fix eval_infer.sh to correctly copy SWE-Bench logs (#4111 )

Update LiteLLLM to 1.48.5 (#4110 )
(fix) Fix logging in shared eval file to prevent key disclosure (#4108 )
2026-04-29 03:00:45 -04:00 · 2024-09-29 18:39:18 -05:00 · 2024-09-29 06:42:59 +00:00 · 2024-09-28 19:33:16 +00:00 · 2024-09-28 18:52:01 +00:00 · 2024-09-29 02:19:59 +08:00
128 changed files with 2563 additions and 1752 deletions
@@ -14,20 +14,38 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Install poetry via pipx
+        run: pipx install poetry
      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.11'
-      - name: Set up environment
-        run: |
-          curl -sSL https://install.python-poetry.org | python3 -
-          poetry install --without evaluation,llama-index
-          poetry run playwright install --with-deps chromium
-          wget https://huggingface.co/BAAI/bge-small-en-v1.5/raw/main/1_Pooling/config.json -P /tmp/llama_index/models--BAAI--bge-small-en-v1.5/snapshots/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/1_Pooling/
+          cache: 'poetry'
+      - name: Install Python dependencies using Poetry
+        run: poetry install --without evaluation,llama-index
+      - name: Build Environment
+        run: make build
      - name: Run tests
        run: |
          set -e
-          poetry run python openhands/core/main.py -t "do a flip" -d ./workspace/ -c DummyAgent
+          poetry run python3 openhands/core/main.py -t "do a flip" -d ./workspace/ -c DummyAgent
      - name: Check exit code
        run: |
          if [ $? -ne 0 ]; then
@@ -25,7 +25,71 @@ on:
        required: true
        default: ''

+env:
+  BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST: nikolaik/python-nodejs:python3.11-nodejs22
+
 jobs:
+  # Builds the OpenHands Docker images
+  ghcr_build_app:
+    name: Build App Image
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    outputs:
+      hash_from_app_image: ${{ steps.get_hash_in_app_image.outputs.hash_from_app_image }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3.0.0
+        with:
+          image: tonistiigi/binfmt:latest
+      - name: Login to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Build and push app image
+        if: "!github.event.pull_request.head.repo.fork"
+        run: |
+          ./containers/build.sh -i openhands -o ${{ github.repository_owner }} --push
+      - name: Build app image
+        if: "github.event.pull_request.head.repo.fork"
+        run: |
+          ./containers/build.sh -i openhands -o ${{ github.repository_owner }} --load
+      - name: Get hash in App Image
+        id: get_hash_in_app_image
+        run: |
+          # Lowercase the repository owner
+          export REPO_OWNER=${{ github.repository_owner }}
+          REPO_OWNER=$(echo $REPO_OWNER | tr '[:upper:]' '[:lower:]')
+          # Run the build script in the app image
+          docker run -e SANDBOX_USER_ID=0 -v /var/run/docker.sock:/var/run/docker.sock ghcr.io/${REPO_OWNER}/openhands:${{ github.sha }} /bin/bash -c "mkdir -p containers/runtime; python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild" 2>&1 | tee docker-outputs.txt
+          # Get the hash from the build script
+          hash_from_app_image=$(cat docker-outputs.txt | grep "Hash for docker build directory" | awk -F "): " '{print $2}' | uniq | head -n1)
+          echo "hash_from_app_image=$hash_from_app_image" >> $GITHUB_OUTPUT
+          echo "Hash from app image: $hash_from_app_image"
+
+
  # Builds the runtime Docker images
  ghcr_build_runtime:
    name: Build Image
@@ -56,7 +120,9 @@ jobs:
          docker-images: false
          swap-storage: true
      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@v3.0.0
+        with:
+          image: tonistiigi/binfmt:latest
      - name: Login to GHCR
        uses: docker/login-action@v3
        with:
@@ -88,7 +154,7 @@ jobs:
      - name: Build and push runtime image ${{ matrix.base_image.image }}
        if: github.event.pull_request.head.repo.fork != true
        run: |
-          ./containers/build.sh runtime ${{ github.repository_owner }} --push ${{ matrix.base_image.tag }}
+          ./containers/build.sh -i runtime -o ${{ github.repository_owner }} --push -t ${{ matrix.base_image.tag }}
      # Forked repos can't push to GHCR, so we need to upload the image as an artifact
      - name: Build runtime image ${{ matrix.base_image.image }} for fork
        if: github.event.pull_request.head.repo.fork
@@ -104,6 +170,56 @@ jobs:
          name: runtime-${{ matrix.base_image.tag }}
          path: /tmp/runtime-${{ matrix.base_image.tag }}.tar

+  verify_hash_equivalence_in_runtime_and_app:
+    name: Verify Hash Equivalence in Runtime and Docker images
+    runs-on: ubuntu-latest
+    needs: [ghcr_build_runtime, ghcr_build_app]
+    strategy:
+      fail-fast: false
+      matrix:
+        base_image: ['nikolaik']
+    steps:
+      - uses: actions/checkout@v4
+      - name: Cache Poetry dependencies
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies
+      - name: Get hash in App Image
+        run: |
+          echo "Hash from app image: ${{ needs.ghcr_build_app.outputs.hash_from_app_image }}"
+          echo "hash_from_app_image=${{ needs.ghcr_build_app.outputs.hash_from_app_image }}" >> $GITHUB_ENV
+
+      - name: Get hash using code (development mode)
+        run: |
+          mkdir -p containers/runtime
+          poetry run python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild > output.txt 2>&1
+          hash_from_code=$(cat output.txt | grep "Hash for docker build directory" | awk -F "): " '{print $2}' | uniq | head -n1)
+          echo "hash_from_code=$hash_from_code" >> $GITHUB_ENV
+
+      - name: Compare hashes
+        run: |
+          echo "Hash from App Image: ${{ env.hash_from_app_image }}"
+          echo "Hash from Code: ${{ env.hash_from_code }}"
+          if [ "${{ env.hash_from_app_image }}" = "${{ env.hash_from_code }}" ]; then
+            echo "Hashes match!"
+          else
+            echo "Hashes do not match!"
+            exit 1
+          fi
+
  # Run unit tests with the EventStream runtime Docker images as root
  test_runtime_root:
    name: RT Unit Tests (Root)
@@ -115,6 +231,23 @@ jobs:
        base_image: ['nikolaik']
    steps:
      - uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
      # Forked repos can't push to GHCR, so we need to download the image as an artifact
      - name: Download runtime image for fork
        if: github.event.pull_request.head.repo.fork
@@ -176,6 +309,23 @@ jobs:
        base_image: ['nikolaik']
    steps:
      - uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
      # Forked repos can't push to GHCR, so we need to download the image as an artifact
      - name: Download runtime image for fork
        if: github.event.pull_request.head.repo.fork
@@ -238,6 +388,23 @@ jobs:
        base_image: ['nikolaik']
    steps:
      - uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
      # Forked repos can't push to GHCR, so we need to download the image as an artifact
      - name: Download runtime image for fork
        if: github.event.pull_request.head.repo.fork
@@ -290,7 +457,7 @@ jobs:
    name: All Runtime Tests Passed
    if: ${{ !cancelled() && !contains(needs.*.result, 'failure') && !contains(needs.*.result, 'cancelled') }}
    runs-on: ubuntu-latest
-    needs: [test_runtime_root, test_runtime_oh, runtime_integration_tests_on_linux]
+    needs: [test_runtime_root, test_runtime_oh, runtime_integration_tests_on_linux, verify_hash_equivalence_in_runtime_and_app]
    steps:
      - name: All tests passed
        run: echo "All runtime tests have passed successfully!"
@@ -299,7 +466,7 @@ jobs:
    name: All Runtime Tests Passed
    if: ${{ cancelled() || contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled') }}
    runs-on: ubuntu-latest
-    needs: [test_runtime_root, test_runtime_oh, runtime_integration_tests_on_linux]
+    needs: [test_runtime_root, test_runtime_oh, runtime_integration_tests_on_linux, verify_hash_equivalence_in_runtime_and_app]
    steps:
      - name: Some tests failed
        run: |
@@ -1,65 +0,0 @@
-# Workflow that builds, tests and then pushes the app docker images to the ghcr.io repository
-name: Build and Publish App Image
-
-# Always run on "main"
-# Always run on tags
-# Always run on PRs
-# Can also be triggered manually
-on:
-  push:
-    branches:
-      - main
-    tags:
-      - '*'
-  pull_request:
-  workflow_dispatch:
-    inputs:
-      reason:
-        description: 'Reason for manual trigger'
-        required: true
-        default: ''
-
-jobs:
-  # Builds the OpenHands Docker images
-  ghcr_build:
-    name: Build App Image
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-      - name: Login to GHCR
-        uses: docker/login-action@v3
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-      - name: Build and push app image
-        if: "!github.event.pull_request.head.repo.fork"
-        run: |
-          ./containers/build.sh openhands ${{ github.repository_owner }} --push
-      - name: Build app image
-        if: "github.event.pull_request.head.repo.fork"
-        run: |
-          ./containers/build.sh openhands image ${{ github.repository_owner }}
@@ -0,0 +1,126 @@
+name: Auto-Fix Tagged Issues with OpenHands
+
+on:
+  issues:
+    types: [labeled]
+
+permissions:
+  contents: write
+  pull-requests: write
+  issues: write
+
+jobs:
+  auto-fix:
+    if: github.event.label.name == 'fix-me'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.11'
+
+      - name: Comment on issue with start message
+        uses: actions/github-script@v6
+        with:
+          github-token: ${{secrets.GITHUB_TOKEN}}
+          script: |
+            github.rest.issues.createComment({
+              issue_number: context.issue.number,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: `OpenHands started fixing the issue! You can monitor the progress [here](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}).`
+            });
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install openhands-resolver
+
+      - name: Attempt to resolve issue
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          LLM_MODEL: ${{ secrets.LLM_MODEL }}
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+        run: |
+          python -m openhands_resolver.resolve_issues \
+            --repo ${{ github.repository }} \
+            --issue-numbers ${{ github.event.issue.number }}
+
+      - name: Check resolution result
+        id: check_result
+        run: |
+          if grep -q '"success":true' output/output.jsonl; then
+            echo "RESOLUTION_SUCCESS=true" >> $GITHUB_OUTPUT
+          else
+            echo "RESOLUTION_SUCCESS=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Create draft PR or push branch
+        env:
+          GITHUB_TOKEN: ${{ secrets.PAT_TOKEN }}
+          GITHUB_USERNAME: ${{ secrets.PAT_USERNAME }}
+          LLM_MODEL: ${{ secrets.LLM_MODEL }}
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+        run: |
+          if [ "${{ steps.check_result.outputs.RESOLUTION_SUCCESS }}" == "true" ]; then
+            python -m openhands_resolver.send_pull_request \
+              --issue-number ${{ github.event.issue.number }} \
+              --pr-type draft | tee pr_result.txt && \
+              grep "draft created" pr_result.txt | sed 's/.*\///g' > pr_number.txt
+          else
+            python -m openhands_resolver.send_pull_request \
+              --issue-number ${{ github.event.issue.number }} \
+              --pr-type branch \
+              --send-on-failure | tee branch_result.txt && \
+              grep "branch created" branch_result.txt | sed 's/.*\///g; s/.expand=1//g' > branch_name.txt
+          fi
+
+      - name: Comment on issue
+        uses: actions/github-script@v6
+        with:
+          github-token: ${{secrets.GITHUB_TOKEN}}
+          script: |
+            const fs = require('fs');
+            const issueNumber = context.issue.number;
+            const success = ${{ steps.check_result.outputs.RESOLUTION_SUCCESS }};
+
+            let prNumber = '';
+            let branchName = '';
+
+            try {
+              if (success) {
+                prNumber = fs.readFileSync('pr_number.txt', 'utf8').trim();
+              } else {
+                branchName = fs.readFileSync('branch_name.txt', 'utf8').trim();
+              }
+            } catch (error) {
+              console.error('Error reading file:', error);
+            }
+
+            if (success && prNumber) {
+              github.rest.issues.createComment({
+                issue_number: issueNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: `A potential fix has been generated and a draft PR #${prNumber} has been created. Please review the changes.`
+              });
+            } else if (!success && branchName) {
+              github.rest.issues.createComment({
+                issue_number: issueNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: `An attempt was made to automatically fix this issue, but it was unsuccessful. A branch named '${branchName}' has been created with the attempted changes. You can view the branch [here](https://github.com/${context.repo.owner}/${context.repo.repo}/tree/${branchName}). Manual intervention may be required.`
+              });
+            } else {
+              github.rest.issues.createComment({
+                issue_number: issueNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: `The workflow to fix this issue encountered an error. Please check the workflow logs for more information.`
+              });
+            }
@@ -89,6 +89,9 @@ jobs:
          sudo ln -sf $HOME/.colima/default/docker.sock /var/run/docker.sock
      - name: Build Environment
        run: make build
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
      - name: Run Tests
        run: poetry run pytest --forked --cov=agenthub --cov=openhands --cov-report=xml ./tests/unit
      - name: Upload coverage to Codecov
@@ -107,6 +110,9 @@ jobs:
        python-version: ['3.11']
    steps:
      - uses: actions/checkout@v4
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
      - name: Install poetry via pipx
        run: pipx install poetry
      - name: Set up Python
@@ -29,6 +29,9 @@ jobs:
    steps:
    - name: Checkout repository
      uses: actions/checkout@v4
+    - name: Set up Docker Buildx
+      id: buildx
+      uses: docker/setup-buildx-action@v3
    - name: Set up Python
      uses: actions/setup-python@v5
      with:
@@ -15,6 +15,9 @@ jobs:
    runs-on: ubuntu-latest
    steps:
    - uses: actions/checkout@v4
+    - name: Set up Docker Buildx
+      id: buildx
+      uses: docker/setup-buildx-action@v3
    - name: Set up Python
      uses: actions/setup-python@v5
      with:
@@ -1,113 +0,0 @@
-# Workflow that uses OpenHands to resolve a GitHub issue. Issue must be labeled 'solve-this'
-name: Use OpenHands to Resolve GitHub Issue
-
-on:
-  issues:
-    types: [labeled]
-
-permissions:
-  contents: write
-  pull-requests: write
-  issues: write
-
-jobs:
-  dogfood:
-    if: github.event.label.name == 'solve-this'
-    runs-on: ubuntu-latest
-    container:
-      image: ghcr.io/all-hands-ai/openhands
-      volumes:
-        - /var/run/docker.sock:/var/run/docker.sock
-    steps:
-    - name: install git, github cli
-      run: apt-get install -y git gh
-    - name: Checkout Repository
-      uses: actions/checkout@v4
-    - name: Write Task File
-      env:
-        ISSUE_TITLE: ${{ github.event.issue.title }}
-        ISSUE_BODY: ${{ github.event.issue.body }}
-      run: |
-        echo "TITLE:" > task.txt
-        echo "${ISSUE_TITLE}" >> task.txt
-        echo "" >> task.txt
-        echo "BODY:" >> task.txt
-        echo "${ISSUE_BODY}" >> task.txt
-    - name: Set up environment
-      run: |
-        curl -sSL https://install.python-poetry.org | python3 -
-        export PATH="/github/home/.local/bin:$PATH"
-        poetry install --without evaluation,llama-index
-        poetry run playwright install --with-deps chromium
-    - name: Run OpenHands
-      env:
-        ISSUE_TITLE: ${{ github.event.issue.title }}
-        ISSUE_BODY: ${{ github.event.issue.body }}
-        LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-      run: |
-        # Append path to launch poetry
-        export PATH="/github/home/.local/bin:$PATH"
-        # Append path to correctly import package, note: must set pwd at first
-        export PYTHONPATH=$(pwd):$PYTHONPATH
-        WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE poetry run python ./openhands/core/main.py -i 50 -f task.txt -d $GITHUB_WORKSPACE
-        rm task.txt
-    - name: Setup Git, Create Branch, and Commit Changes
-      run: |
-        # Setup Git configuration
-        git config --global --add safe.directory $PWD
-        git config --global user.name 'OpenHands'
-        git config --global user.email 'OpenHands@users.noreply.github.com'
-
-        # Create a unique branch name with a timestamp
-        BRANCH_NAME="fix/${{ github.event.issue.number }}-$(date +%Y%m%d%H%M%S)"
-
-        # Checkout new branch
-        git checkout -b $BRANCH_NAME
-
-        # Add all changes to staging, except task.txt
-        git add --all -- ':!task.txt'
-
-        # Commit the changes, if any
-        git commit -m "OpenHands: Resolve Issue #${{ github.event.issue.number }}"
-        if [ $? -ne 0 ]; then
-          echo "No changes to commit."
-          exit 0
-        fi
-
-        # Push changes
-        git push --set-upstream origin $BRANCH_NAME
-    - name: Fetch Default Branch
-      env:
-        GH_TOKEN: ${{ github.token }}
-      run: |
-        # Fetch the default branch using gh cli
-        DEFAULT_BRANCH=$(gh repo view --json defaultBranchRef --jq .defaultBranchRef.name)
-        echo "Default branch is $DEFAULT_BRANCH"
-        echo "DEFAULT_BRANCH=$DEFAULT_BRANCH" >> $GITHUB_ENV
-    - name: Generate PR
-      env:
-        GH_TOKEN: ${{ github.token }}
-      run: |
-        # Create PR and capture URL
-        PR_URL=$(gh pr create \
-          --title "OpenHands: Resolve Issue #2" \
-          --body "This PR was generated by OpenHands to resolve issue #2" \
-          --repo "foragerr/OpenHands" \
-          --head "${{ github.head_ref }}" \
-          --base "${{ env.DEFAULT_BRANCH }}" \
-          | grep -o 'https://github.com/[^ ]*')
-
-        # Extract PR number from URL
-        PR_NUMBER=$(echo "$PR_URL" | grep -o '[0-9]\+$')
-
-        # Set environment vars
-        echo "PR_URL=$PR_URL" >> $GITHUB_ENV
-        echo "PR_NUMBER=$PR_NUMBER" >> $GITHUB_ENV
-
-    - name: Post Comment
-      env:
-        GH_TOKEN: ${{ github.token }}
-      run: |
-        gh issue comment ${{ github.event.issue.number }} \
-          -b "OpenHands raised [PR #${{ env.PR_NUMBER }}](${{ env.PR_URL }}) to resolve this issue."
@@ -217,8 +217,6 @@ config.toml
 config.toml_
 config.toml.bak

-containers/agnostic_sandbox
-
 # swe-bench-eval
 image_build_logs
 run_instance_logs
@@ -0,0 +1,27 @@
+OpenHands is an automated AI software engineer. It is a repo with a Python backend
+(in the `openhands` directory) and TypeScript frontend (in the `frontend` directory).
+
+General Setup:
+- To set up the entire repo, including frontend and backend, run `make build`
+
+Backend:
+- Located in the `openhands` directory
+- Testing:
+  - All tests are in `tests/unit/test_*.py`
+  - To test new code, run `poetry run pytest tests/unit/test_xxx.py` where `xxx` is the appropriate file for the current functionality
+  - Write all tests with pytest
+
+Frontend:
+- Located in the `frontend` directory
+- Prerequisites: A recent version of NodeJS / NPM
+- Setup: Run `npm install` in the frontend directory
+- Testing:
+  - Run tests: `npm run test`
+  - To run specific tests: `npm run test -- -t "TestName"`
+- Building:
+  - Build for production: `npm run build`
+- Environment Variables:
+  - Set in `frontend/.env` or as environment variables
+  - Available variables: VITE_BACKEND_HOST, VITE_USE_TLS, VITE_INSECURE_SKIP_VERIFY, VITE_FRONTEND_PORT
+- Internationalization:
+  - Generate i18n declaration file: `npm run make-i18n`
@@ -190,7 +190,7 @@ build-frontend:
 # Start backend
 start-backend:
 	@echo "$(YELLOW)Starting backend...$(RESET)"
-	@poetry run uvicorn openhands.server.listen:app --host $(BACKEND_HOST) --port $(BACKEND_PORT) --reload --reload-exclude "workspace/*"
+	@poetry run uvicorn openhands.server.listen:app --host $(BACKEND_HOST) --port $(BACKEND_PORT) --reload --reload-exclude "$(shell pwd)/workspace"

 # Start frontend
 start-frontend:
@@ -42,6 +42,8 @@ system requirements and more information.
 ```bash
 export WORKSPACE_BASE=$(pwd)/workspace

+docker pull ghcr.io/all-hands-ai/runtime:0.9-nikolaik
+
 docker run -it --pull=always \
    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.9-nikolaik \
    -e SANDBOX_USER_ID=$(id -u) \
@@ -56,6 +58,10 @@ docker run -it --pull=always \

 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!

+You'll need a model provider and API key. One option that works well: [Claude 3.5 Sonnet](https://www.anthropic.com/api), but you have [many options](https://docs.all-hands.dev/modules/usage/llms).
+
+---
+
 You can also run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
 or as an [interactive CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode).

@@ -218,7 +218,6 @@ class BrowsingAgent(Agent):

        response = self.llm.completion(
            messages=self.llm.format_messages_for_llm(messages),
-            temperature=0.0,
            stop=[')```', ')\n```'],
        )
        return self.response_parser.parse(response)
@@ -10,20 +10,3 @@ The conceptual idea is illustrated below. At each turn, the agent can:
   - Execute any valid `Python` code with [an interactive Python interpreter](https://ipython.org/). This is simulated through `bash` command, see plugin system below for more details.

 ![image](https://github.com/All-Hands-AI/OpenHands/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
-
-## Plugin System
-
-To make the CodeAct agent more powerful with only access to `bash` action space, CodeAct agent leverages OpenHands's plugin system:
- [Jupyter plugin](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/runtime/plugins/jupyter): for IPython execution via bash command
- [Agent Skills plugin](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/runtime/plugins/agent_skills): Powerful bash command line tools for software development tasks introduced by [swe-agent](https://github.com/princeton-nlp/swe-agent).
-
-## Demo
-
-https://github.com/All-Hands-AI/OpenHands/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
-
-*Example of CodeActAgent with `gpt-4-turbo-2024-04-09` performing a data science task (linear regression)*
-
-## Work-in-progress & Next step
-
-[] Support web-browsing
-[] Complete the workflow for CodeAct agent to submit Github PRs
@@ -6,7 +6,6 @@ from openhands.events.action import (
    AgentDelegateAction,
    AgentFinishAction,
    CmdRunAction,
-    FileEditAction,
    IPythonRunCellAction,
    MessageAction,
 )
@@ -17,7 +16,6 @@ class CodeActResponseParser(ResponseParser):
    - CmdRunAction(command) - bash command to run
    - IPythonRunCellAction(code) - IPython code to run
    - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
-    - FileEditAction(diff_block) - Search/Replace block to edit.
    - MessageAction(content) - Message action to run (e.g. ask for clarification)
    - AgentFinishAction() - end the interaction
    """
@@ -30,7 +28,6 @@ class CodeActResponseParser(ResponseParser):
            CodeActActionParserCmdRun(),
            CodeActActionParserIPythonRunCell(),
            CodeActActionParserAgentDelegate(),
-            CodeActActionParserFileEdit(),
        ]
        self.default_parser = CodeActActionParserMessage()

@@ -42,7 +39,11 @@ class CodeActResponseParser(ResponseParser):
        action = response.choices[0].message.content
        if action is None:
            return ''
-        for lang in ['bash', 'ipython', 'edit', 'browse']:
+        for lang in ['bash', 'ipython', 'browse']:
+            # special handling for DeepSeek: it has stop-word bug and returns </execute_ipython instead of </execute_ipython>
+            if f'</execute_{lang}' in action and f'</execute_{lang}>' not in action:
+                action = action.replace(f'</execute_{lang}', f'</execute_{lang}>')
+
            if f'<execute_{lang}>' in action and f'</execute_{lang}>' not in action:
                action += f'</execute_{lang}>'
        return action
@@ -161,33 +162,6 @@ class CodeActActionParserAgentDelegate(ActionParser):
        return AgentDelegateAction(agent='BrowsingAgent', inputs={'task': task})


-class CodeActActionParserFileEdit(ActionParser):
-    """Parser action:
-    - FileEditAction(diff_block) - Search/Replace block to edit.
-    """
-
-    def __init__(
-        self,
-    ):
-        self.diff_block = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.diff_block = re.search(
-            r'<execute_edit>(.*)</execute_edit>', action_str, re.DOTALL
-        )
-        return self.diff_block is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.diff_block is not None
-        ), 'self.diff_block should not be None when parse is called'
-        thought = action_str.replace(self.diff_block.group(0), '').strip()
-        return FileEditAction(
-            diff_block=self.diff_block.group(1).strip(),
-            thought=thought,
-        )
-
-
 class CodeActActionParserMessage(ActionParser):
    """Parser action:
    - MessageAction(content) - Message action to run (e.g. ask for clarification)
@@ -5,22 +5,18 @@ from agenthub.codeact_agent.action_parser import CodeActResponseParser
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig
-from openhands.core.exceptions import OperationCancelled
-from openhands.core.logger import openhands_logger as logger
 from openhands.core.message import ImageContent, Message, TextContent
 from openhands.events.action import (
    Action,
    AgentDelegateAction,
    AgentFinishAction,
    CmdRunAction,
-    FileEditAction,
    IPythonRunCellAction,
    MessageAction,
 )
 from openhands.events.observation import (
    AgentDelegateObservation,
    CmdOutputObservation,
-    FileEditObservation,
    IPythonRunCellObservation,
    UserRejectObservation,
 )
@@ -38,7 +34,7 @@ from openhands.utils.prompt import PromptManager


 class CodeActAgent(Agent):
-    VERSION = '1.10'
+    VERSION = '1.9'
    """
    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.
@@ -106,8 +102,6 @@ class CodeActAgent(Agent):
            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, FileEditAction):
-            return f'{action.thought}\n<execute_edit>\n{action.diff_block}\n</execute_edit>'
        elif isinstance(action, MessageAction):
            return action.content
        elif isinstance(action, AgentFinishAction) and action.source == 'agent':
@@ -117,7 +111,6 @@ class CodeActAgent(Agent):
    def get_action_message(self, action: Action) -> Message | None:
        if (
            isinstance(action, AgentDelegateAction)
-            or isinstance(action, FileEditAction)
            or isinstance(action, CmdRunAction)
            or isinstance(action, IPythonRunCellAction)
            or isinstance(action, MessageAction)
@@ -158,9 +151,6 @@ class CodeActAgent(Agent):
            text = '\n'.join(splitted)
            text = truncate_content(text, max_message_chars)
            return Message(role='user', content=[TextContent(text=text)])
-        elif isinstance(obs, FileEditObservation):
-            text = obs_prefix + truncate_content(obs.content, max_message_chars)
-            return Message(role='user', content=[TextContent(text=text)])
        elif isinstance(obs, AgentDelegateObservation):
            text = obs_prefix + truncate_content(
                obs.outputs['content'] if 'content' in obs.outputs else '',
@@ -172,7 +162,7 @@ class CodeActAgent(Agent):
            text += '\n[Error occurred in processing last action]'
            return Message(role='user', content=[TextContent(text=text)])
        elif isinstance(obs, UserRejectObservation):
-            text = obs_prefix + truncate_content(obs.content, max_message_chars)
+            text = 'OBSERVATION:\n' + truncate_content(obs.content, max_message_chars)
            text += '\n[Last action has been rejected by the user]'
            return Message(role='user', content=[TextContent(text=text)])
        else:
@@ -195,7 +185,6 @@ class CodeActAgent(Agent):
        - CmdRunAction(command) - bash command to run
        - IPythonRunCellAction(code) - IPython code to run
        - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
-        - FileEditAction(diff_block) - Search/Replace block to edit.
        - MessageAction(content) - Message action to run (e.g. ask for clarification)
        - AgentFinishAction() - end the interaction
        """
@@ -212,26 +201,10 @@ class CodeActAgent(Agent):
                '</execute_ipython>',
                '</execute_bash>',
                '</execute_browse>',
-                '</execute_edit>',
            ],
        }

-        if self.llm.is_caching_prompt_active():
-            params['extra_headers'] = {
-                'anthropic-beta': 'prompt-caching-2024-07-31',
-            }
-
-        # TODO: move exception handling to agent_controller
-        try:
-            response = self.llm.completion(**params)
-        except OperationCancelled as e:
-            raise e
-        except Exception as e:
-            logger.error(f'{e}')
-            error_message = '{}: {}'.format(type(e).__name__, str(e).split('\n')[0])
-            return AgentFinishAction(
-                thought=f'Agent encountered an error while processing the last action.\nError: {error_message}\nPlease try again.'
-            )
+        response = self.llm.completion(**params)

        return self.action_parser.parse(response)

@@ -19,44 +19,22 @@ the assistant should retry running the command in the background.
 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>.
-{% endset %}
-{% set EDIT_DIFF_PREFIX %}
-The assistant can edit files with <execute_edit> and </execute_edit>. Each change must be described with a SEARCH/REPLACE block.
-Every SEARCH section must EXACTLY MATCH the existing file content, character for character, including all comments, docstrings, etc. SEARCH/REPLACE blocks will replace all matching occurrences. Include enough lines to make the SEARCH blocks uniquely match the lines to change.
-Keep SEARCH/REPLACE blocks as concise as possible. Break large SEARCH/REPLACE blocks into a series of smaller blocks that each change a small portion of the file.
-To move code within a file, use 2 SEARCH/REPLACE blocks: 1 to delete it from its current location, 1 to insert it in the new location.
-If you want to put code in a new file, use a SEARCH/REPLACE block with: a new file path, an empty `SEARCH` section and the new file's contents in the `REPLACE` section.
-
-Every SEARCH/REPLACE block must use this format:
-1. The FULL file path alone on a line, verbatim. No bold asterisks, no quotes around it, no escaping of characters, etc.
-2. The start of search block: <<<<<<< SEARCH
-3. A contiguous chunk of lines to search for in the existing source code
-4. The dividing line: =======
-5. The lines to replace into the source code
-6. The end of the replace block: >>>>>>> REPLACE
-
-For example,
-<execute_edit>
-demo.py
-<<<<<<< SEARCH
-    print("hello")
-=======
-    print("goodbye")
->>>>>>> REPLACE
-</execute_edit>
-
 {% endset %}
 {% set 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.
 {% endset %}
-{% set SYSTEM_PREFIX = MINIMAL_SYSTEM_PREFIX + BROWSING_PREFIX + EDIT_DIFF_PREFIX + PIP_INSTALL_PREFIX %}
+{% set SYSTEM_PREFIX = MINIMAL_SYSTEM_PREFIX + BROWSING_PREFIX + PIP_INSTALL_PREFIX %}
 {% set COMMAND_DOCS %}
 Apart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:
 {{ agent_skills_docs }}
 IMPORTANT:
 - `open_file` only returns the first 100 lines of the file by default! The assistant MUST use `scroll_down` repeatedly to read the full file BEFORE making edits!
+- The assistant shall adhere to THE `edit_file_by_replace`, `append_file` and `insert_content_at_line` FUNCTIONS REQUIRING PROPER INDENTATION. If the assistant would like to add the line '        print(x)', it must fully write the line out, with all leading spaces before the code!
 - Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
 - Any code issued should be less than 50 lines to avoid context being cut off!
+- After EVERY `create_file` the method `append_file` shall be used to write the FIRST content!
+- For `edit_file_by_replace` NEVER provide empty parameters!
+- For `edit_file_by_replace` the file must be read fully before any replacements!
 {% endset %}
 {% set SYSTEM_SUFFIX %}
 Responses should be concise.
@@ -4,12 +4,23 @@
 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 new Python file `app.py`:
-<execute_edit>
-app.py
-<<<<<<< SEARCH
-=======
-from flask import Flask
+Sure! Let me create a Python file `app.py`:
+<execute_ipython>
+create_file('app.py')
+</execute_ipython>
+
+USER:
+OBSERVATION:
+[File: /workspace/app.py (1 lines total)]
+(this is the beginning of the file)
+1|
+(this is the end of the file)
+[File app.py created.]
+
+ASSISTANT:
+Now I will write the Python code for starting a web server and save it to the file `app.py`:
+<execute_ipython>
+EDITED_CODE="""from flask import Flask
 app = Flask(__name__)

@app.route('/')
@@ -18,17 +29,30 @@ def index():
    return str(numbers)

 if __name__ == '__main__':
-    app.run(port=5000)
->>>>>>> REPLACE
-</execute_edit>
+    app.run(port=5000)"""

+insert_content_at_line(
+  'app.py',
+  1,
+  EDITED_CODE,
+)
+</execute_ipython>

 USER:
 OBSERVATION:
-I updated the file app.py by
-appending:
-from flask import Flask
-app = Flask(__name__)
+(this is the beginning of the file)
+1|from flask import Flask
+2|app = Flask(__name__)
+3|
+4|@app.route('/')
+5|def index():
+6|    numbers = list(range(1, 11))
+7|    return str(numbers)
+8|
+9|if __name__ == '__main__':
+10|    app.run(port=5000)
+(this is the end of the file)
+[File updated (edited at line 1). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]

 ASSISTANT:
 I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you:
@@ -153,22 +177,30 @@ USER:

 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_edit>
-app.py
-<<<<<<< SEARCH
-    return str(numbers)
-=======
-    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
->>>>>>> REPLACE
-</execute_edit>
+<execute_ipython>
+edit_file_by_replace(
+  'app.py',
+  to_replace="    return str(numbers)",
+  new_content="    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'",
+)
+</execute_ipython>

 USER:
 Observation:
-I updated the file app.py by
-replacing:
-    return str(numbers)
-with:
-    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
+[File: /workspace/app.py (10 lines total after edit)]
+(this is the beginning of the file)
+1|from flask import Flask
+2|app = Flask(__name__)
+3|
+4|@app.route('/')
+5|def index():
+6|    numbers = list(range(1, 11))
+7|    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
+8|
+9|if __name__ == '__main__':
+10|    app.run(port=5000)
+(this is the end of the file)
+[File updated (edited at line 7). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]

 ASSISTANT:
 Running the updated file:
@@ -166,7 +166,6 @@ class CodeActSWEAgent(Agent):
                '</execute_ipython>',
                '</execute_bash>',
            ],
-            temperature=0.0,
        )

        return self.response_parser.parse(response)
@@ -78,7 +78,6 @@ class MicroAgent(Agent):
        message = Message(role='user', content=content)
        resp = self.llm.completion(
            messages=self.llm.format_messages_for_llm(message),
-            temperature=0.0,
        )
        action_resp = resp['choices'][0]['message']['content']
        action = parse_response(action_resp)
@@ -112,7 +112,7 @@ api_key = "your-api-key"
 #embedding_deployment_name = ""

 # Embedding model to use
-embedding_model = ""
+embedding_model = "local"

 # Maximum number of characters in an observation's content
 #max_message_chars = 10000
@@ -146,8 +146,8 @@ model = "gpt-4o"
 # Drop any unmapped (unsupported) params without causing an exception
 #drop_params = false

-# Using the prompt caching feature provided by the LLM
-#caching_prompt = false
+# Using the prompt caching feature if provided by the LLM and supported
+#caching_prompt = true

 # Base URL for the OLLAMA API
 #ollama_base_url = ""
@@ -188,7 +188,7 @@ model = "gpt-4o-mini"
 #memory_max_threads = 2

 # LLM config group to use
-#llm_config = 'llm'
+#llm_config = 'your-llm-config-group'

 [agent.RepoExplorerAgent]
 # Example: use a cheaper model for RepoExplorerAgent to reduce cost, especially
@@ -232,7 +232,7 @@ llm_config = 'gpt3'
 [security]

 # Enable confirmation mode
-#confirmation_mode = true
+#confirmation_mode = false

 # The security analyzer to use
 #security_analyzer = ""
@@ -70,10 +70,11 @@ RUN playwright install --with-deps chromium
 COPY --chown=openhands:app --chmod=770 ./openhands ./openhands
 COPY --chown=openhands:app --chmod=777 ./openhands/runtime/plugins ./openhands/runtime/plugins
 COPY --chown=openhands:app --chmod=770 ./agenthub ./agenthub
-COPY --chown=openhands:app --chmod=770 ./pyproject.toml ./pyproject.toml
-COPY --chown=openhands:app --chmod=770 ./poetry.lock ./poetry.lock
-COPY --chown=openhands:app --chmod=770 ./README.md ./README.md
-COPY --chown=openhands:app --chmod=770 ./MANIFEST.in ./MANIFEST.in
+COPY --chown=openhands:app ./pyproject.toml ./pyproject.toml
+COPY --chown=openhands:app ./poetry.lock ./poetry.lock
+COPY --chown=openhands:app ./README.md ./README.md
+COPY --chown=openhands:app ./MANIFEST.in ./MANIFEST.in
+COPY --chown=openhands:app ./LICENSE ./LICENSE

 # This is run as "openhands" user, and will create __pycache__ with openhands:openhands ownership
 RUN python openhands/core/download.py # No-op to download assets
@@ -1,13 +1,40 @@
 #!/bin/bash
 set -eo pipefail

-image_name=$1
-org_name=$2
+# Initialize variables with default values
+image_name=""
+org_name=""
 push=0
-if [[ $3 == "--push" ]]; then
-  push=1
+load=0
+tag_suffix=""
+
+# Function to display usage information
+usage() {
+    echo "Usage: $0 -i <image_name> [-o <org_name>] [--push] [--load] [-t <tag_suffix>]"
+    echo "  -i: Image name (required)"
+    echo "  -o: Organization name"
+    echo "  --push: Push the image"
+    echo "  --load: Load the image"
+    echo "  -t: Tag suffix"
+    exit 1
+}
+
+# Parse command-line options
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        -i) image_name="$2"; shift 2 ;;
+        -o) org_name="$2"; shift 2 ;;
+        --push) push=1; shift ;;
+        --load) load=1; shift ;;
+        -t) tag_suffix="$2"; shift 2 ;;
+        *) usage ;;
+    esac
+done
+# Check if required arguments are provided
+if [[ -z "$image_name" ]]; then
+    echo "Error: Image name is required."
+    usage
 fi
-tag_suffix=$4

 echo "Building: $image_name"
 tags=()
@@ -95,14 +122,35 @@ if [[ $push -eq 1 ]]; then
  args+=" --cache-to=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag,mode=max"
 fi

+if [[ $load -eq 1 ]]; then
+  args+=" --load"
+fi
+
 echo "Args: $args"

+# Modify the platform selection based on --load flag
+if [[ $load -eq 1 ]]; then
+  # When loading, build only for the current platform
+  platform=$(docker version -f '{{.Server.Os}}/{{.Server.Arch}}')
+else
+  # For push or without load, build for multiple platforms
+  platform="linux/amd64,linux/arm64"
+fi
+
+echo "Building for platform(s): $platform"
+
 docker buildx build \
  $args \
  --build-arg OPENHANDS_BUILD_VERSION="$OPENHANDS_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 \
+  --platform $platform \
  --provenance=false \
  -f "$dir/Dockerfile" \
  "$DOCKER_BASE_DIR"
+
+# If load was requested, print the loaded images
+if [[ $load -eq 1 ]]; then
+  echo "Local images built:"
+  docker images "$DOCKER_REPOSITORY" --format "{{.Repository}}:{{.Tag}}"
+fi
@@ -1,44 +0,0 @@
-FROM ubuntu:22.04
-
-# install basic packages
-RUN apt-get update && apt-get install -y \
-    curl \
-    wget \
-    git \
-    vim \
-    nano \
-    unzip \
-    zip \
-    python3 \
-    python3-pip \
-    python3-venv \
-    python3-dev \
-    build-essential \
-    openssh-server \
-    sudo \
-    gcc \
-    jq \
-    g++ \
-    make \
-    iproute2 \
-    && rm -rf /var/lib/apt/lists/*
-
-RUN mkdir -p -m0755 /var/run/sshd
-
-# symlink python3 to python
-RUN ln -s /usr/bin/python3 /usr/bin/python
-
-# ==== OpenHands Runtime Client ====
-RUN mkdir -p /openhands && mkdir -p /openhands/logs && chmod 777 /openhands/logs
-RUN wget --progress=bar:force -O Miniforge3.sh "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"
-RUN bash Miniforge3.sh -b -p /openhands/miniforge3
-RUN chmod -R g+w /openhands/miniforge3
-RUN bash -c ". /openhands/miniforge3/etc/profile.d/conda.sh && conda config --set changeps1 False && conda config --append channels conda-forge"
-RUN echo "" > /openhands/bash.bashrc
-RUN rm -f Miniforge3.sh
-
-# - agentskills dependencies
-RUN /openhands/miniforge3/bin/pip install --upgrade pip
-RUN /openhands/miniforge3/bin/pip install jupyterlab notebook jupyter_kernel_gateway flake8
-RUN /openhands/miniforge3/bin/pip install python-docx PyPDF2 python-pptx pylatexenc openai
-RUN /openhands/miniforge3/bin/pip install python-dotenv toml termcolor pydantic python-docx pyyaml docker pexpect tenacity e2b browsergym minio
@@ -1,4 +0,0 @@
-DOCKER_REGISTRY=ghcr.io
-DOCKER_ORG=all-hands-ai
-DOCKER_IMAGE=sandbox
-DOCKER_BASE_DIR="."
@@ -18,6 +18,8 @@ existing code that you'd like to modify.
 ```bash
 export WORKSPACE_BASE=$(pwd)/workspace

+docker pull ghcr.io/all-hands-ai/runtime:0.9-nikolaik
+
 docker run -it --pull=always \
    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.9-nikolaik \
    -e SANDBOX_USER_ID=$(id -u) \
@@ -54,7 +56,7 @@ The `Advanced Options` also allow you to specify a `Base URL` if required.

 ## Versions

-The command above pulls the `0.9` tag, which represents the most recent stable release of OpenHands. You have other options as well:
+The command above pulls the most recent stable release of OpenHands. You have other options as well:
 - For a specific release, use `ghcr.io/all-hands-ai/openhands:$VERSION`, replacing $VERSION with the version number.
 - We use semver, and release major, minor, and patch tags. So `0.9` will automatically point to the latest `0.9.x` release, and `0` will point to the latest `0.x.x` release.
 - For the most up-to-date development version, you can use `ghcr.io/all-hands-ai/openhands:main`. This version is unstable and is recommended for testing or development purposes only.
@@ -0,0 +1,71 @@
+# Debugging
+
+The following is intended as a primer on debugging OpenHands for Development purposes.
+
+## Server / VSCode
+
+The following `launch.json` will allow debugging the agent, controller and server elements, but not the sandbox (Which runs inside docker). It will ignore any changes inside the `workspace/` directory:
+
+```
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "OpenHands CLI",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "openhands.core.cli",
+            "justMyCode": false
+        },
+        {
+            "name": "OpenHands WebApp",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "uvicorn",
+            "args": [
+                "openhands.server.listen:app",
+                "--reload",
+                "--reload-exclude",
+                "${workspaceFolder}/workspace",
+                "--port",
+                "3000"
+            ],
+            "justMyCode": false
+        }
+    ]
+}
+```
+
+More specific debugging configurations which include more parameters may be specified:
+
+```
+    ...
+    {
+      "name": "Debug CodeAct",
+      "type": "debugpy",
+      "request": "launch",
+      "module": "openhands.core.main",
+      "args": [
+        "-t",
+        "Ask me what your task is.",
+        "-d",
+        "${workspaceFolder}/workspace",
+        "-c",
+        "CodeActAgent",
+        "-l",
+        "llm.o1",
+        "-n",
+        "prompts"
+      ],
+      "justMyCode": false
+    }
+    ...
+```
+
+Values in the snippet above can be updated such that:
+
+    * *t*: the task
+    * *d*: the openhands workspace directory
+    * *c*: the agent
+    * *l*: the LLM config (pre-defined in config.toml)
+    * *n*: session name (e.g. eventstream name)
@@ -177,6 +177,7 @@ spec:
      claimName: docker-pvc
 ```

+
 ```bash
 # create the pod
 $ oc create -f pod.yaml
@@ -262,3 +263,167 @@ Events:                   <none>
 6. Connect to OpenHands UI, configure the Agent, then test:

 ![image](https://github.com/user-attachments/assets/12f94804-a0c7-4744-b873-e003c9caf40e)
+
+
+
+## GCP GKE Openhands deployment
+
+**Warning**: this deployment grants the OpenHands application access to the Kubernetes docker socket, which creates security risk. Use at your own discretion.
+1- Create policy for privillege access
+2- Create gke credentials(optional)
+3- Create openhands deployment
+4- Verification and ui access commands
+5- Tshoot pod to verify the internal container
+
+1. create policy for privillege access
+```bash
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: privileged-role
+rules:
+- apiGroups: [""]
+  resources: ["pods"]
+  verbs: ["create", "get", "list", "watch", "delete"]
+- apiGroups: ["apps"]
+  resources: ["deployments"]
+  verbs: ["create", "get", "list", "watch", "delete"]
+- apiGroups: [""]
+  resources: ["pods/exec"]
+  verbs: ["create"]
+- apiGroups: [""]
+  resources: ["pods/log"]
+  verbs: ["get"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: privileged-role-binding
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: privileged-role
+subjects:
+- kind: ServiceAccount
+  name: default  # Change to your service account name
+  namespace: default
+```
+2. create gke credentials(optional)
+```bash
+kubectl create secret generic google-cloud-key \
+  --from-file=key.json=/path/to/your/google-cloud-key.json
+  ```
+3. create openhands deployment
+## as this is tested for the single worker node if you have multiple specify the flag for the single worker
+
+```bash
+kind: Deployment
+metadata:
+  name: openhands-app-2024
+  labels:
+    app: openhands-app-2024
+spec:
+  replicas: 1  # You can increase this number for multiple replicas
+  selector:
+    matchLabels:
+      app: openhands-app-2024
+  template:
+    metadata:
+      labels:
+        app: openhands-app-2024
+    spec:
+      containers:
+      - name: openhands-app-2024
+        image: ghcr.io/all-hands-ai/openhands:main
+        env:
+        - name: SANDBOX_USER_ID
+          value: "1000"
+        - name: SANDBOX_API_HOSTNAME
+          value: '10.164.0.4'
+        - name: WORKSPACE_MOUNT_PATH
+          value: "/tmp/workspace_base"
+        - name: GOOGLE_APPLICATION_CREDENTIALS
+          value: "/tmp/workspace_base/google-cloud-key.json"
+        volumeMounts:
+        - name: workspace-volume
+          mountPath: /tmp/workspace_base
+        - name: docker-sock
+          mountPath: /var/run/docker.sock
+        - name: google-credentials
+          mountPath: "/tmp/workspace_base/google-cloud-key.json"
+        securityContext:
+          privileged: true  # Add this to allow privileged access
+        ports:
+        - containerPort: 3000
+      - name: openhands-sandbox-2024
+        image: ghcr.io/opendevin/sandbox:main
+    #    securityContext:
+    #      privileged: true  # Add this to allow privileged access
+        ports:
+        - containerPort: 51963
+        command: ["/usr/sbin/sshd", "-D", "-p 51963", "-o", "PermitRootLogin=yes"]
+      volumes:
+      #- name: workspace-volume
+      #  persistentVolumeClaim:
+      #    claimName: workspace-pvc
+      - name: workspace-volume
+        emptyDir: {}
+      - name: docker-sock
+        hostPath:
+          path: /var/run/docker.sock       # Use host's Docker socket
+          type: Socket
+      - name: google-credentials
+        secret:
+          secretName: google-cloud-key
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: openhands-app-2024-svc
+spec:
+  selector:
+    app: openhands-app-2024
+  ports:
+  - name: http
+    protocol: TCP
+    port: 80
+    targetPort: 3000
+  - name: ssh
+    protocol: TCP
+    port: 51963
+    targetPort: 51963
+  type: LoadBalancer
+  ```
+
+5. Tshoot pod to verify the internal container
+### if you want to know more regarding the internal container runtime use below mention pod deployment use kubectl exec -it to enter into container and you can check the contaienr run time using normal docker commands like "docker ps -a"
+
+```bash
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: docker-in-docker
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: docker-in-docker
+  template:
+    metadata:
+      labels:
+        app: docker-in-docker
+    spec:
+      containers:
+      - name: dind
+        image: docker:20.10-dind
+        securityContext:
+          privileged: true
+        volumeMounts:
+        - name: docker-sock
+          mountPath: /var/run/docker.sock
+      volumes:
+      - name: docker-sock
+        hostPath:
+          path: /var/run/docker.sock
+          type: Socket
+```
@@ -59,9 +59,21 @@ We have a few guides for running OpenHands with specific model providers:

 ### API retries and rate limits

-Some LLMs have rate limits and may require retries. OpenHands will automatically retry requests if it receives a 429 error or API connection error.
-You can set the following environment variables to control the number of retries and the time between retries:
+LLM providers typically have rate limits, sometimes very low, and may require retries. OpenHands will automatically retry requests if it receives a Rate Limit Error (429 error code), API connection error, or other transient errors.
+
+You can customize these options as you need for the provider you're using. Check their documentation, and set the following environment variables to control the number of retries and the time between retries:

 * `LLM_NUM_RETRIES` (Default of 8)
 * `LLM_RETRY_MIN_WAIT` (Default of 15 seconds)
 * `LLM_RETRY_MAX_WAIT` (Default of 120 seconds)
+* `LLM_RETRY_MULTIPLIER` (Default of 2)
+
+If you running `openhands` in development mode, you can also set these options to the values you need in `config.toml` file:
+
+```toml
+[llm]
+num_retries = 8
+retry_min_wait = 15
+retry_max_wait = 120
+retry_multiplier = 2
+```
@@ -83,6 +83,10 @@ const sidebars: SidebarsConfig = {
        {
          type: 'doc',
          id: 'usage/how-to/openshift-example',
+        },
+        {
+          type: 'doc',
+          id: 'usage/how-to/debugging',
        }
      ]
    },
@@ -256,7 +256,6 @@ def process_instance(
 if __name__ == '__main__':
    args = parse_arguments()
    dataset = load_dataset('RajMaheshwari/Exercism-Python')
-    dataset = dataset.shuffle(seed=42)
    aider_bench_tests = dataset['train'].to_pandas()

    llm_config = None
@@ -106,7 +106,7 @@ if [ -z "$INSTANCE_ID" ]; then
        rm -rf $RESULT_OUTPUT_DIR/eval_outputs
    fi

-    mv run_instance_logs/$RUN_ID/$MODEL_NAME_OR_PATH $RESULT_OUTPUT_DIR
+    mv logs/run_evaluation/$RUN_ID/$MODEL_NAME_OR_PATH $RESULT_OUTPUT_DIR
    mv $RESULT_OUTPUT_DIR/$MODEL_NAME_OR_PATH $RESULT_OUTPUT_DIR/eval_outputs
    echo "RUN_ID: $RUN_ID" > $RESULT_OUTPUT_DIR/run_id.txt

@@ -40,9 +40,9 @@ class EvalMetadata(BaseModel):
    def model_dump_json(self, *args, **kwargs):
        dumped = super().model_dump_json(*args, **kwargs)
        dumped_dict = json.loads(dumped)
-        logger.debug(f'Dumped metadata: {dumped_dict}')
        # avoid leaking sensitive information
        dumped_dict['llm_config'] = self.llm_config.to_safe_dict()
+        logger.debug(f'Dumped metadata: {dumped_dict}')
        return json.dumps(dumped_dict)


@@ -375,18 +375,27 @@ def reset_logger_for_multiprocessing(
    # Remove all existing handlers from logger
    for handler in logger.handlers[:]:
        logger.removeHandler(handler)
-    # add back the console handler to print ONE line
-    logger.addHandler(get_console_handler())
+
+    # add console handler to print ONE line
+    console_handler = get_console_handler(log_level=logging.INFO)
+    console_handler.setFormatter(
+        logging.Formatter(
+            f'Instance {instance_id} - ' + '%(asctime)s - %(levelname)s - %(message)s'
+        )
+    )
+    logger.addHandler(console_handler)
    logger.info(
        f'Starting evaluation for instance {instance_id}.\n'
        f'Hint: run "tail -f {log_file}" to see live logs in a separate shell'
    )
-    # Remove all existing handlers from logger
-    for handler in logger.handlers[:]:
-        logger.removeHandler(handler)
+    # Only log WARNING or higher to console
+    console_handler.setLevel(logging.WARNING)
+
+    # Log INFO and above to file
    os.makedirs(os.path.dirname(log_file), exist_ok=True)
    file_handler = logging.FileHandler(log_file)
    file_handler.setFormatter(
        logging.Formatter('%(asctime)s - %(levelname)s - %(message)s')
    )
+    file_handler.setLevel(logging.INFO)
    logger.addHandler(file_handler)
@@ -1,12 +1,12 @@
 {
  "name": "openhands-frontend",
-  "version": "0.9.4",
+  "version": "0.9.6",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "openhands-frontend",
-      "version": "0.9.4",
+      "version": "0.9.6",
      "dependencies": {
        "@monaco-editor/react": "^4.6.0",
        "@nextui-org/react": "^2.4.8",
@@ -33,7 +33,7 @@
        "react-syntax-highlighter": "^15.5.0",
        "remark-gfm": "^4.0.0",
        "tailwind-merge": "^2.5.2",
-        "vite": "^5.4.7",
+        "vite": "^5.4.8",
        "web-vitals": "^3.5.2"
      },
      "devDependencies": {
@@ -41,8 +41,8 @@
        "@testing-library/jest-dom": "^6.5.0",
        "@testing-library/react": "^16.0.1",
        "@testing-library/user-event": "^14.5.2",
-        "@types/node": "^22.6.1",
-        "@types/react": "^18.3.8",
+        "@types/node": "^22.7.3",
+        "@types/react": "^18.3.9",
        "@types/react-dom": "^18.3.0",
        "@types/react-highlight": "^0.12.8",
        "@types/react-syntax-highlighter": "^15.5.13",
@@ -60,11 +60,11 @@
        "eslint-plugin-react": "^7.35.0",
        "eslint-plugin-react-hooks": "^4.6.2",
        "husky": "^9.1.6",
-        "jsdom": "^25.0.0",
+        "jsdom": "^25.0.1",
        "lint-staged": "^15.2.10",
        "postcss": "^8.4.47",
        "prettier": "^3.3.3",
-        "tailwindcss": "^3.4.12",
+        "tailwindcss": "^3.4.13",
        "typescript": "^5.6.2",
        "vite-tsconfig-paths": "^5.0.1",
        "vitest": "^1.6.0"
@@ -4860,9 +4860,9 @@
      "integrity": "sha512-nG96G3Wp6acyAgJqGasjODb+acrI7KltPiRxzHPXnP3NgI28bpQDRv53olbqGXbfcgF5aiiHmO3xpwEpS5Ld9g=="
    },
    "node_modules/@types/node": {
-      "version": "22.6.1",
-      "resolved": "https://registry.npmjs.org/@types/node/-/node-22.6.1.tgz",
-      "integrity": "sha512-V48tCfcKb/e6cVUigLAaJDAILdMP0fUW6BidkPK4GpGjXcfbnoHasCZDwz3N3yVt5we2RHm4XTQCpv0KJz9zqw==",
+      "version": "22.7.3",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-22.7.3.tgz",
+      "integrity": "sha512-qXKfhXXqGTyBskvWEzJZPUxSslAiLaB6JGP1ic/XTH9ctGgzdgYguuLP1C601aRTSDNlLb0jbKqXjZ48GNraSA==",
      "devOptional": true,
      "dependencies": {
        "undici-types": "~6.19.2"
@@ -4874,9 +4874,9 @@
      "integrity": "sha512-5zvhXYtRNRluoE/jAp4GVsSduVUzNWKkOZrCDBWYtE7biZywwdC2AcEzg+cSMLFRfVgeAFqpfNabiPjxFddV1Q=="
    },
    "node_modules/@types/react": {
-      "version": "18.3.8",
-      "resolved": "https://registry.npmjs.org/@types/react/-/react-18.3.8.tgz",
-      "integrity": "sha512-syBUrW3/XpnW4WJ41Pft+I+aPoDVbrBVQGEnbD7NijDGlVC+8gV/XKRY+7vMDlfPpbwYt0l1vd/Sj8bJGMbs9Q==",
+      "version": "18.3.9",
+      "resolved": "https://registry.npmjs.org/@types/react/-/react-18.3.9.tgz",
+      "integrity": "sha512-+BpAVyTpJkNWWSSnaLBk6ePpHLOGJKnEQNbINNovPWzvEUyAe3e+/d494QdEh71RekM/qV7lw6jzf1HGrJyAtQ==",
      "dependencies": {
        "@types/prop-types": "*",
        "csstype": "^3.0.2"
@@ -6160,23 +6160,17 @@
      }
    },
    "node_modules/cssstyle": {
-      "version": "4.0.1",
-      "resolved": "https://registry.npmjs.org/cssstyle/-/cssstyle-4.0.1.tgz",
-      "integrity": "sha512-8ZYiJ3A/3OkDd093CBT/0UKDWry7ak4BdPTFP2+QEP7cmhouyq/Up709ASSj2cK02BbZiMgk7kYjZNS4QP5qrQ==",
+      "version": "4.1.0",
+      "resolved": "https://registry.npmjs.org/cssstyle/-/cssstyle-4.1.0.tgz",
+      "integrity": "sha512-h66W1URKpBS5YMI/V8PyXvTMFT8SupJ1IzoIV8IeBC/ji8WVmrO8dGlTi+2dh6whmdk6BiKJLD/ZBkhWbcg6nA==",
      "dev": true,
      "dependencies": {
-        "rrweb-cssom": "^0.6.0"
+        "rrweb-cssom": "^0.7.1"
      },
      "engines": {
        "node": ">=18"
      }
    },
-    "node_modules/cssstyle/node_modules/rrweb-cssom": {
-      "version": "0.6.0",
-      "resolved": "https://registry.npmjs.org/rrweb-cssom/-/rrweb-cssom-0.6.0.tgz",
-      "integrity": "sha512-APM0Gt1KoXBz0iIkkdB/kfvGOwC4UuJFeG/c+yV7wSc7q96cG/kJ0HiYCnzivD9SB53cLV1MlHFNfOuPaadYSw==",
-      "dev": true
-    },
    "node_modules/csstype": {
      "version": "3.1.3",
      "resolved": "https://registry.npmjs.org/csstype/-/csstype-3.1.3.tgz",
@@ -8872,12 +8866,12 @@
      }
    },
    "node_modules/jsdom": {
-      "version": "25.0.0",
-      "resolved": "https://registry.npmjs.org/jsdom/-/jsdom-25.0.0.tgz",
-      "integrity": "sha512-OhoFVT59T7aEq75TVw9xxEfkXgacpqAhQaYgP9y/fDqWQCMB/b1H66RfmPm/MaeaAIU9nDwMOVTlPN51+ao6CQ==",
+      "version": "25.0.1",
+      "resolved": "https://registry.npmjs.org/jsdom/-/jsdom-25.0.1.tgz",
+      "integrity": "sha512-8i7LzZj7BF8uplX+ZyOlIz86V6TAsSs+np6m1kpW9u0JWi4z/1t+FzcK1aek+ybTnAC4KhBL4uXCNT0wcUIeCw==",
      "dev": true,
      "dependencies": {
-        "cssstyle": "^4.0.1",
+        "cssstyle": "^4.1.0",
        "data-urls": "^5.0.0",
        "decimal.js": "^10.4.3",
        "form-data": "^4.0.0",
@@ -8890,7 +8884,7 @@
        "rrweb-cssom": "^0.7.1",
        "saxes": "^6.0.0",
        "symbol-tree": "^3.2.4",
-        "tough-cookie": "^4.1.4",
+        "tough-cookie": "^5.0.0",
        "w3c-xmlserializer": "^5.0.0",
        "webidl-conversions": "^7.0.0",
        "whatwg-encoding": "^3.1.1",
@@ -11061,12 +11055,6 @@
        "url": "https://github.com/sponsors/wooorm"
      }
    },
-    "node_modules/psl": {
-      "version": "1.9.0",
-      "resolved": "https://registry.npmjs.org/psl/-/psl-1.9.0.tgz",
-      "integrity": "sha512-E/ZsdU4HLs/68gYzgGTkMicWTLPdAftJLfJFlLUAAKZGkStNU72sZjT66SnMDVOfOWY/YAoiD7Jxa9iHvngcag==",
-      "dev": true
-    },
    "node_modules/punycode": {
      "version": "2.3.1",
      "resolved": "https://registry.npmjs.org/punycode/-/punycode-2.3.1.tgz",
@@ -11076,12 +11064,6 @@
        "node": ">=6"
      }
    },
-    "node_modules/querystringify": {
-      "version": "2.2.0",
-      "resolved": "https://registry.npmjs.org/querystringify/-/querystringify-2.2.0.tgz",
-      "integrity": "sha512-FIqgj2EUvTa7R50u0rGsyTftzjYmv/a3hO345bZNrqabNqjtgiDMgmo4mkUjd+nzU5oF3dClKqFIPUKybUyqoQ==",
-      "dev": true
-    },
    "node_modules/queue-microtask": {
      "version": "1.2.3",
      "resolved": "https://registry.npmjs.org/queue-microtask/-/queue-microtask-1.2.3.tgz",
@@ -11593,12 +11575,6 @@
        "url": "https://opencollective.com/unified"
      }
    },
-    "node_modules/requires-port": {
-      "version": "1.0.0",
-      "resolved": "https://registry.npmjs.org/requires-port/-/requires-port-1.0.0.tgz",
-      "integrity": "sha512-KigOCHcocU3XODJxsu8i/j8T9tzT4adHiecwORRQ0ZZFcp7ahwXuRU1m+yuO90C5ZUyGeGfocHDI14M3L3yDAQ==",
-      "dev": true
-    },
    "node_modules/reselect": {
      "version": "5.1.1",
      "resolved": "https://registry.npmjs.org/reselect/-/reselect-5.1.1.tgz",
@@ -12426,9 +12402,9 @@
      }
    },
    "node_modules/tailwindcss": {
-      "version": "3.4.12",
-      "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-3.4.12.tgz",
-      "integrity": "sha512-Htf/gHj2+soPb9UayUNci/Ja3d8pTmu9ONTfh4QY8r3MATTZOzmv6UYWF7ZwikEIC8okpfqmGqrmDehua8mF8w==",
+      "version": "3.4.13",
+      "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-3.4.13.tgz",
+      "integrity": "sha512-KqjHOJKogOUt5Bs752ykCeiwvi0fKVkr5oqsFNt/8px/tA8scFPIlkygsf6jXrfCqGHz7VflA6+yytWuM+XhFw==",
      "dependencies": {
        "@alloc/quick-lru": "^5.2.0",
        "arg": "^5.0.2",
@@ -12566,6 +12542,24 @@
        "node": ">=14.0.0"
      }
    },
+    "node_modules/tldts": {
+      "version": "6.1.47",
+      "resolved": "https://registry.npmjs.org/tldts/-/tldts-6.1.47.tgz",
+      "integrity": "sha512-R/K2tZ5MiY+mVrnSkNJkwqYT2vUv1lcT6wJvd2emGaMJ7PHUGRY4e3tUsdFCXgqxi2QgbHjL3yJgXCo40v9Hxw==",
+      "dev": true,
+      "dependencies": {
+        "tldts-core": "^6.1.47"
+      },
+      "bin": {
+        "tldts": "bin/cli.js"
+      }
+    },
+    "node_modules/tldts-core": {
+      "version": "6.1.47",
+      "resolved": "https://registry.npmjs.org/tldts-core/-/tldts-core-6.1.47.tgz",
+      "integrity": "sha512-6SWyFMnlst1fEt7GQVAAu16EGgFK0cLouH/2Mk6Ftlwhv3Ol40L0dlpGMcnnNiiOMyD2EV/aF3S+U2nKvvLvrA==",
+      "dev": true
+    },
    "node_modules/to-fast-properties": {
      "version": "2.0.0",
      "resolved": "https://registry.npmjs.org/to-fast-properties/-/to-fast-properties-2.0.0.tgz",
@@ -12586,18 +12580,15 @@
      }
    },
    "node_modules/tough-cookie": {
-      "version": "4.1.4",
-      "resolved": "https://registry.npmjs.org/tough-cookie/-/tough-cookie-4.1.4.tgz",
-      "integrity": "sha512-Loo5UUvLD9ScZ6jh8beX1T6sO1w2/MpCRpEP7V280GKMVUQ0Jzar2U3UJPsrdbziLEMMhu3Ujnq//rhiFuIeag==",
+      "version": "5.0.0",
+      "resolved": "https://registry.npmjs.org/tough-cookie/-/tough-cookie-5.0.0.tgz",
+      "integrity": "sha512-FRKsF7cz96xIIeMZ82ehjC3xW2E+O2+v11udrDYewUbszngYhsGa8z6YUMMzO9QJZzzyd0nGGXnML/TReX6W8Q==",
      "dev": true,
      "dependencies": {
-        "psl": "^1.1.33",
-        "punycode": "^2.1.1",
-        "universalify": "^0.2.0",
-        "url-parse": "^1.5.3"
+        "tldts": "^6.1.32"
      },
      "engines": {
-        "node": ">=6"
+        "node": ">=16"
      }
    },
    "node_modules/tr46": {
@@ -12936,15 +12927,6 @@
        "url": "https://opencollective.com/unified"
      }
    },
-    "node_modules/universalify": {
-      "version": "0.2.0",
-      "resolved": "https://registry.npmjs.org/universalify/-/universalify-0.2.0.tgz",
-      "integrity": "sha512-CJ1QgKmNg3CwvAv/kOFmtnEN05f0D/cn9QntgNOQlQF9dgvVTHj3t+8JPdjqawCHk7V/KA+fbUqzZ9XWhcqPUg==",
-      "dev": true,
-      "engines": {
-        "node": ">= 4.0.0"
-      }
-    },
    "node_modules/update-browserslist-db": {
      "version": "1.1.0",
      "resolved": "https://registry.npmjs.org/update-browserslist-db/-/update-browserslist-db-1.1.0.tgz",
@@ -12983,16 +12965,6 @@
        "punycode": "^2.1.0"
      }
    },
-    "node_modules/url-parse": {
-      "version": "1.5.10",
-      "resolved": "https://registry.npmjs.org/url-parse/-/url-parse-1.5.10.tgz",
-      "integrity": "sha512-WypcfiRhfeUP9vvF0j6rw0J3hrWrw6iZv3+22h6iRMJ/8z1Tj6XfLP4DsUix5MhMPnXpiHDoKyoZ/bdCkwBCiQ==",
-      "dev": true,
-      "dependencies": {
-        "querystringify": "^2.1.1",
-        "requires-port": "^1.0.0"
-      }
-    },
    "node_modules/use-callback-ref": {
      "version": "1.3.2",
      "resolved": "https://registry.npmjs.org/use-callback-ref/-/use-callback-ref-1.3.2.tgz",
@@ -13112,9 +13084,9 @@
      }
    },
    "node_modules/vite": {
-      "version": "5.4.7",
-      "resolved": "https://registry.npmjs.org/vite/-/vite-5.4.7.tgz",
-      "integrity": "sha512-5l2zxqMEPVENgvzTuBpHer2awaetimj2BGkhBPdnwKbPNOlHsODU+oiazEZzLK7KhAnOrO+XGYJYn4ZlUhDtDQ==",
+      "version": "5.4.8",
+      "resolved": "https://registry.npmjs.org/vite/-/vite-5.4.8.tgz",
+      "integrity": "sha512-FqrItQ4DT1NC4zCUqMB4c4AZORMKIa0m8/URVCZ77OZ/QSNeJ54bU1vrFADbDsuwfIPcgknRkmqakQcgnL4GiQ==",
      "dependencies": {
        "esbuild": "^0.21.3",
        "postcss": "^8.4.43",
@@ -1,6 +1,6 @@
 {
  "name": "openhands-frontend",
-  "version": "0.9.4",
+  "version": "0.9.6",
  "private": true,
  "type": "module",
  "engines": {
@@ -32,7 +32,7 @@
    "react-syntax-highlighter": "^15.5.0",
    "remark-gfm": "^4.0.0",
    "tailwind-merge": "^2.5.2",
-    "vite": "^5.4.7",
+    "vite": "^5.4.8",
    "web-vitals": "^3.5.2"
  },
  "scripts": {
@@ -64,8 +64,8 @@
    "@testing-library/jest-dom": "^6.5.0",
    "@testing-library/react": "^16.0.1",
    "@testing-library/user-event": "^14.5.2",
-    "@types/node": "^22.6.1",
-    "@types/react": "^18.3.8",
+    "@types/node": "^22.7.3",
+    "@types/react": "^18.3.9",
    "@types/react-dom": "^18.3.0",
    "@types/react-highlight": "^0.12.8",
    "@types/react-syntax-highlighter": "^15.5.13",
@@ -83,11 +83,11 @@
    "eslint-plugin-react": "^7.35.0",
    "eslint-plugin-react-hooks": "^4.6.2",
    "husky": "^9.1.6",
-    "jsdom": "^25.0.0",
+    "jsdom": "^25.0.1",
    "lint-staged": "^15.2.10",
    "postcss": "^8.4.47",
    "prettier": "^3.3.3",
-    "tailwindcss": "^3.4.12",
+    "tailwindcss": "^3.4.13",
    "typescript": "^5.6.2",
    "vite-tsconfig-paths": "^5.0.1",
    "vitest": "^1.6.0"
@@ -94,13 +94,13 @@ function AgentStatusBar() {
  const [statusMessage, setStatusMessage] = React.useState<string>("");

  React.useEffect(() => {
-    const trimmedCustomMessage = curStatusMessage.message.trim();
+    const trimmedCustomMessage = curStatusMessage.status.trim();
    if (trimmedCustomMessage) {
      setStatusMessage(t(trimmedCustomMessage));
    } else {
      setStatusMessage(AgentStatusMap[curAgentState].message);
    }
-  }, [curAgentState, curStatusMessage.message]);
+  }, [curAgentState, curStatusMessage.status]);

  return (
    <div className="flex flex-col items-center">
@@ -7,6 +7,7 @@ import { I18nKey } from "../../../i18n/declaration";
 import { AutocompleteCombobox } from "./AutocompleteCombobox";
 import { Settings } from "#/services/settings";
 import { organizeModelsAndProviders } from "#/utils/organizeModelsAndProviders";
+import { extractModelAndProvider } from "#/utils/extractModelAndProvider";
 import { ModelSelector } from "./ModelSelector";

 interface SettingsFormProps {
@@ -41,17 +42,29 @@ function SettingsForm({
 }: SettingsFormProps) {
  const { t } = useTranslation();
  const { isOpen: isVisible, onOpenChange: onVisibleChange } = useDisclosure();
-  const advancedAlreadyInUse = React.useMemo(
-    () =>
+  const advancedAlreadyInUse = React.useMemo(() => {
+    const organizedModels = organizeModelsAndProviders(models);
+    const { provider, model } = extractModelAndProvider(
+      settings.LLM_MODEL || "",
+    );
+    const isKnownModel =
+      provider in organizedModels &&
+      organizedModels[provider].models.includes(model);
+
+    return (
      !!settings.SECURITY_ANALYZER ||
      !!settings.CONFIRMATION_MODE ||
      !!settings.LLM_BASE_URL ||
-      (!!settings.LLM_MODEL && !models.includes(settings.LLM_MODEL)),
-    [],
-  );
+      (!!settings.LLM_MODEL && !isKnownModel)
+    );
+  }, [settings, models]);
  const [enableAdvanced, setEnableAdvanced] =
    React.useState(advancedAlreadyInUse);

+  React.useEffect(() => {
+    setEnableAdvanced(advancedAlreadyInUse);
+  }, [advancedAlreadyInUse]);
+
  const handleAdvancedChange = (value: boolean) => {
    setEnableAdvanced(value);
  };
@@ -140,11 +140,11 @@ export function handleActionMessage(message: ActionMessage) {
 }

 export function handleStatusMessage(message: StatusMessage) {
-  const msg = message.message == null ? "" : message.message.trim();
+  const msg = message.status == null ? "" : message.status.trim();
  store.dispatch(
    setCurStatusMessage({
      ...message,
-      message: msg,
+      status: msg,
    }),
  );
 }
@@ -160,9 +160,9 @@ export function handleAssistantMessage(data: string | SocketMessage) {

  if ("action" in socketMessage) {
    handleActionMessage(socketMessage);
-  } else if ("observation" in socketMessage) {
-    handleObservationMessage(socketMessage);
-  } else if ("message" in socketMessage) {
+  } else if ("status" in socketMessage) {
    handleStatusMessage(socketMessage);
+  } else {
+    handleObservationMessage(socketMessage);
  }
 }
@@ -2,7 +2,7 @@ import { createSlice, PayloadAction } from "@reduxjs/toolkit";
 import { StatusMessage } from "#/types/Message";

 const initialStatusMessage: StatusMessage = {
-  message: "",
+  status: "",
  is_error: false,
 };

@@ -38,5 +38,5 @@ export interface StatusMessage {
  is_error: boolean;

  // A status message to display to the user
-  message: string;
+  status: string;
 }
@@ -1,3 +1,6 @@
+import os
+
+
 def get_version():
    try:
        from importlib.metadata import PackageNotFoundError, version
@@ -19,6 +22,16 @@ def get_version():
    except ImportError:
        pass

+    # Try getting the version from pyproject.toml
+    try:
+        root_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+        with open(os.path.join(root_dir, 'pyproject.toml'), 'r') as f:
+            for line in f:
+                if line.startswith('version ='):
+                    return line.split('=')[1].strip().strip('"')
+    except FileNotFoundError:
+        pass
+
    return 'unknown'


@@ -1,4 +1,5 @@
 import asyncio
+import copy
 import traceback
 from typing import Type

@@ -36,6 +37,7 @@ from openhands.events.observation import (
    ErrorObservation,
    Observation,
 )
+from openhands.events.serialization.event import truncate_content
 from openhands.llm.llm import LLM
 from openhands.runtime.utils.shutdown_listener import should_continue

@@ -117,8 +119,6 @@ class AgentController:

    async def close(self):
        """Closes the agent controller, canceling any ongoing tasks and unsubscribing from the event stream."""
-        if self.agent_task is not None:
-            self.agent_task.cancel()
        await self.set_agent_state_to(AgentState.STOPPED)
        self.event_stream.unsubscribe(EventStreamSubscriber.AGENT_CONTROLLER)

@@ -220,7 +220,13 @@ class AgentController:
        ):
            return

-        logger.info(observation, extra={'msg_type': 'OBSERVATION'})
+        # Make sure we print the observation in the same way as the LLM sees it
+        observation_to_print = copy.deepcopy(observation)
+        if len(observation_to_print.content) > self.agent.llm.config.max_message_chars:
+            observation_to_print.content = truncate_content(
+                observation_to_print.content, self.agent.llm.config.max_message_chars
+            )
+        logger.info(observation_to_print, extra={'msg_type': 'OBSERVATION'})
        if self._pending_action and self._pending_action.id == observation.cause:
            self._pending_action = None
            if self.state.agent_state == AgentState.USER_CONFIRMED:
@@ -1,3 +1,4 @@
+import os
 from dataclasses import dataclass, fields

 from openhands.core.config.config_utils import get_field_info
@@ -36,7 +37,7 @@ class LLMConfig:
        ollama_base_url: The base URL for the OLLAMA API.
        drop_params: Drop any unmapped (unsupported) params without causing an exception.
        disable_vision: If model is vision capable, this option allows to disable image processing (useful for cost reduction).
-        caching_prompt: Using the prompt caching feature provided by the LLM.
+        caching_prompt: Use the prompt caching feature if provided by the LLM and supported by the provider.
        log_completions: Whether to log LLM completions to the state.
    """

@@ -68,7 +69,7 @@ class LLMConfig:
    ollama_base_url: str | None = None
    drop_params: bool = True
    disable_vision: bool | None = None
-    caching_prompt: bool = False
+    caching_prompt: bool = True
    log_completions: bool = False

    def defaults_to_dict(self) -> dict:
@@ -78,6 +79,18 @@ class LLMConfig:
            result[f.name] = get_field_info(f)
        return result

+    def __post_init__(self):
+        """
+        Post-initialization hook to assign OpenRouter-related variables to environment variables.
+        This ensures that these values are accessible to litellm at runtime.
+        """
+
+        # Assign OpenRouter-specific variables to environment variables
+        if self.openrouter_site_url:
+            os.environ['OR_SITE_URL'] = self.openrouter_site_url
+        if self.openrouter_app_name:
+            os.environ['OR_APP_NAME'] = self.openrouter_app_name
+
    def __str__(self):
        attr_str = []
        for f in fields(self):
@@ -101,9 +114,3 @@ class LLMConfig:
            if k in LLM_SENSITIVE_FIELDS:
                ret[k] = '******' if v else None
        return ret
-
-    def set_missing_attributes(self):
-        """Set any missing attributes to their default values."""
-        for field_name, field_obj in self.__dataclass_fields__.items():
-            if not hasattr(self, field_name):
-                setattr(self, field_name, field_obj.default)
@@ -50,6 +50,8 @@ class ImageContent(Content):
 class Message(BaseModel):
    role: Literal['user', 'system', 'assistant']
    content: list[TextContent | ImageContent] = Field(default=list)
+    cache_enabled: bool = False
+    vision_enabled: bool = False

    @property
    def contains_image(self) -> bool:
@@ -58,23 +60,22 @@ class Message(BaseModel):
    @model_serializer
    def serialize_model(self) -> dict:
        content: list[dict] | str
-        if self.role == 'system':
-            # For system role, concatenate all text content into a single string
-            content = '\n'.join(
-                item.text for item in self.content if isinstance(item, TextContent)
-            )
-        elif self.role == 'assistant' and not self.contains_image:
-            # For assistant role without vision, concatenate all text content into a single string
-            content = '\n'.join(
-                item.text for item in self.content if isinstance(item, TextContent)
-            )
-        else:
-            # For user role or assistant role with vision enabled, serialize each content item
+        # two kinds of serializer:
+        # 1. vision serializer: when prompt caching or vision is enabled
+        # 2. single text serializer: for other cases
+        # remove this when liteLLM or providers support this format translation
+        if self.cache_enabled or self.vision_enabled:
+            # when prompt caching or vision is enabled, use vision serializer
            content = []
            for item in self.content:
                if isinstance(item, TextContent):
                    content.append(item.model_dump())
                elif isinstance(item, ImageContent):
                    content.extend(item.model_dump())
-
+        else:
+            # for other cases, concatenate all text content
+            # into a single string per message
+            content = '\n'.join(
+                item.text for item in self.content if isinstance(item, TextContent)
+            )
        return {'content': content, 'role': self.role}
@@ -24,10 +24,6 @@ class ActionTypeSchema(BaseModel):
    """Writes the content to a file.
    """

-    EDIT: str = Field(default='edit')
-    """Edits the content of a file.
-    """
-
    RUN: str = Field(default='run')
    """Runs a command.
    """
@@ -10,10 +10,6 @@ class ObservationTypeSchema(BaseModel):

    WRITE: str = Field(default='write')

-    EDIT: str = Field(default='edit')
-    """The edited file
-    """
-
    BROWSE: str = Field(default='browse')
    """The HTML content of a URL
    """
@@ -9,11 +9,7 @@ from openhands.events.action.agent import (
 from openhands.events.action.browse import BrowseInteractiveAction, BrowseURLAction
 from openhands.events.action.commands import CmdRunAction, IPythonRunCellAction
 from openhands.events.action.empty import NullAction
-from openhands.events.action.files import (
-    FileEditAction,
-    FileReadAction,
-    FileWriteAction,
-)
+from openhands.events.action.files import FileReadAction, FileWriteAction
 from openhands.events.action.message import MessageAction
 from openhands.events.action.tasks import AddTaskAction, ModifyTaskAction

@@ -25,7 +21,6 @@ __all__ = [
    'BrowseInteractiveAction',
    'FileReadAction',
    'FileWriteAction',
-    'FileEditAction',
    'AgentFinishAction',
    'AgentRejectAction',
    'AgentDelegateAction',
@@ -39,23 +39,3 @@ class FileWriteAction(Action):
    @property
    def message(self) -> str:
        return f'Writing file: {self.path}'
-
-
-@dataclass
-class FileEditAction(Action):
-    diff_block: str
-    thought: str = ''
-    action: str = ActionType.EDIT
-    runnable: ClassVar[bool] = True
-    security_risk: ActionSecurityRisk | None = None
-
-    def __str__(self) -> str:
-        ret = '**EditFileAction**\n'
-        if self.thought:
-            ret += f'THOUGHT: {self.thought}\n'
-        ret += f'DIFF BLOCK:\n{self.diff_block}\n'
-        return ret
-
-    @property
-    def message(self) -> str:
-        return f'Edit Diff block: {self.diff_block}'
@@ -7,11 +7,7 @@ from openhands.events.observation.commands import (
 from openhands.events.observation.delegate import AgentDelegateObservation
 from openhands.events.observation.empty import NullObservation
 from openhands.events.observation.error import ErrorObservation
-from openhands.events.observation.files import (
-    FileEditObservation,
-    FileReadObservation,
-    FileWriteObservation,
-)
+from openhands.events.observation.files import FileReadObservation, FileWriteObservation
 from openhands.events.observation.observation import Observation
 from openhands.events.observation.reject import UserRejectObservation
 from openhands.events.observation.success import SuccessObservation
@@ -24,7 +20,6 @@ __all__ = [
    'BrowserOutputObservation',
    'FileReadObservation',
    'FileWriteObservation',
-    'FileEditObservation',
    'ErrorObservation',
    'AgentStateChangedObservation',
    'AgentDelegateObservation',
@@ -26,30 +26,3 @@ class FileWriteObservation(Observation):
    @property
    def message(self) -> str:
        return f'I wrote to the file {self.path}.'
-
-
-@dataclass
-class FileEditObservation(Observation):
-    """This data class represents a file edit operation"""
-
-    path: str
-    search_block: str
-    replace_block: str
-    observation: str = ObservationType.EDIT
-
-    @property
-    def message(self) -> str:
-        if self.search_block:
-            return (
-                f'I updated the file {self.path} by \n'
-                f'replacing:\n {self.search_block}\n'
-                f'with:\n {self.replace_block}\n'
-            )
-        else:
-            return (
-                f'I updated the file {self.path} by \n'
-                f'appending:\n {self.replace_block}\n'
-            )
-
-    def __str__(self) -> str:
-        return f'**FileEditObservation**\n' f'DIFF BLOCK: {self.content}\n'
@@ -12,11 +12,7 @@ from openhands.events.action.commands import (
    IPythonRunCellAction,
 )
 from openhands.events.action.empty import NullAction
-from openhands.events.action.files import (
-    FileEditAction,
-    FileReadAction,
-    FileWriteAction,
-)
+from openhands.events.action.files import FileReadAction, FileWriteAction
 from openhands.events.action.message import MessageAction
 from openhands.events.action.tasks import AddTaskAction, ModifyTaskAction

@@ -28,7 +24,6 @@ actions = (
    BrowseInteractiveAction,
    FileReadAction,
    FileWriteAction,
-    FileEditAction,
    AgentFinishAction,
    AgentRejectAction,
    AgentDelegateAction,
@@ -7,11 +7,7 @@ from openhands.events.observation.commands import (
 from openhands.events.observation.delegate import AgentDelegateObservation
 from openhands.events.observation.empty import NullObservation
 from openhands.events.observation.error import ErrorObservation
-from openhands.events.observation.files import (
-    FileEditObservation,
-    FileReadObservation,
-    FileWriteObservation,
-)
+from openhands.events.observation.files import FileReadObservation, FileWriteObservation
 from openhands.events.observation.observation import Observation
 from openhands.events.observation.reject import UserRejectObservation
 from openhands.events.observation.success import SuccessObservation
@@ -23,7 +19,6 @@ observations = (
    BrowserOutputObservation,
    FileReadObservation,
    FileWriteObservation,
-    FileEditObservation,
    AgentDelegateObservation,
    SuccessObservation,
    ErrorObservation,
@@ -0,0 +1,5 @@
+from openhands.llm.async_llm import AsyncLLM
+from openhands.llm.llm import LLM
+from openhands.llm.streaming_llm import StreamingLLM
+
+__all__ = ['LLM', 'AsyncLLM', 'StreamingLLM']
@@ -0,0 +1,117 @@
+import asyncio
+from functools import partial
+from typing import Any
+
+from litellm import completion as litellm_acompletion
+
+from openhands.core.exceptions import UserCancelledError
+from openhands.core.logger import openhands_logger as logger
+from openhands.llm.llm import LLM, LLM_RETRY_EXCEPTIONS
+from openhands.runtime.utils.shutdown_listener import should_continue
+
+
+class AsyncLLM(LLM):
+    """Asynchronous LLM class."""
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+        self._async_completion = partial(
+            self._call_acompletion,
+            model=self.config.model,
+            api_key=self.config.api_key,
+            base_url=self.config.base_url,
+            api_version=self.config.api_version,
+            custom_llm_provider=self.config.custom_llm_provider,
+            max_tokens=self.config.max_output_tokens,
+            timeout=self.config.timeout,
+            temperature=self.config.temperature,
+            top_p=self.config.top_p,
+            drop_params=self.config.drop_params,
+        )
+
+        async_completion_unwrapped = self._async_completion
+
+        @self.retry_decorator(
+            num_retries=self.config.num_retries,
+            retry_exceptions=LLM_RETRY_EXCEPTIONS,
+            retry_min_wait=self.config.retry_min_wait,
+            retry_max_wait=self.config.retry_max_wait,
+            retry_multiplier=self.config.retry_multiplier,
+        )
+        async def async_completion_wrapper(*args, **kwargs):
+            """Wrapper for the litellm acompletion function."""
+            messages: list[dict[str, Any]] | dict[str, Any] = []
+
+            # some callers might send the model and messages directly
+            # litellm allows positional args, like completion(model, messages, **kwargs)
+            # see llm.py for more details
+            if len(args) > 1:
+                messages = args[1] if len(args) > 1 else args[0]
+                kwargs['messages'] = messages
+
+                # remove the first args, they're sent in kwargs
+                args = args[2:]
+            elif 'messages' in kwargs:
+                messages = kwargs['messages']
+
+            # ensure we work with a list of messages
+            messages = messages if isinstance(messages, list) else [messages]
+
+            # if we have no messages, something went very wrong
+            if not messages:
+                raise ValueError(
+                    'The messages list is empty. At least one message is required.'
+                )
+
+            self.log_prompt(messages)
+
+            async def check_stopped():
+                while should_continue():
+                    if (
+                        hasattr(self.config, 'on_cancel_requested_fn')
+                        and self.config.on_cancel_requested_fn is not None
+                        and await self.config.on_cancel_requested_fn()
+                    ):
+                        raise UserCancelledError('LLM request cancelled by user')
+                    await asyncio.sleep(0.1)
+
+            stop_check_task = asyncio.create_task(check_stopped())
+
+            try:
+                # Directly call and await litellm_acompletion
+                resp = await async_completion_unwrapped(*args, **kwargs)
+
+                message_back = resp['choices'][0]['message']['content']
+                self.log_response(message_back)
+                self._post_completion(resp)
+
+                # We do not support streaming in this method, thus return resp
+                return resp
+
+            except UserCancelledError:
+                logger.info('LLM request cancelled by user.')
+                raise
+            except Exception as e:
+                logger.error(f'Completion Error occurred:\n{e}')
+                raise
+
+            finally:
+                await asyncio.sleep(0.1)
+                stop_check_task.cancel()
+                try:
+                    await stop_check_task
+                except asyncio.CancelledError:
+                    pass
+
+        self._async_completion = async_completion_wrapper  # type: ignore
+
+    async def _call_acompletion(self, *args, **kwargs):
+        """Wrapper for the litellm acompletion function."""
+        # Used in testing?
+        return await litellm_acompletion(*args, **kwargs)
+
+    @property
+    def async_completion(self):
+        """Decorator for the async litellm acompletion function."""
+        return self._async_completion
@@ -0,0 +1,51 @@
+from typing import Any
+
+from openhands.core.logger import llm_prompt_logger, llm_response_logger
+from openhands.core.logger import openhands_logger as logger
+
+MESSAGE_SEPARATOR = '\n\n----------\n\n'
+
+
+class DebugMixin:
+    def log_prompt(self, messages: list[dict[str, Any]] | dict[str, Any]):
+        if not messages:
+            logger.debug('No completion messages!')
+            return
+
+        messages = messages if isinstance(messages, list) else [messages]
+        debug_message = MESSAGE_SEPARATOR.join(
+            self._format_message_content(msg) for msg in messages if msg['content']
+        )
+
+        if debug_message:
+            llm_prompt_logger.debug(debug_message)
+        else:
+            logger.debug('No completion messages!')
+
+    def log_response(self, message_back: str):
+        if message_back:
+            llm_response_logger.debug(message_back)
+
+    def _format_message_content(self, message: dict[str, Any]):
+        content = message['content']
+        if isinstance(content, list):
+            return '\n'.join(
+                self._format_content_element(element) for element in content
+            )
+        return str(content)
+
+    def _format_content_element(self, element: dict[str, Any]):
+        if isinstance(element, dict):
+            if 'text' in element:
+                return element['text']
+            if (
+                self.vision_is_active()
+                and 'image_url' in element
+                and 'url' in element['image_url']
+            ):
+                return element['image_url']['url']
+        return str(element)
+
+    # This method should be implemented in the class that uses DebugMixin
+    def vision_is_active(self):
+        raise NotImplementedError
@@ -1,59 +1,54 @@
-import asyncio
 import copy
-import os
 import time
 import warnings
 from functools import partial
 from typing import Any

 from openhands.core.config import LLMConfig
-from openhands.runtime.utils.shutdown_listener import should_continue

 with warnings.catch_warnings():
    warnings.simplefilter('ignore')
    import litellm
+from litellm import ModelInfo
 from litellm import completion as litellm_completion
 from litellm import completion_cost as litellm_completion_cost
 from litellm.exceptions import (
    APIConnectionError,
-    ContentPolicyViolationError,
    InternalServerError,
-    NotFoundError,
-    OpenAIError,
    RateLimitError,
    ServiceUnavailableError,
 )
-from litellm.types.utils import CostPerToken
-from tenacity import (
-    retry,
-    retry_if_exception_type,
-    retry_if_not_exception_type,
-    stop_after_attempt,
-    wait_exponential,
-)
+from litellm.types.utils import CostPerToken, ModelResponse, Usage

-from openhands.core.exceptions import (
-    LLMResponseError,
-    OperationCancelled,
-    UserCancelledError,
-)
-from openhands.core.logger import llm_prompt_logger, llm_response_logger
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.message import Message
 from openhands.core.metrics import Metrics
-from openhands.runtime.utils.shutdown_listener import should_exit
+from openhands.llm.debug_mixin import DebugMixin
+from openhands.llm.retry_mixin import RetryMixin

 __all__ = ['LLM']

-message_separator = '\n\n----------\n\n'
+# tuple of exceptions to retry on
+LLM_RETRY_EXCEPTIONS: tuple[type[Exception], ...] = (
+    APIConnectionError,
+    InternalServerError,
+    RateLimitError,
+    ServiceUnavailableError,
+)

-cache_prompting_supported_models = [
+# cache prompt supporting models
+# remove this when we gemini and deepseek are supported
+CACHE_PROMPT_SUPPORTED_MODELS = [
    'claude-3-5-sonnet-20240620',
    'claude-3-haiku-20240307',
+    'claude-3-opus-20240229',
+    'anthropic/claude-3-opus-20240229',
+    'anthropic/claude-3-haiku-20240307',
+    'anthropic/claude-3-5-sonnet-20240620',
 ]


-class LLM:
+class LLM(RetryMixin, DebugMixin):
    """The LLM class represents a Language Model instance.

    Attributes:
@@ -70,25 +65,20 @@ class LLM:
        Passing simple parameters always overrides config.

        Args:
-            config: The LLM configuration
+            config: The LLM configuration.
+            metrics: The metrics to use.
        """
-        self.metrics = metrics if metrics is not None else Metrics()
-        self.cost_metric_supported = True
-        self.config = copy.deepcopy(config)
-
-        os.environ['OR_SITE_URL'] = self.config.openrouter_site_url
-        os.environ['OR_APP_NAME'] = self.config.openrouter_app_name
+        self.metrics: Metrics = metrics if metrics is not None else Metrics()
+        self.cost_metric_supported: bool = True
+        self.config: LLMConfig = copy.deepcopy(config)

        # list of LLM completions (for logging purposes). Each completion is a dict with the following keys:
        # - 'messages': list of messages
        # - 'response': response from the LLM
        self.llm_completions: list[dict[str, Any]] = []

-        # Set up config attributes with default values to prevent AttributeError
-        LLMConfig.set_missing_attributes(self.config)
-
        # litellm actually uses base Exception here for unknown model
-        self.model_info = None
+        self.model_info: ModelInfo | None = None
        try:
            if self.config.model.startswith('openrouter'):
                self.model_info = litellm.get_model_info(self.config.model)
@@ -100,15 +90,6 @@ class LLM:
        except Exception as e:
            logger.warning(f'Could not get model info for {config.model}:\n{e}')

-        # Tuple of exceptions to retry on
-        self.retry_exceptions = (
-            APIConnectionError,
-            ContentPolicyViolationError,
-            InternalServerError,
-            OpenAIError,
-            RateLimitError,
-        )
-
        # Set the max tokens in an LM-specific way if not set
        if self.config.max_input_tokens is None:
            if (
@@ -136,30 +117,6 @@ class LLM:
                ):
                    self.config.max_output_tokens = self.model_info['max_tokens']

-        # This only seems to work with Google as the provider, not with OpenRouter!
-        gemini_safety_settings = (
-            [
-                {
-                    'category': 'HARM_CATEGORY_HARASSMENT',
-                    'threshold': 'BLOCK_NONE',
-                },
-                {
-                    'category': 'HARM_CATEGORY_HATE_SPEECH',
-                    'threshold': 'BLOCK_NONE',
-                },
-                {
-                    'category': 'HARM_CATEGORY_SEXUALLY_EXPLICIT',
-                    'threshold': 'BLOCK_NONE',
-                },
-                {
-                    'category': 'HARM_CATEGORY_DANGEROUS_CONTENT',
-                    'threshold': 'BLOCK_NONE',
-                },
-            ]
-            if self.config.model.lower().startswith('gemini')
-            else None
-        )
-
        self._completion = partial(
            litellm_completion,
            model=self.config.model,
@@ -172,84 +129,52 @@ class LLM:
            temperature=self.config.temperature,
            top_p=self.config.top_p,
            drop_params=self.config.drop_params,
-            **(
-                {'safety_settings': gemini_safety_settings}
-                if gemini_safety_settings is not None
-                else {}
-            ),
        )

        if self.vision_is_active():
            logger.debug('LLM: model has vision enabled')
+        if self.is_caching_prompt_active():
+            logger.debug('LLM: caching prompt enabled')

        completion_unwrapped = self._completion

-        def log_retry_attempt(retry_state):
-            """With before_sleep, this is called before `custom_completion_wait` and
-            ONLY if the retry is triggered by an exception."""
-            if should_exit():
-                raise OperationCancelled(
-                    'Operation cancelled.'
-                )  # exits the @retry loop
-            exception = retry_state.outcome.exception()
-            logger.error(
-                f'{exception}. Attempt #{retry_state.attempt_number} | You can customize retry values in the configuration.',
-                exc_info=False,
-            )
-
-        def custom_completion_wait(retry_state):
-            """Custom wait function for litellm completion."""
-            if not retry_state:
-                return 0
-            exception = retry_state.outcome.exception() if retry_state.outcome else None
-            if exception is None:
-                return 0
-
-            min_wait_time = self.config.retry_min_wait
-            max_wait_time = self.config.retry_max_wait
-
-            # for rate limit errors, wait 1 minute by default, max 4 minutes between retries
-            exception_type = type(exception).__name__
-            logger.error(f'\nexception_type: {exception_type}\n')
-
-            if exception_type == 'RateLimitError':
-                min_wait_time = 60
-                max_wait_time = 240
-            elif exception_type == 'BadRequestError' and exception.response:
-                # this should give us the burried, actual error message from
-                # the LLM model.
-                logger.error(f'\n\nBadRequestError: {exception.response}\n\n')
-
-            # Return the wait time using exponential backoff
-            exponential_wait = wait_exponential(
-                multiplier=self.config.retry_multiplier,
-                min=min_wait_time,
-                max=max_wait_time,
-            )
-
-            # Call the exponential wait function with retry_state to get the actual wait time
-            return exponential_wait(retry_state)
-
-        @retry(
-            before_sleep=log_retry_attempt,
-            stop=stop_after_attempt(self.config.num_retries),
-            reraise=True,
-            retry=(
-                retry_if_exception_type(self.retry_exceptions)
-                & retry_if_not_exception_type(OperationCancelled)
-            ),
-            wait=custom_completion_wait,
+        @self.retry_decorator(
+            num_retries=self.config.num_retries,
+            retry_exceptions=LLM_RETRY_EXCEPTIONS,
+            retry_min_wait=self.config.retry_min_wait,
+            retry_max_wait=self.config.retry_max_wait,
+            retry_multiplier=self.config.retry_multiplier,
        )
        def wrapper(*args, **kwargs):
            """Wrapper for the litellm completion function. Logs the input and output of the completion function."""
-            # some callers might just send the messages directly
-            if 'messages' in kwargs:
-                messages = kwargs['messages']
-            else:
-                messages = args[1] if len(args) > 1 else []
+            messages: list[dict[str, Any]] | dict[str, Any] = []

-            # this serves to prevent empty messages and logging the messages
-            debug_message = self._get_debug_message(messages)
+            # some callers might send the model and messages directly
+            # litellm allows positional args, like completion(model, messages, **kwargs)
+            if len(args) > 1:
+                # ignore the first argument if it's provided (it would be the model)
+                # design wise: we don't allow overriding the configured values
+                # implementation wise: the partial function set the model as a kwarg already
+                # as well as other kwargs
+                messages = args[1] if len(args) > 1 else args[0]
+                kwargs['messages'] = messages
+
+                # remove the first args, they're sent in kwargs
+                args = args[2:]
+            elif 'messages' in kwargs:
+                messages = kwargs['messages']
+
+            # ensure we work with a list of messages
+            messages = messages if isinstance(messages, list) else [messages]
+
+            # if we have no messages, something went very wrong
+            if not messages:
+                raise ValueError(
+                    'The messages list is empty. At least one message is required.'
+                )
+
+            # log the entire LLM prompt
+            self.log_prompt(messages)

            if self.is_caching_prompt_active():
                # Anthropic-specific prompt caching
@@ -258,239 +183,31 @@ class LLM:
                        'anthropic-beta': 'prompt-caching-2024-07-31',
                    }

-            # skip if messages is empty (thus debug_message is empty)
-            if debug_message:
-                llm_prompt_logger.debug(debug_message)
-                resp = completion_unwrapped(*args, **kwargs)
-            else:
-                logger.debug('No completion messages!')
-                resp = {'choices': [{'message': {'content': ''}}]}
+            # we don't support streaming here, thus we get a ModelResponse
+            resp: ModelResponse = completion_unwrapped(*args, **kwargs)

+            # log for evals or other scripts that need the raw completion
            if self.config.log_completions:
                self.llm_completions.append(
                    {
                        'messages': messages,
                        'response': resp,
                        'timestamp': time.time(),
-                        'cost': self.completion_cost(resp),
+                        'cost': self._completion_cost(resp),
                    }
                )

-            # log the response
-            message_back = resp['choices'][0]['message']['content']
-            if message_back:
-                llm_response_logger.debug(message_back)
+            message_back: str = resp['choices'][0]['message']['content']

-                # post-process to log costs
-                self._post_completion(resp)
+            # log the LLM response
+            self.log_response(message_back)
+
+            # post-process the response
+            self._post_completion(resp)

            return resp

-        self._completion = wrapper  # type: ignore
-
-        # Async version
-        self._async_completion = partial(
-            self._call_acompletion,
-            model=self.config.model,
-            api_key=self.config.api_key,
-            base_url=self.config.base_url,
-            api_version=self.config.api_version,
-            custom_llm_provider=self.config.custom_llm_provider,
-            max_tokens=self.config.max_output_tokens,
-            timeout=self.config.timeout,
-            temperature=self.config.temperature,
-            top_p=self.config.top_p,
-            drop_params=self.config.drop_params,
-            **(
-                {'safety_settings': gemini_safety_settings}
-                if gemini_safety_settings is not None
-                else {}
-            ),
-        )
-
-        async_completion_unwrapped = self._async_completion
-
-        @retry(
-            before_sleep=log_retry_attempt,
-            stop=stop_after_attempt(self.config.num_retries),
-            reraise=True,
-            retry=(
-                retry_if_exception_type(self.retry_exceptions)
-                & retry_if_not_exception_type(OperationCancelled)
-            ),
-            wait=custom_completion_wait,
-        )
-        async def async_completion_wrapper(*args, **kwargs):
-            """Async wrapper for the litellm acompletion function."""
-            # some callers might just send the messages directly
-            if 'messages' in kwargs:
-                messages = kwargs['messages']
-            else:
-                messages = args[1] if len(args) > 1 else []
-
-            # this serves to prevent empty messages and logging the messages
-            debug_message = self._get_debug_message(messages)
-
-            async def check_stopped():
-                while should_continue():
-                    if (
-                        hasattr(self.config, 'on_cancel_requested_fn')
-                        and self.config.on_cancel_requested_fn is not None
-                        and await self.config.on_cancel_requested_fn()
-                    ):
-                        raise UserCancelledError('LLM request cancelled by user')
-                    await asyncio.sleep(0.1)
-
-            stop_check_task = asyncio.create_task(check_stopped())
-
-            try:
-                # Directly call and await litellm_acompletion
-                if debug_message:
-                    llm_prompt_logger.debug(debug_message)
-                    resp = await async_completion_unwrapped(*args, **kwargs)
-                else:
-                    logger.debug('No completion messages!')
-                    resp = {'choices': [{'message': {'content': ''}}]}
-
-                # skip if messages is empty (thus debug_message is empty)
-                if debug_message:
-                    message_back = resp['choices'][0]['message']['content']
-                    llm_response_logger.debug(message_back)
-                else:
-                    resp = {'choices': [{'message': {'content': ''}}]}
-                self._post_completion(resp)
-
-                # We do not support streaming in this method, thus return resp
-                return resp
-
-            except UserCancelledError:
-                logger.info('LLM request cancelled by user.')
-                raise
-            except (
-                APIConnectionError,
-                ContentPolicyViolationError,
-                InternalServerError,
-                NotFoundError,
-                OpenAIError,
-                RateLimitError,
-                ServiceUnavailableError,
-            ) as e:
-                logger.error(f'Completion Error occurred:\n{e}')
-                raise
-
-            finally:
-                await asyncio.sleep(0.1)
-                stop_check_task.cancel()
-                try:
-                    await stop_check_task
-                except asyncio.CancelledError:
-                    pass
-
-        @retry(
-            before_sleep=log_retry_attempt,
-            stop=stop_after_attempt(self.config.num_retries),
-            reraise=True,
-            retry=(
-                retry_if_exception_type(self.retry_exceptions)
-                & retry_if_not_exception_type(OperationCancelled)
-            ),
-            wait=custom_completion_wait,
-        )
-        async def async_acompletion_stream_wrapper(*args, **kwargs):
-            """Async wrapper for the litellm acompletion with streaming function."""
-            # some callers might just send the messages directly
-            if 'messages' in kwargs:
-                messages = kwargs['messages']
-            else:
-                messages = args[1] if len(args) > 1 else []
-
-            # log the prompt
-            debug_message = ''
-            for message in messages:
-                debug_message += message_separator + message['content']
-            llm_prompt_logger.debug(debug_message)
-
-            try:
-                # Directly call and await litellm_acompletion
-                resp = await async_completion_unwrapped(*args, **kwargs)
-
-                # For streaming we iterate over the chunks
-                async for chunk in resp:
-                    # Check for cancellation before yielding the chunk
-                    if (
-                        hasattr(self.config, 'on_cancel_requested_fn')
-                        and self.config.on_cancel_requested_fn is not None
-                        and await self.config.on_cancel_requested_fn()
-                    ):
-                        raise UserCancelledError(
-                            'LLM request cancelled due to CANCELLED state'
-                        )
-                    # with streaming, it is "delta", not "message"!
-                    message_back = chunk['choices'][0]['delta']['content']
-                    llm_response_logger.debug(message_back)
-                    self._post_completion(chunk)
-
-                    yield chunk
-
-            except UserCancelledError:
-                logger.info('LLM request cancelled by user.')
-                raise
-            except (
-                APIConnectionError,
-                ContentPolicyViolationError,
-                InternalServerError,
-                NotFoundError,
-                OpenAIError,
-                RateLimitError,
-                ServiceUnavailableError,
-            ) as e:
-                logger.error(f'Completion Error occurred:\n{e}')
-                raise
-
-            finally:
-                if kwargs.get('stream', False):
-                    await asyncio.sleep(0.1)
-
-        self._async_completion = async_completion_wrapper  # type: ignore
-        self._async_streaming_completion = async_acompletion_stream_wrapper  # type: ignore
-
-    def _get_debug_message(self, messages):
-        if not messages:
-            return ''
-
-        messages = messages if isinstance(messages, list) else [messages]
-        return message_separator.join(
-            self._format_message_content(msg) for msg in messages if msg['content']
-        )
-
-    def _format_message_content(self, message):
-        content = message['content']
-        if isinstance(content, list):
-            return self._format_list_content(content)
-        return str(content)
-
-    def _format_list_content(self, content_list):
-        return '\n'.join(
-            self._format_content_element(element) for element in content_list
-        )
-
-    def _format_content_element(self, element):
-        if isinstance(element, dict):
-            if 'text' in element:
-                return element['text']
-            if (
-                self.vision_is_active()
-                and 'image_url' in element
-                and 'url' in element['image_url']
-            ):
-                return element['image_url']['url']
-        return str(element)
-
-    async def _call_acompletion(self, *args, **kwargs):
-        """This is a wrapper for the litellm acompletion function which
-        makes it mockable for testing.
-        """
-        return await litellm.acompletion(*args, **kwargs)
+        self._completion = wrapper

    @property
    def completion(self):
@@ -498,32 +215,7 @@ class LLM:

        Check the complete documentation at https://litellm.vercel.app/docs/completion
        """
-        try:
-            return self._completion
-        except Exception as e:
-            raise LLMResponseError(e)
-
-    @property
-    def async_completion(self):
-        """Decorator for the async litellm acompletion function.
-
-        Check the complete documentation at https://litellm.vercel.app/docs/providers/ollama#example-usage---streaming--acompletion
-        """
-        try:
-            return self._async_completion
-        except Exception as e:
-            raise LLMResponseError(e)
-
-    @property
-    def async_streaming_completion(self):
-        """Decorator for the async litellm acompletion function with streaming.
-
-        Check the complete documentation at https://litellm.vercel.app/docs/providers/ollama#example-usage---streaming--acompletion
-        """
-        try:
-            return self._async_streaming_completion
-        except Exception as e:
-            raise LLMResponseError(e)
+        return self._completion

    def vision_is_active(self):
        return not self.config.disable_vision and self._supports_vision()
@@ -534,38 +226,50 @@ class LLM:
        Returns:
            bool: True if model is vision capable. If model is not supported by litellm, it will return False.
        """
-        try:
-            return litellm.supports_vision(self.config.model)
-        except Exception:
-            return False
-
-    def is_caching_prompt_active(self) -> bool:
-        """Check if prompt caching is enabled and supported for current model.
-
-        Returns:
-            boolean: True if prompt caching is active for the given model.
-        """
-        return self.config.caching_prompt is True and any(
-            model in self.config.model for model in cache_prompting_supported_models
+        # litellm.supports_vision currently returns False for 'openai/gpt-...' or 'anthropic/claude-...' (with prefixes)
+        # but model_info will have the correct value for some reason.
+        # we can go with it, but we will need to keep an eye if model_info is correct for Vertex or other providers
+        # remove when litellm is updated to fix https://github.com/BerriAI/litellm/issues/5608
+        return litellm.supports_vision(self.config.model) or (
+            self.model_info is not None
+            and self.model_info.get('supports_vision', False)
        )

-    def _post_completion(self, response) -> None:
-        """Post-process the completion response."""
+    def is_caching_prompt_active(self) -> bool:
+        """Check if prompt caching is supported and enabled for current model.
+
+        Returns:
+            boolean: True if prompt caching is supported and enabled for the given model.
+        """
+        return (
+            self.config.caching_prompt is True
+            and self.model_info is not None
+            and self.model_info.get('supports_prompt_caching', False)
+            and self.config.model in CACHE_PROMPT_SUPPORTED_MODELS
+        )
+
+    def _post_completion(self, response: ModelResponse) -> None:
+        """Post-process the completion response.
+
+        Logs the cost and usage stats of the completion call.
+        """
        try:
-            cur_cost = self.completion_cost(response)
+            cur_cost = self._completion_cost(response)
        except Exception:
            cur_cost = 0

        stats = ''
        if self.cost_metric_supported:
+            # keep track of the cost
            stats = 'Cost: %.2f USD | Accumulated Cost: %.2f USD\n' % (
                cur_cost,
                self.metrics.accumulated_cost,
            )

-        usage = response.get('usage')
+        usage: Usage | None = response.get('usage')

        if usage:
+            # keep track of the input and output tokens
            input_tokens = usage.get('prompt_tokens')
            output_tokens = usage.get('completion_tokens')

@@ -580,6 +284,7 @@ class LLM:
                    + '\n'
                )

+            # read the prompt caching status as received from the provider
            model_extra = usage.get('model_extra', {})

            cache_creation_input_tokens = model_extra.get('cache_creation_input_tokens')
@@ -596,6 +301,7 @@ class LLM:
                    'Input tokens (cache read): ' + str(cache_read_input_tokens) + '\n'
                )

+        # log the stats
        if stats:
            logger.info(stats)

@@ -614,7 +320,7 @@ class LLM:
            # TODO: this is to limit logspam in case token count is not supported
            return 0

-    def is_local(self):
+    def _is_local(self):
        """Determines if the system is using a locally running LLM.

        Returns:
@@ -629,7 +335,7 @@ class LLM:
                return True
        return False

-    def completion_cost(self, response):
+    def _completion_cost(self, response):
        """Calculate the cost of a completion response based on the model.  Local models are treated as free.
        Add the current cost into total cost in metrics.

@@ -654,7 +360,7 @@ class LLM:
            logger.info(f'Using custom cost per token: {cost_per_token}')
            extra_kwargs['custom_cost_per_token'] = cost_per_token

-        if not self.is_local():
+        if not self._is_local():
            try:
                cost = litellm_completion_cost(
                    completion_response=response, **extra_kwargs
@@ -682,5 +388,12 @@ class LLM:

    def format_messages_for_llm(self, messages: Message | list[Message]) -> list[dict]:
        if isinstance(messages, Message):
-            return [messages.model_dump()]
+            messages = [messages]
+
+        # set flags to know how to serialize the messages
+        for message in messages:
+            message.cache_enabled = self.is_caching_prompt_active()
+            message.vision_enabled = self.vision_is_active()
+
+        # let pydantic handle the serialization
        return [message.model_dump() for message in messages]
@@ -0,0 +1,53 @@
+from tenacity import (
+    retry,
+    retry_if_exception_type,
+    stop_after_attempt,
+    wait_exponential,
+)
+
+from openhands.core.exceptions import OperationCancelled
+from openhands.core.logger import openhands_logger as logger
+from openhands.runtime.utils.shutdown_listener import should_exit
+
+
+class RetryMixin:
+    """Mixin class for retry logic."""
+
+    def retry_decorator(self, **kwargs):
+        """
+        Create a LLM retry decorator with customizable parameters. This is used for 429 errors, and a few other exceptions in LLM classes.
+
+        Args:
+            **kwargs: Keyword arguments to override default retry behavior.
+                      Keys: num_retries, retry_exceptions, retry_min_wait, retry_max_wait, retry_multiplier
+
+        Returns:
+            A retry decorator with the parameters customizable in configuration.
+        """
+        num_retries = kwargs.get('num_retries')
+        retry_exceptions = kwargs.get('retry_exceptions')
+        retry_min_wait = kwargs.get('retry_min_wait')
+        retry_max_wait = kwargs.get('retry_max_wait')
+        retry_multiplier = kwargs.get('retry_multiplier')
+
+        return retry(
+            before_sleep=self.log_retry_attempt,
+            stop=stop_after_attempt(num_retries),
+            reraise=True,
+            retry=(retry_if_exception_type(retry_exceptions)),
+            wait=wait_exponential(
+                multiplier=retry_multiplier,
+                min=retry_min_wait,
+                max=retry_max_wait,
+            ),
+        )
+
+    def log_retry_attempt(self, retry_state):
+        """Log retry attempts."""
+        if should_exit():
+            raise OperationCancelled('Operation cancelled.')  # exits the @retry loop
+        exception = retry_state.outcome.exception()
+        logger.error(
+            f'{exception}. Attempt #{retry_state.attempt_number} | You can customize retry values in the configuration.',
+            exc_info=False,
+        )
@@ -0,0 +1,106 @@
+import asyncio
+from functools import partial
+from typing import Any
+
+from openhands.core.exceptions import UserCancelledError
+from openhands.core.logger import openhands_logger as logger
+from openhands.llm.async_llm import LLM_RETRY_EXCEPTIONS, AsyncLLM
+
+
+class StreamingLLM(AsyncLLM):
+    """Streaming LLM class."""
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+        self._async_streaming_completion = partial(
+            self._call_acompletion,
+            model=self.config.model,
+            api_key=self.config.api_key,
+            base_url=self.config.base_url,
+            api_version=self.config.api_version,
+            custom_llm_provider=self.config.custom_llm_provider,
+            max_tokens=self.config.max_output_tokens,
+            timeout=self.config.timeout,
+            temperature=self.config.temperature,
+            top_p=self.config.top_p,
+            drop_params=self.config.drop_params,
+            stream=True,  # Ensure streaming is enabled
+        )
+
+        async_streaming_completion_unwrapped = self._async_streaming_completion
+
+        @self.retry_decorator(
+            num_retries=self.config.num_retries,
+            retry_exceptions=LLM_RETRY_EXCEPTIONS,
+            retry_min_wait=self.config.retry_min_wait,
+            retry_max_wait=self.config.retry_max_wait,
+            retry_multiplier=self.config.retry_multiplier,
+        )
+        async def async_streaming_completion_wrapper(*args, **kwargs):
+            messages: list[dict[str, Any]] | dict[str, Any] = []
+
+            # some callers might send the model and messages directly
+            # litellm allows positional args, like completion(model, messages, **kwargs)
+            # see llm.py for more details
+            if len(args) > 1:
+                messages = args[1] if len(args) > 1 else args[0]
+                kwargs['messages'] = messages
+
+                # remove the first args, they're sent in kwargs
+                args = args[2:]
+            elif 'messages' in kwargs:
+                messages = kwargs['messages']
+
+            # ensure we work with a list of messages
+            messages = messages if isinstance(messages, list) else [messages]
+
+            # if we have no messages, something went very wrong
+            if not messages:
+                raise ValueError(
+                    'The messages list is empty. At least one message is required.'
+                )
+
+            self.log_prompt(messages)
+
+            try:
+                # Directly call and await litellm_acompletion
+                resp = await async_streaming_completion_unwrapped(*args, **kwargs)
+
+                # For streaming we iterate over the chunks
+                async for chunk in resp:
+                    # Check for cancellation before yielding the chunk
+                    if (
+                        hasattr(self.config, 'on_cancel_requested_fn')
+                        and self.config.on_cancel_requested_fn is not None
+                        and await self.config.on_cancel_requested_fn()
+                    ):
+                        raise UserCancelledError(
+                            'LLM request cancelled due to CANCELLED state'
+                        )
+                    # with streaming, it is "delta", not "message"!
+                    message_back = chunk['choices'][0]['delta'].get('content', '')
+                    if message_back:
+                        self.log_response(message_back)
+                    self._post_completion(chunk)
+
+                    yield chunk
+
+            except UserCancelledError:
+                logger.info('LLM request cancelled by user.')
+                raise
+            except Exception as e:
+                logger.error(f'Completion Error occurred:\n{e}')
+                raise
+
+            finally:
+                # sleep for 0.1 seconds to allow the stream to be flushed
+                if kwargs.get('stream', False):
+                    await asyncio.sleep(0.1)
+
+        self._async_streaming_completion = async_streaming_completion_wrapper
+
+    @property
+    def async_streaming_completion(self):
+        """Decorator for the async litellm acompletion function with streaming."""
+        return self._async_streaming_completion
@@ -26,12 +26,13 @@ class RuntimeBuilder(abc.ABC):
        pass

    @abc.abstractmethod
-    def image_exists(self, image_name: str) -> bool:
+    def image_exists(self, image_name: str, pull_from_repo: bool = True) -> bool:
        """
        Check if the runtime image exists.

        Args:
            image_name (str): The name of the runtime image (e.g., "repo:sha").
+            pull_from_repo (bool): Whether to pull from the remote repo if the image not present locally

        Returns:
            bool: Whether the runtime image exists.
@@ -1,7 +1,12 @@
+import datetime
+import os
+import subprocess
 import sys
+import time

 import docker

+from openhands import __version__ as oh_version
 from openhands.core.logger import openhands_logger as logger
 from openhands.runtime.builder.base import RuntimeBuilder

@@ -10,45 +15,139 @@ class DockerRuntimeBuilder(RuntimeBuilder):
    def __init__(self, docker_client: docker.DockerClient):
        self.docker_client = docker_client

-    def build(self, path: str, tags: list[str]) -> str:
+        version_info = self.docker_client.version()
+        server_version = version_info.get('Version', '')
+        if tuple(map(int, server_version.split('.'))) < (18, 9):
+            raise RuntimeError('Docker server version must be >= 18.09 to use BuildKit')
+
+        self.max_lines = 10
+        self.log_lines = [''] * self.max_lines
+
+    def build(
+        self,
+        path: str,
+        tags: list[str],
+        use_local_cache: bool = False,
+        extra_build_args: list[str] | None = None,
+    ) -> str:
+        """Builds a Docker image using BuildKit and handles the build logs appropriately.
+
+        Args:
+            path (str): The path to the Docker build context.
+            tags (list[str]): A list of image tags to apply to the built image.
+            use_local_cache (bool, optional): Whether to use and update the local build cache. Defaults to True.
+            extra_build_args (list[str], optional): Additional arguments to pass to the Docker build command. Defaults to None.
+
+        Returns:
+            str: The name of the built Docker image.
+
+        Raises:
+            RuntimeError: If the Docker server version is incompatible or if the build process fails.
+
+        Note:
+            This method uses Docker BuildKit for improved build performance and caching capabilities.
+            If `use_local_cache` is True, it will attempt to use and update the build cache in a local directory.
+            The `extra_build_args` parameter allows for passing additional Docker build arguments as needed.
+        """
+        self.docker_client = docker.from_env()
+        version_info = self.docker_client.version()
+        server_version = version_info.get('Version', '')
+        if tuple(map(int, server_version.split('.'))) < (18, 9):
+            raise RuntimeError('Docker server version must be >= 18.09 to use BuildKit')
+
        target_image_hash_name = tags[0]
        target_image_repo, target_image_hash_tag = target_image_hash_name.split(':')
        target_image_tag = tags[1].split(':')[1] if len(tags) > 1 else None

-        try:
-            build_logs = self.docker_client.api.build(
-                path=path,
-                tag=target_image_hash_name,
-                rm=True,
-                decode=True,
-            )
-        except docker.errors.BuildError as e:
-            logger.error(f'Sandbox image build failed: {e}')
-            raise RuntimeError(f'Sandbox image build failed: {e}')
+        # Check if the image exists and pull if necessary
+        self.image_exists(target_image_repo)

-        layers: dict[str, dict[str, str]] = {}
-        previous_layer_count = 0
-        for log in build_logs:
-            if 'stream' in log:
-                logger.info(log['stream'].strip())
-            elif 'error' in log:
-                logger.error(log['error'].strip())
-            elif 'status' in log:
-                self._output_build_progress(log, layers, previous_layer_count)
-                previous_layer_count = len(layers)
-            else:
-                logger.info(str(log))
+        buildx_cmd = [
+            'docker',
+            'buildx',
+            'build',
+            '--progress=plain',
+            f'--build-arg=OPENHANDS_RUNTIME_VERSION={oh_version}',
+            f'--build-arg=OPENHANDS_RUNTIME_BUILD_TIME={datetime.datetime.now().isoformat()}',
+            f'--tag={target_image_hash_name}',
+            '--load',
+        ]
+
+        cache_dir = '/tmp/.buildx-cache'
+        if use_local_cache and self._is_cache_usable(cache_dir):
+            buildx_cmd.extend(
+                [
+                    f'--cache-from=type=local,src={cache_dir}',
+                    f'--cache-to=type=local,dest={cache_dir},mode=max',
+                ]
+            )
+
+        if extra_build_args:
+            buildx_cmd.extend(extra_build_args)
+
+        buildx_cmd.append(path)  # must be last!
+
+        print('================ DOCKER BUILD STARTED ================')
+        if sys.stdout.isatty():
+            sys.stdout.write('\n' * self.max_lines)
+            sys.stdout.flush()
+
+        try:
+            process = subprocess.Popen(
+                buildx_cmd,
+                stdout=subprocess.PIPE,
+                stderr=subprocess.STDOUT,
+                universal_newlines=True,
+                bufsize=1,
+            )
+
+            if process.stdout:
+                for line in iter(process.stdout.readline, ''):
+                    line = line.strip()
+                    if line:
+                        self._output_logs(line)
+
+            return_code = process.wait()
+
+            if return_code != 0:
+                raise subprocess.CalledProcessError(
+                    return_code,
+                    process.args,
+                    output=None,
+                    stderr=None,
+                )
+
+        except subprocess.CalledProcessError as e:
+            logger.error(f'Image build failed:\n{e}')
+            logger.error(f'Command output:\n{e.output}')
+            raise
+
+        except subprocess.TimeoutExpired:
+            logger.error('Image build timed out')
+            raise
+
+        except FileNotFoundError as e:
+            logger.error(f'Python executable not found: {e}')
+            raise
+
+        except PermissionError as e:
+            logger.error(
+                f'Permission denied when trying to execute the build command:\n{e}'
+            )
+            raise
+
+        except Exception as e:
+            logger.error(f'An unexpected error occurred during the build process: {e}')
+            raise

        logger.info(f'Image [{target_image_hash_name}] build finished.')

-        assert (
-            target_image_tag
-        ), f'Expected target image tag [{target_image_tag}] is None'
-        image = self.docker_client.images.get(target_image_hash_name)
-        image.tag(target_image_repo, target_image_tag)
-        logger.info(
-            f'Re-tagged image [{target_image_hash_name}] with more generic tag [{target_image_tag}]'
-        )
+        if target_image_tag:
+            image = self.docker_client.images.get(target_image_hash_name)
+            image.tag(target_image_repo, target_image_tag)
+            logger.info(
+                f'Re-tagged image [{target_image_hash_name}] with more generic tag [{target_image_tag}]'
+            )

        # Check if the image is built successfully
        image = self.docker_client.images.get(target_image_hash_name)
@@ -67,11 +166,12 @@ class DockerRuntimeBuilder(RuntimeBuilder):
        )
        return target_image_hash_name

-    def image_exists(self, image_name: str) -> bool:
+    def image_exists(self, image_name: str, pull_from_repo: bool = True) -> bool:
        """Check if the image exists in the registry (try to pull it first) or in the local store.

        Args:
            image_name (str): The Docker image to check (<image repo>:<image tag>)
+            pull_from_repo (bool): Whether to pull from the remote repo if the image not present locally
        Returns:
            bool: Whether the Docker image exists in the registry or in the local store
        """
@@ -80,13 +180,18 @@ class DockerRuntimeBuilder(RuntimeBuilder):
            return False

        try:
-            logger.info(f'Checking, if image exists locally:\n{image_name}')
+            logger.debug(f'Checking, if image exists locally:\n{image_name}')
            self.docker_client.images.get(image_name)
-            logger.info('Image found locally.')
+            logger.debug('Image found locally.')
            return True
        except docker.errors.ImageNotFound:
+            if not pull_from_repo:
+                logger.debug(
+                    f'Image {image_name} not found locally'
+                )
+                return False
            try:
-                logger.info(
+                logger.debug(
                    'Image not found locally. Trying to pull it, please wait...'
                )

@@ -97,10 +202,10 @@ class DockerRuntimeBuilder(RuntimeBuilder):
                ):
                    self._output_build_progress(line, layers, previous_layer_count)
                    previous_layer_count = len(layers)
-                logger.info('Image pulled')
+                logger.debug('Image pulled')
                return True
            except docker.errors.ImageNotFound:
-                logger.info('Could not find image locally or in registry.')
+                logger.debug('Could not find image locally or in registry.')
                return False
            except Exception as e:
                msg = 'Image could not be pulled: '
@@ -109,9 +214,30 @@ class DockerRuntimeBuilder(RuntimeBuilder):
                    msg += 'image not found in registry.'
                else:
                    msg += f'{ex_msg}'
-                logger.warning(msg)
+                logger.debug(msg)
                return False

+    def _output_logs(self, new_line: str) -> None:
+        """Display the last 10 log_lines in the console (not for file logging).
+        This will create the effect of a rolling display in the console.
+
+        '\033[F'    moves the cursor up one line.
+        '\033[2K\r' clears the line and moves the cursor to the beginning of the line.
+        """
+        if not sys.stdout.isatty():
+            logger.debug(new_line)
+            return
+
+        self.log_lines.pop(0)
+        self.log_lines.append(new_line[:80])
+
+        sys.stdout.write('\033[F' * (self.max_lines))
+        sys.stdout.flush()
+
+        for line in self.log_lines:
+            sys.stdout.write('\033[2K' + line + '\n')
+            sys.stdout.flush()
+
    def _output_build_progress(
        self, current_line: dict, layers: dict, previous_layer_count: int
    ) -> None:
@@ -126,31 +252,93 @@ class DockerRuntimeBuilder(RuntimeBuilder):
            if 'progress' in current_line:
                layers[layer_id]['progress'] = current_line['progress']

-            if (
-                'total' in current_line['progressDetail']
-                and 'current' in current_line['progressDetail']
-            ):
-                total = current_line['progressDetail']['total']
-                current = current_line['progressDetail']['current']
-                percentage = (current / total) * 100
-            else:
-                percentage = 0
+            if 'progressDetail' in current_line:
+                progress_detail = current_line['progressDetail']
+                if 'total' in progress_detail and 'current' in progress_detail:
+                    total = progress_detail['total']
+                    current = progress_detail['current']
+                    percentage = min(
+                        (current / total) * 100, 100
+                    )  # Ensure it doesn't exceed 100%
+                else:
+                    percentage = (
+                        100 if layers[layer_id]['status'] == 'Download complete' else 0
+                    )

-            # refresh process bar in console if stdout is a tty
            if sys.stdout.isatty():
                sys.stdout.write('\033[F' * previous_layer_count)
                for lid, layer_data in sorted(layers.items()):
-                    sys.stdout.write('\033[K')
-                    print(
-                        f'Layer {lid}: {layer_data["progress"]} {layer_data["status"]}'
-                    )
+                    sys.stdout.write('\033[2K\r')
+                    status = layer_data['status']
+                    progress = layer_data['progress']
+                    if status == 'Download complete':
+                        print(f'Layer {lid}: Download complete')
+                    elif status == 'Already exists':
+                        print(f'Layer {lid}: Already exists')
+                    else:
+                        print(f'Layer {lid}: {progress} {status}')
                sys.stdout.flush()
-            # otherwise Log only if percentage is at least 10% higher than last logged
-            elif percentage != 0 and percentage - layers[layer_id]['last_logged'] >= 10:
-                logger.info(
+            elif percentage != 0 and (
+                percentage - layers[layer_id]['last_logged'] >= 10 or percentage == 100
+            ):
+                logger.debug(
                    f'Layer {layer_id}: {layers[layer_id]["progress"]} {layers[layer_id]["status"]}'
                )

            layers[layer_id]['last_logged'] = percentage
        elif 'status' in current_line:
-            logger.info(current_line['status'])
+            logger.debug(current_line['status'])
+
+    def _prune_old_cache_files(self, cache_dir: str, max_age_days: int = 7) -> None:
+        """
+        Prune cache files older than the specified number of days.
+
+        Args:
+            cache_dir (str): The path to the cache directory.
+            max_age_days (int): The maximum age of cache files in days.
+        """
+        try:
+            current_time = time.time()
+            max_age_seconds = max_age_days * 24 * 60 * 60
+
+            for root, _, files in os.walk(cache_dir):
+                for file in files:
+                    file_path = os.path.join(root, file)
+                    try:
+                        file_age = current_time - os.path.getmtime(file_path)
+                        if file_age > max_age_seconds:
+                            os.remove(file_path)
+                            logger.debug(f'Removed old cache file: {file_path}')
+                    except Exception as e:
+                        logger.warning(f'Error processing cache file {file_path}: {e}')
+        except Exception as e:
+            logger.warning(f'Error during build cache pruning: {e}')
+
+    def _is_cache_usable(self, cache_dir: str) -> bool:
+        """
+        Check if the cache directory is usable (exists and is writable).
+
+        Args:
+            cache_dir (str): The path to the cache directory.
+
+        Returns:
+            bool: True if the cache directory is usable, False otherwise.
+        """
+        if not os.path.exists(cache_dir):
+            try:
+                os.makedirs(cache_dir, exist_ok=True)
+                logger.debug(f'Created cache directory: {cache_dir}')
+            except OSError as e:
+                logger.debug(f'Failed to create cache directory {cache_dir}: {e}')
+                return False
+
+        if not os.access(cache_dir, os.W_OK):
+            logger.warning(
+                f'Cache directory {cache_dir} is not writable. Caches will not be used for Docker builds.'
+            )
+            return False
+
+        self._prune_old_cache_files(cache_dir)
+
+        logger.debug(f'Cache directory {cache_dir} is usable')
+        return True
@@ -98,7 +98,7 @@ class RemoteRuntimeBuilder(RuntimeBuilder):
            # Wait before polling again
            sleep_if_should_continue(30)

-    def image_exists(self, image_name: str) -> bool:
+    def image_exists(self, image_name: str, pull_from_repo: bool = True) -> bool:
        """Checks if an image exists in the remote registry using the /image_exists endpoint."""
        params = {'image': image_name}
        response = send_request(
@@ -11,6 +11,7 @@ import os
 import re
 import shutil
 import subprocess
+import time
 from contextlib import asynccontextmanager
 from pathlib import Path

@@ -28,7 +29,6 @@ from openhands.events.action import (
    BrowseInteractiveAction,
    BrowseURLAction,
    CmdRunAction,
-    FileEditAction,
    FileReadAction,
    FileWriteAction,
    IPythonRunCellAction,
@@ -36,7 +36,6 @@ from openhands.events.action import (
 from openhands.events.observation import (
    CmdOutputObservation,
    ErrorObservation,
-    FileEditObservation,
    FileReadObservation,
    FileWriteObservation,
    IPythonRunCellObservation,
@@ -50,11 +49,6 @@ from openhands.runtime.plugins import (
    JupyterPlugin,
    Plugin,
 )
-from openhands.runtime.plugins.agent_skills.file_ops import (
-    append_file,
-    create_file,
-    edit_file_by_replace,
-)
 from openhands.runtime.utils import split_bash_commands
 from openhands.runtime.utils.files import insert_lines, read_lines

@@ -69,10 +63,6 @@ INIT_COMMANDS = [
 ]
 SOFT_TIMEOUT_SECONDS = 5

-HEAD = '<<<<<<< SEARCH'
-DIVIDER = '======='
-TAIL = '>>>>>>> REPLACE'
-

 class RuntimeClient:
    """RuntimeClient is running inside docker sandbox.
@@ -97,6 +87,8 @@ class RuntimeClient:
        self.lock = asyncio.Lock()
        self.plugins: dict[str, Plugin] = {}
        self.browser = BrowserEnv(browsergym_eval_env)
+        self.start_time = time.time()
+        self.last_execution_time = self.start_time

    @property
    def initial_pwd(self):
@@ -331,7 +323,13 @@ class RuntimeClient:
            logger.debug('Requesting exit code...')
            self.shell.expect(self.__bash_expect_regex, timeout=timeout)
            _exit_code_output = self.shell.before
-            exit_code = int(_exit_code_output.strip().split()[0])
+            try:
+                exit_code = int(_exit_code_output.strip().split()[0])
+            except:
+                logger.error('Error getting exit code from bash script')
+                # If we try to run an invalid shell script the output sometimes includes error text
+                # rather than the error code - we assume this is an error
+                exit_code = 2

        except pexpect.TIMEOUT as e:
            if kill_on_timeout:
@@ -520,55 +518,6 @@ class RuntimeClient:
            return ErrorObservation(f'Malformed paths not permitted: {filepath}')
        return FileWriteObservation(content='', path=filepath)

-    async def edit(self, action: FileEditAction) -> Observation:
-        diff_blocks = re.search(
-            f'(.*)\n{HEAD}(.*)\n{DIVIDER}(.*)\n{TAIL}', action.diff_block, re.DOTALL
-        )
-        if not diff_blocks or len(diff_blocks.groups()) < 3:
-            found_head = re.search(f'{HEAD}', action.diff_block) is not None
-            found_divider = re.search(f'{DIVIDER}', action.diff_block) is not None
-            found_tail = re.search(f'{TAIL}', action.diff_block) is not None
-
-            error_msg = 'Could not resolve diff block into search/replace blocks.'
-            if found_head and (not found_tail):
-                error_msg = 'The diff block got cut off because it is too long. Try breaking it into smaller SEARCH/REPLACE blocks.'
-            elif found_head and found_tail and (not found_divider):
-                error_msg = 'Could not find the divider between SEARCH/REPLACE blocks.'
-            return ErrorObservation(error_msg)
-
-        path = diff_blocks.group(1)
-        search_block = diff_blocks.group(2)
-        replace_block = diff_blocks.group(3)
-        if search_block:
-            search_block = search_block[1:]
-        if replace_block:
-            replace_block = replace_block[1:]
-
-        working_dir = self._get_working_directory()
-        filepath = self._resolve_path(path, working_dir)
-        if not search_block:
-            create_file(filename=filepath)
-            append_file(
-                file_name=filepath,
-                content=replace_block,
-            )
-        else:
-            if search_block == replace_block:
-                return ErrorObservation(
-                    'Search block should not be same as Replace block.'
-                )
-            edit_file_by_replace(
-                file_name=filepath,
-                to_replace=search_block,
-                new_content=replace_block,
-            )
-        return FileEditObservation(
-            content=action.diff_block,
-            path=filepath,
-            search_block=search_block,
-            replace_block=replace_block,
-        )
-
    async def browse(self, action: BrowseURLAction) -> Observation:
        return await browse(action, self.browser)

@@ -660,6 +609,14 @@ if __name__ == '__main__':
            response = await call_next(request)
        return response

+    @app.get('/server_info')
+    async def get_server_info():
+        assert client is not None
+        current_time = time.time()
+        uptime = current_time - client.start_time
+        idle_time = current_time - client.last_execution_time
+        return {'uptime': uptime, 'idle_time': idle_time}
+
    @app.post('/execute_action')
    async def execute_action(action_request: ActionRequest):
        assert client is not None
@@ -667,10 +624,11 @@ if __name__ == '__main__':
            action = event_from_dict(action_request.action)
            if not isinstance(action, Action):
                raise HTTPException(status_code=400, detail='Invalid action type')
+            client.last_execution_time = time.time()
            observation = await client.run_action(action)
            return event_to_dict(observation)
        except Exception as e:
-            logger.error(f'Error processing command: {str(e)}')
+            logger.error(f'Error processing command: {str(e)}', exc_info=True, stack_info=True)
            raise HTTPException(status_code=500, detail=str(e))

    @app.post('/upload_file')
@@ -10,6 +10,7 @@ import requests
 import tenacity

 from openhands.core.config import AppConfig
+from openhands.core.logger import DEBUG
 from openhands.core.logger import openhands_logger as logger
 from openhands.events import EventStream
 from openhands.events.action import (
@@ -17,7 +18,6 @@ from openhands.events.action import (
    BrowseInteractiveAction,
    BrowseURLAction,
    CmdRunAction,
-    FileEditAction,
    FileReadAction,
    FileWriteAction,
    IPythonRunCellAction,
@@ -249,7 +249,7 @@ class EventStreamRuntime(Runtime):
                'port': str(self._container_port),
                'PYTHONUNBUFFERED': 1,
            }
-            if self.config.debug:
+            if self.config.debug or DEBUG:
                environment['DEBUG'] = 'true'

            logger.debug(f'Workspace Base: {self.config.workspace_base}')
@@ -452,9 +452,6 @@ class EventStreamRuntime(Runtime):
    def write(self, action: FileWriteAction) -> Observation:
        return self.run_action(action)

-    def edit(self, action: FileEditAction) -> Observation:
-        return self.run_action(action)
-
    def browse(self, action: BrowseURLAction) -> Observation:
        return self.run_action(action)

@@ -10,18 +10,9 @@ import_functions(
    module=file_reader, function_names=file_reader.__all__, target_globals=globals()
 )
 __all__ = file_ops.__all__ + file_reader.__all__
-__except__ = [
-    'create_file',
-    'edit_file_by_replace',
-    'insert_content_at_line',
-    'append_file',
-]  ## DISABLED TEMPORARILY.

 DOCUMENTATION = ''
 for func_name in __all__:
-    if func_name in __except__:
-        continue
-
    func = globals()[func_name]

    cur_doc = func.__doc__
@@ -5,8 +5,3 @@ import_functions(
    module=file_ops, function_names=file_ops.__all__, target_globals=globals()
 )
 __all__ = file_ops.__all__
-
-create_file = file_ops.create_file
-append_file = file_ops.append_file
-edit_file_by_replace = file_ops.edit_file_by_replace
-insert_content_at_line = file_ops.insert_content_at_line
@@ -786,7 +786,6 @@ def append_file(file_name: str, content: str) -> None:

    Args:
        file_name: str: The name of the file to edit.
-        line_number: int: The line number (starting from 1) to insert the content after.
        content: str: The content to insert.
    """
    ret_str = _edit_file_impl(
@@ -61,7 +61,7 @@ class RemoteRuntime(Runtime):
        self.config = config
        if self.config.sandbox.api_hostname == 'localhost':
            self.config.sandbox.api_hostname = 'api.all-hands.dev/v0/runtime'
-            logger.warning(
+            logger.info(
                'Using localhost as the API hostname is not supported in the RemoteRuntime. Please set a proper hostname.\n'
                'Setting it to default value: api.all-hands.dev/v0/runtime'
            )
@@ -14,7 +14,6 @@ from openhands.events.action import (
    BrowseInteractiveAction,
    BrowseURLAction,
    CmdRunAction,
-    FileEditAction,
    FileReadAction,
    FileWriteAction,
    IPythonRunCellAction,
@@ -180,10 +179,6 @@ class Runtime:
    def write(self, action: FileWriteAction) -> Observation:
        pass

-    @abstractmethod
-    def edit(self, action: FileEditAction) -> Observation:
-        pass
-
    @abstractmethod
    def browse(self, action: BrowseURLAction) -> Observation:
        pass
@@ -6,11 +6,11 @@ import subprocess
 import tempfile

 import docker
-import toml
 from dirhash import dirhash
 from jinja2 import Environment, FileSystemLoader

 import openhands
+from openhands import __version__ as oh_version
 from openhands.core.logger import openhands_logger as logger
 from openhands.runtime.builder import DockerRuntimeBuilder, RuntimeBuilder

@@ -19,19 +19,6 @@ def get_runtime_image_repo():
    return os.getenv('OH_RUNTIME_RUNTIME_IMAGE_REPO', 'ghcr.io/all-hands-ai/runtime')


-def _get_package_version():
-    """Read the version from pyproject.toml.
-
-    Returns:
-    - The version specified in pyproject.toml under [tool.poetry]
-    """
-    project_root = os.path.dirname(os.path.dirname(os.path.abspath(openhands.__file__)))
-    pyproject_path = os.path.join(project_root, 'pyproject.toml')
-    with open(pyproject_path, 'r') as f:
-        pyproject_data = toml.load(f)
-    return pyproject_data['tool']['poetry']['version']
-
-
 def _put_source_code_to_dir(temp_dir: str):
    """Builds the project source tarball directly in temp_dir and unpacks it.
    The OpenHands source code ends up in the temp_dir/code directory.
@@ -46,7 +33,7 @@ def _put_source_code_to_dir(temp_dir: str):
    logger.info(f'Building source distribution using project root: {project_root}')

    # Fetch the correct version from pyproject.toml
-    package_version = _get_package_version()
+    package_version = oh_version
    tarball_filename = f'openhands_ai-{package_version}.tar.gz'
    tarball_path = os.path.join(temp_dir, tarball_filename)

@@ -154,14 +141,23 @@ def prep_docker_build_folder(
        file.write(dockerfile_content)

    # Get the MD5 hash of the dir_path directory
-    dist_hash = dirhash(dir_path, 'md5')
+    dir_hash = dirhash(
+        dir_path,
+        'md5',
+        ignore=[
+            '.*/',  # hidden directories
+            '__pycache__/',
+            '*.pyc',
+        ],
+    )
+    hash = f'v{oh_version}_{dir_hash}'
    logger.info(
        f'Input base image: {base_image}\n'
        f'Skip init: {skip_init}\n'
        f'Extra deps: {extra_deps}\n'
-        f'Hash for docker build directory [{dir_path}] (contents: {os.listdir(dir_path)}): {dist_hash}\n'
+        f'Hash for docker build directory [{dir_path}] (contents: {os.listdir(dir_path)}): {hash}\n'
    )
-    return dist_hash
+    return hash


 def get_runtime_image_repo_and_tag(base_image: str) -> tuple[str, str]:
@@ -188,7 +184,6 @@ def get_runtime_image_repo_and_tag(base_image: str) -> tuple[str, str]:
        if ':' not in base_image:
            base_image = base_image + ':latest'
        [repo, tag] = base_image.split(':')
-        oh_version = _get_package_version()

        # Hash the repo if it's too long
        if len(repo) > 32:
@@ -256,7 +251,7 @@ def build_runtime_image(

    # Scenario 1: If we already have an image with the exact same hash, then it means the image is already built
    # with the exact same source code and Dockerfile, so we will reuse it. Building it is not required.
-    if not force_rebuild and runtime_builder.image_exists(hash_runtime_image_name):
+    if not force_rebuild and runtime_builder.image_exists(hash_runtime_image_name, False):
        logger.info(
            f'Image [{hash_runtime_image_name}] already exists so we will reuse it.'
        )
@@ -370,14 +365,20 @@ def _build_sandbox_image(
    target_image_hash_name = f'{target_image_repo}:{target_image_hash_tag}'
    target_image_generic_name = f'{target_image_repo}:{target_image_tag}'

+    tags_to_add = [target_image_hash_name]
+
+    # Only add the generic tag if the image does not exist
+    # so it does not get overwritten & only points to the earliest version
+    # to avoid "too many layers" after many re-builds
+    if not runtime_builder.image_exists(target_image_generic_name):
+        tags_to_add.append(target_image_generic_name)
+
    try:
-        image_name = runtime_builder.build(
-            path=docker_folder, tags=[target_image_hash_name, target_image_generic_name]
-        )
+        image_name = runtime_builder.build(path=docker_folder, tags=tags_to_add)
        if not image_name:
            raise RuntimeError(f'Build failed for image {target_image_hash_name}')
    except Exception as e:
-        logger.error(f'Sandbox image build failed: {e}')
+        logger.error(f'Sandbox image build failed: {str(e)}')
        raise

    return image_name
@@ -69,8 +69,7 @@ RUN \
    /openhands/miniforge3/bin/mamba run -n base poetry run pip install playwright && \
    /openhands/miniforge3/bin/mamba run -n base poetry run playwright install --with-deps chromium && \
    # Set environment variables
-    export OH_INTERPRETER_PATH=$(/openhands/miniforge3/bin/mamba run -n base poetry run python -c "import sys; print(sys.executable)") && \
-    export OH_VENV_PATH=$(/openhands/miniforge3/bin/mamba run -n base poetry env info --path) && \
+    echo "OH_INTERPRETER_PATH=$(/openhands/miniforge3/bin/mamba run -n base poetry run python -c "import sys; print(sys.executable)")" >> /etc/environment && \
    # Install extra dependencies if specified
    {{ extra_deps }} {% if extra_deps %} && {% endif %} \
    # Clear caches
@@ -81,16 +80,6 @@ RUN \
    # Clean up
    apt-get clean && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \
    /openhands/miniforge3/bin/mamba clean --all
-{% if not skip_init %}
-RUN \
-    # Add the Poetry virtual environment to the bashrc
-    echo "export OH_INTERPRETER_PATH=\"$OH_INTERPRETER_PATH\"" >> /etc/bash.bashrc && \
-    echo "export OH_VENV_PATH=\"$OH_VENV_PATH\"" >> /etc/bash.bashrc && \
-    # Activate the Poetry virtual environment
-    echo 'source "$OH_VENV_PATH/bin/activate"' >> /etc/bash.bashrc && \
-    # Use the Poetry virtual environment's Python interpreter
-    echo 'alias python="$OH_INTERPRETER_PATH"' >> /etc/bash.bashrc
-{% endif %}
 # ================================================================
 # END: Copy Project and Install/Update Dependencies
 # ================================================================
@@ -1,5 +1,4 @@
 import asyncio
-
 from threading import Thread
 from typing import Callable, Optional

@@ -8,6 +7,9 @@ from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig, AppConfig, LLMConfig
 from openhands.core.logger import openhands_logger as logger
+from openhands.core.schema.agent import AgentState
+from openhands.events.action.agent import ChangeAgentStateAction
+from openhands.events.event import EventSource
 from openhands.events.stream import EventStream
 from openhands.runtime import get_runtime_cls
 from openhands.runtime.runtime import Runtime
@@ -29,6 +31,7 @@ class AgentSession:
    runtime: Runtime | None = None
    security_analyzer: SecurityAnalyzer | None = None
    _closed: bool = False
+    loop: asyncio.AbstractEventLoop

    def __init__(self, sid: str, file_store: FileStore):
        """Initializes a new instance of the Session class
@@ -41,6 +44,7 @@ class AgentSession:
        self.sid = sid
        self.event_stream = EventStream(sid, file_store)
        self.file_store = file_store
+        self.loop = asyncio.new_event_loop()

    async def start(
        self,
@@ -68,10 +72,32 @@ class AgentSession:
                'Session already started. You need to close this session and start a new one.'
            )

-        self.loop = asyncio.new_event_loop()
        self.thread = Thread(target=self._run, daemon=True)
        self.thread.start()

+        coro = self._start(
+            runtime_name,
+            config,
+            agent,
+            max_iterations,
+            max_budget_per_task,
+            agent_to_llm_config,
+            agent_configs,
+            status_message_callback,
+        )
+        asyncio.run_coroutine_threadsafe(coro, self.loop)  # type: ignore
+
+    async def _start(
+        self,
+        runtime_name: str,
+        config: AppConfig,
+        agent: Agent,
+        max_iterations: int,
+        max_budget_per_task: float | None = None,
+        agent_to_llm_config: dict[str, LLMConfig] | None = None,
+        agent_configs: dict[str, AgentConfig] | None = None,
+        status_message_callback: Optional[Callable] = None,
+    ):
        self._create_security_analyzer(config.security.security_analyzer)
        self._create_runtime(runtime_name, config, agent, status_message_callback)
        self._create_controller(
@@ -82,9 +108,12 @@ class AgentSession:
            agent_to_llm_config=agent_to_llm_config,
            agent_configs=agent_configs,
        )
-        
-        if self.controller is not None:
-            self.controller.agent_task = asyncio.run_coroutine_threadsafe(self.controller.start_step_loop(), self.loop) # type: ignore
+        self.event_stream.add_event(
+            ChangeAgentStateAction(AgentState.INIT), EventSource.USER
+        )
+        if self.controller:
+            self.controller.agent_task = self.controller.start_step_loop()
+            await self.controller.agent_task  # type: ignore

    def _run(self):
        asyncio.set_event_loop(self.loop)
@@ -123,9 +123,6 @@ class Session:
                f'Error creating controller. Please check Docker is running and visit `{TROUBLESHOOTING_URL}` for more debugging information..'
            )
            return
-        self.agent_session.event_stream.add_event(
-            ChangeAgentStateAction(AgentState.INIT), EventSource.USER
-        )

    async def on_event(self, event: Event):
        """Callback function for events that mainly come from the agent.
@@ -165,6 +162,9 @@ class Session:
                        'Model does not support image upload, change to a different model or try without an image.'
                    )
                    return
+        asyncio.run_coroutine_threadsafe(self._add_event(event, EventSource.USER), self.agent_session.loop) # type: ignore
+
+    async def _add_event(self, event, event_source):
        self.agent_session.event_stream.add_event(event, EventSource.USER)

    async def send(self, data: dict[str, object]) -> bool:
@@ -190,6 +190,10 @@ class Session:
        """Sends a message to the client."""
        return await self.send({'message': message})

+    async def send_status_message(self, message: str) -> bool:
+        """Sends a status message to the client."""
+        return await self.send({'status': message})
+
    def update_connection(self, ws: WebSocket):
        self.websocket = ws
        self.is_alive = True
@@ -205,4 +209,4 @@ class Session:
    def queue_status_message(self, message: str):
        """Queues a status message to be sent asynchronously."""
        # Ensure the coroutine runs in the main event loop
-        asyncio.run_coroutine_threadsafe(self.send_message(message), self.loop)
+        asyncio.run_coroutine_threadsafe(self.send_status_message(message), self.loop)
@@ -571,17 +571,17 @@ files = [

 [[package]]
 name = "boto3"
-version = "1.35.25"
+version = "1.35.28"
 description = "The AWS SDK for Python"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "boto3-1.35.25-py3-none-any.whl", hash = "sha256:b1cfad301184cdd44dfd4805187ccab12de8dd28dd12a11a5cfdace17918c6de"},
-    {file = "boto3-1.35.25.tar.gz", hash = "sha256:5df4e2cbe3409db07d3a0d8d63d5220ce3202a78206ad87afdbb41519b26ce45"},
+    {file = "boto3-1.35.28-py3-none-any.whl", hash = "sha256:dc088b86a14f17d3cd2e96915c6ccfd31bce640dfe9180df579ed311bc6bf0fc"},
+    {file = "boto3-1.35.28.tar.gz", hash = "sha256:8960fc458b9ba3c8a9890a607c31cee375db821f39aefaec9ff638248e81644a"},
 ]

 [package.dependencies]
-botocore = ">=1.35.25,<1.36.0"
+botocore = ">=1.35.28,<1.36.0"
 jmespath = ">=0.7.1,<2.0.0"
 s3transfer = ">=0.10.0,<0.11.0"

@@ -590,13 +590,13 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"]

 [[package]]
 name = "botocore"
-version = "1.35.25"
+version = "1.35.28"
 description = "Low-level, data-driven core of boto 3."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "botocore-1.35.25-py3-none-any.whl", hash = "sha256:e58d60260abf10ccc4417967923117c9902a6a0cff9fddb6ea7ff42dc1bd4630"},
-    {file = "botocore-1.35.25.tar.gz", hash = "sha256:76c5706b2c6533000603ae8683a297c887abbbaf6ee31e1b2e2863b74b2989bc"},
+    {file = "botocore-1.35.28-py3-none-any.whl", hash = "sha256:b66c78f3d6379bd16f0362f07168fa7699cdda3921fc880047192d96f2c8c527"},
+    {file = "botocore-1.35.28.tar.gz", hash = "sha256:115d13f2172d8e9fa92e8d913f0e80092b97624d190f46772ed2930d4a355d55"},
 ]

 [package.dependencies]
@@ -609,32 +609,32 @@ crt = ["awscrt (==0.21.5)"]

 [[package]]
 name = "browsergym"
-version = "0.7.0"
+version = "0.7.1"
 description = "BrowserGym: a gym environment for web task automation in the Chromium browser"
 optional = false
 python-versions = ">3.7"
 files = [
-    {file = "browsergym-0.7.0-py3-none-any.whl", hash = "sha256:e2b98d2990ec1bfd80fd3e8034e60a60f363a5240be794e0ace975f24601d1a8"},
-    {file = "browsergym-0.7.0.tar.gz", hash = "sha256:e1cd9812b32a9387bac42b726bf7669c35a46b5fe6d1faf939333f095d5a6ba5"},
+    {file = "browsergym-0.7.1-py3-none-any.whl", hash = "sha256:af216abf3e1ad538e4d31e5bf96da03768ac4aabc9a566159355fa2b6af093da"},
+    {file = "browsergym-0.7.1.tar.gz", hash = "sha256:c269eb8b6da4bd186c05529f3492a9bef2210a89e2cdae4b7557b6ae7091c28e"},
 ]

 [package.dependencies]
-browsergym-core = "0.7.0"
-browsergym-experiments = "0.7.0"
-browsergym-miniwob = "0.7.0"
-browsergym-visualwebarena = "0.7.0"
-browsergym-webarena = "0.7.0"
+browsergym-core = "0.7.1"
+browsergym-experiments = "0.7.1"
+browsergym-miniwob = "0.7.1"
+browsergym-visualwebarena = "0.7.1"
+browsergym-webarena = "0.7.1"
 browsergym-workarena = "*"

 [[package]]
 name = "browsergym-core"
-version = "0.7.0"
+version = "0.7.1"
 description = "BrowserGym: a gym environment for web task automation in the Chromium browser"
 optional = false
 python-versions = ">3.9"
 files = [
-    {file = "browsergym_core-0.7.0-py3-none-any.whl", hash = "sha256:4f4c7a153daa984701f76e81eaa358b4a9684e8f3fb4dcd80c807e7ed8112914"},
-    {file = "browsergym_core-0.7.0.tar.gz", hash = "sha256:069987057dcdea2c25b1b631691f93d77c2d042108079c16874128dcc459d809"},
+    {file = "browsergym_core-0.7.1-py3-none-any.whl", hash = "sha256:28a79537e91fd0dff639fbed9d1f3318b99f8aa5efe054f2468fc0bf2d220ba6"},
+    {file = "browsergym_core-0.7.1.tar.gz", hash = "sha256:da6bdd190a8ccdc8394e68a2a17701b7af3208e0267ca7ed9fd33dc4c2c7ea99"},
 ]

 [package.dependencies]
@@ -643,67 +643,67 @@ gymnasium = ">=0.27"
 lxml = ">=4.9"
 numpy = ">=1.14"
 pillow = ">=10.1"
-playwright = ">=1.32,<1.40"
+playwright = ">=1.39,<2.0"
 pyparsing = ">=3"

 [[package]]
 name = "browsergym-experiments"
-version = "0.7.0"
+version = "0.7.1"
 description = "Experimentation tools for BrowserGym"
 optional = false
 python-versions = ">3.7"
 files = [
-    {file = "browsergym_experiments-0.7.0-py3-none-any.whl", hash = "sha256:c10f810eb631622804ebbf5e5783636cf8aff2a53ea0e38bfcfb129273865b1b"},
-    {file = "browsergym_experiments-0.7.0.tar.gz", hash = "sha256:9ee937720d2b84563851a2ae2c94c685da299fbadd957ba743ef7f1351fd0e23"},
+    {file = "browsergym_experiments-0.7.1-py3-none-any.whl", hash = "sha256:0f3104da708436fe93460cd609590d28aa9dcbeda68d8a51599a56daaea7cd96"},
+    {file = "browsergym_experiments-0.7.1.tar.gz", hash = "sha256:75f9e5676e625cb7ec4a5fbce8d6832708b01cb4e5af9c150cfd27182af60a74"},
 ]

 [package.dependencies]
-browsergym-core = "0.7.0"
+browsergym-core = "0.7.1"
 tiktoken = ">=0.4"

 [[package]]
 name = "browsergym-miniwob"
-version = "0.7.0"
+version = "0.7.1"
 description = "MiniWoB++ benchmark for BrowserGym"
 optional = false
 python-versions = ">3.7"
 files = [
-    {file = "browsergym_miniwob-0.7.0-py3-none-any.whl", hash = "sha256:9223400aa737dcbca79884a6174b67635ec5b913f490232b60e5391fc34eecb4"},
-    {file = "browsergym_miniwob-0.7.0.tar.gz", hash = "sha256:b4d248541a86f9dc21c9fc5a03699ef16dfd96a97d9347d3c6ef4ae9145f691f"},
+    {file = "browsergym_miniwob-0.7.1-py3-none-any.whl", hash = "sha256:69f560b5d0210a5db3b2672d0ac48e274170f765832e3628da3fd0ba694d3f40"},
+    {file = "browsergym_miniwob-0.7.1.tar.gz", hash = "sha256:635909cbe0646985699fc65715c463e258c04dad16521bfa59cb0ae4ec797f8f"},
 ]

 [package.dependencies]
-browsergym-core = "0.7.0"
+browsergym-core = "0.7.1"

 [[package]]
 name = "browsergym-visualwebarena"
-version = "0.7.0"
+version = "0.7.1"
 description = "VisualWebArena benchmark for BrowserGym"
 optional = false
 python-versions = ">3.7"
 files = [
-    {file = "browsergym_visualwebarena-0.7.0-py3-none-any.whl", hash = "sha256:499124dd8a0619905049598428205cad4d3237e6acef80225f3c734f428b16b9"},
-    {file = "browsergym_visualwebarena-0.7.0.tar.gz", hash = "sha256:78fd89a922b94b7de912b6ab44d48845a25283eb7265c526811542f6833edbaa"},
+    {file = "browsergym_visualwebarena-0.7.1-py3-none-any.whl", hash = "sha256:bf9bb0d2f406276531aee10dd04371b152cfa2c703402291e57a04ea47847c43"},
+    {file = "browsergym_visualwebarena-0.7.1.tar.gz", hash = "sha256:b26db1d75a9ecae7d97a1bbefad2d7ea10e49119e4aec8320cf6f8bcd265e45c"},
 ]

 [package.dependencies]
-browsergym-core = "0.7.0"
+browsergym-core = "0.7.1"
 libvisualwebarena = "0.0.8"
 requests = "*"

 [[package]]
 name = "browsergym-webarena"
-version = "0.7.0"
+version = "0.7.1"
 description = "WebArena benchmark for BrowserGym"
 optional = false
 python-versions = ">3.7"
 files = [
-    {file = "browsergym_webarena-0.7.0-py3-none-any.whl", hash = "sha256:d04b2cdadce47ffc9b4d6751f7f5dbd403e561cf4bf2b80801edcbb03bcf8ce6"},
-    {file = "browsergym_webarena-0.7.0.tar.gz", hash = "sha256:f7b0839ca009962457a03c948261fb36fbcbababd60208132ec77f92c6a19a59"},
+    {file = "browsergym_webarena-0.7.1-py3-none-any.whl", hash = "sha256:117cb2946d8a9b3536d0a55300eb28b7650c0e70339855bed8890f0f8fc887e9"},
+    {file = "browsergym_webarena-0.7.1.tar.gz", hash = "sha256:568de29ab0a7a1a569855e1bb71af5cfd4e982156988a64e30ada3bfe309b399"},
 ]

 [package.dependencies]
-browsergym-core = "0.7.0"
+browsergym-core = "0.7.1"
 libwebarena = "0.0.3"

 [[package]]
@@ -1014,13 +1014,13 @@ numpy = "*"

 [[package]]
 name = "chromadb"
-version = "0.5.7"
+version = "0.5.11"
 description = "Chroma."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "chromadb-0.5.7-py3-none-any.whl", hash = "sha256:2358f92804cd198b125de73076ec48f9f55c729df119919a76a6716ad0e465f6"},
-    {file = "chromadb-0.5.7.tar.gz", hash = "sha256:3432865025ef3ceeaee0a59b265a784d8b5978cb7c41593c74ddd2427c776c94"},
+    {file = "chromadb-0.5.11-py3-none-any.whl", hash = "sha256:f02d9326869cea926f980bd6c9a0150a0ef2e151072f325998c16a9502fb4b25"},
+    {file = "chromadb-0.5.11.tar.gz", hash = "sha256:252e970b3e1a27b594cc7b3685238691bf8eaa232225d4dee9e33ec83580775f"},
 ]

 [package.dependencies]
@@ -1351,13 +1351,13 @@ typing-inspect = ">=0.4.0,<1"

 [[package]]
 name = "datasets"
-version = "3.0.0"
+version = "3.0.1"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-3.0.0-py3-none-any.whl", hash = "sha256:c23fefb6c953dcb1cd5f6deb6c502729c733ef98791e0c3f2d80c7ca2d9a01dd"},
-    {file = "datasets-3.0.0.tar.gz", hash = "sha256:592317eb137f0fc5aac068ff283ba13c3c66d10c9c034d44bc8aa584126cf3e2"},
+    {file = "datasets-3.0.1-py3-none-any.whl", hash = "sha256:db080aab41c8cc68645117a0f172e5c6789cbc672f066de0aa5a08fc3eebc686"},
+    {file = "datasets-3.0.1.tar.gz", hash = "sha256:40d63b09e76a3066c32e746d6fdc36fd3f29ed2acd49bf5b1a2100da32936511"},
 ]

 [package.dependencies]
@@ -1379,15 +1379,15 @@ xxhash = "*"
 [package.extras]
 audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "transformers (>=4.42.0)", "zstandard"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "torchdata", "transformers", "transformers (>=4.42.0)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "zstandard"]
-tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "zstandard"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=9.4.0)"]

@@ -2142,13 +2142,13 @@ test = ["coverage[toml]", "ddt (>=1.1.1,!=1.4.3)", "mock", "mypy", "pre-commit",

 [[package]]
 name = "google-ai-generativelanguage"
-version = "0.6.9"
+version = "0.6.10"
 description = "Google Ai Generativelanguage API client library"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "google_ai_generativelanguage-0.6.9-py3-none-any.whl", hash = "sha256:50360cd80015d1a8cc70952e98560f32fa06ddee2e8e9f4b4b98e431dc561e0b"},
-    {file = "google_ai_generativelanguage-0.6.9.tar.gz", hash = "sha256:899f1d3a06efa9739f1cd9d2788070178db33c89d4a76f2e8f4da76f649155fa"},
+    {file = "google_ai_generativelanguage-0.6.10-py3-none-any.whl", hash = "sha256:854a2bf833d18be05ad5ef13c755567b66a4f4a870f099b62c61fe11bddabcf4"},
+    {file = "google_ai_generativelanguage-0.6.10.tar.gz", hash = "sha256:6fa642c964d8728006fe7e8771026fc0b599ae0ebeaf83caf550941e8e693455"},
 ]

 [package.dependencies]
@@ -2240,13 +2240,13 @@ httplib2 = ">=0.19.0"

 [[package]]
 name = "google-cloud-aiplatform"
-version = "1.67.1"
+version = "1.68.0"
 description = "Vertex AI API client library"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "google-cloud-aiplatform-1.67.1.tar.gz", hash = "sha256:701a19061c8c670baa93464ca0b8a1a8720494f802187cef06bc9fcf952db315"},
-    {file = "google_cloud_aiplatform-1.67.1-py2.py3-none-any.whl", hash = "sha256:2ff0e1794839fcf74d644f3f54ff2de5d8099b3e388edecc48f6d620c1f3582c"},
+    {file = "google-cloud-aiplatform-1.68.0.tar.gz", hash = "sha256:d74e9f33707c7a14c6a32a7cfe9acd32b90975dfba9fac487d105c8ba5197f40"},
+    {file = "google_cloud_aiplatform-1.68.0-py2.py3-none-any.whl", hash = "sha256:24dacc34457665ab6054bdf47e2475793dcf2d865b568420a909b452a477b3e6"},
 ]

 [package.dependencies]
@@ -2277,7 +2277,7 @@ pipelines = ["pyyaml (>=5.3.1,<7)"]
 prediction = ["docker (>=5.0.3)", "fastapi (>=0.71.0,<=0.114.0)", "httpx (>=0.23.0,<0.25.0)", "starlette (>=0.17.1)", "uvicorn[standard] (>=0.16.0)"]
 private-endpoints = ["requests (>=2.28.1)", "urllib3 (>=1.21.1,<1.27)"]
 ray = ["google-cloud-bigquery", "google-cloud-bigquery-storage", "immutabledict", "pandas (>=1.0.0,<2.2.0)", "pyarrow (>=6.0.1)", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<2.10.dev0 || >=2.33.dev0,<=2.33.0)", "ray[default] (>=2.5,<=2.33.0)", "setuptools (<70.0.0)"]
-ray-testing = ["google-cloud-bigquery", "google-cloud-bigquery-storage", "immutabledict", "pandas (>=1.0.0,<2.2.0)", "pyarrow (>=6.0.1)", "pytest-xdist", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<2.10.dev0 || >=2.33.dev0,<=2.33.0)", "ray[default] (>=2.5,<=2.33.0)", "ray[train] (==2.9.3)", "scikit-learn", "setuptools (<70.0.0)", "tensorflow", "torch (>=2.0.0,<2.1.0)", "xgboost", "xgboost-ray"]
+ray-testing = ["google-cloud-bigquery", "google-cloud-bigquery-storage", "immutabledict", "pandas (>=1.0.0,<2.2.0)", "pyarrow (>=6.0.1)", "pytest-xdist", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<2.10.dev0 || >=2.33.dev0,<=2.33.0)", "ray[default] (>=2.5,<=2.33.0)", "ray[train]", "scikit-learn", "setuptools (<70.0.0)", "tensorflow", "torch (>=2.0.0,<2.1.0)", "xgboost", "xgboost-ray"]
 reasoningengine = ["cloudpickle (>=3.0,<4.0)", "google-cloud-trace (<2)", "opentelemetry-exporter-gcp-trace (<2)", "opentelemetry-sdk (<2)", "pydantic (>=2.6.3,<3)"]
 tensorboard = ["tensorboard-plugin-profile (>=2.4.0,<3.0.0dev)", "tensorflow (>=2.3.0,<3.0.0dev)", "tensorflow (>=2.4.0,<3.0.0dev)", "werkzeug (>=2.0.0,<2.1.0dev)"]
 testing = ["bigframes", "docker (>=5.0.3)", "explainable-ai-sdk (>=1.0.0)", "fastapi (>=0.71.0,<=0.114.0)", "google-api-core (>=2.11,<3.0.0)", "google-cloud-bigquery", "google-cloud-bigquery-storage", "google-vizier (>=0.1.6)", "grpcio-testing", "httpx (>=0.23.0,<0.25.0)", "immutabledict", "ipython", "kfp (>=2.6.0,<3.0.0)", "lit-nlp (==0.4.0)", "mlflow (>=1.27.0,<=2.16.0)", "nltk", "numpy (>=1.15.0)", "pandas (>=1.0.0)", "pandas (>=1.0.0,<2.2.0)", "pyarrow (>=10.0.1)", "pyarrow (>=14.0.0)", "pyarrow (>=3.0.0,<8.0dev)", "pyarrow (>=6.0.1)", "pytest-asyncio", "pytest-xdist", "pyyaml (>=5.3.1,<7)", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<2.10.dev0 || >=2.33.dev0,<=2.33.0)", "ray[default] (>=2.5,<=2.33.0)", "requests (>=2.28.1)", "requests-toolbelt (<1.0.0)", "scikit-learn", "sentencepiece (>=0.2.0)", "setuptools (<70.0.0)", "starlette (>=0.17.1)", "tensorboard-plugin-profile (>=2.4.0,<3.0.0dev)", "tensorflow (==2.13.0)", "tensorflow (==2.16.1)", "tensorflow (>=2.3.0,<3.0.0dev)", "tensorflow (>=2.3.0,<3.0.0dev)", "tensorflow (>=2.4.0,<3.0.0dev)", "torch (>=2.0.0,<2.1.0)", "torch (>=2.2.0)", "tqdm (>=4.23.0)", "urllib3 (>=1.21.1,<1.27)", "uvicorn[standard] (>=0.16.0)", "werkzeug (>=2.0.0,<2.1.0dev)", "xgboost"]
@@ -2457,16 +2457,16 @@ testing = ["pytest"]

 [[package]]
 name = "google-generativeai"
-version = "0.8.1"
+version = "0.8.2"
 description = "Google Generative AI High level API client library and tools."
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "google_generativeai-0.8.1-py3-none-any.whl", hash = "sha256:b031877f24d51af0945207657c085896a0a886eceec7a1cb7029327b0aa6e2f6"},
+    {file = "google_generativeai-0.8.2-py3-none-any.whl", hash = "sha256:fabc0e2e8d2bfb6fdb1653e91dba83fecb2a2a6878883b80017def90fda8032d"},
 ]

 [package.dependencies]
-google-ai-generativelanguage = "0.6.9"
+google-ai-generativelanguage = "0.6.10"
 google-api-core = "*"
 google-api-python-client = "*"
 google-auth = ">=2.15.0"
@@ -3234,13 +3234,13 @@ files = [

 [[package]]
 name = "json-repair"
-version = "0.29.4"
+version = "0.29.5"
 description = "A package to repair broken json strings"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "json_repair-0.29.4-py3-none-any.whl", hash = "sha256:2d7addfa01e3b4c295c4ebabd5f393127adae0d345616d3a2517df8260429dae"},
-    {file = "json_repair-0.29.4.tar.gz", hash = "sha256:2921760e707ac0d0b63478402fd6ea3162d4191adf873b396becb31c47a1ac30"},
+    {file = "json_repair-0.29.5-py3-none-any.whl", hash = "sha256:4932e65ce9d61f820e1741c9fff4e9801db87cd542166bfff56f2ea4f2a94104"},
+    {file = "json_repair-0.29.5.tar.gz", hash = "sha256:a6bb7999ee179856efc404fe1b96c15b1e26bb371dd2f246382464b5332d4d1a"},
 ]

 [[package]]
@@ -3762,13 +3762,13 @@ types-tqdm = "*"

 [[package]]
 name = "litellm"
-version = "1.48.0"
+version = "1.48.5"
 description = "Library to easily interface with LLM API providers"
 optional = false
 python-versions = "!=2.7.*,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,!=3.7.*,>=3.8"
 files = [
-    {file = "litellm-1.48.0-py3-none-any.whl", hash = "sha256:7765e8a92069778f5fc66aacfabd0e2f8ec8d74fb117f5e475567d89b0d376b9"},
-    {file = "litellm-1.48.0.tar.gz", hash = "sha256:31a9b8a25a9daf44c24ddc08bf74298da920f2c5cea44135e5061278d0aa6fc9"},
+    {file = "litellm-1.48.5-py3-none-any.whl", hash = "sha256:d69ae3809047922f1051f0c501759be3363421e1e17230dc4483f8e630f364d1"},
+    {file = "litellm-1.48.5.tar.gz", hash = "sha256:7b698623647c588e7740ada3b1faea2ee005804d93c4e6c3c975a7f0a77b751a"},
 ]

 [package.dependencies]
@@ -3805,19 +3805,19 @@ pydantic = ">=1.10"

 [[package]]
 name = "llama-index"
-version = "0.11.12"
+version = "0.11.14"
 description = "Interface between LLMs and your data"
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "llama_index-0.11.12-py3-none-any.whl", hash = "sha256:a7d0b4065df2689cec1baeab9bfaed4d94e4ddc7e941df2ee47abfb218ce3ea1"},
-    {file = "llama_index-0.11.12.tar.gz", hash = "sha256:6b9220bf4c76a4ac0a82ccc642c3ea94f51381a9718ac601021f2fa95b74aab1"},
+    {file = "llama_index-0.11.14-py3-none-any.whl", hash = "sha256:69447a25cb73f910146200e8f45579e0a6e5e390bb2818f229e68fbb625e0a2d"},
+    {file = "llama_index-0.11.14.tar.gz", hash = "sha256:6d18093550bdf92442dc7aa0e4d9fef2616941e3d101409340d47c7a99b9f739"},
 ]

 [package.dependencies]
 llama-index-agent-openai = ">=0.3.4,<0.4.0"
 llama-index-cli = ">=0.3.1,<0.4.0"
-llama-index-core = ">=0.11.11,<0.12.0"
+llama-index-core = ">=0.11.14,<0.12.0"
 llama-index-embeddings-openai = ">=0.2.4,<0.3.0"
 llama-index-indices-managed-llama-cloud = ">=0.3.0"
 llama-index-legacy = ">=0.9.48,<0.10.0"
@@ -3863,13 +3863,13 @@ llama-index-llms-openai = ">=0.2.0,<0.3.0"

 [[package]]
 name = "llama-index-core"
-version = "0.11.12"
+version = "0.11.14"
 description = "Interface between LLMs and your data"
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "llama_index_core-0.11.12-py3-none-any.whl", hash = "sha256:7dc7ead649bac8f09e61c6c8bf93d257f68a7315223552421be4f0ffc3a8054d"},
-    {file = "llama_index_core-0.11.12.tar.gz", hash = "sha256:ce2dd037ff889d9ea6b25872228cc9de614c10445d19377f6ae5c66b93a50c61"},
+    {file = "llama_index_core-0.11.14-py3-none-any.whl", hash = "sha256:e63e5b1f4daa56952a7846cbbf0265b1288909efaea866216a4c6fb65daa2923"},
+    {file = "llama_index_core-0.11.14.tar.gz", hash = "sha256:6ff7be9f5bbb04be0d8064f76510edf79f8a9833ebae28b46261b274556827ca"},
 ]

 [package.dependencies]
@@ -5365,13 +5365,13 @@ sympy = "*"

 [[package]]
 name = "openai"
-version = "1.47.1"
+version = "1.50.2"
 description = "The official Python library for the openai API"
 optional = false
 python-versions = ">=3.7.1"
 files = [
-    {file = "openai-1.47.1-py3-none-any.whl", hash = "sha256:34277583bf268bb2494bc03f48ac123788c5e2a914db1d5a23d5edc29d35c825"},
-    {file = "openai-1.47.1.tar.gz", hash = "sha256:62c8f5f478f82ffafc93b33040f8bb16a45948306198bd0cba2da2ecd9cf7323"},
+    {file = "openai-1.50.2-py3-none-any.whl", hash = "sha256:822dd2051baa3393d0d5406990611975dd6f533020dc9375a34d4fe67e8b75f7"},
+    {file = "openai-1.50.2.tar.gz", hash = "sha256:3987ae027152fc8bea745d60b02c8f4c4a76e1b5c70e73565fa556db6f78c9e6"},
 ]

 [package.dependencies]
@@ -7123,13 +7123,13 @@ files = [

 [[package]]
 name = "reportlab"
-version = "4.2.2"
+version = "4.2.4"
 description = "The Reportlab Toolkit"
 optional = false
 python-versions = "<4,>=3.7"
 files = [
-    {file = "reportlab-4.2.2-py3-none-any.whl", hash = "sha256:927616931637e2f13e2ee3b3b6316d7a07803170e258621cff7d138bde17fbb5"},
-    {file = "reportlab-4.2.2.tar.gz", hash = "sha256:765eecbdd68491c56947e29c38b8b69b834ee5dbbdd2fb7409f08ebdebf04428"},
+    {file = "reportlab-4.2.4-py3-none-any.whl", hash = "sha256:6e4d86647b8bfd772f475a58f9b0dcba4b340b1969f0db36333089f6ca9ab362"},
+    {file = "reportlab-4.2.4.tar.gz", hash = "sha256:a00b57292e156a7bda84edf31d60c25578153076c8fb96331d0c59eddda052c8"},
 ]

 [package.dependencies]
@@ -7367,29 +7367,29 @@ pyasn1 = ">=0.1.3"

 [[package]]
 name = "ruff"
-version = "0.6.7"
+version = "0.6.8"
 description = "An extremely fast Python linter and code formatter, written in Rust."
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "ruff-0.6.7-py3-none-linux_armv6l.whl", hash = "sha256:08277b217534bfdcc2e1377f7f933e1c7957453e8a79764d004e44c40db923f2"},
-    {file = "ruff-0.6.7-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:c6707a32e03b791f4448dc0dce24b636cbcdee4dd5607adc24e5ee73fd86c00a"},
-    {file = "ruff-0.6.7-py3-none-macosx_11_0_arm64.whl", hash = "sha256:533d66b7774ef224e7cf91506a7dafcc9e8ec7c059263ec46629e54e7b1f90ab"},
-    {file = "ruff-0.6.7-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:17a86aac6f915932d259f7bec79173e356165518859f94649d8c50b81ff087e9"},
-    {file = "ruff-0.6.7-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:b3f8822defd260ae2460ea3832b24d37d203c3577f48b055590a426a722d50ef"},
-    {file = "ruff-0.6.7-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9ba4efe5c6dbbb58be58dd83feedb83b5e95c00091bf09987b4baf510fee5c99"},
-    {file = "ruff-0.6.7-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:525201b77f94d2b54868f0cbe5edc018e64c22563da6c5c2e5c107a4e85c1c0d"},
-    {file = "ruff-0.6.7-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8854450839f339e1049fdbe15d875384242b8e85d5c6947bb2faad33c651020b"},
-    {file = "ruff-0.6.7-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2f0b62056246234d59cbf2ea66e84812dc9ec4540518e37553513392c171cb18"},
-    {file = "ruff-0.6.7-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b1462fa56c832dc0cea5b4041cfc9c97813505d11cce74ebc6d1aae068de36b"},
-    {file = "ruff-0.6.7-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:02b083770e4cdb1495ed313f5694c62808e71764ec6ee5db84eedd82fd32d8f5"},
-    {file = "ruff-0.6.7-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:0c05fd37013de36dfa883a3854fae57b3113aaa8abf5dea79202675991d48624"},
-    {file = "ruff-0.6.7-py3-none-musllinux_1_2_i686.whl", hash = "sha256:f49c9caa28d9bbfac4a637ae10327b3db00f47d038f3fbb2195c4d682e925b14"},
-    {file = "ruff-0.6.7-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:a0e1655868164e114ba43a908fd2d64a271a23660195017c17691fb6355d59bb"},
-    {file = "ruff-0.6.7-py3-none-win32.whl", hash = "sha256:a939ca435b49f6966a7dd64b765c9df16f1faed0ca3b6f16acdf7731969deb35"},
-    {file = "ruff-0.6.7-py3-none-win_amd64.whl", hash = "sha256:590445eec5653f36248584579c06252ad2e110a5d1f32db5420de35fb0e1c977"},
-    {file = "ruff-0.6.7-py3-none-win_arm64.whl", hash = "sha256:b28f0d5e2f771c1fe3c7a45d3f53916fc74a480698c4b5731f0bea61e52137c8"},
-    {file = "ruff-0.6.7.tar.gz", hash = "sha256:44e52129d82266fa59b587e2cd74def5637b730a69c4542525dfdecfaae38bd5"},
+    {file = "ruff-0.6.8-py3-none-linux_armv6l.whl", hash = "sha256:77944bca110ff0a43b768f05a529fecd0706aac7bcce36d7f1eeb4cbfca5f0f2"},
+    {file = "ruff-0.6.8-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:27b87e1801e786cd6ede4ada3faa5e254ce774de835e6723fd94551464c56b8c"},
+    {file = "ruff-0.6.8-py3-none-macosx_11_0_arm64.whl", hash = "sha256:cd48f945da2a6334f1793d7f701725a76ba93bf3d73c36f6b21fb04d5338dcf5"},
+    {file = "ruff-0.6.8-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:677e03c00f37c66cea033274295a983c7c546edea5043d0c798833adf4cf4c6f"},
+    {file = "ruff-0.6.8-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:9f1476236b3eacfacfc0f66aa9e6cd39f2a624cb73ea99189556015f27c0bdeb"},
+    {file = "ruff-0.6.8-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6f5a2f17c7d32991169195d52a04c95b256378bbf0de8cb98478351eb70d526f"},
+    {file = "ruff-0.6.8-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:5fd0d4b7b1457c49e435ee1e437900ced9b35cb8dc5178921dfb7d98d65a08d0"},
+    {file = "ruff-0.6.8-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f8034b19b993e9601f2ddf2c517451e17a6ab5cdb1c13fdff50c1442a7171d87"},
+    {file = "ruff-0.6.8-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:6cfb227b932ba8ef6e56c9f875d987973cd5e35bc5d05f5abf045af78ad8e098"},
+    {file = "ruff-0.6.8-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6ef0411eccfc3909269fed47c61ffebdcb84a04504bafa6b6df9b85c27e813b0"},
+    {file = "ruff-0.6.8-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:007dee844738c3d2e6c24ab5bc7d43c99ba3e1943bd2d95d598582e9c1b27750"},
+    {file = "ruff-0.6.8-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:ce60058d3cdd8490e5e5471ef086b3f1e90ab872b548814e35930e21d848c9ce"},
+    {file = "ruff-0.6.8-py3-none-musllinux_1_2_i686.whl", hash = "sha256:1085c455d1b3fdb8021ad534379c60353b81ba079712bce7a900e834859182fa"},
+    {file = "ruff-0.6.8-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:70edf6a93b19481affd287d696d9e311388d808671bc209fb8907b46a8c3af44"},
+    {file = "ruff-0.6.8-py3-none-win32.whl", hash = "sha256:792213f7be25316f9b46b854df80a77e0da87ec66691e8f012f887b4a671ab5a"},
+    {file = "ruff-0.6.8-py3-none-win_amd64.whl", hash = "sha256:ec0517dc0f37cad14a5319ba7bba6e7e339d03fbf967a6d69b0907d61be7a263"},
+    {file = "ruff-0.6.8-py3-none-win_arm64.whl", hash = "sha256:8d3bb2e3fbb9875172119021a13eed38849e762499e3cfde9588e4b4d70968dc"},
+    {file = "ruff-0.6.8.tar.gz", hash = "sha256:a5bf44b1aa0adaf6d9d20f86162b34f7c593bfedabc51239953e446aefc8ce18"},
 ]

 [[package]]
@@ -9688,4 +9688,4 @@ testing = ["coverage (>=5.0.3)", "zope.event", "zope.testing"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.11"
-content-hash = "90636ce436e5c05146a69730f461f46fd3185b595be37d3eafd8aef36667db81"
+content-hash = "78e09d0b5c33f39ec951659658b5b4b46ba206d8f95e9a154be4e0ef869b7c79"
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "openhands-ai"
-version = "0.9.4"
+version = "0.9.6"
 description = "OpenHands: Code Less, Make More"
 authors = ["OpenHands"]
 license = "MIT"
@@ -27,7 +27,7 @@ uvicorn = "*"
 types-toml = "*"
 numpy = "*"
 json-repair = "*"
-browsergym = "0.7.0" # integrate browsergym as the browsing interface
+browsergym = "0.7.1" # integrate browsergym as the browsing interface
 html2text = "*"
 e2b = "^0.17.1"
 pexpect = "*"
@@ -65,7 +65,7 @@ llama-index-embeddings-azure-openai = "*"
 llama-index-embeddings-ollama = "*"

 [tool.poetry.group.dev.dependencies]
-ruff = "0.6.7"
+ruff = "0.6.8"
 mypy = "1.11.2"
 pre-commit = "3.8.0"
 build = "*"
@@ -85,6 +85,7 @@ reportlab = "*"
 [tool.coverage.run]
 concurrency = ["gevent"]

+
 [tool.poetry.group.runtime.dependencies]
 jupyterlab = "*"
 notebook = "*"
@@ -115,6 +116,7 @@ ignore = ["D1"]
 [tool.ruff.lint.pydocstyle]
 convention = "google"

+
 [tool.poetry.group.evaluation.dependencies]
 streamlit = "*"
 whatthepatch = "*"
@@ -11,7 +11,7 @@ from http.server import HTTPServer, SimpleHTTPRequestHandler
 import pytest
 from litellm import completion

-from openhands.llm.llm import message_separator
+from openhands.llm.debug_mixin import MESSAGE_SEPARATOR

 script_dir = os.environ.get('SCRIPT_DIR')
 project_root = os.environ.get('PROJECT_ROOT')
@@ -81,19 +81,19 @@ def _format_messages(messages):
    message_str = ''
    for message in messages:
        if isinstance(message, str):
-            message_str += message_separator + message if message_str else message
+            message_str += MESSAGE_SEPARATOR + message if message_str else message
        elif isinstance(message, dict):
            if isinstance(message['content'], list):
                for m in message['content']:
                    if isinstance(m, str):
-                        message_str += message_separator + m if message_str else m
+                        message_str += MESSAGE_SEPARATOR + m if message_str else m
                    elif isinstance(m, dict) and m['type'] == 'text':
                        message_str += (
-                            message_separator + m['text'] if message_str else m['text']
+                            MESSAGE_SEPARATOR + m['text'] if message_str else m['text']
                        )
            elif isinstance(message['content'], str):
                message_str += (
-                    message_separator + message['content']
+                    MESSAGE_SEPARATOR + message['content']
                    if message_str
                    else message['content']
                )
@@ -117,7 +117,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -117,7 +117,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -117,7 +117,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -117,7 +117,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -117,7 +117,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -116,7 +116,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -116,7 +116,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -116,7 +116,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -116,7 +116,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -418,9 +417,9 @@ git status
 ----------

 OBSERVATION:
-fatal: not a git repository (or any parent up to mount point /)
-Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
-
+fatal: not a git repository (or any parent up to mount point /)
+Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -418,9 +417,9 @@ git status
 ----------

 OBSERVATION:
-fatal: not a git repository (or any parent up to mount point /)
-Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
-
+fatal: not a git repository (or any parent up to mount point /)
+Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -437,19 +436,19 @@ git init
 ----------

 OBSERVATION:
-hint: Using 'master' as the name for the initial branch. This default branch name
-hint: is subject to change. To configure the initial branch name to use in all
-hint: of your new repositories, which will suppress this warning, call:
-hint:
-hint: 	git config --global init.defaultBranch <name>
-hint:
-hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
-hint: 'development'. The just-created branch can be renamed via this command:
-hint:
-hint: 	git branch -m <name>
-error: chmod on /workspace/.git/config.lock failed: Operation not permitted
-fatal: could not set 'core.filemode' to 'false'
-
+hint: Using 'master' as the name for the initial branch. This default branch name
+hint: is subject to change. To configure the initial branch name to use in all
+hint: of your new repositories, which will suppress this warning, call:
+hint:
+hint: 	git config --global init.defaultBranch <name>
+hint:
+hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
+hint: 'development'. The just-created branch can be renamed via this command:
+hint:
+hint: 	git branch -m <name>
+error: chmod on /workspace/.git/config.lock failed: Operation not permitted
+fatal: could not set 'core.filemode' to 'false'
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -418,9 +417,9 @@ git status
 ----------

 OBSERVATION:
-fatal: not a git repository (or any parent up to mount point /)
-Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
-
+fatal: not a git repository (or any parent up to mount point /)
+Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -437,19 +436,19 @@ git init
 ----------

 OBSERVATION:
-hint: Using 'master' as the name for the initial branch. This default branch name
-hint: is subject to change. To configure the initial branch name to use in all
-hint: of your new repositories, which will suppress this warning, call:
-hint:
-hint: 	git config --global init.defaultBranch <name>
-hint:
-hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
-hint: 'development'. The just-created branch can be renamed via this command:
-hint:
-hint: 	git branch -m <name>
-error: chmod on /workspace/.git/config.lock failed: Operation not permitted
-fatal: could not set 'core.filemode' to 'false'
-
+hint: Using 'master' as the name for the initial branch. This default branch name
+hint: is subject to change. To configure the initial branch name to use in all
+hint: of your new repositories, which will suppress this warning, call:
+hint:
+hint: 	git config --global init.defaultBranch <name>
+hint:
+hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
+hint: 'development'. The just-created branch can be renamed via this command:
+hint:
+hint: 	git branch -m <name>
+error: chmod on /workspace/.git/config.lock failed: Operation not permitted
+fatal: could not set 'core.filemode' to 'false'
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -466,11 +465,11 @@ ls -la
 ----------

 OBSERVATION:
-total 4
-drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .
-drwxr-xr-x 1 root root 4096 Sep  8 15:57 ..
-drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .git
-
+total 4
+drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .
+drwxr-xr-x 1 root root 4096 Sep  8 15:57 ..
+drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .git
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 0]
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -418,9 +417,9 @@ git status
 ----------

 OBSERVATION:
-fatal: not a git repository (or any parent up to mount point /)
-Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
-
+fatal: not a git repository (or any parent up to mount point /)
+Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -437,19 +436,19 @@ git init
 ----------

 OBSERVATION:
-hint: Using 'master' as the name for the initial branch. This default branch name
-hint: is subject to change. To configure the initial branch name to use in all
-hint: of your new repositories, which will suppress this warning, call:
-hint:
-hint: 	git config --global init.defaultBranch <name>
-hint:
-hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
-hint: 'development'. The just-created branch can be renamed via this command:
-hint:
-hint: 	git branch -m <name>
-error: chmod on /workspace/.git/config.lock failed: Operation not permitted
-fatal: could not set 'core.filemode' to 'false'
-
+hint: Using 'master' as the name for the initial branch. This default branch name
+hint: is subject to change. To configure the initial branch name to use in all
+hint: of your new repositories, which will suppress this warning, call:
+hint:
+hint: 	git config --global init.defaultBranch <name>
+hint:
+hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
+hint: 'development'. The just-created branch can be renamed via this command:
+hint:
+hint: 	git branch -m <name>
+error: chmod on /workspace/.git/config.lock failed: Operation not permitted
+fatal: could not set 'core.filemode' to 'false'
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -466,11 +465,11 @@ ls -la
 ----------

 OBSERVATION:
-total 4
-drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .
-drwxr-xr-x 1 root root 4096 Sep  8 15:57 ..
-drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .git
-
+total 4
+drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .
+drwxr-xr-x 1 root root 4096 Sep  8 15:57 ..
+drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .git
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 0]
@@ -485,9 +484,9 @@ git status
 ----------

 OBSERVATION:
-fatal: not a git repository (or any parent up to mount point /)
-Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
-
+fatal: not a git repository (or any parent up to mount point /)
+Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -418,9 +417,9 @@ git status
 ----------

 OBSERVATION:
-fatal: not a git repository (or any parent up to mount point /)
-Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
-
+fatal: not a git repository (or any parent up to mount point /)
+Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -437,19 +436,19 @@ git init
 ----------

 OBSERVATION:
-hint: Using 'master' as the name for the initial branch. This default branch name
-hint: is subject to change. To configure the initial branch name to use in all
-hint: of your new repositories, which will suppress this warning, call:
-hint:
-hint: 	git config --global init.defaultBranch <name>
-hint:
-hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
-hint: 'development'. The just-created branch can be renamed via this command:
-hint:
-hint: 	git branch -m <name>
-error: chmod on /workspace/.git/config.lock failed: Operation not permitted
-fatal: could not set 'core.filemode' to 'false'
-
+hint: Using 'master' as the name for the initial branch. This default branch name
+hint: is subject to change. To configure the initial branch name to use in all
+hint: of your new repositories, which will suppress this warning, call:
+hint:
+hint: 	git config --global init.defaultBranch <name>
+hint:
+hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
+hint: 'development'. The just-created branch can be renamed via this command:
+hint:
+hint: 	git branch -m <name>
+error: chmod on /workspace/.git/config.lock failed: Operation not permitted
+fatal: could not set 'core.filemode' to 'false'
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -466,11 +465,11 @@ ls -la
 ----------

 OBSERVATION:
-total 4
-drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .
-drwxr-xr-x 1 root root 4096 Sep  8 15:57 ..
-drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .git
-
+total 4
+drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .
+drwxr-xr-x 1 root root 4096 Sep  8 15:57 ..
+drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .git
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 0]
@@ -485,9 +484,9 @@ git status
 ----------

 OBSERVATION:
-fatal: not a git repository (or any parent up to mount point /)
-Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
-
+fatal: not a git repository (or any parent up to mount point /)
+Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -504,7 +503,7 @@ mkdir my_project && cd my_project
 ----------

 OBSERVATION:
-
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace/my_project $
 [Command -1 finished with exit code 0]
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -418,9 +417,9 @@ git status
 ----------

 OBSERVATION:
-fatal: not a git repository (or any parent up to mount point /)
-Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
-
+fatal: not a git repository (or any parent up to mount point /)
+Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -437,19 +436,19 @@ git init
 ----------

 OBSERVATION:
-hint: Using 'master' as the name for the initial branch. This default branch name
-hint: is subject to change. To configure the initial branch name to use in all
-hint: of your new repositories, which will suppress this warning, call:
-hint:
-hint: 	git config --global init.defaultBranch <name>
-hint:
-hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
-hint: 'development'. The just-created branch can be renamed via this command:
-hint:
-hint: 	git branch -m <name>
-error: chmod on /workspace/.git/config.lock failed: Operation not permitted
-fatal: could not set 'core.filemode' to 'false'
-
+hint: Using 'master' as the name for the initial branch. This default branch name
+hint: is subject to change. To configure the initial branch name to use in all
+hint: of your new repositories, which will suppress this warning, call:
+hint:
+hint: 	git config --global init.defaultBranch <name>
+hint:
+hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
+hint: 'development'. The just-created branch can be renamed via this command:
+hint:
+hint: 	git branch -m <name>
+error: chmod on /workspace/.git/config.lock failed: Operation not permitted
+fatal: could not set 'core.filemode' to 'false'
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -466,11 +465,11 @@ ls -la
 ----------

 OBSERVATION:
-total 4
-drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .
-drwxr-xr-x 1 root root 4096 Sep  8 15:57 ..
-drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .git
-
+total 4
+drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .
+drwxr-xr-x 1 root root 4096 Sep  8 15:57 ..
+drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .git
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 0]
@@ -485,9 +484,9 @@ git status
 ----------

 OBSERVATION:
-fatal: not a git repository (or any parent up to mount point /)
-Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
-
+fatal: not a git repository (or any parent up to mount point /)
+Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -504,7 +503,7 @@ mkdir my_project && cd my_project
 ----------

 OBSERVATION:
-
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace/my_project $
 [Command -1 finished with exit code 0]
@@ -521,7 +520,7 @@ echo "Hello, this is a test file." > test.txt
 ----------

 OBSERVATION:
-
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace/my_project $
 [Command -1 finished with exit code 0]
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -418,9 +417,9 @@ git status
 ----------

 OBSERVATION:
-fatal: not a git repository (or any parent up to mount point /)
-Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
-
+fatal: not a git repository (or any parent up to mount point /)
+Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -437,19 +436,19 @@ git init
 ----------

 OBSERVATION:
-hint: Using 'master' as the name for the initial branch. This default branch name
-hint: is subject to change. To configure the initial branch name to use in all
-hint: of your new repositories, which will suppress this warning, call:
-hint:
-hint: 	git config --global init.defaultBranch <name>
-hint:
-hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
-hint: 'development'. The just-created branch can be renamed via this command:
-hint:
-hint: 	git branch -m <name>
-error: chmod on /workspace/.git/config.lock failed: Operation not permitted
-fatal: could not set 'core.filemode' to 'false'
-
+hint: Using 'master' as the name for the initial branch. This default branch name
+hint: is subject to change. To configure the initial branch name to use in all
+hint: of your new repositories, which will suppress this warning, call:
+hint:
+hint: 	git config --global init.defaultBranch <name>
+hint:
+hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
+hint: 'development'. The just-created branch can be renamed via this command:
+hint:
+hint: 	git branch -m <name>
+error: chmod on /workspace/.git/config.lock failed: Operation not permitted
+fatal: could not set 'core.filemode' to 'false'
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -466,11 +465,11 @@ ls -la
 ----------

 OBSERVATION:
-total 4
-drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .
-drwxr-xr-x 1 root root 4096 Sep  8 15:57 ..
-drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .git
-
+total 4
+drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .
+drwxr-xr-x 1 root root 4096 Sep  8 15:57 ..
+drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .git
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 0]
@@ -485,9 +484,9 @@ git status
 ----------

 OBSERVATION:
-fatal: not a git repository (or any parent up to mount point /)
-Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
-
+fatal: not a git repository (or any parent up to mount point /)
+Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -504,7 +503,7 @@ mkdir my_project && cd my_project
 ----------

 OBSERVATION:
-
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace/my_project $
 [Command -1 finished with exit code 0]
@@ -521,7 +520,7 @@ echo "Hello, this is a test file." > test.txt
 ----------

 OBSERVATION:
-
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace/my_project $
 [Command -1 finished with exit code 0]
@@ -538,19 +537,19 @@ git init && git add test.txt && git status
 ----------

 OBSERVATION:
-hint: Using 'master' as the name for the initial branch. This default branch name
-hint: is subject to change. To configure the initial branch name to use in all
-hint: of your new repositories, which will suppress this warning, call:
-hint:
-hint: 	git config --global init.defaultBranch <name>
-hint:
-hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
-hint: 'development'. The just-created branch can be renamed via this command:
-hint:
-hint: 	git branch -m <name>
-error: chmod on /workspace/my_project/.git/config.lock failed: Operation not permitted
-fatal: could not set 'core.filemode' to 'false'
-
+hint: Using 'master' as the name for the initial branch. This default branch name
+hint: is subject to change. To configure the initial branch name to use in all
+hint: of your new repositories, which will suppress this warning, call:
+hint:
+hint: 	git config --global init.defaultBranch <name>
+hint:
+hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
+hint: 'development'. The just-created branch can be renamed via this command:
+hint:
+hint: 	git branch -m <name>
+error: chmod on /workspace/my_project/.git/config.lock failed: Operation not permitted
+fatal: could not set 'core.filemode' to 'false'
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace/my_project $
 [Command -1 finished with exit code 128]
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -418,9 +417,9 @@ git status
 ----------

 OBSERVATION:
-fatal: not a git repository (or any parent up to mount point /)
-Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
-
+fatal: not a git repository (or any parent up to mount point /)
+Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -437,19 +436,19 @@ git init
 ----------

 OBSERVATION:
-hint: Using 'master' as the name for the initial branch. This default branch name
-hint: is subject to change. To configure the initial branch name to use in all
-hint: of your new repositories, which will suppress this warning, call:
-hint:
-hint: 	git config --global init.defaultBranch <name>
-hint:
-hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
-hint: 'development'. The just-created branch can be renamed via this command:
-hint:
-hint: 	git branch -m <name>
-error: chmod on /workspace/.git/config.lock failed: Operation not permitted
-fatal: could not set 'core.filemode' to 'false'
-
+hint: Using 'master' as the name for the initial branch. This default branch name
+hint: is subject to change. To configure the initial branch name to use in all
+hint: of your new repositories, which will suppress this warning, call:
+hint:
+hint: 	git config --global init.defaultBranch <name>
+hint:
+hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
+hint: 'development'. The just-created branch can be renamed via this command:
+hint:
+hint: 	git branch -m <name>
+error: chmod on /workspace/.git/config.lock failed: Operation not permitted
+fatal: could not set 'core.filemode' to 'false'
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -466,11 +465,11 @@ ls -la
 ----------

 OBSERVATION:
-total 4
-drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .
-drwxr-xr-x 1 root root 4096 Sep  8 15:57 ..
-drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .git
-
+total 4
+drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .
+drwxr-xr-x 1 root root 4096 Sep  8 15:57 ..
+drwxrwxrwx 1 pn   pn   4096 Sep  8 15:57 .git
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 0]
@@ -485,9 +484,9 @@ git status
 ----------

 OBSERVATION:
-fatal: not a git repository (or any parent up to mount point /)
-Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
-
+fatal: not a git repository (or any parent up to mount point /)
+Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 128]
@@ -504,7 +503,7 @@ mkdir my_project && cd my_project
 ----------

 OBSERVATION:
-
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace/my_project $
 [Command -1 finished with exit code 0]
@@ -521,7 +520,7 @@ echo "Hello, this is a test file." > test.txt
 ----------

 OBSERVATION:
-
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace/my_project $
 [Command -1 finished with exit code 0]
@@ -538,19 +537,19 @@ git init && git add test.txt && git status
 ----------

 OBSERVATION:
-hint: Using 'master' as the name for the initial branch. This default branch name
-hint: is subject to change. To configure the initial branch name to use in all
-hint: of your new repositories, which will suppress this warning, call:
-hint:
-hint: 	git config --global init.defaultBranch <name>
-hint:
-hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
-hint: 'development'. The just-created branch can be renamed via this command:
-hint:
-hint: 	git branch -m <name>
-error: chmod on /workspace/my_project/.git/config.lock failed: Operation not permitted
-fatal: could not set 'core.filemode' to 'false'
-
+hint: Using 'master' as the name for the initial branch. This default branch name
+hint: is subject to change. To configure the initial branch name to use in all
+hint: of your new repositories, which will suppress this warning, call:
+hint:
+hint: 	git config --global init.defaultBranch <name>
+hint:
+hint: Names commonly chosen instead of 'master' are 'main', 'trunk' and
+hint: 'development'. The just-created branch can be renamed via this command:
+hint:
+hint: 	git branch -m <name>
+error: chmod on /workspace/my_project/.git/config.lock failed: Operation not permitted
+fatal: could not set 'core.filemode' to 'false'
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace/my_project $
 [Command -1 finished with exit code 128]
@@ -570,11 +569,11 @@ echo "Initial commit: Add test.txt
 ----------

 OBSERVATION:
-Initial commit: Add test.txt
-
- Created a new file 'test.txt' with a simple hello message
- This is the first commit in the repository
-
+Initial commit: Add test.txt
+
+- Created a new file 'test.txt' with a simple hello message
+- This is the first commit in the repository
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace/my_project $
 [Command -1 finished with exit code 0]
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -121,7 +121,6 @@ append_file(file_name: str, content: str) -> None:
    It appends text `content` to the end of the specified file, ideal after a `create_file`!
    Args:
    file_name: str: The name of the file to edit.
-    line_number: int: The line number (starting from 1) to insert the content after.
    content: str: The content to insert.

 search_dir(search_term: str, dir_path: str = './') -> None:
@@ -420,14 +419,14 @@ chmod +x hello.sh
 ----------

 OBSERVATION:
-
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
-openhands@docker-desktop:/workspace $ echo 'echo "hello"' >> hello.sh
-
+openhands@docker-desktop:/workspace $ echo 'echo "hello"' >> hello.sh
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
-openhands@docker-desktop:/workspace $ chmod +x hello.sh
-chmod: changing permissions of 'hello.sh': Operation not permitted
-
+openhands@docker-desktop:/workspace $ chmod +x hello.sh
+chmod: changing permissions of 'hello.sh': Operation not permitted
+
 [Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.11/bin/python]
 openhands@docker-desktop:/workspace $
 [Command -1 finished with exit code 1]
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Xingyao Wang	8d6eda3623	fix eval_infer.sh to correctly copy SWE-Bench logs (#4111 )	2024-09-29 18:39:18 -05:00
Cole Murray	d5f965b474	Update LiteLLLM to 1.48.5 (#4110 )	2024-09-29 06:42:59 +00:00
tobitege	c3bbe604eb	(fix) Fix logging in shared eval file to prevent key disclosure (#4108 )	2024-09-28 19:33:16 +00:00
Ana Noemi	c7fe39998c	Update README to decrease unsuccessful drivebys (#4091 )	2024-09-28 18:52:01 +00:00
Xingyao Wang	ec6e07647f	fix hash equivalance verification ci for fork (#4107 )	2024-09-29 02:19:59 +08:00
Graham Neubig	e744eadb8b	Robustify openhands resolver workflow (#4105 )	2024-09-28 11:35:56 -04:00
Engel Nyst	e582806004	Vision and prompt caching fixes (#4014 )	2024-09-28 14:37:29 +02:00
OpenHands	f427f9d8d4	Fix issue #4103 : Improve description of how to do frontend setup and testing in `.openhands_instructions` (#4104 ) Co-authored-by: Graham Neubig <neubig@gmail.com>	2024-09-28 06:41:34 +00:00
Graham Neubig	d669c7b60d	Add github issue resolution workflow (#4102 )	2024-09-28 04:52:52 +00:00
dependabot[bot]	42be4ee5bc	chore(deps-dev): bump openai from 1.48.0 to 1.50.2 (#4101 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-28 05:04:03 +02:00
Engel Nyst	f994277d0f	Make agents follow configured temperature (#4099 )	2024-09-28 01:15:46 +00:00
tofarr	5ccee7c8a7	Fix Bash commands now do not block and actually respect the timeout (#4058 )	2024-09-28 08:40:00 +08:00
tobitege	575a829d94	(enh) add test_python_version to test_bash.py runtime tests (#4098 )	2024-09-28 08:21:14 +08:00
Xingyao Wang	2bed3a424c	chore: pass logger DEBUG mode to client side (#4096 )	2024-09-28 08:21:04 +08:00
Xingyao Wang	a4cc010110	chore: parser fix for deepseek (#4097 )	2024-09-28 08:20:51 +08:00
tobitege	9651368e6a	revert #3871 dockerfile template: don't write to .bashrc file (#4095 )	2024-09-27 21:49:51 +00:00
tofarr	c5025fb66e	Fix Reducing the amount being downloaded every time the hash changes. (#4078 )	2024-09-27 15:48:33 -06:00
Robert Brennan	3f9111c615	add idle time to client server (#4084 )	2024-09-27 19:41:16 +00:00
dependabot[bot]	89e95f2671	chore(deps): bump boto3 from 1.35.27 to 1.35.28 (#4090 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-27 16:48:34 +00:00
dependabot[bot]	5bfa0c2f8d	chore(deps): bump browsergym from 0.7.0 to 0.7.1 (#4089 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-27 16:21:58 +00:00
dependabot[bot]	84141f656d	chore(deps-dev): bump chromadb from 0.5.9 to 0.5.11 (#4088 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-27 16:19:17 +00:00
dependabot[bot]	6ff7506581	chore(deps-dev): bump reportlab from 4.2.2 to 4.2.4 (#4086 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-27 16:01:32 +00:00
dependabot[bot]	41dc7f0256	chore(deps-dev): bump llama-index from 0.11.13 to 0.11.14 (#4085 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-27 15:50:17 +00:00
Xingyao Wang	34f3b61536	[runtime hash] fix runtime hash mismatch between inside `app` image and in "development mode" (#4039 )	2024-09-27 15:26:26 +00:00
dependabot[bot]	4533c47595	chore(deps-dev): bump @types/node from 22.7.2 to 22.7.3 in /frontend (#4081 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-27 15:20:11 +00:00
Xingyao Wang	47774e60b0	chore: remove deprecated dockerfile (#4079 )	2024-09-27 15:03:23 +00:00
Robert Brennan	b78f646b65	Release 0.9.6 (#4076 )	2024-09-26 21:27:17 +00:00
Amir	3e5c01dfc8	Remove param from docstring that does not exist in the append_file (#4060 )	2024-09-26 22:25:11 +02:00
tobitege	29c34e0b6a	(fix) actions.ts: restored handleAssistantMessage handling order (#4074 )	2024-09-26 19:56:12 +00:00
tofarr	c919086e25	Fix for regression (#4075 ) Regression fixed	2024-09-26 12:58:00 -06:00
Engel Nyst	0a03c802f5	Refactor llm.py (#4057 )	2024-09-26 17:44:18 +00:00
Xingyao Wang	081ebdbdd8	[runtime] do not keep rebuilding from generic image (#4072 )	2024-09-26 17:19:46 +00:00
dependabot[bot]	572c7b726d	chore(deps-dev): bump ruff from 0.6.7 to 0.6.8 (#4067 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-26 17:19:16 +00:00
Xingyao Wang	cfc5bb70c1	Update README.md for CodeAct (#4070 )	2024-09-26 16:55:08 +00:00
dependabot[bot]	008b866a38	chore(deps-dev): bump jsdom from 25.0.0 to 25.0.1 in /frontend (#3992 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-26 16:34:29 +00:00
dependabot[bot]	676ad3e140	chore(deps-dev): bump chromadb from 0.5.7 to 0.5.9 (#4069 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-26 16:08:17 +00:00
dependabot[bot]	19278de5d0	chore(deps): bump json-repair from 0.29.4 to 0.29.5 (#4068 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-26 15:48:39 +00:00
dependabot[bot]	891e4a8d34	chore(deps): bump datasets from 3.0.0 to 3.0.1 (#4065 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-26 15:35:36 +00:00
dependabot[bot]	85be8607e0	chore(deps): bump litellm from 1.48.1 to 1.48.2 (#4066 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-26 23:33:24 +08:00
dependabot[bot]	49b244610c	chore(deps-dev): bump openai from 1.47.1 to 1.48.0 (#4063 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-26 17:16:59 +02:00
dependabot[bot]	b347b1d06f	chore(deps): bump boto3 from 1.35.26 to 1.35.27 (#4064 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-26 17:15:11 +02:00
dependabot[bot]	0c86a60b35	chore(deps-dev): bump @types/node from 22.7.0 to 22.7.2 in /frontend (#4062 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-26 19:11:06 +04:00
tofarr	01317138e2	Fix: uvicorn reloading when python files in workspace change, & started section for debugging instructions for developers (#4041 ) Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>	2024-09-26 08:57:37 -06:00
Xingyao Wang	e03855cd7f	Make sure we print the observation in the same way as the LLM sees it	2024-09-26 14:01:48 +00:00
jaki300	757c9593f1	Create gke-example.md (#3795 ) Co-authored-by: Robert Brennan <accounts@rbren.io>	2024-09-26 09:11:33 -04:00
mamoodi	266e8ff951	Release 0.9.5 (#4061 )	2024-09-26 08:36:31 -04:00
dependabot[bot]	3e79cd12a6	chore(deps-dev): bump @types/react from 18.3.8 to 18.3.9 in /frontend (#4029 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-26 14:41:21 +04:00
tobitege	2cc1c3ef42	(enh) Docker runtime builder with BuildKit support, enh. caching (#4009 )	2024-09-26 08:50:53 +02:00
dependabot[bot]	ef0b08a46e	chore(deps-dev): bump tailwindcss from 3.4.12 to 3.4.13 in /frontend (#4030 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-26 05:28:03 +00:00
dependabot[bot]	f1d5202884	chore(deps): bump vite from 5.4.7 to 5.4.8 in /frontend (#4046 )	2024-09-26 12:56:35 +08:00
dependabot[bot]	11cedfb854	chore(deps): bump google-cloud-aiplatform from 1.67.1 to 1.68.0 (#4051 )	2024-09-26 12:56:16 +08:00
dependabot[bot]	6d103a0db2	chore(deps-dev): bump @types/node from 22.6.1 to 22.7.0 in /frontend (#4047 )	2024-09-26 12:56:00 +08:00
Engel Nyst	798aaeaef6	remove Exception in the agent (#4054 )	2024-09-26 06:39:17 +02:00
tofarr	0df4b97e5b	Fix startup statuses (#4053 )	2024-09-25 14:38:32 -06:00
Xingyao Wang	81b3cd71b3	[eval] log evaluating warnings directly to console (#4026 )	2024-09-26 03:42:32 +08:00
Robert Brennan	9241ae2148	Fix persistence of "advanced settings" (#4038 )	2024-09-25 12:57:08 -04:00
dependabot[bot]	d3f86e052a	chore(deps-dev): bump llama-index from 0.11.12 to 0.11.13 (#4044 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-25 18:24:09 +02:00
dependabot[bot]	e0c65f8f9c	chore(deps): bump google-generativeai from 0.8.1 to 0.8.2 (#4050 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-25 18:22:01 +02:00
dependabot[bot]	394ab360a8	chore(deps): bump boto3 from 1.35.25 to 1.35.26 (#4048 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-25 18:21:27 +02:00
dependabot[bot]	8a146d5ced	chore(deps): bump litellm from 1.48.0 to 1.48.1 (#4049 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-09-25 18:20:47 +02:00