ko-qmd 2.8.3-ko.4 → 2.8.3-ko.5

package/CHANGELOG.md

@@ -2,6 +2,45 @@
 
 ## [Unreleased]
 
+## [2.8.3-ko.5] - 2026-09-24
+
+Rerank gets an input cap. Truncating each document to 128 tokens keeps KB
+goldset quality (Hit@5 0.97 / Recall@5 0.77) while cutting cold rerank p90 from
+3.6s to 0.9s on an M3 Max. The cap can be set daemon-wide
+(`QMD_RERANK_MAX_DOC_TOKENS`) or per request (`rerankMaxDocTokens` on REST
+`/query` and SDK `search()`). The README is now a Korean guide to ko-qmd itself,
+and the English reference lives in `docs/REFERENCE.md`.
+
+### Changes
+
+- README.md is rewritten in Korean around ko-qmd itself: what differs from
+  upstream, install, quick start, MCP/REST/SDK, environment variables and the
+  maintenance guide that used to live in `README.ko.md` (now removed). The
+  upstream-derived English reference (full CLI, MCP tool parameters, SDK API,
+  score fusion) moved to `docs/REFERENCE.md`, with install and import names
+  switched to `ko-qmd`.
+- REST `POST /query` and SDK `search()` take `rerankMaxDocTokens`, a
+  per-request rerank doc token cap. For that request it overrides the daemon's
+  `QMD_RERANK_MAX_DOC_TOKENS`, and it never raises the context budget. A caller
+  like the KB seam can then turn a capped rerank on for one machine without
+  changing the daemon's env. The rerank cache key follows the effective cap
+  (request, else env). Invalid values (non-integer, ≤ 0, strings) are ignored.
+- `QMD_RERANK_MAX_DOC_TOKENS` caps the tokens of each document sent to the
+  reranker, below the context budget. Unset keeps today's behaviour. On the KB
+  goldset (40 queries, candidateLimit 15), a cap of 128 keeps quality at
+  Hit@5 0.97 / Recall@5 0.77 against 0.95 / 0.76 uncapped. It cuts cold p90 from
+  3623ms to 897ms on an M3 Max and from 4720ms to 2192ms on another Apple Silicon
+  Mac. The cap is part of the rerank cache key, so capped and uncapped scores
+  never mix. Listed in `qmd doctor`.
+- `scripts/dogfood.sh` warms the embedding model with one vec query after
+  every daemon restart (deploy and `--restore`). A fresh daemon's first vec
+  query took 15.5s, so the first KB seam search after a restart hit its 20s
+  limit and fell back to rg. A failed warm-up is a warning, not a failed restart.
+- `scripts/dogfood.sh` waits for the *restarted* daemon. `launchctl kickstart -k`
+  returns while the old process is still shutting down and answering `/health`,
+  so the restart looked done ~9s before the new process listened. A `/health`
+  whose `uptime` predates the kickstart is now treated as the old process.
+
 ## [2.8.3-ko.4] - 2026-09-24
 
 Korean documents are now chunked at their real token budget, and Hangul