Shang Chieh Tseng e06deff40f Enhance LLM judge prompt and add separate verdict display ...

- Add step results, timing context, and build notes to LLM prompt
- LLM now sees exit codes, durations, and simple judge result
- Add guidance that long build times within timeout are acceptable

- Add separate simple/LLM verdict tracking in dual-judge mode
- Console output shows both Simple and LLM pass/fail status
- JSON summary includes separate simple/llm breakdown
- Each test report includes simplePass/llmPass fields

This helps distinguish between simple judge failures (exit code != 0)
and LLM judge failures (semantic analysis), making debugging easier.

2025-12-17 15:04:05 +08:00

..

src

Enhance LLM judge prompt and add separate verdict display

2025-12-17 15:04:05 +08:00

testcases

Fix runtime test log checks that require model loading

2025-12-17 00:00:24 +08:00

package-lock.json

Add GitHub Actions CI/CD pipeline and test framework

2025-12-15 14:06:44 +08:00

package.json

Add GitHub Actions CI/CD pipeline and test framework

2025-12-15 14:06:44 +08:00

tsconfig.json

Add GitHub Actions CI/CD pipeline and test framework

2025-12-15 14:06:44 +08:00