diff --git a/.claude/settings.local.json b/.claude/settings.local.json
deleted file mode 100644
index a1022be..0000000
--- a/.claude/settings.local.json
+++ /dev/null
@@ -1,16 +0,0 @@
-{
-  "permissions": {
-    "allow": [
-      "Bash(cat PRD.md)",
-      "Bash(cat API.md)",
-      "Bash(cat AGENTS.md)",
-      "Bash(cat DB_GUIDE.md)",
-      "Bash(cat .env)",
-      "Bash(cat:*)",
-      "Bash(rm CLAUDE.md)"
-    ],
-    "deny": [],
-    "ask": [],
-"defaultMode":"bypassPermissions"
-  }
-}
diff --git a/.gitignore b/.gitignore
index b89d941..989ae92 100644
--- a/.gitignore
+++ b/.gitignore
@@ -7,4 +7,7 @@ __pycache__/
 *.log
 .DS_Store
 Thumbs.db
-.env.*
\ No newline at end of file
+.env.*
+.claude/
+AGENTS.md
+CLAUDE.md
\ No newline at end of file
diff --git a/AGENTS.md b/AGENTS.md
deleted file mode 100644
index deb88e5..0000000
--- a/AGENTS.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# Repository Guidelines
-## 必须使用中文回复我
-## Project Structure & Module Organization
-`app.py` boots the Flask service and loads blueprints from `lawrisk/`, whose subpackages mirror the request flow: `api/` (v1/v2 routes), `services/` (retrieval logic, PostgreSQL access, DashScope orchestration), `middleware/`, and `utils/` for ingestion/export helpers. Static assets for manual QA live in `static/`, while `data/` stores exported JSON/SQL snapshots used by the ingestion scripts. Formal specs, API references, and prior agent notes are in `docs/`. Python tests (pytest) belong under `tests/`; favor mirroring the module paths (e.g., `tests/api/test_v2.py`).
-
-## Build, Test, and Development Commands
-Install dependencies with `pip install -r requirements.txt` from a Python 3.11+ shell. Launch the server via `python app.py`, which binds to `http://localhost:8000` and exposes `/healthz`. Run the lightweight regression suite with `pytest`. Format and lint before submitting using `black .` and `ruff .`; both read `pyproject.toml` defaults so no extra flags are needed. For manual API smoke tests, open `static/v2_tester.html` in a browser or send `curl` requests as shown in `README.md`.
-
-## Coding Style & Naming Conventions
-Use Black’s default 88-column formatting and Ruff-compatible imports; never hand-wrap lines differently. Modules, packages, and files are lowercase with underscores (`lawrisk_service.py`). Public functions favor descriptive verbs (`fetch_risk_snapshot`). Prefer dataclass-like dicts for payloads, and keep API responses snake_case to match existing endpoints. Add concise docstrings for service-layer functions that hit external systems. Configuration should be read through `lawrisk.utils.env_loader` rather than `os.environ` directly.
-
-## Testing Guidelines
-Pytest is the standard; each new feature should include a focused unit test plus, when feasible, a service-level test hitting the Flask test client. Name tests after the behavior under check (`test_query_returns_ranked_risks`). Use fixtures for sample licenses/risk tables to keep tests deterministic. Aim to cover error paths (missing env vars, DashScope failures) because they are the common regressions. Run `pytest -q` locally before opening a PR, and attach logs when failures are environment-specific.
-
-## Commit & Pull Request Guidelines
-Follow the existing Conventional Commit style (`feat: …`, `fix: …`, `chore: …`). Limit commits to one logical change and reference the affected domain in the subject when possible (e.g., `feat: enhance v2 risk scoring`). PRs should describe intent, summarize testing (`pytest`, manual curl, etc.), and link to any tracking issue or checklist. Include screenshots or JSON snippets when adjusting responses so reviewers can verify payload diffs quickly.
diff --git a/CLAUDE.md b/CLAUDE.md
deleted file mode 100644
index f8766d1..0000000
--- a/CLAUDE.md
+++ /dev/null
@@ -1,681 +0,0 @@
-
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
-
----
-
-# LawRisk Backend - Claude Code Analysis
-
-## Project Overview
-
-**LawRisk** is a Flask-based Python backend service that provides intelligent legal compliance risk retrieval for business licensing and permit requirements. It uses vector embeddings and LLM-based matching to help users find relevant permits, licenses, and associated legal risks based on natural language queries (in Chinese).
-
-**Python Version Requirement**: Python 3.10+ (uses PEP 604 union types like `str | None`)
-
-### Key Features
-- **Semantic Search**: Uses Aliyun DashScope embeddings (text-embedding-v4) to find similar legal topics
-- **LLM-Powered Matching**: Qwen (qwen-plus-latest) for intelligent subject selection
-- **Two Database Architecture**: 
-  - `fs_law_risk`: Vector embeddings and subject-permit mappings
-  - `licensing_risks`: Structured permit and risk data with regions, themes, and compliance information
-- **RESTful APIs**: Clean REST endpoints for V1 (legacy) and V2 (enhanced) search
-- **CORS Enabled**: Built-in CORS middleware for frontend integration
-
----
-
-## Architecture & Project Structure
-
-### Core Framework & Libraries
-- **Framework**: Flask (Python web framework)
-- **Database Driver**: pg8000 (PostgreSQL adapter)
-- **Vector Embeddings**: Aliyun DashScope OpenAI-compatible API
-- **LLM**: Qwen via DashScope (qwen-plus-latest)
-- **Dependencies**: Minimal footprint - Flask, pg8000, concurrent.futures
-
-### Directory Structure
-```
-市监局-lawRisk-backend/
-├── app.py                          # Flask application entry point
-├── requirements.txt                # Python dependencies
-├── .env                            # Environment configuration
-├── lawrisk/                        # Main application package
-│   ├── __init__.py
-│   ├── api/                        # API route handlers
-│   │   ├── v1.py                   # V1 API (legacy)
-│   │   └── v2.py                   # V2 API (current)
-│   ├── services/                   # Business logic layer
-│   │   ├── lawrisk_service.py      # Core search & embeddings
-│   │   ├── lawrisk_v2_service.py   # V2 enhanced service
-│   │   └── licensing_repo.py       # Data repository
-│   ├── middleware/                 # HTTP middleware
-│   │   └── smart_cors_middleware.py
-│   └── utils/                      # Utility functions
-│       ├── env_loader.py
-│       ├── export_risk_json.py
-│       └── ingest_lawrisk.py
-├── static/                         # Static assets
-│   └── v2_tester.html              # Web-based API tester
-├── tests/                          # Test suite (planned)
-├── data/                           # Data files
-│   ├── risk_tables_export.json
-│   └── licensing_risks_dump.sql
-└── docs/                           # Documentation
-    ├── PRD.md
-    ├── API.md
-    ├── V2_API文档.md
-    ├── AGENTS.md
-    ├── DB_GUIDE.md
-    └── CLAUDE.md
-```
-
----
-
-## Quick Reference
-
-### Most Common Commands
-```bash
-# Run the application
-python app.py
-
-# Export data from database
-python export_risk_json.py
-
-# Ingest data with embeddings (requires DASHSCOPE_API_KEY)
-python ingest_lawrisk.py
-
-# Format and lint code
-black .
-ruff .
-
-# Test locally via browser
-# Open static/v2_tester.html after starting the app
-```
-
-### Key Files
-- `app.py` - Flask application entry point
-- `lawrisk/` - Main application package
-  - `api/v1.py` - V1 API routes (legacy)
-  - `api/v2.py` - V2 API routes (current)
-  - `services/lawrisk_service.py` - Core search & embeddings
-  - `services/lawrisk_v2_service.py` - V2 enhanced service
-  - `services/licensing_repo.py` - Data repository
-  - `middleware/smart_cors_middleware.py` - CORS middleware
-  - `utils/` - Utility functions
-- `static/v2_tester.html` - Web-based API testing interface
-- `requirements.txt` - Python dependencies
-- `.env` - Environment configuration
-
----
-
-## Development Workflow
-
-### Initial Setup
-```bash
-# 1. Create virtual environment (Windows PowerShell)
-python -m venv .venv
-.venv\Scripts\activate
-
-# 2. Install dependencies
-pip install Flask pg8000 black ruff pytest
-
-# 3. Configure environment
-# Edit .env with your database credentials and DashScope API key
-```
-
-### Virtual Environment Activation
-```powershell
-# Windows PowerShell
-.venv\Scripts\activate
-
-# Windows CMD
-.venv\Scripts\activate.bat
-
-# Git Bash (Windows)
-source .venv/Scripts/activate
-```
-
-### Common Commands
-
-#### Run the Application
-```bash
-# Development mode
-python app.py
-
-# Custom port
-PORT=8000 python app.py
-
-# With debug logging
-FLASK_DEBUG=1 python app.py
-```
-
-#### Data Management
-```bash
-# Export data from fs_law_risk database to JSON
-python export_risk_json.py
-
-# Ingest data with embeddings into database
-python ingest_lawrisk.py
-# Requires DASHSCOPE_API_KEY in .env
-```
-
-#### Code Quality
-```bash
-# Format code with Black (100 char line length)
-black .
-
-# Lint with Ruff
-ruff .
-
-# Format and lint specific file
-black lawrisk/services/lawrisk_v2_service.py
-ruff lawrisk/services/lawrisk_v2_service.py
-
-# Run tests (when added)
-pytest -q
-
-# Run tests with coverage
-pytest --cov=lawrisk
-```
-
-### Data Management Commands
-```bash
-# Export data from fs_law_risk database to JSON
-# Output: data/risk_tables_export.json
-python lawrisk/utils/export_risk_json.py
-
-# Ingest data with embeddings into database
-# Requires DASHSCOPE_API_KEY in .env
-python lawrisk/utils/ingest_lawrisk.py
-
-# Verify exported data
-ls -lh data/
-cat data/risk_tables_export.json | head -50
-```
-
-#### Database Operations
-```bash
-# Connect to PostgreSQL
-psql -h 8.138.196.105 -U postgres -d fs_law_risk
-
-# Connect to licensing_risks database
-psql -h 8.138.196.105 -U postgres -d licensing_risks
-```
-
----
-
-## API Endpoints
-
-### V1 API (Legacy)
-- **Path**: `/fs-ai-asistant/api/workflow/lawrisk`
-- **Methods**: GET, POST
-- **Mode**: `llm` (default) or `embed`
-- **Input**: `query` (user question)
-- **Output**: Simple array of matching subjects with permit IDs
-
-### V2 API (Current/Recommended)
-- **Base Path**: `/fs-ai-asistant/api/workflow/lawrisk/v2`
-- **Methods**: GET, POST
-- **Features**:
-  - Structured results with regions, themes, permits, and risks
-  - Optional region filtering
-  - Debug mode with detailed execution info
-  - Direct permit matching by name
-
-#### V2 Sub-endpoints
-
-1. **Search Endpoint**
-   - Path: `/fs-ai-asistant/api/workflow/lawrisk/v2`
-   - Parameters:
-     - `query` (required): User question
-     - `region` (optional): Filter by region (市级, 禅城区, etc.)
-     - `debug` (optional): Enable debug output (1/true/yes/on)
-     - `top` (optional): Number of recommendations (default: 5)
-
-2. **Regions List**
-   - Path: `/fs-ai-asistant/api/workflow/lawrisk/v2/regions`
-   - Method: GET
-   - Returns: All available regions for filtering
-
-3. **Get Permits**
-   - Path: `/fs-ai-asistant/api/workflow/lawrisk/getPermits`
-   - Method: GET, POST
-   - Input: `region` (region ID or name)
-   - Returns: All permits for a specific region
-
-### Health Check
-- Path: `/healthz`
-- Method: GET
-- Returns: `{"status": "ok"}`
-
----
-
-## Database Schema
-
-### Database 1: fs_law_risk
-Used for vector embeddings and semantic search.
-
-#### Tables
-- **`law_sub`**: Subject matter with embeddings
-  - `id` (TEXT, PK): Subject ID
-  - `name` (TEXT): Subject name
-  - `vector` (JSONB): Embedding vector
-
-- **`law_sub_per`**: Subject-permit mappings
-  - `sub_id` (TEXT, PK): Subject ID
-  - `per_ids` (JSONB): Array of permit IDs
-
-- **`law_per`**: Permit information
-  - `id` (TEXT, PK): Permit ID
-  - `name` (TEXT): Permit name
-  - `risk_ids` (JSONB): Array of risk IDs
-
-### Database 2: licensing_risks
-Used for structured compliance data.
-
-#### Tables
-- **`regions`**: Administrative areas
-  - `id` (PK), `name` (unique)
-
-- **`business_scopes`**: Business scope definitions
-  - `id` (PK), `description`
-
-- **`region_scopes`**: Region-scope mappings
-
-- **`themes`**: Legal themes/subjects
-  - `id` (PK), `name`
-
-- **`region_themes`**: Region-theme mappings
-
-- **`permits`**: License/permit items
-  - `id` (PK), `name`
-
-- **`region_theme_permits`**: Tripartite linkage
-
-- **`risks`**: Risk information
-  - `id` (PK), `risk_content`, `legal_basis`, `document_no`, `summary`
-
-- **`region_permit_risks`**: Risk associations
-
----
-
-## Configuration
-
-### Environment Variables (.env)
-
-#### DashScope (Embeddings & LLM)
-```
-DASHSCOPE_API_KEY=sk-288824ef003e4e02bb963b8b3024b06a
-DASHSCOPE_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
-DASHSCOPE_EMBED_MODEL=text-embedding-v4
-DASHSCOPE_EMBED_DIM=1024
-DASHSCOPE_MAX_BATCH=10
-DASHSCOPE_CHAT_MODEL=qwen-plus-latest
-```
-
-#### PostgreSQL Configuration
-```
-# fs_law_risk database
-PG_HOST=8.138.196.105
-PG_PORT=5432
-PG_USER=postgres
-PG_PASSWORD=difyai123456
-PG_DATABASE=fs_law_risk
-PG_ADMIN_DB=postgres
-
-# licensing_risks database
-LIC_PG_HOST=8.138.196.105
-LIC_PG_PORT=5432
-LIC_PG_USER=postgres
-LIC_PG_PASSWORD=difyai123456
-LIC_PG_DATABASE=licensing_risks
-```
-
-#### Application Settings
-```
-FLASK_ENV=development
-
-# Search thresholds (tunable)
-LAWRISK_RETURN_IF_GE=0.7
-LAWRISK_FALLBACK_GT=0.5
-```
-
----
-
-## Testing
-
-### Current Testing Status
-- **No dedicated test suite** in the repository
-- pytest framework is recommended but not configured
-- Manual testing available via `static/v2_tester.html`
-
-### Testing Framework & Guidelines
-When adding tests, use:
-- **Framework**: pytest with Flask test client
-- **Dependencies**: pytest-cov for coverage reporting
-- **Focus Areas**:
-  - API endpoints (V1 and V2)
-  - Middleware behavior (CORS)
-  - Database operations
-  - LLM selection logic
-  - Region filtering
-  - Checkpoint operations (create, list, restore, delete)
-
-**Recommended test structure:**
-```
-tests/
-├── conftest.py                  # Shared fixtures and test configuration
-├── test_api_v1.py               # V1 API endpoint tests
-├── test_api_v2.py               # V2 API endpoint tests
-├── test_admin_endpoints.py      # Admin endpoint tests
-├── test_search_service.py       # Core search logic
-├── test_licensing_repo.py       # Database repository
-└── test_cors_middleware.py      # CORS middleware behavior
-
-# Test naming: test_*.py (pytest discovery pattern)
-# Test functions: test_<feature>_<scenario>()
-```
-
-**Testing CORS Middleware** (from AGENTS.md):
-- Origin matching: wildcard, exact, subdomains
-- Preflight OPTIONS handling
-- X-CORS-Decision header behavior
-- NGINX_CORS_MODE functionality
-- Environment variable configurations (ALLOWED_ORIGINS, CORS_STRICT, etc.)
-
-**Example test case:**
-```python
-def test_v2_search_with_debug():
-    client = app.test_client()
-    response = client.post('/fs-ai-asistant/api/workflow/lawrisk/v2',
-                          data={'query': '电影院', 'debug': '1'})
-    assert response.status_code == 200
-    data = response.get_json()['data']
-    assert 'debug' in data
-    assert 'executionTime' in data
-```
-
-### Testing Commands
-```bash
-# Run all tests
-pytest
-
-# Run with coverage
-pytest --cov=lawrisk_service
-
-# Run specific test file
-pytest tests/test_api_v2.py -v
-```
-
-### Manual Testing with V2 Tester
-1. Start the application: `python app.py` (defaults to port 8000)
-2. Open `static/v2_tester.html` in your browser
-3. Test queries like:
-   - "我要办一家电影院"
-   - "开办旅馆需要哪些许可"
-   - "公共场所卫生许可"
-   - Query with region filter: "电影院&region=市级&debug=1"
-
-The tester provides a simple UI to experiment with the V2 API and view debug information.
-
----
-
-## Coding Standards & Best Practices
-
-### Python Style Guidelines
-- **Indentation**: 4 spaces (no tabs)
-- **Encoding**: UTF-8 for all source files
-- **Naming Conventions**:
-  - Functions/variables: `snake_case`
-  - Constants: `SCREAMING_SNAKE_CASE`
-  - Classes: `PascalCase`
-- **Type Hints**: Prefer type hints for all public functions
-- **Code Formatting**: Use `black` with 100-character line length
-- **Linting**: Use `ruff` with default rules
-
-### Code Quality Guidelines
-- Keep functions small and side-effect free
-- Prefer pure functions where possible
-- Document complex logic with comments
-- Use type hints from `typing` module
-- Handle errors gracefully with appropriate logging
-
-### Documentation Files
-- **PRD.md** (docs/PRD.md) - Product Requirements Document
-  - Business logic and requirements specification
-  - Feature specifications and user stories
-
-- **API.md** (docs/API.md) - V1 API documentation
-  - Legacy API endpoints and usage
-  - Request/response formats
-
-- **V2_API文档.md** (docs/V2_API文档.md) - Detailed V2 API documentation
-  - Enhanced API specification
-  - Admin endpoints and checkpoint operations
-  - Request/response examples
-
-- **AGENTS.md** (docs/AGENTS.md) - Development guidelines
-  - Repository structure and module organization
-  - Coding style and naming conventions
-  - Commit and PR guidelines
-  - Security and configuration tips
-
-- **DB_GUIDE.md** (docs/DB_GUIDE.md) - Database reference
-  - Schema reference for both databases
-  - Query examples and optimization tips
-
-- **README.md** (README.md) - Project overview and quick start
-
----
-
-## Key Components Deep Dive
-
-### 1. app.py - Application Entry Point (C:\Users\WIN10\Desktop\work\11th-week\法律风险提示-new\市监局-lawRisk-backend\app.py)
-- Creates Flask app with CORS enabled
-- Registers all API routes (v1_bp, v2_bp)
-- Database initialization and schema checks on startup
-- Health check endpoint at `/healthz`
-- Logs all registered routes on startup
-- Error handling doesn't block app startup (errors surface on first request)
-
-### 2. lawrisk_service.py - Core Search Logic (C:\Users\WIN10\Desktop\work\11th-week\法律风险提示-new\市监局-lawRisk-backend\lawrisk\services\lawrisk_service.py)
-- **EmbeddingClient**: DashScope API integration for vector embeddings
-- **ChatClient**: Qwen LLM interaction for intelligent subject selection
-- Database helpers using pg8000 for PostgreSQL
-- Search algorithms:
-  - Embedding-based cosine similarity search
-  - LLM-based subject matching using `qwen-plus-latest`
-- Similarity threshold management (tunable via LAWRISK_RETURN_IF_GE, LAWRISK_FALLBACK_GT)
-- Concurrent execution support with ThreadPoolExecutor
-
-### 3. lawrisk_v2_service.py - Enhanced API (C:\Users\WIN10\Desktop\work\11th-week\法律风险提示-new\市监局-lawRisk-backend\lawrisk\services\lawrisk_v2_service.py)
-- Structured response formatting with regions, themes, permits, and risks
-- Region filtering logic with normalization
-- Direct permit matching by name
-- Markdown formatting for legal text
-- Complex query execution pipeline
-- Helper functions:
-  - `_compose_prompt()`: Builds natural-language prompts from structured data
-  - `_normalize_region_filter()`: Normalizes region filters for matching
-
-### 4. licensing_repo.py - Data Repository (C:\Users\WIN10\Desktop\work\11th-week\法律风险提示-new\市监局-lawRisk-backend\lawrisk\services\licensing_repo.py)
-- Separate database connection for `licensing_risks` database
-- Multi-table join query optimization
-- Legal text formatting helpers
-- Chinese legal document pattern matching
-- Checkpoint management:
-  - `create_checkpoint()`: Database backup functionality
-  - `list_checkpoints()`: List available backups
-  - `restore_checkpoint()`: Restore from checkpoint (DANGEROUS!)
-  - `delete_checkpoint()`: Remove old checkpoints
-
-### 5. smart_cors_middleware.py - Reusable CORS (C:\Users\WIN10\Desktop\work\11th-week\法律风险提示-new\市监局-lawRisk-backend\lawrisk\middleware\smart_cors_middleware.py)
-- Wildcard and exact origin matching
-- Subdomain support with flexible patterns
-- Preflight OPTIONS handling
-- NGINX integration mode (NGINX_CORS_MODE)
-- Debug and logging features (CORS_DEBUG)
-- Environment variable support:
-  - ALLOWED_ORIGINS, CORS_STRICT, CORS_DEBUG
-  - NGINX_CORS_MODE, CORS_MAX_AGE, CORS_EXPOSE_HEADERS
-
-### 6. v2.py API Routes (C:\Users\WIN10\Desktop\work\11th-week\法律风险提示-new\市监局-lawRisk-backend\lawrisk\api\v2.py)
-- **Public endpoints**: `/v2`, `/v2/regions`, `/getPermits`
-- **Admin endpoints**: `/admin/test`, `/admin/regions`, `/admin/themes`, `/admin/permits`, `/admin/checkpoints`
-- Parameter extraction supporting GET, POST, JSON, and form data
-- Concurrent execution using ThreadPoolExecutor (max_workers=2)
-- Structured error responses with consistent format
-
-### 7. Utility Scripts
-- **env_loader.py**: Environment variable loading from .env file
-- **export_risk_json.py**: PostgreSQL data export utility (outputs to data/risk_tables_export.json)
-- **ingest_lawrisk.py**: Data ingestion with embeddings (requires DASHSCOPE_API_KEY)
-
----
-
-## Security & Best Practices
-
-### Security Guidelines
-- **NEVER hardcode secrets** in source code
-- All credentials must be in `.env` file or environment variables
-- API keys (DASHSCOPE_API_KEY) and database passwords must be externalized
-- Admin endpoints (`/admin/*`) should be protected in production
-- Database checkpoint restore is a **DANGEROUS OPERATION** and should be restricted
-
-### Configuration Best Practices
-- Use `.env` file for all configuration (database, API keys, thresholds)
-- Environment variables supported by CORS middleware:
-  - ALLOWED_ORIGINS: Comma-separated list of allowed origins
-  - CORS_STRICT: Enable strict origin checking
-  - CORS_DEBUG: Enable debug logging
-  - NGINX_CORS_MODE: Enable NGINX integration
-  - CORS_MAX_AGE: Preflight cache duration
-  - CORS_EXPOSE_HEADERS: Headers to expose to browsers
-- Regularly backup databases using checkpoint system
-- Monitor DashScope API quota and rate limits
-
-## Troubleshooting Guide
-
-### Common Issues
-
-#### Database Connection Errors
-**Symptom**: `pg8000.dbapi.Error` when starting the app
-**Solutions**:
-- Check `.env` file exists with correct PostgreSQL credentials
-- Verify network connectivity to the database server
-- Ensure PostgreSQL server is running and accessible
-- Check database names: `fs_law_risk` and `licensing_risks`
-- Verify PG_HOST, PG_PORT, PG_USER, PG_PASSWORD are correct
-
-#### Missing Environment Variables
-**Symptom**: Key errors, default values being used, or API failures
-**Solutions**:
-- Create `.env` file from the template (see Configuration section)
-- Ensure `DASHSCOPE_API_KEY` is set for embedding/chat features
-- Verify all required PG_* and LIC_* environment variables
-- Check that pg8000 is installed: `pip install pg8000>=1.30.0`
-
-#### LLM/Embedding API Errors
-**Symptom**: API authentication failures, timeout errors, or embedding errors
-**Solutions**:
-- Verify `DASHSCOPE_API_KEY` is valid and has sufficient quota
-- Check `DASHSCOPE_BASE_URL` matches: `https://dashscope.aliyuncs.com/compatible-mode/v1`
-- Ensure network access to DashScope API servers
-- Review API rate limits and batch sizes (DASHSCOPE_MAX_BATCH)
-- Test API key: curl -H "Authorization: Bearer $DASHSCOPE_API_KEY" "$DASHSCOPE_BASE_URL/models"
-
-#### Empty Search Results
-**Symptom**: API returns empty `risk_subject` array
-**Solutions**:
-- Check if database tables are populated:
-  ```sql
-  SELECT COUNT(*) FROM fs_law_risk.law_sub;
-  SELECT COUNT(*) FROM fs_law_risk.law_sub_per;
-  ```
-- Try `debug=1` parameter to see detailed execution info
-- Verify similarity thresholds in `.env`:
-  - `LAWRISK_RETURN_IF_GE=0.7` (return if similarity >= 0.7)
-  - `LAWRISK_FALLBACK_GT=0.5` (fallback if similarity > 0.5)
-- Test with known queries like "我要办一家电影院" or "开办旅馆"
-- Check if embeddings exist: `SELECT id FROM fs_law_risk.law_sub LIMIT 5;`
-
-#### Port Already in Use
-**Symptom**: `OSError: [Errno 10048] Only one usage of each socket address`
-**Solutions**:
-- Change port: `PORT=8001 python app.py`
-- Kill existing process using the port:
-  ```powershell
-  netstat -ano | findstr :8000
-  taskkill /PID <PID> /F
-  ```
-
-#### Data Export/Import Issues
-**Symptom**: export_risk_json.py or ingest_lawrisk.py fails
-**Solutions**:
-- Verify PostgreSQL credentials in `.env` match database access
-- Ensure export script isn't writing outside the repository
-- For ingestion, confirm DASHSCOPE_API_KEY is valid
-- Check data files exist: `data/risk_tables_export.json`
-- Run export first, then ingestion if needed
-
-### Health Check Commands
-```bash
-# Basic health check
-curl http://localhost:8000/healthz
-
-# Check registered routes (see app startup logs)
-python app.py 2>&1 | grep "Registered routes"
-
-# Test V2 API with debug
-curl -X POST "http://localhost:8000/fs-ai-asistant/api/workflow/lawrisk/v2" \
-  -H "Content-Type: application/x-www-form-urlencoded" \
-  -d "query=我要办一家电影院&debug=1"
-
-# Test regions endpoint
-curl http://localhost:8000/fs-ai-asistant/api/workflow/lawrisk/v2/regions
-
-# Test admin endpoints
-curl http://localhost:8000/fs-ai-asistant/api/workflow/lawrisk/admin/test
-```
-
-### Database Verification
-Verify database content with queries from `DB_GUIDE.md`:
-```sql
--- Check subject count
-SELECT COUNT(*) FROM fs_law_risk.law_sub;
-
--- Check region-theme pairs
-SELECT COUNT(*) FROM licensing_risks.region_themes;
-
--- Check if embeddings exist
-SELECT id, name FROM fs_law_risk.law_sub LIMIT 5;
-
--- List available regions
-SELECT * FROM licensing_risks.regions ORDER BY name;
-```
-
-### Debug Mode
-Enable debug logging to troubleshoot issues:
-```bash
-# Enable Flask debug mode
-FLASK_DEBUG=1 python app.py
-
-# Enable CORS debug mode
-CORS_DEBUG=1 python app.py
-
-# Check app logs for registered routes and errors
-# Logs are printed to console when starting the app
-```
-
-### Health Checks
-- **Basic health**: `GET /healthz` → `{"status": "ok"}`
-- **V2 regions**: `GET /fs-ai-asistant/api/workflow/lawrisk/v2/regions`
-- Check logs for registered routes on app startup
-
-### Data Verification
-Verify database content with queries from `DB_GUIDE.md`:
-```sql
--- Check subject count
-SELECT COUNT(*) FROM fs_law_risk.law_sub;
-
--- Check region-theme pairs
-SELECT COUNT(*) FROM licensing_risks.region_themes;
-```