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/routers/sentiment.py

@@ -30,7 +30,7 @@ def _parse_citations(citations_json: str) -> list[CitationItem]:
 @router.get("/sentiment/{symbol}", response_model=APIEnvelope)
 async def read_sentiment(
     symbol: str,
-    lookback_hours: float = Query(24, gt=0, description="Lookback window in hours"),
+    lookback_hours: float = Query(168, gt=0, description="Lookback window in hours"),
     _user=Depends(require_access),
     db: AsyncSession = Depends(get_db),
 ) -> APIEnvelope:
@@ -51,6 +51,7 @@ async def read_sentiment(
                 timestamp=s.timestamp,
                 reasoning=s.reasoning,
                 citations=_parse_citations(s.citations_json),
+                recommendation=s.recommendation,
             )
             for s in scores
         ],