Skip to content

Commit

Permalink
Merge pull request #11 from All-Hands-AI/main
Browse files Browse the repository at this point in the history
update
  • Loading branch information
EcoSphereNetwork authored Dec 21, 2024
2 parents e9134ff + 252c709 commit ed75313
Show file tree
Hide file tree
Showing 724 changed files with 28,520 additions and 39,981 deletions.
1 change: 0 additions & 1 deletion .devcontainer/README.MD

This file was deleted.

15 changes: 0 additions & 15 deletions .devcontainer/devcontainer.json

This file was deleted.

6 changes: 0 additions & 6 deletions .devcontainer/on_create.sh

This file was deleted.

3 changes: 3 additions & 0 deletions .github/dependabot.yml
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,9 @@ updates:
chromadb:
patterns:
- "chromadb"
browsergym:
patterns:
- "browsergym*"
security-all:
applies-to: "security-updates"
patterns:
Expand Down
31 changes: 4 additions & 27 deletions .github/workflows/eval-runner.yml
Original file line number Diff line number Diff line change
@@ -1,10 +1,8 @@
name: Run Evaluation
name: Run SWE-Bench Evaluation

on:
pull_request:
types: [labeled]
schedule:
- cron: "0 1 * * *" # Run daily at 1 AM UTC
workflow_dispatch:
inputs:
reason:
Expand Down Expand Up @@ -60,24 +58,6 @@ jobs:
echo "api_key = \"$DEEPSEEK_API_KEY\"" >> config.toml
echo "temperature = 0.0" >> config.toml
- name: Run integration test evaluation
env:
ALLHANDS_API_KEY: ${{ secrets.ALLHANDS_EVAL_RUNTIME_API_KEY }}
RUNTIME: remote
SANDBOX_REMOTE_RUNTIME_API_URL: https://runtime.eval.all-hands.dev
EVAL_DOCKER_IMAGE_PREFIX: us-central1-docker.pkg.dev/evaluation-092424/swe-bench-images

run: |
poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' $N_PROCESSES
# get evaluation report
REPORT_FILE=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/deepseek-chat_maxiter_10_N* -name "report.md" -type f | head -n 1)
echo "REPORT_FILE: $REPORT_FILE"
echo "INTEGRATION_TEST_REPORT<<EOF" >> $GITHUB_ENV
cat $REPORT_FILE >> $GITHUB_ENV
echo >> $GITHUB_ENV
echo "EOF" >> $GITHUB_ENV
- name: Run SWE-Bench evaluation
env:
ALLHANDS_API_KEY: ${{ secrets.ALLHANDS_EVAL_RUNTIME_API_KEY }}
Expand All @@ -86,12 +66,12 @@ jobs:
EVAL_DOCKER_IMAGE_PREFIX: us-central1-docker.pkg.dev/evaluation-092424/swe-bench-images

run: |
poetry run ./evaluation/swe_bench/scripts/run_infer.sh llm.eval HEAD CodeActAgent 300 30 $N_PROCESSES "princeton-nlp/SWE-bench_Lite" test
poetry run ./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.eval HEAD CodeActAgent 300 30 $N_PROCESSES "princeton-nlp/SWE-bench_Lite" test
OUTPUT_FOLDER=$(find evaluation/evaluation_outputs/outputs/princeton-nlp__SWE-bench_Lite-test/CodeActAgent -name "deepseek-chat_maxiter_50_N_*-no-hint-run_1" -type d | head -n 1)
echo "OUTPUT_FOLDER for SWE-bench evaluation: $OUTPUT_FOLDER"
poetry run ./evaluation/swe_bench/scripts/eval_infer_remote.sh $OUTPUT_FOLDER/output.jsonl $N_PROCESSES "princeton-nlp/SWE-bench_Lite" test
poetry run ./evaluation/benchmarks/swe_bench/scripts/eval_infer_remote.sh $OUTPUT_FOLDER/output.jsonl $N_PROCESSES "princeton-nlp/SWE-bench_Lite" test
poetry run ./evaluation/swe_bench/scripts/eval/summarize_outputs.py $OUTPUT_FOLDER/output.jsonl > summarize_outputs.log 2>&1
poetry run ./evaluation/benchmarks/swe_bench/scripts/eval/summarize_outputs.py $OUTPUT_FOLDER/output.jsonl > summarize_outputs.log 2>&1
echo "SWEBENCH_REPORT<<EOF" >> $GITHUB_ENV
cat summarize_outputs.log >> $GITHUB_ENV
echo "EOF" >> $GITHUB_ENV
Expand Down Expand Up @@ -145,9 +125,6 @@ jobs:
**SWE-Bench Evaluation Report**
${{ env.SWEBENCH_REPORT }}
---
**Integration Tests Evaluation Report**
${{ env.INTEGRATION_TEST_REPORT }}
---
You can download the full evaluation outputs [here](${{ env.ARTIFACT_URL }}).
- name: Post to a Slack channel
Expand Down
6 changes: 5 additions & 1 deletion .github/workflows/fe-unit-tests.yml
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,8 @@ jobs:
runs-on: ubuntu-latest
strategy:
matrix:
node-version: [20]
node-version: [20, 22]
fail-fast: true
steps:
- name: Checkout
uses: actions/checkout@v4
Expand All @@ -35,6 +36,9 @@ jobs:
- name: Install dependencies
working-directory: ./frontend
run: npm ci
- name: Run TypeScript compilation
working-directory: ./frontend
run: npm run make-i18n && tsc
- name: Run tests and collect coverage
working-directory: ./frontend
run: npm run test:coverage
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/ghcr-build.yml
Original file line number Diff line number Diff line change
Expand Up @@ -291,7 +291,7 @@ jobs:
SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
TEST_IN_CI=true \
RUN_AS_OPENHANDS=false \
poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime
poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v4
env:
Expand Down Expand Up @@ -368,7 +368,7 @@ jobs:
SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
TEST_IN_CI=true \
RUN_AS_OPENHANDS=true \
poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime
poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v4
env:
Expand Down
158 changes: 158 additions & 0 deletions .github/workflows/integration-runner.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,158 @@
name: Run Integration Tests

on:
pull_request:
types: [labeled]
workflow_dispatch:
inputs:
reason:
description: 'Reason for manual trigger'
required: true
default: ''
schedule:
- cron: '30 22 * * *' # Runs at 10:30pm UTC every day

env:
N_PROCESSES: 10 # Global configuration for number of parallel processes for evaluation

jobs:
run-integration-tests:
if: github.event.label.name == 'integration-test' || github.event_name == 'workflow_dispatch' || github.event_name == 'schedule'
runs-on: ubuntu-latest
permissions:
contents: "read"
id-token: "write"
pull-requests: "write"
issues: "write"
strategy:
matrix:
python-version: ["3.12"]
steps:
- name: Checkout repository
uses: actions/checkout@v4

- name: Install poetry via pipx
run: pipx install poetry

- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
cache: "poetry"

- name: Comment on PR if 'integration-test' label is present
if: github.event_name == 'pull_request' && github.event.label.name == 'integration-test'
uses: KeisukeYamashita/create-comment@v1
with:
unique: false
comment: |
Hi! I started running the integration tests on your PR. You will receive a comment with the results shortly.
- name: Install Python dependencies using Poetry
run: poetry install --without evaluation,llama-index

- name: Configure config.toml for testing with Haiku
env:
LLM_MODEL: "litellm_proxy/claude-3-5-haiku-20241022"
LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
run: |
echo "[llm.eval]" > config.toml
echo "model = \"$LLM_MODEL\"" >> config.toml
echo "api_key = \"$LLM_API_KEY\"" >> config.toml
echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
echo "temperature = 0.0" >> config.toml
- name: Build environment
run: make build

- name: Run integration test evaluation for Haiku
env:
SANDBOX_FORCE_REBUILD_RUNTIME: True
run: |
poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' $N_PROCESSES '' 'haiku_run'
# get integration tests report
REPORT_FILE_HAIKU=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/*haiku*_maxiter_10_N* -name "report.md" -type f | head -n 1)
echo "REPORT_FILE: $REPORT_FILE_HAIKU"
echo "INTEGRATION_TEST_REPORT_HAIKU<<EOF" >> $GITHUB_ENV
cat $REPORT_FILE_HAIKU >> $GITHUB_ENV
echo >> $GITHUB_ENV
echo "EOF" >> $GITHUB_ENV
- name: Wait a little bit
run: sleep 10

- name: Configure config.toml for testing with DeepSeek
env:
LLM_MODEL: "litellm_proxy/deepseek-chat"
LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
run: |
echo "[llm.eval]" > config.toml
echo "model = \"$LLM_MODEL\"" >> config.toml
echo "api_key = \"$LLM_API_KEY\"" >> config.toml
echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
echo "temperature = 0.0" >> config.toml
- name: Run integration test evaluation for DeepSeek
env:
SANDBOX_FORCE_REBUILD_RUNTIME: True
run: |
poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' $N_PROCESSES '' 'deepseek_run'
# get integration tests report
REPORT_FILE_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/deepseek*_maxiter_10_N* -name "report.md" -type f | head -n 1)
echo "REPORT_FILE: $REPORT_FILE_DEEPSEEK"
echo "INTEGRATION_TEST_REPORT_DEEPSEEK<<EOF" >> $GITHUB_ENV
cat $REPORT_FILE_DEEPSEEK >> $GITHUB_ENV
echo >> $GITHUB_ENV
echo "EOF" >> $GITHUB_ENV
- name: Create archive of evaluation outputs
run: |
TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
cd evaluation/evaluation_outputs/outputs # Change to the outputs directory
tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/* # Only include the actual result directories
- name: Upload evaluation results as artifact
uses: actions/upload-artifact@v4
id: upload_results_artifact
with:
name: integration-test-outputs-${{ github.run_id }}-${{ github.run_attempt }}
path: integration_tests_*.tar.gz

- name: Get artifact URLs
run: |
echo "ARTIFACT_URL=${{ steps.upload_results_artifact.outputs.artifact-url }}" >> $GITHUB_ENV
- name: Set timestamp and trigger reason
run: |
echo "TIMESTAMP=$(date +'%Y-%m-%d-%H-%M')" >> $GITHUB_ENV
if [[ "${{ github.event_name }}" == "pull_request" ]]; then
echo "TRIGGER_REASON=pr-${{ github.event.pull_request.number }}" >> $GITHUB_ENV
elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
echo "TRIGGER_REASON=manual-${{ github.event.inputs.reason }}" >> $GITHUB_ENV
else
echo "TRIGGER_REASON=nightly-scheduled" >> $GITHUB_ENV
fi
- name: Comment with results and artifact link
id: create_comment
uses: KeisukeYamashita/create-comment@v1
with:
# if triggered by PR, use PR number, otherwise use 5318 as fallback issue number for manual triggers
number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || 5318 }}
unique: false
comment: |
Trigger by: ${{ github.event_name == 'pull_request' && format('Pull Request (integration-test label on PR #{0})', github.event.pull_request.number) || (github.event_name == 'workflow_dispatch' && format('Manual Trigger: {0}', github.event.inputs.reason)) || 'Nightly Scheduled Run' }}
Commit: ${{ github.sha }}
**Integration Tests Report (Haiku)**
Haiku LLM Test Results:
${{ env.INTEGRATION_TEST_REPORT_HAIKU }}
---
**Integration Tests Report (DeepSeek)**
DeepSeek LLM Test Results:
${{ env.INTEGRATION_TEST_REPORT_DEEPSEEK }}
---
Download testing outputs (includes both Haiku and DeepSeek results): [Download](${{ steps.upload_results_artifact.outputs.artifact-url }})
91 changes: 91 additions & 0 deletions .github/workflows/lint-fix.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,91 @@
name: Lint Fix

on:
pull_request:
types: [labeled]

jobs:
# Frontend lint fixes
lint-fix-frontend:
if: github.event.label.name == 'lint-fix'
name: Fix frontend linting issues
runs-on: ubuntu-latest
permissions:
contents: write
pull-requests: write
steps:
- uses: actions/checkout@v4
with:
ref: ${{ github.head_ref }}
repository: ${{ github.event.pull_request.head.repo.full_name }}
fetch-depth: 0
token: ${{ secrets.GITHUB_TOKEN }}

- name: Install Node.js 20
uses: actions/setup-node@v4
with:
node-version: 20
- name: Install frontend dependencies
run: |
cd frontend
npm install --frozen-lockfile
- name: Fix frontend lint issues
run: |
cd frontend
npm run lint:fix
# Commit and push changes if any
- name: Check for changes
id: git-check
run: |
git diff --quiet || echo "changes=true" >> $GITHUB_OUTPUT
- name: Commit and push if there are changes
if: steps.git-check.outputs.changes == 'true'
run: |
git config --local user.email "openhands@all-hands.dev"
git config --local user.name "OpenHands Bot"
git add -A
git commit -m "🤖 Auto-fix frontend linting issues"
git push
# Python lint fixes
lint-fix-python:
if: github.event.label.name == 'lint-fix'
name: Fix Python linting issues
runs-on: ubuntu-latest
permissions:
contents: write
pull-requests: write
steps:
- uses: actions/checkout@v4
with:
ref: ${{ github.head_ref }}
repository: ${{ github.event.pull_request.head.repo.full_name }}
fetch-depth: 0
token: ${{ secrets.GITHUB_TOKEN }}

- name: Set up python
uses: actions/setup-python@v5
with:
python-version: 3.12
cache: 'pip'
- name: Install pre-commit
run: pip install pre-commit==3.7.0
- name: Fix python lint issues
run: |
# Run all pre-commit hooks and continue even if they modify files (exit code 1)
pre-commit run --config ./dev_config/python/.pre-commit-config.yaml --files openhands/**/* evaluation/**/* tests/**/* || true
# Commit and push changes if any
- name: Check for changes
id: git-check
run: |
git diff --quiet || echo "changes=true" >> $GITHUB_OUTPUT
- name: Commit and push if there are changes
if: steps.git-check.outputs.changes == 'true'
run: |
git config --local user.email "openhands@all-hands.dev"
git config --local user.name "OpenHands Bot"
git add -A
git commit -m "🤖 Auto-fix Python linting issues"
git push
3 changes: 2 additions & 1 deletion .github/workflows/lint.yml
Original file line number Diff line number Diff line change
Expand Up @@ -30,10 +30,11 @@ jobs:
run: |
cd frontend
npm install --frozen-lockfile
- name: Lint
- name: Lint and TypeScript compilation
run: |
cd frontend
npm run lint
npm run make-i18n && tsc
# Run lint on the python code
lint-python:
Expand Down
Loading

0 comments on commit ed75313

Please sign in to comment.