admin-valentin/AIClient-2-API
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix(openai): 修复推理努力参数在快速模型上的设置

Browse source 
当使用快速模型时，始终使用默认的推理努力值，而不是从请求体中读取。这确保了快速模型的一致性行为。
This commit is contained in:
hex2077 2026-03-08 21:36:40 +08:00
parent dd8f30f5a8
commit d9396ef56c
2 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
VERSION
View file

@ -1 +1 @@
2.10.8.4
2.10.9

2
src/providers/openai/codex-core.js
View file

@ -380,7 +380,7 @@ export class CodexApiService {
service_tier: cleanedBody.service_tier || defaultServiceTier,
reasoning: {
...cleanedBody.reasoning,
effort: cleanedBody.reasoning?.effort || defaultReasoningEffort
effort: isFastModel ? defaultReasoningEffort : cleanedBody.reasoning?.effort
},
stream,
prompt_cache_key: cache.id