Merge branch 'main' into feat/consent-disable

server/reflector/db/recordings.py

@@ -3,6 +3,7 @@ from typing import Literal
 
 import sqlalchemy as sa
 from pydantic import BaseModel, Field
+from sqlalchemy import or_
 
 from reflector.db import get_database, metadata
 from reflector.utils import generate_uuid4
@@ -79,5 +80,35 @@ class RecordingController:
         results = await get_database().fetch_all(query)
         return [Recording(**row) for row in results]
 
+    async def get_multitrack_needing_reprocessing(
+        self, bucket_name: str
+    ) -> list[Recording]:
+        """
+        Get multitrack recordings that need reprocessing:
+        - Have track_keys (multitrack)
+        - Either have no transcript OR transcript has error status
+
+        This is more efficient than fetching all recordings and filtering in Python.
+        """
+        from reflector.db.transcripts import (
+            transcripts,  # noqa: PLC0415 cyclic import
+        )
+
+        query = (
+            recordings.select()
+            .outerjoin(transcripts, recordings.c.id == transcripts.c.recording_id)
+            .where(
+                recordings.c.bucket_name == bucket_name,
+                recordings.c.track_keys.isnot(None),
+                or_(
+                    transcripts.c.id.is_(None),
+                    transcripts.c.status == "error",
+                ),
+            )
+        )
+        results = await get_database().fetch_all(query)
+        recordings_list = [Recording(**row) for row in results]
+        return [r for r in recordings_list if r.is_multitrack]
+
 
 recordings_controller = RecordingController()

server/reflector/db/transcripts.py

@@ -44,6 +44,7 @@ transcripts = sqlalchemy.Table(
     sqlalchemy.Column("title", sqlalchemy.String),
     sqlalchemy.Column("short_summary", sqlalchemy.String),
     sqlalchemy.Column("long_summary", sqlalchemy.String),
+    sqlalchemy.Column("action_items", sqlalchemy.JSON),
     sqlalchemy.Column("topics", sqlalchemy.JSON),
     sqlalchemy.Column("events", sqlalchemy.JSON),
     sqlalchemy.Column("participants", sqlalchemy.JSON),
@@ -164,6 +165,10 @@ class TranscriptFinalLongSummary(BaseModel):
     long_summary: str
 
 
+class TranscriptActionItems(BaseModel):
+    action_items: dict
+
+
 class TranscriptFinalTitle(BaseModel):
     title: str
 
@@ -204,6 +209,7 @@ class Transcript(BaseModel):
     locked: bool = False
     short_summary: str | None = None
     long_summary: str | None = None
+    action_items: dict | None = None
     topics: list[TranscriptTopic] = []
     events: list[TranscriptEvent] = []
     participants: list[TranscriptParticipant] | None = []
@@ -368,7 +374,12 @@ class TranscriptController:
         room_id: str | None = None,
         search_term: str | None = None,
         return_query: bool = False,
-        exclude_columns: list[str] = ["topics", "events", "participants"],
+        exclude_columns: list[str] = [
+            "topics",
+            "events",
+            "participants",
+            "action_items",
+        ],
     ) -> list[Transcript]:
         """
         Get all transcripts