Big refactoring

app/services/ingestion_service.py

@@ -9,10 +9,11 @@ import logging
 from dataclasses import dataclass
 from datetime import date, timedelta
 
-from sqlalchemy import select
+from sqlalchemy import func, select
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.exceptions import NotFoundError, ProviderError, RateLimitError
+from app.models.ohlcv import OHLCVRecord
 from app.models.settings import IngestionProgress
 from app.models.ticker import Ticker
 from app.providers.protocol import MarketDataProvider
@@ -50,6 +51,13 @@ async def _get_progress(db: AsyncSession, ticker_id: int) -> IngestionProgress |
     return result.scalar_one_or_none()
 
 
+async def _get_ohlcv_bar_count(db: AsyncSession, ticker_id: int) -> int:
+    result = await db.execute(
+        select(func.count()).select_from(OHLCVRecord).where(OHLCVRecord.ticker_id == ticker_id)
+    )
+    return int(result.scalar() or 0)
+
+
 async def _update_progress(
     db: AsyncSession, ticker_id: int, last_date: date
 ) -> None:
@@ -84,10 +92,17 @@ async def fetch_and_ingest(
     if end_date is None:
         end_date = date.today()
 
-    # Resolve start_date: use progress resume or default to 1 year ago
+    # Resolve start_date: use progress resume or default to 1 year ago.
+    # If we have too little history, force a one-year backfill even if
+    # ingestion progress exists (upsert makes this safe and idempotent).
     if start_date is None:
         progress = await _get_progress(db, ticker.id)
-        if progress is not None:
+        bar_count = await _get_ohlcv_bar_count(db, ticker.id)
+        minimum_backfill_bars = 200
+
+        if bar_count < minimum_backfill_bars:
+            start_date = end_date - timedelta(days=365)
+        elif progress is not None:
             start_date = progress.last_ingested_date + timedelta(days=1)
         else:
             start_date = end_date - timedelta(days=365)