Autogen Termination Conditions

Team uses TextMentionTermination('DONE'). Agent emits 'we are done with the task' (lowercase 'done'). Team does not stop.

TextMentionTermination matches the configured substring as-is — semantics are case-sensitive substring containment. Choose unambiguous sentinels (e.g. '<<TERMINATE>>') that won't appear in normal prose, and prime the agent's system_message to emit the exact token at task completion.

Team uses TokenUsageTermination(max_total_token=20000). One model_client doesn't report usage and the counter stays at 0.

TokenUsageTermination relies on the model_client surfacing per-call usage. Verify your model_client populates the usage field on every response (some custom clients may not). Without usage signal, the termination never fires — pair with MaxMessageTermination as a backstop.

Two AssistantAgents in a RoundRobinGroupChat keep asking each other clarifying questions; no agent ever emits 'TERMINATE' or a HandoffMessage. There is no MaxMessageTermination configured.

Every team MUST have at least one always-firing termination condition (MaxMessage or TokenUsage or Timeout). Without one, two clarifying agents loop indefinitely and burn upstream model spend. Treat 'no termination condition' as a CI failure.