Fix issue #4735: Update msw mocks (#4736)

Co-authored-by: tofarr <tofarr@gmail.com>

.devcontainer/README.MD

@@ -0,0 +1 @@
+The files in this directory configure a development container for GitHub Codespaces.

.devcontainer/devcontainer.json

@@ -0,0 +1,15 @@
+{
+	"name": "OpenHands Codespaces",
+	"image": "mcr.microsoft.com/devcontainers/universal",
+	"customizations":{
+        "vscode":{
+            "extensions": [
+                "ms-python.python"
+            ]
+        }
+    },
+	"onCreateCommand": "sh ./.devcontainer/on_create.sh",
+	"postCreateCommand": "make build",
+	"postStartCommand": "USE_HOST_NETWORK=True nohup bash -c 'make run &'"
+
+}

.devcontainer/on_create.sh

@@ -0,0 +1,6 @@
+#!/usr/bin/env bash
+sudo apt update
+sudo apt install -y netcat
+sudo add-apt-repository -y ppa:deadsnakes/ppa
+sudo apt install -y python3.12
+curl -sSL https://install.python-poetry.org | python3.12 -

.github/.codecov.yml

@@ -1,6 +1,9 @@
 codecov:
   notify:
     wait_for_ci: true
+    # our project is large, so 6 builds are typically uploaded. this waits till 5/6
+    # See https://docs.codecov.com/docs/notifications#section-preventing-notifications-until-after-n-builds
+    after_n_builds: 5
 
 coverage:
   status:
@@ -14,6 +17,3 @@ coverage:
 comment: false
 github_checks:
     annotations: false
-
-ignore:
-  - "agenthub/SWE_agent/**" # SWE agent is deprecated

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -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://opendevin.github.io/OpenDevin/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: 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

@@ -1,15 +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"
-  - 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: 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: "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

@@ -0,0 +1,11 @@
+**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**
+
+
+
+---
+**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

@@ -1,33 +1,61 @@
-name: Run e2e test with dummy agent
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+# Workflow that uses the DummyAgent to run a simple task
+name: Run E2E test with dummy agent
 
+# 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
-          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: |
-          poetry run python opendevin/core/main.py -t "do a flip" -m ollama/not-a-model -d ./workspace/ -c DummyAgent
+          set -e
+          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
+            echo "Test failed"
+            exit 1
+          else
+            echo "Test passed"
+          fi

.github/workflows/eval-runner.yml

@@ -0,0 +1,160 @@
+name: Run Evaluation
+
+on:
+  pull_request:
+    types: [labeled]
+  schedule:
+    - cron: "0 1 * * *" # Run daily at 1 AM UTC
+  workflow_dispatch:
+    inputs:
+      reason:
+        description: "Reason for manual trigger"
+        required: true
+        default: ""
+
+env:
+  N_PROCESSES: 32 # Global configuration for number of parallel processes for evaluation
+
+jobs:
+  run-evaluation:
+    if: github.event.label.name == 'eval-this' || github.event_name != 'pull_request'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: "read"
+      id-token: "write"
+      pull-requests: "write"
+      issues: "write"
+    strategy:
+      matrix:
+        python-version: ["3.12"]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "poetry"
+
+      - name: Comment on PR if 'eval-this' label is present
+        if: github.event_name == 'pull_request' && github.event.label.name == 'eval-this'
+        uses: KeisukeYamashita/create-comment@v1
+        with:
+          unique: false
+          comment: |
+            Hi! I started running the evaluation on your PR. You will receive a comment with the results shortly.
+
+      - name: Install Python dependencies using Poetry
+        run: poetry install
+
+      - name: Configure config.toml for evaluation
+        env:
+          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_LLM_API_KEY }}
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"deepseek/deepseek-chat\"" >> config.toml
+          echo "api_key = \"$DEEPSEEK_API_KEY\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+
+      - name: Run integration test evaluation
+        env:
+          ALLHANDS_API_KEY: ${{ secrets.ALLHANDS_EVAL_RUNTIME_API_KEY }}
+          RUNTIME: remote
+          SANDBOX_REMOTE_RUNTIME_API_URL: https://runtime.eval.all-hands.dev
+          EVAL_DOCKER_IMAGE_PREFIX: us-central1-docker.pkg.dev/evaluation-092424/swe-bench-images
+
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' $N_PROCESSES
+
+          # get evaluation report
+          REPORT_FILE=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/deepseek-chat_maxiter_10_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE: $REPORT_FILE"
+          echo "INTEGRATION_TEST_REPORT<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      - name: Run SWE-Bench evaluation
+        env:
+          ALLHANDS_API_KEY: ${{ secrets.ALLHANDS_EVAL_RUNTIME_API_KEY }}
+          RUNTIME: remote
+          SANDBOX_REMOTE_RUNTIME_API_URL: https://runtime.eval.all-hands.dev
+          EVAL_DOCKER_IMAGE_PREFIX: us-central1-docker.pkg.dev/evaluation-092424/swe-bench-images
+
+        run: |
+          poetry run ./evaluation/swe_bench/scripts/run_infer.sh llm.eval HEAD CodeActAgent 300 30 $N_PROCESSES "princeton-nlp/SWE-bench_Lite" test
+          OUTPUT_FOLDER=$(find evaluation/evaluation_outputs/outputs/princeton-nlp__SWE-bench_Lite-test/CodeActAgent -name "deepseek-chat_maxiter_50_N_*-no-hint-run_1" -type d | head -n 1)
+          echo "OUTPUT_FOLDER for SWE-bench evaluation: $OUTPUT_FOLDER"
+          poetry run ./evaluation/swe_bench/scripts/eval_infer_remote.sh $OUTPUT_FOLDER/output.jsonl $N_PROCESSES "princeton-nlp/SWE-bench_Lite" test
+
+          poetry run ./evaluation/swe_bench/scripts/eval/summarize_outputs.py $OUTPUT_FOLDER/output.jsonl > summarize_outputs.log 2>&1
+          echo "SWEBENCH_REPORT<<EOF" >> $GITHUB_ENV
+          cat summarize_outputs.log >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      - name: Create tar.gz of evaluation outputs
+        run: |
+          TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
+          tar -czvf evaluation_outputs_${TIMESTAMP}.tar.gz evaluation/evaluation_outputs/outputs
+
+      - name: Upload evaluation results as artifact
+        uses: actions/upload-artifact@v4
+        id: upload_results_artifact
+        with:
+          name: evaluation-outputs
+          path: evaluation_outputs_*.tar.gz
+
+      - name: Get artifact URL
+        run: echo "ARTIFACT_URL=${{ steps.upload_results_artifact.outputs.artifact-url }}" >> $GITHUB_ENV
+
+      - name: Authenticate to Google Cloud
+        uses: 'google-github-actions/auth@v2'
+        with:
+          credentials_json: ${{ secrets.GCP_RESEARCH_OBJECT_CREATOR_SA_KEY }}
+
+      - name: Set timestamp and trigger reason
+        run: |
+          echo "TIMESTAMP=$(date +'%Y-%m-%d-%H-%M')" >> $GITHUB_ENV
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            echo "TRIGGER_REASON=pr-${{ github.event.pull_request.number }}" >> $GITHUB_ENV
+          elif [[ "${{ github.event_name }}" == "schedule" ]]; then
+            echo "TRIGGER_REASON=schedule" >> $GITHUB_ENV
+          else
+            echo "TRIGGER_REASON=manual-${{ github.event.inputs.reason }}" >> $GITHUB_ENV
+          fi
+
+      - name: Upload evaluation results to Google Cloud Storage
+        uses: 'google-github-actions/upload-cloud-storage@v2'
+        with:
+          path: 'evaluation/evaluation_outputs/outputs'
+          destination: 'openhands-oss-eval-results/${{ env.TIMESTAMP }}-${{ env.TRIGGER_REASON }}'
+
+      - name: Comment with evaluation results and artifact link
+        id: create_comment
+        uses: KeisukeYamashita/create-comment@v1
+        with:
+          number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || 4504 }}
+          unique: false
+          comment: |
+              Trigger by: ${{ github.event_name == 'pull_request' && format('Pull Request (eval-this label on PR #{0})', github.event.pull_request.number) || github.event_name == 'schedule' && 'Daily Schedule' || format('Manual Trigger: {0}', github.event.inputs.reason) }}
+              Commit: ${{ github.sha }}
+              **SWE-Bench Evaluation Report**
+              ${{ env.SWEBENCH_REPORT }}
+              ---
+              **Integration Tests Evaluation Report**
+              ${{ env.INTEGRATION_TEST_REPORT }}
+              ---
+              You can download the full evaluation outputs [here](${{ env.ARTIFACT_URL }}).
+
+      - name: Post to a Slack channel
+        id: slack
+        uses: slackapi/slack-github-action@v1.27.0
+        with:
+          channel-id: 'C07SVQSCR6F'
+          slack-message: "*Evaluation Trigger:* ${{ github.event_name == 'pull_request' && format('Pull Request (eval-this label on PR #{0})', github.event.pull_request.number) || github.event_name == 'schedule' && 'Daily Schedule' || format('Manual Trigger: {0}', github.event.inputs.reason) }}\n\nLink to summary: [here](https://github.com/${{ github.repository }}/issues/${{ github.event_name == 'pull_request' && github.event.pull_request.number || 4504 }}#issuecomment-${{ steps.create_comment.outputs.comment-id }})"
+        env:
+          SLACK_BOT_TOKEN: ${{ secrets.EVAL_NOTIF_SLACK_BOT_TOKEN }}

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

@@ -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 +1,447 @@
+# Workflow that builds, tests and then pushes the OpenHands and runtime docker images to the ghcr.io repository
+name: Docker
+
+# Always run on "main"
+# Always run on tags
+# Always run on PRs
+# Can also be triggered manually
+on:
+  push:
+    branches:
+      - main
+    tags:
+      - '*'
+  pull_request:
+  workflow_dispatch:
+    inputs:
+      reason:
+        description: 'Reason for manual trigger'
+        required: true
+        default: ''
+
+# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
+concurrency:
+  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST: nikolaik/python-nodejs:python3.12-nodejs22
+  RELEVANT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
+
+jobs:
+  # Builds the OpenHands Docker images
+  ghcr_build_app:
+    name: Build App Image
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    outputs:
+      hash_from_app_image: ${{ steps.get_hash_in_app_image.outputs.hash_from_app_image }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3.0.0
+        with:
+          image: tonistiigi/binfmt:latest
+      - name: Login to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Build and push app image
+        if: "!github.event.pull_request.head.repo.fork"
+        run: |
+          ./containers/build.sh -i openhands -o ${{ github.repository_owner }} --push
+      - name: Build app image
+        if: "github.event.pull_request.head.repo.fork"
+        run: |
+          ./containers/build.sh -i openhands -o ${{ github.repository_owner }} --load
+      - name: Get hash in App Image
+        id: get_hash_in_app_image
+        run: |
+          # Lowercase the repository owner
+          export REPO_OWNER=${{ github.repository_owner }}
+          REPO_OWNER=$(echo $REPO_OWNER | tr '[:upper:]' '[:lower:]')
+          # Run the build script in the app image
+          docker run -e SANDBOX_USER_ID=0 -v /var/run/docker.sock:/var/run/docker.sock ghcr.io/${REPO_OWNER}/openhands:${{ env.RELEVANT_SHA }} /bin/bash -c "mkdir -p containers/runtime; python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild" 2>&1 | tee docker-outputs.txt
+          # Get the hash from the build script
+          hash_from_app_image=$(cat docker-outputs.txt | grep "Hash for docker build directory" | awk -F "): " '{print $2}' | uniq | head -n1)
+          echo "hash_from_app_image=$hash_from_app_image" >> $GITHUB_OUTPUT
+          echo "Hash from app image: $hash_from_app_image"
+
+  # Builds the runtime Docker images
+  ghcr_build_runtime:
+    name: Build Image
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    strategy:
+      matrix:
+        base_image:
+          - image: 'nikolaik/python-nodejs:python3.12-nodejs22'
+            tag: nikolaik
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3.0.0
+        with:
+          image: tonistiigi/binfmt:latest
+      - name: Login to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      - name: Cache Poetry dependencies
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies
+      - name: Create source distribution and Dockerfile
+        run: poetry run python3 openhands/runtime/utils/runtime_build.py --base_image ${{ matrix.base_image.image }} --build_folder containers/runtime --force_rebuild
+      - name: Build and push runtime image ${{ matrix.base_image.image }}
+        if: github.event.pull_request.head.repo.fork != true
+        run: |
+          ./containers/build.sh -i runtime -o ${{ github.repository_owner }} --push -t ${{ matrix.base_image.tag }}
+      # Forked repos can't push to GHCR, so we need to upload the image as an artifact
+      - name: Build runtime image ${{ matrix.base_image.image }} for fork
+        if: github.event.pull_request.head.repo.fork
+        uses: docker/build-push-action@v6
+        with:
+          tags: ghcr.io/all-hands-ai/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+          outputs: type=docker,dest=/tmp/runtime-${{ matrix.base_image.tag }}.tar
+          context: containers/runtime
+      - name: Upload runtime image for fork
+        if: github.event.pull_request.head.repo.fork
+        uses: actions/upload-artifact@v4
+        with:
+          name: runtime-${{ matrix.base_image.tag }}
+          path: /tmp/runtime-${{ matrix.base_image.tag }}.tar
+
+  verify_hash_equivalence_in_runtime_and_app:
+    name: Verify Hash Equivalence in Runtime and Docker images
+    runs-on: ubuntu-latest
+    needs: [ghcr_build_runtime, ghcr_build_app]
+    strategy:
+      fail-fast: false
+      matrix:
+        base_image: ['nikolaik']
+    steps:
+      - uses: actions/checkout@v4
+      - name: Cache Poetry dependencies
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies
+      - name: Get hash in App Image
+        run: |
+          echo "Hash from app image: ${{ needs.ghcr_build_app.outputs.hash_from_app_image }}"
+          echo "hash_from_app_image=${{ needs.ghcr_build_app.outputs.hash_from_app_image }}" >> $GITHUB_ENV
+
+      - name: Get hash using code (development mode)
+        run: |
+          mkdir -p containers/runtime
+          poetry run python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild > output.txt 2>&1
+          hash_from_code=$(cat output.txt | grep "Hash for docker build directory" | awk -F "): " '{print $2}' | uniq | head -n1)
+          echo "hash_from_code=$hash_from_code" >> $GITHUB_ENV
+
+      - name: Compare hashes
+        run: |
+          echo "Hash from App Image: ${{ env.hash_from_app_image }}"
+          echo "Hash from Code: ${{ env.hash_from_code }}"
+          if [ "${{ env.hash_from_app_image }}" = "${{ env.hash_from_code }}" ]; then
+            echo "Hashes match!"
+          else
+            echo "Hashes do not match!"
+            exit 1
+          fi
+
+  # Run unit tests with the EventStream runtime Docker images as root
+  test_runtime_root:
+    name: RT Unit Tests (Root)
+    needs: [ghcr_build_runtime]
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        base_image: ['nikolaik']
+    steps:
+      - uses: actions/checkout@v4
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+      # Forked repos can't push to GHCR, so we need to download the image as an artifact
+      - name: Download runtime image for fork
+        if: github.event.pull_request.head.repo.fork
+        uses: actions/download-artifact@v4
+        with:
+          name: runtime-${{ matrix.base_image }}
+          path: /tmp
+      - name: Load runtime image for fork
+        if: github.event.pull_request.head.repo.fork
+        run: |
+          docker load --input /tmp/runtime-${{ matrix.base_image }}.tar
+      - name: Cache Poetry dependencies
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies
+      - name: Run runtime tests
+        run: |
+          # We install pytest-xdist in order to run tests across CPUs
+          poetry run pip install pytest-xdist
+
+          # Install to be able to retry on failures for flaky tests
+          poetry run pip install pytest-rerunfailures
+
+          image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
+          image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
+
+          SKIP_CONTAINER_LOGS=true \
+          TEST_RUNTIME=eventstream \
+          SANDBOX_USER_ID=$(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: ${{ cancelled() || contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled') }}
+    runs-on: ubuntu-latest
+    needs: [test_runtime_root, test_runtime_oh, verify_hash_equivalence_in_runtime_and_app]
+    steps:
+      - name: Some tests failed
+        run: |
+          echo "Some runtime tests failed or were cancelled"
+          exit 1
+  update_pr_description:
+    name: Update PR Description
+    if: github.event_name == 'pull_request' && !github.event.pull_request.head.repo.fork && github.actor != 'dependabot[bot]'
+    needs: [ghcr_build_runtime]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Get short SHA
+        id: short_sha
+        run: echo "SHORT_SHA=$(echo ${{ github.event.pull_request.head.sha }} | cut -c1-7)" >> $GITHUB_OUTPUT
+
+      - name: Update PR Description
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+          REPO: ${{ github.repository }}
+          SHORT_SHA: ${{ steps.short_sha.outputs.SHORT_SHA }}
+        run: |
+          echo "updating PR description"
+          DOCKER_RUN_COMMAND="docker run -it --rm \
+            -p 3000:3000 \
+            -v /var/run/docker.sock:/var/run/docker.sock \
+            --add-host host.docker.internal:host-gateway \
+            -e SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:$SHORT_SHA-nikolaik \
+            --name openhands-app-$SHORT_SHA \
+            ghcr.io/all-hands-ai/runtime:$SHORT_SHA"
+
+          PR_BODY=$(gh pr view $PR_NUMBER --json body --jq .body)
+
+          if echo "$PR_BODY" | grep -q "To run this PR locally, use the following command:"; then
+            UPDATED_PR_BODY=$(echo "${PR_BODY}" | sed -E "s|docker run -it --rm.*|$DOCKER_RUN_COMMAND|")
+          else
+            UPDATED_PR_BODY="${PR_BODY}
+
+          ---
+
+          To run this PR locally, use the following command:
+          \`\`\`
+          $DOCKER_RUN_COMMAND
+          \`\`\`"
+          fi
+
+          echo "updated body: $UPDATED_PR_BODY"
+          gh pr edit $PR_NUMBER --body "$UPDATED_PR_BODY"

.github/workflows/ghcr.yml

@@ -1,82 +0,0 @@
-name: Publish Docker 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_and_push:
-    runs-on: ubuntu-latest
-
-    permissions:
-      contents: read
-      packages: write
-
-    strategy:
-      matrix:
-        image: ["app", "sandbox"]
-
-    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: Login to ghcr
-        uses: docker/login-action@v1
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Build and push ${{ matrix.image }}
-        if: "!github.event.pull_request.head.repo.fork"
-        run: |
-          ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} --push
-
-      - name: Build ${{ matrix.image }}
-        if: "github.event.pull_request.head.repo.fork"
-        run: |
-          ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }}
-
-  docker_build_success:
-    name: Docker Build Success
-    runs-on: ubuntu-latest
-    needs: ghcr_build_and_push
-    steps:
-    - run: echo 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/**/* --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 +1,15 @@
+name: Resolve Issues with OpenHands
+
+on:
+  issues:
+    types: [labeled]
+  pull_request:
+    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

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

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

@@ -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:
@@ -12,29 +13,31 @@ jobs:
   dogfood:
     if: contains(github.event.pull_request.labels.*.name, 'review-this')
     runs-on: ubuntu-latest
-    container:
-      image: ghcr.io/opendevin/opendevin
-      volumes:
-        - /var/run/docker.sock:/var/run/docker.sock
-
     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: '3.12'
     - name: install git, github cli
       run: |
-        apt-get install -y git gh
+        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. Read and review ${{ github.event.pull_request.number }}.diff file. Create a review-${{ github.event.pull_request.number }}.txt and write your concise comments and suggestions there." > task.txt
+        echo "Your coworker wants to apply a pull request to this project." > task.txt
+        echo "Read and review ${{ github.event.pull_request.number }}.diff file. Create a review-${{ github.event.pull_request.number }}.txt and write your concise comments and suggestions there." >> task.txt
+        echo "Do not ask me for confirmation at any point." >> task.txt
         echo "" >> task.txt
         echo "Title" >> task.txt
         echo "${{ github.event.pull_request.title }}" >> task.txt
@@ -43,27 +46,25 @@ jobs:
         echo "${{ 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
+        poetry install --without evaluation,llama-index
         poetry run playwright install --with-deps chromium
-
-    - name: Run OpenDevin
+    - name: Run OpenHands
       env:
-        LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-        SANDBOX_TYPE: exec
+        LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+        LLM_MODEL: ${{ vars.LLM_MODEL }}
       run: |
         # Append path to launch poetry
         export PATH="/github/home/.local/bin:$PATH"
         # Append path to correctly import package, note: must set pwd at first
         export PYTHONPATH=$(pwd):$PYTHONPATH
-        WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE poetry run python ./opendevin/core/main.py -i 50 -f task.txt -d $GITHUB_WORKSPACE
+        export WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE
+        export WORKSPACE_BASE=$GITHUB_WORKSPACE
+        echo -e "/exit\n" | poetry run python openhands/core/main.py -i 50 -f task.txt
         rm task.txt
-
     - name: Check if review file is non-empty
       id: check_file
       run: |
@@ -72,7 +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/run-integration-tests.yml

@@ -1,104 +0,0 @@
-name: Run Integration Tests
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-
-on:
-  push:
-    branches:
-      - main
-    paths-ignore:
-      - '**/*.md'
-      - 'frontend/**'
-      - 'docs/**'
-      - 'evaluation/**'
-  pull_request:
-
-env:
-  PERSIST_SANDBOX : "false"
-
-jobs:
-  integration-tests-on-linux:
-    name: Integration Tests on Linux
-    runs-on: ubuntu-latest
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ["3.11"]
-        sandbox: ["ssh", "exec", "local"]
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install
-
-      - name: Build Environment
-        run: make build
-
-      - name: Run Integration Tests
-        env:
-          SANDBOX_TYPE: ${{ matrix.sandbox }}
-        run: |
-          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 }}
-
-  integration-tests-on-mac:
-    name: Integration Tests on MacOS
-    runs-on: macos-13
-    if: contains(github.event.pull_request.title, 'mac') || contains(github.event.pull_request.title, 'Mac')
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ["3.11"]
-        sandbox: ["ssh"]
-    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
-
-      - name: Install & Start Docker
-        run: |
-          brew install colima docker
-          colima start
-
-          # For testcontainers to find the Colima socket
-          # https://github.com/abiosoft/colima/blob/main/docs/FAQ.md#cannot-connect-to-the-docker-daemon-at-unixvarrundockersock-is-the-docker-daemon-running
-          sudo ln -sf $HOME/.colima/default/docker.sock /var/run/docker.sock
-
-      - name: Build Environment
-        run: make build
-
-      - name: Run Integration Tests
-        env:
-          SANDBOX_TYPE: ${{ matrix.sandbox }}
-        run: |
-          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 }}

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

@@ -1,129 +0,0 @@
-name: Run Unit Tests
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-
-on:
-  push:
-    branches:
-      - main
-    paths-ignore:
-      - '**/*.md'
-      - 'frontend/**'
-      - 'docs/**'
-      - 'evaluation/**'
-  pull_request:
-
-env:
-  PERSIST_SANDBOX : "false"
-
-jobs:
-  test-on-macos:
-    name: Test on macOS
-    runs-on: macos-13
-    env:
-      INSTALL_DOCKER: "1" # Set to '0' to skip Docker installation
-    strategy:
-      matrix:
-        python-version: ["3.11"]
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install
-
-      - name: Install & Start Docker
-        if: env.INSTALL_DOCKER == '1'
-        run: |
-          brew install colima docker
-          colima start
-
-          # For testcontainers to find the Colima socket
-          # https://github.com/abiosoft/colima/blob/main/docs/FAQ.md#cannot-connect-to-the-docker-daemon-at-unixvarrundockersock-is-the-docker-daemon-running
-          sudo ln -sf $HOME/.colima/default/docker.sock /var/run/docker.sock
-
-      - name: Build Environment
-        run: make build
-
-      - name: Run Tests
-        run: poetry run pytest --forked --cov=agenthub --cov=opendevin --cov-report=xml ./tests/unit -k "not test_sandbox"
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-  test-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
-
-      - 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"
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
-  test-for-sandbox:
-    name: Test for Sandbox
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-          cache: "poetry"
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install
-
-      - name: Build Environment
-        run: make build
-
-      - name: Run Integration Test for Sandbox
-        run: |
-          poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml -s ./tests/unit/test_sandbox.py
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

.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
-        poetry run playwright install --with-deps chromium
-
-
-    - name: Run OpenDevin
-      env:
-        ISSUE_TITLE: ${{ github.event.issue.title }}
-        ISSUE_BODY: ${{ github.event.issue.body }}
-        LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-        SANDBOX_TYPE: exec
-      run: |
-        # Append path to launch poetry
-        export PATH="/github/home/.local/bin:$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

.gitignore

@@ -121,6 +121,7 @@ celerybeat.pid
 
 # Environments
 .env
+frontend/.env
 .venv
 env/
 venv/
@@ -169,11 +170,15 @@ 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
+evaluation/scienceagentbench/benchmark
 
 # frontend
 
 # dependencies
-frontend/node_modules
 frontend/.pnp
 frontend/bun.lockb
 frontend/yarn.lock
@@ -210,4 +215,17 @@ cache
 
 # configuration
 config.toml
+config.toml_
 config.toml.bak
+
+# swe-bench-eval
+image_build_logs
+run_instance_logs
+
+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`

CODE_OF_CONDUCT.md

@@ -61,7 +61,7 @@ representative at an online or offline event.
 
 Instances of abusive, harassing, or otherwise unacceptable behavior may be
 reported to the community leaders responsible for enforcement at
-contact@rbren.io
+contact@all-hands.dev
 All complaints will be reviewed and investigated promptly and fairly.
 
 All community leaders are obligated to respect the privacy and security of the

CONTRIBUTING.md

@@ -1,63 +1,82 @@
 # Contributing
 
-Thanks for your interest in contributing to OpenDevin! We welcome and appreciate contributions.
-To report bugs, create a [GitHub issue](https://github.com/OpenDevin/OpenDevin/issues/new/choose).
+Thanks for your interest in contributing to OpenHands! We welcome and appreciate contributions.
 
-## Contribution Guide
-### 1. Fork the Official Repository
+## Understanding OpenHands's CodeBase
 
-Fork [OpenDevin repository](https://github.com/OpenDevin/OpenDevin) into your own account.
-Clone your own forked repository into your local environment.
+To understand the codebase, please refer to the README in each module:
+- [frontend](./frontend/README.md)
+- [evaluation](./evaluation/README.md)
+- [openhands](./openhands/README.md)
+   - [agenthub](./openhands/agenthub/README.md)
+   - [server](./openhands/server/README.md)
 
-```shell
-git clone git@github.com:<YOUR-USERNAME>/OpenDevin.git
-```
+## Setting up your development environment
 
-### 2. Configure Git
+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.
 
-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
+## How can I contribute?
 
-```shell
-cd OpenDevin
-git remote add upstream git@github.com:OpenDevin/OpenDevin.git
-```
+There are many ways that you can contribute:
 
-Verify that the remote is set.
-```shell
-git remote -v
-```
-You should see both `origin` and `upstream` in the output.
+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.
 
-### 3. Synchronize with Official Repository
-Synchronize latest commit with official repository before coding.
+## What can I build?
+Here are a few ways you can help improve the codebase.
 
-```shell
-git fetch upstream
-git checkout main
-git merge upstream/main
-git push origin main
-```
+#### 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.
 
-### 4. Create a New Branch And Open a Pull Request
-After you finish implementation, open forked repository. The source branch is your new branch, and the target branch is `OpenDevin/OpenDevin` `main` branch. Then PR should appears in [OpenDevin PRs](https://github.com/OpenDevin/OpenDevin/pulls).
+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.
 
-Then OpenDevin team will review your code.
+#### 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)
 
-## PR Rules
+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.
 
-### 1. Pull Request title
+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.
 
-As described in [here](https://github.com/commitizen/conventional-commit-types/blob/master/index.json), a valid PR title should begin with one of the following prefixes:
+#### 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 OpenHands
+
+You'll need to fork our repository to send us a Pull Request. You can learn more
+about how to fork a GitHub repo and open a PR with your changes in [this article](https://medium.com/swlh/forks-and-pull-requests-how-to-contribute-to-github-repos-8843fac34ce8)
+
+### 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
 - `fix`: A bug fix
-- `doc`: Documentation only changes
+- `docs`: Documentation only changes
+- `style`: Changes that do not affect the meaning of the code (white space, formatting, missing semicolons, etc.)
 - `refactor`: A code change that neither fixes a bug nor adds a feature
-- `style`: A refactoring that improves code style
 - `perf`: A code change that improves performance
 - `test`: Adding missing tests or correcting existing tests
-- `ci`: Changes to CI configuration files and scripts (example scopes: `.github`, `ci` (Buildkite))
+- `build`: Changes that affect the build system or external dependencies (example scopes: gulp, broccoli, npm)
+- `ci`: Changes to our CI configuration files and scripts (example scopes: Travis, Circle, BrowserStack, SauceLabs)
 - `chore`: Other changes that don't modify src or test files
 - `revert`: Reverts a previous commit
 
@@ -65,26 +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).
-
-As described in [here](https://github.com/OpenDevin/OpenDevin/labels), we create several labels. Every PR should be tagged with the corresponding labels.
-
-### 2. Pull Request description
+You may also check out previous PRs in the [PR list](https://github.com/All-Hands-AI/OpenHands/pulls).
 
+### Pull Request description
 - If your PR is small (such as a typo fix), you can go brief.
-- If it is large and you have changed a lot, it's better to write more details.
+- If it contains a lot of changes, it's better to write more details.
 
-
-## How to begin
-Please refer to the README in each module:
-- [frontend](./frontend/README.md)
-- [agenthub](./agenthub/README.md)
-- [evaluation](./evaluation/README.md)
-- [opendevin](./opendevin/README.md)
-    - [server](./opendevin/server/README.md)
-    - [mock server](./opendevin/mock/README.md)
-
-## Tests
-Please navigate to `tests` folder to see existing test suites.
-At the moment, we have two kinds of tests: `unit` and `integration`. Please refer to the README for each test suite. These tests also run on CI to ensure quality of
-the project.
+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

@@ -0,0 +1,312 @@
+# 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
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+
+
+### 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

@@ -1,14 +1,18 @@
 # Development Guide
-This guide is for people working on OpenDevin and editing the source code.
+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)
+* 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
+* 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`.
 
@@ -20,49 +24,47 @@ 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 OpenHands is ready to run on your system:
 
-- **Build the Project:** Begin by building the project, which includes setting up the environment and installing dependencies. This step ensures that OpenDevin is ready to run smoothly on your system.
-    ```bash
-    make build
-    ```
+```bash
+make build
+```
 
 ### 3. Configuring the Language Model
+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.
 
-OpenDevin supports a diverse array of Language Models (LMs) through the powerful [litellm](https://docs.litellm.ai) library. By default, we've chosen the mighty GPT-4 from OpenAI as our go-to model, but the world is your oyster! You can unleash the potential of Anthropic's suave Claude, the enigmatic Llama, or any other LM that piques your interest.
+To configure the LM of your choice, run:
 
-To configure the LM of your choice, follow these steps:
-
-1. **Using the Makefile: The Effortless Approach**
-   With a single command, you can have a smooth LM setup for your OpenDevin experience. Simply run:
    ```bash
    make setup-config
    ```
-   This command will prompt you to enter the LLM API key, model name, and other variables ensuring that OpenDevin is tailored to your specific needs. Note that the model name will apply only when you run headless. If you use the UI, please set the model in the UI.
-   Set `persist_sandbox` to false if you want to use clean sandbox for each task. If `persist_sandbox` is set to true, you will need to set the `ssh_password` as well.
+
+   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 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](https://github.com/OpenDevin/OpenDevin/issues/417).
+Some alternative models may prove more challenging to tame than others. Fear not, brave adventurer! We shall soon unveil LLM-specific documentation to guide you on your quest.
+And if you've already mastered the art of wielding a model other than OpenAI's GPT, we encourage you to share your setup instructions with us by creating instructions and adding it [to our documentation](https://github.com/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).
 
-There is also [documentation for running with local models using ollama](./docs/documentation/LOCAL_LLM_GUIDE.md).
-
-### 4. Run the Application
-
-- **Run the Application:** Once the setup is complete, launching OpenDevin is as simple as running a single command. This command starts both the backend and frontend servers seamlessly, allowing you to interact with OpenDevin without any hassle.
-    ```bash
-    make run
-    ```
-
-### 5. Individual Server Startup
+### 4. Running the application
+#### Option A: Run the Full Application
+Once the setup is complete, launching 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
+```
 
+#### Option B: Individual Server Startup
 - **Start the Backend Server:** If you prefer, you can start the backend server independently to focus on backend-related tasks or configurations.
     ```bash
     make start-backend
@@ -74,29 +76,53 @@ There is also [documentation for running with local models using ollama](./docs/
     ```
 
 ### 6. LLM Debugging
-
-If you encounter any issues with the Language Model (LM) or you're simply curious, you can inspect the actual LLM prompts and responses. To do so, export DEBUG=1 in the environment and restart the backend. OpenDevin will then log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
+If you encounter any issues with the Language Model (LM) or you're simply curious, you can inspect the actual LLM prompts and responses. To do so, export DEBUG=1 in the environment and restart the backend.
+OpenHands will then log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
 
 ### 7. Help
-
-- **Get Some Help:** Need assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenDevin.
-    ```bash
-    make help
-    ```
+Need assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenHands.
+```bash
+make help
+ ```
 
 ### 8. Testing
-
+To run tests, refer to the following:
 #### Unit tests
 
 ```bash
-poetry run pytest ./tests/unit/test_sandbox.py
+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.

ISSUE_TRIAGE.md

@@ -0,0 +1,25 @@
+# Issue Triage
+These are the procedures and guidelines on how issues are triaged in this repo by the maintainers.
+
+## General
+* Most issues must be tagged with **enhancement** or **bug**
+* Issues may be tagged with what it relates to (**backend**, **frontend**, **agent quality**, etc.)
+
+## Severity
+* **Low**: Minor issues, single user report
+* **Medium**: Affecting multiple users
+* **Critical**: Affecting all users or potential security issues
+
+## Effort
+* Issues may be estimated with effort required (**small effort**, **medium effort**, **large effort**)
+
+## Difficulty
+* Issues with low implementation difficulty may be tagged with **good first issue**
+
+## Not Enough Information
+* User is asked to provide more information (logs, how to reproduce, etc.) when the issue is not clear
+* If an issue is unclear and the author does not provide more information or respond to a request, the issue may be closed as **not planned** (Usually after a week)
+
+## Multiple Requests/Fixes in One Issue
+* These issues will be narrowed down to one request/fix so the issue is more easily tracked and fixed
+* Issues may be broken down into multiple issues if required

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
+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
-PRECOMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
-PYTHON_VERSION = 3.11
+PRE_COMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
+PYTHON_VERSION = 3.12
 
 # ANSI color codes
 GREEN=$(shell tput -Txterm setaf 2)
@@ -23,12 +23,9 @@ RESET=$(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-precommit-hooks
+	@$(MAKE) -s install-pre-commit-hooks
 	@$(MAKE) -s build-frontend
 	@echo "$(GREEN)Build completed successfully.$(RESET)"
 
@@ -124,20 +121,19 @@ 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 \
+		echo "Defaulting TZ (timezone) to UTC"; \
+		export TZ="UTC"; \
+	fi
 	poetry env use python$(PYTHON_VERSION)
 	@if [ "$(shell uname)" = "Darwin" ]; then \
 		echo "$(BLUE)Installing chroma-hnswlib...$(RESET)"; \
 		export HNSWLIB_NO_NATIVE=1; \
 		poetry run pip install chroma-hnswlib; \
 	fi
-	@poetry install
+	@poetry install --without llama-index
 	@if [ -f "/etc/manjaro-release" ]; then \
 		echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
 		poetry run pip install playwright; \
@@ -158,22 +154,19 @@ install-frontend-dependencies:
 	@echo "$(YELLOW)Setting up frontend environment...$(RESET)"
 	@echo "$(YELLOW)Detect Node.js version...$(RESET)"
 	@cd frontend && node ./scripts/detect-node-version.js
-	@cd frontend && \
-		echo "$(BLUE)Installing frontend dependencies with npm...$(RESET)" && \
-		npm install && \
-		echo "$(BLUE)Running make-i18n with npm...$(RESET)" && \
-		npm run make-i18n
+	echo "$(BLUE)Installing frontend dependencies with npm...$(RESET)"
+	@cd frontend && npm install
 	@echo "$(GREEN)Frontend dependencies installed successfully.$(RESET)"
 
-install-precommit-hooks:
+install-pre-commit-hooks:
 	@echo "$(YELLOW)Installing pre-commit hooks...$(RESET)"
 	@git config --unset-all core.hooksPath || true
-	@poetry run pre-commit install --config $(PRECOMMIT_CONFIG_PATH)
+	@poetry run pre-commit install --config $(PRE_COMMIT_CONFIG_PATH)
 	@echo "$(GREEN)Pre-commit hooks installed successfully.$(RESET)"
 
 lint-backend:
 	@echo "$(YELLOW)Running linters...$(RESET)"
-	@poetry run pre-commit run --files opendevin/**/* agenthub/**/* evaluation/**/* --show-diff-on-failure --config $(PRECOMMIT_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)"
@@ -197,29 +190,54 @@ 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) --host $(BACKEND_HOST)
 
-# Run the app
-run:
-	@echo "$(YELLOW)Running the app...$(RESET)"
+# Common setup for running the app (non-callable)
+_run_setup:
 	@if [ "$(OS)" = "Windows_NT" ]; then \
-		echo "$(RED)`make run` is not supported on Windows. Please run `make start-frontend` and `make start-backend` separately.$(RESET)"; \
+		echo "$(RED) Windows is not supported, use WSL instead!$(RESET)"; \
 		exit 1; \
 	fi
 	@mkdir -p logs
 	@echo "$(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.$(RESET)"
-	@cd frontend && echo "$(BLUE)Starting frontend with npm...$(RESET)" && npm run start -- --port $(FRONTEND_PORT)
+
+# Run the app (standard mode)
+run:
+	@echo "$(YELLOW)Running the app...$(RESET)"
+	@$(MAKE) -s _run_setup
+	@$(MAKE) -s start-frontend
 	@echo "$(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...$(RESET)"
+	@$(MAKE) -s _run_setup
+	@cd frontend && echo "$(BLUE)Starting frontend with npm (WSL mode)...$(RESET)" && npm run dev_wsl -- --port $(FRONTEND_PORT)
+	@echo "$(GREEN)Application started successfully in WSL mode.$(RESET)"
+
 # Setup config.toml
 setup-config:
 	@echo "$(YELLOW)Setting up config.toml...$(RESET)"
@@ -234,16 +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: true]: " persist_sandbox; \
-	 persist_sandbox=$${persist_sandbox:-true}; \
-	 if [ "$$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
@@ -267,6 +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; \
@@ -283,10 +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
@@ -295,13 +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-precommit-hooks lint start-backend start-frontend run 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

@@ -1,117 +1,106 @@
 <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/openhands-ai/shared_invite/zt-2tom0er4l-JeNUGHt_AxpEfIBstbLPiw"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
   <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
+  <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="Credits"></a>
   <br/>
-  <a href="https://huggingface.co/spaces/OpenDevin/evaluation"><img src="https://img.shields.io/badge/SWE--bench%20Lite-25.0%25-green?style=for-the-badge" alt="SWE-bench "></a>
-  <a href="https://codecov.io/github/opendevin/opendevin?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/opendevin/opendevin?style=for-the-badge"></a>
+  <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>
 
-<!-- PROJECT LOGO -->
-<div align="center">
-  <img src="./docs/static/img/logo.png" alt="Logo" width="200" height="200">
-  <h1 align="center">OpenDevin: Code Less, Make More</h1>
-  <a href="https://opendevin.github.io/OpenDevin/"><img src="https://img.shields.io/badge/Documentation-OpenDevin-blue?logo=googledocs&logoColor=white&style=for-the-badge" alt="Check out the documentation"></a>
-</div>
-<hr>
+Welcome to OpenHands (formerly OpenDevin), a platform for software development agents powered by AI.
 
-Welcome to OpenDevin, a platform for autonomous software engineers, powered by AI and LLMs.
+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.
 
-OpenDevin agents collaborate with human developers to write code, fix bugs, and ship features.
+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
-The easiest way to run OpenDevin is inside a Docker container. It works best with the most recent version of Docker, `26.0.0`.
-You must be using Linux, Mac OS, or WSL on Windows.
+## ⚡ Quick Start
 
-To start OpenDevin in a docker container, run the following commands in your terminal:
-
-> [!WARNING]
-> When you run the following command, files in `./workspace` may be modified or deleted.
+The easiest way to run OpenHands is in Docker.
+See the [Installation](https://docs.all-hands.dev/modules/usage/installation) guide for
+system requirements and more information.
 
 ```bash
-OPENDEVIN_WORKSPACE=$(pwd)/workspace
-docker run -it \
-    --pull=always \
-    -e SANDBOX_USER_ID=$(id -u) \
-    -e PERSIST_SANDBOX="true" \
-    -e SSH_PASSWORD="make something up here" \
-    -e WORKSPACE_MOUNT_PATH=$OPENDEVIN_WORKSPACE \
-    -v $OPENDEVIN_WORKSPACE:/opt/workspace_base \
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik
+
+docker run -it --rm --pull=always \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
-    --name opendevin-app-$(date +%Y%m%d%H%M%S) \
-    ghcr.io/opendevin/opendevin:0.6
+    --name openhands-app \
+    docker.all-hands.dev/all-hands-ai/openhands:0.12
 ```
 
-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`.
+You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
 
-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.
+Finally, you'll need a model provider and API key.
+[Anthropic's Claude 3.5 Sonnet](https://www.anthropic.com/api) (`anthropic/claude-3-5-sonnet-20241022`)
+works best, but you have [many options](https://docs.all-hands.dev/modules/usage/llms).
 
-## 🚀 Documentation
+---
 
-To learn more about the project, and for tips on using OpenDevin,
-**check out our [documentation](https://opendevin.github.io/OpenDevin/)**.
+You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes),
+run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
+interact with it via a [friendly CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode),
+or run it on tagged issues with [a github action](https://github.com/All-Hands-AI/OpenHands-resolver).
 
-There you'll find resources on how to use different LLM providers (like ollama and Anthropic's Claude),
+Visit [Installation](https://docs.all-hands.dev/modules/usage/installation) for more information and setup instructions.
+
+If you want to modify the OpenHands source code, check out [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
+
+Having issues? The [Troubleshooting Guide](https://docs.all-hands.dev/modules/usage/troubleshooting) can help.
+
+## 📖 Documentation
+
+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/openhands-ai/shared_invite/zt-2tom0er4l-JeNUGHt_AxpEfIBstbLPiw) - Here we talk about research, architecture, and future development.
 - [Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
 
 ## 📈 Progress
-<p align="center">
-    <a href="https://www.swebench.com/lite.html">
-        <img src="/docs/static/img/results.png" alt="SWE-Bench Lite Score" width="500" height="auto">
-    </a>
-</p>
 
 <p align="center">
-  <a href="https://star-history.com/#OpenDevin/OpenDevin&Date">
-    <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>
 
@@ -119,26 +108,22 @@ 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{opendevin2024,
-  author       = {{OpenDevin Team}},
-  title        = {{OpenDevin: An Open Platform for AI Software Developers as Generalist Agents}},
-  year         = {2024},
-  version      = {v1.0},
-  howpublished = {\url{https://github.com/OpenDevin/OpenDevin}},
-  note         = {Accessed: ENTER THE DATE YOU ACCESSED THE PROJECT}
+@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},
 }
-```
+```

agenthub/README.md

@@ -1,87 +0,0 @@
-# Agent Framework Research
-
-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
-- [`CmdKillAction`](../opendevin/events/action/commands.py) - Kills a background command
-- [`IPythonRunCellAction`](../opendevin/events/action/commands.py) - Execute a block of Python code interactively (in Jupyter notebook) and receives `CmdOutputObservation`. Requires setting up `jupyter` [plugin](../opendevin/runtime/plugins) as a requirement.
-- [`FileReadAction`](../opendevin/events/action/files.py) - Reads the content of a file
-- [`FileWriteAction`](../opendevin/events/action/files.py) - Writes new content to a file
-- [`BrowseURLAction`](../opendevin/events/action/browse.py) - Gets the content of a URL
-- [`AgentRecallAction`](../opendevin/events/action/agent.py) - Searches memory (e.g. a vector database)
-- [`AddTaskAction`](../opendevin/events/action/tasks.py) - Adds a subtask to the plan
-- [`ModifyTaskAction`](../opendevin/events/action/tasks.py) - Changes the state of a subtask.
-- [`AgentFinishAction`](../opendevin/events/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
-- [`AgentRejectAction`](../opendevin/events/action/agent.py) - Stops the control loop, allowing the user/delegator agent to enter a new task
-- [`AgentFinishAction`](../opendevin/events/action/agent.py) - Stops the control loop, allowing the user to enter a new task
-- [`MessageAction`](../opendevin/events/action/message.py) - Represents a message from an agent or the user
-
-You can use `action.to_dict()` and `action_from_dict` to serialize and deserialize actions.
-
-## 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, logs from a command running
-in the background).
-
-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)
-- [`AgentRecallObservation`](../opendevin/events/observation/recall.py)
-- [`ErrorObservation`](../opendevin/events/observation/error.py)
-- [`SuccessObservation`](../opendevin/events/observation/success.py)
-
-You can use `observation.to_dict()` and `observation_from_dict` to serialize and deserialize observations.
-
-## 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`.
-
-### `search_memory`
-
-```
-def search_memory(self, query: str) -> list[str]:
-```
-
-`search_memory` should return a list of events that match the query. This will be used
-for the `recall` action.
-
-You can optionally just return `[]` for this method, meaning the agent has no long-term memory.

agenthub/SWE_agent/Examples.md

@@ -1,405 +0,0 @@
-# GPT-4 Examples:
-
-### Notes:
-- The final result is not completed as I only gave it 10 steps, but shows very promising use of the tools.
-- This whole run costs: $0.35 using gpt-4-turbo
-  - Input Tokens: 29,734
-  - Completion Tokens: 1,636
-
-Interesting things:
-1. Using comments as an initial placeholder for the next move and then having that output in memory is a very cool behavior.
-2. It makes very small iterative changes due to the prompting.
-3. A lot of the logic for the game is present but not put together well
-4. There are a lot of odd quirks with the code that it has written.
-5. Some odd agent behavior with putting random lines of code in random places?
-6. The structure of the feedback loop needs some improvement so the agent can see the changes it has made better in context.
-7. Might be beneficial to add in some line numbers so the model knows what lines it is looking at.
-
-
-```
-==============
-STEP 0
-
-PLAN:
-Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
-Usage(completion_tokens=91, prompt_tokens=2047, total_tokens=2138)
-
-==== RAW OUTPUT ====
-Thoughts:
-To start implementing Conway's Game of Life in Python using the pygame library, I first need to set up a Python script file where I can write the code. I'll create a new Python file named `game_of_life.py`. This file will serve as the base for writing the game logic and using pygame functionalities.
-
-Action:
-"""
-write game_of_life.py # This is a placeholder for the game of life implementation using pygame.
-"""
-
-==== END RAW ====
-
-
-ACTION:
-FileWriteAction(path='game_of_life.py', content='# This is a placeholder for the game of life implementation using pygame.', start=0, end=-1, thoughts="Thoughts:\nTo start implementing Conway's Game of Life in Python using the pygame library, I first need to set up a Python script file where I can write the code. I'll create a new Python file named `game_of_life.py`. This file will serve as the base for writing the game logic and using pygame functionalities.\n\nAction:", action=<ActionType.WRITE: 'write'>)
-
-OBSERVATION:
-WRITE OPERATION:
-You have written to "game_of_life.py" on these lines: 0:-1.
-
-
-==============
-STEP 1
-
-PLAN:
-Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
-Usage(completion_tokens=101, prompt_tokens=2351, total_tokens=2452)
-
-==== RAW OUTPUT ====
-Thoughts:
-The placeholder for the game of life implementation using pygame has been set up in the file `game_of_life.py`. The next step is to start implementing the basic structure of the game. This includes importing necessary libraries, initializing the pygame module, setting up the display window, and defining the main game loop. I will begin by importing pygame and initializing it, which are the foundational steps for any pygame application.
-
-Action:
-"""
-edit 0 0 import pygame
-
-pygame.init()
-"""
-
-==== END RAW ====
-
-
-ACTION:
-FileWriteAction(path='game_of_life.py', content='import pygame\n\npygame.init()', start=0, end=0, thoughts='Thoughts:\nThe placeholder for the game of life implementation using pygame has been set up in the file `game_of_life.py`. The next step is to start implementing the basic structure of the game. This includes importing necessary libraries, initializing the pygame module, setting up the display window, and defining the main game loop. I will begin by importing pygame and initializing it, which are the foundational steps for any pygame application.\n\nAction:', action=<ActionType.WRITE: 'write'>)
-
-OBSERVATION:
-WRITE OPERATION:
-You have written to "game_of_life.py" on these lines: 0:0.
-
-
-==============
-STEP 2
-
-PLAN:
-Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
-Usage(completion_tokens=123, prompt_tokens=2552, total_tokens=2675)
-
-==== RAW OUTPUT ====
-Thoughts:
-Previously, I initialized pygame in the `game_of_life.py` file. The next step is to set up the display window for the game. This involves defining the size of the window and setting the title. This is crucial as it provides the visual interface for the game. I will also add a comment to indicate that this is the setup for the display window.
-
-Action:
-"""
-edit 2 2
-# Setup the display window
-screen_size = (800, 600)
-screen = pygame.display.set_mode(screen_size)
-pygame.display.set_caption("Conway's Game of Life")
-"""
-==== END RAW ====
-
-
-ACTION:
-FileWriteAction(path='game_of_life.py', content='# Setup the display window\nscreen_size = (800, 600)\nscreen = pygame.display.set_mode(screen_size)\npygame.display.set_caption("Conway\'s Game of Life")', start=2, end=2, thoughts='Thoughts:\nPreviously, I initialized pygame in the `game_of_life.py` file. The next step is to set up the display window for the game. This involves defining the size of the window and setting the title. This is crucial as it provides the visual interface for the game. I will also add a comment to indicate that this is the setup for the display window.\n\nAction:', action=<ActionType.WRITE: 'write'>)
-
-OBSERVATION:
-WRITE OPERATION:
-You have written to "game_of_life.py" on these lines: 2:2.
-
-
-==============
-STEP 3
-
-PLAN:
-Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
-Usage(completion_tokens=144, prompt_tokens=2777, total_tokens=2921)
-
-==== RAW OUTPUT ====
-Thoughts:
-So far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame and setting up the display window. The next step is to define the main game loop where the game's logic will be continuously updated and rendered. This loop will handle events, update the game state, and redraw the screen. I will start by defining the main loop structure and a basic event handling mechanism to allow for quitting the game when the user presses the close button.
-
-Action:
-"""
-edit 5 5 # Main game loop
-running = True
-while running:
-    for event in pygame.event.get():
-        if event.type == pygame.QUIT:
-            running = False
-"""
-
-==== END RAW ====
-
-
-ACTION:
-FileWriteAction(path='game_of_life.py', content='# Main game loop\nrunning = True\nwhile running:\n    for event in pygame.event.get():\n        if event.type == pygame.QUIT:\n            running = False', start=5, end=5, thoughts="Thoughts:\nSo far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame and setting up the display window. The next step is to define the main game loop where the game's logic will be continuously updated and rendered. This loop will handle events, update the game state, and redraw the screen. I will start by defining the main loop structure and a basic event handling mechanism to allow for quitting the game when the user presses the close button.\n\nAction:", action=<ActionType.WRITE: 'write'>)
-
-OBSERVATION:
-WRITE OPERATION:
-You have written to "game_of_life.py" on these lines: 5:5.
-
-
-==============
-STEP 4
-
-PLAN:
-Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
-Usage(completion_tokens=222, prompt_tokens=3022, total_tokens=3244)
-
-==== RAW OUTPUT ====
-Thoughts:
-So far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, and defining the main game loop. The next step is to implement the logic for Conway's Game of Life. This involves creating a grid to represent the game state, initializing it with a random pattern, and defining the rules for cell survival, birth, and death. I will start by defining the grid size and initializing the grid with random states.
-
-Action:
-"""
-edit 7 7 # Define grid size and initialize grid
-grid_size = (50, 50)  # Grid size as a tuple (rows, columns)
-grid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]  # Initialize grid with zeros
-import random
-for y in range(grid_size[0]):
-    for x in range(grid_size[1]):
-        grid[y][x] = random.randint(0, 1)  # Randomly assign cells as alive (1) or dead (0)
-"""
-==== END RAW ====
-
-
-ACTION:
-FileWriteAction(path='game_of_life.py', content='# Define grid size and initialize grid\ngrid_size = (50, 50)  # Grid size as a tuple (rows, columns)\ngrid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]  # Initialize grid with zeros\nimport random\nfor y in range(grid_size[0]):\n    for x in range(grid_size[1]):\n        grid[y][x] = random.randint(0, 1)  # Randomly assign cells as alive (1) or dead (0)', start=7, end=7, thoughts="Thoughts:\nSo far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, and defining the main game loop. The next step is to implement the logic for Conway's Game of Life. This involves creating a grid to represent the game state, initializing it with a random pattern, and defining the rules for cell survival, birth, and death. I will start by defining the grid size and initializing the grid with random states.\n\nAction:", action=<ActionType.WRITE: 'write'>)
-
-OBSERVATION:
-WRITE OPERATION:
-You have written to "game_of_life.py" on these lines: 7:7.
-
-
-==============
-STEP 5
-
-PLAN:
-Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
-Usage(completion_tokens=234, prompt_tokens=3158, total_tokens=3392)
-
-==== RAW OUTPUT ====
-Thoughts:
-So far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, and initializing the grid with random states. The next step is to implement the rules for Conway's Game of Life. This involves checking each cell's neighbors to determine its next state based on the number of alive neighbors. I will start by defining a function to count the alive neighbors for a given cell.
-
-Action:
-"""
-edit 9 9 def count_alive_neighbors(grid, x, y):
-    directions = [(-1, -1), (-1, 0), (-1, 1), (0, -1), (0, 1), (1, -1), (1, 0), (1, 1)]
-    count = 0
-    for dx, dy in directions:
-        nx, ny = x + dx, y + dy
-        if 0 <= nx < grid_size[1] and 0 <= ny < grid_size[0]:
-            count += grid[ny][nx]
-    return count
-"""
-
-==== END RAW ====
-
-
-ACTION:
-FileWriteAction(path='game_of_life.py', content='def count_alive_neighbors(grid, x, y):\n    directions = [(-1, -1), (-1, 0), (-1, 1), (0, -1), (0, 1), (1, -1), (1, 0), (1, 1)]\n    count = 0\n    for dx, dy in directions:\n        nx, ny = x + dx, y + dy\n        if 0 <= nx < grid_size[1] and 0 <= ny < grid_size[0]:\n            count += grid[ny][nx]\n    return count', start=9, end=9, thoughts="Thoughts:\nSo far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, and initializing the grid with random states. The next step is to implement the rules for Conway's Game of Life. This involves checking each cell's neighbors to determine its next state based on the number of alive neighbors. I will start by defining a function to count the alive neighbors for a given cell.\n\nAction:", action=<ActionType.WRITE: 'write'>)
-
-OBSERVATION:
-WRITE OPERATION:
-You have written to "game_of_life.py" on these lines: 9:9.
-
-
-==============
-STEP 6
-
-PLAN:
-Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
-Usage(completion_tokens=257, prompt_tokens=3290, total_tokens=3547)
-
-==== RAW OUTPUT ====
-Thoughts:
-So far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating a function to count alive neighbors. The next step is to implement the rules for Conway's Game of Life. This involves updating the grid state based on the number of alive neighbors each cell has. I will define a function `update_grid` that applies the rules of the game to update the grid for the next generation.
-
-Action:
-"""
-write game_of_life.py def update_grid(grid):
-    new_grid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]
-    for y in range(grid_size[0]):
-        for x in range(grid_size[1]):
-            alive_neighbors = count_alive_neighbors(grid, x, y)
-            if grid[y][x] == 1 and (alive_neighbors == 2 or alive_neighbors == 3):
-                new_grid[y][x] = 1
-            elif grid[y][x] == 0 and alive_neighbors == 3:
-                new_grid[y][x] = 1
-    return new_grid
- 11
- 11
-"""
-==== END RAW ====
-
-
-ACTION:
-FileWriteAction(path='game_of_life.py', content='def update_grid(grid):\n    new_grid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]\n    for y in range(grid_size[0]):\n        for x in range(grid_size[1]):\n            alive_neighbors = count_alive_neighbors(grid, x, y)\n            if grid[y][x] == 1 and (alive_neighbors == 2 or alive_neighbors == 3):\n                new_grid[y][x] = 1\n            elif grid[y][x] == 0 and alive_neighbors == 3:\n                new_grid[y][x] = 1\n    return new_grid', start=11, end=11, thoughts="Thoughts:\nSo far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating a function to count alive neighbors. The next step is to implement the rules for Conway's Game of Life. This involves updating the grid state based on the number of alive neighbors each cell has. I will define a function `update_grid` that applies the rules of the game to update the grid for the next generation.\n\nAction:", action=<ActionType.WRITE: 'write'>)
-
-OBSERVATION:
-WRITE OPERATION:
-You have written to "game_of_life.py" on these lines: 11:11.
-
-
-==============
-STEP 7
-
-PLAN:
-Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
-Usage(completion_tokens=124, prompt_tokens=3416, total_tokens=3540)
-
-==== RAW OUTPUT ====
-Thoughts:
-So far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating functions to count alive neighbors and update the grid. The next step is to integrate the `update_grid` function into the main game loop to continuously update the state of the grid based on the game rules. This will allow the game to evolve over time, showing different generations of the cell population.
-
-Action:
-"""
-edit 6 6
-    grid = update_grid(grid)
-"""
-==== END RAW ====
-
-
-ACTION:
-FileWriteAction(path='game_of_life.py', content='grid = update_grid(grid)', start=6, end=6, thoughts="Thoughts:\nSo far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating functions to count alive neighbors and update the grid. The next step is to integrate the `update_grid` function into the main game loop to continuously update the state of the grid based on the game rules. This will allow the game to evolve over time, showing different generations of the cell population.\n\nAction:", action=<ActionType.WRITE: 'write'>)
-
-OBSERVATION:
-WRITE OPERATION:
-You have written to "game_of_life.py" on these lines: 6:6.
-
-
-==============
-STEP 8
-
-PLAN:
-Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
-Usage(completion_tokens=166, prompt_tokens=3393, total_tokens=3559)
-
-==== RAW OUTPUT ====
-Thoughts:
-So far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating functions to count alive neighbors and update the grid. The next step is to integrate the `update_grid` function into the main game loop to continuously update the state of the grid based on the game rules. This will allow the game to evolve over time, showing different generations of the cell population. I need to ensure that the `update_grid` function is called within the main game loop and that the display is updated accordingly. I will start by checking the current content of the main game loop to see where to integrate the `update_grid` function.
-
-Action:
-"""
-goto 6
-"""
-==== END RAW ====
-
-
-ACTION:
-FileReadAction(path='game_of_life.py', start=6, end=106, thoughts="Thoughts:\nSo far, I have set up the basic structure for Conway's Game of Life using pygame, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating functions to count alive neighbors and update the grid. The next step is to integrate the `update_grid` function into the main game loop to continuously update the state of the grid based on the game rules. This will allow the game to evolve over time, showing different generations of the cell population. I need to ensure that the `update_grid` function is called within the main game loop and that the display is updated accordingly. I will start by checking the current content of the main game loop to see where to integrate the `update_grid` function.\n\nAction:", action=<ActionType.READ: 'read'>)
-
-OBSERVATION:
-grid = update_grid(grid)
-running = True
-# Define grid size and initialize grid
-grid_size = (50, 50)  # Grid size as a tuple (rows, columns)
-def count_alive_neighbors(grid, x, y):
-    directions = [(-1, -1), (-1, 0), (-1, 1), (0, -1), (0, 1), (1, -1), (1, 0), (1, 1)]
-def update_grid(grid):
-    new_grid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]
-    for y in range(grid_size[0]):
-        for x in range(grid_size[1]):
-            alive_neighbors = count_alive_neighbors(grid, x, y)
-            if grid[y][x] == 1 and (alive_neighbors == 2 or alive_neighbors == 3):
-                new_grid[y][x] = 1
-            elif grid[y][x] == 0 and alive_neighbors == 3:
-                new_grid[y][x] = 1
-    return new_grid
-    count = 0
-    for dx, dy in directions:
-        nx, ny = x + dx, y + dy
-        if 0 <= nx < grid_size[1] and 0 <= ny < grid_size[0]:
-            count += grid[ny][nx]
-    return count
-grid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]  # Initialize grid with zeros
-import random
-for y in range(grid_size[0]):
-    for x in range(grid_size[1]):
-        grid[y][x] = random.randint(0, 1)  # Randomly assign cells as alive (1) or dead (0)
-while running:
-    for event in pygame.event.get():
-        if event.type == pygame.QUIT:
-            running = False
-pygame.display.set_caption("Conway's Game of Life")
-pygame.init()
-
-
-
-==============
-STEP 9
-
-PLAN:
-Please make conway's game of life in python using the pygame library. Be sure to use the tools in your workspace to help you out.
-Usage(completion_tokens=174, prompt_tokens=3728, total_tokens=3902)
-
-==== RAW OUTPUT ====
-Thoughts:
-From the previous actions, it seems that the basic structure for Conway's Game of Life using pygame has been set up, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating functions to count alive neighbors and update the grid. The next step is to ensure that the game loop properly updates the grid and refreshes the display to show the new state of the grid in each iteration. This involves calling `pygame.display.update()` to update the entire screen and using `pygame.time.Clock()` to control the frame rate. I will start by adding these necessary updates to the game loop.
-
-Action:
-"""
-edit 95 95
-    pygame.display.update()
-    clock = pygame.time.Clock()
-    clock.tick(10)  # Control the frame rate (10 frames per second)
-"""
-
-==== END RAW ====
-
-
-ACTION:
-FileWriteAction(path='game_of_life.py', content='pygame.display.update()\n    clock = pygame.time.Clock()\n    clock.tick(10)  # Control the frame rate (10 frames per second)', start=95, end=95, thoughts="Thoughts:\nFrom the previous actions, it seems that the basic structure for Conway's Game of Life using pygame has been set up, including initializing pygame, setting up the display window, defining the main game loop, initializing the grid with random states, and creating functions to count alive neighbors and update the grid. The next step is to ensure that the game loop properly updates the grid and refreshes the display to show the new state of the grid in each iteration. This involves calling `pygame.display.update()` to update the entire screen and using `pygame.time.Clock()` to control the frame rate. I will start by adding these necessary updates to the game loop.\n\nAction:", action=<ActionType.WRITE: 'write'>)
-
-OBSERVATION:
-WRITE OPERATION:
-You have written to "game_of_life.py" on these lines: 95:95.
-16:43:55 - opendevin:INFO: agent_controller.py:125 - Exited before finishing the task.
-
-
-```
-
-## Result:
-
-```
-import pygame
-
-# Setup the display window
-screen_size = (800, 600)
-screen = pygame.display.set_mode(screen_size)
-# Main game loop
-grid = update_grid(grid)
-running = True
-# Define grid size and initialize grid
-grid_size = (50, 50)  # Grid size as a tuple (rows, columns)
-def count_alive_neighbors(grid, x, y):
-    directions = [(-1, -1), (-1, 0), (-1, 1), (0, -1), (0, 1), (1, -1), (1, 0), (1, 1)]
-def update_grid(grid):
-    new_grid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]
-    for y in range(grid_size[0]):
-        for x in range(grid_size[1]):
-            alive_neighbors = count_alive_neighbors(grid, x, y)
-            if grid[y][x] == 1 and (alive_neighbors == 2 or alive_neighbors == 3):
-                new_grid[y][x] = 1
-            elif grid[y][x] == 0 and alive_neighbors == 3:
-                new_grid[y][x] = 1
-    return new_grid
-    count = 0
-    for dx, dy in directions:
-        nx, ny = x + dx, y + dy
-        if 0 <= nx < grid_size[1] and 0 <= ny < grid_size[0]:
-            count += grid[ny][nx]
-    return count
-grid = [[0 for x in range(grid_size[1])] for y in range(grid_size[0])]  # Initialize grid with zeros
-import random
-for y in range(grid_size[0]):
-    for x in range(grid_size[1]):
-        grid[y][x] = random.randint(0, 1)  # Randomly assign cells as alive (1) or dead (0)
-while running:
-    for event in pygame.event.get():
-        if event.type == pygame.QUIT:
-            running = False
-pygame.display.set_caption("Conway's Game of Life")
-pygame.init()
-# This is a placeholder for the game of life implementation using pygame.pygame.display.update()
-    clock = pygame.time.Clock()
-    clock.tick(10)  # Control the frame rate (10 frames per second)
-
-```

agenthub/SWE_agent/__init__.py

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

agenthub/SWE_agent/agent.py

@@ -1,117 +0,0 @@
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.events.action import (
-    Action,
-    FileReadAction,
-    FileWriteAction,
-    MessageAction,
-)
-from opendevin.events.serialization.event import event_to_memory
-from opendevin.llm.llm import LLM
-from opendevin.runtime.tools import RuntimeTool
-
-from .parser import parse_command
-from .prompts import (
-    CONTEXT_PROMPT,
-    MEMORY_FORMAT,
-    NO_ACTION,
-    STEP_PROMPT,
-    SYSTEM_MESSAGE,
-)
-
-
-class SWEAgent(Agent):
-    VERSION = '1.0'
-    DEPRECATED = True
-    """
-    An attempt to recreate swe_agent with output parsing, prompting style, and Application Computer Interface (ACI).
-
-    SWE-agent includes ACI functions like 'goto', 'search_for', 'edit', 'scroll', 'run'
-    """
-    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
-
-    def __init__(self, llm: LLM):
-        super().__init__(llm)
-        self.memory_window = 4
-        self.max_retries = 2
-        self.cur_file: str = ''
-        self.cur_line: int = 0
-
-    def _think_act(self, messages: list[dict]) -> tuple[Action, str]:
-        resp = self.llm.do_completion(
-            messages=messages,
-            temperature=0.05,
-        )
-        action_resp = resp['choices'][0]['message']['content']
-        print(f"\033[1m\033[91m{resp['usage']}\033[0m")
-        print(
-            '\n==== RAW OUTPUT ====',
-            f'\033[96m{action_resp}\033[0m',
-            '==== END RAW ====\n',
-            sep='\n',
-        )
-        return parse_command(action_resp, self.cur_file, self.cur_line)
-
-    def _update(self, action: Action) -> None:
-        if isinstance(action, (FileReadAction, FileWriteAction)):
-            self.cur_file = action.path
-            self.cur_line = action.start
-
-    def step(self, state: State) -> Action:
-        """
-        SWE-Agent step:
-            1. Get context - past actions, custom commands, current step
-            2. Perform think-act - prompt model for action and reasoning
-            3. Catch errors - ensure model takes action (5 attempts max)
-        """
-        # retrieve short term memories from state.history, up to memory_window
-        memory_window = min(self.memory_window, len(state.history))
-        running_memory: list[str] = []
-        for prev_action, obs in state.history[-memory_window:]:
-            running_memory.append(
-                MEMORY_FORMAT(event_to_memory(prev_action), event_to_memory(obs))
-            )
-
-        goal = state.get_current_user_intent()
-
-        # always in the prompt if they exist: file and line
-        prompt = STEP_PROMPT(goal, self.cur_file, self.cur_line)
-
-        # prepare messages
-        msgs = [
-            {'content': SYSTEM_MESSAGE, 'role': 'system'},
-            {'content': prompt, 'role': 'user'},
-        ]
-
-        # insert memories
-        if len(running_memory) > 0:
-            context = CONTEXT_PROMPT(running_memory, self.memory_window)
-            msgs.insert(1, {'content': context, 'role': 'user'})
-        # clrs = [''] * (len(msgs)-2) + ['\033[0;36m', '\033[0;35m']
-        # print('\n\n'.join([c+m['content']+'\033[0m' for c, m in zip(clrs, msgs)]))
-
-        # send it over
-        action, thought = self._think_act(messages=msgs)
-
-        # be robust with malformed responses
-        start_msg_len = len(msgs)
-        while not action and len(msgs) < self.max_retries + start_msg_len:
-            error = NO_ACTION(thought)
-            error_msg = {'content': error, 'role': 'user'}
-            msgs.append(error_msg)
-            action, thought = self._think_act(messages=msgs)
-
-        if not action:
-            action = MessageAction(thought)
-
-        self._update(action)
-        self.latest_action = action
-        return action
-
-    def search_memory(self, query: str) -> list[str]:
-        # return [item for item in self.running_memory if query in item]
-        raise NotImplementedError('Search_memory not implemented currently')
-
-    def reset(self) -> None:
-        """Used to reset the agent"""
-        super().reset()

agenthub/SWE_agent/parser.py

@@ -1,167 +0,0 @@
-import re
-
-from opendevin.events.action import (
-    Action,
-    AgentFinishAction,
-    BrowseURLAction,
-    CmdRunAction,
-    FileReadAction,
-    FileWriteAction,
-    MessageAction,
-)
-
-from .prompts import COMMAND_USAGE, CUSTOM_DOCS
-
-# commands: exit, read, write, browse, kill, search_file, search_dir
-
-no_open_file_error = MessageAction(
-    'You are not currently in a file. You can use the read command to open a file and then use goto to navigate through it.'
-)
-
-
-def invalid_error(cmd, docs):
-    return f"""ERROR:
-Invalid command structure for
-```
-{cmd}
-```
-You may have caused this error by having multiple commands within your command block.
-If so, try again by running only one of the commands:
-
-Try again using this format:
-{COMMAND_USAGE[docs]}
-"""
-
-
-def get_action_from_string(
-    command_string: str, path: str, line: int, thoughts: str = ''
-) -> Action | None:
-    """
-    Parses the command string to find which command the agent wants to run
-    Converts the command into a proper Action and returns
-    """
-    vars = command_string.split(' ')
-    cmd = vars[0]
-    args = [] if len(vars) == 1 else vars[1:]
-
-    if 'exit' == cmd:
-        return AgentFinishAction()
-
-    elif 'think' == cmd:
-        return MessageAction(' '.join(args))
-
-    elif 'scroll_up' == cmd:
-        if not path:
-            return no_open_file_error
-        return FileReadAction(path, line + 100, line + 200, thoughts)
-
-    elif 'scroll_down' == cmd:
-        if not path:
-            return no_open_file_error
-        return FileReadAction(path, line - 100, line, thoughts)
-
-    elif 'goto' == cmd:
-        if not path:
-            return no_open_file_error
-        rex = r'^goto\s+(\d+)$'
-        valid = re.match(rex, command_string)
-        if valid:
-            start = int(valid.group(1))
-            end = start + 100
-            return FileReadAction(path, start, end, thoughts)
-        else:
-            return MessageAction(invalid_error(command_string, 'goto'))
-
-    elif 'edit' == cmd:
-        if not path:
-            return no_open_file_error
-        rex = r'^edit\s+(\d+)\s+(-?\d+)\s+(\S.*)$'
-        valid = re.match(rex, command_string, re.DOTALL)
-        if valid:
-            start = int(valid.group(1))
-            end = int(valid.group(2))
-            change = valid.group(3)
-            if '"' == change[-1] and '"' == change[0]:
-                change = change[1:-1]
-            return FileWriteAction(path, change, start, end, thoughts)
-        else:
-            return MessageAction(invalid_error(command_string, 'edit'))
-
-    elif 'read' == cmd:
-        rex = r'^read\s+(\S+)(?:\s+(\d+))?(?:\s+(-?\d+))?$'
-        valid = re.match(rex, command_string, re.DOTALL)
-        if valid:
-            file = valid.group(1)
-            start_str = valid.group(2)
-            end_str = valid.group(3)
-
-            start = 0 if not start_str else int(start_str)
-            end = -1 if not end_str else int(end_str)
-
-            return FileReadAction(file, start, end, thoughts)
-        else:
-            return MessageAction(invalid_error(command_string, 'read'))
-
-    elif 'write' == cmd:
-        rex = r'^write\s+(\S+)\s+(.*?)\s*(\d+)?\s*(-?\d+)?$'
-        valid = re.match(rex, command_string, re.DOTALL)
-
-        if valid:
-            file = valid.group(1)
-            content = valid.group(2)
-            start_str = valid.group(3)
-            end_str = valid.group(4)
-
-            start = 0 if not start_str else int(start_str)
-            end = -1 if not end_str else int(end_str)
-
-            if '"' == content[-1] and '"' == content[0]:
-                content = content[1:-1]
-
-            return FileWriteAction(file, content, start, end, thoughts)
-        else:
-            return MessageAction(invalid_error(command_string, 'write'))
-
-    elif 'browse' == cmd:
-        return BrowseURLAction(args[0].strip())
-
-    elif cmd in ['search_file', 'search_dir', 'find_file']:
-        rex = r'^(search_file|search_dir|find_file)\s+(\S+)(?:\s+(\S+))?$'
-        valid = re.match(rex, command_string, re.DOTALL)
-        if valid:
-            return CmdRunAction(command_string)
-        else:
-            return MessageAction(
-                f'Invalid command structure for\n ```\n{command_string}\n```.\nTry again using this format:\n{CUSTOM_DOCS}'
-            )
-    else:
-        # check bash command
-        obs = str(CmdRunAction(f'type {cmd}'))
-        if obs.split(':')[-1].strip() == 'not found':
-            # echo not found error for llm
-            return MessageAction(content=obs)
-        else:
-            # run valid command
-            return CmdRunAction(command_string)
-
-
-def parse_command(input_str: str, path: str, line: int):
-    """
-    Parses a given string and separates the command (enclosed in triple backticks) from any accompanying text.
-
-    Args:
-        input_str (str): The input string to be parsed.
-
-    Returns:
-        tuple: A tuple containing the command and the accompanying text (if any).
-    """
-    input_str = input_str.strip()
-    if '```' in input_str:
-        parts = input_str.split('```')
-        command_str = parts[1].strip()
-        ind = 2 if len(parts) > 2 else 1
-        accompanying_text = ''.join(parts[:-ind]).strip()
-        action = get_action_from_string(command_str, path, line, accompanying_text)
-        if action:
-            return action, accompanying_text
-    return None, input_str  # used for retry

agenthub/SWE_agent/prompts.py

@@ -1,208 +0,0 @@
-DEFAULT_COMMANDS_DICT = {
-    'exit': 'Executed when task is complete',
-    'read <file_name> [<start_line>] [<end_line>]': "Shows a given file's contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. By default the whole file will be read.",
-    'write <file> <changes> [<start_line>] [<end_line>]': 'Modifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>. Default start_line = 0 and end_line = -1. Calling this with no line args will replace the whole file.',
-    'browse <url>': 'Returns the text version of any url, this can be useful to look up documentation or finding issues on github',
-    'scroll_up': 'Takes no arguments. This will scroll up and show you the 100 lines above your current lines',
-    'scroll_down': 'Takes no arguments. This will scroll down and show you the 100 lines below your current lines',
-    'edit <start_line> <end_line> <changes>': 'This will modify lines in the currently open file. use start_line and end_line to designate which lines to change and then write the multiline changes. Set end_line to -1 to denote the end of the file',
-    'goto <line_num>': 'This will take you directly to a line and show you the 100 lines below it.',
-    '<bash_command> <args>': 'You can use any bash command you need (cd, ls, rm, grep, dir, mv, wget, git, zip, etc.) with their arguments included',
-    'pip install <package>': 'You can use this to import python packages. Make sure you include the correct package name when using this command.',
-    'ls': 'Use the ls command to view all the files in your current directory, this is a good starting point.',
-    'NOT ALLOWED': 'You cannot use interactive commands like python or node',
-}
-
-COMMAND_USAGE = {
-    'exit': 'Usage:\n```\nexit\n```\nExecuted when task is complete',
-    'read': "Args:\n<file_name> [<start_line>] [<end_line>]\nUsage:\n```\nread file.py\n```\nor\n```\nread example.py <start_line> <end_line>\n```\nShows a given file's contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. by default the whole file will be read.",
-    'write': 'Args:\n<file> <changes> [<start_line>] [<end_line>]\nUsage:\n```\nwrite "def main():\n    print("This is line one")" 0 2\n```\nModifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>. Default start_line = 0 and end_line = -1. Calling this with no line args will replace the whole file.',
-    'edit': 'Args:\n<start_line> <end_line> <changes>\nUsage:\n```\nedit 0 1 import pandas as pd\n```\nThis will modify the current file you are in with the changes you make between the line numbers you designate',
-    'goto': 'Args:\n<line_num>\nUsage:\n```\ngoto <line_num>\n```\nThis will show you the 100 lines below and including the line you specify within your current file.',
-    'scroll_up': 'Usage:\n```\nscroll_up\n```\nThis will return the 100 lines above where you are currently at',
-    'scroll_down': 'Usage:\n```\nscroll_down\n```\nThis will return the 100 line below where you are currently at',
-    'browse': 'Args:\n<url>\nUsage:\n```\nbrowse https://github.com/OpenDevin/OpenDevin\n```\nThis will fetch the Text elements from the given url and show them to you.',
-}
-
-DEFAULT_COMMANDS = '\n'.join([k + ' - ' + v for k, v in DEFAULT_COMMANDS_DICT.items()])
-
-# from opendevin.parse_commands import parse_command_file
-# USE parse_command_file(filepath) to get the custom commands
-CUSTOM_DOCS = None
-
-CUSTOM_COMMANDS = f"""Custom bash commands:
-{CUSTOM_DOCS}
-"""
-
-DOCUMENTATION = f"""DOCUMENTATION:
-It is recommend that you use the commands provided for interacting with files and your directory because they have been specially built for you.
-They will make it much easier for you to look at files and make changes. Using these commands will help you be better at your task.
-You can open an file by using either the read or write operations.
-- If a file already exists you should read it before making any changes. Use the `edit` command to make changes once you have read it.
-- If you are creating a new file use the write command. Use the `edit` command to make changes once you have created the new file.
-
-Commands:
-{DEFAULT_COMMANDS}
-{CUSTOM_COMMANDS}
-
-The following commands require an open file to be used: edit, scroll_up, scroll_down, goto
-To modify the current file use 'edit'. To move through the current file use 'goto' or 'scroll_up'/'scroll_down'
-when using write and edit do not surround the code with any "" just write the code.
-"""
-
-GENERAL_GUIDELINES = """INSTRUCTIONS:
-Now, you're going to solve this issue on your own. You can use any bash commands or custom commands you wish to complete your task. Edit all the files you need to and run any checks or tests that you want.
-Remember, YOU CAN ONLY ENTER ONE COMMAND AT A TIME. You should always wait for feedback after every command.
-When you're satisfied with all of the changes you've made, you can indicate that you are done by running the exit command.
-Note however that you cannot use any interactive session commands (e.g. python, vim, node) in this environment, but you can write scripts and run them. E.g. you can write a python script and then run it with `python <script_name>.py`.
-
-NOTE ABOUT THE write COMMAND: Indentation really matters! When editing a file, make sure to insert appropriate indentation before each line!
-
-IMPORTANT TIPS:
-1. Reproduce the bug: Always start by trying to replicate the bug that the issue discusses. If the issue includes code for reproducing the bug, we recommend that you re-implement that in your environment and run it to ensure you can reproduce the bug. Then, start trying to fix it. When you think you've fixed the bug, re-run the bug reproduction script to make sure that the issue has indeed been resolved.
-   If the bug reproduction script does not print anything when it successfully runs, we recommend adding a print("Script completed successfully, no errors.") command at the end of the file, so that you can be sure the script ran fine all the way through.
-2. Try different commands: If you run a command and it doesn't work, try running a different command. A command that did not work once will not work the second time unless you modify it.
-3. Navigate large files: If you open a file and need to get to an area around a specific line that is not in the first 100 lines, say line 583, you would use the 'read' command like this: 'read <file> 583'. This is a much faster way to read through the file.
-4. Handle input files: If the bug reproduction script requires inputting/reading a specific file, such as 'buggy-input.png', and you'd like to understand how to input that file, conduct a search in the existing repository code to see whether someone else has already done that. Do this by running the command: 'search_dir "buggy-input.png"'. If that doesn't work, use the Linux 'find' command.
-5. Understand your context: Always make sure to look at the currently open file and the current working directory. The currently open file might be in a different directory than the working directory.
-6. Verify your edits: When editing files, it is easy to accidentally specify a wrong line number or to write code with incorrect indentation. Always check the code after you issue an edit to make sure that it reflects what you wanted to accomplish. If it didn't, issue another command to fix it.
-7. Thoroughly test your solution: After making any changes to fix a bug, be sure to thoroughly test your solution to ensure the bug has been resolved. Re-run the bug reproduction script and verify that the issue has been addressed.
-"""
-
-RESPONSE_FORMAT = """RESPONSE FORMAT:
-This is the format of the response you will make in order to solve the current issue.
-You will be given multiple iterations to complete this task so break it into steps and solve them one by one.
-
-Your output must contain the following:
-- First, thoughts about what your next action should be and plan it out.
-    - You will have a memory of your thoughts so you can use this to remember things for the next step.
-    - Use your thoughts to think about what you are currently doing, what you have done on prior steps and how that relates to solving the problem.
-- Second, create a piece of code that will execute your next action based on the thoughts you have.
-    - Remember that you can only have one action for each thought, do not include multiple actions.
-
-Your code MUST be surrounded in triple back ticks EXACTLY like this:
-```
-<code>
-```
-
-Notes:
-- Adhere to the format so that the program loop continues smoothly, it is very important to only give one command per output.
-- DO NOT give more than one command within the triple backticks. This will just throw an error and nothing will happen as a result.
-- Do not give multiple code blocks, if you do only the second one will be captured and run, this might give an error if the first one was necessary.
-- To execute multiple commands you should write them down in your thoughts section so you can remember it on the next step and execute them then.
-- The only commands you are not capable of executing are interactive commands like `python` or `node` by themselves.
-- If you think that you have completed the task that has been given to you based on your previous actions and outputs then use ``` exit ``` as the command to let the system know that you are done.
-- DO NOT make any copies of your previous memories, those will be provided to you at each step, making copies just wastes time and energy. Think smarter not harder.
-- The write and edit commands requires proper indentation in the content section ex. `write hw.py def hello():\n    print(\'Hello World\')` this is how you would have to format your write command.
-    - The white spaces matter as the code changes will be added to the code so they must have proper syntax.
-
-This is a template using the format described above
-Items in <> are suggestions for you, fill them out based on the context of the problem you are solving.
-
-[ FORMAT ]
-Thoughts:
-<Provide clear and concise thoughts on the next step to take, highlighting any important details or context that should be remembered.>
-<You can use multiple lines to express your thoughts>
-
-Action:
-```
-<command> <params>
-```
-[ END FORMAT ]
-
-Do not provide anything extra just your thought and action.
-"""
-
-SYSTEM_MESSAGE = f"""SYSTEM INFO:
-You are an autonomous coding agent, here to provide solutions for coding issues.
-You have been designed to assist with a wide range of programming tasks, from code editing and debugging to testing and deployment.
-You have access to a variety of tools and commands that you can use to help you solve problems efficiently.
-
-{GENERAL_GUIDELINES}
-
-{DOCUMENTATION}
-""".strip()
-
-
-def NO_ACTION(latest):
-    return f"""
-You did not include any action to take in your most recent output:
-
-===== Output ======
-{latest}
-==== End Output ===
-
-Remember these are the custom commands you can use:
-{DOCUMENTATION}
-
-Lets try that again, it is very important that you adhere to the output format
-This time, be sure to use the exact format below, replacing anything in <> with the appropriate value(s):
-{RESPONSE_FORMAT}
-
-It is crucial you use the format provided as the output will be parsed automatically.
-"""
-
-
-def file_info(file: str, line: int):
-    if file:
-        return f"""CURRENT WORKSPACE:
-    Open File: {file} on line {line}
-    You can use these commands with the current file:
-    Navigation: `scroll_up`, `scroll_down`, and `goto <line>`
-    Modification: `edit <start_line> <end_line> <changes>`
-    """
-
-
-def STEP_PROMPT(task, file, line_num):
-    return f"""
-{RESPONSE_FORMAT}
-You are currently trying to complete this task:
-{task}
-
-{file_info(file, line_num)}
-
-Keep all of the guidelines above in mind when you are thinking and making code.
-Please come up with a thought and action based on your current task and latest steps.
-Make sure that you do not repeat the same actions, there will not be any changes in result if you do not changes anything.
-Be very strict about the formatting that you use and make sure you follow the guidelines.
-NEVER output multiple commands. ONLY take ONE STEP at a time.
-When you have completed your task run the "exit" command.
-Begin with your thought about the next step and then come up with an action to perform your thought.
-""".strip()
-
-
-def unpack_dict(data: dict, restrict: list[str] | None = None):
-    lines = []
-    restrict = [] if restrict is None else restrict
-    for key, value in data.items():
-        if key in restrict:
-            continue
-        elif isinstance(value, dict):
-            nested_str = unpack_dict(value, restrict).replace('\n', '\n  ')
-            val = f'{key}:' + '\n  ' + f'{nested_str}'
-            lines.append(val)
-        else:
-            lines.append(f'{key}: {value}')
-    return '\n'.join(lines)
-
-
-def MEMORY_FORMAT(act, obs):
-    return f"""
-Previous Action:
-{unpack_dict(act, ["content"])}
-
-Output from Action:
-{unpack_dict(obs)}
-""".strip()
-
-
-def CONTEXT_PROMPT(memory, window):
-    res = f'These are your past {window} actions:\n'
-    window_size = window if len(memory) > window else len(memory)
-    cur_mems = memory[-window_size:]
-    res += '===== Previous Actions =====\n'
-    for idx, mem in enumerate(cur_mems):
-        res += f'\nMemory {idx}:\n{mem}\n'
-    res += '======= End Actions =======\n'
-    res += 'Use these memories to provide additional context to the problem you are solving.\nRemember that you have already completed these steps so you do not need to perform them again.'
-    return res

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/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/action_parser.py

@@ -1,182 +0,0 @@
-import re
-
-from opendevin.controller.action_parser import ActionParser, ResponseParser
-from opendevin.events.action import (
-    Action,
-    AgentDelegateAction,
-    AgentFinishAction,
-    CmdRunAction,
-    IPythonRunCellAction,
-    MessageAction,
-)
-
-
-class CodeActResponseParser(ResponseParser):
-    """
-    Parser action:
-        - CmdRunAction(command) - bash command to run
-        - IPythonRunCellAction(code) - IPython code to run
-        - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
-        - MessageAction(content) - Message action to run (e.g. ask for clarification)
-        - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(
-        self,
-    ):
-        # Need pay attention to the item order in self.action_parsers
-        self.action_parsers = [
-            CodeActActionParserFinish(),
-            CodeActActionParserCmdRun(),
-            CodeActActionParserIPythonRunCell(),
-            CodeActActionParserAgentDelegate(),
-        ]
-        self.default_parser = CodeActActionParserMessage()
-
-    def parse(self, response: str) -> Action:
-        action_str = self.parse_response(response)
-        return self.parse_action(action_str)
-
-    def parse_response(self, response) -> str:
-        action = response.choices[0].message.content
-        for lang in ['bash', 'ipython', 'browse']:
-            if f'<execute_{lang}>' in action and f'</execute_{lang}>' not in action:
-                action += f'</execute_{lang}>'
-        return action
-
-    def parse_action(self, action_str: str) -> Action:
-        for action_parser in self.action_parsers:
-            if action_parser.check_condition(action_str):
-                return action_parser.parse(action_str)
-        return self.default_parser.parse(action_str)
-
-
-class CodeActActionParserFinish(ActionParser):
-    """
-    Parser action:
-        - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(
-        self,
-    ):
-        self.finish_command = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.finish_command = re.search(r'<finish>.*</finish>', action_str, re.DOTALL)
-        return self.finish_command is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.finish_command is not None
-        ), 'self.finish_command should not be None when parse is called'
-        thought = action_str.replace(self.finish_command.group(0), '').strip()
-        return AgentFinishAction(thought=thought)
-
-
-class CodeActActionParserCmdRun(ActionParser):
-    """
-    Parser action:
-        - CmdRunAction(command) - bash command to run
-        - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(
-        self,
-    ):
-        self.bash_command = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.bash_command = re.search(
-            r'<execute_bash>(.*?)</execute_bash>', action_str, re.DOTALL
-        )
-        return self.bash_command is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.bash_command is not None
-        ), 'self.bash_command should not be None when parse is called'
-        thought = action_str.replace(self.bash_command.group(0), '').strip()
-        # a command was found
-        command_group = self.bash_command.group(1).strip()
-        if command_group.strip() == 'exit':
-            return AgentFinishAction()
-        return CmdRunAction(command=command_group, thought=thought)
-
-
-class CodeActActionParserIPythonRunCell(ActionParser):
-    """
-    Parser action:
-        - IPythonRunCellAction(code) - IPython code to run
-    """
-
-    def __init__(
-        self,
-    ):
-        self.python_code = None
-        self.jupyter_kernel_init_code: str = 'from agentskills import *'
-
-    def check_condition(self, action_str: str) -> bool:
-        self.python_code = re.search(
-            r'<execute_ipython>(.*?)</execute_ipython>', action_str, re.DOTALL
-        )
-        return self.python_code is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.python_code is not None
-        ), 'self.python_code should not be None when parse is called'
-        code_group = self.python_code.group(1).strip()
-        thought = action_str.replace(self.python_code.group(0), '').strip()
-        return IPythonRunCellAction(
-            code=code_group,
-            thought=thought,
-            kernel_init_code=self.jupyter_kernel_init_code,
-        )
-
-
-class CodeActActionParserAgentDelegate(ActionParser):
-    """
-    Parser action:
-        - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
-    """
-
-    def __init__(
-        self,
-    ):
-        self.agent_delegate = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.agent_delegate = re.search(
-            r'<execute_browse>(.*)</execute_browse>', action_str, re.DOTALL
-        )
-        return self.agent_delegate is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.agent_delegate is not None
-        ), 'self.agent_delegate should not be None when parse is called'
-        thought = action_str.replace(self.agent_delegate.group(0), '').strip()
-        browse_actions = self.agent_delegate.group(1).strip()
-        task = f'{thought}. I should start with: {browse_actions}'
-        return AgentDelegateAction(agent='BrowsingAgent', inputs={'task': task})
-
-
-class CodeActActionParserMessage(ActionParser):
-    """
-    Parser action:
-        - MessageAction(content) - Message action to run (e.g. ask for clarification)
-    """
-
-    def __init__(
-        self,
-    ):
-        pass
-
-    def check_condition(self, action_str: str) -> bool:
-        # We assume the LLM is GOOD enough that when it returns pure natural language
-        # it wants to talk to the user
-        return True
-
-    def parse(self, action_str: str) -> Action:
-        return MessageAction(content=action_str, wait_for_response=True)

agenthub/codeact_agent/codeact_agent.py

@@ -1,239 +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,
-    AgentFinishAction,
-    BrowseInteractiveAction,
-    CmdRunAction,
-    IPythonRunCellAction,
-    MessageAction,
-)
-from opendevin.events.observation import (
-    AgentDelegateObservation,
-    BrowserOutputObservation,
-    CmdOutputObservation,
-    IPythonRunCellObservation,
-)
-from opendevin.llm.llm import LLM
-from opendevin.runtime.plugins import (
-    AgentSkillsRequirement,
-    JupyterRequirement,
-    PluginRequirement,
-)
-from opendevin.runtime.tools import RuntimeTool
-
-ENABLE_GITHUB = True
-
-
-def action_to_str(action: Action) -> str:
-    if isinstance(action, CmdRunAction):
-        return f'{action.thought}\n<execute_bash>\n{action.command}\n</execute_bash>'
-    elif isinstance(action, IPythonRunCellAction):
-        return f'{action.thought}\n<execute_ipython>\n{action.code}\n</execute_ipython>'
-    elif isinstance(action, BrowseInteractiveAction):
-        return f'{action.thought}\n<execute_browse>\n{action.browser_actions}\n</execute_browse>'
-    elif isinstance(action, MessageAction):
-        return action.content
-    return ''
-
-
-def get_action_message(action: Action) -> dict[str, str] | None:
-    if (
-        isinstance(action, BrowseInteractiveAction)
-        or isinstance(action, CmdRunAction)
-        or isinstance(action, IPythonRunCellAction)
-        or isinstance(action, MessageAction)
-    ):
-        return {
-            'role': 'user' if action.source == 'user' else 'assistant',
-            'content': action_to_str(action),
-        }
-    return None
-
-
-def get_observation_message(obs) -> dict[str, str] | None:
-    if isinstance(obs, CmdOutputObservation):
-        content = 'OBSERVATION:\n' + truncate_observation(obs.content)
-        content += (
-            f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]]'
-        )
-        return {'role': 'user', 'content': content}
-    elif isinstance(obs, IPythonRunCellObservation):
-        content = 'OBSERVATION:\n' + obs.content
-        # replace base64 images with a placeholder
-        splitted = content.split('\n')
-        for i, line in enumerate(splitted):
-            if '![image](data:image/png;base64,' in line:
-                splitted[i] = (
-                    '![image](data:image/png;base64, ...) already displayed to user'
-                )
-        content = '\n'.join(splitted)
-        content = truncate_observation(content)
-        return {'role': 'user', 'content': content}
-    elif isinstance(obs, BrowserOutputObservation):
-        content = 'OBSERVATION:\n' + truncate_observation(obs.content)
-        return {'role': 'user', 'content': content}
-    elif isinstance(obs, AgentDelegateObservation):
-        content = 'OBSERVATION:\n' + truncate_observation(str(obs.outputs))
-        return {'role': 'user', 'content': content}
-    return None
-
-
-def truncate_observation(observation: str, max_chars: int = 10_000) -> str:
-    """
-    Truncate the middle of the observation if it is too long.
-    """
-    if len(observation) <= max_chars:
-        return observation
-    half = max_chars // 2
-    return (
-        observation[:half]
-        + '\n[... Observation truncated due to length ...]\n'
-        + observation[-half:]
-    )
-
-
-# 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 = '1.6'
-    """
-    The Code Act Agent is a minimalist agent.
-    The agent works by passing the model a list of action-observation pairs and prompting the model to take the next step.
-
-    ### Overview
-
-    This agent implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.13463), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a unified **code** action space for both *simplicity* and *performance* (see paper for more details).
-
-    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 need 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 reset(self) -> None:
-        """
-        Resets the CodeAct Agent.
-        """
-        super().reset()
-
-    def step(self, state: State) -> Action:
-        """
-        Performs one step using the CodeAct Agent.
-        This includes gathering info on previous steps and prompting the model to make a command to execute.
-
-        Parameters:
-        - state (State): used to get updated info and background commands
-
-        Returns:
-        - CmdRunAction(command) - bash command to run
-        - IPythonRunCellAction(code) - IPython code to run
-        - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
-        - MessageAction(content) - Message action to run (e.g. ask for clarification)
-        - AgentFinishAction() - end the interaction
-        """
-        messages: list[dict[str, str]] = [
-            {'role': 'system', 'content': self.system_message},
-            {'role': 'user', 'content': self.in_context_example},
-        ]
-
-        for prev_action, obs in state.history:
-            action_message = get_action_message(prev_action)
-            if action_message:
-                messages.append(action_message)
-
-            obs_message = get_observation_message(obs)
-            if obs_message:
-                messages.append(obs_message)
-
-        latest_user_message = [m for m in messages if m['role'] == 'user'][-1]
-        if latest_user_message:
-            if latest_user_message['content'].strip() == '/exit':
-                return AgentFinishAction()
-            latest_user_message['content'] += (
-                f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task.'
-            )
-
-        response = self.llm.do_completion(
-            messages=messages,
-            stop=[
-                '</execute_ipython>',
-                '</execute_bash>',
-                '</execute_browse>',
-            ],
-            temperature=0.0,
-        )
-        state.num_of_chars += sum(
-            len(message['content']) for message in messages
-        ) + len(response.choices[0].message.content)
-        return self.action_parser.parse(response)
-
-    def search_memory(self, query: str) -> list[str]:
-        raise NotImplementedError('Implement this abstract method')

agenthub/codeact_agent/prompt.py

@@ -1,255 +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` and `append_file` FUNCTIONS REQUIRE PROPER INDENTATION. If the assistant would like to add the line '        print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run."
-)
-
-# ======= SYSTEM 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 much commands OR 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 need more input or action from the user in order to proceed.
-IMPORTANT: Execute code using <execute_ipython>, <execute_bash>, or <execute_browse> whenever possible.
-"""
-
-
-# ======= 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)]
-1|
-[File app.py created.]
-
-ASSISTANT:
-Now I will write the Python code for starting a web server and save it to the file `app.py`:
-<execute_ipython>
-EDITED_CODE=\"\"\"from flask import Flask
-app = Flask(__name__)
-
-@app.route('/')
-def index():
-    numbers = list(range(1, 11))
-    return str(numbers)
-
-if __name__ == '__main__':
-    app.run(port=5000)\"\"\"
-edit_file('app.py', start=1, end=1, content=EDITED_CODE)
-</execute_ipython>
-
-USER:
-OBSERVATION:
-1|from flask import Flask
-2|app = Flask(__name__)
-3|
-4|@app.route('/')
-5|def index():
-6|    numbers = list(range(1, 11))
-7|    return str(numbers)
-8|
-9|if __name__ == '__main__':
-10|    app.run(port=5000)
-[File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
-
-ASSISTANT:
-I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you:
-<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)]
-1|from flask import Flask
-2|app = Flask(__name__)
-3|
-4|@app.route('/')
-5|def index():
-6|    numbers = list(range(1, 11))
-7|    return str(numbers)
-8|
-9|if __name__ == '__main__':
-10|    app.run(port=5000)
-
-ASSISTANT:
-I should edit the file to display the numbers in a table format. I should include correct indentation. Let me update the file:
-<execute_ipython>
-edit_file('app.py', start=7, end=7, content="    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'")
-</execute_ipython>
-
-USER:
-Observation:
-[File: /workspace/app.py (10 lines total after edit)]
-1|from flask import Flask
-2|app = Flask(__name__)
-3|
-4|@app.route('/')
-5|def index():
-6|    numbers = list(range(1, 11))
-7|    return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
-8|
-9|if __name__ == '__main__':
-10|    app.run(port=5000)
-[File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
-
-ASSISTANT:
-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!
-
---- 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/codeact_swe_agent/codeact_swe_agent.py

@@ -1,248 +0,0 @@
-import re
-
-from agenthub.codeact_swe_agent.prompt import (
-    COMMAND_DOCS,
-    MINIMAL_SYSTEM_PREFIX,
-    SWE_EXAMPLE,
-    SYSTEM_SUFFIX,
-)
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.events.action import (
-    Action,
-    AgentFinishAction,
-    BrowseInteractiveAction,
-    CmdRunAction,
-    IPythonRunCellAction,
-    MessageAction,
-)
-from opendevin.events.observation import (
-    BrowserOutputObservation,
-    CmdOutputObservation,
-    IPythonRunCellObservation,
-)
-from opendevin.llm.llm import LLM
-from opendevin.runtime.plugins import (
-    AgentSkillsRequirement,
-    JupyterRequirement,
-    PluginRequirement,
-)
-from opendevin.runtime.tools import RuntimeTool
-
-
-def parse_response(response) -> str:
-    action = response.choices[0].message.content
-    for lang in ['bash', 'ipython', 'browse']:
-        if f'<execute_{lang}>' in action and f'</execute_{lang}>' not in action:
-            action += f'</execute_{lang}>'
-    return action
-
-
-def action_to_str(action: Action) -> str:
-    if isinstance(action, CmdRunAction):
-        return f'{action.thought}\n<execute_bash>\n{action.command}\n</execute_bash>'
-    elif isinstance(action, IPythonRunCellAction):
-        return f'{action.thought}\n<execute_ipython>\n{action.code}\n</execute_ipython>'
-    elif isinstance(action, BrowseInteractiveAction):
-        return f'{action.thought}\n<execute_browse>\n{action.browser_actions}\n</execute_browse>'
-    elif isinstance(action, MessageAction):
-        return action.content
-    return ''
-
-
-def get_action_message(action: Action) -> dict[str, str] | None:
-    if (
-        isinstance(action, BrowseInteractiveAction)
-        or isinstance(action, CmdRunAction)
-        or isinstance(action, IPythonRunCellAction)
-        or isinstance(action, MessageAction)
-    ):
-        return {
-            'role': 'user' if action.source == 'user' else 'assistant',
-            'content': action_to_str(action),
-        }
-    return None
-
-
-def get_observation_message(obs) -> dict[str, str] | None:
-    if isinstance(obs, CmdOutputObservation):
-        content = 'OBSERVATION:\n' + truncate_observation(obs.content)
-        content += (
-            f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]]'
-        )
-        return {'role': 'user', 'content': content}
-    elif isinstance(obs, IPythonRunCellObservation):
-        content = 'OBSERVATION:\n' + obs.content
-        # replace base64 images with a placeholder
-        splitted = content.split('\n')
-        for i, line in enumerate(splitted):
-            if '![image](data:image/png;base64,' in line:
-                splitted[i] = (
-                    '![image](data:image/png;base64, ...) already displayed to user'
-                )
-        content = '\n'.join(splitted)
-        content = truncate_observation(content)
-        return {'role': 'user', 'content': content}
-    elif isinstance(obs, BrowserOutputObservation):
-        content = 'OBSERVATION:\n' + truncate_observation(obs.content)
-        return {'role': 'user', 'content': content}
-    return None
-
-
-def truncate_observation(observation: str, max_chars: int = 10_000) -> str:
-    """
-    Truncate the middle of the observation if it is too long.
-    """
-    if len(observation) <= max_chars:
-        return observation
-    half = max_chars // 2
-    return (
-        observation[:half]
-        + '\n[... Observation truncated due to length ...]\n'
-        + observation[-half:]
-    )
-
-
-def get_system_message() -> str:
-    return f'{MINIMAL_SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
-
-
-def get_in_context_example() -> str:
-    return SWE_EXAMPLE
-
-
-class CodeActSWEAgent(Agent):
-    VERSION = '1.5'
-    """
-    This agent is an adaptation of the original [SWE Agent](https://swe-agent.com/) based on CodeAct 1.5 using the `agentskills` library of OpenDevin.
-
-    It is intended use is **solving Github issues**.
-
-    It removes web-browsing and Github capability from the original CodeAct agent to avoid confusion to the agent.
-    """
-
-    sandbox_plugins: list[PluginRequirement] = [
-        # NOTE: AgentSkillsRequirement need to go before JupyterRequirement, since
-        # AgentSkillsRequirement provides a lot of Python functions
-        # and it need to be initialized before Jupyter for Jupyter to use those functions.
-        AgentSkillsRequirement(),
-        JupyterRequirement(),
-    ]
-    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
-    jupyter_kernel_init_code: str = 'from agentskills import *'
-
-    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!"
-
-    def __init__(
-        self,
-        llm: LLM,
-    ) -> None:
-        """
-        Initializes a new instance of the CodeActAgent class.
-
-        Parameters:
-        - llm (LLM): The llm to be used by this agent
-        """
-        super().__init__(llm)
-        self.reset()
-
-    def reset(self) -> None:
-        """
-        Resets the CodeAct Agent.
-        """
-        super().reset()
-
-    def step(self, state: State) -> Action:
-        """
-        Performs one step using the CodeAct Agent.
-        This includes gathering info on previous steps and prompting the model to make a command to execute.
-
-        Parameters:
-        - state (State): used to get updated info and background commands
-
-        Returns:
-        - CmdRunAction(command) - bash command to run
-        - IPythonRunCellAction(code) - IPython code to run
-        - BrowseInteractiveAction(browsergym_command) - BrowserGym commands to run
-        - MessageAction(content) - Message action to run (e.g. ask for clarification)
-        - AgentFinishAction() - end the interaction
-        """
-        messages: list[dict[str, str]] = [
-            {'role': 'system', 'content': self.system_message},
-            {'role': 'user', 'content': self.in_context_example},
-        ]
-
-        for prev_action, obs in state.history:
-            action_message = get_action_message(prev_action)
-            if action_message:
-                messages.append(action_message)
-
-            obs_message = get_observation_message(obs)
-            if obs_message:
-                messages.append(obs_message)
-
-        latest_user_message = [m for m in messages if m['role'] == 'user'][-1]
-        if latest_user_message:
-            if latest_user_message['content'].strip() == '/exit':
-                return AgentFinishAction()
-            latest_user_message['content'] += (
-                f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task.'
-            )
-
-        response = self.llm.do_completion(
-            messages=messages,
-            stop=[
-                '</execute_ipython>',
-                '</execute_bash>',
-                '</execute_browse>',
-            ],
-            temperature=0.0,
-        )
-
-        action_str: str = parse_response(response)
-        state.num_of_chars += sum(
-            len(message['content']) for message in messages
-        ) + len(action_str)
-
-        if finish_command := re.search(r'<finish>.*</finish>', action_str, re.DOTALL):
-            thought = action_str.replace(finish_command.group(0), '').strip()
-            return AgentFinishAction(thought=thought)
-        if bash_command := re.search(
-            r'<execute_bash>(.*?)</execute_bash>', action_str, re.DOTALL
-        ):
-            # remove the command from the action string to get thought
-            thought = action_str.replace(bash_command.group(0), '').strip()
-            # a command was found
-            command_group = bash_command.group(1).strip()
-
-            if command_group.strip() == 'exit':
-                return AgentFinishAction()
-            return CmdRunAction(command=command_group, thought=thought)
-        elif python_code := re.search(
-            r'<execute_ipython>(.*?)</execute_ipython>', action_str, re.DOTALL
-        ):
-            # a code block was found
-            code_group = python_code.group(1).strip()
-            thought = action_str.replace(python_code.group(0), '').strip()
-            return IPythonRunCellAction(
-                code=code_group,
-                thought=thought,
-                kernel_init_code=self.jupyter_kernel_init_code,
-            )
-        elif browse_command := re.search(
-            r'<execute_browse>(.*)</execute_browse>', action_str, re.DOTALL
-        ):
-            # BrowserGym actions was found
-            browse_actions = browse_command.group(1).strip()
-            thought = action_str.replace(browse_command.group(0), '').strip()
-            return BrowseInteractiveAction(
-                browser_actions=browse_actions, thought=thought
-            )
-        else:
-            # We assume the LLM is GOOD enough that when it returns pure natural language
-            # it want to talk to the user
-            return MessageAction(content=action_str, wait_for_response=True)
-
-    def search_memory(self, query: str) -> list[str]:
-        raise NotImplementedError('Implement this abstract method')

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/dummy_agent/agent.py

@@ -1,175 +0,0 @@
-import time
-from typing import TypedDict
-
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.events.action import (
-    Action,
-    AddTaskAction,
-    AgentFinishAction,
-    AgentRecallAction,
-    AgentRejectAction,
-    BrowseInteractiveAction,
-    BrowseURLAction,
-    CmdRunAction,
-    FileReadAction,
-    FileWriteAction,
-    MessageAction,
-    ModifyTaskAction,
-)
-from opendevin.events.observation import (
-    AgentRecallObservation,
-    CmdOutputObservation,
-    FileReadObservation,
-    FileWriteObservation,
-    NullObservation,
-    Observation,
-)
-from opendevin.events.serialization.event import event_to_dict
-from opendevin.llm.llm import LLM
-
-"""
-FIXME: There are a few problems this surfaced
-* FileWrites seem to add an unintended newline at the end of the file
-* command_id is sometimes a number, sometimes a string
-* Why isn't the output of the background command split between two steps?
-* Browser not working
-"""
-
-ActionObs = TypedDict(
-    'ActionObs', {'action': Action, 'observations': list[Observation]}
-)
-
-BACKGROUND_CMD = 'echo "This is in the background" && sleep .1 && echo "This too"'
-
-
-class DummyAgent(Agent):
-    VERSION = '1.0'
-    """
-    The DummyAgent is used for e2e testing. It just sends the same set of actions deterministically,
-    without making any LLM calls.
-    """
-
-    def __init__(self, llm: LLM):
-        super().__init__(llm)
-        self.steps: list[ActionObs] = [
-            {
-                'action': AddTaskAction(parent='0', goal='check the current directory'),
-                'observations': [NullObservation('')],
-            },
-            {
-                'action': AddTaskAction(parent='0.0', goal='run ls'),
-                'observations': [NullObservation('')],
-            },
-            {
-                'action': ModifyTaskAction(task_id='0.0', state='in_progress'),
-                'observations': [NullObservation('')],
-            },
-            {
-                'action': MessageAction('Time to get started!'),
-                'observations': [NullObservation('')],
-            },
-            {
-                'action': CmdRunAction(command='echo "foo"'),
-                'observations': [
-                    CmdOutputObservation('foo', command_id=-1, command='echo "foo"')
-                ],
-            },
-            {
-                'action': FileWriteAction(
-                    content='echo "Hello, World!"', path='hello.sh'
-                ),
-                'observations': [FileWriteObservation('', path='hello.sh')],
-            },
-            {
-                'action': FileReadAction(path='hello.sh'),
-                'observations': [
-                    FileReadObservation('echo "Hello, World!"\n', path='hello.sh')
-                ],
-            },
-            {
-                'action': CmdRunAction(command='bash hello.sh'),
-                'observations': [
-                    CmdOutputObservation(
-                        'Hello, World!', command_id=-1, command='bash hello.sh'
-                    )
-                ],
-            },
-            {
-                'action': CmdRunAction(command=BACKGROUND_CMD, background=True),
-                'observations': [
-                    CmdOutputObservation(
-                        'Background command started. To stop it, send a `kill` action with command_id 42',
-                        command_id='42',  # type: ignore[arg-type]
-                        command=BACKGROUND_CMD,
-                    ),
-                    CmdOutputObservation(
-                        'This is in the background\nThis too\n',
-                        command_id='42',  # type: ignore[arg-type]
-                        command=BACKGROUND_CMD,
-                    ),
-                ],
-            },
-            {
-                'action': AgentRecallAction(query='who am I?'),
-                'observations': [
-                    AgentRecallObservation('', memories=['I am a computer.']),
-                    # CmdOutputObservation('This too\n', command_id='42', command=BACKGROUND_CMD),
-                ],
-            },
-            {
-                'action': BrowseURLAction(url='https://google.com'),
-                'observations': [
-                    # BrowserOutputObservation('<html></html>', url='https://google.com', screenshot=""),
-                ],
-            },
-            {
-                'action': BrowseInteractiveAction(
-                    browser_actions='goto("https://google.com")'
-                ),
-                'observations': [
-                    # BrowserOutputObservation('<html></html>', url='https://google.com', screenshot=""),
-                ],
-            },
-            {
-                'action': AgentFinishAction(),
-                'observations': [],
-            },
-            {
-                'action': AgentRejectAction(),
-                'observations': [],
-            },
-        ]
-
-    def step(self, state: State) -> Action:
-        time.sleep(0.1)
-        if state.iteration > 0:
-            prev_step = self.steps[state.iteration - 1]
-            if 'observations' in prev_step:
-                expected_observations = prev_step['observations']
-                hist_start = len(state.history) - len(expected_observations)
-                for i in range(len(expected_observations)):
-                    hist_obs = event_to_dict(state.history[hist_start + i][1])
-                    expected_obs = event_to_dict(expected_observations[i])
-                    if (
-                        'command_id' in hist_obs['extras']
-                        and hist_obs['extras']['command_id'] != -1
-                    ):
-                        del hist_obs['extras']['command_id']
-                        hist_obs['content'] = ''
-                    if (
-                        'command_id' in expected_obs['extras']
-                        and expected_obs['extras']['command_id'] != -1
-                    ):
-                        del expected_obs['extras']['command_id']
-                        expected_obs['content'] = ''
-                    if hist_obs != expected_obs:
-                        print('\nactual', hist_obs)
-                        print('\nexpect', expected_obs)
-                    assert (
-                        hist_obs == expected_obs
-                    ), f'Expected observation {expected_obs}, got {hist_obs}'
-        return self.steps[state.iteration]['action']
-
-    def search_memory(self, query: str) -> list[str]:
-        return ['I am a computer.']

agenthub/micro/_instructions/actions/kill.md

@@ -1,2 +0,0 @@
-* `kill` - kills a background command
-  * `command_id` - the ID of the background command to kill

agenthub/micro/_instructions/actions/run.md

@@ -1,3 +0,0 @@
-* `run` - runs a command on the command line in a Linux shell. Arguments:
-  * `command` - the command to run
-  * `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.

agenthub/micro/agent.py

@@ -1,74 +0,0 @@
-from jinja2 import BaseLoader, Environment
-
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.core.utils import json
-from opendevin.events.action import Action
-from opendevin.events.serialization.action import action_from_dict
-from opendevin.events.serialization.event import event_to_memory
-from opendevin.llm.llm import LLM
-
-from .instructions import instructions
-from .registry import all_microagents
-
-
-def parse_response(orig_response: str) -> Action:
-    # attempt to load the JSON dict from the response
-    action_dict = json.loads(orig_response)
-
-    # load the action from the dict
-    return action_from_dict(action_dict)
-
-
-def to_json(obj, **kwargs):
-    """
-    Serialize an object to str format
-    """
-    return json.dumps(obj, **kwargs)
-
-
-def history_to_json(obj, **kwargs):
-    """
-    Serialize and simplify history to str format
-    """
-    if isinstance(obj, list):
-        # process history, make it simpler.
-        processed_history = []
-        for action, observation in obj:
-            processed_history.append(
-                (event_to_memory(action), event_to_memory(observation))
-            )
-        return json.dumps(processed_history, **kwargs)
-
-
-class MicroAgent(Agent):
-    VERSION = '1.0'
-    prompt = ''
-    agent_definition: dict = {}
-
-    def __init__(self, llm: LLM):
-        super().__init__(llm)
-        if 'name' not in self.agent_definition:
-            raise ValueError('Agent definition must contain a name')
-        self.prompt_template = Environment(loader=BaseLoader).from_string(self.prompt)
-        self.delegates = all_microagents.copy()
-        del self.delegates[self.agent_definition['name']]
-
-    def step(self, state: State) -> Action:
-        prompt = self.prompt_template.render(
-            state=state,
-            instructions=instructions,
-            to_json=to_json,
-            history_to_json=history_to_json,
-            delegates=self.delegates,
-            latest_user_message=state.get_current_user_intent(),
-        )
-        messages = [{'content': prompt, 'role': 'user'}]
-        resp = self.llm.do_completion(messages=messages)
-        action_resp = resp['choices'][0]['message']['content']
-        state.num_of_chars += len(prompt) + len(action_resp)
-        action = parse_response(action_resp)
-        return action
-
-    def search_memory(self, query: str) -> list[str]:
-        return []

agenthub/monologue_agent/.dockerignore

@@ -1,2 +0,0 @@
-.envrc
-workspace

agenthub/monologue_agent/README.md

@@ -1,8 +0,0 @@
-# LLM control loop
-This is currently a standalone utility. It will need to be integrated into OpenDevin's backend.
-
-## Usage
-```bash
-# Run this in project root
-./agenthub/monologue_agent/build-and-run.sh "write a bash script that prints 'hello world'"
-```

agenthub/monologue_agent/TODO.md

@@ -1,8 +0,0 @@
-# TODO
-There's a lot of low-hanging fruit for this agent:
-
-* Strip `<script>`, `<style>`, and other non-text tags from the HTML before sending it to the LLM
-* Keep track of the working directory when the agent uses `cd`
-* Improve memory condensing--condense earlier memories more aggressively
-* Limit the time that `run` can wait (in case agent runs an interactive command and it's hanging)
-* Figure out how to run background processes, e.g. `node server.js` to start a server

agenthub/monologue_agent/__init__.py

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

agenthub/monologue_agent/agent.py

@@ -1,240 +0,0 @@
-import agenthub.monologue_agent.utils.prompts as prompts
-from agenthub.monologue_agent.utils.prompts import INITIAL_THOUGHTS
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.core.config import config
-from opendevin.core.exceptions import AgentNoInstructionError
-from opendevin.core.schema import ActionType
-from opendevin.events.action import (
-    Action,
-    AgentRecallAction,
-    BrowseURLAction,
-    CmdRunAction,
-    FileReadAction,
-    FileWriteAction,
-    MessageAction,
-    NullAction,
-)
-from opendevin.events.observation import (
-    AgentRecallObservation,
-    BrowserOutputObservation,
-    CmdOutputObservation,
-    FileReadObservation,
-    NullObservation,
-    Observation,
-)
-from opendevin.events.serialization.event import event_to_memory
-from opendevin.llm.llm import LLM
-from opendevin.memory.condenser import MemoryCondenser
-from opendevin.runtime.tools import RuntimeTool
-
-if config.agent.memory_enabled:
-    from opendevin.memory.memory import LongTermMemory
-
-MAX_TOKEN_COUNT_PADDING = 512
-MAX_OUTPUT_LENGTH = 5000
-
-
-class MonologueAgent(Agent):
-    VERSION = '1.0'
-    """
-    The Monologue Agent utilizes long and short term memory to complete tasks.
-    Long term memory is stored as a LongTermMemory object and the model uses it to search for examples from the past.
-    Short term memory is stored as a Monologue object and the model can condense it as necessary.
-    """
-
-    _initialized = False
-    initial_thoughts: list[dict[str, str]]
-    memory: 'LongTermMemory | None'
-    memory_condenser: MemoryCondenser
-    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
-
-    def __init__(self, llm: LLM):
-        """
-        Initializes the Monologue Agent with an llm.
-
-        Parameters:
-        - llm (LLM): The llm to be used by this agent
-        """
-        super().__init__(llm)
-
-    def _initialize(self, task: str):
-        """
-        Utilizes the INITIAL_THOUGHTS list to give the agent a context for its capabilities
-        and how to navigate the WORKSPACE_MOUNT_PATH_IN_SANDBOX in `config` (e.g., /workspace by default).
-        Short circuited to return when already initialized.
-        Will execute again when called after reset.
-
-        Parameters:
-        - task (str): The initial goal statement provided by the user
-
-        Raises:
-        - AgentNoInstructionError: If task is not provided
-        """
-
-        if self._initialized:
-            return
-
-        if task is None or task == '':
-            raise AgentNoInstructionError()
-
-        self.initial_thoughts = []
-        if config.agent.memory_enabled:
-            self.memory = LongTermMemory()
-        else:
-            self.memory = None
-
-        self.memory_condenser = MemoryCondenser()
-
-        self._add_initial_thoughts(task)
-        self._initialized = True
-
-    def _add_initial_thoughts(self, task):
-        previous_action = ''
-        for thought in INITIAL_THOUGHTS:
-            thought = thought.replace('$TASK', task)
-            if previous_action != '':
-                observation: Observation = NullObservation(content='')
-                if previous_action in {ActionType.RUN, ActionType.PUSH}:
-                    observation = CmdOutputObservation(
-                        content=thought, command_id=0, command=''
-                    )
-                elif previous_action == ActionType.READ:
-                    observation = FileReadObservation(content=thought, path='')
-                elif previous_action == ActionType.RECALL:
-                    observation = AgentRecallObservation(content=thought, memories=[])
-                elif previous_action == ActionType.BROWSE:
-                    observation = BrowserOutputObservation(
-                        content=thought, url='', screenshot=''
-                    )
-                self.initial_thoughts.append(event_to_memory(observation))
-                previous_action = ''
-            else:
-                action: Action = NullAction()
-                if thought.startswith('RUN'):
-                    command = thought.split('RUN ')[1]
-                    action = CmdRunAction(command)
-                    previous_action = ActionType.RUN
-                elif thought.startswith('WRITE'):
-                    parts = thought.split('WRITE ')[1].split(' > ')
-                    path = parts[1]
-                    content = parts[0]
-                    action = FileWriteAction(path=path, content=content)
-                elif thought.startswith('READ'):
-                    path = thought.split('READ ')[1]
-                    action = FileReadAction(path=path)
-                    previous_action = ActionType.READ
-                elif thought.startswith('RECALL'):
-                    query = thought.split('RECALL ')[1]
-                    action = AgentRecallAction(query=query)
-                    previous_action = ActionType.RECALL
-                elif thought.startswith('BROWSE'):
-                    url = thought.split('BROWSE ')[1]
-                    action = BrowseURLAction(url=url)
-                    previous_action = ActionType.BROWSE
-                else:
-                    action = MessageAction(thought)
-                self.initial_thoughts.append(event_to_memory(action))
-
-    def step(self, state: State) -> Action:
-        """
-        Modifies the current state by adding the most recent actions and observations, then prompts the model to think about it's next action to take using monologue, memory, and hint.
-
-        Parameters:
-        - state (State): The current state based on previous steps taken
-
-        Returns:
-        - Action: The next action to take based on LLM response
-        """
-
-        goal = state.get_current_user_intent()
-        self._initialize(goal)
-
-        recent_events: list[dict[str, str]] = []
-
-        # add the events from state.history
-        for prev_action, obs in state.history:
-            if not isinstance(prev_action, NullAction):
-                recent_events.append(event_to_memory(prev_action))
-            if not isinstance(obs, NullObservation):
-                recent_events.append(self._truncate_output(event_to_memory(obs)))
-
-        # add the last messages to long term memory
-        if self.memory is not None and state.history and len(state.history) > 0:
-            self.memory.add_event(event_to_memory(state.history[-1][0]))
-            self.memory.add_event(
-                self._truncate_output(event_to_memory(state.history[-1][1]))
-            )
-
-        # the action prompt with initial thoughts and recent events
-        prompt = prompts.get_request_action_prompt(
-            goal,
-            self.initial_thoughts,
-            recent_events,
-            state.background_commands_obs,
-        )
-
-        messages: list[dict[str, str]] = [
-            {'role': 'user', 'content': prompt},
-        ]
-
-        # format all as a single message, a monologue
-        resp = self.llm.do_completion(messages=messages)
-
-        # get the next action from the response
-        action_resp = resp['choices'][0]['message']['content']
-
-        # keep track of max_chars fallback option
-        state.num_of_chars += len(prompt) + len(action_resp)
-
-        action = prompts.parse_action_response(action_resp)
-        self.latest_action = action
-        return action
-
-    def _truncate_output(
-        self, observation: dict, max_chars: int = MAX_OUTPUT_LENGTH
-    ) -> dict[str, str]:
-        """
-        Truncates the output of an observation to a maximum number of characters.
-
-        Parameters:
-        - output (str): The observation whose output to truncate
-        - max_chars (int): The maximum number of characters to allow
-
-        Returns:
-        - str: The truncated output
-        """
-        if (
-            'args' in observation
-            and 'output' in observation['args']
-            and len(observation['args']['output']) > max_chars
-        ):
-            output = observation['args']['output']
-            half = max_chars // 2
-            observation['args']['output'] = (
-                output[:half]
-                + '\n[... Output truncated due to length...]\n'
-                + output[-half:]
-            )
-        return observation
-
-    def search_memory(self, query: str) -> list[str]:
-        """
-        Uses VectorIndexRetriever to find related memories within the long term memory.
-        Uses search to produce top 10 results.
-
-        Parameters:
-        - query (str): The query that we want to find related memories for
-
-        Returns:
-        - list[str]: A list of top 10 text results that matched the query
-        """
-        if self.memory is None:
-            return []
-        return self.memory.search(query)
-
-    def reset(self) -> None:
-        super().reset()
-
-        # Reset the initial monologue and memory
-        self._initialized = False

agenthub/monologue_agent/utils/prompts.py

@@ -1,245 +0,0 @@
-from opendevin.core.config import config
-from opendevin.core.utils import json
-from opendevin.events.action import (
-    Action,
-)
-from opendevin.events.observation import (
-    CmdOutputObservation,
-)
-from opendevin.events.serialization.action import action_from_dict
-
-ACTION_PROMPT = """
-You're a thoughtful robot. Your main task is this:
-%(task)s
-
-Don't expand the scope of your task--just complete it as written.
-
-This is your internal monologue, in JSON format:
-
-%(monologue)s
-
-Your most recent thought is at the bottom of that monologue. Continue your train of thought.
-What is your next single thought or action? Your response must be in JSON format.
-It must be a single object, and it must contain two fields:
-* `action`, which is one of the actions below
-* `args`, which is a map of key-value pairs, specifying the arguments for that action
-
-Here are the possible actions:
-* `read` - reads the content of a file. Arguments:
-  * `path` - the path of the file to read
-* `write` - writes the content to a file. Arguments:
-  * `path` - the path of the file to write
-  * `content` - the content to write to the file
-* `run` - runs a command. Arguments:
-  * `command` - the command to run
-  * `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
-* `kill` - kills a background command
-  * `command_id` - the ID of the background command to kill
-* `browse` - opens a web page. Arguments:
-  * `url` - the URL to open
-* `push` - Push a branch from the current repo to github:
-  * `owner` - the owner of the repo to push to
-  * `repo` - the name of the repo to push to
-  * `branch` - the name of the branch to push
-* `recall` - recalls a past memory. Arguments:
-  * `query` - the query to search for
-* `message` - make a plan, set a goal, record your thoughts, or ask for more input from the user. Arguments:
-  * `content` - the message to record
-  * `wait_for_response` - set to `true` to wait for the user to respond before proceeding
-* `finish` - if you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.
-
-%(background_commands)s
-
-You MUST take time to think in between read, write, run, kill, browse, push, and recall actions--do this with the `message` action.
-You should never act twice in a row without thinking. But if your last several
-actions are all `message` actions, you should consider taking a different action.
-
-Notes:
-* you are logged in as %(user)s, but sudo will always work without a password.
-* all non-background commands will be forcibly stopped if they remain running for over %(timeout)s seconds.
-* your environment is Debian Linux. You can install software with `sudo apt-get`, but remember to use -y.
-* don't run interactive commands, or commands that don't return (e.g. `node server.js`). You may run commands in the background (e.g. `node server.js &`)
-* don't run interactive text editors (e.g. `nano` or 'vim'), instead use the 'write' or 'read' action.
-* don't run gui applications (e.g. software IDEs (like vs code or codium), web browsers (like firefox or chromium), or other complex software packages). Use non-interactive cli applications, or special actions instead.
-* whenever an action fails, always send a `message` about why it may have happened before acting again.
-
-What is your next single thought or action? Again, you must reply with JSON, and only with JSON. You must respond with exactly one 'action' object.
-
-%(hint)s
-"""
-
-MONOLOGUE_SUMMARY_PROMPT = """
-Below is the internal monologue of an automated LLM agent. Each
-thought is an item in a JSON array. The thoughts may be memories,
-actions taken by the agent, or outputs from those actions.
-Please return a new, smaller JSON array, which summarizes the
-internal monologue. You can summarize individual thoughts, and
-you can condense related thoughts together with a description
-of their content.
-
-%(monologue)s
-
-Make the summaries as pithy and informative as possible.
-Be specific about what happened and what was learned. The summary
-will be used as keywords for searching for the original memory.
-Be sure to preserve any key words or important information.
-
-Your response must be in JSON format. It must be an object with the
-key `new_monologue`, which is a JSON array containing the summarized monologue.
-Each entry in the array must have an `action` key, and an `args` key.
-The action key may be `summarize`, and `args.summary` should contain the summary.
-You can also use the same action and args from the source monologue.
-"""
-
-INITIAL_THOUGHTS = [
-    'I exist!',
-    'Hmm...looks like I can type in a command line prompt',
-    'Looks like I have a web browser too!',
-    "Here's what I want to do: $TASK",
-    'How am I going to get there though?',
-    'It seems like I have some kind of short term memory.',
-    'Each of my thoughts seems to be stored in a JSON array.',
-    'It seems whatever I say next will be added as an object to the list.',
-    'But no one has perfect short-term memory. My list of thoughts will be summarized and condensed over time, losing information in the process.',
-    'Fortunately I have long term memory!',
-    'I can just perform a recall action, followed by the thing I want to remember. And then related thoughts just spill out!',
-    "Sometimes they're random thoughts that don't really have to do with what I wanted to remember. But usually they're exactly what I need!",
-    "Let's try it out!",
-    'RECALL what it is I want to do',
-    "Here's what I want to do: $TASK",
-    'How am I going to get there though?',
-    "Neat! And it looks like it's easy for me to use the command line too! I just have to perform a run action and include the command I want to run in the command argument. The command output just jumps into my head!",
-    'RUN echo "hello world"',
-    'hello world',
-    'Cool! I bet I can write files too using the write action.',
-    'WRITE echo "console.log(\'hello world\')" > test.js',
-    '',
-    "I just created test.js. I'll try and run it now.",
-    'RUN node test.js',
-    'hello world',
-    'It works!',
-    "I'm going to try reading it now using the read action.",
-    'READ test.js',
-    "console.log('hello world')",
-    'Nice! I can read files too!',
-    'And if I want to use the browser, I just need to use the browse action and include the url I want to visit in the url argument',
-    "Let's try that...",
-    'BROWSE google.com',
-    '<form><input type="text"></input><button type="submit"></button></form>',
-    'I can browse the web too!',
-    'And once I have completed my task, I can use the finish action to stop working.',
-    "But I should only use the finish action when I'm absolutely certain that I've completed my task and have tested my work.",
-    'Very cool. Now to accomplish my task.',
-    "I'll need a strategy. And as I make progress, I'll need to keep refining that strategy. I'll need to set goals, and break them into sub-goals.",
-    'In between actions, I must always take some time to think, strategize, and set new goals. I should never take two actions in a row.',
-    "OK so my task is to $TASK. I haven't made any progress yet. Where should I start?",
-    'It seems like there might be an existing project here. I should probably start by running `pwd` and `ls` to orient myself.',
-]
-
-
-def get_summarize_monologue_prompt(thoughts: list[dict]):
-    """
-    Gets the prompt for summarizing the monologue
-
-    Returns:
-    - str: A formatted string with the current monologue within the prompt
-    """
-    return MONOLOGUE_SUMMARY_PROMPT % {
-        'monologue': json.dumps({'old_monologue': thoughts}, indent=2),
-    }
-
-
-def get_request_action_prompt(
-    task: str,
-    thoughts: list[dict],
-    recent_events: list[dict],
-    background_commands_obs: list[CmdOutputObservation] | None = None,
-):
-    """
-    Gets the action prompt formatted with appropriate values.
-
-    Parameters:
-    - task (str): The current task the agent is trying to accomplish
-    - thoughts (list[dict]): The agent's current thoughts
-    - background_commands_obs (list[CmdOutputObservation]): list of all observed background commands running
-
-    Returns:
-    - str: Formatted prompt string with hint, task, monologue, and background commands included
-    """
-
-    if background_commands_obs is None:
-        background_commands_obs = []
-
-    hint = ''
-    if len(recent_events) > 0:
-        latest_event = recent_events[-1]
-        if 'action' in latest_event:
-            if (
-                latest_event['action'] == 'message'
-                and 'source' in latest_event
-                and latest_event['source'] == 'agent'
-            ):
-                hint = (
-                    "You've been thinking a lot lately. Maybe it's time to take action?"
-                )
-            elif latest_event['action'] == 'error':
-                hint = 'Looks like that last command failed. Maybe you need to fix it, or try something else.'
-    else:
-        hint = "You're just getting started! What should you do first?"
-
-    bg_commands_message = ''
-    if len(background_commands_obs) > 0:
-        bg_commands_message = 'The following commands are running in the background:'
-        for command_obs in background_commands_obs:
-            bg_commands_message += (
-                f'\n`{command_obs.command_id}`: {command_obs.command}'
-            )
-        bg_commands_message += '\nYou can end any process by sending a `kill` action with the numerical `command_id` above.'
-
-    user = 'opendevin' if config.run_as_devin else 'root'
-
-    monologue = thoughts + recent_events
-
-    return ACTION_PROMPT % {
-        'task': task,
-        'monologue': json.dumps(monologue, indent=2),
-        'background_commands': bg_commands_message,
-        'hint': hint,
-        'user': user,
-        'timeout': config.sandbox_timeout,
-        'WORKSPACE_MOUNT_PATH_IN_SANDBOX': config.workspace_mount_path_in_sandbox,
-    }
-
-
-def parse_action_response(orig_response: str) -> Action:
-    """
-    Parses a string to find an action within it
-
-    Parameters:
-    - response (str): The string to be parsed
-
-    Returns:
-    - Action: The action that was found in the response string
-    """
-    # attempt to load the JSON dict from the response
-    action_dict = json.loads(orig_response)
-
-    if 'content' in action_dict:
-        # The LLM gets confused here. Might as well be robust
-        action_dict['contents'] = action_dict.pop('content')
-
-    return action_from_dict(action_dict)
-
-
-def parse_summary_response(response: str) -> list[dict]:
-    """
-    Parses a summary of the monologue
-
-    Parameters:
-    - response (str): The response string to be parsed
-
-    Returns:
-    - list[dict]: The list of summaries output by the model
-    """
-    parsed = json.loads(response)
-    return parsed['new_monologue']

agenthub/planner_agent/__init__.py

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

agenthub/planner_agent/agent.py

@@ -1,55 +0,0 @@
-from opendevin.controller.agent import Agent
-from opendevin.controller.state.state import State
-from opendevin.events.action import Action, AgentFinishAction
-from opendevin.llm.llm import LLM
-from opendevin.runtime.tools import RuntimeTool
-
-from .prompt import get_prompt, parse_response
-
-
-class PlannerAgent(Agent):
-    VERSION = '1.0'
-    """
-    The planner agent utilizes a special prompting strategy to create long term plans for solving problems.
-    The agent is given its previous action-observation pairs, current task, and hint based on last action taken at every step.
-    """
-    runtime_tools: list[RuntimeTool] = [RuntimeTool.BROWSER]
-
-    def __init__(self, llm: LLM):
-        """
-        Initialize the Planner Agent with an LLM
-
-        Parameters:
-        - llm (LLM): The llm to be used by this agent
-        """
-        super().__init__(llm)
-
-    def step(self, state: State) -> Action:
-        """
-        Checks to see if current step is completed, returns AgentFinishAction if True.
-        Otherwise, creates a plan prompt and sends to model for inference, returning the result as the next action.
-
-        Parameters:
-        - state (State): The current state given the previous actions and observations
-
-        Returns:
-        - AgentFinishAction: If the last state was 'completed', 'verified', or 'abandoned'
-        - Action: The next action to take based on llm response
-        """
-
-        if state.root_task.state in [
-            'completed',
-            'verified',
-            'abandoned',
-        ]:
-            return AgentFinishAction()
-        prompt = get_prompt(state)
-        messages = [{'content': prompt, 'role': 'user'}]
-        resp = self.llm.do_completion(messages=messages)
-        action_resp = resp['choices'][0]['message']['content']
-        state.num_of_chars += len(prompt) + len(action_resp)
-        action = parse_response(action_resp)
-        return action
-
-    def search_memory(self, query: str) -> list[str]:
-        return []

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

@@ -0,0 +1,248 @@
+###################### OpenHands Configuration Example ######################
+#
+# All settings have default values, so you only need to uncomment and
+# modify what you want to change
+# The fields within each section are sorted in alphabetical order.
+#
+##############################################################################
+
+#################################### Core ####################################
+# General core configurations
+##############################################################################
+[core]
+# 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"
+
+# Cache directory path
+#cache_dir = "/tmp/cache"
+
+# Debugging enabled
+#debug = false
+
+# Disable color in terminal output
+#disable_color = false
+
+# 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"
+
+# File store type
+#file_store = "memory"
+
+# List of allowed file extensions for uploads
+#file_uploads_allowed_extensions = [".*"]
+
+# Maximum file size for uploads, in megabytes
+#file_uploads_max_file_size_mb = 0
+
+# Maximum budget per task, 0.0 means no limit
+#max_budget_per_task = 0.0
+
+# Maximum number of iterations
+#max_iterations = 100
+
+# Path to mount the workspace in the sandbox
+#workspace_mount_path_in_sandbox = "/workspace"
+
+# Path to mount the workspace
+#workspace_mount_path = ""
+
+# Path to rewrite the workspace mount path to
+#workspace_mount_rewrite = ""
+
+# Run as openhands
+#run_as_openhands = true
+
+# Runtime environment
+#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
+##############################################################################
+[llm]
+# AWS access key ID
+#aws_access_key_id = ""
+
+# AWS region name
+#aws_region_name = ""
+
+# AWS secret access key
+#aws_secret_access_key = ""
+
+# API key to use
+api_key = "your-api-key"
+
+# API base URL
+#base_url = ""
+
+# API version
+#api_version = ""
+
+# Cost per input token
+#input_cost_per_token = 0.0
+
+# Cost per output token
+#output_cost_per_token = 0.0
+
+# Custom LLM provider
+#custom_llm_provider = ""
+
+# Embedding API base URL
+#embedding_base_url = ""
+
+# Embedding deployment name
+#embedding_deployment_name = ""
+
+# Embedding model to use
+embedding_model = "local"
+
+# Maximum number of characters in an observation's content
+#max_message_chars = 10000
+
+# Maximum number of input tokens
+#max_input_tokens = 0
+
+# Maximum number of output tokens
+#max_output_tokens = 0
+
+# Model to use
+model = "gpt-4o"
+
+# Number of retries to attempt when an operation fails with the LLM.
+# Increase this value to allow more attempts before giving up
+#num_retries = 8
+
+# Maximum wait time (in seconds) between retry attempts
+# This caps the exponential backoff to prevent excessively long
+#retry_max_wait = 120
+
+# 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
+
+# Timeout for the API
+#timeout = 0
+
+# Top p for the API
+#top_p = 1.0
+
+# If model is vision capable, this option allows to disable image processing (useful for cost reduction).
+#disable_vision = true
+
+[llm.gpt4o-mini]
+api_key = "your-api-key"
+model = "gpt-4o"
+
+
+#################################### Agent ###################################
+# Configuration for agents (group name starts with 'agent')
+# Use 'agent' for the default agent config
+# otherwise, group name must be `agent.<agent_name>` (case-sensitive), e.g.
+# agent.CodeActAgent
+##############################################################################
+[agent]
+# Name of the micro agent to use for this agent
+#micro_agent_name = ""
+
+# Memory enabled
+#memory_enabled = false
+
+# Memory maximum threads
+#memory_max_threads = 3
+
+# LLM config group to use
+#llm_config = 'your-llm-config-group'
+
+[agent.RepoExplorerAgent]
+# Example: use a cheaper model for RepoExplorerAgent to reduce cost, especially
+# useful when an agent doesn't demand high quality but uses a lot of tokens
+llm_config = 'gpt3'
+
+#################################### Sandbox ###################################
+# Configuration for the sandbox
+##############################################################################
+[sandbox]
+# Sandbox timeout in seconds
+#timeout = 120
+
+# Sandbox user ID
+#user_id = 1000
+
+# Container image to use for the sandbox
+#base_container_image = "nikolaik/python-nodejs:python3.12-nodejs22"
+
+# Use host network
+#use_host_network = false
+
+# 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

@@ -1,11 +1,12 @@
 # Docker Containers
+
 Each folder here contains a Dockerfile, and a config.sh describing how to build
-the image and where to push it. These are images are built and pushed in GitHub Actions
+the images and where to push them. These images are built and pushed in GitHub Actions
 by the `ghcr.yml` workflow.
 
 ## Building Manually
 
-```
-docker build -f containers/app/Dockerfile -t opendevin .
+```bash
+docker build -f containers/app/Dockerfile -t openhands .
 docker build -f containers/sandbox/Dockerfile -t sandbox .
 ```

containers/app/Dockerfile

@@ -1,5 +1,5 @@
-ARG OPEN_DEVIN_BUILD_VERSION=dev
-FROM node:21.7.2-bookworm-slim as frontend-builder
+ARG OPENHANDS_BUILD_VERSION=dev
+FROM node:21.7.2-bookworm-slim AS frontend-builder
 
 WORKDIR /app
 
@@ -8,12 +8,12 @@ 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
+FROM python:3.12.3-slim AS backend-builder
 
 WORKDIR /app
-ENV PYTHONPATH '/app'
+ENV PYTHONPATH='/app'
 
 ENV POETRY_NO_INTERACTION=1 \
     POETRY_VIRTUALENVS_IN_PROJECT=1 \
@@ -26,57 +26,69 @@ RUN apt-get update -y \
 
 COPY ./pyproject.toml ./poetry.lock ./
 RUN touch README.md
-RUN poetry install --without evaluation --no-root && rm -rf $POETRY_CACHE_DIR
+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
+ENV SANDBOX_USER_ID=0
 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
 
@@ -18,11 +18,18 @@ if [ -z "$SANDBOX_USER_ID" ]; then
   exit 1
 fi
 
+if [ -z "$WORKSPACE_MOUNT_PATH" ]; then
+  # This is set to /opt/workspace in the Dockerfile. But if the user isn't mounting, we want to unset it so that OpenHands doesn't mount at all
+  unset WORKSPACE_BASE
+fi
+
 if [[ "$SANDBOX_USER_ID" -eq 0 ]]; then
-  echo "Running OpenDevin as root"
-  export RUN_AS_DEVIN=false
+  echo "Running OpenHands as root"
+  export RUN_AS_OPENHANDS=false
   mkdir -p /root/.cache/ms-playwright/
-  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
   echo "Setting up enduser with id $SANDBOX_USER_ID"
@@ -30,9 +37,9 @@ 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 $SANDBOX_USER_ID for a second time. Exiting."
         exit 1
@@ -40,7 +47,7 @@ else
     fi
   fi
   usermod -aG app enduser
-  # get the user group of /var/run/docker.sock and set opendevin to that group
+  # get the user group of /var/run/docker.sock and set openhands to that group
   DOCKER_SOCKET_GID=$(stat -c '%g' /var/run/docker.sock)
   echo "Docker socket group id: $DOCKER_SOCKET_GID"
   if getent group $DOCKER_SOCKET_GID; then
@@ -52,9 +59,11 @@ else
 
   mkdir -p /home/enduser/.cache/huggingface/hub/
   mkdir -p /home/enduser/.cache/ms-playwright/
-  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

@@ -1,67 +1,156 @@
 #!/bin/bash
 set -eo pipefail
 
-image_name=$1
-org_name=$2
+# Initialize variables with default values
+image_name=""
+org_name=""
 push=0
-if [[ $3 == "--push" ]]; then
-  push=1
+load=0
+tag_suffix=""
+
+# Function to display usage information
+usage() {
+    echo "Usage: $0 -i <image_name> [-o <org_name>] [--push] [--load] [-t <tag_suffix>]"
+    echo "  -i: Image name (required)"
+    echo "  -o: Organization name"
+    echo "  --push: Push the image"
+    echo "  --load: Load the image"
+    echo "  -t: Tag suffix"
+    exit 1
+}
+
+# Parse command-line options
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        -i) image_name="$2"; shift 2 ;;
+        -o) org_name="$2"; shift 2 ;;
+        --push) push=1; shift ;;
+        --load) load=1; shift ;;
+        -t) tag_suffix="$2"; shift 2 ;;
+        *) usage ;;
+    esac
+done
+# Check if required arguments are provided
+if [[ -z "$image_name" ]]; then
+    echo "Error: Image name is required."
+    usage
 fi
 
-echo -e "Building: $image_name"
+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
   if [[ $GITHUB_REF_NAME =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
-    major_version=$(echo $GITHUB_REF_NAME | cut -d. -f1)
-    minor_version=$(echo $GITHUB_REF_NAME | cut -d. -f1,2)
-    tags+=($major_version $minor_version)
+    major_version=$(echo "$GITHUB_REF_NAME" | cut -d. -f1)
+    minor_version=$(echo "$GITHUB_REF_NAME" | cut -d. -f1,2)
+    tags+=("$major_version" "$minor_version")
+    tags+=("latest")
   fi
-  sanitized=$(echo $GITHUB_REF_NAME | sed 's/[^a-zA-Z0-9.-]\+/-/g')
-  OPEN_DEVIN_BUILD_VERSION=$sanitized
-  cache_tag+="-${sanitized}"
-  tags+=($sanitized)
+  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[@]}"
 
-dir=./containers/$image_name
-if [ ! -f $dir/Dockerfile ]; then
+if [[ "$image_name" == "openhands" ]]; then
+  dir="./containers/app"
+elif [[ "$image_name" == "runtime" ]]; then
+  dir="./containers/runtime"
+else
+  dir="./containers/$image_name"
+fi
+
+if [[ (! -f "$dir/Dockerfile") && "$image_name" != "runtime" ]]; then
+  # Allow runtime to be built without a Dockerfile
   echo "No Dockerfile found"
   exit 1
 fi
-if [ ! -f $dir/config.sh ]; then
+if [[ ! -f "$dir/config.sh" ]]; then
   echo "No config.sh found for Dockerfile"
   exit 1
 fi
-source $dir/config.sh
+
+source "$dir/config.sh"
+
 if [[ -n "$org_name" ]]; then
   DOCKER_ORG="$org_name"
 fi
-DOCKER_REPOSITORY=$DOCKER_REGISTRY/$DOCKER_ORG/$DOCKER_IMAGE
+
+# If $DOCKER_IMAGE_SOURCE_TAG is set, add it to the tags
+if [[ -n "$DOCKER_IMAGE_SOURCE_TAG" ]]; then
+  tags+=("$DOCKER_IMAGE_SOURCE_TAG")
+fi
+# If $DOCKER_IMAGE_TAG is set, add it to the tags
+if [[ -n "$DOCKER_IMAGE_TAG" ]]; then
+  tags+=("$DOCKER_IMAGE_TAG")
+fi
+
+DOCKER_REPOSITORY="$DOCKER_REGISTRY/$DOCKER_ORG/$DOCKER_IMAGE"
 DOCKER_REPOSITORY=${DOCKER_REPOSITORY,,} # lowercase
 echo "Repo: $DOCKER_REPOSITORY"
 echo "Base dir: $DOCKER_BASE_DIR"
 
 args=""
-for tag in ${tags[@]}; do
+for tag in "${tags[@]}"; do
   args+=" -t $DOCKER_REPOSITORY:$tag"
 done
+
 if [[ $push -eq 1 ]]; then
   args+=" --push"
   args+=" --cache-to=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag,mode=max"
 fi
 
+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 \
+  --build-arg OPENHANDS_BUILD_VERSION="$OPENHANDS_BUILD_VERSION" \
   --cache-from=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag \
   --cache-from=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag_base-main \
-  --platform linux/amd64,linux/arm64 \
+  --platform $platform \
   --provenance=false \
-  -f $dir/Dockerfile $DOCKER_BASE_DIR
+  -f "$dir/Dockerfile" \
+  "$DOCKER_BASE_DIR"
+
+# If load was requested, print the loaded images
+if [[ $load -eq 1 ]]; then
+  echo "Local images built:"
+  docker images "$DOCKER_REPOSITORY" --format "{{.Repository}}:{{.Tag}}"
+fi

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

@@ -0,0 +1,12 @@
+# Dynamically constructed Dockerfile
+
+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 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 openhands/runtime/utils/runtime_build.py \
+    --base_image nikolaik/python-nodejs:python3.12-nodejs22 \
+    --build_folder containers/runtime
+```

containers/runtime/config.sh

@@ -0,0 +1,7 @@
+DOCKER_REGISTRY=ghcr.io
+DOCKER_ORG=all-hands-ai
+DOCKER_BASE_DIR="./containers/runtime"
+DOCKER_IMAGE=runtime
+# These variables will be appended by the runtime_build.py script
+# DOCKER_IMAGE_TAG=
+# DOCKER_IMAGE_SOURCE_TAG=

containers/sandbox/Dockerfile

@@ -1,37 +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 \
-    bash \
-    gcc \
-    jq \
-    g++ \
-    make \
-    iproute2 \
-    libgl1-mesa-glx \
-    && 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
-
-# install basic dependencies for CodeActAgent
-RUN pip3 install --upgrade pip
-RUN pip3 install jupyterlab notebook jupyter_kernel_gateway flake8
-# TODO: those dependencies are needed for agentskills, we should pack them in a new sandbox image
-RUN pip3 install python-docx PyPDF2 python-pptx pylatexenc openai opencv-python

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

dev_config/python/mypy.ini

@@ -7,5 +7,3 @@ warn_unreachable = True
 warn_redundant_casts = True
 no_implicit_optional = True
 strict_optional = True
-
-exclude = agenthub/monologue_agent/regression

dev_config/python/ruff.toml

@@ -1,7 +1,3 @@
-exclude = [
-    "agenthub/monologue_agent/regression/",
-]
-
 [lint]
 select = [
     "E",

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://OpenDevin.github.io",
-  baseUrl: "/OpenDevin/",
+  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",
@@ -23,10 +23,19 @@ const config: Config = {
   // useful metadata like html lang. For example, if your site is Chinese, you
   // may want to replace "en" with "zh-Hans".
   i18n: {
-    defaultLocale: "en",
-    locales: ["en"],
+    defaultLocale: 'en',
+    locales: ['en', 'fr', 'zh-Hans'],
+    localeConfigs: {
+      en: {
+        htmlLang: 'en-GB',
+      },
+    },
   },
 
+  markdown: {
+    mermaid: true,
+  },
+  themes: ['@docusaurus/theme-mermaid'],
   presets: [
     [
       "classic",
@@ -54,9 +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: [
@@ -64,17 +73,25 @@ const config: Config = {
           type: "docSidebar",
           sidebarId: "docsSidebar",
           position: "left",
-          label: "Docs",
+          label: "User Guides",
         },
         {
           type: "docSidebar",
           sidebarId: "apiSidebar",
           position: "left",
-          label: "Codebase",
+          label: "Python API",
         },
-        { to: "/faq", label: "FAQ", position: "left" },
         {
-          href: "https://github.com/OpenDevin/OpenDevin",
+          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",
         },

docs/i18n/fr/code.json

@@ -0,0 +1,406 @@
+{
+  "footer.title": {
+    "message": "OpenHands"
+  },
+  "footer.docs": {
+    "message": "Documents"
+  },
+  "footer.community": {
+    "message": "Communauté"
+  },
+  "footer.copyright": {
+    "message": "© {year} OpenHands"
+  },
+  "faq.title": {
+    "message": "Questions Fréquemment Posées",
+    "description": "FAQ Title"
+  },
+  "faq.description": {
+    "message": "Questions Fréquemment Posées"
+  },
+  "faq.section.title.1": {
+    "message": "Qu'est-ce qu'OpenHands ?",
+    "description": "First Section Title"
+  },
+  "faq.section.highlight": {
+    "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 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, 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",
+    "description": "Support Section Title"
+  },
+  "faq.section.support.answer": {
+    "message": "Si vous rencontrez un problème que d'autres utilisateurs peuvent également avoir, merci de le signaler sur {githubLink}. Si vous avez des difficultés à l'installation ou des questions générales, rejoignez-vous sur {discordLink} ou {slackLink}.",
+    "description": "Support Answer"
+  },
+  "faq.section.title.3": {
+    "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 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/All-Hands-AI/OpenHands/issues/1611",
+    "description": "GitHub Step 1"
+  },
+  "faq.section.github.step2": {
+    "message": "Cloner le dépôt et vérifier une nouvelle branche",
+    "description": "GitHub Step 2"
+  },
+  "faq.section.github.step3": {
+    "message": "Sur la base des instructions dans la description de l'issue, modifiez les fichiers pour résoudre le problème",
+    "description": "GitHub Step 3"
+  },
+  "faq.section.github.step4": {
+    "message": "Pousser le résultat à GitHub en utilisant la variable d'environnement GITHUB_TOKEN",
+    "description": "GitHub Step 4"
+  },
+  "faq.section.github.step5": {
+    "message": "Dites-moi le lien que je dois utiliser pour envoyer une demande de pull",
+    "description": "GitHub Step 5"
+  },
+  "faq.section.github.steps.preRun": {
+    "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 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": {
+    "message": "où USERNAME est votre nom GitHub.",
+    "description": "GitHub Steps Username Info"
+  },
+  "faq.section.title.4": {
+    "message": "Comment OpenHands est-il différent de Devin ?",
+    "description": "Devin Section Title"
+  },
+  "faq.section.openhands.linkText": {
+    "message": "Devin",
+    "description": "Devin Link Text"
+  },
+  "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.openhands.contribute": {
+    "message": "contribuer",
+    "description": "Contribute Link"
+  },
+  "faq.section.title.5": {
+    "message": "Comment OpenHands est-il différent de ChatGPT ?",
+    "description": "ChatGPT Section Title"
+  },
+  "faq.section.chatgpt.description": {
+    "message": "ChatGPT vous pouvez accéder en ligne, il ne se connecte pas aux fichiers locaux et ses capacités d'exécution du code sont limitées. Alors qu'il peut écrire du code, mais c'est difficile à tester ou à exécuter.",
+    "description": "ChatGPT Description"
+  },
+  "homepage.description": {
+    "message": "Génération d'code AI pour l'ingénierie logicielle.",
+    "description": "The homepage description"
+  },
+  "homepage.getStarted": {
+    "message": "Commencer"
+  },
+  "welcome.message": {
+    "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.",
+    "description": "The title of the fallback page when the page crashed"
+  },
+  "theme.BackToTopButton.buttonAriaLabel": {
+    "message": "Retourner en haut de la page",
+    "description": "The ARIA label for the back to top button"
+  },
+  "theme.blog.archive.title": {
+    "message": "Archives",
+    "description": "The page & hero title of the blog archive page"
+  },
+  "theme.blog.archive.description": {
+    "message": "Archives",
+    "description": "The page & hero description of the blog archive page"
+  },
+  "theme.blog.paginator.navAriaLabel": {
+    "message": "Pagination des listes d'articles du blog",
+    "description": "The ARIA label for the blog pagination"
+  },
+  "theme.blog.paginator.newerEntries": {
+    "message": "Nouvelles entrées",
+    "description": "The label used to navigate to the newer blog posts page (previous page)"
+  },
+  "theme.blog.paginator.olderEntries": {
+    "message": "Anciennes entrées",
+    "description": "The label used to navigate to the older blog posts page (next page)"
+  },
+  "theme.blog.post.paginator.navAriaLabel": {
+    "message": "Pagination des articles du blog",
+    "description": "The ARIA label for the blog posts pagination"
+  },
+  "theme.blog.post.paginator.newerPost": {
+    "message": "Article plus récent",
+    "description": "The blog post button label to navigate to the newer/previous post"
+  },
+  "theme.blog.post.paginator.olderPost": {
+    "message": "Article plus ancien",
+    "description": "The blog post button label to navigate to the older/next post"
+  },
+  "theme.blog.post.plurals": {
+    "message": "Un article|{count} articles",
+    "description": "Pluralized label for \"{count} posts\". Use as much plural forms (separated by \"|\") as your language support (see https://www.unicode.org/cldr/cldr-aux/charts/34/supplemental/language_plural_rules.html)"
+  },
+  "theme.blog.tagTitle": {
+    "message": "{nPosts} tags avec « {tagName} »",
+    "description": "The title of the page for a blog tag"
+  },
+  "theme.tags.tagsPageLink": {
+    "message": "Voir tous les tags",
+    "description": "The label of the link targeting the tag list page"
+  },
+  "theme.colorToggle.ariaLabel": {
+    "message": "Basculer entre le mode sombre et clair (actuellement {mode})",
+    "description": "The ARIA label for the navbar color mode toggle"
+  },
+  "theme.colorToggle.ariaLabel.mode.dark": {
+    "message": "mode sombre",
+    "description": "The name for the dark color mode"
+  },
+  "theme.colorToggle.ariaLabel.mode.light": {
+    "message": "mode clair",
+    "description": "The name for the light color mode"
+  },
+  "theme.docs.breadcrumbs.navAriaLabel": {
+    "message": "Bouton de navigation des liens de la page",
+    "description": "The ARIA label for the breadcrumbs"
+  },
+  "theme.docs.DocCard.categoryDescription.plurals": {
+    "message": "1 élément|{count} éléments",
+    "description": "The default description for a category card in the generated index about how many items this category includes"
+  },
+  "theme.docs.paginator.navAriaLabel": {
+    "message": "Pages de documentation",
+    "description": "The ARIA label for the docs pagination"
+  },
+  "theme.docs.paginator.previous": {
+    "message": "Précédent",
+    "description": "The label used to navigate to the previous doc"
+  },
+  "theme.docs.paginator.next": {
+    "message": "Suivant",
+    "description": "The label used to navigate to the next doc"
+  },
+  "theme.docs.tagDocListPageTitle.nDocsTagged": {
+    "message": "Un document tagué|{count} documents tagués",
+    "description": "Pluralized label for \"{count} docs tagged\". Use as much plural forms (separated by \"|\") as your language support (see https://www.unicode.org/cldr/cldr-aux/charts/34/supplemental/language_plural_rules.html)"
+  },
+  "theme.docs.tagDocListPageTitle": {
+    "message": "{nDocsTagged} avec \"{tagName}\"",
+    "description": "The title of the page for a docs tag"
+  },
+  "theme.docs.versionBadge.label": {
+    "message": "Version: {versionLabel}"
+  },
+  "theme.docs.versions.unreleasedVersionLabel": {
+    "message": "Ceci est la documentation de la prochaine version {versionLabel} de {siteTitle}.",
+    "description": "The label used to tell the user that he's browsing an unreleased doc version"
+  },
+  "theme.docs.versions.unmaintainedVersionLabel": {
+    "message": "Ceci est la documentation de {siteTitle} {versionLabel}, qui n'est plus activement maintenue.",
+    "description": "The label used to tell the user that he's browsing an unmaintained doc version"
+  },
+  "theme.docs.versions.latestVersionSuggestionLabel": {
+    "message": "Pour une documentation à jour, consultez la {latestVersionLink} ({versionLabel}).",
+    "description": "The label used to tell the user to check the latest version"
+  },
+  "theme.docs.versions.latestVersionLinkLabel": {
+    "message": "dernière version",
+    "description": "The label used for the latest version suggestion link label"
+  },
+  "theme.common.editThisPage": {
+    "message": "Éditer cette page",
+    "description": "The link label to edit the current page"
+  },
+  "theme.common.headingLinkTitle": {
+    "message": "Lien direct vers {heading}",
+    "description": "Title for link to heading"
+  },
+  "theme.lastUpdated.atDate": {
+    "message": " le {date}",
+    "description": "The words used to describe on which date a page has been last updated"
+  },
+  "theme.lastUpdated.byUser": {
+    "message": " par {user}",
+    "description": "The words used to describe by who the page has been last updated"
+  },
+  "theme.lastUpdated.lastUpdatedAtBy": {
+    "message": "Dernière mise à jour{atDate}{byUser}",
+    "description": "The sentence used to display when a page has been last updated, and by who"
+  },
+  "theme.navbar.mobileVersionsDropdown.label": {
+    "message": "Versions",
+    "description": "The label for the navbar versions dropdown on mobile view"
+  },
+  "theme.NotFound.title": {
+    "message": "Page introuvable",
+    "description": "The title of the 404 page"
+  },
+  "theme.tags.tagsListLabel": {
+    "message": "Tags :",
+    "description": "The label alongside a tag list"
+  },
+  "theme.admonition.caution": {
+    "message": "prudence",
+    "description": "The default label used for the Caution admonition (:::caution)"
+  },
+  "theme.admonition.danger": {
+    "message": "danger",
+    "description": "The default label used for the Danger admonition (:::danger)"
+  },
+  "theme.admonition.info": {
+    "message": "information",
+    "description": "The default label used for the Info admonition (:::info)"
+  },
+  "theme.admonition.note": {
+    "message": "remarque",
+    "description": "The default label used for the Note admonition (:::note)"
+  },
+  "theme.admonition.tip": {
+    "message": "astuce",
+    "description": "The default label used for the Tip admonition (:::tip)"
+  },
+  "theme.admonition.warning": {
+    "message": "prudence",
+    "description": "The default label used for the Warning admonition (:::warning)"
+  },
+  "theme.AnnouncementBar.closeButtonAriaLabel": {
+    "message": "Fermer",
+    "description": "The ARIA label for close button of announcement bar"
+  },
+  "theme.blog.sidebar.navAriaLabel": {
+    "message": "Navigation vers les articles récents du blog",
+    "description": "The ARIA label for recent posts in the blog sidebar"
+  },
+  "theme.CodeBlock.copied": {
+    "message": "Copié",
+    "description": "The copied button label on code blocks"
+  },
+  "theme.CodeBlock.copyButtonAriaLabel": {
+    "message": "Copier le code",
+    "description": "The ARIA label for copy code blocks button"
+  },
+  "theme.CodeBlock.copy": {
+    "message": "Copier",
+    "description": "The copy button label on code blocks"
+  },
+  "theme.CodeBlock.wordWrapToggle": {
+    "message": "Activer/désactiver le retour à la ligne",
+    "description": "The title attribute for toggle word wrapping button of code block lines"
+  },
+  "theme.DocSidebarItem.expandCategoryAriaLabel": {
+    "message": "Développer la catégorie '{label}' de la barre latérale",
+    "description": "The ARIA label to expand the sidebar category"
+  },
+  "theme.DocSidebarItem.collapseCategoryAriaLabel": {
+    "message": "Réduire la catégorie '{label}' de la barre latérale",
+    "description": "The ARIA label to collapse the sidebar category"
+  },
+  "theme.NavBar.navAriaLabel": {
+    "message": "Main",
+    "description": "The ARIA label for the main navigation"
+  },
+  "theme.navbar.mobileLanguageDropdown.label": {
+    "message": "Langues",
+    "description": "The label for the mobile language switcher dropdown"
+  },
+  "theme.NotFound.p1": {
+    "message": "Nous n'avons pas trouvé ce que vous recherchez.",
+    "description": "The first paragraph of the 404 page"
+  },
+  "theme.NotFound.p2": {
+    "message": "Veuillez contacter le propriétaire du site qui vous a lié à l'URL d'origine et leur faire savoir que leur lien est cassé.",
+    "description": "The 2nd paragraph of the 404 page"
+  },
+  "theme.TOCCollapsible.toggleButtonLabel": {
+    "message": "Sur cette page",
+    "description": "The label used by the button on the collapsible TOC component"
+  },
+  "theme.blog.post.readMore": {
+    "message": "Lire plus",
+    "description": "The label used in blog post item excerpts to link to full blog posts"
+  },
+  "theme.blog.post.readMoreLabel": {
+    "message": "En savoir plus sur {title}",
+    "description": "The ARIA label for the link to full blog posts from excerpts"
+  },
+  "theme.blog.post.readingTime.plurals": {
+    "message": "Une minute de lecture|{readingTime} minutes de lecture",
+    "description": "Pluralized label for \"{readingTime} min read\". Use as much plural forms (separated by \"|\") as your language support (see https://www.unicode.org/cldr/cldr-aux/charts/34/supplemental/language_plural_rules.html)"
+  },
+  "theme.docs.breadcrumbs.home": {
+    "message": "Page d'accueil",
+    "description": "The ARIA label for the home page in the breadcrumbs"
+  },
+  "theme.docs.sidebar.collapseButtonTitle": {
+    "message": "Réduire le menu latéral",
+    "description": "The title attribute for collapse button of doc sidebar"
+  },
+  "theme.docs.sidebar.collapseButtonAriaLabel": {
+    "message": "Réduire le menu latérale",
+    "description": "The title attribute for collapse button of doc sidebar"
+  },
+  "theme.docs.sidebar.navAriaLabel": {
+    "message": "Barre de navigation latérale des docs",
+    "description": "The ARIA label for the sidebar navigation"
+  },
+  "theme.docs.sidebar.closeSidebarButtonAriaLabel": {
+    "message": "Fermer la barre de navigation",
+    "description": "The ARIA label for close button of mobile sidebar"
+  },
+  "theme.navbar.mobileSidebarSecondaryMenu.backButtonLabel": {
+    "message": "← Retour au menu principal",
+    "description": "The label of the back button to return to main menu, inside the mobile navbar sidebar secondary menu (notably used to display the docs sidebar)"
+  },
+  "theme.docs.sidebar.toggleSidebarButtonAriaLabel": {
+    "message": "Ouvrir/fermer la barre de navigation",
+    "description": "The ARIA label for hamburger menu button of mobile navigation"
+  },
+  "theme.docs.sidebar.expandButtonTitle": {
+    "message": "Déplier le menu latéral",
+    "description": "The ARIA label and title attribute for expand button of doc sidebar"
+  },
+  "theme.docs.sidebar.expandButtonAriaLabel": {
+    "message": "Déployer le menu latérale",
+    "description": "The ARIA label and title attribute for expand button of doc sidebar"
+  },
+  "theme.ErrorPageContent.tryAgain": {
+    "message": "Réessayer",
+    "description": "The label of the button to try again rendering when the React error boundary captures an error"
+  },
+  "theme.common.skipToMainContent": {
+    "message": "Aller directement au contenu principal",
+    "description": "The skip to content label used for accessibility, allowing to rapidly navigate to main content with keyboard tab/enter navigation"
+  },
+  "theme.tags.tagsPageTitle": {
+    "message": "Tags",
+    "description": "The title of the tag list page"
+  },
+  "theme.unlistedContent.title": {
+    "message": "Page non répertoriée",
+    "description": "The unlisted content banner title"
+  },
+  "theme.unlistedContent.message": {
+    "message": "Cette page n'est pas répertoriée. Les moteurs de recherche ne l'indexeront pas, et seuls les utilisateurs ayant un lien direct peuvent y accéder.",
+    "description": "The unlisted content banner message"
+  }
+}

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

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

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

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

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

@@ -0,0 +1,5 @@
+
+
+# Documentation Python
+
+La documentation apparaîtra ici après le déploiement.

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

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

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

@@ -0,0 +1,49 @@
+# 📚 Divers
+
+## ⭐️ Stratégie de recherche
+
+La réplication complète d'applications de niveau production avec des LLM est une entreprise complexe. Notre stratégie implique :
+
+1. **Recherche technique fondamentale :** Se concentrer sur la recherche fondamentale pour comprendre et améliorer les aspects techniques de la génération et de la gestion de code
+2. **Capacités spécialisées :** Améliorer l'efficacité des composants de base grâce à la curation de données, aux méthodes d'entraînement, etc.
+3. **Planification des tâches :** Développer des capacités de détection de bugs, de gestion de base de code et d'optimisation
+4. **Évaluation :** Établir des métriques d'évaluation complètes pour mieux comprendre et améliorer nos modèles
+
+## 🚧 Agent par défaut
+
+Notre Agent par défaut est actuellement le [CodeActAgent](agents), qui est capable de générer du code et de gérer des fichiers.
+
+## 🤝 Comment contribuer
+
+OpenHands est un projet communautaire et nous accueillons les contributions de tous. 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 s'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 dans l'ingénierie logicielle, participez à l'évaluation des modèles ou suggérez des améliorations
+- **Retours et tests :** Utilisez la boîte à outils OpenHands, signalez des bugs, suggérez des fonctionnalités ou donnez votre avis sur la facilité d'utilisation
+
+Pour plus de détails, veuillez consulter [ce document](https://github.com/All-Hands-AI/OpenHands/blob/main/CONTRIBUTING.md).
+
+## 🤖 Rejoignez notre communauté
+
+Nous avons 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, LLM, agent, etc.
+
+- [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 ensemble l'ingénierie logicielle !
+
+🐚 **Codez moins, faites plus avec OpenHands.**
+
+[![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
+
+OpenHands est construit en utilisant une combinaison de frameworks et de bibliothèques puissants, fournissant une base solide pour son développement. Voici les principales technologies 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 technologies existantes peuvent être supprimées à mesure que le projet évolue. Nous nous efforçons d'adopter les outils les plus appropriés et les plus efficaces pour améliorer les capacités d'OpenHands.
+
+## 📜 Licence
+
+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

@@ -0,0 +1,25 @@
+
+
+# 🧠 Agent Principal et Capacités
+
+## CodeActAgent
+
+### Description
+
+Cet agent implémente l'idée de CodeAct ([article](https://arxiv.org/abs/2402.01030), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) qui consolide les **act**ions des agents LLM dans un espace d'action de **code** unifié à la fois pour la _simplicité_ et la _performance_.
+
+L'idée conceptuelle est illustrée ci-dessous. À chaque tour, l'agent peut :
+
+1. **Converser** : Communiquer avec les humains en langage naturel pour demander des clarifications, des confirmations, etc.
+2. **CodeAct** : Choisir d'effectuer la tâche en exécutant du code
+
+- Exécuter n'importe quelle commande Linux `bash` valide
+- Exécuter n'importe quel code `Python` valide avec [un interpréteur Python interactif](https://ipython.org/). Ceci est simulé via une commande `bash`, voir le système de plugin ci-dessous pour plus de détails.
+
+![image](https://github.com/All-Hands-AI/OpenHands/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
+
+### Démo
+
+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

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

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

@@ -0,0 +1,54 @@
+
+
+# 🏛️ Architecture du Système
+
+<div style={{ textAlign: 'center' }}>
+  <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>Diagramme de l'Architecture du Système OpenHands (4 juillet 2024)</em></p>
+</div>
+
+Ceci est une vue d'ensemble de haut niveau de l'architecture du système. Le système est divisé en deux composants principaux : le frontend et le backend. Le frontend est responsable de la gestion des interactions utilisateur et de l'affichage des résultats. Le backend est responsable de la gestion de la logique métier et de l'exécution des agents.
+
+# Architecture du Frontend {#frontend-architecture-fr}
+
+![system_architecture.svg](/img/system_architecture.svg)
+
+Cette vue d'ensemble est simplifiée pour montrer les principaux composants et leurs interactions. Pour une vue plus détaillée de l'architecture du backend, voir la section Architecture du Backend ci-dessous.
+
+# Architecture du Backend {#backend-architecture-fr}
+
+_**Avertissement** : L'architecture du backend est en cours de développement et est sujette à changement. Le diagramme suivant montre l'architecture actuelle du backend basée sur le commit indiqué dans le pied de page du diagramme._
+
+![backend_architecture.svg](/img/backend_architecture.svg)
+
+<details>
+  <summary>Mise à jour de ce Diagramme</summary>
+  <div>
+    La génération du diagramme d'architecture du backend est partiellement automatisée.
+    Le diagramme est généré à partir des indications de type dans le code en utilisant l'outil py2puml. Le diagramme est ensuite manuellement revu, ajusté et exporté en PNG et SVG.
+
+    ## Prérequis
+
+    - Environnement python fonctionnel 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.  Générer automatiquement le diagramme en exécutant la commande suivante depuis la racine du dépôt :
+    `py2puml openhands openhands > docs/architecture/backend_architecture.puml`
+
+2.  Ouvrir le fichier généré dans un éditeur PlantUML, par ex. Visual Studio Code avec l'extension PlantUML ou [PlantText](https://www.planttext.com/)
+
+3.  Revoir le PUML généré et effectuer tous les ajustements nécessaires au diagramme (ajouter les parties manquantes, corriger les erreurs, améliorer le positionnement).
+    _py2puml crée le diagramme en se basant sur les indications de type dans le code, donc des indications manquantes ou incorrectes peuvent entraîner un diagramme incomplet ou incorrect._
+
+4.  Revoir la différence entre le nouveau diagramme et le précédent et vérifier manuellement si les changements sont corrects.
+    _S'assurer de ne pas supprimer des parties qui ont été ajoutées manuellement au diagramme par le passé et qui sont toujours pertinentes._
+
+5.  Ajouter le hash du commit qui a été utilisé pour générer le diagramme dans le pied de page du diagramme.
+
+6.  Exporter le diagramme sous forme de fichiers PNG et SVG et remplacer les diagrammes existants dans le répertoire `docs/architecture`. Cela peut être fait avec (par ex. [PlantText](https://www.planttext.com/))
+
+  </div>
+</details>

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

@@ -0,0 +1,138 @@
+
+
+# 📦 Runtime EventStream
+
+Le Runtime EventStream d'OpenHands est le composant principal qui permet l'exécution sécurisée et flexible des actions des agents d'IA.
+Il crée un environnement en bac à sable (sandbox) en utilisant Docker, où du code arbitraire peut être exécuté en toute sécurité sans risquer le système hôte.
+
+## Pourquoi avons-nous besoin d'un runtime en bac à sable ?
+
+OpenHands doit exécuter du code arbitraire dans un environnement sécurisé et isolé pour plusieurs raisons :
+
+1. Sécurité : L'exécution de code non fiable peut poser des risques importants pour le système hôte. Un environnement en bac à sable empêche le code malveillant d'accéder ou de modifier les ressources du système hôte
+2. Cohérence : Un environnement en bac à sable garantit que l'exécution du code est cohérente sur différentes machines et configurations, éliminant les problèmes du type "ça fonctionne sur ma machine"
+3. Contrôle des ressources : Le bac à sable permet un meilleur contrôle de l'allocation et de l'utilisation des ressources, empêchant les processus incontrôlés d'affecter le système hôte
+4. Isolation : Différents projets ou utilisateurs peuvent travailler dans des environnements isolés sans interférer les uns avec les autres ou avec le système hôte
+5. Reproductibilité : Les environnements en bac à sable facilitent la reproduction des bugs et des problèmes, car l'environnement d'exécution est cohérent et contrôlable
+
+## Comment fonctionne le Runtime ?
+
+Le système Runtime d'OpenHands utilise une architecture client-serveur implémentée avec des conteneurs Docker. Voici un aperçu de son fonctionnement :
+
+```mermaid
+graph TD
+    A[Image Docker personnalisée fournie par l'utilisateur] --> B[Backend OpenHands]
+    B -->|Construit| C[Image OH Runtime]
+    C -->|Lance| D[Exécuteur d'actions]
+    D -->|Initialise| E[Navigateur]
+    D -->|Initialise| F[Shell Bash]
+    D -->|Initialise| G[Plugins]
+    G -->|Initialise| L[Serveur Jupyter]
+
+    B -->|Génère| H[Agent]
+    B -->|Génère| I[EventStream]
+    I <--->|Exécute l'action pour
+    obtenir l'observation
+    via l'API REST
+    | D
+
+    H -->|Génère l'action| I
+    I -->|Obtient l'observation| H
+
+    subgraph "Conteneur Docker"
+    D
+    E
+    F
+    G
+    L
+    end
+```
+
+1. Entrée utilisateur : L'utilisateur fournit une image Docker de base personnalisée
+2. Construction de l'image : OpenHands construit une nouvelle image Docker (l'"image OH runtime") basée sur l'image fournie par l'utilisateur. Cette nouvelle image inclut le code spécifique à OpenHands, principalement le "client runtime"
+3. Lancement du conteneur : Lorsqu'OpenHands démarre, il lance un conteneur Docker en utilisant l'image OH runtime
+4. Initialisation du serveur d'exécution des actions : Le serveur d'exécution des actions initialise un `ActionExecutor` à l'intérieur du conteneur, mettant en place les composants nécessaires comme un shell bash et chargeant les plugins spécifiés
+5. Communication : Le backend OpenHands (`openhands/runtime/impl/eventstream/eventstream_runtime.py`) communique avec le serveur d'exécution des actions via une API RESTful, envoyant des actions et recevant des observations
+6. Exécution des actions : Le client runtime reçoit les actions du backend, les exécute dans l'environnement en bac à sable et renvoie les observations
+7. Retour des observations : Le serveur d'exécution des actions renvoie les résultats d'exécution au backend OpenHands sous forme d'observations
+
+
+Le rôle du client :
+- Il agit comme un intermédiaire entre le backend OpenHands et l'environnement en bac à sable
+- Il exécute différents types d'actions (commandes shell, opérations sur les fichiers, code Python, etc.) en toute sécurité dans le conteneur
+- Il gère l'état de l'environnement en bac à sable, y compris le répertoire de travail courant et les plugins chargés
+- Il formate et renvoie les observations au backend, assurant une interface cohérente pour le traitement des résultats
+
+
+## Comment OpenHands construit et maintient les images OH Runtime
+
+L'approche d'OpenHands pour la construction et la gestion des images runtime assure l'efficacité, la cohérence et la flexibilité dans la création et la maintenance des images Docker pour les environnements de production et de développement.
+
+Consultez le [code pertinent](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/utils/runtime_build.py) si vous souhaitez plus de détails.
+
+### Système de balises d'images
+
+OpenHands utilise un système à trois balises pour ses images runtime afin d'équilibrer la reproductibilité et la flexibilité.
+Les balises peuvent être dans l'un des 2 formats suivants :
+
+- **Balise versionnée** : `oh_v{openhands_version}_{base_image}` (ex : `oh_v0.9.9_nikolaik_s_python-nodejs_t_python3.12-nodejs22`)
+- **Balise de verrouillage** : `oh_v{openhands_version}_{16_digit_lock_hash}` (ex : `oh_v0.9.9_1234567890abcdef`)
+- **Balise source** : `oh_v{openhands_version}_{16_digit_lock_hash}_{16_digit_source_hash}`
+  (ex : `oh_v0.9.9_1234567890abcdef_1234567890abcdef`)
+
+
+#### Balise source - La plus spécifique
+
+Il s'agit des 16 premiers chiffres du MD5 du hash du répertoire pour le répertoire source. Cela donne un hash
+uniquement pour la source d'openhands
+
+
+#### Balise de verrouillage
+
+Ce hash est construit à partir des 16 premiers chiffres du MD5 de :
+- Le nom de l'image de base sur laquelle l'image a été construite (ex : `nikolaik/python-nodejs:python3.12-nodejs22`)
+- Le contenu du `pyproject.toml` inclus dans l'image.
+- Le contenu du `poetry.lock` inclus dans l'image.
+
+Cela donne effectivement un hash pour les dépendances d'Openhands indépendamment du code source.
+
+#### Balise versionnée - La plus générique
+
+Cette balise est une concaténation de la version d'openhands et du nom de l'image de base (transformé pour s'adapter au standard des balises).
+
+#### Processus de construction
+
+Lors de la génération d'une image...
+
+- **Pas de reconstruction** : OpenHands vérifie d'abord si une image avec la même **balise source la plus spécifique** existe. S'il existe une telle image,
+  aucune construction n'est effectuée - l'image existante est utilisée.
+- **Reconstruction la plus rapide** : OpenHands vérifie ensuite si une image avec la **balise de verrouillage générique** existe. S'il existe une telle image,
+  OpenHands construit une nouvelle image basée sur celle-ci, en contournant toutes les étapes d'installation (comme `poetry install` et
+  `apt-get`) sauf une opération finale pour copier le code source actuel. La nouvelle image est balisée avec une
+  balise **source** uniquement.
+- **Reconstruction correcte** : Si ni une balise **source** ni une balise **de verrouillage** n'existe, une image sera construite sur la base de l'image avec la balise **versionnée**.
+  Dans l'image avec la balise versionnée, la plupart des dépendances devraient déjà être installées, ce qui permet de gagner du temps.
+- **Reconstruction la plus lente** : Si les trois balises n'existent pas, une toute nouvelle image est construite à partir de
+  l'image de base (ce qui est une opération plus lente). Cette nouvelle image est balisée avec toutes les balises **source**, **de verrouillage** et **versionnée**.
+
+Cette approche de balisage permet à OpenHands de gérer efficacement les environnements de développement et de production.
+
+1. Un code source et un Dockerfile identiques produisent toujours la même image (via des balises basées sur des hashs)
+2. Le système peut reconstruire rapidement les images lorsque des changements mineurs se produisent (en s'appuyant sur des images compatibles récentes)
+3. La balise **de verrouillage** (ex : `runtime:oh_v0.9.3_1234567890abcdef`) pointe toujours vers la dernière version pour une combinaison particulière d'image de base, de dépendances et de version d'OpenHands
+
+## Système de plugins du Runtime
+
+Le Runtime d'OpenHands prend en charge un système de plugins qui permet d'étendre les fonctionnalités et de personnaliser l'environnement d'exécution. Les plugins sont initialisés lorsque le client runtime démarre.
+
+Consultez [un exemple de plugin Jupyter ici](https://github.com/All-Hands-AI/OpenHands/blob/ecf4aed28b0cf7c18d4d8ff554883ba182fc6bdd/openhands/runtime/plugins/jupyter/__init__.py#L21-L55) si vous souhaitez implémenter votre propre plugin.
+
+*Plus de détails sur le système de plugins sont encore en construction - les contributions sont les bienvenues !*
+
+Aspects clés du système de plugins :
+
+1. Définition des plugins : Les plugins sont définis comme des classes Python qui héritent d'une classe de base `Plugin`
+2. Enregistrement des plugins : Les plugins disponibles sont enregistrés dans un dictionnaire `ALL_PLUGINS`
+3. Spécification des plugins : Les plugins sont associés à `Agent.sandbox_plugins: list[PluginRequirement]`. Les utilisateurs peuvent spécifier quels plugins charger lors de l'initialisation du runtime
+4. Initialisation : Les plugins sont initialisés de manière asynchrone lorsque le client runtime démarre
+5. Utilisation : Le client runtime peut utiliser les plugins initialisés pour étendre ses capacités (par exemple, le JupyterPlugin pour exécuter des cellules IPython)

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

@@ -0,0 +1,101 @@
+# 💿 Comment Créer un Soutien Docker sur Mesure
+
+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 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 OpenHands ait accès au "node" binaire, nous utiliserions ce Dockerfile:
+
+```bash
+# Commencez avec l'image ubuntu la plus récente
+FROM ubuntu:latest
+
+# Effectuez les mises à jour nécessaires
+RUN apt-get update && apt-get install
+
+# Installez nodejs
+RUN apt-get install -y nodejs
+```
+
+Ensuite, construisez votre image docker avec le nom de votre choix. Par exemple "image_personnalisée". Pour cela, créez un répertoire et placez le fichier à l'intérieur avec le nom "Dockerfile", puis dans le répertoire exécutez cette commande:
+
+```bash
+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, 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 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"
+run_as_openhands=true
+sandbox_base_container_image="image_personnalisée"
+```
+
+> Assurez-vous que ```sandbox_base_container_image``` est défini sur le nom de votre image personnalisée précédente.
+
+## Exécution
+
+Exécutez OpenHands en exécutant ```make run``` dans le répertoire racine.
+
+Naviguez vers ```localhost:3001``` et vérifiez si vos dépendances souhaitées sont disponibles.
+
+Dans le cas de l'exemple ci-dessus, la commande ```node -v``` dans la console produit ```v18.19.1```
+
+Félicitations !
+
+## Explication technique
+
+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/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 /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 /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/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 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"
+run_as_openhands=true
+sandbox_base_container_image="image_personnalisée"
+sandbox_user_id="1001"
+```
+
+### Erreurs de port d'utilisation
+
+Si vous voyez un message d'erreur indiquant que le port est utilisé ou indisponible, essayez de supprimer toutes les containers docker en cours d'exécution (exécutez `docker ps` et `docker rm` des containers concernés) puis ré-exécutez ```make run```
+
+## Discuter
+
+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

@@ -0,0 +1,41 @@
+
+
+# ✅ Fournir des commentaires
+
+Lorsque vous utilisez OpenHands, vous rencontrerez 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 à donner des retours à l'équipe de développement, et peut-être plus important encore, créer un corpus ouvert d'exemples d'entraînement d'agents de codage -- Share-OpenHands !
+
+## 📝 Comment fournir des commentaires
+
+Fournir des commentaires est facile ! Lorsque vous utilisez OpenHands, vous pouvez appuyer sur le bouton pouce vers le haut ou pouce vers le bas à tout moment pendant votre interaction. Vous serez invité à fournir votre adresse e-mail (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="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>
+
+## 📜 Utilisation des données et confidentialité
+
+### Paramètres de partage des données
+
+Lorsque vous soumettez des données, vous pouvez les soumettre publiquement ou en privé.
+
+* Les données **publiques** seront distribuées sous la licence MIT, comme OpenHands lui-même, et pourront être utilisées par la communauté pour entraîner 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.
+
+### Qui collecte et stocke les données ?
+
+Les données sont collectées et stockées par [All Hands AI](https://all-hands.dev), une entreprise fondée par les mainteneurs d'OpenHands pour soutenir et améliorer OpenHands.
+
+### Comment les données publiques seront-elles publiées ?
+
+Les données publiques seront publiées lorsque nous atteindrons des jalons fixes, tels que 1 000 exemples publics, 10 000 exemples publics, etc.
+À ce moment-là, nous suivrons le processus de publication suivant :
+
+1. Toutes les personnes qui ont contribué à des commentaires publics recevront un e-mail décrivant la publication des données et auront la possibilité de se retirer.
+2. La ou les personnes en charge de la publication des données effectueront un contrôle de la qualité des données, en supprimant les commentaires de mauvaise qualité, en supprimant les adresses e-mail des soumissionnaires et en essayant de supprimer toute information sensible.
+3. Les données seront publiées publiquement sous la licence MIT via des sites couramment utilisés tels que GitHub ou Hugging Face.
+
+### Que faire si je veux que mes données soient supprimées ?
+
+Pour les données sur les serveurs d'All Hands AI, nous sommes heureux de les supprimer sur demande :
+
+**Une pièce de données :** Si vous souhaitez supprimer une pièce de données, nous ajouterons prochainement un mécanisme pour supprimer les pièces de données en utilisant le lien et le mot de passe qui s'affichent sur l'interface lorsque vous soumettez des données.
+
+**Toutes les données :** Si vous souhaitez que toutes vos données soient supprimées, ou si vous n'avez pas l'ID et le mot de passe que vous avez reçus lors de la soumission des données, veuillez contacter `contact@all-hands.dev` à partir de l'adresse e-mail que vous avez enregistrée lorsque vous avez initialement soumis les données.

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

@@ -0,0 +1,113 @@
+
+
+# Démarrer avec OpenHands
+
+Vous avez donc [installé OpenHands](./installation) et avez
+[configuré votre LLM](./installation#setup). Et maintenant ?
+
+OpenHands peut vous aider à vous attaquer à une grande variété de tâches d'ingénierie. Mais la technologie
+est encore nouvelle, et nous sommes loin d'avoir des agents capables de prendre en charge des tâches
+d'ingénierie vastes et compliquées sans aucune aide. Il est donc important de se faire une idée de ce que l'agent
+fait bien, et où il pourrait avoir besoin d'un coup de main.
+
+## Hello World
+
+La première chose que vous voudrez peut-être essayer est un simple exemple "hello world".
+Cela peut être plus compliqué qu'il n'y paraît !
+
+Essayez de demander à l'agent :
+> Please write a bash script hello.sh that prints "hello world!"
+
+Vous devriez constater que l'agent non seulement écrit le script, mais définit également les
+permissions correctes et exécute le script pour vérifier la sortie.
+
+Vous pouvez continuer à demander à l'agent d'affiner votre code. C'est une excellente façon de
+travailler avec les agents. Commencez simplement, et itérez.
+
+> Please modify hello.sh so that it accepts a name as the first argument, but defaults to "world"
+
+Vous pouvez également travailler dans n'importe quel langage dont vous avez besoin, bien que l'agent puisse avoir besoin de passer un peu de
+temps à configurer son environnement !
+
+> Please convert hello.sh to a Ruby script, and run it
+
+## Construire à partir de zéro
+
+Les agents se débrouillent exceptionnellement bien pour les tâches "greenfield" (tâches où ils n'ont pas besoin
+de contexte sur une base de code existante) et ils peuvent simplement commencer à partir de zéro.
+
+Il est préférable de commencer par une tâche simple, puis d'itérer. Il est également préférable d'être
+aussi précis que possible sur ce que vous voulez, sur la pile technologique à utiliser, etc.
+
+Par exemple, nous pourrions construire une application TODO :
+
+> Please build a basic TODO list app in React. It should be frontend-only, and all state
+> should be kept in localStorage.
+
+Nous pouvons continuer à itérer sur l'application une fois le squelette en place :
+
+> Please allow adding an optional due date to every task
+
+Tout comme avec le développement normal, il est bon de commiter et de pousser votre code fréquemment.
+De cette façon, vous pouvez toujours revenir à un ancien état si l'agent dévie.
+Vous pouvez demander à l'agent de commiter et de pousser pour vous :
+
+> Please commit the changes and push them to a new branch called "feature/due-dates"
+
+
+## Ajouter du nouveau code
+
+OpenHands peut également faire un excellent travail en ajoutant du nouveau code à une base de code existante.
+
+Par exemple, vous pouvez demander à OpenHands d'ajouter une nouvelle action GitHub à votre projet
+qui analyse votre code. OpenHands peut jeter un coup d'œil à votre base de code pour voir quel langage
+il doit utiliser, mais ensuite il peut simplement déposer un nouveau fichier dans `./github/workflows/lint.yml`.
+
+> Please add a GitHub action that lints the code in this repository
+
+Certaines tâches peuvent nécessiter un peu plus de contexte. Bien qu'OpenHands puisse utiliser `ls` et `grep`
+pour rechercher dans votre base de code, fournir le contexte à l'avance lui permet d'aller plus vite,
+et plus précisément. Et cela vous coûtera moins de 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 est excellent pour refactoriser du code existant, surtout par petits morceaux.
+Vous ne voulez probablement pas essayer de réarchitecturer toute votre base de code, mais diviser
+les longs fichiers et fonctions, renommer les variables, etc. ont tendance à très bien fonctionner.
+
+> 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
+
+## Corrections de bugs
+
+OpenHands peut également vous aider à traquer et corriger des bugs dans votre code. Mais, comme tout
+développeur le sait, la correction de bugs peut être extrêmement délicate, et souvent OpenHands aura besoin de plus de contexte.
+Cela aide si vous avez diagnostiqué le bug, mais que vous voulez qu'OpenHands trouve la logique.
+
+> 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.
+
+Il est souvent utile de faire du développement piloté par les tests lors de la correction de bugs avec un agent.
+Vous pouvez demander à l'agent d'écrire un nouveau test, puis d'itérer jusqu'à ce qu'il corrige le bug :
+
+> The `hello` function crashes on the empty string. Please write a test that reproduces this bug, then fix the code so it passes.
+
+## Plus
+
+OpenHands est capable d'aider sur à peu près n'importe quelle tâche de codage. Mais il faut un peu de pratique
+pour en tirer le meilleur parti. N'oubliez pas de :
+* Garder vos tâches petites
+* Être aussi précis que possible
+* Fournir autant de contexte que possible
+* Commiter et pousser fréquemment
+
+Voir [Bonnes pratiques de prompting](./prompting-best-practices) pour plus de conseils sur la façon de tirer le meilleur parti d'OpenHands.

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -0,0 +1,110 @@
+
+
+# Mode CLI
+
+OpenHands peut être exécuté en mode CLI interactif, ce qui permet aux utilisateurs de démarrer une session interactive via la ligne de commande.
+
+Ce mode est différent du [mode headless](headless-mode), qui est non interactif et mieux adapté aux scripts.
+
+## Avec Python
+
+Pour démarrer une session OpenHands interactive via la ligne de commande, suivez ces étapes :
+
+1. Assurez-vous d'avoir suivi les [instructions de configuration de développement](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
+
+2. Exécutez la commande suivante :
+
+```bash
+poetry run python -m openhands.core.cli
+```
+
+Cette commande démarrera une session interactive où vous pourrez saisir des tâches et recevoir des réponses d'OpenHands.
+
+Vous devrez vous assurer de définir votre modèle, votre clé API et d'autres paramètres via des variables d'environnement
+[ou le fichier `config.toml`](https://github.com/All-Hands-AI/OpenHands/blob/main/config.template.toml).
+
+
+## Avec Docker
+
+Pour exécuter OpenHands en mode CLI avec Docker, suivez ces étapes :
+
+1. Définissez `WORKSPACE_BASE` sur le répertoire que vous souhaitez qu'OpenHands modifie :
+
+```bash
+WORKSPACE_BASE=$(pwd)/workspace
+```
+
+2. Définissez `LLM_MODEL` sur le modèle que vous souhaitez utiliser :
+
+```bash
+LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"
+```
+
+3. Définissez `LLM_API_KEY` sur votre clé API :
+
+```bash
+LLM_API_KEY="sk_test_12345"
+```
+
+4. Exécutez la commande Docker suivante :
+
+```bash
+docker run -it \
+    --pull=always \
+    -e SANDBOX_USER_ID=$(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
+```
+
+Cette commande démarrera une session interactive dans Docker où vous pourrez saisir des tâches et recevoir des réponses d'OpenHands.
+
+## Exemples de commandes CLI et de sorties attendues
+
+Voici quelques exemples de commandes CLI et leurs sorties attendues :
+
+### Exemple 1 : Tâche simple
+
+```bash
+Comment puis-je vous aider ? >> Écrivez un script Python qui affiche "Hello, World!"
+```
+
+Sortie attendue :
+
+```bash
+🤖 Bien sûr ! Voici un script Python qui affiche "Hello, World!" :
+
+❯ print("Hello, World!")
+```
+
+### Exemple 2 : Commande Bash
+
+```bash
+Comment puis-je vous aider ? >> Créez un répertoire nommé "test_dir"
+```
+
+Sortie attendue :
+
+```bash
+🤖 Création d'un répertoire nommé "test_dir" :
+
+❯ mkdir test_dir
+```
+
+### Exemple 3 : Gestion des erreurs
+
+```bash
+Comment puis-je vous aider ? >> Supprimez un fichier inexistant
+```
+
+Sortie attendue :
+
+```bash
+🤖 Une erreur s'est produite. Veuillez réessayer.
+```

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/custom-sandbox-guide.md

@@ -0,0 +1,83 @@
+
+
+# Sandbox Personnalisé
+
+Le sandbox est l'endroit où l'agent effectue ses tâches. Au lieu d'exécuter des commandes directement sur votre ordinateur (ce qui pourrait être risqué), l'agent les exécute à l'intérieur d'un conteneur Docker.
+
+Le sandbox OpenHands par défaut (`python-nodejs:python3.12-nodejs22` de [nikolaik/python-nodejs](https://hub.docker.com/r/nikolaik/python-nodejs)) est livré avec certains paquets installés tels que Python et Node.js, mais peut nécessiter l'installation d'autres logiciels par défaut.
+
+Vous avez deux options pour la personnalisation :
+
+1. Utiliser une image existante avec les logiciels requis.
+2. Créer votre propre image Docker personnalisée.
+
+Si vous choisissez la première option, vous pouvez passer la section `Créer Votre Image Docker`.
+
+## Créer Votre Image Docker
+
+Pour créer une image Docker personnalisée, elle doit être basée sur Debian.
+
+Par exemple, si vous voulez qu'OpenHands ait `ruby` installé, créez un `Dockerfile` avec le contenu suivant :
+
+```dockerfile
+FROM debian:latest
+
+# Installer les paquets requis
+RUN apt-get update && apt-get install -y ruby
+```
+
+Enregistrez ce fichier dans un dossier. Ensuite, construisez votre image Docker (par exemple, nommée custom-image) en naviguant vers le dossier dans le terminal et en exécutant :
+
+```bash
+docker build -t custom-image .
+```
+
+Cela produira une nouvelle image appelée `custom-image`, qui sera disponible dans Docker.
+
+> Notez que dans la configuration décrite dans ce document, OpenHands s'exécutera en tant qu'utilisateur "openhands" à l'intérieur du sandbox et donc tous les paquets installés via le docker file devraient être disponibles pour tous les utilisateurs du système, pas seulement root.
+
+## Utiliser le Workflow de Développement
+
+### Configuration
+
+Tout d'abord, assurez-vous de pouvoir exécuter OpenHands en suivant les instructions dans [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
+
+### Spécifier l'Image de Base du Sandbox
+
+Dans le fichier `config.toml` dans le répertoire OpenHands, définissez `sandbox_base_container_image` sur l'image que vous souhaitez utiliser. Cela peut être une image que vous avez déjà extraite ou une que vous avez construite :
+
+```bash
+[core]
+...
+sandbox_base_container_image="custom-image"
+```
+
+### Exécuter
+
+Exécutez OpenHands en exécutant ```make run``` dans le répertoire de niveau supérieur.
+
+## Explication Technique
+
+Veuillez vous référer à la [section image docker personnalisée de la documentation d'exécution](https://docs.all-hands.dev/modules/usage/architecture/runtime#advanced-how-openhands-builds-and-maintains-od-runtime-images) pour plus de détails.
+
+## Dépannage / Erreurs
+
+### Erreur : ```useradd: UID 1000 is not unique```
+
+Si vous voyez cette erreur dans la sortie de la console, c'est parce qu'OpenHands essaie de créer l'utilisateur openhands dans le sandbox avec un UID de 1000, mais cet UID est déjà utilisé dans l'image (pour une raison quelconque). Pour corriger cela, changez le champ sandbox_user_id dans le fichier config.toml à une valeur différente :
+
+```toml
+[core]
+workspace_base="./workspace"
+run_as_openhands=true
+sandbox_base_container_image="custom_image"
+sandbox_user_id="1001"
+```
+
+### Erreurs d'utilisation de port
+
+Si vous voyez une erreur concernant un port déjà utilisé ou indisponible, essayez de supprimer tous les conteneurs Docker en cours d'exécution (exécutez `docker ps` et `docker rm` sur les conteneurs pertinents) puis réexécutez ```make run```.
+
+## Discuter
+
+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 !