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

fix: instruct LLM to never quote toxic content in note_updates

Browse Source 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
AJ Isaacs
2026-03-02 21:58:04 -05:00
parent 09f83f8c2f
commit f75a3ca3f4
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
utils/llm_client.py
View File

@@ -86,7 +86,7 @@ ANALYSIS_TOOL = {
},
"note_update": {
"type": ["string", "null"],
"description": "Brief new observation about this user's style/behavior for future reference, or null if nothing new.",
"description": "Brief new observation about this user's style/behavior for future reference, or null if nothing new. NEVER quote toxic language — describe patterns abstractly (e.g. 'uses personal insults when frustrated').",
},
"detected_game": {
"type": ["string", "null"],
@@ -189,7 +189,7 @@ CONVERSATION_TOOL = {
},
"note_update": {
"type": ["string", "null"],
"description": "New observation about this user's pattern, or null.",
"description": "New observation about this user's pattern, or null. NEVER quote toxic language — describe patterns abstractly.",
},
"detected_game": {
"type": ["string", "null"],