chiguyong be45fe42c5 feat(compressor): CJK-aware token estimation + linear compress flow ... U1: Add estimate_text_tokens() module-level function with CJK 1:1 / ASCII 4:1 heuristic. Update estimate_tokens(), _summarize() pre-truncation, and react.py _should_compress() fallback to use it. Fixes 4x token underestimation for Chinese/Japanese/Korean conversations. U3: Rewrite compress() from recursive _compression_depth to linear flow (summarize -> aggressive -> truncate). Add _log_compression() structured logging with tokens_before/after/ratio/strategy. Remove _compression_depth parameter from compress() and _compress_aggressive(). Per plan: docs/plans/2026-07-02-003-feat-context-compressor-cjk-prefix-enhancement-plan.md		2026-07-03 07:32:57 +08:00
..
brainstorms	docs: add brainstorm/plan decision artifacts + plan progress update	2026-07-02 21:27:20 +08:00
plans	feat(compressor): CJK-aware token estimation + linear compress flow	2026-07-03 07:32:57 +08:00
research	feat: 私董会讨论模式 + 回测集成 + WS持久化修复	2026-06-17 23:52:53 +08:00
residual-review-findings	feat: UI/UE enhancement — streaming, sticky header, hover actions, calendar tokens	2026-07-01 12:51:45 +08:00
solutions	refactor: remove all emoji from source code (#20)	2026-07-03 02:46:40 +08:00
DEPLOYMENT-GITEA-ACTIONS.md	feat: 私董会讨论模式 + 回测集成 + WS持久化修复	2026-06-17 23:52:53 +08:00
GEO-INTEGRATION-GUIDE.md	feat: accumulated frontend enhancements, docs, and static assets	2026-06-14 16:35:01 +08:00