feat: implement SmartWardrobe with BodyAnchors, PilotEngine, save_silhouette, and get_mix_and_match

[Copilot]

Introduces the SmartWardrobe class (Pilot points 3 & 4) along with supporting types BodyAnchors and PilotEngine, none of which existed in the codebase.

New: api/smart_wardrobe.py

• BodyAnchors — dataclass capturing shoulder_w / torso_h from the digital mirror scan
• PilotEngine — owns PILOT_COLLECTION (eg0–eg4), each entry carrying recoveryPct and a garment_id mapped to existing inventory records
• SmartWardrobe — core wardrobe class:
  • save_silhouette(anchors) stores shoulderW, torsoH, and a Unix timestamp into self.saved_silhouette
  • get_mix_and_match(engine, current_look_id) returns up to 4 alternative look IDs from engine.PILOT_COLLECTION, excluding the current selection

engine = PilotEngine()
wardrobe = SmartWardrobe("user_123")

anchors = BodyAnchors(shoulder_w=44.0, torso_h=60.0)
wardrobe.save_silhouette(anchors)
# → "Silueta protegida bajo cifrado local."
# wardrobe.saved_silhouette == {"shoulderW": 44.0, "torsoH": 60.0, "timestamp": ...}

wardrobe.get_mix_and_match(engine, "eg0")
# → ["eg1", "eg2", "eg3", "eg4"]

New: tests/test_smart_wardrobe.py

14 unit tests covering initialization state, silhouette persistence (including overwrite), timestamp bounds, suggestion exclusion, and PILOT_COLLECTION schema invariants.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
tryonyou-pilot	Error		Apr 7, 2026 1:43pm