Grayscale/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: treat reasoning_effort="none" as thinking disabled and route gemma to Gemini provider

Browse Source 
- Do not send reasoning_effort="none" to APIs (prevents 400 on gemma/Gemini)
- Treat "none" as thinking disabled in thinking_style, Kimi, and reasoning_content backfill paths
- Fix Anthropic extended thinking not respecting "none"
- Fix Azure OpenAI temperature suppression and reasoning body for "none"
- Fix Codex reasoning body for "none"
- Add "gemma" keyword to Gemini ProviderSpec for correct auto routing
This commit is contained in:
masterlyj
2026-04-29 15:41:11 +08:00
committed by Xubin Ren
parent 28f9bbff31
commit b94bc18e59
5 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nanobot/providers/openai_codex_provider.py
+1 -1
View File
@@ -60,7 +60,7 @@ class OpenAICodexProvider(LLMProvider):
"tool_choice": tool_choice or "auto",
"parallel_tool_calls": True,
}
if reasoning_effort:
if reasoning_effort and reasoning_effort.lower() != "none":
body["reasoning"] = {"effort": reasoning_effort}
if tools:
body["tools"] = convert_tools(tools)