bulk commit changes!

backend/news_service.py

@@ -5,6 +5,7 @@ import logging
 import os
 import re
 import time
+from collections.abc import Awaitable, Callable
 from io import BytesIO
 from urllib.parse import quote_plus
 
@@ -23,6 +24,7 @@ from backend.repository import (
 logger = logging.getLogger(__name__)
 
 PLACEHOLDER_IMAGE_PATH = "/static/images/placeholder.png"
+GENERIC_AI_FALLBACK_URL = "https://placehold.co/1200x630/0f172a/e2e8f0/png?text=AI+News"
 
 
 async def call_perplexity_api(query: str) -> dict | None:
@@ -419,7 +421,7 @@ def extract_image_keywords(headline: str) -> str:
     - Handles edge cases (empty, only stop words, special characters)
     """
     if not headline or not headline.strip():
-        return "news technology"
+        return "ai machine learning deep learning"
 
     # Normalize: remove special characters, keep alphanumeric and spaces
     cleaned = re.sub(r"[^\w\s]", " ", headline)
@@ -433,7 +435,7 @@ def extract_image_keywords(headline: str) -> str:
     keywords = keywords[:5]
 
     if not keywords:
-        return "news technology"
+        return "ai machine learning deep learning"
 
     return " ".join(keywords)
 
@@ -465,7 +467,7 @@ async def fetch_pixabay_image(query: str) -> tuple[str | None, str | None]:
     except Exception:
         logger.exception("Pixabay image retrieval failed")
 
-    return None, None
+    return GENERIC_AI_FALLBACK_URL, "Generic AI fallback"
 
 
 async def fetch_unsplash_image(query: str) -> tuple[str | None, str | None]:
@@ -569,7 +571,9 @@ _PROVIDER_REGISTRY: dict[str, tuple] = {
 }
 
 
-def get_enabled_providers() -> list[tuple[str, callable]]:
+def get_enabled_providers() -> list[
+    tuple[str, Callable[[str], Awaitable[tuple[str | None, str | None]]]]
+]:
     """Get ordered list of enabled providers based on config and available API keys."""
     provider_names = [
         p.strip().lower() for p in config.ROYALTY_IMAGE_PROVIDERS.split(",") if p.strip()
@@ -663,8 +667,16 @@ async def download_and_optimize_image(image_url: str) -> str | None:
         return None
 
 
-async def fetch_news_with_retry(max_attempts: int = 3) -> list[dict]:
+async def fetch_news_with_retry(
+    max_attempts: int = 3, article_count: int | None = None
+) -> list[dict]:
     query = "What are the latest AI news from the last hour? Include source URLs and image URLs."
+    if article_count is not None:
+        bounded = max(1, min(50, int(article_count)))
+        query = (
+            f"What are the latest AI news from the last hour? Return exactly {bounded} items. "
+            "Include source URLs and image URLs."
+        )
 
     for attempt in range(max_attempts):
         try:
@@ -687,8 +699,8 @@ async def fetch_news_with_retry(max_attempts: int = 3) -> list[dict]:
     return []
 
 
-async def process_and_store_news() -> int:
-    items = await fetch_news_with_retry()
+async def process_and_store_news(article_count: int | None = None) -> int:
+    items = await fetch_news_with_retry(article_count=article_count)
     if not items:
         logger.warning("No news items fetched this cycle")
         return 0