mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-11 00:07:07 +00:00
4de7dd453b
Changes: 1. Update quick test to use gemma3:4b (was gemma2:2b) - Increased timeout to 60s for larger model 2. Implement Claude headless validation (validate.go) - Hybrid approach: simple checks first, then Claude validation ALWAYS runs - Claude validates response quality, coherence, relevance - Detects gibberish, errors, and malformed responses - Falls back to simple validation if Claude CLI unavailable - Verbose logging shows Claude validation results 3. Validation flow: - Step 1: Fast checks (empty response, token count) - Step 2: Claude AI analysis (runs regardless of simple check) - Claude result overrides simple checks - If Claude unavailable, uses simple validation only 4. Workflow improvements: - Remove useless GPU memory check step (server already stopped) - Cleaner workflow output Benefits: - Intelligent response quality validation - Catches subtle issues (gibberish, off-topic responses) - Better than hardcoded pattern matching - Graceful degradation when Claude unavailable
88 lines
2.4 KiB
YAML
88 lines
2.4 KiB
YAML
name: Tesla K80 Tests
|
|
|
|
on:
|
|
workflow_dispatch: # Manual trigger only
|
|
|
|
jobs:
|
|
test:
|
|
runs-on: self-hosted
|
|
|
|
timeout-minutes: 60
|
|
|
|
steps:
|
|
- name: Checkout code
|
|
uses: actions/checkout@v4
|
|
|
|
- name: Verify ollama binary exists
|
|
run: |
|
|
if [ ! -f ./ollama ]; then
|
|
echo "Error: ollama binary not found. Please run the build workflow first."
|
|
exit 1
|
|
fi
|
|
ls -lh ollama
|
|
|
|
- name: Build test-runner
|
|
run: |
|
|
cd cmd/test-runner
|
|
go mod init github.com/ollama/ollama/cmd/test-runner || true
|
|
go mod tidy
|
|
go build -o ../../test-runner .
|
|
cd ../..
|
|
ls -lh test-runner
|
|
|
|
- name: Validate test configuration
|
|
run: |
|
|
./test-runner validate --config test/config/quick.yaml
|
|
|
|
- name: Run quick tests
|
|
run: |
|
|
./test-runner run --profile quick --config test/config/quick.yaml --output test-report-quick --verbose
|
|
timeout-minutes: 10
|
|
|
|
- name: Check quick test results
|
|
run: |
|
|
if ! jq -e '.summary.failed == 0' test-report-quick.json; then
|
|
echo "Quick tests failed!"
|
|
jq '.results[] | select(.status == "FAILED")' test-report-quick.json
|
|
exit 1
|
|
fi
|
|
echo "Quick tests passed!"
|
|
|
|
- name: Upload quick test results
|
|
if: always()
|
|
uses: actions/upload-artifact@v4
|
|
with:
|
|
name: quick-test-results
|
|
path: |
|
|
test-report-quick.json
|
|
test-report-quick.md
|
|
ollama.log
|
|
retention-days: 7
|
|
|
|
- name: Run full tests (if quick tests passed)
|
|
if: success()
|
|
run: |
|
|
./test-runner run --profile full --config test/config/models.yaml --output test-report-full --verbose
|
|
timeout-minutes: 45
|
|
|
|
- name: Check full test results
|
|
if: success()
|
|
run: |
|
|
if ! jq -e '.summary.failed == 0' test-report-full.json; then
|
|
echo "Full tests failed!"
|
|
jq '.results[] | select(.status == "FAILED")' test-report-full.json
|
|
exit 1
|
|
fi
|
|
echo "All tests passed!"
|
|
|
|
- name: Upload full test results
|
|
if: always()
|
|
uses: actions/upload-artifact@v4
|
|
with:
|
|
name: full-test-results
|
|
path: |
|
|
test-report-full.json
|
|
test-report-full.md
|
|
ollama.log
|
|
retention-days: 14
|