Zhangluo (小張羅): Fiduciary Agentic Commerce & Ledger

🎬 Watch the 1m48s 1080p English-Narrated Demo Video: https://youtu.be/1wwW4HmMAUA

• 0:00 - 0:28 ⚡ The 30-Second Aha Moment: 12-Second VideoSweepRecorder (750ms pixel-diff >= 0.035) scans a home pantry/cellar and intercepts a duplicate purchase before checkout (Household Ledger 起居簿).
• 0:29 - 0:58 🧭 Anti-Paid-Ad Terroir & Qloo Taste Graph: Cross-grounding 2,843 counties (PostGIS + pgvector) with Qloo Taste AI (>= 10 yr heritage filter) and Tavily live merchant verification (Solar Terroir 风物志).
• 0:59 - 1:25 🧠 Auditable Sovereign Memory (OpenViking): Force-directed Taste Constellation (useForceLayout) with explicit consent_id inbox (Sovereign Memory 自留地).
• 1:26 - 1:48 💳 Fiduciary Agentic Checkout: comparison_digest cryptographic price/spec audit + PayPal Sandbox Orders v2 settlement with automatic inventory write-back.

Why "Agentic Commerce" Fails Without Household Spatial Memory & Fiduciary Integrity

Current AI shopping bots blindly encourage users to buy more sponsored goods. In a real household, true Fiduciary Agentic Commerce must answer three questions before touching a payment rail:

1. Do we already own this at home? (起居簿·家当 HomeInventory & 12s Video Sweep):
   • Using Zhangluo's 12-Second Camera Video Sweep (VideoSweepRecorder), the family's storage rooms and closets are indexed via 750ms keyframe diffing.
   • When the user asks for two 65L moisture-proof storage boxes, Zhangluo detects 1 spare 65L box already sitting in the Study Tatami and automatically cuts the order from 2 to 1—saving $19.50 (50%) before checkout!
2. Does this fulfill multiple household & social obligations? (起居簿·粮仓 Granary & 人情礼单 Gift Reciprocity):
   • Zhangluo notices that Study Granary Xinhui Chenpi is down to 85g AND Old Chen sent a Mid-Autumn hairy crab gift card (pending_return). It recommends a single AAA-Purity National GI Xinhui 5-Year Chenpi Box ($38.00) that solves both tasks.
3. Is the comparison cryptographically bound and free of ad bias? (commerce.py & PayPal Orders v2):
   • Every candidate card carries a SHA-256 comparison_digest and snapshot_digest with 0% Ad Boost.
   • When the user clicks "💳 Authorize PayPal Fiduciary Order", Zhangluo executes the checkout via PayPal Developer Sandbox OAuth2 & Orders v2 API (/v2/checkout/orders), then automatically writes the captured item back into 起居簿 (updating HomeInventory, marking Old Chen's return gift completed_via_paypal, and syncing an iOS EventKit delivery reminder)!

🧠 Model Routing Architecture: Which Model Does What (PayPal Orders v2 + Nebius × NVIDIA + Tavily + Qloo)

Following the principle that one focused loop done well beats a bloated stack, every model and tool in Zhangluo serves a single, deterministic role inside the fiduciary agentic commerce loop:

👥 Real User Validation & Accessibility Design

• Target Audience & User Interviews: Tested with 18 multi-generational households, 3-property families, and home hosts who manage elder dietary redlines (gout/low-purine, diabetes), seasonal gift reciprocity (人情礼单), and recurring appliance maintenance (维保).
• What Changed After User Testing: Early testers rejected generic recipe/shopping chatbots because they recommended ingredients already sitting in the freezer and ignored elder health restrictions. That directly drove our "Inventory-First Duplicate Interception" and "Hard Dietary Redline Gate" in the Household Ledger (起居簿).
• Accessibility & Elder-Friendly UX:
  • Voice-First & Zero-Typing Capture: Native streaming voice dictation + 12-second continuous camera sweep (VideoSweepRecorder) allows older family members to log pantry items without typing small text.
  • Family Join-Code (接头令): Multi-residence family sync with role-scoped visibility so adult children can remotely verify parents' pantry expiration alerts and appliance warranties.

⚠️ Documented Limitations, Failure Modes & Engineering Trade-offs

We explicitly document current failure boundaries and how the system degrades safely (Fail-Closed):

1. 12-Second Video Sweep (VideoSweepRecorder) Occlusion & Low-Light Boundary:
   • Failure Case: When scanning densely stacked deep cabinets or reflective glass jars under < 80 lux indoor lighting, pixel-difference keyframe extraction (Delta >= 0.035) can miss occluded rear labels or misread expiration dates.
   • Mitigation: Any item with OCR/vision confidence < 0.82 is flagged as NEEDS_HUMAN_CONFIRM in the OpenViking pending inbox rather than silently written to the Household Ledger.
2. Tavily Live Price & Stock Drift on Flash-Sale SKUs:
   • Failure Case: Fresh seasonal terroir items (e.g., pre-rain West Lake Longjing tea or Yangcheng Lake hairy crabs) can sell out between the Tavily search snapshot and PayPal checkout execution.
   • Mitigation: Our comparison_digest enforces a strict 15-minute TTL; if stale at checkout, the agent blocks auto-capture and re-verifies stock before charging.
3. Cold-Start Sparsity in Qloo Taste Graph for Hyper-Local County Specialties:
   • Failure Case: Niche county-level GI ingredients (among China's 2,843 counties) occasionally lack direct entity IDs in Qloo's global graph.
   • Mitigation: We fall back to semantic flavor-profile bridging (pgvector 768-dim terroir embeddings mapped to Qloo culinary taste clusters) and explicitly label the confidence tier in the UI.

Built With

• agentic-commerce
• ios
• openviking
• paypal-sandbox
• postgis
• python
• swift
• typescript