Oliver/presenton
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge pull request #206 from presenton/fix/llm-client-issues

Browse source 
fix: only add enable thinking false if disable thinking is set to true for custom models
This commit is contained in:
Saurav Niraula 2025-08-12 06:46:25 +05:45 • committed by GitHub
commit 6937885b47
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 20 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
servers/fastapi/services/llm_client.py
View file

@ -387,7 +387,11 @@ class LLMClient:
max_tokens: Optional[int] = None,
depth: int = 0,
):
extra_body = {"enable_thinking": not self.disable_thinking()}
extra_body = (
{"enable_thinking": False}
if self.disable_thinking()
else None
)
return await self._generate_openai(
model=model,
messages=messages,
@ -754,7 +758,11 @@ class LLMClient:
max_tokens: Optional[int] = None,
depth: int = 0,
):
extra_body = {"enable_thinking": not self.disable_thinking()}
extra_body = (
{"enable_thinking": False}
if self.disable_thinking()
else None
)
return await self._generate_openai_structured(
model=model,
messages=messages,
@ -1071,7 +1079,11 @@ class LLMClient:
max_tokens: Optional[int] = None,
depth: int = 0,
):
extra_body = {"enable_thinking": not self.disable_thinking()}
extra_body = (
{"enable_thinking": False}
if self.disable_thinking()
else None
)
return self._stream_openai(
model=model,
messages=messages,
@ -1484,7 +1496,11 @@ class LLMClient:
max_tokens: Optional[int] = None,
depth: int = 0,
):
extra_body = {"enable_thinking": not self.disable_thinking()}
extra_body = (
{"enable_thinking": False}
if self.disable_thinking()
else None
)
return self._stream_openai_structured(
model=model,
messages=messages,