fix: disable qwen3.5 thinking mode for analyzer (was consuming all tokens), increase timeout
This commit is contained in:
@@ -134,6 +134,7 @@ Analyze these results and suggest 1-3 specific modifications to the config. Retu
|
||||
{"role": "user", "content": user_prompt},
|
||||
],
|
||||
"stream": False,
|
||||
"think": False,
|
||||
"options": {
|
||||
"temperature": 0.7,
|
||||
"num_predict": 4096,
|
||||
@@ -141,7 +142,7 @@ Analyze these results and suggest 1-3 specific modifications to the config. Retu
|
||||
}
|
||||
|
||||
print(f" Calling LLM ({MODEL} on Mac Mini)...")
|
||||
resp = requests.post(f"{OLLAMA_URL}/api/chat", json=payload, timeout=300)
|
||||
resp = requests.post(f"{OLLAMA_URL}/api/chat", json=payload, timeout=600)
|
||||
resp.raise_for_status()
|
||||
content = resp.json()["message"]["content"]
|
||||
|
||||
|
||||
Reference in New Issue
Block a user