fix(strategy): use word-boundary token matching for short crypto tickers to prevent false positives

Substring matching over question_lower flagged non-crypto markets as crypto:
'dissolved' matched 'sol', 'Canada' matched 'ada', 'Seth' matched 'eth'.
Those false flags armed the BTC-dominance signal (btc_dom_lo=+0.06 observed
on politics markets in production).

Short tickers (btc, eth, sol, xrp, doge, ltc, bnb, ada, avax) now go through
has_token(), which requires non-alphanumeric boundaries so 'ETH', '$ETH' and
'ETH/USD' still match. Long unambiguous names (bitcoin, ethereum, solana,
cardano, ...) remain substring checks.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

bot/strategy/bayesian.py

@@ -13,6 +13,7 @@ Polymarket might reflect in a slow-moving order book.
 import logging
 import math
 import os
+import re
 import uuid
 from dataclasses import dataclass, field
 from datetime import datetime, timedelta, timezone
@@ -159,6 +160,21 @@ def _days_to_resolution(end_date: str) -> int:
         return 30
 
 
+def has_token(text: str, token: str) -> bool:
+    """
+    True if `token` appears in `text` as a standalone word.
+
+    Short crypto tickers (eth, sol, ada, …) must NOT match inside ordinary
+    words — "Seth", "dissolved", "Canada" — but must still match the usual
+    market phrasings: "ETH", "$ETH", "ETH/USD", "SOL reach $200".  Boundaries
+    are any non-alphanumeric character (or start/end of string), so "$" and
+    "/" delimit correctly.
+    """
+    return re.search(
+        rf"(?<![A-Za-z0-9]){re.escape(token)}(?![A-Za-z0-9])", text, re.IGNORECASE
+    ) is not None
+
+
 # ─────────────────────────────────────────────────────────────────────────────
 # Phase 3 — GNews priority scoring
 # ─────────────────────────────────────────────────────────────────────────────
@@ -345,13 +361,18 @@ class BayesianStrategy:
             "below", "under", "less than", "lower", "drop",
         ])
 
-        is_btc = "btc" in question_lower or "bitcoin" in question_lower
-        is_eth = "eth" in question_lower or "ethereum" in question_lower
-        is_sol = "sol" in question_lower or "solana" in question_lower
-        is_xrp = "xrp" in question_lower or "ripple" in question_lower
-        is_doge = "doge" in question_lower or "dogecoin" in question_lower
+        # Short tickers need word boundaries: "Seth" contains "eth",
+        # "dissolved" contains "sol", "Canada" contains "ada".  Long
+        # unambiguous names (bitcoin, ethereum, …) stay as substrings.
+        is_btc = has_token(question_lower, "btc") or "bitcoin" in question_lower
+        is_eth = has_token(question_lower, "eth") or "ethereum" in question_lower
+        is_sol = has_token(question_lower, "sol") or "solana" in question_lower
+        is_xrp = has_token(question_lower, "xrp") or "ripple" in question_lower
+        is_doge = has_token(question_lower, "doge") or "dogecoin" in question_lower
         is_altcoin = is_sol or is_xrp or is_doge or any(
-            w in question_lower for w in ["ltc", "litecoin", "bnb", "ada", "cardano", "avax", "avalanche"]
+            has_token(question_lower, t) for t in ["ltc", "bnb", "ada", "avax"]
+        ) or any(
+            w in question_lower for w in ["litecoin", "cardano", "avalanche"]
         )
         is_general_crypto = any(
             w in question_lower for w in ["crypto", "market cap", "total market", "altcoin", "defi"]