on_summary | SignalWire

Callback method invoked when a post-prompt summary is received after a conversation ends. Override this method in a subclass to process summaries — for example, saving them to a CRM, triggering follow-up workflows, or logging call outcomes.

A post-prompt must be configured via set_post_prompt() for summaries to be generated.

For the full transcript at hangup rather than the summary, register on_call_end(). To read voice and chat post-prompt bodies with one shape, see normalize_post_prompt().

The default implementation does nothing. You must override it in a subclass or set a set_post_prompt_url() to receive summaries at an external endpoint.

Parameters

summary

dict[str, Any] | NoneRequired

The summary object generated by the AI based on your post-prompt instructions. None if no summary could be extracted from the response.

raw_data

dict[str, Any] | NoneDefaults to None

The complete raw POST data from the post-prompt request, including metadata like call_id and the full AI response.

Returns

None

Example

from signalwire import AgentBase
class SupportAgent(AgentBase):
    def __init__(self):
        super().__init__(name="support", route="/support")
        self.set_prompt_text("You are a helpful customer support agent.")
        self.set_post_prompt("""
            Summarize this call as JSON:
            - intent: caller's primary intent
            - resolved: yes/no/partial
            - sentiment: positive/neutral/negative
        """)
    def on_summary(self, summary, raw_data=None):
        if summary:
            call_id = raw_data.get("call_id") if raw_data else "unknown"
            print(f"Call {call_id} summary: {summary}")
            # save_to_database(call_id, summary)
agent = SupportAgent()
agent.run()