ChowBox/CLAUDE.md

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project: ChowBox (吃啥盲盒)

WeChat Mini Program for solving "what to eat" decisions. Three modes:

• Takeout Box (外卖盲盒): Random nearby quality delivery recommendation, jump to Meituan/Ele.me to order.
• Fridge Box (冰箱盲盒): Input ingredients, get recipe matches ranked by match %, highlight missing items.
• Explore Box (探店盲盒): Random nearby dine-in restaurant discovery, navigate via map apps.

Status: Pre-development planning. Zero code written. Docs in doc/ are the source of truth.

Tech Stack

• Frontend: Native WeChat Mini Program (WXML + WXSS + JavaScript), WeChat Developer Tools
• Backend: Java 8 + Spring Boot 2.x (classic MVC)
• Database: MySQL 5.7+ (primary) + Redis (cache)
• External APIs: Amap Web API (POI search, primary), Tencent Location Service (backup), WeChat Open APIs (navigation, subscribe messages)

Design Tokens

• Primary: #FF6A3D (orange), Background: #FFFBF4 (warm white), Text: #333, Accent: #4CAF50
• Card border-radius: 16px, Button border-radius: 24px
• Font: WeChat default Chinese font, bold titles at 16-20px

Architecture

• Bottom tab navigation: Home (盲盒大厅), Records (记录), My (我的)
• Data flow: user location → backend → map POI API (cached by geo-grid + time) → filtering/weighting → weighted random selection → result
• POI cache: 1h client-side, 6h server-side for hot zones
• Box opening animation: 1.8-2.2s, 3-act (shake → lid open with glow → card reveal), Lottie + CSS keyframes, degrade to CSS-only on low-end devices (see doc/box.md)

Key Docs

• doc/plan.md — Full product plan v1.0 (features, architecture, roadmap, budget)
• doc/box.md — Opening animation storyboard and dev parameters
• doc/ui.md — ASCII wireframes for all 6 core pages

Roadmap

• Phase 1 (MVP, 4-6 weeks): Scaffold mini program + Spring Boot backend, MySQL schema, Amap POI integration for takeout box, 100 recipes, basic box animation
• Phase 2 (3-4 weeks): Explore box, voice ingredient input, user feedback weighting, 500+ recipes
• Phase 3 (2-3 weeks): User preferences, share cards, subscribe messages, perf optimization
• Phase 4: Testing, WeChat review submission, iteration

No build/lint/test commands exist yet.

---

Behavioral Guidelines

Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:

• State your assumptions explicitly. If uncertain, ask.
• If multiple interpretations exist, present them - don't pick silently.
• If a simpler approach exists, say so. Push back when warranted.
• If something is unclear, stop. Name what's confusing. Ask.

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

• No features beyond what was asked.
• No abstractions for single-use code.
• No "flexibility" or "configurability" that wasn't requested.
• No error handling for impossible scenarios.
• If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

• Don't "improve" adjacent code, comments, or formatting.
• Don't refactor things that aren't broken.
• Match existing style, even if you'd do it differently.
• If you notice unrelated dead code, mention it - don't delete it.

When your changes create orphans:

• Remove imports/variables/functions that YOUR changes made unused.
• Don't remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

• "Add validation" → "Write tests for invalid inputs, then make them pass"
• "Fix the bug" → "Write a test that reproduces it, then make it pass"
• "Refactor X" → "Ensure tests pass before and after"

For multi-step tasks, state a brief plan:

1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]

Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.

---

These guidelines are working if: fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.