Fix pitcher resolution: add MLB roster fallback for batter team lookup

Root cause: _resolve_batter_team() used historical statcast (2025 season)
to identify a batter's team. Players who changed teams in the offseason
had stale team names that no longer matched either participant in today's
game, causing `batter_team_unresolved` and leaving pitchers unresolved
even when both starters were known.

Changes:
- props_mapper.py: restructure _resolve_batter_team() so statcast early-
exits no longer skip the roster fallback; suppress stale historical-team
returns that don't match the current game (removed old line 349)
- mlb_starters.py: add fetch_mlb_current_roster_map() (MLB Stats API
/api/v1/sports/1/players?season=2026, process-lifetime cached) and
lookup_batter_current_team() which is called as Level 4 fallback
in _resolve_batter_team() when statcast resolution fails

Players now resolve via "mlb_roster_lookup" source for offseason
acquisitions, new players, and anyone not in statcast data.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

analytics/props_mapper.py

@@ -13,7 +13,7 @@ import pandas as pd
 
 from analytics.no_vig_props import american_to_implied_prob, compute_bet_ev, compute_edge
 from analytics.model_voice import build_hr_model_voice, build_strikeout_model_voice
-from data.mlb_starters import lookup_pitchers_for_game
+from data.mlb_starters import lookup_pitchers_for_game, lookup_batter_current_team
 from data.odds_name_map import map_odds_name_to_model_name
 from models.hr_probability_engine import build_hr_probability_result
 from models.pitcher_adjustment import build_pitcher_feature_row
@@ -316,37 +316,41 @@ def _resolve_batter_team(
     away_norm = _normalize_team_name(away_team)
     home_norm = _normalize_team_name(home_team)
 
-    if (
-        batter_statcast_df is None
-        or batter_statcast_df.empty
-        or not batter_name
-        or "player_name" not in batter_statcast_df.columns
-    ):
-        return ("", "unresolved")
-
-    normalized_target = _normalize_person_name(batter_name)
-    player_rows = batter_statcast_df[
-        batter_statcast_df["player_name"].astype(str).map(_normalize_person_name) == normalized_target
-    ].copy()
-    if player_rows.empty:
-        return ("", "unresolved")
-
-    if "source_season" in player_rows.columns:
-        current_rows = player_rows[pd.to_numeric(player_rows["source_season"], errors="coerce") == 2026].copy()
-        current_team = _infer_batter_team(batter_name=batter_name, batter_statcast_df=current_rows)
-        if current_team:
-            if current_team == away_norm and away_team:
-                return (away_team, "current_season_statcast")
-            if current_team == home_norm and home_team:
-                return (home_team, "current_season_statcast")
-
-    historical_team = _infer_batter_team(batter_name=batter_name, batter_statcast_df=player_rows)
-    if historical_team:
-        if historical_team == away_norm and away_team:
-            return (away_team, "historical_statcast")
-        if historical_team == home_norm and home_team:
-            return (home_team, "historical_statcast")
-        return (historical_team, "historical_statcast")
+    statcast_ok = (
+        batter_statcast_df is not None
+        and not batter_statcast_df.empty
+        and batter_name
+        and "player_name" in batter_statcast_df.columns
+    )
+    if statcast_ok:
+        normalized_target = _normalize_person_name(batter_name)
+        player_rows = batter_statcast_df[
+            batter_statcast_df["player_name"].astype(str).map(_normalize_person_name) == normalized_target
+        ].copy()
+        if not player_rows.empty:
+            if "source_season" in player_rows.columns:
+                current_rows = player_rows[pd.to_numeric(player_rows["source_season"], errors="coerce") == 2026].copy()
+                current_team = _infer_batter_team(batter_name=batter_name, batter_statcast_df=current_rows)
+                if current_team:
+                    if current_team == away_norm and away_team:
+                        return (away_team, "current_season_statcast")
+                    if current_team == home_norm and home_team:
+                        return (home_team, "current_season_statcast")
+
+            historical_team = _infer_batter_team(batter_name=batter_name, batter_statcast_df=player_rows)
+            if historical_team:
+                if historical_team == away_norm and away_team:
+                    return (away_team, "historical_statcast")
+                if historical_team == home_norm and home_team:
+                    return (home_team, "historical_statcast")
+                # historical_team doesn't match either current game team (player changed teams);
+                # fall through to roster lookup instead of returning a stale team name
+
+    # Level 4: current-season MLB roster lookup (handles offseason moves and new players)
+    if batter_name:
+        roster_team = lookup_batter_current_team(batter_name, away_team or "", home_team or "")
+        if roster_team:
+            return (roster_team, "mlb_roster_lookup")
 
     return ("", "unresolved")
 

data/mlb_starters.py

@@ -465,3 +465,72 @@ def lookup_pitchers_for_game(
             return v
 
     return {"home_pitcher": None, "away_pitcher": None}
+
+
+# ---------------------------------------------------------------------------
+# Current-season roster lookup (batter team resolution fallback)
+# ---------------------------------------------------------------------------
+
+_ROSTER_MAP_CACHE: dict[str, str] | None = None
+
+
+def fetch_mlb_current_roster_map(season: int = 2026) -> dict[str, str]:
+    """
+    Returns {normalized_player_name: canonical_team_code} for all active MLB players.
+    Cached for the process lifetime.  Uses MLB Stats API players endpoint.
+    """
+    global _ROSTER_MAP_CACHE
+    if _ROSTER_MAP_CACHE is not None:
+        return _ROSTER_MAP_CACHE
+
+    url = "https://statsapi.mlb.com/api/v1/sports/1/players"
+    params: dict[str, Any] = {"season": season, "gameType": "R"}
+    try:
+        r = requests.get(url, params=params, timeout=15)
+        r.raise_for_status()
+        data = r.json()
+    except Exception as exc:
+        _log.warning("[mlb_roster] fetch failed: %s", exc)
+        _ROSTER_MAP_CACHE = {}
+        return _ROSTER_MAP_CACHE
+
+    people = data.get("people", []) if isinstance(data, dict) else []
+    roster: dict[str, str] = {}
+    for person in people:
+        full_name = str(person.get("fullName", "") or "")
+        team_name = str((person.get("currentTeam") or {}).get("name", "") or "")
+        if not full_name or not team_name:
+            continue
+        norm_name = _normalize_person(full_name)
+        canon_team = _canonical_team(team_name)
+        if norm_name and canon_team:
+            roster[norm_name] = canon_team
+
+    _log.warning("[mlb_roster] loaded %d players for season %d", len(roster), season)
+    _ROSTER_MAP_CACHE = roster
+    return _ROSTER_MAP_CACHE
+
+
+def lookup_batter_current_team(
+    batter_name: str,
+    away_team: str,
+    home_team: str,
+    season: int = 2026,
+) -> str | None:
+    """
+    Returns the display team name (away_team or home_team) for a batter based on
+    the current MLB roster.  Returns None if the player is not found or is not
+    participating in this specific game.
+    """
+    roster = fetch_mlb_current_roster_map(season)
+    if not roster:
+        return None
+    norm_name = _normalize_person(batter_name)
+    canon_team = roster.get(norm_name)
+    if not canon_team:
+        return None
+    if canon_team == _canonical_team(away_team) and away_team:
+        return away_team
+    if canon_team == _canonical_team(home_team) and home_team:
+        return home_team
+    return None