feat: improve transcript listing with room_id (#496)

Added a new field in transcript for room_id, and set room_id/meeting_id
in a transcript now. Use this field to list the transcripts. URL is now
very fast.

server/migrations/versions/d7fbb74b673b_add_room_id_to_transcript.py

@@ -0,0 +1,59 @@
+"""Add room_id to transcript
+
+Revision ID: d7fbb74b673b
+Revises: a9c9c229ee36
+Create Date: 2025-07-17 12:00:00.000000
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "d7fbb74b673b"
+down_revision: Union[str, None] = "a9c9c229ee36"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # Add room_id column to transcript table
+    op.add_column("transcript", sa.Column("room_id", sa.String(), nullable=True))
+
+    # Add index for room_id for better query performance
+    op.create_index("idx_transcript_room_id", "transcript", ["room_id"])
+
+    # Populate room_id for existing ROOM-type transcripts
+    # This joins through recording -> meeting -> room to get the room_id
+    op.execute("""
+        UPDATE transcript AS t
+        SET room_id = r.id
+        FROM recording rec
+        JOIN meeting m ON rec.meeting_id = m.id
+        JOIN room r ON m.room_id = r.id
+        WHERE t.recording_id = rec.id
+        AND t.source_kind = 'room'
+        AND t.room_id IS NULL
+    """)
+
+    # Fix missing meeting_id for ROOM-type transcripts
+    # The meeting_id field exists but was never populated
+    op.execute("""
+        UPDATE transcript AS t
+        SET meeting_id = rec.meeting_id
+        FROM recording rec
+        WHERE t.recording_id = rec.id
+        AND t.source_kind = 'room'
+        AND t.meeting_id IS NULL
+        AND rec.meeting_id IS NOT NULL
+    """)
+
+
+def downgrade() -> None:
+    # Drop the index first
+    op.drop_index("idx_transcript_room_id", "transcript")
+
+    # Drop the room_id column
+    op.drop_column("transcript", "room_id")

server/reflector/db/transcripts.py

@@ -74,10 +74,12 @@ transcripts = sqlalchemy.Table(
     # the main "audio deleted" is the presence of the audio itself / consents not-given
     # same field could've been in recording/meeting, and it's maybe even ok to dupe it at need
     sqlalchemy.Column("audio_deleted", sqlalchemy.Boolean),
+    sqlalchemy.Column("room_id", sqlalchemy.String),
     sqlalchemy.Index("idx_transcript_recording_id", "recording_id"),
     sqlalchemy.Index("idx_transcript_user_id", "user_id"),
     sqlalchemy.Index("idx_transcript_created_at", "created_at"),
     sqlalchemy.Index("idx_transcript_user_id_recording_id", "user_id", "recording_id"),
+    sqlalchemy.Index("idx_transcript_room_id", "room_id"),
 )
 
 
@@ -167,6 +169,7 @@ class Transcript(BaseModel):
     zulip_message_id: int | None = None
     source_kind: SourceKind
     audio_deleted: bool | None = None
+    room_id: str | None = None
 
     @field_serializer("created_at", when_used="json")
     def serialize_datetime(self, dt: datetime) -> str:
@@ -331,17 +334,10 @@ class TranscriptController:
         - `room_id`: filter transcripts by room ID
         - `search_term`: filter transcripts by search term
         """
-        from reflector.db.meetings import meetings
-        from reflector.db.recordings import recordings
         from reflector.db.rooms import rooms
 
-        query = (
+        query = transcripts.select().join(
-            transcripts.select()
+            rooms, transcripts.c.room_id == rooms.c.id, isouter=True
-            .join(
-                recordings, transcripts.c.recording_id == recordings.c.id, isouter=True
-            )
-            .join(meetings, recordings.c.meeting_id == meetings.c.id, isouter=True)
-            .join(rooms, meetings.c.room_id == rooms.c.id, isouter=True)
         )
 
         if user_id:
@@ -355,7 +351,7 @@ class TranscriptController:
             query = query.where(transcripts.c.source_kind == source_kind)
 
         if room_id:
-            query = query.where(rooms.c.id == room_id)
+            query = query.where(transcripts.c.room_id == room_id)
 
         if search_term:
             query = query.where(transcripts.c.title.ilike(f"%{search_term}%"))
@@ -368,7 +364,6 @@ class TranscriptController:
         query = query.with_only_columns(
             transcript_columns
             + [
-                rooms.c.id.label("room_id"),
                 rooms.c.name.label("room_name"),
             ]
         )
@@ -419,6 +414,22 @@ class TranscriptController:
             return None
         return Transcript(**result)
 
+    async def get_by_room_id(self, room_id: str, **kwargs) -> list[Transcript]:
+        """
+        Get transcripts by room_id (direct access without joins)
+        """
+        query = transcripts.select().where(transcripts.c.room_id == room_id)
+        if "user_id" in kwargs:
+            query = query.where(transcripts.c.user_id == kwargs["user_id"])
+        if "order_by" in kwargs:
+            order_by = kwargs["order_by"]
+            field = getattr(transcripts.c, order_by[1:])
+            if order_by.startswith("-"):
+                field = field.desc()
+            query = query.order_by(field)
+        results = await database.fetch_all(query)
+        return [Transcript(**result) for result in results]
+
     async def get_by_id_for_http(
         self,
         transcript_id: str,
@@ -469,6 +480,8 @@ class TranscriptController:
         user_id: str | None = None,
         recording_id: str | None = None,
         share_mode: str = "private",
+        meeting_id: str | None = None,
+        room_id: str | None = None,
     ):
         """
         Add a new transcript
@@ -481,6 +494,8 @@ class TranscriptController:
             user_id=user_id,
             recording_id=recording_id,
             share_mode=share_mode,
+            meeting_id=meeting_id,
+            room_id=room_id,
         )
         query = transcripts.insert().values(**transcript.model_dump())
         await database.execute(query)

server/reflector/worker/process.py

@@ -101,6 +101,8 @@ async def process_recording(bucket_name: str, object_key: str):
             user_id=room.user_id,
             recording_id=recording.id,
             share_mode="public",
+            meeting_id=meeting.id,
+            room_id=room.id,
         )
 
     _, extension = os.path.splitext(object_key)