Diana Personal MCP Shopper — Architecture Spec (retry 1)

Design the foundational architecture for Diana as a Personal MCP Shopper. This is the skeleton ALL 12 consumer skills inherit from. DELIVERABLES: 1. DianaSkill base interface — the universal pattern every skill implements: - intent parsing (what the consumer wants) - personal context ingestion (from connected MCPs) - C8 intelligence pipeline (classify→comply→calculate→filter→rank) - personalized result output 2. PersonalContext schema — unified schema for consuming data from 6 personal MCPs: - Health MCP: allergies, conditions, dietary needs, medications, fitness data - Finance MCP: budget, spending patterns, currency, tax status - Home MCP: inventory, consumption rates, warranties, household size - Sustainability MCP: carbon budget, ethical sourcing prefs, certifications - Location MCP: address, import regulations, local tax rates, delivery zones - Social MCP: gift recipients, occasions, shared wishlists 3. PersonalizedResult schema — what every skill returns: - product/option recommendations with TRUE landed cost (not sticker price) - compliance status for user's country - supply chain provenance (origin, factory, trade agreement) - personal fit score (how well it matches THIS user's constraints) - action options (buy now, track price, set auto-order, compare more) 4. Domain Config pattern — how new domains register without changing core: - classify_mapping: what taxonomy this domain uses - comply_rules: what regulations apply - orchestrate_targets: where results flow - personal_context_schema: which MCPs are relevant 5. MCP tool registration pattern — how each skill exposes as an MCP tool that Claude/agents can call CONTEXT: - Diana already has: diana_shop, diana_dream_sketch, diana_search, diana_checkout (existing tools) - Rosetta already has: classify_hts, calculate_duty, determine_pga_requirements, validate_fda_label - 10.5M product archetypes with NVIDIA embeddings in product_digital_twins - Scout nearest archetype search working - The goal is to COMPOSE existing C8 tools into consumer-facing skill interfaces, not rebuild EXISTING C8 TOOL SIGNATURES TO INTEGRATE: - classify_hts(product_description, material?, country_of_origin?) - calculate_duty(hts_code, declared_value, country_of_origin, destination_state?) - determine_pga_requirements(product_description, hts_code?, intended_use?) - scout_nearest_archetype(product_description, k?) - diana_shop(query, persona?, limit?) - diana_checkout(items, persona?) Output as a complete Python module with dataclasses/Pydantic models, abstract base class, and one concrete example skill (diana_landed_cost_compare) to prove the pattern works.