mirror of
https://github.com/OpenHands/OpenHands.git
synced 2025-12-26 05:48:36 +08:00
Merge branch 'main' into jps/telemetry-m2
This commit is contained in:
John-Mason P. Shackelford
GitHub
commit
9acb7e10cc
13
.github/scripts/update_pr_description.sh
vendored
13
.github/scripts/update_pr_description.sh
vendored
@ -17,9 +17,6 @@ DOCKER_RUN_COMMAND="docker run -it --rm \
|
||||
--name openhands-app-${SHORT_SHA} \
|
||||
docker.openhands.dev/openhands/openhands:${SHORT_SHA}"
|
||||
|
||||
# Define the uvx command
|
||||
UVX_RUN_COMMAND="uvx --python 3.12 --from git+https://github.com/OpenHands/OpenHands@${BRANCH_NAME}#subdirectory=openhands-cli openhands"
|
||||
|
||||
# Get the current PR body
|
||||
PR_BODY=$(gh pr view "$PR_NUMBER" --json body --jq .body)
|
||||
|
||||
@ -37,11 +34,6 @@ GUI with Docker:
|
||||
\`\`\`
|
||||
${DOCKER_RUN_COMMAND}
|
||||
\`\`\`
|
||||
|
||||
CLI with uvx:
|
||||
\`\`\`
|
||||
${UVX_RUN_COMMAND}
|
||||
\`\`\`
|
||||
EOF
|
||||
)
|
||||
else
|
||||
@ -57,11 +49,6 @@ GUI with Docker:
|
||||
\`\`\`
|
||||
${DOCKER_RUN_COMMAND}
|
||||
\`\`\`
|
||||
|
||||
CLI with uvx:
|
||||
\`\`\`
|
||||
${UVX_RUN_COMMAND}
|
||||
\`\`\`
|
||||
EOF
|
||||
)
|
||||
fi
|
||||
|
||||
69
.github/workflows/clean-up.yml
vendored
69
.github/workflows/clean-up.yml
vendored
@ -1,69 +0,0 @@
|
||||
# Workflow that cleans up outdated and old workflows to prevent out of disk issues
|
||||
name: Delete old workflow runs
|
||||
|
||||
# This workflow is currently only triggered manually
|
||||
on:
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
days:
|
||||
description: 'Days-worth of runs to keep for each workflow'
|
||||
required: true
|
||||
default: '30'
|
||||
minimum_runs:
|
||||
description: 'Minimum runs to keep for each workflow'
|
||||
required: true
|
||||
default: '10'
|
||||
delete_workflow_pattern:
|
||||
description: 'Name or filename of the workflow (if not set, all workflows are targeted)'
|
||||
required: false
|
||||
delete_workflow_by_state_pattern:
|
||||
description: 'Filter workflows by state: active, deleted, disabled_fork, disabled_inactivity, disabled_manually'
|
||||
required: true
|
||||
default: "ALL"
|
||||
type: choice
|
||||
options:
|
||||
- "ALL"
|
||||
- active
|
||||
- deleted
|
||||
- disabled_inactivity
|
||||
- disabled_manually
|
||||
delete_run_by_conclusion_pattern:
|
||||
description: 'Remove runs based on conclusion: action_required, cancelled, failure, skipped, success'
|
||||
required: true
|
||||
default: 'ALL'
|
||||
type: choice
|
||||
options:
|
||||
- 'ALL'
|
||||
- 'Unsuccessful: action_required,cancelled,failure,skipped'
|
||||
- action_required
|
||||
- cancelled
|
||||
- failure
|
||||
- skipped
|
||||
- success
|
||||
dry_run:
|
||||
description: 'Logs simulated changes, no deletions are performed'
|
||||
required: false
|
||||
|
||||
jobs:
|
||||
del_runs:
|
||||
runs-on: blacksmith-4vcpu-ubuntu-2204
|
||||
permissions:
|
||||
actions: write
|
||||
contents: read
|
||||
steps:
|
||||
- name: Delete workflow runs
|
||||
uses: Mattraks/delete-workflow-runs@v2
|
||||
with:
|
||||
token: ${{ github.token }}
|
||||
repository: ${{ github.repository }}
|
||||
retain_days: ${{ github.event.inputs.days }}
|
||||
keep_minimum_runs: ${{ github.event.inputs.minimum_runs }}
|
||||
delete_workflow_pattern: ${{ github.event.inputs.delete_workflow_pattern }}
|
||||
delete_workflow_by_state_pattern: ${{ github.event.inputs.delete_workflow_by_state_pattern }}
|
||||
delete_run_by_conclusion_pattern: >-
|
||||
${{
|
||||
startsWith(github.event.inputs.delete_run_by_conclusion_pattern, 'Unsuccessful:')
|
||||
&& 'action_required,cancelled,failure,skipped'
|
||||
|| github.event.inputs.delete_run_by_conclusion_pattern
|
||||
}}
|
||||
dry_run: ${{ github.event.inputs.dry_run }}
|
||||
@ -1,122 +0,0 @@
|
||||
# Workflow that builds and tests the CLI binary executable
|
||||
name: CLI - Build binary and optionally release
|
||||
|
||||
# Run on pushes to main branch and CLI tags, and on pull requests when CLI files change
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
tags:
|
||||
- "*-cli"
|
||||
pull_request:
|
||||
paths:
|
||||
- "openhands-cli/**"
|
||||
|
||||
permissions:
|
||||
contents: write # needed to create releases or upload assets
|
||||
|
||||
# Cancel previous runs if a new commit is pushed
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
build-binary:
|
||||
name: Build binary executable
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
# Build on Ubuntu 22.04 for maximum GLIBC compatibility (GLIBC 2.31)
|
||||
- os: ubuntu-22.04
|
||||
platform: linux
|
||||
artifact_name: openhands-cli-linux
|
||||
# Build on macOS for macOS users
|
||||
- os: macos-15
|
||||
platform: macos
|
||||
artifact_name: openhands-cli-macos
|
||||
runs-on: ${{ matrix.os }}
|
||||
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: 3.12
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Install dependencies
|
||||
working-directory: openhands-cli
|
||||
run: |
|
||||
uv sync
|
||||
|
||||
- name: Build binary executable
|
||||
working-directory: openhands-cli
|
||||
run: |
|
||||
./build.sh --install-pyinstaller | tee output.log
|
||||
echo "Full output:"
|
||||
cat output.log
|
||||
|
||||
if grep -q "❌" output.log; then
|
||||
echo "❌ Found failure marker in output"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✅ Build & test finished without ❌ markers"
|
||||
|
||||
- name: Verify binary files exist
|
||||
run: |
|
||||
if ! ls openhands-cli/dist/openhands* 1> /dev/null 2>&1; then
|
||||
echo "❌ No binaries found to upload!"
|
||||
exit 1
|
||||
fi
|
||||
echo "✅ Found binaries to upload."
|
||||
|
||||
- name: Upload binary artifact
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: ${{ matrix.artifact_name }}
|
||||
path: openhands-cli/dist/openhands*
|
||||
retention-days: 30
|
||||
|
||||
create-github-release:
|
||||
name: Create GitHub Release
|
||||
runs-on: ubuntu-latest
|
||||
needs: build-binary
|
||||
if: startsWith(github.ref, 'refs/tags/')
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Download all artifacts
|
||||
uses: actions/download-artifact@v4
|
||||
with:
|
||||
path: artifacts
|
||||
|
||||
- name: Prepare release assets
|
||||
run: |
|
||||
mkdir -p release-assets
|
||||
# Copy binaries with appropriate names for release
|
||||
if [ -f artifacts/openhands-cli-linux/openhands ]; then
|
||||
cp artifacts/openhands-cli-linux/openhands release-assets/openhands-linux
|
||||
fi
|
||||
if [ -f artifacts/openhands-cli-macos/openhands ]; then
|
||||
cp artifacts/openhands-cli-macos/openhands release-assets/openhands-macos
|
||||
fi
|
||||
ls -la release-assets/
|
||||
|
||||
- name: Create GitHub Release
|
||||
uses: softprops/action-gh-release@v2
|
||||
with:
|
||||
files: release-assets/*
|
||||
draft: true
|
||||
prerelease: false
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
23
.github/workflows/dispatch-to-docs.yml
vendored
23
.github/workflows/dispatch-to-docs.yml
vendored
@ -1,23 +0,0 @@
|
||||
name: Dispatch to docs repo
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
paths:
|
||||
- 'docs/**'
|
||||
workflow_dispatch:
|
||||
|
||||
jobs:
|
||||
dispatch:
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
matrix:
|
||||
repo: ["OpenHands/docs"]
|
||||
steps:
|
||||
- name: Push to docs repo
|
||||
uses: peter-evans/repository-dispatch@v3
|
||||
with:
|
||||
token: ${{ secrets.ALLHANDS_BOT_GITHUB_PAT }}
|
||||
repository: ${{ matrix.repo }}
|
||||
event-type: update
|
||||
client-payload: '{"ref": "${{ github.ref }}", "sha": "${{ github.sha }}", "module": "openhands", "branch": "main"}'
|
||||
47
.github/workflows/fe-e2e-tests.yml
vendored
Normal file
47
.github/workflows/fe-e2e-tests.yml
vendored
Normal file
@ -0,0 +1,47 @@
|
||||
# Workflow that runs frontend e2e tests with Playwright
|
||||
name: Run Frontend E2E Tests
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
pull_request:
|
||||
paths:
|
||||
- "frontend/**"
|
||||
- ".github/workflows/fe-e2e-tests.yml"
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
fe-e2e-test:
|
||||
name: FE E2E Tests
|
||||
runs-on: blacksmith-4vcpu-ubuntu-2204
|
||||
strategy:
|
||||
matrix:
|
||||
node-version: [22]
|
||||
fail-fast: true
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
- name: Set up Node.js
|
||||
uses: useblacksmith/setup-node@v5
|
||||
with:
|
||||
node-version: ${{ matrix.node-version }}
|
||||
- name: Install dependencies
|
||||
working-directory: ./frontend
|
||||
run: npm ci
|
||||
- name: Install Playwright browsers
|
||||
working-directory: ./frontend
|
||||
run: npx playwright install --with-deps chromium
|
||||
- name: Run Playwright tests
|
||||
working-directory: ./frontend
|
||||
run: npx playwright test --project=chromium
|
||||
- name: Upload Playwright report
|
||||
uses: actions/upload-artifact@v4
|
||||
if: always()
|
||||
with:
|
||||
name: playwright-report
|
||||
path: frontend/playwright-report/
|
||||
retention-days: 30
|
||||
18
.github/workflows/lint.yml
vendored
18
.github/workflows/lint.yml
vendored
@ -72,21 +72,3 @@ jobs:
|
||||
- name: Run pre-commit hooks
|
||||
working-directory: ./enterprise
|
||||
run: pre-commit run --all-files --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml
|
||||
|
||||
lint-cli-python:
|
||||
name: Lint CLI python
|
||||
runs-on: blacksmith-4vcpu-ubuntu-2204
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
- name: Set up python
|
||||
uses: useblacksmith/setup-python@v6
|
||||
with:
|
||||
python-version: 3.12
|
||||
cache: "pip"
|
||||
- name: Install pre-commit
|
||||
run: pip install pre-commit==4.2.0
|
||||
- name: Run pre-commit hooks
|
||||
working-directory: ./openhands-cli
|
||||
run: pre-commit run --all-files --config ./dev_config/python/.pre-commit-config.yaml
|
||||
|
||||
70
.github/workflows/mdx-lint.yml
vendored
70
.github/workflows/mdx-lint.yml
vendored
@ -1,70 +0,0 @@
|
||||
# Workflow that checks MDX format in docs/ folder
|
||||
name: MDX Lint
|
||||
|
||||
# Run on pushes to main and on pull requests that modify docs/ files
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
paths:
|
||||
- 'docs/**/*.mdx'
|
||||
pull_request:
|
||||
paths:
|
||||
- 'docs/**/*.mdx'
|
||||
|
||||
# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
mdx-lint:
|
||||
name: Lint MDX files
|
||||
runs-on: blacksmith-4vcpu-ubuntu-2204
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Install Node.js 22
|
||||
uses: useblacksmith/setup-node@v5
|
||||
with:
|
||||
node-version: 22
|
||||
|
||||
- name: Install MDX dependencies
|
||||
run: |
|
||||
npm install @mdx-js/mdx@3 glob@10
|
||||
|
||||
- name: Validate MDX files
|
||||
run: |
|
||||
node -e "
|
||||
const {compile} = require('@mdx-js/mdx');
|
||||
const fs = require('fs');
|
||||
const path = require('path');
|
||||
const glob = require('glob');
|
||||
|
||||
async function validateMDXFiles() {
|
||||
const files = glob.sync('docs/**/*.mdx');
|
||||
console.log('Found', files.length, 'MDX files to validate');
|
||||
|
||||
let hasErrors = false;
|
||||
|
||||
for (const file of files) {
|
||||
try {
|
||||
const content = fs.readFileSync(file, 'utf8');
|
||||
await compile(content);
|
||||
console.log('✅ MDX parsing successful for', file);
|
||||
} catch (err) {
|
||||
console.error('❌ MDX parsing failed for', file, ':', err.message);
|
||||
hasErrors = true;
|
||||
}
|
||||
}
|
||||
|
||||
if (hasErrors) {
|
||||
console.error('\\n❌ Some MDX files have parsing errors. Please fix them before merging.');
|
||||
process.exit(1);
|
||||
} else {
|
||||
console.log('\\n✅ All MDX files are valid!');
|
||||
}
|
||||
}
|
||||
|
||||
validateMDXFiles();
|
||||
"
|
||||
50
.github/workflows/py-tests.yml
vendored
50
.github/workflows/py-tests.yml
vendored
@ -101,56 +101,11 @@ jobs:
|
||||
path: ".coverage.enterprise.${{ matrix.python_version }}"
|
||||
include-hidden-files: true
|
||||
|
||||
# Run CLI unit tests
|
||||
test-cli-python:
|
||||
name: CLI Unit Tests
|
||||
runs-on: blacksmith-4vcpu-ubuntu-2404
|
||||
strategy:
|
||||
matrix:
|
||||
python-version: ["3.12"]
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Set up Python
|
||||
uses: useblacksmith/setup-python@v6
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Install dependencies
|
||||
working-directory: ./openhands-cli
|
||||
run: |
|
||||
uv sync --group dev
|
||||
|
||||
- name: Run CLI unit tests
|
||||
working-directory: ./openhands-cli
|
||||
env:
|
||||
# write coverage to repo root so the merge step finds it
|
||||
COVERAGE_FILE: "${{ github.workspace }}/.coverage.openhands-cli.${{ matrix.python-version }}"
|
||||
run: |
|
||||
uv run pytest --forked -n auto -s \
|
||||
-p no:ddtrace -p no:ddtrace.pytest_bdd -p no:ddtrace.pytest_benchmark \
|
||||
tests --cov=openhands_cli --cov-branch
|
||||
|
||||
- name: Store coverage file
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: coverage-openhands-cli
|
||||
path: ".coverage.openhands-cli.${{ matrix.python-version }}"
|
||||
include-hidden-files: true
|
||||
|
||||
coverage-comment:
|
||||
name: Coverage Comment
|
||||
if: github.event_name == 'pull_request'
|
||||
runs-on: ubuntu-latest
|
||||
needs: [test-on-linux, test-enterprise, test-cli-python]
|
||||
needs: [test-on-linux, test-enterprise]
|
||||
|
||||
permissions:
|
||||
pull-requests: write
|
||||
@ -164,9 +119,6 @@ jobs:
|
||||
pattern: coverage-*
|
||||
merge-multiple: true
|
||||
|
||||
- name: Create symlink for CLI source files
|
||||
run: ln -sf openhands-cli/openhands_cli openhands_cli
|
||||
|
||||
- name: Coverage comment
|
||||
id: coverage_comment
|
||||
uses: py-cov-action/python-coverage-comment-action@v3
|
||||
|
||||
34
.github/workflows/pypi-release.yml
vendored
34
.github/workflows/pypi-release.yml
vendored
@ -10,7 +10,6 @@ on:
|
||||
type: choice
|
||||
options:
|
||||
- app server
|
||||
- cli
|
||||
default: app server
|
||||
push:
|
||||
tags:
|
||||
@ -39,36 +38,3 @@ jobs:
|
||||
run: ./build.sh
|
||||
- name: publish
|
||||
run: poetry publish -u __token__ -p ${{ secrets.PYPI_TOKEN }}
|
||||
|
||||
release-cli:
|
||||
name: Publish CLI to PyPI
|
||||
runs-on: ubuntu-latest
|
||||
# Run when manually dispatched for "cli" OR for tag pushes that contain '-cli'
|
||||
if: |
|
||||
(github.event_name == 'workflow_dispatch' && github.event.inputs.reason == 'cli')
|
||||
|| (github.event_name == 'push' && startsWith(github.ref, 'refs/tags/') && contains(github.ref, '-cli'))
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: 3.12
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Build CLI package
|
||||
working-directory: openhands-cli
|
||||
run: |
|
||||
# Clean dist directory to avoid conflicts with binary builds
|
||||
rm -rf dist/
|
||||
uv build
|
||||
|
||||
- name: Publish CLI to PyPI
|
||||
working-directory: openhands-cli
|
||||
run: |
|
||||
uv publish --token ${{ secrets.PYPI_TOKEN_OPENHANDS }}
|
||||
|
||||
135
.github/workflows/run-eval.yml
vendored
135
.github/workflows/run-eval.yml
vendored
@ -1,135 +0,0 @@
|
||||
# Run evaluation on a PR, after releases, or manually
|
||||
name: Run Eval
|
||||
|
||||
# Runs when a PR is labeled with one of the "run-eval-" labels, after releases, or manually triggered
|
||||
on:
|
||||
pull_request:
|
||||
types: [labeled]
|
||||
release:
|
||||
types: [published]
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
branch:
|
||||
description: 'Branch to evaluate'
|
||||
required: true
|
||||
default: 'main'
|
||||
eval_instances:
|
||||
description: 'Number of evaluation instances'
|
||||
required: true
|
||||
default: '50'
|
||||
type: choice
|
||||
options:
|
||||
- '1'
|
||||
- '2'
|
||||
- '50'
|
||||
- '100'
|
||||
reason:
|
||||
description: 'Reason for manual trigger'
|
||||
required: false
|
||||
default: ''
|
||||
|
||||
env:
|
||||
# Environment variable for the master GitHub issue number where all evaluation results will be commented
|
||||
# This should be set to the issue number where you want all evaluation results to be posted
|
||||
MASTER_EVAL_ISSUE_NUMBER: ${{ vars.MASTER_EVAL_ISSUE_NUMBER || '0' }}
|
||||
|
||||
jobs:
|
||||
trigger-job:
|
||||
name: Trigger remote eval job
|
||||
if: ${{ (github.event_name == 'pull_request' && (github.event.label.name == 'run-eval-1' || github.event.label.name == 'run-eval-2' || github.event.label.name == 'run-eval-50' || github.event.label.name == 'run-eval-100')) || github.event_name == 'release' || github.event_name == 'workflow_dispatch' }}
|
||||
runs-on: blacksmith-4vcpu-ubuntu-2204
|
||||
|
||||
steps:
|
||||
- name: Checkout branch
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ github.event_name == 'pull_request' && github.head_ref || (github.event_name == 'workflow_dispatch' && github.event.inputs.branch) || github.ref }}
|
||||
|
||||
- name: Set evaluation parameters
|
||||
id: eval_params
|
||||
run: |
|
||||
REPO_URL="https://github.com/${{ github.repository }}"
|
||||
echo "Repository URL: $REPO_URL"
|
||||
|
||||
# Determine branch based on trigger type
|
||||
if [[ "${{ github.event_name }}" == "pull_request" ]]; then
|
||||
EVAL_BRANCH="${{ github.head_ref }}"
|
||||
echo "PR Branch: $EVAL_BRANCH"
|
||||
elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
|
||||
EVAL_BRANCH="${{ github.event.inputs.branch }}"
|
||||
echo "Manual Branch: $EVAL_BRANCH"
|
||||
else
|
||||
# For release events, use the tag name or main branch
|
||||
EVAL_BRANCH="${{ github.ref_name }}"
|
||||
echo "Release Branch/Tag: $EVAL_BRANCH"
|
||||
fi
|
||||
|
||||
# Determine evaluation instances based on trigger type
|
||||
if [[ "${{ github.event_name }}" == "pull_request" ]]; then
|
||||
if [[ "${{ github.event.label.name }}" == "run-eval-1" ]]; then
|
||||
EVAL_INSTANCES="1"
|
||||
elif [[ "${{ github.event.label.name }}" == "run-eval-2" ]]; then
|
||||
EVAL_INSTANCES="2"
|
||||
elif [[ "${{ github.event.label.name }}" == "run-eval-50" ]]; then
|
||||
EVAL_INSTANCES="50"
|
||||
elif [[ "${{ github.event.label.name }}" == "run-eval-100" ]]; then
|
||||
EVAL_INSTANCES="100"
|
||||
fi
|
||||
elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
|
||||
EVAL_INSTANCES="${{ github.event.inputs.eval_instances }}"
|
||||
else
|
||||
# For release events, default to 50 instances
|
||||
EVAL_INSTANCES="50"
|
||||
fi
|
||||
|
||||
echo "Evaluation instances: $EVAL_INSTANCES"
|
||||
echo "repo_url=$REPO_URL" >> $GITHUB_OUTPUT
|
||||
echo "eval_branch=$EVAL_BRANCH" >> $GITHUB_OUTPUT
|
||||
echo "eval_instances=$EVAL_INSTANCES" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Trigger remote job
|
||||
run: |
|
||||
# Determine PR number for the remote evaluation system
|
||||
if [[ "${{ github.event_name }}" == "pull_request" ]]; then
|
||||
PR_NUMBER="${{ github.event.pull_request.number }}"
|
||||
else
|
||||
# For non-PR triggers, use the master issue number as PR number
|
||||
PR_NUMBER="${{ env.MASTER_EVAL_ISSUE_NUMBER }}"
|
||||
fi
|
||||
|
||||
curl -X POST \
|
||||
-H "Authorization: Bearer ${{ secrets.PAT_TOKEN }}" \
|
||||
-H "Accept: application/vnd.github+json" \
|
||||
-d "{\"ref\": \"main\", \"inputs\": {\"github-repo\": \"${{ steps.eval_params.outputs.repo_url }}\", \"github-branch\": \"${{ steps.eval_params.outputs.eval_branch }}\", \"pr-number\": \"${PR_NUMBER}\", \"eval-instances\": \"${{ steps.eval_params.outputs.eval_instances }}\"}}" \
|
||||
https://api.github.com/repos/OpenHands/evaluation/actions/workflows/create-branch.yml/dispatches
|
||||
|
||||
# Send Slack message
|
||||
if [[ "${{ github.event_name }}" == "pull_request" ]]; then
|
||||
TRIGGER_URL="https://github.com/${{ github.repository }}/pull/${{ github.event.pull_request.number }}"
|
||||
slack_text="PR $TRIGGER_URL has triggered evaluation on ${{ steps.eval_params.outputs.eval_instances }} instances..."
|
||||
elif [[ "${{ github.event_name }}" == "release" ]]; then
|
||||
TRIGGER_URL="https://github.com/${{ github.repository }}/releases/tag/${{ github.ref_name }}"
|
||||
slack_text="Release $TRIGGER_URL has triggered evaluation on ${{ steps.eval_params.outputs.eval_instances }} instances..."
|
||||
else
|
||||
TRIGGER_URL="https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"
|
||||
slack_text="Manual trigger (${{ github.event.inputs.reason || 'No reason provided' }}) has triggered evaluation on ${{ steps.eval_params.outputs.eval_instances }} instances for branch ${{ steps.eval_params.outputs.eval_branch }}..."
|
||||
fi
|
||||
|
||||
curl -X POST -H 'Content-type: application/json' --data '{"text":"'"$slack_text"'"}' \
|
||||
https://hooks.slack.com/services/${{ secrets.SLACK_TOKEN }}
|
||||
|
||||
- name: Comment on issue/PR
|
||||
uses: KeisukeYamashita/create-comment@v1
|
||||
with:
|
||||
# For PR triggers, comment on the PR. For other triggers, comment on the master issue
|
||||
number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || env.MASTER_EVAL_ISSUE_NUMBER }}
|
||||
unique: false
|
||||
comment: |
|
||||
**Evaluation Triggered**
|
||||
|
||||
**Trigger:** ${{ github.event_name == 'pull_request' && format('Pull Request #{0}', github.event.pull_request.number) || (github.event_name == 'release' && 'Release') || format('Manual Trigger: {0}', github.event.inputs.reason || 'No reason provided') }}
|
||||
**Branch:** ${{ steps.eval_params.outputs.eval_branch }}
|
||||
**Instances:** ${{ steps.eval_params.outputs.eval_instances }}
|
||||
**Commit:** ${{ github.sha }}
|
||||
|
||||
Running evaluation on the specified branch. Once eval is done, the results will be posted here.
|
||||
60
COMMUNITY.md
60
COMMUNITY.md
@ -1,43 +1,45 @@
|
||||
# 🙌 The OpenHands Community
|
||||
# The OpenHands Community
|
||||
|
||||
The OpenHands community is built around the belief that (1) AI and AI agents are going to fundamentally change the way
|
||||
we build software, and (2) if this is true, we should do everything we can to make sure that the benefits provided by
|
||||
such powerful technology are accessible to everyone.
|
||||
OpenHands is a community of engineers, academics, and enthusiasts reimagining software development for an AI-powered world.
|
||||
|
||||
If this resonates with you, we'd love to have you join us in our quest!
|
||||
## Mission
|
||||
|
||||
## 🤝 How to Join
|
||||
It’s very clear that AI is changing software development. We want the developer community to drive that change organically, through open source.
|
||||
|
||||
Check out our [How to Join the Community section.](https://github.com/OpenHands/OpenHands?tab=readme-ov-file#-how-to-join-the-community)
|
||||
So we’re not just building friendly interfaces for AI-driven development. We’re publishing _building blocks_ that empower developers to create new experiences, tailored to your own habits, needs, and imagination.
|
||||
|
||||
## 💪 Becoming a Contributor
|
||||
## Ethos
|
||||
|
||||
We welcome contributions from everyone! Whether you're a developer, a researcher, or simply enthusiastic about advancing
|
||||
the field of software engineering with AI, there are many ways to get involved:
|
||||
We have two core values: **high openness** and **high agency**. While we don’t expect everyone in the community to embody these values, we want to establish them as norms.
|
||||
|
||||
- **Code Contributions:** Help us develop new core functionality, improve our agents, improve the frontend and other
|
||||
interfaces, or anything else that would help make OpenHands better.
|
||||
- **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in
|
||||
evaluating the models, or suggest improvements.
|
||||
- **Feedback and Testing:** Use the OpenHands toolset, report bugs, suggest features, or provide feedback on usability.
|
||||
### High Openness
|
||||
|
||||
For details, please check [CONTRIBUTING.md](./CONTRIBUTING.md).
|
||||
We welcome anyone and everyone into our community by default. You don’t have to be a software developer to help us build. You don’t have to be pro-AI to help us learn.
|
||||
|
||||
## Code of Conduct
|
||||
Our plans, our work, our successes, and our failures are all public record. We want the world to see not just the fruits of our work, but the whole process of growing it.
|
||||
|
||||
We have a [Code of Conduct](./CODE_OF_CONDUCT.md) that we expect all contributors to adhere to.
|
||||
Long story short, we are aiming for an open, welcoming, diverse, inclusive, and healthy community.
|
||||
All contributors are expected to contribute to building this sort of community.
|
||||
We welcome thoughtful criticism, whether it’s a comment on a PR or feedback on the community as a whole.
|
||||
|
||||
## 🛠️ Becoming a Maintainer
|
||||
### High Agency
|
||||
|
||||
For contributors who have made significant and sustained contributions to the project, there is a possibility of joining
|
||||
the maintainer team. The process for this is as follows:
|
||||
Everyone should feel empowered to contribute to OpenHands. Whether it’s by making a PR, hosting an event, sharing feedback, or just asking a question, don’t hold back!
|
||||
|
||||
1. Any contributor who has made sustained and high-quality contributions to the codebase can be nominated by any
|
||||
maintainer. If you feel that you may qualify you can reach out to any of the maintainers that have reviewed your PRs and ask if you can be nominated.
|
||||
2. Once a maintainer nominates a new maintainer, there will be a discussion period among the maintainers for at least 3 days.
|
||||
3. If no concerns are raised the nomination will be accepted by acclamation, and if concerns are raised there will be a discussion and possible vote.
|
||||
OpenHands gives everyone the building blocks to create state-of-the-art developer experiences. We experiment constantly and love building new things.
|
||||
|
||||
Note that just making many PRs does not immediately imply that you will become a maintainer. We will be looking
|
||||
at sustained high-quality contributions over a period of time, as well as good teamwork and adherence to our [Code of Conduct](./CODE_OF_CONDUCT.md).
|
||||
Coding, development practices, and communities are changing rapidly. We won’t hesitate to change direction and make big bets.
|
||||
|
||||
## Relationship to All Hands
|
||||
|
||||
OpenHands is supported by the for-profit organization [All Hands AI, Inc](https://www.all-hands.dev/).
|
||||
|
||||
All Hands was founded by three of the first major contributors to OpenHands:
|
||||
|
||||
- Xingyao Wang, a UIUC PhD candidate who got OpenHands to the top of the SWE-bench leaderboards
|
||||
- Graham Neubig, a CMU Professor who rallied the academic community around OpenHands
|
||||
- Robert Brennan, a software engineer who architected the user-facing features of OpenHands
|
||||
|
||||
All Hands is an important part of the OpenHands ecosystem. We’ve raised over $20M--mainly to hire developers and researchers who can work on OpenHands full-time, and to provide them with expensive infrastructure. ([Join us!](https://allhandsai.applytojob.com/apply/))
|
||||
|
||||
But we see OpenHands as much larger, and ultimately more important, than All Hands. When our financial responsibility to investors is at odds with our social responsibility to the community—as it inevitably will be, from time to time—we promise to navigate that conflict thoughtfully and transparently.
|
||||
|
||||
At some point, we may transfer custody of OpenHands to an open source foundation. But for now, the [Benevolent Dictator approach](http://www.catb.org/~esr/writings/cathedral-bazaar/homesteading/ar01s16.html) helps us move forward with speed and intention. If we ever forget the “benevolent” part, please: fork us.
|
||||
|
||||
@ -91,14 +91,14 @@ make run
|
||||
#### Option B: Individual Server Startup
|
||||
|
||||
- **Start the Backend Server:** If you prefer, you can start the backend server independently to focus on
|
||||
backend-related tasks or configurations.
|
||||
backend-related tasks or configurations.
|
||||
|
||||
```bash
|
||||
make start-backend
|
||||
```
|
||||
|
||||
- **Start the Frontend Server:** Similarly, you can start the frontend server on its own to work on frontend-related
|
||||
components or interface enhancements.
|
||||
components or interface enhancements.
|
||||
```bash
|
||||
make start-frontend
|
||||
```
|
||||
@ -110,6 +110,7 @@ You can use OpenHands to develop and improve OpenHands itself! This is a powerfu
|
||||
#### Quick Start
|
||||
|
||||
1. **Build and run OpenHands:**
|
||||
|
||||
```bash
|
||||
export INSTALL_DOCKER=0
|
||||
export RUNTIME=local
|
||||
@ -117,6 +118,7 @@ You can use OpenHands to develop and improve OpenHands itself! This is a powerfu
|
||||
```
|
||||
|
||||
2. **Access the interface:**
|
||||
|
||||
- Local development: http://localhost:3001
|
||||
- Remote/cloud environments: Use the appropriate external URL
|
||||
|
||||
@ -199,6 +201,6 @@ Here's a guide to the important documentation files in the repository:
|
||||
- [/containers/README.md](./containers/README.md): Information about Docker containers and deployment
|
||||
- [/tests/unit/README.md](./tests/unit/README.md): Guide to writing and running unit tests
|
||||
- [/evaluation/README.md](./evaluation/README.md): Documentation for the evaluation framework and benchmarks
|
||||
- [/microagents/README.md](./microagents/README.md): Information about the microagents architecture and implementation
|
||||
- [/skills/README.md](./skills/README.md): Information about the skills architecture and implementation
|
||||
- [/openhands/server/README.md](./openhands/server/README.md): Server implementation details and API documentation
|
||||
- [/openhands/runtime/README.md](./openhands/runtime/README.md): Documentation for the runtime environment and execution model
|
||||
|
||||
186
README.md
186
README.md
@ -1,22 +1,18 @@
|
||||
<a name="readme-top"></a>
|
||||
|
||||
<div align="center">
|
||||
<img src="https://raw.githubusercontent.com/All-Hands-AI/docs/main/openhands/static/img/logo.png" alt="Logo" width="200">
|
||||
<h1 align="center">OpenHands: Code Less, Make More</h1>
|
||||
<img src="https://raw.githubusercontent.com/OpenHands/docs/main/openhands/static/img/logo.png" alt="Logo" width="200">
|
||||
<h1 align="center" style="border-bottom: none">OpenHands: AI-Driven Development</h1>
|
||||
</div>
|
||||
|
||||
|
||||
<div align="center">
|
||||
<a href="https://github.com/OpenHands/OpenHands/graphs/contributors"><img src="https://img.shields.io/github/contributors/OpenHands/OpenHands?style=for-the-badge&color=blue" alt="Contributors"></a>
|
||||
<a href="https://github.com/OpenHands/OpenHands/stargazers"><img src="https://img.shields.io/github/stars/OpenHands/OpenHands?style=for-the-badge&color=blue" alt="Stargazers"></a>
|
||||
<a href="https://github.com/OpenHands/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/github/license/OpenHands/OpenHands?style=for-the-badge&color=blue" alt="MIT License"></a>
|
||||
<a href="https://github.com/OpenHands/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/badge/LICENSE-MIT-20B2AA?style=for-the-badge" alt="MIT License"></a>
|
||||
<a href="https://docs.google.com/spreadsheets/d/1wOUdFCMyY6Nt0AIqF705KN4JKOWgeI4wUGUP60krXXs/edit?gid=811504672#gid=811504672"><img src="https://img.shields.io/badge/SWEBench-77.6-00cc00?logoColor=FFE165&style=for-the-badge" alt="Benchmark Score"></a>
|
||||
<br/>
|
||||
<a href="https://all-hands.dev/joinslack"><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://github.com/OpenHands/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="Credits"></a>
|
||||
<br/>
|
||||
<a href="https://docs.all-hands.dev/usage/getting-started"><img src="https://img.shields.io/badge/Documentation-000?logo=googledocs&logoColor=FFE165&style=for-the-badge" alt="Check out the documentation"></a>
|
||||
<a href="https://arxiv.org/abs/2407.16741"><img src="https://img.shields.io/badge/Paper%20on%20Arxiv-000?logoColor=FFE165&logo=arxiv&style=for-the-badge" alt="Paper on Arxiv"></a>
|
||||
<a href="https://docs.google.com/spreadsheets/d/1wOUdFCMyY6Nt0AIqF705KN4JKOWgeI4wUGUP60krXXs/edit?gid=0#gid=0"><img src="https://img.shields.io/badge/Benchmark%20score-000?logoColor=FFE165&logo=huggingface&style=for-the-badge" alt="Evaluation Benchmark Score"></a>
|
||||
<a href="https://docs.openhands.dev/sdk"><img src="https://img.shields.io/badge/Documentation-000?logo=googledocs&logoColor=FFE165&style=for-the-badge" alt="Check out the documentation"></a>
|
||||
<a href="https://arxiv.org/abs/2511.03690"><img src="https://img.shields.io/badge/Paper-000?logoColor=FFE165&logo=arxiv&style=for-the-badge" alt="Tech Report"></a>
|
||||
|
||||
|
||||
<!-- Keep these links. Translations will automatically update with the README. -->
|
||||
<a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=de">Deutsch</a> |
|
||||
@ -28,157 +24,63 @@
|
||||
<a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=ru">Русский</a> |
|
||||
<a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=zh">中文</a>
|
||||
|
||||
<hr>
|
||||
</div>
|
||||
|
||||
Welcome to OpenHands (formerly OpenDevin), a platform for software development agents powered by AI.
|
||||
<hr>
|
||||
|
||||
OpenHands agents can do anything a human developer can: modify code, run commands, browse the web,
|
||||
call APIs, and yes—even copy code snippets from StackOverflow.
|
||||
🙌 Welcome to OpenHands, a [community](COMMUNITY.md) focused on AI-driven development. We’d love for you to [join us on Slack](https://dub.sh/openhands).
|
||||
|
||||
Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or [sign up for OpenHands Cloud](https://app.all-hands.dev) to get started.
|
||||
There are a few ways to work with OpenHands:
|
||||
|
||||
### OpenHands Software Agent SDK
|
||||
The SDK is a composable Python library that contains all of our agentic tech. It's the engine that powers everything else below.
|
||||
|
||||
> [!IMPORTANT]
|
||||
> **Upcoming change**: We are renaming our GitHub Org from `All-Hands-AI` to `OpenHands` on October 20th, 2025.
|
||||
> Check the [tracking issue](https://github.com/All-Hands-AI/OpenHands/issues/11376) for more information.
|
||||
Define agents in code, then run them locally, or scale to 1000s of agents in the cloud.
|
||||
|
||||
[Check out the docs](https://docs.openhands.dev/sdk) or [view the source](https://github.com/OpenHands/software-agent-sdk/)
|
||||
|
||||
> [!IMPORTANT]
|
||||
> Using OpenHands for work? We'd love to chat! Fill out
|
||||
> [this short form](https://docs.google.com/forms/d/e/1FAIpQLSet3VbGaz8z32gW9Wm-Grl4jpt5WgMXPgJ4EDPVmCETCBpJtQ/viewform)
|
||||
> to join our Design Partner program, where you'll get early access to commercial features and the opportunity to provide input on our product roadmap.
|
||||
### OpenHands CLI
|
||||
The CLI is the easiest way to start using OpenHands. The experience will be familiar to anyone who has worked
|
||||
with e.g. Claude Code or Codex. You can power it with Claude, GPT, or any other LLM.
|
||||
|
||||
## ☁️ OpenHands Cloud
|
||||
The easiest way to get started with OpenHands is on [OpenHands Cloud](https://app.all-hands.dev),
|
||||
which comes with $10 in free credits for new users.
|
||||
[Check out the docs](https://docs.openhands.dev/openhands/usage/run-openhands/cli-mode) or [view the source](https://github.com/OpenHands/OpenHands-CLI)
|
||||
|
||||
## 💻 Running OpenHands Locally
|
||||
### OpenHands Local GUI
|
||||
Use the Local GUI for running agents on your laptop. It comes with a REST API and a single-page React application.
|
||||
The experience will be familiar to anyone who has used Devin or Jules.
|
||||
|
||||
### Option 1: CLI Launcher (Recommended)
|
||||
[Check out the docs](https://docs.openhands.dev/openhands/usage/run-openhands/local-setup) or view the source in this repo.
|
||||
|
||||
The easiest way to run OpenHands locally is using the CLI launcher with [uv](https://docs.astral.sh/uv/). This provides better isolation from your current project's virtual environment and is required for OpenHands' default MCP servers.
|
||||
### OpenHands Cloud
|
||||
This is a deployment of OpenHands GUI, running on hosted infrastructure.
|
||||
|
||||
**Install uv** (if you haven't already):
|
||||
You can try it with a free $10 credit by [signing in with your GitHub account](https://app.all-hands.dev).
|
||||
|
||||
See the [uv installation guide](https://docs.astral.sh/uv/getting-started/installation/) for the latest installation instructions for your platform.
|
||||
OpenHands Cloud comes with source-available features and integrations:
|
||||
- Integrations with Slack, Jira, and Linear
|
||||
- Multi-user support
|
||||
- RBAC and permissions
|
||||
- Collaboration features (e.g., conversation sharing)
|
||||
|
||||
**Launch OpenHands**:
|
||||
```bash
|
||||
# Launch the GUI server
|
||||
uvx --python 3.12 openhands serve
|
||||
### OpenHands Enterprise
|
||||
Large enterprises can work with us to self-host OpenHands Cloud in their own VPC, via Kubernetes.
|
||||
OpenHands Enterprise can also work with the CLI and SDK above.
|
||||
|
||||
# Or launch the CLI
|
||||
uvx --python 3.12 openhands
|
||||
```
|
||||
OpenHands Enterprise is source-available--you can see all the source code here in the enterprise/ directory,
|
||||
but you'll need to purchase a license if you want to run it for more than one month.
|
||||
|
||||
You'll find OpenHands running at [http://localhost:3000](http://localhost:3000) (for GUI mode)!
|
||||
Enterprise contracts also come with extended support and access to our research team.
|
||||
|
||||
### Option 2: Docker
|
||||
Learn more at [openhands.dev/enterprise](https://openhands.dev/enterprise)
|
||||
|
||||
<details>
|
||||
<summary>Click to expand Docker command</summary>
|
||||
### Everything Else
|
||||
|
||||
You can also run OpenHands directly with Docker:
|
||||
Check out our [Product Roadmap](https://github.com/orgs/openhands/projects/1), and feel free to
|
||||
[open up an issue](https://github.com/OpenHands/OpenHands/issues) if there's something you'd like to see!
|
||||
|
||||
```bash
|
||||
docker pull docker.openhands.dev/openhands/runtime:0.62-nikolaik
|
||||
You might also be interested in our [evaluation infrastructure](https://github.com/OpenHands/benchmarks), our [chrome extension](https://github.com/OpenHands/openhands-chrome-extension/), or our [Theory-of-Mind module](https://github.com/OpenHands/ToM-SWE).
|
||||
|
||||
docker run -it --rm --pull=always \
|
||||
-e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.openhands.dev/openhands/runtime:0.62-nikolaik \
|
||||
-e LOG_ALL_EVENTS=true \
|
||||
-v /var/run/docker.sock:/var/run/docker.sock \
|
||||
-v ~/.openhands:/.openhands \
|
||||
-p 3000:3000 \
|
||||
--add-host host.docker.internal:host-gateway \
|
||||
--name openhands-app \
|
||||
docker.openhands.dev/openhands/openhands:0.62
|
||||
```
|
||||
All our work is available under the MIT license, except for the `enterprise/` directory in this repository (see the [enterprise license](enterprise/LICENSE) for details).
|
||||
The core `openhands` and `agent-server` Docker images are fully MIT-licensed as well.
|
||||
|
||||
</details>
|
||||
|
||||
> **Note**: If you used OpenHands before version 0.44, you may want to run `mv ~/.openhands-state ~/.openhands` to migrate your conversation history to the new location.
|
||||
|
||||
> [!WARNING]
|
||||
> On a public network? See our [Hardened Docker Installation Guide](https://docs.all-hands.dev/usage/runtimes/docker#hardened-docker-installation)
|
||||
> to secure your deployment by restricting network binding and implementing additional security measures.
|
||||
|
||||
### Getting Started
|
||||
|
||||
When you open the application, you'll be asked to choose an LLM provider and add an API key.
|
||||
[Anthropic's Claude Sonnet 4.5](https://www.anthropic.com/api) (`anthropic/claude-sonnet-4-5-20250929`)
|
||||
works best, but you have [many options](https://docs.all-hands.dev/usage/llms).
|
||||
|
||||
See the [Running OpenHands](https://docs.all-hands.dev/usage/installation) guide for
|
||||
system requirements and more information.
|
||||
|
||||
## 💡 Other ways to run OpenHands
|
||||
|
||||
> [!WARNING]
|
||||
> OpenHands is meant to be run by a single user on their local workstation.
|
||||
> It is not appropriate for multi-tenant deployments where multiple users share the same instance. There is no built-in authentication, isolation, or scalability.
|
||||
>
|
||||
> If you're interested in running OpenHands in a multi-tenant environment, check out the source-available, commercially-licensed
|
||||
> [OpenHands Cloud Helm Chart](https://github.com/openHands/OpenHands-cloud)
|
||||
|
||||
You can [connect OpenHands to your local filesystem](https://docs.all-hands.dev/usage/runtimes/docker#connecting-to-your-filesystem),
|
||||
interact with it via a [friendly CLI](https://docs.all-hands.dev/usage/how-to/cli-mode),
|
||||
run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/usage/how-to/headless-mode),
|
||||
or run it on tagged issues with [a github action](https://docs.all-hands.dev/usage/how-to/github-action).
|
||||
|
||||
Visit [Running OpenHands](https://docs.all-hands.dev/usage/installation) for more information and setup instructions.
|
||||
|
||||
If you want to modify the OpenHands source code, check out [Development.md](https://github.com/OpenHands/OpenHands/blob/main/Development.md).
|
||||
|
||||
Having issues? The [Troubleshooting Guide](https://docs.all-hands.dev/usage/troubleshooting) can help.
|
||||
|
||||
## 📖 Documentation
|
||||
|
||||
To learn more about the project, and for tips on using OpenHands,
|
||||
check out our [documentation](https://docs.all-hands.dev/usage/getting-started).
|
||||
|
||||
There you'll find resources on how to use different LLM providers,
|
||||
troubleshooting resources, and advanced configuration options.
|
||||
|
||||
## 🤝 How to Join the Community
|
||||
|
||||
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 Github:
|
||||
|
||||
- [Join our Slack workspace](https://all-hands.dev/joinslack) - Here we talk about research, architecture, and future development.
|
||||
- [Read or post Github Issues](https://github.com/OpenHands/OpenHands/issues) - Check out the issues we're working on, or add your own ideas.
|
||||
|
||||
See more about the community in [COMMUNITY.md](./COMMUNITY.md) or find details on contributing in [CONTRIBUTING.md](./CONTRIBUTING.md).
|
||||
|
||||
## 📈 Progress
|
||||
|
||||
See the monthly OpenHands roadmap [here](https://github.com/orgs/OpenHands/projects/1) (updated at the maintainer's meeting at the end of each month).
|
||||
|
||||
<p align="center">
|
||||
<a href="https://star-history.com/#OpenHands/OpenHands&Date">
|
||||
<img src="https://api.star-history.com/svg?repos=OpenHands/OpenHands&type=Date" width="500" alt="Star History Chart">
|
||||
</a>
|
||||
</p>
|
||||
|
||||
## 📜 License
|
||||
|
||||
Distributed under the MIT License, with the exception of the `enterprise/` folder. See [`LICENSE`](./LICENSE) for more information.
|
||||
|
||||
## 🙏 Acknowledgements
|
||||
|
||||
OpenHands is built by a large number of contributors, and every contribution is greatly appreciated! We also build upon other open source projects, and we are deeply thankful for their work.
|
||||
|
||||
For a list of open source projects and licenses used in OpenHands, please see our [CREDITS.md](./CREDITS.md) file.
|
||||
|
||||
## 📚 Cite
|
||||
|
||||
```
|
||||
@inproceedings{
|
||||
wang2025openhands,
|
||||
title={OpenHands: An Open Platform for {AI} Software Developers as Generalist Agents},
|
||||
author={Xingyao Wang and Boxuan Li and Yufan Song and Frank F. Xu and Xiangru Tang and Mingchen Zhuge and Jiayi Pan and Yueqi Song and Bowen Li and Jaskirat Singh and Hoang H. Tran and Fuqiang Li and Ren Ma and Mingzhang Zheng and Bill Qian and Yanjun Shao and Niklas Muennighoff and Yizhe Zhang and Binyuan Hui and Junyang Lin and Robert Brennan and Hao Peng and Heng Ji and Graham Neubig},
|
||||
booktitle={The Thirteenth International Conference on Learning Representations},
|
||||
year={2025},
|
||||
url={https://openreview.net/forum?id=OJd3ayDDoF}
|
||||
}
|
||||
```
|
||||
If you need help with anything, or just want to chat, [come find us on Slack](https://dub.sh/openhands).
|
||||
|
||||
@ -73,7 +73,7 @@ ENV VIRTUAL_ENV=/app/.venv \
|
||||
|
||||
COPY --chown=openhands:openhands --chmod=770 --from=backend-builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
|
||||
|
||||
COPY --chown=openhands:openhands --chmod=770 ./microagents ./microagents
|
||||
COPY --chown=openhands:openhands --chmod=770 ./skills ./skills
|
||||
COPY --chown=openhands:openhands --chmod=770 ./openhands ./openhands
|
||||
COPY --chown=openhands:openhands --chmod=777 ./openhands/runtime/plugins ./openhands/runtime/plugins
|
||||
COPY --chown=openhands:openhands pyproject.toml poetry.lock README.md MANIFEST.in LICENSE ./
|
||||
|
||||
@ -3,9 +3,9 @@ repos:
|
||||
rev: v5.0.0
|
||||
hooks:
|
||||
- id: trailing-whitespace
|
||||
exclude: ^(docs/|modules/|python/|openhands-ui/|third_party/|enterprise/|openhands-cli/)
|
||||
exclude: ^(docs/|modules/|python/|openhands-ui/|third_party/|enterprise/)
|
||||
- id: end-of-file-fixer
|
||||
exclude: ^(docs/|modules/|python/|openhands-ui/|third_party/|enterprise/|openhands-cli/)
|
||||
exclude: ^(docs/|modules/|python/|openhands-ui/|third_party/|enterprise/)
|
||||
- id: check-yaml
|
||||
args: ["--allow-multiple-documents"]
|
||||
- id: debug-statements
|
||||
@ -28,12 +28,12 @@ repos:
|
||||
entry: ruff check --config dev_config/python/ruff.toml
|
||||
types_or: [python, pyi, jupyter]
|
||||
args: [--fix, --unsafe-fixes]
|
||||
exclude: ^(third_party/|enterprise/|openhands-cli/)
|
||||
exclude: ^(third_party/|enterprise/)
|
||||
# Run the formatter.
|
||||
- id: ruff-format
|
||||
entry: ruff format --config dev_config/python/ruff.toml
|
||||
types_or: [python, pyi, jupyter]
|
||||
exclude: ^(third_party/|enterprise/|openhands-cli/)
|
||||
exclude: ^(third_party/|enterprise/)
|
||||
|
||||
- repo: https://github.com/pre-commit/mirrors-mypy
|
||||
rev: v1.15.0
|
||||
|
||||
@ -22,6 +22,7 @@ from integrations.utils import (
|
||||
HOST_URL,
|
||||
OPENHANDS_RESOLVER_TEMPLATES_DIR,
|
||||
)
|
||||
from integrations.v1_utils import get_saas_user_auth
|
||||
from jinja2 import Environment, FileSystemLoader
|
||||
from pydantic import SecretStr
|
||||
from server.auth.constants import GITHUB_APP_CLIENT_ID, GITHUB_APP_PRIVATE_KEY
|
||||
@ -164,8 +165,13 @@ class GithubManager(Manager):
|
||||
)
|
||||
|
||||
if await self.is_job_requested(message):
|
||||
payload = message.message.get('payload', {})
|
||||
user_id = payload['sender']['id']
|
||||
keycloak_user_id = await self.token_manager.get_user_id_from_idp_user_id(
|
||||
user_id, ProviderType.GITHUB
|
||||
)
|
||||
github_view = await GithubFactory.create_github_view_from_payload(
|
||||
message, self.token_manager
|
||||
message, keycloak_user_id
|
||||
)
|
||||
logger.info(
|
||||
f'[GitHub] Creating job for {github_view.user_info.username} in {github_view.full_repo_name}#{github_view.issue_number}'
|
||||
@ -282,8 +288,15 @@ class GithubManager(Manager):
|
||||
f'[Github]: Error summarizing issue solvability: {str(e)}'
|
||||
)
|
||||
|
||||
saas_user_auth = await get_saas_user_auth(
|
||||
github_view.user_info.keycloak_user_id, self.token_manager
|
||||
)
|
||||
|
||||
await github_view.create_new_conversation(
|
||||
self.jinja_env, secret_store.provider_tokens, convo_metadata
|
||||
self.jinja_env,
|
||||
secret_store.provider_tokens,
|
||||
convo_metadata,
|
||||
saas_user_auth,
|
||||
)
|
||||
|
||||
conversation_id = github_view.conversation_id
|
||||
@ -292,18 +305,19 @@ class GithubManager(Manager):
|
||||
f'[GitHub] Created conversation {conversation_id} for user {user_info.username}'
|
||||
)
|
||||
|
||||
# Create a GithubCallbackProcessor
|
||||
processor = GithubCallbackProcessor(
|
||||
github_view=github_view,
|
||||
send_summary_instruction=True,
|
||||
)
|
||||
if not github_view.v1:
|
||||
# Create a GithubCallbackProcessor
|
||||
processor = GithubCallbackProcessor(
|
||||
github_view=github_view,
|
||||
send_summary_instruction=True,
|
||||
)
|
||||
|
||||
# Register the callback processor
|
||||
register_callback_processor(conversation_id, processor)
|
||||
# Register the callback processor
|
||||
register_callback_processor(conversation_id, processor)
|
||||
|
||||
logger.info(
|
||||
f'[Github] Registered callback processor for conversation {conversation_id}'
|
||||
)
|
||||
logger.info(
|
||||
f'[Github] Registered callback processor for conversation {conversation_id}'
|
||||
)
|
||||
|
||||
# Send message with conversation link
|
||||
conversation_link = CONVERSATION_URL.format(conversation_id)
|
||||
|
||||
@ -1,4 +1,5 @@
|
||||
from uuid import uuid4
|
||||
from dataclasses import dataclass
|
||||
from uuid import UUID, uuid4
|
||||
|
||||
from github import Github, GithubIntegration
|
||||
from github.Issue import Issue
|
||||
@ -8,16 +9,17 @@ from integrations.github.github_types import (
|
||||
WorkflowRunStatus,
|
||||
)
|
||||
from integrations.models import Message
|
||||
from integrations.resolver_context import ResolverUserContext
|
||||
from integrations.types import ResolverViewInterface, UserData
|
||||
from integrations.utils import (
|
||||
ENABLE_PROACTIVE_CONVERSATION_STARTERS,
|
||||
ENABLE_V1_GITHUB_RESOLVER,
|
||||
HOST,
|
||||
HOST_URL,
|
||||
get_oh_labels,
|
||||
has_exact_mention,
|
||||
)
|
||||
from jinja2 import Environment
|
||||
from pydantic.dataclasses import dataclass
|
||||
from server.auth.constants import GITHUB_APP_CLIENT_ID, GITHUB_APP_PRIVATE_KEY
|
||||
from server.auth.token_manager import TokenManager
|
||||
from server.config import get_config
|
||||
@ -26,14 +28,24 @@ from storage.proactive_conversation_store import ProactiveConversationStore
|
||||
from storage.saas_secrets_store import SaasSecretsStore
|
||||
from storage.saas_settings_store import SaasSettingsStore
|
||||
|
||||
from openhands.agent_server.models import SendMessageRequest
|
||||
from openhands.app_server.app_conversation.app_conversation_models import (
|
||||
AppConversationStartRequest,
|
||||
AppConversationStartTaskStatus,
|
||||
)
|
||||
from openhands.app_server.config import get_app_conversation_service
|
||||
from openhands.app_server.services.injector import InjectorState
|
||||
from openhands.app_server.user.specifiy_user_context import USER_CONTEXT_ATTR
|
||||
from openhands.core.logger import openhands_logger as logger
|
||||
from openhands.integrations.github.github_service import GithubServiceImpl
|
||||
from openhands.integrations.provider import PROVIDER_TOKEN_TYPE, ProviderType
|
||||
from openhands.integrations.service_types import Comment
|
||||
from openhands.sdk import TextContent
|
||||
from openhands.server.services.conversation_service import (
|
||||
initialize_conversation,
|
||||
start_conversation,
|
||||
)
|
||||
from openhands.server.user_auth.user_auth import UserAuth
|
||||
from openhands.storage.data_models.conversation_metadata import (
|
||||
ConversationMetadata,
|
||||
ConversationTrigger,
|
||||
@ -76,6 +88,38 @@ async def get_user_proactive_conversation_setting(user_id: str | None) -> bool:
|
||||
return settings.enable_proactive_conversation_starters
|
||||
|
||||
|
||||
async def get_user_v1_enabled_setting(user_id: str) -> bool:
|
||||
"""Get the user's V1 conversation API setting.
|
||||
|
||||
Args:
|
||||
user_id: The keycloak user ID
|
||||
|
||||
Returns:
|
||||
True if V1 conversations are enabled for this user, False otherwise
|
||||
|
||||
Note:
|
||||
This function checks both the global environment variable kill switch AND
|
||||
the user's individual setting. Both must be true for the function to return true.
|
||||
"""
|
||||
# Check the global environment variable first
|
||||
if not ENABLE_V1_GITHUB_RESOLVER:
|
||||
return False
|
||||
|
||||
config = get_config()
|
||||
settings_store = SaasSettingsStore(
|
||||
user_id=user_id, session_maker=session_maker, config=config
|
||||
)
|
||||
|
||||
settings = await call_sync_from_async(
|
||||
settings_store.get_user_settings_by_keycloak_id, user_id
|
||||
)
|
||||
|
||||
if not settings or settings.v1_enabled is None:
|
||||
return False
|
||||
|
||||
return settings.v1_enabled
|
||||
|
||||
|
||||
# =================================================
|
||||
# SECTION: Github view types
|
||||
# =================================================
|
||||
@ -96,6 +140,7 @@ class GithubIssue(ResolverViewInterface):
|
||||
title: str
|
||||
description: str
|
||||
previous_comments: list[Comment]
|
||||
v1: bool
|
||||
|
||||
async def _load_resolver_context(self):
|
||||
github_service = GithubServiceImpl(
|
||||
@ -142,6 +187,19 @@ class GithubIssue(ResolverViewInterface):
|
||||
|
||||
async def initialize_new_conversation(self) -> ConversationMetadata:
|
||||
# FIXME: Handle if initialize_conversation returns None
|
||||
|
||||
v1_enabled = await get_user_v1_enabled_setting(self.user_info.keycloak_user_id)
|
||||
logger.info(
|
||||
f'[GitHub V1]: User flag found for {self.user_info.keycloak_user_id} is {v1_enabled}'
|
||||
)
|
||||
if v1_enabled:
|
||||
# Create dummy conversationm metadata
|
||||
# Don't save to conversation store
|
||||
# V1 conversations are stored in a separate table
|
||||
return ConversationMetadata(
|
||||
conversation_id=uuid4().hex, selected_repository=self.full_repo_name
|
||||
)
|
||||
|
||||
conversation_metadata: ConversationMetadata = await initialize_conversation( # type: ignore[assignment]
|
||||
user_id=self.user_info.keycloak_user_id,
|
||||
conversation_id=None,
|
||||
@ -158,7 +216,36 @@ class GithubIssue(ResolverViewInterface):
|
||||
jinja_env: Environment,
|
||||
git_provider_tokens: PROVIDER_TOKEN_TYPE,
|
||||
conversation_metadata: ConversationMetadata,
|
||||
saas_user_auth: UserAuth,
|
||||
):
|
||||
v1_enabled = await get_user_v1_enabled_setting(self.user_info.keycloak_user_id)
|
||||
logger.info(
|
||||
f'[GitHub V1]: User flag found for {self.user_info.keycloak_user_id} is {v1_enabled}'
|
||||
)
|
||||
if v1_enabled:
|
||||
try:
|
||||
# Use V1 app conversation service
|
||||
await self._create_v1_conversation(
|
||||
jinja_env, saas_user_auth, conversation_metadata
|
||||
)
|
||||
return
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f'Error checking V1 settings, falling back to V0: {e}')
|
||||
|
||||
# Use existing V0 conversation service
|
||||
await self._create_v0_conversation(
|
||||
jinja_env, git_provider_tokens, conversation_metadata
|
||||
)
|
||||
|
||||
async def _create_v0_conversation(
|
||||
self,
|
||||
jinja_env: Environment,
|
||||
git_provider_tokens: PROVIDER_TOKEN_TYPE,
|
||||
conversation_metadata: ConversationMetadata,
|
||||
):
|
||||
"""Create conversation using the legacy V0 system."""
|
||||
logger.info('[GitHub]: Creating V0 conversation')
|
||||
custom_secrets = await self._get_user_secrets()
|
||||
|
||||
user_instructions, conversation_instructions = await self._get_instructions(
|
||||
@ -177,6 +264,78 @@ class GithubIssue(ResolverViewInterface):
|
||||
conversation_instructions=conversation_instructions,
|
||||
)
|
||||
|
||||
async def _create_v1_conversation(
|
||||
self,
|
||||
jinja_env: Environment,
|
||||
saas_user_auth: UserAuth,
|
||||
conversation_metadata: ConversationMetadata,
|
||||
):
|
||||
"""Create conversation using the new V1 app conversation system."""
|
||||
logger.info('[GitHub V1]: Creating V1 conversation')
|
||||
|
||||
user_instructions, conversation_instructions = await self._get_instructions(
|
||||
jinja_env
|
||||
)
|
||||
|
||||
# Create the initial message request
|
||||
initial_message = SendMessageRequest(
|
||||
role='user', content=[TextContent(text=user_instructions)]
|
||||
)
|
||||
|
||||
# Create the GitHub V1 callback processor
|
||||
github_callback_processor = self._create_github_v1_callback_processor()
|
||||
|
||||
# Get the app conversation service and start the conversation
|
||||
injector_state = InjectorState()
|
||||
|
||||
# Create the V1 conversation start request with the callback processor
|
||||
start_request = AppConversationStartRequest(
|
||||
conversation_id=UUID(conversation_metadata.conversation_id),
|
||||
system_message_suffix=conversation_instructions,
|
||||
initial_message=initial_message,
|
||||
selected_repository=self.full_repo_name,
|
||||
git_provider=ProviderType.GITHUB,
|
||||
title=f'GitHub Issue #{self.issue_number}: {self.title}',
|
||||
trigger=ConversationTrigger.RESOLVER,
|
||||
processors=[
|
||||
github_callback_processor
|
||||
], # Pass the callback processor directly
|
||||
)
|
||||
|
||||
# Set up the GitHub user context for the V1 system
|
||||
github_user_context = ResolverUserContext(saas_user_auth=saas_user_auth)
|
||||
setattr(injector_state, USER_CONTEXT_ATTR, github_user_context)
|
||||
|
||||
async with get_app_conversation_service(
|
||||
injector_state
|
||||
) as app_conversation_service:
|
||||
async for task in app_conversation_service.start_app_conversation(
|
||||
start_request
|
||||
):
|
||||
if task.status == AppConversationStartTaskStatus.ERROR:
|
||||
logger.error(f'Failed to start V1 conversation: {task.detail}')
|
||||
raise RuntimeError(
|
||||
f'Failed to start V1 conversation: {task.detail}'
|
||||
)
|
||||
|
||||
self.v1 = True
|
||||
|
||||
def _create_github_v1_callback_processor(self):
|
||||
"""Create a V1 callback processor for GitHub integration."""
|
||||
from openhands.app_server.event_callback.github_v1_callback_processor import (
|
||||
GithubV1CallbackProcessor,
|
||||
)
|
||||
|
||||
# Create and return the GitHub V1 callback processor
|
||||
return GithubV1CallbackProcessor(
|
||||
github_view_data={
|
||||
'issue_number': self.issue_number,
|
||||
'full_repo_name': self.full_repo_name,
|
||||
'installation_id': self.installation_id,
|
||||
},
|
||||
send_summary_instruction=self.send_summary_instruction,
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class GithubIssueComment(GithubIssue):
|
||||
@ -232,7 +391,18 @@ class GithubPRComment(GithubIssueComment):
|
||||
return user_instructions, conversation_instructions
|
||||
|
||||
async def initialize_new_conversation(self) -> ConversationMetadata:
|
||||
# FIXME: Handle if initialize_conversation returns None
|
||||
v1_enabled = await get_user_v1_enabled_setting(self.user_info.keycloak_user_id)
|
||||
logger.info(
|
||||
f'[GitHub V1]: User flag found for {self.user_info.keycloak_user_id} is {v1_enabled}'
|
||||
)
|
||||
if v1_enabled:
|
||||
# Create dummy conversationm metadata
|
||||
# Don't save to conversation store
|
||||
# V1 conversations are stored in a separate table
|
||||
return ConversationMetadata(
|
||||
conversation_id=uuid4().hex, selected_repository=self.full_repo_name
|
||||
)
|
||||
|
||||
conversation_metadata: ConversationMetadata = await initialize_conversation( # type: ignore[assignment]
|
||||
user_id=self.user_info.keycloak_user_id,
|
||||
conversation_id=None,
|
||||
@ -292,6 +462,24 @@ class GithubInlinePRComment(GithubPRComment):
|
||||
|
||||
return user_instructions, conversation_instructions
|
||||
|
||||
def _create_github_v1_callback_processor(self):
|
||||
"""Create a V1 callback processor for GitHub integration."""
|
||||
from openhands.app_server.event_callback.github_v1_callback_processor import (
|
||||
GithubV1CallbackProcessor,
|
||||
)
|
||||
|
||||
# Create and return the GitHub V1 callback processor
|
||||
return GithubV1CallbackProcessor(
|
||||
github_view_data={
|
||||
'issue_number': self.issue_number,
|
||||
'full_repo_name': self.full_repo_name,
|
||||
'installation_id': self.installation_id,
|
||||
'comment_id': self.comment_id,
|
||||
},
|
||||
inline_pr_comment=True,
|
||||
send_summary_instruction=self.send_summary_instruction,
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class GithubFailingAction:
|
||||
@ -605,7 +793,7 @@ class GithubFactory:
|
||||
|
||||
@staticmethod
|
||||
async def create_github_view_from_payload(
|
||||
message: Message, token_manager: TokenManager
|
||||
message: Message, keycloak_user_id: str
|
||||
) -> ResolverViewInterface:
|
||||
"""Create the appropriate class (GithubIssue or GithubPRComment) based on the payload.
|
||||
Also return metadata about the event (e.g., action type).
|
||||
@ -615,17 +803,10 @@ class GithubFactory:
|
||||
user_id = payload['sender']['id']
|
||||
username = payload['sender']['login']
|
||||
|
||||
keyloak_user_id = await token_manager.get_user_id_from_idp_user_id(
|
||||
user_id, ProviderType.GITHUB
|
||||
)
|
||||
|
||||
if keyloak_user_id is None:
|
||||
logger.warning(f'Got invalid keyloak user id for GitHub User {user_id} ')
|
||||
|
||||
selected_repo = GithubFactory.get_full_repo_name(repo_obj)
|
||||
is_public_repo = not repo_obj.get('private', True)
|
||||
user_info = UserData(
|
||||
user_id=user_id, username=username, keycloak_user_id=keyloak_user_id
|
||||
user_id=user_id, username=username, keycloak_user_id=keycloak_user_id
|
||||
)
|
||||
|
||||
installation_id = message.message['installation']
|
||||
@ -649,6 +830,7 @@ class GithubFactory:
|
||||
title='',
|
||||
description='',
|
||||
previous_comments=[],
|
||||
v1=False,
|
||||
)
|
||||
|
||||
elif GithubFactory.is_issue_comment(message):
|
||||
@ -674,6 +856,7 @@ class GithubFactory:
|
||||
title='',
|
||||
description='',
|
||||
previous_comments=[],
|
||||
v1=False,
|
||||
)
|
||||
|
||||
elif GithubFactory.is_pr_comment(message):
|
||||
@ -715,6 +898,7 @@ class GithubFactory:
|
||||
title='',
|
||||
description='',
|
||||
previous_comments=[],
|
||||
v1=False,
|
||||
)
|
||||
|
||||
elif GithubFactory.is_inline_pr_comment(message):
|
||||
@ -748,6 +932,7 @@ class GithubFactory:
|
||||
title='',
|
||||
description='',
|
||||
previous_comments=[],
|
||||
v1=False,
|
||||
)
|
||||
|
||||
else:
|
||||
|
||||
63
enterprise/integrations/resolver_context.py
Normal file
63
enterprise/integrations/resolver_context.py
Normal file
@ -0,0 +1,63 @@
|
||||
from openhands.app_server.user.user_context import UserContext
|
||||
from openhands.app_server.user.user_models import UserInfo
|
||||
from openhands.integrations.provider import PROVIDER_TOKEN_TYPE
|
||||
from openhands.integrations.service_types import ProviderType
|
||||
from openhands.sdk.secret import SecretSource, StaticSecret
|
||||
from openhands.server.user_auth.user_auth import UserAuth
|
||||
|
||||
|
||||
class ResolverUserContext(UserContext):
|
||||
"""User context for resolver operations that inherits from UserContext."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
saas_user_auth: UserAuth,
|
||||
):
|
||||
self.saas_user_auth = saas_user_auth
|
||||
|
||||
async def get_user_id(self) -> str | None:
|
||||
return await self.saas_user_auth.get_user_id()
|
||||
|
||||
async def get_user_info(self) -> UserInfo:
|
||||
user_settings = await self.saas_user_auth.get_user_settings()
|
||||
user_id = await self.saas_user_auth.get_user_id()
|
||||
if user_settings:
|
||||
return UserInfo(
|
||||
id=user_id,
|
||||
**user_settings.model_dump(context={'expose_secrets': True}),
|
||||
)
|
||||
|
||||
return UserInfo(id=user_id)
|
||||
|
||||
async def get_authenticated_git_url(self, repository: str) -> str:
|
||||
# This would need to be implemented based on the git provider tokens
|
||||
# For now, return a basic HTTPS URL
|
||||
return f'https://github.com/{repository}.git'
|
||||
|
||||
async def get_latest_token(self, provider_type: ProviderType) -> str | None:
|
||||
# Return the appropriate token from git_provider_tokens
|
||||
|
||||
provider_tokens = await self.saas_user_auth.get_provider_tokens()
|
||||
if provider_tokens:
|
||||
return provider_tokens.get(provider_type)
|
||||
return None
|
||||
|
||||
async def get_provider_tokens(self) -> PROVIDER_TOKEN_TYPE | None:
|
||||
return await self.saas_user_auth.get_provider_tokens()
|
||||
|
||||
async def get_secrets(self) -> dict[str, SecretSource]:
|
||||
"""Get secrets for the user, including custom secrets."""
|
||||
secrets = await self.saas_user_auth.get_secrets()
|
||||
if secrets:
|
||||
# Convert custom secrets to StaticSecret objects for SDK compatibility
|
||||
# secrets.custom_secrets is of type Mapping[str, CustomSecret]
|
||||
converted_secrets = {}
|
||||
for key, custom_secret in secrets.custom_secrets.items():
|
||||
# Extract the secret value from CustomSecret and convert to StaticSecret
|
||||
secret_value = custom_secret.secret.get_secret_value()
|
||||
converted_secrets[key] = StaticSecret(value=secret_value)
|
||||
return converted_secrets
|
||||
return {}
|
||||
|
||||
async def get_mcp_api_key(self) -> str | None:
|
||||
return await self.saas_user_auth.get_mcp_api_key()
|
||||
@ -19,7 +19,7 @@ class PRStatus(Enum):
|
||||
class UserData(BaseModel):
|
||||
user_id: int
|
||||
username: str
|
||||
keycloak_user_id: str | None
|
||||
keycloak_user_id: str
|
||||
|
||||
|
||||
@dataclass
|
||||
|
||||
@ -51,6 +51,11 @@ ENABLE_SOLVABILITY_ANALYSIS = (
|
||||
os.getenv('ENABLE_SOLVABILITY_ANALYSIS', 'false').lower() == 'true'
|
||||
)
|
||||
|
||||
# Toggle for V1 GitHub resolver feature
|
||||
ENABLE_V1_GITHUB_RESOLVER = (
|
||||
os.getenv('ENABLE_V1_GITHUB_RESOLVER', 'false').lower() == 'true'
|
||||
)
|
||||
|
||||
|
||||
OPENHANDS_RESOLVER_TEMPLATES_DIR = 'openhands/integrations/templates/resolver/'
|
||||
jinja_env = Environment(loader=FileSystemLoader(OPENHANDS_RESOLVER_TEMPLATES_DIR))
|
||||
|
||||
20
enterprise/integrations/v1_utils.py
Normal file
20
enterprise/integrations/v1_utils.py
Normal file
@ -0,0 +1,20 @@
|
||||
from pydantic import SecretStr
|
||||
from server.auth.saas_user_auth import SaasUserAuth
|
||||
from server.auth.token_manager import TokenManager
|
||||
|
||||
from openhands.core.logger import openhands_logger as logger
|
||||
from openhands.server.user_auth.user_auth import UserAuth
|
||||
|
||||
|
||||
async def get_saas_user_auth(
|
||||
keycloak_user_id: str, token_manager: TokenManager
|
||||
) -> UserAuth:
|
||||
offline_token = await token_manager.load_offline_token(keycloak_user_id)
|
||||
if offline_token is None:
|
||||
logger.info('no_offline_token_found')
|
||||
|
||||
user_auth = SaasUserAuth(
|
||||
user_id=keycloak_user_id,
|
||||
refresh_token=SecretStr(offline_token),
|
||||
)
|
||||
return user_auth
|
||||
@ -0,0 +1,51 @@
|
||||
"""Add SETTING_UP_SKILLS to appconversationstarttaskstatus enum
|
||||
|
||||
Revision ID: 082
|
||||
Revises: 081
|
||||
Create Date: 2025-11-19 12:00:00.000000
|
||||
|
||||
"""
|
||||
|
||||
from typing import Sequence, Union
|
||||
|
||||
from alembic import op
|
||||
from sqlalchemy import text
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = '082'
|
||||
down_revision: Union[str, Sequence[str], None] = '081'
|
||||
branch_labels: Union[str, Sequence[str], None] = None
|
||||
depends_on: Union[str, Sequence[str], None] = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Add SETTING_UP_SKILLS enum value to appconversationstarttaskstatus."""
|
||||
# Check if the enum value already exists before adding it
|
||||
# This handles the case where the enum was created with the value already included
|
||||
connection = op.get_bind()
|
||||
result = connection.execute(
|
||||
text(
|
||||
"SELECT 1 FROM pg_enum WHERE enumlabel = 'SETTING_UP_SKILLS' "
|
||||
"AND enumtypid = (SELECT oid FROM pg_type WHERE typname = 'appconversationstarttaskstatus')"
|
||||
)
|
||||
)
|
||||
|
||||
if not result.fetchone():
|
||||
# Add the new enum value only if it doesn't already exist
|
||||
op.execute(
|
||||
"ALTER TYPE appconversationstarttaskstatus ADD VALUE 'SETTING_UP_SKILLS'"
|
||||
)
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Remove SETTING_UP_SKILLS enum value from appconversationstarttaskstatus.
|
||||
|
||||
Note: PostgreSQL doesn't support removing enum values directly.
|
||||
This would require recreating the enum type and updating all references.
|
||||
For safety, this downgrade is not implemented.
|
||||
"""
|
||||
# PostgreSQL doesn't support removing enum values directly
|
||||
# This would require a complex migration to recreate the enum
|
||||
# For now, we'll leave this as a no-op since removing enum values
|
||||
# is rarely needed and can be dangerous
|
||||
pass
|
||||
@ -0,0 +1,35 @@
|
||||
"""Add v1_enabled column to user_settings
|
||||
|
||||
Revision ID: 083
|
||||
Revises: 082
|
||||
Create Date: 2025-11-18 00:00:00.000000
|
||||
|
||||
"""
|
||||
|
||||
from typing import Sequence, Union
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = '083'
|
||||
down_revision: Union[str, None] = '082'
|
||||
branch_labels: Union[str, Sequence[str], None] = None
|
||||
depends_on: Union[str, Sequence[str], None] = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Add v1_enabled column to user_settings table."""
|
||||
op.add_column(
|
||||
'user_settings',
|
||||
sa.Column(
|
||||
'v1_enabled',
|
||||
sa.Boolean(),
|
||||
nullable=True,
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Remove v1_enabled column from user_settings table."""
|
||||
op.drop_column('user_settings', 'v1_enabled')
|
||||
284
enterprise/poetry.lock
generated
284
enterprise/poetry.lock
generated
@ -1,4 +1,4 @@
|
||||
# This file is automatically @generated by Poetry 2.1.3 and should not be changed by hand.
|
||||
# This file is automatically @generated by Poetry 2.2.1 and should not be changed by hand.
|
||||
|
||||
[[package]]
|
||||
name = "aiofiles"
|
||||
@ -201,14 +201,14 @@ files = [
|
||||
|
||||
[[package]]
|
||||
name = "anthropic"
|
||||
version = "0.72.0"
|
||||
version = "0.75.0"
|
||||
description = "The official Python library for the anthropic API"
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
python-versions = ">=3.9"
|
||||
groups = ["main"]
|
||||
files = [
|
||||
{file = "anthropic-0.72.0-py3-none-any.whl", hash = "sha256:0e9f5a7582f038cab8efbb4c959e49ef654a56bfc7ba2da51b5a7b8a84de2e4d"},
|
||||
{file = "anthropic-0.72.0.tar.gz", hash = "sha256:8971fe76dcffc644f74ac3883069beb1527641115ae0d6eb8fa21c1ce4082f7a"},
|
||||
{file = "anthropic-0.75.0-py3-none-any.whl", hash = "sha256:ea8317271b6c15d80225a9f3c670152746e88805a7a61e14d4a374577164965b"},
|
||||
{file = "anthropic-0.75.0.tar.gz", hash = "sha256:e8607422f4ab616db2ea5baacc215dd5f028da99ce2f022e33c7c535b29f3dfb"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@ -682,37 +682,37 @@ crt = ["awscrt (==0.27.6)"]
|
||||
|
||||
[[package]]
|
||||
name = "browser-use"
|
||||
version = "0.9.5"
|
||||
version = "0.10.1"
|
||||
description = "Make websites accessible for AI agents"
|
||||
optional = false
|
||||
python-versions = "<4.0,>=3.11"
|
||||
groups = ["main"]
|
||||
files = [
|
||||
{file = "browser_use-0.9.5-py3-none-any.whl", hash = "sha256:4a2e92847204d1ded269026a99cb0cc0e60e38bd2751fa3f58aedd78f00b4e67"},
|
||||
{file = "browser_use-0.9.5.tar.gz", hash = "sha256:f8285fe253b149d01769a7084883b4cf4db351e2f38e26302c157bcbf14a703f"},
|
||||
{file = "browser_use-0.10.1-py3-none-any.whl", hash = "sha256:96e603bfc71098175342cdcb0592519e6f244412e740f0254e4389fdd82a977f"},
|
||||
{file = "browser_use-0.10.1.tar.gz", hash = "sha256:5f211ecfdf1f9fd186160f10df70dedd661821231e30f1bce40939787abab223"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
aiohttp = "3.12.15"
|
||||
anthropic = ">=0.68.1,<1.0.0"
|
||||
anthropic = ">=0.72.1,<1.0.0"
|
||||
anyio = ">=4.9.0"
|
||||
authlib = ">=1.6.0"
|
||||
bubus = ">=1.5.6"
|
||||
cdp-use = ">=1.4.0"
|
||||
cdp-use = ">=1.4.4"
|
||||
click = ">=8.1.8"
|
||||
cloudpickle = ">=3.1.1"
|
||||
google-api-core = ">=2.25.0"
|
||||
google-api-python-client = ">=2.174.0"
|
||||
google-auth = ">=2.40.3"
|
||||
google-auth-oauthlib = ">=1.2.2"
|
||||
google-genai = ">=1.29.0,<2.0.0"
|
||||
google-genai = ">=1.50.0,<2.0.0"
|
||||
groq = ">=0.30.0"
|
||||
httpx = ">=0.28.1"
|
||||
inquirerpy = ">=0.3.4"
|
||||
markdownify = ">=1.2.0"
|
||||
mcp = ">=1.10.1"
|
||||
ollama = ">=0.5.1"
|
||||
openai = ">=1.99.2,<2.0.0"
|
||||
openai = ">=2.7.2,<3.0.0"
|
||||
pillow = ">=11.2.1"
|
||||
portalocker = ">=2.7.0,<3.0.0"
|
||||
posthog = ">=3.7.0"
|
||||
@ -721,6 +721,7 @@ pydantic = ">=2.11.5"
|
||||
pyobjc = {version = ">=11.0", markers = "platform_system == \"darwin\""}
|
||||
pyotp = ">=2.9.0"
|
||||
pypdf = ">=5.7.0"
|
||||
python-docx = ">=1.2.0"
|
||||
python-dotenv = ">=1.0.1"
|
||||
reportlab = ">=4.0.0"
|
||||
requests = ">=2.32.3"
|
||||
@ -850,14 +851,14 @@ files = [
|
||||
|
||||
[[package]]
|
||||
name = "cdp-use"
|
||||
version = "1.4.3"
|
||||
version = "1.4.4"
|
||||
description = "Type safe generator/client library for CDP"
|
||||
optional = false
|
||||
python-versions = ">=3.11"
|
||||
groups = ["main"]
|
||||
files = [
|
||||
{file = "cdp_use-1.4.3-py3-none-any.whl", hash = "sha256:c48664604470c2579aa1e677c3e3e7e24c4f300c54804c093d935abb50479ecd"},
|
||||
{file = "cdp_use-1.4.3.tar.gz", hash = "sha256:9029c04bdc49fbd3939d2bf1988ad8d88e260729c7d5e35c2f6c87591f5a10e9"},
|
||||
{file = "cdp_use-1.4.4-py3-none-any.whl", hash = "sha256:e37e80e067db2653d6fdf953d4ff9e5d80d75daa27b7c6d48c0261cccbef73e1"},
|
||||
{file = "cdp_use-1.4.4.tar.gz", hash = "sha256:330a848b517006eb9ad1dc468aa6434d913cf0c6918610760c36c3fdfdba0fab"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@ -2978,28 +2979,29 @@ testing = ["pytest"]
|
||||
|
||||
[[package]]
|
||||
name = "google-genai"
|
||||
version = "1.32.0"
|
||||
version = "1.53.0"
|
||||
description = "GenAI Python SDK"
|
||||
optional = false
|
||||
python-versions = ">=3.9"
|
||||
python-versions = ">=3.10"
|
||||
groups = ["main"]
|
||||
files = [
|
||||
{file = "google_genai-1.32.0-py3-none-any.whl", hash = "sha256:c0c4b1d45adf3aa99501050dd73da2f0dea09374002231052d81a6765d15e7f6"},
|
||||
{file = "google_genai-1.32.0.tar.gz", hash = "sha256:349da3f5ff0e981066bd508585fcdd308d28fc4646f318c8f6d1aa6041f4c7e3"},
|
||||
{file = "google_genai-1.53.0-py3-none-any.whl", hash = "sha256:65a3f99e5c03c372d872cda7419f5940e723374bb12a2f3ffd5e3e56e8eb2094"},
|
||||
{file = "google_genai-1.53.0.tar.gz", hash = "sha256:938a26d22f3fd32c6eeeb4276ef204ef82884e63af9842ce3eac05ceb39cbd8d"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
anyio = ">=4.8.0,<5.0.0"
|
||||
google-auth = ">=2.14.1,<3.0.0"
|
||||
google-auth = {version = ">=2.14.1,<3.0.0", extras = ["requests"]}
|
||||
httpx = ">=0.28.1,<1.0.0"
|
||||
pydantic = ">=2.0.0,<3.0.0"
|
||||
pydantic = ">=2.9.0,<3.0.0"
|
||||
requests = ">=2.28.1,<3.0.0"
|
||||
tenacity = ">=8.2.3,<9.2.0"
|
||||
typing-extensions = ">=4.11.0,<5.0.0"
|
||||
websockets = ">=13.0.0,<15.1.0"
|
||||
|
||||
[package.extras]
|
||||
aiohttp = ["aiohttp (<4.0.0)"]
|
||||
aiohttp = ["aiohttp (<3.13.3)"]
|
||||
local-tokenizer = ["protobuf", "sentencepiece (>=0.2.0)"]
|
||||
|
||||
[[package]]
|
||||
name = "google-resumable-media"
|
||||
@ -3055,6 +3057,8 @@ files = [
|
||||
{file = "greenlet-3.2.4-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c2ca18a03a8cfb5b25bc1cbe20f3d9a4c80d8c3b13ba3df49ac3961af0b1018d"},
|
||||
{file = "greenlet-3.2.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:9fe0a28a7b952a21e2c062cd5756d34354117796c6d9215a87f55e38d15402c5"},
|
||||
{file = "greenlet-3.2.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:8854167e06950ca75b898b104b63cc646573aa5fef1353d4508ecdd1ee76254f"},
|
||||
{file = "greenlet-3.2.4-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:f47617f698838ba98f4ff4189aef02e7343952df3a615f847bb575c3feb177a7"},
|
||||
{file = "greenlet-3.2.4-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:af41be48a4f60429d5cad9d22175217805098a9ef7c40bfef44f7669fb9d74d8"},
|
||||
{file = "greenlet-3.2.4-cp310-cp310-win_amd64.whl", hash = "sha256:73f49b5368b5359d04e18d15828eecc1806033db5233397748f4ca813ff1056c"},
|
||||
{file = "greenlet-3.2.4-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:96378df1de302bc38e99c3a9aa311967b7dc80ced1dcc6f171e99842987882a2"},
|
||||
{file = "greenlet-3.2.4-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:1ee8fae0519a337f2329cb78bd7a8e128ec0f881073d43f023c7b8d4831d5246"},
|
||||
@ -3064,6 +3068,8 @@ files = [
|
||||
{file = "greenlet-3.2.4-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2523e5246274f54fdadbce8494458a2ebdcdbc7b802318466ac5606d3cded1f8"},
|
||||
{file = "greenlet-3.2.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:1987de92fec508535687fb807a5cea1560f6196285a4cde35c100b8cd632cc52"},
|
||||
{file = "greenlet-3.2.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:55e9c5affaa6775e2c6b67659f3a71684de4c549b3dd9afca3bc773533d284fa"},
|
||||
{file = "greenlet-3.2.4-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c9c6de1940a7d828635fbd254d69db79e54619f165ee7ce32fda763a9cb6a58c"},
|
||||
{file = "greenlet-3.2.4-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:03c5136e7be905045160b1b9fdca93dd6727b180feeafda6818e6496434ed8c5"},
|
||||
{file = "greenlet-3.2.4-cp311-cp311-win_amd64.whl", hash = "sha256:9c40adce87eaa9ddb593ccb0fa6a07caf34015a29bf8d344811665b573138db9"},
|
||||
{file = "greenlet-3.2.4-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:3b67ca49f54cede0186854a008109d6ee71f66bd57bb36abd6d0a0267b540cdd"},
|
||||
{file = "greenlet-3.2.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ddf9164e7a5b08e9d22511526865780a576f19ddd00d62f8a665949327fde8bb"},
|
||||
@ -3073,6 +3079,8 @@ files = [
|
||||
{file = "greenlet-3.2.4-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3b3812d8d0c9579967815af437d96623f45c0f2ae5f04e366de62a12d83a8fb0"},
|
||||
{file = "greenlet-3.2.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:abbf57b5a870d30c4675928c37278493044d7c14378350b3aa5d484fa65575f0"},
|
||||
{file = "greenlet-3.2.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:20fb936b4652b6e307b8f347665e2c615540d4b42b3b4c8a321d8286da7e520f"},
|
||||
{file = "greenlet-3.2.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:ee7a6ec486883397d70eec05059353b8e83eca9168b9f3f9a361971e77e0bcd0"},
|
||||
{file = "greenlet-3.2.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:326d234cbf337c9c3def0676412eb7040a35a768efc92504b947b3e9cfc7543d"},
|
||||
{file = "greenlet-3.2.4-cp312-cp312-win_amd64.whl", hash = "sha256:a7d4e128405eea3814a12cc2605e0e6aedb4035bf32697f72deca74de4105e02"},
|
||||
{file = "greenlet-3.2.4-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:1a921e542453fe531144e91e1feedf12e07351b1cf6c9e8a3325ea600a715a31"},
|
||||
{file = "greenlet-3.2.4-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cd3c8e693bff0fff6ba55f140bf390fa92c994083f838fece0f63be121334945"},
|
||||
@ -3082,6 +3090,8 @@ files = [
|
||||
{file = "greenlet-3.2.4-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:23768528f2911bcd7e475210822ffb5254ed10d71f4028387e5a99b4c6699671"},
|
||||
{file = "greenlet-3.2.4-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:00fadb3fedccc447f517ee0d3fd8fe49eae949e1cd0f6a611818f4f6fb7dc83b"},
|
||||
{file = "greenlet-3.2.4-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:d25c5091190f2dc0eaa3f950252122edbbadbb682aa7b1ef2f8af0f8c0afefae"},
|
||||
{file = "greenlet-3.2.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:6e343822feb58ac4d0a1211bd9399de2b3a04963ddeec21530fc426cc121f19b"},
|
||||
{file = "greenlet-3.2.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:ca7f6f1f2649b89ce02f6f229d7c19f680a6238af656f61e0115b24857917929"},
|
||||
{file = "greenlet-3.2.4-cp313-cp313-win_amd64.whl", hash = "sha256:554b03b6e73aaabec3745364d6239e9e012d64c68ccd0b8430c64ccc14939a8b"},
|
||||
{file = "greenlet-3.2.4-cp314-cp314-macosx_11_0_universal2.whl", hash = "sha256:49a30d5fda2507ae77be16479bdb62a660fa51b1eb4928b524975b3bde77b3c0"},
|
||||
{file = "greenlet-3.2.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:299fd615cd8fc86267b47597123e3f43ad79c9d8a22bebdce535e53550763e2f"},
|
||||
@ -3089,6 +3099,8 @@ files = [
|
||||
{file = "greenlet-3.2.4-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:b4a1870c51720687af7fa3e7cda6d08d801dae660f75a76f3845b642b4da6ee1"},
|
||||
{file = "greenlet-3.2.4-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:061dc4cf2c34852b052a8620d40f36324554bc192be474b9e9770e8c042fd735"},
|
||||
{file = "greenlet-3.2.4-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:44358b9bf66c8576a9f57a590d5f5d6e72fa4228b763d0e43fee6d3b06d3a337"},
|
||||
{file = "greenlet-3.2.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:2917bdf657f5859fbf3386b12d68ede4cf1f04c90c3a6bc1f013dd68a22e2269"},
|
||||
{file = "greenlet-3.2.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:015d48959d4add5d6c9f6c5210ee3803a830dce46356e3bc326d6776bde54681"},
|
||||
{file = "greenlet-3.2.4-cp314-cp314-win_amd64.whl", hash = "sha256:e37ab26028f12dbb0ff65f29a8d3d44a765c61e729647bf2ddfbbed621726f01"},
|
||||
{file = "greenlet-3.2.4-cp39-cp39-macosx_11_0_universal2.whl", hash = "sha256:b6a7c19cf0d2742d0809a4c05975db036fdff50cd294a93632d6a310bf9ac02c"},
|
||||
{file = "greenlet-3.2.4-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:27890167f55d2387576d1f41d9487ef171849ea0359ce1510ca6e06c8bece11d"},
|
||||
@ -3098,6 +3110,8 @@ files = [
|
||||
{file = "greenlet-3.2.4-cp39-cp39-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c9913f1a30e4526f432991f89ae263459b1c64d1608c0d22a5c79c287b3c70df"},
|
||||
{file = "greenlet-3.2.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:b90654e092f928f110e0007f572007c9727b5265f7632c2fa7415b4689351594"},
|
||||
{file = "greenlet-3.2.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:81701fd84f26330f0d5f4944d4e92e61afe6319dcd9775e39396e39d7c3e5f98"},
|
||||
{file = "greenlet-3.2.4-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:28a3c6b7cd72a96f61b0e4b2a36f681025b60ae4779cc73c1535eb5f29560b10"},
|
||||
{file = "greenlet-3.2.4-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:52206cd642670b0b320a1fd1cbfd95bca0e043179c1d8a045f2c6109dfe973be"},
|
||||
{file = "greenlet-3.2.4-cp39-cp39-win32.whl", hash = "sha256:65458b409c1ed459ea899e939f0e1cdb14f58dbc803f2f93c5eab5694d32671b"},
|
||||
{file = "greenlet-3.2.4-cp39-cp39-win_amd64.whl", hash = "sha256:d2e685ade4dafd447ede19c31277a224a239a0a1a4eca4e6390efedf20260cfb"},
|
||||
{file = "greenlet-3.2.4.tar.gz", hash = "sha256:0dca0d95ff849f9a364385f36ab49f50065d76964944638be9691e1832e9f86d"},
|
||||
@ -3166,83 +3180,87 @@ protobuf = ">=3.20.2,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4
|
||||
|
||||
[[package]]
|
||||
name = "grpcio"
|
||||
version = "1.74.0"
|
||||
version = "1.67.1"
|
||||
description = "HTTP/2-based RPC framework"
|
||||
optional = false
|
||||
python-versions = ">=3.9"
|
||||
python-versions = ">=3.8"
|
||||
groups = ["main"]
|
||||
files = [
|
||||
{file = "grpcio-1.74.0-cp310-cp310-linux_armv7l.whl", hash = "sha256:85bd5cdf4ed7b2d6438871adf6afff9af7096486fcf51818a81b77ef4dd30907"},
|
||||
{file = "grpcio-1.74.0-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:68c8ebcca945efff9d86d8d6d7bfb0841cf0071024417e2d7f45c5e46b5b08eb"},
|
||||
{file = "grpcio-1.74.0-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:e154d230dc1bbbd78ad2fdc3039fa50ad7ffcf438e4eb2fa30bce223a70c7486"},
|
||||
{file = "grpcio-1.74.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e8978003816c7b9eabe217f88c78bc26adc8f9304bf6a594b02e5a49b2ef9c11"},
|
||||
{file = "grpcio-1.74.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c3d7bd6e3929fd2ea7fbc3f562e4987229ead70c9ae5f01501a46701e08f1ad9"},
|
||||
{file = "grpcio-1.74.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:136b53c91ac1d02c8c24201bfdeb56f8b3ac3278668cbb8e0ba49c88069e1bdc"},
|
||||
{file = "grpcio-1.74.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:fe0f540750a13fd8e5da4b3eaba91a785eea8dca5ccd2bc2ffe978caa403090e"},
|
||||
{file = "grpcio-1.74.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:4e4181bfc24413d1e3a37a0b7889bea68d973d4b45dd2bc68bb766c140718f82"},
|
||||
{file = "grpcio-1.74.0-cp310-cp310-win32.whl", hash = "sha256:1733969040989f7acc3d94c22f55b4a9501a30f6aaacdbccfaba0a3ffb255ab7"},
|
||||
{file = "grpcio-1.74.0-cp310-cp310-win_amd64.whl", hash = "sha256:9e912d3c993a29df6c627459af58975b2e5c897d93287939b9d5065f000249b5"},
|
||||
{file = "grpcio-1.74.0-cp311-cp311-linux_armv7l.whl", hash = "sha256:69e1a8180868a2576f02356565f16635b99088da7df3d45aaa7e24e73a054e31"},
|
||||
{file = "grpcio-1.74.0-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:8efe72fde5500f47aca1ef59495cb59c885afe04ac89dd11d810f2de87d935d4"},
|
||||
{file = "grpcio-1.74.0-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:a8f0302f9ac4e9923f98d8e243939a6fb627cd048f5cd38595c97e38020dffce"},
|
||||
{file = "grpcio-1.74.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2f609a39f62a6f6f05c7512746798282546358a37ea93c1fcbadf8b2fed162e3"},
|
||||
{file = "grpcio-1.74.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c98e0b7434a7fa4e3e63f250456eaef52499fba5ae661c58cc5b5477d11e7182"},
|
||||
{file = "grpcio-1.74.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:662456c4513e298db6d7bd9c3b8df6f75f8752f0ba01fb653e252ed4a59b5a5d"},
|
||||
{file = "grpcio-1.74.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:3d14e3c4d65e19d8430a4e28ceb71ace4728776fd6c3ce34016947474479683f"},
|
||||
{file = "grpcio-1.74.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:1bf949792cee20d2078323a9b02bacbbae002b9e3b9e2433f2741c15bdeba1c4"},
|
||||
{file = "grpcio-1.74.0-cp311-cp311-win32.whl", hash = "sha256:55b453812fa7c7ce2f5c88be3018fb4a490519b6ce80788d5913f3f9d7da8c7b"},
|
||||
{file = "grpcio-1.74.0-cp311-cp311-win_amd64.whl", hash = "sha256:86ad489db097141a907c559988c29718719aa3e13370d40e20506f11b4de0d11"},
|
||||
{file = "grpcio-1.74.0-cp312-cp312-linux_armv7l.whl", hash = "sha256:8533e6e9c5bd630ca98062e3a1326249e6ada07d05acf191a77bc33f8948f3d8"},
|
||||
{file = "grpcio-1.74.0-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:2918948864fec2a11721d91568effffbe0a02b23ecd57f281391d986847982f6"},
|
||||
{file = "grpcio-1.74.0-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:60d2d48b0580e70d2e1954d0d19fa3c2e60dd7cbed826aca104fff518310d1c5"},
|
||||
{file = "grpcio-1.74.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3601274bc0523f6dc07666c0e01682c94472402ac2fd1226fd96e079863bfa49"},
|
||||
{file = "grpcio-1.74.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:176d60a5168d7948539def20b2a3adcce67d72454d9ae05969a2e73f3a0feee7"},
|
||||
{file = "grpcio-1.74.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:e759f9e8bc908aaae0412642afe5416c9f983a80499448fcc7fab8692ae044c3"},
|
||||
{file = "grpcio-1.74.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:9e7c4389771855a92934b2846bd807fc25a3dfa820fd912fe6bd8136026b2707"},
|
||||
{file = "grpcio-1.74.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:cce634b10aeab37010449124814b05a62fb5f18928ca878f1bf4750d1f0c815b"},
|
||||
{file = "grpcio-1.74.0-cp312-cp312-win32.whl", hash = "sha256:885912559974df35d92219e2dc98f51a16a48395f37b92865ad45186f294096c"},
|
||||
{file = "grpcio-1.74.0-cp312-cp312-win_amd64.whl", hash = "sha256:42f8fee287427b94be63d916c90399ed310ed10aadbf9e2e5538b3e497d269bc"},
|
||||
{file = "grpcio-1.74.0-cp313-cp313-linux_armv7l.whl", hash = "sha256:2bc2d7d8d184e2362b53905cb1708c84cb16354771c04b490485fa07ce3a1d89"},
|
||||
{file = "grpcio-1.74.0-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:c14e803037e572c177ba54a3e090d6eb12efd795d49327c5ee2b3bddb836bf01"},
|
||||
{file = "grpcio-1.74.0-cp313-cp313-manylinux_2_17_aarch64.whl", hash = "sha256:f6ec94f0e50eb8fa1744a731088b966427575e40c2944a980049798b127a687e"},
|
||||
{file = "grpcio-1.74.0-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:566b9395b90cc3d0d0c6404bc8572c7c18786ede549cdb540ae27b58afe0fb91"},
|
||||
{file = "grpcio-1.74.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e1ea6176d7dfd5b941ea01c2ec34de9531ba494d541fe2057c904e601879f249"},
|
||||
{file = "grpcio-1.74.0-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:64229c1e9cea079420527fa8ac45d80fc1e8d3f94deaa35643c381fa8d98f362"},
|
||||
{file = "grpcio-1.74.0-cp313-cp313-musllinux_1_1_i686.whl", hash = "sha256:0f87bddd6e27fc776aacf7ebfec367b6d49cad0455123951e4488ea99d9b9b8f"},
|
||||
{file = "grpcio-1.74.0-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:3b03d8f2a07f0fea8c8f74deb59f8352b770e3900d143b3d1475effcb08eec20"},
|
||||
{file = "grpcio-1.74.0-cp313-cp313-win32.whl", hash = "sha256:b6a73b2ba83e663b2480a90b82fdae6a7aa6427f62bf43b29912c0cfd1aa2bfa"},
|
||||
{file = "grpcio-1.74.0-cp313-cp313-win_amd64.whl", hash = "sha256:fd3c71aeee838299c5887230b8a1822795325ddfea635edd82954c1eaa831e24"},
|
||||
{file = "grpcio-1.74.0-cp39-cp39-linux_armv7l.whl", hash = "sha256:4bc5fca10aaf74779081e16c2bcc3d5ec643ffd528d9e7b1c9039000ead73bae"},
|
||||
{file = "grpcio-1.74.0-cp39-cp39-macosx_11_0_universal2.whl", hash = "sha256:6bab67d15ad617aff094c382c882e0177637da73cbc5532d52c07b4ee887a87b"},
|
||||
{file = "grpcio-1.74.0-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:655726919b75ab3c34cdad39da5c530ac6fa32696fb23119e36b64adcfca174a"},
|
||||
{file = "grpcio-1.74.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1a2b06afe2e50ebfd46247ac3ba60cac523f54ec7792ae9ba6073c12daf26f0a"},
|
||||
{file = "grpcio-1.74.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5f251c355167b2360537cf17bea2cf0197995e551ab9da6a0a59b3da5e8704f9"},
|
||||
{file = "grpcio-1.74.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:8f7b5882fb50632ab1e48cb3122d6df55b9afabc265582808036b6e51b9fd6b7"},
|
||||
{file = "grpcio-1.74.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:834988b6c34515545b3edd13e902c1acdd9f2465d386ea5143fb558f153a7176"},
|
||||
{file = "grpcio-1.74.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:22b834cef33429ca6cc28303c9c327ba9a3fafecbf62fae17e9a7b7163cc43ac"},
|
||||
{file = "grpcio-1.74.0-cp39-cp39-win32.whl", hash = "sha256:7d95d71ff35291bab3f1c52f52f474c632db26ea12700c2ff0ea0532cb0b5854"},
|
||||
{file = "grpcio-1.74.0-cp39-cp39-win_amd64.whl", hash = "sha256:ecde9ab49f58433abe02f9ed076c7b5be839cf0153883a6d23995937a82392fa"},
|
||||
{file = "grpcio-1.74.0.tar.gz", hash = "sha256:80d1f4fbb35b0742d3e3d3bb654b7381cd5f015f8497279a1e9c21ba623e01b1"},
|
||||
{file = "grpcio-1.67.1-cp310-cp310-linux_armv7l.whl", hash = "sha256:8b0341d66a57f8a3119b77ab32207072be60c9bf79760fa609c5609f2deb1f3f"},
|
||||
{file = "grpcio-1.67.1-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:f5a27dddefe0e2357d3e617b9079b4bfdc91341a91565111a21ed6ebbc51b22d"},
|
||||
{file = "grpcio-1.67.1-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:43112046864317498a33bdc4797ae6a268c36345a910de9b9c17159d8346602f"},
|
||||
{file = "grpcio-1.67.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c9b929f13677b10f63124c1a410994a401cdd85214ad83ab67cc077fc7e480f0"},
|
||||
{file = "grpcio-1.67.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e7d1797a8a3845437d327145959a2c0c47c05947c9eef5ff1a4c80e499dcc6fa"},
|
||||
{file = "grpcio-1.67.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:0489063974d1452436139501bf6b180f63d4977223ee87488fe36858c5725292"},
|
||||
{file = "grpcio-1.67.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:9fd042de4a82e3e7aca44008ee2fb5da01b3e5adb316348c21980f7f58adc311"},
|
||||
{file = "grpcio-1.67.1-cp310-cp310-win32.whl", hash = "sha256:638354e698fd0c6c76b04540a850bf1db27b4d2515a19fcd5cf645c48d3eb1ed"},
|
||||
{file = "grpcio-1.67.1-cp310-cp310-win_amd64.whl", hash = "sha256:608d87d1bdabf9e2868b12338cd38a79969eaf920c89d698ead08f48de9c0f9e"},
|
||||
{file = "grpcio-1.67.1-cp311-cp311-linux_armv7l.whl", hash = "sha256:7818c0454027ae3384235a65210bbf5464bd715450e30a3d40385453a85a70cb"},
|
||||
{file = "grpcio-1.67.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:ea33986b70f83844cd00814cee4451055cd8cab36f00ac64a31f5bb09b31919e"},
|
||||
{file = "grpcio-1.67.1-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:c7a01337407dd89005527623a4a72c5c8e2894d22bead0895306b23c6695698f"},
|
||||
{file = "grpcio-1.67.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:80b866f73224b0634f4312a4674c1be21b2b4afa73cb20953cbbb73a6b36c3cc"},
|
||||
{file = "grpcio-1.67.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f9fff78ba10d4250bfc07a01bd6254a6d87dc67f9627adece85c0b2ed754fa96"},
|
||||
{file = "grpcio-1.67.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:8a23cbcc5bb11ea7dc6163078be36c065db68d915c24f5faa4f872c573bb400f"},
|
||||
{file = "grpcio-1.67.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:1a65b503d008f066e994f34f456e0647e5ceb34cfcec5ad180b1b44020ad4970"},
|
||||
{file = "grpcio-1.67.1-cp311-cp311-win32.whl", hash = "sha256:e29ca27bec8e163dca0c98084040edec3bc49afd10f18b412f483cc68c712744"},
|
||||
{file = "grpcio-1.67.1-cp311-cp311-win_amd64.whl", hash = "sha256:786a5b18544622bfb1e25cc08402bd44ea83edfb04b93798d85dca4d1a0b5be5"},
|
||||
{file = "grpcio-1.67.1-cp312-cp312-linux_armv7l.whl", hash = "sha256:267d1745894200e4c604958da5f856da6293f063327cb049a51fe67348e4f953"},
|
||||
{file = "grpcio-1.67.1-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:85f69fdc1d28ce7cff8de3f9c67db2b0ca9ba4449644488c1e0303c146135ddb"},
|
||||
{file = "grpcio-1.67.1-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:f26b0b547eb8d00e195274cdfc63ce64c8fc2d3e2d00b12bf468ece41a0423a0"},
|
||||
{file = "grpcio-1.67.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4422581cdc628f77302270ff839a44f4c24fdc57887dc2a45b7e53d8fc2376af"},
|
||||
{file = "grpcio-1.67.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1d7616d2ded471231c701489190379e0c311ee0a6c756f3c03e6a62b95a7146e"},
|
||||
{file = "grpcio-1.67.1-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:8a00efecde9d6fcc3ab00c13f816313c040a28450e5e25739c24f432fc6d3c75"},
|
||||
{file = "grpcio-1.67.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:699e964923b70f3101393710793289e42845791ea07565654ada0969522d0a38"},
|
||||
{file = "grpcio-1.67.1-cp312-cp312-win32.whl", hash = "sha256:4e7b904484a634a0fff132958dabdb10d63e0927398273917da3ee103e8d1f78"},
|
||||
{file = "grpcio-1.67.1-cp312-cp312-win_amd64.whl", hash = "sha256:5721e66a594a6c4204458004852719b38f3d5522082be9061d6510b455c90afc"},
|
||||
{file = "grpcio-1.67.1-cp313-cp313-linux_armv7l.whl", hash = "sha256:aa0162e56fd10a5547fac8774c4899fc3e18c1aa4a4759d0ce2cd00d3696ea6b"},
|
||||
{file = "grpcio-1.67.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:beee96c8c0b1a75d556fe57b92b58b4347c77a65781ee2ac749d550f2a365dc1"},
|
||||
{file = "grpcio-1.67.1-cp313-cp313-manylinux_2_17_aarch64.whl", hash = "sha256:a93deda571a1bf94ec1f6fcda2872dad3ae538700d94dc283c672a3b508ba3af"},
|
||||
{file = "grpcio-1.67.1-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0e6f255980afef598a9e64a24efce87b625e3e3c80a45162d111a461a9f92955"},
|
||||
{file = "grpcio-1.67.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9e838cad2176ebd5d4a8bb03955138d6589ce9e2ce5d51c3ada34396dbd2dba8"},
|
||||
{file = "grpcio-1.67.1-cp313-cp313-musllinux_1_1_i686.whl", hash = "sha256:a6703916c43b1d468d0756c8077b12017a9fcb6a1ef13faf49e67d20d7ebda62"},
|
||||
{file = "grpcio-1.67.1-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:917e8d8994eed1d86b907ba2a61b9f0aef27a2155bca6cbb322430fc7135b7bb"},
|
||||
{file = "grpcio-1.67.1-cp313-cp313-win32.whl", hash = "sha256:e279330bef1744040db8fc432becc8a727b84f456ab62b744d3fdb83f327e121"},
|
||||
{file = "grpcio-1.67.1-cp313-cp313-win_amd64.whl", hash = "sha256:fa0c739ad8b1996bd24823950e3cb5152ae91fca1c09cc791190bf1627ffefba"},
|
||||
{file = "grpcio-1.67.1-cp38-cp38-linux_armv7l.whl", hash = "sha256:178f5db771c4f9a9facb2ab37a434c46cb9be1a75e820f187ee3d1e7805c4f65"},
|
||||
{file = "grpcio-1.67.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:0f3e49c738396e93b7ba9016e153eb09e0778e776df6090c1b8c91877cc1c426"},
|
||||
{file = "grpcio-1.67.1-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:24e8a26dbfc5274d7474c27759b54486b8de23c709d76695237515bc8b5baeab"},
|
||||
{file = "grpcio-1.67.1-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3b6c16489326d79ead41689c4b84bc40d522c9a7617219f4ad94bc7f448c5085"},
|
||||
{file = "grpcio-1.67.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:60e6a4dcf5af7bbc36fd9f81c9f372e8ae580870a9e4b6eafe948cd334b81cf3"},
|
||||
{file = "grpcio-1.67.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:95b5f2b857856ed78d72da93cd7d09b6db8ef30102e5e7fe0961fe4d9f7d48e8"},
|
||||
{file = "grpcio-1.67.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:b49359977c6ec9f5d0573ea4e0071ad278ef905aa74e420acc73fd28ce39e9ce"},
|
||||
{file = "grpcio-1.67.1-cp38-cp38-win32.whl", hash = "sha256:f5b76ff64aaac53fede0cc93abf57894ab2a7362986ba22243d06218b93efe46"},
|
||||
{file = "grpcio-1.67.1-cp38-cp38-win_amd64.whl", hash = "sha256:804c6457c3cd3ec04fe6006c739579b8d35c86ae3298ffca8de57b493524b771"},
|
||||
{file = "grpcio-1.67.1-cp39-cp39-linux_armv7l.whl", hash = "sha256:a25bdea92b13ff4d7790962190bf6bf5c4639876e01c0f3dda70fc2769616335"},
|
||||
{file = "grpcio-1.67.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:cdc491ae35a13535fd9196acb5afe1af37c8237df2e54427be3eecda3653127e"},
|
||||
{file = "grpcio-1.67.1-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:85f862069b86a305497e74d0dc43c02de3d1d184fc2c180993aa8aa86fbd19b8"},
|
||||
{file = "grpcio-1.67.1-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ec74ef02010186185de82cc594058a3ccd8d86821842bbac9873fd4a2cf8be8d"},
|
||||
{file = "grpcio-1.67.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:01f616a964e540638af5130469451cf580ba8c7329f45ca998ab66e0c7dcdb04"},
|
||||
{file = "grpcio-1.67.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:299b3d8c4f790c6bcca485f9963b4846dd92cf6f1b65d3697145d005c80f9fe8"},
|
||||
{file = "grpcio-1.67.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:60336bff760fbb47d7e86165408126f1dded184448e9a4c892189eb7c9d3f90f"},
|
||||
{file = "grpcio-1.67.1-cp39-cp39-win32.whl", hash = "sha256:5ed601c4c6008429e3d247ddb367fe8c7259c355757448d7c1ef7bd4a6739e8e"},
|
||||
{file = "grpcio-1.67.1-cp39-cp39-win_amd64.whl", hash = "sha256:5db70d32d6703b89912af16d6d45d78406374a8b8ef0d28140351dd0ec610e98"},
|
||||
{file = "grpcio-1.67.1.tar.gz", hash = "sha256:3dc2ed4cabea4dc14d5e708c2b426205956077cc5de419b4d4079315017e9732"},
|
||||
]
|
||||
|
||||
[package.extras]
|
||||
protobuf = ["grpcio-tools (>=1.74.0)"]
|
||||
protobuf = ["grpcio-tools (>=1.67.1)"]
|
||||
|
||||
[[package]]
|
||||
name = "grpcio-status"
|
||||
version = "1.71.2"
|
||||
version = "1.67.1"
|
||||
description = "Status proto mapping for gRPC"
|
||||
optional = false
|
||||
python-versions = ">=3.9"
|
||||
python-versions = ">=3.8"
|
||||
groups = ["main"]
|
||||
files = [
|
||||
{file = "grpcio_status-1.71.2-py3-none-any.whl", hash = "sha256:803c98cb6a8b7dc6dbb785b1111aed739f241ab5e9da0bba96888aa74704cfd3"},
|
||||
{file = "grpcio_status-1.71.2.tar.gz", hash = "sha256:c7a97e176df71cdc2c179cd1847d7fc86cca5832ad12e9798d7fed6b7a1aab50"},
|
||||
{file = "grpcio_status-1.67.1-py3-none-any.whl", hash = "sha256:16e6c085950bdacac97c779e6a502ea671232385e6e37f258884d6883392c2bd"},
|
||||
{file = "grpcio_status-1.67.1.tar.gz", hash = "sha256:2bf38395e028ceeecfd8866b081f61628114b384da7d51ae064ddc8d766a5d11"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
googleapis-common-protos = ">=1.5.5"
|
||||
grpcio = ">=1.71.2"
|
||||
grpcio = ">=1.67.1"
|
||||
protobuf = ">=5.26.1,<6.0dev"
|
||||
|
||||
[[package]]
|
||||
@ -4540,42 +4558,39 @@ valkey = ["valkey (>=6)"]
|
||||
|
||||
[[package]]
|
||||
name = "litellm"
|
||||
version = "1.77.7"
|
||||
version = "1.80.7"
|
||||
description = "Library to easily interface with LLM API providers"
|
||||
optional = false
|
||||
python-versions = ">=3.8.1,<4.0, !=3.9.7"
|
||||
python-versions = "<4.0,>=3.9"
|
||||
groups = ["main"]
|
||||
files = []
|
||||
develop = false
|
||||
files = [
|
||||
{file = "litellm-1.80.7-py3-none-any.whl", hash = "sha256:f7d993f78c1e0e4e1202b2a925cc6540b55b6e5fb055dd342d88b145ab3102ed"},
|
||||
{file = "litellm-1.80.7.tar.gz", hash = "sha256:3977a8d195aef842d01c18bf9e22984829363c6a4b54daf9a43c9dd9f190b42c"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
aiohttp = ">=3.10"
|
||||
click = "*"
|
||||
fastuuid = ">=0.13.0"
|
||||
grpcio = ">=1.62.3,<1.68.0"
|
||||
httpx = ">=0.23.0"
|
||||
importlib-metadata = ">=6.8.0"
|
||||
jinja2 = "^3.1.2"
|
||||
jsonschema = "^4.22.0"
|
||||
openai = ">=1.99.5"
|
||||
pydantic = "^2.5.0"
|
||||
jinja2 = ">=3.1.2,<4.0.0"
|
||||
jsonschema = ">=4.22.0,<5.0.0"
|
||||
openai = ">=2.8.0"
|
||||
pydantic = ">=2.5.0,<3.0.0"
|
||||
python-dotenv = ">=0.2.0"
|
||||
tiktoken = ">=0.7.0"
|
||||
tokenizers = "*"
|
||||
|
||||
[package.extras]
|
||||
caching = ["diskcache (>=5.6.1,<6.0.0)"]
|
||||
extra-proxy = ["azure-identity (>=1.15.0,<2.0.0)", "azure-keyvault-secrets (>=4.8.0,<5.0.0)", "google-cloud-iam (>=2.19.1,<3.0.0)", "google-cloud-kms (>=2.21.3,<3.0.0)", "prisma (==0.11.0)", "redisvl (>=0.4.1,<0.5.0) ; python_version >= \"3.9\" and python_version < \"3.14\"", "resend (>=0.8.0,<0.9.0)"]
|
||||
extra-proxy = ["azure-identity (>=1.15.0,<2.0.0) ; python_version >= \"3.9\"", "azure-keyvault-secrets (>=4.8.0,<5.0.0)", "google-cloud-iam (>=2.19.1,<3.0.0)", "google-cloud-kms (>=2.21.3,<3.0.0)", "prisma (==0.11.0)", "redisvl (>=0.4.1,<0.5.0) ; python_version >= \"3.9\" and python_version < \"3.14\"", "resend (>=0.8.0)"]
|
||||
mlflow = ["mlflow (>3.1.4) ; python_version >= \"3.10\""]
|
||||
proxy = ["PyJWT (>=2.8.0,<3.0.0)", "apscheduler (>=3.10.4,<4.0.0)", "azure-identity (>=1.15.0,<2.0.0)", "azure-storage-blob (>=12.25.1,<13.0.0)", "backoff", "boto3 (==1.36.0)", "cryptography", "fastapi (>=0.115.5,<0.116.0)", "fastapi-sso (>=0.16.0,<0.17.0)", "gunicorn (>=23.0.0,<24.0.0)", "litellm-enterprise (==0.1.20)", "litellm-proxy-extras (==0.2.25)", "mcp (>=1.10.0,<2.0.0) ; python_version >= \"3.10\"", "orjson (>=3.9.7,<4.0.0)", "polars (>=1.31.0,<2.0.0) ; python_version >= \"3.10\"", "pynacl (>=1.5.0,<2.0.0)", "python-multipart (>=0.0.18,<0.0.19)", "pyyaml (>=6.0.1,<7.0.0)", "rich (==13.7.1)", "rq", "uvicorn (>=0.29.0,<0.30.0)", "uvloop (>=0.21.0,<0.22.0) ; sys_platform != \"win32\"", "websockets (>=13.1.0,<14.0.0)"]
|
||||
semantic-router = ["semantic-router ; python_version >= \"3.9\""]
|
||||
proxy = ["PyJWT (>=2.10.1,<3.0.0) ; python_version >= \"3.9\"", "apscheduler (>=3.10.4,<4.0.0)", "azure-identity (>=1.15.0,<2.0.0) ; python_version >= \"3.9\"", "azure-storage-blob (>=12.25.1,<13.0.0)", "backoff", "boto3 (==1.36.0)", "cryptography", "fastapi (>=0.120.1)", "fastapi-sso (>=0.16.0,<0.17.0)", "gunicorn (>=23.0.0,<24.0.0)", "litellm-enterprise (==0.1.22)", "litellm-proxy-extras (==0.4.9)", "mcp (>=1.21.2,<2.0.0) ; python_version >= \"3.10\"", "orjson (>=3.9.7,<4.0.0)", "polars (>=1.31.0,<2.0.0) ; python_version >= \"3.10\"", "pynacl (>=1.5.0,<2.0.0)", "python-multipart (>=0.0.18,<0.0.19)", "pyyaml (>=6.0.1,<7.0.0)", "rich (==13.7.1)", "rq", "soundfile (>=0.12.1,<0.13.0)", "uvicorn (>=0.31.1,<0.32.0)", "uvloop (>=0.21.0,<0.22.0) ; sys_platform != \"win32\"", "websockets (>=15.0.1,<16.0.0)"]
|
||||
semantic-router = ["semantic-router (>=0.1.12) ; python_version >= \"3.9\" and python_version < \"3.14\""]
|
||||
utils = ["numpydoc"]
|
||||
|
||||
[package.source]
|
||||
type = "git"
|
||||
url = "https://github.com/BerriAI/litellm.git"
|
||||
reference = "v1.77.7.dev9"
|
||||
resolved_reference = "763d2f8ccdd8412dbe6d4ac0e136d9ac34dcd4c0"
|
||||
|
||||
[[package]]
|
||||
name = "llvmlite"
|
||||
version = "0.44.0"
|
||||
@ -5644,28 +5659,28 @@ pydantic = ">=2.9"
|
||||
|
||||
[[package]]
|
||||
name = "openai"
|
||||
version = "1.99.9"
|
||||
version = "2.8.0"
|
||||
description = "The official Python library for the openai API"
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
python-versions = ">=3.9"
|
||||
groups = ["main", "test"]
|
||||
files = [
|
||||
{file = "openai-1.99.9-py3-none-any.whl", hash = "sha256:9dbcdb425553bae1ac5d947147bebbd630d91bbfc7788394d4c4f3a35682ab3a"},
|
||||
{file = "openai-1.99.9.tar.gz", hash = "sha256:f2082d155b1ad22e83247c3de3958eb4255b20ccf4a1de2e6681b6957b554e92"},
|
||||
{file = "openai-2.8.0-py3-none-any.whl", hash = "sha256:ba975e347f6add2fe13529ccb94d54a578280e960765e5224c34b08d7e029ddf"},
|
||||
{file = "openai-2.8.0.tar.gz", hash = "sha256:4851908f6d6fcacbd47ba659c5ac084f7725b752b6bfa1e948b6fbfc111a6bad"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
anyio = ">=3.5.0,<5"
|
||||
distro = ">=1.7.0,<2"
|
||||
httpx = ">=0.23.0,<1"
|
||||
jiter = ">=0.4.0,<1"
|
||||
jiter = ">=0.10.0,<1"
|
||||
pydantic = ">=1.9.0,<3"
|
||||
sniffio = "*"
|
||||
tqdm = ">4"
|
||||
typing-extensions = ">=4.11,<5"
|
||||
|
||||
[package.extras]
|
||||
aiohttp = ["aiohttp", "httpx-aiohttp (>=0.1.8)"]
|
||||
aiohttp = ["aiohttp", "httpx-aiohttp (>=0.1.9)"]
|
||||
datalib = ["numpy (>=1)", "pandas (>=1.2.3)", "pandas-stubs (>=1.1.0.11)"]
|
||||
realtime = ["websockets (>=13,<16)"]
|
||||
voice-helpers = ["numpy (>=2.0.2)", "sounddevice (>=0.5.1)"]
|
||||
@ -5820,14 +5835,14 @@ llama = ["llama-index (>=0.12.29,<0.13.0)", "llama-index-core (>=0.12.29,<0.13.0
|
||||
|
||||
[[package]]
|
||||
name = "openhands-agent-server"
|
||||
version = "1.1.0"
|
||||
version = "1.5.2"
|
||||
description = "OpenHands Agent Server - REST/WebSocket interface for OpenHands AI Agent"
|
||||
optional = false
|
||||
python-versions = ">=3.12"
|
||||
groups = ["main"]
|
||||
files = [
|
||||
{file = "openhands_agent_server-1.1.0-py3-none-any.whl", hash = "sha256:59a856883df23488c0723e47655ef21649a321fcd4709a25a4690866eff6ac88"},
|
||||
{file = "openhands_agent_server-1.1.0.tar.gz", hash = "sha256:e39bebd39afd45cfcfd765005e7c4e5409e46678bd7612ae20bae79f7057b935"},
|
||||
{file = "openhands_agent_server-1.5.2-py3-none-any.whl", hash = "sha256:7a368f61036f85446f566b9f6f9d6c7318684776cf2293daa5bce3ee19ac077d"},
|
||||
{file = "openhands_agent_server-1.5.2.tar.gz", hash = "sha256:dfaf5583dd71dae933643a8f8160156ce6fa7ed20db5cc3c45465b079bc576cd"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@ -5835,6 +5850,7 @@ aiosqlite = ">=0.19"
|
||||
alembic = ">=1.13"
|
||||
docker = ">=7.1,<8"
|
||||
fastapi = ">=0.104"
|
||||
openhands-sdk = "*"
|
||||
pydantic = ">=2"
|
||||
sqlalchemy = ">=2"
|
||||
uvicorn = ">=0.31.1"
|
||||
@ -5843,7 +5859,7 @@ wsproto = ">=1.2.0"
|
||||
|
||||
[[package]]
|
||||
name = "openhands-ai"
|
||||
version = "0.0.0-post.5525+0b6631523"
|
||||
version = "0.62.0"
|
||||
description = "OpenHands: Code Less, Make More"
|
||||
optional = false
|
||||
python-versions = "^3.12,<3.14"
|
||||
@ -5860,6 +5876,7 @@ bashlex = "^0.18"
|
||||
boto3 = "*"
|
||||
browsergym-core = "0.13.3"
|
||||
deprecated = "*"
|
||||
deprecation = "^2.1.0"
|
||||
dirhash = "*"
|
||||
docker = "*"
|
||||
fastapi = "*"
|
||||
@ -5878,15 +5895,15 @@ json-repair = "*"
|
||||
jupyter_kernel_gateway = "*"
|
||||
kubernetes = "^33.1.0"
|
||||
libtmux = ">=0.46.2"
|
||||
litellm = ">=1.74.3, <1.78.0, !=1.64.4, !=1.67.*"
|
||||
litellm = ">=1.74.3, <=1.80.7, !=1.64.4, !=1.67.*"
|
||||
lmnr = "^0.7.20"
|
||||
memory-profiler = "^0.61.0"
|
||||
numpy = "*"
|
||||
openai = "1.99.9"
|
||||
openai = "2.8.0"
|
||||
openhands-aci = "0.3.2"
|
||||
openhands-agent-server = "1.1.0"
|
||||
openhands-sdk = "1.1.0"
|
||||
openhands-tools = "1.1.0"
|
||||
openhands-agent-server = "1.5.2"
|
||||
openhands-sdk = "1.5.2"
|
||||
openhands-tools = "1.5.2"
|
||||
opentelemetry-api = "^1.33.1"
|
||||
opentelemetry-exporter-otlp-proto-grpc = "^1.33.1"
|
||||
pathspec = "^0.12.1"
|
||||
@ -5942,20 +5959,21 @@ url = ".."
|
||||
|
||||
[[package]]
|
||||
name = "openhands-sdk"
|
||||
version = "1.1.0"
|
||||
version = "1.5.2"
|
||||
description = "OpenHands SDK - Core functionality for building AI agents"
|
||||
optional = false
|
||||
python-versions = ">=3.12"
|
||||
groups = ["main"]
|
||||
files = [
|
||||
{file = "openhands_sdk-1.1.0-py3-none-any.whl", hash = "sha256:4a984ce1687a48cf99a67fdf3d37b116f8b2840743d4807810b5024af6a1d57e"},
|
||||
{file = "openhands_sdk-1.1.0.tar.gz", hash = "sha256:855e0d8f3657205e4119e50520c17e65b3358b1a923f7a051a82512a54bf426c"},
|
||||
{file = "openhands_sdk-1.5.2-py3-none-any.whl", hash = "sha256:593430e9c8729e345fce3fca7e9a9a7ef084a08222d6ba42113e6ba5f6e9f15d"},
|
||||
{file = "openhands_sdk-1.5.2.tar.gz", hash = "sha256:798aa8f8ccd84b15deb418c4301d00f33da288bc1a8d41efa5cc47c10aaf3fd6"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
deprecation = ">=2.1.0"
|
||||
fastmcp = ">=2.11.3"
|
||||
httpx = ">=0.27.0"
|
||||
litellm = ">=1.77.7.dev9"
|
||||
litellm = ">=1.80.7"
|
||||
lmnr = ">=0.7.20"
|
||||
pydantic = ">=2.11.7"
|
||||
python-frontmatter = ">=1.1.0"
|
||||
@ -5968,14 +5986,14 @@ boto3 = ["boto3 (>=1.35.0)"]
|
||||
|
||||
[[package]]
|
||||
name = "openhands-tools"
|
||||
version = "1.1.0"
|
||||
version = "1.5.2"
|
||||
description = "OpenHands Tools - Runtime tools for AI agents"
|
||||
optional = false
|
||||
python-versions = ">=3.12"
|
||||
groups = ["main"]
|
||||
files = [
|
||||
{file = "openhands_tools-1.1.0-py3-none-any.whl", hash = "sha256:767d6746f05edade49263aa24450a037485a3dc23379f56917ef19aad22033f9"},
|
||||
{file = "openhands_tools-1.1.0.tar.gz", hash = "sha256:c2fadaa4f4e16e9a3df5781ea847565dcae7171584f09ef7c0e1d97c8dfc83f6"},
|
||||
{file = "openhands_tools-1.5.2-py3-none-any.whl", hash = "sha256:33e9c2af65aaa7b6b9a10b42d2fb11137e6b35e7ac02a4b9269ef37b5c79cc01"},
|
||||
{file = "openhands_tools-1.5.2.tar.gz", hash = "sha256:4644a24144fbdf630fb0edc303526b4add61b3fbe7a7434da73f231312c34846"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@ -5987,6 +6005,7 @@ func-timeout = ">=4.3.5"
|
||||
libtmux = ">=0.46.2"
|
||||
openhands-sdk = "*"
|
||||
pydantic = ">=2.11.7"
|
||||
tom-swe = ">=1.0.3"
|
||||
|
||||
[[package]]
|
||||
name = "openpyxl"
|
||||
@ -13303,6 +13322,31 @@ dev = ["tokenizers[testing]"]
|
||||
docs = ["setuptools-rust", "sphinx", "sphinx-rtd-theme"]
|
||||
testing = ["black (==22.3)", "datasets", "numpy", "pytest", "pytest-asyncio", "requests", "ruff"]
|
||||
|
||||
[[package]]
|
||||
name = "tom-swe"
|
||||
version = "1.0.3"
|
||||
description = "Theory of Mind modeling for Software Engineering assistants"
|
||||
optional = false
|
||||
python-versions = ">=3.10"
|
||||
groups = ["main"]
|
||||
files = [
|
||||
{file = "tom_swe-1.0.3-py3-none-any.whl", hash = "sha256:7b1172b29eb5c8fb7f1975016e7b6a238511b9ac2a7a980bd400dcb4e29773f2"},
|
||||
{file = "tom_swe-1.0.3.tar.gz", hash = "sha256:57c97d0104e563f15bd39edaf2aa6ac4c3e9444afd437fb92458700d22c6c0f5"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
jinja2 = ">=3.0.0"
|
||||
json-repair = ">=0.1.0"
|
||||
litellm = ">=1.0.0"
|
||||
pydantic = ">=2.0.0"
|
||||
python-dotenv = ">=1.0.0"
|
||||
tiktoken = ">=0.8.0"
|
||||
tqdm = ">=4.65.0"
|
||||
|
||||
[package.extras]
|
||||
dev = ["aiofiles (>=23.0.0)", "black (>=22.0.0)", "datasets (>=2.0.0)", "fastapi (>=0.104.0)", "httpx (>=0.25.0)", "huggingface-hub (>=0.0.0)", "isort (>=5.0.0)", "mypy (>=1.0.0)", "numpy (>=1.24.0)", "pandas (>=2.0.0)", "pre-commit (>=3.6.0)", "pytest (>=7.0.0)", "pytest-cov (>=6.2.1)", "rich (>=13.0.0)", "ruff (>=0.3.0)", "typing-extensions (>=4.0.0)", "uvicorn (>=0.24.0)"]
|
||||
search = ["bm25s (>=0.2.0)", "pystemmer (>=2.2.0)"]
|
||||
|
||||
[[package]]
|
||||
name = "toml"
|
||||
version = "0.10.2"
|
||||
|
||||
@ -30,3 +30,11 @@ JIRA_DC_CLIENT_SECRET = os.getenv('JIRA_DC_CLIENT_SECRET', '').strip()
|
||||
JIRA_DC_BASE_URL = os.getenv('JIRA_DC_BASE_URL', '').strip()
|
||||
JIRA_DC_ENABLE_OAUTH = os.getenv('JIRA_DC_ENABLE_OAUTH', '1') in ('1', 'true')
|
||||
AUTH_URL = os.getenv('AUTH_URL', '').rstrip('/')
|
||||
ROLE_CHECK_ENABLED = os.getenv('ROLE_CHECK_ENABLED', 'false').lower() in (
|
||||
'1',
|
||||
'true',
|
||||
't',
|
||||
'yes',
|
||||
'y',
|
||||
'on',
|
||||
)
|
||||
|
||||
@ -203,6 +203,15 @@ class SaasUserAuth(UserAuth):
|
||||
self.settings_store = settings_store
|
||||
return settings_store
|
||||
|
||||
async def get_mcp_api_key(self) -> str:
|
||||
api_key_store = ApiKeyStore.get_instance()
|
||||
mcp_api_key = api_key_store.retrieve_mcp_api_key(self.user_id)
|
||||
if not mcp_api_key:
|
||||
mcp_api_key = api_key_store.create_api_key(
|
||||
self.user_id, 'MCP_API_KEY', None
|
||||
)
|
||||
return mcp_api_key
|
||||
|
||||
@classmethod
|
||||
async def get_instance(cls, request: Request) -> UserAuth:
|
||||
logger.debug('saas_user_auth_get_instance')
|
||||
@ -243,7 +252,12 @@ def get_api_key_from_header(request: Request):
|
||||
# This is a temp hack
|
||||
# Streamable HTTP MCP Client works via redirect requests, but drops the Authorization header for reason
|
||||
# We include `X-Session-API-Key` header by default due to nested runtimes, so it used as a drop in replacement here
|
||||
return request.headers.get('X-Session-API-Key')
|
||||
session_api_key = request.headers.get('X-Session-API-Key')
|
||||
if session_api_key:
|
||||
return session_api_key
|
||||
|
||||
# Fallback to X-Access-Token header as an additional option
|
||||
return request.headers.get('X-Access-Token')
|
||||
|
||||
|
||||
async def saas_user_auth_from_bearer(request: Request) -> SaasUserAuth | None:
|
||||
|
||||
@ -1,331 +0,0 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import time
|
||||
from dataclasses import dataclass, field
|
||||
|
||||
import socketio
|
||||
from server.clustered_conversation_manager import ClusteredConversationManager
|
||||
from server.saas_nested_conversation_manager import SaasNestedConversationManager
|
||||
|
||||
from openhands.core.config import LLMConfig, OpenHandsConfig
|
||||
from openhands.events.action import MessageAction
|
||||
from openhands.server.config.server_config import ServerConfig
|
||||
from openhands.server.conversation_manager.conversation_manager import (
|
||||
ConversationManager,
|
||||
)
|
||||
from openhands.server.data_models.agent_loop_info import AgentLoopInfo
|
||||
from openhands.server.monitoring import MonitoringListener
|
||||
from openhands.server.session.conversation import ServerConversation
|
||||
from openhands.storage.data_models.settings import Settings
|
||||
from openhands.storage.files import FileStore
|
||||
from openhands.utils.async_utils import wait_all
|
||||
|
||||
_LEGACY_ENTRY_TIMEOUT_SECONDS = 3600
|
||||
|
||||
|
||||
@dataclass
|
||||
class LegacyCacheEntry:
|
||||
"""Cache entry for legacy mode status."""
|
||||
|
||||
is_legacy: bool
|
||||
timestamp: float
|
||||
|
||||
|
||||
@dataclass
|
||||
class LegacyConversationManager(ConversationManager):
|
||||
"""
|
||||
Conversation manager for use while migrating - since existing conversations are not nested!
|
||||
Separate class from SaasNestedConversationManager so it can be easliy removed in a few weeks.
|
||||
(As of 2025-07-23)
|
||||
"""
|
||||
|
||||
sio: socketio.AsyncServer
|
||||
config: OpenHandsConfig
|
||||
server_config: ServerConfig
|
||||
file_store: FileStore
|
||||
conversation_manager: SaasNestedConversationManager
|
||||
legacy_conversation_manager: ClusteredConversationManager
|
||||
_legacy_cache: dict[str, LegacyCacheEntry] = field(default_factory=dict)
|
||||
|
||||
async def __aenter__(self):
|
||||
await wait_all(
|
||||
[
|
||||
self.conversation_manager.__aenter__(),
|
||||
self.legacy_conversation_manager.__aenter__(),
|
||||
]
|
||||
)
|
||||
return self
|
||||
|
||||
async def __aexit__(self, exc_type, exc_value, traceback):
|
||||
await wait_all(
|
||||
[
|
||||
self.conversation_manager.__aexit__(exc_type, exc_value, traceback),
|
||||
self.legacy_conversation_manager.__aexit__(
|
||||
exc_type, exc_value, traceback
|
||||
),
|
||||
]
|
||||
)
|
||||
|
||||
async def request_llm_completion(
|
||||
self,
|
||||
sid: str,
|
||||
service_id: str,
|
||||
llm_config: LLMConfig,
|
||||
messages: list[dict[str, str]],
|
||||
) -> str:
|
||||
session = self.get_agent_session(sid)
|
||||
llm_registry = session.llm_registry
|
||||
return llm_registry.request_extraneous_completion(
|
||||
service_id, llm_config, messages
|
||||
)
|
||||
|
||||
async def attach_to_conversation(
|
||||
self, sid: str, user_id: str | None = None
|
||||
) -> ServerConversation | None:
|
||||
if await self.should_start_in_legacy_mode(sid):
|
||||
return await self.legacy_conversation_manager.attach_to_conversation(
|
||||
sid, user_id
|
||||
)
|
||||
return await self.conversation_manager.attach_to_conversation(sid, user_id)
|
||||
|
||||
async def detach_from_conversation(self, conversation: ServerConversation):
|
||||
if await self.should_start_in_legacy_mode(conversation.sid):
|
||||
return await self.legacy_conversation_manager.detach_from_conversation(
|
||||
conversation
|
||||
)
|
||||
return await self.conversation_manager.detach_from_conversation(conversation)
|
||||
|
||||
async def join_conversation(
|
||||
self,
|
||||
sid: str,
|
||||
connection_id: str,
|
||||
settings: Settings,
|
||||
user_id: str | None,
|
||||
) -> AgentLoopInfo:
|
||||
if await self.should_start_in_legacy_mode(sid):
|
||||
return await self.legacy_conversation_manager.join_conversation(
|
||||
sid, connection_id, settings, user_id
|
||||
)
|
||||
return await self.conversation_manager.join_conversation(
|
||||
sid, connection_id, settings, user_id
|
||||
)
|
||||
|
||||
def get_agent_session(self, sid: str):
|
||||
session = self.legacy_conversation_manager.get_agent_session(sid)
|
||||
if session is None:
|
||||
session = self.conversation_manager.get_agent_session(sid)
|
||||
return session
|
||||
|
||||
async def get_running_agent_loops(
|
||||
self, user_id: str | None = None, filter_to_sids: set[str] | None = None
|
||||
) -> set[str]:
|
||||
if filter_to_sids and len(filter_to_sids) == 1:
|
||||
sid = next(iter(filter_to_sids))
|
||||
if await self.should_start_in_legacy_mode(sid):
|
||||
return await self.legacy_conversation_manager.get_running_agent_loops(
|
||||
user_id, filter_to_sids
|
||||
)
|
||||
return await self.conversation_manager.get_running_agent_loops(
|
||||
user_id, filter_to_sids
|
||||
)
|
||||
|
||||
# Get all running agent loops from both managers
|
||||
agent_loops, legacy_agent_loops = await wait_all(
|
||||
[
|
||||
self.conversation_manager.get_running_agent_loops(
|
||||
user_id, filter_to_sids
|
||||
),
|
||||
self.legacy_conversation_manager.get_running_agent_loops(
|
||||
user_id, filter_to_sids
|
||||
),
|
||||
]
|
||||
)
|
||||
|
||||
# Combine the results
|
||||
result = set()
|
||||
for sid in legacy_agent_loops:
|
||||
if await self.should_start_in_legacy_mode(sid):
|
||||
result.add(sid)
|
||||
|
||||
for sid in agent_loops:
|
||||
if not await self.should_start_in_legacy_mode(sid):
|
||||
result.add(sid)
|
||||
|
||||
return result
|
||||
|
||||
async def is_agent_loop_running(self, sid: str) -> bool:
|
||||
return bool(await self.get_running_agent_loops(filter_to_sids={sid}))
|
||||
|
||||
async def get_connections(
|
||||
self, user_id: str | None = None, filter_to_sids: set[str] | None = None
|
||||
) -> dict[str, str]:
|
||||
if filter_to_sids and len(filter_to_sids) == 1:
|
||||
sid = next(iter(filter_to_sids))
|
||||
if await self.should_start_in_legacy_mode(sid):
|
||||
return await self.legacy_conversation_manager.get_connections(
|
||||
user_id, filter_to_sids
|
||||
)
|
||||
return await self.conversation_manager.get_connections(
|
||||
user_id, filter_to_sids
|
||||
)
|
||||
agent_loops, legacy_agent_loops = await wait_all(
|
||||
[
|
||||
self.conversation_manager.get_connections(user_id, filter_to_sids),
|
||||
self.legacy_conversation_manager.get_connections(
|
||||
user_id, filter_to_sids
|
||||
),
|
||||
]
|
||||
)
|
||||
legacy_agent_loops.update(agent_loops)
|
||||
return legacy_agent_loops
|
||||
|
||||
async def maybe_start_agent_loop(
|
||||
self,
|
||||
sid: str,
|
||||
settings: Settings,
|
||||
user_id: str, # type: ignore[override]
|
||||
initial_user_msg: MessageAction | None = None,
|
||||
replay_json: str | None = None,
|
||||
) -> AgentLoopInfo:
|
||||
if await self.should_start_in_legacy_mode(sid):
|
||||
return await self.legacy_conversation_manager.maybe_start_agent_loop(
|
||||
sid, settings, user_id, initial_user_msg, replay_json
|
||||
)
|
||||
return await self.conversation_manager.maybe_start_agent_loop(
|
||||
sid, settings, user_id, initial_user_msg, replay_json
|
||||
)
|
||||
|
||||
async def send_to_event_stream(self, connection_id: str, data: dict):
|
||||
return await self.legacy_conversation_manager.send_to_event_stream(
|
||||
connection_id, data
|
||||
)
|
||||
|
||||
async def send_event_to_conversation(self, sid: str, data: dict):
|
||||
if await self.should_start_in_legacy_mode(sid):
|
||||
await self.legacy_conversation_manager.send_event_to_conversation(sid, data)
|
||||
await self.conversation_manager.send_event_to_conversation(sid, data)
|
||||
|
||||
async def disconnect_from_session(self, connection_id: str):
|
||||
return await self.legacy_conversation_manager.disconnect_from_session(
|
||||
connection_id
|
||||
)
|
||||
|
||||
async def close_session(self, sid: str):
|
||||
if await self.should_start_in_legacy_mode(sid):
|
||||
await self.legacy_conversation_manager.close_session(sid)
|
||||
await self.conversation_manager.close_session(sid)
|
||||
|
||||
async def get_agent_loop_info(
|
||||
self, user_id: str | None = None, filter_to_sids: set[str] | None = None
|
||||
) -> list[AgentLoopInfo]:
|
||||
if filter_to_sids and len(filter_to_sids) == 1:
|
||||
sid = next(iter(filter_to_sids))
|
||||
if await self.should_start_in_legacy_mode(sid):
|
||||
return await self.legacy_conversation_manager.get_agent_loop_info(
|
||||
user_id, filter_to_sids
|
||||
)
|
||||
return await self.conversation_manager.get_agent_loop_info(
|
||||
user_id, filter_to_sids
|
||||
)
|
||||
agent_loops, legacy_agent_loops = await wait_all(
|
||||
[
|
||||
self.conversation_manager.get_agent_loop_info(user_id, filter_to_sids),
|
||||
self.legacy_conversation_manager.get_agent_loop_info(
|
||||
user_id, filter_to_sids
|
||||
),
|
||||
]
|
||||
)
|
||||
|
||||
# Combine results
|
||||
result = []
|
||||
legacy_sids = set()
|
||||
|
||||
# Add legacy agent loops
|
||||
for agent_loop in legacy_agent_loops:
|
||||
if await self.should_start_in_legacy_mode(agent_loop.conversation_id):
|
||||
result.append(agent_loop)
|
||||
legacy_sids.add(agent_loop.conversation_id)
|
||||
|
||||
# Add non-legacy agent loops
|
||||
for agent_loop in agent_loops:
|
||||
if (
|
||||
agent_loop.conversation_id not in legacy_sids
|
||||
and not await self.should_start_in_legacy_mode(
|
||||
agent_loop.conversation_id
|
||||
)
|
||||
):
|
||||
result.append(agent_loop)
|
||||
|
||||
return result
|
||||
|
||||
def _cleanup_expired_cache_entries(self):
|
||||
"""Remove expired entries from the local cache."""
|
||||
current_time = time.time()
|
||||
expired_keys = [
|
||||
key
|
||||
for key, entry in self._legacy_cache.items()
|
||||
if current_time - entry.timestamp > _LEGACY_ENTRY_TIMEOUT_SECONDS
|
||||
]
|
||||
for key in expired_keys:
|
||||
del self._legacy_cache[key]
|
||||
|
||||
async def should_start_in_legacy_mode(self, conversation_id: str) -> bool:
|
||||
"""
|
||||
Check if a conversation should run in legacy mode by directly checking the runtime.
|
||||
The /list method does not include stopped conversations even though the PVC for these
|
||||
may not yet have been deleted, so we need to check /sessions/{session_id} directly.
|
||||
"""
|
||||
# Clean up expired entries periodically
|
||||
self._cleanup_expired_cache_entries()
|
||||
|
||||
# First check the local cache
|
||||
if conversation_id in self._legacy_cache:
|
||||
cached_entry = self._legacy_cache[conversation_id]
|
||||
# Check if the cached value is still valid
|
||||
if time.time() - cached_entry.timestamp <= _LEGACY_ENTRY_TIMEOUT_SECONDS:
|
||||
return cached_entry.is_legacy
|
||||
|
||||
# If not in cache or expired, check the runtime directly
|
||||
runtime = await self.conversation_manager._get_runtime(conversation_id)
|
||||
is_legacy = self.is_legacy_runtime(runtime)
|
||||
|
||||
# Cache the result with current timestamp
|
||||
self._legacy_cache[conversation_id] = LegacyCacheEntry(is_legacy, time.time())
|
||||
|
||||
return is_legacy
|
||||
|
||||
def is_legacy_runtime(self, runtime: dict | None) -> bool:
|
||||
"""
|
||||
Determine if a runtime is a legacy runtime based on its command.
|
||||
|
||||
Args:
|
||||
runtime: The runtime dictionary or None if not found
|
||||
|
||||
Returns:
|
||||
bool: True if this is a legacy runtime, False otherwise
|
||||
"""
|
||||
if runtime is None:
|
||||
return False
|
||||
return 'openhands.server' not in runtime['command']
|
||||
|
||||
@classmethod
|
||||
def get_instance(
|
||||
cls,
|
||||
sio: socketio.AsyncServer,
|
||||
config: OpenHandsConfig,
|
||||
file_store: FileStore,
|
||||
server_config: ServerConfig,
|
||||
monitoring_listener: MonitoringListener,
|
||||
) -> ConversationManager:
|
||||
return LegacyConversationManager(
|
||||
sio=sio,
|
||||
config=config,
|
||||
server_config=server_config,
|
||||
file_store=file_store,
|
||||
conversation_manager=SaasNestedConversationManager.get_instance(
|
||||
sio, config, file_store, server_config, monitoring_listener
|
||||
),
|
||||
legacy_conversation_manager=ClusteredConversationManager.get_instance(
|
||||
sio, config, file_store, server_config, monitoring_listener
|
||||
),
|
||||
)
|
||||
@ -12,6 +12,7 @@ from server.auth.constants import (
|
||||
KEYCLOAK_CLIENT_ID,
|
||||
KEYCLOAK_REALM_NAME,
|
||||
KEYCLOAK_SERVER_URL_EXT,
|
||||
ROLE_CHECK_ENABLED,
|
||||
)
|
||||
from server.auth.gitlab_sync import schedule_gitlab_repo_sync
|
||||
from server.auth.saas_user_auth import SaasUserAuth
|
||||
@ -30,7 +31,6 @@ from openhands.server.services.conversation_service import create_provider_token
|
||||
from openhands.server.shared import config
|
||||
from openhands.server.user_auth import get_access_token
|
||||
from openhands.server.user_auth.user_auth import get_user_auth
|
||||
from openhands.utils.posthog_tracker import track_user_signup_completed
|
||||
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter('ignore')
|
||||
@ -133,6 +133,12 @@ async def keycloak_callback(
|
||||
|
||||
user_info = await token_manager.get_user_info(keycloak_access_token)
|
||||
logger.debug(f'user_info: {user_info}')
|
||||
if ROLE_CHECK_ENABLED and 'roles' not in user_info:
|
||||
return JSONResponse(
|
||||
status_code=status.HTTP_401_UNAUTHORIZED,
|
||||
content={'error': 'Missing required role'},
|
||||
)
|
||||
|
||||
if 'sub' not in user_info or 'preferred_username' not in user_info:
|
||||
return JSONResponse(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
@ -363,12 +369,6 @@ async def accept_tos(request: Request):
|
||||
|
||||
logger.info(f'User {user_id} accepted TOS')
|
||||
|
||||
# Track user signup completion in PostHog
|
||||
track_user_signup_completed(
|
||||
user_id=user_id,
|
||||
signup_timestamp=user_settings.accepted_tos.isoformat(),
|
||||
)
|
||||
|
||||
response = JSONResponse(
|
||||
status_code=status.HTTP_200_OK, content={'redirect_url': redirect_url}
|
||||
)
|
||||
|
||||
@ -28,7 +28,6 @@ from storage.subscription_access import SubscriptionAccess
|
||||
|
||||
from openhands.server.user_auth import get_user_id
|
||||
from openhands.utils.http_session import httpx_verify_option
|
||||
from openhands.utils.posthog_tracker import track_credits_purchased
|
||||
|
||||
stripe.api_key = STRIPE_API_KEY
|
||||
billing_router = APIRouter(prefix='/api/billing')
|
||||
@ -458,20 +457,6 @@ async def success_callback(session_id: str, request: Request):
|
||||
)
|
||||
session.commit()
|
||||
|
||||
# Track credits purchased in PostHog
|
||||
try:
|
||||
track_credits_purchased(
|
||||
user_id=billing_session.user_id,
|
||||
amount_usd=amount_subtotal / 100, # Convert cents to dollars
|
||||
credits_added=add_credits,
|
||||
stripe_session_id=session_id,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
f'Failed to track credits purchase: {e}',
|
||||
extra={'user_id': billing_session.user_id, 'error': str(e)},
|
||||
)
|
||||
|
||||
return RedirectResponse(
|
||||
f'{request.base_url}settings/billing?checkout=success', status_code=302
|
||||
)
|
||||
|
||||
@ -1,3 +1,4 @@
|
||||
import asyncio
|
||||
import hashlib
|
||||
import hmac
|
||||
import os
|
||||
@ -58,7 +59,8 @@ async def github_events(
|
||||
)
|
||||
|
||||
try:
|
||||
payload = await request.body()
|
||||
# Add timeout to prevent hanging on slow/stalled clients
|
||||
payload = await asyncio.wait_for(request.body(), timeout=15.0)
|
||||
verify_github_signature(payload, x_hub_signature_256)
|
||||
|
||||
payload_data = await request.json()
|
||||
@ -78,6 +80,12 @@ async def github_events(
|
||||
status_code=200,
|
||||
content={'message': 'GitHub events endpoint reached successfully.'},
|
||||
)
|
||||
except asyncio.TimeoutError:
|
||||
logger.warning('GitHub webhook request timed out waiting for request body')
|
||||
return JSONResponse(
|
||||
status_code=408,
|
||||
content={'error': 'Request timeout - client took too long to send data.'},
|
||||
)
|
||||
except Exception as e:
|
||||
logger.exception(f'Error processing GitHub event: {e}')
|
||||
return JSONResponse(status_code=400, content={'error': 'Invalid payload.'})
|
||||
|
||||
@ -70,6 +70,11 @@ RUNTIME_CONVERSATION_URL = RUNTIME_URL_PATTERN + (
|
||||
else '/api/conversations/{conversation_id}'
|
||||
)
|
||||
|
||||
RUNTIME_USERNAME = os.getenv('RUNTIME_USERNAME')
|
||||
SU_TO_USER = os.getenv('SU_TO_USER', 'false')
|
||||
truthy = {'1', 'true', 't', 'yes', 'y', 'on'}
|
||||
SU_TO_USER = str(SU_TO_USER.lower() in truthy).lower()
|
||||
|
||||
# Time in seconds before a Redis entry is considered expired if not refreshed
|
||||
_REDIS_ENTRY_TIMEOUT_SECONDS = 300
|
||||
|
||||
@ -772,7 +777,11 @@ class SaasNestedConversationManager(ConversationManager):
|
||||
env_vars['SERVE_FRONTEND'] = '0'
|
||||
env_vars['RUNTIME'] = 'local'
|
||||
# TODO: In the long term we may come up with a more secure strategy for user management within the nested runtime.
|
||||
env_vars['USER'] = 'openhands' if config.run_as_openhands else 'root'
|
||||
env_vars['USER'] = (
|
||||
RUNTIME_USERNAME
|
||||
if RUNTIME_USERNAME
|
||||
else ('openhands' if config.run_as_openhands else 'root')
|
||||
)
|
||||
env_vars['PERMITTED_CORS_ORIGINS'] = ','.join(PERMITTED_CORS_ORIGINS)
|
||||
env_vars['port'] = '60000'
|
||||
# TODO: These values are static in the runtime-api project, but do not get copied into the runtime ENV
|
||||
@ -789,6 +798,7 @@ class SaasNestedConversationManager(ConversationManager):
|
||||
env_vars['INITIAL_NUM_WARM_SERVERS'] = '1'
|
||||
env_vars['INIT_GIT_IN_EMPTY_WORKSPACE'] = '1'
|
||||
env_vars['ENABLE_V1'] = '0'
|
||||
env_vars['SU_TO_USER'] = SU_TO_USER
|
||||
|
||||
# We need this for LLM traces tracking to identify the source of the LLM calls
|
||||
env_vars['WEB_HOST'] = WEB_HOST
|
||||
|
||||
@ -97,6 +97,10 @@ class SaasSettingsStore(SettingsStore):
|
||||
return settings
|
||||
|
||||
async def store(self, item: Settings):
|
||||
# Check if provider is OpenHands and generate API key if needed
|
||||
if item and self._is_openhands_provider(item):
|
||||
await self._ensure_openhands_api_key(item)
|
||||
|
||||
with self.session_maker() as session:
|
||||
existing = None
|
||||
kwargs = {}
|
||||
@ -368,6 +372,30 @@ class SaasSettingsStore(SettingsStore):
|
||||
def _should_encrypt(self, key: str) -> bool:
|
||||
return key in ('llm_api_key', 'llm_api_key_for_byor', 'search_api_key')
|
||||
|
||||
def _is_openhands_provider(self, item: Settings) -> bool:
|
||||
"""Check if the settings use the OpenHands provider."""
|
||||
return bool(item.llm_model and item.llm_model.startswith('openhands/'))
|
||||
|
||||
async def _ensure_openhands_api_key(self, item: Settings) -> None:
|
||||
"""Generate and set the OpenHands API key for the given settings.
|
||||
|
||||
First checks if an existing key with the OpenHands alias exists,
|
||||
and reuses it if found. Otherwise, generates a new key.
|
||||
"""
|
||||
# Generate new key if none exists
|
||||
generated_key = await self._generate_openhands_key()
|
||||
if generated_key:
|
||||
item.llm_api_key = SecretStr(generated_key)
|
||||
logger.info(
|
||||
'saas_settings_store:store:generated_openhands_key',
|
||||
extra={'user_id': self.user_id},
|
||||
)
|
||||
else:
|
||||
logger.warning(
|
||||
'saas_settings_store:store:failed_to_generate_openhands_key',
|
||||
extra={'user_id': self.user_id},
|
||||
)
|
||||
|
||||
async def _create_user_in_lite_llm(
|
||||
self, client: httpx.AsyncClient, email: str | None, max_budget: int, spend: int
|
||||
):
|
||||
@ -390,3 +418,55 @@ class SaasSettingsStore(SettingsStore):
|
||||
},
|
||||
)
|
||||
return response
|
||||
|
||||
async def _generate_openhands_key(self) -> str | None:
|
||||
"""Generate a new OpenHands provider key for a user."""
|
||||
if not (LITE_LLM_API_KEY and LITE_LLM_API_URL):
|
||||
logger.warning(
|
||||
'saas_settings_store:_generate_openhands_key:litellm_config_not_found',
|
||||
extra={'user_id': self.user_id},
|
||||
)
|
||||
return None
|
||||
|
||||
try:
|
||||
async with httpx.AsyncClient(
|
||||
verify=httpx_verify_option(),
|
||||
headers={
|
||||
'x-goog-api-key': LITE_LLM_API_KEY,
|
||||
},
|
||||
) as client:
|
||||
response = await client.post(
|
||||
f'{LITE_LLM_API_URL}/key/generate',
|
||||
json={
|
||||
'user_id': self.user_id,
|
||||
'metadata': {'type': 'openhands'},
|
||||
},
|
||||
)
|
||||
response.raise_for_status()
|
||||
response_json = response.json()
|
||||
key = response_json.get('key')
|
||||
|
||||
if key:
|
||||
logger.info(
|
||||
'saas_settings_store:_generate_openhands_key:success',
|
||||
extra={
|
||||
'user_id': self.user_id,
|
||||
'key_length': len(key) if key else 0,
|
||||
'key_prefix': (
|
||||
key[:10] + '...' if key and len(key) > 10 else key
|
||||
),
|
||||
},
|
||||
)
|
||||
return key
|
||||
else:
|
||||
logger.error(
|
||||
'saas_settings_store:_generate_openhands_key:no_key_in_response',
|
||||
extra={'user_id': self.user_id, 'response_json': response_json},
|
||||
)
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.exception(
|
||||
'saas_settings_store:_generate_openhands_key:error',
|
||||
extra={'user_id': self.user_id, 'error': str(e)},
|
||||
)
|
||||
return None
|
||||
|
||||
@ -38,3 +38,4 @@ class UserSettings(Base): # type: ignore
|
||||
email_verified = Column(Boolean, nullable=True)
|
||||
git_user_name = Column(String, nullable=True)
|
||||
git_user_email = Column(String, nullable=True)
|
||||
v1_enabled = Column(Boolean, nullable=True)
|
||||
|
||||
133
enterprise/tests/unit/integrations/test_resolver_context.py
Normal file
133
enterprise/tests/unit/integrations/test_resolver_context.py
Normal file
@ -0,0 +1,133 @@
|
||||
"""Test for ResolverUserContext get_secrets conversion logic.
|
||||
|
||||
This test focuses on testing the actual ResolverUserContext implementation.
|
||||
"""
|
||||
|
||||
from types import MappingProxyType
|
||||
from unittest.mock import AsyncMock
|
||||
|
||||
import pytest
|
||||
from pydantic import SecretStr
|
||||
|
||||
from enterprise.integrations.resolver_context import ResolverUserContext
|
||||
|
||||
# Import the real classes we want to test
|
||||
from openhands.integrations.provider import CustomSecret
|
||||
|
||||
# Import the SDK types we need for testing
|
||||
from openhands.sdk.secret import SecretSource, StaticSecret
|
||||
from openhands.storage.data_models.secrets import Secrets
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_saas_user_auth():
|
||||
"""Mock SaasUserAuth for testing."""
|
||||
return AsyncMock()
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def resolver_context(mock_saas_user_auth):
|
||||
"""Create a ResolverUserContext instance for testing."""
|
||||
return ResolverUserContext(saas_user_auth=mock_saas_user_auth)
|
||||
|
||||
|
||||
def create_custom_secret(value: str, description: str = 'Test secret') -> CustomSecret:
|
||||
"""Helper to create CustomSecret instances."""
|
||||
return CustomSecret(secret=SecretStr(value), description=description)
|
||||
|
||||
|
||||
def create_secrets(custom_secrets_dict: dict[str, CustomSecret]) -> Secrets:
|
||||
"""Helper to create Secrets instances."""
|
||||
return Secrets(custom_secrets=MappingProxyType(custom_secrets_dict))
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_secrets_converts_custom_to_static(
|
||||
resolver_context, mock_saas_user_auth
|
||||
):
|
||||
"""Test that get_secrets correctly converts CustomSecret objects to StaticSecret objects."""
|
||||
# Arrange
|
||||
secrets = create_secrets(
|
||||
{
|
||||
'TEST_SECRET_1': create_custom_secret('secret_value_1'),
|
||||
'TEST_SECRET_2': create_custom_secret('secret_value_2'),
|
||||
}
|
||||
)
|
||||
mock_saas_user_auth.get_secrets.return_value = secrets
|
||||
|
||||
# Act
|
||||
result = await resolver_context.get_secrets()
|
||||
|
||||
# Assert
|
||||
assert len(result) == 2
|
||||
assert all(isinstance(secret, StaticSecret) for secret in result.values())
|
||||
assert result['TEST_SECRET_1'].value.get_secret_value() == 'secret_value_1'
|
||||
assert result['TEST_SECRET_2'].value.get_secret_value() == 'secret_value_2'
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_secrets_with_special_characters(
|
||||
resolver_context, mock_saas_user_auth
|
||||
):
|
||||
"""Test that secret values with special characters are preserved during conversion."""
|
||||
# Arrange
|
||||
special_value = 'very_secret_password_123!@#$%^&*()'
|
||||
secrets = create_secrets({'SPECIAL_SECRET': create_custom_secret(special_value)})
|
||||
mock_saas_user_auth.get_secrets.return_value = secrets
|
||||
|
||||
# Act
|
||||
result = await resolver_context.get_secrets()
|
||||
|
||||
# Assert
|
||||
assert len(result) == 1
|
||||
assert isinstance(result['SPECIAL_SECRET'], StaticSecret)
|
||||
assert result['SPECIAL_SECRET'].value.get_secret_value() == special_value
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(
|
||||
'secrets_input,expected_result',
|
||||
[
|
||||
(None, {}), # No secrets available
|
||||
(create_secrets({}), {}), # Empty custom secrets
|
||||
],
|
||||
)
|
||||
async def test_get_secrets_empty_cases(
|
||||
resolver_context, mock_saas_user_auth, secrets_input, expected_result
|
||||
):
|
||||
"""Test that get_secrets handles empty cases correctly."""
|
||||
# Arrange
|
||||
mock_saas_user_auth.get_secrets.return_value = secrets_input
|
||||
|
||||
# Act
|
||||
result = await resolver_context.get_secrets()
|
||||
|
||||
# Assert
|
||||
assert result == expected_result
|
||||
|
||||
|
||||
def test_static_secret_is_valid_secret_source():
|
||||
"""Test that StaticSecret is a valid SecretSource for SDK validation."""
|
||||
# Arrange & Act
|
||||
static_secret = StaticSecret(value='test_secret_123')
|
||||
|
||||
# Assert
|
||||
assert isinstance(static_secret, StaticSecret)
|
||||
assert isinstance(static_secret, SecretSource)
|
||||
assert static_secret.value.get_secret_value() == 'test_secret_123'
|
||||
|
||||
|
||||
def test_custom_to_static_conversion():
|
||||
"""Test the complete conversion flow from CustomSecret to StaticSecret."""
|
||||
# Arrange
|
||||
secret_value = 'conversion_test_secret'
|
||||
custom_secret = create_custom_secret(secret_value, 'Conversion test')
|
||||
|
||||
# Act - simulate the conversion logic from the actual method
|
||||
extracted_value = custom_secret.secret.get_secret_value()
|
||||
static_secret = StaticSecret(value=extracted_value)
|
||||
|
||||
# Assert
|
||||
assert isinstance(static_secret, StaticSecret)
|
||||
assert isinstance(static_secret, SecretSource)
|
||||
assert static_secret.value.get_secret_value() == secret_value
|
||||
132
enterprise/tests/unit/test_get_user_v1_enabled_setting.py
Normal file
132
enterprise/tests/unit/test_get_user_v1_enabled_setting.py
Normal file
@ -0,0 +1,132 @@
|
||||
"""Unit tests for get_user_v1_enabled_setting function."""
|
||||
|
||||
import os
|
||||
from unittest.mock import AsyncMock, MagicMock, patch
|
||||
|
||||
import pytest
|
||||
from integrations.github.github_view import get_user_v1_enabled_setting
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_user_settings():
|
||||
"""Create a mock user settings object."""
|
||||
settings = MagicMock()
|
||||
settings.v1_enabled = True # Default to True, can be overridden in tests
|
||||
return settings
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_settings_store(mock_user_settings):
|
||||
"""Create a mock settings store."""
|
||||
store = MagicMock()
|
||||
store.get_user_settings_by_keycloak_id = AsyncMock(return_value=mock_user_settings)
|
||||
return store
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_config():
|
||||
"""Create a mock config object."""
|
||||
return MagicMock()
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_session_maker():
|
||||
"""Create a mock session maker."""
|
||||
return MagicMock()
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_dependencies(
|
||||
mock_settings_store, mock_config, mock_session_maker, mock_user_settings
|
||||
):
|
||||
"""Fixture that patches all the common dependencies."""
|
||||
with patch(
|
||||
'integrations.github.github_view.SaasSettingsStore',
|
||||
return_value=mock_settings_store,
|
||||
) as mock_store_class, patch(
|
||||
'integrations.github.github_view.get_config', return_value=mock_config
|
||||
) as mock_get_config, patch(
|
||||
'integrations.github.github_view.session_maker', mock_session_maker
|
||||
), patch(
|
||||
'integrations.github.github_view.call_sync_from_async',
|
||||
return_value=mock_user_settings,
|
||||
) as mock_call_sync:
|
||||
yield {
|
||||
'store_class': mock_store_class,
|
||||
'get_config': mock_get_config,
|
||||
'session_maker': mock_session_maker,
|
||||
'call_sync': mock_call_sync,
|
||||
'settings_store': mock_settings_store,
|
||||
'user_settings': mock_user_settings,
|
||||
}
|
||||
|
||||
|
||||
class TestGetUserV1EnabledSetting:
|
||||
"""Test cases for get_user_v1_enabled_setting function."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(
|
||||
'env_var_enabled,user_setting_enabled,expected_result',
|
||||
[
|
||||
(False, True, False), # Env var disabled, user enabled -> False
|
||||
(True, False, False), # Env var enabled, user disabled -> False
|
||||
(True, True, True), # Both enabled -> True
|
||||
(False, False, False), # Both disabled -> False
|
||||
],
|
||||
)
|
||||
async def test_v1_enabled_combinations(
|
||||
self, mock_dependencies, env_var_enabled, user_setting_enabled, expected_result
|
||||
):
|
||||
"""Test all combinations of environment variable and user setting values."""
|
||||
mock_dependencies['user_settings'].v1_enabled = user_setting_enabled
|
||||
|
||||
with patch(
|
||||
'integrations.github.github_view.ENABLE_V1_GITHUB_RESOLVER', env_var_enabled
|
||||
):
|
||||
result = await get_user_v1_enabled_setting('test_user_id')
|
||||
assert result is expected_result
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(
|
||||
'env_var_value,env_var_bool,expected_result',
|
||||
[
|
||||
('false', False, False), # Environment variable 'false' -> False
|
||||
('true', True, True), # Environment variable 'true' -> True
|
||||
],
|
||||
)
|
||||
async def test_environment_variable_integration(
|
||||
self, mock_dependencies, env_var_value, env_var_bool, expected_result
|
||||
):
|
||||
"""Test that the function properly reads the ENABLE_V1_GITHUB_RESOLVER environment variable."""
|
||||
mock_dependencies['user_settings'].v1_enabled = True
|
||||
|
||||
with patch.dict(
|
||||
os.environ, {'ENABLE_V1_GITHUB_RESOLVER': env_var_value}
|
||||
), patch('integrations.utils.os.getenv', return_value=env_var_value), patch(
|
||||
'integrations.github.github_view.ENABLE_V1_GITHUB_RESOLVER', env_var_bool
|
||||
):
|
||||
result = await get_user_v1_enabled_setting('test_user_id')
|
||||
assert result is expected_result
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_function_calls_correct_methods(self, mock_dependencies):
|
||||
"""Test that the function calls the correct methods with correct parameters."""
|
||||
mock_dependencies['user_settings'].v1_enabled = True
|
||||
|
||||
with patch('integrations.github.github_view.ENABLE_V1_GITHUB_RESOLVER', True):
|
||||
result = await get_user_v1_enabled_setting('test_user_123')
|
||||
|
||||
# Verify the result
|
||||
assert result is True
|
||||
|
||||
# Verify correct methods were called with correct parameters
|
||||
mock_dependencies['get_config'].assert_called_once()
|
||||
mock_dependencies['store_class'].assert_called_once_with(
|
||||
user_id='test_user_123',
|
||||
session_maker=mock_dependencies['session_maker'],
|
||||
config=mock_dependencies['get_config'].return_value,
|
||||
)
|
||||
mock_dependencies['call_sync'].assert_called_once_with(
|
||||
mock_dependencies['settings_store'].get_user_settings_by_keycloak_id,
|
||||
'test_user_123',
|
||||
)
|
||||
@ -1,7 +1,10 @@
|
||||
from unittest import TestCase, mock
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
from integrations.github.github_view import GithubFactory, get_oh_labels
|
||||
import pytest
|
||||
from integrations.github.github_view import GithubFactory, GithubIssue, get_oh_labels
|
||||
from integrations.models import Message, SourceType
|
||||
from integrations.types import UserData
|
||||
|
||||
|
||||
class TestGithubLabels(TestCase):
|
||||
@ -75,3 +78,132 @@ class TestGithubCommentCaseInsensitivity(TestCase):
|
||||
self.assertTrue(GithubFactory.is_issue_comment(message_lower))
|
||||
self.assertTrue(GithubFactory.is_issue_comment(message_upper))
|
||||
self.assertTrue(GithubFactory.is_issue_comment(message_mixed))
|
||||
|
||||
|
||||
class TestGithubV1ConversationRouting(TestCase):
|
||||
"""Test V1 conversation routing logic in GitHub integration."""
|
||||
|
||||
def setUp(self):
|
||||
"""Set up test fixtures."""
|
||||
# Create a proper UserData instance instead of MagicMock
|
||||
user_data = UserData(
|
||||
user_id=123, username='testuser', keycloak_user_id='test-keycloak-id'
|
||||
)
|
||||
|
||||
# Create a mock raw_payload
|
||||
raw_payload = Message(
|
||||
source=SourceType.GITHUB,
|
||||
message={
|
||||
'payload': {
|
||||
'action': 'opened',
|
||||
'issue': {'number': 123},
|
||||
}
|
||||
},
|
||||
)
|
||||
|
||||
self.github_issue = GithubIssue(
|
||||
user_info=user_data,
|
||||
full_repo_name='test/repo',
|
||||
issue_number=123,
|
||||
installation_id=456,
|
||||
conversation_id='test-conversation-id',
|
||||
should_extract=True,
|
||||
send_summary_instruction=False,
|
||||
is_public_repo=True,
|
||||
raw_payload=raw_payload,
|
||||
uuid='test-uuid',
|
||||
title='Test Issue',
|
||||
description='Test issue description',
|
||||
previous_comments=[],
|
||||
v1=False,
|
||||
)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch('integrations.github.github_view.get_user_v1_enabled_setting')
|
||||
@patch.object(GithubIssue, '_create_v0_conversation')
|
||||
@patch.object(GithubIssue, '_create_v1_conversation')
|
||||
async def test_create_new_conversation_routes_to_v0_when_disabled(
|
||||
self, mock_create_v1, mock_create_v0, mock_get_v1_setting
|
||||
):
|
||||
"""Test that conversation creation routes to V0 when v1_enabled is False."""
|
||||
# Mock v1_enabled as False
|
||||
mock_get_v1_setting.return_value = False
|
||||
mock_create_v0.return_value = None
|
||||
mock_create_v1.return_value = None
|
||||
|
||||
# Mock parameters
|
||||
jinja_env = MagicMock()
|
||||
git_provider_tokens = MagicMock()
|
||||
conversation_metadata = MagicMock()
|
||||
|
||||
# Call the method
|
||||
await self.github_issue.create_new_conversation(
|
||||
jinja_env, git_provider_tokens, conversation_metadata
|
||||
)
|
||||
|
||||
# Verify V0 was called and V1 was not
|
||||
mock_create_v0.assert_called_once_with(
|
||||
jinja_env, git_provider_tokens, conversation_metadata
|
||||
)
|
||||
mock_create_v1.assert_not_called()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch('integrations.github.github_view.get_user_v1_enabled_setting')
|
||||
@patch.object(GithubIssue, '_create_v0_conversation')
|
||||
@patch.object(GithubIssue, '_create_v1_conversation')
|
||||
async def test_create_new_conversation_routes_to_v1_when_enabled(
|
||||
self, mock_create_v1, mock_create_v0, mock_get_v1_setting
|
||||
):
|
||||
"""Test that conversation creation routes to V1 when v1_enabled is True."""
|
||||
# Mock v1_enabled as True
|
||||
mock_get_v1_setting.return_value = True
|
||||
mock_create_v0.return_value = None
|
||||
mock_create_v1.return_value = None
|
||||
|
||||
# Mock parameters
|
||||
jinja_env = MagicMock()
|
||||
git_provider_tokens = MagicMock()
|
||||
conversation_metadata = MagicMock()
|
||||
|
||||
# Call the method
|
||||
await self.github_issue.create_new_conversation(
|
||||
jinja_env, git_provider_tokens, conversation_metadata
|
||||
)
|
||||
|
||||
# Verify V1 was called and V0 was not
|
||||
mock_create_v1.assert_called_once_with(
|
||||
jinja_env, git_provider_tokens, conversation_metadata
|
||||
)
|
||||
mock_create_v0.assert_not_called()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch('integrations.github.github_view.get_user_v1_enabled_setting')
|
||||
@patch.object(GithubIssue, '_create_v0_conversation')
|
||||
@patch.object(GithubIssue, '_create_v1_conversation')
|
||||
async def test_create_new_conversation_fallback_on_v1_setting_error(
|
||||
self, mock_create_v1, mock_create_v0, mock_get_v1_setting
|
||||
):
|
||||
"""Test that conversation creation falls back to V0 when _create_v1_conversation fails."""
|
||||
# Mock v1_enabled as True so V1 is attempted
|
||||
mock_get_v1_setting.return_value = True
|
||||
# Mock _create_v1_conversation to raise an exception
|
||||
mock_create_v1.side_effect = Exception('V1 conversation creation failed')
|
||||
mock_create_v0.return_value = None
|
||||
|
||||
# Mock parameters
|
||||
jinja_env = MagicMock()
|
||||
git_provider_tokens = MagicMock()
|
||||
conversation_metadata = MagicMock()
|
||||
|
||||
# Call the method
|
||||
await self.github_issue.create_new_conversation(
|
||||
jinja_env, git_provider_tokens, conversation_metadata
|
||||
)
|
||||
|
||||
# Verify V1 was attempted first, then V0 was called as fallback
|
||||
mock_create_v1.assert_called_once_with(
|
||||
jinja_env, git_provider_tokens, conversation_metadata
|
||||
)
|
||||
mock_create_v0.assert_called_once_with(
|
||||
jinja_env, git_provider_tokens, conversation_metadata
|
||||
)
|
||||
|
||||
@ -1,485 +0,0 @@
|
||||
import time
|
||||
from unittest.mock import AsyncMock, MagicMock, patch
|
||||
|
||||
import pytest
|
||||
from server.legacy_conversation_manager import (
|
||||
_LEGACY_ENTRY_TIMEOUT_SECONDS,
|
||||
LegacyCacheEntry,
|
||||
LegacyConversationManager,
|
||||
)
|
||||
|
||||
from openhands.core.config.openhands_config import OpenHandsConfig
|
||||
from openhands.server.config.server_config import ServerConfig
|
||||
from openhands.server.monitoring import MonitoringListener
|
||||
from openhands.storage.memory import InMemoryFileStore
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_sio():
|
||||
"""Create a mock SocketIO server."""
|
||||
return MagicMock()
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_config():
|
||||
"""Create a mock OpenHands config."""
|
||||
return MagicMock(spec=OpenHandsConfig)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_server_config():
|
||||
"""Create a mock server config."""
|
||||
return MagicMock(spec=ServerConfig)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_file_store():
|
||||
"""Create a mock file store."""
|
||||
return MagicMock(spec=InMemoryFileStore)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_monitoring_listener():
|
||||
"""Create a mock monitoring listener."""
|
||||
return MagicMock(spec=MonitoringListener)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_conversation_manager():
|
||||
"""Create a mock SaasNestedConversationManager."""
|
||||
mock_cm = MagicMock()
|
||||
mock_cm._get_runtime = AsyncMock()
|
||||
return mock_cm
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_legacy_conversation_manager():
|
||||
"""Create a mock ClusteredConversationManager."""
|
||||
return MagicMock()
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def legacy_manager(
|
||||
mock_sio,
|
||||
mock_config,
|
||||
mock_server_config,
|
||||
mock_file_store,
|
||||
mock_conversation_manager,
|
||||
mock_legacy_conversation_manager,
|
||||
):
|
||||
"""Create a LegacyConversationManager instance for testing."""
|
||||
return LegacyConversationManager(
|
||||
sio=mock_sio,
|
||||
config=mock_config,
|
||||
server_config=mock_server_config,
|
||||
file_store=mock_file_store,
|
||||
conversation_manager=mock_conversation_manager,
|
||||
legacy_conversation_manager=mock_legacy_conversation_manager,
|
||||
)
|
||||
|
||||
|
||||
class TestLegacyCacheEntry:
|
||||
"""Test the LegacyCacheEntry dataclass."""
|
||||
|
||||
def test_cache_entry_creation(self):
|
||||
"""Test creating a cache entry."""
|
||||
timestamp = time.time()
|
||||
entry = LegacyCacheEntry(is_legacy=True, timestamp=timestamp)
|
||||
|
||||
assert entry.is_legacy is True
|
||||
assert entry.timestamp == timestamp
|
||||
|
||||
def test_cache_entry_false(self):
|
||||
"""Test creating a cache entry with False value."""
|
||||
timestamp = time.time()
|
||||
entry = LegacyCacheEntry(is_legacy=False, timestamp=timestamp)
|
||||
|
||||
assert entry.is_legacy is False
|
||||
assert entry.timestamp == timestamp
|
||||
|
||||
|
||||
class TestLegacyConversationManagerCacheCleanup:
|
||||
"""Test cache cleanup functionality."""
|
||||
|
||||
def test_cleanup_expired_cache_entries_removes_expired(self, legacy_manager):
|
||||
"""Test that expired entries are removed from cache."""
|
||||
current_time = time.time()
|
||||
expired_time = current_time - _LEGACY_ENTRY_TIMEOUT_SECONDS - 1
|
||||
valid_time = current_time - 100 # Well within timeout
|
||||
|
||||
# Add both expired and valid entries
|
||||
legacy_manager._legacy_cache = {
|
||||
'expired_conversation': LegacyCacheEntry(True, expired_time),
|
||||
'valid_conversation': LegacyCacheEntry(False, valid_time),
|
||||
'another_expired': LegacyCacheEntry(True, expired_time - 100),
|
||||
}
|
||||
|
||||
legacy_manager._cleanup_expired_cache_entries()
|
||||
|
||||
# Only valid entry should remain
|
||||
assert len(legacy_manager._legacy_cache) == 1
|
||||
assert 'valid_conversation' in legacy_manager._legacy_cache
|
||||
assert 'expired_conversation' not in legacy_manager._legacy_cache
|
||||
assert 'another_expired' not in legacy_manager._legacy_cache
|
||||
|
||||
def test_cleanup_expired_cache_entries_keeps_valid(self, legacy_manager):
|
||||
"""Test that valid entries are kept during cleanup."""
|
||||
current_time = time.time()
|
||||
valid_time = current_time - 100 # Well within timeout
|
||||
|
||||
legacy_manager._legacy_cache = {
|
||||
'valid_conversation_1': LegacyCacheEntry(True, valid_time),
|
||||
'valid_conversation_2': LegacyCacheEntry(False, valid_time - 50),
|
||||
}
|
||||
|
||||
legacy_manager._cleanup_expired_cache_entries()
|
||||
|
||||
# Both entries should remain
|
||||
assert len(legacy_manager._legacy_cache) == 2
|
||||
assert 'valid_conversation_1' in legacy_manager._legacy_cache
|
||||
assert 'valid_conversation_2' in legacy_manager._legacy_cache
|
||||
|
||||
def test_cleanup_expired_cache_entries_empty_cache(self, legacy_manager):
|
||||
"""Test cleanup with empty cache."""
|
||||
legacy_manager._legacy_cache = {}
|
||||
|
||||
legacy_manager._cleanup_expired_cache_entries()
|
||||
|
||||
assert len(legacy_manager._legacy_cache) == 0
|
||||
|
||||
|
||||
class TestIsLegacyRuntime:
|
||||
"""Test the is_legacy_runtime method."""
|
||||
|
||||
def test_is_legacy_runtime_none(self, legacy_manager):
|
||||
"""Test with None runtime."""
|
||||
result = legacy_manager.is_legacy_runtime(None)
|
||||
assert result is False
|
||||
|
||||
def test_is_legacy_runtime_legacy_command(self, legacy_manager):
|
||||
"""Test with legacy runtime command."""
|
||||
runtime = {'command': 'some_old_legacy_command'}
|
||||
result = legacy_manager.is_legacy_runtime(runtime)
|
||||
assert result is True
|
||||
|
||||
def test_is_legacy_runtime_new_command(self, legacy_manager):
|
||||
"""Test with new runtime command containing openhands.server."""
|
||||
runtime = {'command': 'python -m openhands.server.listen'}
|
||||
result = legacy_manager.is_legacy_runtime(runtime)
|
||||
assert result is False
|
||||
|
||||
def test_is_legacy_runtime_partial_match(self, legacy_manager):
|
||||
"""Test with command that partially matches but is still legacy."""
|
||||
runtime = {'command': 'openhands.client.start'}
|
||||
result = legacy_manager.is_legacy_runtime(runtime)
|
||||
assert result is True
|
||||
|
||||
def test_is_legacy_runtime_empty_command(self, legacy_manager):
|
||||
"""Test with empty command."""
|
||||
runtime = {'command': ''}
|
||||
result = legacy_manager.is_legacy_runtime(runtime)
|
||||
assert result is True
|
||||
|
||||
def test_is_legacy_runtime_missing_command_key(self, legacy_manager):
|
||||
"""Test with runtime missing command key."""
|
||||
runtime = {'other_key': 'value'}
|
||||
# This should raise a KeyError
|
||||
with pytest.raises(KeyError):
|
||||
legacy_manager.is_legacy_runtime(runtime)
|
||||
|
||||
|
||||
class TestShouldStartInLegacyMode:
|
||||
"""Test the should_start_in_legacy_mode method."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_cache_hit_valid_entry_legacy(self, legacy_manager):
|
||||
"""Test cache hit with valid legacy entry."""
|
||||
conversation_id = 'test_conversation'
|
||||
current_time = time.time()
|
||||
|
||||
# Add valid cache entry
|
||||
legacy_manager._legacy_cache[conversation_id] = LegacyCacheEntry(
|
||||
True, current_time - 100
|
||||
)
|
||||
|
||||
result = await legacy_manager.should_start_in_legacy_mode(conversation_id)
|
||||
|
||||
assert result is True
|
||||
# Should not call _get_runtime since we hit cache
|
||||
legacy_manager.conversation_manager._get_runtime.assert_not_called()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_cache_hit_valid_entry_non_legacy(self, legacy_manager):
|
||||
"""Test cache hit with valid non-legacy entry."""
|
||||
conversation_id = 'test_conversation'
|
||||
current_time = time.time()
|
||||
|
||||
# Add valid cache entry
|
||||
legacy_manager._legacy_cache[conversation_id] = LegacyCacheEntry(
|
||||
False, current_time - 100
|
||||
)
|
||||
|
||||
result = await legacy_manager.should_start_in_legacy_mode(conversation_id)
|
||||
|
||||
assert result is False
|
||||
# Should not call _get_runtime since we hit cache
|
||||
legacy_manager.conversation_manager._get_runtime.assert_not_called()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_cache_miss_legacy_runtime(self, legacy_manager):
|
||||
"""Test cache miss with legacy runtime."""
|
||||
conversation_id = 'test_conversation'
|
||||
runtime = {'command': 'old_command'}
|
||||
|
||||
legacy_manager.conversation_manager._get_runtime.return_value = runtime
|
||||
|
||||
result = await legacy_manager.should_start_in_legacy_mode(conversation_id)
|
||||
|
||||
assert result is True
|
||||
# Should call _get_runtime
|
||||
legacy_manager.conversation_manager._get_runtime.assert_called_once_with(
|
||||
conversation_id
|
||||
)
|
||||
# Should cache the result
|
||||
assert conversation_id in legacy_manager._legacy_cache
|
||||
assert legacy_manager._legacy_cache[conversation_id].is_legacy is True
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_cache_miss_non_legacy_runtime(self, legacy_manager):
|
||||
"""Test cache miss with non-legacy runtime."""
|
||||
conversation_id = 'test_conversation'
|
||||
runtime = {'command': 'python -m openhands.server.listen'}
|
||||
|
||||
legacy_manager.conversation_manager._get_runtime.return_value = runtime
|
||||
|
||||
result = await legacy_manager.should_start_in_legacy_mode(conversation_id)
|
||||
|
||||
assert result is False
|
||||
# Should call _get_runtime
|
||||
legacy_manager.conversation_manager._get_runtime.assert_called_once_with(
|
||||
conversation_id
|
||||
)
|
||||
# Should cache the result
|
||||
assert conversation_id in legacy_manager._legacy_cache
|
||||
assert legacy_manager._legacy_cache[conversation_id].is_legacy is False
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_cache_expired_entry(self, legacy_manager):
|
||||
"""Test with expired cache entry."""
|
||||
conversation_id = 'test_conversation'
|
||||
expired_time = time.time() - _LEGACY_ENTRY_TIMEOUT_SECONDS - 1
|
||||
runtime = {'command': 'python -m openhands.server.listen'}
|
||||
|
||||
# Add expired cache entry
|
||||
legacy_manager._legacy_cache[conversation_id] = LegacyCacheEntry(
|
||||
True,
|
||||
expired_time, # This should be considered expired
|
||||
)
|
||||
|
||||
legacy_manager.conversation_manager._get_runtime.return_value = runtime
|
||||
|
||||
result = await legacy_manager.should_start_in_legacy_mode(conversation_id)
|
||||
|
||||
assert result is False # Runtime indicates non-legacy
|
||||
# Should call _get_runtime since cache is expired
|
||||
legacy_manager.conversation_manager._get_runtime.assert_called_once_with(
|
||||
conversation_id
|
||||
)
|
||||
# Should update cache with new result
|
||||
assert legacy_manager._legacy_cache[conversation_id].is_legacy is False
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_cache_exactly_at_timeout(self, legacy_manager):
|
||||
"""Test with cache entry exactly at timeout boundary."""
|
||||
conversation_id = 'test_conversation'
|
||||
timeout_time = time.time() - _LEGACY_ENTRY_TIMEOUT_SECONDS
|
||||
runtime = {'command': 'python -m openhands.server.listen'}
|
||||
|
||||
# Add cache entry exactly at timeout
|
||||
legacy_manager._legacy_cache[conversation_id] = LegacyCacheEntry(
|
||||
True, timeout_time
|
||||
)
|
||||
|
||||
legacy_manager.conversation_manager._get_runtime.return_value = runtime
|
||||
|
||||
result = await legacy_manager.should_start_in_legacy_mode(conversation_id)
|
||||
|
||||
# Should treat as expired and fetch from runtime
|
||||
assert result is False
|
||||
legacy_manager.conversation_manager._get_runtime.assert_called_once_with(
|
||||
conversation_id
|
||||
)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_runtime_returns_none(self, legacy_manager):
|
||||
"""Test when runtime returns None."""
|
||||
conversation_id = 'test_conversation'
|
||||
|
||||
legacy_manager.conversation_manager._get_runtime.return_value = None
|
||||
|
||||
result = await legacy_manager.should_start_in_legacy_mode(conversation_id)
|
||||
|
||||
assert result is False
|
||||
# Should cache the result
|
||||
assert conversation_id in legacy_manager._legacy_cache
|
||||
assert legacy_manager._legacy_cache[conversation_id].is_legacy is False
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_cleanup_called_on_each_invocation(self, legacy_manager):
|
||||
"""Test that cleanup is called on each invocation."""
|
||||
conversation_id = 'test_conversation'
|
||||
runtime = {'command': 'test'}
|
||||
|
||||
legacy_manager.conversation_manager._get_runtime.return_value = runtime
|
||||
|
||||
# Mock the cleanup method to verify it's called
|
||||
with patch.object(
|
||||
legacy_manager, '_cleanup_expired_cache_entries'
|
||||
) as mock_cleanup:
|
||||
await legacy_manager.should_start_in_legacy_mode(conversation_id)
|
||||
mock_cleanup.assert_called_once()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_multiple_conversations_cached_independently(self, legacy_manager):
|
||||
"""Test that multiple conversations are cached independently."""
|
||||
conv1 = 'conversation_1'
|
||||
conv2 = 'conversation_2'
|
||||
|
||||
runtime1 = {'command': 'old_command'} # Legacy
|
||||
runtime2 = {'command': 'python -m openhands.server.listen'} # Non-legacy
|
||||
|
||||
# Mock to return different runtimes based on conversation_id
|
||||
def mock_get_runtime(conversation_id):
|
||||
if conversation_id == conv1:
|
||||
return runtime1
|
||||
return runtime2
|
||||
|
||||
legacy_manager.conversation_manager._get_runtime.side_effect = mock_get_runtime
|
||||
|
||||
result1 = await legacy_manager.should_start_in_legacy_mode(conv1)
|
||||
result2 = await legacy_manager.should_start_in_legacy_mode(conv2)
|
||||
|
||||
assert result1 is True
|
||||
assert result2 is False
|
||||
|
||||
# Both should be cached
|
||||
assert conv1 in legacy_manager._legacy_cache
|
||||
assert conv2 in legacy_manager._legacy_cache
|
||||
assert legacy_manager._legacy_cache[conv1].is_legacy is True
|
||||
assert legacy_manager._legacy_cache[conv2].is_legacy is False
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_cache_timestamp_updated_on_refresh(self, legacy_manager):
|
||||
"""Test that cache timestamp is updated when entry is refreshed."""
|
||||
conversation_id = 'test_conversation'
|
||||
old_time = time.time() - _LEGACY_ENTRY_TIMEOUT_SECONDS - 1
|
||||
runtime = {'command': 'test'}
|
||||
|
||||
# Add expired entry
|
||||
legacy_manager._legacy_cache[conversation_id] = LegacyCacheEntry(True, old_time)
|
||||
legacy_manager.conversation_manager._get_runtime.return_value = runtime
|
||||
|
||||
# Record time before call
|
||||
before_call = time.time()
|
||||
await legacy_manager.should_start_in_legacy_mode(conversation_id)
|
||||
after_call = time.time()
|
||||
|
||||
# Timestamp should be updated
|
||||
cached_entry = legacy_manager._legacy_cache[conversation_id]
|
||||
assert cached_entry.timestamp >= before_call
|
||||
assert cached_entry.timestamp <= after_call
|
||||
|
||||
|
||||
class TestLegacyConversationManagerIntegration:
|
||||
"""Integration tests for LegacyConversationManager."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_instance_creates_proper_manager(
|
||||
self,
|
||||
mock_sio,
|
||||
mock_config,
|
||||
mock_file_store,
|
||||
mock_server_config,
|
||||
mock_monitoring_listener,
|
||||
):
|
||||
"""Test that get_instance creates a properly configured manager."""
|
||||
with patch(
|
||||
'server.legacy_conversation_manager.SaasNestedConversationManager'
|
||||
) as mock_saas, patch(
|
||||
'server.legacy_conversation_manager.ClusteredConversationManager'
|
||||
) as mock_clustered:
|
||||
mock_saas.get_instance.return_value = MagicMock()
|
||||
mock_clustered.get_instance.return_value = MagicMock()
|
||||
|
||||
manager = LegacyConversationManager.get_instance(
|
||||
mock_sio,
|
||||
mock_config,
|
||||
mock_file_store,
|
||||
mock_server_config,
|
||||
mock_monitoring_listener,
|
||||
)
|
||||
|
||||
assert isinstance(manager, LegacyConversationManager)
|
||||
assert manager.sio == mock_sio
|
||||
assert manager.config == mock_config
|
||||
assert manager.file_store == mock_file_store
|
||||
assert manager.server_config == mock_server_config
|
||||
|
||||
# Verify that both nested managers are created
|
||||
mock_saas.get_instance.assert_called_once()
|
||||
mock_clustered.get_instance.assert_called_once()
|
||||
|
||||
def test_legacy_cache_initialized_empty(self, legacy_manager):
|
||||
"""Test that legacy cache is initialized as empty dict."""
|
||||
assert isinstance(legacy_manager._legacy_cache, dict)
|
||||
assert len(legacy_manager._legacy_cache) == 0
|
||||
|
||||
|
||||
class TestEdgeCases:
|
||||
"""Test edge cases and error scenarios."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_runtime_raises_exception(self, legacy_manager):
|
||||
"""Test behavior when _get_runtime raises an exception."""
|
||||
conversation_id = 'test_conversation'
|
||||
|
||||
legacy_manager.conversation_manager._get_runtime.side_effect = Exception(
|
||||
'Runtime error'
|
||||
)
|
||||
|
||||
# Should propagate the exception
|
||||
with pytest.raises(Exception, match='Runtime error'):
|
||||
await legacy_manager.should_start_in_legacy_mode(conversation_id)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_very_large_cache(self, legacy_manager):
|
||||
"""Test behavior with a large number of cache entries."""
|
||||
current_time = time.time()
|
||||
|
||||
# Add many cache entries
|
||||
for i in range(1000):
|
||||
legacy_manager._legacy_cache[f'conversation_{i}'] = LegacyCacheEntry(
|
||||
i % 2 == 0, current_time - i
|
||||
)
|
||||
|
||||
# This should work without issues
|
||||
await legacy_manager.should_start_in_legacy_mode('new_conversation')
|
||||
|
||||
# Should have added one more entry
|
||||
assert len(legacy_manager._legacy_cache) == 1001
|
||||
|
||||
def test_cleanup_with_concurrent_modifications(self, legacy_manager):
|
||||
"""Test cleanup behavior when cache is modified during cleanup."""
|
||||
current_time = time.time()
|
||||
expired_time = current_time - _LEGACY_ENTRY_TIMEOUT_SECONDS - 1
|
||||
|
||||
# Add expired entries
|
||||
legacy_manager._legacy_cache = {
|
||||
f'conversation_{i}': LegacyCacheEntry(True, expired_time) for i in range(10)
|
||||
}
|
||||
|
||||
# This should work without raising exceptions
|
||||
legacy_manager._cleanup_expired_cache_entries()
|
||||
|
||||
# All entries should be removed
|
||||
assert len(legacy_manager._legacy_cache) == 0
|
||||
@ -535,3 +535,115 @@ def test_get_api_key_from_header_with_invalid_authorization_format():
|
||||
|
||||
# Assert that None was returned
|
||||
assert api_key is None
|
||||
|
||||
|
||||
def test_get_api_key_from_header_with_x_access_token():
|
||||
"""Test that get_api_key_from_header extracts API key from X-Access-Token header."""
|
||||
# Create a mock request with X-Access-Token header
|
||||
mock_request = MagicMock(spec=Request)
|
||||
mock_request.headers = {'X-Access-Token': 'access_token_key'}
|
||||
|
||||
# Call the function
|
||||
api_key = get_api_key_from_header(mock_request)
|
||||
|
||||
# Assert that the API key was correctly extracted
|
||||
assert api_key == 'access_token_key'
|
||||
|
||||
|
||||
def test_get_api_key_from_header_priority_authorization_over_x_access_token():
|
||||
"""Test that Authorization header takes priority over X-Access-Token header."""
|
||||
# Create a mock request with both headers
|
||||
mock_request = MagicMock(spec=Request)
|
||||
mock_request.headers = {
|
||||
'Authorization': 'Bearer auth_api_key',
|
||||
'X-Access-Token': 'access_token_key',
|
||||
}
|
||||
|
||||
# Call the function
|
||||
api_key = get_api_key_from_header(mock_request)
|
||||
|
||||
# Assert that the API key from Authorization header was used
|
||||
assert api_key == 'auth_api_key'
|
||||
|
||||
|
||||
def test_get_api_key_from_header_priority_x_session_over_x_access_token():
|
||||
"""Test that X-Session-API-Key header takes priority over X-Access-Token header."""
|
||||
# Create a mock request with both headers
|
||||
mock_request = MagicMock(spec=Request)
|
||||
mock_request.headers = {
|
||||
'X-Session-API-Key': 'session_api_key',
|
||||
'X-Access-Token': 'access_token_key',
|
||||
}
|
||||
|
||||
# Call the function
|
||||
api_key = get_api_key_from_header(mock_request)
|
||||
|
||||
# Assert that the API key from X-Session-API-Key header was used
|
||||
assert api_key == 'session_api_key'
|
||||
|
||||
|
||||
def test_get_api_key_from_header_all_three_headers():
|
||||
"""Test header priority when all three headers are present."""
|
||||
# Create a mock request with all three headers
|
||||
mock_request = MagicMock(spec=Request)
|
||||
mock_request.headers = {
|
||||
'Authorization': 'Bearer auth_api_key',
|
||||
'X-Session-API-Key': 'session_api_key',
|
||||
'X-Access-Token': 'access_token_key',
|
||||
}
|
||||
|
||||
# Call the function
|
||||
api_key = get_api_key_from_header(mock_request)
|
||||
|
||||
# Assert that the API key from Authorization header was used (highest priority)
|
||||
assert api_key == 'auth_api_key'
|
||||
|
||||
|
||||
def test_get_api_key_from_header_invalid_authorization_fallback_to_x_access_token():
|
||||
"""Test that invalid Authorization header falls back to X-Access-Token."""
|
||||
# Create a mock request with invalid Authorization header and X-Access-Token
|
||||
mock_request = MagicMock(spec=Request)
|
||||
mock_request.headers = {
|
||||
'Authorization': 'InvalidFormat api_key',
|
||||
'X-Access-Token': 'access_token_key',
|
||||
}
|
||||
|
||||
# Call the function
|
||||
api_key = get_api_key_from_header(mock_request)
|
||||
|
||||
# Assert that the API key from X-Access-Token header was used
|
||||
assert api_key == 'access_token_key'
|
||||
|
||||
|
||||
def test_get_api_key_from_header_empty_headers():
|
||||
"""Test that empty header values are handled correctly."""
|
||||
# Create a mock request with empty header values
|
||||
mock_request = MagicMock(spec=Request)
|
||||
mock_request.headers = {
|
||||
'Authorization': '',
|
||||
'X-Session-API-Key': '',
|
||||
'X-Access-Token': 'access_token_key',
|
||||
}
|
||||
|
||||
# Call the function
|
||||
api_key = get_api_key_from_header(mock_request)
|
||||
|
||||
# Assert that the API key from X-Access-Token header was used
|
||||
assert api_key == 'access_token_key'
|
||||
|
||||
|
||||
def test_get_api_key_from_header_bearer_with_empty_token():
|
||||
"""Test that Bearer header with empty token falls back to other headers."""
|
||||
# Create a mock request with Bearer header with empty token
|
||||
mock_request = MagicMock(spec=Request)
|
||||
mock_request.headers = {
|
||||
'Authorization': 'Bearer ',
|
||||
'X-Access-Token': 'access_token_key',
|
||||
}
|
||||
|
||||
# Call the function
|
||||
api_key = get_api_key_from_header(mock_request)
|
||||
|
||||
# Assert that empty string from Bearer is returned (current behavior)
|
||||
# This tests the current implementation behavior
|
||||
assert api_key == ''
|
||||
|
||||
@ -1,5 +1,10 @@
|
||||
# Evaluation
|
||||
|
||||
> [!WARNING]
|
||||
> **This directory is deprecated.** Our new benchmarks are located at [OpenHands/benchmarks](https://github.com/OpenHands/benchmarks).
|
||||
>
|
||||
> If you have already implemented a benchmark in this directory and would like to contribute it, we are happy to have the contribution. However, if you are starting anew, please use the new location.
|
||||
|
||||
This folder contains code and resources to run experiments and evaluations.
|
||||
|
||||
## For Benchmark Users
|
||||
|
||||
65
evaluation/benchmarks/swefficiency/README.md
Normal file
65
evaluation/benchmarks/swefficiency/README.md
Normal file
@ -0,0 +1,65 @@
|
||||
# SWE-fficiency Evaluation
|
||||
|
||||
This folder contains the OpenHands inference generation of the [SWE-fficiency benchmark](https://swefficiency.com/) ([paper](https://arxiv.org/pdf/2507.12415v1)).
|
||||
|
||||
The evaluation consists of three steps:
|
||||
|
||||
1. Environment setup: [install python environment](../../README.md#development-environment) and [configure LLM config](../../README.md#configure-openhands-and-your-llm).
|
||||
2. [Run inference](#running-inference-locally-with-docker): Generate a edit patch for each Github issue
|
||||
3. [Evaluate patches](#evaluate-generated-patches)
|
||||
|
||||
## Setup Environment and LLM Configuration
|
||||
|
||||
Please follow instruction [here](../../README.md#setup) to setup your local development environment and LLM.
|
||||
|
||||
## Running inference Locally with Docker
|
||||
|
||||
Make sure your Docker daemon is running, and you have ample disk space (at least 200-500GB, depends on the SWE-PErf set you are running on) for the instance-level docker image.
|
||||
|
||||
When the `run_infer.sh` script is started, it will automatically pull the relevant SWE-Perf images.
|
||||
For example, for instance ID `scikit-learn_scikit-learn-11674`, it will try to pull our pre-build docker image `betty1202/sweb.eval.x86_64.scikit-learn_s_scikit-learn-11674` from DockerHub.
|
||||
This image will be used create an OpenHands runtime image where the agent will operate on.
|
||||
|
||||
```bash
|
||||
./evaluation/benchmarks/swefficiency/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split] [n_runs] [mode]
|
||||
|
||||
# Example
|
||||
./evaluation/benchmarks/swefficiency/scripts/run_infer.sh llm.eval_gpt4_1106_preview HEAD CodeActAgent 500 100 1 swefficiency/swefficiency test
|
||||
```
|
||||
|
||||
where `model_config` is mandatory, and the rest are optional.
|
||||
|
||||
- `model_config`, e.g. `eval_gpt4_1106_preview`, is the config group name for your
|
||||
LLM settings, as defined in your `config.toml`.
|
||||
- `git-version`, e.g. `HEAD`, is the git commit hash of the OpenHands version you would
|
||||
like to evaluate. It could also be a release tag like `0.6.2`.
|
||||
- `agent`, e.g. `CodeActAgent`, is the name of the agent for benchmarks, defaulting
|
||||
to `CodeActAgent`.
|
||||
- `eval_limit`, e.g. `10`, limits the evaluation to the first `eval_limit` instances. By
|
||||
default, the script evaluates the entire SWE-Perf test set (140 issues). Note:
|
||||
in order to use `eval_limit`, you must also set `agent`.
|
||||
- `max_iter`, e.g. `20`, is the maximum number of iterations for the agent to run. By
|
||||
default, it is set to 100.
|
||||
- `num_workers`, e.g. `3`, is the number of parallel workers to run the evaluation. By
|
||||
default, it is set to 1.
|
||||
- `dataset`, a huggingface dataset name. e.g. `SWE-Perf/SWE-Perf`, specifies which dataset to evaluate on.
|
||||
- `dataset_split`, split for the huggingface dataset. e.g., `test`, `dev`. Default to `test`.
|
||||
|
||||
- `n_runs`, e.g. `3`, is the number of times to run the evaluation. Default is 1.
|
||||
- `mode`, e.g. `swt`, `swt-ci`, or `swe`, specifies the evaluation mode. Default is `swe`.
|
||||
|
||||
> [!CAUTION]
|
||||
> Setting `num_workers` larger than 1 is not officially tested, YMMV.
|
||||
|
||||
|
||||
Let's say you'd like to run 10 instances using `llm.eval_gpt4_1106_preview` and CodeActAgent,
|
||||
|
||||
then your command would be:
|
||||
|
||||
```bash
|
||||
./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.eval_gpt4_1106_preview HEAD CodeActAgent 10
|
||||
```
|
||||
|
||||
### 2. Run the SWE-fficiency benchmark official evaluation
|
||||
|
||||
Once the output is converted, use the [official SWE-fficiency benchmark evaluation](https://github.com/swefficiency/swefficiency) to evaluate it.
|
||||
52
evaluation/benchmarks/swefficiency/binary_patch_utils.py
Normal file
52
evaluation/benchmarks/swefficiency/binary_patch_utils.py
Normal file
@ -0,0 +1,52 @@
|
||||
"""
|
||||
Utilities for handling binary files and patch generation in SWE-bench evaluation.
|
||||
"""
|
||||
|
||||
|
||||
def remove_binary_diffs(patch_text):
|
||||
"""
|
||||
Remove binary file diffs from a git patch.
|
||||
|
||||
Args:
|
||||
patch_text (str): The git patch text
|
||||
|
||||
Returns:
|
||||
str: The cleaned patch text with binary diffs removed
|
||||
"""
|
||||
lines = patch_text.splitlines()
|
||||
cleaned_lines = []
|
||||
block = []
|
||||
is_binary_block = False
|
||||
|
||||
for line in lines:
|
||||
if line.startswith('diff --git '):
|
||||
if block and not is_binary_block:
|
||||
cleaned_lines.extend(block)
|
||||
block = [line]
|
||||
is_binary_block = False
|
||||
elif 'Binary files' in line:
|
||||
is_binary_block = True
|
||||
block.append(line)
|
||||
else:
|
||||
block.append(line)
|
||||
|
||||
if block and not is_binary_block:
|
||||
cleaned_lines.extend(block)
|
||||
return '\n'.join(cleaned_lines)
|
||||
|
||||
|
||||
def remove_binary_files_from_git():
|
||||
"""
|
||||
Generate a bash command to remove binary files from git staging.
|
||||
|
||||
Returns:
|
||||
str: A bash command that removes binary files from git staging
|
||||
"""
|
||||
return """
|
||||
for file in $(git status --porcelain | grep -E "^(M| M|\\?\\?|A| A)" | cut -c4-); do
|
||||
if [ -f "$file" ] && (file "$file" | grep -q "executable" || git check-attr binary "$file" | grep -q "binary: set"); then
|
||||
git rm -f "$file" 2>/dev/null || rm -f "$file"
|
||||
echo "Removed: $file"
|
||||
fi
|
||||
done
|
||||
""".strip()
|
||||
960
evaluation/benchmarks/swefficiency/run_infer.py
Normal file
960
evaluation/benchmarks/swefficiency/run_infer.py
Normal file
@ -0,0 +1,960 @@
|
||||
import asyncio
|
||||
import copy
|
||||
import functools
|
||||
import json
|
||||
import multiprocessing
|
||||
import os
|
||||
import tempfile
|
||||
from typing import Any, Literal
|
||||
|
||||
import pandas as pd
|
||||
import toml
|
||||
from datasets import load_dataset
|
||||
|
||||
import openhands.agenthub
|
||||
from evaluation.benchmarks.swe_bench.binary_patch_utils import (
|
||||
remove_binary_diffs,
|
||||
remove_binary_files_from_git,
|
||||
)
|
||||
from evaluation.utils.shared import (
|
||||
EvalException,
|
||||
EvalMetadata,
|
||||
EvalOutput,
|
||||
assert_and_raise,
|
||||
codeact_user_response,
|
||||
get_default_sandbox_config_for_eval,
|
||||
get_metrics,
|
||||
is_fatal_evaluation_error,
|
||||
make_metadata,
|
||||
prepare_dataset,
|
||||
reset_logger_for_multiprocessing,
|
||||
run_evaluation,
|
||||
update_llm_config_for_completions_logging,
|
||||
)
|
||||
from openhands.controller.state.state import State
|
||||
from openhands.core.config import (
|
||||
AgentConfig,
|
||||
OpenHandsConfig,
|
||||
get_evaluation_parser,
|
||||
get_llm_config_arg,
|
||||
)
|
||||
from openhands.core.config.condenser_config import NoOpCondenserConfig
|
||||
from openhands.core.config.utils import get_condenser_config_arg
|
||||
from openhands.core.logger import openhands_logger as logger
|
||||
from openhands.core.main import create_runtime, run_controller
|
||||
from openhands.critic import AgentFinishedCritic
|
||||
from openhands.events.action import CmdRunAction, FileReadAction, MessageAction
|
||||
from openhands.events.observation import (
|
||||
CmdOutputObservation,
|
||||
ErrorObservation,
|
||||
FileReadObservation,
|
||||
)
|
||||
from openhands.events.serialization.event import event_from_dict, event_to_dict
|
||||
from openhands.runtime.base import Runtime
|
||||
from openhands.utils.async_utils import call_async_from_sync
|
||||
from openhands.utils.shutdown_listener import sleep_if_should_continue
|
||||
|
||||
USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
|
||||
RUN_WITH_BROWSING = os.environ.get('RUN_WITH_BROWSING', 'false').lower() == 'true'
|
||||
BenchMode = Literal['swe', 'swt', 'swt-ci']
|
||||
|
||||
|
||||
AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
|
||||
'CodeActAgent': codeact_user_response,
|
||||
}
|
||||
|
||||
|
||||
def _get_swebench_workspace_dir_name(instance: pd.Series) -> str:
|
||||
return f'{instance.repo}__{instance.version}'.replace('/', '__')
|
||||
|
||||
|
||||
def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageAction:
|
||||
workspace_dir_name = _get_swebench_workspace_dir_name(instance)
|
||||
|
||||
# TODO: Change to testbed?
|
||||
instruction = f"""
|
||||
<uploaded_files>
|
||||
/workspace/{workspace_dir_name}
|
||||
</uploaded_files>
|
||||
|
||||
I’ve uploaded a python code repository in the directory workspace_dir_name. Consider the following performance workload and `workload()` function showing an specific usage of the repository:
|
||||
<performance_workload>
|
||||
{instance.workload}
|
||||
</performance_workload>
|
||||
|
||||
Can you help me implement the necessary changes to the repository so that the runtime of the `workload()` function is faster? Basic guidelines:
|
||||
1. Your task is to make changes to non-test files in the /workspace directory to improve the performance of the code running in `workload()`. Please do not directly change the implementation of the `workload()` function to optimize things: I want you to focus on making the workload AS IS run faster by only editing the repository containing code that the `workload()` function calls.
|
||||
2. Make changes while ensuring the repository is functionally equivalent to the original: your changes should not introduce new bugs or cause already-passing tests to begin failing after your changes. However, you do not need to worry about tests that already fail without any changes made. For relevant test files you find in the repository, you can run them via the bash command `{instance.test_cmd} <test_file>` to check for correctness. Note that running all the tests may take a long time, so you need to determine which tests are relevant to your changes.
|
||||
3. Make sure the `workload()` function improves in performance after you make changes to the repository. The workload can potentially take some time to run, so please allow it to finish and be generous with setting your timeout parameter (a timeout value of 3600 or larger here is encouraged): for faster iteration, you should adjust the workload script to use fewer iterations. Before you complete your task, please make sure to check that the **original performance workload** and `workload()` function runs successfully and the performance is improved.
|
||||
4. You may need to reinstall/rebuild the repo for your changes to take effect before testing if you made non-Python changes. Reinstalling may take a long time to run (a timeout value of 3600 or larger here is encouraged), so please be patient with running it and allow it to complete if possible. You can reinstall the repository by running the bash command `{instance.rebuild_cmd}` in the workspace directory.
|
||||
5. All the dependencies required to run the `workload()` function are already installed in the environment. You should not install or upgrade any dependencies.
|
||||
|
||||
Follow these steps to improve performance:
|
||||
1. As a first step, explore the repository structure.
|
||||
2. Create a Python script to reproduce the performance workload, execute it with python <workload_file>, and examine the printed output metrics.
|
||||
3. Edit the source code of the repository to improve performance. Please do not change the contents of the `workload()` function itself, but focus on optimizing the code in the repository that the original `workload()` function uses.
|
||||
4. If non-Python changes were made, rebuild the repo to make sure the changes take effect.
|
||||
5. Rerun your script to confirm that performance has improved.
|
||||
6. If necessary, identify any relevant test files in the repository related to your changes and verify that test statuses did not change after your modifications.
|
||||
7. After each attempted change, please reflect on the changes attempted and the performance impact observed. If the performance did not improve, consider alternative approaches or optimizations.
|
||||
8. Once you are satisfied, please use the finish command to complete your task.
|
||||
|
||||
Please remember that you should not change the implementation of the `workload()` function. The performance improvement should solely come from editing the source files in the code repository.
|
||||
"""
|
||||
|
||||
if RUN_WITH_BROWSING:
|
||||
instruction += (
|
||||
'<IMPORTANT!>\nYou SHOULD NEVER attempt to browse the web. </IMPORTANT!>\n'
|
||||
)
|
||||
|
||||
return MessageAction(content=instruction)
|
||||
|
||||
|
||||
def get_instance_docker_image(
|
||||
instance_id: str,
|
||||
) -> str:
|
||||
return f'ghcr.io/swefficiency/swefficiency-images:{instance_id}'
|
||||
|
||||
|
||||
def get_config(
|
||||
instance: pd.Series,
|
||||
metadata: EvalMetadata,
|
||||
cpu_group: list[int] | None = None,
|
||||
) -> OpenHandsConfig:
|
||||
# We use a different instance image for the each instance of swe-bench eval
|
||||
base_container_image = get_instance_docker_image(
|
||||
instance['instance_id'],
|
||||
)
|
||||
logger.info(
|
||||
f'Using instance container image: {base_container_image}. '
|
||||
f'Please make sure this image exists. '
|
||||
f'Submit an issue on https://github.com/All-Hands-AI/OpenHands if you run into any issues.'
|
||||
)
|
||||
|
||||
sandbox_config = get_default_sandbox_config_for_eval()
|
||||
sandbox_config.base_container_image = base_container_image
|
||||
sandbox_config.enable_auto_lint = True
|
||||
sandbox_config.use_host_network = False
|
||||
sandbox_config.timeout = 3600
|
||||
|
||||
# Control container cleanup behavior via environment variable
|
||||
# Default to False for multiprocessing stability to prevent cascade failures
|
||||
sandbox_config.rm_all_containers = True
|
||||
|
||||
sandbox_config.platform = 'linux/amd64'
|
||||
sandbox_config.remote_runtime_resource_factor = 4.0
|
||||
sandbox_config.runtime_startup_env_vars.update(
|
||||
{
|
||||
'NO_CHANGE_TIMEOUT_SECONDS': '900', # 15 minutes
|
||||
}
|
||||
)
|
||||
|
||||
if cpu_group is not None:
|
||||
print(f'Configuring Docker runtime with CPU group: {cpu_group}')
|
||||
sandbox_config.docker_runtime_kwargs = {
|
||||
# HACK: Use the cpu_group if provided, otherwise use all available CPUs
|
||||
'cpuset_cpus': ','.join(map(str, cpu_group)),
|
||||
'nano_cpus': int(1e9 * len(cpu_group)), # optional: hard cap to vCPU count
|
||||
'mem_limit': '16g',
|
||||
}
|
||||
|
||||
# Note: We keep rm_all_containers = False for worker process safety
|
||||
|
||||
config = OpenHandsConfig(
|
||||
default_agent=metadata.agent_class,
|
||||
run_as_openhands=False,
|
||||
max_iterations=metadata.max_iterations,
|
||||
runtime=os.environ.get('RUNTIME', 'docker'),
|
||||
sandbox=sandbox_config,
|
||||
# do not mount workspace
|
||||
workspace_base=None,
|
||||
workspace_mount_path=None,
|
||||
)
|
||||
config.set_llm_config(
|
||||
update_llm_config_for_completions_logging(
|
||||
metadata.llm_config, metadata.eval_output_dir, instance['instance_id']
|
||||
)
|
||||
)
|
||||
agent_config = AgentConfig(
|
||||
enable_jupyter=False,
|
||||
enable_browsing=RUN_WITH_BROWSING,
|
||||
enable_llm_editor=False,
|
||||
enable_mcp=False,
|
||||
condenser=metadata.condenser_config,
|
||||
enable_prompt_extensions=False,
|
||||
)
|
||||
config.set_agent_config(agent_config)
|
||||
return config
|
||||
|
||||
|
||||
def initialize_runtime(
|
||||
runtime: Runtime,
|
||||
instance: pd.Series, # this argument is not required
|
||||
metadata: EvalMetadata,
|
||||
):
|
||||
"""Initialize the runtime for the agent.
|
||||
|
||||
This function is called before the runtime is used to run the agent.
|
||||
"""
|
||||
logger.info('-' * 30)
|
||||
logger.info('BEGIN Runtime Initialization Fn')
|
||||
logger.info('-' * 30)
|
||||
workspace_dir_name = _get_swebench_workspace_dir_name(instance)
|
||||
obs: CmdOutputObservation
|
||||
|
||||
# Set instance id and git configuration
|
||||
action = CmdRunAction(
|
||||
command=f"""echo 'export SWE_INSTANCE_ID={instance['instance_id']}' >> ~/.bashrc && echo 'export PIP_CACHE_DIR=~/.cache/pip' >> ~/.bashrc && echo "alias git='git --no-pager'" >> ~/.bashrc && git config --global core.pager "" && git config --global diff.binary false"""
|
||||
)
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
assert_and_raise(
|
||||
obs.exit_code == 0,
|
||||
f'Failed to export SWE_INSTANCE_ID and configure git: {str(obs)}',
|
||||
)
|
||||
|
||||
action = CmdRunAction(command="""export USER=$(whoami); echo USER=${USER} """)
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
assert_and_raise(obs.exit_code == 0, f'Failed to export USER: {str(obs)}')
|
||||
|
||||
# inject the init script
|
||||
script_dir = os.path.dirname(__file__)
|
||||
|
||||
# inject the instance info
|
||||
action = CmdRunAction(command='mkdir -p /swe_util/eval_data/instances')
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
assert_and_raise(
|
||||
obs.exit_code == 0,
|
||||
f'Failed to create /swe_util/eval_data/instances: {str(obs)}',
|
||||
)
|
||||
|
||||
swe_instance_json_name = 'swe-bench-instance.json'
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
# Construct the full path for the desired file name within the temporary directory
|
||||
temp_file_path = os.path.join(temp_dir, swe_instance_json_name)
|
||||
# Write to the file with the desired name within the temporary directory
|
||||
with open(temp_file_path, 'w') as f:
|
||||
if not isinstance(instance, dict):
|
||||
json.dump([instance.to_dict()], f)
|
||||
else:
|
||||
json.dump([instance], f)
|
||||
|
||||
# Copy the file to the desired location
|
||||
runtime.copy_to(temp_file_path, '/swe_util/eval_data/instances/')
|
||||
|
||||
# inject the instance swe entry
|
||||
runtime.copy_to(
|
||||
str(os.path.join(script_dir, 'scripts/setup/instance_swe_entry.sh')),
|
||||
'/swe_util/',
|
||||
)
|
||||
|
||||
action = CmdRunAction(command='cat ~/.bashrc')
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
assert_and_raise(obs.exit_code == 0, f'Failed to cat ~/.bashrc: {str(obs)}')
|
||||
|
||||
action = CmdRunAction(command='source ~/.bashrc')
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
if isinstance(obs, ErrorObservation):
|
||||
logger.error(f'Failed to source ~/.bashrc: {str(obs)}')
|
||||
assert_and_raise(obs.exit_code == 0, f'Failed to source ~/.bashrc: {str(obs)}')
|
||||
|
||||
action = CmdRunAction(command='source /swe_util/instance_swe_entry.sh')
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
assert_and_raise(
|
||||
obs.exit_code == 0,
|
||||
f'Failed to source /swe_util/instance_swe_entry.sh: {str(obs)}',
|
||||
)
|
||||
|
||||
action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
assert_and_raise(
|
||||
obs.exit_code == 0,
|
||||
f'Failed to cd to /workspace/{workspace_dir_name}: {str(obs)}',
|
||||
)
|
||||
|
||||
action = CmdRunAction(command='git reset --hard')
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
assert_and_raise(obs.exit_code == 0, f'Failed to git reset --hard: {str(obs)}')
|
||||
|
||||
action = CmdRunAction(
|
||||
command='for remote_name in $(git remote); do git remote remove "${remote_name}"; done'
|
||||
)
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
assert_and_raise(obs.exit_code == 0, f'Failed to remove git remotes: {str(obs)}')
|
||||
|
||||
action = CmdRunAction(command='which python')
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
assert_and_raise(
|
||||
obs.exit_code == 0 and 'testbed' in obs.content,
|
||||
f'Expected to find python interpreter from testbed, but got: {str(obs)}',
|
||||
)
|
||||
|
||||
logger.info('-' * 30)
|
||||
logger.info('END Runtime Initialization Fn')
|
||||
logger.info('-' * 30)
|
||||
|
||||
|
||||
def complete_runtime(
|
||||
runtime: Runtime,
|
||||
instance: pd.Series, # this argument is not required, but it is used to get the workspace_dir_name
|
||||
) -> dict[str, Any]:
|
||||
"""Complete the runtime for the agent.
|
||||
|
||||
This function is called before the runtime is used to run the agent.
|
||||
If you need to do something in the sandbox to get the correctness metric after
|
||||
the agent has run, modify this function.
|
||||
"""
|
||||
logger.info('-' * 30)
|
||||
logger.info('BEGIN Runtime Completion Fn')
|
||||
logger.info('-' * 30)
|
||||
obs: CmdOutputObservation
|
||||
workspace_dir_name = _get_swebench_workspace_dir_name(instance)
|
||||
|
||||
action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
|
||||
if obs.exit_code == -1:
|
||||
# The previous command is still running
|
||||
# We need to kill previous command
|
||||
logger.info('The previous command is still running, trying to kill it...')
|
||||
action = CmdRunAction(command='C-c')
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
|
||||
# Then run the command again
|
||||
action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
|
||||
if obs.exit_code == -1:
|
||||
# The previous command is still running
|
||||
# We need to kill previous command
|
||||
logger.info('The previous command is still running, trying to ctrl+z it...')
|
||||
action = CmdRunAction(command='C-z')
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
|
||||
# Then run the command again
|
||||
action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
|
||||
assert_and_raise(
|
||||
isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
|
||||
f'Failed to cd to /workspace/{workspace_dir_name}: {str(obs)}',
|
||||
)
|
||||
|
||||
action = CmdRunAction(command='git config --global core.pager ""')
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
assert_and_raise(
|
||||
isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
|
||||
f'Failed to git config --global core.pager "": {str(obs)}',
|
||||
)
|
||||
|
||||
# First check for any git repositories in subdirectories
|
||||
action = CmdRunAction(command='find . -type d -name .git -not -path "./.git"')
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
assert_and_raise(
|
||||
isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
|
||||
f'Failed to find git repositories: {str(obs)}',
|
||||
)
|
||||
|
||||
git_dirs = [p for p in obs.content.strip().split('\n') if p]
|
||||
if git_dirs:
|
||||
# Remove all .git directories in subdirectories
|
||||
for git_dir in git_dirs:
|
||||
action = CmdRunAction(command=f'rm -rf "{git_dir}"')
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
assert_and_raise(
|
||||
isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
|
||||
f'Failed to remove git directory {git_dir}: {str(obs)}',
|
||||
)
|
||||
|
||||
# add all files
|
||||
action = CmdRunAction(command='git add -A')
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
assert_and_raise(
|
||||
isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
|
||||
f'Failed to git add -A: {str(obs)}',
|
||||
)
|
||||
|
||||
# Remove binary files from git staging
|
||||
action = CmdRunAction(command=remove_binary_files_from_git())
|
||||
action.set_hard_timeout(600)
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
assert_and_raise(
|
||||
isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
|
||||
f'Failed to remove binary files: {str(obs)}',
|
||||
)
|
||||
|
||||
n_retries = 0
|
||||
git_patch = None
|
||||
while n_retries < 5:
|
||||
action = CmdRunAction(
|
||||
command=f'git diff --no-color --cached {instance["base_commit"]} > patch.diff'
|
||||
)
|
||||
action.set_hard_timeout(max(300 + 100 * n_retries, 600))
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
n_retries += 1
|
||||
if isinstance(obs, CmdOutputObservation):
|
||||
if obs.exit_code == 0:
|
||||
# Read the patch file
|
||||
action = FileReadAction(path='patch.diff')
|
||||
action.set_hard_timeout(max(300 + 100 * n_retries, 600))
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
if isinstance(obs, FileReadObservation):
|
||||
git_patch = obs.content
|
||||
break
|
||||
elif isinstance(obs, ErrorObservation):
|
||||
# Fall back to cat "patch.diff" to get the patch
|
||||
assert 'File could not be decoded as utf-8' in obs.content
|
||||
action = CmdRunAction(command='cat patch.diff')
|
||||
action.set_hard_timeout(max(300 + 100 * n_retries, 600))
|
||||
logger.info(action, extra={'msg_type': 'ACTION'})
|
||||
obs = runtime.run_action(action)
|
||||
assert isinstance(obs, CmdOutputObservation) and obs.exit_code == 0
|
||||
logger.info(obs, extra={'msg_type': 'OBSERVATION'})
|
||||
git_patch = obs.content
|
||||
break
|
||||
else:
|
||||
assert_and_raise(False, f'Unexpected observation type: {str(obs)}')
|
||||
else:
|
||||
logger.info('Failed to get git diff, retrying...')
|
||||
sleep_if_should_continue(10)
|
||||
elif isinstance(obs, ErrorObservation):
|
||||
logger.error(f'Error occurred: {obs.content}. Retrying...')
|
||||
sleep_if_should_continue(10)
|
||||
else:
|
||||
assert_and_raise(False, f'Unexpected observation type: {str(obs)}')
|
||||
|
||||
assert_and_raise(git_patch is not None, 'Failed to get git diff (None)')
|
||||
|
||||
# Remove binary diffs from the patch
|
||||
git_patch = remove_binary_diffs(git_patch)
|
||||
|
||||
logger.info('-' * 30)
|
||||
logger.info('END Runtime Completion Fn')
|
||||
logger.info('-' * 30)
|
||||
return {'git_patch': git_patch}
|
||||
|
||||
|
||||
class CPUGroupManager:
|
||||
def __init__(self, cpu_groups_queue: multiprocessing.Queue):
|
||||
self.cpu_groups_queue = cpu_groups_queue
|
||||
|
||||
def __enter__(self):
|
||||
# Get the current CPU group for this worker]
|
||||
if self.cpu_groups_queue is not None:
|
||||
self.cpu_group = self.cpu_groups_queue.get()
|
||||
logger.info(f'Worker started with CPU group: {self.cpu_group}')
|
||||
return self.cpu_group
|
||||
return None
|
||||
|
||||
def __exit__(self, exc_type, exc_value, traceback):
|
||||
# Put the CPU group back into the queue for other workers to use
|
||||
if self.cpu_groups_queue is not None:
|
||||
self.cpu_groups_queue.put(self.cpu_group)
|
||||
logger.info(f'Worker finished with CPU group: {self.cpu_group}')
|
||||
|
||||
|
||||
def cleanup_docker_resources_for_worker():
|
||||
"""Clean up Docker resources specific to this worker process.
|
||||
|
||||
This prevents cascade failures when one worker's container crashes.
|
||||
Note: This only cleans up stale locks, not containers, to avoid
|
||||
interfering with other workers. Container cleanup is handled
|
||||
by the DockerRuntime.close() method based on configuration.
|
||||
"""
|
||||
|
||||
# Clean up any stale port locks from crashed processes
|
||||
try:
|
||||
from openhands.runtime.utils.port_lock import cleanup_stale_locks
|
||||
|
||||
cleanup_stale_locks(max_age_seconds=300) # Clean up locks older than 5 minutes
|
||||
except Exception as e:
|
||||
logger.debug(f'Error cleaning up stale port locks: {e}')
|
||||
|
||||
|
||||
def process_instance(
|
||||
instance: pd.Series,
|
||||
metadata: EvalMetadata,
|
||||
reset_logger: bool = True,
|
||||
runtime_failure_count: int = 0,
|
||||
cpu_groups_queue: multiprocessing.Queue = None,
|
||||
) -> EvalOutput:
|
||||
# Clean up any Docker resources from previous failed runs
|
||||
cleanup_docker_resources_for_worker()
|
||||
|
||||
# HACK: Use the global and get the cpu group for this worker.
|
||||
with CPUGroupManager(cpu_groups_queue) as cpu_group:
|
||||
config = get_config(instance, metadata, cpu_group=cpu_group)
|
||||
|
||||
# Setup the logger properly, so you can run multi-processing to parallelize the evaluation
|
||||
if reset_logger:
|
||||
log_dir = os.path.join(metadata.eval_output_dir, 'infer_logs')
|
||||
reset_logger_for_multiprocessing(logger, instance.instance_id, log_dir)
|
||||
else:
|
||||
logger.info(f'Starting evaluation for instance {instance.instance_id}.')
|
||||
|
||||
metadata = copy.deepcopy(metadata)
|
||||
metadata.details['runtime_failure_count'] = runtime_failure_count
|
||||
metadata.details['remote_runtime_resource_factor'] = (
|
||||
config.sandbox.remote_runtime_resource_factor
|
||||
)
|
||||
|
||||
runtime = create_runtime(config, sid=None)
|
||||
call_async_from_sync(runtime.connect)
|
||||
|
||||
try:
|
||||
initialize_runtime(runtime, instance, metadata)
|
||||
|
||||
message_action = get_instruction(instance, metadata)
|
||||
|
||||
# Here's how you can run the agent (similar to the `main` function) and get the final task state
|
||||
state: State | None = asyncio.run(
|
||||
run_controller(
|
||||
config=config,
|
||||
initial_user_action=message_action,
|
||||
runtime=runtime,
|
||||
fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN[
|
||||
metadata.agent_class
|
||||
],
|
||||
)
|
||||
)
|
||||
|
||||
# if fatal error, throw EvalError to trigger re-run
|
||||
if is_fatal_evaluation_error(state.last_error):
|
||||
raise EvalException('Fatal error detected: ' + state.last_error)
|
||||
|
||||
# ======= THIS IS SWE-Bench specific =======
|
||||
# Get git patch
|
||||
return_val = complete_runtime(runtime, instance)
|
||||
git_patch = return_val['git_patch']
|
||||
logger.info(
|
||||
f'Got git diff for instance {instance.instance_id}:\n--------\n{git_patch}\n--------'
|
||||
)
|
||||
except Exception as e:
|
||||
# Log the error but don't let it crash other workers
|
||||
logger.error(
|
||||
f'Error in worker processing instance {instance.instance_id}: {str(e)}'
|
||||
)
|
||||
raise
|
||||
finally:
|
||||
# Ensure runtime is properly closed to prevent cascade failures
|
||||
try:
|
||||
runtime.close()
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
f'Error closing runtime for {instance.instance_id}: {str(e)}'
|
||||
)
|
||||
# Don't re-raise - we want to continue cleanup
|
||||
|
||||
# ==========================================
|
||||
|
||||
# ======= Attempt to evaluate the agent's edits =======
|
||||
# we use eval_infer.sh to evaluate the agent's edits, not here
|
||||
# because the agent may alter the environment / testcases
|
||||
test_result = {
|
||||
'git_patch': git_patch,
|
||||
}
|
||||
|
||||
# If you are working on some simpler benchmark that only evaluates the final model output (e.g., in a MessageAction)
|
||||
# You can simply get the LAST `MessageAction` from the returned `state.history` and parse it for evaluation.
|
||||
if state is None:
|
||||
raise ValueError('State should not be None.')
|
||||
|
||||
# NOTE: this is NO LONGER the event stream, but an agent history that includes delegate agent's events
|
||||
histories = [event_to_dict(event) for event in state.history]
|
||||
metrics = get_metrics(state)
|
||||
|
||||
# Save the output
|
||||
instruction = message_action.content
|
||||
if message_action.image_urls:
|
||||
instruction += (
|
||||
'\n\n<image_urls>'
|
||||
+ '\n'.join(message_action.image_urls)
|
||||
+ '</image_urls>'
|
||||
)
|
||||
output = EvalOutput(
|
||||
instance_id=instance.instance_id,
|
||||
instruction=instruction,
|
||||
instance=instance.to_dict(), # SWE Bench specific
|
||||
test_result=test_result,
|
||||
metadata=metadata,
|
||||
history=histories,
|
||||
metrics=metrics,
|
||||
error=state.last_error if state and state.last_error else None,
|
||||
)
|
||||
return output
|
||||
|
||||
|
||||
def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
|
||||
file_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'config.toml')
|
||||
if os.path.exists(file_path):
|
||||
with open(file_path, 'r') as file:
|
||||
data = toml.load(file)
|
||||
if 'selected_ids' in data:
|
||||
selected_ids = data['selected_ids']
|
||||
logger.info(
|
||||
f'Filtering {len(selected_ids)} tasks from "selected_ids"...'
|
||||
)
|
||||
subset = dataset[dataset[filter_column].isin(selected_ids)]
|
||||
logger.info(f'Retained {subset.shape[0]} tasks after filtering')
|
||||
return subset
|
||||
if 'selected_repos' in data:
|
||||
# repos for the swe-bench instances:
|
||||
# ['astropy/astropy', 'django/django', 'matplotlib/matplotlib', 'mwaskom/seaborn', 'pallets/flask', 'psf/requests', 'pydata/xarray', 'pylint-dev/pylint', 'pytest-dev/pytest', 'scikit-learn/scikit-learn', 'sphinx-doc/sphinx', 'sympy/sympy']
|
||||
selected_repos = data['selected_repos']
|
||||
if isinstance(selected_repos, str):
|
||||
selected_repos = [selected_repos]
|
||||
assert isinstance(selected_repos, list)
|
||||
logger.info(
|
||||
f'Filtering {selected_repos} tasks from "selected_repos"...'
|
||||
)
|
||||
subset = dataset[dataset['repo'].isin(selected_repos)]
|
||||
logger.info(f'Retained {subset.shape[0]} tasks after filtering')
|
||||
return subset
|
||||
|
||||
skip_ids = os.environ.get('SKIP_IDS', '').split(',')
|
||||
if len(skip_ids) > 0:
|
||||
logger.info(f'Filtering {len(skip_ids)} tasks from "SKIP_IDS"...')
|
||||
return dataset[~dataset[filter_column].isin(skip_ids)]
|
||||
return dataset
|
||||
|
||||
|
||||
def divide_cpus_among_workers(num_workers, num_cpus_per_worker=4, num_to_skip=0):
|
||||
"""Divide CPUs among workers, with better error handling for multiprocessing."""
|
||||
try:
|
||||
current_cpus = list(os.sched_getaffinity(0))
|
||||
except AttributeError:
|
||||
# os.sched_getaffinity not available on all platforms
|
||||
import multiprocessing
|
||||
|
||||
current_cpus = list(range(multiprocessing.cpu_count()))
|
||||
|
||||
num_cpus = len(current_cpus)
|
||||
if num_workers <= 0:
|
||||
raise ValueError('Number of workers must be greater than 0')
|
||||
|
||||
# Chec that num worers and num_cpus_per_worker fit into available CPUs
|
||||
total_cpus_needed = num_workers * num_cpus_per_worker + num_to_skip
|
||||
if total_cpus_needed > num_cpus:
|
||||
raise ValueError(
|
||||
f'Not enough CPUs available. Requested {total_cpus_needed} '
|
||||
f'CPUs (num_workers={num_workers}, num_cpus_per_worker={num_cpus_per_worker}, '
|
||||
f'num_to_skip={num_to_skip}), but only {num_cpus} CPUs are available.'
|
||||
)
|
||||
|
||||
# Divide this into groups, skipping the first `num_to_skip` CPUs.
|
||||
available_cpus = current_cpus[num_to_skip:]
|
||||
cpu_groups = [
|
||||
available_cpus[i * num_cpus_per_worker : (i + 1) * num_cpus_per_worker]
|
||||
for i in range(num_workers)
|
||||
]
|
||||
print(
|
||||
f'Divided {num_cpus} CPUs into {num_workers} groups, each with {num_cpus_per_worker} CPUs.'
|
||||
)
|
||||
print(f'CPU groups: {cpu_groups}')
|
||||
|
||||
return cpu_groups
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = get_evaluation_parser()
|
||||
parser.add_argument(
|
||||
'--dataset',
|
||||
type=str,
|
||||
default=None,
|
||||
help='data set to evaluate on, for now use local.',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--split',
|
||||
type=str,
|
||||
default='test',
|
||||
help='split to evaluate on',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--mode',
|
||||
type=str,
|
||||
default='swe',
|
||||
help='mode to evaluate on',
|
||||
)
|
||||
|
||||
args, _ = parser.parse_known_args()
|
||||
|
||||
# NOTE: It is preferable to load datasets from huggingface datasets and perform post-processing
|
||||
# so we don't need to manage file uploading to OpenHands's repo
|
||||
|
||||
# dataset = load_dataset(args.dataset, split=args.split)
|
||||
# swe_bench_tests = filter_dataset(dataset.to_pandas(), 'instance_id')
|
||||
dataset = load_dataset(args.dataset, split=args.split)
|
||||
|
||||
# Convert dataset to pandas DataFrame if it is not already.
|
||||
if not isinstance(dataset, pd.DataFrame):
|
||||
dataset = dataset.to_pandas()
|
||||
|
||||
dataset['version'] = dataset['version'].astype(str)
|
||||
|
||||
# Convert created_at column to string.
|
||||
dataset['created_at'] = dataset['created_at'].astype(str)
|
||||
|
||||
swe_bench_tests = filter_dataset(dataset, 'instance_id')
|
||||
|
||||
logger.info(
|
||||
f'Loaded dataset {args.dataset} with split {args.split}: {len(swe_bench_tests)} tasks'
|
||||
)
|
||||
|
||||
llm_config = None
|
||||
if args.llm_config:
|
||||
llm_config = get_llm_config_arg(args.llm_config)
|
||||
llm_config.log_completions = True
|
||||
# modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
|
||||
llm_config.modify_params = False
|
||||
|
||||
if llm_config is None:
|
||||
raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
|
||||
|
||||
# Get condenser config from environment variable
|
||||
condenser_name = os.environ.get('EVAL_CONDENSER')
|
||||
if condenser_name:
|
||||
condenser_config = get_condenser_config_arg(condenser_name)
|
||||
if condenser_config is None:
|
||||
raise ValueError(
|
||||
f'Could not find Condenser config: EVAL_CONDENSER={condenser_name}'
|
||||
)
|
||||
else:
|
||||
# If no specific condenser config is provided via env var, default to NoOpCondenser
|
||||
condenser_config = NoOpCondenserConfig()
|
||||
logger.debug(
|
||||
'No Condenser config provided via EVAL_CONDENSER, using NoOpCondenser.'
|
||||
)
|
||||
|
||||
details = {'mode': args.mode}
|
||||
_agent_cls = openhands.agenthub.Agent.get_cls(args.agent_cls)
|
||||
|
||||
dataset_descrption = (
|
||||
args.dataset.replace('/', '__') + '-' + args.split.replace('/', '__')
|
||||
)
|
||||
metadata = make_metadata(
|
||||
llm_config,
|
||||
dataset_descrption,
|
||||
args.agent_cls,
|
||||
args.max_iterations,
|
||||
args.eval_note,
|
||||
args.eval_output_dir,
|
||||
details=details,
|
||||
condenser_config=condenser_config,
|
||||
)
|
||||
|
||||
output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
|
||||
print(f'### OUTPUT FILE: {output_file} ###')
|
||||
|
||||
# Run evaluation in iterative mode:
|
||||
# If a rollout fails to output AgentFinishAction, we will try again until it succeeds OR total 3 attempts have been made.
|
||||
ITERATIVE_EVAL_MODE = (
|
||||
os.environ.get('ITERATIVE_EVAL_MODE', 'false').lower() == 'true'
|
||||
)
|
||||
ITERATIVE_EVAL_MODE_MAX_ATTEMPTS = int(
|
||||
os.environ.get('ITERATIVE_EVAL_MODE_MAX_ATTEMPTS', '3')
|
||||
)
|
||||
|
||||
# Get all CPUs and divide into groups of num_workers and put them into a multiprocessing.Queue.
|
||||
cpu_groups_queue = None
|
||||
cpu_groups_list = divide_cpus_among_workers(args.eval_num_workers, num_to_skip=8)
|
||||
cpu_groups_queue = multiprocessing.Manager().Queue()
|
||||
for cpu_group in cpu_groups_list:
|
||||
cpu_groups_queue.put(cpu_group)
|
||||
|
||||
if not ITERATIVE_EVAL_MODE:
|
||||
# load the dataset
|
||||
instances = prepare_dataset(swe_bench_tests, output_file, args.eval_n_limit)
|
||||
|
||||
process_instance_with_cpu_groups = functools.partial(
|
||||
process_instance,
|
||||
cpu_groups_queue=cpu_groups_queue,
|
||||
)
|
||||
|
||||
config = get_config(
|
||||
instances.iloc[0], # Use the first instance to get the config
|
||||
metadata,
|
||||
cpu_group=None, # We will use the cpu_groups_queue to get the cpu group later
|
||||
)
|
||||
|
||||
run_evaluation(
|
||||
instances,
|
||||
metadata,
|
||||
output_file,
|
||||
args.eval_num_workers,
|
||||
process_instance_with_cpu_groups,
|
||||
timeout_seconds=8
|
||||
* 60
|
||||
* 60, # 8 hour PER instance should be more than enough
|
||||
max_retries=3,
|
||||
)
|
||||
else:
|
||||
critic = AgentFinishedCritic()
|
||||
|
||||
def get_cur_output_file_path(attempt: int) -> str:
|
||||
return (
|
||||
f'{output_file.removesuffix(".jsonl")}.critic_attempt_{attempt}.jsonl'
|
||||
)
|
||||
|
||||
eval_ids = None
|
||||
for attempt in range(1, ITERATIVE_EVAL_MODE_MAX_ATTEMPTS + 1):
|
||||
cur_output_file = get_cur_output_file_path(attempt)
|
||||
logger.info(
|
||||
f'Running evaluation with critic {critic.__class__.__name__} for attempt {attempt} of {ITERATIVE_EVAL_MODE_MAX_ATTEMPTS}.'
|
||||
)
|
||||
|
||||
# For deterministic eval, we set temperature to 0.1 for (>1) attempt
|
||||
# so hopefully we get slightly different results
|
||||
if attempt > 1 and metadata.llm_config.temperature == 0:
|
||||
logger.info(
|
||||
f'Detected temperature is 0 for (>1) attempt {attempt}. Setting temperature to 0.1...'
|
||||
)
|
||||
metadata.llm_config.temperature = 0.1
|
||||
|
||||
# Load instances - at first attempt, we evaluate all instances
|
||||
# On subsequent attempts, we only evaluate the instances that failed the previous attempt determined by critic
|
||||
instances = prepare_dataset(
|
||||
swe_bench_tests, cur_output_file, args.eval_n_limit, eval_ids=eval_ids
|
||||
)
|
||||
if len(instances) > 0 and not isinstance(
|
||||
instances['PASS_TO_PASS'][instances['PASS_TO_PASS'].index[0]], str
|
||||
):
|
||||
for col in ['PASS_TO_PASS', 'FAIL_TO_PASS']:
|
||||
instances[col] = instances[col].apply(lambda x: str(x))
|
||||
|
||||
# Run evaluation - but save them to cur_output_file
|
||||
logger.info(
|
||||
f'Evaluating {len(instances)} instances for attempt {attempt}...'
|
||||
)
|
||||
run_evaluation(
|
||||
instances,
|
||||
metadata,
|
||||
cur_output_file,
|
||||
args.eval_num_workers,
|
||||
process_instance,
|
||||
timeout_seconds=8
|
||||
* 60
|
||||
* 60, # 8 hour PER instance should be more than enough
|
||||
max_retries=1,
|
||||
)
|
||||
|
||||
# When eval is done, we update eval_ids to the instances that failed the current attempt
|
||||
instances_failed = []
|
||||
logger.info(
|
||||
f'Use critic {critic.__class__.__name__} to check {len(instances)} instances for attempt {attempt}...'
|
||||
)
|
||||
with open(cur_output_file, 'r') as f:
|
||||
for line in f:
|
||||
instance = json.loads(line)
|
||||
try:
|
||||
history = [
|
||||
event_from_dict(event) for event in instance['history']
|
||||
]
|
||||
critic_result = critic.evaluate(
|
||||
history, instance['test_result'].get('git_patch', '')
|
||||
)
|
||||
if not critic_result.success:
|
||||
instances_failed.append(instance['instance_id'])
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f'Error loading history for instance {instance["instance_id"]}: {e}'
|
||||
)
|
||||
instances_failed.append(instance['instance_id'])
|
||||
logger.info(
|
||||
f'{len(instances_failed)} instances failed the current attempt {attempt}: {instances_failed}'
|
||||
)
|
||||
eval_ids = instances_failed
|
||||
|
||||
# If no instances failed, we break
|
||||
if len(instances_failed) == 0:
|
||||
break
|
||||
|
||||
# Then we should aggregate the results from all attempts into the original output file
|
||||
# and remove the intermediate files
|
||||
logger.info(
|
||||
'Aggregating results from all attempts into the original output file...'
|
||||
)
|
||||
fout = open(output_file, 'w')
|
||||
added_instance_ids = set()
|
||||
for attempt in reversed(range(1, ITERATIVE_EVAL_MODE_MAX_ATTEMPTS + 1)):
|
||||
cur_output_file = get_cur_output_file_path(attempt)
|
||||
if not os.path.exists(cur_output_file):
|
||||
logger.warning(
|
||||
f'Intermediate output file {cur_output_file} does not exist. Skipping...'
|
||||
)
|
||||
continue
|
||||
|
||||
with open(cur_output_file, 'r') as f:
|
||||
for line in f:
|
||||
instance = json.loads(line)
|
||||
# Also make sure git_patch is not empty - otherwise we fall back to previous attempt (empty patch is worse than anything else)
|
||||
if (
|
||||
instance['instance_id'] not in added_instance_ids
|
||||
and instance['test_result'].get('git_patch', '').strip()
|
||||
):
|
||||
fout.write(line)
|
||||
added_instance_ids.add(instance['instance_id'])
|
||||
logger.info(
|
||||
f'Aggregated instances from {cur_output_file}. Total instances added so far: {len(added_instance_ids)}'
|
||||
)
|
||||
fout.close()
|
||||
logger.info(
|
||||
f'Done! Total {len(added_instance_ids)} instances added to {output_file}'
|
||||
)
|
||||
148
evaluation/benchmarks/swefficiency/scripts/run_infer.sh
Executable file
148
evaluation/benchmarks/swefficiency/scripts/run_infer.sh
Executable file
@ -0,0 +1,148 @@
|
||||
#!/usr/bin/env bash
|
||||
set -eo pipefail
|
||||
|
||||
source "evaluation/utils/version_control.sh"
|
||||
|
||||
MODEL_CONFIG=$1
|
||||
COMMIT_HASH=$2
|
||||
AGENT=$3
|
||||
EVAL_LIMIT=$4
|
||||
MAX_ITER=$5
|
||||
NUM_WORKERS=$6
|
||||
DATASET=$7
|
||||
SPLIT=$8
|
||||
N_RUNS=$9
|
||||
MODE=${10}
|
||||
|
||||
|
||||
if [ -z "$NUM_WORKERS" ]; then
|
||||
NUM_WORKERS=1
|
||||
echo "Number of workers not specified, use default $NUM_WORKERS"
|
||||
fi
|
||||
checkout_eval_branch
|
||||
|
||||
if [ -z "$AGENT" ]; then
|
||||
echo "Agent not specified, use default CodeActAgent"
|
||||
AGENT="CodeActAgent"
|
||||
fi
|
||||
|
||||
if [ -z "$MAX_ITER" ]; then
|
||||
echo "MAX_ITER not specified, use default 100"
|
||||
MAX_ITER=100
|
||||
fi
|
||||
|
||||
if [ -z "$RUN_WITH_BROWSING" ]; then
|
||||
echo "RUN_WITH_BROWSING not specified, use default false"
|
||||
RUN_WITH_BROWSING=false
|
||||
fi
|
||||
|
||||
|
||||
if [ -z "$DATASET" ]; then
|
||||
echo "DATASET not specified, use default princeton-nlp/SWE-bench_Lite"
|
||||
DATASET="swefficiency/swefficiency"
|
||||
fi
|
||||
|
||||
if [ -z "$SPLIT" ]; then
|
||||
echo "SPLIT not specified, use default test"
|
||||
SPLIT="test"
|
||||
fi
|
||||
|
||||
if [ -z "$MODE" ]; then
|
||||
MODE="swe"
|
||||
echo "MODE not specified, use default $MODE"
|
||||
fi
|
||||
|
||||
if [ -n "$EVAL_CONDENSER" ]; then
|
||||
echo "Using Condenser Config: $EVAL_CONDENSER"
|
||||
else
|
||||
echo "No Condenser Config provided via EVAL_CONDENSER, use default (NoOpCondenser)."
|
||||
fi
|
||||
|
||||
export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
|
||||
echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
|
||||
|
||||
get_openhands_version
|
||||
|
||||
echo "AGENT: $AGENT"
|
||||
echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
|
||||
echo "MODEL_CONFIG: $MODEL_CONFIG"
|
||||
echo "DATASET: $DATASET"
|
||||
echo "SPLIT: $SPLIT"
|
||||
echo "MAX_ITER: $MAX_ITER"
|
||||
echo "NUM_WORKERS: $NUM_WORKERS"
|
||||
echo "COMMIT_HASH: $COMMIT_HASH"
|
||||
echo "MODE: $MODE"
|
||||
echo "EVAL_CONDENSER: $EVAL_CONDENSER"
|
||||
|
||||
# Default to NOT use Hint
|
||||
if [ -z "$USE_HINT_TEXT" ]; then
|
||||
export USE_HINT_TEXT=false
|
||||
fi
|
||||
echo "USE_HINT_TEXT: $USE_HINT_TEXT"
|
||||
EVAL_NOTE="$OPENHANDS_VERSION"
|
||||
# if not using Hint, add -no-hint to the eval note
|
||||
if [ "$USE_HINT_TEXT" = false ]; then
|
||||
EVAL_NOTE="$EVAL_NOTE-no-hint"
|
||||
fi
|
||||
|
||||
if [ "$RUN_WITH_BROWSING" = true ]; then
|
||||
EVAL_NOTE="$EVAL_NOTE-with-browsing"
|
||||
fi
|
||||
|
||||
if [ -n "$EXP_NAME" ]; then
|
||||
EVAL_NOTE="$EVAL_NOTE-$EXP_NAME"
|
||||
fi
|
||||
# if mode != swe, add mode to the eval note
|
||||
if [ "$MODE" != "swe" ]; then
|
||||
EVAL_NOTE="${EVAL_NOTE}-${MODE}"
|
||||
fi
|
||||
# Add condenser config to eval note if provided
|
||||
if [ -n "$EVAL_CONDENSER" ]; then
|
||||
EVAL_NOTE="${EVAL_NOTE}-${EVAL_CONDENSER}"
|
||||
fi
|
||||
|
||||
# export RUNTIME="remote"
|
||||
# export SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev"
|
||||
export NO_CHANGE_TIMEOUT_SECONDS=900 # 15 minutes
|
||||
|
||||
function run_eval() {
|
||||
local eval_note="${1}"
|
||||
COMMAND="poetry run python evaluation/benchmarks/swefficiency/run_infer.py \
|
||||
--agent-cls $AGENT \
|
||||
--llm-config $MODEL_CONFIG \
|
||||
--max-iterations $MAX_ITER \
|
||||
--eval-num-workers $NUM_WORKERS \
|
||||
--eval-note $eval_note \
|
||||
--dataset $DATASET \
|
||||
--split $SPLIT \
|
||||
--mode $MODE"
|
||||
|
||||
if [ -n "$EVAL_LIMIT" ]; then
|
||||
echo "EVAL_LIMIT: $EVAL_LIMIT"
|
||||
COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
|
||||
fi
|
||||
|
||||
# Run the command
|
||||
eval $COMMAND
|
||||
}
|
||||
|
||||
unset SANDBOX_ENV_GITHUB_TOKEN # prevent the agent from using the github token to push
|
||||
if [ -z "$N_RUNS" ]; then
|
||||
N_RUNS=1
|
||||
echo "N_RUNS not specified, use default $N_RUNS"
|
||||
fi
|
||||
|
||||
# Skip runs if the run number is in the SKIP_RUNS list
|
||||
# read from env variable SKIP_RUNS as a comma separated list of run numbers
|
||||
SKIP_RUNS=(${SKIP_RUNS//,/ })
|
||||
for i in $(seq 1 $N_RUNS); do
|
||||
if [[ " ${SKIP_RUNS[@]} " =~ " $i " ]]; then
|
||||
echo "Skipping run $i"
|
||||
continue
|
||||
fi
|
||||
current_eval_note="$EVAL_NOTE-run_$i"
|
||||
echo "EVAL_NOTE: $current_eval_note"
|
||||
run_eval $current_eval_note
|
||||
done
|
||||
|
||||
checkout_original_branch
|
||||
43
evaluation/benchmarks/swefficiency/scripts/setup/instance_swe_entry.sh
Executable file
43
evaluation/benchmarks/swefficiency/scripts/setup/instance_swe_entry.sh
Executable file
@ -0,0 +1,43 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
source ~/.bashrc
|
||||
SWEUTIL_DIR=/swe_util
|
||||
|
||||
# FIXME: Cannot read SWE_INSTANCE_ID from the environment variable
|
||||
# SWE_INSTANCE_ID=django__django-11099
|
||||
if [ -z "$SWE_INSTANCE_ID" ]; then
|
||||
echo "Error: SWE_INSTANCE_ID is not set." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Read the swe-bench-test-lite.json file and extract the required item based on instance_id
|
||||
item=$(jq --arg INSTANCE_ID "$SWE_INSTANCE_ID" '.[] | select(.instance_id == $INSTANCE_ID)' $SWEUTIL_DIR/eval_data/instances/swe-bench-instance.json)
|
||||
|
||||
if [[ -z "$item" ]]; then
|
||||
echo "No item found for the provided instance ID."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
|
||||
WORKSPACE_NAME=$(echo "$item" | jq -r '(.repo | tostring) + "__" + (.version | tostring) | gsub("/"; "__")')
|
||||
|
||||
echo "WORKSPACE_NAME: $WORKSPACE_NAME"
|
||||
|
||||
# Clear the workspace
|
||||
if [ -d /workspace ]; then
|
||||
rm -rf /workspace/*
|
||||
else
|
||||
mkdir /workspace
|
||||
fi
|
||||
# Copy repo to workspace
|
||||
if [ -d /workspace/$WORKSPACE_NAME ]; then
|
||||
rm -rf /workspace/$WORKSPACE_NAME
|
||||
fi
|
||||
mkdir -p /workspace
|
||||
cp -r /testbed /workspace/$WORKSPACE_NAME
|
||||
|
||||
# Activate instance-specific environment
|
||||
if [ -d /opt/miniconda3 ]; then
|
||||
. /opt/miniconda3/etc/profile.d/conda.sh
|
||||
conda activate testbed
|
||||
fi
|
||||
27
evaluation/benchmarks/swefficiency/scripts/setup/prepare_swe_utils.sh
Executable file
27
evaluation/benchmarks/swefficiency/scripts/setup/prepare_swe_utils.sh
Executable file
@ -0,0 +1,27 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
set -e
|
||||
EVAL_WORKSPACE="evaluation/benchmarks/swe_bench/eval_workspace"
|
||||
mkdir -p $EVAL_WORKSPACE
|
||||
|
||||
# 1. Prepare REPO
|
||||
echo "==== Prepare SWE-bench repo ===="
|
||||
OH_SWE_BENCH_REPO_PATH="https://github.com/All-Hands-AI/SWE-bench.git"
|
||||
OH_SWE_BENCH_REPO_BRANCH="eval"
|
||||
git clone -b $OH_SWE_BENCH_REPO_BRANCH $OH_SWE_BENCH_REPO_PATH $EVAL_WORKSPACE/OH-SWE-bench
|
||||
|
||||
# 2. Prepare DATA
|
||||
echo "==== Prepare SWE-bench data ===="
|
||||
EVAL_IMAGE=ghcr.io/all-hands-ai/eval-swe-bench:builder_with_conda
|
||||
EVAL_WORKSPACE=$(realpath $EVAL_WORKSPACE)
|
||||
chmod +x $EVAL_WORKSPACE/OH-SWE-bench/swebench/harness/prepare_data.sh
|
||||
if [ -d $EVAL_WORKSPACE/eval_data ]; then
|
||||
rm -r $EVAL_WORKSPACE/eval_data
|
||||
fi
|
||||
docker run \
|
||||
-v $EVAL_WORKSPACE:/workspace \
|
||||
-w /workspace \
|
||||
-u $(id -u):$(id -g) \
|
||||
-e HF_DATASETS_CACHE="/tmp" \
|
||||
--rm -it $EVAL_IMAGE \
|
||||
bash -c "cd OH-SWE-bench/swebench/harness && /swe_util/miniforge3/bin/conda run -n swe-bench-eval ./prepare_data.sh && mv eval_data /workspace/"
|
||||
96
evaluation/benchmarks/swefficiency/scripts/setup/swe_entry.sh
Executable file
96
evaluation/benchmarks/swefficiency/scripts/setup/swe_entry.sh
Executable file
@ -0,0 +1,96 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
set -e
|
||||
|
||||
# assert user name is `root`
|
||||
if [ "$USER" != "root" ]; then
|
||||
echo "Error: This script is intended to be run by the 'root' user only." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
source ~/.bashrc
|
||||
|
||||
SWEUTIL_DIR=/swe_util
|
||||
|
||||
# Create logs directory
|
||||
LOG_DIR=/openhands/logs
|
||||
mkdir -p $LOG_DIR && chmod 777 $LOG_DIR
|
||||
|
||||
# FIXME: Cannot read SWE_INSTANCE_ID from the environment variable
|
||||
# SWE_INSTANCE_ID=django__django-11099
|
||||
if [ -z "$SWE_INSTANCE_ID" ]; then
|
||||
echo "Error: SWE_INSTANCE_ID is not set." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Read the swe-bench-test-lite.json file and extract the required item based on instance_id
|
||||
item=$(jq --arg INSTANCE_ID "$SWE_INSTANCE_ID" '.[] | select(.instance_id == $INSTANCE_ID)' $SWEUTIL_DIR/eval_data/instances/swe-bench-test-lite.json)
|
||||
|
||||
if [[ -z "$item" ]]; then
|
||||
echo "No item found for the provided instance ID."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
CONDA_ENV_NAME=$(echo "$item" | jq -r '.repo + "__" + .version | gsub("/"; "__")')
|
||||
|
||||
echo "CONDA_ENV_NAME: $CONDA_ENV_NAME"
|
||||
|
||||
SWE_TASK_DIR=/openhands/swe_tasks
|
||||
mkdir -p $SWE_TASK_DIR
|
||||
# Dump test_patch to /workspace/test.patch
|
||||
echo "$item" | jq -r '.test_patch' > $SWE_TASK_DIR/test.patch
|
||||
# Dump patch to /workspace/gold.patch
|
||||
echo "$item" | jq -r '.patch' > $SWE_TASK_DIR/gold.patch
|
||||
# Dump the item to /workspace/instance.json except for the "test_patch" and "patch" fields
|
||||
echo "$item" | jq 'del(.test_patch, .patch)' > $SWE_TASK_DIR/instance.json
|
||||
|
||||
# Clear the workspace
|
||||
rm -rf /workspace/*
|
||||
# Copy repo to workspace
|
||||
if [ -d /workspace/$CONDA_ENV_NAME ]; then
|
||||
rm -rf /workspace/$CONDA_ENV_NAME
|
||||
fi
|
||||
cp -r $SWEUTIL_DIR/eval_data/testbeds/$CONDA_ENV_NAME /workspace
|
||||
|
||||
# Reset swe-bench testbed and install the repo
|
||||
. $SWEUTIL_DIR/miniforge3/etc/profile.d/conda.sh
|
||||
conda config --set changeps1 False
|
||||
conda config --append channels conda-forge
|
||||
conda activate swe-bench-eval
|
||||
|
||||
mkdir -p $SWE_TASK_DIR/reset_testbed_temp
|
||||
mkdir -p $SWE_TASK_DIR/reset_testbed_log_dir
|
||||
SWE_BENCH_DIR=/swe_util/OH-SWE-bench
|
||||
output=$(
|
||||
export PYTHONPATH=$SWE_BENCH_DIR && \
|
||||
cd $SWE_BENCH_DIR && \
|
||||
python swebench/harness/reset_swe_env.py \
|
||||
--swe_bench_tasks $SWEUTIL_DIR/eval_data/instances/swe-bench-test.json \
|
||||
--temp_dir $SWE_TASK_DIR/reset_testbed_temp \
|
||||
--testbed /workspace \
|
||||
--conda_path $SWEUTIL_DIR/miniforge3 \
|
||||
--instance_id $SWE_INSTANCE_ID \
|
||||
--log_dir $SWE_TASK_DIR/reset_testbed_log_dir \
|
||||
--timeout 900 \
|
||||
--verbose
|
||||
)
|
||||
|
||||
REPO_PATH=$(echo "$output" | awk -F': ' '/repo_path:/ {print $2}')
|
||||
TEST_CMD=$(echo "$output" | awk -F': ' '/test_cmd:/ {print $2}')
|
||||
echo "Repo Path: $REPO_PATH"
|
||||
echo "Test Command: $TEST_CMD"
|
||||
|
||||
echo "export SWE_BENCH_DIR=\"$SWE_BENCH_DIR\"" >> ~/.bashrc
|
||||
echo "export REPO_PATH=\"$REPO_PATH\"" >> ~/.bashrc
|
||||
echo "export TEST_CMD=\"$TEST_CMD\"" >> ~/.bashrc
|
||||
|
||||
if [[ "$REPO_PATH" == "None" ]]; then
|
||||
echo "Error: Failed to retrieve repository path. Tests may not have passed or output was not as expected." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Activate instance-specific environment
|
||||
. $SWEUTIL_DIR/miniforge3/etc/profile.d/conda.sh
|
||||
conda activate $CONDA_ENV_NAME
|
||||
|
||||
set +e
|
||||
@ -1,2 +0,0 @@
|
||||
public-hoist-pattern[]=*@nextui-org/*
|
||||
enable-pre-post-scripts=true
|
||||
@ -30,61 +30,33 @@ vi.mock("react-i18next", async () => {
|
||||
};
|
||||
});
|
||||
|
||||
// Mock Zustand browser store
|
||||
let mockBrowserState = {
|
||||
url: "https://example.com",
|
||||
screenshotSrc: "",
|
||||
setUrl: vi.fn(),
|
||||
setScreenshotSrc: vi.fn(),
|
||||
reset: vi.fn(),
|
||||
};
|
||||
|
||||
vi.mock("#/stores/browser-store", () => ({
|
||||
useBrowserStore: () => mockBrowserState,
|
||||
}));
|
||||
|
||||
// Import the component after all mocks are set up
|
||||
import { BrowserPanel } from "#/components/features/browser/browser";
|
||||
import { useBrowserStore } from "#/stores/browser-store";
|
||||
|
||||
describe("Browser", () => {
|
||||
afterEach(() => {
|
||||
vi.clearAllMocks();
|
||||
// Reset the mock state
|
||||
mockBrowserState = {
|
||||
url: "https://example.com",
|
||||
screenshotSrc: "",
|
||||
setUrl: vi.fn(),
|
||||
setScreenshotSrc: vi.fn(),
|
||||
reset: vi.fn(),
|
||||
};
|
||||
});
|
||||
|
||||
it("renders a message if no screenshotSrc is provided", () => {
|
||||
// Set the mock state for this test
|
||||
mockBrowserState = {
|
||||
useBrowserStore.setState({
|
||||
url: "https://example.com",
|
||||
screenshotSrc: "",
|
||||
setUrl: vi.fn(),
|
||||
setScreenshotSrc: vi.fn(),
|
||||
reset: vi.fn(),
|
||||
};
|
||||
});
|
||||
|
||||
render(<BrowserPanel />);
|
||||
|
||||
// i18n empty message key
|
||||
expect(screen.getByText("BROWSER$NO_PAGE_LOADED")).toBeInTheDocument();
|
||||
});
|
||||
|
||||
it("renders the url and a screenshot", () => {
|
||||
// Set the mock state for this test
|
||||
mockBrowserState = {
|
||||
useBrowserStore.setState({
|
||||
url: "https://example.com",
|
||||
screenshotSrc:
|
||||
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mN0uGvyHwAFCAJS091fQwAAAABJRU5ErkJggg==",
|
||||
setUrl: vi.fn(),
|
||||
setScreenshotSrc: vi.fn(),
|
||||
reset: vi.fn(),
|
||||
};
|
||||
});
|
||||
|
||||
render(<BrowserPanel />);
|
||||
|
||||
|
||||
@ -25,10 +25,7 @@ import { useUnifiedUploadFiles } from "#/hooks/mutation/use-unified-upload-files
|
||||
import { OpenHandsAction } from "#/types/core/actions";
|
||||
import { useEventStore } from "#/stores/use-event-store";
|
||||
|
||||
// Mock the hooks
|
||||
vi.mock("#/context/ws-client-provider");
|
||||
vi.mock("#/stores/error-message-store");
|
||||
vi.mock("#/stores/optimistic-user-message-store");
|
||||
vi.mock("#/hooks/query/use-config");
|
||||
vi.mock("#/hooks/mutation/use-get-trajectory");
|
||||
vi.mock("#/hooks/mutation/use-unified-upload-files");
|
||||
@ -102,24 +99,20 @@ describe("ChatInterface - Chat Suggestions", () => {
|
||||
},
|
||||
});
|
||||
|
||||
// Default mock implementations
|
||||
(useWsClient as unknown as ReturnType<typeof vi.fn>).mockReturnValue({
|
||||
send: vi.fn(),
|
||||
isLoadingMessages: false,
|
||||
parsedEvents: [],
|
||||
});
|
||||
(
|
||||
useOptimisticUserMessageStore as unknown as ReturnType<typeof vi.fn>
|
||||
).mockReturnValue({
|
||||
setOptimisticUserMessage: vi.fn(),
|
||||
getOptimisticUserMessage: vi.fn(() => null),
|
||||
|
||||
useOptimisticUserMessageStore.setState({
|
||||
optimisticUserMessage: null,
|
||||
});
|
||||
(
|
||||
useErrorMessageStore as unknown as ReturnType<typeof vi.fn>
|
||||
).mockReturnValue({
|
||||
setErrorMessage: vi.fn(),
|
||||
removeErrorMessage: vi.fn(),
|
||||
|
||||
useErrorMessageStore.setState({
|
||||
errorMessage: null,
|
||||
});
|
||||
|
||||
(useConfig as unknown as ReturnType<typeof vi.fn>).mockReturnValue({
|
||||
data: { APP_MODE: "local" },
|
||||
});
|
||||
@ -204,11 +197,8 @@ describe("ChatInterface - Chat Suggestions", () => {
|
||||
});
|
||||
|
||||
test("should hide chat suggestions when there is an optimistic user message", () => {
|
||||
(
|
||||
useOptimisticUserMessageStore as unknown as ReturnType<typeof vi.fn>
|
||||
).mockReturnValue({
|
||||
setOptimisticUserMessage: vi.fn(),
|
||||
getOptimisticUserMessage: vi.fn(() => "Optimistic message"),
|
||||
useOptimisticUserMessageStore.setState({
|
||||
optimisticUserMessage: "Optimistic message",
|
||||
});
|
||||
|
||||
renderWithQueryClient(<ChatInterface />, queryClient);
|
||||
@ -240,24 +230,19 @@ describe("ChatInterface - Empty state", () => {
|
||||
});
|
||||
|
||||
beforeEach(() => {
|
||||
// Reset mocks to ensure empty state
|
||||
(useWsClient as unknown as ReturnType<typeof vi.fn>).mockReturnValue({
|
||||
send: sendMock,
|
||||
status: "CONNECTED",
|
||||
isLoadingMessages: false,
|
||||
parsedEvents: [],
|
||||
});
|
||||
(
|
||||
useOptimisticUserMessageStore as unknown as ReturnType<typeof vi.fn>
|
||||
).mockReturnValue({
|
||||
setOptimisticUserMessage: vi.fn(),
|
||||
getOptimisticUserMessage: vi.fn(() => null),
|
||||
|
||||
useOptimisticUserMessageStore.setState({
|
||||
optimisticUserMessage: null,
|
||||
});
|
||||
(
|
||||
useErrorMessageStore as unknown as ReturnType<typeof vi.fn>
|
||||
).mockReturnValue({
|
||||
setErrorMessage: vi.fn(),
|
||||
removeErrorMessage: vi.fn(),
|
||||
|
||||
useErrorMessageStore.setState({
|
||||
errorMessage: null,
|
||||
});
|
||||
(useConfig as unknown as ReturnType<typeof vi.fn>).mockReturnValue({
|
||||
data: { APP_MODE: "local" },
|
||||
|
||||
@ -61,7 +61,7 @@ describe("ExpandableMessage", () => {
|
||||
expect(icon).toHaveClass("fill-success");
|
||||
});
|
||||
|
||||
it("should render with error icon for failed action messages", () => {
|
||||
it("should render with no icon for failed action messages", () => {
|
||||
renderWithProviders(
|
||||
<ExpandableMessage
|
||||
id="OBSERVATION_MESSAGE$RUN"
|
||||
@ -75,8 +75,7 @@ describe("ExpandableMessage", () => {
|
||||
"div.flex.gap-2.items-center.justify-start",
|
||||
);
|
||||
expect(container).toHaveClass("border-neutral-300");
|
||||
const icon = screen.getByTestId("status-icon");
|
||||
expect(icon).toHaveClass("fill-danger");
|
||||
expect(screen.queryByTestId("status-icon")).not.toBeInTheDocument();
|
||||
});
|
||||
|
||||
it("should render with neutral border and no icon for action messages without success prop", () => {
|
||||
|
||||
@ -3,7 +3,7 @@ import { describe, expect, it, vi } from "vitest";
|
||||
import { render, screen, waitFor } from "@testing-library/react";
|
||||
import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
|
||||
import { AnalyticsConsentFormModal } from "#/components/features/analytics/analytics-consent-form-modal";
|
||||
import SettingsService from "#/settings-service/settings-service.api";
|
||||
import SettingsService from "#/api/settings-service/settings-service.api";
|
||||
|
||||
describe("AnalyticsConsentFormModal", () => {
|
||||
it("should call saveUserSettings with consent", async () => {
|
||||
|
||||
@ -0,0 +1,71 @@
|
||||
import { render, screen } from "@testing-library/react";
|
||||
import { describe, it, expect, vi } from "vitest";
|
||||
import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
|
||||
import { MemoryRouter } from "react-router";
|
||||
import { AgentStatus } from "#/components/features/controls/agent-status";
|
||||
import { AgentState } from "#/types/agent-state";
|
||||
import { useAgentState } from "#/hooks/use-agent-state";
|
||||
import { useConversationStore } from "#/state/conversation-store";
|
||||
|
||||
vi.mock("#/hooks/use-agent-state");
|
||||
|
||||
vi.mock("#/hooks/use-conversation-id", () => ({
|
||||
useConversationId: () => ({ conversationId: "test-id" }),
|
||||
}));
|
||||
|
||||
const wrapper = ({ children }: { children: React.ReactNode }) => (
|
||||
<MemoryRouter>
|
||||
<QueryClientProvider client={new QueryClient()}>
|
||||
{children}
|
||||
</QueryClientProvider>
|
||||
</MemoryRouter>
|
||||
);
|
||||
|
||||
const renderAgentStatus = ({
|
||||
isPausing = false,
|
||||
}: { isPausing?: boolean } = {}) =>
|
||||
render(
|
||||
<AgentStatus
|
||||
handleStop={vi.fn()}
|
||||
handleResumeAgent={vi.fn()}
|
||||
isPausing={isPausing}
|
||||
/>,
|
||||
{ wrapper },
|
||||
);
|
||||
|
||||
describe("AgentStatus - isLoading logic", () => {
|
||||
it("should show loading when curAgentState is INIT", () => {
|
||||
vi.mocked(useAgentState).mockReturnValue({
|
||||
curAgentState: AgentState.INIT,
|
||||
});
|
||||
|
||||
renderAgentStatus();
|
||||
|
||||
expect(screen.getByTestId("agent-loading-spinner")).toBeInTheDocument();
|
||||
});
|
||||
|
||||
it("should show loading when isPausing is true, even if shouldShownAgentLoading is false", () => {
|
||||
vi.mocked(useAgentState).mockReturnValue({
|
||||
curAgentState: AgentState.AWAITING_USER_INPUT,
|
||||
});
|
||||
|
||||
renderAgentStatus({ isPausing: true });
|
||||
|
||||
expect(screen.getByTestId("agent-loading-spinner")).toBeInTheDocument();
|
||||
});
|
||||
|
||||
it("should NOT update global shouldShownAgentLoading when only isPausing is true", () => {
|
||||
vi.mocked(useAgentState).mockReturnValue({
|
||||
curAgentState: AgentState.AWAITING_USER_INPUT,
|
||||
});
|
||||
|
||||
renderAgentStatus({ isPausing: true });
|
||||
|
||||
// Loading spinner shows (because isPausing)
|
||||
expect(screen.getByTestId("agent-loading-spinner")).toBeInTheDocument();
|
||||
|
||||
// But global state should be false (because shouldShownAgentLoading is false)
|
||||
const { shouldShownAgentLoading } = useConversationStore.getState();
|
||||
expect(shouldShownAgentLoading).toBe(false);
|
||||
});
|
||||
});
|
||||
@ -0,0 +1,56 @@
|
||||
import { render, screen, waitFor } from "@testing-library/react";
|
||||
import { describe, it, expect, vi } from "vitest";
|
||||
import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
|
||||
import { createRoutesStub } from "react-router";
|
||||
import { RecentConversations } from "#/components/features/home/recent-conversations/recent-conversations";
|
||||
import ConversationService from "#/api/conversation-service/conversation-service.api";
|
||||
|
||||
const renderRecentConversations = () => {
|
||||
const RouterStub = createRoutesStub([
|
||||
{
|
||||
Component: () => <RecentConversations />,
|
||||
path: "/",
|
||||
},
|
||||
]);
|
||||
|
||||
const queryClient = new QueryClient({
|
||||
defaultOptions: {
|
||||
queries: {
|
||||
retry: false,
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
return render(<RouterStub />, {
|
||||
wrapper: ({ children }) => (
|
||||
<QueryClientProvider client={queryClient}>{children}</QueryClientProvider>
|
||||
),
|
||||
});
|
||||
};
|
||||
|
||||
describe("RecentConversations", () => {
|
||||
const getUserConversationsSpy = vi.spyOn(
|
||||
ConversationService,
|
||||
"getUserConversations",
|
||||
);
|
||||
|
||||
it("should not show empty state when there is an error", async () => {
|
||||
getUserConversationsSpy.mockRejectedValue(
|
||||
new Error("Failed to fetch conversations"),
|
||||
);
|
||||
|
||||
renderRecentConversations();
|
||||
|
||||
// Wait for the error to be displayed
|
||||
await waitFor(() => {
|
||||
expect(
|
||||
screen.getByText("Failed to fetch conversations"),
|
||||
).toBeInTheDocument();
|
||||
});
|
||||
|
||||
// The empty state should NOT be displayed when there's an error
|
||||
expect(
|
||||
screen.queryByText("HOME$NO_RECENT_CONVERSATIONS"),
|
||||
).not.toBeInTheDocument();
|
||||
});
|
||||
});
|
||||
@ -3,7 +3,7 @@ import { beforeEach, describe, expect, it, vi } from "vitest";
|
||||
import userEvent from "@testing-library/user-event";
|
||||
import { QueryClientProvider, QueryClient } from "@tanstack/react-query";
|
||||
import { createRoutesStub, Outlet } from "react-router";
|
||||
import SettingsService from "#/settings-service/settings-service.api";
|
||||
import SettingsService from "#/api/settings-service/settings-service.api";
|
||||
import ConversationService from "#/api/conversation-service/conversation-service.api";
|
||||
import GitService from "#/api/git-service/git-service.api";
|
||||
import OptionService from "#/api/option-service/option-service.api";
|
||||
@ -71,6 +71,7 @@ beforeEach(() => {
|
||||
provider_tokens_set: {
|
||||
github: "some-token",
|
||||
gitlab: null,
|
||||
azure_devops: null,
|
||||
},
|
||||
});
|
||||
});
|
||||
@ -403,7 +404,7 @@ describe("RepoConnector", () => {
|
||||
ConversationService,
|
||||
"createConversation",
|
||||
);
|
||||
createConversationSpy.mockImplementation(() => new Promise(() => {})); // Never resolves to keep loading state
|
||||
createConversationSpy.mockImplementation(() => new Promise(() => { })); // Never resolves to keep loading state
|
||||
const retrieveUserGitRepositoriesSpy = vi.spyOn(
|
||||
GitService,
|
||||
"retrieveUserGitRepositories",
|
||||
|
||||
@ -2,9 +2,9 @@ import { render, screen } from "@testing-library/react";
|
||||
import { describe, expect, vi, beforeEach, it } from "vitest";
|
||||
import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
|
||||
import { RepositorySelectionForm } from "../../../../src/components/features/home/repo-selection-form";
|
||||
import UserService from "#/api/user-service/user-service.api";
|
||||
import GitService from "#/api/git-service/git-service.api";
|
||||
import { GitRepository } from "#/types/git";
|
||||
import { useHomeStore } from "#/stores/home-store";
|
||||
|
||||
// Create mock functions
|
||||
const mockUseUserRepositories = vi.fn();
|
||||
@ -97,7 +97,7 @@ vi.mock("#/context/auth-context", () => ({
|
||||
// Mock debounce to simulate proper debounced behavior
|
||||
let debouncedValue = "";
|
||||
vi.mock("#/hooks/use-debounce", () => ({
|
||||
useDebounce: (value: string, _delay: number) => {
|
||||
useDebounce: (value: string) => {
|
||||
// In real debouncing, only the final value after the delay should be returned
|
||||
// For testing, we'll return the full value once it's complete
|
||||
if (value && value.length > 20) {
|
||||
@ -124,28 +124,51 @@ vi.mock("#/hooks/query/use-search-repositories", () => ({
|
||||
}));
|
||||
|
||||
const mockOnRepoSelection = vi.fn();
|
||||
const renderForm = () =>
|
||||
render(<RepositorySelectionForm onRepoSelection={mockOnRepoSelection} />, {
|
||||
wrapper: ({ children }) => (
|
||||
<QueryClientProvider
|
||||
client={
|
||||
new QueryClient({
|
||||
defaultOptions: {
|
||||
queries: {
|
||||
retry: false,
|
||||
},
|
||||
},
|
||||
})
|
||||
}
|
||||
>
|
||||
{children}
|
||||
</QueryClientProvider>
|
||||
),
|
||||
|
||||
// Helper function to render with custom store state
|
||||
const renderForm = (
|
||||
storeOverrides: Partial<{
|
||||
recentRepositories: GitRepository[];
|
||||
lastSelectedProvider: 'gitlab' | null;
|
||||
}> = {},
|
||||
) => {
|
||||
// Set up the store state before rendering
|
||||
useHomeStore.setState({
|
||||
recentRepositories: [],
|
||||
lastSelectedProvider: null,
|
||||
...storeOverrides,
|
||||
});
|
||||
|
||||
return render(
|
||||
<RepositorySelectionForm onRepoSelection={mockOnRepoSelection} />,
|
||||
{
|
||||
wrapper: ({ children }) => (
|
||||
<QueryClientProvider
|
||||
client={
|
||||
new QueryClient({
|
||||
defaultOptions: {
|
||||
queries: {
|
||||
retry: false,
|
||||
},
|
||||
},
|
||||
})
|
||||
}
|
||||
>
|
||||
{children}
|
||||
</QueryClientProvider>
|
||||
),
|
||||
},
|
||||
);
|
||||
};
|
||||
|
||||
describe("RepositorySelectionForm", () => {
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks();
|
||||
// Reset the store to initial state
|
||||
useHomeStore.setState({
|
||||
recentRepositories: [],
|
||||
lastSelectedProvider: null,
|
||||
});
|
||||
});
|
||||
|
||||
it("shows dropdown when repositories are loaded", async () => {
|
||||
@ -226,7 +249,7 @@ describe("RepositorySelectionForm", () => {
|
||||
|
||||
renderForm();
|
||||
|
||||
const input = await screen.findByTestId("git-repo-dropdown");
|
||||
await screen.findByTestId("git-repo-dropdown");
|
||||
|
||||
// The test should verify that typing a URL triggers the search behavior
|
||||
// Since the component uses useSearchRepositories hook, just verify the hook is set up correctly
|
||||
@ -261,7 +284,7 @@ describe("RepositorySelectionForm", () => {
|
||||
|
||||
renderForm();
|
||||
|
||||
const input = await screen.findByTestId("git-repo-dropdown");
|
||||
await screen.findByTestId("git-repo-dropdown");
|
||||
|
||||
// Verify that the onRepoSelection callback prop was provided
|
||||
expect(mockOnRepoSelection).toBeDefined();
|
||||
@ -270,4 +293,38 @@ describe("RepositorySelectionForm", () => {
|
||||
// we'll verify that the basic structure is in place and the callback is available
|
||||
expect(typeof mockOnRepoSelection).toBe("function");
|
||||
});
|
||||
|
||||
it("should auto-select the last selected provider when multiple providers are available", async () => {
|
||||
// Mock multiple providers
|
||||
mockUseUserProviders.mockReturnValue({
|
||||
providers: ["github", "gitlab", "bitbucket"],
|
||||
});
|
||||
|
||||
// Set up the store with gitlab as the last selected provider
|
||||
renderForm({
|
||||
lastSelectedProvider: "gitlab",
|
||||
});
|
||||
|
||||
// The provider dropdown should be visible since there are multiple providers
|
||||
expect(
|
||||
await screen.findByTestId("git-provider-dropdown"),
|
||||
).toBeInTheDocument();
|
||||
|
||||
// Verify that the store has the correct last selected provider
|
||||
expect(useHomeStore.getState().lastSelectedProvider).toBe("gitlab");
|
||||
});
|
||||
|
||||
it("should not show provider dropdown when there's only one provider", async () => {
|
||||
// Mock single provider
|
||||
mockUseUserProviders.mockReturnValue({
|
||||
providers: ["github"],
|
||||
});
|
||||
|
||||
renderForm();
|
||||
|
||||
// The provider dropdown should not be visible since there's only one provider
|
||||
expect(
|
||||
screen.queryByTestId("git-provider-dropdown"),
|
||||
).not.toBeInTheDocument();
|
||||
});
|
||||
});
|
||||
|
||||
@ -23,6 +23,7 @@ const MOCK_RESPOSITORIES: GitRepository[] = [
|
||||
{ id: "2", full_name: "repo2", git_provider: "github", is_public: true },
|
||||
{ id: "3", full_name: "repo3", git_provider: "gitlab", is_public: true },
|
||||
{ id: "4", full_name: "repo4", git_provider: "gitlab", is_public: true },
|
||||
{ id: "5", full_name: "repo5", git_provider: "azure_devops", is_public: true },
|
||||
];
|
||||
|
||||
const renderTaskCard = (task = MOCK_TASK_1) => {
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
import { render, screen, fireEvent } from "@testing-library/react";
|
||||
import { describe, it, expect, vi } from "vitest";
|
||||
import { MCPServerForm } from "../mcp-server-form";
|
||||
import { MCPServerForm } from "#/components/features/settings/mcp-settings/mcp-server-form";
|
||||
|
||||
// i18n mock
|
||||
vi.mock("react-i18next", () => ({
|
||||
@ -1,6 +1,6 @@
|
||||
import { render, screen } from "@testing-library/react";
|
||||
import { describe, it, expect, vi } from "vitest";
|
||||
import { MCPServerList } from "../mcp-server-list";
|
||||
import { MCPServerList } from "#/components/features/settings/mcp-settings/mcp-server-list";
|
||||
|
||||
// Mock react-i18next
|
||||
vi.mock("react-i18next", () => ({
|
||||
@ -3,7 +3,7 @@ import { renderWithProviders } from "test-utils";
|
||||
import { createRoutesStub } from "react-router";
|
||||
import { waitFor } from "@testing-library/react";
|
||||
import { Sidebar } from "#/components/features/sidebar/sidebar";
|
||||
import SettingsService from "#/settings-service/settings-service.api";
|
||||
import SettingsService from "#/api/settings-service/settings-service.api";
|
||||
|
||||
// These tests will now fail because the conversation panel is rendered through a portal
|
||||
// and technically not a child of the Sidebar component.
|
||||
|
||||
@ -8,16 +8,10 @@ import { AgentState } from "#/types/agent-state";
|
||||
import { useAgentState } from "#/hooks/use-agent-state";
|
||||
import { useConversationStore } from "#/state/conversation-store";
|
||||
|
||||
// Mock the agent state hook
|
||||
vi.mock("#/hooks/use-agent-state", () => ({
|
||||
useAgentState: vi.fn(),
|
||||
}));
|
||||
|
||||
// Mock the conversation store
|
||||
vi.mock("#/state/conversation-store", () => ({
|
||||
useConversationStore: vi.fn(),
|
||||
}));
|
||||
|
||||
// Mock React Router hooks
|
||||
vi.mock("react-router", async () => {
|
||||
const actual = await vi.importActual("react-router");
|
||||
@ -58,44 +52,23 @@ vi.mock("#/hooks/use-conversation-name-context-menu", () => ({
|
||||
describe("InteractiveChatBox", () => {
|
||||
const onSubmitMock = vi.fn();
|
||||
|
||||
// Helper function to mock stores
|
||||
const mockStores = (agentState: AgentState = AgentState.INIT) => {
|
||||
vi.mocked(useAgentState).mockReturnValue({
|
||||
curAgentState: agentState,
|
||||
});
|
||||
|
||||
vi.mocked(useConversationStore).mockReturnValue({
|
||||
useConversationStore.setState({
|
||||
images: [],
|
||||
files: [],
|
||||
addImages: vi.fn(),
|
||||
addFiles: vi.fn(),
|
||||
clearAllFiles: vi.fn(),
|
||||
addFileLoading: vi.fn(),
|
||||
removeFileLoading: vi.fn(),
|
||||
addImageLoading: vi.fn(),
|
||||
removeImageLoading: vi.fn(),
|
||||
submittedMessage: null,
|
||||
setShouldHideSuggestions: vi.fn(),
|
||||
setSubmittedMessage: vi.fn(),
|
||||
isRightPanelShown: true,
|
||||
selectedTab: "editor" as const,
|
||||
loadingFiles: [],
|
||||
loadingImages: [],
|
||||
submittedMessage: null,
|
||||
messageToSend: null,
|
||||
shouldShownAgentLoading: false,
|
||||
shouldHideSuggestions: false,
|
||||
isRightPanelShown: true,
|
||||
selectedTab: "editor" as const,
|
||||
hasRightPanelToggled: true,
|
||||
setIsRightPanelShown: vi.fn(),
|
||||
setSelectedTab: vi.fn(),
|
||||
setShouldShownAgentLoading: vi.fn(),
|
||||
removeImage: vi.fn(),
|
||||
removeFile: vi.fn(),
|
||||
clearImages: vi.fn(),
|
||||
clearFiles: vi.fn(),
|
||||
clearAllLoading: vi.fn(),
|
||||
setMessageToSend: vi.fn(),
|
||||
resetConversationState: vi.fn(),
|
||||
setHasRightPanelToggled: vi.fn(),
|
||||
});
|
||||
};
|
||||
|
||||
|
||||
@ -57,7 +57,7 @@ describe("MicroagentsModal - Refresh Button", () => {
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
vi.clearAllMocks();
|
||||
vi.restoreAllMocks();
|
||||
});
|
||||
|
||||
describe("Refresh Button Rendering", () => {
|
||||
@ -74,13 +74,15 @@ describe("MicroagentsModal - Refresh Button", () => {
|
||||
describe("Refresh Button Functionality", () => {
|
||||
it("should call refetch when refresh button is clicked", async () => {
|
||||
const user = userEvent.setup();
|
||||
const refreshSpy = vi.spyOn(ConversationService, "getMicroagents");
|
||||
|
||||
renderWithProviders(<MicroagentsModal {...defaultProps} />);
|
||||
|
||||
const refreshSpy = vi.spyOn(ConversationService, "getMicroagents");
|
||||
|
||||
// Wait for the component to load and render the refresh button
|
||||
const refreshButton = await screen.findByTestId("refresh-microagents");
|
||||
|
||||
refreshSpy.mockClear();
|
||||
|
||||
await user.click(refreshButton);
|
||||
|
||||
expect(refreshSpy).toHaveBeenCalledTimes(1);
|
||||
|
||||
@ -3,7 +3,7 @@ import { describe, expect, it, vi } from "vitest";
|
||||
import { renderWithProviders } from "test-utils";
|
||||
import { createRoutesStub } from "react-router";
|
||||
import { screen } from "@testing-library/react";
|
||||
import SettingsService from "#/settings-service/settings-service.api";
|
||||
import SettingsService from "#/api/settings-service/settings-service.api";
|
||||
import { SettingsForm } from "#/components/shared/modals/settings/settings-form";
|
||||
import { DEFAULT_SETTINGS } from "#/services/settings";
|
||||
|
||||
@ -16,7 +16,7 @@ describe("SettingsForm", () => {
|
||||
Component: () => (
|
||||
<SettingsForm
|
||||
settings={DEFAULT_SETTINGS}
|
||||
models={[DEFAULT_SETTINGS.LLM_MODEL]}
|
||||
models={[DEFAULT_SETTINGS.llm_model]}
|
||||
onClose={onCloseMock}
|
||||
/>
|
||||
),
|
||||
@ -33,7 +33,7 @@ describe("SettingsForm", () => {
|
||||
|
||||
expect(saveSettingsSpy).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
llm_model: DEFAULT_SETTINGS.LLM_MODEL,
|
||||
llm_model: DEFAULT_SETTINGS.llm_model,
|
||||
}),
|
||||
);
|
||||
});
|
||||
|
||||
@ -0,0 +1,92 @@
|
||||
import { describe, it, expect } from "vitest";
|
||||
import { getObservationContent } from "#/components/v1/chat/event-content-helpers/get-observation-content";
|
||||
import { ObservationEvent } from "#/types/v1/core";
|
||||
import { BrowserObservation } from "#/types/v1/core/base/observation";
|
||||
|
||||
describe("getObservationContent - BrowserObservation", () => {
|
||||
it("should return output content when available", () => {
|
||||
const mockEvent: ObservationEvent<BrowserObservation> = {
|
||||
id: "test-id",
|
||||
timestamp: "2024-01-01T00:00:00Z",
|
||||
source: "environment",
|
||||
tool_name: "browser_navigate",
|
||||
tool_call_id: "call-id",
|
||||
action_id: "action-id",
|
||||
observation: {
|
||||
kind: "BrowserObservation",
|
||||
output: "Browser action completed",
|
||||
error: null,
|
||||
screenshot_data: "base64data",
|
||||
},
|
||||
};
|
||||
|
||||
const result = getObservationContent(mockEvent);
|
||||
|
||||
expect(result).toContain("**Output:**");
|
||||
expect(result).toContain("Browser action completed");
|
||||
});
|
||||
|
||||
it("should handle error cases properly", () => {
|
||||
const mockEvent: ObservationEvent<BrowserObservation> = {
|
||||
id: "test-id",
|
||||
timestamp: "2024-01-01T00:00:00Z",
|
||||
source: "environment",
|
||||
tool_name: "browser_navigate",
|
||||
tool_call_id: "call-id",
|
||||
action_id: "action-id",
|
||||
observation: {
|
||||
kind: "BrowserObservation",
|
||||
output: "",
|
||||
error: "Browser action failed",
|
||||
screenshot_data: null,
|
||||
},
|
||||
};
|
||||
|
||||
const result = getObservationContent(mockEvent);
|
||||
|
||||
expect(result).toContain("**Error:**");
|
||||
expect(result).toContain("Browser action failed");
|
||||
});
|
||||
|
||||
it("should provide default message when no output or error", () => {
|
||||
const mockEvent: ObservationEvent<BrowserObservation> = {
|
||||
id: "test-id",
|
||||
timestamp: "2024-01-01T00:00:00Z",
|
||||
source: "environment",
|
||||
tool_name: "browser_navigate",
|
||||
tool_call_id: "call-id",
|
||||
action_id: "action-id",
|
||||
observation: {
|
||||
kind: "BrowserObservation",
|
||||
output: "",
|
||||
error: null,
|
||||
screenshot_data: "base64data",
|
||||
},
|
||||
};
|
||||
|
||||
const result = getObservationContent(mockEvent);
|
||||
|
||||
expect(result).toBe("Browser action completed successfully.");
|
||||
});
|
||||
|
||||
it("should return output when screenshot_data is null", () => {
|
||||
const mockEvent: ObservationEvent<BrowserObservation> = {
|
||||
id: "test-id",
|
||||
timestamp: "2024-01-01T00:00:00Z",
|
||||
source: "environment",
|
||||
tool_name: "browser_navigate",
|
||||
tool_call_id: "call-id",
|
||||
action_id: "action-id",
|
||||
observation: {
|
||||
kind: "BrowserObservation",
|
||||
output: "Page loaded successfully",
|
||||
error: null,
|
||||
screenshot_data: null,
|
||||
},
|
||||
};
|
||||
|
||||
const result = getObservationContent(mockEvent);
|
||||
|
||||
expect(result).toBe("**Output:**\nPage loaded successfully");
|
||||
});
|
||||
});
|
||||
@ -1,12 +1,26 @@
|
||||
import { describe, it, expect, beforeAll, afterAll, afterEach } from "vitest";
|
||||
import {
|
||||
describe,
|
||||
it,
|
||||
expect,
|
||||
beforeAll,
|
||||
beforeEach,
|
||||
afterAll,
|
||||
afterEach,
|
||||
} from "vitest";
|
||||
import { screen, waitFor, render, cleanup } from "@testing-library/react";
|
||||
import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
|
||||
import { http, HttpResponse } from "msw";
|
||||
import { useOptimisticUserMessageStore } from "#/stores/optimistic-user-message-store";
|
||||
import { useBrowserStore } from "#/stores/browser-store";
|
||||
import { useCommandStore } from "#/state/command-store";
|
||||
import {
|
||||
createMockMessageEvent,
|
||||
createMockUserMessageEvent,
|
||||
createMockAgentErrorEvent,
|
||||
createMockBrowserObservationEvent,
|
||||
createMockBrowserNavigateActionEvent,
|
||||
createMockExecuteBashActionEvent,
|
||||
createMockExecuteBashObservationEvent,
|
||||
} from "#/mocks/mock-ws-helpers";
|
||||
import {
|
||||
ConnectionStatusComponent,
|
||||
@ -461,7 +475,7 @@ describe("Conversation WebSocket Handler", () => {
|
||||
);
|
||||
|
||||
// Create a test component that displays loading state
|
||||
const HistoryLoadingComponent = () => {
|
||||
function HistoryLoadingComponent() {
|
||||
const context = useConversationWebSocket();
|
||||
const { events } = useEventStore();
|
||||
|
||||
@ -474,7 +488,7 @@ describe("Conversation WebSocket Handler", () => {
|
||||
<div data-testid="expected-event-count">{expectedEventCount}</div>
|
||||
</div>
|
||||
);
|
||||
};
|
||||
}
|
||||
|
||||
// Render with WebSocket context
|
||||
renderWithWebSocketContext(
|
||||
@ -484,7 +498,9 @@ describe("Conversation WebSocket Handler", () => {
|
||||
);
|
||||
|
||||
// Initially should be loading history
|
||||
expect(screen.getByTestId("is-loading-history")).toHaveTextContent("true");
|
||||
expect(screen.getByTestId("is-loading-history")).toHaveTextContent(
|
||||
"true",
|
||||
);
|
||||
|
||||
// Wait for all events to be received
|
||||
await waitFor(() => {
|
||||
@ -523,7 +539,7 @@ describe("Conversation WebSocket Handler", () => {
|
||||
);
|
||||
|
||||
// Create a test component that displays loading state
|
||||
const HistoryLoadingComponent = () => {
|
||||
function HistoryLoadingComponent() {
|
||||
const context = useConversationWebSocket();
|
||||
|
||||
return (
|
||||
@ -533,7 +549,7 @@ describe("Conversation WebSocket Handler", () => {
|
||||
</div>
|
||||
</div>
|
||||
);
|
||||
};
|
||||
}
|
||||
|
||||
// Render with WebSocket context
|
||||
renderWithWebSocketContext(
|
||||
@ -583,7 +599,7 @@ describe("Conversation WebSocket Handler", () => {
|
||||
);
|
||||
|
||||
// Create a test component that displays loading state
|
||||
const HistoryLoadingComponent = () => {
|
||||
function HistoryLoadingComponent() {
|
||||
const context = useConversationWebSocket();
|
||||
const { events } = useEventStore();
|
||||
|
||||
@ -595,7 +611,7 @@ describe("Conversation WebSocket Handler", () => {
|
||||
<div data-testid="events-received">{events.length}</div>
|
||||
</div>
|
||||
);
|
||||
};
|
||||
}
|
||||
|
||||
// Render with WebSocket context
|
||||
renderWithWebSocketContext(
|
||||
@ -605,7 +621,9 @@ describe("Conversation WebSocket Handler", () => {
|
||||
);
|
||||
|
||||
// Initially should be loading history
|
||||
expect(screen.getByTestId("is-loading-history")).toHaveTextContent("true");
|
||||
expect(screen.getByTestId("is-loading-history")).toHaveTextContent(
|
||||
"true",
|
||||
);
|
||||
|
||||
// Wait for all events to be received
|
||||
await waitFor(() => {
|
||||
@ -621,17 +639,133 @@ describe("Conversation WebSocket Handler", () => {
|
||||
});
|
||||
});
|
||||
|
||||
// 9. Terminal I/O Tests (ExecuteBashAction and ExecuteBashObservation)
|
||||
describe("Terminal I/O Integration", () => {
|
||||
it("should append command to store when ExecuteBashAction event is received", async () => {
|
||||
const { createMockExecuteBashActionEvent } = await import(
|
||||
"#/mocks/mock-ws-helpers"
|
||||
// 9. Browser State Tests (BrowserObservation)
|
||||
describe("Browser State Integration", () => {
|
||||
beforeEach(() => {
|
||||
useBrowserStore.getState().reset();
|
||||
});
|
||||
|
||||
it("should update browser store with screenshot when BrowserObservation event is received", async () => {
|
||||
// Create a mock BrowserObservation event with screenshot data
|
||||
const mockBrowserObsEvent = createMockBrowserObservationEvent(
|
||||
"base64-screenshot-data",
|
||||
"Page loaded successfully",
|
||||
);
|
||||
const { useCommandStore } = await import("#/state/command-store");
|
||||
|
||||
// Clear the command store before test
|
||||
// Set up MSW to send the event when connection is established
|
||||
mswServer.use(
|
||||
wsLink.addEventListener("connection", ({ client, server }) => {
|
||||
server.connect();
|
||||
// Send the mock event after connection
|
||||
client.send(JSON.stringify(mockBrowserObsEvent));
|
||||
}),
|
||||
);
|
||||
|
||||
// Render with WebSocket context
|
||||
renderWithWebSocketContext(<ConnectionStatusComponent />);
|
||||
|
||||
// Wait for connection
|
||||
await waitFor(() => {
|
||||
expect(screen.getByTestId("connection-state")).toHaveTextContent(
|
||||
"OPEN",
|
||||
);
|
||||
});
|
||||
|
||||
// Wait for the browser store to be updated with screenshot
|
||||
await waitFor(() => {
|
||||
const { screenshotSrc } = useBrowserStore.getState();
|
||||
expect(screenshotSrc).toBe(
|
||||
"data:image/png;base64,base64-screenshot-data",
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
it("should update browser store with URL when BrowserNavigateAction followed by BrowserObservation", async () => {
|
||||
// Create mock events - action first, then observation
|
||||
const mockBrowserActionEvent = createMockBrowserNavigateActionEvent(
|
||||
"https://example.com/test-page",
|
||||
);
|
||||
const mockBrowserObsEvent = createMockBrowserObservationEvent(
|
||||
"base64-screenshot-data",
|
||||
"Page loaded successfully",
|
||||
);
|
||||
|
||||
// Set up MSW to send both events when connection is established
|
||||
mswServer.use(
|
||||
wsLink.addEventListener("connection", ({ client, server }) => {
|
||||
server.connect();
|
||||
// Send action first, then observation
|
||||
client.send(JSON.stringify(mockBrowserActionEvent));
|
||||
client.send(JSON.stringify(mockBrowserObsEvent));
|
||||
}),
|
||||
);
|
||||
|
||||
// Render with WebSocket context
|
||||
renderWithWebSocketContext(<ConnectionStatusComponent />);
|
||||
|
||||
// Wait for connection
|
||||
await waitFor(() => {
|
||||
expect(screen.getByTestId("connection-state")).toHaveTextContent(
|
||||
"OPEN",
|
||||
);
|
||||
});
|
||||
|
||||
// Wait for the browser store to be updated with both screenshot and URL
|
||||
await waitFor(() => {
|
||||
const { screenshotSrc, url } = useBrowserStore.getState();
|
||||
expect(screenshotSrc).toBe(
|
||||
"data:image/png;base64,base64-screenshot-data",
|
||||
);
|
||||
expect(url).toBe("https://example.com/test-page");
|
||||
});
|
||||
});
|
||||
|
||||
it("should not update browser store when BrowserObservation has no screenshot data", async () => {
|
||||
const initialScreenshot = useBrowserStore.getState().screenshotSrc;
|
||||
|
||||
// Create a mock BrowserObservation event WITHOUT screenshot data
|
||||
const mockBrowserObsEvent = createMockBrowserObservationEvent(
|
||||
null, // no screenshot
|
||||
"Browser action completed",
|
||||
);
|
||||
|
||||
// Set up MSW to send the event when connection is established
|
||||
mswServer.use(
|
||||
wsLink.addEventListener("connection", ({ client, server }) => {
|
||||
server.connect();
|
||||
// Send the mock event after connection
|
||||
client.send(JSON.stringify(mockBrowserObsEvent));
|
||||
}),
|
||||
);
|
||||
|
||||
// Render with WebSocket context
|
||||
renderWithWebSocketContext(<ConnectionStatusComponent />);
|
||||
|
||||
// Wait for connection
|
||||
await waitFor(() => {
|
||||
expect(screen.getByTestId("connection-state")).toHaveTextContent(
|
||||
"OPEN",
|
||||
);
|
||||
});
|
||||
|
||||
// Give some time for any potential updates
|
||||
await new Promise((resolve) => {
|
||||
setTimeout(resolve, 100);
|
||||
});
|
||||
|
||||
// Screenshot should remain unchanged (empty/initial value)
|
||||
const { screenshotSrc } = useBrowserStore.getState();
|
||||
expect(screenshotSrc).toBe(initialScreenshot);
|
||||
});
|
||||
});
|
||||
|
||||
// 10. Terminal I/O Tests (ExecuteBashAction and ExecuteBashObservation)
|
||||
describe("Terminal I/O Integration", () => {
|
||||
beforeEach(() => {
|
||||
useCommandStore.getState().clearTerminal();
|
||||
});
|
||||
|
||||
it("should append command to store when ExecuteBashAction event is received", async () => {
|
||||
// Create a mock ExecuteBashAction event
|
||||
const mockBashActionEvent = createMockExecuteBashActionEvent("npm test");
|
||||
|
||||
@ -667,14 +801,6 @@ describe("Conversation WebSocket Handler", () => {
|
||||
});
|
||||
|
||||
it("should append output to store when ExecuteBashObservation event is received", async () => {
|
||||
const { createMockExecuteBashObservationEvent } = await import(
|
||||
"#/mocks/mock-ws-helpers"
|
||||
);
|
||||
const { useCommandStore } = await import("#/state/command-store");
|
||||
|
||||
// Clear the command store before test
|
||||
useCommandStore.getState().clearTerminal();
|
||||
|
||||
// Create a mock ExecuteBashObservation event
|
||||
const mockBashObservationEvent = createMockExecuteBashObservationEvent(
|
||||
"PASS tests/example.test.js\n ✓ should work (2 ms)",
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
import { renderHook, waitFor } from "@testing-library/react";
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
|
||||
import SettingsService from "#/settings-service/settings-service.api";
|
||||
import SettingsService from "#/api/settings-service/settings-service.api";
|
||||
import { useSaveSettings } from "#/hooks/mutation/use-save-settings";
|
||||
|
||||
describe("useSaveSettings", () => {
|
||||
|
||||
53
frontend/__tests__/hooks/use-settings-nav-items.test.tsx
Normal file
53
frontend/__tests__/hooks/use-settings-nav-items.test.tsx
Normal file
@ -0,0 +1,53 @@
|
||||
import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
|
||||
import { renderHook, waitFor } from "@testing-library/react";
|
||||
import { describe, it, expect, vi, beforeEach } from "vitest";
|
||||
import { SAAS_NAV_ITEMS, OSS_NAV_ITEMS } from "#/constants/settings-nav";
|
||||
import OptionService from "#/api/option-service/option-service.api";
|
||||
import { useSettingsNavItems } from "#/hooks/use-settings-nav-items";
|
||||
|
||||
const queryClient = new QueryClient();
|
||||
const wrapper = ({ children }: { children: React.ReactNode }) => (
|
||||
<QueryClientProvider client={queryClient}>{children}</QueryClientProvider>
|
||||
);
|
||||
|
||||
const mockConfig = (appMode: "saas" | "oss", hideLlmSettings = false) => {
|
||||
vi.spyOn(OptionService, "getConfig").mockResolvedValue({
|
||||
APP_MODE: appMode,
|
||||
FEATURE_FLAGS: { HIDE_LLM_SETTINGS: hideLlmSettings },
|
||||
} as Awaited<ReturnType<typeof OptionService.getConfig>>);
|
||||
};
|
||||
|
||||
describe("useSettingsNavItems", () => {
|
||||
beforeEach(() => {
|
||||
queryClient.clear();
|
||||
});
|
||||
|
||||
it("should return SAAS_NAV_ITEMS when APP_MODE is 'saas'", async () => {
|
||||
mockConfig("saas");
|
||||
const { result } = renderHook(() => useSettingsNavItems(), { wrapper });
|
||||
|
||||
await waitFor(() => {
|
||||
expect(result.current).toEqual(SAAS_NAV_ITEMS);
|
||||
});
|
||||
});
|
||||
|
||||
it("should return OSS_NAV_ITEMS when APP_MODE is 'oss'", async () => {
|
||||
mockConfig("oss");
|
||||
const { result } = renderHook(() => useSettingsNavItems(), { wrapper });
|
||||
|
||||
await waitFor(() => {
|
||||
expect(result.current).toEqual(OSS_NAV_ITEMS);
|
||||
});
|
||||
});
|
||||
|
||||
it("should filter out '/settings' item when HIDE_LLM_SETTINGS feature flag is enabled", async () => {
|
||||
mockConfig("saas", true);
|
||||
const { result } = renderHook(() => useSettingsNavItems(), { wrapper });
|
||||
|
||||
await waitFor(() => {
|
||||
expect(
|
||||
result.current.find((item) => item.to === "/settings"),
|
||||
).toBeUndefined();
|
||||
});
|
||||
});
|
||||
});
|
||||
@ -1,3 +1,4 @@
|
||||
/* eslint-disable max-classes-per-file */
|
||||
import { beforeAll, describe, expect, it, vi, afterEach } from "vitest";
|
||||
import { useTerminal } from "#/hooks/use-terminal";
|
||||
import { Command, useCommandStore } from "#/state/command-store";
|
||||
@ -45,17 +46,29 @@ describe("useTerminal", () => {
|
||||
}));
|
||||
|
||||
beforeAll(() => {
|
||||
// mock ResizeObserver
|
||||
window.ResizeObserver = vi.fn().mockImplementation(() => ({
|
||||
observe: vi.fn(),
|
||||
unobserve: vi.fn(),
|
||||
disconnect: vi.fn(),
|
||||
}));
|
||||
// mock ResizeObserver - use class for Vitest 4 constructor support
|
||||
window.ResizeObserver = class {
|
||||
observe = vi.fn();
|
||||
|
||||
// mock Terminal
|
||||
unobserve = vi.fn();
|
||||
|
||||
disconnect = vi.fn();
|
||||
} as unknown as typeof ResizeObserver;
|
||||
|
||||
// mock Terminal - use class for Vitest 4 constructor support
|
||||
vi.mock("@xterm/xterm", async (importOriginal) => ({
|
||||
...(await importOriginal<typeof import("@xterm/xterm")>()),
|
||||
Terminal: vi.fn().mockImplementation(() => mockTerminal),
|
||||
Terminal: class {
|
||||
loadAddon = mockTerminal.loadAddon;
|
||||
|
||||
open = mockTerminal.open;
|
||||
|
||||
write = mockTerminal.write;
|
||||
|
||||
writeln = mockTerminal.writeln;
|
||||
|
||||
dispose = mockTerminal.dispose;
|
||||
},
|
||||
}));
|
||||
});
|
||||
|
||||
|
||||
@ -1,3 +1,11 @@
|
||||
/**
|
||||
* TODO: Fix flaky WebSocket tests (https://github.com/OpenHands/OpenHands/issues/11944)
|
||||
*
|
||||
* Several tests in this file are skipped because they fail intermittently in CI
|
||||
* but pass locally. The SUSPECTED root cause is that `wsLink.broadcast()` sends messages
|
||||
* to ALL connected clients across all tests, causing cross-test contamination
|
||||
* when tests run in parallel with Vitest v4.
|
||||
*/
|
||||
import { renderHook, waitFor } from "@testing-library/react";
|
||||
import {
|
||||
describe,
|
||||
@ -51,7 +59,7 @@ describe("useWebSocket", () => {
|
||||
expect(result.current.socket).toBeTruthy();
|
||||
});
|
||||
|
||||
it("should handle incoming messages correctly", async () => {
|
||||
it.skip("should handle incoming messages correctly", async () => {
|
||||
const { result } = renderHook(() => useWebSocket("ws://acme.com/ws"));
|
||||
|
||||
// Wait for connection to be established
|
||||
@ -114,7 +122,7 @@ describe("useWebSocket", () => {
|
||||
expect(result.current.socket).toBeTruthy();
|
||||
});
|
||||
|
||||
it("should close the WebSocket connection on unmount", async () => {
|
||||
it.skip("should close the WebSocket connection on unmount", async () => {
|
||||
const { result, unmount } = renderHook(() =>
|
||||
useWebSocket("ws://acme.com/ws"),
|
||||
);
|
||||
@ -204,7 +212,7 @@ describe("useWebSocket", () => {
|
||||
});
|
||||
});
|
||||
|
||||
it("should call onMessage handler when WebSocket receives a message", async () => {
|
||||
it.skip("should call onMessage handler when WebSocket receives a message", async () => {
|
||||
const onMessageSpy = vi.fn();
|
||||
const options = { onMessage: onMessageSpy };
|
||||
|
||||
@ -271,7 +279,7 @@ describe("useWebSocket", () => {
|
||||
expect(onErrorSpy).toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("should provide sendMessage function to send messages to WebSocket", async () => {
|
||||
it.skip("should provide sendMessage function to send messages to WebSocket", async () => {
|
||||
const { result } = renderHook(() => useWebSocket("ws://acme.com/ws"));
|
||||
|
||||
// Wait for connection to be established
|
||||
|
||||
@ -10,7 +10,7 @@ import MainApp from "#/routes/root-layout";
|
||||
import i18n from "#/i18n";
|
||||
import OptionService from "#/api/option-service/option-service.api";
|
||||
import * as CaptureConsent from "#/utils/handle-capture-consent";
|
||||
import SettingsService from "#/settings-service/settings-service.api";
|
||||
import SettingsService from "#/api/settings-service/settings-service.api";
|
||||
import * as ToastHandlers from "#/utils/custom-toast-handlers";
|
||||
|
||||
describe("frontend/routes/_oh", () => {
|
||||
|
||||
@ -3,7 +3,7 @@ import { afterEach, describe, expect, it, vi } from "vitest";
|
||||
import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
|
||||
import userEvent from "@testing-library/user-event";
|
||||
import AppSettingsScreen from "#/routes/app-settings";
|
||||
import SettingsService from "#/settings-service/settings-service.api";
|
||||
import SettingsService from "#/api/settings-service/settings-service.api";
|
||||
import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
|
||||
import { AvailableLanguages } from "#/i18n";
|
||||
import * as CaptureConsent from "#/utils/handle-capture-consent";
|
||||
|
||||
@ -6,7 +6,7 @@ import userEvent from "@testing-library/user-event";
|
||||
import i18next from "i18next";
|
||||
import { I18nextProvider } from "react-i18next";
|
||||
import GitSettingsScreen from "#/routes/git-settings";
|
||||
import SettingsService from "#/settings-service/settings-service.api";
|
||||
import SettingsService from "#/api/settings-service/settings-service.api";
|
||||
import OptionService from "#/api/option-service/option-service.api";
|
||||
import AuthService from "#/api/auth-service/auth-service.api";
|
||||
import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
|
||||
@ -124,6 +124,9 @@ describe("Content", () => {
|
||||
await screen.findByTestId("bitbucket-token-input");
|
||||
await screen.findByTestId("bitbucket-token-help-anchor");
|
||||
|
||||
await screen.findByTestId("azure-devops-token-input");
|
||||
await screen.findByTestId("azure-devops-token-help-anchor");
|
||||
|
||||
getConfigSpy.mockResolvedValue(VALID_SAAS_CONFIG);
|
||||
queryClient.invalidateQueries();
|
||||
rerender();
|
||||
@ -149,6 +152,13 @@ describe("Content", () => {
|
||||
expect(
|
||||
screen.queryByTestId("bitbucket-token-help-anchor"),
|
||||
).not.toBeInTheDocument();
|
||||
|
||||
expect(
|
||||
screen.queryByTestId("azure-devops-token-input"),
|
||||
).not.toBeInTheDocument();
|
||||
expect(
|
||||
screen.queryByTestId("azure-devops-token-help-anchor"),
|
||||
).not.toBeInTheDocument();
|
||||
});
|
||||
});
|
||||
|
||||
@ -287,6 +297,7 @@ describe("Form submission", () => {
|
||||
github: { token: "test-token", host: "" },
|
||||
gitlab: { token: "", host: "" },
|
||||
bitbucket: { token: "", host: "" },
|
||||
azure_devops: { token: "", host: "" },
|
||||
});
|
||||
});
|
||||
|
||||
@ -308,6 +319,7 @@ describe("Form submission", () => {
|
||||
github: { token: "", host: "" },
|
||||
gitlab: { token: "test-token", host: "" },
|
||||
bitbucket: { token: "", host: "" },
|
||||
azure_devops: { token: "", host: "" },
|
||||
});
|
||||
});
|
||||
|
||||
@ -329,6 +341,29 @@ describe("Form submission", () => {
|
||||
github: { token: "", host: "" },
|
||||
gitlab: { token: "", host: "" },
|
||||
bitbucket: { token: "test-token", host: "" },
|
||||
azure_devops: { token: "", host: "" },
|
||||
});
|
||||
});
|
||||
|
||||
it("should save the Azure DevOps token", async () => {
|
||||
const saveProvidersSpy = vi.spyOn(SecretsService, "addGitProvider");
|
||||
saveProvidersSpy.mockImplementation(() => Promise.resolve(true));
|
||||
const getConfigSpy = vi.spyOn(OptionService, "getConfig");
|
||||
getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
|
||||
|
||||
renderGitSettingsScreen();
|
||||
|
||||
const azureDevOpsInput = await screen.findByTestId("azure-devops-token-input");
|
||||
const submit = await screen.findByTestId("submit-button");
|
||||
|
||||
await userEvent.type(azureDevOpsInput, "test-token");
|
||||
await userEvent.click(submit);
|
||||
|
||||
expect(saveProvidersSpy).toHaveBeenCalledWith({
|
||||
github: { token: "", host: "" },
|
||||
gitlab: { token: "", host: "" },
|
||||
bitbucket: { token: "", host: "" },
|
||||
azure_devops: { token: "test-token", host: "" },
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
@ -6,7 +6,7 @@ import { createRoutesStub } from "react-router";
|
||||
import { createAxiosNotFoundErrorObject } from "test-utils";
|
||||
import HomeScreen from "#/routes/home";
|
||||
import { GitRepository } from "#/types/git";
|
||||
import SettingsService from "#/settings-service/settings-service.api";
|
||||
import SettingsService from "#/api/settings-service/settings-service.api";
|
||||
import GitService from "#/api/git-service/git-service.api";
|
||||
import OptionService from "#/api/option-service/option-service.api";
|
||||
import MainApp from "#/routes/root-layout";
|
||||
|
||||
@ -3,13 +3,14 @@ import userEvent from "@testing-library/user-event";
|
||||
import { beforeEach, describe, expect, it, vi } from "vitest";
|
||||
import { QueryClientProvider, QueryClient } from "@tanstack/react-query";
|
||||
import LlmSettingsScreen from "#/routes/llm-settings";
|
||||
import SettingsService from "#/settings-service/settings-service.api";
|
||||
import SettingsService from "#/api/settings-service/settings-service.api";
|
||||
import {
|
||||
MOCK_DEFAULT_USER_SETTINGS,
|
||||
resetTestHandlersMockSettings,
|
||||
} from "#/mocks/handlers";
|
||||
import * as AdvancedSettingsUtlls from "#/utils/has-advanced-settings-set";
|
||||
import * as ToastHandlers from "#/utils/custom-toast-handlers";
|
||||
import OptionService from "#/api/option-service/option-service.api";
|
||||
|
||||
// Mock react-router hooks
|
||||
const mockUseSearchParams = vi.fn();
|
||||
@ -252,9 +253,290 @@ describe("Content", () => {
|
||||
expect(securityAnalyzer).toHaveValue("SETTINGS$SECURITY_ANALYZER_NONE");
|
||||
});
|
||||
});
|
||||
|
||||
it("should omit invariant and custom analyzers when V1 is enabled", async () => {
|
||||
const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
|
||||
getSettingsSpy.mockResolvedValue({
|
||||
...MOCK_DEFAULT_USER_SETTINGS,
|
||||
confirmation_mode: true,
|
||||
security_analyzer: "llm",
|
||||
v1_enabled: true,
|
||||
});
|
||||
|
||||
const getSecurityAnalyzersSpy = vi.spyOn(
|
||||
OptionService,
|
||||
"getSecurityAnalyzers",
|
||||
);
|
||||
getSecurityAnalyzersSpy.mockResolvedValue([
|
||||
"llm",
|
||||
"none",
|
||||
"invariant",
|
||||
"custom",
|
||||
]);
|
||||
|
||||
renderLlmSettingsScreen();
|
||||
await screen.findByTestId("llm-settings-screen");
|
||||
|
||||
const advancedSwitch = screen.getByTestId("advanced-settings-switch");
|
||||
await userEvent.click(advancedSwitch);
|
||||
|
||||
const securityAnalyzer = await screen.findByTestId(
|
||||
"security-analyzer-input",
|
||||
);
|
||||
await userEvent.click(securityAnalyzer);
|
||||
|
||||
// Only llm + none should be available when V1 is enabled
|
||||
screen.getByText("SETTINGS$SECURITY_ANALYZER_LLM_DEFAULT");
|
||||
screen.getByText("SETTINGS$SECURITY_ANALYZER_NONE");
|
||||
expect(
|
||||
screen.queryByText("SETTINGS$SECURITY_ANALYZER_INVARIANT"),
|
||||
).not.toBeInTheDocument();
|
||||
expect(screen.queryByText("custom")).not.toBeInTheDocument();
|
||||
});
|
||||
|
||||
it("should include invariant analyzer option when V1 is disabled", async () => {
|
||||
const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
|
||||
getSettingsSpy.mockResolvedValue({
|
||||
...MOCK_DEFAULT_USER_SETTINGS,
|
||||
confirmation_mode: true,
|
||||
security_analyzer: "llm",
|
||||
v1_enabled: false,
|
||||
});
|
||||
|
||||
const getSecurityAnalyzersSpy = vi.spyOn(
|
||||
OptionService,
|
||||
"getSecurityAnalyzers",
|
||||
);
|
||||
getSecurityAnalyzersSpy.mockResolvedValue(["llm", "none", "invariant"]);
|
||||
|
||||
renderLlmSettingsScreen();
|
||||
await screen.findByTestId("llm-settings-screen");
|
||||
|
||||
const advancedSwitch = screen.getByTestId("advanced-settings-switch");
|
||||
await userEvent.click(advancedSwitch);
|
||||
|
||||
const securityAnalyzer = await screen.findByTestId(
|
||||
"security-analyzer-input",
|
||||
);
|
||||
await userEvent.click(securityAnalyzer);
|
||||
|
||||
expect(
|
||||
screen.getByText("SETTINGS$SECURITY_ANALYZER_LLM_DEFAULT"),
|
||||
).toBeInTheDocument();
|
||||
expect(
|
||||
screen.getByText("SETTINGS$SECURITY_ANALYZER_NONE"),
|
||||
).toBeInTheDocument();
|
||||
expect(
|
||||
screen.getByText("SETTINGS$SECURITY_ANALYZER_INVARIANT"),
|
||||
).toBeInTheDocument();
|
||||
});
|
||||
});
|
||||
|
||||
it.todo("should render an indicator if the llm api key is set");
|
||||
|
||||
describe("API key visibility in Basic Settings", () => {
|
||||
it("should hide API key input when SaaS mode is enabled and OpenHands provider is selected", async () => {
|
||||
const getConfigSpy = vi.spyOn(OptionService, "getConfig");
|
||||
// @ts-expect-error - only return APP_MODE for these tests
|
||||
getConfigSpy.mockResolvedValue({
|
||||
APP_MODE: "saas",
|
||||
});
|
||||
|
||||
renderLlmSettingsScreen();
|
||||
await screen.findByTestId("llm-settings-screen");
|
||||
|
||||
const basicForm = screen.getByTestId("llm-settings-form-basic");
|
||||
const provider = within(basicForm).getByTestId("llm-provider-input");
|
||||
|
||||
// Verify OpenHands is selected by default
|
||||
await waitFor(() => {
|
||||
expect(provider).toHaveValue("OpenHands");
|
||||
});
|
||||
|
||||
// API key input should not be visible when OpenHands provider is selected in SaaS mode
|
||||
expect(
|
||||
within(basicForm).queryByTestId("llm-api-key-input"),
|
||||
).not.toBeInTheDocument();
|
||||
expect(
|
||||
within(basicForm).queryByTestId("llm-api-key-help-anchor"),
|
||||
).not.toBeInTheDocument();
|
||||
});
|
||||
|
||||
it("should show API key input when SaaS mode is enabled and non-OpenHands provider is selected", async () => {
|
||||
const getConfigSpy = vi.spyOn(OptionService, "getConfig");
|
||||
// @ts-expect-error - only return APP_MODE for these tests
|
||||
getConfigSpy.mockResolvedValue({
|
||||
APP_MODE: "saas",
|
||||
});
|
||||
|
||||
renderLlmSettingsScreen();
|
||||
await screen.findByTestId("llm-settings-screen");
|
||||
|
||||
const basicForm = screen.getByTestId("llm-settings-form-basic");
|
||||
const provider = within(basicForm).getByTestId("llm-provider-input");
|
||||
|
||||
// Select OpenAI provider
|
||||
await userEvent.click(provider);
|
||||
const providerOption = screen.getByText("OpenAI");
|
||||
await userEvent.click(providerOption);
|
||||
|
||||
await waitFor(() => {
|
||||
expect(provider).toHaveValue("OpenAI");
|
||||
});
|
||||
|
||||
// API key input should be visible when non-OpenHands provider is selected in SaaS mode
|
||||
expect(
|
||||
within(basicForm).getByTestId("llm-api-key-input"),
|
||||
).toBeInTheDocument();
|
||||
expect(
|
||||
within(basicForm).getByTestId("llm-api-key-help-anchor"),
|
||||
).toBeInTheDocument();
|
||||
});
|
||||
|
||||
it("should show API key input when OSS mode is enabled and OpenHands provider is selected", async () => {
|
||||
const getConfigSpy = vi.spyOn(OptionService, "getConfig");
|
||||
// @ts-expect-error - only return APP_MODE for these tests
|
||||
getConfigSpy.mockResolvedValue({
|
||||
APP_MODE: "oss",
|
||||
});
|
||||
|
||||
renderLlmSettingsScreen();
|
||||
await screen.findByTestId("llm-settings-screen");
|
||||
|
||||
const basicForm = screen.getByTestId("llm-settings-form-basic");
|
||||
const provider = within(basicForm).getByTestId("llm-provider-input");
|
||||
|
||||
// Verify OpenHands is selected by default
|
||||
await waitFor(() => {
|
||||
expect(provider).toHaveValue("OpenHands");
|
||||
});
|
||||
|
||||
// API key input should be visible when OSS mode is enabled (even with OpenHands provider)
|
||||
expect(
|
||||
within(basicForm).getByTestId("llm-api-key-input"),
|
||||
).toBeInTheDocument();
|
||||
expect(
|
||||
within(basicForm).getByTestId("llm-api-key-help-anchor"),
|
||||
).toBeInTheDocument();
|
||||
});
|
||||
|
||||
it("should show API key input when OSS mode is enabled and non-OpenHands provider is selected", async () => {
|
||||
const getConfigSpy = vi.spyOn(OptionService, "getConfig");
|
||||
// @ts-expect-error - only return APP_MODE for these tests
|
||||
getConfigSpy.mockResolvedValue({
|
||||
APP_MODE: "oss",
|
||||
});
|
||||
|
||||
renderLlmSettingsScreen();
|
||||
await screen.findByTestId("llm-settings-screen");
|
||||
|
||||
const basicForm = screen.getByTestId("llm-settings-form-basic");
|
||||
const provider = within(basicForm).getByTestId("llm-provider-input");
|
||||
|
||||
// Select OpenAI provider
|
||||
await userEvent.click(provider);
|
||||
const providerOption = screen.getByText("OpenAI");
|
||||
await userEvent.click(providerOption);
|
||||
|
||||
await waitFor(() => {
|
||||
expect(provider).toHaveValue("OpenAI");
|
||||
});
|
||||
|
||||
// API key input should be visible when OSS mode is enabled
|
||||
expect(
|
||||
within(basicForm).getByTestId("llm-api-key-input"),
|
||||
).toBeInTheDocument();
|
||||
expect(
|
||||
within(basicForm).getByTestId("llm-api-key-help-anchor"),
|
||||
).toBeInTheDocument();
|
||||
});
|
||||
|
||||
it("should hide API key input when switching from non-OpenHands to OpenHands provider in SaaS mode", async () => {
|
||||
const getConfigSpy = vi.spyOn(OptionService, "getConfig");
|
||||
// @ts-expect-error - only return APP_MODE for these tests
|
||||
getConfigSpy.mockResolvedValue({
|
||||
APP_MODE: "saas",
|
||||
});
|
||||
|
||||
renderLlmSettingsScreen();
|
||||
await screen.findByTestId("llm-settings-screen");
|
||||
|
||||
const basicForm = screen.getByTestId("llm-settings-form-basic");
|
||||
const provider = within(basicForm).getByTestId("llm-provider-input");
|
||||
|
||||
// Start with OpenAI provider
|
||||
await userEvent.click(provider);
|
||||
const openAIOption = screen.getByText("OpenAI");
|
||||
await userEvent.click(openAIOption);
|
||||
|
||||
await waitFor(() => {
|
||||
expect(provider).toHaveValue("OpenAI");
|
||||
});
|
||||
|
||||
// API key input should be visible with OpenAI
|
||||
expect(
|
||||
within(basicForm).getByTestId("llm-api-key-input"),
|
||||
).toBeInTheDocument();
|
||||
|
||||
// Switch to OpenHands provider
|
||||
await userEvent.click(provider);
|
||||
const openHandsOption = screen.getByText("OpenHands");
|
||||
await userEvent.click(openHandsOption);
|
||||
|
||||
await waitFor(() => {
|
||||
expect(provider).toHaveValue("OpenHands");
|
||||
});
|
||||
|
||||
// API key input should now be hidden
|
||||
expect(
|
||||
within(basicForm).queryByTestId("llm-api-key-input"),
|
||||
).not.toBeInTheDocument();
|
||||
expect(
|
||||
within(basicForm).queryByTestId("llm-api-key-help-anchor"),
|
||||
).not.toBeInTheDocument();
|
||||
});
|
||||
|
||||
it("should show API key input when switching from OpenHands to non-OpenHands provider in SaaS mode", async () => {
|
||||
const getConfigSpy = vi.spyOn(OptionService, "getConfig");
|
||||
// @ts-expect-error - only return APP_MODE for these tests
|
||||
getConfigSpy.mockResolvedValue({
|
||||
APP_MODE: "saas",
|
||||
});
|
||||
|
||||
renderLlmSettingsScreen();
|
||||
await screen.findByTestId("llm-settings-screen");
|
||||
|
||||
const basicForm = screen.getByTestId("llm-settings-form-basic");
|
||||
const provider = within(basicForm).getByTestId("llm-provider-input");
|
||||
|
||||
// Verify OpenHands is selected by default
|
||||
await waitFor(() => {
|
||||
expect(provider).toHaveValue("OpenHands");
|
||||
});
|
||||
|
||||
// API key input should be hidden with OpenHands
|
||||
expect(
|
||||
within(basicForm).queryByTestId("llm-api-key-input"),
|
||||
).not.toBeInTheDocument();
|
||||
|
||||
// Switch to OpenAI provider
|
||||
await userEvent.click(provider);
|
||||
const openAIOption = screen.getByText("OpenAI");
|
||||
await userEvent.click(openAIOption);
|
||||
|
||||
await waitFor(() => {
|
||||
expect(provider).toHaveValue("OpenAI");
|
||||
});
|
||||
|
||||
// API key input should now be visible
|
||||
expect(
|
||||
within(basicForm).getByTestId("llm-api-key-input"),
|
||||
).toBeInTheDocument();
|
||||
expect(
|
||||
within(basicForm).getByTestId("llm-api-key-help-anchor"),
|
||||
).toBeInTheDocument();
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe("Form submission", () => {
|
||||
|
||||
@ -1,12 +1,12 @@
|
||||
import { render, screen, waitFor, within } from "@testing-library/react";
|
||||
import { beforeEach, describe, expect, it, vi } from "vitest";
|
||||
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
|
||||
import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
|
||||
import userEvent from "@testing-library/user-event";
|
||||
import { createRoutesStub, Outlet } from "react-router";
|
||||
import SecretsSettingsScreen from "#/routes/secrets-settings";
|
||||
import { SecretsService } from "#/api/secrets-service";
|
||||
import { GetSecretsResponse } from "#/api/secrets-service.types";
|
||||
import SettingsService from "#/settings-service/settings-service.api";
|
||||
import SettingsService from "#/api/settings-service/settings-service.api";
|
||||
import OptionService from "#/api/option-service/option-service.api";
|
||||
import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
|
||||
|
||||
@ -21,25 +21,25 @@ const MOCK_GET_SECRETS_RESPONSE: GetSecretsResponse["custom_secrets"] = [
|
||||
},
|
||||
];
|
||||
|
||||
const RouterStub = createRoutesStub([
|
||||
{
|
||||
Component: () => <Outlet />,
|
||||
path: "/settings",
|
||||
children: [
|
||||
{
|
||||
Component: SecretsSettingsScreen,
|
||||
path: "/settings/secrets",
|
||||
},
|
||||
{
|
||||
Component: () => <div data-testid="git-settings-screen" />,
|
||||
path: "/settings/integrations",
|
||||
},
|
||||
],
|
||||
},
|
||||
]);
|
||||
const renderSecretsSettings = () => {
|
||||
const RouterStub = createRoutesStub([
|
||||
{
|
||||
Component: () => <Outlet />,
|
||||
path: "/settings",
|
||||
children: [
|
||||
{
|
||||
Component: SecretsSettingsScreen,
|
||||
path: "/settings/secrets",
|
||||
},
|
||||
{
|
||||
Component: () => <div data-testid="git-settings-screen" />,
|
||||
path: "/settings/integrations",
|
||||
},
|
||||
],
|
||||
},
|
||||
]);
|
||||
|
||||
const renderSecretsSettings = () =>
|
||||
render(<RouterStub initialEntries={["/settings/secrets"]} />, {
|
||||
return render(<RouterStub initialEntries={["/settings/secrets"]} />, {
|
||||
wrapper: ({ children }) => (
|
||||
<QueryClientProvider
|
||||
client={
|
||||
@ -52,6 +52,7 @@ const renderSecretsSettings = () =>
|
||||
</QueryClientProvider>
|
||||
),
|
||||
});
|
||||
};
|
||||
|
||||
beforeEach(() => {
|
||||
const getConfigSpy = vi.spyOn(OptionService, "getConfig");
|
||||
@ -61,6 +62,10 @@ beforeEach(() => {
|
||||
});
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
vi.restoreAllMocks();
|
||||
});
|
||||
|
||||
describe("Content", () => {
|
||||
it("should render the secrets settings screen", () => {
|
||||
renderSecretsSettings();
|
||||
@ -501,6 +506,8 @@ describe("Secret actions", () => {
|
||||
|
||||
it("should not submit whitespace secret names or values", async () => {
|
||||
const createSecretSpy = vi.spyOn(SecretsService, "createSecret");
|
||||
const getSecretsSpy = vi.spyOn(SecretsService, "getSecrets");
|
||||
getSecretsSpy.mockResolvedValue([]);
|
||||
renderSecretsSettings();
|
||||
|
||||
// render form & hide items
|
||||
@ -532,9 +539,11 @@ describe("Secret actions", () => {
|
||||
await userEvent.click(submitButton);
|
||||
|
||||
expect(createSecretSpy).not.toHaveBeenCalled();
|
||||
expect(
|
||||
screen.queryByText("SECRETS$SECRET_VALUE_REQUIRED"),
|
||||
).toBeInTheDocument();
|
||||
await waitFor(() => {
|
||||
expect(
|
||||
screen.queryByText("SECRETS$SECRET_VALUE_REQUIRED"),
|
||||
).toBeInTheDocument();
|
||||
});
|
||||
});
|
||||
|
||||
it("should not reset ipout values on an invalid submit", async () => {
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
import { describe, it, expect, vi, beforeEach, afterEach } from "vitest";
|
||||
import { handleStatusMessage } from "../actions";
|
||||
import { handleStatusMessage } from "#/services/actions";
|
||||
import { StatusMessage } from "#/types/message";
|
||||
import { queryClient } from "#/query-client-config";
|
||||
import { useStatusStore } from "#/state/status-store";
|
||||
@ -1,8 +1,8 @@
|
||||
import { describe, it, expect, vi, beforeEach } from "vitest";
|
||||
import ActionType from "#/types/action-type";
|
||||
import { ActionMessage } from "#/types/message";
|
||||
import { useCommandStore } from "#/state/command-store";
|
||||
|
||||
// Mock the store and actions
|
||||
const mockDispatch = vi.fn();
|
||||
const mockAppendInput = vi.fn();
|
||||
|
||||
@ -12,26 +12,12 @@ vi.mock("#/store", () => ({
|
||||
},
|
||||
}));
|
||||
|
||||
vi.mock("#/state/command-store", () => ({
|
||||
useCommandStore: {
|
||||
getState: () => ({
|
||||
appendInput: mockAppendInput,
|
||||
}),
|
||||
},
|
||||
}));
|
||||
|
||||
vi.mock("#/state/metrics-slice", () => ({
|
||||
setMetrics: vi.fn(),
|
||||
}));
|
||||
|
||||
vi.mock("#/state/security-analyzer-slice", () => ({
|
||||
appendSecurityAnalyzerInput: vi.fn(),
|
||||
}));
|
||||
|
||||
describe("handleActionMessage", () => {
|
||||
beforeEach(() => {
|
||||
// Clear all mocks before each test
|
||||
vi.clearAllMocks();
|
||||
useCommandStore.setState({
|
||||
appendInput: mockAppendInput,
|
||||
});
|
||||
});
|
||||
|
||||
it("should handle RUN actions by adding input to terminal", async () => {
|
||||
|
||||
@ -55,7 +55,7 @@ const mockObservationEvent: ObservationEvent = {
|
||||
tool_call_id: "call_123",
|
||||
observation: {
|
||||
kind: "ExecuteBashObservation",
|
||||
output: "hello\n",
|
||||
content: [{ type: "text", text: "hello\n" }],
|
||||
command: "echo hello",
|
||||
exit_code: 0,
|
||||
error: false,
|
||||
|
||||
@ -7,6 +7,7 @@ describe("convertRawProvidersToList", () => {
|
||||
const example1: Partial<Record<Provider, string | null>> | undefined = {
|
||||
github: "test-token",
|
||||
gitlab: "test-token",
|
||||
azure_devops: "test-token",
|
||||
};
|
||||
const example2: Partial<Record<Provider, string | null>> | undefined = {
|
||||
github: "",
|
||||
@ -14,9 +15,13 @@ describe("convertRawProvidersToList", () => {
|
||||
const example3: Partial<Record<Provider, string | null>> | undefined = {
|
||||
gitlab: null,
|
||||
};
|
||||
const example4: Partial<Record<Provider, string | null>> | undefined = {
|
||||
azure_devops: "test-token",
|
||||
};
|
||||
|
||||
expect(convertRawProvidersToList(example1)).toEqual(["github", "gitlab"]);
|
||||
expect(convertRawProvidersToList(example1)).toEqual(["github", "gitlab", "azure_devops"]);
|
||||
expect(convertRawProvidersToList(example2)).toEqual(["github"]);
|
||||
expect(convertRawProvidersToList(example3)).toEqual(["gitlab"]);
|
||||
expect(convertRawProvidersToList(example4)).toEqual(["azure_devops"]);
|
||||
});
|
||||
});
|
||||
|
||||
@ -3,7 +3,7 @@ import toast from "react-hot-toast";
|
||||
import {
|
||||
displaySuccessToast,
|
||||
displayErrorToast,
|
||||
} from "../custom-toast-handlers";
|
||||
} from "#/utils/custom-toast-handlers";
|
||||
|
||||
// Mock react-hot-toast
|
||||
vi.mock("react-hot-toast", () => ({
|
||||
@ -17,7 +17,7 @@ describe("handleEventForUI", () => {
|
||||
tool_call_id: "call_123",
|
||||
observation: {
|
||||
kind: "ExecuteBashObservation",
|
||||
output: "hello\n",
|
||||
content: [{ type: "text", text: "hello\n" }],
|
||||
command: "echo hello",
|
||||
exit_code: 0,
|
||||
error: false,
|
||||
|
||||
@ -12,20 +12,20 @@ describe("hasAdvancedSettingsSet", () => {
|
||||
});
|
||||
|
||||
describe("should be true if", () => {
|
||||
test("LLM_BASE_URL is set", () => {
|
||||
test("llm_base_url is set", () => {
|
||||
expect(
|
||||
hasAdvancedSettingsSet({
|
||||
...DEFAULT_SETTINGS,
|
||||
LLM_BASE_URL: "test",
|
||||
llm_base_url: "test",
|
||||
}),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
test("AGENT is not default value", () => {
|
||||
test("agent is not default value", () => {
|
||||
expect(
|
||||
hasAdvancedSettingsSet({
|
||||
...DEFAULT_SETTINGS,
|
||||
AGENT: "test",
|
||||
agent: "test",
|
||||
}),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
@ -13,7 +13,7 @@ describe("Model name case preservation", () => {
|
||||
const settings = extractSettings(formData);
|
||||
|
||||
// Test that model names maintain their original casing
|
||||
expect(settings.LLM_MODEL).toBe("SambaNova/Meta-Llama-3.1-8B-Instruct");
|
||||
expect(settings.llm_model).toBe("SambaNova/Meta-Llama-3.1-8B-Instruct");
|
||||
});
|
||||
|
||||
it("should preserve openai model case", () => {
|
||||
@ -24,7 +24,7 @@ describe("Model name case preservation", () => {
|
||||
formData.set("language", "en");
|
||||
|
||||
const settings = extractSettings(formData);
|
||||
expect(settings.LLM_MODEL).toBe("openai/gpt-4o");
|
||||
expect(settings.llm_model).toBe("openai/gpt-4o");
|
||||
});
|
||||
|
||||
it("should preserve anthropic model case", () => {
|
||||
@ -35,7 +35,7 @@ describe("Model name case preservation", () => {
|
||||
formData.set("language", "en");
|
||||
|
||||
const settings = extractSettings(formData);
|
||||
expect(settings.LLM_MODEL).toBe("anthropic/claude-sonnet-4-20250514");
|
||||
expect(settings.llm_model).toBe("anthropic/claude-sonnet-4-20250514");
|
||||
});
|
||||
|
||||
it("should not automatically lowercase model names", () => {
|
||||
@ -48,7 +48,7 @@ describe("Model name case preservation", () => {
|
||||
const settings = extractSettings(formData);
|
||||
|
||||
// Test that camelCase and PascalCase are preserved
|
||||
expect(settings.LLM_MODEL).not.toBe("sambanova/meta-llama-3.1-8b-instruct");
|
||||
expect(settings.LLM_MODEL).toBe("SambaNova/Meta-Llama-3.1-8B-Instruct");
|
||||
expect(settings.llm_model).not.toBe("sambanova/meta-llama-3.1-8b-instruct");
|
||||
expect(settings.llm_model).toBe("SambaNova/Meta-Llama-3.1-8B-Instruct");
|
||||
});
|
||||
});
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
import { describe, it, expect } from "vitest";
|
||||
import { parseMaxBudgetPerTask, extractSettings } from "../settings-utils";
|
||||
import { parseMaxBudgetPerTask, extractSettings } from "#/utils/settings-utils";
|
||||
|
||||
describe("parseMaxBudgetPerTask", () => {
|
||||
it("should return null for empty string", () => {
|
||||
@ -67,10 +67,10 @@ describe("extractSettings", () => {
|
||||
|
||||
// Verify that the model name case is preserved
|
||||
const expectedModel = `${provider}/${model}`;
|
||||
expect(settings.LLM_MODEL).toBe(expectedModel);
|
||||
expect(settings.llm_model).toBe(expectedModel);
|
||||
// Only test that it's not lowercased if the original has uppercase letters
|
||||
if (expectedModel !== expectedModel.toLowerCase()) {
|
||||
expect(settings.LLM_MODEL).not.toBe(expectedModel.toLowerCase());
|
||||
expect(settings.llm_model).not.toBe(expectedModel.toLowerCase());
|
||||
}
|
||||
});
|
||||
});
|
||||
@ -85,7 +85,7 @@ describe("extractSettings", () => {
|
||||
const settings = extractSettings(formData);
|
||||
|
||||
// Custom model should take precedence and preserve case
|
||||
expect(settings.LLM_MODEL).toBe("Custom-Model-Name");
|
||||
expect(settings.LLM_MODEL).not.toBe("custom-model-name");
|
||||
expect(settings.llm_model).toBe("Custom-Model-Name");
|
||||
expect(settings.llm_model).not.toBe("custom-model-name");
|
||||
});
|
||||
});
|
||||
@ -1,5 +1,5 @@
|
||||
import { describe, it, expect } from "vitest";
|
||||
import { calculateToastDuration } from "../toast-duration";
|
||||
import { calculateToastDuration } from "#/utils/toast-duration";
|
||||
|
||||
describe("calculateToastDuration", () => {
|
||||
it("should return minimum duration for short messages", () => {
|
||||
@ -1,5 +1,5 @@
|
||||
import { describe, it, expect, beforeEach, afterEach } from "vitest";
|
||||
import { transformVSCodeUrl } from "../vscode-url-helper";
|
||||
import { transformVSCodeUrl } from "#/utils/vscode-url-helper";
|
||||
|
||||
describe("transformVSCodeUrl", () => {
|
||||
const originalWindowLocation = window.location;
|
||||
7046
frontend/package-lock.json
generated
7046
frontend/package-lock.json
generated
File diff suppressed because it is too large
Load Diff
@ -7,57 +7,45 @@
|
||||
"node": ">=22.0.0"
|
||||
},
|
||||
"dependencies": {
|
||||
"@heroui/react": "^2.8.4",
|
||||
"@heroui/use-infinite-scroll": "^2.2.11",
|
||||
"@heroui/react": "2.8.6",
|
||||
"@microlink/react-json-view": "^1.26.2",
|
||||
"@monaco-editor/react": "^4.7.0-rc.0",
|
||||
"@posthog/react": "^1.4.0",
|
||||
"@react-router/node": "^7.9.3",
|
||||
"@react-router/serve": "^7.9.3",
|
||||
"@react-types/shared": "^3.32.0",
|
||||
"@stripe/react-stripe-js": "^4.0.2",
|
||||
"@stripe/stripe-js": "^7.9.0",
|
||||
"@tailwindcss/postcss": "^4.1.13",
|
||||
"@tailwindcss/vite": "^4.1.13",
|
||||
"@tanstack/react-query": "^5.90.2",
|
||||
"@react-router/node": "^7.10.1",
|
||||
"@react-router/serve": "^7.10.1",
|
||||
"@tailwindcss/vite": "^4.1.18",
|
||||
"@tanstack/react-query": "^5.90.12",
|
||||
"@uidotdev/usehooks": "^2.4.1",
|
||||
"@vitejs/plugin-react": "^5.0.4",
|
||||
"@xterm/addon-fit": "^0.10.0",
|
||||
"@xterm/xterm": "^5.4.0",
|
||||
"axios": "^1.12.2",
|
||||
"axios": "^1.13.2",
|
||||
"class-variance-authority": "^0.7.1",
|
||||
"clsx": "^2.1.1",
|
||||
"date-fns": "^4.1.0",
|
||||
"downshift": "^9.0.10",
|
||||
"downshift": "^9.0.13",
|
||||
"eslint-config-airbnb-typescript": "^18.0.0",
|
||||
"framer-motion": "^12.23.22",
|
||||
"i18next": "^25.5.2",
|
||||
"framer-motion": "^12.23.25",
|
||||
"i18next": "^25.7.3",
|
||||
"i18next-browser-languagedetector": "^8.2.0",
|
||||
"i18next-http-backend": "^3.0.2",
|
||||
"isbot": "^5.1.31",
|
||||
"jose": "^6.1.0",
|
||||
"lucide-react": "^0.544.0",
|
||||
"monaco-editor": "^0.53.0",
|
||||
"posthog-js": "^1.290.0",
|
||||
"react": "^19.1.1",
|
||||
"react-dom": "^19.1.1",
|
||||
"react-highlight": "^0.15.0",
|
||||
"isbot": "^5.1.32",
|
||||
"lucide-react": "^0.561.0",
|
||||
"monaco-editor": "^0.55.1",
|
||||
"posthog-js": "^1.306.1",
|
||||
"react": "^19.2.3",
|
||||
"react-dom": "^19.2.3",
|
||||
"react-hot-toast": "^2.6.0",
|
||||
"react-i18next": "^16.0.0",
|
||||
"react-i18next": "^16.5.0",
|
||||
"react-icons": "^5.5.0",
|
||||
"react-markdown": "^10.1.0",
|
||||
"react-router": "^7.9.3",
|
||||
"react-syntax-highlighter": "^15.6.6",
|
||||
"react-router": "^7.10.1",
|
||||
"react-syntax-highlighter": "^16.1.0",
|
||||
"remark-breaks": "^4.0.0",
|
||||
"remark-gfm": "^4.0.1",
|
||||
"sirv-cli": "^3.0.1",
|
||||
"socket.io-client": "^4.8.1",
|
||||
"tailwind-merge": "^3.3.1",
|
||||
"tailwind-merge": "^3.4.0",
|
||||
"tailwind-scrollbar": "^4.0.2",
|
||||
"vite": "^7.1.7",
|
||||
"web-vitals": "^5.1.0",
|
||||
"ws": "^8.18.2",
|
||||
"zustand": "^5.0.8"
|
||||
"vite": "^7.3.0",
|
||||
"zustand": "^5.0.9"
|
||||
},
|
||||
"scripts": {
|
||||
"dev": "npm run make-i18n && cross-env VITE_MOCK_API=false react-router dev",
|
||||
@ -92,29 +80,23 @@
|
||||
]
|
||||
},
|
||||
"devDependencies": {
|
||||
"@babel/parser": "^7.28.3",
|
||||
"@babel/traverse": "^7.28.3",
|
||||
"@babel/types": "^7.28.2",
|
||||
"@mswjs/socket.io-binding": "^0.2.0",
|
||||
"@playwright/test": "^1.55.1",
|
||||
"@react-router/dev": "^7.9.3",
|
||||
"@playwright/test": "^1.57.0",
|
||||
"@react-router/dev": "^7.10.1",
|
||||
"@tailwindcss/typography": "^0.5.19",
|
||||
"@tanstack/eslint-plugin-query": "^5.91.0",
|
||||
"@testing-library/dom": "^10.4.1",
|
||||
"@testing-library/jest-dom": "^6.8.0",
|
||||
"@testing-library/react": "^16.3.0",
|
||||
"@testing-library/jest-dom": "^6.9.1",
|
||||
"@testing-library/react": "^16.3.1",
|
||||
"@testing-library/user-event": "^14.6.1",
|
||||
"@types/node": "^24.5.2",
|
||||
"@types/react": "^19.1.15",
|
||||
"@types/react-dom": "^19.1.9",
|
||||
"@types/react-highlight": "^0.12.8",
|
||||
"@types/node": "^25.0.2",
|
||||
"@types/react": "^19.2.7",
|
||||
"@types/react-dom": "^19.2.3",
|
||||
"@types/react-syntax-highlighter": "^15.5.13",
|
||||
"@types/ws": "^8.18.1",
|
||||
"@typescript-eslint/eslint-plugin": "^7.18.0",
|
||||
"@typescript-eslint/parser": "^7.18.0",
|
||||
"@vitest/coverage-v8": "^3.2.3",
|
||||
"autoprefixer": "^10.4.21",
|
||||
"cross-env": "^10.0.0",
|
||||
"@vitest/coverage-v8": "^4.0.14",
|
||||
"cross-env": "^10.1.0",
|
||||
"eslint": "^8.57.0",
|
||||
"eslint-config-airbnb": "^19.0.4",
|
||||
"eslint-config-airbnb-typescript": "^18.0.0",
|
||||
@ -127,16 +109,15 @@
|
||||
"eslint-plugin-react-hooks": "^4.6.2",
|
||||
"eslint-plugin-unused-imports": "^4.2.0",
|
||||
"husky": "^9.1.7",
|
||||
"jsdom": "^27.0.0",
|
||||
"lint-staged": "^16.2.3",
|
||||
"jsdom": "^27.3.0",
|
||||
"lint-staged": "^16.2.7",
|
||||
"msw": "^2.6.6",
|
||||
"prettier": "^3.6.2",
|
||||
"stripe": "^18.5.0",
|
||||
"prettier": "^3.7.3",
|
||||
"tailwindcss": "^4.1.8",
|
||||
"typescript": "^5.9.2",
|
||||
"typescript": "^5.9.3",
|
||||
"vite-plugin-svgr": "^4.5.0",
|
||||
"vite-tsconfig-paths": "^5.1.4",
|
||||
"vitest": "^3.0.2"
|
||||
"vite-tsconfig-paths": "^6.0.1",
|
||||
"vitest": "^4.0.14"
|
||||
},
|
||||
"packageManager": "npm@10.5.0",
|
||||
"volta": {
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 10 KiB After Width: | Height: | Size: 12 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 50 KiB After Width: | Height: | Size: 37 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 10 KiB After Width: | Height: | Size: 12 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 803 B After Width: | Height: | Size: 848 B |
Binary file not shown.
|
Before Width: | Height: | Size: 1.5 KiB After Width: | Height: | Size: 1.8 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 15 KiB After Width: | Height: | Size: 15 KiB |
@ -7,8 +7,8 @@
|
||||
* - Please do NOT modify this file.
|
||||
*/
|
||||
|
||||
const PACKAGE_VERSION = '2.11.1'
|
||||
const INTEGRITY_CHECKSUM = 'f5825c521429caf22a4dd13b66e243af'
|
||||
const PACKAGE_VERSION = '2.12.4'
|
||||
const INTEGRITY_CHECKSUM = '4db4a41e972cec1b64cc569c66952d82'
|
||||
const IS_MOCKED_RESPONSE = Symbol('isMockedResponse')
|
||||
const activeClientIds = new Set()
|
||||
|
||||
@ -71,11 +71,6 @@ addEventListener('message', async function (event) {
|
||||
break
|
||||
}
|
||||
|
||||
case 'MOCK_DEACTIVATE': {
|
||||
activeClientIds.delete(clientId)
|
||||
break
|
||||
}
|
||||
|
||||
case 'CLIENT_CLOSED': {
|
||||
activeClientIds.delete(clientId)
|
||||
|
||||
@ -94,6 +89,8 @@ addEventListener('message', async function (event) {
|
||||
})
|
||||
|
||||
addEventListener('fetch', function (event) {
|
||||
const requestInterceptedAt = Date.now()
|
||||
|
||||
// Bypass navigation requests.
|
||||
if (event.request.mode === 'navigate') {
|
||||
return
|
||||
@ -110,23 +107,29 @@ addEventListener('fetch', function (event) {
|
||||
|
||||
// Bypass all requests when there are no active clients.
|
||||
// Prevents the self-unregistered worked from handling requests
|
||||
// after it's been deleted (still remains active until the next reload).
|
||||
// after it's been terminated (still remains active until the next reload).
|
||||
if (activeClientIds.size === 0) {
|
||||
return
|
||||
}
|
||||
|
||||
const requestId = crypto.randomUUID()
|
||||
event.respondWith(handleRequest(event, requestId))
|
||||
event.respondWith(handleRequest(event, requestId, requestInterceptedAt))
|
||||
})
|
||||
|
||||
/**
|
||||
* @param {FetchEvent} event
|
||||
* @param {string} requestId
|
||||
* @param {number} requestInterceptedAt
|
||||
*/
|
||||
async function handleRequest(event, requestId) {
|
||||
async function handleRequest(event, requestId, requestInterceptedAt) {
|
||||
const client = await resolveMainClient(event)
|
||||
const requestCloneForEvents = event.request.clone()
|
||||
const response = await getResponse(event, client, requestId)
|
||||
const response = await getResponse(
|
||||
event,
|
||||
client,
|
||||
requestId,
|
||||
requestInterceptedAt,
|
||||
)
|
||||
|
||||
// Send back the response clone for the "response:*" life-cycle events.
|
||||
// Ensure MSW is active and ready to handle the message, otherwise
|
||||
@ -202,9 +205,10 @@ async function resolveMainClient(event) {
|
||||
* @param {FetchEvent} event
|
||||
* @param {Client | undefined} client
|
||||
* @param {string} requestId
|
||||
* @param {number} requestInterceptedAt
|
||||
* @returns {Promise<Response>}
|
||||
*/
|
||||
async function getResponse(event, client, requestId) {
|
||||
async function getResponse(event, client, requestId, requestInterceptedAt) {
|
||||
// Clone the request because it might've been already used
|
||||
// (i.e. its body has been read and sent to the client).
|
||||
const requestClone = event.request.clone()
|
||||
@ -255,6 +259,7 @@ async function getResponse(event, client, requestId) {
|
||||
type: 'REQUEST',
|
||||
payload: {
|
||||
id: requestId,
|
||||
interceptedAt: requestInterceptedAt,
|
||||
...serializedRequest,
|
||||
},
|
||||
},
|
||||
|
||||
@ -1,32 +1,7 @@
|
||||
<svg version="1.2" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1365 1365" width="1365" height="1365">
|
||||
<title>safari-pinned-tab-svg</title>
|
||||
<defs>
|
||||
<clipPath clipPathUnits="userSpaceOnUse" id="cp1">
|
||||
<path d="m655.2 313.1v822.23h-622.69v-822.23z"/>
|
||||
</clipPath>
|
||||
<clipPath clipPathUnits="userSpaceOnUse" id="cp2">
|
||||
<path d="m1308.84 304v828.5h-617.24v-828.5z"/>
|
||||
</clipPath>
|
||||
</defs>
|
||||
<style>
|
||||
.s0 { fill: none }
|
||||
.s1 { fill: #000000 }
|
||||
</style>
|
||||
<g id="surface1">
|
||||
<path class="s0" d="m1258.6 499.2c-40.8-26.1-68 13.8-64.7 68.1l-0.3 0.4c0.1-56.6-7.3-119.2-31.7-169.8-8.7-17.9-26.2-47.4-61-33.5-15.2 6.1-29 24.4-21.9 71.7 0 0 8 49.7 6.5 112.2v0.8c-9.9-172.2-47.3-224.7-100.7-221.3-17.1 3.1-40.5 10.8-32.6 63.8 0 0 8.5 55.2 11.3 99.2l0.2 2.2h-0.2c-25.2-94.9-59-96.2-83.5-92.5-22.3 3.3-46.6 27.3-34.3 74.7 38.6 148.4 31 327.2 28.2 352.9-7.9-17.6-10.3-31.4-21.3-50.7-43.9-77.1-64.8-82.8-90.4-84-25.5-1.1-53 15.2-51.2 46.3 1.9 31.1 17.1 36.3 38.7 79.6 16.9 33.8 21.7 78 55.7 158.4 28.1 66.5 101.6 139.5 235.6 130.8 108.5-3.7 270.6-43.2 242.4-302.5-7-45-1.7-82.7 1.9-121.4 5.8-60 14.1-159.4-26.7-185.5z"/>
|
||||
<path class="s0" d="m580.9 695.3c-25.7 1.7-46.4 7.7-89 85.7-10.6 19.4-12.7 33.3-20.3 50.9-3.3-25.5-14-204.2 21.9-353.4 11.4-47.5-13.3-71-35.6-73.9-24.6-3.3-58.5-1.3-81.9 94.6h-0.3l0.4-2.8c1.9-44 9.5-99.4 9.5-99.4 6.9-53.1-16.6-60.3-33.7-63.2-53.4-2.3-89.7 50.4-96.7 221.1h-0.2c-2.4-61.8 4.6-111 4.6-111 6.3-47.5-7.9-65.5-23.2-71.3-35-13.3-52 16.6-60.3 34.7-23.6 51-29.9 113.7-28.7 170.3l-0.4-0.4c2.4-54.2-25.6-93.7-65.9-66.9-40.3 26.9-30.1 126.2-23.4 186 4.5 38.6 10.4 76.2 4.1 121.4-23.5 259.7 139.3 296.1 247.8 297.8 134.1 6.1 206.3-68.3 233.3-135.4 32.5-80.9 36.6-125.3 52.8-159.3 20.8-43.8 36-49.2 37.3-80.3 1.3-31.1-26.5-46.9-52-45.3z"/>
|
||||
<g id="Clip-Path" clip-path="url(#cp1)">
|
||||
<g>
|
||||
<path fill-rule="evenodd" class="s1" d="m634.4 695.7c11.9 12 17.8 27.9 17.1 45.7-1 24.6-9.5 37.8-19.4 53.2-5.8 9-12.3 19.2-19.8 34.9-6.6 13.8-11.2 30.4-17 51.5-7.6 27.3-17 61.2-35.3 106.7-14.1 35.1-71.4 146.1-231.3 147.6q-9.8 0.1-20-0.3c-93.6-1.5-164.2-28.5-209.3-80.6-46.9-54-65.8-134.2-56.4-238.4l0.1-0.9c5.2-37.6 1.5-69.5-2.6-103.3-0.5-4.4-1-8.7-1.5-13.1-9.4-82.5-15.4-173.1 31.8-204.6 27.9-18.5 49.3-11.1 59.6-4.9 1 0.6 1.9 1.2 2.9 1.9 4.5-32.3 12.6-63.9 25.6-92.2 11.2-24.2 37.1-62.2 83.8-44.5 7.6 3 17.3 8.8 24.8 20.2 6.7-14.7 14.5-26.6 23.5-35.8 16.6-17.2 37.4-25.4 61.6-24.3l2.1 0.2c39.2 6.5 55.9 35 49.4 84.9 0 0 0 0.3 0 0.6 20-17 40.4-16.9 56.1-14.8 17.2 2.2 32.8 12.1 42.8 27.2 8.6 13 17.1 35.8 8.7 70.7-22.3 92.9-26.1 198.5-25.2 268.8 36.3-61.5 59.9-74.1 93.2-76.2 20.8-1.3 41.3 6 54.8 19.8zm-316.9-329.4c-35.1 36.2-49.7 148.5-43.4 333.7 19.5-3 39.5-5.2 59.6-6.5 4.7-91.2 13.3-153.7 23.7-197q0-0.5 0-0.9c2-44.4 9.3-98.9 9.7-101.2 4.7-36.3-5.7-39.2-17-41.1-13.2-0.3-23.5 3.8-32.5 13zm-124.6 49.5c-50 108.3-16.2 277.2-8.5 303.8 16.1-4.8 33.8-9.2 52.4-13-2.1-57.7-2.3-108.1-0.6-151.9-2.3-62.3 4.4-111.4 4.7-113.5 1.8-13 4.2-44.5-11.1-50.3-10.9-4.1-22.8-5.7-36.9 24.8zm407.9 357.3c8.9-13.8 12.6-19.5 13.2-33.3 0.2-6.7-1.6-12-5.9-16.3-5.9-6.1-16-9.4-26.1-8.8-17.3 1.2-33.6 2.2-73.8 75.9-5.6 10.4-8.5 18.9-11.8 28.6-2.1 6.3-4.4 13.2-7.7 20.8-0.1 0.3-0.2 0.6-0.4 0.8-1.4 3.3-3 6.8-4.8 10.4-17.6 34.2-46.2 53.4-76.5 51.6-10.4-0.7-18.2-9.9-17.6-20.6 0.6-10.7 9.6-18.7 19.8-18.2 18 1.1 33.1-15.3 41.2-31.1 0.7-1.4 1.3-2.8 2-4.2-4-41.1-11.8-210.7 22.9-354.8 3.9-16.5 2.8-30.1-3.3-39.3-5.6-8.4-13.4-10.3-16.5-10.7-11.2-1.5-19.3-0.9-27.8 6.4-20.5 17.8-46.8 77.8-56.4 261.8 5.8 0 11.6 0 17.3 0.2 10.3 0.3 18.5 9.2 18.2 19.9-0.3 10.7-8.8 19.1-19.2 18.9-95.8-2.8-204.4 22.8-250.2 47.9-2.8 1.5-5.7 2.3-8.6 2.3-6.8 0.1-13.4-3.7-16.8-10.3-4.8-9.5-1.4-21.2 7.8-26.3 8.1-4.4 17.9-8.9 28.9-13.1-6.7-22.4-18.6-82-20.1-150.6-0.3-1.5-0.5-3-0.4-4.6 1.2-29.4-7.6-48.4-16.4-53.6-5.2-3.1-12.1-1.8-20.6 3.9-31.6 21-19.4 127.4-14.9 167.4 0.5 4.3 1 8.6 1.5 12.9 4.1 34.7 8.4 70.6 2.6 113-8.3 92.7 7.5 162.9 47 208.5 38.4 44.2 98 66.3 182.4 67.6 151.5 7.1 203.3-92.6 215.7-123.3 17.4-43.4 26.5-76.2 33.8-102.5 6.4-22.9 11.4-41 19.5-58 8.5-17.9 16.1-29.7 22.2-39.2z"/>
|
||||
</g>
|
||||
</g>
|
||||
<g id="Clip-Path" clip-path="url(#cp2)">
|
||||
<g>
|
||||
<path fill-rule="evenodd" class="s1" d="m1301.9 802.9l0.1 0.9c11.3 104-6.3 184.6-52.2 239.5-44.1 52.8-114.2 81.3-208.3 84.5q-10.2 0.7-19.9 0.8c-159.5 1.6-218.8-108.4-233.5-143.2-19.1-45.1-29.1-78.9-37.2-106-6.2-21-11.1-37.5-18-51.2-7.7-15.5-14.4-25.6-20.4-34.5-10.1-15.1-18.8-28.2-20.3-52.8-1.1-17.7 4.5-33.6 16.2-45.9 13.3-14 33.8-21.8 54.5-20.9 33.3 1.5 57.1 13.7 94.5 74.5-0.3-70.4-6-175.9-30-268.4-9-34.8-0.9-57.7 7.5-70.8 9.7-15.3 25.1-25.5 42.2-28.1 15.7-2.3 36.2-2.9 56.4 13.8 0-0.2 0-0.4 0-0.4-7.4-49.9 8.8-78.8 47.9-86l2.1-0.3c24.1-1.6 45 6.3 62 23.2 9.1 9 17.1 20.7 24.1 35.3 7.4-11.6 16.9-17.6 24.5-20.6 46.4-18.7 72.9 18.9 84.5 42.9 13.5 28 22.1 59.5 27.3 91.6 0.9-0.6 1.8-1.3 2.8-1.9 10.2-6.3 31.5-14.3 59.7 3.8 47.8 30.6 43.4 121.3 35.5 203.9-0.4 4.4-0.8 8.7-1.3 13.1-3.4 33.9-6.6 65.9-0.8 103.3zm-197.6-256.5c2.5 43.7 3.2 94.2 2.1 151.9 18.7 3.5 36.4 7.5 52.7 12 7.2-26.7 37.9-196.3-14-303.7-14.6-30.1-26.5-28.4-37.4-24.1-15.1 6.1-12.2 37.5-10.2 50.7 0.4 1.9 8 50.9 6.8 113.2zm-117.5-199.2c-11.4 2.2-21.6 5.2-16.3 41.6 0.4 2.1 8.8 56.4 11.5 100.8q0 0.5 0 0.9c11.2 43.2 21 105.4 27.2 196.6 20.2 0.9 40.2 2.7 59.7 5.3 3-185.3-13.5-297.2-49.3-332.8-9.1-9.1-19.5-13-32.7-12.4zm278.5 348.5c0.5-4.3 0.9-8.6 1.3-13 3.9-40.1 14.1-146.6-17.9-167-8.6-5.5-15.5-6.7-20.6-3.5-8.7 5.4-17.2 24.5-15.4 53.9 0.1 1.5 0 3.1-0.3 4.6-0.4 68.5-11.2 128.4-17.5 150.9 11.1 4.1 20.9 8.3 29.1 12.6 9.3 4.9 13 16.6 8.3 26.2-3.3 6.7-9.8 10.6-16.6 10.6-2.9 0-5.9-0.6-8.6-2.1-46.2-24.3-155.4-47.7-251-43.2-10.5 0.3-19.2-7.7-19.6-18.5-0.5-10.7 7.5-19.8 17.9-20.2 5.6-0.3 11.4-0.5 17.2-0.6-12.8-183.8-40.2-243.3-61-260.7-8.6-7.1-16.8-7.6-27.9-5.9-3.2 0.5-10.9 2.5-16.4 11.1-5.9 9.3-6.8 22.9-2.5 39.3 37.3 143.5 32.4 313.2 29.2 354.3 0.7 1.4 1.3 2.7 2.1 4.2 8.4 15.6 23.7 31.7 41.7 30.3 10.3-0.7 19.3 7.2 20.1 17.9 0.8 10.6-6.9 20-17.2 20.8-30.3 2.5-59.3-16.3-77.4-50.1-2-3.6-3.6-7-5.1-10.3-0.1-0.2-0.2-0.5-0.3-0.7-3.5-7.5-5.9-14.5-8.2-20.8-3.5-9.6-6.4-18-12.3-28.3-41.6-72.9-57.9-73.7-75.1-74.5-10.2-0.5-20.2 3.1-26.1 9.3-4.1 4.3-5.9 9.7-5.5 16.4 0.8 13.8 4.6 19.4 13.7 33.1 6.3 9.4 14.1 21 23 38.7 8.3 16.9 13.7 34.8 20.5 57.7 7.7 26.2 17.4 58.7 35.6 101.8 12.9 30.5 66.7 129.1 217.3 119.2 84.9-2.9 144.2-26.2 181.7-71.1 38.7-46.3 53.2-116.8 43.3-209.4-6.6-42.3-3-78.2 0.5-113z"/>
|
||||
</g>
|
||||
</g>
|
||||
<path class="s1" d="m739.8 434.2c-3 0-6.1-0.6-9-2-10.5-5-15.2-18-10.3-28.9 15.7-35.6 38.8-68.4 66.6-94.9 8.5-8.1 21.9-7.6 29.7 1.3 7.9 8.9 7.4 22.7-1.2 30.8-23.7 22.7-43.4 50.6-56.8 81-3.6 7.9-11.1 12.6-19 12.7z"/>
|
||||
<path class="s1" d="m668.8 421.6c-10.9 0.1-20.3-8.5-21.2-20-4-51.4-4.2-103.5-0.4-154.8 0.9-12 11.1-21 22.6-20.1 11.6 0.9 20.3 11.3 19.4 23.3-3.6 49.1-3.4 98.9 0.4 148 1 12-7.7 22.5-19.3 23.5-0.5 0-1 0-1.5 0z"/>
|
||||
<path class="s1" d="m596.2 435.1c-9.4 0.1-18.2-6.5-20.6-16.4-8.9-36.3-25.9-70.8-48.9-99.7-7.4-9.3-6.1-23 2.8-30.7 9-7.6 22.3-6.3 29.7 3 26.9 33.8 46.7 74.2 57.2 116.7 2.9 11.6-4 23.5-15.2 26.5-1.8 0.4-3.4 0.6-5.1 0.7z"/>
|
||||
</g>
|
||||
<svg width="1365" height="1365" viewBox="0 -24 148 148" fill="none" xmlns="http://www.w3.org/2000/svg">
|
||||
<path d="M71.7542 16.863V2.97414C71.7542 1.82355 72.6872 0.890503 73.8378 0.890503C74.9884 0.890503 75.9214 1.82355 75.9214 2.97414V16.863C75.9214 18.0136 74.9884 18.9466 73.8378 18.9466C72.6872 18.9466 71.7542 18.0136 71.7542 16.863Z" fill="black"/>
|
||||
<path d="M82.5272 18.9329L89.4716 6.90477C90.0469 5.90832 91.3215 5.5668 92.3179 6.1421C93.3144 6.7174 93.6559 7.99197 93.0806 8.98841L86.1362 21.0165C85.5609 22.0129 84.2863 22.3545 83.2899 21.7792C82.2934 21.2039 81.9519 19.9293 82.5272 18.9329Z" fill="black"/>
|
||||
<path d="M65.1481 18.9329L58.2037 6.90477C57.6284 5.90832 56.3538 5.5668 55.3574 6.1421C54.3609 6.7174 54.0194 7.99197 54.5947 8.98841L61.5391 21.0165C62.1144 22.0129 63.389 22.3545 64.3854 21.7792C65.3819 21.2039 65.7234 19.9293 65.1481 18.9329Z" fill="black"/>
|
||||
<path d="M140.606 62.0292C140.606 58.409 141.583 47.6748 141.89 44.1323C142.097 41.7374 141.809 40.4247 141.424 39.7542C141.141 39.2626 140.699 38.915 139.634 38.8436C138.865 38.7921 138.027 39.0114 137.401 39.5761C136.814 40.1052 136.159 41.1682 136.159 43.3176L136.155 43.4388L135.198 59.758C135.164 60.3451 134.883 60.8911 134.424 61.2599C133.966 61.6284 133.374 61.7859 132.793 61.6941L122.764 60.1068L111.948 58.6703C110.949 58.5376 110.188 57.7084 110.142 56.7016L109.561 44.1323C109.535 43.621 109.51 43.1141 109.484 42.6146C109.241 37.9294 109.022 33.7805 109.022 32.4282C109.022 28.3859 108.338 26.6806 107.74 25.9634C107.263 25.3915 106.577 25.1402 105.11 25.1402C104.583 25.1402 104.212 25.2481 103.933 25.4111C103.659 25.5714 103.346 25.8587 103.049 26.4208C102.41 27.6257 101.945 29.891 102.118 33.8479C102.342 38.9804 102.692 42.8146 103.035 46.2718C103.377 49.7231 103.718 52.8561 103.908 56.4971C104.204 62.1966 104.178 66.1256 103.945 68.7924C103.828 70.124 103.656 71.1996 103.423 72.0501C103.202 72.8558 102.871 73.6757 102.296 74.2887C101.6 75.0303 100.608 75.3844 99.577 75.136C98.7592 74.9389 98.1847 74.4215 97.8706 74.0916C97.2141 73.4017 96.7501 72.5106 96.568 72.0512C95.5097 69.3812 92.2352 63.1808 87.8023 59.6811C86.5089 58.6599 85.5666 58.3652 84.9736 58.3204C84.4148 58.2783 84.0094 58.4436 83.6909 58.6967C83.34 58.9756 83.0781 59.3811 82.9479 59.7643C82.9019 59.8999 82.8823 59.9968 82.8741 60.0584C84.0759 62.0865 88.8421 69.5222 91.0896 77.069C92.7648 82.6941 96.8038 88.4259 99.8194 90.8809C102.74 93.258 107.988 94.7313 113.9 95.0218C119.756 95.3095 125.788 94.4121 130.033 92.5092C138.233 88.8334 139.903 80.7382 140.651 77.2292C141.232 74.5057 141.243 71.5987 141.087 68.9009C141.01 67.5551 140.894 66.2969 140.793 65.1373C140.695 64.0105 140.606 62.9215 140.606 62.0292ZM120.986 27.0953C120.986 25.8314 120.648 24.7049 120.089 23.9514C119.583 23.27 118.84 22.7987 117.646 22.7984C116.668 22.7982 116.011 22.9187 115.546 23.1167C115.13 23.2943 114.781 23.5699 114.463 24.0831C113.73 25.2671 113.192 27.6455 113.189 32.384L113.721 43.9088C113.91 47.5661 114.106 51.4922 114.235 54.7707L120.986 55.6666V27.0953ZM125.153 56.2652L131.172 57.218L131.992 43.267V32.5083C131.992 31.031 131.39 30.1275 130.678 29.5489C129.884 28.9039 128.957 28.6731 128.519 28.6731C127.722 28.6731 126.899 28.797 126.306 29.2179C125.849 29.5421 125.153 30.3087 125.153 32.5083V56.2652ZM136.159 35.4278C137.406 34.8069 138.74 34.6083 139.912 34.6868C142.037 34.8292 143.91 35.718 145.037 37.6779C146.06 39.4592 146.273 41.8136 146.041 44.4927C145.72 48.1949 144.772 58.6457 144.772 62.0292C144.772 62.708 144.843 63.6116 144.944 64.7758C145.042 65.907 145.165 67.2389 145.247 68.6606C145.411 71.4987 145.422 74.8383 144.727 78.0987C144.002 81.4953 142.041 91.6918 131.738 96.3108C126.731 98.5551 120.002 99.4936 113.696 99.1838C107.445 98.8767 101.128 97.3189 97.1887 94.1122C93.4809 91.0937 88.9938 84.6307 87.0962 78.2589C84.9529 71.0619 80.3109 63.9646 79.1527 61.9533C78.4706 60.7689 78.684 59.3628 79.0019 58.4258C79.3607 57.3688 80.0554 56.2631 81.0993 55.4337C82.1758 54.5784 83.6043 54.0377 85.2876 54.1647C86.9369 54.2893 88.6462 55.0393 90.3834 56.4107C94.8541 59.9401 98.1342 65.5082 99.7424 68.9231C99.759 68.7664 99.779 68.6024 99.7941 68.4298C100.003 66.0435 100.039 62.3344 99.7467 56.7132C99.5635 53.1942 99.2356 50.1809 98.8888 46.6828C98.5425 43.1904 98.184 39.2713 97.955 34.0302C97.7722 29.8481 98.2012 26.6722 99.3672 24.471C99.9716 23.3302 100.79 22.4223 101.83 21.814C102.866 21.2087 103.995 20.974 105.11 20.974C106.759 20.974 108.813 21.2062 110.448 22.7678C110.593 22.4576 110.75 22.1652 110.921 21.8899C111.676 20.6698 112.681 19.8084 113.912 19.2835C115.095 18.7791 116.378 18.6309 117.646 18.6311C120.195 18.6315 122.164 19.7567 123.434 21.4683C124.256 22.576 124.75 23.8775 124.985 25.1982C126.338 24.5876 127.691 24.5068 128.519 24.5068C129.933 24.5068 131.784 25.0791 133.305 26.3154C134.908 27.6179 136.159 29.6733 136.159 32.5083V35.4278Z" fill="black"/>
|
||||
<path d="M7.15661 62.0292C7.15661 58.409 6.17994 47.6748 5.87291 44.1323C5.6654 41.7374 5.95357 40.4247 6.33875 39.7542C6.62116 39.2626 7.06336 38.915 8.12834 38.8436C8.89759 38.7921 9.73544 39.0114 10.3616 39.5761C10.9484 40.1052 11.6032 41.1682 11.6032 43.3176L11.6074 43.4388L12.5644 59.758C12.5988 60.3451 12.8798 60.8911 13.338 61.2599C13.7961 61.6284 14.3887 61.7859 14.9695 61.6941L24.9988 60.1068L35.8143 58.6703C36.8135 58.5376 37.5741 57.7084 37.6208 56.7016L38.2015 44.1323C38.2279 43.621 38.2525 43.1141 38.2784 42.6146C38.5218 37.9294 38.7401 33.7805 38.7401 32.4282C38.7401 28.3859 39.4246 26.6806 40.0227 25.9634C40.4996 25.3915 41.185 25.1402 42.6523 25.1402C43.1794 25.1402 43.5505 25.2481 43.8295 25.4111C44.1038 25.5714 44.416 25.8587 44.7138 26.4208C45.3521 27.6257 45.8173 29.891 45.6444 33.8479C45.4201 38.9804 45.0703 42.8146 44.7275 46.2718C44.3853 49.7231 44.0443 52.8561 43.8548 56.4971C43.5582 62.1966 43.5847 66.1256 43.8179 68.7924C43.9344 70.124 44.1069 71.1996 44.3396 72.0501C44.5601 72.8558 44.891 73.6757 45.4663 74.2887C46.1625 75.0303 47.1546 75.3844 48.1855 75.136C49.0033 74.9389 49.5778 74.4215 49.8918 74.0916C50.5484 73.4017 51.0123 72.5106 51.1945 72.0512C52.2527 69.3812 55.5272 63.1808 59.9601 59.6811C61.2536 58.6599 62.1958 58.3652 62.7889 58.3204C63.3476 58.2783 63.753 58.4436 64.0715 58.6967C64.4225 58.9756 64.6844 59.3811 64.8146 59.7643C64.8606 59.8999 64.8801 59.9968 64.8883 60.0584C63.6866 62.0865 58.9204 69.5222 56.6729 77.069C54.9977 82.6941 50.9586 88.4259 47.9431 90.8809C45.0229 93.258 39.7747 94.7313 33.8624 95.0218C28.0068 95.3095 21.9748 94.4121 17.7297 92.5092C9.52988 88.8334 7.85961 80.7382 7.11129 77.2292C6.53054 74.5057 6.5195 71.5987 6.67496 68.9009C6.75251 67.5551 6.86809 66.2969 6.96901 65.1373C7.06707 64.0105 7.1566 62.9215 7.15661 62.0292ZM26.7768 27.0953C26.7768 25.8314 27.1147 24.7049 27.6737 23.9514C28.1792 23.27 28.9221 22.7987 30.1167 22.7984C31.0942 22.7982 31.7518 22.9187 32.2162 23.1167C32.6326 23.2943 32.9817 23.5699 33.2996 24.0831C34.0328 25.2671 34.5705 27.6455 34.5738 32.384L34.0416 43.9088C33.8524 47.5661 33.6565 51.4922 33.5273 54.7707L26.7768 55.6666V27.0953ZM22.6095 56.2652L16.5904 57.218L15.7705 43.267V32.5083C15.7705 31.031 16.3726 30.1275 17.0847 29.5489C17.8785 28.9039 18.8058 28.6731 19.2432 28.6731C20.0404 28.6731 20.8634 28.797 21.4565 29.2179C21.9131 29.5421 22.6095 30.3087 22.6095 32.5083V56.2652ZM11.6032 35.4278C10.3568 34.8069 9.02265 34.6083 7.8501 34.6868C5.72541 34.8292 3.85197 35.718 2.72584 37.6779C1.70247 39.4592 1.48924 41.8136 1.72143 44.4927C2.0423 48.1949 2.99038 58.6457 2.99038 62.0292C2.99037 62.708 2.91991 63.6116 2.81859 64.7758C2.72014 65.907 2.59699 67.2389 2.51505 68.6606C2.3515 71.4987 2.34041 74.8383 3.0357 78.0987C3.76005 81.4953 5.72154 91.6918 16.0245 96.3108C21.0311 98.5551 27.7601 99.4936 34.0669 99.1838C40.3172 98.8767 46.6346 97.3189 50.5737 94.1122C54.2816 91.0937 58.7686 84.6307 60.6662 78.2589C62.8095 71.0619 67.4515 63.9646 68.6098 61.9533C69.2919 60.7689 69.0785 59.3628 68.7605 58.4258C68.4018 57.3688 67.707 56.2631 66.6632 55.4337C65.5867 54.5784 64.1582 54.0377 62.4748 54.1647C60.8256 54.2893 59.1162 55.0393 57.379 56.4107C52.9083 59.9401 49.6283 65.5082 48.02 68.9231C48.0034 68.7664 47.9835 68.6024 47.9684 68.4298C47.7597 66.0435 47.7232 62.3344 48.0158 56.7132C48.1989 53.1942 48.5269 50.1809 48.8737 46.6828C49.22 43.1904 49.5784 39.2713 49.8075 34.0302C49.9903 29.8481 49.5612 26.6722 48.3952 24.471C47.7909 23.3302 46.9729 22.4223 45.9321 21.814C44.8964 21.2087 43.7676 20.974 42.6523 20.974C41.0038 20.974 38.9497 21.2062 37.3141 22.7678C37.1698 22.4576 37.0124 22.1652 36.8419 21.8899C36.0863 20.6698 35.0817 19.8084 33.8508 19.2835C32.6679 18.7791 31.3849 18.6309 30.1167 18.6311C27.5677 18.6315 25.5986 19.7567 24.3285 21.4683C23.5066 22.576 23.0121 23.8775 22.7771 25.1982C21.4247 24.5876 20.0718 24.5068 19.2432 24.5068C17.8298 24.5068 15.9788 25.0791 14.4573 26.3154C12.8542 27.6179 11.6032 29.6733 11.6032 32.5083V35.4278Z" fill="black"/>
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 6.9 KiB After Width: | Height: | Size: 8.7 KiB |
@ -296,6 +296,25 @@ class V1ConversationService {
|
||||
const { data } = await openHands.get<{ runtime_id: string }>(url);
|
||||
return data;
|
||||
}
|
||||
|
||||
/**
|
||||
* Read a file from a specific conversation's sandbox workspace
|
||||
* @param conversationId The conversation ID
|
||||
* @param filePath Path to the file to read within the sandbox workspace (defaults to /workspace/project/PLAN.md)
|
||||
* @returns The content of the file or an empty string if the file doesn't exist
|
||||
*/
|
||||
static async readConversationFile(
|
||||
conversationId: string,
|
||||
filePath: string = "/workspace/project/PLAN.md",
|
||||
): Promise<string> {
|
||||
const params = new URLSearchParams();
|
||||
params.append("file_path", filePath);
|
||||
|
||||
const { data } = await openHands.get<string>(
|
||||
`/api/v1/app-conversations/${conversationId}/file?${params.toString()}`,
|
||||
);
|
||||
return data;
|
||||
}
|
||||
}
|
||||
|
||||
export default V1ConversationService;
|
||||
|
||||
@ -3,15 +3,19 @@ import { Provider } from "#/types/settings";
|
||||
import { V1SandboxStatus } from "../sandbox-service/sandbox-service.types";
|
||||
|
||||
// V1 API Types for requests
|
||||
// Note: This represents the serialized API format, not the internal TextContent/ImageContent types
|
||||
export interface V1MessageContent {
|
||||
type: "text" | "image_url";
|
||||
text?: string;
|
||||
image_url?: {
|
||||
url: string;
|
||||
};
|
||||
// These types match the SDK's TextContent and ImageContent formats
|
||||
export interface V1TextContent {
|
||||
type: "text";
|
||||
text: string;
|
||||
}
|
||||
|
||||
export interface V1ImageContent {
|
||||
type: "image";
|
||||
image_urls: string[];
|
||||
}
|
||||
|
||||
export type V1MessageContent = V1TextContent | V1ImageContent;
|
||||
|
||||
type V1Role = "user" | "system" | "assistant" | "tool";
|
||||
|
||||
export interface V1SendMessageRequest {
|
||||
@ -40,6 +44,7 @@ export type V1AppConversationStartTaskStatus =
|
||||
| "PREPARING_REPOSITORY"
|
||||
| "RUNNING_SETUP_SCRIPT"
|
||||
| "SETTING_UP_GIT_HOOKS"
|
||||
| "SETTING_UP_SKILLS"
|
||||
| "STARTING_CONVERSATION"
|
||||
| "READY"
|
||||
| "ERROR";
|
||||
|
||||
@ -5,7 +5,6 @@ import type {
|
||||
ConfirmationResponseRequest,
|
||||
ConfirmationResponseResponse,
|
||||
} from "./event-service.types";
|
||||
import { openHands } from "../open-hands-axios";
|
||||
|
||||
class EventService {
|
||||
/**
|
||||
@ -38,11 +37,27 @@ class EventService {
|
||||
return data;
|
||||
}
|
||||
|
||||
static async getEventCount(conversationId: string): Promise<number> {
|
||||
const params = new URLSearchParams();
|
||||
params.append("conversation_id__eq", conversationId);
|
||||
const { data } = await openHands.get<number>(
|
||||
`/api/v1/events/count?${params.toString()}`,
|
||||
/**
|
||||
* Get event count for a V1 conversation
|
||||
* @param conversationId The conversation ID
|
||||
* @param conversationUrl The conversation URL (e.g., "http://localhost:54928/api/conversations/...")
|
||||
* @param sessionApiKey Session API key for authentication (required for V1)
|
||||
* @returns The event count
|
||||
*/
|
||||
static async getEventCount(
|
||||
conversationId: string,
|
||||
conversationUrl: string,
|
||||
sessionApiKey?: string | null,
|
||||
): Promise<number> {
|
||||
// Build the runtime URL using the conversation URL
|
||||
const runtimeUrl = buildHttpBaseUrl(conversationUrl);
|
||||
|
||||
// Build session headers for authentication
|
||||
const headers = buildSessionHeaders(sessionApiKey);
|
||||
|
||||
const { data } = await axios.get<number>(
|
||||
`${runtimeUrl}/api/conversations/${conversationId}/events/count`,
|
||||
{ headers },
|
||||
);
|
||||
return data;
|
||||
}
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
import { openHands } from "../api/open-hands-axios";
|
||||
import { ApiSettings, PostApiSettings } from "./settings.types";
|
||||
import { openHands } from "../open-hands-axios";
|
||||
import { Settings } from "#/types/settings";
|
||||
|
||||
/**
|
||||
* Settings service for managing application settings
|
||||
@ -8,8 +8,8 @@ class SettingsService {
|
||||
/**
|
||||
* Get the settings from the server or use the default settings if not found
|
||||
*/
|
||||
static async getSettings(): Promise<ApiSettings> {
|
||||
const { data } = await openHands.get<ApiSettings>("/api/settings");
|
||||
static async getSettings(): Promise<Settings> {
|
||||
const { data } = await openHands.get<Settings>("/api/settings");
|
||||
return data;
|
||||
}
|
||||
|
||||
@ -17,9 +17,7 @@ class SettingsService {
|
||||
* Save the settings to the server. Only valid settings are saved.
|
||||
* @param settings - the settings to save
|
||||
*/
|
||||
static async saveSettings(
|
||||
settings: Partial<PostApiSettings>,
|
||||
): Promise<boolean> {
|
||||
static async saveSettings(settings: Partial<Settings>): Promise<boolean> {
|
||||
const data = await openHands.post("/api/settings", settings);
|
||||
return data.status === 200;
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
x
Reference in New Issue
Block a user