mirror of https://github.com/garrytan/gstack.git
59752fc510
callJudge/judge now return {result, meta} with SHA-based caching
(~$0.18/run savings when SKILL.md unchanged) and dynamic model
selection via EVAL_JUDGE_TIER env var. E2E tests pass --model from
EVAL_TIER to claude -p. outcomeJudge retains simple return type.
All 8 LLM eval test sites updated with real costs and costs[].
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| fixtures | ||
| helpers | ||
| gen-skill-docs.test.ts | ||
| lib-eval-cache.test.ts | ||
| lib-eval-cli.test.ts | ||
| lib-eval-cost.test.ts | ||
| lib-eval-format.test.ts | ||
| lib-eval-tier.test.ts | ||
| lib-sync-config.test.ts | ||
| lib-sync.test.ts | ||
| lib-util.test.ts | ||
| skill-e2e.test.ts | ||
| skill-llm-eval.test.ts | ||
| skill-parser.test.ts | ||
| skill-validation.test.ts | ||