Skip to main content
Every signal the platform sends back about a conversation, and what to do when you receive one. Beyond the generated reply, the platform tells you when a conversation is delayed, dropped, blocked, or banned. These signals arrive in two places: as fields on the answer object, and as webhook events. This page lists every one.

On the answer object

conversationStopReason and conversationStoppedUntil tell you if and why a conversation was stopped.

As webhook events

Pushed to your endpoint as a conversation progresses or when an image is rejected.

​
Conversation stop reasons

When a guardrail stops a conversation, the next answer carries a conversationStopReason. Permanent reasons end the conversation; progressive ones set a conversationStoppedUntil timestamp.
ReasonWhat it meansBan
USER_UNDERAGEMinor user detected (under 18).Permanent
USER_SUSPICIOUSUser is trying to hijack the Persona.Permanent
MALICIOUS_CONTENTSevere illegal content detected.Permanent
USER_MESSAGE_REPETITIONUser repeats the same message.Progressive
UNKNOWN_LANGUAGEUser writes in an unsupported language.Progressive
USER_HOSTILEHostile behaviour toward the Persona.Progressive
AI_SUSPICIONUser suspects the Persona is an AI.Progressive
What to do. Progressive bans default to 2h → 12h → 24h → 48h → permanent. Wait until conversationStoppedUntil before sending again; for permanent reasons, stop the conversation. Durations are configurable per project in Core Guardian.A ban applies only to the current conversation. The user’s other conversations are unaffected, and they can start a new one normally.

​
Webhook events

EventWhat it meansWhat to do
answer.processingGeneration has started.Optionally show a “typing” state.
answer.createdAnswer is ready (carries any stop reason).Deliver it to your end-user.
conversation.droppedGeneration exceeded the max time; no answer produced.Resend or raise the timeout.
chat.image.rejectedA submitted image failed moderation.See rejection reasons below.

​
Image rejection reasons

A chat.image.rejected event includes a reason explaining the moderation failure.
ReasonWhat it means
VIOLENT_CONTENTViolence or graphic/unsafe violent material.
SELF_HARMSelf-harm, suicidal, or related imagery.
ILLEGAL_CONTENTIllegal or illicit content prohibited by policy or law.
Configure what triggers these signals in Core Guardian. See full field definitions in the Answer data type.