feat: enhance call end coordination with state management

- Added support for tracking call end states (pending, speaking, cancelled) in CallEndCoordinator.
- Introduced a callback mechanism for state changes to allow external handling of call end states.
- Updated pipeline and tests to accommodate new state management features, ensuring proper handling of call end scenarios.

backend/services/pipecat/call_lifecycle.py

@@ -63,11 +63,19 @@ def playback_marker_for(
     return FixedSpeechPlaybackMarkerFrame(completion=completion)
 
 
+CallEndStateHandler = Callable[[str, bool], Awaitable[None]]
+
+
 class CallEndCoordinator:
     """Coordinate committed and user-cancellable conversation endings."""
 
-    def __init__(self, queue_end: Callable[[str], Awaitable[None]]):
+    def __init__(
+        self,
+        queue_end: Callable[[str], Awaitable[None]],
+        on_state_change: CallEndStateHandler | None = None,
+    ):
         self._queue_end = queue_end
+        self._on_state_change = on_state_change
         self._ending = False
         self._interruptible = False
         self._armed = False
@@ -110,6 +118,7 @@ class CallEndCoordinator:
         self._armed = False
         self._finish_after_tracked_speech = False
         self._reason = reason or "completed"
+        self._schedule_state("speaking" if self._speaking else "pending")
 
     def cancel_pending_end(self) -> bool:
         """Cancel one pending ending when its tool explicitly allows it."""
@@ -123,8 +132,13 @@ class CallEndCoordinator:
         # Transport speech state remains authoritative: if audio is currently
         # playing, the interruption path will still emit BotStoppedSpeakingFrame.
         logger.info("用户打断结束语,已撤销待挂断状态")
+        self._schedule_state("cancelled")
         return True
 
+    def _schedule_state(self, state: str) -> None:
+        if self._on_state_change is not None:
+            asyncio.create_task(self._on_state_change(state, self.interruptible))
+
     def begin_response(self) -> None:
         """Start tracking speech produced by one LLM response."""
         self._response_speech_started = False
@@ -200,6 +214,8 @@ class CallEndCoordinator:
             self._speaking = True
             self._speech_stopped.clear()
             self._response_speech_started = True
+            if self._ending:
+                await self._emit_state("speaking")
         elif isinstance(frame, BotStoppedSpeakingFrame) and self._speaking:
             self._speaking = False
             self._speech_stopped.set()
@@ -207,6 +223,10 @@ class CallEndCoordinator:
                 logger.info("结束语播报完毕,挂断通话")
                 await self.finish()
 
+    async def _emit_state(self, state: str) -> None:
+        if self._on_state_change is not None:
+            await self._on_state_change(state, self.interruptible)
+
 
 class EndCallAfterSpeechProcessor(FrameProcessor):
     def __init__(self, coordinator: CallEndCoordinator):

backend/services/pipecat/pipeline.py

@@ -201,6 +201,23 @@ def _multimodal_user_input_frame(
     )
 
 
+def _call_end_state_frame(
+    state: str,
+    *,
+    interruptible: bool,
+    voice_interruptible: bool,
+) -> OutputTransportMessageUrgentFrame:
+    """Build the client event used to render the pending call-end state."""
+    return OutputTransportMessageUrgentFrame(
+        message={
+            "type": "call-end-state",
+            "state": state,
+            "interruptible": interruptible,
+            "voice_interruptible": voice_interruptible,
+        }
+    )
+
+
 async def run_pipeline(
     transport,
     cfg: AssistantConfig,
@@ -295,7 +312,24 @@ async def run_pipeline(
         )
         await worker.queue_frame(EndFrame())
 
-    call_end = CallEndCoordinator(queue_call_end)
+    async def queue_call_end_state(state: str, interruptible: bool) -> None:
+        worker = worker_holder.get("worker")
+        if worker is None:
+            return
+        await worker.queue_frame(
+            _call_end_state_frame(
+                state,
+                interruptible=interruptible,
+                voice_interruptible=(
+                    interruptible and current_enable_interrupt
+                ),
+            )
+        )
+
+    call_end = CallEndCoordinator(
+        queue_call_end,
+        on_state_change=queue_call_end_state,
+    )
 
     knowledge_config = cfg.knowledge_retrieval_config
     knowledge_mode = str(knowledge_config.get("mode", "automatic"))
@@ -976,7 +1010,24 @@ async def run_realtime_pipeline(
         )
         await worker.queue_frame(EndFrame())
 
-    call_end = CallEndCoordinator(queue_call_end)
+    async def queue_call_end_state(state: str, interruptible: bool) -> None:
+        worker = worker_holder.get("worker")
+        if worker is None:
+            return
+        await worker.queue_frame(
+            _call_end_state_frame(
+                state,
+                interruptible=interruptible,
+                voice_interruptible=(
+                    interruptible and cfg.enableInterrupt
+                ),
+            )
+        )
+
+    call_end = CallEndCoordinator(
+        queue_call_end,
+        on_state_change=queue_call_end_state,
+    )
     client_tools = ClientToolBroker()
 
     async def interrupt_for_client_tool_result() -> None: