>
+<a href="https://github.com/OpenDevin/OpenDevin/network/members">
+  <img
+    src="https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge"
+    alt="Forks"
+  />
+</a>
+<a href="https://github.com/OpenDevin/OpenDevin/stargazers">
+  <img
+    src="https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge"
+    alt="Stargazers"
+  />
+</a>
+<a href="https://github.com/OpenDevin/OpenDevin/issues">
+  <img
+    src="https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge"
+    alt="Issues"
+  />
+</a>
+<br></br>
+<a href="https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE">
+  <img
+    src="https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge"
+    alt="MIT License"
+  />
+</a>
+<br></br>
+<a href="https://join.slack.com/t/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA">
+  <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>
+:::
+
+## 🛠️ Pour commencer
+
+La manière la plus simple d'exécuter OpenDevin est à l'intérieur d'un conteneur Docker. Il fonctionne mieux avec la version la plus récente de Docker, `26.0.0`.
+Vous devez utiliser Linux, Mac OS ou WSL sur Windows.
+
+Pour démarrer OpenDevin dans un conteneur docker, exécutez les commandes suivantes dans votre terminal :
+
+:::warning
+Lorsque vous exécutez la commande suivante, les fichiers dans `./workspace` peuvent être modifiés ou supprimés.
+:::
+
+```bash
+WORKSPACE_BASE=$(pwd)/workspace
+docker run -it \
+    --pull=always \
+    -e SANDBOX_USER_ID=$(id -u) \
+    -e PERSIST_SANDBOX="true" \
+    -e SSH_PASSWORD="make something up here" \
+    -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:0.6
+```
+
+Vous trouverez OpenDevin fonctionnant à l'adresse [http://localhost:3000](http://localhost:3000) avec accès à `./workspace`. Pour qu'OpenDevin fonctionne sur votre code, placez-le dans `./workspace`.
+
+OpenDevin n'aura accès qu'à ce dossier de workspace. Le reste de votre système ne sera pas affecté car il s'exécute dans un bac à sable sécurisé de docker.
+
+:::tip
+Si vous souhaitez utiliser la version **(instable !)** la plus récente, vous pouvez utiliser `ghcr.io/opendevin/opendevin:main` comme image (dernière ligne).
+:::
+
+Pour le workflow de développement, consultez [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md).
+
+Avez-vous des problèmes ? Consultez notre [Guide de dépannage](https://opendevin.github.io/OpenDevin/modules/usage/troubleshooting).
+
+:::warning
+OpenDevin est actuellement en cours de développement, mais vous pouvez déjà exécuter la version alpha pour voir le système de bout en bout en action.
+:::
+
+[contributors-shield]: https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge
+[contributors-url]: https://github.com/OpenDevin/OpenDevin/graphs/contributors
+[forks-shield]: https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge
+[forks-url]: https://github.com/OpenDevin/OpenDevin/network/members
+[stars-shield]: https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge
+[stars-url]: https://github.com/OpenDevin/OpenDevin/stargazers
+[issues-shield]: https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge
+[issues-url]: https://github.com/OpenDevin/OpenDevin/issues
+[license-shield]: https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge
+[license-url]: https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/llms/azureLLMs.md

@@ -0,0 +1,37 @@
+# Azure OpenAI LLM
+
+## Complétion
+
+OpenDevin utilise LiteLLM pour les appels de complétion. Vous pouvez trouver leur documentation sur Azure [ici](https://docs.litellm.ai/docs/providers/azure)
+
+### Configurations openai Azure
+
+Lors de l'exécution de l'image Docker OpenDevin, vous devrez définir les variables d'environnement suivantes en utilisant `-e` :
+
+```
+LLM_BASE_URL="<azure-api-base-url>"          # e.g. "https://openai-gpt-4-test-v-1.openai.azure.com/"
+LLM_API_KEY="<azure-api-key>"
+LLM_MODEL="azure/<your-gpt-deployment-name>"
+LLM_API_VERSION = "<api-version>"          # e.g. "2024-02-15-preview"
+```
+
+:::note
+Vous pouvez trouver le nom de votre déploiement ChatGPT sur la page des déploiements sur Azure. Par défaut ou initialement, il pourrait être le même que le nom du modèle de chat (par exemple 'GPT4-1106-preview'), mais il n'est pas obligé de l'être. Exécutez OpenDevin, et une fois chargé dans le navigateur, allez dans Paramètres et définissez le modèle comme suit : "azure/&lt;your-actual-gpt-deployment-name&gt;". Si ce n'est pas dans la liste, entrez votre propre texte et enregistrez-le.
+:::
+
+## Embeddings
+
+OpenDevin utilise llama-index pour les embeddings. Vous pouvez trouver leur documentation sur Azure [ici](https://docs.llamaindex.ai/en/stable/api_reference/embeddings/azure_openai/)
+
+### Configurations openai Azure
+
+Le modèle utilisé pour les embeddings Azure OpenAI est "text-embedding-ada-002".
+Vous avez besoin du nom de déploiement correct pour ce modèle dans votre compte Azure.
+
+Lors de l'exécution d'OpenDevin dans Docker, définissez les variables d'environnement suivantes en utilisant `-e` :
+
+```
+LLM_EMBEDDING_MODEL="azureopenai"
+LLM_EMBEDDING_DEPLOYMENT_NAME = "<your-embedding-deployment-name>"        # e.g. "TextEmbedding...<etc>"
+LLM_API_VERSION = "<api-version>"         # e.g. "2024-02-15-preview"
+```

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/llms/googleLLMs.md

@@ -0,0 +1,28 @@
+# Google Gemini/Vertex LLM
+
+## Complétion
+
+OpenDevin utilise LiteLLM pour les appels de complétion. Les ressources suivantes sont pertinentes pour utiliser OpenDevin avec les LLMs de Google :
+
+- [Gemini - Google AI Studio](https://docs.litellm.ai/docs/providers/gemini)
+- [VertexAI - Google Cloud Platform](https://docs.litellm.ai/docs/providers/vertex)
+
+### Configurations de Gemini - Google AI Studio
+
+Pour utiliser Gemini via Google AI Studio lors de l'exécution de l'image Docker d'OpenDevin, vous devez définir les variables d'environnement suivantes en utilisant `-e` :
+
+```
+GEMINI_API_KEY="<votre-cle-api-google>"
+LLM_MODEL="gemini/gemini-1.5-pro"
+```
+
+### Configurations de Vertex AI - Google Cloud Platform
+
+Pour utiliser Vertex AI via Google Cloud Platform lors de l'exécution de l'image Docker d'OpenDevin, vous devez définir les variables d'environnement suivantes en utilisant `-e` :
+
+```
+GOOGLE_APPLICATION_CREDENTIALS="<dump-json-du-compte-de-service-gcp-json>"
+VERTEXAI_PROJECT="<votre-id-de-projet-gcp>"
+VERTEXAI_LOCATION="<votre-localisation-gcp>"
+LLM_MODEL="vertex_ai/<modele-llm-desire>"
+```

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/llms/llms.md

@@ -0,0 +1,44 @@
+---
+sidebar_position: 2
+---
+
+# 🤖 Backends LLM
+
+OpenDevin peut fonctionner avec n'importe quel backend LLM.
+Pour une liste complète des fournisseurs et des modèles LM disponibles, veuillez consulter la
+[documentation litellm](https://docs.litellm.ai/docs/providers).
+
+:::warning
+OpenDevin émettra de nombreuses invitations au LLM que vous configurez. La plupart de ces LLM coûtent de l'argent -- assurez-vous de définir des limites de dépenses et de surveiller l'utilisation.
+:::
+
+La variable d'environnement `LLM_MODEL` contrôle le modèle utilisé dans les interactions programmatiques.
+Mais en utilisant l'interface utilisateur OpenDevin, vous devrez choisir votre modèle dans la fenêtre des paramètres (la roue dentée en bas à gauche).
+
+Les variables d'environnement suivantes peuvent être nécessaires pour certains LLM :
+
+- `LLM_API_KEY`
+- `LLM_BASE_URL`
+- `LLM_EMBEDDING_MODEL`
+- `LLM_EMBEDDING_DEPLOYMENT_NAME`
+- `LLM_API_VERSION`
+
+Nous avons quelques guides pour exécuter OpenDevin avec des fournisseurs de modèles spécifiques :
+
+- [ollama](llms/localLLMs)
+- [Azure](llms/azureLLMs)
+
+Si vous utilisez un autre fournisseur, nous vous encourageons à ouvrir une PR pour partager votre configuration !
+
+## Remarque sur les modèles alternatifs
+
+Les meilleurs modèles sont GPT-4 et Claude 3. Les modèles locaux et open source actuels ne sont pas aussi puissants.
+Lors de l'utilisation d'un modèle alternatif, vous pouvez constater des temps d'attente prolongés entre les messages,
+des réponses de mauvaise qualité ou des erreurs sur des JSON mal formés. OpenDevin
+ne peut être aussi puissant que les modèles qui le pilotent -- heureusement, les membres de notre équipe travaillent activement à la construction de meilleurs modèles open source !
+
+## Réessais d'API et limites de taux
+
+Certains LLM ont des limites de taux et peuvent nécessiter des réessais. OpenDevin réessaiera automatiquement les demandes s'il reçoit une erreur 429 ou une erreur de connexion API.
+Vous pouvez définir les variables d'environnement `LLM_NUM_RETRIES`, `LLM_RETRY_MIN_WAIT`, `LLM_RETRY_MAX_WAIT` pour contrôler le nombre de réessais et le temps entre les réessais.
+Par défaut, `LLM_NUM_RETRIES` est 5 et `LLM_RETRY_MIN_WAIT`, `LLM_RETRY_MAX_WAIT` sont respectivement de 3 secondes et 60 secondes.

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/llms/localLLMs.md

@@ -0,0 +1,141 @@
+# LLM Local avec Ollama
+
+Assurez-vous que le serveur Ollama est en cours d'exécution.
+Pour des instructions détaillées de démarrage, consultez [ici](https://github.com/ollama/ollama)
+
+Ce guide suppose que vous avez démarré ollama avec `ollama serve`. Si vous exécutez ollama différemment (par exemple, à l'intérieur de docker), les instructions pourraient devoir être modifiées. Veuillez noter que si vous utilisez WSL, la configuration par défaut de ollama bloque les requêtes des conteneurs docker. Voir [ici](#configuring-ollama-service-fr).
+
+## Télécharger des modèles
+
+Les noms des modèles Ollama peuvent être trouvés [ici](https://ollama.com/library). Pour un petit exemple, vous pouvez utiliser
+le modèle `codellama:7b`. Des modèles plus grands offriront généralement de meilleures performances.
+
+```bash
+ollama pull codellama:7b
+```
+
+vous pouvez vérifier quels modèles vous avez téléchargés de cette manière :
+
+```bash
+~$ ollama list
+NAME                            ID              SIZE    MODIFIED
+codellama:7b                    8fdf8f752f6e    3.8 GB  6 weeks ago
+mistral:7b-instruct-v0.2-q4_K_M eb14864c7427    4.4 GB  2 weeks ago
+starcoder2:latest               f67ae0f64584    1.7 GB  19 hours ago
+```
+
+## Démarrer OpenDevin
+
+### Docker
+
+Utilisez les instructions [ici](../intro) pour démarrer OpenDevin en utilisant Docker.
+Mais lors de l'exécution de `docker run`, vous devrez ajouter quelques arguments supplémentaires :
+
+```bash
+--add-host host.docker.internal:host-gateway \
+-e LLM_API_KEY="ollama" \
+-e LLM_BASE_URL="http://host.docker.internal:11434" \
+```
+
+Par exemple :
+
+```bash
+# Le répertoire que vous souhaitez qu'OpenDevin modifie. DOIT être un chemin absolu !
+export WORKSPACE_BASE=$(pwd)/workspace
+
+docker run \
+    -it \
+    --pull=always \
+    --add-host host.docker.internal:host-gateway \
+    -e SANDBOX_USER_ID=$(id -u) \
+    -e LLM_API_KEY="ollama" \
+    -e LLM_BASE_URL="http://host.docker.internal:11434" \
+    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
+    -v $WORKSPACE_BASE:/opt/workspace_base \
+    -v /var/run/docker.sock:/var/run/docker.sock \
+    -p 3000:3000 \
+    ghcr.io/opendevin/opendevin:main
+```
+
+Vous devriez maintenant pouvoir vous connecter à `http://localhost:3000/`
+
+### Compiler à partir des sources
+
+Utilisez les instructions dans [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md) pour compiler OpenDevin.
+Assurez-vous que `config.toml` soit présent en exécutant `make setup-config` qui en créera un pour vous. Dans `config.toml`, saisissez les éléments suivants :
+
+```
+LLM_MODEL="ollama/codellama:7b"
+LLM_API_KEY="ollama"
+LLM_EMBEDDING_MODEL="local"
+LLM_BASE_URL="http://localhost:11434"
+WORKSPACE_BASE="./workspace"
+WORKSPACE_DIR="$(pwd)/workspace"
+```
+
+Remplacez `LLM_MODEL` par celui de votre choix si nécessaire.
+
+Fini ! Vous pouvez maintenant démarrer Devin avec : `make run` sans Docker. Vous devriez maintenant pouvoir vous connecter à `http://localhost:3000/`
+
+## Sélection de votre modèle
+
+Dans l'interface OpenDevin, cliquez sur l'icône des paramètres en bas à gauche.
+Ensuite, dans l'entrée `Model`, saisissez `ollama/codellama:7b`, ou le nom du modèle que vous avez téléchargé précédemment.
+S'il n'apparaît pas dans un menu déroulant, ce n'est pas grave, tapez-le simplement. Cliquez sur Enregistrer lorsque vous avez terminé.
+
+Et maintenant, vous êtes prêt à démarrer !
+
+## Configuration du service ollama (WSL){#configuring-ollama-service-fr}
+
+La configuration par défaut pour ollama sous WSL ne sert que localhost. Cela signifie que vous ne pouvez pas l'atteindre depuis un conteneur docker, par exemple, il ne fonctionnera pas avec OpenDevin. Testons d'abord que ollama est en cours d'exécution correctement.
+
+```bash
+ollama list # obtenir la liste des modèles installés
+curl http://localhost:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
+#ex. curl http://localhost:11434/api/generate -d '{"model":"codellama:7b","prompt":"hi"}'
+#ex. curl http://localhost:11434/api/generate -d '{"model":"codellama","prompt":"hi"}' #le tag est optionnel s'il n'y en a qu'un seul
+```
+
+Une fois cela fait, testez qu'il accepte les requêtes "externes", comme celles provenant d'un conteneur docker.
+
+```bash
+docker ps # obtenir la liste des conteneurs docker en cours d'exécution, pour un test le plus précis choisissez le conteneur de sandbox open devin.
+docker exec [CONTAINER ID] curl http://host.docker.internal:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
+#ex. docker exec cd9cc82f7a11 curl http://host.docker.internal:11434/api/generate -d '{"model":"codellama","prompt":"hi"}'
+```
+
+## Correction
+
+Maintenant faisons en sorte que cela fonctionne. Modifiez /etc/systemd/system/ollama.service avec les privilèges sudo. (Le chemin peut varier selon la distribution Linux)
+
+```bash
+sudo vi /etc/systemd/system/ollama.service
+```
+
+ou
+
+```bash
+sudo nano /etc/systemd/system/ollama.service
+```
+
+Dans la section [Service], ajoutez ces lignes
+
+```
+Environment="OLLAMA_HOST=0.0.0.0:11434"
+Environment="OLLAMA_ORIGINS=*"
+```
+
+Ensuite, sauvegardez, rechargez la configuration et redémarrez le service.
+
+```bash
+sudo systemctl daemon-reload
+sudo systemctl restart ollama
+```
+
+Enfin, testez que ollama est accessible depuis le conteneur
+
+```bash
+ollama list # obtenir la liste des modèles installés
+docker ps # obtenir la liste des conteneurs docker en cours d'exécution, pour un test le plus précis choisissez le conteneur de sandbox open devin.
+docker exec [CONTAINER ID] curl http://host.docker.internal:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
+```

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/troubleshooting/troubleshooting.md

@@ -0,0 +1,208 @@
+---
+sidebar_position: 5
+---
+
+# 🚧 Dépannage
+
+Il existe certains messages d'erreur qui sont souvent signalés par les utilisateurs.
+
+Nous essaierons de rendre le processus d'installation plus facile et ces messages d'erreur
+mieux à l'avenir. Mais pour l'instant, vous pouvez rechercher votre message d'erreur ci-dessous et voir s'il existe des solutions de contournement.
+
+Pour chacun de ces messages d'erreur, **il existe un problème existant**. Veuillez ne pas
+ouvrir un nouveau problème - commentez simplement dessus.
+
+Si vous trouvez plus d'informations ou une solution de contournement pour l'un de ces problèmes, veuillez ouvrir un *PR* pour ajouter des détails à ce fichier.
+
+:::tip
+Si vous utilisez Windows et que vous rencontrez des problèmes, consultez notre [guide pour les utilisateurs de Windows (WSL)](troubleshooting/windows).
+:::
+
+## Impossible de se connecter à Docker
+
+[Problème GitHub](https://github.com/OpenDevin/OpenDevin/issues/1226)
+
+### Symptômes
+
+```bash
+Erreur lors de la création du contrôleur. Veuillez vérifier que Docker est en cours d'exécution et visitez `https://opendevin.github.io/OpenDevin/modules/usage/troubleshooting` pour plus d'informations sur le débogage.
+```
+
+```bash
+docker.errors.DockerException: Erreur lors de la récupération de la version de l'API du serveur : ('Connection aborted.', FileNotFoundError(2, 'Aucun fichier ou répertoire de ce type'))
+```
+
+### Détails
+
+OpenDevin utilise un conteneur Docker pour effectuer son travail en toute sécurité, sans risquer de briser votre machine.
+
+### Solutions de contournement
+
+* Exécutez `docker ps` pour vous assurer que docker est en cours d'exécution
+* Assurez-vous que vous n'avez pas besoin de `sudo` pour exécuter docker [voir ici](https://www.baeldung.com/linux/docker-run-without-sudo)
+* Si vous êtes sur un Mac, vérifiez les [exigences en matière d'autorisations](https://docs.docker.com/desktop/mac/permission-requirements/) et envisagez particulièrement d'activer l'option `Allow the default Docker socket to be used` sous `Settings > Advanced` dans Docker Desktop.
+* De plus, mettez à jour Docker vers la dernière version sous `Check for Updates`
+
+## Impossible de se connecter à la boîte SSH
+
+[Problème GitHub](https://github.com/OpenDevin/OpenDevin/issues/1156)
+
+### Symptômes
+
+```python
+self.shell = DockerSSHBox(
+...
+pexpect.pxssh.ExceptionPxssh: Impossible d'établir une connexion avec l'hôte
+```
+
+### Détails
+
+Par défaut, OpenDevin se connecte à un conteneur en cours d'exécution via SSH. Sur certaines machines,
+en particulier Windows, cela semble échouer.
+
+### Solutions de contournement
+
+* Redémarrez votre ordinateur (parfois cela fonctionne)
+* Assurez-vous d'avoir les dernières versions de WSL et Docker
+* Vérifiez que votre distribution dans WSL est également à jour
+* Essayez [ce guide de réinstallation](https://github.com/OpenDevin/OpenDevin/issues/1156#issuecomment-2064549427)
+* Définissez `-e SANDBOX_TYPE=exec` pour passer au conteneur ExecBox de Docker
+
+## Impossible de se connecter à LLM
+
+[Problème GitHub](https://github.com/OpenDevin/OpenDevin/issues/1208)
+
+### Symptômes
+
+```python
+  File "/app/.venv/lib/python3.12/site-packages/openai/_exceptions.py", line 81, in __init__
+    super().__init__(message, response.request, body=body)
+                              ^^^^^^^^^^^^^^^^
+AttributeError: 'NoneType' object has no attribute 'request'
+```
+
+### Détails
+
+[Problèmes GitHub](https://github.com/OpenDevin/OpenDevin/issues?q=is%3Aissue+is%3Aopen+404)
+
+Cela se produit généralement avec les configurations de LLM *locales*, lorsque OpenDevin ne parvient pas à se connecter au serveur LLM.
+Consultez notre guide pour [LLMs locaux](llms/localLLMs) pour plus d'informations.
+
+### Solutions de contournement
+
+* Vérifiez votre `base_url` dans votre config.toml (si elle existe) sous la section "llm"
+* Vérifiez que ollama (ou tout autre LLM que vous utilisez) fonctionne correctement
+* Assurez-vous d'utiliser `--add-host host.docker.internal:host-gateway` lorsque vous utilisez Docker
+
+## `404 Ressource non trouvée`
+
+### Symptômes
+
+```python
+Traceback (most recent call last):
+  File "/app/.venv/lib/python3.12/site-packages/litellm/llms/openai.py", line 414, in completion
+    raise e
+  File "/app/.venv/lib/python3.12/site-packages/litellm/llms/openai.py", line 373, in completion
+    response = openai_client.chat.completions.create(**data, timeout=timeout)  # type: ignore
+               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/app/.venv/lib/python3.12/site-packages/openai/_utils/_utils.py", line 277, in wrapper
+    return func(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^
+  File "/app/.venv/lib/python3.12/site-packages/openai/resources/chat/completions.py", line 579, in create
+    return self._post(
+           ^^^^^^^^^^^
+  File "/app/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1232, in post
+    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
+                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/app/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 921, in request
+    return self._request(
+           ^^^^^^^^^^^^^^
+  File "/app/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1012, in _request
+    raise self._make_status_error_from_response(err.response) from None
+openai.NotFoundError: Code d'erreur : 404 - {'error': {'code': '404', 'message': 'Ressource non trouvée'}}
+```
+
+### Détails
+
+Cela se produit lorsque LiteLLM (notre bibliothèque pour se connecter à différents fournisseurs de LLM) ne parvient pas à trouver
+le point de terminaison API avec lequel vous essayez de vous connecter. Cela arrive le plus souvent aux utilisateurs de Azure ou ollama.
+
+### Solutions de contournement
+
+* Vérifiez que vous avez correctement défini `LLM_BASE_URL`
+* Vérifiez que le modèle est correctement défini, en fonction des [docs de LiteLLM](https://docs.litellm.ai/docs/providers)
+  * Si vous êtes en cours d'exécution dans l'interface utilisateur, assurez-vous de définir le `model` dans le modal des paramètres
+  * Si vous êtes en cours d'exécution sans interface (via main.py), assurez-vous de définir `LLM_MODEL` dans votre env/config
+* Assurez-vous de suivre les instructions spéciales de votre fournisseur de LLM
+  * [ollama](/fr/modules/usage/llms/localLLMs)
+  * [Azure](/fr/modules/usage/llms/azureLLMs)
+  * [Google](/fr/modules/usage/llms/googleLLMs)
+* Assurez-vous que votre clé API est correcte
+* Voyez si vous pouvez vous connecter au LLM en utilisant `curl`
+* Essayez de [vous connecter via LiteLLM directement](https://github.com/BerriAI/litellm) pour tester votre configuration
+
+## `make build` bloqué sur les installations de packages
+
+### Symptômes
+
+Installation de package bloquée sur `En attente...` sans aucun message d'erreur :
+
+```bash
+Opérations de package : 286 installations, 0 mises à jour, 0 suppressions
+
+  - Installation de certifi (2024.2.2) : En attente...
+  - Installation de h11 (0.14.0) : En attente...
+  - Installation de idna (3.7) : En attente...
+  - Installation de sniffio (1.3.1) : En attente...
+  - Installation de typing-extensions (4.11.0) : En attente...
+```
+
+### Détails
+
+Dans de rares cas, `make build` peut sembler bloqué sur les installations de packages
+sans aucun message d'erreur.
+
+### Solutions de contournement
+
+* Le gestionnaire de packages Poetry peut manquer d'un paramètre de configuration concernant
+l'emplacement où doivent être recherchées les informations d'identification (keyring).
+
+### Solution de contournement
+
+Tout d'abord, vérifiez avec `env` si une valeur pour `PYTHON_KEYRING_BACKEND` existe.
+Sinon, exécutez la commande ci-dessous pour la définir à une valeur connue et réessayez la construction :
+
+```bash
+export PYTHON_KEYRING_BACKEND=keyring.backends.null.Keyring
+```
+
+## Les sessions ne sont pas restaurées
+
+### Symptômes
+
+OpenDevin demande généralement s'il faut reprendre ou commencer une nouvelle session lors de l'ouverture de l'interface utilisateur.
+Mais cliquer sur "Reprendre" démarre toujours une toute nouvelle discussion.
+
+### Détails
+
+Avec une installation standard à ce jour, les données de session sont stockées en mémoire.
+Actuellement, si le service OpenDevin est redémarré, les sessions précédentes deviennent
+invalides (un nouveau secret est généré) et donc non récupérables.
+
+### Solutions de contournement
+
+* Modifiez la configuration pour rendre les sessions persistantes en éditant le fichier `config.toml`
+(dans le dossier racine d'OpenDevin) en spécifiant un `file_store` et un
+`file_store_path` absolu :
+
+```toml
+file_store="local"
+file_store_path="/absolute/path/to/opendevin/cache/directory"
+```
+
+* Ajoutez un secret jwt fixe dans votre .bashrc, comme ci-dessous, afin que les id de session précédents
+restent acceptés.
+
+```bash
+EXPORT JWT_SECRET=A_CONST_VALUE
+```

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/troubleshooting/windows.md

@@ -0,0 +1,76 @@
+# Notes pour les utilisateurs de Windows et WSL
+
+OpenDevin ne supporte Windows que via [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
+Veuillez vous assurer de lancer toutes les commandes à l'intérieur de votre terminal WSL.
+
+## Dépannage
+
+### Erreur : 'docker' n'a pas pu être trouvé dans cette distribution WSL 2.
+
+Si vous utilisez Docker Desktop, assurez-vous de le démarrer avant d'exécuter toute commande docker depuis l'intérieur de WSL.
+Docker doit également avoir l'option d'intégration WSL activée.
+
+### Recommandation : Ne pas exécuter en tant qu'utilisateur root
+
+Pour des raisons de sécurité, il est fortement recommandé de ne pas exécuter OpenDevin en tant qu'utilisateur root, mais en tant qu'utilisateur avec un UID non nul.
+De plus, les sandboxes persistants ne seront pas pris en charge lors de l'exécution en tant que root et un message approprié pourrait apparaître lors du démarrage d'OpenDevin.
+
+Références :
+
+* [Pourquoi il est mauvais de se connecter en tant que root](https://askubuntu.com/questions/16178/why-is-it-bad-to-log-in-as-root)
+* [Définir l'utilisateur par défaut dans WSL](https://www.tenforums.com/tutorials/128152-set-default-user-windows-subsystem-linux-distro-windows-10-a.html#option2)
+Astuce pour la 2e référence : pour les utilisateurs d'Ubuntu, la commande pourrait en fait être "ubuntupreview" au lieu de "ubuntu".
+
+### Échec de la création de l'utilisateur opendevin
+
+Si vous rencontrez l'erreur suivante lors de l'installation :
+
+```sh
+Exception: Failed to create opendevin user in sandbox: 'useradd: UID 0 is not unique'
+```
+
+Vous pouvez la résoudre en exécutant :
+
+```sh
+export SANDBOX_USER_ID=1000
+```
+
+### Installation de Poetry
+
+* Si vous rencontrez des problèmes pour exécuter Poetry même après l'avoir installé pendant le processus de construction, il peut être nécessaire d'ajouter son chemin binaire à votre environnement :
+
+```sh
+export PATH="$HOME/.local/bin:$PATH"
+```
+
+* Si `make build` s'arrête avec une erreur telle que :
+
+```sh
+ModuleNotFoundError: no module named <module-name>
+```
+
+Cela pourrait être un problème avec le cache de Poetry.
+Essayez d'exécuter ces 2 commandes l'une après l'autre :
+
+```sh
+rm -r ~/.cache/pypoetry
+make build
+```
+
+### L'objet NoneType n'a pas d'attribut 'request'
+
+Si vous rencontrez des problèmes liés au réseau, tels que `NoneType object has no attribute 'request'` lors de l'exécution de `make run`, il peut être nécessaire de configurer vos paramètres réseau WSL2. Suivez ces étapes :
+
+* Ouvrez ou créez le fichier `.wslconfig` situé à `C:\Users\%username%\.wslconfig` sur votre machine hôte Windows.
+* Ajoutez la configuration suivante au fichier `.wslconfig` :
+
+```sh
+[wsl2]
+networkingMode=mirrored
+localhostForwarding=true
+```
+
+* Enregistrez le fichier `.wslconfig`.
+* Redémarrez WSL2 complètement en quittant toute instance WSL2 en cours d'exécution et en exécutant la commande `wsl --shutdown` dans votre invite de commande ou terminal.
+* Après avoir redémarré WSL, essayez d'exécuter `make run` à nouveau.
+Le problème réseau devrait être résolu.

docs/i18n/fr/docusaurus-theme-classic/navbar.json

@@ -0,0 +1,26 @@
+{
+  "title": {
+    "message": "OpenDevin",
+    "description": "The title in the navbar"
+  },
+  "logo.alt": {
+    "message": "OpenDevin",
+    "description": "The alt text of navbar logo"
+  },
+  "item.label.Docs": {
+    "message": "Docs",
+    "description": "Navbar item with label Docs"
+  },
+  "item.label.Codebase": {
+    "message": "Codebase",
+    "description": "Navbar item with label Codebase"
+  },
+  "item.label.FAQ": {
+    "message": "FAQ",
+    "description": "Navbar item with label FAQ"
+  },
+  "item.label.GitHub": {
+    "message": "GitHub",
+    "description": "Navbar item with label GitHub"
+  }
+}

docs/i18n/zh-Hans/code.json

@@ -0,0 +1,406 @@
+{
+  "footer.title": {
+    "message": "OpenDevin"
+  },
+  "footer.docs": {
+    "message": "Docs"
+  },
+  "footer.community": {
+    "message": "Community"
+  },
+  "footer.copyright": {
+    "message": "Copyright © {year} OpenDevin"
+  },
+  "faq.title": {
+    "message": "Frequently Asked Questions",
+    "description": "FAQ Title"
+  },
+  "faq.description": {
+    "message": "Frequently Asked Questions"
+  },
+  "faq.section.title.1": {
+    "message": "What is OpenDevin?",
+    "description": "First Section Title"
+  },
+  "faq.section.highlight": {
+    "message": "OpenDevin",
+    "description": "Highlight Text"
+  },
+  "faq.section.description.1": {
+    "message": "is an autonomous software engineer that can solve software engineering and web-browsing tasks end-to-end. It can perform data science queries, such as \"Find the number of pull requests to the OpenDevin repository in the last month,\" and software engineering tasks, such as \"Please add tests to this file and verify that all the tests pass. If they don't fix the file.\"",
+    "description": "Description for OpenDevin"
+  },
+  "faq.section.description.2": {
+    "message": "At the same time, OpenDevin is a platform and community for agent developers to test out and evaluate new agents.",
+    "description": "Further Description for OpenDevin"
+  },
+  "faq.section.title.2": {
+    "message": "Support",
+    "description": "Support Section Title"
+  },
+  "faq.section.support.answer": {
+    "message": "Please file a bug on {githubLink} if you notice a problem that likely affects others. If you're having trouble installing, or have general questions, reach out on {discordLink} or {slackLink}.",
+    "description": "Support Answer"
+  },
+  "faq.section.title.3": {
+    "message": "How to fix a GitHub issue with OpenDevin?",
+    "description": "GitHub Issue Section Title"
+  },
+  "faq.section.github.steps.intro": {
+    "message": "To fix an issue on GitHub using OpenDevin, send a prompt to OpenDevin asking it to follow steps like the following:",
+    "description": "GitHub Steps Introduction"
+  },
+  "faq.section.github.step1": {
+    "message": "Read the issue https://github.com/OpenDevin/OpenDevin/issues/1611",
+    "description": "GitHub Step 1"
+  },
+  "faq.section.github.step2": {
+    "message": "Clone the repository and check out a new branch",
+    "description": "GitHub Step 2"
+  },
+  "faq.section.github.step3": {
+    "message": "Based on the instructions in the issue description, modify files to fix the issue",
+    "description": "GitHub Step 3"
+  },
+  "faq.section.github.step4": {
+    "message": "Push the resulting output to GitHub using the GITHUB_TOKEN environment variable",
+    "description": "GitHub Step 4"
+  },
+  "faq.section.github.step5": {
+    "message": "Tell me the link that I need to go to to send a pull request",
+    "description": "GitHub Step 5"
+  },
+  "faq.section.github.steps.preRun": {
+    "message": "Before you run OpenDevin, you can do:",
+    "description": "GitHub Steps Pre-Run"
+  },
+  "faq.section.github.steps.tokenInfo": {
+    "message": "where XXX is a GitHub token that you created that has permissions to push to the OpenDevin repo. If you don’t have write permission to the OpenDevin repo, you might need to change that to:",
+    "description": "GitHub Steps Token Info"
+  },
+  "faq.section.github.steps.usernameInfo": {
+    "message": "where USERNAME is your GitHub username.",
+    "description": "GitHub Steps Username Info"
+  },
+  "faq.section.title.4": {
+    "message": "How is OpenDevin different from Devin?",
+    "description": "Devin Section Title"
+  },
+  "faq.section.devin.linkText": {
+    "message": "Devin",
+    "description": "Devin Link Text"
+  },
+  "faq.section.devin.description": {
+    "message": "is a commercial product by Cognition Inc., that served as the initial inspiration for OpenDevin. They both aim to do a good job at solving software engineering tasks, but OpenDevin you can download, use, and modify, while Devin you can only use through the Cognition site. In addition, OpenDevin has evolved beyond the initial inspiration, and now serves as a community-driven ecosystem for agent development in general, and we'd love to have you join and",
+    "description": "Devin Description"
+  },
+  "faq.section.devin.contribute": {
+    "message": "contribute",
+    "description": "Contribute Link"
+  },
+  "faq.section.title.5": {
+    "message": "How is OpenDevin different from ChatGPT?",
+    "description": "ChatGPT Section Title"
+  },
+  "faq.section.chatgpt.description": {
+    "message": "ChatGPT you can access online, it does not interface with local files, and its ability to execute code is limited. So it can write code, but it is not easy to test or execute it.",
+    "description": "ChatGPT Description"
+  },
+  "homepage.description": {
+    "message": "AI-powered code generation for software engineering.",
+    "description": "The homepage description"
+  },
+  "homepage.getStarted": {
+    "message": "Get Started"
+  },
+  "welcome.message": {
+    "message": "Welcome to OpenDevin, an open-source autonomous AI software engineer that is capable of executing complex engineering tasks and collaborating actively with users on software development projects."
+  },
+  "theme.ErrorPageContent.title": {
+    "message": "页面已崩溃。",
+    "description": "The title of the fallback page when the page crashed"
+  },
+  "theme.BackToTopButton.buttonAriaLabel": {
+    "message": "回到顶部",
+    "description": "The ARIA label for the back to top button"
+  },
+  "theme.blog.archive.title": {
+    "message": "历史博文",
+    "description": "The page & hero title of the blog archive page"
+  },
+  "theme.blog.archive.description": {
+    "message": "历史博文",
+    "description": "The page & hero description of the blog archive page"
+  },
+  "theme.blog.paginator.navAriaLabel": {
+    "message": "博文列表分页导航",
+    "description": "The ARIA label for the blog pagination"
+  },
+  "theme.blog.paginator.newerEntries": {
+    "message": "较新的博文",
+    "description": "The label used to navigate to the newer blog posts page (previous page)"
+  },
+  "theme.blog.paginator.olderEntries": {
+    "message": "较旧的博文",
+    "description": "The label used to navigate to the older blog posts page (next page)"
+  },
+  "theme.blog.post.paginator.navAriaLabel": {
+    "message": "博文分页导航",
+    "description": "The ARIA label for the blog posts pagination"
+  },
+  "theme.blog.post.paginator.newerPost": {
+    "message": "较新一篇",
+    "description": "The blog post button label to navigate to the newer/previous post"
+  },
+  "theme.blog.post.paginator.olderPost": {
+    "message": "较旧一篇",
+    "description": "The blog post button label to navigate to the older/next post"
+  },
+  "theme.blog.post.plurals": {
+    "message": "{count} 篇博文",
+    "description": "Pluralized label for \"{count} posts\". Use as much plural forms (separated by \"|\") as your language support (see https://www.unicode.org/cldr/cldr-aux/charts/34/supplemental/language_plural_rules.html)"
+  },
+  "theme.blog.tagTitle": {
+    "message": "{nPosts} 含有标签「{tagName}」",
+    "description": "The title of the page for a blog tag"
+  },
+  "theme.tags.tagsPageLink": {
+    "message": "查看所有标签",
+    "description": "The label of the link targeting the tag list page"
+  },
+  "theme.colorToggle.ariaLabel": {
+    "message": "切换浅色/暗黑模式（当前为{mode}）",
+    "description": "The ARIA label for the navbar color mode toggle"
+  },
+  "theme.colorToggle.ariaLabel.mode.dark": {
+    "message": "暗黑模式",
+    "description": "The name for the dark color mode"
+  },
+  "theme.colorToggle.ariaLabel.mode.light": {
+    "message": "浅色模式",
+    "description": "The name for the light color mode"
+  },
+  "theme.docs.breadcrumbs.navAriaLabel": {
+    "message": "页面路径",
+    "description": "The ARIA label for the breadcrumbs"
+  },
+  "theme.docs.DocCard.categoryDescription.plurals": {
+    "message": "{count} 个项目",
+    "description": "The default description for a category card in the generated index about how many items this category includes"
+  },
+  "theme.docs.paginator.navAriaLabel": {
+    "message": "文件选项卡",
+    "description": "The ARIA label for the docs pagination"
+  },
+  "theme.docs.paginator.previous": {
+    "message": "上一页",
+    "description": "The label used to navigate to the previous doc"
+  },
+  "theme.docs.paginator.next": {
+    "message": "下一页",
+    "description": "The label used to navigate to the next doc"
+  },
+  "theme.docs.tagDocListPageTitle.nDocsTagged": {
+    "message": "{count} 篇文档带有标签",
+    "description": "Pluralized label for \"{count} docs tagged\". Use as much plural forms (separated by \"|\") as your language support (see https://www.unicode.org/cldr/cldr-aux/charts/34/supplemental/language_plural_rules.html)"
+  },
+  "theme.docs.tagDocListPageTitle": {
+    "message": "{nDocsTagged}「{tagName}」",
+    "description": "The title of the page for a docs tag"
+  },
+  "theme.docs.versionBadge.label": {
+    "message": "版本：{versionLabel}"
+  },
+  "theme.docs.versions.unreleasedVersionLabel": {
+    "message": "此为 {siteTitle} {versionLabel} 版尚未发行的文档。",
+    "description": "The label used to tell the user that he's browsing an unreleased doc version"
+  },
+  "theme.docs.versions.unmaintainedVersionLabel": {
+    "message": "此为 {siteTitle} {versionLabel} 版的文档，现已不再积极维护。",
+    "description": "The label used to tell the user that he's browsing an unmaintained doc version"
+  },
+  "theme.docs.versions.latestVersionSuggestionLabel": {
+    "message": "最新的文档请参阅 {latestVersionLink} ({versionLabel})。",
+    "description": "The label used to tell the user to check the latest version"
+  },
+  "theme.docs.versions.latestVersionLinkLabel": {
+    "message": "最新版本",
+    "description": "The label used for the latest version suggestion link label"
+  },
+  "theme.common.editThisPage": {
+    "message": "编辑此页",
+    "description": "The link label to edit the current page"
+  },
+  "theme.common.headingLinkTitle": {
+    "message": "{heading}的直接链接",
+    "description": "Title for link to heading"
+  },
+  "theme.lastUpdated.atDate": {
+    "message": "于 {date} ",
+    "description": "The words used to describe on which date a page has been last updated"
+  },
+  "theme.lastUpdated.byUser": {
+    "message": "由 {user} ",
+    "description": "The words used to describe by who the page has been last updated"
+  },
+  "theme.lastUpdated.lastUpdatedAtBy": {
+    "message": "最后{byUser}{atDate}更新",
+    "description": "The sentence used to display when a page has been last updated, and by who"
+  },
+  "theme.navbar.mobileVersionsDropdown.label": {
+    "message": "选择版本",
+    "description": "The label for the navbar versions dropdown on mobile view"
+  },
+  "theme.NotFound.title": {
+    "message": "找不到页面",
+    "description": "The title of the 404 page"
+  },
+  "theme.tags.tagsListLabel": {
+    "message": "标签：",
+    "description": "The label alongside a tag list"
+  },
+  "theme.admonition.caution": {
+    "message": "警告",
+    "description": "The default label used for the Caution admonition (:::caution)"
+  },
+  "theme.admonition.danger": {
+    "message": "危险",
+    "description": "The default label used for the Danger admonition (:::danger)"
+  },
+  "theme.admonition.info": {
+    "message": "信息",
+    "description": "The default label used for the Info admonition (:::info)"
+  },
+  "theme.admonition.note": {
+    "message": "备注",
+    "description": "The default label used for the Note admonition (:::note)"
+  },
+  "theme.admonition.tip": {
+    "message": "提示",
+    "description": "The default label used for the Tip admonition (:::tip)"
+  },
+  "theme.admonition.warning": {
+    "message": "注意",
+    "description": "The default label used for the Warning admonition (:::warning)"
+  },
+  "theme.AnnouncementBar.closeButtonAriaLabel": {
+    "message": "关闭",
+    "description": "The ARIA label for close button of announcement bar"
+  },
+  "theme.blog.sidebar.navAriaLabel": {
+    "message": "最近博文导航",
+    "description": "The ARIA label for recent posts in the blog sidebar"
+  },
+  "theme.CodeBlock.copied": {
+    "message": "复制成功",
+    "description": "The copied button label on code blocks"
+  },
+  "theme.CodeBlock.copyButtonAriaLabel": {
+    "message": "复制代码到剪贴板",
+    "description": "The ARIA label for copy code blocks button"
+  },
+  "theme.CodeBlock.copy": {
+    "message": "复制",
+    "description": "The copy button label on code blocks"
+  },
+  "theme.CodeBlock.wordWrapToggle": {
+    "message": "切换自动换行",
+    "description": "The title attribute for toggle word wrapping button of code block lines"
+  },
+  "theme.DocSidebarItem.expandCategoryAriaLabel": {
+    "message": "展开侧边栏分类 '{label}'",
+    "description": "The ARIA label to expand the sidebar category"
+  },
+  "theme.DocSidebarItem.collapseCategoryAriaLabel": {
+    "message": "折叠侧边栏分类 '{label}'",
+    "description": "The ARIA label to collapse the sidebar category"
+  },
+  "theme.NavBar.navAriaLabel": {
+    "message": "主导航",
+    "description": "The ARIA label for the main navigation"
+  },
+  "theme.navbar.mobileLanguageDropdown.label": {
+    "message": "选择语言",
+    "description": "The label for the mobile language switcher dropdown"
+  },
+  "theme.NotFound.p1": {
+    "message": "我们找不到您要找的页面。",
+    "description": "The first paragraph of the 404 page"
+  },
+  "theme.NotFound.p2": {
+    "message": "请联系原始链接来源网站的所有者，并告知他们链接已损坏。",
+    "description": "The 2nd paragraph of the 404 page"
+  },
+  "theme.TOCCollapsible.toggleButtonLabel": {
+    "message": "本页总览",
+    "description": "The label used by the button on the collapsible TOC component"
+  },
+  "theme.blog.post.readMore": {
+    "message": "阅读更多",
+    "description": "The label used in blog post item excerpts to link to full blog posts"
+  },
+  "theme.blog.post.readMoreLabel": {
+    "message": "阅读 {title} 的全文",
+    "description": "The ARIA label for the link to full blog posts from excerpts"
+  },
+  "theme.blog.post.readingTime.plurals": {
+    "message": "阅读需 {readingTime} 分钟",
+    "description": "Pluralized label for \"{readingTime} min read\". Use as much plural forms (separated by \"|\") as your language support (see https://www.unicode.org/cldr/cldr-aux/charts/34/supplemental/language_plural_rules.html)"
+  },
+  "theme.docs.breadcrumbs.home": {
+    "message": "主页面",
+    "description": "The ARIA label for the home page in the breadcrumbs"
+  },
+  "theme.docs.sidebar.collapseButtonTitle": {
+    "message": "收起侧边栏",
+    "description": "The title attribute for collapse button of doc sidebar"
+  },
+  "theme.docs.sidebar.collapseButtonAriaLabel": {
+    "message": "收起侧边栏",
+    "description": "The title attribute for collapse button of doc sidebar"
+  },
+  "theme.docs.sidebar.navAriaLabel": {
+    "message": "文档侧边栏",
+    "description": "The ARIA label for the sidebar navigation"
+  },
+  "theme.docs.sidebar.closeSidebarButtonAriaLabel": {
+    "message": "关闭导航栏",
+    "description": "The ARIA label for close button of mobile sidebar"
+  },
+  "theme.navbar.mobileSidebarSecondaryMenu.backButtonLabel": {
+    "message": "← 回到主菜单",
+    "description": "The label of the back button to return to main menu, inside the mobile navbar sidebar secondary menu (notably used to display the docs sidebar)"
+  },
+  "theme.docs.sidebar.toggleSidebarButtonAriaLabel": {
+    "message": "切换导航栏",
+    "description": "The ARIA label for hamburger menu button of mobile navigation"
+  },
+  "theme.docs.sidebar.expandButtonTitle": {
+    "message": "展开侧边栏",
+    "description": "The ARIA label and title attribute for expand button of doc sidebar"
+  },
+  "theme.docs.sidebar.expandButtonAriaLabel": {
+    "message": "展开侧边栏",
+    "description": "The ARIA label and title attribute for expand button of doc sidebar"
+  },
+  "theme.ErrorPageContent.tryAgain": {
+    "message": "重试",
+    "description": "The label of the button to try again rendering when the React error boundary captures an error"
+  },
+  "theme.common.skipToMainContent": {
+    "message": "跳到主要内容",
+    "description": "The skip to content label used for accessibility, allowing to rapidly navigate to main content with keyboard tab/enter navigation"
+  },
+  "theme.tags.tagsPageTitle": {
+    "message": "标签",
+    "description": "The title of the tag list page"
+  },
+  "theme.unlistedContent.title": {
+    "message": "未列出页",
+    "description": "The unlisted content banner title"
+  },
+  "theme.unlistedContent.message": {
+    "message": "此页面未列出。搜索引擎不会对其索引，只有拥有直接链接的用户才能访问。",
+    "description": "The unlisted content banner message"
+  }
+}

docs/i18n/zh-Hans/docusaurus-plugin-content-blog/options.json

@@ -0,0 +1,14 @@
+{
+  "title": {
+    "message": "博客",
+    "description": "The title for the blog used in SEO"
+  },
+  "description": {
+    "message": "博客",
+    "description": "The description for the blog used in SEO"
+  },
+  "sidebar.title": {
+    "message": "最近文章",
+    "description": "The label for the left sidebar"
+  }
+}

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current.json

@@ -0,0 +1,18 @@
+{
+  "version.label": {
+    "message": "Next",
+    "description": "The label for version current"
+  },
+  "sidebar.docsSidebar.category.🤖 LLM 支持": {
+    "message": "🤖 LLM 支持",
+    "description": "The label for category 🤖 LLM 支持 in sidebar docsSidebar"
+  },
+  "sidebar.docsSidebar.category.🚧 故障排除": {
+    "message": "🚧 故障排除",
+    "description": "The label for category 🚧 故障排除 in sidebar docsSidebar"
+  },
+  "sidebar.apiSidebar.category.Backend": {
+    "message": "Backend",
+    "description": "The label for category Backend in sidebar apiSidebar"
+  }
+}

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/python/python.md

@@ -0,0 +1,3 @@
+# Python 文档
+
+部署后文档将会显示在这里。

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/python/sidebar.json

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

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/about.md

@@ -0,0 +1,53 @@
+---
+sidebar_position: 7
+---
+
+# 📚 杂项
+
+## ⭐️ 研究策略
+
+通过 LLM 完全复制生产级应用程序是一个复杂的任务。我们的策略包含以下几个方面：
+
+1. **核心技术研究:** 专注于基础研究，以理解和改进代码生成和处理的技术方面。
+2. **专家能力:** 通过数据策划、训练方法等方式增强核心组件的有效性。
+3. **任务规划:** 开发错误检测、代码库管理和优化的能力。
+4. **评价:** 建立全面的评价指标，以更好地理解和改进我们的模型。
+
+## 🚧 默认代理
+
+- 我们当前的默认代理是 CodeActAgent，具备生成代码和处理文件的能力。我们正在开发其他代理实现，包括 [SWE Agent](https://swe-agent.com/)。您可以[在这里阅读我们当前的代理集合](./agents)。
+
+## 🤝 如何贡献
+
+OpenDevin 是一个社区驱动的项目，我们欢迎每个人的贡献。无论您是开发人员、研究人员，还是对用 AI 提升软件工程领域有兴趣，只要您愿意参与，我们都有很多方式可供选择：
+
+- **代码贡献:** 帮助我们开发核心功能、前端界面或沙箱解决方案。
+- **研究和评价:** 贡献您对 LLM 在软件工程领域理解的见解，参与评估模型，或提出改进建议。
+- **反馈和测试:** 使用 OpenDevin 工具集，报告错误，建议功能，或提供可用性方面的反馈。
+
+详情请查阅[此文件](https://github.com/OpenDevin/OpenDevin/blob/main/CONTRIBUTING.md)。
+
+## 🤖 加入我们的社区
+
+我们现在有一个 Slack 工作区，用于合作建设 OpenDevin，还设有一个 Discord 服务器，用于讨论与该项目、LLM、代理等相关的任何事情。
+
+- [Slack 工作区](https://join.slack.com/t/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA)
+- [Discord 服务器](https://discord.gg/ESHStjSjD4)
+
+如果您愿意贡献，请随时加入我们的社区。让我们一起简化软件工程！
+
+🐚 **少写代码，用 OpenDevin 做更多的事情。**
+
+[![Star History Chart](https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date)](https://star-history.com/#OpenDevin/OpenDevin&Date)
+
+## 🛠️ 技术选型
+
+OpenDevin 使用了一系列强大的框架和库，提供了坚实的开发基础。以下是项目中使用的关键技术：
+
+![FastAPI](https://img.shields.io/badge/FastAPI-black?style=for-the-badge) ![uvicorn](https://img.shields.io/badge/uvicorn-black?style=for-the-badge) ![LiteLLM](https://img.shields.io/badge/LiteLLM-black?style=for-the-badge) ![Docker](https://img.shields.io/badge/Docker-black?style=for-the-badge) ![Ruff](https://img.shields.io/badge/Ruff-black?style=for-the-badge) ![MyPy](https://img.shields.io/badge/MyPy-black?style=for-the-badge) ![LlamaIndex](https://img.shields.io/badge/LlamaIndex-black?style=for-the-badge) ![React](https://img.shields.io/badge/React-black?style=for-the-badge)
+
+请注意，这些技术选型仍在进行中，随着项目的发展，可能会添加新的技术或移除现有的技术。我们努力采用最适合、最高效的工具，以增强 OpenDevin 的能力。
+
+## 📜 许可证
+
+根据 MIT 许可证分发。详见[我们的许可证](https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE)了解更多信息。

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/agents.md

@@ -0,0 +1,142 @@
+---
+sidebar_position: 3
+---
+
+# 🧠 Agents and Capabilities
+
+## CodeAct Agent
+
+### 描述
+
+该Agent实现了CodeAct的思想（[论文](https://arxiv.org/abs/2402.01030)，[推特](https://twitter.com/xingyaow_/status/1754556835703751087)），将LLM agents的**行为**合并到一个统一的**代码**动作空间中，以实现_简化_和_性能_（详情见论文）。
+
+概念理念如下图所示。在每个回合，Agent可以：
+
+1. **对话**：用自然语言与人类交流，进行澄清、确认等。
+2. **CodeAct**：选择通过执行代码来完成任务
+
+- 执行任何有效的Linux `bash`命令
+- 使用[交互式Python解释器](https://ipython.org/)执行任何有效的 `Python`代码。这是通过`bash`命令模拟的，详细信息请参见插件系统。
+
+![image](https://github.com/OpenDevin/OpenDevin/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
+
+### 插件系统
+
+为了使CodeAct agent在仅能访问`bash`动作空间时更强大，CodeAct agent利用了OpenDevin的插件系统：
+
+- [Jupyter插件](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/jupyter)：通过bash命令实现IPython执行
+- [SWE-agent工具插件](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/swe_agent_commands)：为软件开发任务引入的强大bash命令行工具，由[swe-agent](https://github.com/princeton-nlp/swe-agent)提供。
+
+### 演示
+
+https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
+
+_CodeActAgent使用`gpt-4-turbo-2024-04-09`执行数据科学任务（线性回归）的示例_
+
+### 动作
+
+`Action`,
+`CmdRunAction`,
+`IPythonRunCellAction`,
+`AgentEchoAction`,
+`AgentFinishAction`,
+`AgentTalkAction`
+
+### 观测
+
+`CmdOutputObservation`,
+`IPythonRunCellObservation`,
+`AgentMessageObservation`,
+`UserMessageObservation`
+
+### 方法
+
+| 方法           | 描述                                                                                                                                     |
+| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
+| `__init__`     | 使用`llm`和一系列信息`list[Mapping[str, str]]`初始化Agent                                                                                  |
+| `step`         | 使用CodeAct Agent执行一步操作，包括收集前一步的信息并提示模型执行命令。                                                                     |
+| `search_memory`| 尚未实现                                                                                                                                    |
+
+### 进行中的工作 & 下一步
+
+[] 支持Web浏览
+[] 完成CodeAct agent提交Github PR的工作流程
+
+## Monologue Agent
+
+### 描述
+
+Monologue Agent利用长短期记忆来完成任务。
+长期记忆存储为LongTermMemory对象，模型使用它来搜索过去的示例。
+短期记忆存储为Monologue对象，模型可以根据需要进行压缩。
+
+### 动作
+
+`Action`,
+`NullAction`,
+`CmdRunAction`,
+`FileWriteAction`,
+`FileReadAction`,
+`AgentRecallAction`,
+`BrowseURLAction`,
+`GithubPushAction`,
+`AgentThinkAction`
+
+### 观测
+
+`Observation`,
+`NullObservation`,
+`CmdOutputObservation`,
+`FileReadObservation`,
+`AgentRecallObservation`,
+`BrowserOutputObservation`
+
+### 方法
+
+| 方法           | 描述                                                                                                                                       |
+| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
+| `__init__`     | 使用长期记忆和内部独白初始化Agent                                                                                                            |
+| `_add_event`   | 将事件附加到Agent的独白中，如独白过长自动与摘要一起压缩                                                                                    |
+| `_initialize`  | 使用`INITIAL_THOUGHTS`列表为agent提供其能力的上下文以及如何导航`/workspace`                                                                 |
+| `step`         | 通过添加最近的动作和观测修改当前状态，然后提示模型考虑其接下来的动作。                                                                     |
+| `search_memory`| 使用`VectorIndexRetriever`在长期记忆中查找相关记忆。                                                                                         |
+
+## Planner Agent
+
+### 描述
+
+Planner agent利用特殊的提示策略为解决问题创建长期计划。
+在每一步中，Agent会获得其先前的动作-观测对、当前任务以及基于上一次操作提供的提示。
+
+### 动作
+
+`NullAction`,
+`CmdRunAction`,
+`CmdKillAction`,
+`BrowseURLAction`,
+`GithubPushAction`,
+`FileReadAction`,
+`FileWriteAction`,
+`AgentRecallAction`,
+`AgentThinkAction`,
+`AgentFinishAction`,
+`AgentSummarizeAction`,
+`AddTaskAction`,
+`ModifyTaskAction`
+
+### 观测
+
+`Observation`,
+`NullObservation`,
+`CmdOutputObservation`,
+`FileReadObservation`,
+`AgentRecallObservation`,
+`BrowserOutputObservation`
+
+### 方法
+
+| 方法           | 描述                                                                                                                                                                                   |
+| -------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `__init__`     | 使用`llm`初始化Agent                                                                                                                                                                   |
+| `step`         | 检查当前步骤是否完成，如果是则返回`AgentFinishAction`。否则，创建计划提示并发送给模型进行推理，将结果作为下一步动作。                                                                      |
+| `search_memory`| 尚未实现                                                                                                                                                                               |

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/architecture.mdx

@@ -0,0 +1,49 @@
+---
+sidebar_position: 4
+---
+
+# 🏛️ 系统架构概览
+
+这是系统架构的高层概览。系统分为两个主要组件：前端和后端。前端负责处理用户交互并显示结果。后端负责处理业务逻辑并执行代理。
+
+![system_architecture.svg](/img/system_architecture.svg)
+
+此概览简化显示了主要组件及其交互。有关后端架构的更详细视图，请参见[后端架构](#backend-architecture-zh-Hans)部分。
+
+# 后端架构 {#backend-architecture-zh-Hans}
+
+_**免责声明**：后端架构正在进行中，可能会有所变化。下图显示了基于图表页脚中的提交内容的当前后端架构。_
+
+![backend_architecture.svg](/img/backend_architecture.svg)
+
+<details>
+  <summary>更新此图表</summary>
+  <div>
+    后端架构图的生成部分是自动化的。
+    图表是使用 py2puml 工具从代码中的类型提示生成的。
+    然后人工审核、调整并导出为 PNG 和 SVG。
+
+    ## 前提条件
+
+    - 能运行 python 环境，其中 opendevin 可以执行（根据存储库根目录中的 README.md 文件中的说明）
+    - 安装了 [py2puml](https://github.com/lucsorel/py2puml)
+
+## 步骤
+
+1.  通过从存储库根目录运行以下命令自动生成图表：
+    `py2puml opendevin opendevin > docs/architecture/backend_architecture.puml`
+
+2.  在 PlantUML 编辑器中打开生成的文件，例如使用 PlantUML 扩展的 Visual Studio Code 或 [PlantText](https://www.planttext.com/)
+
+3.  审查生成的 PUML 并对图表进行所有必要的调整（添加缺失部分、修正错误、改进定位）。
+    _py2puml 根据代码中的类型提示创建图表，因此缺失或不正确的类型提示可能导致图表不完整或不正确。_
+
+4.  审查新旧图表之间的差异，并手动检查更改是否正确。
+    _确保不移除过去手动添加到图表中的和仍然相关的部分。_
+
+5.  将用于生成图表的提交哈希添加到图表页脚。
+
+6.  将图表导出为 PNG 和 SVG 文件，并替换 `docs/architecture` 目录中的现有图表。这可以通过（例如 [PlantText](https://www.planttext.com/)）完成。
+
+  </div>
+</details>

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/feedback.md

@@ -0,0 +1,18 @@
+---
+sidebar_position: 6
+---
+
+# ✅ 提供反馈
+
+在使用 OpenDevin 时，你无疑会遇到一些情况，某些地方工作得很好，而另一些地方则可能不尽如人意。我们鼓励你在使用 OpenDevin 时提供反馈，这不仅有助于开发团队改善应用，更为重要的是，可以创建一个开放的编码代理训练样例语料库——Share-OpenDevin！
+
+## 📝 如何提供反馈
+
+提供反馈很简单！在使用 OpenDevin 时，你可以在任意时刻按下点赞或点踩按钮。你将被要求提供你的电子邮件地址（例如，以便我们在需要进一步询问时联系你），你可以选择公开或私密地提供反馈。
+
+<iframe width="560" height="315" src="https://www.youtube.com/embed/5rFx-StMVV0?si=svo7xzp6LhGK_GXr" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
+
+## 📜 数据许可与隐私
+
+* **公开** 数据将与 OpenDevin 本身一样以 MIT 许可协议发布，并可被社区用来训练和测试模型。显然，你能够公开的反馈对整个社区来说更有价值，因此当你不涉及敏感信息时，我们鼓励你选择这个选项！
+* **私密** 数据将仅与 OpenDevin 团队分享，用于改进 OpenDevin。

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/intro.mdx

@@ -0,0 +1,111 @@
+---
+sidebar_position: 1
+---
+
+# 💻 OpenDevin
+
+OpenDevin 是一个**自主 AI 软件工程师**，能够执行复杂的工程任务，并在软件开发项目中积极与用户合作。
+这个项目是完全开源的，所以你可以随意使用和修改它。
+
+:::tip
+在 [GitHub](https://github.com/OpenDevin/OpenDevin) 上探索 OpenDevin 的代码库或加入我们的社区！
+
+<a href="https://github.com/OpenDevin/OpenDevin/graphs/contributors">
+  <img
+    src="https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge"
+    alt="Contributors"
+  />
+</a>
+<a href="https://github.com/OpenDevin/OpenDevin/network/members">
+  <img
+    src="https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge"
+    alt="Forks"
+  />
+</a>
+<a href="https://github.com/OpenDevin/OpenDevin/stargazers">
+  <img
+    src="https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge"
+    alt="Stargazers"
+  />
+</a>
+<a href="https://github.com/OpenDevin/OpenDevin/issues">
+  <img
+    src="https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge"
+    alt="Issues"
+  />
+</a>
+<br></br>
+<a href="https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE">
+  <img
+    src="https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge"
+    alt="MIT License"
+  />
+</a>
+<br></br>
+<a href="https://join.slack.com/t/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA">
+  <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>
+:::
+
+## 🛠️ 入门指南
+
+运行 OpenDevin 最简单的方法是在 Docker 容器中。它在 Docker 的最新版本 `26.0.0` 上运行效果最佳。
+你必须使用 Linux、Mac OS 或 Windows 上的 WSL。
+
+要在 Docker 容器中启动 OpenDevin，请在终端中运行以下命令：
+
+:::warning
+运行以下命令时，`./workspace` 中的文件可能会被修改或删除。
+:::
+
+```bash
+WORKSPACE_BASE=$(pwd)/workspace
+docker run -it \
+    --pull=always \
+    -e SANDBOX_USER_ID=$(id -u) \
+    -e PERSIST_SANDBOX="true" \
+    -e SSH_PASSWORD="make something up here" \
+    -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:0.6
+```
+
+你会发现 OpenDevin 在 [http://localhost:3000](http://localhost:3000) 运行，并可以访问 `./workspace`。要让 OpenDevin 操作你的代码，请将代码放在 `./workspace` 中。
+
+OpenDevin 只会访问这个工作区文件夹。它在一个安全的 docker 沙盒中运行，不会影响你系统的其他部分。
+
+:::tip
+如果你想使用**（不稳定！）**最新版本，可以使用 `ghcr.io/opendevin/opendevin:main` 作为镜像（最后一行）。
+:::
+
+有关开发工作流程，请参阅 [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md)。
+
+遇到问题了吗？查看我们的 [故障排除指南](https://opendevin.github.io/OpenDevin/modules/usage/troubleshooting)。
+
+:::warning
+OpenDevin 目前正在开发中，但你已经可以运行 alpha 版本来查看端到端系统的运作情况。
+:::
+
+[contributors-shield]: https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge
+[contributors-url]: https://github.com/OpenDevin/OpenDevin/graphs/contributors
+[forks-shield]: https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge
+[forks-url]: https://github.com/OpenDevin/OpenDevin/network/members
+[stars-shield]: https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge
+[stars-url]: https://github.com/OpenDevin/OpenDevin/stargazers
+[issues-shield]: https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge
+[issues-url]: https://github.com/OpenDevin/OpenDevin/issues
+[license-shield]: https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge
+[license-url]: https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/llms/azureLLMs.md

@@ -0,0 +1,37 @@
+# Azure OpenAI 大型语言模型
+
+## 完成
+
+OpenDevin 使用 LiteLLM 进行完成调用。你可以在 Azure 的文档中找到他们的文档 [这里](https://docs.litellm.ai/docs/providers/azure)
+
+### Azure openai 配置
+
+在运行 OpenDevin Docker 镜像时，你需要使用 `-e` 设置以下环境变量：
+
+```
+LLM_BASE_URL="<azure-api-base-url>"          # 示例: "https://openai-gpt-4-test-v-1.openai.azure.com/"
+LLM_API_KEY="<azure-api-key>"
+LLM_MODEL="azure/<your-gpt-deployment-name>"
+LLM_API_VERSION = "<api-version>"          # 示例: "2024-02-15-preview"
+```
+
+:::note
+你可以在 Azure 的部署页面找到你的 ChatGPT 部署名称。它可能与默认或最初设置的聊天模型名称相同（例如 'GPT4-1106-preview'），但不一定相同。运行 OpenDevin，当你在浏览器中加载它时，进入设置并按照上述方式设置模型: "azure/&lt;your-actual-gpt-deployment-name&gt;"。如果列表中没有，请输入你自己的文本并保存。
+:::
+
+## 嵌入
+
+OpenDevin 使用 llama-index 进行嵌入。你可以在 Azure 的文档中找到他们的文档 [这里](https://docs.llamaindex.ai/en/stable/api_reference/embeddings/azure_openai/)
+
+### Azure openai 配置
+
+Azure OpenAI 嵌入使用的模型是 "text-embedding-ada-002"。
+你需要在你的 Azure 账户中为这个模型设置正确的部署名称。
+
+在 Docker 中运行 OpenDevin 时，使用 `-e` 设置以下环境变量：
+
+```
+LLM_EMBEDDING_MODEL="azureopenai"
+LLM_EMBEDDING_DEPLOYMENT_NAME = "<your-embedding-deployment-name>"        # 示例: "TextEmbedding...<etc>"
+LLM_API_VERSION = "<api-version>"         # 示例: "2024-02-15-preview"
+```

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/llms/googleLLMs.md

@@ -0,0 +1,28 @@
+# Google Gemini/Vertex LLM
+
+## Completion
+
+OpenDevin 使用 LiteLLM 进行补全调用。以下资源与使用 OpenDevin 和 Google 的 LLM 相关：
+
+- [Gemini - Google AI Studio](https://docs.litellm.ai/docs/providers/gemini)
+- [VertexAI - Google Cloud Platform](https://docs.litellm.ai/docs/providers/vertex)
+
+### Gemini - Google AI Studio 配置
+
+在运行 OpenDevin Docker 镜像时，通过 Google AI Studio 使用 Gemini，你需要使用 `-e` 设置以下环境变量：
+
+```
+GEMINI_API_KEY="<your-google-api-key>"
+LLM_MODEL="gemini/gemini-1.5-pro"
+```
+
+### Vertex AI - Google Cloud Platform 配置
+
+在运行 OpenDevin Docker 镜像时，通过 Google Cloud Platform 使用 Vertex AI，你需要使用 `-e` 设置以下环境变量：
+
+```
+GOOGLE_APPLICATION_CREDENTIALS="<json-dump-of-gcp-service-account-json>"
+VERTEXAI_PROJECT="<your-gcp-project-id>"
+VERTEXAI_LOCATION="<your-gcp-location>"
+LLM_MODEL="vertex_ai/<desired-llm-model>"
+```

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/llms/llms.md

@@ -0,0 +1,46 @@
+---
+sidebar_position: 2
+---
+
+# 🤖 LLM 支持
+
+OpenDevin 可以兼容任何 LLM 后端。
+关于所有可用 LM 提供商和模型的完整列表，请参阅
+[litellm 文档](https://docs.litellm.ai/docs/providers)。
+
+:::warning
+OpenDevin 将向你配置的 LLM 发出许多提示。大多数这些 LLM 都是收费的——请务必设定支出限额并监控使用情况。
+:::
+
+`LLM_MODEL` 环境变量控制在编程交互中使用的模型。
+但在使用 OpenDevin UI 时，你需要在设置窗口中选择你的模型（左下角的齿轮）。
+
+某些 LLM 可能需要以下环境变量：
+
+- `LLM_API_KEY`
+- `LLM_BASE_URL`
+- `LLM_EMBEDDING_MODEL`
+- `LLM_EMBEDDING_DEPLOYMENT_NAME`
+- `LLM_API_VERSION`
+
+我们有一些指南，介绍了如何使用特定模型提供商运行 OpenDevin：
+
+- [ollama](llms/localLLMs)
+- [Azure](llms/azureLLMs)
+
+如果你使用其他提供商，我们鼓励你打开一个 PR 来分享你的配置！
+
+## 关于替代模型的注意事项
+
+最好的模型是 GPT-4 和 Claude 3。目前的本地和开源模型
+远没有那么强大。当使用替代模型时，
+你可能会看到信息之间的长时间等待，
+糟糕的响应，或关于 JSON格式错误的错误。OpenDevin
+的强大程度依赖于其驱动的模型——幸运的是，我们团队的人员
+正在积极致力于构建更好的开源模型！
+
+## API 重试和速率限制
+
+一些 LLM 有速率限制，可能需要重试操作。OpenDevin 会在收到 429 错误或 API 连接错误时自动重试请求。
+你可以设置 `LLM_NUM_RETRIES`，`LLM_RETRY_MIN_WAIT`，`LLM_RETRY_MAX_WAIT` 环境变量来控制重试次数和重试之间的时间。
+默认情况下，`LLM_NUM_RETRIES` 为 5，`LLM_RETRY_MIN_WAIT` 和 `LLM_RETRY_MAX_WAIT` 分别为 3 秒和 60 秒。

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/llms/localLLMs.md

@@ -0,0 +1,140 @@
+# 使用 Ollama 的本地 LLM
+
+确保您的 Ollama 服务器已启动运行。有关详细的启动说明，请参阅[此处](https://github.com/ollama/ollama)
+
+本指南假定您已通过 `ollama serve` 启动 ollama。如果您以其他方式运行 ollama（例如在 docker 内），说明可能需要进行修改。请注意，如果您在运行 WSL，默认的 ollama 配置会阻止来自 docker 容器的请求。请参阅[此处](#configuring-ollama-service-zh-Hans)。
+
+## 拉取模型
+
+Ollama 模型名称可以在[这里](https://ollama.com/library)找到。一个小例子，您可以使用
+`codellama:7b` 模型。较大的模型通常表现更好。
+
+```bash
+ollama pull codellama:7b
+```
+
+您可以这样检查已下载的模型：
+
+```bash
+~$ ollama list
+NAME                            ID              SIZE    MODIFIED
+codellama:7b                    8fdf8f752f6e    3.8 GB  6 weeks ago
+mistral:7b-instruct-v0.2-q4_K_M eb14864c7427    4.4 GB  2 weeks ago
+starcoder2:latest               f67ae0f64584    1.7 GB  19 hours ago
+```
+
+## 启动 OpenDevin
+
+### Docker
+
+使用[此处](../intro)的说明通过 Docker 启动 OpenDevin。
+但是在运行 `docker run` 时，您需要添加一些额外的参数：
+
+```bash
+--add-host host.docker.internal:host-gateway \
+-e LLM_API_KEY="ollama" \
+-e LLM_BASE_URL="http://host.docker.internal:11434" \
+```
+
+例如：
+
+```bash
+# 您希望 OpenDevin 修改的目录。必须是绝对路径！
+export WORKSPACE_BASE=$(pwd)/workspace
+
+docker run \
+    -it \
+    --pull=always \
+    --add-host host.docker.internal:host-gateway \
+    -e SANDBOX_USER_ID=$(id -u) \
+    -e LLM_API_KEY="ollama" \
+    -e LLM_BASE_URL="http://host.docker.internal:11434" \
+    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
+    -v $WORKSPACE_BASE:/opt/workspace_base \
+    -v /var/run/docker.sock:/var/run/docker.sock \
+    -p 3000:3000 \
+    ghcr.io/opendevin/opendevin:main
+```
+
+现在您应该可以连接到 `http://localhost:3000/`
+
+### 从源代码构建
+
+使用[Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md)中的说明构建 OpenDevin。
+通过运行 `make setup-config` 确保 `config.toml` 存在，这将为您创建一个。在 `config.toml` 中，输入以下内容：
+
+```
+LLM_MODEL="ollama/codellama:7b"
+LLM_API_KEY="ollama"
+LLM_EMBEDDING_MODEL="local"
+LLM_BASE_URL="http://localhost:11434"
+WORKSPACE_BASE="./workspace"
+WORKSPACE_DIR="$(pwd)/workspace"
+```
+
+如有需要，可以替换您选择的 `LLM_MODEL`。
+
+完成！现在您可以通过 `make run` 启动 Devin 而无需 Docker。现在您应该可以连接到 `http://localhost:3000/`
+
+## 选择您的模型
+
+在 OpenDevin UI 中，点击左下角的设置齿轮。
+然后在 `Model` 输入中，输入 `ollama/codellama:7b`，或者您之前拉取的模型名称。
+如果它没有出现在下拉列表中，也没关系，只需输入即可。完成后点击保存。
+
+现在您已经准备好了！
+
+## 配置 ollama 服务（WSL）{#configuring-ollama-service-zh-Hans}
+
+WSL 中 ollama 的默认配置仅为 localhost 提供服务。这意味着您无法从 docker 容器中访问它。比如，它不会与 OpenDevin 一起工作。首先让我们测试 ollama 是否正常运行。
+
+```bash
+ollama list # 获取已安装模型列表
+curl http://localhost:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
+#例如，curl http://localhost:11434/api/generate -d '{"model":"codellama:7b","prompt":"hi"}'
+#例如，curl http://localhost:11434/api/generate -d '{"model":"codellama","prompt":"hi"}'  # 如果只有一个模型，标签是可选的
+```
+
+完成后，测试它是否允许“外部”请求，比如那些来自 docker 容器内的请求。
+
+```bash
+docker ps # 获取正在运行的 docker 容器列表，最准确的测试选择 open devin sandbox 容器。
+docker exec [CONTAINER ID] curl http://host.docker.internal:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
+#例如，docker exec cd9cc82f7a11 curl http://host.docker.internal:11434/api/generate -d '{"model":"codellama","prompt":"hi"}'
+```
+
+## 修复它
+
+现在让我们使其工作。使用 sudo 权限编辑 /etc/systemd/system/ollama.service。 （路径可能因 linux 版本而异）
+
+```bash
+sudo vi /etc/systemd/system/ollama.service
+```
+
+或者
+
+```bash
+sudo nano /etc/systemd/system/ollama.service
+```
+
+在 [Service] 括号内添加以下行
+
+```
+Environment="OLLAMA_HOST=0.0.0.0:11434"
+Environment="OLLAMA_ORIGINS=*"
+```
+
+然后保存，重新加载配置并重新启动服务。
+
+```bash
+sudo systemctl daemon-reload
+sudo systemctl restart ollama
+```
+
+最后测试 ollama 是否可以从容器内访问
+
+```bash
+ollama list # 获取已安装模型列表
+docker ps # 获取正在运行的 docker 容器列表，最准确的测试选择 open devin sandbox 容器。
+docker exec [CONTAINER ID] curl http://host.docker.internal:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
+```