fix(mem0): disable thinking for fact extraction calls
Fact extraction inherited the instance thinking_budget (10000), causing the model to spend tokens on thinking instead of outputting JSON. The response content was empty, failing JSON parse every time. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -177,6 +177,7 @@ class Mem0MemoryStore:
|
||||
model=model,
|
||||
max_tokens=2000,
|
||||
temperature=0.3,
|
||||
thinking_budget=0,
|
||||
)
|
||||
text = (response.content or "").strip()
|
||||
if text.startswith("```"):
|
||||
|
||||
Reference in New Issue
Block a user