Make end call tool can be cancelled

backend/services/brains/base.py

@@ -58,7 +58,12 @@ class CallEndPort(Protocol):
     @property
     def ending(self) -> bool: ...
 
-    def begin(self, reason: str) -> None: ...
+    @property
+    def accepts_input(self) -> bool: ...
+
+    def begin(self, reason: str, *, interruptible: bool = False) -> None: ...
+
+    def cancel_pending_end(self) -> bool: ...
 
     def begin_response(self) -> None: ...
 

backend/services/brains/prompt_brain.py

@@ -488,15 +488,12 @@ class PromptBrain(BaseBrain):
         if content and not interrupted:
             self._store.record("agent", content, completed_agent_turn=True)
             self._refresh_prompt()
-        if (
-            self._waiting_for_generated_end_speech
-            and self._runtime is not None
-            and self._runtime.call_end.ending
-        ):
+        if self._waiting_for_generated_end_speech:
             self._waiting_for_generated_end_speech = False
-            await self._runtime.call_end.finish_after_current_speech(
-                has_text=bool(content.strip()) and not interrupted
-            )
+            if self._runtime is not None and self._runtime.call_end.ending:
+                await self._runtime.call_end.finish_after_current_speech(
+                    has_text=bool(content.strip()) and not interrupted
+                )
 
     def _refresh_prompt(self) -> None:
         if self._dynamic_enabled and self._runtime is not None:
@@ -594,12 +591,18 @@ class PromptBrain(BaseBrain):
         message_type = str(config.get("message_type") or "none")
         custom_message = str(config.get("custom_message") or "").strip()
         capture_reason = bool(config.get("capture_reason", True))
+        allow_end_interruption = bool(
+            config.get("allow_end_interruption", False)
+        )
 
         async def end_call(params: FunctionCallParams) -> None:
             reason = str(params.arguments.get("reason") or "end_call_tool").strip()
             uses_custom_message = message_type == "custom" and bool(custom_message)
             self._waiting_for_generated_end_speech = not uses_custom_message
-            runtime.call_end.begin(reason)
+            runtime.call_end.begin(
+                reason,
+                interruptible=allow_end_interruption,
+            )
             await params.result_callback(
                 {"status": "success", "action": "ending_call"},
                 properties=FunctionCallResultProperties(run_llm=False),
@@ -610,6 +613,8 @@ class PromptBrain(BaseBrain):
                 # invoking this tool. Decide at assistant-text-end whether to
                 # wait for that TTS audio or finish immediately for tool-only calls.
                 return
+            if not runtime.call_end.ending:
+                return
 
             turn_id = uuid4().hex
             timestamp = time_now_iso8601()
@@ -634,6 +639,8 @@ class PromptBrain(BaseBrain):
                 await runtime.queue_frame(
                     OutputTransportMessageUrgentFrame(message=message)
                 )
+            if not runtime.call_end.ending:
+                return
             runtime.call_end.arm_after_speech()
             await runtime.queue_frame(
                 TTSSpeakFrame(custom_message, append_to_context=False)

backend/services/brains/workflow_brain.py

@@ -603,15 +603,12 @@ class WorkflowBrain(BaseBrain):
             self._state.consume_user_turn()
             if self._engine.node_type(self._state.current_node_id) == "agent":
                 self._state.status = WorkflowStatus.WAITING_USER
-        if (
-            self._waiting_for_generated_end_speech
-            and self._runtime is not None
-            and self._runtime.call_end.ending
-        ):
+        if self._waiting_for_generated_end_speech:
             self._waiting_for_generated_end_speech = False
-            await self._runtime.call_end.finish_after_current_speech(
-                has_text=bool(content.strip()) and not interrupted
-            )
+            if self._runtime is not None and self._runtime.call_end.ending:
+                await self._runtime.call_end.finish_after_current_speech(
+                    has_text=bool(content.strip()) and not interrupted
+                )
 
     async def on_realtime_user_speech_started(self) -> None:
         if self._realtime_controller is not None:
@@ -1090,13 +1087,19 @@ class WorkflowBrain(BaseBrain):
         message_type = str(config.get("message_type") or "none")
         custom_message = str(config.get("custom_message") or "").strip()
         capture_reason = bool(config.get("capture_reason", True))
+        allow_end_interruption = bool(
+            config.get("allow_end_interruption", False)
+        )
 
         async def handler(args, _flow_manager):
             reason = str((args or {}).get("reason") or "end_conversation").strip()
             uses_custom_message = message_type == "custom" and bool(custom_message)
             self._waiting_for_generated_end_speech = not uses_custom_message
             runtime = self._require_runtime()
-            runtime.call_end.begin(reason)
+            runtime.call_end.begin(
+                reason,
+                interruptible=allow_end_interruption,
+            )
             if uses_custom_message:
                 await self._queue_visible_speech(
                     custom_message,