update summarize prompt

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.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/devcontainer.json

@@ -1,5 +1,5 @@
 {
-	"name": "OpenDevin Codespaces",
+	"name": "OpenHands Codespaces",
 	"image": "mcr.microsoft.com/devcontainers/universal",
 	"customizations":{
         "vscode":{

.devcontainer/on_create.sh

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

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -1,75 +1,59 @@
 name: Bug
-description: Report a problem with OpenDevin
+description: Report a problem with OpenHands
 title: '[Bug]: '
 labels: ['bug']
 body:
   - type: markdown
     attributes:
-      value: Thank you for taking the time to fill out this bug report. We greatly appreciate your effort to complete this template fully. Please provide as much information as possible to help us understand and address the issue effectively.
+      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.
 
   - type: checkboxes
     attributes:
       label: Is there an existing issue for the same bug?
       description: Please check if an issue already exists for the bug you encountered.
       options:
-      - label: I have checked the troubleshooting document at https://docs.all-hands.dev/modules/usage/troubleshooting
-        required: true
       - label: I have checked the existing issues.
         required: true
 
   - type: textarea
     id: bug-description
     attributes:
-      label: Describe the bug
-      description: Provide a short description of the problem.
+      label: Describe the bug and reproduction steps
+      description: Provide a description of the issue along with any reproduction steps.
     validations:
       required: true
 
-  - type: textarea
-    id: current-version
+  - type: dropdown
+    id: installation
     attributes:
-      label: Current OpenDevin version
-      description: What version of OpenDevin are you using? If you're running in docker, tell us the tag you're using (e.g. ghcr.io/opendevin/opendevin:0.3.1).
-      render: bash
-    validations:
-      required: true
+      label: OpenHands Installation
+      description: How are you running OpenHands?
+      options:
+        - Docker command in README
+        - Development workflow
+      default: 0
 
-  - type: textarea
-    id: config
+  - type: input
+    id: openhands-version
     attributes:
-      label: Installation and Configuration
-      description: Please provide any commands you ran and any configuration (redacting API keys)
-      render: bash
-    validations:
-      required: true
+      label: OpenHands Version
+      description: What version of OpenHands are you using?
+      placeholder: ex. 0.9.8, main, etc.
 
-  - 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
+  - type: dropdown
+    id: os
     attributes:
       label: Operating System
-      description: What Operating System are you using? Linux, Mac OS, WSL on Windows
-
-  - type: textarea
-    id: repro-steps
-    attributes:
-      label: Reproduction Steps
-      description: Please list the steps to reproduce the issue.
-      placeholder: |
-        1.
-        2.
-        3.
+      options:
+        - MacOS
+        - Linux
+        - WSL on Windows
 
   - type: textarea
     id: additional-context
     attributes:
       label: Logs, Errors, Screenshots, and Additional Context
-      description: If you want to share the chat history you can click the thumbs-down (👎) button above the input field and you will get a shareable link (you can also click thumbs up when things are going well of course!). LLM logs will be stored in the `logs/llm/default` folder. Please add any additional context about the problem here.
+      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.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,6 +1,6 @@
 ---
 name: Feature Request
-about: Suggest an idea for OpenDevin features
+about: Suggest an idea for OpenHands features
 title: ''
 labels: 'enhancement'
 assignees: ''

.github/dependabot.yml

@@ -1,22 +1,69 @@
-# To get started with Dependabot version updates, you'll need to specify which
-# package ecosystems to update and where the package manifests are located.
-# Please see the documentation for all configuration options:
-# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
-
 version: 2
 updates:
-  - package-ecosystem: "pip" # See documentation for possible values
-    directory: "/" # Location of package manifests
+  - package-ecosystem: "pip"
+    directory: "/"
     schedule:
       interval: "daily"
-    open-pull-requests-limit: 20
-  - package-ecosystem: "npm" # See documentation for possible values
-    directory: "/frontend" # Location of package manifests
+    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"
+      security-all:
+        applies-to: "security-updates"
+        patterns:
+          - "*"
+      version-all:
+        applies-to: "version-updates"
+        patterns:
+          - "*"
+
+  - package-ecosystem: "npm"
+    directory: "/frontend"
     schedule:
       interval: "daily"
-    open-pull-requests-limit: 20
-  - package-ecosystem: "npm" # See documentation for possible values
-    directory: "/docs" # Location of package manifests
+    open-pull-requests-limit: 1
+    groups:
+      docusaurus:
+        patterns:
+          - "*docusaurus*"
+      eslint:
+        patterns:
+          - "*eslint*"
+      security-all:
+        applies-to: "security-updates"
+        patterns:
+          - "*"
+      version-all:
+        applies-to: "version-updates"
+        patterns:
+          - "*"
+
+  - package-ecosystem: "npm"
+    directory: "/docs"
     schedule:
-      interval: "daily"
-    open-pull-requests-limit: 20
+      interval: "weekly"
+      day: "wednesday"
+    open-pull-requests-limit: 1
+    groups:
+      docusaurus:
+        patterns:
+          - "*docusaurus*"
+      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 @@
-**What is the problem that this fixes or functionality that this introduces? Does it fix any open issues?**
-
+**End-user friendly description of the problem this fixes or functionality that this introduces**
 
+- [ ] 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 @@
 
 
 ---
-**Other references**
+**Link of any specific issues this addresses**

.github/workflows/clean-up.yml

@@ -0,0 +1,69 @@
+# Workflow that cleans up outdated and old workflows to prevent out of disk issues
+name: Delete old workflow runs
+
+# This workflow is currently only triggered manually
+on:
+  workflow_dispatch:
+    inputs:
+      days:
+        description: 'Days-worth of runs to keep for each workflow'
+        required: true
+        default: '30'
+      minimum_runs:
+        description: 'Minimum runs to keep for each workflow'
+        required: true
+        default: '10'
+      delete_workflow_pattern:
+        description: 'Name or filename of the workflow (if not set, all workflows are targeted)'
+        required: false
+      delete_workflow_by_state_pattern:
+        description: 'Filter workflows by state: active, deleted, disabled_fork, disabled_inactivity, disabled_manually'
+        required: true
+        default: "ALL"
+        type: choice
+        options:
+          - "ALL"
+          - active
+          - deleted
+          - disabled_inactivity
+          - disabled_manually
+      delete_run_by_conclusion_pattern:
+        description: 'Remove runs based on conclusion: action_required, cancelled, failure, skipped, success'
+        required: true
+        default: 'ALL'
+        type: choice
+        options:
+          - 'ALL'
+          - 'Unsuccessful: action_required,cancelled,failure,skipped'
+          - action_required
+          - cancelled
+          - failure
+          - skipped
+          - success
+      dry_run:
+        description: 'Logs simulated changes, no deletions are performed'
+        required: false
+
+jobs:
+  del_runs:
+    runs-on: ubuntu-latest
+    permissions:
+      actions: write
+      contents: read
+    steps:
+      - name: Delete workflow runs
+        uses: Mattraks/delete-workflow-runs@v2
+        with:
+          token: ${{ github.token }}
+          repository: ${{ github.repository }}
+          retain_days: ${{ github.event.inputs.days }}
+          keep_minimum_runs: ${{ github.event.inputs.minimum_runs }}
+          delete_workflow_pattern: ${{ github.event.inputs.delete_workflow_pattern }}
+          delete_workflow_by_state_pattern: ${{ github.event.inputs.delete_workflow_by_state_pattern }}
+          delete_run_by_conclusion_pattern: >-
+            ${{
+              startsWith(github.event.inputs.delete_run_by_conclusion_pattern, 'Unsuccessful:')
+              && 'action_required,cancelled,failure,skipped'
+              || github.event.inputs.delete_run_by_conclusion_pattern
+            }}
+          dry_run: ${{ github.event.inputs.dry_run }}

.github/workflows/deploy-docs.yml

@@ -1,18 +1,30 @@
+# Workflow that builds and deploys the documentation website
 name: Deploy Docs to GitHub Pages
 
+# * Always run on "main"
+# * Run on PRs that target the "main" branch and have changes in the "docs" folder or this workflow
 on:
   push:
     branches:
       - main
   pull_request:
+    paths:
+      - 'docs/**'
+      - '.github/workflows/deploy-docs.yml'
     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:
+    if: github.repository == 'All-Hands-AI/OpenHands'
     name: Build Docusaurus
     runs-on: ubuntu-latest
-    if: github.repository == 'OpenDevin/OpenDevin'
     steps:
       - uses: actions/checkout@v4
         with:
@@ -25,25 +37,29 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.11"
-
+          python-version: '3.12'
       - name: Generate Python Docs
         run: rm -rf docs/modules/python && pip install pydoc-markdown && pydoc-markdown
       - name: Install dependencies
         run: cd docs && npm ci
       - name: Build website
         run: cd docs && npm run build
-
       - name: Upload Build Artifact
         if: github.ref == 'refs/heads/main'
         uses: actions/upload-pages-artifact@v3
         with:
           path: docs/build
 
+  # Deploy the documentation website
   deploy:
+    if: github.ref == 'refs/heads/main' && github.repository == 'All-Hands-AI/OpenHands'
     name: Deploy to GitHub Pages
+    runs-on: ubuntu-latest
+    # This job only runs on "main" so only run one of these jobs at a time
+    # otherwise it will fail if one is already running
+    concurrency:
+      group: ${{ github.workflow }}-${{ github.ref }}
     needs: build
-    if: github.ref == 'refs/heads/main' && github.repository == 'OpenDevin/OpenDevin'
     # Grant GITHUB_TOKEN the permissions required to make a Pages deployment
     permissions:
       pages: write # to deploy to Pages
@@ -52,7 +68,6 @@ jobs:
     environment:
       name: github-pages
       url: ${{ steps.deployment.outputs.page_url }}
-    runs-on: ubuntu-latest
     steps:
       - name: Deploy to GitHub Pages
         id: deployment

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

@@ -1,37 +1,56 @@
+# Workflow that uses the DummyAgent to run a simple task
 name: Run E2E test with dummy agent
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-
+# Always run on "main"
+# Always run on PRs
 on:
   push:
     branches:
     - main
   pull_request:
 
-env:
-  PERSIST_SANDBOX : "false"
+# 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: '3.11'
-      - 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/
+          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
       - name: Run tests
         run: |
           set -e
-          poetry run python opendevin/core/main.py -t "do a flip" -d ./workspace/ -c DummyAgent
+          SANDBOX_FORCE_REBUILD_RUNTIME=True poetry run python3 openhands/core/main.py -t "do a flip" -d ./workspace/ -c DummyAgent
       - name: Check exit code
         run: |
           if [ $? -ne 0 ]; then

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

@@ -0,0 +1,44 @@
+# Workflow that runs frontend unit tests
+name: Run Frontend Unit Tests
+
+# * Always run on "main"
+# * Run on PRs that have changes in the "frontend" folder or this workflow
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    paths:
+      - '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:
+    name: FE Unit Tests
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        node-version: [20]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ matrix.node-version }}
+      - name: Install dependencies
+        working-directory: ./frontend
+        run: npm ci
+      - name: Run tests and collect coverage
+        working-directory: ./frontend
+        run: npm run test:coverage
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

.github/workflows/ghcr-build.yml

@@ -0,0 +1,401 @@
+# Workflow that builds, tests and then pushes the OpenHands and runtime docker images to the ghcr.io repository
+name: Build, Test and Publish RT 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: ''
+
+# 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 $image_name | tr '[:upper:]' '[:lower:]')
+
+          SKIP_CONTAINER_LOGS=true \
+          TEST_RUNTIME=eventstream \
+          SANDBOX_USER_ID=$(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
+      - 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 $image_name | tr '[:upper:]' '[:lower:]')
+
+          SKIP_CONTAINER_LOGS=true \
+          TEST_RUNTIME=eventstream \
+          SANDBOX_USER_ID=$(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
+      - 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

.github/workflows/ghcr.yml

@@ -1,481 +0,0 @@
-name: Build Publish and Test Runtime Image
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-
-on:
-  push:
-    branches:
-      - main
-    tags:
-      - '*'
-  pull_request:
-  workflow_dispatch:
-    inputs:
-      reason:
-        description: 'Reason for manual trigger'
-        required: true
-        default: ''
-
-jobs:
-  ghcr_build:
-    runs-on: ubuntu-latest
-
-    outputs:
-      tags: ${{ steps.capture-tags.outputs.tags }}
-
-    permissions:
-      contents: read
-      packages: write
-
-    strategy:
-      matrix:
-        image: ["sandbox", "opendevin"]
-        platform: ["amd64", "arm64"]
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Build and export image
-        id: build
-        run: ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} ${{ matrix.platform }}
-
-      - name: Capture tags
-        id: capture-tags
-        run: |
-          tags=$(cat tags.txt)
-          echo "tags=$tags"
-          echo "tags=$tags" >> $GITHUB_OUTPUT
-
-      - name: Upload Docker image as artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
-          path: /tmp/${{ matrix.image }}_image_${{ matrix.platform }}.tar
-
-  ghcr_build_runtime:
-    runs-on: ubuntu-latest
-
-    outputs:
-      tags: ${{ steps.capture-tags.outputs.tags }}
-
-    permissions:
-      contents: read
-      packages: write
-
-    strategy:
-      matrix:
-        image: ["od_runtime"]
-        base_image: ["ubuntu:22.04"]
-        platform: ["amd64", "arm64"]
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-          cache: "poetry"
-
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-
-      - name: Create source distribution and Dockerfile
-        run: poetry run python3 opendevin/runtime/utils/runtime_build.py --base_image ${{ matrix.base_image }} --build_folder containers/runtime
-
-      - name: Build and export image
-        id: build
-        run: ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} ${{ matrix.platform }}
-
-      - name: Capture tags
-        id: capture-tags
-        run: |
-          tags=$(cat tags.txt)
-          echo "tags=$tags"
-          echo "tags=$tags" >> $GITHUB_OUTPUT
-
-      - name: Upload Docker image as artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
-          path: /tmp/${{ matrix.image }}_image_${{ matrix.platform }}.tar
-
-  test_runtime:
-    name: Test Runtime
-    runs-on: ubuntu-latest
-    needs: [ghcr_build_runtime, ghcr_build]
-    env:
-      PERSIST_SANDBOX: "false"
-
-    strategy:
-      matrix:
-        runtime_type: ["eventstream", "server"]
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # when set to "true" but frees about 6 GB
-          tool-cache: true
-
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          swap-storage: true
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-          cache: "poetry"
-
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-
-      - name: Download Runtime Docker image
-        if: matrix.runtime_type == 'eventstream'
-        uses: actions/download-artifact@v4
-        with:
-          name: od_runtime-docker-image-amd64
-          path: /tmp/
-
-      - name: Download Sandbox Docker image
-        if: matrix.runtime_type == 'server'
-        uses: actions/download-artifact@v4
-        with:
-          name: sandbox-docker-image-amd64
-          path: /tmp/
-
-      - name: Load Runtime image and run runtime tests
-        run: |
-          # Load the Docker image and capture the output
-          if [ "${{ matrix.runtime_type }}" == "eventstream" ]; then
-            output=$(docker load -i /tmp/od_runtime_image_amd64.tar)
-          else
-            output=$(docker load -i /tmp/sandbox_image_amd64.tar)
-          fi
-
-          # Extract the first image name from the output
-          image_name=$(echo "$output" | grep -oP 'Loaded image: \K.*' | head -n 1)
-
-          # Print the full name of the image
-          echo "Loaded Docker image: $image_name"
-
-          TEST_RUNTIME=${{ matrix.runtime_type }} SANDBOX_USER_ID=$(id -u) SANDBOX_CONTAINER_IMAGE=$image_name TEST_IN_CI=true poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml -s ./tests/unit/test_runtime.py
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
-  integration_tests_on_linux:
-    name: Integration Tests on Linux
-    runs-on: ubuntu-latest
-    needs: ghcr_build
-    env:
-      PERSIST_SANDBOX: "false"
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ["3.11"]
-        sandbox: ["ssh", "local"]
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
-
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-
-      - name: Download sandbox Docker image
-        uses: actions/download-artifact@v4
-        with:
-          name: sandbox-docker-image-amd64
-          path: /tmp/
-
-      - name: Load sandbox image and run integration tests
-        env:
-          SANDBOX_BOX_TYPE: ${{ matrix.sandbox }}
-        run: |
-          # Load the Docker image and capture the output
-          output=$(docker load -i /tmp/sandbox_image_amd64.tar)
-
-          # Extract the first image name from the output
-          image_name=$(echo "$output" | grep -oP 'Loaded image: \K.*' | head -n 1)
-
-          # Print the full name of the image
-          echo "Loaded Docker image: $image_name"
-
-          SANDBOX_CONTAINER_IMAGE=$image_name TEST_IN_CI=true TEST_ONLY=true ./tests/integration/regenerate.sh
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
-
-  ghcr_push:
-    runs-on: ubuntu-latest
-    # don't push if integration tests or sandbox tests fail
-    needs: [ghcr_build, test_runtime, integration_tests_on_linux]
-    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
-
-    env:
-      tags: ${{ needs.ghcr_build.outputs.tags }}
-
-    permissions:
-      contents: read
-      packages: write
-
-    strategy:
-      matrix:
-        image: ["sandbox", "opendevin"]
-        platform: ["amd64", "arm64"]
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Login to GHCR
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Download Docker images
-        uses: actions/download-artifact@v4
-        with:
-          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
-          path: /tmp/${{ matrix.platform }}
-
-      - name: Load images and push to registry
-        run: |
-          mv /tmp/${{ matrix.platform }}/${{ matrix.image }}_image_${{ matrix.platform }}.tar .
-          loaded_image=$(docker load -i ${{ matrix.image }}_image_${{ matrix.platform }}.tar | grep "Loaded image:" | head -n 1 | awk '{print $3}')
-          echo "loaded image = $loaded_image"
-          tags=$(echo ${tags} | tr ' ' '\n')
-          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
-          echo "image name = $image_name"
-          for tag in $tags; do
-            echo "tag = $tag"
-            docker tag $loaded_image $image_name:${tag}_${{ matrix.platform }}
-            docker push $image_name:${tag}_${{ matrix.platform }}
-          done
-
-  ghcr_push_runtime:
-    runs-on: ubuntu-latest
-    # don't push if runtime tests fail
-    needs: [ghcr_build_runtime, test_runtime, integration_tests_on_linux]
-    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
-
-    env:
-      tags: ${{ needs.ghcr_build_runtime.outputs.tags }}
-
-    permissions:
-      contents: read
-      packages: write
-
-    strategy:
-      matrix:
-        image: ["od_runtime"]
-        platform: ["amd64", "arm64"]
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          tool-cache: true
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: false
-          swap-storage: true
-
-      - name: Login to GHCR
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Download Docker images
-        uses: actions/download-artifact@v4
-        with:
-          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
-          path: /tmp/${{ matrix.platform }}
-
-      - name: List downloaded files
-        run: |
-          ls -la /tmp/${{ matrix.platform }}
-          file /tmp/${{ matrix.platform }}/*
-
-      - name: Load images and push to registry
-        run: |
-          mv /tmp/${{ matrix.platform }}/${{ matrix.image }}_image_${{ matrix.platform }}.tar ./${{ matrix.image }}_image_${{ matrix.platform }}.tar
-          if ! loaded_image=$(docker load -i ${{ matrix.image }}_image_${{ matrix.platform }}.tar | grep "Loaded image:" | head -n 1 | awk '{print $3}'); then
-            echo "Failed to load Docker image"
-            exit 1
-          fi
-          echo "loaded image = $loaded_image"
-          tags=$(echo ${tags} | tr ' ' '\n')
-          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
-          echo "image name = $image_name"
-          for tag in $tags; do
-            echo "tag = $tag"
-            if [ -n "$image_name" ]; then
-              docker tag $loaded_image $image_name:${tag}_${{ matrix.platform }}
-              docker push $image_name:${tag}_${{ matrix.platform }}
-            else
-              echo "Skipping tag and push due to empty image_name"
-            fi
-          done
-
-  create_manifest:
-    runs-on: ubuntu-latest
-    needs: [ghcr_build, ghcr_push]
-    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
-
-    env:
-      tags: ${{ needs.ghcr_build.outputs.tags }}
-
-    strategy:
-      matrix:
-        image: ["sandbox", "opendevin"]
-
-    permissions:
-      contents: read
-      packages: write
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Login to GHCR
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Create and push multi-platform manifest
-        run: |
-          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
-          echo "image name = $image_name"
-          tags=$(echo ${tags} | tr ' ' '\n')
-          for tag in $tags; do
-            echo 'tag = $tag'
-            docker buildx imagetools create --tag $image_name:$tag \
-              $image_name:${tag}_amd64 \
-              $image_name:${tag}_arm64
-          done
-
-  create_manifest_runtime:
-    runs-on: ubuntu-latest
-    needs: [ghcr_build_runtime, ghcr_push_runtime]
-    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
-
-    env:
-      tags: ${{ needs.ghcr_build_runtime.outputs.tags }}
-
-    strategy:
-      matrix:
-        image: ["od_runtime"]
-
-    permissions:
-      contents: read
-      packages: write
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Login to GHCR
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Create and push multi-platform manifest
-        run: |
-          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
-          echo "image name = $image_name"
-          tags=$(echo ${tags} | tr ' ' '\n')
-          for tag in $tags; do
-            echo 'tag = $tag'
-            docker buildx imagetools create --tag $image_name:$tag \
-              $image_name:${tag}_amd64 \
-              $image_name:${tag}_arm64
-          done

.github/workflows/lint.yml

@@ -1,37 +1,41 @@
+# Workflow that runs lint on the frontend and python code
 name: Lint
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-
+# The jobs in this workflow are required, so they must run at all times
+# Always run on "main"
+# Always run on PRs
 on:
   push:
     branches:
     - 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:
     name: Lint frontend
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-
       - name: Install Node.js 20
         uses: actions/setup-node@v4
         with:
           node-version: 20
-
       - name: Install dependencies
         run: |
           cd frontend
           npm install --frozen-lockfile
-
       - name: Lint
         run: |
           cd frontend
           npm run lint
 
+  # Run lint on the python code
   lint-python:
     name: Lint python
     runs-on: ubuntu-latest
@@ -42,9 +46,9 @@ jobs:
       - name: Set up python
         uses: actions/setup-python@v5
         with:
-          python-version: 3.11
+          python-version: 3.12
           cache: 'pip'
       - name: Install pre-commit
         run: pip install pre-commit==3.7.0
       - name: Run pre-commit hooks
-        run: pre-commit run --files opendevin/**/* agenthub/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
+        run: pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml

.github/workflows/openhands-resolver.yml

@@ -0,0 +1,13 @@
+name: Resolve Issues with OpenHands
+
+on:
+  issues:
+    types: [labeled]
+
+jobs:
+  call-openhands-resolver:
+    uses: All-Hands-AI/openhands-resolver/.github/workflows/openhands-resolver.yml@main
+    if: github.event.label.name == 'fix-me'
+    with:
+      issue_number: ${{ github.event.issue.number }}
+    secrets: inherit

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

@@ -1,77 +1,40 @@
-name: Run Unit Tests
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+# Workflow that runs python unit tests on mac
+name: Run Python Unit Tests Mac
 
+# This job is flaky so only run it nightly
 on:
-  push:
-    branches:
-      - main
-    paths-ignore:
-      - '**/*.md'
-      - 'frontend/**'
-      - 'docs/**'
-      - 'evaluation/**'
-  pull_request:
-
-env:
-  PERSIST_SANDBOX : "false"
+  schedule:
+    - cron: '0 0 * * *'
 
 jobs:
-  fe-test:
-    runs-on: ubuntu-latest
-
-    strategy:
-      matrix:
-        node-version: [20]
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Set up Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: ${{ matrix.node-version }}
-
-      - name: Install dependencies
-        working-directory: ./frontend
-        run: npm ci
-
-      - name: Run tests and collect coverage
-        working-directory: ./frontend
-        run: npm run test:coverage
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
+  # Run python unit tests on macOS
   test-on-macos:
-    name: Test on macOS
-    runs-on: macos-12
+    name: Python Unit Tests on macOS
+    runs-on: macos-14
     env:
-      INSTALL_DOCKER: "1" # Set to '0' to skip Docker installation
+      INSTALL_DOCKER: '1' # Set to '0' to skip Docker installation
     strategy:
       matrix:
-        python-version: ["3.11"]
-
+        python-version: ['3.12']
     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: 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: |
@@ -120,47 +83,13 @@ jobs:
           # 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=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox.py and not test_runtime.py"
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-  test-on-linux:
-    name: Test on Linux
-    runs-on: ubuntu-latest
-    env:
-      INSTALL_DOCKER: "0" # Set to '0' to skip Docker installation
-    strategy:
-      matrix:
-        python-version: ["3.11"]
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation,llama-index
-
-      - name: Build Environment
-        run: make build
-
-      - name: Run Tests
-        run: poetry run pytest --forked --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox.py and not test_runtime.py"
-
+        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:

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

@@ -0,0 +1,49 @@
+# Workflow that runs python unit tests
+name: Run Python Unit Tests
+
+# The jobs in this workflow are required, so they must run at all times
+# * Always run on "main"
+# * Always run on PRs
+on:
+  push:
+    branches:
+      - 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 Linux
+  test-on-linux:
+    name: Python Unit Tests on Linux
+    runs-on: ubuntu-latest
+    env:
+      INSTALL_DOCKER: '0' # Set to '0' to skip Docker installation
+    strategy:
+      matrix:
+        python-version: ['3.12']
+    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
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'poetry'
+      - name: Install Python dependencies using Poetry
+        run: poetry install --without evaluation,llama-index
+      - name: Build Environment
+        run: make build
+      - name: Run Tests
+        run: poetry run pytest --forked --cov=openhands --cov-report=xml -svv ./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/pypi-release.yml

@@ -0,0 +1,31 @@
+# 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

@@ -1,4 +1,5 @@
-name: Use OpenDevin to Review Pull Request
+# 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:
@@ -14,24 +15,24 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v4
+    - name: Set up Docker Buildx
+      id: buildx
+      uses: docker/setup-buildx-action@v3
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
-        python-version: '3.11'
+        python-version: '3.12'
     - 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
@@ -45,19 +46,16 @@ jobs:
         echo "${{ github.event.pull_request.body }}" >> task.txt
         echo "" >> task.txt
         echo "Diff file is: ${{ github.event.pull_request.number }}.diff" >> task.txt
-
     - name: Set up environment
       run: |
         curl -sSL https://install.python-poetry.org | python3 -
         export PATH="/github/home/.local/bin:$PATH"
         poetry install --without evaluation,llama-index
         poetry run playwright install --with-deps chromium
-
-    - name: Run OpenDevin
+    - name: Run OpenHands
       env:
         LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
         LLM_MODEL: ${{ vars.LLM_MODEL }}
-        SANDBOX_BOX_TYPE: ssh
       run: |
         # Append path to launch poetry
         export PATH="/github/home/.local/bin:$PATH"
@@ -65,9 +63,8 @@ jobs:
         export PYTHONPATH=$(pwd):$PYTHONPATH
         export WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE
         export WORKSPACE_BASE=$GITHUB_WORKSPACE
-        echo -e "/exit\n" | poetry run python opendevin/core/main.py -i 50 -f task.txt
+        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: |
@@ -76,7 +73,6 @@ jobs:
           echo "non_empty=true" >> $GITHUB_OUTPUT
         fi
       shell: bash
-
     - name: Create PR review if file is non-empty
       env:
         GH_TOKEN: ${{ github.token }}

.github/workflows/solve-issue.yml

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

.github/workflows/stale.yml

@@ -1,4 +1,7 @@
+# Workflow that marks issues and PRs with no activity for 30 days with "Stale" and closes them after 7 more days of no activity
 name: 'Close stale issues'
+
+# Runs every day at 01:30
 on:
   schedule:
     - cron: '30 1 * * *'
@@ -9,21 +12,10 @@ jobs:
     steps:
       - uses: actions/stale@v9
         with:
-          # Aggressively close issues that have been explicitly labeled `age-out`
-          any-of-labels: age-out
-          stale-issue-message: 'This issue is stale because it has been open for 7 days with no activity. Remove stale label or comment or this will be closed in 1 day.'
-          close-issue-message: 'This issue was closed because it has been stalled for over 7 days with no activity.'
-          stale-pr-message: 'This PR is stale because it has been open for 7 days with no activity. Remove stale label or comment or this will be closed in 1 days.'
-          close-pr-message: 'This PR was closed because it has been stalled for over 7 days with no activity.'
-          days-before-stale: 7
-          days-before-close: 1
-
-      - uses: actions/stale@v9
-        with:
-          # Be more lenient with other issues
           stale-issue-message: 'This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
-          close-issue-message: 'This issue was closed because it has been stalled for over 30 days with no activity.'
           stale-pr-message: 'This PR is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
-          close-pr-message: 'This PR was closed because it has been stalled for over 30 days with no activity.'
           days-before-stale: 30
+          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

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

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

.gitignore

@@ -121,6 +121,7 @@ celerybeat.pid
 
 # Environments
 .env
+frontend/.env
 .venv
 env/
 venv/
@@ -169,11 +170,14 @@ evaluation/outputs
 evaluation/swe_bench/eval_workspace*
 evaluation/SWE-bench/data
 evaluation/webarena/scripts/webarena_env.sh
+evaluation/bird/data
+evaluation/gaia/data
+evaluation/gorilla/data
+evaluation/toolqa/data
 
 # frontend
 
 # dependencies
-frontend/node_modules
 frontend/.pnp
 frontend/bun.lockb
 frontend/yarn.lock
@@ -213,14 +217,14 @@ config.toml
 config.toml_
 config.toml.bak
 
-containers/agnostic_sandbox
-
 # swe-bench-eval
 image_build_logs
 run_instance_logs
 
-od_runtime_*.tar
+runtime_*.tar
 
 # docker build
 containers/runtime/Dockerfile
 containers/runtime/project.tar.gz
+containers/runtime/code
+**/node_modules/

.openhands_instructions

@@ -0,0 +1,28 @@
+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`

CONTRIBUTING.md

@@ -1,96 +1,71 @@
 # Contributing
 
-Thanks for your interest in contributing to OpenDevin! We welcome and appreciate contributions.
+Thanks for your interest in contributing to OpenHands! We welcome and appreciate contributions.
 
-## How Can I Contribute?
-
-There are many ways that you can contribute:
-
-1. **Download and use** OpenDevin, and send [issues](https://github.com/OpenDevin/OpenDevin/issues) when you encounter something that isn't working or a feature that you'd like to see.
-2. **Send feedback** after each session by [clicking the thumbs-up thumbs-down buttons](https://docs.all-hands.dev/modules/usage/feedback), so we can see where things are working and failing, and also build an open dataset for training code agents.
-3. **Improve the Codebase** by sending PRs (see details below). In particular, we have some [good first issue](https://github.com/OpenDevin/OpenDevin/labels/good%20first%20issue) issues that may be ones to start on.
-
-## Understanding OpenDevin's CodeBase
+## Understanding OpenHands's CodeBase
 
 To understand the codebase, please refer to the README in each module:
 - [frontend](./frontend/README.md)
-- [agenthub](./agenthub/README.md)
 - [evaluation](./evaluation/README.md)
-- [opendevin](./opendevin/README.md)
-    - [server](./opendevin/server/README.md)
+- [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?
+
+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 (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.
+
+## What can I build?
+Here are a few ways you can help improve the 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` directory.
+
+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`
+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/runtime.py).
+
+#### Testing
 When you write code, it is also good to write tests. Please navigate to the `tests` folder to see existing test suites.
 At the moment, we have two kinds of tests: `unit` and `integration`. Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
 
-## Sending Pull Requests to OpenDevin
+## Sending Pull Requests to OpenHands
 
-### 1. Fork the Official Repository
-Fork the [OpenDevin repository](https://github.com/OpenDevin/OpenDevin) into your own account.
-Clone your own forked repository into your local environment:
+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)
 
-```shell
-git clone git@github.com:<YOUR-USERNAME>/OpenDevin.git
-```
-
-### 2. Configure Git
-
-Set the official repository as your [upstream](https://www.atlassian.com/git/tutorials/git-forks-and-upstreams) to synchronize with the latest update in the official repository.
-Add the original repository as upstream:
-
-```shell
-cd OpenDevin
-git remote add upstream git@github.com:OpenDevin/OpenDevin.git
-```
-
-Verify that the remote is set:
-
-```shell
-git remote -v
-```
-
-You should see both `origin` and `upstream` in the output.
-
-### 3. Synchronize with Official Repository
-Synchronize latest commit with official repository before coding:
-
-```shell
-git fetch upstream
-git checkout main
-git merge upstream/main
-git push origin main
-```
-
-### 4. Set up the Development Environment
-
-We have a separate doc [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md) that tells you how to set up a development workflow.
-
-### 5. Write Code and Commit It
-
-Once you have done this, you can write code, test it, and commit it to a branch (replace `my_branch` with an appropriate name):
-
-```shell
-git checkout -b my_branch
-git add .
-git commit
-git push origin my_branch
-```
-
-### 6. Open a Pull Request
-
-* On GitHub, go to the page of your forked repository, and create a Pull Request:
-   - Click on `Branches`
-   - Click on the `...` beside your branch and click on `New pull request`
-   - Set `base repository` to `OpenDevin/OpenDevin`
-   - Set `base` to `main`
-   - Click `Create pull request`
-
-The PR should appear in [OpenDevin PRs](https://github.com/OpenDevin/OpenDevin/pulls).
-
-Then the OpenDevin team will review your code.
-
-## PR Rules
-
-### 1. Pull Request title
+### 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
@@ -109,8 +84,11 @@ For example, a PR title could be:
 - `refactor: modify package path`
 - `feat(frontend): xxxx`, where `(frontend)` means that this PR mainly focuses on the frontend component.
 
-You may also check out previous PRs in the [PR list](https://github.com/OpenDevin/OpenDevin/pulls).
+You may also check out previous PRs in the [PR list](https://github.com/All-Hands-AI/OpenHands/pulls).
 
-### 2. Pull Request description
+### 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.

CREDITS.md

@@ -1,3 +1,82 @@
+# Credits
+
+## 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.
+
+## Open Source Projects
+
+OpenHands includes and adapts the following open source projects. We are grateful for their contributions to the open source community:
+
+#### [SWE Agent](https://github.com/princeton-nlp/swe-agent)
+   - License: MIT License
+   - Description: Adapted for use in OpenHands's agent hub
+
+#### [Aider](https://github.com/paul-gauthier/aider)
+   - License: Apache License 2.0
+   - Description: AI pair programming tool. OpenHands has adapted and integrated its linter module for code-related tasks in [`agentskills utilities`](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/runtime/plugins/agent_skills/utils/aider)
+
+#### [BrowserGym](https://github.com/ServiceNow/BrowserGym)
+   - License: Apache License 2.0
+   - Description: Adapted in implementing the browsing agent
+
+
+### Reference Implementations for Evaluation Benchmarks
+OpenHands integrates code of the reference implementations for the following agent evaluation benchmarks:
+
+#### [HumanEval](https://github.com/openai/human-eval)
+   - License: MIT License
+
+#### [DSP](https://github.com/microsoft/DataScienceProblems)
+   - License: MIT License
+
+#### [HumanEvalPack](https://github.com/bigcode-project/bigcode-evaluation-harness)
+   - License: Apache License 2.0
+
+#### [AgentBench](https://github.com/THUDM/AgentBench)
+   - License: Apache License 2.0
+
+#### [SWE-Bench](https://github.com/princeton-nlp/SWE-bench)
+   - License: MIT License
+
+#### [BIRD](https://bird-bench.github.io/)
+   - License: MIT License
+   - Dataset: CC-BY-SA 4.0
+
+#### [Gorilla APIBench](https://github.com/ShishirPatil/gorilla)
+   - License: Apache License 2.0
+
+#### [GPQA](https://github.com/idavidrein/gpqa)
+   - License: MIT License
+
+#### [ProntoQA](https://github.com/asaparov/prontoqa)
+   - License: Apache License 2.0
+
+
+## Open Source licenses
+
+### MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+### BSD 3-Clause License
+
+Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+### Apache License 2.0
+
 
                                  Apache License
                            Version 2.0, January 2004
@@ -189,14 +268,45 @@
 
    Copyright [yyyy] [name of copyright owner]
 
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
 
-       http://www.apache.org/licenses/LICENSE-2.0
 
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.
+### Non-Open Source Reference Implementations:
+
+#### [MultiPL-E](https://github.com/nuprl/MultiPL-E)
+   - License: BSD 3-Clause License with Machine Learning Restriction
+
+BSD 3-Clause License with Machine Learning Restriction
+
+Copyright (c) 2022, Northeastern University, Oberlin College, Roblox Inc,
+Stevens Institute of Technology, University of Massachusetts Amherst, and
+Wellesley College.
+
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+4.  The contents of this repository may not be used as training data for any
+    machine learning model, including but not limited to neural networks.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

Development.md

@@ -1,16 +1,18 @@
 # Development Guide
-This guide is for people working on OpenDevin and editing the source code.
-If you wish to contribute your changes, check out the [CONTRIBUTING.md](https://github.com/OpenDevin/OpenDevin/blob/main/CONTRIBUTING.md) on how to clone and setup the project initially before moving on.
-Otherwise, you can clone the OpenDevin project directly.
+This guide is for people working on OpenHands and editing the source code.
+If you wish to contribute your changes, check out the [CONTRIBUTING.md](https://github.com/All-Hands-AI/OpenHands/blob/main/CONTRIBUTING.md) on how to clone and setup the project initially before moving on.
+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/) = 3.11
+* [Python](https://www.python.org/downloads/) = 3.12
 * [NodeJS](https://nodejs.org/en/download/package-manager) >= 18.17.1
 * [Poetry](https://python-poetry.org/docs/#installing-with-the-official-installer) >= 1.8
-* netcat => sudo apt-get install netcat
+* OS-specific dependencies:
+  - Ubuntu: build-essential => `sudo apt-get install build-essential`
+  - WSL: netcat => `sudo apt-get install netcat`
 
 Make sure you have all these dependencies installed before moving on to `make build`.
 
@@ -22,21 +24,21 @@ 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 3.11, nodejs, and poetry
-mamba install python=3.11
+# Install Python 3.12, nodejs, and poetry
+mamba install python=3.12
 mamba install conda-forge::nodejs
 mamba install conda-forge::poetry
 ```
 
 ### 2. Build and Setup The Environment
-Begin by building the project which includes setting up the environment and installing dependencies. This step ensures that OpenDevin is ready to run on your system:
+Begin by building the project which includes setting up the environment and installing dependencies. This step ensures that OpenHands is ready to run on your system:
 
 ```bash
 make build
 ```
 
 ### 3. Configuring the Language Model
-OpenDevin supports a diverse array of Language Models (LMs) through the powerful [litellm](https://docs.litellm.ai) library. By default, we've chosen the mighty GPT-4 from OpenAI as our go-to model, but the world is your oyster! You can unleash the potential of Anthropic's suave Claude, the enigmatic Llama, or any other LM that piques your interest.
+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:
 
@@ -44,20 +46,20 @@ To configure the LM of your choice, run:
    make setup-config
    ```
 
-   This command will prompt you to enter the LLM API key, model name, and other variables ensuring that OpenDevin is tailored to your specific needs. Note that the model name will apply only when you run headless. If you use the UI, please set the model in the UI.
+   This command will prompt you to enter the LLM API key, model name, and other variables ensuring that OpenHands is tailored to your specific needs. Note that the model name will apply only when you run headless. If you use the UI, please set the model in the UI.
 
-   Note: If you have previously run OpenDevin using the docker command, you may have already set some environmental variables in your terminal. The final configurations are set from highest to lowest priority:
+   Note: If you have previously run OpenHands using the docker command, you may have already set some environmental variables in your terminal. The final configurations are set from highest to lowest priority:
    Environment variables > config.toml variables > default variables
 
 **Note on Alternative Models:**
 Some alternative models may prove more challenging to tame than others. Fear not, brave adventurer! We shall soon unveil LLM-specific documentation to guide you on your quest.
-And if you've already mastered the art of wielding a model other than OpenAI's GPT, we encourage you to share your setup instructions with us by creating instructions and adding it [to our documentation](https://github.com/OpenDevin/OpenDevin/tree/main/docs/modules/usage/llms).
+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
-Once the setup is complete, launching OpenDevin is as simple as running a single command. This command starts both the backend and frontend servers seamlessly, allowing you to interact with OpenDevin:
+Once the setup is complete, launching OpenHands is as simple as running a single command. This command starts both the backend and frontend servers seamlessly, allowing you to interact with OpenHands:
 ```bash
 make run
 ```
@@ -75,10 +77,10 @@ make run
 
 ### 6. LLM Debugging
 If you encounter any issues with the Language Model (LM) or you're simply curious, you can inspect the actual LLM prompts and responses. To do so, export DEBUG=1 in the environment and restart the backend.
-OpenDevin will then log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
+OpenHands will then log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
 
 ### 7. Help
-Need assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenDevin.
+Need assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenHands.
 ```bash
 make help
  ```
@@ -91,9 +93,36 @@ 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. Follow these steps:
+1. Set the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
+2. Example: export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.9-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.

MANIFEST.in

@@ -0,0 +1,5 @@
+# Exclude all Python bytecode files
+global-exclude *.pyc
+
+# Exclude Python cache directories
+global-exclude __pycache__

Makefile

@@ -1,16 +1,16 @@
 SHELL=/bin/bash
-# Makefile for OpenDevin project
+# Makefile for OpenHands project
 
 # Variables
-DOCKER_IMAGE = ghcr.io/opendevin/sandbox:main
+BACKEND_HOST ?= "127.0.0.1"
 BACKEND_PORT = 3000
-BACKEND_HOST = "127.0.0.1:$(BACKEND_PORT)"
+BACKEND_HOST_PORT = "$(BACKEND_HOST):$(BACKEND_PORT)"
 FRONTEND_PORT = 3001
 DEFAULT_WORKSPACE_DIR = "./workspace"
 DEFAULT_MODEL = "gpt-4o"
 CONFIG_FILE = config.toml
 PRE_COMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
-PYTHON_VERSION = 3.11
+PYTHON_VERSION = 3.12
 
 # ANSI color codes
 GREEN=$(shell tput -Txterm setaf 2)
@@ -23,9 +23,6 @@ RESET=$(shell tput -Txterm sgr0)
 build:
 	@echo "$(GREEN)Building project...$(RESET)"
 	@$(MAKE) -s check-dependencies
-ifeq ($(INSTALL_DOCKER),)
-	@$(MAKE) -s pull-docker-image
-endif
 	@$(MAKE) -s install-python-dependencies
 	@$(MAKE) -s install-frontend-dependencies
 	@$(MAKE) -s install-pre-commit-hooks
@@ -124,11 +121,6 @@ check-poetry:
 		exit 1; \
 	fi
 
-pull-docker-image:
-	@echo "$(YELLOW)Pulling Docker image...$(RESET)"
-	@docker pull $(DOCKER_IMAGE)
-	@echo "$(GREEN)Docker image pulled successfully.$(RESET)"
-
 install-python-dependencies:
 	@echo "$(GREEN)Installing Python dependencies...$(RESET)"
 	@if [ -z "${TZ}" ]; then \
@@ -174,7 +166,7 @@ install-pre-commit-hooks:
 
 lint-backend:
 	@echo "$(YELLOW)Running linters...$(RESET)"
-	@poetry run pre-commit run --files opendevin/**/* agenthub/**/* evaluation/**/* --show-diff-on-failure --config $(PRE_COMMIT_CONFIG_PATH)
+	@poetry run pre-commit run --files openhands/**/* agenthub/**/* evaluation/**/* --show-diff-on-failure --config $(PRE_COMMIT_CONFIG_PATH)
 
 lint-frontend:
 	@echo "$(YELLOW)Running linters for frontend...$(RESET)"
@@ -198,12 +190,12 @@ build-frontend:
 # Start backend
 start-backend:
 	@echo "$(YELLOW)Starting backend...$(RESET)"
-	@poetry run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT) --reload --reload-exclude "workspace/*"
+	@poetry run uvicorn openhands.server.listen:app --host $(BACKEND_HOST) --port $(BACKEND_PORT) --reload --reload-exclude "$(shell pwd)/workspace"
 
 # Start frontend
 start-frontend:
 	@echo "$(YELLOW)Starting frontend...$(RESET)"
-	@cd frontend && VITE_BACKEND_HOST=$(BACKEND_HOST) VITE_FRONTEND_PORT=$(FRONTEND_PORT) npm run start
+	@cd frontend && VITE_BACKEND_HOST=$(BACKEND_HOST_PORT) VITE_FRONTEND_PORT=$(FRONTEND_PORT) npm run dev -- --port $(FRONTEND_PORT)
 
 # Common setup for running the app (non-callable)
 _run_setup:
@@ -213,7 +205,7 @@ _run_setup:
 	fi
 	@mkdir -p logs
 	@echo "$(YELLOW)Starting backend server...$(RESET)"
-	@poetry run uvicorn opendevin.server.listen:app --port $(BACKEND_PORT) &
+	@poetry run uvicorn openhands.server.listen:app --host $(BACKEND_HOST) --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.$(RESET)"
@@ -222,9 +214,23 @@ _run_setup:
 run:
 	@echo "$(YELLOW)Running the app...$(RESET)"
 	@$(MAKE) -s _run_setup
-	@cd frontend && echo "$(BLUE)Starting frontend with npm...$(RESET)" && npm run start -- --port $(FRONTEND_PORT)
+	@cd frontend && echo "$(BLUE)Starting frontend with npm...$(RESET)" && npm run dev -- --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)"
@@ -246,16 +252,6 @@ setup-config-prompts:
 	 workspace_dir=$${workspace_dir:-$(DEFAULT_WORKSPACE_DIR)}; \
 	 echo "workspace_base=\"$$workspace_dir\"" >> $(CONFIG_FILE).tmp
 
-	@read -p "Do you want to persist the sandbox container? [true/false] [default: false]: " persist_sandbox; \
-	 persist_sandbox=$${persist_sandbox:-false}; \
-	 if [ "$$persist_sandbox" = "true" ]; then \
-		 read -p "Enter a password for the sandbox container: " ssh_password; \
-		 echo "ssh_password=\"$$ssh_password\"" >> $(CONFIG_FILE).tmp; \
-		 echo "persist_sandbox=$$persist_sandbox" >> $(CONFIG_FILE).tmp; \
-	 else \
-		echo "persist_sandbox=$$persist_sandbox" >> $(CONFIG_FILE).tmp; \
-	 fi
-
 	@echo "" >> $(CONFIG_FILE).tmp
 
 	@echo "[llm]" >> $(CONFIG_FILE).tmp
@@ -279,6 +275,10 @@ 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; \
@@ -295,10 +295,20 @@ 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...$(RESET)"
-	@rm -rf opendevin/.cache
+	@rm -rf openhands/.cache
 	@echo "$(GREEN)Caches cleaned up successfully.$(RESET)"
 
 # Help
@@ -307,13 +317,16 @@ help:
 	@echo "Targets:"
 	@echo "  $(GREEN)build$(RESET)               - Build project, including environment setup and dependencies."
 	@echo "  $(GREEN)lint$(RESET)                - Run linters on the project."
-	@echo "  $(GREEN)setup-config$(RESET)        - Setup the configuration for OpenDevin by providing LLM API key,"
+	@echo "  $(GREEN)setup-config$(RESET)        - Setup the configuration for OpenHands by providing LLM API key,"
 	@echo "                        LLM Model name, and workspace directory."
-	@echo "  $(GREEN)start-backend$(RESET)       - Start the backend server for the OpenDevin project."
-	@echo "  $(GREEN)start-frontend$(RESET)      - Start the frontend server for the OpenDevin project."
-	@echo "  $(GREEN)run$(RESET)                 - Run the OpenDevin application, starting both backend and frontend servers."
+	@echo "  $(GREEN)start-backend$(RESET)       - Start the backend server for the OpenHands project."
+	@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 pull-docker-image install-python-dependencies install-frontend-dependencies install-pre-commit-hooks lint start-backend start-frontend run run-wsl setup-config setup-config-prompts help
+.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

@@ -1,124 +1,109 @@
 <a name="readme-top"></a>
 
-<!--
-*** Thanks for checking out the Best-README-Template. If you have a suggestion
-*** that would make this better, please fork the repo and create a pull request
-*** or simply open an issue with the tag "enhancement".
-*** Don't forget to give the project a star!
-*** Thanks again! Now go create something AMAZING! :D
--->
+<div align="center">
+  <img src="./docs/static/img/logo.png" alt="Logo" width="200">
+  <h1 align="center">OpenHands: Code Less, Make More</h1>
+</div>
 
-<!-- PROJECT SHIELDS -->
-<!--
-*** I'm using markdown "reference style" links for readability.
-*** Reference links are enclosed in brackets [ ] instead of parentheses ( ).
-*** See the bottom of this document for the declaration of the reference variables
-*** for contributors-url, forks-url, etc. This is an optional, concise syntax you may use.
-*** https://www.markdownguide.org/basic-syntax/#reference-style-links
--->
 
 <div align="center">
-  <a href="https://github.com/OpenDevin/OpenDevin/graphs/contributors"><img src="https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge&color=blue" alt="Contributors"></a>
-  <a href="https://github.com/OpenDevin/OpenDevin/network/members"><img src="https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge&color=blue" alt="Forks"></a>
-  <a href="https://github.com/OpenDevin/OpenDevin/stargazers"><img src="https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge&color=blue" alt="Stargazers"></a>
-  <a href="https://github.com/OpenDevin/OpenDevin/issues"><img src="https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge&color=blue" alt="Issues"></a>
-  <a href="https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE"><img src="https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge&color=blue" alt="MIT License"></a>
+  <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/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/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>
   <br/>
-  <a href="https://join.slack.com/t/opendevin/shared_invite/zt-2i1iqdag6-bVmvamiPA9EZUu7oCO6KhA"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
+  <a href="https://join.slack.com/t/opendevin/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://codecov.io/github/opendevin/opendevin?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/opendevin/opendevin?style=for-the-badge"></a>
-</div>
-
-<!-- PROJECT LOGO -->
-<div align="center">
-  <img src="./docs/static/img/logo.png" alt="Logo" width="200" height="200">
-  <h1 align="center">OpenDevin: Code Less, Make More</h1>
-  <a href="https://docs.all-hands.dev/modules/usage/intro"><img src="https://img.shields.io/badge/Documentation-OpenDevin-blue?logo=googledocs&logoColor=white&style=for-the-badge" alt="Check out the documentation"></a>
-  <a href="https://arxiv.org/abs/2407.16741"><img src="https://img.shields.io/badge/Paper-%20on%20Arxiv-red?logo=arxiv&style=for-the-badge" alt="Paper on Arxiv"></a>
+  <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://huggingface.co/spaces/OpenDevin/evaluation"><img src="https://img.shields.io/badge/Evaluation-Benchmark%20on%20HF%20Space-green?logo=huggingface&style=for-the-badge" alt="Evaluation Benchmark"></a>
+  <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>
 </div>
-<hr>
 
-Welcome to OpenDevin, a platform for autonomous software engineers, powered by AI and LLMs.
+Welcome to OpenHands (formerly OpenDevin), a platform for software development agents powered by AI.
 
-OpenDevin agents collaborate with human developers to write code, fix bugs, and ship features.
+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.
+
+Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or jump to the [Quick Start](#-quick-start).
 
 ![App screenshot](./docs/static/img/screenshot.png)
 
-## ⚡ Getting Started
-OpenDevin works best with Docker version 26.0.0+ (Docker Desktop 4.31.0+).
-You must be using Linux, Mac OS, or WSL on Windows.
+## ⚡ Quick Start
 
-To start OpenDevin in a docker container, run the following commands in your terminal:
+The easiest way to run OpenHands is in Docker. You can change `WORKSPACE_BASE` below to
+point OpenHands to existing code that you'd like to modify.
 
-> [!WARNING]
-> When you run the following command, files in `./workspace` may be modified or deleted.
+See the [Installation](https://docs.all-hands.dev/modules/usage/installation) guide for
+system requirements and more information.
 
 ```bash
-WORKSPACE_BASE=$(pwd)/workspace
-docker run -it \
-    --pull=always \
+export WORKSPACE_BASE=$(pwd)/workspace
+
+docker pull ghcr.io/all-hands-ai/runtime:0.11-nikolaik
+
+docker run -it --pull=always \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.11-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -v $WORKSPACE_BASE:/opt/workspace_base \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
-    --name opendevin-app-$(date +%Y%m%d%H%M%S) \
-    ghcr.io/opendevin/opendevin
+    --name openhands-app-$(date +%Y%m%d%H%M%S) \
+    ghcr.io/all-hands-ai/openhands:0.11
 ```
 
-> [!NOTE]
-> By default, this command pulls the `latest` tag, which represents the most recent release of OpenDevin. You have other options as well:
-> - For a specific release version, use `ghcr.io/opendevin/opendevin:<OpenDevin_version>` (replace <OpenDevin_version> with the desired version number).
-> - For the most up-to-date development version, use `ghcr.io/opendevin/opendevin:main`. This version may be **(unstable!)** and is recommended for testing or development purposes only.
->
-> Choose the tag that best suits your needs based on stability requirements and desired features.
+You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
 
-You'll find OpenDevin running at [http://localhost:3000](http://localhost:3000) with access to `./workspace`. To have OpenDevin operate on your code, place it in `./workspace`.
-OpenDevin will only have access to this workspace folder. The rest of your system will not be affected as it runs in a secured docker sandbox.
+You'll need a model provider and API key. One option that works well: [Claude 3.5 Sonnet](https://www.anthropic.com/api), but you have [many options](https://docs.all-hands.dev/modules/usage/llms).
 
-Upon opening OpenDevin, you must select the appropriate `Model` and enter the `API Key` within the settings that should pop up automatically. These can be set at any time by selecting
-the `Settings` button (gear icon) in the UI. If the required `Model` does not exist in the list, you can manually enter it in the text box.
+---
 
-For the development workflow, see [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md).
+You can also run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
+or as an [interactive CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode).
 
-Are you having trouble? Check out our [Troubleshooting Guide](https://docs.all-hands.dev/modules/usage/troubleshooting).
+Visit [Installation](https://docs.all-hands.dev/modules/usage/installation) for more information and setup instructions.
 
-## 🚀 Documentation
+If you want to modify the OpenHands source code, check out [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
 
-To learn more about the project, and for tips on using OpenDevin,
-**check out our [documentation](https://docs.all-hands.dev/modules/usage/intro)**.
+Having issues? The [Troubleshooting Guide](https://docs.all-hands.dev/modules/usage/troubleshooting) can help.
 
-There you'll find resources on how to use different LLM providers (like ollama and Anthropic's Claude),
+## 📖 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)**.
+
+There you'll find resources on how to use different LLM providers,
 troubleshooting resources, and advanced configuration options.
 
 ## 🤝 How to Contribute
 
-OpenDevin is a community-driven project, and we welcome contributions from everyone.
+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:
 
 - **Code Contributions:** Help us develop new agents, core functionality, the frontend and other interfaces, or sandboxing solutions.
 - **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in evaluating the models, or suggest improvements.
-- **Feedback and Testing:** Use the OpenDevin toolset, report bugs, suggest features, or provide feedback on usability.
+- **Feedback and Testing:** Use the OpenHands toolset, report bugs, suggest features, or provide feedback on usability.
 
 For details, please check [CONTRIBUTING.md](./CONTRIBUTING.md).
 
 ## 🤖 Join Our Community
 
-Whether you're a developer, a researcher, or simply enthusiastic about OpenDevin, we'd love to have you in our community.
+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/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA) - Here we talk about research, architecture, and future development.
+- [Slack workspace](https://join.slack.com/t/opendevin/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
 
 <p align="center">
-  <a href="https://star-history.com/#OpenDevin/OpenDevin&Date">
-    <img src="https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date" width="500" alt="Star History Chart">
+  <a 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">
   </a>
 </p>
 
@@ -126,27 +111,22 @@ Let's make software engineering better together!
 
 Distributed under the MIT License. See [`LICENSE`](./LICENSE) for more information.
 
-[contributors-shield]: https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge
-[contributors-url]: https://github.com/OpenDevin/OpenDevin/graphs/contributors
-[forks-shield]: https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge
-[forks-url]: https://github.com/OpenDevin/OpenDevin/network/members
-[stars-shield]: https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge
-[stars-url]: https://github.com/OpenDevin/OpenDevin/stargazers
-[issues-shield]: https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge
-[issues-url]: https://github.com/OpenDevin/OpenDevin/issues
-[license-shield]: https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge
-[license-url]: https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE
+## 🙏 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.
+
+For a list of open source projects and licenses used in OpenHands, please see our [CREDITS.md](./CREDITS.md) file.
 
 ## 📚 Cite
 
 ```
-@misc{opendevin,
-      title={{OpenDevin: An Open Platform for AI Software Developers as Generalist Agents}}, 
+@misc{openhands,
+      title={{OpenHands: An Open Platform for AI Software Developers as Generalist Agents}},
       author={Xingyao Wang and Boxuan Li and Yufan Song and Frank F. Xu and Xiangru Tang and Mingchen Zhuge and Jiayi Pan and Yueqi Song and Bowen Li and Jaskirat Singh and Hoang H. Tran and Fuqiang Li and Ren Ma and Mingzhang Zheng and Bill Qian and Yanjun Shao and Niklas Muennighoff and Yizhe Zhang and Binyuan Hui and Junyang Lin and Robert Brennan and Hao Peng and Heng Ji and Graham Neubig},
       year={2024},
       eprint={2407.16741},
       archivePrefix={arXiv},
       primaryClass={cs.SE},
-      url={https://arxiv.org/abs/2407.16741}, 
+      url={https://arxiv.org/abs/2407.16741},
 }
 ```

agenthub/README.md

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

agenthub/browsing_agent/__init__.py

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

agenthub/browsing_agent/response_parser.py

@@ -1,88 +0,0 @@
-import ast
-
-from opendevin.controller.action_parser import ActionParser, ResponseParser
-from opendevin.core.logger import opendevin_logger as logger
-from opendevin.events.action import (
-    Action,
-    BrowseInteractiveAction,
-)
-
-
-class BrowsingResponseParser(ResponseParser):
-    def __init__(self):
-        # Need to pay attention to the item order in self.action_parsers
-        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

@@ -1,29 +0,0 @@
-# CodeAct Agent Framework
-
-This folder implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.01030), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a unified **code** action space for both *simplicity* and *performance* (see paper for more details).
-
-The conceptual idea is illustrated below. At each turn, the agent can:
-
-1. **Converse**: Communicate with humans in natural language to ask for clarification, confirmation, etc.
-2. **CodeAct**: Choose to perform the task by executing code
-   - Execute any valid Linux `bash` command
-   - Execute any valid `Python` code with [an interactive Python interpreter](https://ipython.org/). This is simulated through `bash` command, see plugin system below for more details.
-
-![image](https://github.com/OpenDevin/OpenDevin/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
-
-## Plugin System
-
-To make the CodeAct agent more powerful with only access to `bash` action space, CodeAct agent leverages OpenDevin's plugin system:
-- [Jupyter plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/jupyter): for IPython execution via bash command
-- [SWE-agent tool plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/swe_agent_commands): Powerful bash command line tools for software development tasks introduced by [swe-agent](https://github.com/princeton-nlp/swe-agent).
-
-## Demo
-
-https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
-
-*Example of CodeActAgent with `gpt-4-turbo-2024-04-09` performing a data science task (linear regression)*
-
-## Work-in-progress & Next step
-
-[] Support web-browsing
-[] Complete the workflow for CodeAct agent to submit Github PRs

agenthub/codeact_agent/__init__.py

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

agenthub/codeact_agent/codeact_agent.py

@@ -1,245 +0,0 @@
-from agenthub.codeact_agent.action_parser import CodeActResponseParser
-from agenthub.codeact_agent.prompt import (
-    COMMAND_DOCS,
-    EXAMPLES,
-    GITHUB_MESSAGE,
-    SYSTEM_PREFIX,
-    SYSTEM_SUFFIX,
-)
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.events.action import (
-    Action,
-    AgentDelegateAction,
-    AgentFinishAction,
-    CmdRunAction,
-    IPythonRunCellAction,
-    MessageAction,
-)
-from opendevin.events.observation import (
-    AgentDelegateObservation,
-    CmdOutputObservation,
-    IPythonRunCellObservation,
-)
-from opendevin.events.observation.observation import Observation
-from opendevin.events.serialization.event import truncate_content
-from opendevin.llm.llm import LLM
-from opendevin.runtime.plugins import (
-    AgentSkillsRequirement,
-    JupyterRequirement,
-    PluginRequirement,
-)
-from opendevin.runtime.tools import RuntimeTool
-
-ENABLE_GITHUB = True
-
-
-# FIXME: We can tweak these two settings to create MicroAgents specialized toward different area
-def get_system_message() -> str:
-    if ENABLE_GITHUB:
-        return f'{SYSTEM_PREFIX}\n{GITHUB_MESSAGE}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
-    else:
-        return f'{SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
-
-
-def get_in_context_example() -> str:
-    return EXAMPLES
-
-
-class CodeActAgent(Agent):
-    VERSION = '1.8'
-    """
-    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/OpenDevin/OpenDevin/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
-
-    ### Plugin System
-
-    To make the CodeAct agent more powerful with only access to `bash` action space, CodeAct agent leverages OpenDevin's plugin system:
-    - [Jupyter plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/jupyter): for IPython execution via bash command
-    - [SWE-agent tool plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/swe_agent_commands): Powerful bash command line tools for software development tasks introduced by [swe-agent](https://github.com/princeton-nlp/swe-agent).
-
-    ### Demo
-
-    https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
-
-    *Example of CodeActAgent with `gpt-4-turbo-2024-04-09` performing a data science task (linear regression)*
-
-    ### Work-in-progress & Next step
-
-    [] Support web-browsing
-    [] Complete the workflow for CodeAct agent to submit Github PRs
-
-    """
-
-    sandbox_plugins: list[PluginRequirement] = [
-        # NOTE: AgentSkillsRequirement need to go before JupyterRequirement, since
-        # AgentSkillsRequirement provides a lot of Python functions,
-        # and it needs to be initialized before Jupyter for Jupyter to use those functions.
-        AgentSkillsRequirement(),
-        JupyterRequirement(),
-    ]
-    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
-
-    system_message: str = get_system_message()
-    in_context_example: str = f"Here is an example of how you can interact with the environment for task solving:\n{get_in_context_example()}\n\nNOW, LET'S START!"
-
-    action_parser = CodeActResponseParser()
-
-    def __init__(
-        self,
-        llm: LLM,
-    ) -> None:
-        """Initializes a new instance of the CodeActAgent class.
-
-        Parameters:
-        - llm (LLM): The llm to be used by this agent
-        """
-        super().__init__(llm)
-        self.reset()
-
-    def action_to_str(self, action: Action) -> str:
-        if isinstance(action, CmdRunAction):
-            return (
-                f'{action.thought}\n<execute_bash>\n{action.command}\n</execute_bash>'
-            )
-        elif isinstance(action, IPythonRunCellAction):
-            return f'{action.thought}\n<execute_ipython>\n{action.code}\n</execute_ipython>'
-        elif isinstance(action, 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) -> dict[str, str] | None:
-        if (
-            isinstance(action, AgentDelegateAction)
-            or isinstance(action, CmdRunAction)
-            or isinstance(action, IPythonRunCellAction)
-            or isinstance(action, MessageAction)
-            or (isinstance(action, AgentFinishAction) and action.source == 'agent')
-        ):
-            return {
-                'role': 'user' if action.source == 'user' else 'assistant',
-                'content': self.action_to_str(action),
-            }
-        return None
-
-    def get_observation_message(self, obs: Observation) -> dict[str, str] | None:
-        max_message_chars = self.llm.config.max_message_chars
-        if isinstance(obs, CmdOutputObservation):
-            content = 'OBSERVATION:\n' + truncate_content(
-                obs.content, max_message_chars
-            )
-            content += (
-                f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]'
-            )
-            return {'role': 'user', 'content': content}
-        elif isinstance(obs, IPythonRunCellObservation):
-            content = 'OBSERVATION:\n' + obs.content
-            # replace base64 images with a placeholder
-            splitted = content.split('\n')
-            for i, line in enumerate(splitted):
-                if '![image](data:image/png;base64,' in line:
-                    splitted[i] = (
-                        '![image](data:image/png;base64, ...) already displayed to user'
-                    )
-            content = '\n'.join(splitted)
-            content = truncate_content(content, max_message_chars)
-            return {'role': 'user', 'content': content}
-        elif isinstance(obs, AgentDelegateObservation):
-            content = 'OBSERVATION:\n' + truncate_content(
-                str(obs.outputs), max_message_chars
-            )
-            return {'role': 'user', 'content': content}
-        return None
-
-    def reset(self) -> None:
-        """Resets the CodeAct Agent."""
-        super().reset()
-
-    def step(self, state: State) -> Action:
-        """Performs one step using the CodeAct Agent.
-        This includes gathering info on previous steps and prompting the model to make a command to execute.
-
-        Parameters:
-        - state (State): used to get updated info
-
-        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: list[dict[str, str]] = self._get_messages(state)
-
-        response = self.llm.completion(
-            messages=messages,
-            stop=[
-                '</execute_ipython>',
-                '</execute_bash>',
-                '</execute_browse>',
-            ],
-            temperature=0.0,
-        )
-        return self.action_parser.parse(response)
-
-    def _get_messages(self, state: State) -> list[dict[str, str]]:
-        messages = [
-            {'role': 'system', 'content': self.system_message},
-            {'role': 'user', 'content': self.in_context_example},
-        ]
-
-        for event in state.history.get_events():
-            # create a regular message from an event
-            if isinstance(event, Action):
-                message = self.get_action_message(event)
-            elif isinstance(event, Observation):
-                message = self.get_observation_message(event)
-            else:
-                raise ValueError(f'Unknown event type: {type(event)}')
-
-            # add regular message
-            if message:
-                # handle error if the message is the SAME role as the previous message
-                # litellm.exceptions.BadRequestError: litellm.BadRequestError: OpenAIException - Error code: 400 - {'detail': 'Only supports u/a/u/a/u...'}
-                # there should not have two consecutive messages from the same role
-                if messages and messages[-1]['role'] == message['role']:
-                    messages[-1]['content'] += '\n\n' + message['content']
-                else:
-                    messages.append(message)
-
-        # the latest user message is important:
-        # we want to remind the agent of the environment constraints
-        latest_user_message = next(
-            (m for m in reversed(messages) if m['role'] == 'user'), None
-        )
-
-        # add a reminder to the prompt
-        if latest_user_message:
-            latest_user_message['content'] += (
-                f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task. When finished reply with <finish></finish>'
-            )
-
-        return messages

agenthub/codeact_agent/prompt.py

@@ -1,275 +0,0 @@
-from opendevin.runtime.plugins import AgentSkillsRequirement
-
-_AGENT_SKILLS_DOCS = AgentSkillsRequirement.documentation
-
-COMMAND_DOCS = (
-    '\nApart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:\n'
-    f'{_AGENT_SKILLS_DOCS}'
-    "Please note that THE `edit_file_by_replace`, `append_file` and `insert_content_at_line` FUNCTIONS REQUIRE PROPER INDENTATION. If the assistant would like to add the line '        print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run."
-)
-
-# ======= SYSTEM MESSAGE =======
-MINIMAL_SYSTEM_PREFIX = """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
-The assistant can use an interactive Python (Jupyter Notebook) environment, executing code with <execute_ipython>.
-<execute_ipython>
-print("Hello World!")
-</execute_ipython>
-The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
-
-For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
-Important, however: do not run interactive commands. You do not have access to stdin.
-Also, you need to handle commands that may run indefinitely and not return a result. For such cases, you should redirect the output to a file and run the command in the background to avoid blocking the execution.
-For example, to run a Python script that might run indefinitely without returning immediately, you can use the following format: <execute_bash> python3 app.py > server.log 2>&1 & </execute_bash>
-Also, if a command execution result saying like: Command: "npm start" timed out. Sending SIGINT to the process, you should also retry with running the command in the background.
-"""
-
-BROWSING_PREFIX = """The assistant can browse the Internet with <execute_browse> and </execute_browse>.
-For example, <execute_browse> Tell me the usa's president using google search </execute_browse>.
-Or <execute_browse> Tell me what is in http://example.com </execute_browse>.
-"""
-PIP_INSTALL_PREFIX = """The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them."""
-
-SYSTEM_PREFIX = MINIMAL_SYSTEM_PREFIX + BROWSING_PREFIX + PIP_INSTALL_PREFIX
-
-GITHUB_MESSAGE = """To interact with GitHub, use the $GITHUB_TOKEN environment variable.
-For example, to push a branch `my_branch` to the GitHub repo `owner/repo`:
-<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
-If $GITHUB_TOKEN is not set, ask the user to set it."""
-
-SYSTEM_SUFFIX = """Responses should be concise.
-The assistant should attempt fewer things at a time instead of putting too many commands OR too much code in one "execute" block.
-Include ONLY ONE <execute_ipython>, <execute_bash>, or <execute_browse> per response, unless the assistant is finished with the task or needs more input or action from the user in order to proceed.
-If the assistant is finished with the task you MUST include <finish></finish> in your response.
-IMPORTANT: Execute code using <execute_ipython>, <execute_bash>, or <execute_browse> whenever possible.
-When handling files, try to use full paths and pwd to avoid errors.
-"""
-
-
-# ======= EXAMPLE MESSAGE =======
-EXAMPLES = """
---- START OF EXAMPLE ---
-
-USER: Create a list of numbers from 1 to 10, and display them in a web page at port 5000.
-
-ASSISTANT:
-Sure! Let me create a Python file `app.py`:
-<execute_ipython>
-create_file('app.py')
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[File: /workspace/app.py (1 lines total)]
-(this is the beginning of the file)
-1|
-(this is the end of the file)
-[File app.py created.]
-
-ASSISTANT:
-Now I will write the Python code for starting a web server and save it to the file `app.py`:
-<execute_ipython>
-EDITED_CODE=\"\"\"from flask import Flask
-app = Flask(__name__)
-
-@app.route('/')
-def index():
-    numbers = list(range(1, 11))
-    return str(numbers)
-
-if __name__ == '__main__':
-    app.run(port=5000)\"\"\"
-
-insert_content_at_line(
-  'app.py',
-  1,
-  EDITED_CODE,
-)
-</execute_ipython>
-
-USER:
-OBSERVATION:
-(this is the beginning of the file)
-1|from flask import Flask
-2|app = Flask(__name__)
-3|
-4|@app.route('/')
-5|def index():
-6|    numbers = list(range(1, 11))
-7|    return str(numbers)
-8|
-9|if __name__ == '__main__':
-10|    app.run(port=5000)
-(this is the end of the file)
-[File updated (edited at line 1). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
-
-ASSISTANT:
-I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you:
-<execute_bash>
-python3 app.py > server.log 2>&1 &
-</execute_bash>
-
-USER:
-OBSERVATION:
-[1] 121[1]+  Exit 1                  python3 app.py > server.log 2>&1
-
-ASSISTANT: Looks like the server is running with PID 121 then crashed. Let me check the server log:
-<execute_bash>
-cat server.log
-</execute_bash>
-
-USER:
-OBSERVATION:
-Traceback (most recent call last):
-  File "/workspace/app.py", line 2, in <module>
-    from flask import Flask
-ModuleNotFoundError: No module named 'flask'
-
-ASSISTANT:
-It seems that Flask is not installed. Let me install Flask for you:
-<execute_bash>
-pip install flask
-</execute_bash>
-
-USER:
-OBSERVATION:
-Defaulting to user installation because normal site-packages is not writeable
-Collecting flask
-  Using cached flask-3.0.3-py3-none-any.whl (101 kB)
-Collecting blinker>=1.6.2
-  Using cached blinker-1.7.0-py3-none-any.whl (13 kB)
-Collecting Werkzeug>=3.0.0
-  Using cached werkzeug-3.0.2-py3-none-any.whl (226 kB)
-Collecting click>=8.1.3
-  Using cached click-8.1.7-py3-none-any.whl (97 kB)
-Collecting itsdangerous>=2.1.2
-  Using cached itsdangerous-2.2.0-py3-none-any.whl (16 kB)
-Requirement already satisfied: Jinja2>=3.1.2 in /home/opendevin/.local/lib/python3.10/site-packages (from flask) (3.1.3)
-Requirement already satisfied: MarkupSafe>=2.0 in /home/opendevin/.local/lib/python3.10/site-packages (from Jinja2>=3.1.2->flask) (2.1.5)
-Installing collected packages: Werkzeug, itsdangerous, click, blinker, flask
-Successfully installed Werkzeug-3.0.2 blinker-1.7.0 click-8.1.7 flask-3.0.3 itsdangerous-2.2.0
-
-ASSISTANT:
-Now that Flask is installed, let me run the Python file again:
-<execute_bash>
-python3 app.py > server.log 2>&1 &
-</execute_bash>
-
-USER:
-OBSERVATION:
-[1] 124
-
-ASSISTANT:
-Let me check the server log again:
-<execute_bash>
-cat server.log
-</execute_bash>
-
-USER:
-OBSERVATION:
-* Serving Flask app 'app'
- * Debug mode: off
-WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
- * Running on http://127.0.0.1:5000
-Press CTRL+C to quit
-
-ASSISTANT:
-The server is running on port 5000 with PID 124. You can access the list of numbers by visiting http://127.0.0.1:5000. If you have any further questions, feel free to ask!
-
-USER: Now browse the newly started server's homepage and show me the content.
-
-ASSISTANT:
-Sure! Let me browse the server's homepage at http://127.0.0.1:5000:
-<execute_browse>
-Get the content on "http://127.0.0.1:5000"
-</execute_browse>
-
-USER:
-OBSERVATION:
-[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
-
-ASSISTANT:
-The content of the server's homepage is "[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]". If you have any further questions, feel free to ask!
-
-USER: Now kill the server, make it display the numbers in a table format.
-
-ASSISTANT:
-Sure! Let me stop the server first:
-<execute_bash>
-kill 124
-</execute_bash>
-
-USER:
-OBSERVATION:
-[1]+  Terminated              python3 app.py > server.log 2>&1
-
-ASSISTANT:
-The server has been stopped. Let me open the Python file and modify it.
-<execute_ipython>
-open_file('app.py')
-</execute_ipython>
-
-USER:
-[File: /workspace/app.py (10 lines total)]
-(this is the beginning of the file)
-1|from flask import Flask
-2|app = Flask(__name__)
-3|
-4|@app.route('/')
-5|def index():
-6|    numbers = list(range(1, 11))
-7|    return str(numbers)
-8|
-9|if __name__ == '__main__':
-10|    app.run(port=5000)
-(this is the end of the file)
-
-ASSISTANT:
-I should edit the file to display the numbers in a table format. I should include correct indentation. Let me update the file:
-<execute_ipython>
-edit_file_by_replace(
-  'app.py',
-  to_replace="    return str(numbers)",
-  new_content="    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'",
-)
-</execute_ipython>
-
-USER:
-Observation:
-[File: /workspace/app.py (10 lines total after edit)]
-(this is the beginning of the file)
-1|from flask import Flask
-2|app = Flask(__name__)
-3|
-4|@app.route('/')
-5|def index():
-6|    numbers = list(range(1, 11))
-7|    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
-8|
-9|if __name__ == '__main__':
-10|    app.run(port=5000)
-(this is the end of the file)
-[File updated (edited at line 7). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
-
-ASSISTANT:
-Running the updated file:
-<execute_bash>
-python3 app.py > server.log 2>&1 &
-</execute_bash>
-
-USER:
-Observation:
-[1] 126
-
-ASSISTANT:
-The server is running on port 5000 with PID 126. You can access the list of numbers in a table format by visiting http://127.0.0.1:5000. Let me know if you have any further requests!
-<finish></finish>
-
---- END OF EXAMPLE ---
-"""
-
-INVALID_INPUT_MESSAGE = (
-    "I don't understand your input. \n"
-    'For bash commands, use <execute_bash> YOUR_COMMAND </execute_bash>.\n'
-    'For Python code, use <execute_ipython> YOUR_CODE </execute_ipython>.\n'
-    'For browsing, use <execute_browse> YOUR_COMMAND </execute_browse>.\n'
-)

agenthub/codeact_swe_agent/__init__.py

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

agenthub/delegator_agent/__init__.py

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

agenthub/dummy_agent/__init__.py

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

agenthub/planner_agent/__init__.py

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

build.sh

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

compose.yml

@@ -0,0 +1,22 @@
+#
+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:0.9-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

@@ -1,4 +1,4 @@
-###################### OpenDevin Configuration Example ######################
+###################### OpenHands Configuration Example ######################
 #
 # All settings have default values, so you only need to uncomment and
 # modify what you want to change
@@ -13,6 +13,10 @@
 # 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"
 
@@ -28,6 +32,9 @@ workspace_base = "./workspace"
 # Enable saving and restoring the session when run from CLI
 #enable_cli_session = false
 
+# Path to store trajectories
+#trajectories_path="./trajectories"
+
 # File store path
 #file_store_path = "/tmp/file_store"
 
@@ -55,28 +62,24 @@ workspace_base = "./workspace"
 # Path to rewrite the workspace mount path to
 #workspace_mount_rewrite = ""
 
-# Persist the sandbox
-persist_sandbox = false
-
-# Run as devin
-#run_as_devin = true
+# Run as openhands
+#run_as_openhands = true
 
 # Runtime environment
-#runtime = "server"
-
-# SSH hostname for the sandbox
-#ssh_hostname = "localhost"
-
-# SSH password for the sandbox
-#ssh_password = ""
-
-# SSH port for the sandbox
-#ssh_port = 63710
-
+#runtime = "eventstream"
 
 # 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
@@ -116,7 +119,7 @@ api_key = "your-api-key"
 #embedding_deployment_name = ""
 
 # Embedding model to use
-embedding_model = ""
+embedding_model = "local"
 
 # Maximum number of characters in an observation's content
 #max_message_chars = 10000
@@ -130,14 +133,31 @@ embedding_model = ""
 # Model to use
 model = "gpt-4o"
 
-# Number of retries to attempt
-#num_retries = 5
+# 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
 
-# Retry maximum wait time
-#retry_max_wait = 60
+# Maximum wait time (in seconds) between retry attempts
+# This caps the exponential backoff to prevent excessively long
+#retry_max_wait = 120
 
-# Retry minimum wait time
-#retry_min_wait = 3
+# 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 = ""
 
 # Temperature for the API
 #temperature = 0.0
@@ -146,14 +166,33 @@ model = "gpt-4o"
 #timeout = 0
 
 # Top p for the API
-#top_p = 0.5
+#top_p = 1.0
 
-[llm.gpt3]
-# API key to use
+# If model is vision capable, this option allows to disable image processing (useful for cost reduction).
+#disable_vision = true
+
+# maximum number of messages in a conversation, after which they are truncated or summarized
+# max_conversation_window = 10
+
+# number of results when recalling message history
+# conversation_top_k = 5
+
+# fraction of the conversation window to summarize
+# message_summary_trunc_tokens_fraction = 0.75
+
+# summary LLM
+[llm.summary]
+model = "deepseek"
+
+# default LLM
+[llm.default]
+model = "claude"
+
+
+[llm.gpt4o-mini]
 api_key = "your-api-key"
+model = "gpt-4o"
 
-# Model to use
-model = "gpt-3.5"
 
 #################################### Agent ###################################
 # Configuration for agents (group name starts with 'agent')
@@ -162,14 +201,17 @@ model = "gpt-3.5"
 # 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 = 2
+#memory_max_threads = 3
 
 # LLM config group to use
-#llm_config = 'llm'
+#llm_config = 'your-llm-config-group'
 
 [agent.RepoExplorerAgent]
 # Example: use a cheaper model for RepoExplorerAgent to reduce cost, especially
@@ -183,14 +225,11 @@ llm_config = 'gpt3'
 # Sandbox timeout in seconds
 #timeout = 120
 
-# Sandbox type (ssh, e2b, local)
-#box_type = "ssh"
-
 # Sandbox user ID
 #user_id = 1000
 
 # Container image to use for the sandbox
-#container_image = "ghcr.io/opendevin/sandbox:main"
+#base_container_image = "nikolaik/python-nodejs:python3.12-nodejs22"
 
 # Use host network
 #use_host_network = false
@@ -198,6 +237,29 @@ 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
+
+# The security analyzer to use
+#security_analyzer = ""
+
 #################################### Eval ####################################
 # Configuration for the evaluation, please refer to the specific evaluation
 # plugin for the available options

containers/README.md

@@ -7,6 +7,6 @@ by the `ghcr.yml` workflow.
 ## Building Manually
 
 ```bash
-docker build -f containers/app/Dockerfile -t opendevin .
+docker build -f containers/app/Dockerfile -t openhands .
 docker build -f containers/sandbox/Dockerfile -t sandbox .
 ```

containers/app/Dockerfile

@@ -1,4 +1,4 @@
-ARG OPEN_DEVIN_BUILD_VERSION=dev
+ARG OPENHANDS_BUILD_VERSION=dev
 FROM node:21.7.2-bookworm-slim AS frontend-builder
 
 WORKDIR /app
@@ -8,7 +8,7 @@ RUN npm install -g npm@10.5.1
 RUN npm ci
 
 COPY ./frontend ./
-RUN npm run make-i18n && npm run build
+RUN npm run build
 
 FROM python:3.12.3-slim AS backend-builder
 
@@ -28,55 +28,66 @@ COPY ./pyproject.toml ./poetry.lock ./
 RUN touch README.md
 RUN export POETRY_CACHE_DIR && poetry install --without evaluation,llama-index --no-root && rm -rf $POETRY_CACHE_DIR
 
-FROM python:3.12.3-slim AS runtime
+FROM python:3.12.3-slim AS openhands-app
 
 WORKDIR /app
 
-ENV RUN_AS_DEVIN=true
+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 OPENDEVIN_USER_ID=42420
+ENV OPENHANDS_USER_ID=42420
+ENV SANDBOX_LOCAL_RUNTIME_URL=http://host.docker.internal
 ENV USE_HOST_NETWORK=false
-ENV SSH_HOSTNAME=host.docker.internal
 ENV WORKSPACE_BASE=/opt/workspace_base
-ENV OPEN_DEVIN_BUILD_VERSION=$OPEN_DEVIN_BUILD_VERSION
+ENV OPENHANDS_BUILD_VERSION=$OPENHANDS_BUILD_VERSION
 RUN mkdir -p $WORKSPACE_BASE
 
 RUN apt-get update -y \
     && apt-get install -y curl ssh sudo
 
-RUN sed -i 's/^UID_MIN.*/UID_MIN 499/' /etc/login.defs # Default is 1000, but OSX is often 501
-RUN sed -i 's/^UID_MAX.*/UID_MAX 1000000/' /etc/login.defs # Default is 60000, but we've seen up to 200000
+# Default is 1000, but OSX is often 501
+RUN sed -i 's/^UID_MIN.*/UID_MIN 499/' /etc/login.defs
+# Default is 60000, but we've seen up to 200000
+RUN sed -i 's/^UID_MAX.*/UID_MAX 1000000/' /etc/login.defs
 
 RUN groupadd app
-RUN useradd -l -m -u $OPENDEVIN_USER_ID -s /bin/bash opendevin && \
-    usermod -aG app opendevin && \
-    usermod -aG sudo opendevin && \
+RUN useradd -l -m -u $OPENHANDS_USER_ID -s /bin/bash openhands && \
+    usermod -aG app openhands && \
+    usermod -aG sudo openhands && \
     echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
-RUN chown -R opendevin:app /app && chmod -R 770 /app
-RUN sudo chown -R opendevin:app $WORKSPACE_BASE && sudo chmod -R 770 $WORKSPACE_BASE
-USER opendevin
+RUN chown -R openhands:app /app && chmod -R 770 /app
+RUN sudo chown -R openhands:app $WORKSPACE_BASE && sudo chmod -R 770 $WORKSPACE_BASE
+USER openhands
 
 ENV VIRTUAL_ENV=/app/.venv \
     PATH="/app/.venv/bin:$PATH" \
     PYTHONPATH='/app'
 
-COPY --chown=opendevin:app --chmod=770 --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
+COPY --chown=openhands:app --chmod=770 --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
 RUN playwright install --with-deps chromium
 
-COPY --chown=opendevin:app --chmod=770 ./opendevin ./opendevin
-COPY --chown=opendevin:app --chmod=777 ./opendevin/runtime/plugins ./opendevin/runtime/plugins
-COPY --chown=opendevin:app --chmod=770 ./agenthub ./agenthub
+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
 
-RUN python opendevin/core/download.py # No-op to download assets
-RUN chown -R opendevin:app /app/logs && chmod -R 770 /app/logs # This gets created by the download.py script
+# 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
+# Add this line to set group ownership of all files/directories not already in "app" group
+# openhands:openhands -> openhands:app
+RUN find /app \! -group app -exec chgrp app {} +
 
-
-COPY --chown=opendevin:app --chmod=770 --from=frontend-builder /app/dist ./frontend/dist
-COPY --chown=opendevin:app --chmod=770 ./containers/app/entrypoint.sh /app/entrypoint.sh
+COPY --chown=openhands:app --chmod=770 --from=frontend-builder /app/build ./frontend/build
+COPY --chown=openhands:app --chmod=770 ./containers/app/entrypoint.sh /app/entrypoint.sh
 
 USER root
 
 WORKDIR /app
 
 ENTRYPOINT ["/app/entrypoint.sh"]
-CMD ["uvicorn", "opendevin.server.listen:app", "--host", "0.0.0.0", "--port", "3000"]
+CMD ["uvicorn", "openhands.server.listen:app", "--host", "0.0.0.0", "--port", "3000"]

containers/app/config.sh

@@ -1,4 +1,4 @@
 DOCKER_REGISTRY=ghcr.io
-DOCKER_ORG=opendevin
-DOCKER_IMAGE=opendevin
+DOCKER_ORG=all-hands-ai
+DOCKER_IMAGE=openhands
 DOCKER_BASE_DIR="."

containers/app/entrypoint.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 set -eo pipefail
 
-echo "Starting OpenDevin..."
+echo "Starting OpenHands..."
 if [[ $NO_SETUP == "true" ]]; then
   echo "Skipping setup, running as $(whoami)"
   "$@"
@@ -9,7 +9,7 @@ if [[ $NO_SETUP == "true" ]]; then
 fi
 
 if [ "$(id -u)" -ne 0 ]; then
-  echo "The OpenDevin entrypoint.sh must run as root"
+  echo "The OpenHands entrypoint.sh must run as root"
   exit 1
 fi
 
@@ -19,11 +19,11 @@ if [ -z "$SANDBOX_USER_ID" ]; then
 fi
 
 if [[ "$SANDBOX_USER_ID" -eq 0 ]]; then
-  echo "Running OpenDevin as root"
-  export RUN_AS_DEVIN=false
+  echo "Running OpenHands as root"
+  export RUN_AS_OPENHANDS=false
   mkdir -p /root/.cache/ms-playwright/
-  if [ -d "/home/opendevin/.cache/ms-playwright/" ]; then
-    mv /home/opendevin/.cache/ms-playwright/ /root/.cache/
+  if [ -d "/home/openhands/.cache/ms-playwright/" ]; then
+    mv /home/openhands/.cache/ms-playwright/ /root/.cache/
   fi
   "$@"
 else
@@ -32,9 +32,9 @@ else
     echo "User enduser already exists. Skipping creation."
   else
     if ! useradd -l -m -u $SANDBOX_USER_ID -s /bin/bash enduser; then
-      echo "Failed to create user enduser with id $SANDBOX_USER_ID. Moving opendevin user."
+      echo "Failed to create user enduser with id $SANDBOX_USER_ID. Moving openhands user."
       incremented_id=$(($SANDBOX_USER_ID + 1))
-      usermod -u $incremented_id opendevin
+      usermod -u $incremented_id openhands
       if ! useradd -l -m -u $SANDBOX_USER_ID -s /bin/bash enduser; then
         echo "Failed to create user enduser with id $SANDBOX_USER_ID for a second time. Exiting."
         exit 1
@@ -42,7 +42,7 @@ else
     fi
   fi
   usermod -aG app enduser
-  # get the user group of /var/run/docker.sock and set opendevin to that group
+  # get the user group of /var/run/docker.sock and set openhands to that group
   DOCKER_SOCKET_GID=$(stat -c '%g' /var/run/docker.sock)
   echo "Docker socket group id: $DOCKER_SOCKET_GID"
   if getent group $DOCKER_SOCKET_GID; then
@@ -54,11 +54,11 @@ else
 
   mkdir -p /home/enduser/.cache/huggingface/hub/
   mkdir -p /home/enduser/.cache/ms-playwright/
-  if [ -d "/home/opendevin/.cache/ms-playwright/" ]; then
-    mv /home/opendevin/.cache/ms-playwright/ /home/enduser/.cache/
+  if [ -d "/home/openhands/.cache/ms-playwright/" ]; then
+    mv /home/openhands/.cache/ms-playwright/ /home/enduser/.cache/
   fi
 
   usermod -aG $DOCKER_SOCKET_GID enduser
   echo "Running as enduser"
-  su enduser /bin/bash -c "$*"
+  su enduser /bin/bash -c "${*@Q}" # This magically runs any arguments passed to the script as a command
 fi

containers/build.sh

@@ -1,14 +1,54 @@
 #!/bin/bash
 set -eo pipefail
 
-image_name=$1
-org_name=$2
-platform=$3
+# Initialize variables with default values
+image_name=""
+org_name=""
+push=0
+load=0
+tag_suffix=""
 
-echo "Building: $image_name for platform: $platform"
+# 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"
 tags=()
 
-OPEN_DEVIN_BUILD_VERSION="dev"
+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
@@ -18,22 +58,31 @@ if [[ -n $GITHUB_REF_NAME ]]; then
     tags+=("$major_version" "$minor_version")
     tags+=("latest")
   fi
-  sanitized=$(echo "$GITHUB_REF_NAME" | sed 's/[^a-zA-Z0-9.-]\+/-/g')
-  OPEN_DEVIN_BUILD_VERSION=$sanitized
-  tag=$(echo "$sanitized" | tr '[:upper:]' '[:lower:]') # lower case is required in tagging
-  tags+=("$tag")
+  sanitized_ref_name=$(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}"
 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 [[ "$image_name" == "opendevin" ]]; then
+if [[ "$image_name" == "openhands" ]]; then
   dir="./containers/app"
-elif [[ "$image_name" == "od_runtime" ]]; then
+elif [[ "$image_name" == "runtime" ]]; then
   dir="./containers/runtime"
 else
   dir="./containers/$image_name"
 fi
 
-if [[ (! -f "$dir/Dockerfile") && "$image_name" != "od_runtime" ]]; then
+if [[ (! -f "$dir/Dockerfile") && "$image_name" != "runtime" ]]; then
   # Allow runtime to be built without a Dockerfile
   echo "No Dockerfile found"
   exit 1
@@ -49,6 +98,10 @@ if [[ -n "$org_name" ]]; then
   DOCKER_ORG="$org_name"
 fi
 
+# 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
   tags+=("$DOCKER_IMAGE_TAG")
@@ -64,15 +117,40 @@ for tag in "${tags[@]}"; do
   args+=" -t $DOCKER_REPOSITORY:$tag"
 done
 
-output_image="/tmp/${image_name}_image_${platform}.tar"
+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"
 
 docker buildx build \
   $args \
-  --build-arg OPEN_DEVIN_BUILD_VERSION="$OPEN_DEVIN_BUILD_VERSION" \
-  --platform linux/$platform \
+  --build-arg OPENHANDS_BUILD_VERSION="$OPENHANDS_BUILD_VERSION" \
+  --cache-from=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag \
+  --cache-from=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag_base-main \
+  --platform $platform \
   --provenance=false \
   -f "$dir/Dockerfile" \
-  --output type=docker,dest="$output_image" \
   "$DOCKER_BASE_DIR"
 
-echo "${tags[*]}" > tags.txt
+# 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

containers/dev/Dockerfile

@@ -0,0 +1,124 @@
+# syntax=docker/dockerfile:1
+
+###
+FROM ubuntu:22.04 AS dind
+
+# https://docs.docker.com/engine/install/ubuntu/
+RUN apt-get update && apt-get install -y \
+	ca-certificates \
+	curl \
+	&& install -m 0755 -d /etc/apt/keyrings \
+	&& curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc \
+	&& chmod a+r /etc/apt/keyrings/docker.asc \
+	&& echo \
+		"deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
+		$(. /etc/os-release && echo "$VERSION_CODENAME") stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null
+
+RUN apt-get update && apt-get install -y \
+	docker-ce \
+	docker-ce-cli \
+	containerd.io \
+	docker-buildx-plugin \
+	docker-compose-plugin \
+	&& rm -rf /var/lib/apt/lists/* \
+	&& apt-get clean \
+	&& apt-get autoremove -y
+
+###
+FROM dind AS openhands
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+#
+RUN apt-get update && apt-get install -y \
+	bash \
+    build-essential \
+    curl \
+	git \
+	git-lfs \
+	software-properties-common \
+	make \
+    netcat \
+    sudo \
+	wget \
+	&& rm -rf /var/lib/apt/lists/* \
+	&& apt-get clean \
+	&& apt-get autoremove -y
+
+# https://github.com/cli/cli/blob/trunk/docs/install_linux.md
+RUN curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg | dd of=/usr/share/keyrings/githubcli-archive-keyring.gpg \
+	&& chmod go+r /usr/share/keyrings/githubcli-archive-keyring.gpg \
+	&& echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" | tee /etc/apt/sources.list.d/github-cli.list > /dev/null \
+	&& apt-get update && apt-get -y install \
+    gh \
+  && rm -rf /var/lib/apt/lists/* \
+  && apt-get clean \
+  && apt-get autoremove -y
+
+# Python 3.12
+RUN add-apt-repository ppa:deadsnakes/ppa \
+    && apt-get update \
+    && apt-get install -y python3.12 python3.12-venv python3.12-dev python3-pip \
+    && ln -s /usr/bin/python3.12 /usr/bin/python
+
+# NodeJS >= 18.17.1
+RUN curl -fsSL https://deb.nodesource.com/setup_18.x | bash - \
+    && apt-get install -y nodejs
+
+# Poetry >= 1.8
+RUN curl -fsSL https://install.python-poetry.org | python3.12 - \
+    && ln -s ~/.local/bin/poetry /usr/local/bin/poetry
+
+#
+RUN <<EOF
+#!/bin/bash
+printf "#!/bin/bash
+set +x
+uname -a
+docker --version
+gh --version | head -n 1
+git --version
+#
+python --version
+echo node `node --version`
+echo npm `npm --version`
+poetry --version
+netcat -h 2>&1 | head -n 1
+" > /version.sh
+chmod a+x /version.sh
+EOF
+
+###
+FROM openhands AS dev
+
+RUN apt-get update && apt-get install -y \
+	dnsutils \
+	file \
+	iproute2 \
+	jq \
+	lsof \
+	ripgrep \
+	silversearcher-ag \
+	vim \
+	&& rm -rf /var/lib/apt/lists/* \
+	&& apt-get clean \
+	&& apt-get autoremove -y
+
+WORKDIR /app
+
+# cache build dependencies
+RUN \
+  --mount=type=bind,source=./,target=/app/ \
+  <<EOF
+#!/bin/bash
+make -s clean
+make -s check-dependencies
+make -s install-python-dependencies
+
+# NOTE
+# node_modules are .dockerignore-d therefore not mountable
+# make -s install-frontend-dependencies
+EOF
+
+#
+CMD ["bash"]

containers/dev/README.md

@@ -0,0 +1,54 @@
+# Develop in Docker
+
+Install [Docker](https://docs.docker.com/engine/install/) on your host machine and run:
+
+```bash
+make docker-dev
+# same as:
+cd ./containers/dev
+./dev.sh
+```
+
+It could take some time if you are running for the first time as Docker will pull all the  tools required for building OpenHands. The next time you run again, it should be instant.
+
+## Build and run
+
+If everything goes well, you should be inside a container after Docker finishes building the `openhands:dev` image similar to the following:
+
+```bash
+Build and run in Docker ...
+root@93fc0005fcd2:/app#
+```
+
+You may now proceed with the normal [build and run](../../Development.md) workflow as if you were on the host.
+
+## Make changes
+
+The source code on the host is mounted as `/app` inside docker. You may edit the files as usual either inside the Docker container or on your host with your favorite IDE/editors.
+
+The following are also mapped as readonly from your host:
+
+```yaml
+# host credentials
+- $HOME/.git-credentials:/root/.git-credentials:ro
+- $HOME/.gitconfig:/root/.gitconfig:ro
+- $HOME/.npmrc:/root/.npmrc:ro
+```
+
+## VSCode
+
+Alternatively, if you use VSCode, you could also [attach to the running container](https://code.visualstudio.com/docs/devcontainers/attach-container).
+
+See details for [developing in docker](https://code.visualstudio.com/docs/devcontainers/containers) or simply ask `OpenHands` ;-)
+
+## Rebuild dev image
+
+You could optionally pass additional options to the build script.
+
+```bash
+make docker-dev OPTIONS="--build"
+# or
+./containers/dev/dev.sh --build
+```
+
+See [docker compose run](https://docs.docker.com/reference/cli/docker/compose/run/) for more options.

containers/dev/compose.yml

@@ -0,0 +1,38 @@
+#
+services:
+  dev:
+    privileged: true
+    build:
+      context: ${OPENHANDS_WORKSPACE:-../../}
+      dockerfile: ./containers/dev/Dockerfile
+    image: openhands:dev
+    container_name: openhands-dev
+    environment:
+      - BACKEND_HOST=${BACKEND_HOST:-"0.0.0.0"}
+      - SANDBOX_API_HOSTNAME=host.docker.internal
+      #
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.9-nikolaik}
+      - SANDBOX_USER_ID=${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
+      # source code
+      - ${OPENHANDS_WORKSPACE:-../../}:/app
+      # host credentials
+      - $HOME/.git-credentials:/root/.git-credentials:ro
+      - $HOME/.gitconfig:/root/.gitconfig:ro
+      - $HOME/.npmrc:/root/.npmrc:ro
+      # cache
+      - cache-data:/root/.cache
+    pull_policy: never
+    stdin_open: true
+    tty: true
+
+##
+volumes:
+  cache-data:

containers/dev/dev.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+set -o pipefail
+
+function get_docker() {
+    echo "Docker is required to build and run OpenHands."
+    echo "https://docs.docker.com/get-started/get-docker/"
+    exit 1
+}
+
+function check_tools() {
+	command -v docker &>/dev/null || get_docker
+}
+
+function exit_if_indocker() {
+    if [ -f /.dockerenv ]; then
+        echo "Running inside a Docker container. Exiting..."
+        exit 1
+    fi
+}
+
+#
+exit_if_indocker
+
+check_tools
+
+##
+OPENHANDS_WORKSPACE=$(git rev-parse --show-toplevel)
+
+cd "$OPENHANDS_WORKSPACE/containers/dev/" || exit 1
+
+##
+export BACKEND_HOST="0.0.0.0"
+#
+export SANDBOX_USER_ID=$(id -u)
+export WORKSPACE_BASE=${WORKSPACE_BASE:-$OPENHANDS_WORKSPACE/workspace}
+
+docker compose run --rm --service-ports "$@" dev
+
+##

containers/e2b-sandbox/README.md

@@ -1,4 +1,4 @@
-# How to build custom E2B sandbox for OpenDevin
+# How to build custom E2B sandbox for OpenHands
 
 [E2B](https://e2b.dev) is an [open-source](https://github.com/e2b-dev/e2b) secure cloud environment (sandbox) made for running AI-generated code and agents. E2B offers [Python](https://pypi.org/project/e2b/) and [JS/TS](https://www.npmjs.com/package/e2b) SDK to spawn and control these sandboxes.
 
@@ -11,5 +11,5 @@
 
 1. Build the sandbox
   ```sh
-  e2b template build --dockerfile ./Dockerfile --name "open-devin"
+  e2b template build --dockerfile ./Dockerfile --name "openhands"
   ```

containers/e2b-sandbox/e2b.toml

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

containers/runtime/README.md

@@ -1,11 +1,12 @@
-# Dynamic constructed Dockerfile
+# Dynamically constructed Dockerfile
 
-This folder builds runtime image (sandbox), which will use a `Dockerfile` that is dynamically generated depends on the `base_image` AND a [Python source distribution](https://docs.python.org/3.10/distutils/sourcedist.html) that's based on the current commit of `opendevin`.
+This folder builds a runtime image (sandbox), which will use a dynamically generated `Dockerfile`
+that depends on the `base_image` **AND** a [Python source distribution](https://docs.python.org/3.10/distutils/sourcedist.html) that is based on the current commit of `openhands`.
 
-The following command will generate Dockerfile for `ubuntu:22.04` and the source distribution `.tar` into `containers/runtime`.
+The following command will generate a `Dockerfile` file for `nikolaik/python-nodejs:python3.12-nodejs22` (the default base image), an updated `config.sh` and the runtime source distribution files/folders into `containers/runtime`:
 
 ```bash
-poetry run python3 opendevin/runtime/utils/runtime_build.py \
-    --base_image ubuntu:22.04 \
+poetry run python3 openhands/runtime/utils/runtime_build.py \
+    --base_image nikolaik/python-nodejs:python3.12-nodejs22 \
     --build_folder containers/runtime
 ```

containers/runtime/config.sh

@@ -1,8 +1,7 @@
 DOCKER_REGISTRY=ghcr.io
-DOCKER_ORG=opendevin
+DOCKER_ORG=all-hands-ai
 DOCKER_BASE_DIR="./containers/runtime"
-# These two variables will be appended by the runtime_build.py script
-# DOCKER_IMAGE=
+DOCKER_IMAGE=runtime
+# These variables will be appended by the runtime_build.py script
 # DOCKER_IMAGE_TAG=
-DOCKER_IMAGE=od_runtime
-DOCKER_IMAGE_TAG=od_v0.8.1_image_ubuntu_tag_22.04
+# DOCKER_IMAGE_HASH_TAG=

containers/sandbox/Dockerfile

@@ -1,44 +0,0 @@
-FROM ubuntu:22.04
-
-# install basic packages
-RUN apt-get update && apt-get install -y \
-    curl \
-    wget \
-    git \
-    vim \
-    nano \
-    unzip \
-    zip \
-    python3 \
-    python3-pip \
-    python3-venv \
-    python3-dev \
-    build-essential \
-    openssh-server \
-    sudo \
-    gcc \
-    jq \
-    g++ \
-    make \
-    iproute2 \
-    && rm -rf /var/lib/apt/lists/*
-
-RUN mkdir -p -m0755 /var/run/sshd
-
-# symlink python3 to python
-RUN ln -s /usr/bin/python3 /usr/bin/python
-
-# ==== OpenDevin Runtime Client ====
-RUN mkdir -p /opendevin && mkdir -p /opendevin/logs && chmod 777 /opendevin/logs
-RUN wget --progress=bar:force -O Miniforge3.sh "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"
-RUN bash Miniforge3.sh -b -p /opendevin/miniforge3
-RUN chmod -R g+w /opendevin/miniforge3
-RUN bash -c ". /opendevin/miniforge3/etc/profile.d/conda.sh && conda config --set changeps1 False && conda config --append channels conda-forge"
-RUN echo "" > /opendevin/bash.bashrc
-RUN rm -f Miniforge3.sh
-
-# - agentskills dependencies
-RUN /opendevin/miniforge3/bin/pip install --upgrade pip
-RUN /opendevin/miniforge3/bin/pip install jupyterlab notebook jupyter_kernel_gateway flake8
-RUN /opendevin/miniforge3/bin/pip install python-docx PyPDF2 python-pptx pylatexenc openai
-RUN /opendevin/miniforge3/bin/pip install python-dotenv toml termcolor pydantic python-docx pyyaml docker pexpect tenacity e2b browsergym minio

containers/sandbox/config.sh

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

dev_config/python/.pre-commit-config.yaml

@@ -38,6 +38,6 @@ repos:
       - id: mypy
         additional_dependencies:
           [types-requests, types-setuptools, types-pyyaml, types-toml]
-        entry: mypy --config-file dev_config/python/mypy.ini opendevin/ agenthub/
+        entry: mypy --config-file dev_config/python/mypy.ini openhands/
         always_run: true
         pass_filenames: false

docs/docusaurus.config.ts

@@ -3,17 +3,17 @@ import type { Config } from "@docusaurus/types";
 import { themes as prismThemes } from "prism-react-renderer";
 
 const config: Config = {
-  title: "OpenDevin",
+  title: "OpenHands",
   tagline: "Code Less, Make More",
-  favicon: "img/logo.png",
+  favicon: "img/logo-square.png",
 
   // Set the production url of your site here
   url: "https://docs.all-hands.dev",
   baseUrl: "/",
 
   // GitHub pages deployment config.
-  organizationName: "OpenDevin",
-  projectName: "OpenDevin",
+  organizationName: "All-Hands-AI",
+  projectName: "OpenHands",
   trailingSlash: false,
 
   onBrokenLinks: "throw",
@@ -32,6 +32,10 @@ const config: Config = {
     },
   },
 
+  markdown: {
+    mermaid: true,
+  },
+  themes: ['@docusaurus/theme-mermaid'],
   presets: [
     [
       "classic",
@@ -59,9 +63,9 @@ const config: Config = {
   themeConfig: {
     image: "img/docusaurus.png",
     navbar: {
-      title: "OpenDevin",
+      title: "OpenHands",
       logo: {
-        alt: "OpenDevin",
+        alt: "OpenHands",
         src: "img/logo.png",
       },
       items: [
@@ -69,24 +73,28 @@ const config: Config = {
           type: "docSidebar",
           sidebarId: "docsSidebar",
           position: "left",
-          label: "Docs",
+          label: "User Guides",
         },
         {
           type: "docSidebar",
           sidebarId: "apiSidebar",
           position: "left",
-          label: "Codebase",
-        },
-        { to: "/faq", label: "FAQ", position: "left" },
-        {
-          href: "https://github.com/OpenDevin/OpenDevin",
-          label: "GitHub",
-          position: "right",
+          label: "Python API",
         },
         {
           type: 'localeDropdown',
           position: 'left',
         },
+        {
+          href: "https://all-hands.dev",
+          label: "Company",
+          position: "right",
+        },
+        {
+          href: "https://github.com/All-Hands-AI/OpenHands",
+          label: "GitHub",
+          position: "right",
+        },
       ],
     },
     prism: {

docs/i18n/fr/code.json

@@ -1,6 +1,6 @@
 {
   "footer.title": {
-    "message": "OpenDevin"
+    "message": "OpenHands"
   },
   "footer.docs": {
     "message": "Documents"
@@ -9,7 +9,7 @@
     "message": "Communauté"
   },
   "footer.copyright": {
-    "message": "© {year} OpenDevin"
+    "message": "© {year} OpenHands"
   },
   "faq.title": {
     "message": "Questions Fréquemment Posées",
@@ -19,20 +19,20 @@
     "message": "Questions Fréquemment Posées"
   },
   "faq.section.title.1": {
-    "message": "Qu'est-ce qu'OpenDevin ?",
+    "message": "Qu'est-ce qu'OpenHands ?",
     "description": "First Section Title"
   },
   "faq.section.highlight": {
-    "message": "OpenDevin",
+    "message": "OpenHands",
     "description": "Highlight Text"
   },
   "faq.section.description.1": {
-    "message": "est un ingénieur logiciel autonome qui peut résoudre des tâches d'ingénierie logicielle et de navigation web à tout moment. Il peut exécuter des requêtes en sciences des données, telles que \"Trouver le nombre de demandes de pull à l'repository OpenDevin dans les derniers mois\", et des tâches d'ingénierie logicielle, comme \"Veuillez ajouter des tests à ce fichier et vérifier si tous les tests passent. Si ce n'est pas le cas, réparez le fichier.\"",
-    "description": "Description for OpenDevin"
+    "message": "est un ingénieur logiciel autonome qui peut résoudre des tâches d'ingénierie logicielle et de navigation web à tout moment. Il peut exécuter des requêtes en sciences des données, telles que \"Trouver le nombre de demandes de pull à l'repository OpenHands dans les derniers mois\", et des tâches d'ingénierie logicielle, comme \"Veuillez ajouter des tests à ce fichier et vérifier si tous les tests passent. Si ce n'est pas le cas, réparez le fichier.\"",
+    "description": "Description for OpenHands"
   },
   "faq.section.description.2": {
-    "message": "De plus, OpenDevin est une plateforme et communauté pour les développeurs d'agents qui souhaitent tester et évaluer de nouveaux agents.",
-    "description": "Further Description for OpenDevin"
+    "message": "De plus, OpenHands est une plateforme et communauté pour les développeurs d'agents qui souhaitent tester et évaluer de nouveaux agents.",
+    "description": "Further Description for OpenHands"
   },
   "faq.section.title.2": {
     "message": "Support",
@@ -43,15 +43,15 @@
     "description": "Support Answer"
   },
   "faq.section.title.3": {
-    "message": "Comment résoudre un problème sur GitHub avec OpenDevin ?",
+    "message": "Comment résoudre un problème sur GitHub avec OpenHands ?",
     "description": "GitHub Issue Section Title"
   },
   "faq.section.github.steps.intro": {
-    "message": "Pour résoudre un problème sur GitHub en utilisant OpenDevin, envoyez une commande à OpenDevin demandant qu'il suit des étapes comme les suivantes :",
+    "message": "Pour résoudre un problème sur GitHub en utilisant OpenHands, envoyez une commande à OpenHands demandant qu'il suit des étapes comme les suivantes :",
     "description": "GitHub Steps Introduction"
   },
   "faq.section.github.step1": {
-    "message": "Lisez l'issue https://github.com/OpenDevin/OpenDevin/issues/1611",
+    "message": "Lisez l'issue https://github.com/All-Hands-AI/OpenHands/issues/1611",
     "description": "GitHub Step 1"
   },
   "faq.section.github.step2": {
@@ -71,11 +71,11 @@
     "description": "GitHub Step 5"
   },
   "faq.section.github.steps.preRun": {
-    "message": "Avant de lancer OpenDevin, vous pouvez faire :",
+    "message": "Avant de lancer OpenHands, vous pouvez faire :",
     "description": "GitHub Steps Pre-Run"
   },
   "faq.section.github.steps.tokenInfo": {
-    "message": "où XXX est un jeton GitHub que vous avez créé et qui a les autorisations pour pousser dans le dépôt OpenDevin. Si vous n'avez pas d'autorisations de modification du dépôt OpenDevin, vous devrez peut-être changer cela en :",
+    "message": "où XXX est un jeton GitHub que vous avez créé et qui a les autorisations pour pousser dans le dépôt OpenHands. Si vous n'avez pas d'autorisations de modification du dépôt OpenHands, vous devrez peut-être changer cela en :",
     "description": "GitHub Steps Token Info"
   },
   "faq.section.github.steps.usernameInfo": {
@@ -83,23 +83,23 @@
     "description": "GitHub Steps Username Info"
   },
   "faq.section.title.4": {
-    "message": "Comment OpenDevin est-il différent de Devin ?",
+    "message": "Comment OpenHands est-il différent de Devin ?",
     "description": "Devin Section Title"
   },
-  "faq.section.devin.linkText": {
+  "faq.section.openhands.linkText": {
     "message": "Devin",
     "description": "Devin Link Text"
   },
-  "faq.section.devin.description": {
-    "message": "est un produit commercial par Cognition Inc., qui a servi d'inspiration initiale pour OpenDevin. Les deux visent à bien faire le travail d'ingénierie logicielle, mais vous pouvez télécharger, utiliser et modifier OpenDevin, tandis que Devin peut être utilisé uniquement via le site de Cognition. De plus, OpenDevin a évolué au-delà de l'inspiration initiale, et est maintenant un écosystème communautaire pour le développement d'agents en général, et nous serions ravis de vous voir rejoindre et",
+  "faq.section.openhands.description": {
+    "message": "est un produit commercial par Cognition Inc., qui a servi d'inspiration initiale pour OpenHands. Les deux visent à bien faire le travail d'ingénierie logicielle, mais vous pouvez télécharger, utiliser et modifier OpenHands, tandis que Devin peut être utilisé uniquement via le site de Cognition. De plus, OpenHands a évolué au-delà de l'inspiration initiale, et est maintenant un écosystème communautaire pour le développement d'agents en général, et nous serions ravis de vous voir rejoindre et",
     "description": "Devin Description"
   },
-  "faq.section.devin.contribute": {
+  "faq.section.openhands.contribute": {
     "message": "contribuer",
     "description": "Contribute Link"
   },
   "faq.section.title.5": {
-    "message": "Comment OpenDevin est-il différent de ChatGPT ?",
+    "message": "Comment OpenHands est-il différent de ChatGPT ?",
     "description": "ChatGPT Section Title"
   },
   "faq.section.chatgpt.description": {
@@ -114,7 +114,7 @@
     "message": "Commencer"
   },
   "welcome.message": {
-    "message": "Bienvenue à OpenDevin, un système d'IA autonome ingénieur logiciel capable d'exécuter des tâches d'ingénierie complexes et de collaborer activement avec les utilisateurs sur les projets de développement logiciel."
+    "message": "Bienvenue à OpenHands, un système d'IA autonome ingénieur logiciel capable d'exécuter des tâches d'ingénierie complexes et de collaborer activement avec les utilisateurs sur les projets de développement logiciel."
   },
   "theme.ErrorPageContent.title": {
     "message": "Cette page a planté.",

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

@@ -19,35 +19,35 @@ La réalisation d'une réplication complète des applications de production avec
 
 ## 🤝 Comment Contribuer {#how-to-contribute}
 
-OpenDevin est un projet communautaire, et nous accueillons les contributions de tout le monde. Que vous soyez développeur, chercheur, ou simplement enthousiaste à l'idée de faire progresser le domaine de l'ingénierie logicielle avec l'IA, il existe de nombreuses façons de vous impliquer :
+OpenHands est un projet communautaire, et nous accueillons les contributions de tout le monde. Que vous soyez développeur, chercheur, ou simplement enthousiaste à l'idée de faire progresser le domaine de l'ingénierie logicielle avec l'IA, il existe de nombreuses façons de vous impliquer :
 
 - **Contributions de Code :** Aidez-nous à développer les fonctionnalités de base, l'interface frontend ou les solutions de sandboxing.
 - **Recherche et Évaluation :** Contribuez à notre compréhension des LLM en ingénierie logicielle, participez à l'évaluation des modèles ou suggérez des améliorations.
-- **Retour d'Information et Tests :** Utilisez l'ensemble d'outils OpenDevin, signalez des bogues, suggérez des fonctionnalités ou fournissez des retours sur l'ergonomie.
+- **Retour d'Information et Tests :** Utilisez l'ensemble d'outils OpenHands, signalez des bogues, suggérez des fonctionnalités ou fournissez des retours sur l'ergonomie.
 
-Pour plus de détails, veuillez consulter [ce document](https://github.com/OpenDevin/OpenDevin/blob/main/CONTRIBUTING.md).
+Pour plus de détails, veuillez consulter [ce document](https://github.com/All-Hands-AI/OpenHands/blob/main/CONTRIBUTING.md).
 
 ## 🤖 Rejoignez Notre Communauté {#join-our-community}
 
-Nous avons maintenant à la fois un espace de travail Slack pour la collaboration sur la construction d'OpenDevin et un serveur Discord pour discuter de tout ce qui est lié, par exemple, à ce projet, aux LLM, aux agents, etc.
+Nous avons maintenant à la fois un espace de travail Slack pour la collaboration sur la construction d'OpenHands et un serveur Discord pour discuter de tout ce qui est lié, par exemple, à ce projet, aux LLM, aux agents, etc.
 
-- [Espace de travail Slack](https://join.slack.com/t/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA)
+- [Espace de travail Slack](https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA)
 - [Serveur Discord](https://discord.gg/ESHStjSjD4)
 
 Si vous souhaitez contribuer, n'hésitez pas à rejoindre notre communauté. Simplifions l'ingénierie logicielle ensemble !
 
-🐚 **Codez moins, créez plus avec OpenDevin.**
+🐚 **Codez moins, créez plus avec OpenHands.**
 
-[![Star History Chart](https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date)](https://star-history.com/#OpenDevin/OpenDevin&Date)
+[![Star History Chart](https://api.star-history.com/svg?repos=All-Hands-AI/OpenHands&type=Date)](https://star-history.com/#All-Hands-AI/OpenHands&Date)
 
 ## 🛠️ Construit Avec {#built-with}
 
-OpenDevin est construit en utilisant une combinaison de cadres et de bibliothèques puissants, offrant une base robuste pour son développement. Voici les technologies clés utilisées dans le projet :
+OpenHands est construit en utilisant une combinaison de cadres et de bibliothèques puissants, offrant une base robuste pour son développement. Voici les technologies clés utilisées dans le projet :
 
 ![FastAPI](https://img.shields.io/badge/FastAPI-black?style=for-the-badge) ![uvicorn](https://img.shields.io/badge/uvicorn-black?style=for-the-badge) ![LiteLLM](https://img.shields.io/badge/LiteLLM-black?style=for-the-badge) ![Docker](https://img.shields.io/badge/Docker-black?style=for-the-badge) ![Ruff](https://img.shields.io/badge/Ruff-black?style=for-the-badge) ![MyPy](https://img.shields.io/badge/MyPy-black?style=for-the-badge) ![LlamaIndex](https://img.shields.io/badge/LlamaIndex-black?style=for-the-badge) ![React](https://img.shields.io/badge/React-black?style=for-the-badge)
 
-Veuillez noter que la sélection de ces technologies est en cours, et que des technologies supplémentaires peuvent être ajoutées ou des existantes supprimées au fur et à mesure de l'évolution du projet. Nous nous efforçons d'adopter les outils les plus adaptés et efficaces pour améliorer les capacités d'OpenDevin.
+Veuillez noter que la sélection de ces technologies est en cours, et que des technologies supplémentaires peuvent être ajoutées ou des existantes supprimées au fur et à mesure de l'évolution du projet. Nous nous efforçons d'adopter les outils les plus adaptés et efficaces pour améliorer les capacités d'OpenHands.
 
 ## 📜 Licence {#license}
 
-Distribué sous la licence MIT. Voir [notre licence](https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE) pour plus d'informations.
+Distribué sous la licence MIT. Voir [notre licence](https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE) pour plus d'informations.

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

@@ -18,18 +18,18 @@ L'idée conceptuelle est illustrée ci-dessous. À chaque tour, l'agent peut :
 - Exécuter toute commande `bash` Linux valide
 - Exécuter tout code `Python` valide avec [un interpréteur Python interactif](https://ipython.org/). Cela est simulé à travers la commande `bash`, voir le système de plugin ci-dessous pour plus de détails.
 
-![image](https://github.com/OpenDevin/OpenDevin/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
+![image](https://github.com/All-Hands-AI/OpenHands/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
 
 ### Système de Plugin
 
-Pour rendre l'agent CodeAct plus puissant avec seulement l'accès à l'espace d'action `bash`, l'agent CodeAct exploite le système de plugins d'OpenDevin:
+Pour rendre l'agent CodeAct plus puissant avec seulement l'accès à l'espace d'action `bash`, l'agent CodeAct exploite le système de plugins d'OpenHands:
 
-- [Plugin Jupyter](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/jupyter) : pour l'exécution d'IPython via la commande bash
-- [Plugin outil agent SWE](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/swe_agent_commands) : Outils de ligne de commande bash puissants pour les tâches de développement logiciel introduits par [swe-agent](https://github.com/princeton-nlp/swe-agent).
+- [Plugin Jupyter](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/runtime/plugins/jupyter) : pour l'exécution d'IPython via la commande bash
+- [Plugin outil agent SWE](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/runtime/plugins/swe_agent_commands) : Outils de ligne de commande bash puissants pour les tâches de développement logiciel introduits par [swe-agent](https://github.com/princeton-nlp/swe-agent).
 
 ### Démonstration
 
-https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
+https://github.com/All-Hands-AI/OpenHands/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
 
 _Exemple de CodeActAgent avec `gpt-4-turbo-2024-04-09` effectuant une tâche de science des données (régression linéaire)_
 

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

@@ -25,14 +25,14 @@ _**Avertissement**: L'architecture du backend est en cours de développement et
 
     ## Prérequis
 
-    - Un environnement Python dans lequel opendevin est exécutable
+    - Un environnement Python dans lequel openhands est exécutable
     (selon les instructions du fichier README.md à la racine du dépôt)
     - [py2puml](https://github.com/lucsorel/py2puml) installé
 
 ## Étapes
 
 1.  Générez automatiquement le schéma en exécutant la commande suivante depuis la racine du dépôt :
-    `py2puml opendevin opendevin > docs/architecture/backend_architecture.puml`
+    `py2puml openhands openhands > docs/architecture/backend_architecture.puml`
 
 2.  Ouvrez le fichier généré dans un éditeur PlantUML, par exemple Visual Studio Code avec l'extension PlantUML ou [PlantText](https://www.planttext.com/)
 

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

@@ -1,14 +1,14 @@
 # 💿 Comment Créer un Soutien Docker sur Mesure
 
-Le sandbox par défaut OpenDevin est équipé d'une configuration ubuntu minimaliste. Votre cas d'utilisation pourrait nécessiter des logiciels installés par défaut. Cet article vous enseignera comment réaliser cela en utilisant une image docker personnalisée.
+Le sandbox par défaut OpenHands est équipé d'une configuration ubuntu minimaliste. Votre cas d'utilisation pourrait nécessiter des logiciels installés par défaut. Cet article vous enseignera comment réaliser cela en utilisant une image docker personnalisée.
 
 ## Configuration
 
-Assurez-vous de pouvoir utiliser OpenDevin en suivant la documentation [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md).
+Assurez-vous de pouvoir utiliser OpenHands en suivant la documentation [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
 
 ## Créer Votre Image Docker
 
-Ensuite, vous devez créer votre image docker personnalisée qui doit être basée sur debian/ubuntu. Par exemple, si nous souhaitons que OpenDevin ait accès au "node" binaire, nous utiliserions ce Dockerfile:
+Ensuite, vous devez créer votre image docker personnalisée qui doit être basée sur debian/ubuntu. Par exemple, si nous souhaitons que OpenHands ait accès au "node" binaire, nous utiliserions ce Dockerfile:
 
 ```bash
 # Commencez avec l'image ubuntu la plus récente
@@ -29,28 +29,27 @@ docker build -t image_personnalisée .
 
 Cela produira une nouvelle image appelée ```image_personnalisée``` qui sera disponible dans Docker Engine.
 
-> Remarque: Dans la configuration décrite ici, OpenDevin va fonctionner en tant que utilisateur "opendevin" à l'intérieur du sandbox et donc tous les packages installés via le Dockerfile seront disponibles pour tous les utilisateurs sur le système, pas seulement root.
+> Remarque: Dans la configuration décrite ici, OpenHands va fonctionner en tant que utilisateur "openhands" à l'intérieur du sandbox et donc tous les packages installés via le Dockerfile seront disponibles pour tous les utilisateurs sur le système, pas seulement root.
 >
 > L'installation avec apt-get ci-dessus installe nodejs pour tous les utilisateurs.
 
 ## Spécifiez votre image personnalisée dans le fichier config.toml
 
-La configuration OpenDevin se fait via le fichier de niveau supérieur ```config.toml``` .
-Créez un fichier ```config.toml``` dans le répertoire OpenDevin et entrez ces contenus:
+La configuration OpenHands se fait via le fichier de niveau supérieur ```config.toml``` .
+Créez un fichier ```config.toml``` dans le répertoire OpenHands et entrez ces contenus:
 
 ```toml
 [core]
 workspace_base="./workspace"
-persist_sandbox=false
-run_as_devin=true
-sandbox_container_image="image_personnalisée"
+run_as_openhands=true
+sandbox_base_container_image="image_personnalisée"
 ```
 
-> Assurez-vous que ```sandbox_container_image``` est défini sur le nom de votre image personnalisée précédente.
+> Assurez-vous que ```sandbox_base_container_image``` est défini sur le nom de votre image personnalisée précédente.
 
 ## Exécution
 
-Exécutez OpenDevin en exécutant ```make run``` dans le répertoire racine.
+Exécutez OpenHands en exécutant ```make run``` dans le répertoire racine.
 
 Naviguez vers ```localhost:3001``` et vérifiez si vos dépendances souhaitées sont disponibles.
 
@@ -60,41 +59,36 @@ Félicitations !
 
 ## Explication technique
 
-Le code pertinent est défini dans [ssh_box.py](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/ssh_box.py) et [image_agnostic_util.py](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py).
-
-En particulier, ssh_box.py vérifie l'objet config pour ```config.sandbox_container_image``` et ensuite tente de récupérer l'image à l'aide de [get_od_sandbox_image](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py#L72), qui est défini dans image_agnostic_util.py.
-
 Lorsqu'une image personnalisée est utilisée pour la première fois, elle ne sera pas trouvée et donc elle sera construite (à l'exécution ultérieure, l'image construite sera trouvée et renvoyée).
 
-L'image personnalisée est construite avec [_build_sandbox_image()](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py#L29), qui crée un fichier docker en utilisant votre image personnalisée comme base et configure ensuite l'environnement pour OpenDevin, comme ceci:
+L'image personnalisée est construite avec [_build_sandbox_image()](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/docker/image_agnostic_util.py#L29), qui crée un fichier docker en utilisant votre image personnalisée comme base et configure ensuite l'environnement pour OpenHands, comme ceci:
 
 ```python
 dockerfile_content = (
         f'FROM {base_image}\n'
         'RUN apt update && apt install -y openssh-server wget sudo\n'
         'RUN mkdir -p -m0755 /var/run/sshd\n'
-        'RUN mkdir -p /opendevin && mkdir -p /opendevin/logs && chmod 777 /opendevin/logs\n'
+        'RUN mkdir -p /openhands && mkdir -p /openhands/logs && chmod 777 /openhands/logs\n'
         'RUN wget "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"\n'
-        'RUN bash Miniforge3-$(uname)-$(uname -m).sh -b -p /opendevin/miniforge3\n'
-        'RUN bash -c ". /opendevin/miniforge3/etc/profile.d/conda.sh && conda config --set changeps1 False && conda config --append channels conda-forge"\n'
-        'RUN echo "export PATH=/opendevin/miniforge3/bin:$PATH" >> ~/.bashrc\n'
-        'RUN echo "export PATH=/opendevin/miniforge3/bin:$PATH" >> /opendevin/bash.bashrc\n'
+        'RUN bash Miniforge3-$(uname)-$(uname -m).sh -b -p /openhands/miniforge3\n'
+        'RUN bash -c ". /openhands/miniforge3/etc/profile.d/conda.sh && conda config --set changeps1 False && conda config --append channels conda-forge"\n'
+        'RUN echo "export PATH=/openhands/miniforge3/bin:$PATH" >> ~/.bashrc\n'
+        'RUN echo "export PATH=/openhands/miniforge3/bin:$PATH" >> /openhands/bash.bashrc\n'
     ).strip()
 ```
 
-> Remarque: Le nom de l'image est modifié via [_get_new_image_name()](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py#L63) et c'est ce nom modifié qui sera recherché lors des exécutions ultérieures.
+> Remarque: Le nom de l'image est modifié via [_get_new_image_name()](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/docker/image_agnostic_util.py#L63) et c'est ce nom modifié qui sera recherché lors des exécutions ultérieures.
 
 ## Dépannage / Erreurs
 
 ### Erreur: ```useradd: UID 1000 est non unique```
-Si vous voyez cette erreur dans la sortie de la console, il s'agit du fait que OpenDevin essaie de créer le utilisateur opendevin dans le sandbox avec un ID d'utilisateur de 1000, cependant cet ID d'utilisateur est déjà utilisé dans l'image (pour une raison inconnue). Pour résoudre ce problème, changez la valeur du champ sandbox_user_id dans le fichier config.toml en une valeur différente:
+Si vous voyez cette erreur dans la sortie de la console, il s'agit du fait que OpenHands essaie de créer le utilisateur openhands dans le sandbox avec un ID d'utilisateur de 1000, cependant cet ID d'utilisateur est déjà utilisé dans l'image (pour une raison inconnue). Pour résoudre ce problème, changez la valeur du champ sandbox_user_id dans le fichier config.toml en une valeur différente:
 
 ```toml
 [core]
 workspace_base="./workspace"
-persist_sandbox=false
-run_as_devin=true
-sandbox_container_image="image_personnalisée"
+run_as_openhands=true
+sandbox_base_container_image="image_personnalisée"
 sandbox_user_id="1001"
 ```
 
@@ -104,4 +98,4 @@ Si vous voyez un message d'erreur indiquant que le port est utilisé ou indispon
 
 ## Discuter
 
-Pour d'autres problèmes ou questions rejoignez le [Slack](https://join.slack.com/t/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA) ou le [Discord](https://discord.gg/ESHStjSjD4) et demandez!
+Pour d'autres problèmes ou questions rejoignez le [Slack](https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA) ou le [Discord](https://discord.gg/ESHStjSjD4) et demandez!

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

@@ -4,15 +4,15 @@ sidebar_position: 6
 
 # ✅ Fournir des Commentaires
 
-Lorsque vous utilisez OpenDevin, vous rencontrerez sans aucun doute des cas où les choses fonctionnent bien et d'autres où elles ne fonctionnent pas. Nous vous encourageons à fournir des commentaires lorsque vous utilisez OpenDevin pour aider l'équipe de développement et, peut-être plus important encore, créer un corpus ouvert d'exemples de formation pour les agents de codage -- Partagez-OpenDevin !
+Lorsque vous utilisez OpenHands, vous rencontrerez sans aucun doute des cas où les choses fonctionnent bien et d'autres où elles ne fonctionnent pas. Nous vous encourageons à fournir des commentaires lorsque vous utilisez OpenHands pour aider l'équipe de développement et, peut-être plus important encore, créer un corpus ouvert d'exemples de formation pour les agents de codage -- Partagez-OpenHands !
 
 ## 📝 Comment Fournir des Commentaires
 
-Fournir des commentaires est simple ! Lorsque vous utilisez OpenDevin, vous pouvez appuyer sur le bouton de pouce vers le haut ou vers le bas à n'importe quel moment de votre interaction. Vous serez invité à fournir votre adresse email (par exemple, afin que nous puissions vous contacter si nous voulons poser des questions de suivi), et vous pouvez choisir si vous souhaitez fournir des commentaires publiquement ou en privé.
+Fournir des commentaires est simple ! Lorsque vous utilisez OpenHands, vous pouvez appuyer sur le bouton de pouce vers le haut ou vers le bas à n'importe quel moment de votre interaction. Vous serez invité à fournir votre adresse email (par exemple, afin que nous puissions vous contacter si nous voulons poser des questions de suivi), et vous pouvez choisir si vous souhaitez fournir des commentaires publiquement ou en privé.
 
 <iframe width="560" height="315" src="https://www.youtube.com/embed/5rFx-StMVV0?si=svo7xzp6LhGK_GXr" title="Lecteur vidéo YouTube" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
 
 ## 📜 Licence de Données et Confidentialité
 
-* Les données **publiques** seront distribuées sous la licence MIT, comme OpenDevin lui-même, et pourront être utilisées par la communauté pour former et tester des modèles. Évidemment, les commentaires que vous pouvez rendre publics seront plus précieux pour la communauté dans son ensemble, donc lorsque vous ne traitez pas d'informations sensibles, nous vous encourageons à choisir cette option !
-* Les données **privées** ne seront partagées qu'avec l'équipe OpenDevin dans le but d'améliorer OpenDevin.
+* Les données **publiques** seront distribuées sous la licence MIT, comme OpenHands lui-même, et pourront être utilisées par la communauté pour former et tester des modèles. Évidemment, les commentaires que vous pouvez rendre publics seront plus précieux pour la communauté dans son ensemble, donc lorsque vous ne traitez pas d'informations sensibles, nous vous encourageons à choisir cette option !
+* Les données **privées** ne seront partagées qu'avec l'équipe OpenHands dans le but d'améliorer OpenHands.

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

@@ -2,47 +2,47 @@
 sidebar_position: 1
 ---
 
-# 💻 OpenDevin
+# 💻 OpenHands
 
-OpenDevin est un **ingénieur logiciel IA autonome** capable d'exécuter des tâches d'ingénierie complexes et de collaborer activement avec les utilisateurs sur des projets de développement logiciel.
+OpenHands est un **ingénieur logiciel IA autonome** capable d'exécuter des tâches d'ingénierie complexes et de collaborer activement avec les utilisateurs sur des projets de développement logiciel.
 Ce projet est entièrement open-source, vous pouvez donc l'utiliser et le modifier comme bon vous semble.
 
 :::tip
-Explorez le code source d'OpenDevin sur [GitHub](https://github.com/OpenDevin/OpenDevin) ou rejoignez l'une de nos communautés !
+Explorez le code source d'OpenHands sur [GitHub](https://github.com/All-Hands-AI/OpenHands) ou rejoignez l'une de nos communautés !
 
-<a href="https://github.com/OpenDevin/OpenDevin/graphs/contributors">
+<a href="https://github.com/All-Hands-AI/OpenHands/graphs/contributors">
   <img
-    src="https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge"
+    src="https://img.shields.io/github/contributors/All-Hands-AI/OpenHands?style=for-the-badge"
     alt="Contributors"
   />
 </a>
-<a href="https://github.com/OpenDevin/OpenDevin/network/members">
+<a href="https://github.com/All-Hands-AI/OpenHands/network/members">
   <img
-    src="https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge"
+    src="https://img.shields.io/github/forks/All-Hands-AI/OpenHands?style=for-the-badge"
     alt="Forks"
   />
 </a>
-<a href="https://github.com/OpenDevin/OpenDevin/stargazers">
+<a href="https://github.com/All-Hands-AI/OpenHands/stargazers">
   <img
-    src="https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge"
+    src="https://img.shields.io/github/stars/All-Hands-AI/OpenHands?style=for-the-badge"
     alt="Stargazers"
   />
 </a>
-<a href="https://github.com/OpenDevin/OpenDevin/issues">
+<a href="https://github.com/All-Hands-AI/OpenHands/issues">
   <img
-    src="https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge"
+    src="https://img.shields.io/github/issues/All-Hands-AI/OpenHands?style=for-the-badge"
     alt="Issues"
   />
 </a>
 <br></br>
-<a href="https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE">
+<a href="https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE">
   <img
-    src="https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge"
+    src="https://img.shields.io/github/license/All-Hands-AI/OpenHands?style=for-the-badge"
     alt="MIT License"
   />
 </a>
 <br></br>
-<a href="https://join.slack.com/t/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA">
+<a href="https://join.slack.com/t/opendevin/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"
@@ -58,10 +58,10 @@ Explorez le code source d'OpenDevin sur [GitHub](https://github.com/OpenDevin/Op
 
 ## 🛠️ Pour commencer
 
-La manière la plus simple d'exécuter OpenDevin est à l'intérieur d'un conteneur Docker. Il fonctionne mieux avec la version la plus récente de Docker, `26.0.0`.
+La manière la plus simple d'exécuter OpenHands est à l'intérieur d'un conteneur Docker. Il fonctionne mieux avec la version la plus récente de Docker, `26.0.0`.
 Vous devez utiliser Linux, Mac OS ou WSL sur Windows.
 
-Pour démarrer OpenDevin dans un conteneur docker, exécutez les commandes suivantes dans votre terminal :
+Pour démarrer OpenHands dans un conteneur docker, exécutez les commandes suivantes dans votre terminal :
 
 :::warning
 Lorsque vous exécutez la commande suivante, les fichiers dans `./workspace` peuvent être modifiés ou supprimés.
@@ -72,40 +72,38 @@ WORKSPACE_BASE=$(pwd)/workspace
 docker run -it \
     --pull=always \
     -e SANDBOX_USER_ID=$(id -u) \
-    -e PERSIST_SANDBOX="true" \
-    -e SSH_PASSWORD="make something up here" \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -v $WORKSPACE_BASE:/opt/workspace_base \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
-    --name opendevin-app-$(date +%Y%m%d%H%M%S) \
-    ghcr.io/opendevin/opendevin:0.6
+    --name openhands-app-$(date +%Y%m%d%H%M%S) \
+    ghcr.io/all-hands-ai/openhands:main
 ```
 
-Vous trouverez OpenDevin fonctionnant à l'adresse [http://localhost:3000](http://localhost:3000) avec accès à `./workspace`. Pour qu'OpenDevin fonctionne sur votre code, placez-le dans `./workspace`.
+Vous trouverez OpenHands fonctionnant à l'adresse [http://localhost:3000](http://localhost:3000) avec accès à `./workspace`. Pour qu'OpenHands fonctionne sur votre code, placez-le dans `./workspace`.
 
-OpenDevin n'aura accès qu'à ce dossier de workspace. Le reste de votre système ne sera pas affecté car il s'exécute dans un bac à sable sécurisé de docker.
+OpenHands n'aura accès qu'à ce dossier de workspace. Le reste de votre système ne sera pas affecté car il s'exécute dans un bac à sable sécurisé de docker.
 
 :::tip
-Si vous souhaitez utiliser la version **(instable !)** la plus récente, vous pouvez utiliser `ghcr.io/opendevin/opendevin:main` comme image (dernière ligne).
+Si vous souhaitez utiliser la version **(instable !)** la plus récente, vous pouvez utiliser `ghcr.io/all-hands-ai/openhands:main` comme image (dernière ligne).
 :::
 
-Pour le workflow de développement, consultez [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md).
+Pour le workflow de développement, consultez [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
 
 Avez-vous des problèmes ? Consultez notre [Guide de dépannage](https://docs.all-hands.dev/modules/usage/troubleshooting).
 
 :::warning
-OpenDevin est actuellement en cours de développement, mais vous pouvez déjà exécuter la version alpha pour voir le système de bout en bout en action.
+OpenHands est actuellement en cours de développement, mais vous pouvez déjà exécuter la version alpha pour voir le système de bout en bout en action.
 :::
 
-[contributors-shield]: https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge
-[contributors-url]: https://github.com/OpenDevin/OpenDevin/graphs/contributors
-[forks-shield]: https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge
-[forks-url]: https://github.com/OpenDevin/OpenDevin/network/members
-[stars-shield]: https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge
-[stars-url]: https://github.com/OpenDevin/OpenDevin/stargazers
-[issues-shield]: https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge
-[issues-url]: https://github.com/OpenDevin/OpenDevin/issues
-[license-shield]: https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge
-[license-url]: https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE
+[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

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

@@ -2,11 +2,11 @@
 
 ## Complétion
 
-OpenDevin utilise LiteLLM pour les appels de complétion. Vous pouvez trouver leur documentation sur Azure [ici](https://docs.litellm.ai/docs/providers/azure)
+OpenHands utilise LiteLLM pour les appels de complétion. Vous pouvez trouver leur documentation sur Azure [ici](https://docs.litellm.ai/docs/providers/azure)
 
 ### Configurations openai Azure
 
-Lors de l'exécution de l'image Docker OpenDevin, vous devrez définir les variables d'environnement suivantes en utilisant `-e` :
+Lors de l'exécution de l'image Docker OpenHands, vous devrez définir les variables d'environnement suivantes en utilisant `-e` :
 
 ```
 LLM_BASE_URL="<azure-api-base-url>"          # e.g. "https://openai-gpt-4-test-v-1.openai.azure.com/"
@@ -16,19 +16,19 @@ LLM_API_VERSION = "<api-version>"          # e.g. "2024-02-15-preview"
 ```
 
 :::note
-Vous pouvez trouver le nom de votre déploiement ChatGPT sur la page des déploiements sur Azure. Par défaut ou initialement, il pourrait être le même que le nom du modèle de chat (par exemple 'GPT4-1106-preview'), mais il n'est pas obligé de l'être. Exécutez OpenDevin, et une fois chargé dans le navigateur, allez dans Paramètres et définissez le modèle comme suit : "azure/&lt;your-actual-gpt-deployment-name&gt;". Si ce n'est pas dans la liste, entrez votre propre texte et enregistrez-le.
+Vous pouvez trouver le nom de votre déploiement ChatGPT sur la page des déploiements sur Azure. Par défaut ou initialement, il pourrait être le même que le nom du modèle de chat (par exemple 'GPT4-1106-preview'), mais il n'est pas obligé de l'être. Exécutez OpenHands, et une fois chargé dans le navigateur, allez dans Paramètres et définissez le modèle comme suit : "azure/&lt;your-actual-gpt-deployment-name&gt;". Si ce n'est pas dans la liste, entrez votre propre texte et enregistrez-le.
 :::
 
 ## Embeddings
 
-OpenDevin utilise llama-index pour les embeddings. Vous pouvez trouver leur documentation sur Azure [ici](https://docs.llamaindex.ai/en/stable/api_reference/embeddings/azure_openai/)
+OpenHands utilise llama-index pour les embeddings. Vous pouvez trouver leur documentation sur Azure [ici](https://docs.llamaindex.ai/en/stable/api_reference/embeddings/azure_openai/)
 
 ### Configurations openai Azure
 
 Le modèle utilisé pour les embeddings Azure OpenAI est "text-embedding-ada-002".
 Vous avez besoin du nom de déploiement correct pour ce modèle dans votre compte Azure.
 
-Lors de l'exécution d'OpenDevin dans Docker, définissez les variables d'environnement suivantes en utilisant `-e` :
+Lors de l'exécution d'OpenHands dans Docker, définissez les variables d'environnement suivantes en utilisant `-e` :
 
 ```
 LLM_EMBEDDING_MODEL="azureopenai"

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

@@ -2,14 +2,14 @@
 
 ## Complétion
 
-OpenDevin utilise LiteLLM pour les appels de complétion. Les ressources suivantes sont pertinentes pour utiliser OpenDevin avec les LLMs de Google :
+OpenHands utilise LiteLLM pour les appels de complétion. Les ressources suivantes sont pertinentes pour utiliser OpenHands avec les LLMs de Google :
 
 - [Gemini - Google AI Studio](https://docs.litellm.ai/docs/providers/gemini)
 - [VertexAI - Google Cloud Platform](https://docs.litellm.ai/docs/providers/vertex)
 
 ### Configurations de Gemini - Google AI Studio
 
-Pour utiliser Gemini via Google AI Studio lors de l'exécution de l'image Docker d'OpenDevin, vous devez définir les variables d'environnement suivantes en utilisant `-e` :
+Pour utiliser Gemini via Google AI Studio lors de l'exécution de l'image Docker d'OpenHands, vous devez définir les variables d'environnement suivantes en utilisant `-e` :
 
 ```
 GEMINI_API_KEY="<votre-cle-api-google>"
@@ -18,7 +18,7 @@ LLM_MODEL="gemini/gemini-1.5-pro"
 
 ### Configurations de Vertex AI - Google Cloud Platform
 
-Pour utiliser Vertex AI via Google Cloud Platform lors de l'exécution de l'image Docker d'OpenDevin, vous devez définir les variables d'environnement suivantes en utilisant `-e` :
+Pour utiliser Vertex AI via Google Cloud Platform lors de l'exécution de l'image Docker d'OpenHands, vous devez définir les variables d'environnement suivantes en utilisant `-e` :
 
 ```
 GOOGLE_APPLICATION_CREDENTIALS="<dump-json-du-compte-de-service-gcp-json>"

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

@@ -4,16 +4,16 @@ sidebar_position: 2
 
 # 🤖 Backends LLM
 
-OpenDevin peut fonctionner avec n'importe quel backend LLM.
+OpenHands peut fonctionner avec n'importe quel backend LLM.
 Pour une liste complète des fournisseurs et des modèles LM disponibles, veuillez consulter la
 [documentation litellm](https://docs.litellm.ai/docs/providers).
 
 :::warning
-OpenDevin émettra de nombreuses invitations au LLM que vous configurez. La plupart de ces LLM coûtent de l'argent -- assurez-vous de définir des limites de dépenses et de surveiller l'utilisation.
+OpenHands émettra de nombreuses invitations au LLM que vous configurez. La plupart de ces LLM coûtent de l'argent -- assurez-vous de définir des limites de dépenses et de surveiller l'utilisation.
 :::
 
 La variable d'environnement `LLM_MODEL` contrôle le modèle utilisé dans les interactions programmatiques.
-Mais en utilisant l'interface utilisateur OpenDevin, vous devrez choisir votre modèle dans la fenêtre des paramètres (la roue dentée en bas à gauche).
+Mais en utilisant l'interface utilisateur OpenHands, vous devrez choisir votre modèle dans la fenêtre des paramètres (la roue dentée en bas à gauche).
 
 Les variables d'environnement suivantes peuvent être nécessaires pour certains LLM :
 
@@ -23,10 +23,10 @@ Les variables d'environnement suivantes peuvent être nécessaires pour certains
 - `LLM_EMBEDDING_DEPLOYMENT_NAME`
 - `LLM_API_VERSION`
 
-Nous avons quelques guides pour exécuter OpenDevin avec des fournisseurs de modèles spécifiques :
+Nous avons quelques guides pour exécuter OpenHands avec des fournisseurs de modèles spécifiques :
 
-- [ollama](llms/localLLMs)
-- [Azure](llms/azureLLMs)
+- [ollama](llms/local-llms)
+- [Azure](llms/azure-llms)
 
 Si vous utilisez un autre fournisseur, nous vous encourageons à ouvrir une PR pour partager votre configuration !
 
@@ -34,11 +34,11 @@ Si vous utilisez un autre fournisseur, nous vous encourageons à ouvrir une PR p
 
 Les meilleurs modèles sont GPT-4 et Claude 3. Les modèles locaux et open source actuels ne sont pas aussi puissants.
 Lors de l'utilisation d'un modèle alternatif, vous pouvez constater des temps d'attente prolongés entre les messages,
-des réponses de mauvaise qualité ou des erreurs sur des JSON mal formés. OpenDevin
+des réponses de mauvaise qualité ou des erreurs sur des JSON mal formés. OpenHands
 ne peut être aussi puissant que les modèles qui le pilotent -- heureusement, les membres de notre équipe travaillent activement à la construction de meilleurs modèles open source !
 
 ## Réessais d'API et limites de taux
 
-Certains LLM ont des limites de taux et peuvent nécessiter des réessais. OpenDevin réessaiera automatiquement les demandes s'il reçoit une erreur 429 ou une erreur de connexion API.
+Certains LLM ont des limites de taux et peuvent nécessiter des réessais. OpenHands réessaiera automatiquement les demandes s'il reçoit une erreur 429 ou une erreur de connexion API.
 Vous pouvez définir les variables d'environnement `LLM_NUM_RETRIES`, `LLM_RETRY_MIN_WAIT`, `LLM_RETRY_MAX_WAIT` pour contrôler le nombre de réessais et le temps entre les réessais.
-Par défaut, `LLM_NUM_RETRIES` est 5 et `LLM_RETRY_MIN_WAIT`, `LLM_RETRY_MAX_WAIT` sont respectivement de 3 secondes et 60 secondes.
+Par défaut, `LLM_NUM_RETRIES` est 8 et `LLM_RETRY_MIN_WAIT`, `LLM_RETRY_MAX_WAIT` sont respectivement de 15 secondes et 120 secondes.

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

@@ -24,11 +24,11 @@ mistral:7b-instruct-v0.2-q4_K_M eb14864c7427    4.4 GB  2 weeks ago
 starcoder2:latest               f67ae0f64584    1.7 GB  19 hours ago
 ```
 
-## Démarrer OpenDevin
+## Démarrer OpenHands
 
 ### Docker
 
-Utilisez les instructions [ici](../intro) pour démarrer OpenDevin en utilisant Docker.
+Utilisez les instructions [ici](../intro) pour démarrer OpenHands en utilisant Docker.
 Mais lors de l'exécution de `docker run`, vous devrez ajouter quelques arguments supplémentaires :
 
 ```bash
@@ -40,7 +40,7 @@ Mais lors de l'exécution de `docker run`, vous devrez ajouter quelques argument
 Par exemple :
 
 ```bash
-# Le répertoire que vous souhaitez qu'OpenDevin modifie. DOIT être un chemin absolu !
+# Le répertoire que vous souhaitez qu'OpenHands modifie. DOIT être un chemin absolu !
 export WORKSPACE_BASE=$(pwd)/workspace
 
 docker run \
@@ -54,14 +54,14 @@ docker run \
     -v $WORKSPACE_BASE:/opt/workspace_base \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
-    ghcr.io/opendevin/opendevin:main
+    ghcr.io/all-hands-ai/openhands:main
 ```
 
 Vous devriez maintenant pouvoir vous connecter à `http://localhost:3000/`
 
 ### Compiler à partir des sources
 
-Utilisez les instructions dans [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md) pour compiler OpenDevin.
+Utilisez les instructions dans [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) pour compiler OpenHands.
 Assurez-vous que `config.toml` soit présent en exécutant `make setup-config` qui en créera un pour vous. Dans `config.toml`, saisissez les éléments suivants :
 
 ```
@@ -75,11 +75,11 @@ WORKSPACE_DIR="$(pwd)/workspace"
 
 Remplacez `LLM_MODEL` par celui de votre choix si nécessaire.
 
-Fini ! Vous pouvez maintenant démarrer Devin avec : `make run` sans Docker. Vous devriez maintenant pouvoir vous connecter à `http://localhost:3000/`
+Fini ! Vous pouvez maintenant démarrer OpenHands avec : `make run` sans Docker. Vous devriez maintenant pouvoir vous connecter à `http://localhost:3000/`
 
 ## Sélection de votre modèle
 
-Dans l'interface OpenDevin, cliquez sur l'icône des paramètres en bas à gauche.
+Dans l'interface OpenHands, cliquez sur l'icône des paramètres en bas à gauche.
 Ensuite, dans l'entrée `Model`, saisissez `ollama/codellama:7b`, ou le nom du modèle que vous avez téléchargé précédemment.
 S'il n'apparaît pas dans un menu déroulant, ce n'est pas grave, tapez-le simplement. Cliquez sur Enregistrer lorsque vous avez terminé.
 
@@ -87,7 +87,7 @@ Et maintenant, vous êtes prêt à démarrer !
 
 ## Configuration du service ollama (WSL){#configuring-ollama-service-fr}
 
-La configuration par défaut pour ollama sous WSL ne sert que localhost. Cela signifie que vous ne pouvez pas l'atteindre depuis un conteneur docker, par exemple, il ne fonctionnera pas avec OpenDevin. Testons d'abord que ollama est en cours d'exécution correctement.
+La configuration par défaut pour ollama sous WSL ne sert que localhost. Cela signifie que vous ne pouvez pas l'atteindre depuis un conteneur docker, par exemple, il ne fonctionnera pas avec OpenHands. Testons d'abord que ollama est en cours d'exécution correctement.
 
 ```bash
 ollama list # obtenir la liste des modèles installés
@@ -99,7 +99,7 @@ curl http://localhost:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
 Une fois cela fait, testez qu'il accepte les requêtes "externes", comme celles provenant d'un conteneur docker.
 
 ```bash
-docker ps # obtenir la liste des conteneurs docker en cours d'exécution, pour un test le plus précis choisissez le conteneur de sandbox open devin.
+docker ps # obtenir la liste des conteneurs docker en cours d'exécution, pour un test le plus précis choisissez le conteneur de sandbox OpenHands.
 docker exec [CONTAINER ID] curl http://host.docker.internal:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
 #ex. docker exec cd9cc82f7a11 curl http://host.docker.internal:11434/api/generate -d '{"model":"codellama","prompt":"hi"}'
 ```
@@ -136,6 +136,6 @@ Enfin, testez que ollama est accessible depuis le conteneur
 
 ```bash
 ollama list # obtenir la liste des modèles installés
-docker ps # obtenir la liste des conteneurs docker en cours d'exécution, pour un test le plus précis choisissez le conteneur de sandbox open devin.
+docker ps # obtenir la liste des conteneurs docker en cours d'exécution, pour un test le plus précis choisissez le conteneur de sandbox OpenHands.
 docker exec [CONTAINER ID] curl http://host.docker.internal:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
 ```

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

@@ -20,7 +20,7 @@ Si vous utilisez Windows et que vous rencontrez des problèmes, consultez notre
 
 ## Impossible de se connecter à Docker
 
-[Problème GitHub](https://github.com/OpenDevin/OpenDevin/issues/1226)
+[Problème GitHub](https://github.com/All-Hands-AI/OpenHands/issues/1226)
 
 ### Symptômes
 
@@ -34,7 +34,7 @@ docker.errors.DockerException: Erreur lors de la récupération de la version de
 
 ### Détails
 
-OpenDevin utilise un conteneur Docker pour effectuer son travail en toute sécurité, sans risquer de briser votre machine.
+OpenHands utilise un conteneur Docker pour effectuer son travail en toute sécurité, sans risquer de briser votre machine.
 
 ### Solutions de contournement
 
@@ -45,7 +45,7 @@ OpenDevin utilise un conteneur Docker pour effectuer son travail en toute sécur
 
 ## Impossible de se connecter à la boîte SSH
 
-[Problème GitHub](https://github.com/OpenDevin/OpenDevin/issues/1156)
+[Problème GitHub](https://github.com/All-Hands-AI/OpenHands/issues/1156)
 
 ### Symptômes
 
@@ -57,7 +57,7 @@ pexpect.pxssh.ExceptionPxssh: Impossible d'établir une connexion avec l'hôte
 
 ### Détails
 
-Par défaut, OpenDevin se connecte à un conteneur en cours d'exécution via SSH. Sur certaines machines,
+Par défaut, OpenHands se connecte à un conteneur en cours d'exécution via SSH. Sur certaines machines,
 en particulier Windows, cela semble échouer.
 
 ### Solutions de contournement
@@ -65,11 +65,11 @@ en particulier Windows, cela semble échouer.
 * Redémarrez votre ordinateur (parfois cela fonctionne)
 * Assurez-vous d'avoir les dernières versions de WSL et Docker
 * Vérifiez que votre distribution dans WSL est également à jour
-* Essayez [ce guide de réinstallation](https://github.com/OpenDevin/OpenDevin/issues/1156#issuecomment-2064549427)
+* Essayez [ce guide de réinstallation](https://github.com/All-Hands-AI/OpenHands/issues/1156#issuecomment-2064549427)
 
 ## Impossible de se connecter à LLM
 
-[Problème GitHub](https://github.com/OpenDevin/OpenDevin/issues/1208)
+[Problème GitHub](https://github.com/All-Hands-AI/OpenHands/issues/1208)
 
 ### Symptômes
 
@@ -82,10 +82,10 @@ AttributeError: 'NoneType' object has no attribute 'request'
 
 ### Détails
 
-[Problèmes GitHub](https://github.com/OpenDevin/OpenDevin/issues?q=is%3Aissue+is%3Aopen+404)
+[Problèmes GitHub](https://github.com/All-Hands-AI/OpenHands/issues?q=is%3Aissue+is%3Aopen+404)
 
-Cela se produit généralement avec les configurations de LLM *locales*, lorsque OpenDevin ne parvient pas à se connecter au serveur LLM.
-Consultez notre guide pour [LLMs locaux](llms/localLLMs) pour plus d'informations.
+Cela se produit généralement avec les configurations de LLM *locales*, lorsque OpenHands ne parvient pas à se connecter au serveur LLM.
+Consultez notre guide pour [LLMs locaux](llms/local-llms) pour plus d'informations.
 
 ### Solutions de contournement
 
@@ -133,9 +133,9 @@ le point de terminaison API avec lequel vous essayez de vous connecter. Cela arr
   * Si vous êtes en cours d'exécution dans l'interface utilisateur, assurez-vous de définir le `model` dans le modal des paramètres
   * Si vous êtes en cours d'exécution sans interface (via main.py), assurez-vous de définir `LLM_MODEL` dans votre env/config
 * Assurez-vous de suivre les instructions spéciales de votre fournisseur de LLM
-  * [ollama](/fr/modules/usage/llms/localLLMs)
-  * [Azure](/fr/modules/usage/llms/azureLLMs)
-  * [Google](/fr/modules/usage/llms/googleLLMs)
+  * [ollama](/fr/modules/usage/llms/local-llms)
+  * [Azure](/fr/modules/usage/llms/azure-llms)
+  * [Google](/fr/modules/usage/llms/google-llms)
 * Assurez-vous que votre clé API est correcte
 * Voyez si vous pouvez vous connecter au LLM en utilisant `curl`
 * Essayez de [vous connecter via LiteLLM directement](https://github.com/BerriAI/litellm) pour tester votre configuration
@@ -179,24 +179,24 @@ export PYTHON_KEYRING_BACKEND=keyring.backends.null.Keyring
 
 ### Symptômes
 
-OpenDevin demande généralement s'il faut reprendre ou commencer une nouvelle session lors de l'ouverture de l'interface utilisateur.
+OpenHands demande généralement s'il faut reprendre ou commencer une nouvelle session lors de l'ouverture de l'interface utilisateur.
 Mais cliquer sur "Reprendre" démarre toujours une toute nouvelle discussion.
 
 ### Détails
 
 Avec une installation standard à ce jour, les données de session sont stockées en mémoire.
-Actuellement, si le service OpenDevin est redémarré, les sessions précédentes deviennent
+Actuellement, si le service OpenHands est redémarré, les sessions précédentes deviennent
 invalides (un nouveau secret est généré) et donc non récupérables.
 
 ### Solutions de contournement
 
 * Modifiez la configuration pour rendre les sessions persistantes en éditant le fichier `config.toml`
-(dans le dossier racine d'OpenDevin) en spécifiant un `file_store` et un
+(dans le dossier racine d'OpenHands) en spécifiant un `file_store` et un
 `file_store_path` absolu :
 
 ```toml
 file_store="local"
-file_store_path="/absolute/path/to/opendevin/cache/directory"
+file_store_path="/absolute/path/to/openhands/cache/directory"
 ```
 
 * Ajoutez un secret jwt fixe dans votre .bashrc, comme ci-dessous, afin que les id de session précédents

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

@@ -1,6 +1,6 @@
 # Notes pour les utilisateurs de Windows et WSL
 
-OpenDevin ne supporte Windows que via [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
+OpenHands ne supporte Windows que via [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
 Veuillez vous assurer de lancer toutes les commandes à l'intérieur de votre terminal WSL.
 
 ## Dépannage
@@ -12,8 +12,8 @@ Docker doit également avoir l'option d'intégration WSL activée.
 
 ### Recommandation : Ne pas exécuter en tant qu'utilisateur root
 
-Pour des raisons de sécurité, il est fortement recommandé de ne pas exécuter OpenDevin en tant qu'utilisateur root, mais en tant qu'utilisateur avec un UID non nul.
-De plus, les sandboxes persistants ne seront pas pris en charge lors de l'exécution en tant que root et un message approprié pourrait apparaître lors du démarrage d'OpenDevin.
+Pour des raisons de sécurité, il est fortement recommandé de ne pas exécuter OpenHands en tant qu'utilisateur root, mais en tant qu'utilisateur avec un UID non nul.
+De plus, les sandboxes persistants ne seront pas pris en charge lors de l'exécution en tant que root et un message approprié pourrait apparaître lors du démarrage d'OpenHands.
 
 Références :
 
@@ -21,12 +21,12 @@ Références :
 * [Définir l'utilisateur par défaut dans WSL](https://www.tenforums.com/tutorials/128152-set-default-user-windows-subsystem-linux-distro-windows-10-a.html#option2)
 Astuce pour la 2e référence : pour les utilisateurs d'Ubuntu, la commande pourrait en fait être "ubuntupreview" au lieu de "ubuntu".
 
-### Échec de la création de l'utilisateur opendevin
+### Échec de la création de l'utilisateur openhands
 
 Si vous rencontrez l'erreur suivante lors de l'installation :
 
 ```sh
-Exception: Failed to create opendevin user in sandbox: 'useradd: UID 0 is not unique'
+Exception: Failed to create openhands user in sandbox: 'useradd: UID 0 is not unique'
 ```
 
 Vous pouvez la résoudre en exécutant :

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

@@ -1,10 +1,10 @@
 {
   "title": {
-    "message": "OpenDevin",
+    "message": "OpenHands",
     "description": "The title in the navbar"
   },
   "logo.alt": {
-    "message": "OpenDevin",
+    "message": "OpenHands",
     "description": "The alt text of navbar logo"
   },
   "item.label.Docs": {

docs/i18n/zh-Hans/code.json

@@ -1,6 +1,6 @@
 {
   "footer.title": {
-    "message": "OpenDevin"
+    "message": "OpenHands"
   },
   "footer.docs": {
     "message": "文档"
@@ -9,7 +9,7 @@
     "message": "社区"
   },
   "footer.copyright": {
-    "message": "版权所有 © {year} OpenDevin"
+    "message": "版权所有 © {year} OpenHands"
   },
   "faq.title": {
     "message": "常见问题解答",
@@ -19,20 +19,20 @@
     "message": "常见问题解答"
   },
   "faq.section.title.1": {
-    "message": "什么是OpenDevin？",
+    "message": "什么是OpenHands？",
     "description": "First Section Title"
   },
   "faq.section.highlight": {
-    "message": "OpenDevin",
+    "message": "OpenHands",
     "description": "Highlight Text"
   },
   "faq.section.description.1": {
-    "message": "是一个自主的软件工程师，能够端到端地解决软件工程和网页浏览任务。它能执行数据科学查询，如 \"查找上个月OpenDevin仓库中的拉取请求数量\"，还能处理软件工程任务，例如 \"请为这个文件添加测试并验证所有测试都通过，如果没有修复该文件\"。",
-    "description": "Description for OpenDevin"
+    "message": "是一个自主的软件工程师，能够端到端地解决软件工程和网页浏览任务。它能执行数据科学查询，如 \"查找上个月OpenHands仓库中的拉取请求数量\"，还能处理软件工程任务，例如 \"请为这个文件添加测试并验证所有测试都通过，如果没有修复该文件\"。",
+    "description": "Description for OpenHands"
   },
   "faq.section.description.2": {
-    "message": "同时，OpenDevin是一个代理开发者平台和社区，用于测试和评估新代理的环境。",
-    "description": "Further Description for OpenDevin"
+    "message": "同时，OpenHands是一个代理开发者平台和社区，用于测试和评估新代理的环境。",
+    "description": "Further Description for OpenHands"
   },
   "faq.section.title.2": {
     "message": "支持",
@@ -43,15 +43,15 @@
     "description": "Support Answer"
   },
   "faq.section.title.3": {
-    "message": "如何使用OpenDevin解决GitHub上的问题？",
+    "message": "如何使用OpenHands解决GitHub上的问题？",
     "description": "GitHub Issue Section Title"
   },
   "faq.section.github.steps.intro": {
-    "message": "要通过OpenDevin解决GitHub上的问题，您可以发送一个提示给OpenDevin，请它按照以下步骤操作：",
+    "message": "要通过OpenHands解决GitHub上的问题，您可以发送一个提示给OpenHands，请它按照以下步骤操作：",
     "description": "GitHub Steps Introduction"
   },
   "faq.section.github.step1": {
-    "message": "阅读问题 https://github.com/OpenDevin/OpenDevin/issues/1611",
+    "message": "阅读问题 https://github.com/All-Hands-AI/OpenHands/issues/1611",
     "description": "GitHub Step 1"
   },
   "faq.section.github.step2": {
@@ -71,11 +71,11 @@
     "description": "GitHub Step 5"
   },
   "faq.section.github.steps.preRun": {
-    "message": "在运行OpenDevin之前，您可以：",
+    "message": "在运行OpenHands之前，您可以：",
     "description": "GitHub Steps Pre-Run"
   },
   "faq.section.github.steps.tokenInfo": {
-    "message": "其中XXX是您创建的一个具有对OpenDevin仓库写权限的GitHub令牌。如果您的写入权限不足，请将其更改为：",
+    "message": "其中XXX是您创建的一个具有对OpenHands仓库写权限的GitHub令牌。如果您的写入权限不足，请将其更改为：",
     "description": "GitHub Steps Token Info"
   },
   "faq.section.github.steps.usernameInfo": {
@@ -83,23 +83,23 @@
     "description": "GitHub Steps Username Info"
   },
   "faq.section.title.4": {
-    "message": "OpenDevin与Devin有何不同？",
+    "message": "OpenHands与Devin有何不同？",
     "description": "Devin Section Title"
   },
-  "faq.section.devin.linkText": {
+  "faq.section.openhands.linkText": {
     "message": "Devin",
     "description": "Devin Link Text"
   },
-  "faq.section.devin.description": {
-    "message": "是由Cognition Inc.开发的商业产品，它最初为OpenDevin提供了灵感。它们都旨在擅长解决软件工程任务，但您可以下载、使用和修改OpenDevin，而Devin只能通过Cognition网站进行访问。此外，OpenDevin已超越最初的灵感，并成为一个面向代理开发者的社区驱动生态系统，在这里我们欢迎您加入并",
+  "faq.section.openhands.description": {
+    "message": "是由Cognition Inc.开发的商业产品，它最初为OpenHands提供了灵感。它们都旨在擅长解决软件工程任务，但您可以下载、使用和修改OpenHands，而Devin只能通过Cognition网站进行访问。此外，OpenHands已超越最初的灵感，并成为一个面向代理开发者的社区驱动生态系统，在这里我们欢迎您加入并",
     "description": "Devin Description"
   },
-  "faq.section.devin.contribute": {
+  "faq.section.openhands.contribute": {
     "message": "贡献",
     "description": "Contribute Link"
   },
   "faq.section.title.5": {
-    "message": "OpenDevin与ChatGPT有何不同？",
+    "message": "OpenHands与ChatGPT有何不同？",
     "description": "ChatGPT Section Title"
   },
   "faq.section.chatgpt.description": {
@@ -114,7 +114,7 @@
     "message": "开始使用"
   },
   "welcome.message": {
-    "message": "欢迎来到OpenDevin，这是一个开源自主AI软件工程师，能够执行复杂的工程任务，并积极参与用户在软件开发项目中的协作。"
+    "message": "欢迎来到OpenHands，这是一个开源自主AI软件工程师，能够执行复杂的工程任务，并积极参与用户在软件开发项目中的协作。"
   },
   "theme.ErrorPageContent.title": {
     "message": "页面已崩溃。",

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

@@ -19,35 +19,35 @@ sidebar_position: 7
 
 ## 🤝 如何贡献
 
-OpenDevin 是一个社区驱动的项目，我们欢迎每个人的贡献。无论您是开发人员、研究人员，还是对用 AI 提升软件工程领域有兴趣，只要您愿意参与，我们都有很多方式可供选择：
+OpenHands 是一个社区驱动的项目，我们欢迎每个人的贡献。无论您是开发人员、研究人员，还是对用 AI 提升软件工程领域有兴趣，只要您愿意参与，我们都有很多方式可供选择：
 
 - **代码贡献:** 帮助我们开发核心功能、前端界面或沙箱解决方案。
 - **研究和评价:** 贡献您对 LLM 在软件工程领域理解的见解，参与评估模型，或提出改进建议。
-- **反馈和测试:** 使用 OpenDevin 工具集，报告错误，建议功能，或提供可用性方面的反馈。
+- **反馈和测试:** 使用 OpenHands 工具集，报告错误，建议功能，或提供可用性方面的反馈。
 
-详情请查阅[此文件](https://github.com/OpenDevin/OpenDevin/blob/main/CONTRIBUTING.md)。
+详情请查阅[此文件](https://github.com/All-Hands-AI/OpenHands/blob/main/CONTRIBUTING.md)。
 
 ## 🤖 加入我们的社区
 
-我们现在有一个 Slack 工作区，用于合作建设 OpenDevin，还设有一个 Discord 服务器，用于讨论与该项目、LLM、代理等相关的任何事情。
+我们现在有一个 Slack 工作区，用于合作建设 OpenHands，还设有一个 Discord 服务器，用于讨论与该项目、LLM、代理等相关的任何事情。
 
-- [Slack 工作区](https://join.slack.com/t/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA)
+- [Slack 工作区](https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA)
 - [Discord 服务器](https://discord.gg/ESHStjSjD4)
 
 如果您愿意贡献，请随时加入我们的社区。让我们一起简化软件工程！
 
-🐚 **少写代码，用 OpenDevin 做更多的事情。**
+🐚 **少写代码，用 OpenHands 做更多的事情。**
 
-[![Star History Chart](https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date)](https://star-history.com/#OpenDevin/OpenDevin&Date)
+[![Star History Chart](https://api.star-history.com/svg?repos=All-Hands-AI/OpenHands&type=Date)](https://star-history.com/#All-Hands-AI/OpenHands&Date)
 
 ## 🛠️ 技术选型
 
-OpenDevin 使用了一系列强大的框架和库，提供了坚实的开发基础。以下是项目中使用的关键技术：
+OpenHands 使用了一系列强大的框架和库，提供了坚实的开发基础。以下是项目中使用的关键技术：
 
 ![FastAPI](https://img.shields.io/badge/FastAPI-black?style=for-the-badge) ![uvicorn](https://img.shields.io/badge/uvicorn-black?style=for-the-badge) ![LiteLLM](https://img.shields.io/badge/LiteLLM-black?style=for-the-badge) ![Docker](https://img.shields.io/badge/Docker-black?style=for-the-badge) ![Ruff](https://img.shields.io/badge/Ruff-black?style=for-the-badge) ![MyPy](https://img.shields.io/badge/MyPy-black?style=for-the-badge) ![LlamaIndex](https://img.shields.io/badge/LlamaIndex-black?style=for-the-badge) ![React](https://img.shields.io/badge/React-black?style=for-the-badge)
 
-请注意，这些技术选型仍在进行中，随着项目的发展，可能会添加新的技术或移除现有的技术。我们努力采用最适合、最高效的工具，以增强 OpenDevin 的能力。
+请注意，这些技术选型仍在进行中，随着项目的发展，可能会添加新的技术或移除现有的技术。我们努力采用最适合、最高效的工具，以增强 OpenHands 的能力。
 
 ## 📜 许可证
 
-根据 MIT 许可证分发。详见[我们的许可证](https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE)了解更多信息。
+根据 MIT 许可证分发。详见[我们的许可证](https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE)了解更多信息。

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

@@ -18,18 +18,18 @@ sidebar_position: 3
 - 执行任何有效的Linux `bash`命令
 - 使用[交互式Python解释器](https://ipython.org/)执行任何有效的 `Python`代码。这是通过`bash`命令模拟的，详细信息请参见插件系统。
 
-![image](https://github.com/OpenDevin/OpenDevin/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
+![image](https://github.com/All-Hands-AI/OpenHands/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
 
 ### 插件系统
 
-为了使CodeAct agent在仅能访问`bash`动作空间时更强大，CodeAct agent利用了OpenDevin的插件系统：
+为了使CodeAct agent在仅能访问`bash`动作空间时更强大，CodeAct agent利用了OpenHands的插件系统：
 
-- [Jupyter插件](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/jupyter)：通过bash命令实现IPython执行
-- [SWE-agent工具插件](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/swe_agent_commands)：为软件开发任务引入的强大bash命令行工具，由[swe-agent](https://github.com/princeton-nlp/swe-agent)提供。
+- [Jupyter插件](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/runtime/plugins/jupyter)：通过bash命令实现IPython执行
+- [SWE-agent工具插件](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/runtime/plugins/swe_agent_commands)：为软件开发任务引入的强大bash命令行工具，由[swe-agent](https://github.com/princeton-nlp/swe-agent)提供。
 
 ### 演示
 
-https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
+https://github.com/All-Hands-AI/OpenHands/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
 
 _CodeActAgent使用`gpt-4-turbo-2024-04-09`执行数据科学任务（线性回归）的示例_
 

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

@@ -25,13 +25,13 @@ _**免责声明**：后端架构正在进行中，可能会有所变化。下图
 
     ## 前提条件
 
-    - 能运行 python 环境，其中 opendevin 可以执行（根据存储库根目录中的 README.md 文件中的说明）
+    - 能运行 python 环境，其中 openhands 可以执行（根据存储库根目录中的 README.md 文件中的说明）
     - 安装了 [py2puml](https://github.com/lucsorel/py2puml)
 
 ## 步骤
 
 1.  通过从存储库根目录运行以下命令自动生成图表：
-    `py2puml opendevin opendevin > docs/architecture/backend_architecture.puml`
+    `py2puml openhands openhands > docs/architecture/backend_architecture.puml`
 
 2.  在 PlantUML 编辑器中打开生成的文件，例如使用 PlantUML 扩展的 Visual Studio Code 或 [PlantText](https://www.planttext.com/)
 

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

@@ -1,14 +1,31 @@
 # 💿 如何创建自定义 Docker 沙箱
 
-默认的 OpenDevin 沙箱包含一个[最小化 ubuntu 配置](https://github.com/OpenDevin/OpenDevin/blob/main/containers/sandbox/Dockerfile)。您的应用场景可能需要在默认状态下安装额外的软件。本指南将教您如何通过使用自定义 Docker 映像来实现这一目标。
+默认的 OpenHands 沙箱包含一个[最小化 ubuntu 配置](https://github.com/All-Hands-AI/OpenHands/blob/main/containers/sandbox/Dockerfile)。您的应用场景可能需要在默认状态下安装额外的软件。本指南将教您如何通过使用自定义 Docker 映像来实现这一目标。
+
+目前提供两种实现方案：
+1. 从 Docker Hub 拉取已有镜像。例如，如果您想安装 `nodejs` ，您可以通过使用 `node:20` 镜像来实现。
+2. 创建并使用您自定义 Docker 镜像。
+
+若选择第一种方案，您可以直接略过 `Create Your Docker Image` 部分。
+
+为了获得功能更丰富的环境，您可能想要考虑使用预构建的镜像，比如 [nikolaik/python-nodejs](https://hub.docker.com/r/nikolaik/python-nodejs)，这个镜像预装了 Python 和 Node.js，同时还包含了许多其他有用的工具和库，比如：
+
+- Node.js: 22.x
+- npm: 10.x
+- yarn: stable
+- Python: latest
+- pip: latest
+- pipenv: latest
+- poetry: latest
+- uv: latest
 
 ## 环境设置
 
-确保您能够首先通过 [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md) 运行 OpenDevin。
+确保您能够首先通过 [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) 运行 OpenHands。
 
 ## 创建您的 Docker 映像
 
-接下来，您必须创建一个自定义的 Docker 映像，该映像是基于 Debian 或 Ubuntu 的。例如，如果我们希望 OpenDevin 能够访问 "node" 可执行文件，我们可以使用以下 `Dockerfile`:
+接下来，您可以开始创建一个自定义的 Docker 映像，该映像必须是基于 Debian 或 Ubuntu 的。例如，如果我们希望 OpenHands 能够访问 `node` 可执行文件，我们可以使用以下 `Dockerfile`:
 
 ```bash
 # 从最新版 ubuntu 开始
@@ -21,7 +38,7 @@ RUN apt-get update && apt-get install
 RUN apt-get install -y nodejs
 ```
 
-然后构建您选择的映像，例如“custom_image”。为此可以在目录中创建文件夹并将 `Dockerfile` 放入其中，并在该目录内运行以下命令：
+然后命名并构建您选择的映像，例如“custom_image”。为此可以创建一个文件夹并将 `Dockerfile` 放入其中，并在该文件夹内运行以下命令：
 
 ```bash
 docker build -t custom_image .
@@ -29,79 +46,57 @@ docker build -t custom_image .
 
 这将生成一个名为 ```custom_image``` 的新映像，并使其可用于 Docker 服务引擎。
 
-> 注意：在本文档描述的配置中，OpenDevin 将在沙箱内部以“opendevin”用户身份运行。因此，通过 Dockerfile 安装的所有包应可供系统上的所有用户使用，而不仅仅是 root 用户。
+> 注意：在本文档描述的配置中，OpenHands 将在沙箱内部以“openhands”用户身份运行。因此，通过 Dockerfile 安装的所有包应可供系统上的所有用户使用，而不仅仅是 root 用户。
 
-> 使用 `apt-get` 上面安装的 node 是为所有用户安装的。
+> `Dockerfile`中，使用 `apt-get` 安装的 node 是为所有用户安装的。
 
 ## 在 config.toml 文件中指定自定义映像
 
-在 OpenDevin 的配置通过顶层的 `config.toml` 文件发生。在 OpenDevin 目录下创建一个 ```config.toml``` 文件，并输入以下内容：
+在 OpenHands 的配置通过顶层的 `config.toml` 文件发生。在 OpenHands 目录下创建一个 ```config.toml``` 文件，并输入以下内容：
 
 ```
 [core]
 workspace_base="./workspace"
-persist_sandbox=false
-run_as_devin=true
-sandbox_container_image="custom_image"
+run_as_openhands=true
+sandbox_base_container_image="custom_image"
 ```
 
-> 确保 `sandbox_container_image` 设置为您前一步中自定义映像的名称。
+对于 `sandbox_base_container_image` 的值, 您可以选择以下任意一项：
+1. 在上一步中您构建的自定义镜像的名称（例如，`“custom_image”`）
+2. 从 Docker Hub 拉取的镜像（例如，`“node:20”`，如果你需要一个预装 `Node.js` 的沙箱环境）
 
 ## 运行
 
-通过运行 ```make run``` 在顶层目录下运行 OpenDevin。
+在顶层目录下通过执行 ```make run``` 运行 OpenHands。
 
 导航至 ```localhost:3001``` 并检查所需依赖是否可用。
 
-在上述示例的情况下，终端中运行 `node -v` 会输出 `v18.19.1`。
+在上述示例的情况下，终端中运行 `node -v` 会输出 `v20.15.0`。
 
 恭喜您！
 
 ## 技术解释
 
-相关代码定义在 [ssh_box.py](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/ssh_box.py) 和 [image_agnostic_util.py](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py) 中。
-
-特别是 ssh_box.py 检查配置对象中的 ```config.sandbox_container_image```，然后尝试使用 [get_od_sandbox_image](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py#L72)，在 image_agnostic_util.py 定义中进行检索。
-
-初次使用自定义映像时，该映像将不会被找到，因此将被构建（在后续运行中已构建的映像将被查找并返回）。
-
-自定义映像是通过 `_build_sandbox_image()` 构建的，在 [image_agnostic_util.py](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py#L29) 中，使用您的 custom_image 作为基础，并为 OpenDevin 配置环境。例如：
-
-```python
-dockerfile_content = (
-        f'FROM {base_image}\n'
-        'RUN apt update && apt install -y openssh-server wget sudo\n'
-        'RUN mkdir -p -m0755 /var/run/sshd\n'
-        'RUN mkdir -p /opendevin && mkdir -p /opendevin/logs && chmod 777 /opendevin/logs\n'
-        'RUN wget "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"\n'
-        'RUN bash Miniforge3-$(uname)-$(uname -m).sh -b -p /opendevin/miniforge3\n'
-        'RUN bash -c ". /opendevin/miniforge3/etc/profile.d/conda.sh && conda config --set changeps1 False && conda config --append channels conda-forge"\n'
-        'RUN echo "export PATH=/opendevin/miniforge3/bin:$PATH" >> ~/.bashrc\n'
-        'RUN echo "export PATH=/opendevin/miniforge3/bin:$PATH" >> /opendevin/bash.bashrc\n'
-    ).strip()
-```
-
-> 注意：映像名称通过 [_get_new_image_name()](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py#L63) 修改，并且是后续运行中搜索的修改后的名称。
+请参考[运行时文档中自定义 Docker 镜像的章节](https://docs.all-hands.dev/modules/usage/architecture/runtime#advanced-how-openhands-builds-and-maintains-od-runtime-images)获取更详细的解释。
 
 ## 故障排除 / 错误
 
 ### 错误：```useradd: UID 1000 is not unique```
 
-如果在控制台输出中看到此错误，说明 OpenDevin 尝试在沙箱中以 UID 1000 创建 opendevin 用户，但该 UID 已经被映像中的其他部分使用（不知何故）。要解决这个问题，请更改 config.toml 文件中的 sandbox_user_id 字段为不同的值：
+如果在控制台输出中看到此错误，说明 OpenHands 尝试在沙箱中以 UID 1000 创建 openhands 用户，但该 UID 已经被映像中的其他部分使用（不知何故）。要解决这个问题，请更改 config.toml 文件中的 sandbox_user_id 字段为不同的值：
 
 ```
 [core]
 workspace_base="./workspace"
-persist_sandbox=false
-run_as_devin=true
-sandbox_container_image="custom_image"
+run_as_openhands=true
+sandbox_base_container_image="custom_image"
 sandbox_user_id="1001"
 ```
 
 ### 端口使用错误
 
-如果您看到关于端口被占用或不可用的错误，请尝试删除所有正在运行的 Docker 容器（通过运行 `docker ps` 和 `docker rm` 相关容器），然后重新运行 ```make run```。
+如果您遇到端口被占用或不可用的错误提示，可以尝试先用`docker ps`命令列出所有运行中的 Docker 容器，然后使用`docker rm`命令删除相关容器，最后再重新执行```make run```命令。
 
 ## 讨论
 
-对于其他问题或疑问，请加入 [Slack](https://join.slack.com/t/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA) 或 [Discord](https://discord.gg/ESHStjSjD4)，并提问！
+对于其他问题或疑问，请加入 [Slack](https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA) 或 [Discord](https://discord.gg/ESHStjSjD4) 提问！

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

@@ -4,15 +4,15 @@ sidebar_position: 6
 
 # ✅ 提供反馈
 
-在使用 OpenDevin 时，你无疑会遇到一些情况，某些地方工作得很好，而另一些地方则可能不尽如人意。我们鼓励你在使用 OpenDevin 时提供反馈，这不仅有助于开发团队改善应用，更为重要的是，可以创建一个开放的编码代理训练样例语料库——Share-OpenDevin！
+在使用 OpenHands 时，你无疑会遇到一些情况，某些地方工作得很好，而另一些地方则可能不尽如人意。我们鼓励你在使用 OpenHands 时提供反馈，这不仅有助于开发团队改善应用，更为重要的是，可以创建一个开放的编码代理训练样例语料库——Share-OpenHands！
 
 ## 📝 如何提供反馈
 
-提供反馈很简单！在使用 OpenDevin 时，你可以在任意时刻按下点赞或点踩按钮。你将被要求提供你的电子邮件地址（例如，以便我们在需要进一步询问时联系你），你可以选择公开或私密地提供反馈。
+提供反馈很简单！在使用 OpenHands 时，你可以在任意时刻按下点赞或点踩按钮。你将被要求提供你的电子邮件地址（例如，以便我们在需要进一步询问时联系你），你可以选择公开或私密地提供反馈。
 
 <iframe width="560" height="315" src="https://www.youtube.com/embed/5rFx-StMVV0?si=svo7xzp6LhGK_GXr" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
 
 ## 📜 数据许可与隐私
 
-* **公开** 数据将与 OpenDevin 本身一样以 MIT 许可协议发布，并可被社区用来训练和测试模型。显然，你能够公开的反馈对整个社区来说更有价值，因此当你不涉及敏感信息时，我们鼓励你选择这个选项！
-* **私密** 数据将仅与 OpenDevin 团队分享，用于改进 OpenDevin。
+* **公开** 数据将与 OpenHands 本身一样以 MIT 许可协议发布，并可被社区用来训练和测试模型。显然，你能够公开的反馈对整个社区来说更有价值，因此当你不涉及敏感信息时，我们鼓励你选择这个选项！
+* **私密** 数据将仅与 OpenHands 团队分享，用于改进 OpenHands。

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

@@ -2,47 +2,47 @@
 sidebar_position: 1
 ---
 
-# 💻 OpenDevin
+# 💻 OpenHands
 
-OpenDevin 是一个**自主 AI 软件工程师**，能够执行复杂的工程任务，并在软件开发项目中积极与用户合作。
+OpenHands 是一个**自主 AI 软件工程师**，能够执行复杂的工程任务，并在软件开发项目中积极与用户合作。
 这个项目是完全开源的，所以你可以随意使用和修改它。
 
 :::tip
-在 [GitHub](https://github.com/OpenDevin/OpenDevin) 上探索 OpenDevin 的代码库或加入我们的社区！
+在 [GitHub](https://github.com/All-Hands-AI/OpenHands) 上探索 OpenHands 的代码库或加入我们的社区！
 
-<a href="https://github.com/OpenDevin/OpenDevin/graphs/contributors">
+<a href="https://github.com/All-Hands-AI/OpenHands/graphs/contributors">
   <img
-    src="https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge"
+    src="https://img.shields.io/github/contributors/All-Hands-AI/OpenHands?style=for-the-badge"
     alt="Contributors"
   />
 </a>
-<a href="https://github.com/OpenDevin/OpenDevin/network/members">
+<a href="https://github.com/All-Hands-AI/OpenHands/network/members">
   <img
-    src="https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge"
+    src="https://img.shields.io/github/forks/All-Hands-AI/OpenHands?style=for-the-badge"
     alt="Forks"
   />
 </a>
-<a href="https://github.com/OpenDevin/OpenDevin/stargazers">
+<a href="https://github.com/All-Hands-AI/OpenHands/stargazers">
   <img
-    src="https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge"
+    src="https://img.shields.io/github/stars/All-Hands-AI/OpenHands?style=for-the-badge"
     alt="Stargazers"
   />
 </a>
-<a href="https://github.com/OpenDevin/OpenDevin/issues">
+<a href="https://github.com/All-Hands-AI/OpenHands/issues">
   <img
-    src="https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge"
+    src="https://img.shields.io/github/issues/All-Hands-AI/OpenHands?style=for-the-badge"
     alt="Issues"
   />
 </a>
 <br></br>
-<a href="https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE">
+<a href="https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE">
   <img
-    src="https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge"
+    src="https://img.shields.io/github/license/All-Hands-AI/OpenHands?style=for-the-badge"
     alt="MIT License"
   />
 </a>
 <br></br>
-<a href="https://join.slack.com/t/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA">
+<a href="https://join.slack.com/t/opendevin/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"
@@ -58,10 +58,10 @@ OpenDevin 是一个**自主 AI 软件工程师**，能够执行复杂的工程
 
 ## 🛠️ 入门指南
 
-运行 OpenDevin 最简单的方法是在 Docker 容器中。它在 Docker 的最新版本 `26.0.0` 上运行效果最佳。
+运行 OpenHands 最简单的方法是在 Docker 容器中。它在 Docker 的最新版本 `26.0.0` 上运行效果最佳。
 你必须使用 Linux、Mac OS 或 Windows 上的 WSL。
 
-要在 Docker 容器中启动 OpenDevin，请在终端中运行以下命令：
+要在 Docker 容器中启动 OpenHands，请在终端中运行以下命令：
 
 :::warning
 运行以下命令时，`./workspace` 中的文件可能会被修改或删除。
@@ -72,40 +72,38 @@ WORKSPACE_BASE=$(pwd)/workspace
 docker run -it \
     --pull=always \
     -e SANDBOX_USER_ID=$(id -u) \
-    -e PERSIST_SANDBOX="true" \
-    -e SSH_PASSWORD="make something up here" \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -v $WORKSPACE_BASE:/opt/workspace_base \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
-    --name opendevin-app-$(date +%Y%m%d%H%M%S) \
-    ghcr.io/opendevin/opendevin:0.6
+    --name openhands-app-$(date +%Y%m%d%H%M%S) \
+    ghcr.io/all-hands-ai/openhands:main
 ```
 
-你会发现 OpenDevin 在 [http://localhost:3000](http://localhost:3000) 运行，并可以访问 `./workspace`。要让 OpenDevin 操作你的代码，请将代码放在 `./workspace` 中。
+你会发现 OpenHands 在 [http://localhost:3000](http://localhost:3000) 运行，并可以访问 `./workspace`。要让 OpenHands 操作你的代码，请将代码放在 `./workspace` 中。
 
-OpenDevin 只会访问这个工作区文件夹。它在一个安全的 docker 沙盒中运行，不会影响你系统的其他部分。
+OpenHands 只会访问这个工作区文件夹。它在一个安全的 docker 沙盒中运行，不会影响你系统的其他部分。
 
 :::tip
-如果你想使用**（不稳定！）**最新版本，可以使用 `ghcr.io/opendevin/opendevin:main` 作为镜像（最后一行）。
+如果你想使用**（不稳定！）**最新版本，可以使用 `ghcr.io/all-hands-ai/openhands:main` 作为镜像（最后一行）。
 :::
 
-有关开发工作流程，请参阅 [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md)。
+有关开发工作流程，请参阅 [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md)。
 
 遇到问题了吗？查看我们的 [故障排除指南](https://docs.all-hands.dev/modules/usage/troubleshooting)。
 
 :::warning
-OpenDevin 目前正在开发中，但你已经可以运行 alpha 版本来查看端到端系统的运作情况。
+OpenHands 目前正在开发中，但你已经可以运行 alpha 版本来查看端到端系统的运作情况。
 :::
 
-[contributors-shield]: https://img.shields.io/github/contributors/opendevin/opendevin?style=for-the-badge
-[contributors-url]: https://github.com/OpenDevin/OpenDevin/graphs/contributors
-[forks-shield]: https://img.shields.io/github/forks/opendevin/opendevin?style=for-the-badge
-[forks-url]: https://github.com/OpenDevin/OpenDevin/network/members
-[stars-shield]: https://img.shields.io/github/stars/opendevin/opendevin?style=for-the-badge
-[stars-url]: https://github.com/OpenDevin/OpenDevin/stargazers
-[issues-shield]: https://img.shields.io/github/issues/opendevin/opendevin?style=for-the-badge
-[issues-url]: https://github.com/OpenDevin/OpenDevin/issues
-[license-shield]: https://img.shields.io/github/license/opendevin/opendevin?style=for-the-badge
-[license-url]: https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE
+[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

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

@@ -2,11 +2,11 @@
 
 ## 完成
 
-OpenDevin 使用 LiteLLM 进行完成调用。你可以在 Azure 的文档中找到他们的文档 [这里](https://docs.litellm.ai/docs/providers/azure)
+OpenHands 使用 LiteLLM 进行完成调用。你可以在 Azure 的文档中找到他们的文档 [这里](https://docs.litellm.ai/docs/providers/azure)
 
 ### Azure openai 配置
 
-在运行 OpenDevin Docker 镜像时，你需要使用 `-e` 设置以下环境变量：
+在运行 OpenHands Docker 镜像时，你需要使用 `-e` 设置以下环境变量：
 
 ```
 LLM_BASE_URL="<azure-api-base-url>"          # 示例: "https://openai-gpt-4-test-v-1.openai.azure.com/"
@@ -16,19 +16,19 @@ LLM_API_VERSION = "<api-version>"          # 示例: "2024-02-15-preview"
 ```
 
 :::note
-你可以在 Azure 的部署页面找到你的 ChatGPT 部署名称。它可能与默认或最初设置的聊天模型名称相同（例如 'GPT4-1106-preview'），但不一定相同。运行 OpenDevin，当你在浏览器中加载它时，进入设置并按照上述方式设置模型: "azure/&lt;your-actual-gpt-deployment-name&gt;"。如果列表中没有，请输入你自己的文本并保存。
+你可以在 Azure 的部署页面找到你的 ChatGPT 部署名称。它可能与默认或最初设置的聊天模型名称相同（例如 'GPT4-1106-preview'），但不一定相同。运行 OpenHands，当你在浏览器中加载它时，进入设置并按照上述方式设置模型: "azure/&lt;your-actual-gpt-deployment-name&gt;"。如果列表中没有，请输入你自己的文本并保存。
 :::
 
 ## 嵌入
 
-OpenDevin 使用 llama-index 进行嵌入。你可以在 Azure 的文档中找到他们的文档 [这里](https://docs.llamaindex.ai/en/stable/api_reference/embeddings/azure_openai/)
+OpenHands 使用 llama-index 进行嵌入。你可以在 Azure 的文档中找到他们的文档 [这里](https://docs.llamaindex.ai/en/stable/api_reference/embeddings/azure_openai/)
 
 ### Azure openai 配置
 
 Azure OpenAI 嵌入使用的模型是 "text-embedding-ada-002"。
 你需要在你的 Azure 账户中为这个模型设置正确的部署名称。
 
-在 Docker 中运行 OpenDevin 时，使用 `-e` 设置以下环境变量：
+在 Docker 中运行 OpenHands 时，使用 `-e` 设置以下环境变量：
 
 ```
 LLM_EMBEDDING_MODEL="azureopenai"

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

@@ -2,14 +2,14 @@
 
 ## Completion
 
-OpenDevin 使用 LiteLLM 进行补全调用。以下资源与使用 OpenDevin 和 Google 的 LLM 相关：
+OpenHands 使用 LiteLLM 进行补全调用。以下资源与使用 OpenHands 和 Google 的 LLM 相关：
 
 - [Gemini - Google AI Studio](https://docs.litellm.ai/docs/providers/gemini)
 - [VertexAI - Google Cloud Platform](https://docs.litellm.ai/docs/providers/vertex)
 
 ### Gemini - Google AI Studio 配置
 
-在运行 OpenDevin Docker 镜像时，通过 Google AI Studio 使用 Gemini，你需要使用 `-e` 设置以下环境变量：
+在运行 OpenHands Docker 镜像时，通过 Google AI Studio 使用 Gemini，你需要使用 `-e` 设置以下环境变量：
 
 ```
 GEMINI_API_KEY="<your-google-api-key>"
@@ -18,7 +18,7 @@ LLM_MODEL="gemini/gemini-1.5-pro"
 
 ### Vertex AI - Google Cloud Platform 配置
 
-在运行 OpenDevin Docker 镜像时，通过 Google Cloud Platform 使用 Vertex AI，你需要使用 `-e` 设置以下环境变量：
+在运行 OpenHands Docker 镜像时，通过 Google Cloud Platform 使用 Vertex AI，你需要使用 `-e` 设置以下环境变量：
 
 ```
 GOOGLE_APPLICATION_CREDENTIALS="<json-dump-of-gcp-service-account-json>"

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

@@ -4,16 +4,16 @@ sidebar_position: 2
 
 # 🤖 LLM 支持
 
-OpenDevin 可以兼容任何 LLM 后端。
+OpenHands 可以兼容任何 LLM 后端。
 关于所有可用 LM 提供商和模型的完整列表，请参阅
 [litellm 文档](https://docs.litellm.ai/docs/providers)。
 
 :::warning
-OpenDevin 将向你配置的 LLM 发出许多提示。大多数这些 LLM 都是收费的——请务必设定支出限额并监控使用情况。
+OpenHands 将向你配置的 LLM 发出许多提示。大多数这些 LLM 都是收费的——请务必设定支出限额并监控使用情况。
 :::
 
 `LLM_MODEL` 环境变量控制在编程交互中使用的模型。
-但在使用 OpenDevin UI 时，你需要在设置窗口中选择你的模型（左下角的齿轮）。
+但在使用 OpenHands UI 时，你需要在设置窗口中选择你的模型（左下角的齿轮）。
 
 某些 LLM 可能需要以下环境变量：
 
@@ -23,10 +23,10 @@ OpenDevin 将向你配置的 LLM 发出许多提示。大多数这些 LLM 都是
 - `LLM_EMBEDDING_DEPLOYMENT_NAME`
 - `LLM_API_VERSION`
 
-我们有一些指南，介绍了如何使用特定模型提供商运行 OpenDevin：
+我们有一些指南，介绍了如何使用特定模型提供商运行 OpenHands：
 
-- [ollama](llms/localLLMs)
-- [Azure](llms/azureLLMs)
+- [ollama](llms/local-llms)
+- [Azure](llms/azure-llms)
 
 如果你使用其他提供商，我们鼓励你打开一个 PR 来分享你的配置！
 
@@ -35,12 +35,12 @@ OpenDevin 将向你配置的 LLM 发出许多提示。大多数这些 LLM 都是
 最好的模型是 GPT-4 和 Claude 3。目前的本地和开源模型
 远没有那么强大。当使用替代模型时，
 你可能会看到信息之间的长时间等待，
-糟糕的响应，或关于 JSON格式错误的错误。OpenDevin
+糟糕的响应，或关于 JSON格式错误的错误。OpenHands
 的强大程度依赖于其驱动的模型——幸运的是，我们团队的人员
 正在积极致力于构建更好的开源模型！
 
 ## API 重试和速率限制
 
-一些 LLM 有速率限制，可能需要重试操作。OpenDevin 会在收到 429 错误或 API 连接错误时自动重试请求。
+一些 LLM 有速率限制，可能需要重试操作。OpenHands 会在收到 429 错误或 API 连接错误时自动重试请求。
 你可以设置 `LLM_NUM_RETRIES`，`LLM_RETRY_MIN_WAIT`，`LLM_RETRY_MAX_WAIT` 环境变量来控制重试次数和重试之间的时间。
-默认情况下，`LLM_NUM_RETRIES` 为 5，`LLM_RETRY_MIN_WAIT` 和 `LLM_RETRY_MAX_WAIT` 分别为 3 秒和 60 秒。
+默认情况下，`LLM_NUM_RETRIES` 为 8，`LLM_RETRY_MIN_WAIT` 和 `LLM_RETRY_MAX_WAIT` 分别为 15 秒和 120 秒。

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

@@ -23,11 +23,11 @@ mistral:7b-instruct-v0.2-q4_K_M eb14864c7427    4.4 GB  2 weeks ago
 starcoder2:latest               f67ae0f64584    1.7 GB  19 hours ago
 ```
 
-## 启动 OpenDevin
+## 启动 OpenHands
 
 ### Docker
 
-使用[此处](../intro)的说明通过 Docker 启动 OpenDevin。
+使用[此处](../intro)的说明通过 Docker 启动 OpenHands。
 但是在运行 `docker run` 时，您需要添加一些额外的参数：
 
 ```bash
@@ -39,7 +39,7 @@ starcoder2:latest               f67ae0f64584    1.7 GB  19 hours ago
 例如：
 
 ```bash
-# 您希望 OpenDevin 修改的目录。必须是绝对路径！
+# 您希望 OpenHands 修改的目录。必须是绝对路径！
 export WORKSPACE_BASE=$(pwd)/workspace
 
 docker run \
@@ -53,14 +53,14 @@ docker run \
     -v $WORKSPACE_BASE:/opt/workspace_base \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
-    ghcr.io/opendevin/opendevin:main
+    ghcr.io/all-hands-ai/openhands:main
 ```
 
 现在您应该可以连接到 `http://localhost:3000/`
 
 ### 从源代码构建
 
-使用[Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md)中的说明构建 OpenDevin。
+使用[Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md)中的说明构建 OpenHands。
 通过运行 `make setup-config` 确保 `config.toml` 存在，这将为您创建一个。在 `config.toml` 中，输入以下内容：
 
 ```
@@ -74,11 +74,11 @@ WORKSPACE_DIR="$(pwd)/workspace"
 
 如有需要，可以替换您选择的 `LLM_MODEL`。
 
-完成！现在您可以通过 `make run` 启动 Devin 而无需 Docker。现在您应该可以连接到 `http://localhost:3000/`
+完成！现在您可以通过 `make run` 启动 OpenHands 而无需 Docker。现在您应该可以连接到 `http://localhost:3000/`
 
 ## 选择您的模型
 
-在 OpenDevin UI 中，点击左下角的设置齿轮。
+在 OpenHands UI 中，点击左下角的设置齿轮。
 然后在 `Model` 输入中，输入 `ollama/codellama:7b`，或者您之前拉取的模型名称。
 如果它没有出现在下拉列表中，也没关系，只需输入即可。完成后点击保存。
 
@@ -86,7 +86,7 @@ WORKSPACE_DIR="$(pwd)/workspace"
 
 ## 配置 ollama 服务（WSL）{#configuring-ollama-service-zh-Hans}
 
-WSL 中 ollama 的默认配置仅为 localhost 提供服务。这意味着您无法从 docker 容器中访问它。比如，它不会与 OpenDevin 一起工作。首先让我们测试 ollama 是否正常运行。
+WSL 中 ollama 的默认配置仅为 localhost 提供服务。这意味着您无法从 docker 容器中访问它。比如，它不会与 OpenHands 一起工作。首先让我们测试 ollama 是否正常运行。
 
 ```bash
 ollama list # 获取已安装模型列表
@@ -98,7 +98,7 @@ curl http://localhost:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
 完成后，测试它是否允许“外部”请求，比如那些来自 docker 容器内的请求。
 
 ```bash
-docker ps # 获取正在运行的 docker 容器列表，最准确的测试选择 open devin sandbox 容器。
+docker ps # 获取正在运行的 docker 容器列表，最准确的测试选择 OpenHands sandbox 容器。
 docker exec [CONTAINER ID] curl http://host.docker.internal:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
 #例如，docker exec cd9cc82f7a11 curl http://host.docker.internal:11434/api/generate -d '{"model":"codellama","prompt":"hi"}'
 ```
@@ -135,6 +135,6 @@ sudo systemctl restart ollama
 
 ```bash
 ollama list # 获取已安装模型列表
-docker ps # 获取正在运行的 docker 容器列表，最准确的测试选择 open devin sandbox 容器。
+docker ps # 获取正在运行的 docker 容器列表，最准确的测试选择 OpenHands sandbox 容器。
 docker exec [CONTAINER ID] curl http://host.docker.internal:11434/api/generate -d '{"model":"[NAME]","prompt":"hi"}'
 ```

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

@@ -18,7 +18,7 @@ sidebar_position: 5
 
 ## 无法连接到 Docker
 
-[GitHub 问题](https://github.com/OpenDevin/OpenDevin/issues/1226)
+[GitHub 问题](https://github.com/All-Hands-AI/OpenHands/issues/1226)
 
 ### 症状
 
@@ -32,7 +32,7 @@ docker.errors.DockerException: 获取服务器 API 版本时出错: ('连接中
 
 ### 详情
 
-OpenDevin 使用 Docker 容器来安全地完成工作，而不会破坏您的机器。
+OpenHands 使用 Docker 容器来安全地完成工作，而不会破坏您的机器。
 
 ### 解决方法
 
@@ -43,7 +43,7 @@ OpenDevin 使用 Docker 容器来安全地完成工作，而不会破坏您的
 
 ## 无法连接到 DockerSSHBox
 
-[GitHub 问题](https://github.com/OpenDevin/OpenDevin/issues/1156)
+[GitHub 问题](https://github.com/All-Hands-AI/OpenHands/issues/1156)
 
 ### 症状
 
@@ -55,18 +55,18 @@ pexpect.pxssh.ExceptionPxssh: Could not establish connection to host
 
 ### 详情
 
-默认情况下，OpenDevin 使用 SSH 连接到一个运行中的容器。在某些机器上，尤其是 Windows，这似乎会失败。
+默认情况下，OpenHands 使用 SSH 连接到一个运行中的容器。在某些机器上，尤其是 Windows，这似乎会失败。
 
 ### 解决方法
 
 * 重新启动您的计算机（有时会有用）
 * 确保拥有最新版本的 WSL 和 Docker
 * 检查您的 WSL 分发版也已更新
-* 尝试[此重新安装指南](https://github.com/OpenDevin/OpenDevin/issues/1156#issuecomment-2064549427)
+* 尝试[此重新安装指南](https://github.com/All-Hands-AI/OpenHands/issues/1156#issuecomment-2064549427)
 
 ## 无法连接到 LLM
 
-[GitHub 问题](https://github.com/OpenDevin/OpenDevin/issues/1208)
+[GitHub 问题](https://github.com/All-Hands-AI/OpenHands/issues/1208)
 
 ### 症状
 
@@ -79,9 +79,9 @@ AttributeError: 'NoneType' object has no attribute 'request'
 
 ### 详情
 
-[GitHub 问题](https://github.com/OpenDevin/OpenDevin/issues?q=is%3Aissue+is%3Aopen+404)
+[GitHub 问题](https://github.com/All-Hands-AI/OpenHands/issues?q=is%3Aissue+is%3Aopen+404)
 
-这通常发生在本地 LLM 设置中，当 OpenDevin 无法连接到 LLM 服务器时。请参阅我们的 [本地 LLM 指南](llms/localLLMs) 以获取更多信息。
+这通常发生在本地 LLM 设置中，当 OpenHands 无法连接到 LLM 服务器时。请参阅我们的 [本地 LLM 指南](llms/local-llms) 以获取更多信息。
 
 ### 解决方法
 
@@ -128,9 +128,9 @@ openai.NotFoundError: Error code: 404 - {'error': {'code': '404', 'message': 'Re
   * 如果您在 UI 中运行，请确保在设置模式中设置 `model`
   * 如果您通过 main.py 运行，请确保在环境变量/配置中设置 `LLM_MODEL`
 * 确保遵循了您的 LLM 提供商的任何特殊说明
-  * [Ollama](/zh-Hans/modules/usage/llms/localLLMs)
-  * [Azure](/zh-Hans/modules/usage/llms/azureLLMs)
-  * [Google](/zh-Hans/modules/usage/llms/googleLLMs)
+  * [Ollama](/zh-Hans/modules/usage/llms/local-llms)
+  * [Azure](/zh-Hans/modules/usage/llms/azure-llms)
+  * [Google](/zh-Hans/modules/usage/llms/google-llms)
 * 确保您的 API 密钥正确无误
 * 尝试使用 `curl` 连接到 LLM
 * 尝试[直接通过 LiteLLM 连接](https://github.com/BerriAI/litellm)来测试您的设置
@@ -171,19 +171,19 @@ export PYTHON_KEYRING_BACKEND=keyring.backends.null.Keyring
 
 ### 症状
 
-通常情况下，当打开 UI 时，OpenDevin 会询问是否要恢复或开始新会话。但点击“恢复”仍然会开始一个全新的聊天。
+通常情况下，当打开 UI 时，OpenHands 会询问是否要恢复或开始新会话。但点击“恢复”仍然会开始一个全新的聊天。
 
 ### 详情
 
-按今天的标准安装，会话数据存储在内存中。目前，如果 OpenDevin 的服务重启，以前的会话将失效（生成一个新秘密），因此无法恢复。
+按今天的标准安装，会话数据存储在内存中。目前，如果 OpenHands 的服务重启，以前的会话将失效（生成一个新秘密），因此无法恢复。
 
 ### 解决方法
 
-* 通过编辑 OpenDevin 根文件夹中的 `config.toml` 文件，更改配置以使会话持久化，指定一个 `file_store` 和一个绝对路径的 `file_store_path`：
+* 通过编辑 OpenHands 根文件夹中的 `config.toml` 文件，更改配置以使会话持久化，指定一个 `file_store` 和一个绝对路径的 `file_store_path`：
 
 ```toml
 file_store="local"
-file_store_path="/absolute/path/to/opendevin/cache/directory"
+file_store_path="/absolute/path/to/openhands/cache/directory"
 ```
 
 * 在您的 .bashrc 中添加一个固定的 JWT 秘密，如下所示，以便以前的会话 ID 可以被接受。

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

@@ -1,6 +1,6 @@
 # Windows 和 WSL 用户须知
 
-OpenDevin 仅支持通过 [WSL](https://learn.microsoft.com/en-us/windows/wsl/install) 在 Windows 上运行。
+OpenHands 仅支持通过 [WSL](https://learn.microsoft.com/en-us/windows/wsl/install) 在 Windows 上运行。
 请确保在 WSL 终端内运行所有命令。
 
 ## 故障排除
@@ -12,8 +12,8 @@ Docker 还需要启用 WSL 集成选项。
 
 ### 建议：不要以 root 用户身份运行
 
-出于安全原因，非常建议不要以 root 用户身份运行 OpenDevin，而是使用 UID 非零的用户身份运行。
-此外，当以 root 身份运行时，不支持持久化沙箱，并且在启动 OpenDevin 时可能会出现相应消息。
+出于安全原因，非常建议不要以 root 用户身份运行 OpenHands，而是使用 UID 非零的用户身份运行。
+此外，当以 root 身份运行时，不支持持久化沙箱，并且在启动 OpenHands 时可能会出现相应消息。
 
 参考资料：
 
@@ -21,12 +21,12 @@ Docker 还需要启用 WSL 集成选项。
 * [在 WSL 中设置默认用户](https://www.tenforums.com/tutorials/128152-set-default-user-windows-subsystem-linux-distro-windows-10-a.html#option2)
 关于第二个参考资料的小提示：对于 Ubuntu 用户，该命令实际上可能是 "ubuntupreview" 而不是 "ubuntu"。
 
-### 创建 opendevin 用户失败
+### 创建 openhands 用户失败
 
 如果您在设置过程中遇到以下错误：
 
 ```sh
-Exception: Failed to create opendevin user in sandbox: 'useradd: UID 0 is not unique'
+Exception: Failed to create openhands user in sandbox: 'useradd: UID 0 is not unique'
 ```
 
 您可以通过运行以下命令解决：

docs/i18n/zh-Hans/docusaurus-theme-classic/navbar.json

@@ -1,10 +1,10 @@
 {
   "title": {
-    "message": "OpenDevin",
+    "message": "OpenHands",
     "description": "The title in the navbar"
   },
   "logo.alt": {
-    "message": "OpenDevin",
+    "message": "OpenHands",
     "description": "The alt text of navbar logo"
   },
   "item.label.Docs": {

docs/modules/usage/about.md

@@ -1,53 +1,49 @@
----
-sidebar_position: 8
----
-
 # 📚 Misc
 
 ## ⭐️ Research Strategy
 
 Achieving full replication of production-grade applications with LLMs is a complex endeavor. Our strategy involves:
 
-1. **Core Technical Research:** Focusing on foundational research to understand and improve the technical aspects of code generation and handling.
-2. **Specialist Abilities:** Enhancing the effectiveness of core components through data curation, training methods, and more.
-3. **Task Planning:** Developing capabilities for bug detection, codebase management, and optimization.
-4. **Evaluation:** Establishing comprehensive evaluation metrics to better understand and improve our models.
+1. **Core Technical Research:** Focusing on foundational research to understand and improve the technical aspects of code generation and handling
+2. **Specialist Abilities:** Enhancing the effectiveness of core components through data curation, training methods, and more
+3. **Task Planning:** Developing capabilities for bug detection, codebase management, and optimization
+4. **Evaluation:** Establishing comprehensive evaluation metrics to better understand and improve our models
 
 ## 🚧 Default Agent
 
-- Our default Agent is currently the CodeActAgent, which is capable of generating code and handling files. We're working on other Agent implementations, including [SWE Agent](https://swe-agent.com/). You can [read about our current set of agents here](./agents).
+Our default Agent is currently the [CodeActAgent](agents), which is capable of generating code and handling files.
 
 ## 🤝 How to Contribute
 
-OpenDevin is a community-driven project, and we welcome contributions from everyone. Whether you're a developer, a researcher, or simply enthusiastic about advancing the field of software engineering with AI, there are many ways to get involved:
+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:
 
-- **Code Contributions:** Help us develop the core functionalities, frontend interface, or sandboxing solutions.
-- **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in evaluating the models, or suggest improvements.
-- **Feedback and Testing:** Use the OpenDevin toolset, report bugs, suggest features, or provide feedback on usability.
+- **Code Contributions:** Help us develop the core functionalities, frontend interface, 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
 
-For details, please check [this document](https://github.com/OpenDevin/OpenDevin/blob/main/CONTRIBUTING.md).
+For details, please check [this document](https://github.com/All-Hands-AI/OpenHands/blob/main/CONTRIBUTING.md).
 
 ## 🤖 Join Our Community
 
-We have both Slack workspace for the collaboration on building OpenDevin and Discord server for discussion about anything related, e.g., this project, LLM, agent, etc.
+We have both Slack workspace for the collaboration on building OpenHands and Discord server for discussion about anything related, e.g., this project, LLM, agent, etc.
 
-- [Slack workspace](https://join.slack.com/t/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA)
+- [Slack workspace](https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA)
 - [Discord server](https://discord.gg/ESHStjSjD4)
 
 If you would love to contribute, feel free to join our community. Let's simplify software engineering together!
 
-🐚 **Code less, make more with OpenDevin.**
+🐚 **Code less, make more with OpenHands.**
 
-[![Star History Chart](https://api.star-history.com/svg?repos=OpenDevin/OpenDevin&type=Date)](https://star-history.com/#OpenDevin/OpenDevin&Date)
+[![Star History Chart](https://api.star-history.com/svg?repos=All-Hands-AI/OpenHands&type=Date)](https://star-history.com/#All-Hands-AI/OpenHands&Date)
 
 ## 🛠️ Built With
 
-OpenDevin is built using a combination of powerful frameworks and libraries, providing a robust foundation for its development. Here are the key technologies used in the project:
+OpenHands is built using a combination of powerful frameworks and libraries, providing a robust foundation for its development. Here are the key technologies used in the project:
 
 ![FastAPI](https://img.shields.io/badge/FastAPI-black?style=for-the-badge) ![uvicorn](https://img.shields.io/badge/uvicorn-black?style=for-the-badge) ![LiteLLM](https://img.shields.io/badge/LiteLLM-black?style=for-the-badge) ![Docker](https://img.shields.io/badge/Docker-black?style=for-the-badge) ![Ruff](https://img.shields.io/badge/Ruff-black?style=for-the-badge) ![MyPy](https://img.shields.io/badge/MyPy-black?style=for-the-badge) ![LlamaIndex](https://img.shields.io/badge/LlamaIndex-black?style=for-the-badge) ![React](https://img.shields.io/badge/React-black?style=for-the-badge)
 
-Please note that the selection of these technologies is in progress, and additional technologies may be added or existing ones may be removed as the project evolves. We strive to adopt the most suitable and efficient tools to enhance the capabilities of OpenDevin.
+Please note that the selection of these technologies is in progress, and additional technologies may be added or existing ones may be removed as the project evolves. We strive to adopt the most suitable and efficient tools to enhance the capabilities of OpenHands.
 
 ## 📜 License
 
-Distributed under the MIT License. See [our license](https://github.com/OpenDevin/OpenDevin/blob/main/LICENSE) for more information.
+Distributed under the MIT License. See [our license](https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE) for more information.

docs/modules/usage/agents.md

@@ -1,14 +1,11 @@
----
-sidebar_position: 3
----
+# 🧠 Main Agent and Capabilities
 
-# 🧠 Agents and Capabilities
-
-## CodeAct Agent
+## CodeActAgent
 
 ### Description
 
-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).
+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_.
 
 The conceptual idea is illustrated below. At each turn, the agent can:
 
@@ -18,76 +15,10 @@ The conceptual idea is illustrated below. At each turn, the agent can:
 - Execute any valid Linux `bash` command
 - Execute any valid `Python` code with [an interactive Python interpreter](https://ipython.org/). This is simulated through `bash` command, see plugin system below for more details.
 
-![image](https://github.com/OpenDevin/OpenDevin/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
-
-### Plugin System
-
-To make the CodeAct agent more powerful with only access to `bash` action space, CodeAct agent leverages OpenDevin's plugin system:
-
-- [Jupyter plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/jupyter): for IPython execution via bash command
-- [SWE-agent tool plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/swe_agent_commands): Powerful bash command line tools for software development tasks introduced by [swe-agent](https://github.com/princeton-nlp/swe-agent).
+![image](https://github.com/All-Hands-AI/OpenHands/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
 
 ### Demo
 
-https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
+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)_
-
-### Actions
-
-`Action`,
-`CmdRunAction`,
-`IPythonRunCellAction`,
-`AgentEchoAction`,
-`AgentFinishAction`,
-`AgentTalkAction`
-
-### Observations
-
-`CmdOutputObservation`,
-`IPythonRunCellObservation`,
-`AgentMessageObservation`,
-`UserMessageObservation`
-
-### Methods
-
-| Method          | Description                                                                                                                                     |
-| --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- |
-| `__init__`      | Initializes an agent with `llm` and a list of messages `list[Mapping[str, str]]`                                                                |
-| `step`          | Performs one step using the CodeAct Agent. This includes gathering info on previous steps and prompting the model to make a command to execute. |
-
-## Planner Agent
-
-### Description
-
-The planner agent utilizes a special prompting strategy to create long term plans for solving problems.
-The agent is given its previous action-observation pairs, current task, and hint based on last action taken at every step.
-
-### Actions
-
-`NullAction`,
-`CmdRunAction`,
-`BrowseURLAction`,
-`GithubPushAction`,
-`FileReadAction`,
-`FileWriteAction`,
-`AgentThinkAction`,
-`AgentFinishAction`,
-`AgentSummarizeAction`,
-`AddTaskAction`,
-`ModifyTaskAction`,
-
-### Observations
-
-`Observation`,
-`NullObservation`,
-`CmdOutputObservation`,
-`FileReadObservation`,
-`BrowserOutputObservation`
-
-### Methods
-
-| Method          | Description                                                                                                                                                                               |
-| --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `__init__`      | Initializes an agent with `llm`                                                                                                                                                           |
-| `step`          | Checks to see if current step is completed, returns `AgentFinishAction` if True. Otherwise, creates a plan prompt and sends to model for inference, adding the result as the next action. |
+_Example of CodeActAgent with `gpt-4-turbo-2024-04-09` performing a data science task (linear regression)_.

docs/modules/usage/architecture/backend.mdx

@@ -1,12 +1,8 @@
----
-sidebar_position: 7
----
-
-# 🏛️ System Architecture Overview
+# 🏛️ System Architecture
 
 <div style={{ textAlign: 'center' }}>
-  <img src="https://github.com/OpenDevin/OpenDevin/assets/16201837/97d747e3-29d8-4ccb-8d34-6ad1adb17f38" alt="OpenDevin System Architecture Diagram Jul 4 2024" />
-  <p><em>OpenDevin System Architecture Diagram (July 4, 2024)</em></p>
+  <img src="https://github.com/All-Hands-AI/OpenHands/assets/16201837/97d747e3-29d8-4ccb-8d34-6ad1adb17f38" alt="OpenHands System Architecture Diagram Jul 4 2024" />
+  <p><em>OpenHands System Architecture Diagram (July 4, 2024)</em></p>
 </div>
 
 This is a high-level overview of the system architecture. The system is divided into two main components: the frontend and the backend. The frontend is responsible for handling user interactions and displaying the results. The backend is responsible for handling the business logic and executing the agents.
@@ -33,14 +29,14 @@ _**Disclaimer**: The backend architecture is a work in progress and is subject t
 
     ## Prerequisites
 
-    - Running python environment in which opendevin is executable
+    - Running python environment in which openhands is executable
     (according to the instructions in the README.md file in the root of the repository)
     - [py2puml](https://github.com/lucsorel/py2puml) installed
 
 ## Steps
 
 1.  Autogenerate the diagram by running the following command from the root of the repository:
-    `py2puml opendevin opendevin > docs/architecture/backend_architecture.puml`
+    `py2puml openhands openhands > docs/architecture/backend_architecture.puml`
 
 2.  Open the generated file in a PlantUML editor, e.g. Visual Studio Code with the PlantUML extension or [PlantText](https://www.planttext.com/)
 

docs/modules/usage/architecture/runtime.md

@@ -0,0 +1,128 @@
+# 📦 EventStream Runtime
+
+The OpenHands EventStream Runtime is the core component that enables secure and flexible execution of AI agent's action.
+It creates a sandboxed environment using Docker, where arbitrary code can be run safely without risking the host system.
+
+## Why do we need a sandboxed runtime?
+
+OpenHands needs to execute arbitrary code in a secure, isolated environment for several reasons:
+
+1. Security: Executing untrusted code can pose significant risks to the host system. A sandboxed environment prevents malicious code from accessing or modifying the host system's resources
+2. Consistency: A sandboxed environment ensures that code execution is consistent across different machines and setups, eliminating "it works on my machine" issues
+3. Resource Control: Sandboxing allows for better control over resource allocation and usage, preventing runaway processes from affecting the host system
+4. Isolation: Different projects or users can work in isolated environments without interfering with each other or the host system
+5. Reproducibility: Sandboxed environments make it easier to reproduce bugs and issues, as the execution environment is consistent and controllable
+
+## How does the Runtime work?
+
+The OpenHands Runtime system uses a client-server architecture implemented with Docker containers. Here's an overview of how it works:
+
+```mermaid
+graph TD
+    A[User-provided Custom Docker Image] --> B[OpenHands Backend]
+    B -->|Builds| C[OH Runtime Image]
+    C -->|Launches| D[Action Executor]
+    D -->|Initializes| E[Browser]
+    D -->|Initializes| F[Bash Shell]
+    D -->|Initializes| G[Plugins]
+    G -->|Initializes| L[Jupyter Server]
+
+    B -->|Spawn| H[Agent]
+    B -->|Spawn| I[EventStream]
+    I <--->|Execute Action to
+    Get Observation
+    via REST API
+    | D
+
+    H -->|Generate Action| I
+    I -->|Obtain Observation| H
+
+    subgraph "Docker Container"
+    D
+    E
+    F
+    G
+    L
+    end
+```
+
+1. User Input: The user provides a custom base Docker image
+2. Image Building: OpenHands builds a new Docker image (the "OH runtime image") based on the user-provided image. This new image includes OpenHands-specific code, primarily the "runtime client"
+3. Container Launch: When OpenHands starts, it launches a Docker container using the OH runtime image
+4. Action Execution Server Initialization: The action execution server initializes an `ActionExecutor` inside the container, setting up necessary components like a bash shell and loading any specified plugins
+5. Communication: The OpenHands backend (`openhands/runtime/impl/eventstream/eventstream_runtime.py`) communicates with the action execution server over RESTful API, sending actions and receiving observations
+6. Action Execution: The runtime client receives actions from the backend, executes them in the sandboxed environment, and sends back observations
+7. Observation Return: The action execution server sends execution results back to the OpenHands backend as observations
+
+
+The role of the client:
+- It acts as an intermediary between the OpenHands backend and the sandboxed environment
+- It executes various types of actions (shell commands, file operations, Python code, etc.) safely within the container
+- It manages the state of the sandboxed environment, including the current working directory and loaded plugins
+- It formats and returns observations to the backend, ensuring a consistent interface for processing results
+
+
+## How OpenHands builds and maintains OH Runtime images
+
+OpenHands' approach to building and managing runtime images ensures efficiency, consistency, and flexibility in creating and maintaining Docker images for both production and development environments.
+
+Check out the [relevant code](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/utils/runtime_build.py) if you are interested in more details.
+
+### Image Tagging System
+
+OpenHands uses a dual-tagging system for its runtime images to balance reproducibility with flexibility.
+Tags may be in one of 2 formats:
+
+- **Generic**: `oh_v{openhands_version}_{16_digit_lock_hash}` (e.g.: `oh_v0.9.9_1234567890abcdef`)
+- **Specific**: `oh_v{openhands_version}_{16_digit_lock_hash}_{16_digit_source_hash}`
+  (e.g.: `oh_v0.9.9_1234567890abcdef_1234567890abcdef`)
+
+#### Lock Hash
+
+This hash is built from the first 16 digits of the MD5 of:
+- The name of the base image upon which the image was built (e.g.: `nikolaik/python-nodejs:python3.12-nodejs22`)
+- The content of the `pyproject.toml` included in the image.
+- The content of the `poetry.lock` included in the image.
+
+This effectively gives a hash for the dependencies of Openhands independent of the source code.
+
+#### Source Hash
+
+This is the first 16 digits of the MD5 of the directory hash for the source directory. This gives a hash
+for only the openhands source
+
+#### Build Process
+
+When generating an image...
+
+- OpenHands first checks whether an image with the same **Specific** tag exists. If there is such an image,
+  no build is performed - the existing image is used.
+- OpenHands next checks whether an image with the **Generic** tag exists. If there is such an image,
+  OpenHands builds a new image based upon it, bypassing all installation steps (like `poetry install` and
+  `apt-get`) except a final operation to copy the current source code. The new image is tagged with a
+  **Specific** tag only.
+- If neither a **Specific** nor **Generic** tag exists, a brand new image is built based upon the base
+  image (Which is a slower operation). This new image is tagged with both the **Generic** and **Specific**
+  tags.
+
+This dual-tagging approach allows OpenHands to efficiently manage both development and production environments.
+
+1. Identical source code and Dockerfile always produce the same image (via hash-based tags)
+2. The system can quickly rebuild images when minor changes occur (by leveraging recent compatible images)
+3. The generic tag (e.g., `runtime:oh_v0.9.3_1234567890abcdef`) always points to the latest build for a particular base image and OpenHands version combination
+
+## Runtime Plugin System
+
+The OpenHands Runtime supports a plugin system that allows for extending functionality and customizing the runtime environment. Plugins are initialized when the runtime client starts up.
+
+Check [an example of Jupyter plugin here](https://github.com/All-Hands-AI/OpenHands/blob/ecf4aed28b0cf7c18d4d8ff554883ba182fc6bdd/openhands/runtime/plugins/jupyter/__init__.py#L21-L55) if you want to implement your own plugin.
+
+*More details about the Plugin system are still under construction - contributions are welcomed!*
+
+Key aspects of the plugin system:
+
+1. Plugin Definition: Plugins are defined as Python classes that inherit from a base `Plugin` class
+2. Plugin Registration: Available plugins are registered in an `ALL_PLUGINS` dictionary
+3. Plugin Specification: Plugins are associated with `Agent.sandbox_plugins: list[PluginRequirement]`. Users can specify which plugins to load when initializing the runtime
+4. Initialization: Plugins are initialized asynchronously when the runtime client starts
+5. Usage: The runtime client can use initialized plugins to extend its capabilities (e.g., the JupyterPlugin for running IPython cells)

docs/modules/usage/custom_sandbox_guide.md

@@ -1,144 +0,0 @@
----
-sidebar_position: 6
----
-
-# 💿 How to Create and Use a Custom Docker Sandbox
-
-The default OpenDevin sandbox comes with a [minimal ubuntu configuration](https://github.com/OpenDevin/OpenDevin/blob/main/containers/sandbox/Dockerfile).
-
-Your use case may need additional software installed by default.
-
-There are two ways you can do so:
-
-1. Use an existing image from docker hub. For instance, if you want to have `nodejs` installed, you can do so by using the `node:20` image
-2. Creating your own custom docker image and using it
-
-If you want to take the first approach, you can skip the `Create Your Docker Image` section.
-
-For a more feature-rich environment, you might consider using pre-built images like **[nikolaik/python-nodejs](https://hub.docker.com/r/nikolaik/python-nodejs)**, which comes with both Python and Node.js pre-installed, along with many other useful tools and libraries, like:
-
-- Node.js: 22.x
-- npm: 10.x
-- yarn: stable
-- Python: latest
-- pip: latest
-- pipenv: latest
-- poetry: latest
-- uv: latest
-
-## Setup
-
-Make sure you are able to run OpenDevin using the [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md) first.
-
-## Create Your Docker Image
-
-To create a custom docker image, it must be debian/ubuntu based.
-
-For example, if we want OpenDevin to have access to the `node` binary, we would use the following Dockerfile:
-
-```dockerfile
-# Start with latest ubuntu image
-FROM ubuntu:latest
-
-# Run needed updates
-RUN apt-get update && apt-get install -y
-
-# Install node
-RUN apt-get install -y nodejs
-```
-
-Next build your docker image with the name of your choice, for example `custom_image`.
-
-To do this you can create a directory and put your file inside it with the name `Dockerfile`, and inside the directory run the following command:
-
-```bash
-docker build -t custom_image .
-```
-
-This will produce a new image called ```custom_image``` that will be available in Docker Engine.
-
-> Note that in the configuration described in this document, OpenDevin will run as user "opendevin" inside the sandbox and thus all packages installed via the docker file should be available to all users on the system, not just root.
->
-> Installing with apt-get above installs node for all users.
-
-## Specify your sandbox image in config.toml file
-
-OpenDevin configuration occurs via the top-level `config.toml` file.
-
-Create a `config.toml` file in the OpenDevin directory and enter these contents:
-
-```toml
-[core]
-workspace_base="./workspace"
-persist_sandbox=false
-run_as_devin=true
-sandbox_container_image="custom_image"
-```
-
-For `sandbox_container_image`, you can specify either:
-
-1. The name of your custom image that you built in the previous step (e.g., `”custom_image”`)
-2. A pre-existing image from Docker Hub (e.g., `”node:20”` if you want a sandbox with Node.js pre-installed)
-
-## Run
-Run OpenDevin by running ```make run``` in the top level directory.
-
-Navigate to ```localhost:3001``` and check if your desired dependencies are available.
-
-In the case of the example above, running ```node -v``` in the terminal produces ```v20.15.0```
-
-Congratulations!
-
-## Technical Explanation
-
-The relevant code is defined in [ssh_box.py](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/ssh_box.py) and [image_agnostic_util.py](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py).
-
-In particular, `ssh_box.py` checks the config object for ```config.sandbox_container_image``` and then attempts to retrieve the image using [get_od_sandbox_image](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py#L72) which is defined in image_agnostic_util.py.
-
-When first using a custom image, it will not be found and thus it will be built (on subsequent runs the built image will be found and returned).
-
-The custom image is built using [_build_sandbox_image()](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py#L29), which creates a docker file using your custom_image as a base and then configures the environment for OpenDevin, like this:
-
-```python
-dockerfile_content = (
-    f'FROM {base_image}\n'
-    'RUN apt update && apt install -y openssh-server wget sudo\n'
-    'RUN mkdir -p -m0755 /var/run/sshd\n'
-    'RUN mkdir -p /opendevin && mkdir -p /opendevin/logs && chmod 777 /opendevin/logs\n'
-    'RUN echo "" > /opendevin/bash.bashrc\n'
-    'RUN if [ ! -d /opendevin/miniforge3 ]; then \\\n'
-    '        wget "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh" && \\\n'
-    '        bash Miniforge3-$(uname)-$(uname -m).sh -b -p /opendevin/miniforge3 && \\\n'
-    '        chmod -R g+w /opendevin/miniforge3 && \\\n'
-    '        bash -c ". /opendevin/miniforge3/etc/profile.d/conda.sh && conda config --set changeps1 False && conda config --append channels conda-forge"; \\\n'
-    '    fi\n'
-    'RUN /opendevin/miniforge3/bin/pip install --upgrade pip\n'
-    'RUN /opendevin/miniforge3/bin/pip install jupyterlab notebook jupyter_kernel_gateway flake8\n'
-    'RUN /opendevin/miniforge3/bin/pip install python-docx PyPDF2 python-pptx pylatexenc openai\n'
-).strip()
-```
-
-> Note: the name of the image is modified via [_get_new_image_name()](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py#L63) and it is the modified name that is searched for on subsequent runs.
-
-## Troubleshooting / Errors
-
-### Error: ```useradd: UID 1000 is not unique```
-
-If you see this error in the console output it is because OpenDevin is trying to create the opendevin user in the sandbox with a UID of 1000, however this UID is already being used in the image (for some reason). To fix this change the sandbox_user_id field in the config.toml file to a different value:
-
-```toml
-[core]
-workspace_base="./workspace"
-persist_sandbox=false
-run_as_devin=true
-sandbox_container_image="custom_image"
-sandbox_user_id="1001"
-```
-
-### Port use errors
-
-If you see an error about a port being in use or unavailable, try deleting all running Docker Containers (run `docker ps` and `docker rm` relevant containers) and then re-running ```make run``` .
-
-## Discuss
-
-For other issues or questions join the [Slack](https://join.slack.com/t/opendevin/shared_invite/zt-2jsrl32uf-fTeeFjNyNYxqSZt5NPY3fA) or [Discord](https://discord.gg/ESHStjSjD4) and ask!

docs/modules/usage/feedback.md

@@ -1,14 +1,10 @@
----
-sidebar_position: 5
----
-
 # ✅ Providing Feedback
 
-When using OpenDevin, you will undoubtably encounter cases where things work well, and others where they don't. We encourage you to provide feedback when you use OpenDevin to help give feedback to the development team, and perhaps more importantly, create an open corpus of coding agent training examples -- Share-OpenDevin!
+When using OpenHands, you will encounter cases where things work well, and others where they don't. We encourage you to provide feedback when you use OpenHands to help give feedback to the development team, and perhaps more importantly, create an open corpus of coding agent training examples -- Share-OpenHands!
 
 ## 📝 How to Provide Feedback
 
-Providing feedback is easy! When you are using OpenDevin, you can press the thumbs-up or thumbs-down button at any point during your interaction with. You will be prompted to provide your email address (e.g. so we can contact you if we want to ask any follow-up questions), and you can choose whether you want to provide feedback publicly or privately.
+Providing feedback is easy! When you are using OpenHands, you can press the thumbs-up or thumbs-down button at any point during your interaction. You will be prompted to provide your email address (e.g. so we can contact you if we want to ask any follow-up questions), and you can choose whether you want to provide feedback publicly or privately.
 
 <iframe width="560" height="315" src="https://www.youtube.com/embed/5rFx-StMVV0?si=svo7xzp6LhGK_GXr" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
 
@@ -18,12 +14,12 @@ Providing feedback is easy! When you are using OpenDevin, you can press the thum
 
 When you submit data, you can submit it either publicly or privately.
 
-* **Public** data will be distributed under the MIT License, like OpenDevin itself, and can be used by the community to train and test models. Obviously, feedback that you can make public will be more valuable for the community as a whole, so when you are not dealing with sensitive information, we would encourage you to choose this option!
-* **Private** data will only be shared with the OpenDevin team for the purpose of improving OpenDevin.
+* **Public** data will be distributed under the MIT License, like OpenHands itself, and can be used by the community to train and test models. Obviously, feedback that you can make public will be more valuable for the community as a whole, so when you are not dealing with sensitive information, we would encourage you to choose this option!
+* **Private** data will only be shared with the OpenHands team for the purpose of improving OpenHands.
 
 ### Who collects and stores the data?
 
-The data is collected and stored by [All Hands AI](https://all-hands.dev), a company founded by OpenDevin maintainers to support and improve OpenDevin.
+The data is collected and stored by [All Hands AI](https://all-hands.dev), a company founded by OpenHands maintainers to support and improve OpenHands.
 
 ### How will public data be released?
 
@@ -31,7 +27,7 @@ The public data will be released when we hit fixed milestones, such as 1,000 pub
 At this time, we will follow the following release process:
 
 1. All people who contributed public feedback will receive an email describing the data release and being given an opportunity to opt out.
-2. The person or people in charge of the data release will perform quality control of the data, removing low-quality feedback, removing email submitter email addresses, and attempting to remove any sensitive information such as API keys.
+2. The person or people in charge of the data release will perform quality control of the data, removing low-quality feedback, removing email submitter email addresses, and attempting to remove any sensitive information.
 3. The data will be released publicly under the MIT license through commonly used sites such as github or Hugging Face.
 
 ### What if I want my data deleted?

docs/modules/usage/getting-started.mdx

@@ -0,0 +1,111 @@
+# Getting Started with OpenHands
+
+So you've [installed OpenHands](./installation) and have
+[set up your LLM](./installation#setup). Now what?
+
+OpenHands can help you tackle a wide variety of engineering tasks. But the technology
+is still new, and we're a long way off from having agents that can take on large, complicated
+engineering tasks without any guidance. So it's important to get a feel for what the agent
+does well, and where it might need some help.
+
+## Hello World
+
+The first thing you might want to try is a simple "hello world" example.
+This can be more complicated than it sounds!
+
+Try prompting the agent with:
+> Please write a bash script hello.sh that prints "hello world!"
+
+You should see that the agent not only writes the script, it sets the correct
+permissions and runs the script to check the output.
+
+You can continue prompting the agent to refine your code. This is a great way to
+work with agents. Start simple, and iterate.
+
+> Please modify hello.sh so that it accepts a name as the first argument, but defaults to "world"
+
+You can also work in any language you need, though the agent might need to spend some
+time setting up its environment!
+
+> Please convert hello.sh to a Ruby script, and run it
+
+## Building From Scratch
+
+Agents do exceptionally well at "greenfield" tasks (tasks where they don't need
+any context about an existing codebase) and they can just start from scratch.
+
+It's best to start with a simple task, and then iterate on it. It's also best to be
+as specific as possible about what you want, what the tech stack should be, etc.
+
+For example, we might build a TODO app:
+
+> Please build a basic TODO list app in React. It should be frontend-only, and all state
+> should be kept in localStorage.
+
+We can keep iterating on the app once the skeleton is there:
+
+> Please allow adding an optional due date to every task
+
+Just like with normal development, it's good to commit and push your code frequently.
+This way you can always revert back to an old state if the agent goes off track.
+You can ask the agent to commit and push for you:
+
+> Please commit the changes and push them to a new branch called "feature/due-dates"
+
+
+## Adding New Code
+
+OpenHands can also do a great job adding new code to an existing code base.
+
+For example, you can ask OpenHands to add a new GitHub action to your project
+which lints your code. OpenHands may take a peek at your codebase to see what language
+it should use, but then it can just drop a new file into `./github/workflows/lint.yml`
+
+> Please add a GitHub action that lints the code in this repository
+
+Some tasks might require a bit more context. While OpenHands can use `ls` and `grep`
+to search through your codebase, providing context up front allows it to move faster,
+and more accurately. And it'll cost you fewer tokens!
+
+> Please modify ./backend/api/routes.js to add a new route that returns a list of all tasks
+
+> Please add a new React component that displays a list of Widgets to the ./frontend/components
+> directory. It should use the existing Widget component.
+
+## Refactoring
+
+OpenHands does great at refactoring existing code, especially in small chunks.
+You probably don't want to try rearchitecting your whole codebase, but breaking up
+long files and functions, renaming variables, etc. tend to work very well.
+
+> Please rename all the single-letter variables in ./app.go
+
+> Please break the function `build_and_deploy_widgets` into two functions, `build_widgets` and `deploy_widgets` in widget.php
+
+> Please break ./api/routes.js into separate files for each route
+
+## Bug Fixes
+
+OpenHands can also help you track down and fix bugs in your code. But, as any
+developer knows, bug fixing can be extremely tricky, and often OpenHands will need more context.
+It helps if you've diagnosed the bug, but want OpenHands to figure out the logic.
+
+> Currently the email field in the `/subscribe` endpoint is rejecting .io domains. Please fix this.
+
+> The `search_widgets` function in ./app.py is doing a case-sensitive search. Please make it case-insensitive.
+
+It often helps to do test-driven development when bugfixing with an agent.
+You can ask the agent to write a new test, and then iterate until it fixes the bug:
+
+> The `hello` function crashes on the empty string. Please write a test that reproduces this bug, then fix the code so it passes.
+
+## More
+
+OpenHands is capable of helping out on just about any coding task. But it takes some practice
+to get the most out of it. Remember to:
+* Keep your tasks small
+* Be as specific as possible
+* Provide as much context as possible
+* Commit and push frequently
+
+See [Prompting Best Practices](./prompting-best-practices) for more tips on how to get the most out of OpenHands.

docs/modules/usage/how-to/cli-mode.md

@@ -0,0 +1,108 @@
+# CLI Mode
+
+OpenHands can be run in an interactive CLI mode, which allows users to start an interactive session via the command line.
+
+This mode is different from the [headless mode](headless-mode), which is non-interactive and better for scripting.
+
+## With Python
+
+To start an interactive OpenHands session via the command line, follow these steps:
+
+1. Ensure you have followed the [Development setup instructions](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
+
+2. Run the following command:
+
+```bash
+poetry run python -m openhands.core.cli
+```
+
+This command will start an interactive session where you can input tasks and receive responses from OpenHands.
+
+You'll need to be sure to set your model, API key, and other settings via environment variables
+[or the `config.toml` file](https://github.com/All-Hands-AI/OpenHands/blob/main/config.template.toml).
+
+
+## With Docker
+
+To run OpenHands in CLI mode with Docker, follow these steps:
+
+1. Set `WORKSPACE_BASE` to the directory you want OpenHands to edit:
+
+```bash
+WORKSPACE_BASE=$(pwd)/workspace
+```
+
+2. Set `LLM_MODEL` to the model you want to use:
+
+```bash
+LLM_MODEL="anthropic/claude-3-5-sonnet-20240620"
+```
+
+3. Set `LLM_API_KEY` to your API key:
+
+```bash
+LLM_API_KEY="sk_test_12345"
+```
+
+4. Run the following Docker command:
+
+```bash
+docker run -it \
+    --pull=always \
+    -e SANDBOX_USER_ID=$(id -u) \
+    -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
+    -e LLM_API_KEY=$LLM_API_KEY \
+    -e LLM_MODEL=$LLM_MODEL \
+    -v $WORKSPACE_BASE:/opt/workspace_base \
+    -v /var/run/docker.sock:/var/run/docker.sock \
+    --add-host host.docker.internal:host-gateway \
+    --name openhands-app-$(date +%Y%m%d%H%M%S) \
+    ghcr.io/all-hands-ai/openhands:0.11 \
+    python -m openhands.core.cli
+```
+
+This command will start an interactive session in Docker where you can input tasks and receive responses from OpenHands.
+
+## Examples of CLI Commands and Expected Outputs
+
+Here are some examples of CLI commands and their expected outputs:
+
+### Example 1: Simple Task
+
+```bash
+How can I help? >> Write a Python script that prints "Hello, World!"
+```
+
+Expected Output:
+
+```bash
+🤖 Sure! Here is a Python script that prints "Hello, World!":
+
+❯ print("Hello, World!")
+```
+
+### Example 2: Bash Command
+
+```bash
+How can I help? >> Create a directory named "test_dir"
+```
+
+Expected Output:
+
+```bash
+🤖 Creating a directory named "test_dir":
+
+❯ mkdir test_dir
+```
+
+### Example 3: Error Handling
+
+```bash
+How can I help? >> Delete a non-existent file
+```
+
+Expected Output:
+
+```bash
+🤖 An error occurred. Please try again.
+```

docs/modules/usage/how-to/custom-sandbox-guide.md

@@ -0,0 +1,86 @@
+# Custom Sandbox
+
+The sandbox is where the agent performs its tasks. Instead of running commands directly on your computer
+(which could be risky), the agent runs them inside a Docker container.
+
+The default OpenHands sandbox (`python-nodejs:python3.12-nodejs22`
+from [nikolaik/python-nodejs](https://hub.docker.com/r/nikolaik/python-nodejs)) comes with some packages installed such
+as python and Node.js but may need other software installed by default.
+
+You have two options for customization:
+
+1. Use an existing image with the required software.
+2. Create your own custom Docker image.
+
+If you choose the first option, you can skip the `Create Your Docker Image` section.
+
+## Create Your Docker Image
+
+To create a custom Docker image, it must be Debian based.
+
+For example, if you want OpenHands to have `ruby` installed, create a `Dockerfile` with the following content:
+
+```dockerfile
+FROM debian:latest
+
+# Install required packages
+RUN apt-get update && apt-get install -y ruby
+```
+
+Save this file in a folder. Then, build your Docker image (e.g., named custom-image) by navigating to the folder in
+the terminal and running::
+```bash
+docker build -t custom-image .
+```
+
+This will produce a new image called `custom-image`, which will be available in Docker.
+
+> Note that in the configuration described in this document, OpenHands will run as user "openhands" inside the
+> sandbox and thus all packages installed via the docker file should be available to all users on the system, not just root.
+
+## Using the Development Workflow
+
+### Setup
+
+First, ensure you can run OpenHands by following the instructions in [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
+
+### Specify the Base Sandbox Image
+
+In the `config.toml` file within the OpenHands directory, set the `sandbox_base_container_image` to the image you want to use.
+This can be an image you’ve already pulled or one you’ve built:
+
+```bash
+[core]
+...
+sandbox_base_container_image="custom-image"
+```
+
+### Run
+
+Run OpenHands by running ```make run``` in the top level directory.
+
+## Technical Explanation
+
+Please refer to [custom docker image section of the runtime documentation](https://docs.all-hands.dev/modules/usage/architecture/runtime#advanced-how-openhands-builds-and-maintains-od-runtime-images) for more details.
+
+## Troubleshooting / Errors
+
+### Error: ```useradd: UID 1000 is not unique```
+
+If you see this error in the console output it is because OpenHands is trying to create the openhands user in the sandbox with a UID of 1000, however this UID is already being used in the image (for some reason). To fix this change the sandbox_user_id field in the config.toml file to a different value:
+
+```toml
+[core]
+workspace_base="./workspace"
+run_as_openhands=true
+sandbox_base_container_image="custom_image"
+sandbox_user_id="1001"
+```
+
+### Port use errors
+
+If you see an error about a port being in use or unavailable, try deleting all running Docker Containers (run `docker ps` and `docker rm` relevant containers) and then re-running ```make run``` .
+
+## Discuss
+
+For other issues or questions join the [Slack](https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA) or [Discord](https://discord.gg/ESHStjSjD4) and ask!

docs/modules/usage/how-to/debugging.md

@@ -0,0 +1,71 @@
+# Debugging
+
+The following is intended as a primer on debugging OpenHands for Development purposes.
+
+## Server / VSCode
+
+The following `launch.json` will allow debugging the agent, controller and server elements, but not the sandbox (Which runs inside docker). It will ignore any changes inside the `workspace/` directory:
+
+```
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "OpenHands CLI",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "openhands.core.cli",
+            "justMyCode": false
+        },
+        {
+            "name": "OpenHands WebApp",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "uvicorn",
+            "args": [
+                "openhands.server.listen:app",
+                "--reload",
+                "--reload-exclude",
+                "${workspaceFolder}/workspace",
+                "--port",
+                "3000"
+            ],
+            "justMyCode": false
+        }
+    ]
+}
+```
+
+More specific debugging configurations which include more parameters may be specified:
+
+```
+    ...
+    {
+      "name": "Debug CodeAct",
+      "type": "debugpy",
+      "request": "launch",
+      "module": "openhands.core.main",
+      "args": [
+        "-t",
+        "Ask me what your task is.",
+        "-d",
+        "${workspaceFolder}/workspace",
+        "-c",
+        "CodeActAgent",
+        "-l",
+        "llm.o1",
+        "-n",
+        "prompts"
+      ],
+      "justMyCode": false
+    }
+    ...
+```
+
+Values in the snippet above can be updated such that:
+
+    * *t*: the task
+    * *d*: the openhands workspace directory
+    * *c*: the agent
+    * *l*: the LLM config (pre-defined in config.toml)
+    * *n*: session name (e.g. eventstream name)

docs/modules/usage/how-to/evaluation-harness.md

@@ -0,0 +1,278 @@
+# Evaluation
+
+This guide provides an overview of how to integrate your own evaluation benchmark into the OpenHands framework.
+
+## Setup Environment and LLM Configuration
+
+Please follow instructions [here](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) to setup your local development environment.
+OpenHands in development mode uses `config.toml` to keep track of most configurations.
+
+Here's an example configuration file you can use to define and use multiple LLMs:
+
+```toml
+[llm]
+# IMPORTANT: add your API key here, and set the model to the one you want to evaluate
+model = "claude-3-5-sonnet-20240620"
+api_key = "sk-XXX"
+
+[llm.eval_gpt4_1106_preview_llm]
+model = "gpt-4-1106-preview"
+api_key = "XXX"
+temperature = 0.0
+
+[llm.eval_some_openai_compatible_model_llm]
+model = "openai/MODEL_NAME"
+base_url = "https://OPENAI_COMPATIBLE_URL/v1"
+api_key = "XXX"
+temperature = 0.0
+```
+
+
+## How to use OpenHands in the command line
+
+OpenHands can be run from the command line using the following format:
+
+```bash
+poetry run python ./openhands/core/main.py \
+        -i <max_iterations> \
+        -t "<task_description>" \
+        -c <agent_class> \
+        -l <llm_config>
+```
+
+For example:
+
+```bash
+poetry run python ./openhands/core/main.py \
+        -i 10 \
+        -t "Write me a bash script that prints hello world." \
+        -c CodeActAgent \
+        -l llm
+```
+
+This command runs OpenHands with:
+- A maximum of 10 iterations
+- The specified task description
+- Using the CodeActAgent
+- With the LLM configuration defined in the `llm` section of your `config.toml` file
+
+## How does OpenHands work
+
+The main entry point for OpenHands is in `openhands/core/main.py`. Here's a simplified flow of how it works:
+
+1. Parse command-line arguments and load the configuration
+2. Create a runtime environment using `create_runtime()`
+3. Initialize the specified agent
+4. Run the controller using `run_controller()`, which:
+   - Attaches the runtime to the agent
+   - Executes the agent's task
+   - Returns a final state when complete
+
+The `run_controller()` function is the core of OpenHands's execution. It manages the interaction between the agent, the runtime, and the task, handling things like user input simulation and event processing.
+
+
+## Easiest way to get started: Exploring Existing Benchmarks
+
+We encourage you to review the various evaluation benchmarks available in the [`evaluation/` directory](https://github.com/All-Hands-AI/OpenHands/blob/main/evaluation) of our repository.
+
+To integrate your own benchmark, we suggest starting with the one that most closely resembles your needs. This approach can significantly streamline your integration process, allowing you to build upon existing structures and adapt them to your specific requirements.
+
+## How to create an evaluation workflow
+
+
+To create an evaluation workflow for your benchmark, follow these steps:
+
+1. Import relevant OpenHands utilities:
+   ```python
+    import openhands.agenthub
+    from evaluation.utils.shared import (
+        EvalMetadata,
+        EvalOutput,
+        make_metadata,
+        prepare_dataset,
+        reset_logger_for_multiprocessing,
+        run_evaluation,
+    )
+    from openhands.controller.state.state import State
+    from openhands.core.config import (
+        AppConfig,
+        SandboxConfig,
+        get_llm_config_arg,
+        parse_arguments,
+    )
+    from openhands.core.logger import openhands_logger as logger
+    from openhands.core.main import create_runtime, run_controller
+    from openhands.events.action import CmdRunAction
+    from openhands.events.observation import CmdOutputObservation, ErrorObservation
+    from openhands.runtime.runtime import Runtime
+   ```
+
+2. Create a configuration:
+   ```python
+   def get_config(instance: pd.Series, metadata: EvalMetadata) -> AppConfig:
+       config = AppConfig(
+           default_agent=metadata.agent_class,
+           runtime='eventstream',
+           max_iterations=metadata.max_iterations,
+           sandbox=SandboxConfig(
+               base_container_image='your_container_image',
+               enable_auto_lint=True,
+               timeout=300,
+           ),
+       )
+       config.set_llm_config(metadata.llm_config)
+       return config
+   ```
+
+3. Initialize the runtime and set up the evaluation environment:
+   ```python
+   def initialize_runtime(runtime: Runtime, instance: pd.Series):
+       # Set up your evaluation environment here
+       # For example, setting environment variables, preparing files, etc.
+       pass
+   ```
+
+4. Create a function to process each instance:
+   ```python
+   from openhands.utils.async_utils import call_async_from_sync
+   def process_instance(instance: pd.Series, metadata: EvalMetadata) -> EvalOutput:
+       config = get_config(instance, metadata)
+       runtime = create_runtime(config)
+       call_async_from_sync(runtime.connect)
+       initialize_runtime(runtime, instance)
+
+       instruction = get_instruction(instance, metadata)
+
+       state = run_controller(
+           config=config,
+           task_str=instruction,
+           runtime=runtime,
+           fake_user_response_fn=your_user_response_function,
+       )
+
+       # Evaluate the agent's actions
+       evaluation_result = await evaluate_agent_actions(runtime, instance)
+
+       return EvalOutput(
+           instance_id=instance.instance_id,
+           instruction=instruction,
+           test_result=evaluation_result,
+           metadata=metadata,
+           history=state.history.compatibility_for_eval_history_pairs(),
+           metrics=state.metrics.get() if state.metrics else None,
+           error=state.last_error if state and state.last_error else None,
+       )
+   ```
+
+5. Run the evaluation:
+   ```python
+   metadata = make_metadata(llm_config, dataset_name, agent_class, max_iterations, eval_note, eval_output_dir)
+   output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
+   instances = prepare_dataset(your_dataset, output_file, eval_n_limit)
+
+   await run_evaluation(
+       instances,
+       metadata,
+       output_file,
+       num_workers,
+       process_instance
+   )
+   ```
+
+This workflow sets up the configuration, initializes the runtime environment, processes each instance by running the agent and evaluating its actions, and then collects the results into an `EvalOutput` object. The `run_evaluation` function handles parallelization and progress tracking.
+
+Remember to customize the `get_instruction`, `your_user_response_function`, and `evaluate_agent_actions` functions according to your specific benchmark requirements.
+
+By following this structure, you can create a robust evaluation workflow for your benchmark within the OpenHands framework.
+
+
+## Understanding the `user_response_fn`
+
+The `user_response_fn` is a crucial component in OpenHands's evaluation workflow. It simulates user interaction with the agent, allowing for automated responses during the evaluation process. This function is particularly useful when you want to provide consistent, predefined responses to the agent's queries or actions.
+
+
+### Workflow and Interaction
+
+The correct workflow for handling actions and the `user_response_fn` is as follows:
+
+1. Agent receives a task and starts processing
+2. Agent emits an Action
+3. If the Action is executable (e.g., CmdRunAction, IPythonRunCellAction):
+   - The Runtime processes the Action
+   - Runtime returns an Observation
+4. If the Action is not executable (typically a MessageAction):
+   - The `user_response_fn` is called
+   - It returns a simulated user response
+5. The agent receives either the Observation or the simulated response
+6. Steps 2-5 repeat until the task is completed or max iterations are reached
+
+Here's a more accurate visual representation:
+
+```
+                 [Agent]
+                    |
+                    v
+               [Emit Action]
+                    |
+                    v
+            [Is Action Executable?]
+           /                       \
+         Yes                        No
+          |                          |
+          v                          v
+     [Runtime]               [user_response_fn]
+          |                          |
+          v                          v
+  [Return Observation]    [Simulated Response]
+           \                        /
+            \                      /
+             v                    v
+           [Agent receives feedback]
+                    |
+                    v
+         [Continue or Complete Task]
+```
+
+In this workflow:
+
+- Executable actions (like running commands or executing code) are handled directly by the Runtime
+- Non-executable actions (typically when the agent wants to communicate or ask for clarification) are handled by the `user_response_fn`
+- The agent then processes the feedback, whether it's an Observation from the Runtime or a simulated response from the `user_response_fn`
+
+This approach allows for automated handling of both concrete actions and simulated user interactions, making it suitable for evaluation scenarios where you want to test the agent's ability to complete tasks with minimal human intervention.
+
+### Example Implementation
+
+Here's an example of a `user_response_fn` used in the SWE-Bench evaluation:
+
+```python
+def codeact_user_response(state: State | None) -> str:
+    msg = (
+        'Please continue working on the task on whatever approach you think is suitable.\n'
+        'If you think you have solved the task, please first send your answer to user through message and then <execute_bash> exit </execute_bash>.\n'
+        'IMPORTANT: YOU SHOULD NEVER ASK FOR HUMAN HELP.\n'
+    )
+
+    if state and state.history:
+        # check if the agent has tried to talk to the user 3 times, if so, let the agent know it can give up
+        user_msgs = [
+            event
+            for event in state.history.get_events()
+            if isinstance(event, MessageAction) and event.source == 'user'
+        ]
+        if len(user_msgs) >= 2:
+            # let the agent know that it can give up when it has tried 3 times
+            return (
+                msg
+                + 'If you want to give up, run: <execute_bash> exit </execute_bash>.\n'
+            )
+    return msg
+```
+
+This function does the following:
+
+1. Provides a standard message encouraging the agent to continue working
+2. Checks how many times the agent has attempted to communicate with the user
+3. If the agent has made multiple attempts, it provides an option to give up
+
+By using this function, you can ensure consistent behavior across multiple evaluation runs and prevent the agent from getting stuck waiting for human input.