Indoor detection: title-based inference in merge layer + fix _merge_all_locked

- Add _INDOOR_TITLE_RE / _infer_indoor_title() to writer.py (matches zwift,
  ftp-builder, turbo-trainer, rodillo); replaces the narrower zwift-only regex
  that was local to write_athlete_json
- _is_outdoor now delegates to _infer_indoor_title so all four keywords are
  excluded from records and MMP aggregation
- apply_sidecar and _apply_sidecar_summary both set sub_sport=indoor when the
  title matches and no explicit sub_sport is already present
- _merge_one_locked: detect title-inferred activities as needs_merge and call
  apply_sidecar({},{}) so the _merged copy gets sub_sport=indoor written
- _merge_all_locked: read index upfront to populate to_merge with title-inferred
  IDs; call apply_sidecar({},{}) for activities in to_merge without sidecars;
  apply _apply_sidecar_summary to ALL summary entries (not only sidecar ones)

bincio/extract/writer.py

@@ -10,6 +10,18 @@ from bincio.extract.models import LapData, ParsedActivity
 from bincio.extract.simplify import build_geojson, preview_coords
 from bincio.extract.timeseries import build_timeseries
 
+# Titles that reliably identify indoor/virtual activities regardless of sub_sport metadata.
+# Strava imports from Zwift and FTP-builder platforms lose sub_sport on export.
+_INDOOR_TITLE_RE = re.compile(
+    r'\b(zwift|ftp[\s\-]builder|turbo[\s\-]?trainer|rodillo)\b',
+    re.IGNORECASE,
+)
+
+
+def _infer_indoor_title(title: str) -> bool:
+    """Return True if the title reliably identifies an indoor/virtual activity."""
+    return bool(_INDOOR_TITLE_RE.search(title))
+
 
 def make_activity_id(activity: ParsedActivity) -> str:
     """Generate a BAS activity ID from started_at + optional title slug.
@@ -278,14 +290,11 @@ def write_athlete_json(summaries: list[dict], output_dir: Path, athlete_config:
         return [[d, w] for d, w in sorted(best.items())]
 
     _INDOOR_SUB_SPORTS = {"indoor", "treadmill", "virtual"}
-    _INDOOR_TITLE_RE = re.compile(r'\bzwift\b', re.IGNORECASE)
 
     def _is_outdoor(s: dict) -> bool:
         if s.get("sub_sport") in _INDOOR_SUB_SPORTS:
             return False
-        if _INDOOR_TITLE_RE.search(s.get("title") or ""):
-            return False
-        return True
+        return not _infer_indoor_title(s.get("title") or "")
 
     all_mmps = [s["mmp"] for s in summaries if s.get("mmp") and _is_outdoor(s)]
     mmps_365 = [s["mmp"] for s in summaries if s.get("mmp") and _is_outdoor(s) and s["started_at"] >= cutoff_365]