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/config.py

@@ -28,10 +28,10 @@ class Settings(BaseSettings):
     LLM_PROVIDER: str = "openai"  # openai | anthropic | gemini | ollama
 
     OPENAI_API_KEY: str = ""
-    OPENAI_MODEL: str = "gpt-4o"
+    OPENAI_MODEL: str = "gpt-4o-mini"      # gpt-4o-mini: excellent JSON quality at ~10x lower cost than gpt-4o
 
     ANTHROPIC_API_KEY: str = ""
-    ANTHROPIC_MODEL: str = "claude-opus-4-6"
+    ANTHROPIC_MODEL: str = "claude-sonnet-4-6"  # Sonnet matches Opus for structured tasks at ~5x lower cost
 
     GEMINI_API_KEY: str = ""
     GEMINI_MODEL: str = "gemini-2.0-flash"
@@ -39,6 +39,11 @@ class Settings(BaseSettings):
     OLLAMA_BASE_URL: str = "http://host.docker.internal:11434"
     OLLAMA_MODEL: str = "llama3.1"
 
+    # Max LLM requests per minute — Celery enforces this globally across all workers.
+    # Safe defaults: free Gemini=15 RPM, Anthropic paid=50 RPM, OpenAI paid=500 RPM.
+    # Raise this in .env once you confirm your API tier.
+    LLM_RATE_LIMIT_RPM: int = 10
+
     # Google Civic Information API (zip → representative lookup)
     # Free key: https://console.cloud.google.com/apis/library/civicinfo.googleapis.com
     CIVIC_API_KEY: str = ""