tengu_copilot_score_ticker

io.github.Hlobo-dev/tengu-firm · Verify this server

Full per-ticker quant analysis. CALL THIS when the user asks about any specific stock (e.g. 'should I buy NVDA', 'what do you think of TSLA'). Returns blended_score, decile, conformal expected-return interval (90% band), 12-voter breakdown, factor tier, regime context, suggested position size, and a self-contained narrative. Use the narrative as a quotable summary; use the structured fields for follow-up questions. NAMESPACE: FIRM's universe is US EQUITIES. Nine tickers (BTC ETH LINK LTC COMP ARB NEAR APT ATOM) are ALSO crypto symbols; for those the response carries a `ticker_collision` block stating the score describes the US-listed EQUITY. If the user means the CRYPTO asset pass asset_class=crypto, which 404s (no FIRM crypto model yet). For ONE crypto sitting (liquid-book SCAN + scored-ordering RANK + top-N SLEEVE) call GET /api/crypto/sitting — that is DATA, signal_quality_mode=ordering_only, not a forecast. The full liquid book stays on GET /api/crypto/universe (not Alpaca's 36). For overnight movers / watchlist DATA call GET /api/crypto/overnight (X-API-Key) — a SLICE of that universe, data/context, not a score. For ONE US-equity sitting (full-book SCAN + attached factor RANK + top-N SLEEVE) call GET /api/equity/sitting — that is DATA, not a score, and do_not_place_from_mover_rank stays true. NEVER present an equity score as a crypto view.