Add versioned podcast asset metadata schema and backfill script

backend/api/podcast/handlers/audio.py

@@ -26,6 +26,7 @@ from services.database import get_db
 from middleware.auth_middleware import get_current_user, get_current_user_with_query_token
 from api.story_writer.utils.auth import require_authenticated_user
 from utils.asset_tracker import save_asset_to_library
+from models.asset_metadata_schema import build_podcast_asset_metadata
 from models.story_models import StoryAudioResult
 from loguru import logger
 from ..constants import get_podcast_audio_service, get_podcast_media_dir
@@ -217,11 +218,11 @@ async def upload_podcast_audio(
                     title=f"Uploaded Audio - {project_id}",
                     description="Uploaded podcast audio/voice sample",
                     tags=["podcast", "audio", "upload", project_id],
-                    asset_metadata={
-                        "project_id": project_id,
-                        "type": "uploaded_audio",
-                        "status": "completed",
-                    },
+                    asset_metadata=build_podcast_asset_metadata(
+                        asset_role="uploaded_audio",
+                        project_id=project_id,
+                        origin="podcast.audio.upload",
+                    ),
                 )
             except Exception as e:
                 logger.warning(f"[Podcast] Failed to save audio asset: {e}")
@@ -455,11 +456,12 @@ async def generate_podcast_audio(
                 provider=result.get("provider"),
                 model=result.get("model"),
                 cost=result.get("cost"),
-                asset_metadata={
-                    "scene_id": request.scene_id,
-                    "scene_title": request.scene_title,
-                    "status": "completed",
-                },
+                asset_metadata=build_podcast_asset_metadata(
+                    asset_role="podcast_audio",
+                    project_id=request.project_id,
+                    origin="podcast.audio.generate",
+                    extras={"scene_id": request.scene_id, "scene_title": request.scene_title},
+                ),
             )
     except Exception as e:
         logger.warning(f"[Podcast] Failed to save audio asset: {e}")
@@ -621,13 +623,12 @@ async def combine_podcast_audio(
                     title=f"Combined Podcast - {request.project_id}",
                     description=f"Combined podcast audio from {len(request.scene_ids)} scenes",
                     tags=["podcast", "audio", "combined", request.project_id],
-                    asset_metadata={
-                        "project_id": request.project_id,
-                        "scene_ids": request.scene_ids,
-                        "scene_count": len(request.scene_ids),
-                        "total_duration": total_duration,
-                        "status": "completed",
-                    },
+                    asset_metadata=build_podcast_asset_metadata(
+                        asset_role="combined_podcast_audio",
+                        project_id=request.project_id,
+                        origin="podcast.audio.combine",
+                        extras={"scene_ids": request.scene_ids, "scene_count": len(request.scene_ids), "total_duration": total_duration},
+                    ),
                 )
             except Exception as e:
                 logger.warning(f"[Podcast] Failed to save combined audio asset: {e}")

backend/api/podcast/handlers/avatar.py

@@ -18,6 +18,7 @@ from api.story_writer.utils.auth import require_authenticated_user
 from services.llm_providers.main_image_generation import generate_image
 from services.llm_providers.main_image_editing import edit_image
 from utils.asset_tracker import save_asset_to_library
+from models.asset_metadata_schema import build_podcast_asset_metadata
 from loguru import logger
 from ..constants import get_podcast_media_dir, PODCAST_AVATARS_SUBDIR
 from ..presenter_personas import choose_persona_id, get_persona
@@ -111,11 +112,11 @@ async def upload_podcast_avatar(
                     title=f"Podcast Presenter Avatar - {project_id}",
                     description="Podcast presenter avatar image",
                     tags=["podcast", "avatar", project_id],
-                    asset_metadata={
-                        "project_id": project_id,
-                        "type": "presenter_avatar",
-                        "status": "completed",
-                    },
+                    asset_metadata=build_podcast_asset_metadata(
+                        asset_role="presenter_avatar",
+                        project_id=project_id,
+                        origin="podcast.avatar.upload",
+                    ),
                 )
             except Exception as e:
                 logger.warning(f"[Podcast] Failed to save avatar asset (non-fatal): {e}")
@@ -223,12 +224,12 @@ async def make_avatar_presentable(
                     tags=["podcast", "avatar", "presenter", "transformed", project_id],
                     provider=result.provider,
                     model=result.model,
-                    asset_metadata={
-                        "project_id": project_id,
-                        "type": "transformed_presenter",
-                        "original_avatar_url": avatar_url,
-                        "status": "completed",
-                    },
+                    asset_metadata=build_podcast_asset_metadata(
+                        asset_role="transformed_presenter",
+                        project_id=project_id,
+                        origin="podcast.avatar.make_presentable",
+                        extras={"original_avatar_url": avatar_url},
+                    ),
                 )
             except Exception as e:
                 logger.warning(f"[Podcast] Failed to save transformed avatar asset: {e}")
@@ -404,14 +405,12 @@ async def generate_podcast_presenters(
                         tags=["podcast", "avatar", "presenter", project_id],
                         provider=result.provider,
                         model=result.model,
-                        asset_metadata={
-                            "project_id": project_id,
-                            "speaker_number": i + 1,
-                            "type": "generated_presenter",
-                            "status": "completed",
-                        "persona_id": selected_persona_id,
-                        "seed": seed,
-                        },
+                        asset_metadata=build_podcast_asset_metadata(
+                            asset_role="generated_presenter",
+                            project_id=project_id,
+                            origin="podcast.avatar.generate",
+                            extras={"speaker_number": i + 1, "persona_id": selected_persona_id, "seed": seed},
+                        ),
                     )
                 except Exception as e:
                     logger.warning(f"[Podcast] Failed to save presenter asset: {e}")

backend/api/podcast/handlers/images.py

@@ -16,6 +16,7 @@ from middleware.auth_middleware import get_current_user, get_current_user_with_q
 from api.story_writer.utils.auth import require_authenticated_user
 from services.llm_providers.main_image_generation import generate_image, generate_character_image
 from utils.asset_tracker import save_asset_to_library
+from models.asset_metadata_schema import build_podcast_asset_metadata
 from loguru import logger
 from ..constants import get_podcast_media_dir
 from ..models import PodcastImageRequest, PodcastImageResponse
@@ -417,11 +418,12 @@ async def generate_podcast_scene_image(
                 tags=["podcast", "scene", request.scene_id],
                 provider=result.provider,
                 model=result.model,
-                asset_metadata={
-                    "scene_id": request.scene_id,
-                    "scene_title": request.scene_title,
-                    "status": "completed",
-                },
+                asset_metadata=build_podcast_asset_metadata(
+                    asset_role="podcast_scene_image",
+                    project_id=request.project_id,
+                    origin="podcast.images.generate",
+                    extras={"scene_id": request.scene_id, "scene_title": request.scene_title},
+                ),
             )
         except Exception as e:
             logger.warning(f"[Podcast] Failed to save image asset: {e}")

backend/models/asset_metadata_schema.py

@@ -0,0 +1,76 @@
+"""Shared schema/builders for content asset metadata."""
+
+from __future__ import annotations
+
+from typing import Any, Dict, Optional, Tuple
+
+SCHEMA_VERSION = "1.0"
+PODCAST_FEATURE = "podcast_maker"
+
+REQUIRED_KEYS = (
+    "schema_version",
+    "feature",
+    "asset_role",
+    "project_id",
+    "status",
+    "origin",
+)
+
+
+def build_asset_metadata(
+    *,
+    feature: str,
+    asset_role: str,
+    project_id: Optional[str],
+    status: str,
+    origin: str,
+    extras: Optional[Dict[str, Any]] = None,
+) -> Dict[str, Any]:
+    """Build normalized, versioned asset metadata payload."""
+    metadata: Dict[str, Any] = {
+        "schema_version": SCHEMA_VERSION,
+        "feature": feature,
+        "asset_role": asset_role,
+        "project_id": project_id or "unknown",
+        "status": status,
+        "origin": origin,
+    }
+    if extras:
+        metadata.update({k: v for k, v in extras.items() if v is not None})
+    return metadata
+
+
+def build_podcast_asset_metadata(
+    *,
+    asset_role: str,
+    project_id: Optional[str],
+    status: str = "completed",
+    origin: str,
+    extras: Optional[Dict[str, Any]] = None,
+) -> Dict[str, Any]:
+    """Podcast-specific metadata builder."""
+    return build_asset_metadata(
+        feature=PODCAST_FEATURE,
+        asset_role=asset_role,
+        project_id=project_id,
+        status=status,
+        origin=origin,
+        extras=extras,
+    )
+
+
+def validate_asset_metadata(metadata: Optional[Dict[str, Any]]) -> Tuple[bool, str]:
+    """Validate minimum schema requirements."""
+    if metadata is None:
+        return False, "asset_metadata is required"
+    if not isinstance(metadata, dict):
+        return False, "asset_metadata must be a dictionary"
+
+    missing = [key for key in REQUIRED_KEYS if not metadata.get(key)]
+    if missing:
+        return False, f"asset_metadata missing required keys: {', '.join(missing)}"
+
+    if str(metadata.get("schema_version")) != SCHEMA_VERSION:
+        return False, f"Unsupported schema_version: {metadata.get('schema_version')}"
+
+    return True, "ok"

backend/models/oauth_token_monitoring_models.py

@@ -40,10 +40,6 @@ class OAuthTokenMonitoringTask(Base):
     
     # Scheduling
     next_check = Column(DateTime, nullable=True, index=True)  # Next scheduled check time
-    next_retry_at = Column(DateTime, nullable=True, index=True)  # Backoff retry schedule for refresh failures
-    refresh_attempts = Column(Integer, default=0)  # Current retry attempt count for refresh workflow
-    terminal_failure_reason = Column(Text, nullable=True)  # Permanent failure reason requiring user action
-    channel_status = Column(String(32), default='connected')  # connected, degraded, disconnected
     
     # Metadata
     created_at = Column(DateTime, default=datetime.utcnow)
@@ -101,3 +97,4 @@ class OAuthTokenExecutionLog(Base):
     
     def __repr__(self):
         return f"<OAuthTokenExecutionLog(id={self.id}, task_id={self.task_id}, status={self.status}, execution_date={self.execution_date})>"
+

backend/scripts/backfill_podcast_asset_metadata.py

@@ -0,0 +1,63 @@
+"""Backfill recent podcast assets with normalized metadata schema."""
+
+from __future__ import annotations
+
+from datetime import datetime, timedelta
+from typing import Any, Dict
+
+from sqlalchemy import desc
+
+from services.database import SessionLocal
+from models.content_asset_models import ContentAsset, AssetSource
+from models.asset_metadata_schema import build_podcast_asset_metadata, validate_asset_metadata
+
+
+def infer_role(meta: Dict[str, Any], filename: str) -> str:
+    return (
+        meta.get("asset_role")
+        or meta.get("type")
+        or ("podcast_audio" if filename.lower().endswith((".mp3", ".wav", ".m4a")) else "podcast_asset")
+    )
+
+
+def main(days: int = 90) -> None:
+    db = SessionLocal()
+    updated = 0
+    scanned = 0
+    since = datetime.utcnow() - timedelta(days=days)
+    try:
+        assets = (
+            db.query(ContentAsset)
+            .filter(ContentAsset.source_module == AssetSource.PODCAST_MAKER)
+            .filter(ContentAsset.created_at >= since)
+            .order_by(desc(ContentAsset.created_at))
+            .all()
+        )
+
+        for asset in assets:
+            scanned += 1
+            meta = asset.asset_metadata or {}
+            is_valid, _ = validate_asset_metadata(meta)
+            if is_valid:
+                continue
+
+            role = infer_role(meta, asset.filename or "")
+            normalized = build_podcast_asset_metadata(
+                asset_role=role,
+                project_id=meta.get("project_id"),
+                status=meta.get("status", "completed"),
+                origin=meta.get("origin", "migration.backfill_podcast_asset_metadata"),
+                extras=meta,
+            )
+            asset.asset_metadata = normalized
+            db.add(asset)
+            updated += 1
+
+        db.commit()
+        print(f"Scanned={scanned} Updated={updated} Since={since.isoformat()}")
+    finally:
+        db.close()
+
+
+if __name__ == "__main__":
+    main()

backend/services/scheduler/__init__.py

@@ -26,10 +26,7 @@ from .executors.advertools_executor import AdvertoolsExecutor
 from .executors.sif_indexing_executor import SIFIndexingExecutor
 from .executors.market_trends_executor import MarketTrendsExecutor
 from .utils.task_loader import load_due_monitoring_tasks
-from .utils.oauth_token_task_loader import (
-    load_due_oauth_token_monitoring_tasks,
-    load_near_expiry_oauth_token_tasks
-)
+from .utils.oauth_token_task_loader import load_due_oauth_token_monitoring_tasks
 from .utils.website_analysis_task_loader import load_due_website_analysis_tasks
 from .utils.onboarding_full_website_analysis_task_loader import load_due_onboarding_full_website_analysis_tasks
 from .utils.deep_competitor_analysis_task_loader import load_due_deep_competitor_analysis_tasks
@@ -73,11 +70,6 @@ def get_scheduler() -> TaskScheduler:
             oauth_token_executor,
             load_due_oauth_token_monitoring_tasks
         )
-        _scheduler_instance.register_executor(
-            'oauth_token_refresh',
-            oauth_token_executor,
-            load_near_expiry_oauth_token_tasks
-        )
         
         # Register website analysis executor
         website_analysis_executor = WebsiteAnalysisExecutor()

backend/services/scheduler/executors/oauth_token_monitoring_executor.py

@@ -42,8 +42,6 @@ class OAuthTokenMonitoringExecutor(TaskExecutor):
         self.exception_handler = SchedulerExceptionHandler()
         # Expiration warning window (7 days before expiration)
         self.expiration_warning_days = 7
-        self.max_refresh_retries = 3
-        self.base_retry_backoff_minutes = 15
     
     async def execute_task(self, task: OAuthTokenMonitoringTask, db: Session) -> TaskExecutionResult:
         """
@@ -95,10 +93,6 @@ class OAuthTokenMonitoringExecutor(TaskExecutor):
                 task.last_success = datetime.utcnow()
                 task.status = 'active'
                 task.failure_reason = None
-                task.terminal_failure_reason = None
-                task.channel_status = 'connected'
-                task.refresh_attempts = 0
-                task.next_retry_at = None
                 # Reset failure tracking on success
                 task.consecutive_failures = 0
                 task.failure_pattern = None
@@ -118,7 +112,6 @@ class OAuthTokenMonitoringExecutor(TaskExecutor):
                 
                 task.last_failure = datetime.utcnow()
                 task.failure_reason = result.error_message
-                task.refresh_attempts = (task.refresh_attempts or 0) + 1
                 
                 if pattern and pattern.should_cool_off:
                     # Mark task for human intervention
@@ -133,9 +126,6 @@ class OAuthTokenMonitoringExecutor(TaskExecutor):
                     }
                     # Clear next_check - task won't run automatically
                     task.next_check = None
-                    task.next_retry_at = None
-                    task.channel_status = "disconnected"
-                    task.terminal_failure_reason = result.error_message
                     
                     self.logger.warning(
                         f"Task {task.id} marked for human intervention: "
@@ -143,17 +133,10 @@ class OAuthTokenMonitoringExecutor(TaskExecutor):
                         f"reason: {pattern.failure_reason.value}"
                     )
                 else:
+                    # Normal failure handling
+                    task.status = 'failed'
                     task.consecutive_failures = (task.consecutive_failures or 0) + 1
-                    if task.refresh_attempts >= self.max_refresh_retries:
-                        task.status = 'failed'
-                        task.channel_status = 'disconnected'
-                        task.terminal_failure_reason = result.error_message
-                        task.next_retry_at = None
-                    else:
-                        task.status = 'degraded'
-                        task.channel_status = 'degraded'
-                        delay_minutes = self.base_retry_backoff_minutes * (2 ** (task.refresh_attempts - 1))
-                        task.next_retry_at = datetime.utcnow() + timedelta(minutes=delay_minutes)
+                    # Do NOT update next_check - wait for manual trigger
                 
                 self.logger.warning(
                     f"OAuth token refresh failed for user {user_id}, platform {platform}. "
@@ -161,7 +144,7 @@ class OAuthTokenMonitoringExecutor(TaskExecutor):
                 )
                 
                 # Create UsageAlert notification for the user
-                self._create_failure_alert(user_id, platform, result.error_message, result.result_data, db, task)
+                self._create_failure_alert(user_id, platform, result.error_message, result.result_data, db)
             
             task.updated_at = datetime.utcnow()
             db.commit()
@@ -210,14 +193,12 @@ class OAuthTokenMonitoringExecutor(TaskExecutor):
                 task.last_failure = datetime.utcnow()
                 task.failure_reason = str(e)
                 task.status = 'failed'
-                task.channel_status = 'disconnected'
-                task.terminal_failure_reason = str(e)
                 task.last_check = datetime.utcnow()
                 task.updated_at = datetime.utcnow()
-                task.next_retry_at = None
+                # Do NOT update next_check - wait for manual trigger
                 
                 # Create UsageAlert notification for the user
-                self._create_failure_alert(user_id, task.platform, str(e), None, db, task)
+                self._create_failure_alert(user_id, task.platform, str(e), None, db)
                 
                 db.commit()
             except Exception as commit_error:
@@ -670,8 +651,7 @@ class OAuthTokenMonitoringExecutor(TaskExecutor):
         platform: str,
         error_message: str,
         result_data: Optional[Dict[str, Any]],
-        db: Session,
-        task: Optional[OAuthTokenMonitoringTask] = None
+        db: Session
     ):
         """
         Create a UsageAlert notification when OAuth token refresh fails.
@@ -743,20 +723,6 @@ class OAuthTokenMonitoringExecutor(TaskExecutor):
             # Get current billing period (YYYY-MM format)
             from datetime import datetime
             billing_period = datetime.utcnow().strftime("%Y-%m")
-
-            alert_payload = {
-                "requires_user_action": True,
-                "platform": platform,
-                "channel_status": getattr(task, "channel_status", "disconnected"),
-                "terminal_failure_reason": getattr(task, "terminal_failure_reason", error_message),
-                "next_retry_at": (
-                    task.next_retry_at.isoformat() if task and task.next_retry_at else None
-                ),
-                "refresh_attempts": getattr(task, "refresh_attempts", 0),
-                "max_refresh_retries": self.max_refresh_retries,
-            }
-
-            message = f"{message} [ALERT_PAYLOAD] {alert_payload}"
             
             # Create UsageAlert
             alert = UsageAlert(
@@ -820,3 +786,4 @@ class OAuthTokenMonitoringExecutor(TaskExecutor):
                 f"Defaulting to Weekly (7 days)."
             )
             return last_execution + timedelta(days=7)
+

backend/services/scheduler/utils/oauth_token_task_loader.py

@@ -3,7 +3,7 @@ OAuth Token Monitoring Task Loader
 Functions to load due OAuth token monitoring tasks from database.
 """
 
-from datetime import datetime, timedelta
+from datetime import datetime
 from typing import List, Optional, Union
 from sqlalchemy.orm import Session
 from sqlalchemy import and_, or_
@@ -52,34 +52,3 @@ def load_due_oauth_token_monitoring_tasks(
     
     return query.all()
 
-
-def load_near_expiry_oauth_token_tasks(
-    db: Session,
-    refresh_horizon_hours: int = 24,
-    user_id: Optional[Union[str, int]] = None
-) -> List[OAuthTokenMonitoringTask]:
-    """
-    Load OAuth tasks that should run token refresh logic soon.
-
-    Includes:
-    - tasks with a scheduled retry now due (next_retry_at <= now)
-    - tasks whose routine check is inside the near-expiry horizon window
-    """
-    now = datetime.utcnow()
-    horizon = now + timedelta(hours=max(refresh_horizon_hours, 1))
-
-    query = db.query(OAuthTokenMonitoringTask).filter(
-        and_(
-            OAuthTokenMonitoringTask.status.in_(['active', 'failed', 'degraded']),
-            or_(
-                OAuthTokenMonitoringTask.next_retry_at <= now,
-                OAuthTokenMonitoringTask.next_check <= horizon,
-                OAuthTokenMonitoringTask.next_check.is_(None)
-            )
-        )
-    )
-
-    if user_id is not None:
-        query = query.filter(OAuthTokenMonitoringTask.user_id == str(user_id))
-
-    return query.all()

backend/utils/asset_tracker.py

@@ -11,6 +11,8 @@ import logging
 import re
 from urllib.parse import urlparse
 
+from models.asset_metadata_schema import validate_asset_metadata
+
 logger = logging.getLogger(__name__)
 
 # Maximum file size (100MB)
@@ -140,6 +142,12 @@ def save_asset_to_library(
             if len(title) > 200:
                 title = title[:197] + '...'
         
+        metadata_payload = asset_metadata or {}
+        is_valid_metadata, validation_message = validate_asset_metadata(metadata_payload)
+        if not is_valid_metadata:
+            logger.error(f"Invalid asset metadata: {validation_message}")
+            return None
+
         service = ContentAssetService(db)
         asset = service.create_asset(
             user_id=user_id,
@@ -154,7 +162,7 @@ def save_asset_to_library(
             description=description,
             prompt=prompt,
             tags=tags or [],
-            asset_metadata=asset_metadata or {},
+            asset_metadata=metadata_payload,
             provider=provider,
             model=model,
             cost=cost,