dv-pipecat-flows 0.0.0.dev2764__tar.gz → 0.0.0.dev2766__tar.gz

{dv_pipecat_flows-0.0.0.dev2764/src/dv_pipecat_flows.egg-info → dv_pipecat_flows-0.0.0.dev2766}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dv-pipecat-flows
-Version: 0.0.0.dev2764
+Version: 0.0.0.dev2766
 Summary: Conversation Flow management for Pipecat AI applications
 License: BSD 2-Clause License
 Project-URL: Source, https://github.com/pipecat-ai/pipecat-flows

{dv_pipecat_flows-0.0.0.dev2764 → dv_pipecat_flows-0.0.0.dev2766/src/dv_pipecat_flows.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dv-pipecat-flows
-Version: 0.0.0.dev2764
+Version: 0.0.0.dev2766
 Summary: Conversation Flow management for Pipecat AI applications
 License: BSD 2-Clause License
 Project-URL: Source, https://github.com/pipecat-ai/pipecat-flows

{dv_pipecat_flows-0.0.0.dev2764 → dv_pipecat_flows-0.0.0.dev2766}/src/dv_pipecat_flows.egg-info/scm_file_list.json

@@ -642,6 +642,7 @@
     "tests/test_router_mode_guard.py",
     "tests/test_router_no_unclear.py",
     "tests/test_tts_split_cache.py",
+    "tests/test_user_turn_observer.py",
     "tests/test_voicemail_detector.py",
     "uv.lock"
   ]

{dv_pipecat_flows-0.0.0.dev2764 → dv_pipecat_flows-0.0.0.dev2766}/src/dv_pipecat_flows.egg-info/scm_version.json

@@ -1,7 +1,7 @@
 {
   "tag": "0.0.0.dev0",
-  "distance": 2764,
-  "node": "gb247b6b890a5ece19939aba5a216415b690f8e87",
+  "distance": 2766,
+  "node": "g2f9ead0f53048f6c04d0647e37cff236bd770e14",
   "dirty": false,
   "branch": "dv-stage",
   "node_date": "2026-08-08"

{dv_pipecat_flows-0.0.0.dev2764 → dv_pipecat_flows-0.0.0.dev2766}/src/pipecat_flows/processors/user_turn_observer.py

@@ -1,4 +1,5 @@
-"""Observer that timestamps :class:`OpenAILLMContextFrame` so router-mode
+"""Observer that timestamps the user-turn-committed context frame
+(:class:`OpenAILLMContextFrame` **or** :class:`LLMContextFrame`) so router-mode
 nodes can detect "user turn is now committed to context" without reaching
 into the user context aggregator's private state.
 
@@ -7,22 +8,27 @@ Why an observer, not a FrameProcessor:
     public ``PipelineTask.add_observer`` API.
   * We only need a passive timestamp + an ``asyncio.Event`` — no frame routing.
 
-Why ``OpenAILLMContextFrame`` and not ``UserStoppedSpeakingFrame``:
+Why a context frame and not ``UserStoppedSpeakingFrame``:
   * ``UserStoppedSpeakingFrame`` is raw VAD — it fires the instant the mic
     detects silence, BEFORE the STT final lands and BEFORE the user-context
     aggregator appends the turn. Router gates that release on this signal
     classify against an empty/stale context.
-  * ``OpenAILLMContextFrame`` is pushed by ``LLMUserContextAggregator``
+  * The context frame is pushed by ``LLMUserContextAggregator``
     (``llm_response._process_aggregation``) only AFTER the final transcript
     is appended to the LLM context. It is the canonical "user turn is now
     in the context the router will read" event.
   * Router-mode never queues ``LLMRunFrame`` for the router node itself, so
-    the only ``OpenAILLMContextFrame`` produced during a router invocation
-    comes from the aggregator's turn-complete path — no competing source.
+    the only context frame produced during a router invocation comes from
+    the aggregator's turn-complete path — no competing source.
+
+BOTH context-frame flavours must be matched (see
+``_USER_TURN_COMMITTED_FRAME_TYPES``): the aggregator emits
+``LLMContextFrame`` on the Responses-API / google / gemma paths and
+``OpenAILLMContextFrame`` on the Chat Completions path.
 
 State exposed:
   * ``last_user_context_pushed_ts``: monotonic time of the latest
-    ``OpenAILLMContextFrame`` (user turn committed to context).
+    user-turn context frame (user turn committed to context).
   * ``last_user_stopped_ts``: backwards-compatible alias kept in sync with
     ``last_user_context_pushed_ts`` so existing callers keep working.
   * ``event``: ``asyncio.Event`` set on every such frame; the consumer is
@@ -38,26 +44,41 @@ from typing import List, Tuple
 
 from pipecat.frames.frames import (
     InterimTranscriptionFrame,
+    LLMContextFrame,
     TranscriptionFrame,
     UserStartedSpeakingFrame,
 )
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContextFrame
 from pipecat.observers.base_observer import BaseObserver, FramePushed
 
+# Both context-frame flavours mean the same thing here: "the user's turn is now
+# committed to the context the router will read". Which one the aggregator emits
+# is decided by one switch in the bot:
+#
+#     context = LLMContext() if (_use_responses or _use_universal_for_google)
+#               else OpenAILLMContext()
+#
+# They are SIBLINGS (both extend Frame directly, neither subclasses the other),
+# so matching one does NOT match the other. Keying on only OpenAILLMContextFrame
+# left every Responses-API / google / gemma agent's router waiting the full
+# ``router_wait_for_user_timeout`` (15s) after the caller had already replied.
+_USER_TURN_COMMITTED_FRAME_TYPES = (OpenAILLMContextFrame, LLMContextFrame)
+
 # Bound the per-call transcript log so a very long call can't grow it without
 # limit; far more than any single Collect dictation needs.
 _MAX_TRANSCRIPT_LOG = 256
 
 
 class UserTurnObserver(BaseObserver):
-    """Tracks the timestamp of the most recent ``OpenAILLMContextFrame``.
+    """Tracks the timestamp of the most recent user-turn context frame.
 
     Router-mode uses this to (a) detect a user reply already committed to
     context BEFORE the router was entered (barge-in during the preceding
     Speak's TTS) and (b) await the NEXT user reply when none is available.
 
-    The observer is keyed on ``OpenAILLMContextFrame`` rather than the raw
-    VAD ``UserStoppedSpeakingFrame`` because only the former guarantees the
+    The observer is keyed on the context frame (either flavour, see
+    ``_USER_TURN_COMMITTED_FRAME_TYPES``) rather than the raw VAD
+    ``UserStoppedSpeakingFrame`` because only the former guarantees the
     user's transcript has been appended to the LLM context the router reads.
     """
 
@@ -93,7 +114,7 @@ class UserTurnObserver(BaseObserver):
 
     @property
     def event(self) -> asyncio.Event:
-        """The asyncio.Event set on each ``OpenAILLMContextFrame``.
+        """The asyncio.Event set on each user-turn context frame.
 
         Callers MUST ``.clear()`` before awaiting if they want to wait for the
         NEXT frame (vs. immediately returning on a stale set state).
@@ -101,7 +122,7 @@ class UserTurnObserver(BaseObserver):
         return self._event
 
     async def on_push_frame(self, data: FramePushed) -> None:
-        if isinstance(data.frame, OpenAILLMContextFrame):
+        if isinstance(data.frame, _USER_TURN_COMMITTED_FRAME_TYPES):
             now = time.monotonic()
             self.last_user_context_pushed_ts = now
             self.last_user_stopped_ts = now