xiaowei ea4b5a4dfe fix(distill): max_tokens 600→800 — Agnes推理模型JSON不再截断 ... engine.go: max_tokens 600→800 consolidate.go: max_tokens 300→800 根因: Agnes 2.0-flash是推理模型，max_tokens=600里大量是推理token， 正文只剩~300→JSON截断→parse error→蒸馏退化。 800确保推理+正文都够用。		2026-08-20 00:10:51 +08:00
..
api	feat(distill): P4 AAAK压缩索引 + P5 Markdown导出层	2026-08-12 01:37:27 +08:00
consolidate	fix: eps=1.0 (19 clusters from 1486 items), add col_vector() for FixedSizeListArray reading	2026-05-31 14:35:29 +08:00
distill	fix(distill): max_tokens 600→800 — Agnes推理模型JSON不再截断	2026-08-20 00:10:51 +08:00
distributed	…
governance	fix: Phase D/G/H 编译修复	2026-07-10 05:10:12 +08:00
metrics	…
models	feat: E1 BFS 扩展 + 生产部署完整套件	2026-06-02 18:58:38 +08:00
selfoptimize	fix: gap auto-close + conflict_muchen handler	2026-06-08 00:54:40 +08:00
storage	fix: episodes 持久化到 LanceDB（重启不再清零）	2026-08-02 23:41:37 +08:00