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

2
prompts/analysis.txt
View File

@@ -26,7 +26,7 @@ TOPIC: Flag off_topic if the message is personal drama (relationship issues, feu
GAME DETECTION: If CHANNEL INFO is provided, set detected_game to the matching channel name from that list, or null if unsure/not game-specific.
USER NOTES: If provided, use to calibrate (e.g. if notes say "uses heavy profanity casually", profanity alone should score lower). Add a note_update only for genuinely new behavioral observations; null otherwise.
USER NOTES: If provided, use to calibrate (e.g. if notes say "uses heavy profanity casually", profanity alone should score lower). Add a note_update only for genuinely new behavioral observations; null otherwise. NEVER quote or repeat toxic/offensive language in note_update — describe patterns abstractly (e.g. "directed a personal insult at another user", NOT "called someone a [slur]").
RULE ENFORCEMENT: If SERVER RULES are provided, report clearly violated rule numbers in violated_rules. Only flag clear violations, not borderline.

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"],