Split monolithic workflow into modular components

Separate workflows for flexibility:
- build.yml: Build verification (standalone + reusable)
- runtime.yml: Container & runtime tests with container lifecycle
- inference.yml: Inference tests with optional container management
- full-pipeline.yml: Orchestrates all stages with LLM judge

Each workflow can be triggered independently for targeted testing,
or run the full pipeline for complete validation.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Shang Chieh Tseng
2025-12-15 17:57:11 +08:00
parent 54248f42b0
commit fb01b8b1ca
4 changed files with 244 additions and 60 deletions

51
.github/workflows/build.yml vendored Normal file
View File

@@ -0,0 +1,51 @@
name: Build Verification
on:
workflow_dispatch: # Manual trigger
workflow_call: # Called by other workflows
outputs:
result:
description: "Build test result"
value: ${{ jobs.build.outputs.result }}
jobs:
build:
name: Build Verification
runs-on: self-hosted
outputs:
result: ${{ steps.build-tests.outcome }}
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: '20'
- name: Install test runner dependencies
run: cd tests && npm ci
- name: Run build tests
id: build-tests
run: |
cd tests
# Progress goes to stderr (visible), JSON results go to file
npm run --silent dev -- run --suite build --no-llm --output json > /tmp/build-results.json || true
echo "--- JSON Results ---"
cat /tmp/build-results.json
# Check if any tests failed
if grep -q '"pass": false' /tmp/build-results.json; then
echo "Some build tests failed"
exit 1
fi
- name: Upload build results
uses: actions/upload-artifact@v4
if: always()
with:
name: build-test-results
path: /tmp/build-results.json

View File

@@ -1,82 +1,67 @@
name: Build and Test
name: Full Pipeline
on:
workflow_dispatch: # Manual trigger only
workflow_dispatch: # Manual trigger
inputs:
skip_llm_judge:
description: 'Skip LLM judge evaluation'
required: false
default: 'false'
type: choice
options:
- 'true'
- 'false'
env:
TESTLINK_URL: http://localhost:8090
TESTLINK_PROJECT_ID: "1"
OLLAMA_HOST: http://localhost:11434
jobs:
build:
name: Build Verification
runs-on: self-hosted
uses: ./.github/workflows/build.yml
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: '20'
- name: Install test runner dependencies
run: cd tests && npm ci
- name: Run build tests
id: build-tests
run: |
cd tests
# Progress goes to stderr (visible), JSON results go to file
npm run --silent dev -- run --suite build --no-llm --output json > /tmp/build-results.json || true
echo "--- JSON Results ---"
cat /tmp/build-results.json
# Check if any tests failed
if grep -q '"passed": false' /tmp/build-results.json; then
echo "Some build tests failed"
exit 1
fi
- name: Upload build results
uses: actions/upload-artifact@v4
if: always()
with:
name: build-test-results
path: /tmp/build-results.json
runtime:
name: Container & Runtime Tests
start-container:
name: Start Container
runs-on: self-hosted
needs: build
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: '20'
- name: Install test runner dependencies
run: cd tests && npm ci
- name: Start container
run: |
cd docker
docker compose down 2>/dev/null || true
docker compose up -d
echo "Waiting for container to be ready..."
sleep 10
- name: Verify container health
run: |
docker ps
curl -s http://localhost:11434/api/tags || echo "Ollama not ready yet, continuing..."
runtime:
name: Runtime Tests
runs-on: self-hosted
needs: start-container
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: '20'
- name: Install test runner dependencies
run: cd tests && npm ci
- name: Run runtime tests
id: runtime-tests
run: |
cd tests
# Progress goes to stderr (visible), JSON results go to file
npm run --silent dev -- run --suite runtime --no-llm --output json > /tmp/runtime-results.json || true
echo "--- JSON Results ---"
@@ -110,7 +95,6 @@ jobs:
id: inference-tests
run: |
cd tests
# Progress goes to stderr (visible), JSON results go to file
npm run --silent dev -- run --suite inference --no-llm --output json > /tmp/inference-results.json || true
echo "--- JSON Results ---"
@@ -127,7 +111,7 @@ jobs:
name: LLM Judge Evaluation
runs-on: self-hosted
needs: [build, runtime, inference]
if: always()
if: ${{ inputs.skip_llm_judge != 'true' }}
steps:
- name: Checkout
@@ -150,9 +134,6 @@ jobs:
run: |
cd tests
echo "Running LLM judge evaluation..."
# Re-run all tests with LLM judge using local Ollama
# Progress goes to stderr (visible), JSON results go to file
npm run --silent dev -- run --output json > /tmp/llm-judged-results.json || true
echo "--- JSON Results ---"
@@ -183,13 +164,13 @@ jobs:
- name: Summary
run: |
echo "## Build and Test Summary" >> $GITHUB_STEP_SUMMARY
echo "## Full Pipeline Summary" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "| Stage | Status |" >> $GITHUB_STEP_SUMMARY
echo "|-------|--------|" >> $GITHUB_STEP_SUMMARY
echo "| Build Verification | ${{ needs.build.result }} |" >> $GITHUB_STEP_SUMMARY
echo "| Container & Runtime | ${{ needs.runtime.result }} |" >> $GITHUB_STEP_SUMMARY
echo "| Runtime Tests | ${{ needs.runtime.result }} |" >> $GITHUB_STEP_SUMMARY
echo "| Inference Tests | ${{ needs.inference.result }} |" >> $GITHUB_STEP_SUMMARY
echo "| LLM Judge Evaluation | ${{ needs.llm-judge.result }} |" >> $GITHUB_STEP_SUMMARY
echo "| LLM Judge | ${{ needs.llm-judge.result }} |" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "Commit: ${{ github.sha }}" >> $GITHUB_STEP_SUMMARY

78
.github/workflows/inference.yml vendored Normal file
View File

@@ -0,0 +1,78 @@
name: Inference Tests
on:
workflow_dispatch: # Manual trigger
inputs:
use_existing_container:
description: 'Use existing running container'
required: false
default: 'false'
type: choice
options:
- 'true'
- 'false'
workflow_call: # Called by other workflows
inputs:
use_existing_container:
description: 'Container is already running'
required: false
default: false
type: boolean
outputs:
result:
description: "Inference test result"
value: ${{ jobs.inference.outputs.result }}
env:
OLLAMA_HOST: http://localhost:11434
jobs:
inference:
name: Inference Tests
runs-on: self-hosted
outputs:
result: ${{ steps.inference-tests.outcome }}
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: '20'
- name: Install test runner dependencies
run: cd tests && npm ci
- name: Start container (if needed)
if: ${{ inputs.use_existing_container != 'true' && inputs.use_existing_container != true }}
run: |
cd docker
docker compose down 2>/dev/null || true
docker compose up -d
sleep 10
- name: Run inference tests
id: inference-tests
run: |
cd tests
# Progress goes to stderr (visible), JSON results go to file
npm run --silent dev -- run --suite inference --no-llm --output json > /tmp/inference-results.json || true
echo "--- JSON Results ---"
cat /tmp/inference-results.json
- name: Upload inference results
uses: actions/upload-artifact@v4
if: always()
with:
name: inference-test-results
path: /tmp/inference-results.json
- name: Stop container (if we started it)
if: ${{ always() && inputs.use_existing_container != 'true' && inputs.use_existing_container != true }}
run: |
cd docker
docker compose down || true
echo "Container stopped"

74
.github/workflows/runtime.yml vendored Normal file
View File

@@ -0,0 +1,74 @@
name: Runtime Tests
on:
workflow_dispatch: # Manual trigger
inputs:
keep_container:
description: 'Keep container running after tests'
required: false
default: 'false'
type: choice
options:
- 'true'
- 'false'
workflow_call: # Called by other workflows
inputs:
keep_container:
description: 'Keep container running for subsequent jobs'
required: false
default: false
type: boolean
outputs:
result:
description: "Runtime test result"
value: ${{ jobs.runtime.outputs.result }}
jobs:
runtime:
name: Container & Runtime Tests
runs-on: self-hosted
outputs:
result: ${{ steps.runtime-tests.outcome }}
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: '20'
- name: Install test runner dependencies
run: cd tests && npm ci
- name: Start container
run: |
cd docker
docker compose down 2>/dev/null || true
docker compose up -d
sleep 10
- name: Run runtime tests
id: runtime-tests
run: |
cd tests
# Progress goes to stderr (visible), JSON results go to file
npm run --silent dev -- run --suite runtime --no-llm --output json > /tmp/runtime-results.json || true
echo "--- JSON Results ---"
cat /tmp/runtime-results.json
- name: Upload runtime results
uses: actions/upload-artifact@v4
if: always()
with:
name: runtime-test-results
path: /tmp/runtime-results.json
- name: Stop container
if: ${{ inputs.keep_container != 'true' && inputs.keep_container != true }}
run: |
cd docker
docker compose down || true
echo "Container stopped"