gstack

mirror of https://github.com/garrytan/gstack.git synced 2026-05-05 05:05:08 +02:00

Files

T

Garry Tan 9bc6c9416f feat: add eval format validation, tier selection, cost tracking

- lib/eval-format.ts: StandardEvalResult interfaces, validateEvalResult(),
  normalizeFromLegacy/normalizeToLegacy round-trip converters
- lib/eval-tier.ts: EvalTier type, resolveTier/resolveJudgeTier from env,
  tierToModel mapping, TIER_ALIASES (haiku→fast, sonnet→standard, opus→full)
- lib/eval-cost.ts: MODEL_PRICING (last verified 2025-05-01), computeCosts(),
  formatCostDashboard(), aggregateCosts(), fallback for unknown models
- 42 tests across 3 test files

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-15 09:39:18 -05:00

fixtures

fix: 100% E2E pass — isolate test dirs, restart server, relax FP thresholds

2026-03-14 07:17:17 -05:00

helpers

feat: hook eval-store sync, use shared utils, add 30 lib tests

2026-03-15 02:02:54 -05:00

gen-skill-docs.test.ts

feat: template-ify all skills + E2E tests for plan-ceo-review, plan-eng-review, retro

2026-03-14 07:28:02 -05:00

lib-eval-cost.test.ts

feat: add eval format validation, tier selection, cost tracking