wx44wx/ai-video-fullstack
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(realtime): complete workflow message transitions

Browse Source
This commit is contained in:
Xin Wang
2026-08-05 11:25:50 +08:00
parent 17b5e10ed1
commit 11374238f3
4 changed files with 115 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/services/pipecat/pipeline.py
+16 -1
View File
@@ -909,7 +909,22 @@ async def run_realtime_pipeline(
call_end = CallEndCoordinator(queue_call_end)
client_tools = ClientToolBroker()
client_tools.set_interrupt_handler(realtime.interrupt)
async def interrupt_for_client_tool_result() -> None:
"""Release confirmations after the realtime response is interrupted.
Fixed Message speech intentionally suppresses the provider transcript,
so the text aggregator may have no assistant turn from which to emit an
``on_interruption_processed`` event. The realtime adapter owns and
clears that response state itself. Wait for the provider boundary as
well, matching Pipeline's rule that the next node cannot generate until
the interrupted response has fully finished.
"""
await realtime.interrupt()
await realtime.wait_for_response_boundary()
client_tools.on_interruption_processed()
client_tools.set_interrupt_handler(interrupt_for_client_tool_result)
user_input = RealtimeUserInputProcessor(
should_ignore_input=lambda: (
call_end.ending or not input_state["enabled"]
backend/services/pipecat/qwen_audio_realtime.py
+38 -1
View File
@@ -27,6 +27,7 @@ from pipecat.frames.frames import (
OutputTransportMessageUrgentFrame,
StartFrame,
TTSAudioRawFrame,
TTSStoppedFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.ai_service import AIService
@@ -120,6 +121,7 @@ class QwenAudioRealtimeService(AIService):
self._assistant_text = ""
self._assistant_timestamp = ""
self._greeting_request_item_id: str | None = None
self._entry_trigger_item_id: str | None = None
self._user_transcript_pending = False
self._user_transcript_item_id = ""
self._user_transcript_timestamp = ""
@@ -215,9 +217,27 @@ class QwenAudioRealtimeService(AIService):
await self._cancel_active_response()
await self.broadcast_interruption()
async def request_response(self) -> None:
async def request_response(self, *, trigger_text: str | None = None) -> None:
if trigger_text:
item_id = f"item_{uuid4().hex}"
self._entry_trigger_item_id = item_id
await self._send_event(
{
"type": "conversation.item.create",
"item": {
"id": item_id,
"type": "message",
"role": "user",
"content": [{"type": "input_text", "text": trigger_text}],
},
}
)
await self._send_event({"type": "response.create"})
async def wait_for_response_boundary(self) -> None:
"""Wait until Qwen has finished or cancelled the current response."""
await self._response_done.wait()
def set_speech_started_handler(
self,
handler: SpeechStartedHandler | None,
@@ -387,6 +407,7 @@ class QwenAudioRealtimeService(AIService):
self._deferred_assistant_messages.clear()
self._tool_session.clear()
self._function_names.clear()
self._entry_trigger_item_id = None
self._resolve_fixed_speech()
if websocket and websocket.state is State.OPEN:
try:
@@ -412,6 +433,7 @@ class QwenAudioRealtimeService(AIService):
self._session_ready.clear()
self._response_done.set()
self._greeting_request_item_id = None
self._entry_trigger_item_id = None
self._resolve_fixed_speech()
if self._receive_task is asyncio.current_task():
self._receive_task = None
@@ -480,8 +502,10 @@ class QwenAudioRealtimeService(AIService):
status = response.get("status") if isinstance(response, dict) else None
interrupted = status in {"cancelled", "incomplete", "interrupted", "failed"}
self._response_active = False
await self.push_frame(TTSStoppedFrame())
await self._finish_assistant_text(interrupted=interrupted)
await self._delete_greeting_request()
await self._delete_entry_trigger()
self._resolve_fixed_speech()
self._response_done.set()
elif event_type == "response.output_item.added":
@@ -579,6 +603,15 @@ class QwenAudioRealtimeService(AIService):
wait_until_ready=False,
)
async def _delete_entry_trigger(self) -> None:
item_id = self._entry_trigger_item_id
self._entry_trigger_item_id = None
if item_id:
await self._send_event(
{"type": "conversation.item.delete", "item_id": item_id},
wait_until_ready=False,
)
async def _start_user_transcript_turn(
self,
event: dict[str, Any],
@@ -643,6 +676,10 @@ class QwenAudioRealtimeService(AIService):
async def _send_event(
self, payload: dict[str, Any], *, wait_until_ready: bool = True
) -> None:
if payload.get("type") == "response.create":
# Mark the response busy before the server's response.created
# arrives so an immediate confirmation cannot pass the boundary.
self._response_done.clear()
if wait_until_ready and not self._session_ready.is_set():
self._pending_events.append(payload)
return
backend/services/pipecat/stepfun_realtime.py
+38 -1
View File
@@ -21,6 +21,7 @@ from pipecat.frames.frames import (
OutputTransportMessageUrgentFrame,
StartFrame,
TTSAudioRawFrame,
TTSStoppedFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.ai_service import AIService
@@ -85,6 +86,7 @@ class StepFunRealtimeService(AIService):
)
self._fixed_speech_completion: asyncio.Future[None] | None = None
self._fixed_speech_request_item_id: str | None = None
self._entry_trigger_item_id: str | None = None
self._suppress_response_transcript = False
self._speech_started_handler: SpeechStartedHandler | None = None
self._function_names: dict[str, str] = {}
@@ -164,9 +166,27 @@ class StepFunRealtimeService(AIService):
self._resolve_fixed_speech()
await self.broadcast_interruption()
async def request_response(self) -> None:
async def request_response(self, *, trigger_text: str | None = None) -> None:
if trigger_text:
item_id = f"item_{uuid4().hex}"
self._entry_trigger_item_id = item_id
await self._send_event(
{
"type": "conversation.item.create",
"item": {
"id": item_id,
"type": "message",
"role": "user",
"content": [{"type": "input_text", "text": trigger_text}],
},
}
)
await self._send_event({"type": "response.create"})
async def wait_for_response_boundary(self) -> None:
"""Wait until StepFun has finished or cancelled the current response."""
await self._response_done.wait()
def set_speech_started_handler(
self,
handler: SpeechStartedHandler | None,
@@ -246,6 +266,7 @@ class StepFunRealtimeService(AIService):
self._tool_session.clear()
self._function_names.clear()
self._fixed_speech_request_item_id = None
self._entry_trigger_item_id = None
self._resolve_fixed_speech()
if websocket and websocket.state is State.OPEN:
try:
@@ -280,6 +301,7 @@ class StepFunRealtimeService(AIService):
self._session_ready.clear()
self._response_done.set()
self._fixed_speech_request_item_id = None
self._entry_trigger_item_id = None
self._resolve_fixed_speech()
if self._receive_task is asyncio.current_task():
self._receive_task = None
@@ -331,8 +353,10 @@ class StepFunRealtimeService(AIService):
"incomplete",
"interrupted",
}
await self.push_frame(TTSStoppedFrame())
await self._finish_assistant_text(interrupted=interrupted)
await self._delete_fixed_speech_request()
await self._delete_entry_trigger()
self._resolve_fixed_speech()
self._response_done.set()
elif event_type == "response.output_item.added":
@@ -474,9 +498,22 @@ class StepFunRealtimeService(AIService):
wait_until_ready=False,
)
async def _delete_entry_trigger(self) -> None:
item_id = self._entry_trigger_item_id
self._entry_trigger_item_id = None
if item_id:
await self._send_event(
{"type": "conversation.item.delete", "item_id": item_id},
wait_until_ready=False,
)
async def _send_event(
self, payload: dict[str, Any], *, wait_until_ready: bool = True
) -> None:
if payload.get("type") == "response.create":
# Mark the response busy before the server's response.created
# arrives so an immediate confirmation cannot pass the boundary.
self._response_done.clear()
if wait_until_ready and not self._session_ready.is_set():
self._pending_events.append(payload)
return
backend/services/workflow/realtime.py
+23 -4
View File
@@ -35,6 +35,11 @@ from services.workflow_engine import WorkflowEngine
MAX_AUTOMATIC_HOPS = 50
AGENT_ENTRY_TRIGGER = (
"[工作流内部事件，不是用户消息] 当前 Agent 节点已激活。"
"请严格依据当前 instructions 立即生成进入该节点时的回复，"
"不要提及或复述本事件。"
)
ToolHandler = Callable[[dict[str, Any]], Awaitable[RealtimeToolResult]]
@@ -80,10 +85,18 @@ class RealtimeWorkflowOutput(WorkflowOutput):
**({"nodeId": node_id} if node_id else {}),
}
)
return await self._realtime.speak_fixed(
track_speech = getattr(self._runtime.call_end, "track_speech", None)
playback_completion: Awaitable[None] | None = None
if callable(track_speech):
playback_completion = track_speech()
provider_completion = await self._realtime.speak_fixed(
content,
suppress_transcript=True,
)
# Message playback policy and deterministic continuation must use the
# transport boundary. Provider response.done only means generation
# has finished; audio may still be buffered at the output transport.
return playback_completion or provider_completion
class WorkflowRealtimeController:
@@ -138,7 +151,7 @@ class WorkflowRealtimeController:
allow_visible_actions=True,
)
if activation.continue_response:
await self._runtime.realtime.request_response()
await self._request_agent_entry_response()
async def on_client_ready(self) -> None:
await self._output.mark_client_ready()
@@ -160,7 +173,7 @@ class WorkflowRealtimeController:
if activation and activation.after_output:
await activation.after_output()
elif activation and activation.continue_response:
await self._runtime.realtime.request_response()
await self._request_agent_entry_response()
return SessionVariableUpdate(
changed=changed,
dynamic_variables=self._store.public_values(),
@@ -321,7 +334,13 @@ class WorkflowRealtimeController:
if activation.after_output:
await activation.after_output()
elif activation.continue_response:
await self._runtime.realtime.request_response()
await self._request_agent_entry_response()
async def _request_agent_entry_response(self) -> None:
"""Give provider inference a temporary turn for Agent entry speech."""
await self._runtime.realtime.request_response(
trigger_text=AGENT_ENTRY_TRIGGER,
)
async def _follow_edge(
self,