Sync with OpenDevin Main branch

.github/.codecov.yml

@@ -1,6 +1,9 @@
 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:
@@ -14,6 +17,3 @@ coverage:
 comment: false
 github_checks:
     annotations: false
-
-ignore:
-  - "agenthub/SWE_agent/**" # SWE agent is deprecated

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -72,4 +72,4 @@ body:
     id: additional-context
     attributes:
       label: Logs, Errors, Screenshots, and Additional Context
-      description: LLM logs will be stored in the `logs/llm/default` folder. Please add any additional context about the problem here.
+      description: If you want to share the chat history you can click the thumbs-down (👎) button above the input field and you will get a shareable link (you can also click thumbs up when things are going well of course!). LLM logs will be stored in the `logs/llm/default` folder. Please add any additional context about the problem here.

.github/dependabot.yml

@@ -9,7 +9,14 @@ updates:
     directory: "/" # Location of package manifests
     schedule:
       interval: "daily"
+    open-pull-requests-limit: 20
   - package-ecosystem: "npm" # See documentation for possible values
     directory: "/frontend" # Location of package manifests
     schedule:
       interval: "daily"
+    open-pull-requests-limit: 20
+  - package-ecosystem: "npm" # See documentation for possible values
+    directory: "/docs" # Location of package manifests
+    schedule:
+      interval: "daily"
+    open-pull-requests-limit: 20

.github/pull_request_template.md

@@ -0,0 +1,8 @@
+**What is the problem that this fixes or functionality that this introduces? Does it fix any open issues?**
+
+---
+
+**Give a summary of what the PR does, explaining any non-trivial design decisions**
+
+---
+**Other references**

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

@@ -1,4 +1,4 @@
-name: Run e2e test with dummy agent
+name: Run E2E test with dummy agent
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -30,4 +30,13 @@ jobs:
           wget https://huggingface.co/BAAI/bge-small-en-v1.5/raw/main/1_Pooling/config.json -P /tmp/llama_index/models--BAAI--bge-small-en-v1.5/snapshots/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/1_Pooling/
       - name: Run tests
         run: |
-          poetry run python opendevin/core/main.py -t "do a flip" -m ollama/not-a-model -d ./workspace/ -c DummyAgent
+          set -e
+          poetry run python opendevin/core/main.py -t "do a flip" -d ./workspace/ -c DummyAgent
+      - name: Check exit code
+        run: |
+          if [ $? -ne 0 ]; then
+            echo "Test failed"
+            exit 1
+          else
+            echo "Test passed"
+          fi

.github/workflows/ghcr.yml

@@ -1,4 +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 +60,204 @@ 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", "local"]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'poetry'
+
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies
+
+      - name: Download sandbox Docker image
+        uses: actions/download-artifact@v4
+        with:
+          name: sandbox-docker-image-amd64
+          path: /tmp/
+
+      - name: Load sandbox image and run integration tests
+        env:
+          SANDBOX_BOX_TYPE: ${{ matrix.sandbox }}
+        run: |
+          # Load the Docker image and capture the output
+          output=$(docker load -i /tmp/sandbox_image_amd64.tar)
+
+          # Extract the first image name from the output
+          image_name=$(echo "$output" | grep -oP 'Loaded image: \K.*' | head -n 1)
+
+          # Print the full name of the image
+          echo "Loaded Docker image: $image_name"
+
+          SANDBOX_CONTAINER_IMAGE=$image_name TEST_IN_CI=true TEST_ONLY=true ./tests/integration/regenerate.sh
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+  ghcr_push:
+    runs-on: ubuntu-latest
+    # don't push if integration tests or sandbox tests fail
+    needs: [ghcr_build, 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
 
-  docker_build_success:
-    name: Docker Build Success
+  create_manifest:
     runs-on: ubuntu-latest
-    needs: ghcr_build_and_push
+    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:
-    - run: echo Done!
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Login to GHCR
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Create and push multi-platform manifest
+        run: |
+          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
+          echo "image name = $image_name"
+          tags=$(echo ${tags} | tr ' ' '\n')
+          for tag in $tags; do
+            echo 'tag = $tag'
+            docker buildx imagetools create --tag $image_name:$tag \
+              $image_name:${tag}_amd64 \
+              $image_name:${tag}_arm64
+          done

.github/workflows/lint.yml

@@ -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 }}
-        SANDBOX_TYPE: exec
+        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        SANDBOX_BOX_TYPE: ssh
       run: |
-        WORKSPACE_MOUNT_PATH=$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