Fix issue #5234: [Bug]: [Resolver] Error when parsing the JSON response on success

.github/workflows/eval-runner.yml

@@ -1,4 +1,4 @@
-name: Run SWE-Bench Evaluation
+name: Run Evaluation
 
 on:
   pull_request:
@@ -58,6 +58,24 @@ 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 }}
@@ -125,6 +143,9 @@ 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:
@@ -34,36 +34,7 @@ jobs:
           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:
@@ -87,5 +58,5 @@ 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

@@ -16,26 +16,17 @@ on:
         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]
@@ -110,14 +101,13 @@ 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."
@@ -125,19 +115,6 @@ 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 "$PAT_USERNAME" ]; then
-            echo "Warning: PAT_USERNAME is not set, will use openhands-agent"
-          fi
-
       - name: Set environment variables
         run: |
           if [ -n "${{ github.event.review.body }}" ]; then
@@ -161,8 +138,7 @@ 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 }}" >> $GITHUB_ENV
+          echo "SANDBOX_ENV_GITHUB_TOKEN=${{ secrets.GITHUB_TOKEN }}" >> $GITHUB_ENV
 
           # Set branch variables
           echo "TARGET_BRANCH=${{ inputs.target_branch }}" >> $GITHUB_ENV
@@ -170,7 +146,7 @@ jobs:
       - 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({
@@ -195,9 +171,9 @@ jobs:
 
       - 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: ""
@@ -207,7 +183,7 @@ jobs:
             --issue-number ${{ env.ISSUE_NUMBER }} \
             --issue-type ${{ env.ISSUE_TYPE }} \
             --max-iterations ${{ env.MAX_ITERATIONS }} \
-            --comment-id ${{ env.COMMENT_ID }}
+            --comment-id ${{ env.COMMENT_ID }} \
 
       - name: Check resolution result
         id: check_result
@@ -229,9 +205,9 @@ 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: ""
@@ -253,7 +229,7 @@ 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 }};

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
@@ -57,8 +57,8 @@ If you work for a company that provides a cloud-based runtime, you could help us
 by implementing the [interface specified here](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/base.py).
 
 #### Testing
-When you write code, it is also good to write tests. Please navigate to the [`./tests`](./tests) folder to see existing test suites.
-At the moment, we have two kinds of tests: [`unit`](./tests/unit) and [`integration`](./evaluation/integration_tests). Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
+When you write code, it is also good to write tests. Please navigate to the `tests` folder to see existing test suites.
+At the moment, we have two kinds of tests: `unit` and `integration`. Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
 
 ## Sending Pull Requests to OpenHands
 
@@ -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/>
@@ -38,16 +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 --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'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
@@ -82,7 +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.
 

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.
@@ -237,10 +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/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/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/modules/usage/configuration-options.md

@@ -1,12 +1,13 @@
+---
+id: configuration-options
+title: Configuration Options
+sidebar_label: Configuration Options
+---
+
 # 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
@@ -47,10 +48,10 @@ take precedence.
    - [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**
@@ -177,11 +178,8 @@ The core configuration options are defined in the `[core]` section of the `confi
   - 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`
@@ -326,7 +324,6 @@ To use these with the docker command, pass in `-e LLM_<option>`. Example: `-e LL
   - 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**
@@ -385,11 +382,8 @@ The agent configuration options are defined in the `[agent]` and `[agent.<agent_
   - 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`
@@ -442,11 +436,8 @@ To use these with the docker command, pass in `-e SANDBOX_<option>`. Example: `-
   - 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`
@@ -459,6 +450,7 @@ To use these with the docker command, pass in `-e SECURITY_<option>`. Example: `
   - 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.

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/github-action.md

@@ -37,15 +37,12 @@ the [README for the OpenHands Resolver](https://github.com/All-Hands-AI/OpenHand
 
 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
+### Configure custom macro
 
-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:
+To customize the default macro (`@openhands-agent`):
 
-| **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"` |
+1. [Create a repository variable](https://docs.github.com/en/actions/writing-workflows/choosing-what-your-workflow-does/store-information-in-variables#creating-configuration-variables-for-a-repository) named `OPENHANDS_MACRO`
+2. Assign the variable a custom value
 
 ## Writing Effective .openhands_instructions Files
 
@@ -58,7 +55,6 @@ The `.openhands_instructions` file is a file that you can put in the root direct
 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
@@ -73,29 +69,24 @@ The `.openhands_instructions` file is a file that you can put in the root direct
 
 ```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

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 \
+    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/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/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/package-lock.json

@@ -17,14 +17,14 @@
         "prism-react-renderer": "^2.4.0",
         "react": "^18.3.1",
         "react-dom": "^18.3.1",
-        "react-icons": "^5.4.0",
+        "react-icons": "^5.3.0",
         "react-use": "^17.5.1"
       },
       "devDependencies": {
         "@docusaurus/module-type-aliases": "^3.5.1",
         "@docusaurus/tsconfig": "^3.6.3",
         "@docusaurus/types": "^3.5.1",
-        "typescript": "~5.7.2"
+        "typescript": "~5.6.3"
       },
       "engines": {
         "node": ">=18.0"
@@ -15155,10 +15155,9 @@
       }
     },
     "node_modules/react-icons": {
-      "version": "5.4.0",
-      "resolved": "https://registry.npmjs.org/react-icons/-/react-icons-5.4.0.tgz",
-      "integrity": "sha512-7eltJxgVt7X64oHh6wSWNwwbKTCtMfK35hcjvJS0yxEAhPM8oUKdS3+kqaW1vicIltw+kR2unHaa12S9pPALoQ==",
-      "license": "MIT",
+      "version": "5.3.0",
+      "resolved": "https://registry.npmjs.org/react-icons/-/react-icons-5.3.0.tgz",
+      "integrity": "sha512-DnUk8aFbTyQPSkCfF8dbX6kQjXA9DktMeJqfjrg6cK9vwQVMxmcA3BfP4QoiztVmEHtwlTgLFsPuH2NskKT6eg==",
       "peerDependencies": {
         "react": "*"
       }
@@ -16986,10 +16985,9 @@
       }
     },
     "node_modules/typescript": {
-      "version": "5.7.2",
-      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.7.2.tgz",
-      "integrity": "sha512-i5t66RHxDvVN40HfDd1PsEThGNnlMCMT3jMUuoh9/0TaqWevNontacunWyN02LA9/fIbEWlcHZcgTKb9QoaLfg==",
-      "license": "Apache-2.0",
+      "version": "5.6.3",
+      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.6.3.tgz",
+      "integrity": "sha512-hjcS1mhfuyi4WW8IWtjP7brDrG2cuDZukyrYrSauoXGNgx0S7zceP07adYkJycEr56BOUTNPzbInooiN3fn1qw==",
       "bin": {
         "tsc": "bin/tsc",
         "tsserver": "bin/tsserver"

docs/package.json

@@ -24,14 +24,14 @@
     "prism-react-renderer": "^2.4.0",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
-    "react-icons": "^5.4.0",
+    "react-icons": "^5.3.0",
     "react-use": "^17.5.1"
   },
   "devDependencies": {
     "@docusaurus/module-type-aliases": "^3.5.1",
     "@docusaurus/tsconfig": "^3.6.3",
     "@docusaurus/types": "^3.5.1",
-    "typescript": "~5.7.2"
+    "typescript": "~5.6.3"
   },
   "browserslist": {
     "production": [

docs/sidebars.ts

@@ -44,6 +44,17 @@ const sidebars: SidebarsConfig = {
         },
       ],
     },
+    {
+      type: 'category',
+      label: 'Configuration Options',
+      items: [
+        {
+          type: 'doc',
+          label: 'Overview',
+          id: 'usage/configuration-options',
+        },
+      ],
+    },
     {
       type: 'category',
       label: 'Advanced Configuration',
@@ -100,11 +111,6 @@ const sidebars: SidebarsConfig = {
           label: 'Runtime Configuration',
           id: 'usage/runtimes',
         },
-        {
-          type: 'doc',
-          label: 'Configuration Options',
-          id: 'usage/configuration-options',
-        },
         {
           type: 'doc',
           label: 'Custom Sandbox',

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/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
@@ -42,7 +42,7 @@ 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
 
@@ -83,7 +83,7 @@ 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/benchmarks/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/benchmarks/EDA/README.md

@@ -4,10 +4,12 @@ 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]
@@ -35,8 +37,7 @@ For example,
 ```
 
 ## 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/benchmarks/EDA/scripts/run_infer.sh

@@ -21,7 +21,7 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 if [ -z "$DATASET" ]; then
   echo "Dataset not specified, use default 'things'"
@@ -34,9 +34,12 @@ if [ -z "$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"
 
@@ -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/benchmarks/agent_bench/README.md

@@ -4,7 +4,7 @@ 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
 

evaluation/benchmarks/agent_bench/scripts/run_infer.sh

@@ -20,10 +20,10 @@ 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 \
@@ -31,7 +31,7 @@ COMMAND="export PYTHONPATH=evaluation/benchmarks/agent_bench:\$PYTHONPATH && poe
   --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/benchmarks/aider_bench/README.md

@@ -10,7 +10,7 @@ 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

evaluation/benchmarks/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

evaluation/benchmarks/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
 ```
@@ -20,6 +19,7 @@ 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]
 ```
@@ -47,8 +47,7 @@ with current OpenHands version, then your command would be:
 ```
 
 ## 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/benchmarks/biocoder/scripts/run_infer.sh

@@ -21,10 +21,10 @@ 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"
 
@@ -33,7 +33,7 @@ COMMAND="poetry run python evaluation/benchmarks/biocoder/run_infer.py \
   --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/benchmarks/bird/scripts/run_infer.sh

@@ -20,10 +20,10 @@ 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 \
@@ -31,7 +31,7 @@ COMMAND="poetry run python evaluation/benchmarks/bird/run_infer.py \
   --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/benchmarks/browsing_delegation/README.md

@@ -7,7 +7,7 @@ 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
 

evaluation/benchmarks/browsing_delegation/scripts/run_infer.sh

@@ -20,13 +20,13 @@ 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"
 
 COMMAND="poetry run python evaluation/benchmarks/browsing_delegation/run_infer.py \
   --agent-cls $AGENT \

evaluation/benchmarks/commit0_bench/README.md

@@ -4,18 +4,19 @@ This folder contains the evaluation harness that we built on top of the original
 
 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).
+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.
+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).

evaluation/benchmarks/commit0_bench/scripts/run_infer.sh

@@ -61,10 +61,10 @@ echo "USE_INSTANCE_IMAGE: $USE_INSTANCE_IMAGE"
 export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
 echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
 
-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"
 echo "HF SPLIT: $SPLIT"
@@ -75,7 +75,7 @@ if [ -z "$USE_HINT_TEXT" ]; then
   export USE_HINT_TEXT=false
 fi
 echo "USE_HINT_TEXT: $USE_HINT_TEXT"
-EVAL_NOTE="$OPENHANDS_VERSION"
+EVAL_NOTE="$AGENT_VERSION"
 # if not using Hint, add -no-hint to the eval note
 if [ "$USE_HINT_TEXT" = false ]; then
   EVAL_NOTE="$EVAL_NOTE-no-hint"

evaluation/benchmarks/discoverybench/scripts/run_infer.sh

@@ -23,10 +23,10 @@ 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 \
@@ -35,7 +35,7 @@ COMMAND="poetry run python evaluation/benchmarks/discoverybench/run_infer.py \
   --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/benchmarks/gaia/README.md

@@ -4,10 +4,9 @@ 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.
 
@@ -42,7 +41,6 @@ For example,
 ## Get score
 
 Then you can get stats by running the following command:
-
 ```bash
 python ./evaluation/benchmarks/gaia/get_score.py \
 --file <path_to/output.json>

evaluation/benchmarks/gaia/scripts/run_infer.sh

@@ -21,17 +21,17 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 if [ -z "$LEVELS" ]; then
   LEVELS="2023_level1"
   echo "Levels not specified, use default $LEVELS"
 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 "LEVELS: $LEVELS"
 
@@ -42,7 +42,7 @@ COMMAND="poetry run python ./evaluation/benchmarks/gaia/run_infer.py \
   --level $LEVELS \
   --data-split validation \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note ${OPENHANDS_VERSION}_${LEVELS}"
+  --eval-note ${AGENT_VERSION}_${LEVELS}"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/gorilla/README.md

@@ -4,7 +4,7 @@ This folder contains evaluation harness we built on top of the original [Gorilla
 
 ## 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 on APIBench Instances
 

evaluation/benchmarks/gorilla/scripts/run_infer.sh

@@ -21,7 +21,7 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 if [ -z "$HUBS" ]; then
   HUBS="hf,torch,tf"
@@ -29,7 +29,7 @@ if [ -z "$HUBS" ]; then
 fi
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 echo "HUBS: $HUBS"
 
@@ -40,7 +40,7 @@ COMMAND="poetry run python evaluation/benchmarks/gorilla/run_infer.py \
   --hubs $HUBS \
   --data-split validation \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note ${OPENHANDS_VERSION}_${LEVELS}"
+  --eval-note ${AGENT_VERSION}_${LEVELS}"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/gpqa/README.md

@@ -3,7 +3,6 @@
 Implements the evaluation of agents on the GPQA benchmark introduced in [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2308.07124).
 
 This code implements the evaluation of agents on the GPQA Benchmark with Open Book setting.
-
 - The benchmark consists of 448 high-quality and extremely difficult multiple-choice questions in the domains of biology, physics, and chemistry. The questions are intentionally designed to be "Google-proof," meaning that even highly skilled non-expert validators achieve only 34% accuracy despite unrestricted access to the web.
 - Even experts in the corresponding domains achieve only 65% accuracy.
 - State-of-the-art AI systems achieve only 39% accuracy on this challenging dataset.
@@ -12,24 +11,20 @@ This code implements the evaluation of agents on the GPQA Benchmark with Open Bo
 Accurate solving of above graduate level questions would require both tool use (e.g., python for calculations) and web-search for finding related facts as information required for the questions might not be part of the LLM knowledge / training data.
 
 Further references:
-
-- <https://arxiv.org/pdf/2311.12022>
-- <https://paperswithcode.com/dataset/gpqa>
-- <https://github.com/idavidrein/gpqa>
+- https://arxiv.org/pdf/2311.12022
+- https://paperswithcode.com/dataset/gpqa
+- https://github.com/idavidrein/gpqa
 
 ## 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 on GPQA Benchmark
-
 'gpqa_main', 'gqpa_diamond', 'gpqa_experts', 'gpqa_extended' -- data split options
 From the root of the OpenHands repo, run the following command:
-
 ```bash
 ./evaluation/benchmarks/gpqa/scripts/run_infer.sh [model_config_name] [git-version] [num_samples_eval] [data_split] [AgentClass]
 ```
-
 You can replace `model_config_name` with any model you set up in `config.toml`.
 
 - `model_config_name`: The model configuration name from `config.toml` that you want to evaluate.

evaluation/benchmarks/gpqa/scripts/run_infer.sh

@@ -27,10 +27,10 @@ if [ -z "$DATA_SPLIT" ]; then
   DATA_SPLIT="gpqa_diamond"
 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/gpqa/run_infer.py \
@@ -39,7 +39,7 @@ COMMAND="poetry run python evaluation/benchmarks/gpqa/run_infer.py \
   --max-iterations 10 \
   --eval-num-workers $NUM_WORKERS \
   --data-split $DATA_SPLIT \
-  --eval-note $OPENHANDS_VERSION"
+  --eval-note $AGENT_VERSION"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/humanevalfix/README.md

@@ -4,7 +4,7 @@ Implements evaluation of agents on HumanEvalFix from the HumanEvalPack benchmark
 
 ## 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 on HumanEvalFix
 
@@ -14,11 +14,13 @@ Please follow instruction [here](../../README.md#setup) to setup your local deve
 
 You can replace `eval_gpt4_1106_preview` with any model you set up in `config.toml`.
 
+
 ## Examples
 
 For each problem, OpenHands is given a set number of iterations to fix the failing code. The history field shows each iteration's response to correct its code that fails any test case.
 
-```json
+
+```
 {
     "task_id": "Python/2",
     "instruction": "Please fix the function in Python__2.py such that all test cases pass.\nEnvironment has been set up for you to start working. You may assume all necessary tools are installed.\n\n# Problem Statement\ndef truncate_number(number: float) -> float:\n    return number % 1.0 + 1.0\n\n\n\n\n\n\ndef check(truncate_number):\n    assert truncate_number(3.5) == 0.5\n    assert abs(truncate_number(1.33) - 0.33) < 1e-6\n    assert abs(truncate_number(123.456) - 0.456) < 1e-6\n\ncheck(truncate_number)\n\nIMPORTANT: You should ONLY interact with the environment provided to you AND NEVER ASK FOR HUMAN HELP.\nYou should NOT modify any existing test case files. If needed, you can add new test cases in a NEW file to reproduce the issue.\nYou SHOULD INCLUDE PROPER INDENTATION in your edit commands.\nWhen you think you have fixed the issue through code changes, please finish the interaction using the "finish" tool.\n",

evaluation/benchmarks/humanevalfix/scripts/run_infer.sh

@@ -58,10 +58,10 @@ 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/humanevalfix/run_infer.py \
@@ -69,7 +69,7 @@ COMMAND="poetry run python evaluation/benchmarks/humanevalfix/run_infer.py \
   --llm-config $MODEL_CONFIG \
   --max-iterations 10 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note $OPENHANDS_VERSION"
+  --eval-note $AGENT_VERSION"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/logic_reasoning/README.md

@@ -4,10 +4,9 @@ This folder contains evaluation harness for evaluating agents on the logic reaso
 
 ## 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 on logic_reasoning
-
 The following code will run inference on the first example of the ProofWriter dataset,
 
 ```bash

evaluation/benchmarks/logic_reasoning/scripts/run_infer.sh

@@ -28,10 +28,10 @@ if [ -z "$DATASET" ]; then
   DATASET="ProofWriter"
 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/logic_reasoning/run_infer.py \
@@ -40,7 +40,7 @@ COMMAND="poetry run python evaluation/benchmarks/logic_reasoning/run_infer.py \
   --dataset $DATASET \
   --max-iterations 10 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note $OPENHANDS_VERSION"
+  --eval-note $AGENT_VERSION"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/miniwob/README.md

@@ -4,7 +4,7 @@ This folder contains evaluation for [MiniWoB++](https://miniwob.farama.org/) ben
 
 ## 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.
 
 ## Test if your environment works
 
@@ -42,6 +42,7 @@ poetry run python evaluation/benchmarks/miniwob/get_success_rate.py evaluation/e
 
 You can start your own fork of [our huggingface evaluation outputs](https://huggingface.co/spaces/OpenHands/evaluation) and submit a PR of your evaluation results following the guide [here](https://huggingface.co/docs/hub/en/repositories-pull-requests-discussions#pull-requests-and-discussions).
 
+
 ## BrowsingAgent V1.0 result
 
 Tested on BrowsingAgent V1.0

evaluation/benchmarks/miniwob/scripts/run_infer.sh

@@ -25,13 +25,13 @@ if [ -z "$AGENT" ]; then
   AGENT="BrowsingAgent"
 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="${OPENHANDS_VERSION}_${NOTE}"
+EVAL_NOTE="${AGENT_VERSION}_${NOTE}"
 
 COMMAND="export PYTHONPATH=evaluation/benchmarks/miniwob:\$PYTHONPATH && poetry run python evaluation/benchmarks/miniwob/run_infer.py \
   --agent-cls $AGENT \

evaluation/benchmarks/mint/scripts/run_infer.sh

@@ -18,10 +18,10 @@ checkout_eval_branch
 # Only 'CodeActAgent' is supported for MINT now
 AGENT="CodeActAgent"
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 
 export PYTHONPATH=$(pwd)
 

evaluation/benchmarks/ml_bench/README.md

@@ -12,7 +12,7 @@ For more details on the ML-Bench task and dataset, please refer to the paper: [M
 
 ## 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 on ML-Bench
 

evaluation/benchmarks/ml_bench/scripts/run_infer.sh

@@ -26,10 +26,10 @@ 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/ml_bench/run_infer.py \
@@ -37,7 +37,7 @@ COMMAND="poetry run python evaluation/benchmarks/ml_bench/run_infer.py \
   --llm-config $MODEL_CONFIG \
   --max-iterations 10 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note $OPENHANDS_VERSION"
+  --eval-note $AGENT_VERSION"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/scienceagentbench/README.md

@@ -1,10 +1,10 @@
 # ScienceAgentBench Evaluation with OpenHands
 
-This folder contains the evaluation harness for [ScienceAgentBench](https://osu-nlp-group.github.io/ScienceAgentBench/) (paper: <https://arxiv.org/abs/2410.05080>).
+This folder contains the evaluation harness for [ScienceAgentBench](https://osu-nlp-group.github.io/ScienceAgentBench/) (paper: https://arxiv.org/abs/2410.05080).
 
 ## 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.
 
 ## Setup ScienceAgentBench
 
@@ -45,7 +45,6 @@ After the inference is completed, you may use the following command to extract n
 ```bash
 python post_proc.py [log_fname]
 ```
-
 - `log_fname`, e.g. `evaluation/.../output.jsonl`, is the automatically saved trajectory log of an OpenHands agent.
 
 Output will be write to e.g. `evaluation/.../output.converted.jsonl`

evaluation/benchmarks/scienceagentbench/scripts/run_infer.sh

@@ -26,10 +26,10 @@ if [ -z "$USE_KNOWLEDGE" ]; then
   USE_KNOWLEDGE=false
 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/scienceagentbench/run_infer.py \
@@ -38,7 +38,7 @@ COMMAND="poetry run python evaluation/benchmarks/scienceagentbench/run_infer.py
   --use_knowledge $USE_KNOWLEDGE \
   --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/benchmarks/swe_bench/README.md

@@ -6,19 +6,20 @@ This folder contains the evaluation harness that we built on top of the original
 
 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), and [pull docker](#openhands-swe-bench-instance-level-docker-support).
+1. Environment setup: [install python environment](../README.md#development-environment), [configure LLM config](../README.md#configure-openhands-and-your-llm), and [pull docker](#openhands-swe-bench-instance-level-docker-support).
 2. [Run inference](#run-inference-on-swe-bench-instances): Generate a edit patch for each Github issue
 3. [Evaluate patches using SWE-Bench docker](#evaluate-generated-patches)
 
 ## 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.
 
 ## OpenHands SWE-Bench Instance-level Docker Support
 
 OpenHands now support using the [official evaluation docker](https://github.com/princeton-nlp/SWE-bench/blob/main/docs/20240627_docker/README.md) for both **[inference](#run-inference-on-swe-bench-instances) and [evaluation](#evaluate-generated-patches)**.
 This is now the default behavior.
 
+
 ## Run Inference on SWE-Bench Instances
 
 Make sure your Docker daemon is running, and you have ample disk space (at least 200-500GB, depends on the SWE-Bench set you are running on) for the [instance-level docker image](#openhands-swe-bench-instance-level-docker-support).
@@ -51,8 +52,7 @@ default, it is set to 1.
 - `dataset_split`, split for the huggingface dataset. e.g., `test`, `dev`. Default to `test`.
 
 There are also two optional environment variables you can set.
-
-```bash
+```
 export USE_HINT_TEXT=true # if you want to use hint text in the evaluation. Default to false. Ignore this if you are not sure.
 export USE_INSTANCE_IMAGE=true # if you want to use instance-level docker images. Default to true
 ```
@@ -127,7 +127,6 @@ With `output.jsonl` file, you can run `eval_infer.sh` to evaluate generated patc
 **This evaluation is performed using the official dockerized evaluation announced [here](https://github.com/princeton-nlp/SWE-bench/blob/main/docs/20240627_docker/README.md).**
 
 > If you want to evaluate existing results, you should first run this to clone existing outputs
->
 >```bash
 >git clone https://huggingface.co/spaces/OpenHands/evaluation evaluation/evaluation_outputs
 >```
@@ -144,7 +143,6 @@ Then you can run the following:
 ```
 
 The script now accepts optional arguments:
-
 - `instance_id`: Specify a single instance to evaluate (optional)
 - `dataset_name`: The name of the dataset to use (default: `"princeton-nlp/SWE-bench_Lite"`)
 - `split`: The split of the dataset to use (default: `"test"`)
@@ -181,6 +179,7 @@ To clean-up all existing runtimes that you've already started, run:
 ALLHANDS_API_KEY="YOUR-API-KEY" ./evaluation/benchmarks/swe_bench/scripts/cleanup_remote_runtime.sh
 ```
 
+
 ## Visualize Results
 
 First you need to clone `https://huggingface.co/spaces/OpenHands/evaluation` and add your own running results from openhands into the `outputs` of the cloned repo.
@@ -190,7 +189,6 @@ git clone https://huggingface.co/spaces/OpenHands/evaluation
 ```
 
 **(optional) setup streamlit environment with conda**:
-
 ```bash
 cd evaluation
 conda create -n streamlit python=3.10

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

@@ -1,12 +1,8 @@
 #!/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
 
@@ -14,21 +10,25 @@ ERROR_KEYWORDS = [
     'Agent encountered an error while processing the last action',
     'APIError',
     'Action execution failed',
-    'litellm.Timeout: APITimeoutError',
 ]
 
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('output_file', type=str, help='The file to summarize')
+    args = parser.parse_args()
 
-def process_file(file_path):
-    with open(file_path, 'r') as file:
+    with open(args.output_file, '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 = []
@@ -36,11 +36,6 @@ def process_file(file_path):
     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
@@ -94,186 +89,30 @@ def process_file(file_path):
                 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))
+    # print the error counter (with percentage)
+    print(
+        f'Number of resolved: {num_resolved} / {num_lines} ({num_resolved / num_lines * 100:.2f}%)'
+    )
+    print(
+        f'Number of empty patch: {num_empty_patch} / {num_lines} ({num_empty_patch / num_lines * 100:.2f}%)'
+    )
+    print(
+        f'Number of error lines: {num_error_lines} / {num_lines} ({num_error_lines / num_lines * 100:.2f}%)'
+    )
+    print(
+        f'Number of agent stuck in loop: {num_agent_stuck_in_loop} / {num_lines} ({num_agent_stuck_in_loop / num_lines * 100:.2f}%)'
+    )
+    assert len(num_turns) == num_lines
+    assert len(main_agent_cost) == num_lines
+    assert len(editor_cost) == num_lines
+    print('## Statistics')
+    print(f'Avg. num of turns per instance: {sum(num_turns) / num_lines:.2f}')
+    print(f'Avg. agent cost per instance: {sum(main_agent_cost) / num_lines:.2f} USD')
+    print(f'Avg. editor cost per instance: {sum(editor_cost) / num_lines:.2f} USD')
+    print(
+        f'Avg. total cost per instance: {(sum(main_agent_cost) + sum(editor_cost)) / num_lines:.2f} USD'
     )
 
-    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)}')
+    print('## Detailed error breakdown:')
+    for error, count in error_counter.items():
+        print(f'{error}: {count} ({count / num_lines * 100:.2f}%)')

evaluation/benchmarks/swe_bench/scripts/run_infer.sh

@@ -55,10 +55,10 @@ echo "USE_INSTANCE_IMAGE: $USE_INSTANCE_IMAGE"
 export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
 echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
 
-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"
 echo "SPLIT: $SPLIT"
@@ -68,7 +68,7 @@ if [ -z "$USE_HINT_TEXT" ]; then
   export USE_HINT_TEXT=false
 fi
 echo "USE_HINT_TEXT: $USE_HINT_TEXT"
-EVAL_NOTE="$OPENHANDS_VERSION"
+EVAL_NOTE="$AGENT_VERSION"
 # if not using Hint, add -no-hint to the eval note
 if [ "$USE_HINT_TEXT" = false ]; then
   EVAL_NOTE="$EVAL_NOTE-no-hint"

evaluation/benchmarks/toolqa/README.md

@@ -4,7 +4,7 @@ This folder contains an evaluation harness we built on top of the original [Tool
 
 ## 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 on ToolQA Instances
 

evaluation/benchmarks/toolqa/scripts/run_infer.sh

@@ -38,10 +38,10 @@ if [ -z "$WOLFRAM_APPID" ]; then
   echo "WOLFRAM_APPID not specified"
 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"
 echo "HARDNESS: $HARDNESS"
@@ -56,7 +56,7 @@ COMMAND="poetry run python evaluation/benchmarks/toolqa/run_infer.py \
   --wolfram_alpha_appid $WOLFRAM_APPID\
   --data-split validation \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note ${OPENHANDS_VERSION}_${LEVELS}"
+  --eval-note ${AGENT_VERSION}_${LEVELS}"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/webarena/README.md

@@ -4,7 +4,7 @@ This folder contains evaluation for [WebArena](https://github.com/web-arena-x/we
 
 ## 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.
 
 ## Setup WebArena Environment
 

evaluation/benchmarks/webarena/scripts/run_infer.sh

@@ -27,13 +27,13 @@ if [ -z "$AGENT" ]; then
   AGENT="BrowsingAgent"
 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/webarena/run_infer.py \
   --agent-cls $AGENT \

evaluation/integration_tests/run_infer.py

@@ -48,19 +48,13 @@ def get_config(
             # use default base_container_image
             enable_auto_lint=True,
             use_host_network=False,
-            timeout=300,
-            # Add platform to the sandbox config to solve issue 4401
-            platform='linux/amd64',
+            timeout=100,
             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,
-        # debug
-        debug=True,
     )
     config.set_llm_config(
         update_llm_config_for_completions_logging(
@@ -113,37 +107,31 @@ def process_instance(
     # =============================================
     # create sandbox and run the agent
     # =============================================
+
     runtime: Runtime = create_runtime(config)
     call_async_from_sync(runtime.connect)
-    try:
-        test_class.initialize_runtime(runtime)
 
-        # 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=FAKE_RESPONSES[metadata.agent_class],
-            )
+    test_class.initialize_runtime(runtime)
+
+    # 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=FAKE_RESPONSES[metadata.agent_class],
         )
-        if state is None:
-            raise ValueError('State should not be None.')
+    )
+    if state is None:
+        raise ValueError('State should not be None.')
 
-        # # =============================================
-        # # result evaluation
-        # # =============================================
+    # # =============================================
+    # # result evaluation
+    # # =============================================
 
-        histories = state.history
-
-        # some basic check
-        logger.info(f'Total events in history: {len(histories)}')
-        assert len(histories) > 0, 'History should not be empty'
-
-        test_result: TestResult = test_class.verify_result(runtime, histories)
-        metrics = state.metrics.get() if state.metrics else None
-    finally:
-        runtime.close()
+    histories = [event_to_dict(event) for event in state.history]
+    test_result: TestResult = test_class.verify_result(runtime, histories)
+    metrics = state.metrics.get() if state.metrics else None
 
     # Save the output
     output = EvalOutput(
@@ -151,7 +139,7 @@ def process_instance(
         instance=instance.to_dict(),
         instruction=instruction,
         metadata=metadata,
-        history=[event_to_dict(event) for event in histories],
+        history=histories,
         metrics=metrics,
         error=state.last_error if state and state.last_error else None,
         test_result=test_result.model_dump(),
@@ -218,8 +206,6 @@ if __name__ == '__main__':
     )
 
     df = pd.read_json(output_file, lines=True, orient='records')
-
-    # record success and reason for failure for the final report
     df['success'] = df['test_result'].apply(lambda x: x['success'])
     df['reason'] = df['test_result'].apply(lambda x: x['reason'])
     logger.info('-' * 100)
@@ -233,16 +219,9 @@ if __name__ == '__main__':
     )
     logger.info('-' * 100)
 
-    # record cost for each instance, with 3 decimal places
-    df['cost'] = df['metrics'].apply(lambda x: round(x['accumulated_cost'], 3))
-    logger.info(f'Total cost: USD {df["cost"].sum():.2f}')
-
     report_file = os.path.join(metadata.eval_output_dir, 'report.md')
     with open(report_file, 'w') as f:
         f.write(
             f'Success rate: {df["success"].mean():.2%} ({df["success"].sum()}/{len(df)})\n'
         )
-        f.write(f'\nTotal cost: USD {df["cost"].sum():.2f}\n')
-        f.write(
-            df[['instance_id', 'success', 'reason', 'cost']].to_markdown(index=False)
-        )
+        f.write(df[['instance_id', 'success', 'reason']].to_markdown(index=False))

evaluation/integration_tests/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

evaluation/integration_tests/tests/t05_simple_browsing.py

@@ -108,8 +108,6 @@ class Test(BaseIntegrationTest):
 
     @classmethod
     def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
-        from openhands.core.logger import openhands_logger as logger
-
         # check if the "The answer is OpenHands is all you need!" is in any message
         message_actions = [
             event
@@ -118,29 +116,19 @@ class Test(BaseIntegrationTest):
                 event, (MessageAction, AgentFinishAction, AgentDelegateObservation)
             )
         ]
-        logger.debug(f'Total message-like events: {len(message_actions)}')
-
         for event in message_actions:
-            try:
-                if isinstance(event, AgentDelegateObservation):
-                    content = event.content
-                elif isinstance(event, AgentFinishAction):
-                    content = event.outputs.get('content', '')
-                elif isinstance(event, MessageAction):
-                    content = event.content
-                else:
-                    logger.warning(f'Unexpected event type: {type(event)}')
-                    continue
+            if isinstance(event, AgentDelegateObservation):
+                content = event.content
+            elif isinstance(event, AgentFinishAction):
+                content = event.outputs.get('content', '')
+            elif isinstance(event, MessageAction):
+                content = event.content
+            else:
+                raise ValueError(f'Unknown event type: {type(event)}')
 
-                if 'OpenHands is all you need!' in content:
-                    return TestResult(success=True)
-            except Exception as e:
-                logger.error(f'Error processing event: {e}')
-
-        logger.debug(
-            f'Total messages: {len(message_actions)}. Messages: {message_actions}'
-        )
+            if 'OpenHands is all you need!' in content:
+                return TestResult(success=True)
         return TestResult(
             success=False,
-            reason=f'The answer is not found in any message. Total messages: {len(message_actions)}.',
+            reason=f'The answer is not found in any message. Total messages: {len(message_actions)}. Messages: {message_actions}',
         )

evaluation/integration_tests/tests/t06_github_pr_browsing.py

@@ -14,9 +14,7 @@ class Test(BaseIntegrationTest):
 
     @classmethod
     def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
-        from openhands.core.logger import openhands_logger as logger
-
-        # check if the license information is in any message
+        # check if the "The answer is OpenHands is all you need!" is in any message
         message_actions = [
             event
             for event in histories
@@ -24,35 +22,23 @@ class Test(BaseIntegrationTest):
                 event, (MessageAction, AgentFinishAction, AgentDelegateObservation)
             )
         ]
-        logger.info(f'Total message-like events: {len(message_actions)}')
-
         for event in message_actions:
-            try:
-                if isinstance(event, AgentDelegateObservation):
-                    content = event.content
-                elif isinstance(event, AgentFinishAction):
-                    content = event.outputs.get('content', '')
-                    if event.thought:
-                        content += f'\n\n{event.thought}'
-                elif isinstance(event, MessageAction):
-                    content = event.content
-                else:
-                    logger.warning(f'Unexpected event type: {type(event)}')
-                    continue
+            if isinstance(event, AgentDelegateObservation):
+                content = event.content
+            elif isinstance(event, AgentFinishAction):
+                content = event.outputs.get('content', '')
+            elif isinstance(event, MessageAction):
+                content = event.content
+            else:
+                raise ValueError(f'Unknown event type: {type(event)}')
 
-                if (
-                    'non-commercial' in content
-                    or 'MIT' in content
-                    or 'Apache 2.0' in content
-                ):
-                    return TestResult(success=True)
-            except Exception as e:
-                logger.error(f'Error processing event: {e}')
-
-        logger.debug(
-            f'Total messages: {len(message_actions)}. Messages: {message_actions}'
-        )
+            if (
+                'non-commercial' in content
+                or 'MIT' in content
+                or 'Apache 2.0' in content
+            ):
+                return TestResult(success=True)
         return TestResult(
             success=False,
-            reason=f'The answer is not found in any message. Total messages: {len(message_actions)}.',
+            reason=f'The answer is not found in any message. Total messages: {len(message_actions)}. Messages: {message_actions}',
         )

evaluation/utils/version_control.sh

@@ -39,8 +39,8 @@ checkout_original_branch() {
     git checkout $current_branch
 }
 
-get_openhands_version() {
+get_agent_version() {
     # 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
-    OPENHANDS_VERSION=v$(poetry run python -c "from openhands import get_version; print(get_version())")
+    AGENT_VERSION=v$(poetry run python -c "import openhands.agenthub; from openhands.controller.agent import Agent; print(Agent.get_cls('$AGENT').VERSION)")
 }

frontend/.gitignore

@@ -7,4 +7,3 @@ node_modules/
 /playwright-report/
 /blob-report/
 /playwright/.cache/
-.react-router/

frontend/README.md

@@ -9,7 +9,6 @@ This is the frontend of the OpenHands project. It is a React application that pr
 - Remix SPA Mode (React + Vite + React Router)
 - TypeScript
 - Redux
-- TanStack Query
 - Tailwind CSS
 - i18next
 - React Testing Library
@@ -86,7 +85,7 @@ frontend
 ├── src
 │   ├── api # API calls
 │   ├── assets
-│   ├── components
+│   ├── components # Reusable components
 │   ├── context # Local state management
 │   ├── hooks # Custom hooks
 │   ├── i18n # Internationalization
@@ -100,18 +99,6 @@ frontend
 └── .env.sample # Sample environment variables
 ```
 
-#### Components
-
-Components are organized into folders based on their **domain**, **feature**, or **shared functionality**.
-
-```sh
-components
-├── features # Domain-specific components
-├── layout
-├── modals
-└── ui # Shared UI components
-```
-
 ### Features
 
 - Real-time updates with WebSockets

frontend/__tests__/components/browser.test.tsx

@@ -1,8 +1,7 @@
 import { screen } from "@testing-library/react";
 import { describe, it, expect } from "vitest";
 import { renderWithProviders } from "../../test-utils";
-import { BrowserPanel } from "#/components/features/browser/browser";
-
+import BrowserPanel from "#/components/browser";
 
 describe("Browser", () => {
   it("renders a message if no screenshotSrc is provided", () => {

frontend/__tests__/components/chat-message.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { describe, it, expect, test } from "vitest";
-import { ChatMessage } from "#/components/features/chat/chat-message";
+import { ChatMessage } from "#/components/chat-message";
 
 describe("ChatMessage", () => {
   it("should render a user message", () => {

frontend/__tests__/components/chat/chat-input.test.tsx

@@ -1,7 +1,7 @@
 import userEvent from "@testing-library/user-event";
 import { fireEvent, render, screen } from "@testing-library/react";
 import { describe, afterEach, vi, it, expect } from "vitest";
-import { ChatInput } from "#/components/features/chat/chat-input";
+import { ChatInput } from "#/components/chat-input";
 
 describe("ChatInput", () => {
   const onSubmitMock = vi.fn();

frontend/__tests__/components/chat/chat-interface.test.tsx

@@ -6,10 +6,10 @@ import { addUserMessage } from "#/state/chat-slice";
 import { SUGGESTIONS } from "#/utils/suggestions";
 import * as ChatSlice from "#/state/chat-slice";
 import { WsClientProviderStatus } from "#/context/ws-client-provider";
-import { ChatInterface } from "#/components/features/chat/chat-interface";
+import { ChatInterface } from "#/routes/_oh.app/chat-interface";
 
 // eslint-disable-next-line @typescript-eslint/no-unused-vars
-const renderChatInterface = (messages: (Message)[]) =>
+const renderChatInterface = (messages: (Message | ErrorMessage)[]) =>
   renderWithProviders(<ChatInterface />);
 
 describe("Empty state", () => {
@@ -26,8 +26,8 @@ describe("Empty state", () => {
   }));
 
   beforeAll(() => {
-    vi.mock("react-router", async (importActual) => ({
-      ...(await importActual<typeof import("react-router")>()),
+    vi.mock("@remix-run/react", async (importActual) => ({
+      ...(await importActual<typeof import("@remix-run/react")>()),
       useRouteLoaderData: vi.fn(() => ({})),
     }));
 
@@ -56,7 +56,6 @@ describe("Empty state", () => {
           content: "Hello",
           imageUrls: [],
           timestamp: new Date().toISOString(),
-          pending: true,
         }),
       );
     });
@@ -173,14 +172,12 @@ describe.skip("ChatInterface", () => {
         content: "Hello",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
       {
         sender: "assistant",
         content: "Hi",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
     ];
     renderChatInterface(messages);
@@ -214,7 +211,6 @@ describe.skip("ChatInterface", () => {
         content: "Here are some images",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
     ];
     const { rerender } = renderChatInterface(messages);
@@ -227,7 +223,6 @@ describe.skip("ChatInterface", () => {
         content: "Here are some images",
         imageUrls: ["image1", "image2"],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
     ];
 
@@ -249,14 +244,12 @@ describe.skip("ChatInterface", () => {
         content: "Hello",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
       {
         sender: "user",
         content: "Hi",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
     ];
     const { rerender } = renderChatInterface(messages);
@@ -269,7 +262,6 @@ describe.skip("ChatInterface", () => {
       content: "How can I help you?",
       imageUrls: [],
       timestamp: new Date().toISOString(),
-      pending: true,
     });
 
     rerender(<ChatInterface />);
@@ -278,19 +270,17 @@ describe.skip("ChatInterface", () => {
   });
 
   it("should render inline errors", () => {
-    const messages: (Message)[] = [
+    const messages: (Message | ErrorMessage)[] = [
       {
         sender: "assistant",
         content: "Hello",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
       {
-        type: "error",
-        content: "Something went wrong",
-        sender: "assistant",
-        timestamp: new Date().toISOString(),
+        error: true,
+        id: "",
+        message: "Something went wrong",
       },
     ];
     renderChatInterface(messages);
@@ -300,8 +290,8 @@ describe.skip("ChatInterface", () => {
   });
 
   it("should render both GitHub buttons initially when ghToken is available", () => {
-    vi.mock("react-router", async (importActual) => ({
-      ...(await importActual<typeof import("react-router")>()),
+    vi.mock("@remix-run/react", async (importActual) => ({
+      ...(await importActual<typeof import("@remix-run/react")>()),
       useRouteLoaderData: vi.fn(() => ({ ghToken: "test-token" })),
     }));
 
@@ -311,7 +301,6 @@ describe.skip("ChatInterface", () => {
         content: "Hello",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
     ];
     renderChatInterface(messages);
@@ -326,8 +315,8 @@ describe.skip("ChatInterface", () => {
   });
 
   it("should render only 'Push changes to PR' button after PR is created", async () => {
-    vi.mock("react-router", async (importActual) => ({
-      ...(await importActual<typeof import("react-router")>()),
+    vi.mock("@remix-run/react", async (importActual) => ({
+      ...(await importActual<typeof import("@remix-run/react")>()),
       useRouteLoaderData: vi.fn(() => ({ ghToken: "test-token" })),
     }));
 
@@ -337,7 +326,6 @@ describe.skip("ChatInterface", () => {
         content: "Hello",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
     ];
     const { rerender } = renderChatInterface(messages);
@@ -370,21 +358,18 @@ describe.skip("ChatInterface", () => {
         content: "Hello",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
       {
         sender: "user",
         content: "Hi",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
       {
         sender: "assistant",
         content: "How can I help you?",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
     ];
     const { rerender } = renderChatInterface(messages);
@@ -395,7 +380,6 @@ describe.skip("ChatInterface", () => {
       content: "I need help",
       imageUrls: [],
       timestamp: new Date().toISOString(),
-      pending: true,
     });
 
     rerender(<ChatInterface />);

frontend/__tests__/components/context-menu/account-settings-context-menu.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, test, vi } from "vitest";
-import { AccountSettingsContextMenu } from "#/components/features/context-menu/account-settings-context-menu";
+import { AccountSettingsContextMenu } from "#/components/context-menu/account-settings-context-menu";
 
 describe("AccountSettingsContextMenu", () => {
   const user = userEvent.setup();

frontend/__tests__/components/context-menu/context-menu-list-item.test.tsx

@@ -1,7 +1,7 @@
 import { describe, it, expect, vi } from "vitest";
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
-import { ContextMenuListItem } from "#/components/features/context-menu/context-menu-list-item";
+import { ContextMenuListItem } from "#/components/context-menu/context-menu-list-item";
 
 describe("ContextMenuListItem", () => {
   it("should render the component with the children", () => {

frontend/__tests__/components/features/waitlist-modal.test.tsx

@@ -1,45 +0,0 @@
-import { render, screen } from "@testing-library/react";
-import { it, describe, expect, vi } from "vitest";
-import userEvent from "@testing-library/user-event";
-import { WaitlistModal } from "#/components/features/waitlist/waitlist-modal";
-import * as CaptureConsent from "#/utils/handle-capture-consent";
-
-describe("WaitlistModal", () => {
-  it("should render a tos checkbox that is unchecked by default", () => {
-    render(<WaitlistModal ghToken={null} githubAuthUrl={null} />);
-    const checkbox = screen.getByRole("checkbox");
-
-    expect(checkbox).not.toBeChecked();
-  });
-
-  it("should only enable the GitHub button if the tos checkbox is checked", async () => {
-    const user = userEvent.setup();
-    render(<WaitlistModal ghToken={null} githubAuthUrl={null} />);
-    const checkbox = screen.getByRole("checkbox");
-    const button = screen.getByRole("button", { name: "Connect to GitHub" });
-
-    expect(button).toBeDisabled();
-
-    await user.click(checkbox);
-
-    expect(button).not.toBeDisabled();
-  });
-
-  it("should set user analytics consent to true when the user checks the tos checkbox", async () => {
-    const handleCaptureConsentSpy = vi.spyOn(
-      CaptureConsent,
-      "handleCaptureConsent",
-    );
-
-    const user = userEvent.setup();
-    render(<WaitlistModal ghToken={null} githubAuthUrl="mock-url" />);
-
-    const checkbox = screen.getByRole("checkbox");
-    await user.click(checkbox);
-
-    const button = screen.getByRole("button", { name: "Connect to GitHub" });
-    await user.click(button);
-
-    expect(handleCaptureConsentSpy).toHaveBeenCalledWith(true);
-  });
-});

frontend/__tests__/components/feedback-actions.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen, within } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
-import { FeedbackActions } from "#/components/features/feedback/feedback-actions";
+import { FeedbackActions } from "#/components/feedback-actions";
 
 describe("FeedbackActions", () => {
   const user = userEvent.setup();

frontend/__tests__/components/feedback-form.test.tsx

@@ -1,8 +1,8 @@
-import { screen } from "@testing-library/react";
+import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
 import { renderWithProviders } from "test-utils";
-import { FeedbackForm } from "#/components/features/feedback/feedback-form";
+import { FeedbackForm } from "#/components/feedback-form";
 
 describe("FeedbackForm", () => {
   const user = userEvent.setup();

frontend/__tests__/components/file-explorer/explorer-tree.test.tsx

@@ -1,7 +1,7 @@
 import { screen } from "@testing-library/react";
 import { renderWithProviders } from "test-utils";
 import { describe, afterEach, vi, it, expect } from "vitest";
-import { ExplorerTree } from "#/components/features/file-explorer/explorer-tree";
+import ExplorerTree from "#/components/file-explorer/explorer-tree";
 
 const FILES = ["file-1-1.ts", "folder-1-2"];
 

frontend/__tests__/components/file-explorer/file-explorer.test.tsx

@@ -4,8 +4,8 @@ import { renderWithProviders } from "test-utils";
 import { describe, it, expect, vi, Mock, afterEach } from "vitest";
 import toast from "#/utils/toast";
 import AgentState from "#/types/agent-state";
+import FileExplorer from "#/components/file-explorer/file-explorer";
 import OpenHands from "#/api/open-hands";
-import { FileExplorer } from "#/components/features/file-explorer/file-explorer";
 
 const toastSpy = vi.spyOn(toast, "error");
 const uploadFilesSpy = vi.spyOn(OpenHands, "uploadFiles");

frontend/__tests__/components/file-explorer/tree-node.test.tsx

@@ -2,7 +2,7 @@ import { screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { renderWithProviders } from "test-utils";
 import { vi, describe, afterEach, it, expect } from "vitest";
-import TreeNode from "#/components/features/file-explorer/tree-node";
+import TreeNode from "#/components/file-explorer/tree-node";
 import OpenHands from "#/api/open-hands";
 
 const getFileSpy = vi.spyOn(OpenHands, "getFile");

frontend/__tests__/components/image-preview.test.tsx

@@ -1,7 +1,7 @@
-import { ImagePreview } from "#/components/features/images/image-preview";
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { describe, expect, it, vi } from "vitest";
+import { ImagePreview } from "#/components/image-preview";
 
 describe("ImagePreview", () => {
   it("should render an image", () => {

frontend/__tests__/components/interactive-chat-box.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen, within } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, beforeAll, describe, expect, it, vi } from "vitest";
-import { InteractiveChatBox } from "#/components/features/chat/interactive-chat-box";
+import { InteractiveChatBox } from "#/components/interactive-chat-box";
 
 describe("InteractiveChatBox", () => {
   const onSubmitMock = vi.fn();

frontend/__tests__/components/modals/base-modal/base-modal.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen, act } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { describe, it, vi, expect } from "vitest";
-import { BaseModal } from "#/components/shared/modals/base-modal/base-modal";
+import BaseModal from "#/components/modals/base-modal/base-modal";
 
 describe("BaseModal", () => {
   it("should render if the modal is open", () => {

frontend/__tests__/components/modals/settings/model-selector.test.tsx

@@ -1,7 +1,7 @@
 import { describe, it, expect } from "vitest";
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
-import { ModelSelector } from "#/components/shared/modals/settings/model-selector";
+import { ModelSelector } from "#/components/modals/settings/model-selector";
 
 describe("ModelSelector", () => {
   const models = {

frontend/__tests__/components/suggestion-item.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
-import { SuggestionItem } from "#/components/features/suggestions/suggestion-item";
+import { SuggestionItem } from "#/components/suggestion-item";
 
 describe("SuggestionItem", () => {
   const suggestionItem = { label: "suggestion1", value: "a long text value" };

frontend/__tests__/components/suggestions.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
-import { Suggestions } from "#/components/features/suggestions/suggestions";
+import { Suggestions } from "#/components/suggestions";
 
 describe("Suggestions", () => {
   const firstSuggestion = {

frontend/__tests__/components/terminal/terminal.test.tsx

@@ -2,7 +2,7 @@ import { act, screen } from "@testing-library/react";
 import { renderWithProviders } from "test-utils";
 import { vi, describe, afterEach, it, expect } from "vitest";
 import { Command, appendInput, appendOutput } from "#/state/command-slice";
-import Terminal from "#/components/features/terminal/terminal";
+import Terminal from "#/components/terminal/terminal";
 
 global.ResizeObserver = vi.fn().mockImplementation(() => ({
   observe: vi.fn(),

frontend/__tests__/components/upload-image-input.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
-import { UploadImageInput } from "#/components/features/images/upload-image-input";
+import { UploadImageInput } from "#/components/upload-image-input";
 
 describe("UploadImageInput", () => {
   const user = userEvent.setup();

frontend/__tests__/components/user-actions.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen } from "@testing-library/react";
 import { describe, expect, it, test, vi, afterEach } from "vitest";
 import userEvent from "@testing-library/user-event";
-import { UserActions } from "#/components/features/sidebar/user-actions";
+import { UserActions } from "#/components/user-actions";
 
 describe("UserActions", () => {
   const user = userEvent.setup();

frontend/__tests__/components/user-avatar.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
-import { UserAvatar } from "#/components/features/sidebar/user-avatar";
+import { UserAvatar } from "#/components/user-avatar";
 
 describe("UserAvatar", () => {
   const onClickMock = vi.fn();

frontend/__tests__/hooks/use-rate.test.ts

@@ -1,6 +1,6 @@
 import { act, renderHook } from "@testing-library/react";
 import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
-import { useRate } from "#/hooks/use-rate";
+import { useRate } from "#/utils/use-rate";
 
 describe("useRate", () => {
   beforeEach(() => {

frontend/__tests__/routes/_oh.test.tsx

@@ -1,15 +1,14 @@
 import { afterEach, beforeAll, describe, expect, it, vi } from "vitest";
-import { createRoutesStub } from "react-router";
+import { createRemixStub } from "@remix-run/testing";
 import { screen, waitFor, within } from "@testing-library/react";
 import { renderWithProviders } from "test-utils";
 import userEvent from "@testing-library/user-event";
 import MainApp from "#/routes/_oh/route";
-import i18n from "#/i18n";
 import * as CaptureConsent from "#/utils/handle-capture-consent";
-import OpenHands from "#/api/open-hands";
+import i18n from "#/i18n";
 
 describe("frontend/routes/_oh", () => {
-  const RouteStub = createRoutesStub([{ Component: MainApp, path: "/" }]);
+  const RemixStub = createRemixStub([{ Component: MainApp, path: "/" }]);
 
   const { userIsAuthenticatedMock, settingsAreUpToDateMock } = vi.hoisted(
     () => ({
@@ -35,47 +34,40 @@ describe("frontend/routes/_oh", () => {
   });
 
   it("should render", async () => {
-    renderWithProviders(<RouteStub />);
+    renderWithProviders(<RemixStub />);
     await screen.findByTestId("root-layout");
   });
 
   it("should render the AI config modal if the user is authed", async () => {
     // Our mock return value is true by default
-    renderWithProviders(<RouteStub />);
+    renderWithProviders(<RemixStub />);
     await screen.findByTestId("ai-config-modal");
   });
 
   it("should render the AI config modal if settings are not up-to-date", async () => {
     settingsAreUpToDateMock.mockReturnValue(false);
-    renderWithProviders(<RouteStub />);
+    renderWithProviders(<RemixStub />);
 
     await screen.findByTestId("ai-config-modal");
   });
 
   it("should not render the AI config modal if the settings are up-to-date", async () => {
     settingsAreUpToDateMock.mockReturnValue(true);
-    renderWithProviders(<RouteStub />);
+    renderWithProviders(<RemixStub />);
 
     await waitFor(() => {
       expect(screen.queryByTestId("ai-config-modal")).not.toBeInTheDocument();
     });
   });
 
-  it("should render and capture the user's consent if oss mode", async () => {
+  it("should capture the user's consent", async () => {
     const user = userEvent.setup();
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
     const handleCaptureConsentSpy = vi.spyOn(
       CaptureConsent,
       "handleCaptureConsent",
     );
 
-    getConfigSpy.mockResolvedValue({
-      APP_MODE: "oss",
-      GITHUB_CLIENT_ID: "test-id",
-      POSTHOG_CLIENT_KEY: "test-key",
-    });
-
-    renderWithProviders(<RouteStub />);
+    renderWithProviders(<RemixStub />);
 
     // The user has not consented to tracking
     const consentForm = await screen.findByTestId("user-capture-consent-form");
@@ -95,26 +87,9 @@ describe("frontend/routes/_oh", () => {
     ).not.toBeInTheDocument();
   });
 
-  it("should not render the user consent form if saas mode", async () => {
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    getConfigSpy.mockResolvedValue({
-      APP_MODE: "saas",
-      GITHUB_CLIENT_ID: "test-id",
-      POSTHOG_CLIENT_KEY: "test-key",
-    });
-
-    renderWithProviders(<RouteStub />);
-
-    await waitFor(() => {
-      expect(
-        screen.queryByTestId("user-capture-consent-form"),
-      ).not.toBeInTheDocument();
-    });
-  });
-
   it("should not render the user consent form if the user has already made a decision", async () => {
     localStorage.setItem("analytics-consent", "true");
-    renderWithProviders(<RouteStub />);
+    renderWithProviders(<RemixStub />);
 
     await waitFor(() => {
       expect(
@@ -123,15 +98,14 @@ describe("frontend/routes/_oh", () => {
     });
   });
 
-  // TODO: Likely failing due to how tokens are now handled in context. Move to e2e tests
-  it.skip("should render a new project button if a token is set", async () => {
+  it("should render a new project button if a token is set", async () => {
     localStorage.setItem("token", "test-token");
-    const { rerender } = renderWithProviders(<RouteStub />);
+    const { rerender } = renderWithProviders(<RemixStub />);
 
     await screen.findByTestId("new-project-button");
 
     localStorage.removeItem("token");
-    rerender(<RouteStub />);
+    rerender(<RemixStub />);
 
     await waitFor(() => {
       expect(
@@ -143,17 +117,17 @@ describe("frontend/routes/_oh", () => {
   // TODO: Move to e2e tests
   it.skip("should update the i18n language when the language settings change", async () => {
     const changeLanguageSpy = vi.spyOn(i18n, "changeLanguage");
-    const { rerender } = renderWithProviders(<RouteStub />);
+    const { rerender } = renderWithProviders(<RemixStub />);
 
     // The default language is English
     expect(changeLanguageSpy).toHaveBeenCalledWith("en");
 
     localStorage.setItem("LANGUAGE", "es");
 
-    rerender(<RouteStub />);
+    rerender(<RemixStub />);
     expect(changeLanguageSpy).toHaveBeenCalledWith("es");
 
-    rerender(<RouteStub />);
+    rerender(<RemixStub />);
     // The language has not changed, so the spy should not have been called again
     expect(changeLanguageSpy).toHaveBeenCalledTimes(2);
   });
@@ -164,7 +138,7 @@ describe("frontend/routes/_oh", () => {
     localStorage.setItem("ghToken", "test-token");
 
     // const logoutCleanupSpy = vi.spyOn(LogoutCleanup, "logoutCleanup");
-    renderWithProviders(<RouteStub />);
+    renderWithProviders(<RemixStub />);
 
     const userActions = await screen.findByTestId("user-actions");
     const userAvatar = within(userActions).getByTestId("user-avatar");

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.15.1",
+  "version": "0.14.3",
   "private": true,
   "type": "module",
   "engines": {
@@ -9,15 +9,15 @@
   "dependencies": {
     "@monaco-editor/react": "^4.6.0",
     "@nextui-org/react": "^2.4.8",
-    "@react-router/node": "^7.0.1",
-    "@react-router/serve": "^7.0.1",
     "@react-types/shared": "^3.25.0",
     "@reduxjs/toolkit": "^2.3.0",
+    "@remix-run/node": "^2.11.2",
+    "@remix-run/react": "^2.11.2",
+    "@remix-run/serve": "^2.11.2",
     "@tanstack/react-query": "^5.60.5",
     "@vitejs/plugin-react": "^4.3.2",
     "@xterm/addon-fit": "^0.10.0",
     "@xterm/xterm": "^5.4.0",
-    "axios": "^1.7.7",
     "clsx": "^2.1.1",
     "eslint-config-airbnb-typescript": "^18.0.0",
     "i18next": "^23.15.2",
@@ -35,7 +35,7 @@
     "react-icons": "^5.3.0",
     "react-markdown": "^9.0.1",
     "react-redux": "^9.1.2",
-    "react-router": "^7.0.1",
+    "react-router-dom": "^6.26.1",
     "react-syntax-highlighter": "^15.6.1",
     "react-textarea-autosize": "^8.5.4",
     "remark-gfm": "^4.0.0",
@@ -47,9 +47,9 @@
     "ws": "^8.18.0"
   },
   "scripts": {
-    "dev": "npm run make-i18n && cross-env VITE_MOCK_API=false react-router dev",
-    "dev:mock": "npm run make-i18n && cross-env VITE_MOCK_API=true react-router dev",
-    "build": "npm run make-i18n && tsc && react-router build",
+    "dev": "npm run make-i18n && cross-env VITE_MOCK_API=false remix vite:dev",
+    "dev:mock": "npm run make-i18n && cross-env VITE_MOCK_API=true remix vite:dev",
+    "build": "npm run make-i18n && tsc && remix vite:build",
     "start": "npx sirv-cli build/ --single",
     "test": "vitest run",
     "test:e2e": "playwright test",
@@ -60,8 +60,7 @@
     "prelint": "npm run make-i18n",
     "lint": "eslint src --ext .ts,.tsx,.js && prettier --check src/**/*.{ts,tsx}",
     "lint:fix": "eslint src --ext .ts,.tsx,.js --fix && prettier --write src/**/*.{ts,tsx}",
-    "prepare": "cd .. && husky frontend/.husky",
-    "typecheck": "react-router typegen && tsc"
+    "prepare": "cd .. && husky frontend/.husky"
   },
   "husky": {
     "hooks": {
@@ -76,7 +75,8 @@
   },
   "devDependencies": {
     "@playwright/test": "^1.48.2",
-    "@react-router/dev": "^7.0.1",
+    "@remix-run/dev": "^2.11.2",
+    "@remix-run/testing": "^2.11.2",
     "@tailwindcss/typography": "^0.5.15",
     "@tanstack/eslint-plugin-query": "^5.60.1",
     "@testing-library/jest-dom": "^6.6.1",
@@ -105,7 +105,7 @@
     "husky": "^9.1.6",
     "jsdom": "^25.0.1",
     "lint-staged": "^15.2.10",
-    "msw": "^2.6.6",
+    "msw": "^2.3.0-ws.rc-12",
     "postcss": "^8.4.47",
     "prettier": "^3.3.3",
     "tailwindcss": "^3.4.14",