karaoke-gen 0.96.0__py3-none-any.whl → 0.99.3__py3-none-any.whl

backend/api/routes/health.py

@@ -13,6 +13,9 @@ from backend.services.flacfetch_client import get_flacfetch_client
 from backend.services.email_service import get_email_service
 from backend.services.stripe_service import get_stripe_service
 from backend.services.encoding_service import get_encoding_service
+from backend.services.spacy_preloader import get_preloaded_model, is_model_preloaded
+from backend.services.nltk_preloader import get_preloaded_cmudict, is_cmudict_preloaded
+from backend.services.langfuse_preloader import get_preloaded_langfuse_handler, is_langfuse_preloaded, is_langfuse_configured
 
 router = APIRouter()
 logger = logging.getLogger(__name__)
@@ -334,6 +337,68 @@ async def detailed_health_check() -> Dict[str, Any]:
     }
 
 
+@router.get("/health/preload-status")
+async def preload_status() -> Dict[str, Any]:
+    """
+    Check status of preloaded resources for performance optimization.
+
+    Use this endpoint to verify that NLTK, SpaCy, and Langfuse resources
+    were successfully preloaded at container startup. If any show as
+    not preloaded, check Cloud Run startup logs for errors.
+
+    Expected state after successful deployment:
+    - spacy.preloaded: true
+    - nltk.preloaded: true
+    - langfuse.preloaded: true (if configured) or configured: false
+    """
+    # SpaCy status
+    spacy_model = get_preloaded_model("en_core_web_sm")
+    spacy_status = {
+        "preloaded": is_model_preloaded("en_core_web_sm"),
+        "model": "en_core_web_sm",
+    }
+    if spacy_model:
+        spacy_status["vocab_size"] = len(spacy_model.vocab)
+
+    # NLTK status
+    cmudict = get_preloaded_cmudict()
+    nltk_status = {
+        "preloaded": is_cmudict_preloaded(),
+        "resource": "cmudict",
+    }
+    if cmudict:
+        nltk_status["entries"] = len(cmudict)
+
+    # Langfuse status
+    langfuse_handler = get_preloaded_langfuse_handler()
+    langfuse_status = {
+        "configured": is_langfuse_configured(),
+        "preloaded": is_langfuse_preloaded(),
+    }
+    if langfuse_handler:
+        langfuse_status["handler_type"] = type(langfuse_handler).__name__
+
+    # Overall status
+    all_preloaded = (
+        spacy_status["preloaded"]
+        and nltk_status["preloaded"]
+        and (langfuse_status["preloaded"] or not langfuse_status["configured"])
+    )
+
+    return {
+        "status": "ok" if all_preloaded else "degraded",
+        "message": "All resources preloaded" if all_preloaded else "Some resources not preloaded - check startup logs",
+        "spacy": spacy_status,
+        "nltk": nltk_status,
+        "langfuse": langfuse_status,
+        "performance_impact": {
+            "spacy_preload": "Saves ~60s on first lyrics correction",
+            "nltk_preload": "Saves ~100-150s on SyllablesMatchHandler init",
+            "langfuse_preload": "Saves ~200s on AgenticCorrector init",
+        }
+    }
+
+
 @router.get("/readiness")
 async def readiness_check() -> Dict[str, str]:
     """Readiness check endpoint for Cloud Run."""

backend/api/routes/jobs.py

@@ -25,10 +25,12 @@ from backend.models.requests import (
 from backend.services.job_manager import JobManager
 from backend.services.worker_service import get_worker_service
 from backend.services.storage_service import StorageService
+from backend.services.theme_service import get_theme_service
 from backend.config import get_settings
 from backend.api.dependencies import require_admin, require_auth, require_instrumental_auth
 from backend.services.auth_service import UserType, AuthResult
 from backend.services.metrics import metrics
+from backend.utils.test_data import is_test_email
 
 
 logger = logging.getLogger(__name__)
@@ -92,11 +94,22 @@ async def create_job(
         settings = get_settings()
         effective_enable_youtube_upload = request.enable_youtube_upload if request.enable_youtube_upload is not None else settings.default_enable_youtube_upload
 
+        # Apply default theme - all jobs require a theme
+        theme_service = get_theme_service()
+        effective_theme_id = theme_service.get_default_theme_id()
+        if not effective_theme_id:
+            raise HTTPException(
+                status_code=422,
+                detail="No default theme configured. Please contact support or specify a theme_id."
+            )
+        logger.info(f"Applying default theme: {effective_theme_id}")
+
         # Create job with all preferences
         job_create = JobCreate(
             url=str(request.url),
             artist=request.artist,
             title=request.title,
+            theme_id=effective_theme_id,  # Required - all jobs must have a theme
             enable_cdg=request.enable_cdg,
             enable_txt=request.enable_txt,
             enable_youtube_upload=effective_enable_youtube_upload,
@@ -182,6 +195,7 @@ async def list_jobs(
     client_id: Optional[str] = None,
     created_after: Optional[str] = None,
     created_before: Optional[str] = None,
+    exclude_test: bool = True,
     limit: int = 100,
     auth_result: AuthResult = Depends(require_auth)
 ) -> List[Job]:
@@ -196,6 +210,7 @@ async def list_jobs(
         client_id: Filter by request_metadata.client_id (customer identifier)
         created_after: Filter jobs created after this ISO datetime (e.g., 2024-01-01T00:00:00Z)
         created_before: Filter jobs created before this ISO datetime
+        exclude_test: If True (default), exclude jobs from test users (admin only)
         limit: Maximum number of jobs to return (default 100)
 
     Returns:
@@ -242,6 +257,10 @@ async def list_jobs(
             limit=limit
         )
 
+        # Filter out test user jobs if exclude_test is True (admin only)
+        if exclude_test and auth_result.is_admin:
+            jobs = [j for j in jobs if not is_test_email(j.user_email or "")]
+
         logger.debug(f"Listed {len(jobs)} jobs for user={auth_result.user_email}, admin={auth_result.is_admin}")
         return jobs
     except HTTPException: