mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-21 05:07:04 +00:00
1a185f7926
Test case enhancements: - TC-RUNTIME-001: Add startup log error checking (CUDA, CUBLAS, CPU fallback) - TC-RUNTIME-002: Add GPU detection verification, CUDA init checks, error detection - TC-RUNTIME-003: Add server listening verification, runtime error checks - TC-INFERENCE-001: Add model loading logs, layer offload verification - TC-INFERENCE-002: Add inference error checking (CUBLAS/CUDA errors) - TC-INFERENCE-003: Add API request log verification, response time display Workflow enhancements: - Add judge_mode input (simple/llm/dual) to all workflows - Add judge_model input to specify LLM model for judging - Configurable via GitHub Actions UI without code changes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
123 lines
3.4 KiB
YAML
123 lines
3.4 KiB
YAML
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'
|
|
judge_mode:
|
|
description: 'Test judge mode'
|
|
required: false
|
|
default: 'simple'
|
|
type: choice
|
|
options:
|
|
- 'simple'
|
|
- 'llm'
|
|
- 'dual'
|
|
judge_model:
|
|
description: 'LLM model for judging (if llm/dual mode)'
|
|
required: false
|
|
default: 'gemma3:4b'
|
|
type: string
|
|
workflow_call: # Called by other workflows
|
|
inputs:
|
|
keep_container:
|
|
description: 'Keep container running for subsequent jobs'
|
|
required: false
|
|
default: false
|
|
type: boolean
|
|
judge_mode:
|
|
description: 'Test judge mode (simple, llm, dual)'
|
|
required: false
|
|
default: 'simple'
|
|
type: string
|
|
judge_model:
|
|
description: 'LLM model for judging'
|
|
required: false
|
|
default: 'gemma3:4b'
|
|
type: string
|
|
outputs:
|
|
result:
|
|
description: "Runtime test result"
|
|
value: ${{ jobs.runtime.outputs.result }}
|
|
|
|
jobs:
|
|
runtime:
|
|
name: Container & Runtime Tests
|
|
runs-on: self-hosted
|
|
outputs:
|
|
result: ${{ steps.runtime-tests.outcome }}
|
|
|
|
steps:
|
|
- name: Checkout
|
|
uses: actions/checkout@v4
|
|
|
|
- name: Setup Node.js
|
|
uses: actions/setup-node@v4
|
|
with:
|
|
node-version: '20'
|
|
|
|
- name: Install test runner dependencies
|
|
run: cd tests && npm ci
|
|
|
|
- name: Start container
|
|
run: |
|
|
cd docker
|
|
docker compose down 2>/dev/null || true
|
|
docker compose up -d
|
|
sleep 10
|
|
|
|
- name: Run runtime tests
|
|
id: runtime-tests
|
|
run: |
|
|
cd tests
|
|
|
|
# Build judge flags based on input
|
|
JUDGE_FLAGS=""
|
|
if [ "${{ inputs.judge_mode }}" = "simple" ] || [ -z "${{ inputs.judge_mode }}" ]; then
|
|
JUDGE_FLAGS="--no-llm"
|
|
elif [ "${{ inputs.judge_mode }}" = "dual" ]; then
|
|
JUDGE_FLAGS="--dual-judge --judge-model ${{ inputs.judge_model || 'gemma3:4b' }}"
|
|
else
|
|
# llm mode
|
|
JUDGE_FLAGS="--judge-model ${{ inputs.judge_model || 'gemma3:4b' }}"
|
|
fi
|
|
|
|
echo "Judge mode: ${{ inputs.judge_mode || 'simple' }}"
|
|
echo "Judge flags: $JUDGE_FLAGS"
|
|
|
|
# Progress goes to stderr (visible), JSON results go to file
|
|
npm run --silent dev -- run --suite runtime $JUDGE_FLAGS --output json > /tmp/runtime-results.json || true
|
|
|
|
echo "--- JSON Results ---"
|
|
cat /tmp/runtime-results.json
|
|
|
|
- name: Check test results
|
|
run: |
|
|
FAILED=$(jq '.summary.failed' /tmp/runtime-results.json)
|
|
echo "Failed tests: $FAILED"
|
|
if [ "$FAILED" -gt 0 ]; then
|
|
echo "::error::$FAILED runtime test(s) failed"
|
|
exit 1
|
|
fi
|
|
|
|
- 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"
|