Fix issue #5102: [Bug]: lint-fix.yml workflow doesn't work when (frontend) tests are failing

.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/dependabot.yml

@@ -16,9 +16,6 @@ updates:
       chromadb:
         patterns:
           - "chromadb"
-      browsergym:
-        patterns:
-          - "browsergym*"
       security-all:
         applies-to: "security-updates"
         patterns:

.github/workflows/eval-runner.yml

@@ -1,8 +1,10 @@
-name: Run SWE-Bench Evaluation
+name: Run Evaluation
 
 on:
   pull_request:
     types: [labeled]
+  schedule:
+    - cron: "0 1 * * *" # Run daily at 1 AM UTC
   workflow_dispatch:
     inputs:
       reason:
@@ -58,6 +60,24 @@ jobs:
           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 }}
@@ -66,12 +86,12 @@ jobs:
           EVAL_DOCKER_IMAGE_PREFIX: us-central1-docker.pkg.dev/evaluation-092424/swe-bench-images
 
         run: |
-          poetry run ./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.eval HEAD CodeActAgent 300 30 $N_PROCESSES "princeton-nlp/SWE-bench_Lite" test
+          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/benchmarks/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_infer_remote.sh $OUTPUT_FOLDER/output.jsonl $N_PROCESSES "princeton-nlp/SWE-bench_Lite" test
 
-          poetry run ./evaluation/benchmarks/swe_bench/scripts/eval/summarize_outputs.py $OUTPUT_FOLDER/output.jsonl > summarize_outputs.log 2>&1
+          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
@@ -125,6 +145,9 @@ jobs:
               **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

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

@@ -24,8 +24,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        node-version: [20, 22]
-      fail-fast: true
+        node-version: [20]
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -36,9 +35,6 @@ jobs:
       - name: Install dependencies
         working-directory: ./frontend
         run: npm ci
-      - name: Run TypeScript compilation
-        working-directory: ./frontend
-        run: npm run make-i18n && tsc
       - name: Run tests and collect coverage
         working-directory: ./frontend
         run: npm run test:coverage

.github/workflows/ghcr-build.yml

@@ -291,7 +291,7 @@ jobs:
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
           TEST_IN_CI=true \
           RUN_AS_OPENHANDS=false \
-          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py
+          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4
         env:
@@ -368,7 +368,7 @@ jobs:
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
           TEST_IN_CI=true \
           RUN_AS_OPENHANDS=true \
-          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py
+          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:

.github/workflows/integration-runner.yml

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

.github/workflows/lint-fix.yml

@@ -5,10 +5,9 @@ on:
     types: [labeled]
 
 jobs:
-  # Frontend lint fixes
-  lint-fix-frontend:
+  lint-fix:
     if: github.event.label.name == 'lint-fix'
-    name: Fix frontend linting issues
+    name: Fix linting issues
     runs-on: ubuntu-latest
     permissions:
       contents: write
@@ -21,6 +20,7 @@ jobs:
           fetch-depth: 0
           token: ${{ secrets.GITHUB_TOKEN }}
 
+      # Frontend lint fixes
       - name: Install Node.js 20
         uses: actions/setup-node@v4
         with:
@@ -29,41 +29,16 @@ jobs:
         run: |
           cd frontend
           npm install --frozen-lockfile
+      - name: Generate i18n declaration files
+        run: |
+          cd frontend
+          npm run make-i18n
       - name: Fix frontend lint issues
         run: |
           cd frontend
           npm run lint:fix
 
-      # Commit and push changes if any
-      - name: Check for changes
-        id: git-check
-        run: |
-          git diff --quiet || echo "changes=true" >> $GITHUB_OUTPUT
-      - name: Commit and push if there are changes
-        if: steps.git-check.outputs.changes == 'true'
-        run: |
-          git config --local user.email "openhands@all-hands.dev"
-          git config --local user.name "OpenHands Bot"
-          git add -A
-          git commit -m "🤖 Auto-fix frontend linting issues"
-          git push
-
-  # Python lint fixes
-  lint-fix-python:
-    if: github.event.label.name == 'lint-fix'
-    name: Fix Python linting issues
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-      pull-requests: write
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ github.head_ref }}
-          repository: ${{ github.event.pull_request.head.repo.full_name }}
-          fetch-depth: 0
-          token: ${{ secrets.GITHUB_TOKEN }}
-
+      # Python lint fixes
       - name: Set up python
         uses: actions/setup-python@v5
         with:
@@ -73,8 +48,7 @@ jobs:
         run: pip install pre-commit==3.7.0
       - name: Fix python lint issues
         run: |
-          # Run all pre-commit hooks and continue even if they modify files (exit code 1)
-          pre-commit run --config ./dev_config/python/.pre-commit-config.yaml --files openhands/**/* evaluation/**/* tests/**/* || true
+          pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --config ./dev_config/python/.pre-commit-config.yaml
 
       # Commit and push changes if any
       - name: Check for changes
@@ -87,5 +61,5 @@ jobs:
           git config --local user.email "openhands@all-hands.dev"
           git config --local user.name "OpenHands Bot"
           git add -A
-          git commit -m "🤖 Auto-fix Python linting issues"
+          git commit -m "🤖 Auto-fix linting issues"
           git push

.github/workflows/lint.yml

@@ -30,11 +30,10 @@ jobs:
         run: |
           cd frontend
           npm install --frozen-lockfile
-      - name: Lint and TypeScript compilation
+      - name: Lint
         run: |
           cd frontend
           npm run lint
-          npm run make-i18n && tsc
 
   # Run lint on the python code
   lint-python:

.github/workflows/openhands-resolver.yml

@@ -11,31 +11,17 @@ on:
         required: false
         type: string
         default: "@openhands-agent"
-      target_branch:
-        required: false
-        type: string
-        default: "main"
-        description: "Target branch to pull and create PR against"
-      LLM_MODEL:
-        required: false
-        type: string
-        default: "anthropic/claude-3-5-sonnet-20241022"
-      base_container_image:
-        required: false
-        type: string
-        default: ""
-        description: "Custom sandbox env"
     secrets:
       LLM_MODEL:
-        required: false
+        required: true
       LLM_API_KEY:
         required: true
       LLM_BASE_URL:
         required: false
       PAT_TOKEN:
-        required: false
+        required: true
       PAT_USERNAME:
-        required: false
+        required: true
 
   issues:
     types: [labeled]
@@ -54,19 +40,21 @@ permissions:
   issues: write
 
 jobs:
+
   auto-fix:
     if: |
       github.event_name == 'workflow_call' ||
       github.event.label.name == 'fix-me' ||
       github.event.label.name == 'fix-me-experimental' ||
+
       (
         ((github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment') &&
-        contains(github.event.comment.body, inputs.macro || '@openhands-agent') &&
+        startsWith(github.event.comment.body, inputs.macro || '@openhands-agent') &&
         (github.event.comment.author_association == 'OWNER' || github.event.comment.author_association == 'COLLABORATOR' || github.event.comment.author_association == 'MEMBER')
         ) ||
 
         (github.event_name == 'pull_request_review' &&
-        contains(github.event.review.body, inputs.macro || '@openhands-agent') &&
+        startsWith(github.event.review.body, inputs.macro || '@openhands-agent') &&
         (github.event.review.author_association == 'OWNER' || github.event.review.author_association == 'COLLABORATOR' || github.event.review.author_association == 'MEMBER')
         )
       )
@@ -88,18 +76,7 @@ jobs:
           cat requirements.txt
 
       - name: Cache pip dependencies
-        if: |
-          !(
-            github.event.label.name == 'fix-me-experimental' ||
-            (
-              (github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment') &&
-              contains(github.event.comment.body, '@openhands-agent-exp')
-            ) ||
-            (
-              github.event_name == 'pull_request_review' &&
-              contains(github.event.review.body, '@openhands-agent-exp')
-            )
-          )
+        if: github.event.label.name != 'fix-me-experimental'
         uses: actions/cache@v3
         with:
           path: ${{ env.pythonLocation }}/lib/python3.12/site-packages/*
@@ -109,14 +86,13 @@ jobs:
 
       - name: Check required environment variables
         env:
-          LLM_MODEL: ${{ secrets.LLM_MODEL || inputs.LLM_MODEL }}
+          LLM_MODEL: ${{ secrets.LLM_MODEL }}
           LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
           LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
           PAT_TOKEN: ${{ secrets.PAT_TOKEN }}
           PAT_USERNAME: ${{ secrets.PAT_USERNAME }}
-          GITHUB_TOKEN: ${{ github.token }}
         run: |
-          required_vars=("LLM_MODEL" "LLM_API_KEY")
+          required_vars=("LLM_MODEL" "LLM_API_KEY" "PAT_TOKEN" "PAT_USERNAME")
           for var in "${required_vars[@]}"; do
             if [ -z "${!var}" ]; then
               echo "Error: Required environment variable $var is not set."
@@ -124,34 +100,17 @@ jobs:
             fi
           done
 
-          # Check optional variables and warn about fallbacks
-          if [ -z "$PAT_TOKEN" ]; then
-            echo "Warning: PAT_TOKEN is not set, falling back to GITHUB_TOKEN"
-          fi
-
-          if [ -z "$LLM_BASE_URL" ]; then
-            echo "Warning: LLM_BASE_URL is not set, will use default API endpoint"
-          fi
-
-          if [ -z "$PAT_USERNAME" ]; then
-            echo "Warning: PAT_USERNAME is not set, will use openhands-agent"
-          fi
-
       - name: Set environment variables
         run: |
-          # Handle pull request events first
-          if [ -n "${{ github.event.pull_request.number }}" ]; then
+          if [ -n "${{ github.event.review.body }}" ]; then
             echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
             echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
-          # Handle pull request review events
-          elif [ -n "${{ github.event.review.body }}" ]; then
-            echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
-            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
-          # Handle issue comment events that reference a PR
           elif [ -n "${{ github.event.issue.pull_request }}" ]; then
             echo "ISSUE_NUMBER=${{ github.event.issue.number }}" >> $GITHUB_ENV
             echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
-          # Handle regular issue events
+          elif [ -n "${{ github.event.pull_request.number }}" ]; then
+            echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
+            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
           else
             echo "ISSUE_NUMBER=${{ github.event.issue.number }}" >> $GITHUB_ENV
             echo "ISSUE_TYPE=issue" >> $GITHUB_ENV
@@ -164,16 +123,12 @@ jobs:
           fi
 
           echo "MAX_ITERATIONS=${{ inputs.max_iterations || 50 }}" >> $GITHUB_ENV
-          echo "SANDBOX_ENV_GITHUB_TOKEN=${{ secrets.PAT_TOKEN || github.token }}" >> $GITHUB_ENV
-          echo "SANDBOX_ENV_BASE_CONTAINER_IMAGE=${{ inputs.base_container_image }}" >> $GITHUB_ENV
-
-          # Set branch variables
-          echo "TARGET_BRANCH=${{ inputs.target_branch }}" >> $GITHUB_ENV
+          echo "SANDBOX_ENV_GITHUB_TOKEN=${{ secrets.GITHUB_TOKEN }}" >> $GITHUB_ENV
 
       - name: Comment on issue with start message
         uses: actions/github-script@v7
         with:
-          github-token: ${{ secrets.PAT_TOKEN || github.token }}
+          github-token: ${{secrets.GITHUB_TOKEN}}
           script: |
             const issueType = process.env.ISSUE_TYPE;
             github.rest.issues.createComment({
@@ -184,38 +139,19 @@ jobs:
             });
 
       - name: Install OpenHands
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const commentBody = `${{ github.event.comment.body || '' }}`.trim();
-            const reviewBody = `${{ github.event.review.body || '' }}`.trim();
-            const labelName = `${{ github.event.label.name || '' }}`.trim();
-            const eventName = `${{ github.event_name }}`.trim();
-
-            // Check conditions
-            const isExperimentalLabel = labelName === "fix-me-experimental";
-            const isIssueCommentExperimental =
-              (eventName === "issue_comment" || eventName === "pull_request_review_comment") &&
-              commentBody.includes("@openhands-agent-exp");
-            const isReviewCommentExperimental =
-              eventName === "pull_request_review" && reviewBody.includes("@openhands-agent-exp");
-
-            // Perform package installation
-            if (isExperimentalLabel || isIssueCommentExperimental || isReviewCommentExperimental) {
-              console.log("Installing experimental OpenHands...");
-              await exec.exec("python -m pip install --upgrade pip");
-              await exec.exec("pip install git+https://github.com/all-hands-ai/openhands.git");
-            } else {
-              console.log("Installing from requirements.txt...");
-              await exec.exec("python -m pip install --upgrade pip");
-              await exec.exec("pip install -r requirements.txt");
-            }
+        run: |
+          if [ "${{ github.event.label.name }}" == "fix-me-experimental" ]; then
+            python -m pip install --upgrade pip
+            pip install git+https://github.com/all-hands-ai/openhands.git
+          else
+            python -m pip install --upgrade -r requirements.txt
+          fi
 
       - name: Attempt to resolve issue
         env:
-          GITHUB_TOKEN: ${{ secrets.PAT_TOKEN || github.token }}
-          GITHUB_USERNAME: ${{ secrets.PAT_USERNAME || 'openhands-agent' }}
-          LLM_MODEL: ${{ secrets.LLM_MODEL || inputs.LLM_MODEL }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_USERNAME: ${{ secrets.PAT_USERNAME }}
+          LLM_MODEL: ${{ secrets.LLM_MODEL }}
           LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
           LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
           PYTHONPATH: ""
@@ -247,9 +183,9 @@ jobs:
       - name: Create draft PR or push branch
         if: always() # Create PR or branch even if the previous steps fail
         env:
-          GITHUB_TOKEN: ${{ secrets.PAT_TOKEN || github.token }}
-          GITHUB_USERNAME: ${{ secrets.PAT_USERNAME || 'openhands-agent' }}
-          LLM_MODEL: ${{ secrets.LLM_MODEL || inputs.LLM_MODEL }}
+          GITHUB_TOKEN: ${{ secrets.PAT_TOKEN }}
+          GITHUB_USERNAME: ${{ secrets.PAT_USERNAME }}
+          LLM_MODEL: ${{ secrets.LLM_MODEL }}
           LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
           LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
           PYTHONPATH: ""
@@ -257,8 +193,7 @@ jobs:
           if [ "${{ steps.check_result.outputs.RESOLUTION_SUCCESS }}" == "true" ]; then
             cd /tmp && python -m openhands.resolver.send_pull_request \
               --issue-number ${{ env.ISSUE_NUMBER }} \
-              --pr-type draft \
-              --reviewer ${{ github.actor }} | tee pr_result.txt && \
+              --pr-type draft | tee pr_result.txt && \
               grep "draft created" pr_result.txt | sed 's/.*\///g' > pr_number.txt
           else
             cd /tmp && python -m openhands.resolver.send_pull_request \
@@ -272,7 +207,7 @@ jobs:
         uses: actions/github-script@v7
         if: always() # Comment on issue even if the previous steps fail
         with:
-          github-token: ${{ secrets.PAT_TOKEN || github.token }}
+          github-token: ${{secrets.GITHUB_TOKEN}}
           script: |
             const fs = require('fs');
             const issueNumber = ${{ env.ISSUE_NUMBER }};

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

@@ -42,7 +42,7 @@ jobs:
       - name: Build Environment
         run: make build
       - name: Run Tests
-        run: poetry run pytest --forked -n auto --cov=openhands --cov-report=xml -svv ./tests/unit --ignore=tests/unit/test_memory.py
+        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:

.github/workflows/review-pr.yml

@@ -0,0 +1,81 @@
+# Workflow that uses OpenHands to review a pull request. PR must be labeled 'review-this'
+name: Use OpenHands to Review Pull Request
+
+on:
+  pull_request:
+    types: [synchronize, labeled]
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  dogfood:
+    if: contains(github.event.pull_request.labels.*.name, 'review-this')
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up 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: |
+        sudo apt-get install -y git gh
+        git config --global --add safe.directory $PWD
+    - name: Checkout Repository
+      uses: actions/checkout@v4
+      with:
+        ref: ${{ github.event.pull_request.base.ref }} # check out the target branch
+    - name: Download Diff
+      run: |
+        curl -O "${{ github.event.pull_request.diff_url }}" -L
+    - name: Write Task File
+      run: |
+        echo "Your coworker wants to apply a pull request to this project." > task.txt
+        echo "Read and review ${{ github.event.pull_request.number }}.diff file. Create a review-${{ github.event.pull_request.number }}.txt and write your concise comments and suggestions there." >> task.txt
+        echo "Do not ask me for confirmation at any point." >> task.txt
+        echo "" >> task.txt
+        echo "Title" >> task.txt
+        echo "${{ github.event.pull_request.title }}" >> task.txt
+        echo "" >> task.txt
+        echo "Description" >> task.txt
+        echo "${{ github.event.pull_request.body }}" >> task.txt
+        echo "" >> task.txt
+        echo "Diff file is: ${{ github.event.pull_request.number }}.diff" >> task.txt
+    - name: Set up environment
+      run: |
+        curl -sSL https://install.python-poetry.org | python3 -
+        export PATH="/github/home/.local/bin:$PATH"
+        poetry install --without evaluation,llama-index
+        poetry run playwright install --with-deps chromium
+    - name: Run OpenHands
+      env:
+        LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+        LLM_MODEL: ${{ vars.LLM_MODEL }}
+      run: |
+        # Append path to launch poetry
+        export PATH="/github/home/.local/bin:$PATH"
+        # Append path to correctly import package, note: must set pwd at first
+        export PYTHONPATH=$(pwd):$PYTHONPATH
+        export WORKSPACE_MOUNT_PATH=$GITHUB_WORKSPACE
+        export WORKSPACE_BASE=$GITHUB_WORKSPACE
+        echo -e "/exit\n" | poetry run python openhands/core/main.py -i 50 -f task.txt
+        rm task.txt
+    - name: Check if review file is non-empty
+      id: check_file
+      run: |
+        ls -la
+        if [[ -s review-${{ github.event.pull_request.number }}.txt ]]; then
+          echo "non_empty=true" >> $GITHUB_OUTPUT
+        fi
+      shell: bash
+    - name: Create PR review if file is non-empty
+      env:
+        GH_TOKEN: ${{ github.token }}
+      if: steps.check_file.outputs.non_empty == 'true'
+      run: |
+        gh pr review ${{ github.event.pull_request.number }} --comment --body-file "review-${{ github.event.pull_request.number }}.txt"

.github/workflows/run-eval.yml

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

.gitignore

@@ -175,7 +175,6 @@ evaluation/gaia/data
 evaluation/gorilla/data
 evaluation/toolqa/data
 evaluation/scienceagentbench/benchmark
-evaluation/commit0_bench/repos
 
 # openhands resolver
 output/

CONTRIBUTING.md

@@ -21,14 +21,14 @@ There are many ways that you can contribute:
 
 1. **Download and use** OpenHands, and send [issues](https://github.com/All-Hands-AI/OpenHands/issues) when you encounter something that isn't working or a feature that you'd like to see.
 2. **Send feedback** after each session by [clicking the thumbs-up thumbs-down buttons](https://docs.all-hands.dev/modules/usage/feedback), so we can see where things are working and failing, and also build an open dataset for training code agents.
-3. **Improve the Codebase** by sending [PRs](#sending-pull-requests-to-openhands) (see details below). In particular, we have some [good first issues](https://github.com/All-Hands-AI/OpenHands/labels/good%20first%20issue) that may be ones to start on.
+3. **Improve the Codebase** by sending PRs (see details below). In particular, we have some [good first issues](https://github.com/All-Hands-AI/OpenHands/labels/good%20first%20issue) that may be ones to start on.
 
 ## What can I build?
 Here are a few ways you can help improve the codebase.
 
 #### UI/UX
 We're always looking to improve the look and feel of the application. If you've got a small fix
-for something that's bugging you, feel free to open up a PR that changes the [`./frontend`](./frontend) directory.
+for something that's bugging you, feel free to open up a PR that changes the `./frontend` directory.
 
 If you're looking to make a bigger change, add a new UI element, or significantly alter the style
 of the application, please open an issue first, or better, join the #frontend channel in our Slack
@@ -46,7 +46,7 @@ We use the [SWE-bench](https://www.swebench.com/) benchmark to test our agent. Y
 channel in Slack to learn more.
 
 #### Adding a new agent
-You may want to experiment with building new types of agents. You can add an agent to [`openhands/agenthub`](./openhands/agenthub)
+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
@@ -54,11 +54,11 @@ The agent needs a place to run code and commands. When you run OpenHands on your
 to do this by default. But there are other ways of creating a sandbox for the agent.
 
 If you work for a company that provides a cloud-based runtime, you could help us add support for that runtime
-by implementing the [interface specified here](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/base.py).
+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`](./tests) folder to see existing test suites.
-At the moment, we have two kinds of tests: [`unit`](./tests/unit) and [`integration`](./evaluation/integration_tests). Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
+When you write code, it is also good to write tests. Please navigate to the `tests` folder to see existing test suites.
+At the moment, we have two kinds of tests: `unit` and `integration`. Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
 
 ## Sending Pull Requests to OpenHands
 
@@ -103,7 +103,7 @@ Further, if you see an issue you like, please leave a "thumbs-up" or a comment,
 
 ### Making Pull Requests
 
-We're generally happy to consider all [PRs](https://github.com/All-Hands-AI/OpenHands/pulls), with the evaluation process varying based on the type of change:
+We're generally happy to consider all PRs, with the evaluation process varying based on the type of change:
 
 #### For Small Improvements
 

Development.md

@@ -100,7 +100,7 @@ poetry run pytest ./tests/unit/test_*.py
 To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker container image by
 setting the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
 
-Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.15-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.14-nikolaik`
 
 ## Develop inside Docker container
 

README.md

@@ -12,7 +12,7 @@
   <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/openhands-ai/shared_invite/zt-2vbfigwev-G03twSpXaErwzYVD4CFiBg"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
+  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-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/>
@@ -29,11 +29,6 @@ call APIs, and yes—even copy code snippets from StackOverflow.
 
 Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or jump to the [Quick Start](#-quick-start).
 
-> [!IMPORTANT]
-> Using OpenHands for work? We'd love to chat! Fill out
-> [this short form](https://docs.google.com/forms/d/e/1FAIpQLSet3VbGaz8z32gW9Wm-Grl4jpt5WgMXPgJ4EDPVmCETCBpJtQ/viewform)
-> to join our Design Partner program, where you'll get early access to commercial features and the opportunity to provide input on our product roadmap.
-
 ![App screenshot](./docs/static/img/screenshot.png)
 
 ## ⚡ Quick Start
@@ -43,17 +38,16 @@ See the [Installation](https://docs.all-hands.dev/modules/usage/installation) gu
 system requirements and more information.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.15-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.14-nikolaik
 
-docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.15-nikolaik \
+docker run -it --pull=always \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.14-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
-    -v ~/.openhands:/home/openhands/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.15
+    docker.all-hands.dev/all-hands-ai/openhands:0.14
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
@@ -88,7 +82,7 @@ troubleshooting resources, and advanced configuration options.
 OpenHands is a community-driven project, and we welcome contributions from everyone. We do most of our communication
 through Slack, so this is the best place to start, but we also are happy to have you contact us on Discord or Github:
 
-- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-2vbfigwev-G03twSpXaErwzYVD4CFiBg) - Here we talk about research, architecture, and future development.
+- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-2tom0er4l-JeNUGHt_AxpEfIBstbLPiw) - Here we talk about research, architecture, and future development.
 - [Join our Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
 - [Read or post Github Issues](https://github.com/All-Hands-AI/OpenHands/issues) - Check out the issues we're working on, or add your own ideas.
 
@@ -96,8 +90,6 @@ See more about the community in [COMMUNITY.md](./COMMUNITY.md) or find details o
 
 ## 📈 Progress
 
-See the monthly OpenHands roadmap [here](https://github.com/orgs/All-Hands-AI/projects/1) (updated at the maintainer's meeting at the end of each month).
-
 <p align="center">
   <a href="https://star-history.com/#All-Hands-AI/OpenHands&Date">
     <img src="https://api.star-history.com/svg?repos=All-Hands-AI/OpenHands&type=Date" width="500" alt="Star History Chart">

compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.15-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.14-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

config.template.toml

@@ -95,10 +95,10 @@ workspace_base = "./workspace"
 # AWS secret access key
 #aws_secret_access_key = ""
 
-# API key to use (For Headless / CLI only -  In Web this is overridden by Session Init)
+# API key to use
 api_key = "your-api-key"
 
-# API base URL (For Headless / CLI only -  In Web this is overridden by Session Init)
+# API base URL
 #base_url = ""
 
 # API version
@@ -131,7 +131,7 @@ embedding_model = "local"
 # Maximum number of output tokens
 #max_output_tokens = 0
 
-# Model to use. (For Headless / CLI only -  In Web this is overridden by Session Init)
+# Model to use
 model = "gpt-4o"
 
 # Number of retries to attempt when an operation fails with the LLM.
@@ -172,10 +172,6 @@ model = "gpt-4o"
 # If model is vision capable, this option allows to disable image processing (useful for cost reduction).
 #disable_vision = true
 
-# Custom tokenizer to use for token counting
-# https://docs.litellm.ai/docs/completion/token_usage
-#custom_tokenizer = ""
-
 [llm.gpt4o-mini]
 api_key = "your-api-key"
 model = "gpt-4o"
@@ -221,9 +217,6 @@ llm_config = 'gpt3'
 # Use host network
 #use_host_network = false
 
-# runtime extra build args
-#runtime_extra_build_args = ["--network=host", "--add-host=host.docker.internal:host-gateway"]
-
 # Enable auto linting after editing
 #enable_auto_lint = false
 
@@ -244,10 +237,10 @@ llm_config = 'gpt3'
 ##############################################################################
 [security]
 
-# Enable confirmation mode (For Headless / CLI only -  In Web this is overridden by Session Init)
+# Enable confirmation mode
 #confirmation_mode = false
 
-# The security analyzer to use (For Headless / CLI only -  In Web this is overridden by Session Init)
+# The security analyzer to use
 #security_analyzer = ""
 
 #################################### Eval ####################################

containers/app/Dockerfile

@@ -42,8 +42,6 @@ ENV USE_HOST_NETWORK=false
 ENV WORKSPACE_BASE=/opt/workspace_base
 ENV OPENHANDS_BUILD_VERSION=$OPENHANDS_BUILD_VERSION
 ENV SANDBOX_USER_ID=0
-ENV FILE_STORE=local
-ENV FILE_STORE_PATH=~/.openhands
 RUN mkdir -p $WORKSPACE_BASE
 
 RUN apt-get update -y \

containers/dev/README.md

@@ -1,8 +1,5 @@
 # Develop in Docker
 
-> [!WARNING]
-> This is not officially supported and may not work.
-
 Install [Docker](https://docs.docker.com/engine/install/) on your host machine and run:
 
 ```bash

containers/dev/compose.yml

@@ -11,7 +11,7 @@ services:
       - 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:0.15-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.14-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

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

@@ -27,7 +27,7 @@ Pour plus de détails, veuillez consulter [ce document](https://github.com/All-H
 
 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/openhands-ai/shared_invite/zt-2vbfigwev-G03twSpXaErwzYVD4CFiBg)
+- [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 !

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/evaluation-harness.md

@@ -76,7 +76,7 @@ La fonction `run_controller()` est le cœur de l'exécution d'OpenHands. Elle g
 
 ## Le moyen le plus simple de commencer : Explorer les benchmarks existants
 
-Nous vous encourageons à examiner les différents benchmarks d'évaluation disponibles dans le [répertoire `evaluation/benchmarks/`](https://github.com/All-Hands-AI/OpenHands/blob/main/evaluation/benchmarks) de notre dépôt.
+Nous vous encourageons à examiner les différents benchmarks d'évaluation disponibles dans le [répertoire `evaluation/`](https://github.com/All-Hands-AI/OpenHands/blob/main/evaluation) de notre dépôt.
 
 Pour intégrer votre propre benchmark, nous vous suggérons de commencer par celui qui ressemble le plus à vos besoins. Cette approche peut considérablement rationaliser votre processus d'intégration, vous permettant de vous appuyer sur les structures existantes et de les adapter à vos exigences spécifiques.
 

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

@@ -9,6 +9,7 @@ Si vous trouvez plus d'informations ou une solution de contournement pour l'un d
 :::tip
 OpenHands ne prend en charge Windows que via [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
 Veuillez vous assurer d'exécuter toutes les commandes à l'intérieur de votre terminal WSL.
+Consultez les [Notes pour les utilisateurs de WSL sur Windows](troubleshooting/windows) pour des guides de dépannage.
 :::
 
 ## Problèmes courants

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

@@ -0,0 +1,66 @@
+
+
+# Notes pour les utilisateurs de WSL sur Windows
+
+OpenHands ne prend en charge Windows que via [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
+Veuillez vous assurer d'exécuter toutes les commandes dans votre terminal WSL.
+
+## Dépannage
+
+### Recommandation : Ne pas exécuter en tant qu'utilisateur root
+
+Pour des raisons de sécurité, il est fortement recommandé de ne pas exécuter OpenHands en tant qu'utilisateur root, mais en tant qu'utilisateur avec un UID non nul.
+
+Références :
+
+* [Pourquoi il est mauvais de se connecter en tant que root](https://askubuntu.com/questions/16178/why-is-it-bad-to-log-in-as-root)
+* [Définir l'utilisateur par défaut dans WSL](https://www.tenforums.com/tutorials/128152-set-default-user-windows-subsystem-linux-distro-windows-10-a.html#option2)
+Astuce concernant la 2ème référence : pour les utilisateurs d'Ubuntu, la commande pourrait en fait être "ubuntupreview" au lieu de "ubuntu".
+
+---
+### Erreur : 'docker' n'a pas pu être trouvé dans cette distribution WSL 2.
+
+Si vous utilisez Docker Desktop, assurez-vous de le démarrer avant d'appeler toute commande docker depuis WSL.
+Docker doit également avoir l'option d'intégration WSL activée.
+
+---
+### Installation de Poetry
+
+* Si vous rencontrez des problèmes pour exécuter Poetry même après l'avoir installé pendant le processus de build, vous devrez peut-être ajouter son chemin binaire à votre environnement :
+
+```sh
+export PATH="$HOME/.local/bin:$PATH"
+```
+
+* Si make build s'arrête sur une erreur comme celle-ci :
+
+```sh
+ModuleNotFoundError: no module named <module-name>
+```
+
+Cela pourrait être un problème avec le cache de Poetry.
+Essayez d'exécuter ces 2 commandes l'une après l'autre :
+
+```sh
+rm -r ~/.cache/pypoetry
+make build
+```
+
+---
+### L'objet NoneType n'a pas d'attribut 'request'
+
+Si vous rencontrez des problèmes liés au réseau, tels que `NoneType object has no attribute 'request'` lors de l'exécution de `make run`, vous devrez peut-être configurer les paramètres réseau de WSL2. Suivez ces étapes :
+
+* Ouvrez ou créez le fichier `.wslconfig` situé à `C:\Users\%username%\.wslconfig` sur votre machine hôte Windows.
+* Ajoutez la configuration suivante au fichier `.wslconfig` :
+
+```sh
+[wsl2]
+networkingMode=mirrored
+localhostForwarding=true
+```
+
+* Enregistrez le fichier `.wslconfig`.
+* Redémarrez complètement WSL2 en quittant toutes les instances WSL2 en cours d'exécution et en exécutant la commande `wsl --shutdown` dans votre invite de commande ou terminal.
+* Après avoir redémarré WSL, essayez d'exécuter à nouveau `make run`.
+Le problème de réseau devrait être résolu.

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

@@ -27,7 +27,7 @@ OpenHands 是一个社区驱动的项目，我们欢迎每个人的贡献。无
 
 我们有 Slack 工作区用于协作构建 OpenHands，也有 Discord 服务器用于讨论任何相关的内容，例如此项目、大语言模型、代理等。
 
-- [Slack 工作区](https://join.slack.com/t/openhands-ai/shared_invite/zt-2vbfigwev-G03twSpXaErwzYVD4CFiBg)
+- [Slack 工作区](https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA)
 - [Discord 服务器](https://discord.gg/ESHStjSjD4)
 
 如果你想做出贡献，欢迎加入我们的社区。让我们一起简化软件工程！

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/evaluation-harness.md

@@ -73,7 +73,7 @@ OpenHands 的主要入口点在 `openhands/core/main.py` 中。以下是它工
 
 ## 入门最简单的方法：探索现有基准
 
-我们鼓励您查看我们仓库的 [`evaluation/benchmarks/` 目录](https://github.com/All-Hands-AI/OpenHands/blob/main/evaluation/benchmarks)中提供的各种评估基准。
+我们鼓励您查看我们仓库的 [`evaluation/` 目录](https://github.com/All-Hands-AI/OpenHands/blob/main/evaluation)中提供的各种评估基准。
 
 要集成您自己的基准，我们建议从最接近您需求的基准开始。这种方法可以显著简化您的集成过程，允许您在现有结构的基础上进行构建并使其适应您的特定要求。
 

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

@@ -7,6 +7,7 @@
 :::tip
 OpenHands 仅通过 [WSL](https://learn.microsoft.com/en-us/windows/wsl/install) 支持 Windows。
 请确保在您的 WSL 终端内运行所有命令。
+查看 [Windows 用户的 WSL 注意事项](troubleshooting/windows) 以获取一些故障排除指南。
 :::
 
 ## 常见问题

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

@@ -0,0 +1,66 @@
+以下是翻译后的内容:
+
+# 针对 Windows 上 WSL 用户的注意事项
+
+OpenHands 仅通过 [WSL](https://learn.microsoft.com/en-us/windows/wsl/install) 支持 Windows。
+请确保在您的 WSL 终端内运行所有命令。
+
+## 故障排除
+
+### 建议: 不要以 root 用户身份运行
+
+出于安全原因,强烈建议不要以 root 用户身份运行 OpenHands,而是以具有非零 UID 的用户身份运行。
+
+参考:
+
+* [为什么以 root 身份登录不好](https://askubuntu.com/questions/16178/why-is-it-bad-to-log-in-as-root)
+* [在 WSL 中设置默认用户](https://www.tenforums.com/tutorials/128152-set-default-user-windows-subsystem-linux-distro-windows-10-a.html#option2)
+关于第二个参考的提示:对于 Ubuntu 用户,命令实际上可能是 "ubuntupreview" 而不是 "ubuntu"。
+
+---
+### 错误: 在此 WSL 2 发行版中找不到 'docker'。
+
+如果您正在使用 Docker Desktop,请确保在从 WSL 内部调用任何 docker 命令之前启动它。
+Docker 还需要激活 WSL 集成选项。
+
+---
+### Poetry 安装
+
+* 如果您在构建过程中安装 Poetry 后仍然面临运行 Poetry 的问题,您可能需要将其二进制路径添加到环境中:
+
+```sh
+export PATH="$HOME/.local/bin:$PATH"
+```
+
+* 如果 make build 在如下错误上停止:
+
+```sh
+ModuleNotFoundError: no module named <module-name>
+```
+
+这可能是 Poetry 缓存的问题。
+尝试依次运行这两个命令:
+
+```sh
+rm -r ~/.cache/pypoetry
+make build
+```
+
+---
+### NoneType 对象没有属性 'request'
+
+如果您在执行 `make run` 时遇到与网络相关的问题,例如 `NoneType 对象没有属性 'request'`,您可能需要配置 WSL2 网络设置。请按照以下步骤操作:
+
+* 在 Windows 主机上打开或创建位于 `C:\Users\%username%\.wslconfig` 的 `.wslconfig` 文件。
+* 将以下配置添加到 `.wslconfig` 文件中:
+
+```sh
+[wsl2]
+networkingMode=mirrored
+localhostForwarding=true
+```
+
+* 保存 `.wslconfig` 文件。
+* 通过退出任何正在运行的 WSL2 实例并在命令提示符或终端中执行 `wsl --shutdown` 命令来完全重启 WSL2。
+* 重新启动 WSL 后,再次尝试执行 `make run`。
+网络问题应该得到解决。

docs/modules/usage/configuration-options.md

@@ -1,465 +0,0 @@
-# Configuration Options
-
-This guide details all configuration options available for OpenHands, helping you customize its behavior and integrate it with other services.
-
-:::note
-If you are running in [GUI Mode](https://docs.all-hands.dev/modules/usage/how-to/gui-mode), the settings available in the Settings UI will always
-take precedence.
-:::
-
----
-
-# Table of Contents
-
-1. [Core Configuration](#core-configuration)
-   - [API Keys](#api-keys)
-   - [Workspace](#workspace)
-   - [Debugging and Logging](#debugging-and-logging)
-   - [Session Management](#session-management)
-   - [Trajectories](#trajectories)
-   - [File Store](#file-store)
-   - [Task Management](#task-management)
-   - [Sandbox Configuration](#sandbox-configuration)
-   - [Miscellaneous](#miscellaneous)
-2. [LLM Configuration](#llm-configuration)
-   - [AWS Credentials](#aws-credentials)
-   - [API Configuration](#api-configuration)
-   - [Custom LLM Provider](#custom-llm-provider)
-   - [Embeddings](#embeddings)
-   - [Message Handling](#message-handling)
-   - [Model Selection](#model-selection)
-   - [Retrying](#retrying)
-   - [Advanced Options](#advanced-options)
-3. [Agent Configuration](#agent-configuration)
-   - [Microagent Configuration](#microagent-configuration)
-   - [Memory Configuration](#memory-configuration)
-   - [LLM Configuration](#llm-configuration-2)
-   - [ActionSpace Configuration](#actionspace-configuration)
-   - [Microagent Usage](#microagent-usage)
-4. [Sandbox Configuration](#sandbox-configuration-2)
-   - [Execution](#execution)
-   - [Container Image](#container-image)
-   - [Networking](#networking)
-   - [Linting and Plugins](#linting-and-plugins)
-   - [Dependencies and Environment](#dependencies-and-environment)
-   - [Evaluation](#evaluation)
-5. [Security Configuration](#security-configuration)
-   - [Confirmation Mode](#confirmation-mode)
-   - [Security Analyzer](#security-analyzer)
-
----
-
-## Core Configuration
-
-The core configuration options are defined in the `[core]` section of the `config.toml` file.
-
-**API Keys**
-- `e2b_api_key`
-  - Type: `str`
-  - Default: `""`
-  - Description: API key for E2B
-
-- `modal_api_token_id`
-  - Type: `str`
-  - Default: `""`
-  - Description: API token ID for Modal
-
-- `modal_api_token_secret`
-  - Type: `str`
-  - Default: `""`
-  - Description: API token secret for Modal
-
-**Workspace**
-- `workspace_base`
-  - Type: `str`
-  - Default: `"./workspace"`
-  - Description: Base path for the workspace
-
-- `cache_dir`
-  - Type: `str`
-  - Default: `"/tmp/cache"`
-  - Description: Cache directory path
-
-**Debugging and Logging**
-- `debug`
-  - Type: `bool`
-  - Default: `false`
-  - Description: Enable debugging
-
-- `disable_color`
-  - Type: `bool`
-  - Default: `false`
-  - Description: Disable color in terminal output
-
-**Trajectories**
-- `trajectories_path`
-  - Type: `str`
-  - Default: `"./trajectories"`
-  - Description: Path to store trajectories (can be a folder or a file). If it's a folder, the trajectories will be saved in a file named with the session id name and .json extension, in that folder.
-
-**File Store**
-- `file_store_path`
-  - Type: `str`
-  - Default: `"/tmp/file_store"`
-  - Description: File store path
-
-- `file_store`
-  - Type: `str`
-  - Default: `"memory"`
-  - Description: File store type
-
-- `file_uploads_allowed_extensions`
-  - Type: `list of str`
-  - Default: `[".*"]`
-  - Description: List of allowed file extensions for uploads
-
-- `file_uploads_max_file_size_mb`
-  - Type: `int`
-  - Default: `0`
-  - Description: Maximum file size for uploads, in megabytes
-
-- `file_uploads_restrict_file_types`
-  - Type: `bool`
-  - Default: `false`
-  - Description: Restrict file types for file uploads
-
-- `file_uploads_allowed_extensions`
-  - Type: `list of str`
-  - Default: `[".*"]`
-  - Description: List of allowed file extensions for uploads
-
-**Task Management**
-- `max_budget_per_task`
-  - Type: `float`
-  - Default: `0.0`
-  - Description: Maximum budget per task (0.0 means no limit)
-
-- `max_iterations`
-  - Type: `int`
-  - Default: `100`
-  - Description: Maximum number of iterations
-
-**Sandbox Configuration**
-- `workspace_mount_path_in_sandbox`
-  - Type: `str`
-  - Default: `"/workspace"`
-  - Description: Path to mount the workspace in the sandbox
-
-- `workspace_mount_path`
-  - Type: `str`
-  - Default: `""`
-  - Description: Path to mount the workspace
-
-- `workspace_mount_rewrite`
-  - Type: `str`
-  - Default: `""`
-  - Description: Path to rewrite the workspace mount path to. You can usually ignore this, it refers to special cases of running inside another container.
-
-**Miscellaneous**
-- `run_as_openhands`
-  - Type: `bool`
-  - Default: `true`
-  - Description: Run as OpenHands
-
-- `runtime`
-  - Type: `str`
-  - Default: `"eventstream"`
-  - Description: Runtime environment
-
-- `default_agent`
-  - Type: `str`
-  - Default: `"CodeActAgent"`
-  - Description: Name of the default agent
-
-- `jwt_secret`
-  - Type: `str`
-  - Default: `uuid.uuid4().hex`
-  - Description: JWT secret for authentication. Please set it to your own value.
-
-## LLM Configuration
-
-The LLM (Large Language Model) configuration options are defined in the `[llm]` section of the `config.toml` file.
-
-To use these with the docker command, pass in `-e LLM_<option>`. Example: `-e LLM_NUM_RETRIES`.
-
-**AWS Credentials**
-- `aws_access_key_id`
-  - Type: `str`
-  - Default: `""`
-  - Description: AWS access key ID
-
-- `aws_region_name`
-  - Type: `str`
-  - Default: `""`
-  - Description: AWS region name
-
-- `aws_secret_access_key`
-  - Type: `str`
-  - Default: `""`
-  - Description: AWS secret access key
-
-**API Configuration**
-- `api_key`
-  - Type: `str`
-  - Default: `None`
-  - Description: API key to use
-
-- `base_url`
-  - Type: `str`
-  - Default: `""`
-  - Description: API base URL
-
-- `api_version`
-  - Type: `str`
-  - Default: `""`
-  - Description: API version
-
-- `input_cost_per_token`
-  - Type: `float`
-  - Default: `0.0`
-  - Description: Cost per input token
-
-- `output_cost_per_token`
-  - Type: `float`
-  - Default: `0.0`
-  - Description: Cost per output token
-
-**Custom LLM Provider**
-- `custom_llm_provider`
-  - Type: `str`
-  - Default: `""`
-  - Description: Custom LLM provider
-
-**Embeddings**
-- `embedding_base_url`
-  - Type: `str`
-  - Default: `""`
-  - Description: Embedding API base URL
-
-- `embedding_deployment_name`
-  - Type: `str`
-  - Default: `""`
-  - Description: Embedding deployment name
-
-- `embedding_model`
-  - Type: `str`
-  - Default: `"local"`
-  - Description: Embedding model to use
-
-**Message Handling**
-- `max_message_chars`
-  - Type: `int`
-  - Default: `30000`
-  - Description: The approximate maximum number of characters in the content of an event included in the prompt to the LLM. Larger observations are truncated.
-
-- `max_input_tokens`
-  - Type: `int`
-  - Default: `0`
-  - Description: Maximum number of input tokens
-
-- `max_output_tokens`
-  - Type: `int`
-  - Default: `0`
-  - Description: Maximum number of output tokens
-
-**Model Selection**
-- `model`
-  - Type: `str`
-  - Default: `"claude-3-5-sonnet-20241022"`
-  - Description: Model to use
-
-**Retrying**
-- `num_retries`
-  - Type: `int`
-  - Default: `8`
-  - Description: Number of retries to attempt
-
-- `retry_max_wait`
-  - Type: `int`
-  - Default: `120`
-  - Description: Maximum wait time (in seconds) between retry attempts
-
-- `retry_min_wait`
-  - Type: `int`
-  - Default: `15`
-  - Description: Minimum wait time (in seconds) between retry attempts
-
-- `retry_multiplier`
-  - Type: `float`
-  - Default: `2.0`
-  - Description: Multiplier for exponential backoff calculation
-
-**Advanced Options**
-- `drop_params`
-  - Type: `bool`
-  - Default: `false`
-  - Description: Drop any unmapped (unsupported) params without causing an exception
-
-- `caching_prompt`
-  - Type: `bool`
-  - Default: `true`
-  - Description: Using the prompt caching feature if provided by the LLM and supported
-
-- `ollama_base_url`
-  - Type: `str`
-  - Default: `""`
-  - Description: Base URL for the OLLAMA API
-
-- `temperature`
-  - Type: `float`
-  - Default: `0.0`
-  - Description: Temperature for the API
-
-- `timeout`
-  - Type: `int`
-  - Default: `0`
-  - Description: Timeout for the API
-
-- `top_p`
-  - Type: `float`
-  - Default: `1.0`
-  - Description: Top p for the API
-
-- `disable_vision`
-  - Type: `bool`
-  - Default: `None`
-  - Description: If model is vision capable, this option allows to disable image processing (useful for cost reduction)
-
-## Agent Configuration
-
-The agent configuration options are defined in the `[agent]` and `[agent.<agent_name>]` sections of the `config.toml` file.
-
-**Microagent Configuration**
-- `micro_agent_name`
-  - Type: `str`
-  - Default: `""`
-  - Description: Name of the micro agent to use for this agent
-
-**Memory Configuration**
-- `memory_enabled`
-  - Type: `bool`
-  - Default: `false`
-  - Description: Whether long-term memory (embeddings) is enabled
-
-- `memory_max_threads`
-  - Type: `int`
-  - Default: `3`
-  - Description: The maximum number of threads indexing at the same time for embeddings
-
-**LLM Configuration**
-- `llm_config`
-  - Type: `str`
-  - Default: `'your-llm-config-group'`
-  - Description: The name of the LLM config to use
-
-**ActionSpace Configuration**
-- `function_calling`
-  - Type: `bool`
-  - Default: `true`
-  - Description: Whether function calling is enabled
-
-- `codeact_enable_browsing`
-  - Type: `bool`
-  - Default: `false`
-  - Description: Whether browsing delegate is enabled in the action space (only works with function calling)
-
-- `codeact_enable_llm_editor`
-  - Type: `bool`
-  - Default: `false`
-  - Description: Whether LLM editor is enabled in the action space (only works with function calling)
-
-- `codeact_enable_jupyter`
-  - Type: `bool`
-  - Default: `false`
-  - Description: Whether Jupyter is enabled in the action space
-
-**Microagent Usage**
-- `use_microagents`
-  - Type: `bool`
-  - Default: `true`
-  - Description: Whether to use microagents at all
-
-- `disabled_microagents`
-  - Type: `list of str`
-  - Default: `None`
-  - Description: A list of microagents to disable
-
-## Sandbox Configuration
-
-The sandbox configuration options are defined in the `[sandbox]` section of the `config.toml` file.
-
-To use these with the docker command, pass in `-e SANDBOX_<option>`. Example: `-e SANDBOX_TIMEOUT`.
-
-**Execution**
-- `timeout`
-  - Type: `int`
-  - Default: `120`
-  - Description: Sandbox timeout in seconds
-
-- `user_id`
-  - Type: `int`
-  - Default: `1000`
-  - Description: Sandbox user ID
-
-**Container Image**
-- `base_container_image`
-  - Type: `str`
-  - Default: `"nikolaik/python-nodejs:python3.12-nodejs22"`
-  - Description: Container image to use for the sandbox
-
-**Networking**
-- `use_host_network`
-  - Type: `bool`
-  - Default: `false`
-  - Description: Use host network
-
-**Linting and Plugins**
-- `enable_auto_lint`
-  - Type: `bool`
-  - Default: `false`
-  - Description: Enable auto linting after editing
-
-- `initialize_plugins`
-  - Type: `bool`
-  - Default: `true`
-  - Description: Whether to initialize plugins
-
-**Dependencies and Environment**
-- `runtime_extra_deps`
-  - Type: `str`
-  - Default: `""`
-  - Description: Extra dependencies to install in the runtime image
-
-- `runtime_startup_env_vars`
-  - Type: `dict`
-  - Default: `{}`
-  - Description: Environment variables to set at the launch of the runtime
-
-**Evaluation**
-- `browsergym_eval_env`
-  - Type: `str`
-  - Default: `""`
-  - Description: BrowserGym environment to use for evaluation
-
-## Security Configuration
-
-The security configuration options are defined in the `[security]` section of the `config.toml` file.
-
-To use these with the docker command, pass in `-e SECURITY_<option>`. Example: `-e SECURITY_CONFIRMATION_MODE`.
-
-**Confirmation Mode**
-- `confirmation_mode`
-  - Type: `bool`
-  - Default: `false`
-  - Description: Enable confirmation mode
-
-**Security Analyzer**
-- `security_analyzer`
-  - Type: `str`
-  - Default: `""`
-  - Description: The security analyzer to use
-
----
-
-> **Note**: Adjust configurations carefully, especially for memory, security, and network-related settings to ensure optimal performance and security.
-Please note that the configuration options may be subject to change in future versions of OpenHands. It's recommended to refer to the official documentation for the most up-to-date information.

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

@@ -50,7 +50,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.15-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.14-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -59,7 +59,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.15 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.14 \
     python -m openhands.core.cli
 ```
 

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

@@ -73,7 +73,7 @@ The `run_controller()` function is the core of OpenHands's execution. It manages
 
 ## Easiest way to get started: Exploring Existing Benchmarks
 
-We encourage you to review the various evaluation benchmarks available in the [`evaluation/benchmarks/` directory](https://github.com/All-Hands-AI/OpenHands/blob/main/evaluation/benchmarks) of our repository.
+We encourage you to review the various evaluation benchmarks available in the [`evaluation/` directory](https://github.com/All-Hands-AI/OpenHands/blob/main/evaluation) of our repository.
 
 To integrate your own benchmark, we suggest starting with the one that most closely resembles your needs. This approach can significantly streamline your integration process, allowing you to build upon existing structures and adapt them to your specific requirements.
 

docs/modules/usage/how-to/github-action.md

@@ -4,101 +4,13 @@ This guide explains how to use the OpenHands GitHub Action, both within the Open
 
 ## Using the Action in the OpenHands Repository
 
-To use the OpenHands GitHub Action in a repository, you can:
+To use the OpenHands GitHub Action in the OpenHands repository, an OpenHands maintainer can:
 
 1. Create an issue in the repository.
-2. Add the `fix-me` label to the issue or leave a comment on the issue starting with `@openhands-agent`.
-
-The action will automatically trigger and attempt to resolve the issue.
+2. Add the `fix-me` label to the issue.
+3. The action will automatically trigger and attempt to resolve the issue.
 
 ## Installing the Action in a New Repository
 
 To install the OpenHands GitHub Action in your own repository, follow
 the [README for the OpenHands Resolver](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/resolver/README.md).
-
-## Usage Tips
-
-### Iterative resolution
-
-1. Create an issue in the repository.
-2. Add the `fix-me` label to the issue, or leave a comment starting with `@openhands-agent`
-3. Review the attempt to resolve the issue by checking the pull request
-4. Follow up with feedback through general comments, review comments, or inline thread comments
-5. Add the `fix-me` label to the pull request, or address a specific comment by starting with `@openhands-agent`
-
-### Label versus Macro
-
-- Label (`fix-me`): Requests OpenHands to address the **entire** issue or pull request.
-- Macro (`@openhands-agent`): Requests OpenHands to consider only the issue/pull request description and **the specific comment**.
-
-## Advanced Settings
-
-### Add custom repository settings
-
-You can provide custom directions for OpenHands by following the [README for the resolver](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/resolver/README.md#providing-custom-instructions).
-
-### Custom configurations
-
-Github resolver will automatically check for valid [repository secrets](https://docs.github.com/en/actions/security-for-github-actions/security-guides/using-secrets-in-github-actions?tool=webui#creating-secrets-for-a-repository) or [repository variables](https://docs.github.com/en/actions/writing-workflows/choosing-what-your-workflow-does/store-information-in-variables#creating-configuration-variables-for-a-repository) to customize its behavior. The customization options you can set are:
-
-| **Attribute name**               | **Type** | **Purpose**                                                                                         | **Example**                                     |
-| -------------------------------- | -------- | --------------------------------------------------------------------------------------------------- | ----------------------------------------------- |
-| `OPENHANDS_MAX_ITER`             | Variable | Set max limit for agent iterations                                                                  | `OPENHANDS_MAX_ITER=10`                         |
-| `OPENHANDS_MACRO`                | Variable | Customize default macro for invoking the resolver                                                   | `OPENHANDS_MACRO=@resolveit`                    |
-| `OPENHANDS_BASE_CONTAINER_IMAGE` | Variable | Custom Sandbox ([learn more](https://docs.all-hands.dev/modules/usage/how-to/custom-sandbox-guide)) | `OPENHANDS_BASE_CONTAINER_IMAGE="custom_image"` |
-
-## Writing Effective .openhands_instructions Files
-
-The `.openhands_instructions` file is a file that you can put in the root directory of your repository to guide OpenHands in understanding and working with your repository effectively. Here are key tips for writing high-quality instructions:
-
-### Core Principles
-
-1. **Concise but Informative**: Provide a clear, focused overview of the repository that emphasizes the most common actions OpenHands will need to perform.
-
-2. **Repository Structure**: Explain the key directories and their purposes, especially highlighting where different types of code (e.g., frontend, backend) are located.
-
-3. **Development Workflows**: Document the essential commands for:
-
-   - Building and setting up the project
-   - Running tests
-   - Linting and code quality checks
-   - Any environment-specific requirements
-
-4. **Testing Guidelines**: Specify:
-   - Where tests are located
-   - How to run specific test suites
-   - Any testing conventions or requirements
-
-### Example Structure
-
-```markdown
-# Repository Overview
-
-[Brief description of the project]
-
-## General Setup
-
-- Main build command
-- Development environment setup
-- Pre-commit checks
-
-## Backend
-
-- Location and structure
-- Testing instructions
-- Environment requirements
-
-## Frontend
-
-- Setup prerequisites
-- Build and test commands
-- Environment variables
-
-## Additional Guidelines
-
-- Code style requirements
-- Special considerations
-- Common workflows
-```
-
-For a real-world example, refer to the [OpenHands repository's .openhands_instructions](https://github.com/All-Hands-AI/OpenHands/blob/main/.openhands_instructions).

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

@@ -23,75 +23,10 @@ OpenHands provides a user-friendly Graphical User Interface (GUI) mode for inter
 
 OpenHands automatically exports a `GITHUB_TOKEN` to the shell environment if it is available. This can happen in two ways:
 
-1. **Locally (OSS)**: The user directly inputs their GitHub token
-2. **Online (SaaS)**: The token is obtained through GitHub OAuth authentication
+1. Locally (OSS): The user directly inputs their GitHub token.
+2. Online (SaaS): The token is obtained through GitHub OAuth authentication.
 
-#### Setting Up a Local GitHub Token
-
-1. **Generate a Personal Access Token (PAT)**:
-   - Go to GitHub Settings > Developer Settings > Personal Access Tokens > Tokens (classic)
-   - Click "Generate new token (classic)"
-   - Required scopes:
-     - `repo` (Full control of private repositories)
-     - `workflow` (Update GitHub Action workflows)
-     - `read:org` (Read organization data)
-
-2. **Enter Token in OpenHands**:
-   - Click the Settings button (gear icon) in the top right
-   - Navigate to the "GitHub" section
-   - Paste your token in the "GitHub Token" field
-   - Click "Save" to apply the changes
-
-#### Organizational Token Policies
-
-If you're working with organizational repositories, additional setup may be required:
-
-1. **Check Organization Requirements**:
-   - Organization admins may enforce specific token policies
-   - Some organizations require tokens to be created with SSO enabled
-   - Review your organization's [token policy settings](https://docs.github.com/en/organizations/managing-programmatic-access-to-your-organization/setting-a-personal-access-token-policy-for-your-organization)
-
-2. **Verify Organization Access**:
-   - Go to your token settings on GitHub
-   - Look for the organization under "Organization access"
-   - If required, click "Enable SSO" next to your organization
-   - Complete the SSO authorization process
-
-#### OAuth Authentication (Online Mode)
-
-When using OpenHands in online mode, the GitHub OAuth flow:
-
-1. Requests the following permissions:
-   - Repository access (read/write)
-   - Workflow management
-   - Organization read access
-
-2. Authentication steps:
-   - Click "Sign in with GitHub" when prompted
-   - Review the requested permissions
-   - Authorize OpenHands to access your GitHub account
-   - If using an organization, authorize organization access if prompted
-
-#### Troubleshooting
-
-Common issues and solutions:
-
-1. **Token Not Recognized**:
-   - Ensure the token is properly saved in settings
-   - Check that the token hasn't expired
-   - Verify the token has the required scopes
-   - Try regenerating the token
-
-2. **Organization Access Denied**:
-   - Check if SSO is required but not enabled
-   - Verify organization membership
-   - Contact organization admin if token policies are blocking access
-
-3. **Verifying Token Works**:
-   - The app will show a green checkmark if the token is valid
-   - Try accessing a repository to confirm permissions
-   - Check the browser console for any error messages
-   - Use the "Test Connection" button in settings if available
+When you reach the `/app` route, the app checks if a token is present. If it finds one, it sets it in the environment for the agent to use.
 
 ### Advanced Settings
 

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

@@ -44,7 +44,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.15-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.14-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -54,6 +54,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.15 \
-    python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
+    docker.all-hands.dev/all-hands-ai/openhands:0.14 \
+    python -m openhands.core.main -t "write a bash script that prints hi"
 ```

docs/modules/usage/how-to/persist-session-data.md

@@ -1,16 +0,0 @@
-# Persisting Session Data
-
-Using the standard installation, the session data is stored in memory. Currently, if OpenHands' service is restarted,
-previous sessions become invalid (a new secret is generated) and thus not recoverable.
-
-## How to Persist Session Data
-
-### Development Workflow
-In the `config.toml` file, specify the following:
-```
-[core]
-...
-file_store="local"
-file_store_path="/absolute/path/to/openhands/cache/directory"
-jwt_secret="secretpass"
-```

docs/modules/usage/installation.mdx

@@ -11,16 +11,16 @@
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.15-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.14-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.15-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.14-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.15
+    docker.all-hands.dev/all-hands-ai/openhands:0.14
 ```
 
 You can also run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), as an [interactive CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), or using the [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action).

docs/modules/usage/micro-agents.md

@@ -1,213 +0,0 @@
-# Micro-Agents
-
-OpenHands uses specialized micro-agents to handle specific tasks and contexts efficiently. These micro-agents are small, focused components that provide specialized behavior and knowledge for particular scenarios.
-
-## Overview
-
-Micro-agents are defined in markdown files under the `openhands/agenthub/codeact_agent/micro/` directory. Each micro-agent is configured with:
-
-- A unique name
-- The agent type (typically CodeActAgent)
-- Trigger keywords that activate the agent
-- Specific instructions and capabilities
-
-## Available Micro-Agents
-
-### GitHub Agent
-**File**: `github.md`
-**Triggers**: `github`, `git`
-
-The GitHub agent specializes in GitHub API interactions and repository management. It:
-- Has access to a `GITHUB_TOKEN` for API authentication
-- Follows strict guidelines for repository interactions
-- Handles branch management and pull requests
-- Uses the GitHub API instead of web browser interactions
-
-Key features:
-- Branch protection (prevents direct pushes to main/master)
-- Automated PR creation
-- Git configuration management
-- API-first approach for GitHub operations
-
-### NPM Agent
-**File**: `npm.md`
-**Triggers**: `npm`
-
-Specializes in handling npm package management with specific focus on:
-- Non-interactive shell operations
-- Automated confirmation handling using Unix 'yes' command
-- Package installation automation
-
-### Custom Micro-Agents
-
-You can create your own micro-agents by adding new markdown files to the micro-agents directory. Each file should follow this structure:
-
-```markdown
----
-name: agent_name
-agent: CodeActAgent
-triggers:
-- trigger_word1
-- trigger_word2
----
-
-Instructions and capabilities for the micro-agent...
-```
-
-## Best Practices
-
-When working with micro-agents:
-
-1. **Use Appropriate Triggers**: Ensure your commands include the relevant trigger words to activate the correct micro-agent
-2. **Follow Agent Guidelines**: Each agent has specific instructions and limitations - respect these for optimal results
-3. **API-First Approach**: When available, use API endpoints rather than web interfaces
-4. **Automation Friendly**: Design commands that work well in non-interactive environments
-
-## Integration
-
-Micro-agents are automatically integrated into OpenHands' workflow. They:
-- Monitor incoming commands for their trigger words
-- Activate when relevant triggers are detected
-- Apply their specialized knowledge and capabilities
-- Follow their specific guidelines and restrictions
-
-## Example Usage
-
-```bash
-# GitHub agent example
-git checkout -b feature-branch
-git commit -m "Add new feature"
-git push origin feature-branch
-
-# NPM agent example
-yes | npm install package-name
-```
-
-For more information about specific agents, refer to their individual documentation files in the micro-agents directory.
-
-## Contributing a Micro-Agent
-
-To contribute a new micro-agent to OpenHands, follow these guidelines:
-
-### 1. Planning Your Micro-Agent
-
-Before creating a micro-agent, consider:
-- What specific problem or use case will it address?
-- What unique capabilities or knowledge should it have?
-- What trigger words make sense for activating it?
-- What constraints or guidelines should it follow?
-
-### 2. File Structure
-
-Create a new markdown file in `openhands/agenthub/codeact_agent/micro/` with a descriptive name (e.g., `docker.md` for a Docker-focused agent).
-
-### 3. Required Components
-
-Your micro-agent file must include:
-
-1. **Front Matter**: YAML metadata at the start of the file:
-```markdown
----
-name: your_agent_name
-agent: CodeActAgent
-triggers:
-- trigger_word1
-- trigger_word2
----
-```
-
-2. **Instructions**: Clear, specific guidelines for the agent's behavior:
-```markdown
-You are responsible for [specific task/domain].
-
-Key responsibilities:
-1. [Responsibility 1]
-2. [Responsibility 2]
-
-Guidelines:
-- [Guideline 1]
-- [Guideline 2]
-
-Examples of usage:
-[Example 1]
-[Example 2]
-```
-
-### 4. Best Practices for Micro-Agent Development
-
-1. **Clear Scope**: Keep the agent focused on a specific domain or task
-2. **Explicit Instructions**: Provide clear, unambiguous guidelines
-3. **Useful Examples**: Include practical examples of common use cases
-4. **Safety First**: Include necessary warnings and constraints
-5. **Integration Awareness**: Consider how the agent interacts with other components
-
-### 5. Testing Your Micro-Agent
-
-Before submitting:
-1. Test the agent with various prompts
-2. Verify trigger words activate the agent correctly
-3. Ensure instructions are clear and comprehensive
-4. Check for potential conflicts with existing agents
-
-### 6. Example Implementation
-
-Here's a template for a new micro-agent:
-
-```markdown
----
-name: docker
-agent: CodeActAgent
-triggers:
-- docker
-- container
----
-
-You are responsible for Docker container management and Dockerfile creation.
-
-Key responsibilities:
-1. Create and modify Dockerfiles
-2. Manage container lifecycle
-3. Handle Docker Compose configurations
-
-Guidelines:
-- Always use official base images when possible
-- Include necessary security considerations
-- Follow Docker best practices for layer optimization
-
-Examples:
-1. Creating a Dockerfile:
-   ```dockerfile
-   FROM node:18-alpine
-   WORKDIR /app
-   COPY package*.json ./
-   RUN npm install
-   COPY . .
-   CMD ["npm", "start"]
-   ```
-
-2. Docker Compose usage:
-   ```yaml
-   version: '3'
-   services:
-     web:
-       build: .
-       ports:
-         - "3000:3000"
-   ```
-
-Remember to:
-- Validate Dockerfile syntax
-- Check for security vulnerabilities
-- Optimize for build time and image size
-```
-
-### 7. Submission Process
-
-1. Create your micro-agent file in the correct directory
-2. Test thoroughly
-3. Submit a pull request with:
-   - The new micro-agent file
-   - Updated documentation if needed
-   - Description of the agent's purpose and capabilities
-
-Remember that micro-agents are a powerful way to extend OpenHands' capabilities in specific domains. Well-designed agents can significantly improve the system's ability to handle specialized tasks.

docs/modules/usage/prompting-best-practices.md

@@ -2,11 +2,6 @@
 
 When working with OpenHands AI software developer, it's crucial to provide clear and effective prompts. This guide outlines best practices for creating prompts that will yield the most accurate and useful responses.
 
-## Table of Contents
-
-- [Characteristics of Good Prompts](#characteristics-of-good-prompts)
-- [Customizing Prompts for your Project](#customizing-prompts-for-your-project)
-
 ## Characteristics of Good Prompts
 
 Good prompts are:
@@ -44,63 +39,3 @@ Good prompts are:
 Remember, the more precise and informative your prompt is, the better the AI can assist you in developing or modifying the OpenHands software.
 
 See [Getting Started with OpenHands](./getting-started) for more examples of helpful prompts.
-
-## Customizing Prompts for your Project
-
-OpenHands can be customized to work more effectively with specific repositories by providing repository-specific context and guidelines. This section explains how to optimize OpenHands for your project.
-
-### Repository Configuration
-
-You can customize OpenHands' behavior for your repository by creating a `.openhands_instructions` file in your repository's root directory. This file should contain:
-
-1. **Repository Overview**: A brief description of your project's purpose and architecture
-2. **Directory Structure**: Key directories and their purposes
-3. **Development Guidelines**: Project-specific coding standards and practices
-4. **Testing Requirements**: How to run tests and what types of tests are required
-5. **Setup Instructions**: Steps needed to build and run the project
-
-Example `.openhands_instructions` file:
-```
-Repository: MyProject
-Description: A web application for task management
-
-Directory Structure:
-- src/: Main application code
-- tests/: Test files
-- docs/: Documentation
-
-Setup:
-- Run `npm install` to install dependencies
-- Use `npm run dev` for development
-- Run `npm test` for testing
-
-Guidelines:
-- Follow ESLint configuration
-- Write tests for all new features
-- Use TypeScript for new code
-```
-
-### Customizing Prompts
-
-When working with a customized repository:
-
-1. **Reference Project Standards**: Mention specific coding standards or patterns used in your project
-2. **Include Context**: Reference relevant documentation or existing implementations
-3. **Specify Testing Requirements**: Include project-specific testing requirements in your prompts
-
-Example customized prompt:
-```
-Add a new task completion feature to src/components/TaskList.tsx following our existing component patterns.
-Include unit tests in tests/components/ and update the documentation in docs/features/.
-The component should use our shared styling from src/styles/components.
-```
-
-### Best Practices for Repository Customization
-
-1. **Keep Instructions Updated**: Regularly update your `.openhands_instructions` file as your project evolves
-2. **Be Specific**: Include specific paths, patterns, and requirements unique to your project
-3. **Document Dependencies**: List all tools and dependencies required for development
-4. **Include Examples**: Provide examples of good code patterns from your project
-5. **Specify Conventions**: Document naming conventions, file organization, and code style preferences
-
-By customizing OpenHands for your repository, you'll get more accurate and consistent results that align with your project's standards and requirements.

docs/modules/usage/runtimes.md

@@ -16,7 +16,7 @@ some flags being passed to `docker run` that make this possible:
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.15-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.11-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/modules/usage/troubleshooting/troubleshooting.md

@@ -1,44 +1,180 @@
 # 🚧 Troubleshooting
 
+There are some error messages that frequently get reported by users.
+We'll try to make the install process easier, but for now you can look for your error message below and see if there are any workarounds.
+If you find more information or a workaround for one of these issues, please open a *PR* to add details to this file.
+
 :::tip
-OpenHands only supports Windows via WSL. Please be sure to run all commands inside your WSL terminal.
+OpenHands only supports Windows via [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
+Please be sure to run all commands inside your WSL terminal.
+Check out [Notes for WSL on Windows Users](troubleshooting/windows) for some troubleshooting guides.
 :::
 
-### Launch docker client failed
+## Common Issues
 
-**Description**
+* [Unable to connect to Docker](#unable-to-connect-to-docker)
+* [404 Resource not found](#404-resource-not-found)
+* [`make build` getting stuck on package installations](#make-build-getting-stuck-on-package-installations)
+* [Sessions are not restored](#sessions-are-not-restored)
+* [Connection to host.docker.internal timed out](#connection-to-host-docker-internal-timed-out)
 
-When running OpenHands, the following error is seen:
-```
-Launch docker client failed. Please make sure you have installed docker and started docker desktop/daemon.
+### Unable to connect to Docker
+
+[GitHub Issue](https://github.com/All-Hands-AI/OpenHands/issues/1226)
+
+**Symptoms**
+
+```bash
+Error creating controller. Please check Docker is running and visit `https://docs.all-hands.dev/modules/usage/troubleshooting` for more debugging information.
 ```
 
-**Resolution**
+```bash
+docker.errors.DockerException: Error while fetching server API version: ('Connection aborted.', FileNotFoundError(2, 'No such file or directory'))
+```
+
+**Details**
+
+OpenHands uses a Docker container to do its work safely, without potentially breaking your machine.
+
+**Workarounds**
+
+* Run `docker ps` to ensure that docker is running
+* Make sure you don't need `sudo` to run docker [see here](https://www.baeldung.com/linux/docker-run-without-sudo)
+* If you are on a Mac, check the [permissions requirements](https://docs.docker.com/desktop/mac/permission-requirements/) and in particular consider enabling the `Allow the default Docker socket to be used` under `Settings > Advanced` in Docker Desktop.
+* In addition, upgrade your Docker to the latest version under `Check for Updates`
 
-Try these in order:
-* Confirm `docker` is running on your system. You should be able to run `docker ps` in the terminal successfully.
-* If using Docker Desktop, ensure `Settings > Advanced > Allow the default Docker socket to be used` is enabled.
-* Depending on your configuration you may need `Settings > Resources > Network > Enable host networking` enabled in Docker Desktop.
-* Reinstall Docker Desktop.
 ---
+### `404 Resource not found`
 
-# Development Workflow Specific
-### Error building runtime docker image
+**Symptoms**
 
-**Description**
-
-Attempts to start a new session fail, and errors with terms like the following appear in the logs:
-```
-debian-security bookworm-security
-InRelease At least one invalid signature was encountered.
+```python
+Traceback (most recent call last):
+  File "/app/.venv/lib/python3.12/site-packages/litellm/llms/openai.py", line 414, in completion
+    raise e
+  File "/app/.venv/lib/python3.12/site-packages/litellm/llms/openai.py", line 373, in completion
+    response = openai_client.chat.completions.create(**data, timeout=timeout)  # type: ignore
+               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/app/.venv/lib/python3.12/site-packages/openai/_utils/_utils.py", line 277, in wrapper
+    return func(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^
+  File "/app/.venv/lib/python3.12/site-packages/openai/resources/chat/completions.py", line 579, in create
+    return self._post(
+           ^^^^^^^^^^^
+  File "/app/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1232, in post
+    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
+                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/app/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 921, in request
+    return self._request(
+           ^^^^^^^^^^^^^^
+  File "/app/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1012, in _request
+    raise self._make_status_error_from_response(err.response) from None
+openai.NotFoundError: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
 ```
 
-This seems to happen when the hash of an existing external library changes and your local docker instance has
-cached a previous version. To work around this, please try the following:
+**Details**
 
-* Stop any containers where the name has the prefix `openhands-runtime-` :
-  `docker ps --filter name=openhands-runtime- --filter status=running -aq | xargs docker stop`
-* Remove any containers where the name has the prefix `openhands-runtime-` :
-  `docker rmi $(docker images --filter name=openhands-runtime- -q --no-trunc)`
-* Stop and Remove any containers / images where the name has the prefix `openhands-runtime-`
-* Prune containers / images : `docker container prune -f && docker image prune -f`
+This happens when LiteLLM (our library for connecting to different LLM providers) can't find
+the API endpoint you're trying to connect to. Most often this happens for Azure or ollama users.
+
+**Workarounds**
+
+* Check that you've set `LLM_BASE_URL` properly
+* Check that the model is set properly, based on the [LiteLLM docs](https://docs.litellm.ai/docs/providers)
+  * If you're running inside the UI, be sure to set the `model` in the settings modal
+  * If you're running headless (via main.py) be sure to set `LLM_MODEL` in your env/config
+* Make sure you've followed any special instructions for your LLM provider
+  * [Azure](/modules/usage/llms/azure-llms)
+  * [Google](/modules/usage/llms/google-llms)
+* Make sure your API key is correct
+* See if you can connect to the LLM using `curl`
+* Try [connecting via LiteLLM directly](https://github.com/BerriAI/litellm) to test your setup
+
+---
+### `make build` getting stuck on package installations
+
+**Symptoms**
+
+Package installation stuck on `Pending...` without any error message:
+
+```bash
+Package operations: 286 installs, 0 updates, 0 removals
+
+  - Installing certifi (2024.2.2): Pending...
+  - Installing h11 (0.14.0): Pending...
+  - Installing idna (3.7): Pending...
+  - Installing sniffio (1.3.1): Pending...
+  - Installing typing-extensions (4.11.0): Pending...
+```
+
+**Details**
+
+In rare cases, `make build` can seemingly get stuck on package installations
+without any error message.
+
+**Workarounds**
+
+The package installer Poetry may miss a configuration setting for where credentials are to be looked up (keyring).
+
+First check with `env` if a value for `PYTHON_KEYRING_BACKEND` exists.
+If not, run the below command to set it to a known value and retry the build:
+
+```bash
+export PYTHON_KEYRING_BACKEND=keyring.backends.null.Keyring
+```
+
+---
+### Sessions are not restored
+
+**Symptoms**
+
+OpenHands usually asks whether to resume or start a new session when opening the UI.
+But clicking "Resume" still starts a fresh new chat.
+
+**Details**
+
+With a standard installation as of today session data is stored in memory.
+Currently, if OpenHands's service is restarted, previous sessions become
+invalid (a new secret is generated) and thus not recoverable.
+
+**Workarounds**
+
+* Change configuration to make sessions persistent by editing the `config.toml`
+file (in OpenHands's root folder) by specifying a `file_store` and an
+absolute `file_store_path`:
+
+```toml
+file_store="local"
+file_store_path="/absolute/path/to/openhands/cache/directory"
+```
+
+* Add a fixed jwt secret in your .bashrc, like below, so that previous session id's
+should stay accepted.
+
+```bash
+EXPORT JWT_SECRET=A_CONST_VALUE
+```
+
+---
+### Connection to host docker internal timed out
+
+**Symptoms**
+
+When you start the server using the docker command from the main [README](https://github.com/All-Hands-AI/OpenHands/README.md), you get a long timeout
+followed by the a stack trace containing messages like:
+
+* `Connection to host.docker.internal timed out. (connect timeout=310)`
+* `Max retries exceeded with url: /alive`
+
+**Details**
+
+If Docker Engine is installed rather than Docker Desktop, the main command will not work as expected.
+Docker Desktop includes easy DNS configuration for connecting processes running in different containers
+which OpenHands makes use of when the main server is running inside a docker container.
+(Further details: https://forums.docker.com/t/difference-between-docker-desktop-and-docker-engine/124612)
+
+**Workarounds**
+
+* [Install Docker Desktop](https://www.docker.com/products/docker-desktop/)
+* Run OpenHands in [Development Mode](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md),
+  So that the main server is not run inside a container, but still creates dockerized runtime sandboxes.

docs/modules/usage/troubleshooting/windows.md

@@ -0,0 +1,64 @@
+# Notes for WSL on Windows Users
+
+OpenHands only supports Windows via [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
+Please be sure to run all commands inside your WSL terminal.
+
+## Troubleshooting
+
+### Recommendation: Do not run as root user
+
+For security reasons, it is highly recommended to not run OpenHands as the root user, but a user with a non-zero UID.
+
+References:
+
+* [Why it is bad to login as root](https://askubuntu.com/questions/16178/why-is-it-bad-to-log-in-as-root)
+* [Set default user in WSL](https://www.tenforums.com/tutorials/128152-set-default-user-windows-subsystem-linux-distro-windows-10-a.html#option2)
+Hint about the 2nd reference: for Ubuntu users, the command could actually be "ubuntupreview" instead of "ubuntu".
+
+---
+### Error: 'docker' could not be found in this WSL 2 distro.
+
+If you are using Docker Desktop, make sure to start it before calling any docker command from inside WSL.
+Docker also needs to have the WSL integration option activated.
+
+---
+### Poetry Installation
+
+* If you face issues running Poetry even after installing it during the build process, you may need to add its binary path to your environment:
+
+```sh
+export PATH="$HOME/.local/bin:$PATH"
+```
+
+* If make build stops on an error like this:
+
+```sh
+ModuleNotFoundError: no module named <module-name>
+```
+
+This could be an issue with Poetry's cache.
+Try to run these 2 commands after another:
+
+```sh
+rm -r ~/.cache/pypoetry
+make build
+```
+
+---
+### NoneType object has no attribute 'request'
+
+If you are experiencing issues related to networking, such as `NoneType object has no attribute 'request'` when executing `make run`, you may need to configure your WSL2 networking settings. Follow these steps:
+
+* Open or create the `.wslconfig` file located at `C:\Users\%username%\.wslconfig` on your Windows host machine.
+* Add the following configuration to the `.wslconfig` file:
+
+```sh
+[wsl2]
+networkingMode=mirrored
+localhostForwarding=true
+```
+
+* Save the `.wslconfig` file.
+* Restart WSL2 completely by exiting any running WSL2 instances and executing the command `wsl --shutdown` in your command prompt or terminal.
+* After restarting WSL, attempt to execute `make run` again.
+The networking issue should be resolved.

docs/modules/usage/upgrade-guide.md

@@ -0,0 +1,71 @@
+# ⬆️ Upgrade Guide
+
+## 0.8.0 (2024-07-13)
+
+### Config breaking changes
+
+In this release we introduced a few breaking changes to backend configurations.
+If you have only been using OpenHands via frontend (web GUI), nothing needs
+to be taken care of.
+
+Here's a list of breaking changes in configs. They only apply to users who
+use OpenHands CLI via `main.py`. For more detail, see [#2756](https://github.com/All-Hands-AI/OpenHands/pull/2756).
+
+#### Removal of --model-name option from main.py
+
+Please note that `--model-name`, or `-m` option, no longer exists. You should set up the LLM
+configs in `config.toml` or via environmental variables.
+
+#### LLM config groups must be subgroups of 'llm'
+
+Prior to release 0.8, you can use arbitrary name for llm config in `config.toml`, e.g.
+
+```toml
+[gpt-4o]
+model="gpt-4o"
+api_key="<your_api_key>"
+```
+
+and then use `--llm-config` CLI argument to specify the desired LLM config group
+by name. This no longer works. Instead, the config group must be under `llm` group,
+e.g.:
+
+```toml
+[llm.gpt-4o]
+model="gpt-4o"
+api_key="<your_api_key>"
+```
+
+If you have a config group named `llm`, no need to change it, it will be used
+as the default LLM config group.
+
+#### 'agent' group no longer contains 'name' field
+
+Prior to release 0.8, you may or may not have a config group named `agent` that
+looks like this:
+
+```toml
+[agent]
+name="CodeActAgent"
+memory_max_threads=2
+```
+
+Note the `name` field is now removed. Instead, you should put `default_agent` field
+under `core` group, e.g.
+
+```toml
+[core]
+# other configs
+default_agent='CodeActAgent'
+
+[agent]
+llm_config='llm'
+memory_max_threads=2
+
+[agent.CodeActAgent]
+llm_config='gpt-4o'
+```
+
+Note that similar to `llm` subgroups, you can also define `agent` subgroups.
+Moreover, an agent can be associated with a specific LLM config group. For more
+detail, see the examples in `config.template.toml`.

docs/package.json

@@ -15,23 +15,23 @@
     "typecheck": "tsc"
   },
   "dependencies": {
-    "@docusaurus/core": "^3.6.3",
-    "@docusaurus/plugin-content-pages": "^3.6.3",
-    "@docusaurus/preset-classic": "^3.6.3",
-    "@docusaurus/theme-mermaid": "^3.6.3",
+    "@docusaurus/core": "^3.6.0",
+    "@docusaurus/plugin-content-pages": "^3.6.0",
+    "@docusaurus/preset-classic": "^3.6.0",
+    "@docusaurus/theme-mermaid": "^3.6.0",
     "@mdx-js/react": "^3.1.0",
     "clsx": "^2.0.0",
     "prism-react-renderer": "^2.4.0",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
-    "react-icons": "^5.4.0",
-    "react-use": "^17.6.0"
+    "react-icons": "^5.3.0",
+    "react-use": "^17.5.1"
   },
   "devDependencies": {
     "@docusaurus/module-type-aliases": "^3.5.1",
-    "@docusaurus/tsconfig": "^3.6.3",
+    "@docusaurus/tsconfig": "^3.6.0",
     "@docusaurus/types": "^3.5.1",
-    "typescript": "~5.7.2"
+    "typescript": "~5.6.3"
   },
   "browserslist": {
     "production": [

docs/sidebars.ts

@@ -14,20 +14,9 @@ const sidebars: SidebarsConfig = {
       id: 'usage/getting-started',
     },
     {
-      type: 'category',
-      label: 'Prompting',
-      items: [
-        {
-          type: 'doc',
-          label: 'Best Practices',
-          id: 'usage/prompting-best-practices',
-        },
-        {
-          type: 'doc',
-          label: 'Micro-Agents',
-          id: 'usage/micro-agents',
-        },
-      ],
+      type: 'doc',
+      label: 'Prompting Best Practices',
+      id: 'usage/prompting-best-practices',
     },
     {
       type: 'category',
@@ -111,21 +100,11 @@ const sidebars: SidebarsConfig = {
           label: 'Runtime Configuration',
           id: 'usage/runtimes',
         },
-        {
-          type: 'doc',
-          label: 'Configuration Options',
-          id: 'usage/configuration-options',
-        },
         {
           type: 'doc',
           label: 'Custom Sandbox',
           id: 'usage/how-to/custom-sandbox-guide',
         },
-        {
-          type: 'doc',
-          label: 'Persist Session Data',
-          id: 'usage/how-to/persist-session-data',
-        },
       ],
     },
     {

docs/src/components/CustomFooter.tsx

@@ -8,7 +8,7 @@ function CustomFooter() {
     <footer className="custom-footer">
       <div className="footer-content">
         <div className="footer-icons">
-          <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2vbfigwev-G03twSpXaErwzYVD4CFiBg" target="_blank" rel="noopener noreferrer">
+          <a href="https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA" target="_blank" rel="noopener noreferrer">
             <FaSlack />
           </a>
           <a href="https://discord.gg/ESHStjSjD4" target="_blank" rel="noopener noreferrer">

docs/src/components/HomepageHeader/HomepageHeader.tsx

@@ -23,7 +23,7 @@ export function HomepageHeader() {
           <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/openhands-ai/shared_invite/zt-2vbfigwev-G03twSpXaErwzYVD4CFiBg"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community" /></a>
+          <a href="https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community" /></a>
           <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community" /></a>
           <a href="https://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/>

evaluation/EDA/README.md

@@ -4,13 +4,15 @@ This folder contains evaluation harness for evaluating agents on the Entity-dedu
 
 ## Setup Environment and LLM Configuration
 
-Please follow instruction [here](../../README.md#setup) to setup your local development environment and LLM.
+Please follow instruction [here](../README.md#setup) to setup your local development environment and LLM.
+
 
 ## Start the evaluation
 
+
 ```bash
 export OPENAI_API_KEY="sk-XXX"; # This is required for evaluation (to simulate another party of conversation)
-./evaluation/benchmarks/EDA/scripts/run_infer.sh [model_config] [git-version] [agent] [dataset] [eval_limit]
+./evaluation/EDA/scripts/run_infer.sh [model_config] [git-version] [agent] [dataset] [eval_limit]
 ```
 
 where `model_config` is mandatory, while `git-version`, `agent`, `dataset` and `eval_limit` are optional.
@@ -31,12 +33,11 @@ to `CodeActAgent`.
 For example,
 
 ```bash
-./evaluation/benchmarks/EDA/scripts/run_infer.sh eval_gpt4o_2024_05_13 0.6.2 CodeActAgent things
+./evaluation/EDA/scripts/run_infer.sh eval_gpt4o_2024_05_13 0.6.2 CodeActAgent things
 ```
 
 ## Reference
-
-```bibtex
+```
 @inproceedings{zhang2023entity,
   title={Probing the Multi-turn Planning Capabilities of LLMs via 20 Question Games},
   author={Zhang, Yizhe and Lu, Jiarui and Jaitly, Navdeep},

evaluation/EDA/run_infer.py

@@ -4,7 +4,7 @@ import os
 import pandas as pd
 from datasets import load_dataset
 
-from evaluation.benchmarks.EDA.game import Q20Game, Q20GameCelebrity
+from evaluation.EDA.game import Q20Game, Q20GameCelebrity
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,

evaluation/EDA/scripts/run_infer.sh

@@ -21,7 +21,7 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 if [ -z "$DATASET" ]; then
   echo "Dataset not specified, use default 'things'"
@@ -34,13 +34,16 @@ if [ -z "$OPENAI_API_KEY" ]; then
   exit 1
 fi
 
+# IMPORTANT: Because Agent's prompt changes fairly often in the rapidly evolving codebase of OpenHands
+# We need to track the version of Agent in the evaluation to make sure results are comparable
+AGENT_VERSION=v$(poetry run python -c "import openhands.agenthub; from openhands.controller.agent import Agent; print(Agent.get_cls('$AGENT').VERSION)")
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 echo "DATASET: $DATASET"
 
-COMMAND="poetry run python evaluation/benchmarks/EDA/run_infer.py \
+COMMAND="poetry run python evaluation/EDA/run_infer.py \
   --agent-cls $AGENT \
   --llm-config $MODEL_CONFIG \
   --dataset $DATASET \
@@ -48,7 +51,7 @@ COMMAND="poetry run python evaluation/benchmarks/EDA/run_infer.py \
   --max-iterations 20 \
   --OPENAI_API_KEY $OPENAI_API_KEY \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note ${OPENHANDS_VERSION}_${DATASET}"
+  --eval-note ${AGENT_VERSION}_${DATASET}"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/README.md

@@ -6,9 +6,9 @@ This folder contains code and resources to run experiments and evaluations.
 
 ### Setup
 
-Before starting evaluation, follow the instructions [here](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) to setup your local development environment and LLM.
+Before starting evaluation, follow the instructions here [here](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) to setup your local development environment and LLM.
 
-Once you are done with setup, you can follow the benchmark-specific instructions in each subdirectory of the [evaluation directory](#supported-benchmarks).
+Once you are done with setup, you can follow the benchmark-specific instructions in each subdirectory of the evaluation directory.
 Generally these will involve running `run_infer.py` to perform inference with the agents.
 
 ### Implementing and Evaluating an Agent
@@ -42,36 +42,32 @@ temperature = 0.0
 
 ## Supported Benchmarks
 
-The OpenHands evaluation harness supports a wide variety of benchmarks across [software engineering](#software-engineering), [web browsing](#web-browsing), and [miscellaneous assistance](#misc-assistance) tasks.
+The OpenHands evaluation harness supports a wide variety of benchmarks across software engineering, web browsing, and miscellaneous assistance tasks.
 
 ### Software Engineering
 
-- SWE-Bench: [`evaluation/benchmarks/swe_bench`](./benchmarks/swe_bench)
-- HumanEvalFix: [`evaluation/benchmarks/humanevalfix`](./benchmarks/humanevalfix)
-- BIRD: [`evaluation/benchmarks/bird`](./benchmarks/bird)
-- BioCoder: [`evaluation/benchmarks/ml_bench`](./benchmarks/ml_bench)
-- ML-Bench: [`evaluation/benchmarks/ml_bench`](./benchmarks/ml_bench)
-- APIBench: [`evaluation/benchmarks/gorilla`](./benchmarks/gorilla/)
-- ToolQA: [`evaluation/benchmarks/toolqa`](./benchmarks/toolqa/)
-- AiderBench: [`evaluation/benchmarks/aider_bench`](./benchmarks/aider_bench/)
-- Commit0: [`evaluation/benchmarks/commit0_bench`](./benchmarks/commit0_bench/)
-- DiscoveryBench: [`evaluation/benchmarks/discoverybench`](./benchmarks/discoverybench/)
+- SWE-Bench: [`evaluation/swe_bench`](./swe_bench)
+- HumanEvalFix: [`evaluation/humanevalfix`](./humanevalfix)
+- BIRD: [`evaluation/bird`](./bird)
+- BioCoder: [`evaluation/ml_bench`](./ml_bench)
+- ML-Bench: [`evaluation/ml_bench`](./ml_bench)
+- APIBench: [`evaluation/gorilla`](./gorilla/)
+- ToolQA: [`evaluation/toolqa`](./toolqa/)
+- AiderBench: [`evaluation/aider_bench`](./aider_bench/)
 
 ### Web Browsing
 
-- WebArena: [`evaluation/benchmarks/webarena`](./benchmarks/webarena/)
-- MiniWob++: [`evaluation/benchmarks/miniwob`](./benchmarks/miniwob/)
-- Browsing Delegation: [`evaluation/benchmarks/browsing_delegation`](./benchmarks/browsing_delegation/)
+- WebArena: [`evaluation/webarena`](./webarena/)
+- MiniWob++: [`evaluation/miniwob`](./miniwob/)
 
 ### Misc. Assistance
 
-- GAIA: [`evaluation/benchmarks/gaia`](./benchmarks/gaia)
-- GPQA: [`evaluation/benchmarks/gpqa`](./benchmarks/gpqa)
-- AgentBench: [`evaluation/benchmarks/agent_bench`](./benchmarks/agent_bench)
-- MINT: [`evaluation/benchmarks/mint`](./benchmarks/mint)
-- Entity deduction Arena (EDA): [`evaluation/benchmarks/EDA`](./benchmarks/EDA)
-- ProofWriter: [`evaluation/benchmarks/logic_reasoning`](./benchmarks/logic_reasoning)
-- ScienceAgentBench: [`evaluation/benchmarks/scienceagentbench`](./benchmarks/scienceagentbench)
+- GAIA: [`evaluation/gaia`](./gaia)
+- GPQA: [`evaluation/gpqa`](./gpqa)
+- AgentBench: [`evaluation/agent_bench`](./agent_bench)
+- MINT: [`evaluation/mint`](./mint)
+- Entity deduction Arena (EDA): [`evaluation/EDA`](./EDA)
+- ProofWriter: [`evaluation/logic_reasoning`](./logic_reasoning)
 
 ## Result Visualization
 
@@ -83,7 +79,7 @@ You can start your own fork of [our huggingface evaluation outputs](https://hugg
 
 To learn more about how to integrate your benchmark into OpenHands, check out [tutorial here](https://docs.all-hands.dev/modules/usage/how-to/evaluation-harness). Briefly,
 
-- Each subfolder contains a specific benchmark or experiment. For example, [`evaluation/benchmarks/swe_bench`](./benchmarks/swe_bench) should contain
+- Each subfolder contains a specific benchmark or experiment. For example, `evaluation/swe_bench` should contain
 all the preprocessing/evaluation/analysis scripts.
 - Raw data and experimental records should not be stored within this repo.
 - For model outputs, they should be stored at [this huggingface space](https://huggingface.co/spaces/OpenHands/evaluation) for visualization.

evaluation/agent_bench/README.md

@@ -4,12 +4,12 @@ This folder contains evaluation harness for evaluating agents on the [AgentBench
 
 ## Setup Environment and LLM Configuration
 
-Please follow instruction [here](../../README.md#setup) to setup your local development environment and LLM.
+Please follow instruction [here](../README.md#setup) to setup your local development environment and LLM.
 
 ## Start the evaluation
 
 ```bash
-./evaluation/benchmarks/agent_bench/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit]
+./evaluation/agent_bench/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit]
 ```
 
 - `model_config`, e.g. `eval_gpt4_1106_preview`, is the config group name for your
@@ -25,7 +25,7 @@ in order to use `eval_limit`, you must also set `agent`.
 
 Following is the basic command to start the evaluation.
 
-You can update the arguments in the script `evaluation/benchmarks/agent_bench/scripts/run_infer.sh`, such as `--max-iterations`, `--eval-num-workers` and so on.
+You can update the arguments in the script `evaluation/agent_bench/scripts/run_infer.sh`, such as `--max-iterations`, `--eval-num-workers` and so on.
 
 - `--agent-cls`, the agent to use. For example, `CodeActAgent`.
 - `--llm-config`: the LLM configuration to use. For example, `eval_gpt4_1106_preview`.
@@ -34,23 +34,5 @@ You can update the arguments in the script `evaluation/benchmarks/agent_bench/sc
 - `--eval-n-limit`: the number of examples to evaluate. For example, `100`.
 
 ```bash
-./evaluation/benchmarks/agent_bench/scripts/run_infer.sh eval_gpt35_turbo HEAD CodeActAgent 1
+./evaluation/agent_bench/scripts/run_infer.sh eval_gpt35_turbo HEAD CodeActAgent 1
 ```
-
-## Run with Remote Runtime (experimental)
-
-You can run the evaluation using a remote runtime instead of a local Docker container. This is useful when you want to run the evaluation in a cloud environment or when you don't have Docker installed locally.
-
-To use the remote runtime, set the following environment variables:
-
-```bash
-# Required environment variables
-export ALLHANDS_API_KEY="your-api-key"  # Contact the team to get an API key
-export RUNTIME=remote
-export SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev"
-
-# Run the evaluation
-./evaluation/benchmarks/agent_bench/scripts/run_infer.sh llm.eval_gpt4_1106_preview HEAD CodeActAgent 1
-```
-
-The remote runtime will build a container image and run the evaluation in a cloud environment. The results will be saved locally in the same way as when running with a local runtime.

evaluation/agent_bench/run_infer.py

@@ -7,7 +7,7 @@ from typing import Any
 import pandas as pd
 from datasets import load_dataset
 
-from evaluation.benchmarks.agent_bench.helper import (
+from evaluation.agent_bench.helper import (
     FAKE_RESPONSES,
     INST_SUFFIXES,
     compare_results,
@@ -43,16 +43,12 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime='eventstream',
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
-            base_container_image='python:3.12-slim',
+            base_container_image='python:3.12-bookworm',
             enable_auto_lint=True,
             use_host_network=False,
-            api_key=os.environ.get('ALLHANDS_API_KEY', None),
-            remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            keep_runtime_alive=False,
-            remote_runtime_init_timeout=3600,
         ),
         # do not mount workspace
         workspace_base=None,

evaluation/agent_bench/scripts/run_infer.sh

@@ -20,18 +20,18 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
-COMMAND="export PYTHONPATH=evaluation/benchmarks/agent_bench:\$PYTHONPATH && poetry run python evaluation/benchmarks/agent_bench/run_infer.py \
+COMMAND="export PYTHONPATH=evaluation/agent_bench:\$PYTHONPATH && poetry run python evaluation/agent_bench/run_infer.py \
   --agent-cls $AGENT \
   --llm-config $MODEL_CONFIG \
   --max-iterations 30 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note $OPENHANDS_VERSION"
+  --eval-note $AGENT_VERSION"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/aider_bench/README.md

@@ -10,13 +10,13 @@ Hugging Face dataset based on the
 
 ## Setup Environment and LLM Configuration
 
-Please follow instruction [here](../../README.md#setup) to setup your local
+Please follow instruction [here](../README.md#setup) to setup your local
 development environment and LLM.
 
 ## Start the evaluation
 
 ```bash
-./evaluation/benchmarks/aider_bench/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [eval-num-workers] [eval_ids]
+./evaluation/aider_bench/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [eval-num-workers] [eval_ids]
 ```
 
 - `model_config`, e.g. `eval_gpt4_1106_preview`, is the config group name for
@@ -42,7 +42,7 @@ export SKIP_NUM=12 # skip the first 12 instances from the dataset
 Following is the basic command to start the evaluation.
 
 You can update the arguments in the script
-`evaluation/benchmarks/aider_bench/scripts/run_infer.sh`, such as `--max-iterations`,
+`evaluation/aider_bench/scripts/run_infer.sh`, such as `--max-iterations`,
 `--eval-num-workers` and so on:
 
 - `--agent-cls`, the agent to use. For example, `CodeActAgent`.
@@ -53,7 +53,7 @@ You can update the arguments in the script
 - `--eval-ids`: the IDs of the examples to evaluate (comma separated). For example, `"1,3,10"`.
 
 ```bash
-./evaluation/benchmarks/aider_bench/scripts/run_infer.sh eval_gpt35_turbo HEAD CodeActAgent 100 1 "1,3,10"
+./evaluation/aider_bench/scripts/run_infer.sh eval_gpt35_turbo HEAD CodeActAgent 100 1 "1,3,10"
 ```
 
 ### Run Inference on `RemoteRuntime` (experimental)
@@ -61,25 +61,25 @@ You can update the arguments in the script
 This is in limited beta. Contact Xingyao over slack if you want to try this out!
 
 ```bash
-./evaluation/benchmarks/aider_bench/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [eval-num-workers] [eval_ids]
+./evaluation/aider_bench/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [eval-num-workers] [eval_ids]
 
 # Example - This runs evaluation on CodeActAgent for 133 instances on aider_bench test set, with 2 workers running in parallel
 export ALLHANDS_API_KEY="YOUR-API-KEY"
 export RUNTIME=remote
 export SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev"
-./evaluation/benchmarks/aider_bench/scripts/run_infer.sh llm.eval HEAD CodeActAgent 133 2
+./evaluation/aider_bench/scripts/run_infer.sh llm.eval HEAD CodeActAgent 133 2
 ```
 
 ## Summarize Results
 
 ```bash
-poetry run python ./evaluation/benchmarks/aider_bench/scripts/summarize_results.py [path_to_output_jsonl_file]
+poetry run python ./evaluation/aider_bench/scripts/summarize_results.py [path_to_output_jsonl_file]
 ```
 
 Full example:
 
 ```bash
-poetry run python ./evaluation/benchmarks/aider_bench/scripts/summarize_results.py evaluation/evaluation_outputs/outputs/AiderBench/CodeActAgent/claude-3-5-sonnet@20240620_maxiter_30_N_v1.9/output.jsonl
+poetry run python ./evaluation/aider_bench/scripts/summarize_results.py evaluation/evaluation_outputs/outputs/AiderBench/CodeActAgent/claude-3-5-sonnet@20240620_maxiter_30_N_v1.9/output.jsonl
 ```
 
 This will list the instances that passed and the instances that failed. For each

evaluation/aider_bench/run_infer.py

@@ -7,7 +7,7 @@ from typing import Any
 import pandas as pd
 from datasets import load_dataset
 
-from evaluation.benchmarks.aider_bench.helper import (
+from evaluation.aider_bench.helper import (
     FAKE_RESPONSES,
     INST_SUFFIXES,
     INSTRUCTIONS_ADDENDUM,

evaluation/aider_bench/scripts/run_infer.sh

@@ -21,13 +21,13 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
-EVAL_NOTE=$OPENHANDS_VERSION
+EVAL_NOTE=$AGENT_VERSION
 
 # Default to NOT use unit tests.
 if [ -z "$USE_UNIT_TESTS" ]; then
@@ -39,7 +39,7 @@ if [ "$USE_UNIT_TESTS" = true ]; then
   EVAL_NOTE=$EVAL_NOTE-w-test
 fi
 
-COMMAND="export PYTHONPATH=evaluation/benchmarks/aider_bench:\$PYTHONPATH && poetry run python evaluation/benchmarks/aider_bench/run_infer.py \
+COMMAND="export PYTHONPATH=evaluation/aider_bench:\$PYTHONPATH && poetry run python evaluation/aider_bench/run_infer.py \
   --agent-cls $AGENT \
   --llm-config $MODEL_CONFIG \
   --max-iterations 30 \

evaluation/benchmarks/commit0_bench/README.md

@@ -1,81 +0,0 @@
-# Commit0 Evaluation with OpenHands
-
-This folder contains the evaluation harness that we built on top of the original [Commit0](https://commit-0.github.io/) ([paper](TBD)).
-
-The evaluation consists of three steps:
-
-1. Environment setup: [install python environment](../../README.md#development-environment), [configure LLM config](../../README.md#configure-openhands-and-your-llm).
-2. [Run Evaluation](#run-inference-on-commit0-instances): Generate a edit patch for each Commit0 Repo, and get the evaluation results
-
-## Setup Environment and LLM Configuration
-
-Please follow instruction [here](../../README.md#setup) to setup your local development environment and LLM.
-
-## OpenHands Commit0 Instance-level Docker Support
-
-OpenHands supports using the Commit0 Docker for **[inference](#run-inference-on-commit0-instances).
-This is now the default behavior.
-
-## Run Inference on Commit0 Instances
-
-Make sure your Docker daemon is running, and you have ample disk space (at least 200-500GB, depends on the Commit0 set you are running on) for the [instance-level docker image](#openhands-commit0-instance-level-docker-support).
-
-When the `run_infer.sh` script is started, it will automatically pull the `lite` split in Commit0. For example, for instance ID `commit-0/minitorch`, it will try to pull our pre-build docker image `wentingzhao/minitorch` from DockerHub. This image will be used create an OpenHands runtime image where the agent will operate on.
-
-```bash
-./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh [repo_split] [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split]
-
-# Example
-./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 16 100 8 wentingzhao/commit0_combined test
-```
-
-where `model_config` is mandatory, and the rest are optional.
-
-- `repo_split`, e.g. `lite`, is the split of the Commit0 dataset you would like to evaluate on. Available options are `lite`, `all` and each individual repo.
-- `model_config`, e.g. `eval_gpt4_1106_preview`, is the config group name for your
-LLM settings, as defined in your `config.toml`.
-- `git-version`, e.g. `HEAD`, is the git commit hash of the OpenHands version you would
-like to evaluate. It could also be a release tag like `0.6.2`.
-- `agent`, e.g. `CodeActAgent`, is the name of the agent for benchmarks, defaulting
-to `CodeActAgent`.
-- `eval_limit`, e.g. `10`, limits the evaluation to the first `eval_limit` instances. By
-default, the script evaluates the `lite` split of the Commit0 dataset (16 repos). Note:
-in order to use `eval_limit`, you must also set `agent`.
-- `max_iter`, e.g. `20`, is the maximum number of iterations for the agent to run. By
-default, it is set to 30.
-- `num_workers`, e.g. `3`, is the number of parallel workers to run the evaluation. By
-default, it is set to 1.
-- `dataset`, a huggingface dataset name. e.g. `wentingzhao/commit0_combined`, specifies which dataset to evaluate on.
-- `dataset_split`, split for the huggingface dataset. Notice only `test` is supported for Commit0.
-
-Note that the `USE_INSTANCE_IMAGE` environment variable is always set to `true` for Commit0.
-
-Let's say you'd like to run 10 instances using `llm.eval_sonnet` and CodeActAgent,
-
-then your command would be:
-
-```bash
-./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 10 30 1 wentingzhao/commit0_combined test
-```
-
-### Run Inference on `RemoteRuntime` (experimental)
-
-This is in limited beta. Contact Xingyao over slack if you want to try this out!
-
-```bash
-./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh [repo_split] [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split]
-
-# Example - This runs evaluation on CodeActAgent for 10 instances on "wentingzhao/commit0_combined"'s test set, with max 30 iteration per instances, with 1 number of workers running in parallel
-ALLHANDS_API_KEY="YOUR-API-KEY" RUNTIME=remote SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev" EVAL_DOCKER_IMAGE_PREFIX="docker.io/wentingzhao" \
-./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 10 30 1 wentingzhao/commit0_combined test
-```
-
-To clean-up all existing runtime you've already started, run:
-
-```bash
-ALLHANDS_API_KEY="YOUR-API-KEY" ./evaluation/benchmarks/commit0_bench/scripts/cleanup_remote_runtime.sh
-```
-
-### Specify a subset of tasks to run infer
-
-If you would like to specify a list of tasks you'd like to benchmark on, you just need to pass selected repo through `repo_split` option.

evaluation/benchmarks/commit0_bench/run_infer.py

@@ -1,606 +0,0 @@
-import asyncio
-import json
-import os
-from collections import Counter
-from typing import Any
-
-import pandas as pd
-from commit0.harness.constants import SPLIT
-from datasets import load_dataset
-
-import openhands.agenthub
-from evaluation.utils.shared import (
-    EvalException,
-    EvalMetadata,
-    EvalOutput,
-    assert_and_raise,
-    codeact_user_response,
-    make_metadata,
-    prepare_dataset,
-    reset_logger_for_multiprocessing,
-    run_evaluation,
-    update_llm_config_for_completions_logging,
-)
-from openhands.controller.state.state import State
-from openhands.core.config import (
-    AgentConfig,
-    AppConfig,
-    SandboxConfig,
-    get_llm_config_arg,
-    get_parser,
-)
-from openhands.core.logger import openhands_logger as logger
-from openhands.core.main import create_runtime, run_controller
-from openhands.events.action import CmdRunAction, MessageAction
-from openhands.events.observation import CmdOutputObservation, ErrorObservation
-from openhands.events.serialization.event import event_to_dict
-from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync
-from openhands.utils.shutdown_listener import sleep_if_should_continue
-
-USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
-USE_INSTANCE_IMAGE = os.environ.get('USE_INSTANCE_IMAGE', 'false').lower() == 'true'
-RUN_WITH_BROWSING = os.environ.get('RUN_WITH_BROWSING', 'false').lower() == 'true'
-
-AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
-    'CodeActAgent': codeact_user_response,
-    'CodeActCommit0Agent': codeact_user_response,
-}
-
-
-def _get_commit0_workspace_dir_name(instance: pd.Series) -> str:
-    return instance['repo'].split('/')[1]
-
-
-def get_instruction(instance: pd.Series, metadata: EvalMetadata):
-    workspace_dir_name = _get_commit0_workspace_dir_name(instance)
-    # Prepare instruction
-    test_cmd = instance['test']['test_cmd']
-    test_dir = instance['test']['test_dir']
-    # Instruction based on Anthropic's official trajectory
-    # https://github.com/eschluntz/swe-bench-experiments/tree/main/evaluation/verified/20241022_tools_claude-3-5-sonnet-updated/trajs
-    instruction = (
-        '<uploaded_files>\n'
-        f'/workspace/{workspace_dir_name}\n'
-        '</uploaded_files>\n'
-        f"I've uploaded a python code repository in the directory {workspace_dir_name}. Here is your task:\n\n"
-        'Here is your task:\n\n'
-        '  You need to complete the implementations for all functions (i.e., those with pass\n'
-        '  statements) and pass the unit tests.\n\n'
-        '  Do not change the names of existing functions or classes, as they may be referenced\n'
-        '  from other code like unit tests, etc.\n\n'
-        '  When you generate code, you must maintain the original formatting of the function\n'
-        '  stubs (such as whitespaces), otherwise we will not able to search/replace blocks\n'
-        '  for code modifications, and therefore you will receive a score of 0 for your generated\n'
-        '  code.'
-        '\n\n'
-        'Here is the command to run the unit tests:\n'
-        '<test_command>\n'
-        f'{test_cmd} {test_dir}\n'
-        '</test_command>\n\n'
-        'Make a local git commit for each agent step for all code changes. If there is not change in current step, do not make a commit.'
-    )
-
-    if RUN_WITH_BROWSING:
-        instruction += (
-            '<IMPORTANT!>\n'
-            'You SHOULD NEVER attempt to browse the web. '
-            '</IMPORTANT!>\n'
-        )
-    return instruction
-
-
-# TODO: migrate all swe-bench docker to ghcr.io/openhands
-DOCKER_IMAGE_PREFIX = os.environ.get(
-    'EVAL_DOCKER_IMAGE_PREFIX', 'docker.io/wentingzhao/'
-)
-logger.info(f'Using docker image prefix: {DOCKER_IMAGE_PREFIX}')
-
-
-def get_instance_docker_image(repo_name: str) -> str:
-    return (DOCKER_IMAGE_PREFIX.rstrip('/') + '/' + repo_name).lower() + ':v0'
-
-
-def get_config(
-    instance: pd.Series,
-    metadata: EvalMetadata,
-) -> AppConfig:
-    # COMMIT0_CONTAINER_IMAGE = 'wentingzhao/'
-    assert USE_INSTANCE_IMAGE
-    # We use a different instance image for the each instance of commit0 eval
-    repo_name = instance['repo'].split('/')[1]
-    base_container_image = get_instance_docker_image(repo_name)
-    logger.info(
-        f'Using instance container image: {base_container_image}. '
-        f'Please make sure this image exists. '
-        f'Submit an issue on https://github.com/All-Hands-AI/OpenHands if you run into any issues.'
-    )
-    # else:
-    #     raise
-    # base_container_image = SWE_BENCH_CONTAINER_IMAGE
-    # logger.info(f'Using swe-bench container image: {base_container_image}')
-
-    config = AppConfig(
-        default_agent=metadata.agent_class,
-        run_as_openhands=False,
-        max_iterations=metadata.max_iterations,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
-        sandbox=SandboxConfig(
-            base_container_image=base_container_image,
-            enable_auto_lint=True,
-            use_host_network=False,
-            # large enough timeout, since some testcases take very long to run
-            timeout=300,
-            api_key=os.environ.get('ALLHANDS_API_KEY', None),
-            remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            keep_runtime_alive=False,
-            remote_runtime_init_timeout=3600,
-        ),
-        # do not mount workspace
-        workspace_base=None,
-        workspace_mount_path=None,
-    )
-    config.set_llm_config(
-        update_llm_config_for_completions_logging(
-            metadata.llm_config, metadata.eval_output_dir, instance['instance_id']
-        )
-    )
-    agent_config = AgentConfig(
-        codeact_enable_jupyter=False,
-        codeact_enable_browsing=RUN_WITH_BROWSING,
-        codeact_enable_llm_editor=False,
-    )
-    config.set_agent_config(agent_config)
-    return config
-
-
-def initialize_runtime(
-    runtime: Runtime,
-    instance: pd.Series,  # this argument is not required
-):
-    """Initialize the runtime for the agent.
-
-    This function is called before the runtime is used to run the agent.
-    """
-    logger.info('-' * 30)
-    logger.info('BEGIN Runtime Initialization Fn')
-    logger.info('-' * 30)
-    workspace_dir_name = _get_commit0_workspace_dir_name(instance)
-    obs: CmdOutputObservation
-
-    action = CmdRunAction(
-        command=f'git clone -b commit0_combined https://github.com/{instance["repo"]}.git'
-    )
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        obs.exit_code == 0,
-        f'Failed to git clone -b commit0_combined https://github.com/{instance["repo"]}.git: {str(obs)}',
-    )
-
-    action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        obs.exit_code == 0,
-        f'Failed to cd to /workspace/{workspace_dir_name}: {str(obs)}',
-    )
-
-    action = CmdRunAction(command='git checkout -b openhands')
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        obs.exit_code == 0, f'Failed to git checkout new branch openhands: {str(obs)}'
-    )
-
-    # Install commit0
-    action = CmdRunAction(command='/root/.cargo/bin/uv pip install commit0')
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    # logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        obs.exit_code == 0,
-        f'Failed to install commit0: {str(obs)}',
-    )
-    logger.info('-' * 30)
-    logger.info('END Runtime Initialization Fn')
-    logger.info('-' * 30)
-
-
-def complete_runtime(
-    runtime: Runtime,
-    instance: pd.Series,  # this argument is not required, but it is used to get the workspace_dir_name
-) -> dict[str, Any]:
-    """Complete the runtime for the agent.
-
-    This function is called before the runtime is used to run the agent.
-    If you need to do something in the sandbox to get the correctness metric after
-    the agent has run, modify this function.
-    """
-    logger.info('-' * 30)
-    logger.info('BEGIN Runtime Completion Fn')
-    logger.info('-' * 30)
-    obs: CmdOutputObservation
-    workspace_dir_name = _get_commit0_workspace_dir_name(instance)
-
-    action = CmdRunAction(command='git add .')
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
-        f'Failed to git add -A: {str(obs)}',
-    )
-
-    action = CmdRunAction(command='git commit -m "openhands edits"')
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        isinstance(obs, CmdOutputObservation)
-        and (obs.exit_code == 0 or obs.exit_code == 1),
-        f'Failed to git commit -m "openhands": {str(obs)}',
-    )
-
-    # Generate diff patch compared to base commit, excluding spec.pdf.bz2 files
-    n_retries = 0
-    git_patch = None
-    while n_retries < 5:
-        action = CmdRunAction(
-            command=f"git diff {instance['base_commit']} HEAD -- . ':(exclude)spec.pdf.bz2'"
-        )
-        action.timeout = 600 + 100 * n_retries
-        logger.info(action, extra={'msg_type': 'ACTION'})
-        obs = runtime.run_action(action)
-        # logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-        n_retries += 1
-        if isinstance(obs, CmdOutputObservation):
-            if obs.exit_code == 0:
-                git_patch = obs.content.strip()
-                break
-            else:
-                logger.info('Failed to get git diff, retrying...')
-                sleep_if_should_continue(10)
-        elif isinstance(obs, ErrorObservation):
-            logger.error(f'Error occurred: {obs.content}. Retrying...')
-            sleep_if_should_continue(10)
-        else:
-            assert_and_raise(False, f'Unexpected observation type: {str(obs)}')
-
-    assert_and_raise(git_patch is not None, 'Failed to get git diff (None)')
-
-    test_dir = instance['test']['test_dir']
-    action = CmdRunAction(
-        command=f"{instance['test']['test_cmd']} --json-report --json-report-file=report.json --continue-on-collection-errors {test_dir} > test_output.txt 2>&1"
-    )
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        isinstance(obs, CmdOutputObservation),
-        f'Failed to run test command: {str(obs)}',
-    )
-    # Read test output
-    action = CmdRunAction(command='cat test_output.txt')
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    # logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        isinstance(obs, CmdOutputObservation),
-        f'Failed to read test output: {str(obs)}',
-    )
-    test_output = obs.content.strip()
-    # logger.info(f'Test output: {test_output}')
-
-    # Save pytest exit code
-    action = CmdRunAction(command='echo $?')
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    # logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
-        f'Failed to save pytest exit code: {str(obs)}',
-    )
-    pytest_exit_code = obs.content.strip()
-    # logger.info(f'Pytest exit code: {pytest_exit_code}')
-
-    # Read the test report
-    action = CmdRunAction(command='cat report.json')
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    # logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        isinstance(obs, CmdOutputObservation),
-        f'Failed to read test report: {str(obs)}',
-    )
-    # Get test IDs from instance
-    repo_name = instance['repo'].split('/')[1]
-    repo_name = repo_name.replace('.', '-')
-    action = CmdRunAction(command=f'commit0 get-tests {repo_name}')
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    # logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    test_ids = obs.content.strip().split('\n')
-
-    try:
-        report = json.loads(obs.content)
-        tests = {x['nodeid']: x['call'] for x in report['tests'] if 'call' in x}
-
-        # Calculate test statistics
-        status = []
-        runtimes = []
-        no_runs = 0
-
-        for test_id in test_ids:
-            if test_id in tests and tests[test_id] is not None:
-                status.append(tests[test_id]['outcome'])
-                runtimes.append(tests[test_id]['duration'])
-                no_runs += 1
-            else:
-                status.append('failed')
-                runtimes.append(0)
-
-        status_counts = Counter(status)
-        total_runtime = sum(runtimes) if no_runs > 0 else 0
-        num_passed = status_counts.get('passed', 0) + status_counts.get('xfail', 0)
-        passed_ratio = num_passed / len(status) if status else 0
-
-        eval_result = {
-            'name': workspace_dir_name,
-            'sum': total_runtime,
-            'passed': passed_ratio,
-            'num_passed': num_passed,
-            'num_tests': len(test_ids),
-        }
-
-    except json.JSONDecodeError:
-        logger.error('Failed to parse test report JSON')
-        eval_result = {
-            'name': workspace_dir_name,
-            'sum': 0,
-            'passed': 0,
-            'num_passed': 0,
-            'num_tests': len(test_ids),
-        }
-
-    # Create tarball of workspace
-    temp_zip = runtime.copy_from(f'/workspace/{workspace_dir_name}')
-
-    commit0_dir = os.path.dirname(__file__)
-    persistent_zip = os.path.join(commit0_dir, f'{workspace_dir_name}.zip')
-    with open(temp_zip, 'rb') as src, open(persistent_zip, 'wb') as dst:
-        dst.write(src.read())
-    zip_file = persistent_zip
-    return {
-        'eval_result': eval_result,
-        'git_patch': git_patch,
-        'test_output': test_output,
-        'pytest_exit_code': pytest_exit_code,
-        'zip_file': zip_file,
-    }
-
-
-def process_instance(
-    instance: pd.Series,
-    metadata: EvalMetadata,
-    reset_logger: bool = True,
-) -> EvalOutput:
-    config = get_config(instance, metadata)
-    # Setup the logger properly, so you can run multi-processing to parallelize the evaluation
-    if reset_logger:
-        log_dir = os.path.join(metadata.eval_output_dir, 'infer_logs')
-        reset_logger_for_multiprocessing(logger, instance.instance_id, log_dir)
-    else:
-        logger.info(f'Starting evaluation for instance {instance.instance_id}.')
-
-    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
-    try:
-        initialize_runtime(runtime, instance)
-
-        instruction = get_instruction(instance, metadata)
-
-        # Here's how you can run the agent (similar to the `main` function) and get the final task state
-        state: State | None = asyncio.run(
-            run_controller(
-                config=config,
-                initial_user_action=MessageAction(content=instruction),
-                runtime=runtime,
-                fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN[
-                    metadata.agent_class
-                ],
-            )
-        )
-
-        # if fatal error, throw EvalError to trigger re-run
-        if (
-            state.last_error
-            and 'fatal error during agent execution' in state.last_error
-            and 'stuck in a loop' not in state.last_error
-        ):
-            raise EvalException('Fatal error detected: ' + state.last_error)
-
-        # ======= THIS IS Commit0 specific =======
-        # Get git patch
-        return_val = complete_runtime(runtime, instance)
-        eval_result = return_val['eval_result']
-        git_patch = return_val['git_patch']
-        test_output = return_val['test_output']
-        pytest_exit_code = return_val['pytest_exit_code']
-        zip_file = return_val['zip_file']
-
-        repo_name = instance['repo'].split('/')[1]
-        zip_dest = os.path.join(
-            metadata.eval_output_dir, 'repos', repo_name, f'{repo_name}.zip'
-        )
-        patch_file = os.path.join(
-            metadata.eval_output_dir, 'repos', repo_name, f'{repo_name}_patch.diff'
-        )
-        test_output_file = os.path.join(
-            metadata.eval_output_dir, 'repos', repo_name, f'{repo_name}_test_output.txt'
-        )
-        pytest_exit_code_file = os.path.join(
-            metadata.eval_output_dir,
-            'repos',
-            repo_name,
-            f'{repo_name}_pytest_exit_code.txt',
-        )
-
-        os.makedirs(os.path.dirname(zip_dest), exist_ok=True)
-        os.rename(zip_file, zip_dest)
-
-        write_targets = [
-            (patch_file, git_patch),
-            (test_output_file, test_output),
-            (pytest_exit_code_file, pytest_exit_code),
-        ]
-
-        for write_target in write_targets:
-            with open(write_target[0], 'w') as f:
-                f.write(write_target[1])
-
-        logger.info(
-            f'Got evaluation result for repo {instance.instance_id}:\n--------\n{eval_result}\n--------'
-        )
-    finally:
-        runtime.close()
-    # ==========================================
-
-    # ======= Attempt to evaluate the agent's edits =======
-    # we use eval_infer.sh to evaluate the agent's edits, not here
-    # because the agent may alter the environment / testcases
-    test_result = {
-        'eval_result': eval_result,
-    }
-
-    # If you are working on some simpler benchmark that only evaluates the final model output (e.g., in a MessageAction)
-    # You can simply get the LAST `MessageAction` from the returned `state.history` and parse it for evaluation.
-    if state is None:
-        raise ValueError('State should not be None.')
-
-    # NOTE: this is NO LONGER the event stream, but an agent history that includes delegate agent's events
-    histories = [event_to_dict(event) for event in state.history]
-    metrics = state.metrics.get() if state.metrics else None
-
-    # Save the output
-    output = EvalOutput(
-        instance_id=instance.instance_id,
-        instruction=instruction,
-        instance=instance.to_dict(),
-        test_result=test_result,
-        metadata=metadata,
-        history=histories,
-        metrics=metrics,
-        error=state.last_error if state and state.last_error else None,
-    )
-    return output
-
-
-def commit0_setup(dataset: pd.DataFrame, repo_split: str) -> pd.DataFrame:
-    """Setup Commit0 dataset based on split type.
-
-    Args:
-        dataset: Full Commit0 dataset
-        repo_split: Split type ('all', 'lite' or specific repo name)
-
-    Returns:
-        Filtered dataset based on split type
-    """
-
-    filtered_dataset = pd.concat(
-        [
-            dataset[dataset['repo'].str.split('/').str[1] == repo]
-            for repo in SPLIT.get(repo_split, [])
-        ]
-    )
-
-    # Drop setup column if it exists
-    if 'setup' in filtered_dataset.columns:
-        filtered_dataset = filtered_dataset.drop('setup', axis=1)
-
-    # Replace all forward slashes in instance_id with hyphens
-    filtered_dataset['instance_id'] = filtered_dataset['repo'].str.split('/').str[1]
-
-    return filtered_dataset
-
-
-if __name__ == '__main__':
-    parser = get_parser()
-    parser.add_argument(
-        '--dataset',
-        type=str,
-        default='wentingzhao/commit0_combined',
-        help='dataset to evaluate on, only test split exists for this HF dataset',
-    )
-    parser.add_argument(
-        '--split',
-        type=str,
-        default='test',
-        help='this is the HF dataset split',
-    )
-    parser.add_argument(
-        '--repo-split',
-        type=str,
-        default='lite',
-        help='all, lite, or each repo name',
-    )
-    args, _ = parser.parse_known_args()
-
-    # NOTE: It is preferable to load datasets from huggingface datasets and perform post-processing
-    # so we don't need to manage file uploading to OpenHands's repo
-    dataset = load_dataset(args.dataset, split=args.split)
-
-    commit0_datasets = commit0_setup(dataset.to_pandas(), args.repo_split)
-
-    logger.info(f'Loaded dataset {args.dataset} with reposplit {args.repo_split}')
-
-    llm_config = None
-    if args.llm_config:
-        llm_config = get_llm_config_arg(args.llm_config)
-        llm_config.log_completions = True
-
-    if llm_config is None:
-        raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
-
-    details = {}
-    _agent_cls = openhands.agenthub.Agent.get_cls(args.agent_cls)
-
-    dataset_descrption = (
-        args.dataset.replace('/', '__') + '-' + args.repo_split.replace('/', '__')
-    )
-    metadata = make_metadata(
-        llm_config,
-        dataset_descrption,
-        args.agent_cls,
-        args.max_iterations,
-        args.eval_note,
-        args.eval_output_dir,
-        details=details,
-    )
-
-    output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
-
-    instances = prepare_dataset(commit0_datasets, output_file, args.eval_n_limit)
-
-    run_evaluation(
-        instances,
-        metadata,
-        output_file,
-        args.eval_num_workers,
-        process_instance,
-        timeout_seconds=120 * 60,  # 2 hour PER instance should be more than enough
-    )

evaluation/benchmarks/commit0_bench/scripts/run_infer.sh

@@ -1,125 +0,0 @@
-#!/bin/bash
-set -eo pipefail
-
-source "evaluation/utils/version_control.sh"
-
-REPO_SPLIT=$1
-MODEL_CONFIG=$2
-COMMIT_HASH=$3
-AGENT=$4
-EVAL_LIMIT=$5
-MAX_ITER=$6
-NUM_WORKERS=$7
-DATASET=$8
-SPLIT=$9
-N_RUNS=${10}
-
-if [ -z "$NUM_WORKERS" ]; then
-  NUM_WORKERS=1
-  echo "Number of workers not specified, use default $NUM_WORKERS"
-fi
-checkout_eval_branch
-
-if [ -z "$AGENT" ]; then
-  echo "Agent not specified, use default CodeActAgent"
-  AGENT="CodeActAgent"
-fi
-
-if [ -z "$MAX_ITER" ]; then
-  echo "MAX_ITER not specified, use default 100"
-  MAX_ITER=100
-fi
-
-if [ -z "$USE_INSTANCE_IMAGE" ]; then
-  echo "USE_INSTANCE_IMAGE not specified, use default true"
-  USE_INSTANCE_IMAGE=true
-fi
-
-if [ -z "$RUN_WITH_BROWSING" ]; then
-  echo "RUN_WITH_BROWSING not specified, use default false"
-  RUN_WITH_BROWSING=false
-fi
-
-
-if [ -z "$DATASET" ]; then
-  echo "DATASET not specified, use default wentingzhao/commit0_combined"
-  DATASET="wentingzhao/commit0_combined"
-fi
-
-if [ -z "$REPO_SPLIT" ]; then
-  echo "REPO_SPLIT not specified, use default lite"
-  REPO_SPLIT=0
-fi
-
-if [ -z "$SPLIT" ]; then
-  echo "HF SPLIT not specified, use default test"
-  SPLIT="test"
-fi
-
-export USE_INSTANCE_IMAGE=$USE_INSTANCE_IMAGE
-echo "USE_INSTANCE_IMAGE: $USE_INSTANCE_IMAGE"
-export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
-echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
-
-get_openhands_version
-
-echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
-echo "MODEL_CONFIG: $MODEL_CONFIG"
-echo "DATASET: $DATASET"
-echo "HF SPLIT: $SPLIT"
-echo "REPO SPLIT: $REPO_SPLIT"
-
-# Default to NOT use Hint
-if [ -z "$USE_HINT_TEXT" ]; then
-  export USE_HINT_TEXT=false
-fi
-echo "USE_HINT_TEXT: $USE_HINT_TEXT"
-EVAL_NOTE="$OPENHANDS_VERSION"
-# if not using Hint, add -no-hint to the eval note
-if [ "$USE_HINT_TEXT" = false ]; then
-  EVAL_NOTE="$EVAL_NOTE-no-hint"
-fi
-
-if [ "$RUN_WITH_BROWSING" = true ]; then
-  EVAL_NOTE="$EVAL_NOTE-with-browsing"
-fi
-
-if [ -n "$EXP_NAME" ]; then
-  EVAL_NOTE="$EVAL_NOTE-$EXP_NAME"
-fi
-
-function run_eval() {
-  local eval_note=$1
-  COMMAND="poetry run python evaluation/benchmarks/commit0_bench/run_infer.py \
-    --agent-cls $AGENT \
-    --llm-config $MODEL_CONFIG \
-    --max-iterations $MAX_ITER \
-    --eval-num-workers $NUM_WORKERS \
-    --eval-note $eval_note \
-    --dataset $DATASET \
-    --split $SPLIT \
-    --repo-split $REPO_SPLIT"
-
-  if [ -n "$EVAL_LIMIT" ]; then
-    echo "EVAL_LIMIT: $EVAL_LIMIT"
-    COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
-  fi
-
-  # Run the command
-  eval $COMMAND
-}
-
-unset SANDBOX_ENV_GITHUB_TOKEN # prevent the agent from using the github token to push
-if [ -z "$N_RUNS" ]; then
-  N_RUNS=1
-  echo "N_RUNS not specified, use default $N_RUNS"
-fi
-
-for i in $(seq 1 $N_RUNS); do
-  current_eval_note="$EVAL_NOTE-run_$i"
-  echo "EVAL_NOTE: $current_eval_note"
-  run_eval $current_eval_note
-done
-
-checkout_original_branch

evaluation/benchmarks/swe_bench/scripts/cleanup_remote_runtime.sh

@@ -1,33 +0,0 @@
-#!/bin/bash
-
-
-# API base URL
-BASE_URL="https://runtime.eval.all-hands.dev"
-
-# Get the list of runtimes
-response=$(curl --silent --location --request GET "${BASE_URL}/list" \
-  --header "X-API-Key: ${ALLHANDS_API_KEY}")
-
-n_runtimes=$(echo $response | jq -r '.total')
-echo "Found ${n_runtimes} runtimes. Stopping them..."
-
-runtime_ids=$(echo $response | jq -r '.runtimes | .[].runtime_id')
-
-# Function to stop a single runtime
-stop_runtime() {
-  local runtime_id=$1
-  local counter=$2
-  echo "Stopping runtime ${counter}/${n_runtimes}: ${runtime_id}"
-  curl --silent --location --request POST "${BASE_URL}/stop" \
-    --header "X-API-Key: ${ALLHANDS_API_KEY}" \
-    --header "Content-Type: application/json" \
-    --data-raw "{\"runtime_id\": \"${runtime_id}\"}"
-  echo
-}
-export -f stop_runtime
-export BASE_URL ALLHANDS_API_KEY n_runtimes
-
-# Use GNU Parallel to stop runtimes in parallel
-echo "$runtime_ids" | parallel -j 16 --progress stop_runtime {} {#}
-
-echo "All runtimes have been stopped."

evaluation/benchmarks/swe_bench/scripts/eval/summarize_outputs.py

@@ -1,279 +0,0 @@
-#!/usr/bin/env python3
-import argparse
-import glob
-import json
-import os
-from collections import Counter
-
-import pandas as pd
-
-from openhands.events.serialization import event_from_dict
-from openhands.events.utils import get_pairs_from_events
-
-ERROR_KEYWORDS = [
-    'Agent encountered an error while processing the last action',
-    'APIError',
-    'Action execution failed',
-    'litellm.Timeout: APITimeoutError',
-]
-
-
-def process_file(file_path):
-    with open(file_path, 'r') as file:
-        lines = file.readlines()
-
-    num_lines = len(lines)
-    num_error_lines = 0
-    num_agent_stuck_in_loop = 0
-    num_resolved = 0
-    num_empty_patch = 0
-    num_unfinished_runs = 0
-    error_counter = Counter()
-    main_agent_cost = []
-    editor_cost = []
-    num_turns = []
-
-    for line in lines:
-        _d = json.loads(line)
-
-        if 'metrics' not in _d or _d['metrics'] is None:
-            # this is a failed run
-            num_unfinished_runs += 1
-            continue
-
-        # Cost
-        costs = _d['metrics'].get('costs', [])
-        _cur_main_agent_cost = 0
-        _cur_editor_cost = 0
-        for cost in costs:
-            if isinstance(cost, float):
-                # backward compatible
-                _cur_main_agent_cost += cost
-            else:
-                if 'draft_editor' in cost['model']:
-                    _cur_editor_cost += cost['cost']
-                else:
-                    _cur_main_agent_cost += cost['cost']
-
-        main_agent_cost.append(_cur_main_agent_cost)
-        editor_cost.append(_cur_editor_cost)
-
-        # Turn status
-        history = _d.get('history', [])
-        events = [event_from_dict(event) for event in history]
-        pairs = get_pairs_from_events(events)
-        num_turns.append(len(pairs))
-
-        # Patch & resolve status
-        patch = _d.get('test_result', {}).get('git_patch', '')
-        if patch == '':
-            num_empty_patch += 1
-            continue
-
-        report = _d.get('report', {}) or {}
-        resolved = report.get('resolved', False)
-        if resolved:
-            num_resolved += 1
-
-        # Error
-        error = _d.get('error', None)
-
-        if error is not None and isinstance(error, str):
-            agent_stuck_in_loop = 'Agent got stuck in a loop' in error
-            contains_error = bool(error) and not agent_stuck_in_loop
-            if agent_stuck_in_loop:
-                error_counter['Agent got stuck in a loop'] += 1
-                num_agent_stuck_in_loop += 1
-            elif contains_error:
-                error_counter[error] += 1
-            continue
-
-        for keyword in ERROR_KEYWORDS:
-            if keyword in line:
-                error_counter[keyword] += 1
-                num_error_lines += 1
-                break
-
-    return {
-        'file_path': file_path,
-        'total_instances': num_lines,
-        'resolved': {
-            'count': num_resolved,
-            'percentage': (num_resolved / num_lines * 100) if num_lines > 0 else 0,
-        },
-        'empty_patches': {
-            'count': num_empty_patch,
-            'percentage': (num_empty_patch / num_lines * 100) if num_lines > 0 else 0,
-        },
-        'unfinished_runs': {
-            'count': num_unfinished_runs,
-            'percentage': (num_unfinished_runs / num_lines * 100)
-            if num_lines > 0
-            else 0,
-        },
-        'errors': {
-            'total': num_error_lines,
-            'percentage': (num_error_lines / num_lines * 100) if num_lines > 0 else 0,
-            'stuck_in_loop': {
-                'count': num_agent_stuck_in_loop,
-                'percentage': (num_agent_stuck_in_loop / num_lines * 100)
-                if num_lines > 0
-                else 0,
-            },
-            'breakdown': {
-                str(error): {
-                    'count': count,
-                    'percentage': (count / num_lines * 100) if num_lines > 0 else 0,
-                }
-                for error, count in error_counter.items()
-            },
-        },
-        'costs': {
-            'main_agent': sum(main_agent_cost),
-            'editor': sum(editor_cost),
-            'total': sum(main_agent_cost) + sum(editor_cost),
-        },
-        'statistics': {
-            'avg_turns': sum(num_turns) / num_lines if num_lines > 0 else 0,
-            'costs': {
-                'main_agent': sum(main_agent_cost) / num_lines if num_lines > 0 else 0,
-                'editor': sum(editor_cost) / num_lines if num_lines > 0 else 0,
-                'total': (sum(main_agent_cost) + sum(editor_cost)) / num_lines
-                if num_lines > 0
-                else 0,
-            },
-        },
-    }
-
-
-def aggregate_directory(input_path) -> pd.DataFrame:
-    # Process all output.jsonl files in subdirectories
-    pattern = os.path.join(input_path, '**/output.jsonl')
-    files = glob.glob(pattern, recursive=True)
-    print(f'Processing {len(files)} files from directory {input_path}')
-
-    # Process each file silently and collect results
-    results = []
-    for file_path in files:
-        try:
-            result = process_file(file_path)
-            results.append(result)
-        except Exception as e:
-            print(f'Error processing {file_path}: {str(e)}')
-            import traceback
-
-            traceback.print_exc()
-            continue
-
-    # Convert results to pandas DataFrame and sort by resolve rate
-    df = pd.DataFrame(results)
-
-    # Extract directory name from file path
-    df['directory'] = df['file_path'].apply(
-        lambda x: os.path.basename(os.path.dirname(x))
-    )
-
-    df['resolve_rate'] = df['resolved'].apply(lambda x: x['percentage'])
-    df['empty_patch_rate'] = df['empty_patches'].apply(lambda x: x['percentage'])
-    df['unfinished_rate'] = df['unfinished_runs'].apply(lambda x: x['percentage'])
-    df['avg_turns'] = df['statistics'].apply(lambda x: x['avg_turns'])
-    df['error_rate'] = df['errors'].apply(lambda x: x['percentage'])
-    df['avg_cost'] = df['statistics'].apply(lambda x: x['costs']['total'])
-
-    df = df.sort_values('resolve_rate', ascending=False)
-
-    return df
-
-
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        'input_path', type=str, help='The file or directory to summarize'
-    )
-    parser.add_argument(
-        '--output',
-        type=str,
-        help='Output JSONL file for results',
-        default='summary_results.jsonl',
-    )
-    args = parser.parse_args()
-
-    if os.path.isdir(args.input_path):
-        df = aggregate_directory(args.input_path)
-        # Create the summary string
-        columns = [
-            'directory',
-            'resolve_rate',
-            'empty_patch_rate',
-            'unfinished_rate',
-            'error_rate',
-            'avg_turns',
-            'avg_cost',
-            'total_instances',
-        ]
-        summary_str = df[columns].to_string(
-            float_format=lambda x: '{:.2f}'.format(x),
-            formatters={
-                'directory': lambda x: x[:90]
-            },  # Truncate directory names to 20 chars
-            index=False,
-        )
-
-        # Print to console
-        print('\nResults summary (sorted by resolve rate):')
-        print(summary_str)
-
-        # Save to text file
-        txt_output = args.output.rsplit('.', 1)[0] + '.txt'
-        with open(txt_output, 'w') as f:
-            f.write('Results summary (sorted by resolve rate):\n')
-            f.write(summary_str)
-
-        # Save
-        df.to_json(args.output, lines=True, orient='records')
-        df[columns].to_csv(args.output.rsplit('.', 1)[0] + '.csv', index=False)
-    else:
-        # Process single file with detailed output
-        results = []
-        try:
-            result = process_file(args.input_path)
-            results.append(result)
-
-            # Print detailed results for single file
-            print(f'\nResults for {args.input_path}:')
-            print(
-                f"Number of resolved: {result['resolved']['count']} / {result['total_instances']} ({result['resolved']['percentage']:.2f}%)"
-            )
-            print(
-                f"Number of empty patch: {result['empty_patches']['count']} / {result['total_instances']} ({result['empty_patches']['percentage']:.2f}%)"
-            )
-            print(
-                f"Number of error lines: {result['errors']['total']} / {result['total_instances']} ({result['errors']['percentage']:.2f}%)"
-            )
-            print(
-                f"Number of agent stuck in loop: {result['errors']['stuck_in_loop']['count']} / {result['total_instances']} ({result['errors']['stuck_in_loop']['percentage']:.2f}%)"
-            )
-            print(
-                f"Number of unfinished runs: {result['unfinished_runs']['count']} / {result['total_instances']} ({result['unfinished_runs']['percentage']:.2f}%)"
-            )
-            print(f"Total cost: {result['costs']['total']:.2f} USD")
-            print('## Statistics')
-            print(
-                f"Avg. num of turns per instance: {result['statistics']['avg_turns']:.2f}"
-            )
-            print(
-                f"Avg. agent cost per instance: {result['statistics']['costs']['main_agent']:.2f} USD"
-            )
-            print(
-                f"Avg. editor cost per instance: {result['statistics']['costs']['editor']:.2f} USD"
-            )
-            print(
-                f"Avg. total cost per instance: {result['statistics']['costs']['total']:.2f} USD"
-            )
-
-            print('## Detailed error breakdown:')
-            for error, data in result['errors']['breakdown'].items():
-                print(f"{error}: {data['count']} ({data['percentage']:.2f}%)")
-
-        except Exception as e:
-            print(f'Error processing {args.input_path}: {str(e)}')

evaluation/benchmarks/swe_bench/scripts/eval/verify_costs.py

@@ -1,104 +0,0 @@
-import argparse
-
-import pandas as pd
-
-from openhands.core.logger import openhands_logger as logger
-
-
-def verify_instance_costs(row: pd.Series) -> float:
-    """
-    Verifies that the accumulated_cost matches the sum of individual costs in metrics.
-    Also checks for duplicate consecutive costs which might indicate buggy counting.
-    If the consecutive costs are identical, the file is affected by this bug:
-    https://github.com/All-Hands-AI/OpenHands/issues/5383
-
-    Args:
-        row: DataFrame row containing instance data with metrics
-    Returns:
-        float: The verified total cost for this instance (corrected if needed)
-    """
-    try:
-        metrics = row.get('metrics')
-        if not metrics:
-            logger.warning(f"Instance {row['instance_id']}: No metrics found")
-            return 0.0
-
-        accumulated = metrics.get('accumulated_cost')
-        costs = metrics.get('costs', [])
-
-        if accumulated is None:
-            logger.warning(
-                f"Instance {row['instance_id']}: No accumulated_cost in metrics"
-            )
-            return 0.0
-
-        # Check for duplicate consecutive costs and systematic even-odd pairs
-        has_duplicate = False
-        all_pairs_match = True
-
-        # Check each even-odd pair (0-1, 2-3, etc.)
-        for i in range(0, len(costs) - 1, 2):
-            if abs(costs[i]['cost'] - costs[i + 1]['cost']) < 1e-6:
-                has_duplicate = True
-                logger.debug(
-                    f"Instance {row['instance_id']}: Possible buggy double-counting detected! "
-                    f"Steps {i} and {i+1} have identical costs: {costs[i]['cost']:.2f}"
-                )
-            else:
-                all_pairs_match = False
-                break
-
-        # Calculate total cost, accounting for buggy double counting if detected
-        if len(costs) >= 2 and has_duplicate and all_pairs_match:
-            paired_steps_cost = sum(
-                cost_entry['cost']
-                for cost_entry in costs[: -1 if len(costs) % 2 else None]
-            )
-            real_paired_cost = paired_steps_cost / 2
-
-            unpaired_cost = costs[-1]['cost'] if len(costs) % 2 else 0
-            total_cost = real_paired_cost + unpaired_cost
-
-        else:
-            total_cost = sum(cost_entry['cost'] for cost_entry in costs)
-
-        if not abs(total_cost - accumulated) < 1e-6:
-            logger.warning(
-                f"Instance {row['instance_id']}: Cost mismatch: "
-                f"accumulated: {accumulated:.2f}, sum of costs: {total_cost:.2f}, "
-            )
-
-        return total_cost
-
-    except Exception as e:
-        logger.error(
-            f"Error verifying costs for instance {row.get('instance_id', 'UNKNOWN')}: {e}"
-        )
-        return 0.0
-
-
-def main():
-    parser = argparse.ArgumentParser(
-        description='Verify costs in SWE-bench output file'
-    )
-    parser.add_argument(
-        'input_filepath', type=str, help='Path to the output.jsonl file'
-    )
-    args = parser.parse_args()
-
-    try:
-        # Load and verify the JSONL file
-        df = pd.read_json(args.input_filepath, lines=True)
-        logger.info(f'Loaded {len(df)} instances from {args.input_filepath}')
-
-        # Verify costs for each instance and sum up total
-        total_cost = df.apply(verify_instance_costs, axis=1).sum()
-        logger.info(f'Total verified cost across all instances: ${total_cost:.2f}')
-
-    except Exception as e:
-        logger.error(f'Failed to process file: {e}')
-        raise
-
-
-if __name__ == '__main__':
-    main()

evaluation/biocoder/README.md

@@ -4,14 +4,13 @@ Implements evaluation of agents on BioCoder from the BioCoder benchmark introduc
 
 ## Setup Environment and LLM Configuration
 
-Please follow instruction [here](../../README.md#setup) to setup your local development environment and LLM.
+Please follow instruction [here](../README.md#setup) to setup your local development environment and LLM.
 
 ## BioCoder Docker Image
 
 In the openhands branch of the Biocoder repository, we have slightly modified our original Docker image to work with the OpenHands environment. In the Docker image are testing scripts (`/testing/start_test_openhands.py` and aux files in `/testing_files/`) to assist with evaluation. Additionally, we have installed all dependencies, including OpenJDK, mamba (with Python 3.6), and many system libraries. Notably, we have **not** packaged all repositories into the image, so they are downloaded at runtime.
 
 **Before first execution, pull our Docker image with the following command**
-
 ```bash
 docker pull public.ecr.aws/i5g0m1f6/eval_biocoder:v1.0
 ```
@@ -20,8 +19,9 @@ To reproduce this image, please see the Dockerfile_Openopenhands in the `biocode
 
 ## Start the evaluation
 
+
 ```bash
-./evaluation/benchmarks/biocoder/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit]
+./evaluation/biocoder/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit]
 ```
 
 where `model_config` is mandatory, while `git-version`, `agent`, `dataset` and `eval_limit` are optional.
@@ -43,12 +43,11 @@ with current OpenHands version, then your command would be:
 ## Examples
 
 ```bash
-./evaluation/benchmarks/biocoder/scripts/run_infer.sh eval_gpt4o_2024_05_13 HEAD CodeActAgent 1
+./evaluation/biocoder/scripts/run_infer.sh eval_gpt4o_2024_05_13 HEAD CodeActAgent 1
 ```
 
 ## Reference
-
-```bibtex
+```
 @misc{tang2024biocoder,
       title={BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models},
       author={Xiangru Tang and Bill Qian and Rick Gao and Jiakang Chen and Xinyun Chen and Mark Gerstein},

evaluation/biocoder/run_infer.py

@@ -8,7 +8,7 @@ from typing import Any
 import pandas as pd
 from datasets import load_dataset
 
-from evaluation.benchmarks.biocoder.utils import BiocoderData
+from evaluation.biocoder.utils import BiocoderData
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,

evaluation/biocoder/scripts/run_infer.sh

@@ -21,19 +21,19 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 echo "DATASET: $DATASET"
 
-COMMAND="poetry run python evaluation/benchmarks/biocoder/run_infer.py \
+COMMAND="poetry run python evaluation/biocoder/run_infer.py \
   --agent-cls $AGENT \
   --llm-config $MODEL_CONFIG \
   --max-iterations 10 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note ${OPENHANDS_VERSION}_${DATASET}"
+  --eval-note ${AGENT_VERSION}_${DATASET}"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/bird/scripts/run_infer.sh

@@ -20,18 +20,18 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
-COMMAND="poetry run python evaluation/benchmarks/bird/run_infer.py \
+COMMAND="poetry run python evaluation/bird/run_infer.py \
   --agent-cls $AGENT \
   --llm-config $MODEL_CONFIG \
   --max-iterations 5 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note $OPENHANDS_VERSION" \
+  --eval-note $AGENT_VERSION" \
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/browsing_delegation/README.md

@@ -7,12 +7,12 @@ If so, the browsing performance upper-bound of CodeActAgent will be the performa
 
 ## Setup Environment and LLM Configuration
 
-Please follow instruction [here](../../README.md#setup) to setup your local development environment and LLM.
+Please follow instruction [here](../README.md#setup) to setup your local development environment and LLM.
 
 ## Run Inference
 
 ```bash
-./evaluation/benchmarks/browsing_delegation/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit]
+./evaluation/browsing_delegation/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit]
 # e.g., ./evaluation/swe_bench/scripts/run_infer.sh llm.eval_gpt4_1106_preview_llm HEAD CodeActAgent 300
 ```
 

evaluation/browsing_delegation/scripts/run_infer.sh

@@ -20,15 +20,15 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
-EVAL_NOTE="$OPENHANDS_VERSION"
+EVAL_NOTE="$AGENT_VERSION"
 
-COMMAND="poetry run python evaluation/benchmarks/browsing_delegation/run_infer.py \
+COMMAND="poetry run python evaluation/browsing_delegation/run_infer.py \
   --agent-cls $AGENT \
   --llm-config $MODEL_CONFIG \
   --max-iterations 1 \

evaluation/discoverybench/README.md

@@ -16,7 +16,7 @@
 2. Execute the bash script to start DiscoveryBench Evaluation
 
 ```
-./evaluation/benchmarks/discoverybench/scripts/run_infer.sh [YOUR MODEL CONFIG]
+./evaluation/discoverybench/scripts/run_infer.sh [YOUR MODEL CONFIG]
 ```
 Replace `[YOUR MODEL CONFIG]` with any model the model that you have set up in `config.toml`
 
@@ -27,7 +27,7 @@ When the `run_infer.sh` script is started, it will automatically pull the latest
 
 
 ```
-./evaluation/benchmarks/discoverybench/scripts/run_infer.sh [MODEL_CONFIG] [GIT_COMMIT] [AGENT] [EVAL_LIMIT] [NUM_WORKERS]
+./evaluation/discoverybench/scripts/run_infer.sh [MODEL_CONFIG] [GIT_COMMIT] [AGENT] [EVAL_LIMIT] [NUM_WORKERS]
 ```
 
 - `MODEL_CONFIG`: Name of the model you want to evaluate with

evaluation/discoverybench/run_infer.py

@@ -5,10 +5,10 @@ import os
 import git
 import pandas as pd
 
-from evaluation.benchmarks.discoverybench.eval_utils.eval_w_subhypo_gen import (
+from evaluation.discoverybench.eval_utils.eval_w_subhypo_gen import (
     run_eval_gold_vs_gen_NL_hypo_workflow,
 )
-from evaluation.benchmarks.discoverybench.eval_utils.response_parser import (
+from evaluation.discoverybench.eval_utils.response_parser import (
     extract_gen_hypo_from_logs,
 )
 from evaluation.utils.shared import (
@@ -250,6 +250,9 @@ def process_instance(
 
     config = get_config(metadata)
 
+    # use a session id for concurrent evaluation
+    sid = 'ID_' + str(instance.instance_id)
+
     # Setup the logger properly, so you can run
     # multi-processing to parallelize the evaluation
     if reset_logger:
@@ -281,7 +284,7 @@ def process_instance(
     instruction += AGENT_CLS_TO_INST_SUFFIX[metadata.agent_class]
 
     # Here's how you can run the agent (similar to the `main` function) and get the final task state
-    runtime = create_runtime(config)
+    runtime = create_runtime(config, sid=sid)
     call_async_from_sync(runtime.connect)
     initialize_runtime(runtime, instance.data_files)
 

evaluation/discoverybench/scripts/run_infer.sh

@@ -23,19 +23,19 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
-COMMAND="poetry run python evaluation/benchmarks/discoverybench/run_infer.py \
+COMMAND="poetry run python evaluation/discoverybench/run_infer.py \
   --agent-cls $AGENT \
   --llm-config $MODEL_CONFIG \
   --max-iterations 10 \
   --max-chars 10000000 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note $OPENHANDS_VERSION"
+  --eval-note $AGENT_VERSION"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/gaia/README.md

@@ -4,18 +4,17 @@ This folder contains evaluation harness for evaluating agents on the [GAIA bench
 
 ## Setup Environment and LLM Configuration
 
-Please follow instruction [here](../../README.md#setup) to setup your local development environment and LLM.
+Please follow instruction [here](../README.md#setup) to setup your local development environment and LLM.
 
 ## Run the evaluation
-
 We are using the GAIA dataset hosted on [Hugging Face](https://huggingface.co/datasets/gaia-benchmark/GAIA).
 Please accept the terms and make sure to have logged in on your computer by `huggingface-cli login` before running the evaluation.
 
-Following is the basic command to start the evaluation. Here we are evaluating on the validation set for the `2023_all` split. You can adjust `./evaluation/benchmarks/gaia/scripts/run_infer.sh` to change the subset you want to evaluate on.
+Following is the basic command to start the evaluation. Here we are evaluating on the validation set for the `2023_all` split. You can adjust `./evaluation/gaia/scripts/run_infer.sh` to change the subset you want to evaluate on.
 
 ```bash
-./evaluation/benchmarks/gaia/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [gaia_subset]
-# e.g., ./evaluation/benchmarks/gaia/scripts/run_infer.sh eval_gpt4_1106_preview 0.6.2 CodeActAgent 300
+./evaluation/gaia/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [gaia_subset]
+# e.g., ./evaluation/gaia/scripts/run_infer.sh eval_gpt4_1106_preview 0.6.2 CodeActAgent 300
 ```
 
 where `model_config` is mandatory, while `git-version`, `agent`, `eval_limit` and `gaia_subset` are optional.
@@ -36,14 +35,13 @@ to `CodeActAgent`.
 For example,
 
 ```bash
-./evaluation/benchmarks/gaia/scripts/run_infer.sh eval_gpt4_1106_preview 0.6.2 CodeActAgent 10
+./evaluation/gaia/scripts/run_infer.sh eval_gpt4_1106_preview 0.6.2 CodeActAgent 10
 ```
 
 ## Get score
 
 Then you can get stats by running the following command:
-
 ```bash
-python ./evaluation/benchmarks/gaia/get_score.py \
+python ./evaluation/gaia/get_score.py \
 --file <path_to/output.json>
 ```