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
@@ -33,6 +33,16 @@ concurrency:
|
||||
fail_open: true
|
||||
|
||||
models:
|
||||
- name: MiniMax-M2.7
|
||||
display_name: MiniMax-M2.7
|
||||
use: langchain_openai:ChatOpenAI
|
||||
model: MiniMax-M2.7
|
||||
api_key: sk-cp-mrsAGtzDpUl0TpOBPVoiRG_pWF1kDDN9_mDAnONBs6HIPcNUexSKtSbx2QOxfKBvJT6Xw6hDTV6hdkJYFWfNA8UtHQ08TiGJiosdRoW6q1sGb6Cb7D85NHk
|
||||
base_url: https://api.minimaxi.com/v1
|
||||
max_tokens: 4096
|
||||
temperature: 1.0
|
||||
supports_vision: true
|
||||
supports_thinking: true
|
||||
- name: MiniMax-M2.7-fash
|
||||
display_name: MiniMax-M2.7-fash
|
||||
use: langchain_openai:ChatOpenAI
|
||||
@@ -466,7 +476,7 @@ checkpointer:
|
||||
# 三层覆盖优先级(高->低):
|
||||
# users/{user_id}/memory_config.json > .deer-flow/memory_user_overrides.json > 此处
|
||||
memory:
|
||||
enabled: true
|
||||
enabled: false # 临时关闭跨会话记忆(提取/注入/Hindsight 召回与 retain、memory 工具)
|
||||
version:
|
||||
v1 # 记忆版本: 'v1'(原版 DeerFlow, memory.json + LLM 自动提取)
|
||||
# 'v2'(USER.md/MEMORY.md + 可选 Hindsight)
|
||||
|
||||
Reference in new issue
Block a user