fix links with new url

.devcontainer/README.MD

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

.devcontainer/on_create.sh

@@ -2,5 +2,7 @@
 sudo apt update
 sudo apt install -y netcat
 sudo add-apt-repository -y ppa:deadsnakes/ppa
-sudo apt install -y python3.12
-curl -sSL https://install.python-poetry.org | python3.12 -
+sudo apt install -y python3.11
+curl -sSL https://install.python-poetry.org | python3.11 -
+# chromadb requires SQLite > 3.35 but SQLite in Python3.11.9 comes with 3.31.1
+sudo cp /opt/conda/lib/libsqlite3.so.0 /lib/x86_64-linux-gnu/libsqlite3.so.0

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -5,57 +5,71 @@ labels: ['bug']
 body:
   - type: markdown
     attributes:
-      value: Thank you for taking the time to fill out this bug report. Please provide as much information as possible to help us understand and address the issue effectively.
+      value: Thank you for taking the time to fill out this bug report. We greatly appreciate your effort to complete this template fully. Please provide as much information as possible to help us understand and address the issue effectively.
 
   - type: checkboxes
     attributes:
       label: Is there an existing issue for the same bug?
       description: Please check if an issue already exists for the bug you encountered.
       options:
+      - label: I have checked the troubleshooting document at https://docs.all-hands.dev/modules/usage/troubleshooting
+        required: true
       - label: I have checked the existing issues.
         required: true
 
   - type: textarea
     id: bug-description
     attributes:
-      label: Describe the bug and reproduction steps
-      description: Provide a description of the issue along with any reproduction steps.
+      label: Describe the bug
+      description: Provide a short description of the problem.
     validations:
       required: true
 
-  - type: dropdown
-    id: installation
+  - type: textarea
+    id: current-version
     attributes:
-      label: OpenHands Installation
-      description: How are you running OpenHands?
-      options:
-        - Docker command in README
-        - Development workflow
-        - app.all-hands.dev
-        - Other
-      default: 0
+      label: Current OpenHands version
+      description: What version of OpenHands are you using? If you're running in docker, tell us the tag you're using (e.g. ghcr.io/all-hands-ai/openhands:0.3.1).
+      render: bash
+    validations:
+      required: true
 
-  - type: input
-    id: openhands-version
+  - type: textarea
+    id: config
     attributes:
-      label: OpenHands Version
-      description: What version of OpenHands are you using?
-      placeholder: ex. 0.9.8, main, etc.
+      label: Installation and Configuration
+      description: Please provide any commands you ran and any configuration (redacting API keys)
+      render: bash
+    validations:
+      required: true
 
-  - type: dropdown
-    id: os
+  - type: textarea
+    id: model-agent
+    attributes:
+      label: Model and Agent
+      description: What model and agent are you using? You can see these settings in the UI by clicking the settings wheel.
+      placeholder: |
+        - Model:
+        - Agent:
+
+  - type: textarea
+    id: os-version
     attributes:
       label: Operating System
-      options:
-        - MacOS
-        - Linux
-        - WSL on Windows
+      description: What Operating System are you using? Linux, Mac OS, WSL on Windows
+
+  - type: textarea
+    id: repro-steps
+    attributes:
+      label: Reproduction Steps
+      description: Please list the steps to reproduce the issue.
+      placeholder: |
+        1.
+        2.
+        3.
 
   - type: textarea
     id: additional-context
     attributes:
       label: Logs, Errors, Screenshots, and Additional Context
-      description: Please provide any additional information you think might help. If you want to share the chat history
-        you can click the thumbs-down (👎) button above the input field and you will get a shareable link
-        (you can also click thumbs up when things are going well of course!). LLM logs will be stored in the
-        `logs/llm/default` folder. Please add any additional context about the problem here.
+      description: If you want to share the chat history you can click the thumbs-down (👎) button above the input field and you will get a shareable link (you can also click thumbs up when things are going well of course!). LLM logs will be stored in the `logs/llm/default` folder. Please add any additional context about the problem here.

.github/dependabot.yml

@@ -1,38 +1,21 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
 version: 2
 updates:
   - package-ecosystem: "pip"
     directory: "/"
     schedule:
       interval: "daily"
-    open-pull-requests-limit: 1
-    groups:
-      # put packages in their own group if they have a history of breaking the build or needing to be reverted
-      pre-commit:
-        patterns:
-          - "pre-commit"
-      llama:
-        patterns:
-          - "llama*"
-      chromadb:
-        patterns:
-          - "chromadb"
-      browsergym:
-        patterns:
-          - "browsergym"
-      security-all:
-        applies-to: "security-updates"
-        patterns:
-          - "*"
-      version-all:
-        applies-to: "version-updates"
-        patterns:
-          - "*"
+    open-pull-requests-limit: 20
 
   - package-ecosystem: "npm"
     directory: "/frontend"
     schedule:
       interval: "daily"
-    open-pull-requests-limit: 1
+    open-pull-requests-limit: 20
     groups:
       docusaurus:
         patterns:
@@ -40,21 +23,12 @@ updates:
       eslint:
         patterns:
           - "*eslint*"
-      security-all:
-        applies-to: "security-updates"
-        patterns:
-          - "*"
-      version-all:
-        applies-to: "version-updates"
-        patterns:
-          - "*"
 
   - package-ecosystem: "npm"
     directory: "/docs"
     schedule:
-      interval: "weekly"
-      day: "wednesday"
-    open-pull-requests-limit: 1
+      interval: "daily"
+    open-pull-requests-limit: 20
     groups:
       docusaurus:
         patterns:
@@ -62,11 +36,3 @@ updates:
       eslint:
         patterns:
           - "*eslint*"
-      security-all:
-        applies-to: "security-updates"
-        patterns:
-          - "*"
-      version-all:
-        applies-to: "version-updates"
-        patterns:
-          - "*"

.github/pull_request_template.md

@@ -1,6 +1,6 @@
-**End-user friendly description of the problem this fixes or functionality that this introduces**
+**What is the problem that this fixes or functionality that this introduces? Does it fix any open issues?**
+
 
-- [ ] Include this change in the Release Notes. If checked, you must provide an **end-user friendly** description for your change below
 
 ---
 **Give a summary of what the PR does, explaining any non-trivial design decisions**
@@ -8,4 +8,4 @@
 
 
 ---
-**Link of any specific issues this addresses**
+**Other references**

.github/workflows/deploy-docs.yml

@@ -14,11 +14,6 @@ on:
     branches:
       - main
 
-# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: true
-
 jobs:
   # Build the documentation website
   build:
@@ -37,7 +32,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.12'
+          python-version: '3.11'
       - name: Generate Python Docs
         run: rm -rf docs/modules/python && pip install pydoc-markdown && pydoc-markdown
       - name: Install dependencies

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

@@ -9,48 +9,25 @@ on:
     - main
   pull_request:
 
-# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: true
-
 jobs:
   test:
     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: '3.12'
-          cache: 'poetry'
-      - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation,llama-index
-      - name: Build Environment
-        run: make build
+          python-version: '3.11'
+      - name: Set up environment
+        run: |
+          curl -sSL https://install.python-poetry.org | python3 -
+          poetry install --without evaluation,llama-index
+          poetry run playwright install --with-deps chromium
+          wget https://huggingface.co/BAAI/bge-small-en-v1.5/raw/main/1_Pooling/config.json -P /tmp/llama_index/models--BAAI--bge-small-en-v1.5/snapshots/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/1_Pooling/
       - name: Run tests
         run: |
           set -e
-          SANDBOX_FORCE_REBUILD_RUNTIME=True poetry run python3 openhands/core/main.py -t "do a flip" -d ./workspace/ -c DummyAgent
+          poetry run python openhands/core/main.py -t "do a flip" -d ./workspace/ -c DummyAgent
       - name: Check exit code
         run: |
           if [ $? -ne 0 ]; then

.github/workflows/eval-runner.yml

@@ -1,137 +0,0 @@
-name: Run SWE-Bench Evaluation
-
-on:
-  pull_request:
-    types: [labeled]
-  workflow_dispatch:
-    inputs:
-      reason:
-        description: "Reason for manual trigger"
-        required: true
-        default: ""
-
-env:
-  N_PROCESSES: 32 # Global configuration for number of parallel processes for evaluation
-
-jobs:
-  run-evaluation:
-    if: github.event.label.name == 'eval-this' || github.event_name != 'pull_request'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: "read"
-      id-token: "write"
-      pull-requests: "write"
-      issues: "write"
-    strategy:
-      matrix:
-        python-version: ["3.12"]
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-
-      - name: Comment on PR if 'eval-this' label is present
-        if: github.event_name == 'pull_request' && github.event.label.name == 'eval-this'
-        uses: KeisukeYamashita/create-comment@v1
-        with:
-          unique: false
-          comment: |
-            Hi! I started running the evaluation on your PR. You will receive a comment with the results shortly.
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install
-
-      - name: Configure config.toml for evaluation
-        env:
-          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_LLM_API_KEY }}
-        run: |
-          echo "[llm.eval]" > config.toml
-          echo "model = \"deepseek/deepseek-chat\"" >> config.toml
-          echo "api_key = \"$DEEPSEEK_API_KEY\"" >> config.toml
-          echo "temperature = 0.0" >> config.toml
-
-      - name: Run SWE-Bench evaluation
-        env:
-          ALLHANDS_API_KEY: ${{ secrets.ALLHANDS_EVAL_RUNTIME_API_KEY }}
-          RUNTIME: remote
-          SANDBOX_REMOTE_RUNTIME_API_URL: https://runtime.eval.all-hands.dev
-          EVAL_DOCKER_IMAGE_PREFIX: us-central1-docker.pkg.dev/evaluation-092424/swe-bench-images
-
-        run: |
-          poetry run ./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.eval HEAD CodeActAgent 300 30 $N_PROCESSES "princeton-nlp/SWE-bench_Lite" test
-          OUTPUT_FOLDER=$(find evaluation/evaluation_outputs/outputs/princeton-nlp__SWE-bench_Lite-test/CodeActAgent -name "deepseek-chat_maxiter_50_N_*-no-hint-run_1" -type d | head -n 1)
-          echo "OUTPUT_FOLDER for SWE-bench evaluation: $OUTPUT_FOLDER"
-          poetry run ./evaluation/benchmarks/swe_bench/scripts/eval_infer_remote.sh $OUTPUT_FOLDER/output.jsonl $N_PROCESSES "princeton-nlp/SWE-bench_Lite" test
-
-          poetry run ./evaluation/benchmarks/swe_bench/scripts/eval/summarize_outputs.py $OUTPUT_FOLDER/output.jsonl > summarize_outputs.log 2>&1
-          echo "SWEBENCH_REPORT<<EOF" >> $GITHUB_ENV
-          cat summarize_outputs.log >> $GITHUB_ENV
-          echo "EOF" >> $GITHUB_ENV
-
-      - name: Create tar.gz of evaluation outputs
-        run: |
-          TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
-          tar -czvf evaluation_outputs_${TIMESTAMP}.tar.gz evaluation/evaluation_outputs/outputs
-
-      - name: Upload evaluation results as artifact
-        uses: actions/upload-artifact@v4
-        id: upload_results_artifact
-        with:
-          name: evaluation-outputs
-          path: evaluation_outputs_*.tar.gz
-
-      - name: Get artifact URL
-        run: echo "ARTIFACT_URL=${{ steps.upload_results_artifact.outputs.artifact-url }}" >> $GITHUB_ENV
-
-      - name: Authenticate to Google Cloud
-        uses: 'google-github-actions/auth@v2'
-        with:
-          credentials_json: ${{ secrets.GCP_RESEARCH_OBJECT_CREATOR_SA_KEY }}
-
-      - name: Set timestamp and trigger reason
-        run: |
-          echo "TIMESTAMP=$(date +'%Y-%m-%d-%H-%M')" >> $GITHUB_ENV
-          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
-            echo "TRIGGER_REASON=pr-${{ github.event.pull_request.number }}" >> $GITHUB_ENV
-          elif [[ "${{ github.event_name }}" == "schedule" ]]; then
-            echo "TRIGGER_REASON=schedule" >> $GITHUB_ENV
-          else
-            echo "TRIGGER_REASON=manual-${{ github.event.inputs.reason }}" >> $GITHUB_ENV
-          fi
-
-      - name: Upload evaluation results to Google Cloud Storage
-        uses: 'google-github-actions/upload-cloud-storage@v2'
-        with:
-          path: 'evaluation/evaluation_outputs/outputs'
-          destination: 'openhands-oss-eval-results/${{ env.TIMESTAMP }}-${{ env.TRIGGER_REASON }}'
-
-      - name: Comment with evaluation results and artifact link
-        id: create_comment
-        uses: KeisukeYamashita/create-comment@v1
-        with:
-          number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || 4504 }}
-          unique: false
-          comment: |
-              Trigger by: ${{ github.event_name == 'pull_request' && format('Pull Request (eval-this label on PR #{0})', github.event.pull_request.number) || github.event_name == 'schedule' && 'Daily Schedule' || format('Manual Trigger: {0}', github.event.inputs.reason) }}
-              Commit: ${{ github.sha }}
-              **SWE-Bench Evaluation Report**
-              ${{ env.SWEBENCH_REPORT }}
-              ---
-              You can download the full evaluation outputs [here](${{ env.ARTIFACT_URL }}).
-
-      - name: Post to a Slack channel
-        id: slack
-        uses: slackapi/slack-github-action@v1.27.0
-        with:
-          channel-id: 'C07SVQSCR6F'
-          slack-message: "*Evaluation Trigger:* ${{ github.event_name == 'pull_request' && format('Pull Request (eval-this label on PR #{0})', github.event.pull_request.number) || github.event_name == 'schedule' && 'Daily Schedule' || format('Manual Trigger: {0}', github.event.inputs.reason) }}\n\nLink to summary: [here](https://github.com/${{ github.repository }}/issues/${{ github.event_name == 'pull_request' && github.event.pull_request.number || 4504 }}#issuecomment-${{ steps.create_comment.outputs.comment-id }})"
-        env:
-          SLACK_BOT_TOKEN: ${{ secrets.EVAL_NOTIF_SLACK_BOT_TOKEN }}

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

@@ -12,11 +12,6 @@ on:
       - 'frontend/**'
       -  '.github/workflows/fe-unit-tests.yml'
 
-# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: true
-
 jobs:
   # Run frontend unit tests
   fe-test:
@@ -35,9 +30,6 @@ jobs:
       - name: Install dependencies
         working-directory: ./frontend
         run: npm ci
-      - name: Run TypeScript compilation
-        working-directory: ./frontend
-        run: npm run make-i18n && tsc
       - name: Run tests and collect coverage
         working-directory: ./frontend
         run: npm run test:coverage

.github/workflows/ghcr-build.yml

@@ -1,445 +0,0 @@
-# Workflow that builds, tests and then pushes the OpenHands and runtime docker images to the ghcr.io repository
-name: Docker
-
-# 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: ''
-
-# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: true
-
-env:
-  BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST: nikolaik/python-nodejs:python3.12-nodejs22
-  RELEVANT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
-
-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:${{ env.RELEVANT_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
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    strategy:
-      matrix:
-        base_image:
-          - image: 'nikolaik/python-nodejs:python3.12-nodejs22'
-            tag: nikolaik
-    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: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.12'
-      - 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: Install poetry via pipx
-        run: pipx install poetry
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-      - name: Create source distribution and Dockerfile
-        run: poetry run python3 openhands/runtime/utils/runtime_build.py --base_image ${{ matrix.base_image.image }} --build_folder containers/runtime --force_rebuild
-      - name: Build and push runtime image ${{ matrix.base_image.image }}
-        if: github.event.pull_request.head.repo.fork != true
-        run: |
-          ./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 ${{ matrix.base_image.image }} for fork
-        if: github.event.pull_request.head.repo.fork
-        uses: docker/build-push-action@v6
-        with:
-          tags: ghcr.io/all-hands-ai/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
-          outputs: type=docker,dest=/tmp/runtime-${{ matrix.base_image.tag }}.tar
-          context: containers/runtime
-      - name: Upload runtime image for fork
-        if: github.event.pull_request.head.repo.fork
-        uses: actions/upload-artifact@v4
-        with:
-          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: '3.12'
-      - 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 }}" = "${{ env.hash_from_code }}" ]; then
-            echo "Hashes match!"
-          else
-            echo "Hashes do not match!"
-            exit 1
-          fi
-
-  # Run unit tests with the EventStream runtime Docker images as root
-  test_runtime_root:
-    name: RT Unit Tests (Root)
-    needs: [ghcr_build_runtime]
-    runs-on: ubuntu-latest
-    strategy:
-      fail-fast: false
-      matrix:
-        base_image: ['nikolaik']
-    steps:
-      - uses: actions/checkout@v4
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-      # Forked repos can't push to GHCR, so we need to download the image as an artifact
-      - name: Download runtime image for fork
-        if: github.event.pull_request.head.repo.fork
-        uses: actions/download-artifact@v4
-        with:
-          name: runtime-${{ matrix.base_image }}
-          path: /tmp
-      - name: Load runtime image for fork
-        if: github.event.pull_request.head.repo.fork
-        run: |
-          docker load --input /tmp/runtime-${{ matrix.base_image }}.tar
-      - name: Cache Poetry dependencies
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/pypoetry
-            ~/.virtualenvs
-          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-poetry-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.12'
-      - name: Install poetry via pipx
-        run: pipx install poetry
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-      - name: Run runtime tests
-        run: |
-          # We install pytest-xdist in order to run tests across CPUs
-          poetry run pip install pytest-xdist
-
-          # Install to be able to retry on failures for flaky tests
-          poetry run pip install pytest-rerunfailures
-
-          image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
-          image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
-
-          TEST_RUNTIME=eventstream \
-          SANDBOX_USER_ID=$(id -u) \
-          SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
-          TEST_IN_CI=true \
-          RUN_AS_OPENHANDS=false \
-          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
-  # Run unit tests with the EventStream runtime Docker images as openhands user
-  test_runtime_oh:
-    name: RT Unit Tests (openhands)
-    runs-on: ubuntu-latest
-    needs: [ghcr_build_runtime]
-    strategy:
-      matrix:
-        base_image: ['nikolaik']
-    steps:
-      - uses: actions/checkout@v4
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-      # Forked repos can't push to GHCR, so we need to download the image as an artifact
-      - name: Download runtime image for fork
-        if: github.event.pull_request.head.repo.fork
-        uses: actions/download-artifact@v4
-        with:
-          name: runtime-${{ matrix.base_image }}
-          path: /tmp
-      - name: Load runtime image for fork
-        if: github.event.pull_request.head.repo.fork
-        run: |
-          docker load --input /tmp/runtime-${{ matrix.base_image }}.tar
-      - name: Cache Poetry dependencies
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/pypoetry
-            ~/.virtualenvs
-          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-poetry-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.12'
-      - name: Install poetry via pipx
-        run: pipx install poetry
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-      - name: Run runtime tests
-        run: |
-          # We install pytest-xdist in order to run tests across CPUs
-          poetry run pip install pytest-xdist
-
-          # Install to be able to retry on failures for flaky tests
-          poetry run pip install pytest-rerunfailures
-
-          image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
-          image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
-
-          TEST_RUNTIME=eventstream \
-          SANDBOX_USER_ID=$(id -u) \
-          SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
-          TEST_IN_CI=true \
-          RUN_AS_OPENHANDS=true \
-          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
-  # The two following jobs (named identically) are to check whether all the runtime tests have passed as the
-  # "All Runtime Tests Passed" is a required job for PRs to merge
-  # Due to this bug: https://github.com/actions/runner/issues/2566, we want to create a job that runs when the
-  # prerequisites have been cancelled or failed so merging is disallowed, otherwise Github considers "skipped" as "success"
-  runtime_tests_check_success:
-    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, verify_hash_equivalence_in_runtime_and_app]
-    steps:
-      - name: All tests passed
-        run: echo "All runtime tests have passed successfully!"
-
-  runtime_tests_check_fail:
-    name: All Runtime Tests Passed
-    if: ${{ cancelled() || contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled') }}
-    runs-on: ubuntu-latest
-    needs: [test_runtime_root, test_runtime_oh, verify_hash_equivalence_in_runtime_and_app]
-    steps:
-      - name: Some tests failed
-        run: |
-          echo "Some runtime tests failed or were cancelled"
-          exit 1
-  update_pr_description:
-    name: Update PR Description
-    if: github.event_name == 'pull_request' && !github.event.pull_request.head.repo.fork && github.actor != 'dependabot[bot]'
-    needs: [ghcr_build_runtime]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Get short SHA
-        id: short_sha
-        run: echo "SHORT_SHA=$(echo ${{ github.event.pull_request.head.sha }} | cut -c1-7)" >> $GITHUB_OUTPUT
-
-      - name: Update PR Description
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          PR_NUMBER: ${{ github.event.pull_request.number }}
-          REPO: ${{ github.repository }}
-          SHORT_SHA: ${{ steps.short_sha.outputs.SHORT_SHA }}
-        run: |
-          echo "updating PR description"
-          DOCKER_RUN_COMMAND="docker run -it --rm \
-            -p 3000:3000 \
-            -v /var/run/docker.sock:/var/run/docker.sock \
-            --add-host host.docker.internal:host-gateway \
-            -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:$SHORT_SHA-nikolaik \
-            --name openhands-app-$SHORT_SHA \
-            docker.all-hands.dev/all-hands-ai/openhands:$SHORT_SHA"
-
-          PR_BODY=$(gh pr view $PR_NUMBER --json body --jq .body)
-
-          if echo "$PR_BODY" | grep -q "To run this PR locally, use the following command:"; then
-            UPDATED_PR_BODY=$(echo "${PR_BODY}" | sed -E "s|docker run -it --rm.*|$DOCKER_RUN_COMMAND|")
-          else
-            UPDATED_PR_BODY="${PR_BODY}
-
-          ---
-
-          To run this PR locally, use the following command:
-          \`\`\`
-          $DOCKER_RUN_COMMAND
-          \`\`\`"
-          fi
-
-          echo "updated body: $UPDATED_PR_BODY"
-          gh pr edit $PR_NUMBER --body "$UPDATED_PR_BODY"

.github/workflows/ghcr_app.yml

@@ -0,0 +1,124 @@
+# 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
+    outputs:
+      tags: ${{ steps.capture-tags.outputs.tags }}
+      last_tag: ${{ steps.capture-last-tag.outputs.last_tag }}
+    permissions:
+      contents: read
+      packages: write
+    strategy:
+      matrix:
+        image: ['openhands']
+        platform: ['amd64', 'arm64']
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Build and export image
+        id: build
+        run: ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} ${{ matrix.platform }}
+      - name: Capture tags
+        id: capture-tags
+        run: |
+          tags=$(cat tags.txt)
+          echo "tags=$tags"
+          echo "tags=$tags" >> $GITHUB_OUTPUT
+      - name: Capture last tag
+        id: capture-last-tag
+        run: |
+          last_tag=$(cat tags.txt | awk '{print $NF}')
+          echo "last_tag=$last_tag"
+          echo "last_tag=$last_tag" >> $GITHUB_OUTPUT
+      - name: Upload Docker image as artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ matrix.image }}_${{ steps.capture-last-tag.outputs.last_tag }}_${{ matrix.platform }}
+          path: /tmp/${{ matrix.image }}_${{ steps.capture-last-tag.outputs.last_tag }}_${{ matrix.platform }}.tar
+          retention-days: 14
+
+  # Push the OpenHands Docker images to the ghcr.io repository
+  ghcr_push:
+    name: Push App Image
+    runs-on: ubuntu-latest
+    needs: [ghcr_build]
+    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
+    env:
+      tags: ${{ needs.ghcr_build.outputs.tags }}
+    permissions:
+      contents: read
+      packages: write
+    strategy:
+      matrix:
+        image: ['openhands']
+        last_tag: ['${{ needs.ghcr_build.outputs.last_tag }}']
+        platform: ['amd64', 'arm64']
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      - name: Login to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Download Docker images
+        uses: actions/download-artifact@v4
+        with:
+          name: ${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}
+          path: /tmp
+      - name: Load images and push to registry
+        run: |
+          mv /tmp/${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}.tar .
+          loaded_image=$(docker load -i ${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}.tar | grep "Loaded image:" | head -n 1 | awk '{print $3}')
+          echo "loaded image = $loaded_image"
+          tags=$(echo ${tags} | tr ' ' '\n')
+          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
+          echo "image name = $image_name"
+          for tag in $tags; do
+            echo "tag = $tag"
+            docker tag $loaded_image $image_name:${tag}_${{ matrix.platform }}
+            docker push $image_name:${tag}_${{ matrix.platform }}
+            docker buildx imagetools create --tag $image_name:$tag $image_name:${tag}_${{ matrix.platform }}
+          done

.github/workflows/ghcr_runtime.yml

@@ -0,0 +1,325 @@
+# Workflow that builds, tests and then pushes the runtime docker images to the ghcr.io repository
+name: Build, Test and Publish Runtime 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 runtime Docker images
+  ghcr_build_runtime:
+    name: Build Image
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    strategy:
+      matrix:
+        image: ['runtime']
+        base_image: ['nikolaik/python-nodejs:python3.11-nodejs22', 'python:3.11-bookworm', 'node:22-bookworm']
+        platform: ['amd64', 'arm64']
+    outputs:
+      tags: ${{ steps.capture-tags.outputs.tags }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+          cache: 'poetry'
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies
+      - name: Create source distribution and Dockerfile
+        run: poetry run python3 openhands/runtime/utils/runtime_build.py --base_image ${{ matrix.base_image }} --build_folder containers/runtime --force_rebuild
+      - name: Build and export image
+        id: build
+        run: |
+          if [ -f 'containers/runtime/Dockerfile' ]; then
+            echo 'Dockerfile detected, building runtime image...'
+            ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} ${{ matrix.platform }}
+            # Capture the last tag to use in the artifact name
+            last_tag=$(cat tags.txt | awk '{print $NF}')
+          else
+            echo 'No Dockerfile detected which means an exact image is already built. Pulling the image and saving it to a tar file...'
+            source containers/runtime/config.sh
+            echo "$DOCKER_IMAGE_HASH_TAG $DOCKER_IMAGE_TAG" >> tags.txt
+            export last_tag=$DOCKER_IMAGE_TAG
+            echo "Pulling image $DOCKER_REGISTRY/$DOCKER_ORG/$DOCKER_IMAGE:$DOCKER_IMAGE_HASH_TAG to /tmp/${{ matrix.image }}_${last_tag}_${{ matrix.platform }}.tar"
+            docker pull $DOCKER_REGISTRY/$DOCKER_ORG/$DOCKER_IMAGE:$DOCKER_IMAGE_HASH_TAG
+            docker save $DOCKER_REGISTRY/$DOCKER_ORG/$DOCKER_IMAGE:$DOCKER_IMAGE_HASH_TAG -o /tmp/${{ matrix.image }}_${last_tag}_${{ matrix.platform }}.tar
+          fi
+          echo "last_tag=${last_tag}" >> $GITHUB_OUTPUT
+      - name: Capture tags
+        id: capture-tags
+        run: |
+          tags=$(cat tags.txt)
+          echo "tags=$tags"
+          echo "tags=$tags" >> $GITHUB_OUTPUT
+      - name: Upload Docker image as artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ matrix.image }}_${{ steps.build.outputs.last_tag }}_${{ matrix.platform }}
+          path: /tmp/${{ matrix.image }}_${{ steps.build.outputs.last_tag }}_${{ matrix.platform }}.tar
+          retention-days: 14
+      - name: Capture last tag
+        id: capture-last-tag
+        run: |
+          last_tag=$(cat tags.txt | awk '{print $NF}')
+          echo "$last_tag" > /tmp/last-tag-${{ matrix.image }}-${{ matrix.platform }}-${{ steps.build.outputs.last_tag }}.txt
+          echo "Saved last tag to /tmp/last-tag-${{ matrix.image }}-${{ matrix.platform }}-${{ steps.build.outputs.last_tag }}.txt"
+      - name: Upload last tag as artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: last-tag-${{ matrix.image }}-${{ matrix.platform }}-${{ steps.build.outputs.last_tag }}
+          path: /tmp/last-tag-${{ matrix.image }}-${{ matrix.platform }}-${{ steps.build.outputs.last_tag }}.txt
+          retention-days: 1
+
+  prepare_test_image_tags:
+    name: Prepare Test Images Tags
+    needs: ghcr_build_runtime
+    runs-on: ubuntu-latest
+    outputs:
+      test_image_tags: ${{ steps.set-matrix.outputs.test_image_tags }}
+    steps:
+      - name: Download last tags
+        uses: actions/download-artifact@v4
+        with:
+          pattern: last-tag-*
+          path: /tmp/
+          merge-multiple: true
+      - name: Set up test matrix
+        id: set-matrix
+        run: |
+          matrix=$(cat /tmp/last-tag-*.txt | sort -u | jq -R -s -c 'split("\n") | map(select(length > 0))')
+          echo "test_image_tags=$matrix" >> $GITHUB_OUTPUT
+          echo "Generated test_image_tags: $matrix"
+
+  # Run unit tests with the EventStream runtime Docker images
+  test_runtime:
+    name: Test Runtime
+    runs-on: ubuntu-latest
+    needs: prepare_test_image_tags
+    strategy:
+      matrix:
+        image: ['runtime']
+        runtime_type: ['eventstream']
+        platform: ['amd64']
+        last_tag: ${{ fromJson(needs.prepare_test_image_tags.outputs.test_image_tags) }}
+    steps:
+      - uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          tool-cache: true
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          swap-storage: true
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+          cache: 'poetry'
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies
+      - name: Download Runtime Docker image
+        uses: actions/download-artifact@v4
+        with:
+          name: ${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}
+          path: /tmp/
+      - name: Load Runtime image and run runtime tests
+        run: |
+          image_file=$(find /tmp -name "${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}.tar" | head -n 1)
+
+          if [ -z "$image_file" ]; then
+            echo "No matching image file found for tag: ${{ matrix.last_tag }}"
+            exit 1
+          fi
+
+          echo "Loading image from file: $image_file"
+          output=$(docker load -i "$image_file")
+
+          # Extract the image name from the output
+          # Print all tags
+          echo "All tags:"
+          all_tags=$(echo "$output" | grep -oP 'Loaded image: \K.*')
+          echo "$all_tags"
+          # Choose the last tag
+          image_name=$(echo "$all_tags" | tail -n 1)
+
+          # Print the full name of the image
+          echo "Loaded Docker image: $image_name"
+
+          TEST_RUNTIME=${{ matrix.runtime_type }} SANDBOX_USER_ID=$(id -u) SANDBOX_CONTAINER_IMAGE=$image_name TEST_IN_CI=true poetry run pytest --cov=agenthub --cov=openhands --cov-report=xml -s ./tests/unit/test_runtime.py
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+  # Run integration tests with the eventstream runtime Docker image
+  runtime_integration_tests_on_linux:
+    name: Runtime Integration Tests on Linux
+    runs-on: ubuntu-latest
+    needs: prepare_test_image_tags
+    strategy:
+      fail-fast: false
+      matrix:
+        image: ['runtime']
+        runtime_type: ['eventstream']
+        platform: ['amd64']
+        last_tag: ${{ fromJson(needs.prepare_test_image_tags.outputs.test_image_tags) }}
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+          cache: 'poetry'
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies
+      - name: Download Runtime Docker image
+        uses: actions/download-artifact@v4
+        with:
+          name: ${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}
+          path: /tmp/
+      - name: Load runtime image and run integration tests
+        run: |
+          image_file=$(find /tmp -name "${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}.tar" | head -n 1)
+
+          if [ -z "$image_file" ]; then
+            echo "No matching image file found for tag: ${{ matrix.last_tag }}"
+            exit 1
+          fi
+
+          echo "Loading image from file: $image_file"
+          output=$(docker load -i "$image_file")
+
+          # Extract the image name from the output
+          image_name=$(echo "$output" | grep -oP 'Loaded image: \K.*' | head -n 1)
+
+          # Print the full name of the image
+          echo "Loaded Docker image: $image_name"
+
+          TEST_RUNTIME=${{ matrix.runtime_type }} SANDBOX_USER_ID=$(id -u) SANDBOX_CONTAINER_IMAGE=$image_name TEST_IN_CI=true TEST_ONLY=true ./tests/integration/regenerate.sh
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+  # Checks that all runtime tests have passed
+  all_runtime_tests_passed:
+    name: All Runtime Tests Passed
+    runs-on: ubuntu-latest
+    needs: [test_runtime, runtime_integration_tests_on_linux]
+    steps:
+      - name: All tests passed
+        run: echo "All runtime tests have passed successfully!"
+
+  # Push the runtime Docker images to the ghcr.io repository
+  ghcr_push_runtime:
+    name: Push Image
+    runs-on: ubuntu-latest
+    needs: [ghcr_build_runtime, prepare_test_image_tags, all_runtime_tests_passed]
+    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
+    env:
+      RUNTIME_TAGS: ${{ needs.ghcr_build_runtime.outputs.tags }}
+    permissions:
+      contents: read
+      packages: write
+    strategy:
+      matrix:
+        image: ['runtime']
+        runtime_type: ['eventstream']
+        platform: ['amd64', 'arm64']
+        last_tag: ${{ fromJson(needs.prepare_test_image_tags.outputs.test_image_tags) }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          tool-cache: true
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+      - name: Login to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Download Docker images
+        uses: actions/download-artifact@v4
+        with:
+          name: ${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}
+          path: /tmp/
+      - name: Load images and push to registry
+        run: |
+          image_file=$(find /tmp -name "${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}.tar" | head -n 1)
+          if [ -z "$image_file" ]; then
+            echo "No matching image file found for tag: ${{ matrix.last_tag }}"
+            exit 1
+          fi
+
+          echo "Loading image from file: $image_file"
+          if ! loaded_image=$(docker load -i "$image_file" | grep "Loaded image:" | head -n 1 | awk '{print $3}'); then
+            echo "Failed to load Docker image"
+            exit 1
+          fi
+          echo "loaded image = $loaded_image"
+          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
+          echo "image name = $image_name"
+          echo "$RUNTIME_TAGS" | tr ' ' '\n' | while read -r tag; do
+            echo "tag = $tag"
+            if [ -n "$image_name" ] && [ -n "$tag" ]; then
+              docker tag $loaded_image $image_name:${tag}_${{ matrix.platform }}
+              docker push $image_name:${tag}_${{ matrix.platform }}
+              docker buildx imagetools create --tag $image_name:$tag $image_name:${tag}_${{ matrix.platform }}
+            else
+              echo "Skipping tag and push due to empty image_name or tag"
+            fi
+          done

.github/workflows/integration-runner.yml

@@ -1,158 +0,0 @@
-name: Run Integration Tests
-
-on:
-  pull_request:
-    types: [labeled]
-  workflow_dispatch:
-    inputs:
-      reason:
-        description: 'Reason for manual trigger'
-        required: true
-        default: ''
-  schedule:
-    - cron: '30 22 * * *'  # Runs at 10:30pm UTC every day
-
-env:
-  N_PROCESSES: 10 # Global configuration for number of parallel processes for evaluation
-
-jobs:
-  run-integration-tests:
-    if: github.event.label.name == 'integration-test' || github.event_name == 'workflow_dispatch' || github.event_name == 'schedule'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: "read"
-      id-token: "write"
-      pull-requests: "write"
-      issues: "write"
-    strategy:
-      matrix:
-        python-version: ["3.12"]
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-
-      - name: Comment on PR if 'integration-test' label is present
-        if: github.event_name == 'pull_request' && github.event.label.name == 'integration-test'
-        uses: KeisukeYamashita/create-comment@v1
-        with:
-          unique: false
-          comment: |
-            Hi! I started running the integration tests on your PR. You will receive a comment with the results shortly.
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation,llama-index
-
-      - name: Configure config.toml for testing with Haiku
-        env:
-          LLM_MODEL: "litellm_proxy/claude-3-5-haiku-20241022"
-          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
-          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-        run: |
-          echo "[llm.eval]" > config.toml
-          echo "model = \"$LLM_MODEL\"" >> config.toml
-          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
-          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
-          echo "temperature = 0.0" >> config.toml
-
-      - name: Build environment
-        run: make build
-
-      - name: Run integration test evaluation for Haiku
-        env:
-          SANDBOX_FORCE_REBUILD_RUNTIME: True
-        run: |
-          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' $N_PROCESSES '' 'haiku_run'
-
-          # get integration tests report
-          REPORT_FILE_HAIKU=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/*haiku*_maxiter_10_N* -name "report.md" -type f | head -n 1)
-          echo "REPORT_FILE: $REPORT_FILE_HAIKU"
-          echo "INTEGRATION_TEST_REPORT_HAIKU<<EOF" >> $GITHUB_ENV
-          cat $REPORT_FILE_HAIKU >> $GITHUB_ENV
-          echo >> $GITHUB_ENV
-          echo "EOF" >> $GITHUB_ENV
-
-      - name: Wait a little bit
-        run: sleep 10
-
-      - name: Configure config.toml for testing with DeepSeek
-        env:
-          LLM_MODEL: "litellm_proxy/deepseek-chat"
-          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
-          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-        run: |
-          echo "[llm.eval]" > config.toml
-          echo "model = \"$LLM_MODEL\"" >> config.toml
-          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
-          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
-          echo "temperature = 0.0" >> config.toml
-
-      - name: Run integration test evaluation for DeepSeek
-        env:
-          SANDBOX_FORCE_REBUILD_RUNTIME: True
-        run: |
-          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' $N_PROCESSES '' 'deepseek_run'
-
-          # get integration tests report
-          REPORT_FILE_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/deepseek*_maxiter_10_N* -name "report.md" -type f | head -n 1)
-          echo "REPORT_FILE: $REPORT_FILE_DEEPSEEK"
-          echo "INTEGRATION_TEST_REPORT_DEEPSEEK<<EOF" >> $GITHUB_ENV
-          cat $REPORT_FILE_DEEPSEEK >> $GITHUB_ENV
-          echo >> $GITHUB_ENV
-          echo "EOF" >> $GITHUB_ENV
-
-      - name: Create archive of evaluation outputs
-        run: |
-          TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
-          cd evaluation/evaluation_outputs/outputs  # Change to the outputs directory
-          tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/*  # Only include the actual result directories
-
-      - name: Upload evaluation results as artifact
-        uses: actions/upload-artifact@v4
-        id: upload_results_artifact
-        with:
-          name: integration-test-outputs-${{ github.run_id }}-${{ github.run_attempt }}
-          path: integration_tests_*.tar.gz
-
-      - name: Get artifact URLs
-        run: |
-          echo "ARTIFACT_URL=${{ steps.upload_results_artifact.outputs.artifact-url }}" >> $GITHUB_ENV
-
-      - name: Set timestamp and trigger reason
-        run: |
-          echo "TIMESTAMP=$(date +'%Y-%m-%d-%H-%M')" >> $GITHUB_ENV
-          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
-            echo "TRIGGER_REASON=pr-${{ github.event.pull_request.number }}" >> $GITHUB_ENV
-          elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
-            echo "TRIGGER_REASON=manual-${{ github.event.inputs.reason }}" >> $GITHUB_ENV
-          else
-            echo "TRIGGER_REASON=nightly-scheduled" >> $GITHUB_ENV
-          fi
-
-      - name: Comment with results and artifact link
-        id: create_comment
-        uses: KeisukeYamashita/create-comment@v1
-        with:
-          # if triggered by PR, use PR number, otherwise use 5318 as fallback issue number for manual triggers
-          number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || 5318 }}
-          unique: false
-          comment: |
-              Trigger by: ${{ github.event_name == 'pull_request' && format('Pull Request (integration-test label on PR #{0})', github.event.pull_request.number) || (github.event_name == 'workflow_dispatch' && format('Manual Trigger: {0}', github.event.inputs.reason)) || 'Nightly Scheduled Run' }}
-              Commit: ${{ github.sha }}
-              **Integration Tests Report (Haiku)**
-              Haiku LLM Test Results:
-              ${{ env.INTEGRATION_TEST_REPORT_HAIKU }}
-              ---
-              **Integration Tests Report (DeepSeek)**
-              DeepSeek LLM Test Results:
-              ${{ env.INTEGRATION_TEST_REPORT_DEEPSEEK }}
-              ---
-              Download testing outputs (includes both Haiku and DeepSeek results): [Download](${{ steps.upload_results_artifact.outputs.artifact-url }})

.github/workflows/lint-fix.yml

@@ -1,91 +0,0 @@
-name: Lint Fix
-
-on:
-  pull_request:
-    types: [labeled]
-
-jobs:
-  # Frontend lint fixes
-  lint-fix-frontend:
-    if: github.event.label.name == 'lint-fix'
-    name: Fix frontend linting issues
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-      pull-requests: write
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ github.head_ref }}
-          repository: ${{ github.event.pull_request.head.repo.full_name }}
-          fetch-depth: 0
-          token: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Install Node.js 20
-        uses: actions/setup-node@v4
-        with:
-          node-version: 20
-      - name: Install frontend dependencies
-        run: |
-          cd frontend
-          npm install --frozen-lockfile
-      - name: Fix frontend lint issues
-        run: |
-          cd frontend
-          npm run lint:fix
-
-      # Commit and push changes if any
-      - name: Check for changes
-        id: git-check
-        run: |
-          git diff --quiet || echo "changes=true" >> $GITHUB_OUTPUT
-      - name: Commit and push if there are changes
-        if: steps.git-check.outputs.changes == 'true'
-        run: |
-          git config --local user.email "openhands@all-hands.dev"
-          git config --local user.name "OpenHands Bot"
-          git add -A
-          git commit -m "🤖 Auto-fix frontend linting issues"
-          git push
-
-  # Python lint fixes
-  lint-fix-python:
-    if: github.event.label.name == 'lint-fix'
-    name: Fix Python linting issues
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-      pull-requests: write
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ github.head_ref }}
-          repository: ${{ github.event.pull_request.head.repo.full_name }}
-          fetch-depth: 0
-          token: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Set up python
-        uses: actions/setup-python@v5
-        with:
-          python-version: 3.12
-          cache: 'pip'
-      - name: Install pre-commit
-        run: pip install pre-commit==3.7.0
-      - name: Fix python lint issues
-        run: |
-          # Run all pre-commit hooks and continue even if they modify files (exit code 1)
-          pre-commit run --config ./dev_config/python/.pre-commit-config.yaml --files openhands/**/* evaluation/**/* tests/**/* || true
-
-      # Commit and push changes if any
-      - name: Check for changes
-        id: git-check
-        run: |
-          git diff --quiet || echo "changes=true" >> $GITHUB_OUTPUT
-      - name: Commit and push if there are changes
-        if: steps.git-check.outputs.changes == 'true'
-        run: |
-          git config --local user.email "openhands@all-hands.dev"
-          git config --local user.name "OpenHands Bot"
-          git add -A
-          git commit -m "🤖 Auto-fix Python linting issues"
-          git push

.github/workflows/lint.yml

@@ -10,11 +10,6 @@ on:
     - main
   pull_request:
 
-# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: true
-
 jobs:
   # Run lint on the frontend code
   lint-frontend:
@@ -30,11 +25,10 @@ jobs:
         run: |
           cd frontend
           npm install --frozen-lockfile
-      - name: Lint and TypeScript compilation
+      - name: Lint
         run: |
           cd frontend
           npm run lint
-          npm run make-i18n && tsc
 
   # Run lint on the python code
   lint-python:
@@ -47,9 +41,9 @@ jobs:
       - name: Set up python
         uses: actions/setup-python@v5
         with:
-          python-version: 3.12
+          python-version: 3.11
           cache: 'pip'
       - name: Install pre-commit
         run: pip install pre-commit==3.7.0
       - name: Run pre-commit hooks
-        run: pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
+        run: pre-commit run --files openhands/**/* agenthub/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml

.github/workflows/openhands-resolver.yml

@@ -1,297 +0,0 @@
-name: Auto-Fix Tagged Issue with OpenHands
-
-on:
-  workflow_call:
-    inputs:
-      max_iterations:
-        required: false
-        type: number
-        default: 50
-      macro:
-        required: false
-        type: string
-        default: "@openhands-agent"
-      target_branch:
-        required: false
-        type: string
-        default: "main"
-        description: "Target branch to pull and create PR against"
-      base_container_image:
-        required: false
-        type: string
-        default: ""
-        description: "Custom sandbox env"
-    secrets:
-      LLM_MODEL:
-        required: true
-      LLM_API_KEY:
-        required: true
-      LLM_BASE_URL:
-        required: false
-      PAT_TOKEN:
-        required: true
-      PAT_USERNAME:
-        required: true
-
-  issues:
-    types: [labeled]
-  pull_request:
-    types: [labeled]
-  issue_comment:
-    types: [created]
-  pull_request_review_comment:
-    types: [created]
-  pull_request_review:
-    types: [submitted]
-
-permissions:
-  contents: write
-  pull-requests: write
-  issues: write
-
-jobs:
-  auto-fix:
-    if: |
-      github.event_name == 'workflow_call' ||
-      github.event.label.name == 'fix-me' ||
-      github.event.label.name == 'fix-me-experimental' ||
-
-      (
-        ((github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment') &&
-        contains(github.event.comment.body, inputs.macro || '@openhands-agent') &&
-        (github.event.comment.author_association == 'OWNER' || github.event.comment.author_association == 'COLLABORATOR' || github.event.comment.author_association == 'MEMBER')
-        ) ||
-
-        (github.event_name == 'pull_request_review' &&
-        contains(github.event.review.body, inputs.macro || '@openhands-agent') &&
-        (github.event.review.author_association == 'OWNER' || github.event.review.author_association == 'COLLABORATOR' || github.event.review.author_association == 'MEMBER')
-        )
-      )
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-
-      - name: Get latest versions and create requirements.txt
-        run: |
-          python -m pip index versions openhands-ai > openhands_versions.txt
-          OPENHANDS_VERSION=$(head -n 1 openhands_versions.txt | awk '{print $2}' | tr -d '()')
-          echo "openhands-ai==${OPENHANDS_VERSION}" >> requirements.txt
-          cat requirements.txt
-
-      - name: Cache pip dependencies
-        if: |
-          !(
-            github.event.label.name == 'fix-me-experimental' ||
-            (
-              (github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment') &&
-              contains(github.event.comment.body, '@openhands-agent-exp')
-            ) ||
-            (
-              github.event_name == 'pull_request_review' &&
-              contains(github.event.review.body, '@openhands-agent-exp')
-            )
-          )
-        uses: actions/cache@v3
-        with:
-          path: ${{ env.pythonLocation }}/lib/python3.12/site-packages/*
-          key: ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }}
-          restore-keys: |
-            ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }}
-
-      - name: Check required environment variables
-        env:
-          LLM_MODEL: ${{ secrets.LLM_MODEL }}
-          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
-          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-          PAT_TOKEN: ${{ secrets.PAT_TOKEN }}
-          PAT_USERNAME: ${{ secrets.PAT_USERNAME }}
-        run: |
-          required_vars=("LLM_MODEL" "LLM_API_KEY" "PAT_TOKEN" "PAT_USERNAME")
-          for var in "${required_vars[@]}"; do
-            if [ -z "${!var}" ]; then
-              echo "Error: Required environment variable $var is not set."
-              exit 1
-            fi
-          done
-
-      - name: Set environment variables
-        run: |
-          if [ -n "${{ github.event.review.body }}" ]; then
-            echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
-            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
-          elif [ -n "${{ github.event.issue.pull_request }}" ]; then
-            echo "ISSUE_NUMBER=${{ github.event.issue.number }}" >> $GITHUB_ENV
-            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
-          elif [ -n "${{ github.event.pull_request.number }}" ]; then
-            echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
-            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
-          else
-            echo "ISSUE_NUMBER=${{ github.event.issue.number }}" >> $GITHUB_ENV
-            echo "ISSUE_TYPE=issue" >> $GITHUB_ENV
-          fi
-
-          if [ -n "${{ github.event.review.body }}" ]; then
-            echo "COMMENT_ID=${{ github.event.review.id || 'None' }}" >> $GITHUB_ENV
-          else
-            echo "COMMENT_ID=${{ github.event.comment.id || 'None' }}" >> $GITHUB_ENV
-          fi
-
-          echo "MAX_ITERATIONS=${{ inputs.max_iterations || 50 }}" >> $GITHUB_ENV
-          echo "SANDBOX_ENV_GITHUB_TOKEN=${{ secrets.GITHUB_TOKEN }}" >> $GITHUB_ENV
-          echo "SANDBOX_ENV_BASE_CONTAINER_IMAGE=${{ inputs.base_container_image }}" >> $GITHUB_ENV
-
-          # Set branch variables
-          echo "TARGET_BRANCH=${{ inputs.target_branch }}" >> $GITHUB_ENV
-
-      - name: Comment on issue with start message
-        uses: actions/github-script@v7
-        with:
-          github-token: ${{secrets.GITHUB_TOKEN}}
-          script: |
-            const issueType = process.env.ISSUE_TYPE;
-            github.rest.issues.createComment({
-              issue_number: ${{ env.ISSUE_NUMBER }},
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              body: `[OpenHands](https://github.com/All-Hands-AI/OpenHands) started fixing the ${issueType}! You can monitor the progress [here](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}).`
-            });
-
-      - name: Install OpenHands
-        run: |
-          if [[ "${{ github.event.label.name }}" == "fix-me-experimental" ]] ||
-             ([[ "${{ github.event_name }}" == "issue_comment" || "${{ github.event_name }}" == "pull_request_review_comment" ]] &&
-              [[ "${{ github.event.comment.body }}" == "@openhands-agent-exp"* ]]) ||
-             ([[ "${{ github.event_name }}" == "pull_request_review" ]] &&
-              [[ "${{ github.event.review.body }}" == "@openhands-agent-exp"* ]]); then
-            python -m pip install --upgrade pip
-            pip install git+https://github.com/all-hands-ai/openhands.git
-          else
-            python -m pip install --upgrade -r requirements.txt
-          fi
-
-      - name: Attempt to resolve issue
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_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 }}
-          PYTHONPATH: ""
-        run: |
-          cd /tmp && python -m openhands.resolver.resolve_issue \
-            --repo ${{ github.repository }} \
-            --issue-number ${{ env.ISSUE_NUMBER }} \
-            --issue-type ${{ env.ISSUE_TYPE }} \
-            --max-iterations ${{ env.MAX_ITERATIONS }} \
-            --comment-id ${{ env.COMMENT_ID }} \
-
-      - name: Check resolution result
-        id: check_result
-        run: |
-          if cd /tmp && grep -q '"success":true' output/output.jsonl; then
-            echo "RESOLUTION_SUCCESS=true" >> $GITHUB_OUTPUT
-          else
-            echo "RESOLUTION_SUCCESS=false" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Upload output.jsonl as artifact
-        uses: actions/upload-artifact@v4
-        if: always() # Upload even if the previous steps fail
-        with:
-          name: resolver-output
-          path: /tmp/output/output.jsonl
-          retention-days: 30 # Keep the artifact for 30 days
-
-      - name: Create draft PR or push branch
-        if: always() # Create PR or branch even if the previous steps fail
-        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: ${{ secrets.LLM_BASE_URL }}
-          PYTHONPATH: ""
-        run: |
-          if [ "${{ steps.check_result.outputs.RESOLUTION_SUCCESS }}" == "true" ]; then
-            cd /tmp && python -m openhands.resolver.send_pull_request \
-              --issue-number ${{ env.ISSUE_NUMBER }} \
-              --pr-type draft | tee pr_result.txt && \
-              grep "draft created" pr_result.txt | sed 's/.*\///g' > pr_number.txt
-          else
-            cd /tmp && python -m openhands.resolver.send_pull_request \
-              --issue-number ${{ env.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@v7
-        if: always() # Comment on issue even if the previous steps fail
-        with:
-          github-token: ${{secrets.GITHUB_TOKEN}}
-          script: |
-            const fs = require('fs');
-            const issueNumber = ${{ env.ISSUE_NUMBER }};
-            const success = ${{ steps.check_result.outputs.RESOLUTION_SUCCESS }};
-
-            let prNumber = '';
-            let branchName = '';
-            let logContent = '';
-            const noChangesMessage = `No changes to commit for issue #${issueNumber}. Skipping commit.`;
-
-            try {
-              if (success){
-                logContent = fs.readFileSync('/tmp/pr_result.txt', 'utf8').trim();
-              } else {
-                logContent = fs.readFileSync('/tmp/branch_result.txt', 'utf8').trim();
-              }
-            } catch (error) {
-              console.error('Error reading results file:', error);
-            }
-
-            try {
-              if (success) {
-                prNumber = fs.readFileSync('/tmp/pr_number.txt', 'utf8').trim();
-              } else {
-                branchName = fs.readFileSync('/tmp/branch_name.txt', 'utf8').trim();
-              }
-            } catch (error) {
-              console.error('Error reading file:', error);
-            }
-
-            if (logContent.includes(noChangesMessage)) {
-              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. Openhands failed to create any code changes.`
-              });
-            } else 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/${branchName}). Manual intervention may be required.`
-              });
-            } else {
-              github.rest.issues.createComment({
-                issue_number: issueNumber,
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                body: `The workflow to fix this issue encountered an error. Please check the [workflow logs](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}) for more information.`
-              });
-            }

.github/workflows/py-unit-tests-mac.yml

@@ -1,96 +0,0 @@
-# Workflow that runs python unit tests on mac
-name: Run Python Unit Tests Mac
-
-# This job is flaky so only run it nightly
-on:
-  schedule:
-    - cron: '0 0 * * *'
-
-jobs:
-  # Run python unit tests on macOS
-  test-on-macos:
-    name: Python Unit Tests on macOS
-    runs-on: macos-14
-    env:
-      INSTALL_DOCKER: '1' # Set to '0' to skip Docker installation
-    strategy:
-      matrix:
-        python-version: ['3.12']
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-      - name: Cache Poetry dependencies
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/pypoetry
-            ~/.virtualenvs
-          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-poetry-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-      - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation,llama-index
-      - name: Install & Start Docker
-        if: env.INSTALL_DOCKER == '1'
-        run: |
-          INSTANCE_NAME="colima-${GITHUB_RUN_ID}"
-
-          # Uninstall colima to upgrade to the latest version
-          if brew list colima &>/dev/null; then
-            brew uninstall colima
-            # unlinking colima dependency: go
-            brew uninstall go@1.21
-          fi
-          rm -rf ~/.colima ~/.lima
-          brew install --HEAD colima
-          brew install docker
-
-          start_colima() {
-            # Find a free port in the range 10000-20000
-            RANDOM_PORT=$((RANDOM % 10001 + 10000))
-
-            # Original line:
-            if ! colima start --network-address --arch x86_64 --cpu=1 --memory=1 --verbose --ssh-port $RANDOM_PORT; then
-              echo "Failed to start Colima."
-              return 1
-            fi
-            return 0
-          }
-
-          # Attempt to start Colima for 5 total attempts:
-          ATTEMPT_LIMIT=5
-          for ((i=1; i<=ATTEMPT_LIMIT; i++)); do
-
-            if start_colima; then
-              echo "Colima started successfully."
-              break
-            else
-              colima stop -f
-              sleep 10
-              colima delete -f
-              if [ $i -eq $ATTEMPT_LIMIT ]; then
-                exit 1
-              fi
-              sleep 10
-            fi
-          done
-
-          # For testcontainers to find the Colima socket
-          # https://github.com/abiosoft/colima/blob/main/docs/FAQ.md#cannot-connect-to-the-docker-daemon-at-unixvarrundockersock-is-the-docker-daemon-running
-          sudo ln -sf $HOME/.colima/default/docker.sock /var/run/docker.sock
-      - name: Build Environment
-        run: make build
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-      - name: Run Tests
-        run: poetry run pytest --forked --cov=openhands --cov-report=xml ./tests/unit --ignore=tests/unit/test_memory.py
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

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

@@ -10,12 +10,84 @@ on:
       - main
   pull_request:
 
-# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: true
-
 jobs:
+  # Run python unit tests on macOS
+  test-on-macos:
+    name: Python Unit Tests on macOS
+    runs-on: macos-12
+    env:
+      INSTALL_DOCKER: '1' # Set to '0' to skip Docker installation
+    strategy:
+      matrix:
+        python-version: ['3.11']
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'poetry'
+      - name: Install Python dependencies using Poetry
+        run: poetry install --without evaluation,llama-index
+      - name: Install & Start Docker
+        if: env.INSTALL_DOCKER == '1'
+        run: |
+          INSTANCE_NAME="colima-${GITHUB_RUN_ID}"
+
+          # Uninstall colima to upgrade to the latest version
+          if brew list colima &>/dev/null; then
+            brew uninstall colima
+            # unlinking colima dependency: go
+            brew uninstall go@1.21
+          fi
+          rm -rf ~/.colima ~/.lima
+          brew install --HEAD colima
+          brew install docker
+
+          start_colima() {
+            # Find a free port in the range 10000-20000
+            RANDOM_PORT=$((RANDOM % 10001 + 10000))
+
+            # Original line:
+            if ! colima start --network-address --arch x86_64 --cpu=1 --memory=1 --verbose --ssh-port $RANDOM_PORT; then
+              echo "Failed to start Colima."
+              return 1
+            fi
+            return 0
+          }
+
+          # Attempt to start Colima for 5 total attempts:
+          ATTEMPT_LIMIT=5
+          for ((i=1; i<=ATTEMPT_LIMIT; i++)); do
+
+            if start_colima; then
+              echo "Colima started successfully."
+              break
+            else
+              colima stop -f
+              sleep 10
+              colima delete -f
+              if [ $i -eq $ATTEMPT_LIMIT ]; then
+                exit 1
+              fi
+              sleep 10
+            fi
+          done
+
+          # For testcontainers to find the Colima socket
+          # https://github.com/abiosoft/colima/blob/main/docs/FAQ.md#cannot-connect-to-the-docker-daemon-at-unixvarrundockersock-is-the-docker-daemon-running
+          sudo ln -sf $HOME/.colima/default/docker.sock /var/run/docker.sock
+      - name: Build Environment
+        run: make build
+      - name: Run Tests
+        run: poetry run pytest --forked --cov=agenthub --cov=openhands --cov-report=xml ./tests/unit -k "not test_runtime.py"
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
   # Run python unit tests on Linux
   test-on-linux:
     name: Python Unit Tests on Linux
@@ -24,12 +96,9 @@ jobs:
       INSTALL_DOCKER: '0' # Set to '0' to skip Docker installation
     strategy:
       matrix:
-        python-version: ['3.12']
+        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
@@ -42,7 +111,7 @@ jobs:
       - name: Build Environment
         run: make build
       - name: Run Tests
-        run: poetry run pytest --forked --cov=openhands --cov-report=xml -svv ./tests/unit --ignore=tests/unit/test_memory.py
+        run: poetry run pytest --forked --cov=agenthub --cov=openhands --cov-report=xml ./tests/unit -k "not test_runtime.py"
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4
         env:

.github/workflows/pypi-release.yml

@@ -1,31 +0,0 @@
-# Publishes the OpenHands PyPi package
-name: Publish PyPi Package
-
-# Triggered manually
-on:
-  workflow_dispatch:
-    inputs:
-      reason:
-        description: 'Reason for manual trigger'
-        required: true
-        default: ''
-
-jobs:
-  release:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
-        with:
-          python-version: 3.12
-      - name: Install Poetry
-        uses: snok/install-poetry@v1.4.1
-        with:
-          virtualenvs-in-project: true
-          virtualenvs-path: ~/.virtualenvs
-      - name: Install Poetry Dependencies
-        run: poetry install --no-interaction --no-root
-      - name: Build poetry project
-        run: ./build.sh
-      - name: publish
-        run: poetry publish -u __token__ -p ${{ secrets.PYPI_TOKEN }}

.github/workflows/review-pr.yml

@@ -0,0 +1,78 @@
+# Workflow that uses OpenHands to review a pull request. PR must be labeled 'review-this'
+name: Use OpenHands to Review Pull Request
+
+on:
+  pull_request:
+    types: [synchronize, labeled]
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  dogfood:
+    if: contains(github.event.pull_request.labels.*.name, 'review-this')
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.11'
+    - name: install git, github cli
+      run: |
+        sudo apt-get install -y git gh
+        git config --global --add safe.directory $PWD
+    - name: Checkout Repository
+      uses: actions/checkout@v4
+      with:
+        ref: ${{ github.event.pull_request.base.ref }} # check out the target branch
+    - name: Download Diff
+      run: |
+        curl -O "${{ github.event.pull_request.diff_url }}" -L
+    - name: Write Task File
+      run: |
+        echo "Your coworker wants to apply a pull request to this project." > task.txt
+        echo "Read and review ${{ github.event.pull_request.number }}.diff file. Create a review-${{ github.event.pull_request.number }}.txt and write your concise comments and suggestions there." >> task.txt
+        echo "Do not ask me for confirmation at any point." >> task.txt
+        echo "" >> task.txt
+        echo "Title" >> task.txt
+        echo "${{ github.event.pull_request.title }}" >> task.txt
+        echo "" >> task.txt
+        echo "Description" >> task.txt
+        echo "${{ github.event.pull_request.body }}" >> task.txt
+        echo "" >> task.txt
+        echo "Diff file is: ${{ github.event.pull_request.number }}.diff" >> task.txt
+    - name: Set up environment
+      run: |
+        curl -sSL https://install.python-poetry.org | python3 -
+        export PATH="/github/home/.local/bin:$PATH"
+        poetry install --without evaluation,llama-index
+        poetry run playwright install --with-deps chromium
+    - name: Run OpenHands
+      env:
+        LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+        LLM_MODEL: ${{ vars.LLM_MODEL }}
+      run: |
+        # Append path to launch poetry
+        export PATH="/github/home/.local/bin:$PATH"
+        # Append path to correctly import package, note: must set pwd at first
+        export PYTHONPATH=$(pwd):$PYTHONPATH
+        export WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE
+        export WORKSPACE_BASE=$GITHUB_WORKSPACE
+        echo -e "/exit\n" | poetry run python openhands/core/main.py -i 50 -f task.txt
+        rm task.txt
+    - name: Check if review file is non-empty
+      id: check_file
+      run: |
+        ls -la
+        if [[ -s review-${{ github.event.pull_request.number }}.txt ]]; then
+          echo "non_empty=true" >> $GITHUB_OUTPUT
+        fi
+      shell: bash
+    - name: Create PR review if file is non-empty
+      env:
+        GH_TOKEN: ${{ github.token }}
+      if: steps.check_file.outputs.non_empty == 'true'
+      run: |
+        gh pr review ${{ github.event.pull_request.number }} --comment --body-file "review-${{ github.event.pull_request.number }}.txt"

.github/workflows/run-eval.yml

@@ -1,53 +0,0 @@
-# Run evaluation on a PR
-name: Run Eval
-
-# Runs when a PR is labeled with one of the "run-eval-" labels
-on:
-  pull_request:
-    types: [labeled]
-
-jobs:
-  trigger-job:
-    name: Trigger remote eval job
-    if: ${{ github.event.label.name == 'run-eval-xs' || github.event.label.name == 'run-eval-s' || github.event.label.name == 'run-eval-m' }}
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout PR branch
-        uses: actions/checkout@v3
-        with:
-          ref: ${{ github.head_ref }}
-
-      - name: Trigger remote job
-        run: |
-          REPO_URL="https://github.com/${{ github.repository }}"
-          PR_BRANCH="${{ github.head_ref }}"
-          echo "Repository URL: $REPO_URL"
-          echo "PR Branch: $PR_BRANCH"
-
-          if [[ "${{ github.event.label.name }}" == "run-eval-xs" ]]; then
-            EVAL_INSTANCES="1"
-          elif [[ "${{ github.event.label.name }}" == "run-eval-s" ]]; then
-            EVAL_INSTANCES="5"
-          elif [[ "${{ github.event.label.name }}" == "run-eval-m" ]]; then
-            EVAL_INSTANCES="30"
-          fi
-
-          curl -X POST \
-            -H "Authorization: Bearer ${{ secrets.PAT_TOKEN }}" \
-            -H "Accept: application/vnd.github+json" \
-            -d "{\"ref\": \"main\", \"inputs\": {\"github-repo\": \"${REPO_URL}\", \"github-branch\": \"${PR_BRANCH}\", \"pr-number\": \"${{ github.event.pull_request.number }}\", \"eval-instances\": \"${EVAL_INSTANCES}\"}}" \
-            https://api.github.com/repos/All-Hands-AI/evaluation/actions/workflows/create-branch.yml/dispatches
-
-          # Send Slack message
-          PR_URL="https://github.com/${{ github.repository }}/pull/${{ github.event.pull_request.number }}"
-          slack_text="PR $PR_URL has triggered evaluation on $EVAL_INSTANCES instances..."
-          curl -X POST -H 'Content-type: application/json' --data '{"text":"'"$slack_text"'"}' \
-            https://hooks.slack.com/services/${{ secrets.SLACK_TOKEN }}
-
-      - name: Comment on PR
-        uses: KeisukeYamashita/create-comment@v1
-        with:
-          unique: false
-          comment: |
-            Running evaluation on the PR. Once eval is done, the results will be posted.

.github/workflows/solve-issue.yml

@@ -0,0 +1,113 @@
+# 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."

.github/workflows/stale.yml

@@ -15,7 +15,6 @@ jobs:
           stale-issue-message: 'This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
           stale-pr-message: 'This PR is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
           days-before-stale: 30
-          exempt-issue-labels: 'tracked'
           close-issue-message: 'This issue was closed because it has been stalled for over 30 days with no activity.'
           close-pr-message: 'This PR was closed because it has been stalled for over 30 days with no activity.'
           days-before-close: 7

.gitignore

@@ -121,7 +121,6 @@ celerybeat.pid
 
 # Environments
 .env
-frontend/.env
 .venv
 env/
 venv/
@@ -174,15 +173,11 @@ evaluation/bird/data
 evaluation/gaia/data
 evaluation/gorilla/data
 evaluation/toolqa/data
-evaluation/scienceagentbench/benchmark
-evaluation/commit0_bench/repos
-
-# openhands resolver
-output/
 
 # frontend
 
 # dependencies
+frontend/node_modules
 frontend/.pnp
 frontend/bun.lockb
 frontend/yarn.lock
@@ -222,6 +217,8 @@ config.toml
 config.toml_
 config.toml.bak
 
+containers/agnostic_sandbox
+
 # swe-bench-eval
 image_build_logs
 run_instance_logs
@@ -231,5 +228,3 @@ runtime_*.tar
 # docker build
 containers/runtime/Dockerfile
 containers/runtime/project.tar.gz
-containers/runtime/code
-**/node_modules/

.openhands_instructions

@@ -1,28 +0,0 @@
-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`
-- To run linting and type-checking before finishing the job, run `poetry run pre-commit run --all-files --config ./dev_config/python/.pre-commit-config.yaml`
-
-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`

COMMUNITY.md

@@ -1,43 +0,0 @@
-# 🙌 The OpenHands Community
-
-The OpenHands community is built around the belief that (1) AI and AI agents are going to fundamentally change the way
-we build software, and (2) if this is true, we should do everything we can to make sure that the benefits provided by
-such powerful technology are accessible to everyone.
-
-If this resonates with you, we'd love to have you join us in our quest!
-
-## 🤝 How to Join
-
-Check out our [How to Join the Community section.](https://github.com/All-Hands-AI/OpenHands?tab=readme-ov-file#-how-to-join-the-community)
-
-## 💪 Becoming a Contributor
-
-We welcome contributions from everyone! Whether you're a developer, a researcher, or simply enthusiastic about advancing
-the field of software engineering with AI, there are many ways to get involved:
-
-- **Code Contributions:** Help us develop new core functionality, improve our agents, improve the frontend and other
-interfaces, or anything else that would help make OpenHands better.
-- **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in
-evaluating the models, or suggest improvements.
-- **Feedback and Testing:** Use the OpenHands toolset, report bugs, suggest features, or provide feedback on usability.
-
-For details, please check [CONTRIBUTING.md](./CONTRIBUTING.md).
-
-## Code of Conduct
-
-We have a [Code of Conduct](./CODE_OF_CONDUCT.md) that we expect all contributors to adhere to.
-Long story short, we are aiming for an open, welcoming, diverse, inclusive, and healthy community.
-All contributors are expected to contribute to building this sort of community.
-
-## 🛠️ Becoming a Maintainer
-
-For contributors who have made significant and sustained contributions to the project, there is a possibility of joining
-the maintainer team. The process for this is as follows:
-
-1. Any contributor who has made sustained and high-quality contributions to the codebase can be nominated by any
-maintainer. If you feel that you may qualify you can reach out to any of the maintainers that have reviewed your PRs and ask if you can be nominated.
-2. Once a maintainer nominates a new maintainer, there will be a discussion period among the maintainers for at least 3 days.
-3. If no concerns are raised the nomination will be accepted by acclamation, and if concerns are raised there will be a discussion and possible vote.
-
-Note that just making many PRs does not immediately imply that you will become a maintainer. We will be looking
-at sustained high-quality contributions over a period of time, as well as good teamwork and adherence to our [Code of Conduct](./CODE_OF_CONDUCT.md).

CONTRIBUTING.md

@@ -2,70 +2,95 @@
 
 Thanks for your interest in contributing to OpenHands! We welcome and appreciate contributions.
 
-## Understanding OpenHands's CodeBase
-
-To understand the codebase, please refer to the README in each module:
-- [frontend](./frontend/README.md)
-- [evaluation](./evaluation/README.md)
-- [openhands](./openhands/README.md)
-   - [agenthub](./openhands/agenthub/README.md)
-   - [server](./openhands/server/README.md)
-
-## Setting up your development environment
-
-We have a separate doc [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) that tells you how to set up a development workflow.
-
-## How can I contribute?
+## How Can I Contribute?
 
 There are many ways that you can contribute:
 
 1. **Download and use** OpenHands, and send [issues](https://github.com/All-Hands-AI/OpenHands/issues) when you encounter something that isn't working or a feature that you'd like to see.
 2. **Send feedback** after each session by [clicking the thumbs-up thumbs-down buttons](https://docs.all-hands.dev/modules/usage/feedback), so we can see where things are working and failing, and also build an open dataset for training code agents.
-3. **Improve the Codebase** by sending [PRs](#sending-pull-requests-to-openhands) (see details below). In particular, we have some [good first issues](https://github.com/All-Hands-AI/OpenHands/labels/good%20first%20issue) that may be ones to start on.
+3. **Improve the Codebase** by sending PRs (see details below). In particular, we have some [good first issue](https://github.com/All-Hands-AI/OpenHands/labels/good%20first%20issue) issues that may be ones to start on.
 
-## What can I build?
-Here are a few ways you can help improve the codebase.
+## Understanding OpenHands's CodeBase
 
-#### UI/UX
-We're always looking to improve the look and feel of the application. If you've got a small fix
-for something that's bugging you, feel free to open up a PR that changes the [`./frontend`](./frontend) directory.
+To understand the codebase, please refer to the README in each module:
+- [frontend](./frontend/README.md)
+- [agenthub](./agenthub/README.md)
+- [evaluation](./evaluation/README.md)
+- [openhands](./openhands/README.md)
+    - [server](./openhands/server/README.md)
 
-If you're looking to make a bigger change, add a new UI element, or significantly alter the style
-of the application, please open an issue first, or better, join the #frontend channel in our Slack
-to gather consensus from our design team first.
-
-#### Improving the agent
-Our main agent is the CodeAct agent. You can [see its prompts here](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/agenthub/codeact_agent)
-
-Changes to these prompts, and to the underlying behavior in Python, can have a huge impact on user experience.
-You can try modifying the prompts to see how they change the behavior of the agent as you use the app
-locally, but we will need to do an end-to-end evaluation of any changes here to ensure that the agent
-is getting better over time.
-
-We use the [SWE-bench](https://www.swebench.com/) benchmark to test our agent. You can join the #evaluation
-channel in Slack to learn more.
-
-#### Adding a new agent
-You may want to experiment with building new types of agents. You can add an agent to [`openhands/agenthub`](./openhands/agenthub)
-to help expand the capabilities of OpenHands.
-
-#### Adding a new runtime
-The agent needs a place to run code and commands. When you run OpenHands on your laptop, it uses a Docker container
-to do this by default. But there are other ways of creating a sandbox for the agent.
-
-If you work for a company that provides a cloud-based runtime, you could help us add support for that runtime
-by implementing the [interface specified here](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/base.py).
-
-#### Testing
-When you write code, it is also good to write tests. Please navigate to the [`./tests`](./tests) folder to see existing test suites.
-At the moment, we have two kinds of tests: [`unit`](./tests/unit) and [`integration`](./evaluation/integration_tests). Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
+When you write code, it is also good to write tests. Please navigate to the `tests` folder to see existing test suites.
+At the moment, we have two kinds of tests: `unit` and `integration`. Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
 
 ## Sending Pull Requests to OpenHands
 
-You'll need to fork our repository to send us a Pull Request. You can learn more
-about how to fork a GitHub repo and open a PR with your changes in [this article](https://medium.com/swlh/forks-and-pull-requests-how-to-contribute-to-github-repos-8843fac34ce8)
+### 1. Fork the Official Repository
+Fork the [OpenHands repository](https://github.com/All-Hands-AI/OpenHands) into your own account.
+Clone your own forked repository into your local environment:
 
-### Pull Request title
+```shell
+git clone git@github.com:<YOUR-USERNAME>/OpenHands.git
+```
+
+### 2. Configure Git
+
+Set the official repository as your [upstream](https://www.atlassian.com/git/tutorials/git-forks-and-upstreams) to synchronize with the latest update in the official repository.
+Add the original repository as upstream:
+
+```shell
+cd OpenHands
+git remote add upstream git@github.com:All-Hands-AI/OpenHands.git
+```
+
+Verify that the remote is set:
+
+```shell
+git remote -v
+```
+
+You should see both `origin` and `upstream` in the output.
+
+### 3. Synchronize with Official Repository
+Synchronize latest commit with official repository before coding:
+
+```shell
+git fetch upstream
+git checkout main
+git merge upstream/main
+git push origin main
+```
+
+### 4. Set up the Development Environment
+
+We have a separate doc [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) that tells you how to set up a development workflow.
+
+### 5. Write Code and Commit It
+
+Once you have done this, you can write code, test it, and commit it to a branch (replace `my_branch` with an appropriate name):
+
+```shell
+git checkout -b my_branch
+git add .
+git commit
+git push origin my_branch
+```
+
+### 6. Open a Pull Request
+
+* On GitHub, go to the page of your forked repository, and create a Pull Request:
+   - Click on `Branches`
+   - Click on the `...` beside your branch and click on `New pull request`
+   - Set `base repository` to `All-Hands-AI/OpenHands`
+   - Set `base` to `main`
+   - Click `Create pull request`
+
+The PR should appear in [OpenHands PRs](https://github.com/All-Hands-AI/OpenHands/pulls).
+
+Then the OpenHands team will review your code.
+
+## PR Rules
+
+### 1. Pull Request title
 As described [here](https://github.com/commitizen/conventional-commit-types/blob/master/index.json), a valid PR title should begin with one of the following prefixes:
 
 - `feat`: A new feature
@@ -86,38 +111,6 @@ For example, a PR title could be:
 
 You may also check out previous PRs in the [PR list](https://github.com/All-Hands-AI/OpenHands/pulls).
 
-### Pull Request description
+### 2. Pull Request description
 - If your PR is small (such as a typo fix), you can go brief.
 - If it contains a lot of changes, it's better to write more details.
-
-If your changes are user-facing (e.g. a new feature in the UI, a change in behavior, or a bugfix)
-please include a short message that we can add to our changelog.
-
-## How to Make Effective Contributions
-
-### Opening Issues
-
-If you notice any bugs or have any feature requests please open them via the [issues page](https://github.com/All-Hands-AI/OpenHands/issues). We will triage based on how critical the bug is or how potentially useful the improvement is, discuss, and implement the ones that the community has interest/effort for.
-
-Further, if you see an issue you like, please leave a "thumbs-up" or a comment, which will help us prioritize.
-
-### Making Pull Requests
-
-We're generally happy to consider all [PRs](https://github.com/All-Hands-AI/OpenHands/pulls), with the evaluation process varying based on the type of change:
-
-#### For Small Improvements
-
-Small improvements with few downsides are typically reviewed and approved quickly.
-One thing to check when making changes is to ensure that all continuous integration tests pass, which you can check before getting a review.
-
-#### For Core Agent Changes
-
-We need to be more careful with changes to the core agent, as it is imperative to maintain high quality. These PRs are evaluated based on three key metrics:
-
-1. **Accuracy**
-2. **Efficiency**
-3. **Code Complexity**
-
-If it improves accuracy, efficiency, or both with only a minimal change to code quality, that's great we're happy to merge it in!
-If there are bigger tradeoffs (e.g. helping efficiency a lot and hurting accuracy a little) we might want to put it behind a feature flag.
-Either way, please feel free to discuss on github issues or slack, and we will give guidance and preliminary feedback.

CREDITS.md

@@ -2,7 +2,7 @@
 
 ## Contributors
 
-We would like to thank all the [contributors](https://github.com/All-Hands-AI/OpenHands/graphs/contributors) who have helped make OpenHands possible. We greatly appreciate your dedication and hard work.
+We would like to thank all the [contributors](https://github.com/All-Hands-AI/OpenHands/graphs/contributors) who have helped make OpenHands possible. Your dedication and hard work are greatly appreciated.
 
 ## Open Source Projects
 
@@ -10,7 +10,7 @@ OpenHands includes and adapts the following open source projects. We are gratefu
 
 #### [SWE Agent](https://github.com/princeton-nlp/swe-agent)
    - License: MIT License
-   - Description: Adapted for use in OpenHands's agent hub
+   - Description: Adapted for use in OpenHands's agenthub
 
 #### [Aider](https://github.com/paul-gauthier/aider)
    - License: Apache License 2.0

Development.md

@@ -5,14 +5,12 @@ Otherwise, you can clone the OpenHands project directly.
 
 ## Start the server for development
 ### 1. Requirements
-* Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)  [Ubuntu <= 22.04]
+* Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)  [ Ubuntu <= 22.04]
 * [Docker](https://docs.docker.com/engine/install/) (For those on MacOS, make sure to allow the default Docker socket to be used from advanced settings!)
-* [Python](https://www.python.org/downloads/) = 3.12
+* [Python](https://www.python.org/downloads/) = 3.11
 * [NodeJS](https://nodejs.org/en/download/package-manager) >= 18.17.1
 * [Poetry](https://python-poetry.org/docs/#installing-with-the-official-installer) >= 1.8
-* OS-specific dependencies:
-  - Ubuntu: build-essential => `sudo apt-get install build-essential`
-  - WSL: netcat => `sudo apt-get install netcat`
+* netcat => sudo apt-get install netcat
 
 Make sure you have all these dependencies installed before moving on to `make build`.
 
@@ -24,8 +22,8 @@ If you want to develop without system admin/sudo access to upgrade/install `Pyth
 curl -L -O "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"
 bash Miniforge3-$(uname)-$(uname -m).sh
 
-# Install Python 3.12, nodejs, and poetry
-mamba install python=3.12
+# Install Python 3.11, nodejs, and poetry
+mamba install python=3.11
 mamba install conda-forge::nodejs
 mamba install conda-forge::poetry
 ```
@@ -38,9 +36,7 @@ make build
 ```
 
 ### 3. Configuring the Language Model
-OpenHands supports a diverse array of Language Models (LMs) through the powerful [litellm](https://docs.litellm.ai) library.
-By default, we've chosen Claude Sonnet 3.5 as our go-to model, but the world is your oyster! You can unleash the
-potential of any other LM that piques your interest.
+OpenHands supports a diverse array of Language Models (LMs) through the powerful [litellm](https://docs.litellm.ai) library. By default, we've chosen the mighty GPT-4 from OpenAI as our go-to model, but the world is your oyster! You can unleash the potential of Anthropic's suave Claude, the enigmatic Llama, or any other LM that piques your interest.
 
 To configure the LM of your choice, run:
 
@@ -54,7 +50,10 @@ To configure the LM of your choice, run:
    Environment variables > config.toml variables > default variables
 
 **Note on Alternative Models:**
-See [our documentation](https://docs.all-hands.dev/modules/usage/llms) for recommended models.
+Some alternative models may prove more challenging to tame than others. Fear not, brave adventurer! We shall soon unveil LLM-specific documentation to guide you on your quest.
+And if you've already mastered the art of wielding a model other than OpenAI's GPT, we encourage you to share your setup instructions with us by creating instructions and adding it [to our documentation](https://github.com/All-Hands-AI/OpenHands/tree/main/docs/modules/usage/llms).
+
+For a full list of the LM providers and models available, please consult the [litellm documentation](https://docs.litellm.ai/docs/providers).
 
 ### 4. Running the application
 #### Option A: Run the Full Application
@@ -92,37 +91,9 @@ To run tests, refer to the following:
 poetry run pytest ./tests/unit/test_*.py
 ```
 
+#### Integration tests
+Please refer to [this README](./tests/integration/README.md) for details.
+
 ### 9. Add or update dependency
 1. Add your dependency in `pyproject.toml` or use `poetry add xxx`
 2. Update the poetry.lock file via `poetry lock --no-update`
-
-### 9. Use existing Docker image
-To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker container image by
-setting the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
-
-Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.14-nikolaik`
-
-## Develop inside Docker container
-
-TL;DR
-
-```bash
-make docker-dev
-```
-
-See more details [here](./containers/dev/README.md)
-
-If you are just interested in running `OpenHands` without installing all the required tools on your host.
-
-```bash
-make docker-run
-```
-
-If you do not have `make` on your host, run:
-
-```bash
-cd ./containers/dev
-./dev.sh
-```
-
-You do need [Docker](https://docs.docker.com/engine/install/) installed on your host though.

ISSUE_TRIAGE.md

@@ -6,9 +6,9 @@ These are the procedures and guidelines on how issues are triaged in this repo b
 * Issues may be tagged with what it relates to (**backend**, **frontend**, **agent quality**, etc.)
 
 ## Severity
-* **Low**: Minor issues or affecting single user.
-* **Medium**: Affecting multiple users.
-* **Critical**: Affecting all users or potential security issues.
+* **Low**: Minor issues, single user report
+* **Medium**: Affecting multiple users
+* **Critical**: Affecting all users or potential security issues
 
 ## Effort
 * Issues may be estimated with effort required (**small effort**, **medium effort**, **large effort**)
@@ -17,9 +17,9 @@ These are the procedures and guidelines on how issues are triaged in this repo b
 * Issues with low implementation difficulty may be tagged with **good first issue**
 
 ## Not Enough Information
-* User is asked to provide more information (logs, how to reproduce, etc.) when the issue is not clear.
-* If an issue is unclear and the author does not provide more information or respond to a request, the issue may be closed as **not planned** (Usually after a week).
+* User is asked to provide more information (logs, how to reproduce, etc.) when the issue is not clear
+* If an issue is unclear and the author does not provide more information or respond to a request, the issue may be closed as **not planned** (Usually after a week)
 
 ## Multiple Requests/Fixes in One Issue
-* These issues will be narrowed down to one request/fix so the issue is more easily tracked and fixed.
-* Issues may be broken down into multiple issues if required.
+* These issues will be narrowed down to one request/fix so the issue is more easily tracked and fixed
+* Issues may be broken down into multiple issues if required

Makefile

@@ -2,15 +2,14 @@ SHELL=/bin/bash
 # Makefile for OpenHands project
 
 # Variables
-BACKEND_HOST ?= "127.0.0.1"
 BACKEND_PORT = 3000
-BACKEND_HOST_PORT = "$(BACKEND_HOST):$(BACKEND_PORT)"
+BACKEND_HOST = "127.0.0.1:$(BACKEND_PORT)"
 FRONTEND_PORT = 3001
 DEFAULT_WORKSPACE_DIR = "./workspace"
 DEFAULT_MODEL = "gpt-4o"
 CONFIG_FILE = config.toml
 PRE_COMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
-PYTHON_VERSION = 3.12
+PYTHON_VERSION = 3.11
 
 # ANSI color codes
 GREEN=$(shell tput -Txterm setaf 2)
@@ -133,7 +132,7 @@ install-python-dependencies:
 		export HNSWLIB_NO_NATIVE=1; \
 		poetry run pip install chroma-hnswlib; \
 	fi
-	@poetry install --without llama-index,evaluation
+	@poetry install --without llama-index
 	@if [ -f "/etc/manjaro-release" ]; then \
 		echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
 		poetry run pip install playwright; \
@@ -190,12 +189,12 @@ build-frontend:
 # Start backend
 start-backend:
 	@echo "$(YELLOW)Starting backend...$(RESET)"
-	@poetry run uvicorn openhands.server.listen:app --host $(BACKEND_HOST) --port $(BACKEND_PORT) --reload --reload-exclude "$(shell pwd)/workspace"
+	@poetry run uvicorn openhands.server.listen:app --port $(BACKEND_PORT) --reload --reload-exclude "workspace/*"
 
 # Start frontend
 start-frontend:
 	@echo "$(YELLOW)Starting frontend...$(RESET)"
-	@cd frontend && VITE_BACKEND_HOST=$(BACKEND_HOST_PORT) VITE_FRONTEND_PORT=$(FRONTEND_PORT) npm run dev -- --port $(FRONTEND_PORT) --host $(BACKEND_HOST)
+	@cd frontend && VITE_BACKEND_HOST=$(BACKEND_HOST) VITE_FRONTEND_PORT=$(FRONTEND_PORT) npm run start
 
 # Common setup for running the app (non-callable)
 _run_setup:
@@ -205,7 +204,7 @@ _run_setup:
 	fi
 	@mkdir -p logs
 	@echo "$(YELLOW)Starting backend server...$(RESET)"
-	@poetry run uvicorn openhands.server.listen:app --host $(BACKEND_HOST) --port $(BACKEND_PORT) &
+	@poetry run uvicorn openhands.server.listen:app --port $(BACKEND_PORT) &
 	@echo "$(YELLOW)Waiting for the backend to start...$(RESET)"
 	@until nc -z localhost $(BACKEND_PORT); do sleep 0.1; done
 	@echo "$(GREEN)Backend started successfully.$(RESET)"
@@ -214,23 +213,9 @@ _run_setup:
 run:
 	@echo "$(YELLOW)Running the app...$(RESET)"
 	@$(MAKE) -s _run_setup
-	@$(MAKE) -s start-frontend
+	@cd frontend && echo "$(BLUE)Starting frontend with npm...$(RESET)" && npm run start -- --port $(FRONTEND_PORT)
 	@echo "$(GREEN)Application started successfully.$(RESET)"
 
-# Run the app (in docker)
-docker-run: WORKSPACE_BASE ?= $(PWD)/workspace
-docker-run:
-	@if [ -f /.dockerenv ]; then \
-		echo "Running inside a Docker container. Exiting..."; \
-		exit 0; \
-	else \
-		echo "$(YELLOW)Running the app in Docker $(OPTIONS)...$(RESET)"; \
-		export WORKSPACE_BASE=${WORKSPACE_BASE}; \
-		export SANDBOX_USER_ID=$(shell id -u); \
-		export DATE=$(shell date +%Y%m%d%H%M%S); \
-		docker compose up $(OPTIONS); \
-	fi
-
 # Run the app (WSL mode)
 run-wsl:
 	@echo "$(YELLOW)Running the app in WSL mode...$(RESET)"
@@ -275,10 +260,6 @@ setup-config-prompts:
 		echo "    - nomic-embed-text"; \
 		echo "    - all-minilm"; \
 		echo "    - stable-code"; \
-		echo "    - bge-m3"; \
-		echo "    - bge-large"; \
-		echo "    - paraphrase-multilingual"; \
-		echo "    - snowflake-arctic-embed"; \
 		echo "  - Leave blank to default to 'BAAI/bge-small-en-v1.5' via huggingface"; \
 		read -p "> " llm_embedding_model; \
 		echo "embedding_model=\"$$llm_embedding_model\"" >> $(CONFIG_FILE).tmp; \
@@ -295,16 +276,6 @@ setup-config-prompts:
 		fi
 
 
-# Develop in container
-docker-dev:
-	@if [ -f /.dockerenv ]; then \
-		echo "Running inside a Docker container. Exiting..."; \
-		exit 0; \
-	else \
-		echo "$(YELLOW)Build and run in Docker $(OPTIONS)...$(RESET)"; \
-		./containers/dev/dev.sh $(OPTIONS); \
-	fi
-
 # Clean up all caches
 clean:
 	@echo "$(YELLOW)Cleaning up caches...$(RESET)"
@@ -323,10 +294,7 @@ help:
 	@echo "  $(GREEN)start-frontend$(RESET)      - Start the frontend server for the OpenHands project."
 	@echo "  $(GREEN)run$(RESET)                 - Run the OpenHands application, starting both backend and frontend servers."
 	@echo "                        Backend Log file will be stored in the 'logs' directory."
-	@echo "  $(GREEN)docker-dev$(RESET)          - Build and run the OpenHands application in Docker."
-	@echo "  $(GREEN)docker-run$(RESET)          - Run the OpenHands application, starting both backend and frontend servers in Docker."
 	@echo "  $(GREEN)help$(RESET)                - Display this help message, providing information on available targets."
 
 # Phony targets
 .PHONY: build check-dependencies check-python check-npm check-docker check-poetry install-python-dependencies install-frontend-dependencies install-pre-commit-hooks lint start-backend start-frontend run run-wsl setup-config setup-config-prompts help
-.PHONY: docker-dev docker-run

README.md

@@ -1,97 +1,122 @@
 <a name="readme-top"></a>
 
-<div align="center">
-  <img src="./docs/static/img/logo.png" alt="Logo" width="200">
-  <h1 align="center">OpenHands: Code Less, Make More</h1>
-</div>
+<!--
+*** Thanks for checking out the Best-README-Template. If you have a suggestion
+*** that would make this better, please fork the repo and create a pull request
+*** or simply open an issue with the tag "enhancement".
+*** Don't forget to give the project a star!
+*** Thanks again! Now go create something AMAZING! :D
+-->
 
+<!-- PROJECT SHIELDS -->
+<!--
+*** I'm using markdown "reference style" links for readability.
+*** Reference links are enclosed in brackets [ ] instead of parentheses ( ).
+*** See the bottom of this document for the declaration of the reference variables
+*** for contributors-url, forks-url, etc. This is an optional, concise syntax you may use.
+*** https://www.markdownguide.org/basic-syntax/#reference-style-links
+-->
 
 <div align="center">
   <a href="https://github.com/All-Hands-AI/OpenHands/graphs/contributors"><img src="https://img.shields.io/github/contributors/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="Contributors"></a>
+  <a href="https://github.com/All-Hands-AI/OpenHands/network/members"><img src="https://img.shields.io/github/forks/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="Forks"></a>
   <a href="https://github.com/All-Hands-AI/OpenHands/stargazers"><img src="https://img.shields.io/github/stars/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="Stargazers"></a>
-  <a href="https://codecov.io/github/All-Hands-AI/OpenHands?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/All-Hands-AI/OpenHands?style=for-the-badge&color=blue"></a>
+  <a href="https://github.com/All-Hands-AI/OpenHands/issues"><img src="https://img.shields.io/github/issues/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="Issues"></a>
   <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/github/license/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="MIT License"></a>
+  <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=blue" alt="Credits"></a>
   <br/>
-  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2vbfigwev-G03twSpXaErwzYVD4CFiBg"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
+  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
   <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
-  <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="Credits"></a>
-  <br/>
-  <a href="https://docs.all-hands.dev/modules/usage/getting-started"><img src="https://img.shields.io/badge/Documentation-000?logo=googledocs&logoColor=FFE165&style=for-the-badge" alt="Check out the documentation"></a>
-  <a href="https://arxiv.org/abs/2407.16741"><img src="https://img.shields.io/badge/Paper%20on%20Arxiv-000?logoColor=FFE165&logo=arxiv&style=for-the-badge" alt="Paper on Arxiv"></a>
-  <a href="https://huggingface.co/spaces/OpenHands/evaluation"><img src="https://img.shields.io/badge/Benchmark%20score-000?logoColor=FFE165&logo=huggingface&style=for-the-badge" alt="Evaluation Benchmark Score"></a>
-  <hr>
+  <a href="https://codecov.io/github/All-Hands-AI/OpenHands?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/All-Hands-AI/OpenHands?style=for-the-badge"></a>
 </div>
 
-Welcome to OpenHands (formerly OpenDevin), a platform for software development agents powered by AI.
+<!-- PROJECT LOGO -->
+<div align="center">
+  <img src="./docs/static/img/logo.png" alt="Logo" width="200" height="200">
+  <h1 align="center">OpenHands: Code Less, Make More</h1>
+  <a href="https://docs.all-hands.dev/modules/usage/intro"><img src="https://img.shields.io/badge/Documentation-OpenHands-blue?logo=googledocs&logoColor=white&style=for-the-badge" alt="Check out the documentation"></a>
+  <a href="https://arxiv.org/abs/2407.16741"><img src="https://img.shields.io/badge/Paper-%20on%20Arxiv-red?logo=arxiv&style=for-the-badge" alt="Paper on Arxiv"></a>
+  <br/>
+  <a href="https://huggingface.co/spaces/OpenHands/evaluation"><img src="https://img.shields.io/badge/Evaluation-Benchmark%20on%20HF%20Space-green?logo=huggingface&style=for-the-badge" alt="Evaluation Benchmark"></a>
+</div>
+<hr>
 
-OpenHands agents can do anything a human developer can: modify code, run commands, browse the web,
-call APIs, and yes—even copy code snippets from StackOverflow.
+Welcome to OpenHands, a platform for autonomous software engineers, powered by AI and LLMs (previously called "OpenDevin").
 
-Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or jump to the [Quick Start](#-quick-start).
+OpenHands agents collaborate with human developers to write code, fix bugs, and ship features.
 
 ![App screenshot](./docs/static/img/screenshot.png)
 
-## ⚡ Quick Start
+## ⚡ Getting Started
+OpenHands works best with Docker version 26.0.0+ (Docker Desktop 4.31.0+).
+You must be using Linux, Mac OS, or WSL on Windows.
 
-The easiest way to run OpenHands is in Docker.
-See the [Installation](https://docs.all-hands.dev/modules/usage/installation) guide for
-system requirements and more information.
+To start OpenHands in a docker container, run the following commands in your terminal:
+
+> [!WARNING]
+> When you run the following command, files in `./workspace` may be modified or deleted.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.14-nikolaik
-
-docker run -it --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.14-nikolaik \
-    -e LOG_ALL_EVENTS=true \
+WORKSPACE_BASE=$(pwd)/workspace
+docker run -it \
+    --pull=always \
+    -e SANDBOX_USER_ID=$(id -u) \
+    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
+    -v $WORKSPACE_BASE:/opt/workspace_base \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
-    --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.14
+    --name openhands-app-$(date +%Y%m%d%H%M%S) \
+    ghcr.io/all-hands-ai/openhands:0.8
 ```
 
-You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
+> [!NOTE]
+> This command pulls the `0.8` tag, which represents the most recent stable release of OpenHands. You have other options as well:
+> - For a specific release version, use `ghcr.io/all-hands-ai/openhands:<OpenHands_version>` (replace <OpenHands_version> with the desired version number).
+> - For the most up-to-date development version, use `ghcr.io/all-hands-ai/openhands:main`. This version may be **(unstable!)** and is recommended for testing or development purposes only.
+>
+> Choose the tag that best suits your needs based on stability requirements and desired features.
 
-Finally, you'll need a model provider and API key.
-[Anthropic's Claude 3.5 Sonnet](https://www.anthropic.com/api) (`anthropic/claude-3-5-sonnet-20241022`)
-works best, but you have [many options](https://docs.all-hands.dev/modules/usage/llms).
+You'll find OpenHands running at [http://localhost:3000](http://localhost:3000) with access to `./workspace`. To have OpenHands operate on your code, place it in `./workspace`.
+OpenHands will only have access to this workspace folder. The rest of your system will not be affected as it runs in a secured docker sandbox.
 
----
+Upon opening OpenHands, you must select the appropriate `Model` and enter the `API Key` within the settings that should pop up automatically. These can be set at any time by selecting
+the `Settings` button (gear icon) in the UI. If the required `Model` does not exist in the list, you can manually enter it in the text box.
 
-You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes),
-run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
-interact with it via a [friendly CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode),
-or run it on tagged issues with [a github action](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/resolver/README.md).
+For the development workflow, see [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
 
-Visit [Installation](https://docs.all-hands.dev/modules/usage/installation) for more information and setup instructions.
+Are you having trouble? Check out our [Troubleshooting Guide](https://docs.all-hands.dev/modules/usage/troubleshooting).
 
-If you want to modify the OpenHands source code, check out [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
-
-Having issues? The [Troubleshooting Guide](https://docs.all-hands.dev/modules/usage/troubleshooting) can help.
-
-## 📖 Documentation
+## 🚀 Documentation
 
 To learn more about the project, and for tips on using OpenHands,
-**check out our [documentation](https://docs.all-hands.dev/modules/usage/getting-started)**.
+**check out our [documentation](https://docs.all-hands.dev/modules/usage/intro)**.
 
-There you'll find resources on how to use different LLM providers,
+There you'll find resources on how to use different LLM providers (like ollama and Anthropic's Claude),
 troubleshooting resources, and advanced configuration options.
 
-## 🤝 How to Join the Community
+## 🤝 How to Contribute
 
-OpenHands is a community-driven project, and we welcome contributions from everyone. We do most of our communication
-through Slack, so this is the best place to start, but we also are happy to have you contact us on Discord or Github:
+OpenHands is a community-driven project, and we welcome contributions from everyone.
+Whether you're a developer, a researcher, or simply enthusiastic about advancing the field of
+software engineering with AI, there are many ways to get involved:
 
-- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-2vbfigwev-G03twSpXaErwzYVD4CFiBg) - Here we talk about research, architecture, and future development.
-- [Join our Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
-- [Read or post Github Issues](https://github.com/All-Hands-AI/OpenHands/issues) - Check out the issues we're working on, or add your own ideas.
+- **Code Contributions:** Help us develop new agents, core functionality, the frontend and other interfaces, or sandboxing solutions.
+- **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in evaluating the models, or suggest improvements.
+- **Feedback and Testing:** Use the OpenHands toolset, report bugs, suggest features, or provide feedback on usability.
 
-See more about the community in [COMMUNITY.md](./COMMUNITY.md) or find details on contributing in [CONTRIBUTING.md](./CONTRIBUTING.md).
+For details, please check [CONTRIBUTING.md](./CONTRIBUTING.md).
+
+## 🤖 Join Our Community
+
+Whether you're a developer, a researcher, or simply enthusiastic about OpenHands, we'd love to have you in our community.
+Let's make software engineering better together!
+
+- [Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA) - Here we talk about research, architecture, and future development.
+- [Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
 
 ## 📈 Progress
 
-See the monthly OpenHands roadmap [here](https://github.com/orgs/All-Hands-AI/projects/1) (updated at the maintainer's meeting at the end of each month).
-
 <p align="center">
   <a href="https://star-history.com/#All-Hands-AI/OpenHands&Date">
     <img src="https://api.star-history.com/svg?repos=All-Hands-AI/OpenHands&type=Date" width="500" alt="Star History Chart">
@@ -102,6 +127,17 @@ See the monthly OpenHands roadmap [here](https://github.com/orgs/All-Hands-AI/pr
 
 Distributed under the MIT License. See [`LICENSE`](./LICENSE) for more information.
 
+[contributors-shield]: https://img.shields.io/github/contributors/All-Hands-AI/OpenHands?style=for-the-badge
+[contributors-url]: https://github.com/All-Hands-AI/OpenHands/graphs/contributors
+[forks-shield]: https://img.shields.io/github/forks/All-Hands-AI/OpenHands?style=for-the-badge
+[forks-url]: https://github.com/All-Hands-AI/OpenHands/network/members
+[stars-shield]: https://img.shields.io/github/stars/All-Hands-AI/OpenHands?style=for-the-badge
+[stars-url]: https://github.com/All-Hands-AI/OpenHands/stargazers
+[issues-shield]: https://img.shields.io/github/issues/All-Hands-AI/OpenHands?style=for-the-badge
+[issues-url]: https://github.com/All-Hands-AI/OpenHands/issues
+[license-shield]: https://img.shields.io/github/license/All-Hands-AI/OpenHands?style=for-the-badge
+[license-url]: https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE
+
 ## 🙏 Acknowledgements
 
 OpenHands is built by a large number of contributors, and every contribution is greatly appreciated! We also build upon other open source projects, and we are deeply thankful for their work.
@@ -111,8 +147,8 @@ For a list of open source projects and licenses used in OpenHands, please see ou
 ## 📚 Cite
 
 ```
-@misc{openhands,
-      title={{OpenHands: An Open Platform for AI Software Developers as Generalist Agents}},
+@misc{opendevin,
+      title={{OpenDevin: An Open Platform for AI Software Developers as Generalist Agents}},
       author={Xingyao Wang and Boxuan Li and Yufan Song and Frank F. Xu and Xiangru Tang and Mingchen Zhuge and Jiayi Pan and Yueqi Song and Bowen Li and Jaskirat Singh and Hoang H. Tran and Fuqiang Li and Ren Ma and Mingzhang Zheng and Bill Qian and Yanjun Shao and Niklas Muennighoff and Yizhe Zhang and Binyuan Hui and Junyang Lin and Robert Brennan and Hao Peng and Heng Ji and Graham Neubig},
       year={2024},
       eprint={2407.16741},

agenthub/README.md

@@ -2,15 +2,15 @@
 
 In this folder, there may exist multiple implementations of `Agent` that will be used by the framework.
 
-For example, `openhands/agenthub/codeact_agent`, etc.
+For example, `agenthub/codeact_agent`, etc.
 Contributors from different backgrounds and interests can choose to contribute to any (or all!) of these directions.
 
 ## Constructing an Agent
 
-The abstraction for an agent can be found [here](../controller/agent.py).
+The abstraction for an agent can be found [here](../openhands/controller/agent.py).
 
 Agents are run inside of a loop. At each iteration, `agent.step()` is called with a
-[State](../controller/state/state.py) input, and the agent must output an [Action](../events/action).
+[State](../openhands/controller/state/state.py) input, and the agent must output an [Action](../openhands/events/action).
 
 Every agent also has a `self.llm` which it can use to interact with the LLM configured by the user.
 See the [LiteLLM docs for `self.llm.completion`](https://docs.litellm.ai/docs/completion).
@@ -46,17 +46,17 @@ The agent can add and modify subtasks through the `AddTaskAction` and `ModifyTas
 
 Here is a list of available Actions, which can be returned by `agent.step()`:
 
-- [`CmdRunAction`](../events/action/commands.py) - Runs a command inside a sandboxed terminal
-- [`IPythonRunCellAction`](../events/action/commands.py) - Execute a block of Python code interactively (in Jupyter notebook) and receives `CmdOutputObservation`. Requires setting up `jupyter` [plugin](../runtime/plugins) as a requirement.
-- [`FileReadAction`](../events/action/files.py) - Reads the content of a file
-- [`FileWriteAction`](../events/action/files.py) - Writes new content to a file
-- [`BrowseURLAction`](../events/action/browse.py) - Gets the content of a URL
-- [`AddTaskAction`](../events/action/tasks.py) - Adds a subtask to the plan
-- [`ModifyTaskAction`](../events/action/tasks.py) - Changes the state of a subtask.
-- [`AgentFinishAction`](../events/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
-- [`AgentRejectAction`](../events/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
-- [`AgentFinishAction`](../events/action/agent.py) - Stops the control loop, allowing the user to enter a new task
-- [`MessageAction`](../events/action/message.py) - Represents a message from an agent or the user
+- [`CmdRunAction`](../openhands/events/action/commands.py) - Runs a command inside a sandboxed terminal
+- [`IPythonRunCellAction`](../openhands/events/action/commands.py) - Execute a block of Python code interactively (in Jupyter notebook) and receives `CmdOutputObservation`. Requires setting up `jupyter` [plugin](../openhands/runtime/plugins) as a requirement.
+- [`FileReadAction`](../openhands/events/action/files.py) - Reads the content of a file
+- [`FileWriteAction`](../openhands/events/action/files.py) - Writes new content to a file
+- [`BrowseURLAction`](../openhands/events/action/browse.py) - Gets the content of a URL
+- [`AddTaskAction`](../openhands/events/action/tasks.py) - Adds a subtask to the plan
+- [`ModifyTaskAction`](../openhands/events/action/tasks.py) - Changes the state of a subtask.
+- [`AgentFinishAction`](../openhands/events/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
+- [`AgentRejectAction`](../openhands/events/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
+- [`AgentFinishAction`](../openhands/events/action/agent.py) - Stops the control loop, allowing the user to enter a new task
+- [`MessageAction`](../openhands/events/action/message.py) - Represents a message from an agent or the user
 
 To serialize and deserialize an action, you can use:
 - `action.to_dict()` to serialize the action to a dictionary to be sent to the UI, including a user-friendly string representation of the message
@@ -70,12 +70,12 @@ But they may also appear as a result of asynchronous events (e.g. a message from
 
 Here is a list of available Observations:
 
-- [`CmdOutputObservation`](../events/observation/commands.py)
-- [`BrowserOutputObservation`](../events/observation/browse.py)
-- [`FileReadObservation`](../events/observation/files.py)
-- [`FileWriteObservation`](../events/observation/files.py)
-- [`ErrorObservation`](../events/observation/error.py)
-- [`SuccessObservation`](../events/observation/success.py)
+- [`CmdOutputObservation`](../openhands/events/observation/commands.py)
+- [`BrowserOutputObservation`](../openhands/events/observation/browse.py)
+- [`FileReadObservation`](../openhands/events/observation/files.py)
+- [`FileWriteObservation`](../openhands/events/observation/files.py)
+- [`ErrorObservation`](../openhands/events/observation/error.py)
+- [`SuccessObservation`](../openhands/events/observation/success.py)
 
 You can use `observation.to_dict()` and `observation_from_dict` to serialize and deserialize observations.
 

agenthub/__init__.py

@@ -1,13 +1,13 @@
 from dotenv import load_dotenv
 
-from openhands.agenthub.micro.agent import MicroAgent
-from openhands.agenthub.micro.registry import all_microagents
+from agenthub.micro.agent import MicroAgent
+from agenthub.micro.registry import all_microagents
 from openhands.controller.agent import Agent
 
 load_dotenv()
 
 
-from openhands.agenthub import (  # noqa: E402
+from agenthub import (  # noqa: E402
     browsing_agent,
     codeact_agent,
     codeact_swe_agent,

agenthub/browsing_agent/README.md

@@ -12,5 +12,5 @@ poetry run python ./openhands/core/main.py \
            -i 10 \
            -t "tell me the usa's president using google search" \
            -c BrowsingAgent \
-           -m claude-3-5-sonnet-20241022
+           -m gpt-4o-2024-05-13
 ```

agenthub/browsing_agent/__init__.py

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

agenthub/browsing_agent/browsing_agent.py

@@ -3,7 +3,7 @@ import os
 from browsergym.core.action.highlevel import HighLevelActionSet
 from browsergym.utils.obs import flatten_axtree_to_str
 
-from openhands.agenthub.browsing_agent.response_parser import BrowsingResponseParser
+from agenthub.browsing_agent.response_parser import BrowsingResponseParser
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig
@@ -65,15 +65,10 @@ In order to accomplish my goal I need to send the information asked back to the
 """
 
 
-def get_prompt(
-    error_prefix: str, cur_url: str, cur_axtree_txt: str, prev_action_str: str
-) -> str:
+def get_prompt(error_prefix: str, cur_axtree_txt: str, prev_action_str: str) -> str:
     prompt = f"""\
 {error_prefix}
 
-# Current Page URL:
-{cur_url}
-
 # Current Accessibility Tree:
 {cur_axtree_txt}
 
@@ -144,19 +139,18 @@ class BrowsingAgent(Agent):
         """
         messages: list[Message] = []
         prev_actions = []
-        cur_url = ''
         cur_axtree_txt = ''
         error_prefix = ''
         last_obs = None
         last_action = None
 
-        if EVAL_MODE and len(state.history) == 1:
+        if EVAL_MODE and len(state.history.get_events_as_list()) == 1:
             # for webarena and miniwob++ eval, we need to retrieve the initial observation already in browser env
             # initialize and retrieve the first observation by issuing an noop OP
             # For non-benchmark browsing, the browser env starts with a blank page, and the agent is expected to first navigate to desired websites
             return BrowseInteractiveAction(browser_actions='noop()')
 
-        for event in state.history:
+        for event in state.history.get_events():
             if isinstance(event, BrowseInteractiveAction):
                 prev_actions.append(event.browser_actions)
                 last_action = event
@@ -185,9 +179,6 @@ class BrowsingAgent(Agent):
                 self.error_accumulator += 1
                 if self.error_accumulator > 5:
                     return MessageAction('Too many errors encountered. Task failed.')
-
-            cur_url = last_obs.url
-
             try:
                 cur_axtree_txt = flatten_axtree_to_str(
                     last_obs.axtree_object,
@@ -213,11 +204,12 @@ class BrowsingAgent(Agent):
 
         messages.append(Message(role='system', content=[TextContent(text=system_msg)]))
 
-        prompt = get_prompt(error_prefix, cur_url, cur_axtree_txt, prev_action_str)
+        prompt = get_prompt(error_prefix, cur_axtree_txt, prev_action_str)
         messages.append(Message(role='user', content=[TextContent(text=prompt)]))
-
+        logger.debug(prompt)
         response = self.llm.completion(
-            messages=self.llm.format_messages_for_llm(messages),
+            messages=[message.model_dump() for message in messages],
+            temperature=0.0,
             stop=[')```', ')\n```'],
         )
         return self.response_parser.parse(response)

agenthub/browsing_agent/prompt.py

@@ -12,7 +12,7 @@ from browsergym.core.action.base import AbstractActionSet
 from browsergym.core.action.highlevel import HighLevelActionSet
 from browsergym.core.action.python import PythonActionSet
 
-from openhands.agenthub.browsing_agent.utils import (
+from agenthub.browsing_agent.utils import (
     ParseError,
     parse_html_tags_raise,
 )
@@ -57,7 +57,7 @@ class Flags:
 
     @classmethod
     def from_dict(self, flags_dict):
-        """Helper for JSON serializable requirement."""
+        """Helper for JSON serializble requirement."""
         if isinstance(flags_dict, Flags):
             return flags_dict
 
@@ -354,7 +354,7 @@ and executed by a program, make sure to follow the formatting instructions.
         self._prompt += '\n'.join(
             [
                 f"""\
- - [{msg['role']}], {msg['message']}"""
+ - [{msg['role']}] {msg['message']}"""
                 for msg in chat_messages
             ]
         )

agenthub/browsing_agent/response_parser.py

@@ -0,0 +1,88 @@
+import ast
+
+from openhands.controller.action_parser import ActionParser, ResponseParser
+from openhands.core.logger import openhands_logger as logger
+from openhands.events.action import (
+    Action,
+    BrowseInteractiveAction,
+)
+
+
+class BrowsingResponseParser(ResponseParser):
+    def __init__(self):
+        # Need to pay attention to the item order in self.action_parsers
+        super().__init__()
+        self.action_parsers = [BrowsingActionParserMessage()]
+        self.default_parser = BrowsingActionParserBrowseInteractive()
+
+    def parse(self, response: str) -> Action:
+        action_str = self.parse_response(response)
+        return self.parse_action(action_str)
+
+    def parse_response(self, response) -> str:
+        action_str = response['choices'][0]['message']['content']
+        if action_str is None:
+            return ''
+        action_str = action_str.strip()
+        if not action_str.endswith('```'):
+            action_str = action_str + ')```'
+        logger.info(action_str)
+        return action_str
+
+    def parse_action(self, action_str: str) -> Action:
+        for action_parser in self.action_parsers:
+            if action_parser.check_condition(action_str):
+                return action_parser.parse(action_str)
+        return self.default_parser.parse(action_str)
+
+
+class BrowsingActionParserMessage(ActionParser):
+    """Parser action:
+    - BrowseInteractiveAction(browser_actions) - unexpected response format, message back to user
+    """
+
+    def __init__(
+        self,
+    ):
+        pass
+
+    def check_condition(self, action_str: str) -> bool:
+        return '```' not in action_str
+
+    def parse(self, action_str: str) -> Action:
+        msg = f'send_msg_to_user("""{action_str}""")'
+        return BrowseInteractiveAction(
+            browser_actions=msg,
+            thought=action_str,
+            browsergym_send_msg_to_user=action_str,
+        )
+
+
+class BrowsingActionParserBrowseInteractive(ActionParser):
+    """Parser action:
+    - BrowseInteractiveAction(browser_actions) - handle send message to user function call in BrowserGym
+    """
+
+    def __init__(
+        self,
+    ):
+        pass
+
+    def check_condition(self, action_str: str) -> bool:
+        return True
+
+    def parse(self, action_str: str) -> Action:
+        thought = action_str.split('```')[0].strip()
+        action_str = action_str.split('```')[1].strip()
+        msg_content = ''
+        for sub_action in action_str.split('\n'):
+            if 'send_msg_to_user(' in sub_action:
+                tree = ast.parse(sub_action)
+                args = tree.body[0].value.args  # type: ignore
+                msg_content = args[0].value
+
+        return BrowseInteractiveAction(
+            browser_actions=action_str,
+            thought=thought,
+            browsergym_send_msg_to_user=msg_content,
+        )

agenthub/codeact_agent/README.md

@@ -0,0 +1,29 @@
+# CodeAct Agent Framework
+
+This folder implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.01030), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a unified **code** action space for both *simplicity* and *performance* (see paper for more details).
+
+The conceptual idea is illustrated below. At each turn, the agent can:
+
+1. **Converse**: Communicate with humans in natural language to ask for clarification, confirmation, etc.
+2. **CodeAct**: Choose to perform the task by executing code
+   - Execute any valid Linux `bash` command
+   - Execute any valid `Python` code with [an interactive Python interpreter](https://ipython.org/). This is simulated through `bash` command, see plugin system below for more details.
+
+![image](https://github.com/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
+- [SWE-agent tool plugin](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/runtime/plugins/swe_agent_commands): Powerful bash command line tools for software development tasks introduced by [swe-agent](https://github.com/princeton-nlp/swe-agent).
+
+## Demo
+
+https://github.com/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

agenthub/codeact_agent/__init__.py

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

agenthub/codeact_agent/action_parser.py

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

agenthub/codeact_agent/codeact_agent.py

@@ -0,0 +1,249 @@
+import os
+
+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.message import ImageContent, Message, TextContent
+from openhands.events.action import (
+    Action,
+    AgentDelegateAction,
+    AgentFinishAction,
+    CmdRunAction,
+    IPythonRunCellAction,
+    MessageAction,
+)
+from openhands.events.observation import (
+    AgentDelegateObservation,
+    CmdOutputObservation,
+    IPythonRunCellObservation,
+)
+from openhands.events.observation.error import ErrorObservation
+from openhands.events.observation.observation import Observation
+from openhands.events.serialization.event import truncate_content
+from openhands.llm.llm import LLM
+from openhands.runtime.plugins import (
+    AgentSkillsRequirement,
+    JupyterRequirement,
+    PluginRequirement,
+)
+from openhands.utils.prompt import PromptManager
+
+
+class CodeActAgent(Agent):
+    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.
+
+    ### Overview
+
+    This agent implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.01030), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a unified **code** action space for both *simplicity* and *performance* (see paper for more details).
+
+    The conceptual idea is illustrated below. At each turn, the agent can:
+
+    1. **Converse**: Communicate with humans in natural language to ask for clarification, confirmation, etc.
+    2. **CodeAct**: Choose to perform the task by executing code
+    - Execute any valid Linux `bash` command
+    - Execute any valid `Python` code with [an interactive Python interpreter](https://ipython.org/). This is simulated through `bash` command, see plugin system below for more details.
+
+    ![image](https://github.com/All-Hands-AI/OpenHands/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
+
+    """
+
+    sandbox_plugins: list[PluginRequirement] = [
+        # NOTE: AgentSkillsRequirement need to go before JupyterRequirement, since
+        # AgentSkillsRequirement provides a lot of Python functions,
+        # and it needs to be initialized before Jupyter for Jupyter to use those functions.
+        AgentSkillsRequirement(),
+        JupyterRequirement(),
+    ]
+
+    action_parser = CodeActResponseParser()
+
+    def __init__(
+        self,
+        llm: LLM,
+        config: AgentConfig,
+    ) -> None:
+        """Initializes a new instance of the CodeActAgent class.
+
+        Parameters:
+        - llm (LLM): The llm to be used by this agent
+        """
+        super().__init__(llm, config)
+        self.reset()
+        self.prompt_manager = PromptManager(
+            prompt_dir=os.path.join(os.path.dirname(__file__)),
+            agent_skills_docs=AgentSkillsRequirement.documentation,
+            micro_agent_name=None,  # TODO: implement micro-agent
+        )
+
+    def action_to_str(self, action: Action) -> str:
+        if isinstance(action, CmdRunAction):
+            return (
+                f'{action.thought}\n<execute_bash>\n{action.command}\n</execute_bash>'
+            )
+        elif isinstance(action, IPythonRunCellAction):
+            return f'{action.thought}\n<execute_ipython>\n{action.code}\n</execute_ipython>'
+        elif isinstance(action, AgentDelegateAction):
+            return f'{action.thought}\n<execute_browse>\n{action.inputs["task"]}\n</execute_browse>'
+        elif isinstance(action, MessageAction):
+            return action.content
+        elif isinstance(action, AgentFinishAction) and action.source == 'agent':
+            return action.thought
+        return ''
+
+    def get_action_message(self, action: Action) -> Message | None:
+        if (
+            isinstance(action, AgentDelegateAction)
+            or isinstance(action, CmdRunAction)
+            or isinstance(action, IPythonRunCellAction)
+            or isinstance(action, MessageAction)
+            or (isinstance(action, AgentFinishAction) and action.source == 'agent')
+        ):
+            content = [TextContent(text=self.action_to_str(action))]
+
+            if isinstance(action, MessageAction) and action.images_urls:
+                content.append(ImageContent(image_urls=action.images_urls))
+
+            return Message(
+                role='user' if action.source == 'user' else 'assistant', content=content
+            )
+        return None
+
+    def get_observation_message(self, obs: Observation) -> Message | None:
+        max_message_chars = self.llm.config.max_message_chars
+        if isinstance(obs, CmdOutputObservation):
+            text = 'OBSERVATION:\n' + truncate_content(obs.content, max_message_chars)
+            text += (
+                f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]'
+            )
+            return Message(role='user', content=[TextContent(text=text)])
+        elif isinstance(obs, IPythonRunCellObservation):
+            text = 'OBSERVATION:\n' + obs.content
+            # replace base64 images with a placeholder
+            splitted = text.split('\n')
+            for i, line in enumerate(splitted):
+                if '![image](data:image/png;base64,' in line:
+                    splitted[i] = (
+                        '![image](data:image/png;base64, ...) already displayed to user'
+                    )
+            text = '\n'.join(splitted)
+            text = truncate_content(text, max_message_chars)
+            return Message(role='user', content=[TextContent(text=text)])
+        elif isinstance(obs, AgentDelegateObservation):
+            text = 'OBSERVATION:\n' + truncate_content(
+                str(obs.outputs), max_message_chars
+            )
+            return Message(role='user', content=[TextContent(text=text)])
+        elif isinstance(obs, ErrorObservation):
+            text = 'OBSERVATION:\n' + truncate_content(obs.content, max_message_chars)
+            text += '\n[Error occurred in processing last action]'
+            return Message(role='user', content=[TextContent(text=text)])
+        else:
+            # If an observation message is not returned, it will cause an error
+            # when the LLM tries to return the next message
+            raise ValueError(f'Unknown observation type: {type(obs)}')
+
+    def reset(self) -> None:
+        """Resets the CodeAct Agent."""
+        super().reset()
+
+    def step(self, state: State) -> Action:
+        """Performs one step using the CodeAct Agent.
+        This includes gathering info on previous steps and prompting the model to make a command to execute.
+
+        Parameters:
+        - state (State): used to get updated info
+
+        Returns:
+        - CmdRunAction(command) - bash command to run
+        - IPythonRunCellAction(code) - IPython code to run
+        - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
+        - MessageAction(content) - Message action to run (e.g. ask for clarification)
+        - AgentFinishAction() - end the interaction
+        """
+        # if we're done, go back
+        latest_user_message = state.history.get_last_user_message()
+        if latest_user_message and latest_user_message.strip() == '/exit':
+            return AgentFinishAction()
+
+        # prepare what we want to send to the LLM
+        messages = self._get_messages(state)
+
+        response = self.llm.completion(
+            messages=[message.model_dump() for message in messages],
+            stop=[
+                '</execute_ipython>',
+                '</execute_bash>',
+                '</execute_browse>',
+            ],
+            temperature=0.0,
+        )
+        return self.action_parser.parse(response)
+
+    def _get_messages(self, state: State) -> list[Message]:
+        messages: list[Message] = [
+            Message(
+                role='system',
+                content=[TextContent(text=self.prompt_manager.system_message)],
+            ),
+            Message(
+                role='user',
+                content=[TextContent(text=self.prompt_manager.initial_user_message)],
+            ),
+        ]
+
+        for event in state.history.get_events():
+            # create a regular message from an event
+            if isinstance(event, Action):
+                message = self.get_action_message(event)
+            elif isinstance(event, Observation):
+                message = self.get_observation_message(event)
+            else:
+                raise ValueError(f'Unknown event type: {type(event)}')
+
+            # add regular message
+            if message:
+                # handle error if the message is the SAME role as the previous message
+                # litellm.exceptions.BadRequestError: litellm.BadRequestError: OpenAIException - Error code: 400 - {'detail': 'Only supports u/a/u/a/u...'}
+                # there should not have two consecutive messages from the same role
+                if messages and messages[-1].role == message.role:
+                    messages[-1].content.extend(message.content)
+                else:
+                    messages.append(message)
+
+        # the latest user message is important:
+        # we want to remind the agent of the environment constraints
+        latest_user_message = next(
+            (
+                m
+                for m in reversed(messages)
+                if m.role == 'user'
+                and any(isinstance(c, TextContent) for c in m.content)
+            ),
+            None,
+        )
+
+        # Get the last user text inside content
+        if latest_user_message:
+            latest_user_message_text = next(
+                (
+                    t
+                    for t in reversed(latest_user_message.content)
+                    if isinstance(t, TextContent)
+                )
+            )
+            # add a reminder to the prompt
+            reminder_text = f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task. When finished reply with <finish></finish>.'
+
+            if latest_user_message_text:
+                latest_user_message_text.text = (
+                    latest_user_message_text.text + reminder_text
+                )
+            else:
+                latest_user_message_text = TextContent(text=reminder_text)
+                latest_user_message.content.append(latest_user_message_text)
+
+        return messages

agenthub/codeact_agent/system_prompt.j2

@@ -0,0 +1,41 @@
+{% set MINIMAL_SYSTEM_PREFIX %}
+A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
+The assistant can use an interactive Python (Jupyter Notebook) environment, executing code with <execute_ipython>.
+<execute_ipython>
+print("Hello World!")
+</execute_ipython>
+The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
+
+For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
+Important, however: do not run interactive commands. You do not have access to stdin.
+Also, you need to handle commands that may run indefinitely and not return a result. For such cases, you should redirect the output to a file and run the command in the background to avoid blocking the execution.
+For example, to run a Python script that might run indefinitely without returning immediately, you can use the following format: <execute_bash> python3 app.py > server.log 2>&1 & </execute_bash>
+Also, if a command execution result saying like: Command: "npm start" timed out. Sending SIGINT to the process, you should also retry with running the command in the background.
+{% endset %}
+{% set BROWSING_PREFIX %}
+The assistant can browse the Internet with <execute_browse> and </execute_browse>.
+For example, <execute_browse> Tell me the usa's president using google search </execute_browse>.
+Or <execute_browse> Tell me what is in http://example.com </execute_browse>.
+{% 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 + 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 }}
+Please note that THE `edit_file_by_replace`, `append_file` and `insert_content_at_line` FUNCTIONS REQUIRE PROPER INDENTATION. If the assistant would like to add the line '        print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
+{% endset %}
+{% set SYSTEM_SUFFIX %}
+Responses should be concise.
+The assistant should attempt fewer things at a time instead of putting too many commands OR too much code in one "execute" block.
+Include ONLY ONE <execute_ipython>, <execute_bash>, or <execute_browse> per response, unless the assistant is finished with the task or needs more input or action from the user in order to proceed.
+If the assistant is finished with the task you MUST include <finish></finish> in your response.
+IMPORTANT: Execute code using <execute_ipython>, <execute_bash>, or <execute_browse> whenever possible.
+The assistant should utilize full file paths and the 'pwd' command to prevent path-related errors. The assistant should refrain from excessive apologies in its responses.
+
+{% endset %}
+{# Combine all parts without newlines between them #}
+{{ SYSTEM_PREFIX -}}
+{{- COMMAND_DOCS -}}
+{{- SYSTEM_SUFFIX }}

agenthub/codeact_agent/user_prompt.j2

@@ -0,0 +1,231 @@
+{% set DEFAULT_EXAMPLE %}
+--- START OF EXAMPLE ---
+
+USER: Create a list of numbers from 1 to 10, and display them in a web page at port 5000.
+
+ASSISTANT:
+Sure! Let me create a Python file `app.py`:
+<execute_ipython>
+create_file('app.py')
+</execute_ipython>
+
+USER:
+OBSERVATION:
+[File: /workspace/app.py (1 lines total)]
+(this is the beginning of the file)
+1|
+(this is the end of the file)
+[File app.py created.]
+
+ASSISTANT:
+Now I will write the Python code for starting a web server and save it to the file `app.py`:
+<execute_ipython>
+EDITED_CODE="""from flask import Flask
+app = Flask(__name__)
+
+@app.route('/')
+def index():
+    numbers = list(range(1, 11))
+    return str(numbers)
+
+if __name__ == '__main__':
+    app.run(port=5000)"""
+
+insert_content_at_line(
+  'app.py',
+  1,
+  EDITED_CODE,
+)
+</execute_ipython>
+
+USER:
+OBSERVATION:
+(this is the beginning of the file)
+1|from flask import Flask
+2|app = Flask(__name__)
+3|
+4|@app.route('/')
+5|def index():
+6|    numbers = list(range(1, 11))
+7|    return str(numbers)
+8|
+9|if __name__ == '__main__':
+10|    app.run(port=5000)
+(this is the end of the file)
+[File updated (edited at line 1). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
+
+ASSISTANT:
+I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you:
+<execute_bash>
+python3 app.py > server.log 2>&1 &
+</execute_bash>
+
+USER:
+OBSERVATION:
+[1] 121[1]+  Exit 1                  python3 app.py > server.log 2>&1
+
+ASSISTANT: Looks like the server is running with PID 121 then crashed. Let me check the server log:
+<execute_bash>
+cat server.log
+</execute_bash>
+
+USER:
+OBSERVATION:
+Traceback (most recent call last):
+  File "/workspace/app.py", line 2, in <module>
+    from flask import Flask
+ModuleNotFoundError: No module named 'flask'
+
+ASSISTANT:
+It seems that Flask is not installed. Let me install Flask for you:
+<execute_bash>
+pip install flask
+</execute_bash>
+
+USER:
+OBSERVATION:
+Defaulting to user installation because normal site-packages is not writeable
+Collecting flask
+  Using cached flask-3.0.3-py3-none-any.whl (101 kB)
+Collecting blinker>=1.6.2
+  Using cached blinker-1.7.0-py3-none-any.whl (13 kB)
+Collecting Werkzeug>=3.0.0
+  Using cached werkzeug-3.0.2-py3-none-any.whl (226 kB)
+Collecting click>=8.1.3
+  Using cached click-8.1.7-py3-none-any.whl (97 kB)
+Collecting itsdangerous>=2.1.2
+  Using cached itsdangerous-2.2.0-py3-none-any.whl (16 kB)
+Requirement already satisfied: Jinja2>=3.1.2 in /home/openhands/.local/lib/python3.10/site-packages (from flask) (3.1.3)
+Requirement already satisfied: MarkupSafe>=2.0 in /home/openhands/.local/lib/python3.10/site-packages (from Jinja2>=3.1.2->flask) (2.1.5)
+Installing collected packages: Werkzeug, itsdangerous, click, blinker, flask
+Successfully installed Werkzeug-3.0.2 blinker-1.7.0 click-8.1.7 flask-3.0.3 itsdangerous-2.2.0
+
+ASSISTANT:
+Now that Flask is installed, let me run the Python file again:
+<execute_bash>
+python3 app.py > server.log 2>&1 &
+</execute_bash>
+
+USER:
+OBSERVATION:
+[1] 124
+
+ASSISTANT:
+Let me check the server log again:
+<execute_bash>
+cat server.log
+</execute_bash>
+
+USER:
+OBSERVATION:
+* Serving Flask app 'app'
+ * Debug mode: off
+WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
+ * Running on http://127.0.0.1:5000
+Press CTRL+C to quit
+
+ASSISTANT:
+The server is running on port 5000 with PID 124. You can access the list of numbers by visiting http://127.0.0.1:5000. If you have any further questions, feel free to ask!
+
+USER: Now browse the newly started server's homepage and show me the content.
+
+ASSISTANT:
+Sure! Let me browse the server's homepage at http://127.0.0.1:5000:
+<execute_browse>
+Get the content on "http://127.0.0.1:5000"
+</execute_browse>
+
+USER:
+OBSERVATION:
+[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
+
+ASSISTANT:
+The content of the server's homepage is "[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]". If you have any further questions, feel free to ask!
+
+USER: Now kill the server, make it display the numbers in a table format.
+
+ASSISTANT:
+Sure! Let me stop the server first:
+<execute_bash>
+kill 124
+</execute_bash>
+
+USER:
+OBSERVATION:
+[1]+  Terminated              python3 app.py > server.log 2>&1
+
+ASSISTANT:
+The server has been stopped. Let me open the Python file and modify it.
+<execute_ipython>
+open_file('app.py')
+</execute_ipython>
+
+USER:
+[File: /workspace/app.py (10 lines total)]
+(this is the beginning of the file)
+1|from flask import Flask
+2|app = Flask(__name__)
+3|
+4|@app.route('/')
+5|def index():
+6|    numbers = list(range(1, 11))
+7|    return str(numbers)
+8|
+9|if __name__ == '__main__':
+10|    app.run(port=5000)
+(this is the end of the file)
+
+ASSISTANT:
+I should edit the file to display the numbers in a table format. I should include correct indentation. Let me update the file:
+<execute_ipython>
+edit_file_by_replace(
+  'app.py',
+  to_replace="    return str(numbers)",
+  new_content="    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'",
+)
+</execute_ipython>
+
+USER:
+Observation:
+[File: /workspace/app.py (10 lines total after edit)]
+(this is the beginning of the file)
+1|from flask import Flask
+2|app = Flask(__name__)
+3|
+4|@app.route('/')
+5|def index():
+6|    numbers = list(range(1, 11))
+7|    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
+8|
+9|if __name__ == '__main__':
+10|    app.run(port=5000)
+(this is the end of the file)
+[File updated (edited at line 7). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
+
+ASSISTANT:
+Running the updated file:
+<execute_bash>
+python3 app.py > server.log 2>&1 &
+</execute_bash>
+
+USER:
+Observation:
+[1] 126
+
+ASSISTANT:
+The server is running on port 5000 with PID 126. You can access the list of numbers in a table format by visiting http://127.0.0.1:5000. Let me know if you have any further requests!
+<finish></finish>
+
+--- END OF EXAMPLE ---
+{% endset %}
+Here is an example of how you can interact with the environment for task solving:
+{{ DEFAULT_EXAMPLE }}
+{% if micro_agent %}
+--- BEGIN OF GUIDELINE ---
+The following information may assist you in completing your task:
+
+{{ micro_agent }}
+--- END OF GUIDELINE ---
+{% endif %}
+
+NOW, LET'S START!

agenthub/codeact_swe_agent/__init__.py

@@ -1,4 +1,4 @@
-from openhands.agenthub.codeact_swe_agent.codeact_swe_agent import CodeActSWEAgent
+from agenthub.codeact_swe_agent.codeact_swe_agent import CodeActSWEAgent
 from openhands.controller.agent import Agent
 
 Agent.register('CodeActSWEAgent', CodeActSWEAgent)

agenthub/codeact_swe_agent/codeact_swe_agent.py

@@ -1,12 +1,10 @@
-from openhands.agenthub.codeact_swe_agent.prompt import (
+from agenthub.codeact_swe_agent.prompt import (
     COMMAND_DOCS,
     SWE_EXAMPLE,
     SYSTEM_PREFIX,
     SYSTEM_SUFFIX,
 )
-from openhands.agenthub.codeact_swe_agent.response_parser import (
-    CodeActSWEResponseParser,
-)
+from agenthub.codeact_swe_agent.response_parser import CodeActSWEResponseParser
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig
@@ -89,15 +87,15 @@ class CodeActSWEAgent(Agent):
         return ''
 
     def get_action_message(self, action: Action) -> Message | None:
-        if isinstance(action, (CmdRunAction, IPythonRunCellAction, MessageAction)):
+        if (
+            isinstance(action, CmdRunAction)
+            or isinstance(action, IPythonRunCellAction)
+            or isinstance(action, MessageAction)
+        ):
             content = [TextContent(text=self.action_to_str(action))]
 
-            if (
-                self.llm.vision_is_active()
-                and isinstance(action, MessageAction)
-                and action.image_urls
-            ):
-                content.append(ImageContent(image_urls=action.image_urls))
+            if isinstance(action, MessageAction) and action.images_urls:
+                content.append(ImageContent(image_urls=action.images_urls))
 
             return Message(
                 role='user' if action.source == 'user' else 'assistant', content=content
@@ -108,9 +106,7 @@ class CodeActSWEAgent(Agent):
     def get_observation_message(self, obs: Observation) -> Message | None:
         max_message_chars = self.llm.config.max_message_chars
         if isinstance(obs, CmdOutputObservation):
-            text = 'OBSERVATION:\n' + truncate_content(
-                obs.content + obs.interpreter_details, max_message_chars
-            )
+            text = 'OBSERVATION:\n' + truncate_content(obs.content, max_message_chars)
             text += (
                 f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]'
             )
@@ -154,18 +150,20 @@ class CodeActSWEAgent(Agent):
         - AgentFinishAction() - end the interaction
         """
         # if we're done, go back
-        last_user_message = state.get_last_user_message()
-        if last_user_message and last_user_message.content.strip() == '/exit':
+        latest_user_message = state.history.get_last_user_message()
+        if latest_user_message and latest_user_message.strip() == '/exit':
             return AgentFinishAction()
 
         # prepare what we want to send to the LLM
         messages: list[Message] = self._get_messages(state)
+
         response = self.llm.completion(
-            messages=self.llm.format_messages_for_llm(messages),
+            messages=[message.model_dump() for message in messages],
             stop=[
                 '</execute_ipython>',
                 '</execute_bash>',
             ],
+            temperature=0.0,
         )
 
         return self.response_parser.parse(response)
@@ -176,7 +174,7 @@ class CodeActSWEAgent(Agent):
             Message(role='user', content=[TextContent(text=self.in_context_example)]),
         ]
 
-        for event in state.history:
+        for event in state.history.get_events():
             # create a regular message from an event
             if isinstance(event, Action):
                 message = self.get_action_message(event)

agenthub/codeact_swe_agent/response_parser.py

@@ -1,4 +1,4 @@
-from openhands.agenthub.codeact_swe_agent.action_parser import (
+from agenthub.codeact_swe_agent.action_parser import (
     CodeActSWEActionParserCmdRun,
     CodeActSWEActionParserFinish,
     CodeActSWEActionParserIPythonRunCell,

agenthub/delegator_agent/__init__.py

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

agenthub/delegator_agent/agent.py

@@ -2,7 +2,7 @@ from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig
 from openhands.events.action import Action, AgentDelegateAction, AgentFinishAction
-from openhands.events.observation import AgentDelegateObservation, Observation
+from openhands.events.observation import AgentDelegateObservation
 from openhands.llm.llm import LLM
 
 
@@ -41,11 +41,7 @@ class DelegatorAgent(Agent):
             )
 
         # last observation in history should be from the delegate
-        last_observation = None
-        for event in reversed(state.history):
-            if isinstance(event, Observation):
-                last_observation = event
-                break
+        last_observation = state.history.get_last_observation()
 
         if not isinstance(last_observation, AgentDelegateObservation):
             raise Exception('Last observation is not an AgentDelegateObservation')

agenthub/dummy_agent/__init__.py

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

agenthub/dummy_agent/agent.py

@@ -164,7 +164,7 @@ class DummyAgent(Agent):
 
             if 'observations' in prev_step and prev_step['observations']:
                 expected_observations = prev_step['observations']
-                hist_events = state.history[-len(expected_observations) :]
+                hist_events = state.history.get_last_events(len(expected_observations))
 
                 if len(hist_events) < len(expected_observations):
                     print(

agenthub/micro/agent.py

@@ -1,17 +1,17 @@
 from jinja2 import BaseLoader, Environment
 
-from openhands.agenthub.micro.instructions import instructions
-from openhands.agenthub.micro.registry import all_microagents
+from agenthub.micro.instructions import instructions
+from agenthub.micro.registry import all_microagents
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig
 from openhands.core.message import ImageContent, Message, TextContent
 from openhands.core.utils import json
 from openhands.events.action import Action
-from openhands.events.event import Event
 from openhands.events.serialization.action import action_from_dict
 from openhands.events.serialization.event import event_to_memory
 from openhands.llm.llm import LLM
+from openhands.memory.history import ShortTermHistory
 
 
 def parse_response(orig_response: str) -> Action:
@@ -32,14 +32,16 @@ class MicroAgent(Agent):
     prompt = ''
     agent_definition: dict = {}
 
-    def history_to_json(self, history: list[Event], max_events: int = 20, **kwargs):
+    def history_to_json(
+        self, history: ShortTermHistory, max_events: int = 20, **kwargs
+    ):
         """
         Serialize and simplify history to str format
         """
         processed_history = []
         event_count = 0
 
-        for event in reversed(history):
+        for event in history.get_events(reverse=True):
             if event_count >= max_events:
                 break
             processed_history.append(
@@ -71,12 +73,10 @@ class MicroAgent(Agent):
             latest_user_message=last_user_message,
         )
         content = [TextContent(text=prompt)]
-        if self.llm.vision_is_active() and last_image_urls:
+        if last_image_urls:
             content.append(ImageContent(image_urls=last_image_urls))
         message = Message(role='user', content=content)
-        resp = self.llm.completion(
-            messages=self.llm.format_messages_for_llm(message),
-        )
+        resp = self.llm.completion(messages=[message.model_dump()])
         action_resp = resp['choices'][0]['message']['content']
         action = parse_response(action_resp)
         return action

agenthub/micro/manager/prompt.md

@@ -1,7 +1,6 @@
 # Task
 You are in charge of accomplishing the following task:
-{% set goal = latest_user_message if latest_user_message is not none else state.inputs.task %}
-{{ goal }}
+{{ latest_user_message }}
 
 In order to accomplish this goal, you must delegate tasks to one or more agents, who
 can do the actual work. A description of each agent is provided below. You MUST

agenthub/planner_agent/__init__.py

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

agenthub/planner_agent/agent.py

@@ -1,5 +1,5 @@
-from openhands.agenthub.planner_agent.prompt import get_prompt_and_images
-from openhands.agenthub.planner_agent.response_parser import PlannerResponseParser
+from agenthub.planner_agent.prompt import get_prompt_and_images
+from agenthub.planner_agent.response_parser import PlannerResponseParser
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig
@@ -46,8 +46,8 @@ class PlannerAgent(Agent):
             state, self.llm.config.max_message_chars
         )
         content = [TextContent(text=prompt)]
-        if self.llm.vision_is_active() and image_urls:
+        if image_urls:
             content.append(ImageContent(image_urls=image_urls))
         message = Message(role='user', content=content)
-        resp = self.llm.completion(messages=self.llm.format_messages_for_llm(message))
+        resp = self.llm.completion(messages=[message.model_dump()])
         return self.response_parser.parse(resp)

agenthub/planner_agent/prompt.py

@@ -117,7 +117,7 @@ def get_hint(latest_action_id: str) -> str:
 
 def get_prompt_and_images(
     state: State, max_message_chars: int
-) -> tuple[str, list[str] | None]:
+) -> tuple[str, list[str]]:
     """Gets the prompt for the planner agent.
 
     Formatted with the most recent action-observation pairs, current task, and hint based on last action
@@ -136,7 +136,7 @@ def get_prompt_and_images(
     latest_action: Action = NullAction()
 
     # retrieve the latest HISTORY_SIZE events
-    for event_count, event in enumerate(reversed(state.history)):
+    for event_count, event in enumerate(state.history.get_events(reverse=True)):
         if event_count >= HISTORY_SIZE:
             break
         if latest_action == NullAction() and isinstance(event, Action):
@@ -160,7 +160,7 @@ def get_prompt_and_images(
 
     # the hint, based on the last action
     hint = get_hint(event_to_memory(latest_action, max_message_chars).get('action', ''))
-    logger.debug('HINT:\n' + hint, extra={'msg_type': 'DETAIL'})
+    logger.info('HINT:\n' + hint, extra={'msg_type': 'DETAIL'})
 
     # the last relevant user message (the task)
     message, image_urls = state.get_current_user_intent()

build.sh

@@ -1,5 +0,0 @@
-#!/bin/bash
-set -e
-
-cp pyproject.toml poetry.lock openhands
-poetry build -v

compose.yml

@@ -1,22 +0,0 @@
-#
-services:
-  openhands:
-    build:
-      context: ./
-      dockerfile: ./containers/app/Dockerfile
-    image: openhands:latest
-    container_name: openhands-app-${DATE:-}
-    environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.14-nikolaik}
-      - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
-      - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
-    ports:
-      - "3000:3000"
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock
-      - ${WORKSPACE_BASE:-$PWD/workspace}:/opt/workspace_base
-    pull_policy: build
-    stdin_open: true
-    tty: true

config.template.toml

@@ -13,10 +13,6 @@
 # API key for E2B
 #e2b_api_key = ""
 
-# API key for Modal
-#modal_api_token_id = ""
-#modal_api_token_secret = ""
-
 # Base path for the workspace
 workspace_base = "./workspace"
 
@@ -32,10 +28,6 @@ workspace_base = "./workspace"
 # Enable saving and restoring the session when run from CLI
 #enable_cli_session = false
 
-# Path to store trajectories, can be a folder or a file
-# If it's a folder, the session id will be used as the file name
-#trajectories_path="./trajectories"
-
 # File store path
 #file_store_path = "/tmp/file_store"
 
@@ -72,15 +64,6 @@ workspace_base = "./workspace"
 # Name of the default agent
 #default_agent = "CodeActAgent"
 
-# JWT secret for authentication
-#jwt_secret = ""
-
-# Restrict file types for file uploads
-#file_uploads_restrict_file_types = false
-
-# List of allowed file extensions for uploads
-#file_uploads_allowed_extensions = [".*"]
-
 #################################### LLM #####################################
 # Configuration for LLM models (group name starts with 'llm')
 # use 'llm' for the default LLM config
@@ -120,7 +103,7 @@ api_key = "your-api-key"
 #embedding_deployment_name = ""
 
 # Embedding model to use
-embedding_model = "local"
+embedding_model = ""
 
 # Maximum number of characters in an observation's content
 #max_message_chars = 10000
@@ -134,31 +117,14 @@ embedding_model = "local"
 # Model to use
 model = "gpt-4o"
 
-# Number of retries to attempt when an operation fails with the LLM.
-# Increase this value to allow more attempts before giving up
-#num_retries = 8
+# Number of retries to attempt
+#num_retries = 5
 
-# Maximum wait time (in seconds) between retry attempts
-# This caps the exponential backoff to prevent excessively long
-#retry_max_wait = 120
+# Retry maximum wait time
+#retry_max_wait = 60
 
-# Minimum wait time (in seconds) between retry attempts
-# This sets the initial delay before the first retry
-#retry_min_wait = 15
-
-# Multiplier for exponential backoff calculation
-# The wait time increases by this factor after each failed attempt
-# A value of 2.0 means each retry waits twice as long as the previous one
-#retry_multiplier = 2.0
-
-# Drop any unmapped (unsupported) params without causing an exception
-#drop_params = 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 = ""
+# Retry minimum wait time
+#retry_min_wait = 3
 
 # Temperature for the API
 #temperature = 0.0
@@ -167,15 +133,14 @@ model = "gpt-4o"
 #timeout = 0
 
 # Top p for the API
-#top_p = 1.0
+#top_p = 0.5
 
-# If model is vision capable, this option allows to disable image processing (useful for cost reduction).
-#disable_vision = true
-
-[llm.gpt4o-mini]
+[llm.gpt3]
+# API key to use
 api_key = "your-api-key"
-model = "gpt-4o"
 
+# Model to use
+model = "gpt-3.5"
 
 #################################### Agent ###################################
 # Configuration for agents (group name starts with 'agent')
@@ -184,17 +149,14 @@ model = "gpt-4o"
 # agent.CodeActAgent
 ##############################################################################
 [agent]
-# Name of the micro agent to use for this agent
-#micro_agent_name = ""
-
 # Memory enabled
 #memory_enabled = false
 
 # Memory maximum threads
-#memory_max_threads = 3
+#memory_max_threads = 2
 
 # LLM config group to use
-#llm_config = 'your-llm-config-group'
+#llm_config = 'llm'
 
 [agent.RepoExplorerAgent]
 # Example: use a cheaper model for RepoExplorerAgent to reduce cost, especially
@@ -212,7 +174,7 @@ llm_config = 'gpt3'
 #user_id = 1000
 
 # Container image to use for the sandbox
-#base_container_image = "nikolaik/python-nodejs:python3.12-nodejs22"
+#container_image = "nikolaik/python-nodejs:python3.11-nodejs22"
 
 # Use host network
 #use_host_network = false
@@ -220,25 +182,13 @@ llm_config = 'gpt3'
 # Enable auto linting after editing
 #enable_auto_lint = false
 
-# Whether to initialize plugins
-#initialize_plugins = true
-
-# Extra dependencies to install in the runtime image
-#runtime_extra_deps = ""
-
-# Environment variables to set at the launch of the runtime
-#runtime_startup_env_vars = {}
-
-# BrowserGym environment to use for evaluation
-#browsergym_eval_env = ""
-
 #################################### Security ###################################
 # Configuration for security features
 ##############################################################################
 [security]
 
 # Enable confirmation mode
-#confirmation_mode = false
+#confirmation_mode = true
 
 # The security analyzer to use
 #security_analyzer = ""

containers/app/Dockerfile

@@ -8,7 +8,7 @@ RUN npm install -g npm@10.5.1
 RUN npm ci
 
 COPY ./frontend ./
-RUN npm run build
+RUN npm run make-i18n && npm run build
 
 FROM python:3.12.3-slim AS backend-builder
 
@@ -28,7 +28,7 @@ COPY ./pyproject.toml ./poetry.lock ./
 RUN touch README.md
 RUN export POETRY_CACHE_DIR && poetry install --without evaluation,llama-index --no-root && rm -rf $POETRY_CACHE_DIR
 
-FROM python:3.12.3-slim AS openhands-app
+FROM python:3.12.3-slim AS runtime
 
 WORKDIR /app
 
@@ -37,11 +37,10 @@ ARG OPENHANDS_BUILD_VERSION #re-declare for this section
 ENV RUN_AS_OPENHANDS=true
 # A random number--we need this to be different from the user's UID on the host machine
 ENV OPENHANDS_USER_ID=42420
-ENV SANDBOX_LOCAL_RUNTIME_URL=http://host.docker.internal
+ENV SANDBOX_API_HOSTNAME=host.docker.internal
 ENV USE_HOST_NETWORK=false
 ENV WORKSPACE_BASE=/opt/workspace_base
 ENV OPENHANDS_BUILD_VERSION=$OPENHANDS_BUILD_VERSION
-ENV SANDBOX_USER_ID=0
 RUN mkdir -p $WORKSPACE_BASE
 
 RUN apt-get update -y \
@@ -70,12 +69,11 @@ 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 ./openhands/agenthub ./openhands/agenthub
-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
+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
 
 # 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
@@ -83,7 +81,7 @@ RUN python openhands/core/download.py # No-op to download assets
 # openhands:openhands -> openhands:app
 RUN find /app \! -group app -exec chgrp app {} +
 
-COPY --chown=openhands:app --chmod=770 --from=frontend-builder /app/build ./frontend/build
+COPY --chown=openhands:app --chmod=770 --from=frontend-builder /app/dist ./frontend/dist
 COPY --chown=openhands:app --chmod=770 ./containers/app/entrypoint.sh /app/entrypoint.sh
 
 USER root

containers/app/entrypoint.sh

@@ -18,11 +18,6 @@ if [ -z "$SANDBOX_USER_ID" ]; then
   exit 1
 fi
 
-if [ -z "$WORKSPACE_MOUNT_PATH" ]; then
-  # This is set to /opt/workspace in the Dockerfile. But if the user isn't mounting, we want to unset it so that OpenHands doesn't mount at all
-  unset WORKSPACE_BASE
-fi
-
 if [[ "$SANDBOX_USER_ID" -eq 0 ]]; then
   echo "Running OpenHands as root"
   export RUN_AS_OPENHANDS=false

containers/build.sh

@@ -1,55 +1,15 @@
 #!/bin/bash
 set -eo pipefail
 
-# Initialize variables with default values
-image_name=""
-org_name=""
-push=0
-load=0
-tag_suffix=""
+image_name=$1
+org_name=$2
+platform=$3
 
-# 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
-
-echo "Building: $image_name"
+echo "Building: $image_name for platform: $platform"
 tags=()
 
 OPENHANDS_BUILD_VERSION="dev"
 
-cache_tag_base="buildcache"
-cache_tag="$cache_tag_base"
-
-if [[ -n $RELEVANT_SHA ]]; then
-  git_hash=$(git rev-parse --short "$RELEVANT_SHA")
-  tags+=("$git_hash")
-  tags+=("$RELEVANT_SHA")
-fi
-
 if [[ -n $GITHUB_REF_NAME ]]; then
   # check if ref name is a version number
   if [[ $GITHUB_REF_NAME =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
@@ -58,20 +18,11 @@ if [[ -n $GITHUB_REF_NAME ]]; then
     tags+=("$major_version" "$minor_version")
     tags+=("latest")
   fi
-  sanitized_ref_name=$(echo "$GITHUB_REF_NAME" | sed 's/[^a-zA-Z0-9.-]\+/-/g')
-  OPENHANDS_BUILD_VERSION=$sanitized_ref_name
-  sanitized_ref_name=$(echo "$sanitized_ref_name" | tr '[:upper:]' '[:lower:]') # lower case is required in tagging
-  tags+=("$sanitized_ref_name")
-  cache_tag+="-${sanitized_ref_name}"
+  sanitized=$(echo "$GITHUB_REF_NAME" | sed 's/[^a-zA-Z0-9.-]\+/-/g')
+  OPENHANDS_BUILD_VERSION=$sanitized
+  tag=$(echo "$sanitized" | tr '[:upper:]' '[:lower:]') # lower case is required in tagging
+  tags+=("$tag")
 fi
-
-if [[ -n $tag_suffix ]]; then
-  cache_tag+="-${tag_suffix}"
-  for i in "${!tags[@]}"; do
-    tags[$i]="${tags[$i]}-$tag_suffix"
-  done
-fi
-
 echo "Tags: ${tags[@]}"
 
 if [[ "$image_name" == "openhands" ]]; then
@@ -98,9 +49,9 @@ if [[ -n "$org_name" ]]; then
   DOCKER_ORG="$org_name"
 fi
 
-# If $DOCKER_IMAGE_SOURCE_TAG is set, add it to the tags
-if [[ -n "$DOCKER_IMAGE_SOURCE_TAG" ]]; then
-  tags+=("$DOCKER_IMAGE_SOURCE_TAG")
+# If $DOCKER_IMAGE_HASH_TAG is set, add it to the tags
+if [[ -n "$DOCKER_IMAGE_HASH_TAG" ]]; then
+  tags+=("$DOCKER_IMAGE_HASH_TAG")
 fi
 # If $DOCKER_IMAGE_TAG is set, add it to the tags
 if [[ -n "$DOCKER_IMAGE_TAG" ]]; then
@@ -117,40 +68,16 @@ for tag in "${tags[@]}"; do
   args+=" -t $DOCKER_REPOSITORY:$tag"
 done
 
-if [[ $push -eq 1 ]]; then
-  args+=" --push"
-  args+=" --cache-to=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag,mode=max"
-fi
-
-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): $platform"
+output_image="/tmp/${image_name}_${tags[-1]}_${platform}.tar"
+echo "Output image will be saved to: $output_image"
 
 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 $platform \
+  --platform linux/$platform \
   --provenance=false \
   -f "$dir/Dockerfile" \
+  --output type=docker,dest="$output_image" \
   "$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
+echo "${tags[*]}" > tags.txt