sentiment: LLM buy/hold/avoid + full analysis, and search-budget scoping

Richer LLM output (same grounded call, ~no extra cost):
- All providers now also return a recommendation (buy/hold/avoid) and a thorough
  reasoning paragraph; Gemini now actually captures reasoning + grounding
  citations (it was dropping them). Stored on sentiment_scores (migration 008),
  exposed in the API; display-only — NOT fed into the composite/EV.
- Ticker Sentiment panel shows an "LLM view" badge and a "Full analysis & sources"
  expander with the complete reasoning + citations.

Search-budget scoping (Gemini grounding free tier = 5000/mo):
- collect_sentiment now targets only watchlist + open paper trades + top-N by
  composite, skips tickers refreshed within sentiment_fresh_hours (72h), and caps
  per run (sentiment_max_per_run). Once the relevant set is fresh, runs spend 0
  searches until it ages out — bounding monthly usage well under the free tier.
- Widened sentiment lookback to 7d (scoring + display) so sparser collection
  still feeds the dimension score.

Deploy: alembic upgrade (sentiment_scores.recommendation). Switch provider to
Gemini Flash in Admin for the cost win (grounded, cheapest).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

app/config.py

@@ -44,6 +44,12 @@ class Settings(BaseSettings):
     # Scheduled Jobs
     data_collector_frequency: str = "daily"
     sentiment_poll_interval_minutes: int = 30
+    # Sentiment search-budget controls (Gemini grounding free tier = 5000/month).
+    # Only fetch sentiment for relevant tickers (watchlist + open trades + top-N by
+    # composite), skip ones refreshed within fresh_hours, and cap per run.
+    sentiment_fresh_hours: int = 72
+    sentiment_max_per_run: int = 25
+    sentiment_top_composite: int = 30
     fundamental_fetch_frequency: str = "daily"
     rr_scan_frequency: str = "daily"
     alerts_frequency: str = "hourly"