summaryrefslogtreecommitdiff
path: root/packages
diff options
context:
space:
mode:
authorFuwn <[email protected]>2025-09-26 03:42:54 -0700
committerFuwn <[email protected]>2025-09-26 03:42:54 -0700
commit91a143a885d02ac68d8d6814b0afc10efaf84fc5 (patch)
treeef7c71c03821cdba8fca108f844199b7b60be639 /packages
parentfeat(gateway:commands): Add CRP command (diff)
downloadumabotdiscord-91a143a885d02ac68d8d6814b0afc10efaf84fc5.tar.xz
umabotdiscord-91a143a885d02ac68d8d6814b0afc10efaf84fc5.zip
fix(gateway:moderationAgent): Update guidelines
Diffstat (limited to 'packages')
-rw-r--r--packages/gateway/src/listeners/moderationAgent/utilities.ts2
1 files changed, 2 insertions, 0 deletions
diff --git a/packages/gateway/src/listeners/moderationAgent/utilities.ts b/packages/gateway/src/listeners/moderationAgent/utilities.ts
index 26ba55c..adc3fa2 100644
--- a/packages/gateway/src/listeners/moderationAgent/utilities.ts
+++ b/packages/gateway/src/listeners/moderationAgent/utilities.ts
@@ -86,6 +86,8 @@ Respond with a JSON object containing:
If no violation is found, set "violation" to false and provide a brief explanation of why the message is acceptable.
CRITICAL: Only analyze the content in quotes above (the current message). Ignore all content in the chat history section. If the current message is innocent (like "true", "yes", "no", etc.) but appears after inappropriate content in the chat history, do NOT flag it.
+
+CRITICAL: DO NOT FLAG VAGUE OR PHILOSOPHICAL CONTENT. If a message is vague, philosophical, abstract, or unclear in meaning, do NOT flag it. Only flag content that clearly violates specific rules. When in doubt, do NOT flag.
`;
const response = await fetch(
"https://openrouter.ai/api/v1/chat/completions",