wanwu/deer-flow
1
0
Fork 0
mirror of https://gitee.com/wanwujie/deer-flow synced 2026-04-20 12:54:45 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add reasoning_effort configuration support for Doubao/GPT-5 models (#947)

Browse Source 
* feat: Add reasoning effort configuration support

* Add `reasoning_effort` parameter to model config and agent initialization
* Support reasoning effort levels (minimal/low/medium/high) for Doubao/GPT-5 models
* Add UI controls in input box for reasoning effort selection
* Update doubao-seed-1.8 example config with reasoning effort support

Fixes & Cleanup:
* Ensure UTF-8 encoding for file operations
* Remove unused imports

* fix: set reasoning_effort to None for unsupported models

* fix: unit test error

* Update frontend/src/components/workspace/input-box.tsx

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
This commit is contained in:
Zhiyunyao
2026-03-02 20:49:41 +08:00
committed by GitHub
parent e399d09e8f
commit a138d5388a
21 changed files with 212 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
backend/tests/test_lead_agent_model_resolution.py
View File

@@ -84,9 +84,10 @@ def test_make_lead_agent_disables_thinking_when_model_does_not_support_it(monkey
captured: dict[str, object] = {}
def _fake_create_chat_model(*, name, thinking_enabled):
def _fake_create_chat_model(*, name, thinking_enabled, reasoning_effort=None):
captured["name"] = name
captured["thinking_enabled"] = thinking_enabled
captured["reasoning_effort"] = reasoning_effort
return object()
monkeypatch.setattr(lead_agent_module, "create_chat_model", _fake_create_chat_model)