董宏凯andCursor d765afe2ac feat(turbo): add direct LLM chat mode with runtime toggle
Add 极速 mode that streams via /api/direct-chat without the lead agent stack,
plus VITE_TURBO_MODE_VISIBLE in runtime-config.js (default off). Also disable
global memory, tighten Qwen/vLLM thinking control for flash mode, and force
thinking off on the direct-chat endpoint.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-09 21:58:36 +08:00
2026-06-12 18:09:07 +08:00
2026-06-08 22:52:18 +08:00
2026-08-16 19:17:45 +08:00
fix
2026-09-04 11:16:38 +08:00
2026-05-22 20:40:36 +08:00
2026-07-27 19:16:12 +08:00
2026-09-06 20:25:14 +08:00
2026-08-10 14:26:49 +08:00
2026-07-15 16:13:03 +08:00
2026-08-10 15:11:47 +08:00
2026-08-30 01:25:20 +08:00
2026-05-28 17:14:01 +08:00
2026-05-28 17:14:01 +08:00
2026-06-29 16:59:23 +08:00
2026-06-29 16:59:23 +08:00
2026-06-29 16:59:23 +08:00
2026-06-29 16:59:23 +08:00
2026-06-29 18:08:09 +08:00
2026-06-29 18:08:09 +08:00
2026-06-29 16:59:23 +08:00
2026-06-29 16:59:23 +08:00
2026-05-22 20:40:36 +08:00
S
Description
deerflow-code
238 MiB
0 Stars 1 Watchers 0 Forks
Languages
Python 39.2%
TypeScript 35.9%
HTML 22.2%
CSS 1.5%
JavaScript 0.9%
Other 0.2%