fix: participants update from daily (#749)

* Fix participants update from daily

* Use track keys from params
This commit is contained in:
2025-11-27 16:53:26 +01:00
committed by GitHub
parent 692895c859
commit 7f0b728991
3 changed files with 98 additions and 84 deletions

View File

@@ -9,7 +9,10 @@ from av.audio.resampler import AudioResampler
from celery import chain, shared_task
from reflector.asynctask import asynctask
from reflector.dailyco_api import MeetingParticipantsResponse
from reflector.db.transcripts import (
Transcript,
TranscriptParticipant,
TranscriptStatus,
TranscriptWaveform,
transcripts_controller,
@@ -29,7 +32,12 @@ from reflector.processors.audio_waveform_processor import AudioWaveformProcessor
from reflector.processors.types import TitleSummary
from reflector.processors.types import Transcript as TranscriptType
from reflector.storage import Storage, get_transcripts_storage
from reflector.utils.daily import (
filter_cam_audio_tracks,
parse_daily_recording_filename,
)
from reflector.utils.string import NonEmptyString
from reflector.video_platforms.factory import create_platform_client
# Audio encoding constants
OPUS_STANDARD_SAMPLE_RATE = 48000
@@ -494,6 +502,90 @@ class PipelineMainMultitrack(PipelineMainBase):
transcript=transcript, event="WAVEFORM", data=waveform
)
async def update_participants_from_daily(
self, transcript: Transcript, track_keys: list[str]
) -> None:
"""Update transcript participants with user_id and names from Daily.co API."""
if not transcript.recording_id:
return
try:
async with create_platform_client("daily") as daily_client:
id_to_name = {}
id_to_user_id = {}
try:
rec_details = await daily_client.get_recording(
transcript.recording_id
)
mtg_session_id = rec_details.mtgSessionId
if mtg_session_id:
try:
payload: MeetingParticipantsResponse = (
await daily_client.get_meeting_participants(
mtg_session_id
)
)
for p in payload.data:
pid = p.participant_id
name = p.user_name
user_id = p.user_id
if name:
id_to_name[pid] = name
if user_id:
id_to_user_id[pid] = user_id
except Exception as e:
self.logger.warning(
"Failed to fetch Daily meeting participants",
error=str(e),
mtg_session_id=mtg_session_id,
exc_info=True,
)
else:
self.logger.warning(
"No mtgSessionId found for recording; participant names may be generic",
recording_id=transcript.recording_id,
)
except Exception as e:
self.logger.warning(
"Failed to fetch Daily recording details",
error=str(e),
recording_id=transcript.recording_id,
exc_info=True,
)
return
cam_audio_keys = filter_cam_audio_tracks(track_keys)
for idx, key in enumerate(cam_audio_keys):
try:
parsed = parse_daily_recording_filename(key)
participant_id = parsed.participant_id
except ValueError as e:
self.logger.error(
"Failed to parse Daily recording filename",
error=str(e),
key=key,
exc_info=True,
)
continue
default_name = f"Speaker {idx}"
name = id_to_name.get(participant_id, default_name)
user_id = id_to_user_id.get(participant_id)
participant = TranscriptParticipant(
id=participant_id, speaker=idx, name=name, user_id=user_id
)
await transcripts_controller.upsert_participant(
transcript, participant
)
except Exception as e:
self.logger.warning(
"Failed to map participant names", error=str(e), exc_info=True
)
async def process(self, bucket_name: str, track_keys: list[str]):
transcript = await self.get_transcript()
async with self.transaction():
@@ -502,9 +594,12 @@ class PipelineMainMultitrack(PipelineMainBase):
{
"events": [],
"topics": [],
"participants": [],
},
)
await self.update_participants_from_daily(transcript, track_keys)
source_storage = get_transcripts_storage()
transcript_storage = source_storage