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

..

ai_writing

fix: retry httpx timeout family as transient LLM errors

2026-08-30 15:53:51 +08:00

canvas_agent

智能选中文字

2026-05-16 22:00:34 +08:00

deep_research

feat(deep-research): 强化任务链路可靠性并接入 agentfx 报告助手种子

2026-09-04 23:18:52 +08:00

lead_agent

feat(turbo): add direct LLM chat mode with runtime toggle

2026-09-09 21:58:36 +08:00

memory

禁用了知识库技能，添加了知识库memory

2026-06-08 18:35:05 +08:00

middlewares

fix: retry httpx timeout family as transient LLM errors

2026-08-30 15:53:51 +08:00

roundtable_orchestrator

代码提交

2026-08-24 20:47:31 +08:00

__init__.py

新增用户意图确认功能

2026-05-13 14:36:44 +08:00

factory.py

新增用户意图确认功能

2026-05-13 14:36:44 +08:00

features.py

新增用户意图确认功能

2026-05-13 14:36:44 +08:00

fixed_answer_agent.py

feat: add fixed questions and improve authentication

2026-08-21 17:58:39 +08:00

thread_state.py

feat: 上下文压缩支持状态持久化缓存,前端过滤隐藏消息

2026-06-16 22:16:06 +08:00