feat: API optimizations — quota batching, ETags, caching, async sponsor (v0.9.7)

Nine efficiency improvements across the data pipeline:

1. NewsAPI OR batching (news_service.py + news_fetcher.py)
   - Combine up to 4 bills per NewsAPI call using OR query syntax
   - NEWSAPI_BATCH_SIZE=4 means ~4× effective daily quota (100→400 bill-fetches)
   - fetch_news_for_bill_batch task; fetch_news_for_active_bills queues batches

2. Google News RSS cache (news_service.py)
   - 2-hour Redis cache shared between news_fetcher and trend_scorer
   - Eliminates duplicate RSS hits when both workers run against same bill
   - clear_gnews_cache() admin helper + admin endpoint

3. pytrends keyword batching (trends_service.py + trend_scorer.py)
   - Compare up to 5 bills per pytrends call instead of 1
   - get_trends_scores_batch() returns scores in original order
   - Reduces pytrends calls by ~5× and associated rate-limit risk

4. GovInfo ETags (govinfo_api.py + document_fetcher.py)
   - If-None-Match conditional GET; DocumentUnchangedError on HTTP 304
   - ETags stored in Redis (30-day TTL) keyed by MD5(url)
   - document_fetcher catches DocumentUnchangedError → {"status": "unchanged"}

5. Anthropic prompt caching (llm_service.py)
   - cache_control: {type: ephemeral} on system messages in AnthropicProvider
   - Caches the ~700-token system prompt server-side; ~50% cost reduction on
     repeated calls within the 5-minute cache window

6. Async sponsor fetch (congress_poller.py)
   - New fetch_sponsor_for_bill Celery task replaces blocking get_bill_detail()
     inline in poll loop
   - Bills saved immediately with sponsor_id=None; sponsor linked async
   - Removes 0.25s sleep per new bill from poll hot path

7. Skip doc fetch for procedural actions (congress_poller.py)
   - _DOC_PRODUCING_CATEGORIES = {vote, committee_report, presidential, ...}
   - fetch_bill_documents only enqueued when action is likely to produce
     new GovInfo text (saves ~60–70% of unnecessary document fetch attempts)

8. Adaptive poll frequency (congress_poller.py)
   - _is_congress_off_hours(): weekends + before 9AM / after 9PM EST
   - Skips poll if off-hours AND last poll < 1 hour ago
   - Prevents wasteful polling when Congress is not in session

9. Admin panel additions (admin.py + settings/page.tsx + api.ts)
   - GET /api/admin/newsapi-quota → remaining calls today
   - POST /api/admin/clear-gnews-cache → flush RSS cache
   - Settings page shows NewsAPI quota remaining (amber if < 10)
   - "Clear Google News Cache" button in Manual Controls

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

backend/app/workers/llm_processor.py

@@ -7,9 +7,10 @@ import time
 
 from sqlalchemy import text
 
+from app.config import settings
 from app.database import get_sync_db
 from app.models import Bill, BillBrief, BillDocument, Member
-from app.services.llm_service import get_llm_provider
+from app.services.llm_service import RateLimitError, get_llm_provider
 from app.workers.celery_app import celery_app
 
 logger = logging.getLogger(__name__)
@@ -17,8 +18,8 @@ logger = logging.getLogger(__name__)
 
 @celery_app.task(
     bind=True,
-    max_retries=2,
-    rate_limit="10/m",  # Respect LLM provider rate limits
+    max_retries=8,
+    rate_limit=f"{settings.LLM_RATE_LIMIT_RPM}/m",
     name="app.workers.llm_processor.process_document_with_llm",
 )
 def process_document_with_llm(self, document_id: int):
@@ -120,10 +121,14 @@ def process_document_with_llm(self, document_id: int):
 
         return {"status": "ok", "brief_id": db_brief.id, "brief_type": brief_type}
 
+    except RateLimitError as exc:
+        db.rollback()
+        logger.warning(f"LLM rate limit hit ({exc.provider}); retrying in {exc.retry_after}s")
+        raise self.retry(exc=exc, countdown=exc.retry_after)
     except Exception as exc:
         db.rollback()
         logger.error(f"LLM processing failed for document {document_id}: {exc}")
-        raise self.retry(exc=exc, countdown=300)  # 5 min backoff for LLM failures
+        raise self.retry(exc=exc, countdown=300)  # 5 min backoff for other failures
     finally:
         db.close()