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>
This commit is contained in:
1 parent
4f7f07504a
commit
d765afe2ac
23 files changed
+1295
-394
No files matched your search
@@ -42,6 +42,7 @@ from app.gateway.routers import (
|
||||
compact_menu_overrides,
|
||||
dashboard_sessions,
|
||||
deep_research,
|
||||
direct_chat,
|
||||
external_llmwiki,
|
||||
feedback,
|
||||
fixed_questions,
|
||||
@@ -1803,6 +1804,9 @@ This gateway provides custom endpoints for models, MCP configuration, skills, an
|
||||
# 开放问答接口 /api/open/chat —— 无需登录,指定模型 + 智能体做问答,可关闭思考模式
|
||||
app.include_router(open_chat.router)
|
||||
|
||||
# 极速问答 /api/direct-chat/stream —— 直连大模型流式输出,不走 lead agent / 工具 / 技能
|
||||
app.include_router(direct_chat.router)
|
||||
|
||||
# 开放接口 /api/open/3qfx/ask —— 无需登录,按 taskId 直接发起 3qfx 第一次问答(后台运行,落成真实会话)
|
||||
app.include_router(open_3qfx.router)
|
||||
|
||||
|
||||
Reference in new issue
Block a user