th-kim0823 cd5b1e3bfc spec(fb-39): eval foundation design (P@k metric) ...

- AggregateMetrics 에 precision_at_k_chunk: BTreeMap<u32, f32>
  (P@5, P@10) 추가, binary relevance via expected_chunk_ids
- Denominator = k 고정 (hits.len() < k 도 precision 손실 간주)
- Empty expected_chunk_ids query 는 skip (hit_at_k 동일 정책)
- Lever 적용 (chunk policy / RRF / cross-encoder / embedding) 은
  본 spec 범위 외 — fb-39b 이후 별도 task
- Golden set schema 무변경, shipped fixtures 헤더 주석만 강화

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-10 22:05:09 +09:00

..

2026-04-27-kebab-final-form-design.md

docs(fb-42): wire schema + README + SMOKE + design + SKILL + INDEX

2026-05-10 21:07:36 +09:00

2026-05-04-component-docs-design.md

docs(spec): component documentation design (2026-05-04)

2026-05-04 14:47:28 +09:00

2026-05-04-p9-fb-23-incremental-ingest-design.md

spec(p9-fb-23): incremental ingest — skip unchanged docs

2026-05-04 17:27:06 +00:00

2026-05-04-p9-fb-24-tui-affordances-design.md

spec(p9-fb-24): TUI status/key bar + Library header + page scroll

2026-05-04 16:11:17 +00:00

2026-05-05-p9-fb-25-config-include-removal-design.md

spec(p9-fb-25): config workspace.include 제거 + 지원 형식 가시성

2026-05-05 11:21:42 +00:00

2026-05-07-fb-26-fb-28-agent-ux-design.md

docs(spec): fb-26 + fb-28 + schema-sync design doc

2026-05-07 19:11:47 +09:00

2026-05-07-p9-fb-27-introspection-and-error-wire-design.md

📝 docs(spec): p9-fb-27 introspection + error wire 설계 문서

2026-05-07 10:58:24 +09:00

2026-05-07-p9-fb-30-mcp-server-design.md

📝 docs(spec): p9-fb-30 MCP server (stdio) 설계 문서

2026-05-07 14:44:09 +09:00

2026-05-07-p9-fb-31-single-file-stdin-ingest-design.md

📝 docs(spec): p9-fb-31 single-file / stdin ingest 설계 문서

2026-05-07 17:29:30 +09:00

2026-05-08-p9-fb-32-stale-doc-indicator-design.md

spec(fb-32): stale doc indicator — design

2026-05-08 18:00:10 +09:00

2026-05-09-p9-fb-33-streaming-ask-design.md

spec(fb-33): streaming ask (ndjson delta) — design

2026-05-09 14:10:08 +09:00

2026-05-09-p9-fb-34-output-budget-controls-design.md

spec(fb-34): output budget controls — design

2026-05-09 17:36:51 +09:00

2026-05-09-p9-fb-35-verbatim-fetch-design.md

fix(fb-35): address PR #126 round 1 review

2026-05-10 00:45:29 +09:00

2026-05-10-p9-fb-36-search-filters-design.md

spec(fb-36): search filter args — design

2026-05-10 03:26:40 +09:00

2026-05-10-p9-fb-37-trace-and-stats-design.md

spec(fb-37): trace + stats design

2026-05-10 12:05:31 +09:00

2026-05-10-p9-fb-38-score-semantics-design.md

spec(fb-38): score semantics design

2026-05-10 17:40:47 +09:00

2026-05-10-p9-fb-39-eval-foundation-design.md

spec(fb-39): eval foundation design (P@k metric)

2026-05-10 22:05:09 +09:00

2026-05-10-p9-fb-40-fact-grounded-answer-design.md

spec(fb-40): fact-grounded answer design

2026-05-10 18:55:05 +09:00

2026-05-10-p9-fb-42-bulk-multi-query-design.md

spec(fb-42): bulk multi-query design (rerank hint deferred)

2026-05-10 20:05:27 +09:00