oliver 5efac74f87 fix(chat): always persist reasoning_content on assistant event_payload ... Non-thinking profiles previously wrote model reasoning only as separate event_type=reasoning rows whose event_payload held chunk_index metadata, so JSON inspection showed tool payloads but no reasoning_content key. Store the full merged reasoning blob on the primary assistant row whenever present (same shape as thinking mode). Update instruction-leak filtering to scan event_payload.reasoning_content as well as legacy reasoning rows. Co-authored-by: Cursor <cursoragent@cursor.com>		2026-05-12 23:02:38 +08:00
..
static	fix(chat): default reasoning fold on for new browsers and bump chat.js cache	2026-05-12 20:29:58 +08:00
__init__.py	重构仓库目录为统一的 runtime 分层并清理历史 openclaw 残留。	2026-04-25 01:24:23 +08:00
chat_api.py	fix(chat): always persist reasoning_content on assistant event_payload	2026-05-12 23:02:38 +08:00
mcp_e2e_probe.py	重构仓库目录为统一的 runtime 分层并清理历史 openclaw 残留。	2026-04-25 01:24:23 +08:00
models_api.py	feat(models): add toggle to hide chat model selector	2026-05-06 18:58:01 +08:00
routes.py	fix(admin): run_command toggle GET matches DB absent; add disabled hint	2026-05-12 19:17:13 +08:00
skills_api.py	Expose skill role binding stored vs env override in Admin API	2026-05-11 15:59:51 +08:00