aj/Breehavior-Monitor
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add max_tokens=1024 to LLM analysis calls

Browse Source 
The analyze_message and raw_analyze methods had no max_tokens limit,
causing thinking models (Qwen3-VL-32B-Thinking) to generate unlimited
reasoning tokens before responding — taking 5+ minutes per message.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
AJ Isaacs
2026-02-21 14:17:59 -05:00
parent 1151b705c0
commit b410200146
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
utils/llm_client.py
+2
View File
@@ -123,6 +123,7 @@ class LLMClient:
tools=[ANALYSIS_TOOL], tools=[ANALYSIS_TOOL],
tool_choice={"type": "function", "function": {"name": "report_analysis"}}, tool_choice={"type": "function", "function": {"name": "report_analysis"}},
temperature=0.1, temperature=0.1,
max_tokens=1024,
) )
choice = response.choices[0] choice = response.choices[0]
@@ -255,6 +256,7 @@ class LLMClient:
tools=[ANALYSIS_TOOL], tools=[ANALYSIS_TOOL],
tool_choice={"type": "function", "function": {"name": "report_analysis"}}, tool_choice={"type": "function", "function": {"name": "report_analysis"}},
temperature=0.1, temperature=0.1,
max_tokens=1024,
) )
choice = response.choices[0] choice = response.choices[0]