incorporate daily api undocumented feature (#796)

Co-authored-by: Igor Loskutov <igor.loskutoff@gmail.com>

server/reflector/dailyco_api/__init__.py

@@ -18,6 +18,7 @@ from .requests import (
 
 # Response models
 from .responses import (
+    FinishedRecordingResponse,
     MeetingParticipant,
     MeetingParticipantsResponse,
     MeetingResponse,
@@ -79,6 +80,7 @@ __all__ = [
     "MeetingParticipant",
     "MeetingResponse",
     "RecordingResponse",
+    "FinishedRecordingResponse",
     "RecordingS3Info",
     "MeetingTokenResponse",
     "WebhookResponse",

server/reflector/dailyco_api/responses.py

@@ -121,7 +121,10 @@ class RecordingS3Info(BaseModel):
 
 class RecordingResponse(BaseModel):
     """
-    Response from recording retrieval endpoint.
+    Response from recording retrieval endpoint (network layer).
+
+    Duration may be None for recordings still being processed by Daily.
+    Use FinishedRecordingResponse for recordings ready for processing.
 
     Reference: https://docs.daily.co/reference/rest-api/recordings
     """
@@ -135,7 +138,9 @@ class RecordingResponse(BaseModel):
     max_participants: int | None = Field(
         None, description="Maximum participants during recording (may be missing)"
     )
-    duration: int = Field(description="Recording duration in seconds")
+    duration: int | None = Field(
+        None, description="Recording duration in seconds (None if still processing)"
+    )
     share_token: NonEmptyString | None = Field(
         None, description="Token for sharing recording"
     )
@@ -149,6 +154,25 @@ class RecordingResponse(BaseModel):
         None, description="Meeting session identifier (may be missing)"
     )
 
+    def to_finished(self) -> "FinishedRecordingResponse | None":
+        """Convert to FinishedRecordingResponse if duration is available and status is finished."""
+        if self.duration is None or self.status != "finished":
+            return None
+        return FinishedRecordingResponse(**self.model_dump())
+
+
+class FinishedRecordingResponse(RecordingResponse):
+    """
+    Recording with confirmed duration - ready for processing.
+
+    This model guarantees duration is present and status is finished.
+    """
+
+    status: Literal["finished"] = Field(
+        description="Recording status (always 'finished')"
+    )
+    duration: int = Field(description="Recording duration in seconds")
+
 
 class MeetingTokenResponse(BaseModel):
     """

server/reflector/worker/process.py

@@ -12,7 +12,7 @@ from celery import shared_task
 from celery.utils.log import get_task_logger
 from pydantic import ValidationError
 
-from reflector.dailyco_api import RecordingResponse
+from reflector.dailyco_api import FinishedRecordingResponse, RecordingResponse
 from reflector.db.daily_participant_sessions import (
     DailyParticipantSession,
     daily_participant_sessions_controller,
@@ -322,16 +322,38 @@ async def poll_daily_recordings():
         )
         return
 
-    recording_ids = [rec.id for rec in api_recordings]
+    finished_recordings: List[FinishedRecordingResponse] = []
+    for rec in api_recordings:
+        finished = rec.to_finished()
+        if finished is None:
+            logger.debug(
+                "Skipping unfinished recording",
+                recording_id=rec.id,
+                room_name=rec.room_name,
+                status=rec.status,
+            )
+            continue
+        finished_recordings.append(finished)
+
+    if not finished_recordings:
+        logger.debug(
+            "No finished recordings found from Daily.co API",
+            total_api_count=len(api_recordings),
+        )
+        return
+
+    recording_ids = [rec.id for rec in finished_recordings]
     existing_recordings = await recordings_controller.get_by_ids(recording_ids)
     existing_ids = {rec.id for rec in existing_recordings}
 
-    missing_recordings = [rec for rec in api_recordings if rec.id not in existing_ids]
+    missing_recordings = [
+        rec for rec in finished_recordings if rec.id not in existing_ids
+    ]
 
     if not missing_recordings:
         logger.debug(
             "All recordings already in DB",
-            api_count=len(api_recordings),
+            api_count=len(finished_recordings),
             existing_count=len(existing_recordings),
         )
         return
@@ -339,7 +361,7 @@ async def poll_daily_recordings():
     logger.info(
         "Found recordings missing from DB",
         missing_count=len(missing_recordings),
-        total_api_count=len(api_recordings),
+        total_api_count=len(finished_recordings),
         existing_count=len(existing_recordings),
     )