Garry Tan 02925cfc7a feat: wire costs[] from modelUsage into eval results ...

Extract per-model token usage from resultLine.modelUsage (including
cache tokens and exact API cost), flow CostEntry[] through EvalCollector,
aggregate in finalize(). Extend CostEntry with cache_read_input_tokens,
cache_creation_input_tokens, cost_usd. computeCosts() prefers exact
cost_usd over MODEL_PRICING when available (~4x more accurate with
prompt caching).

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

2026-03-15 16:47:27 -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: wire costs[] from modelUsage into eval results

2026-03-15 16:47:27 -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-cache.test.ts

feat: add SHA-based eval caching with EVAL_CACHE=0 bypass

2026-03-15 09:39:26 -05:00

lib-eval-cli.test.ts

feat: unified gstack eval CLI with list, compare, push, cache, cost

2026-03-15 09:39:36 -05:00

lib-eval-cost.test.ts

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

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

lib-eval-format.test.ts

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

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

lib-eval-tier.test.ts

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

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

lib-sync-config.test.ts

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

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

lib-sync.test.ts

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

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

lib-util.test.ts

feat: add listEvalFiles, loadEvalResults, formatTimestamp to lib/util.ts

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

skill-e2e.test.ts

feat: wire costs[] from modelUsage into eval results

2026-03-15 16:47:27 -05:00

skill-llm-eval.test.ts

fix: lower planted-bug detection baselines and LLM judge thresholds for reliability

2026-03-14 05:16:17 -05:00

skill-parser.test.ts

feat: SKILL.md template system, 3-tier testing, DX tools (v0.3.3) (#41)

2026-03-13 21:08:12 -07:00

skill-validation.test.ts

feat: TODOS-aware skills, 2-tier Greptile replies, gitignore fix (#61)

2026-03-14 20:15:11 -07:00