@kiyeonjeon21/datacontext 0.2.0 → 0.3.0

package/README.md

@@ -1,21 +1,69 @@
 # DataContext
 
-**AI-native database context layer** - Make AI understand your data better.
+<div align="center">
 
-DataContext is an MCP (Model Context Protocol) server that enables AI assistants like Claude, Cursor, and ChatGPT to query your databases with full business context. Stop explaining your schema every time - define it once, use it everywhere.
+![npm version](https://img.shields.io/npm/v/@kiyeonjeon21/datacontext)
+![license](https://img.shields.io/npm/l/@kiyeonjeon21/datacontext)
+![downloads](https://img.shields.io/npm/dm/@kiyeonjeon21/datacontext)
+
+**AI-native database context layer** — Make AI understand your data better.
+
+[Quick Start](#quick-start) • [VS Code Extension](#vs-code-extension) • [Documentation](#documentation) • [API Reference](./docs/API.md)
+
+</div>
+
+---
+
+## The Problem
+
+Every time you use AI to write SQL, you explain the same things:
+
+> "The `users` table has a `status` column where 1 means active..."
+> "We have a soft-delete pattern, so add `deleted_at IS NULL`..."
+> "The `orders.total` column is in cents, not dollars..."
+
+**DataContext solves this.** Define your business context once, and AI understands it everywhere.
+
+---
+
+## How It Works
+
+```
+┌─────────────────────────────────────────────────────────────────┐
+│  AI Assistant (Claude, Cursor, ChatGPT)                        │
+└─────────────────────────┬───────────────────────────────────────┘
+                          │ MCP Protocol
+┌─────────────────────────▼───────────────────────────────────────┐
+│  DataContext                                                    │
+│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐              │
+│  │  Knowledge  │  │   Safety    │  │  Learning   │              │
+│  │   Layer     │  │  Validator  │  │    Loop     │              │
+│  └─────────────┘  └─────────────┘  └─────────────┘              │
+└─────────────────────────┬───────────────────────────────────────┘
+                          │
+┌─────────────────────────▼───────────────────────────────────────┐
+│  Your Database (PostgreSQL, MySQL, SQLite)                      │
+└─────────────────────────────────────────────────────────────────┘
+```
+
+---
 
 ## Features
 
-- **MCP Protocol Support** - Works with Claude Desktop, Cursor IDE, and any MCP-compatible client
-- **Multi-Database** - PostgreSQL, MySQL/MariaDB, SQLite
-- **Safety First** - Read-only by default, query validation, timeout protection, and audit logging
-- **Knowledge Layer** - Store table descriptions, business rules, and query examples
-- **Schema Versioning** - Track schema changes and detect drift in your knowledge base
-- **Auto-Harvesting** - Automatically collect DB comments, indexes, and relationships
-- **Cost Estimation** - EXPLAIN-first query analysis to prevent expensive queries
-- **Learning Loop** - Capture SQL corrections and feedback to improve over time
-- **Metrics Collection** - Track execution success rates, edit rates, and guardrail activations
-- **Platform Agnostic** - Use via MCP, REST API, or direct SDK integration
+| Feature | Description |
+|---------|-------------|
+| 🔌 **MCP Protocol** | Works with Claude Desktop, Cursor IDE, and any MCP client |
+| 🗄️ **Multi-Database** | PostgreSQL, MySQL/MariaDB, SQLite |
+| 🔒 **Safety First** | Read-only by default, query validation, timeout protection |
+| 📚 **Knowledge Layer** | Store descriptions, business rules, query examples |
+| 🤖 **AI Glossary** | Auto-generate business terms from natural language (requires Anthropic API key) |
+| 🌾 **Auto-Harvesting** | Collect DB comments, indexes, relationships automatically |
+| 💰 **Cost Estimation** | EXPLAIN-first analysis to prevent expensive queries |
+| 📊 **Learning Loop** | Capture feedback to improve over time |
+| 🌐 **REST API** | HTTP interface for web apps |
+| 🧩 **VS Code Extension** | IDE integration with autocomplete |
+
+---
 
 ## Quick Start
 
@@ -23,340 +71,300 @@ DataContext is an MCP (Model Context Protocol) server that enables AI assistants
 
 ```bash
 npm install -g @kiyeonjeon21/datacontext
-# or use directly with npx
-npx @kiyeonjeon21/datacontext connect postgres://...
+# or use with npx
+npx @kiyeonjeon21/datacontext --help
 ```
 
-### 2. Connect to Your Database
+### 2. Connect & Start Server
 
 ```bash
-# PostgreSQL - Start MCP server
-npx @kiyeonjeon21/datacontext connect postgres://user:password@localhost:5432/mydb
+# Start REST API server (recommended for testing)
+npx @kiyeonjeon21/datacontext serve postgres://user:pass@localhost:5432/mydb --port 3000
 
-# MySQL/MariaDB
-npx @kiyeonjeon21/datacontext connect mysql://user:password@localhost:3306/mydb
+# Or start MCP server directly
+npx @kiyeonjeon21/datacontext connect postgres://user:pass@localhost:5432/mydb
+```
 
-# SQLite
-npx @kiyeonjeon21/datacontext connect ./mydb.sqlite
+### 3. AI Features (Optional)
 
-# Or start REST API server
-npx @kiyeonjeon21/datacontext serve postgres://user:password@localhost:5432/mydb --port 3000
+To use AI-powered glossary generation, set your Anthropic API key:
+
+```bash
+# Option 1: Environment variable (recommended)
+export ANTHROPIC_API_KEY=sk-ant-api03-...
+npx @kiyeonjeon21/datacontext serve postgres://user:pass@localhost:5432/mydb
+
+# Option 2: One-line command
+ANTHROPIC_API_KEY=sk-ant-api03-... npx @kiyeonjeon21/datacontext serve postgres://...
 ```
 
-### 3. Configure Your AI Client
+**Get your API key:** [Anthropic Console](https://console.anthropic.com/)
+
+**Note:** AI features are optional. Basic functionality (queries, descriptions, harvesting) works without an API key.
 
-#### Claude Desktop
+### 4. Configure AI Client
 
-Add to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json`):
+**Claude Desktop** (`~/Library/Application Support/Claude/claude_desktop_config.json`):
 
 ```json
 {
   "mcpServers": {
     "datacontext": {
       "command": "npx",
-      "args": ["datacontext", "connect", "postgres://user:password@localhost:5432/mydb"]
+      "args": ["@kiyeonjeon21/datacontext", "connect", "postgres://user:pass@localhost:5432/mydb"]
     }
   }
 }
 ```
 
-#### Cursor IDE
-
-Add to your Cursor MCP settings:
+**Cursor IDE** (Settings → MCP):
 
 ```json
 {
   "mcpServers": {
     "datacontext": {
       "command": "npx",
-      "args": ["datacontext", "connect", "postgres://user:password@localhost:5432/mydb"]
+      "args": ["@kiyeonjeon21/datacontext", "connect", "postgres://user:pass@localhost:5432/mydb"]
     }
   }
 }
 ```
 
-## CLI Commands
+---
 
-### `datacontext connect`
+## VS Code Extension
 
-Start the MCP server for a database connection.
+Install the DataContext VS Code extension for:
 
-```bash
-npx @kiyeonjeon21/datacontext connect <connection-string> [options]
+- 📊 **Database Explorer** — Browse tables and columns in the sidebar
+- 💡 **SQL Autocomplete** — Intelligent completions based on your schema
+- 📝 **Inline Descriptions** — Hover over tables to see business context
+- 🌾 **Harvest Command** — Auto-collect metadata from your database
+
+**Install:** Search "DataContext" in VS Code Extensions or:
 
-Options:
-  --schema <schema>              Default schema (default: "public")
-  --read-only                    Enable read-only mode (default: true)
-  --no-read-only                 Allow write operations
-  --timeout <ms>                 Query timeout (default: 30000)
-  --max-rows <count>             Maximum rows to return (default: 1000)
-  --allowed-schemas <schemas...> Only allow these schemas
-  --allowed-tables <tables...>   Only allow these tables
+```bash
+code --install-extension kiyeonjeon21.vscode-datacontext
 ```
 
-### `datacontext init`
+**Usage:**
+1. Start DataContext server: `npx @kiyeonjeon21/datacontext serve ...`
+2. In VS Code: `Cmd+Shift+P` → "DataContext: Connect to Database"
+3. Enter API URL: `http://localhost:3000`
 
-Initialize a DataContext configuration in the current directory.
+---
 
-```bash
-npx @kiyeonjeon21/datacontext init [options]
+## MCP Tools
 
-Options:
-  --connection <string>  Database connection string
-```
+When connected via MCP, AI assistants can use these tools:
+
+| Tool | Description |
+|------|-------------|
+| `query` | Execute SQL with safety validation |
+| `list_tables` | List all tables in schema |
+| `describe_table` | Get table structure with context |
+| `get_context` | Get business context for tables |
+| `add_description` | Add table/column descriptions |
+| `generate_glossary` | AI: Generate business terms from natural language |
+| `add_term` | Add a business term to glossary |
+| `list_terms` | List all business terms |
+| `search_terms` | Search for terms matching a query |
+| `enhance_query` | AI: Enhance query with glossary terms |
+| `harvest_metadata` | Auto-collect DB metadata |
+| `estimate_cost` | Analyze query cost before running |
+| `record_feedback` | Record query corrections |
+| `get_metrics` | View success rates and stats |
 
-### `datacontext describe`
+---
 
-Add descriptions to tables and columns.
+## Example: Before & After
 
-```bash
-npx @kiyeonjeon21/datacontext describe <table> <description> [options]
+### Before DataContext
 
-Options:
-  --column <name>        Describe a specific column
-  --connection <string>  Database connection string
-  --schema <schema>      Database schema (default: "public")
+```
+User: "Get active users who spent over $100"
+AI: "SELECT * FROM users WHERE ??? JOIN orders ON ???"
+User: "status=1 means active, and total is in cents..."
 ```
 
-Example:
-```bash
-npx @kiyeonjeon21/datacontext describe users "User accounts with authentication info" \
-  --connection postgres://localhost/mydb
+### After DataContext
 
-npx @kiyeonjeon21/datacontext describe users "Account status: 0=inactive, 1=active, 2=suspended" \
-  --column status \
-  --connection postgres://localhost/mydb
+```
+User: "Get active users who spent over $100"
+AI: [Uses DataContext to understand schema]
+    SELECT u.* FROM users u
+    JOIN orders o ON o.user_id = u.id
+    WHERE u.status = 1  -- Active users
+    AND u.deleted_at IS NULL  -- Not soft-deleted
+    GROUP BY u.id
+    HAVING SUM(o.total) > 10000  -- $100 in cents
 ```
 
-### `datacontext schema`
+### AI Glossary Example
 
-Display database schema information.
+Define business terms once, use everywhere:
 
 ```bash
-npx @kiyeonjeon21/datacontext schema <connection-string> [options]
-
-Options:
-  --schema <schema>  Database schema (default: "public")
-  --table <table>    Show only a specific table
-  --json             Output as JSON
+# Generate glossary from natural language
+curl -X POST http://localhost:3000/api/terms/generate \
+  -H "Content-Type: application/json" \
+  -d '{
+    "terms": "활성 사용자 = status가 1인 사용자\n최근 주문 = 30일 이내 주문"
+  }'
+
+# Now AI understands your terms automatically
+User: "활성 사용자 중 최근 주문한 사람 조회해줘"
+AI: SELECT u.* FROM users u
+    JOIN orders o ON o.user_id = u.id
+    WHERE u.status = 1  -- 활성 사용자 (from glossary)
+    AND o.created_at > NOW() - INTERVAL '30 days'  -- 최근 주문 (from glossary)
 ```
 
-### `datacontext serve`
+---
 
-Start REST API server for web apps and non-MCP clients.
+## CLI Commands
 
-```bash
-npx datacontext serve <connection-string> [options]
-
-Options:
-  --port <port>      Server port (default: 3000)
-  --schema <schema>  Default schema (default: "public")
-  --api-key <key>    API key for authentication
-  --read-only        Enable read-only mode (default: true)
-  --timeout <ms>     Query timeout (default: 30000)
-  --max-rows <count> Maximum rows (default: 1000)
-  --cors             Enable CORS (default: true)
-```
+### Server Commands
 
-## REST API
-
-When running with `datacontext serve`, these endpoints are available:
-
-| Method | Endpoint | Description |
-|--------|----------|-------------|
-| GET | `/health` | Health check |
-| POST | `/api/query` | Execute SQL query |
-| POST | `/api/query/estimate` | Estimate query cost |
-| GET | `/api/tables` | List all tables |
-| GET | `/api/tables/:name` | Get table details |
-| GET | `/api/schema` | Get full schema |
-| POST | `/api/context` | Get context for tables |
-| PUT | `/api/tables/:name/description` | Set table description |
-| POST | `/api/examples` | Add query example |
-| POST | `/api/rules` | Add business rule |
-| POST | `/api/harvest` | Run auto-harvesting |
-| POST | `/api/feedback` | Record feedback |
-| GET | `/api/metrics` | Get metrics |
-
-Example:
 ```bash
-# Query
-curl -X POST http://localhost:3000/api/query \
-  -H "Content-Type: application/json" \
-  -d '{"sql": "SELECT * FROM users LIMIT 10"}'
+# Start MCP server (for AI clients like Claude/Cursor)
+npx @kiyeonjeon21/datacontext connect <connection-string> [options]
 
-# List tables
-curl http://localhost:3000/api/tables
+# Start REST API server (for web apps)
+npx @kiyeonjeon21/datacontext serve <connection-string> [options]
 ```
 
-## MCP Tools
-
-DataContext exposes these tools to AI clients:
+### Schema Commands
 
-### Core Tools
-| Tool | Description |
-|------|-------------|
-| `query` | Execute a read-only SQL query |
-| `list_tables` | List all tables with descriptions |
-| `describe_table` | Get detailed schema and context for a table |
-| `get_context` | Get business context for tables |
-| `add_description` | Add descriptions to tables/columns |
-
-### Advanced Tools
-| Tool | Description |
-|------|-------------|
-| `harvest_metadata` | Auto-collect DB comments, indexes, relationships |
-| `estimate_cost` | Analyze query cost before execution (EXPLAIN-first) |
-| `record_feedback` | Report SQL corrections for learning loop |
-| `get_metrics` | Get execution success rates and statistics |
-| `add_query_example` | Add verified query examples for reference |
-| `add_business_rule` | Add business rules for specific tables |
-
-## MCP Resources
-
-DataContext provides these resources:
+```bash
+# View database schema
+npx @kiyeonjeon21/datacontext schema <connection-string>
 
-| Resource | Description |
-|----------|-------------|
-| `schema://database` | Complete database schema |
-| `schema://table/{name}` | Specific table schema with context |
-| `context://knowledge` | All stored knowledge (descriptions, rules, examples) |
+# Add table/column description
+npx @kiyeonjeon21/datacontext describe <table> <description> --connection <string>
+```
 
-## Knowledge Store
+### Glossary Commands
 
-DataContext stores business knowledge locally in `~/.datacontext/`:
+```bash
+# List all business terms
+npx @kiyeonjeon21/datacontext glossary list
 
-- **Table Descriptions** - Business meaning of tables and columns
-- **Query Examples** - Sample queries with natural language intent
-- **Business Rules** - Domain rules that affect queries (e.g., "fiscal year starts in April")
+# Add a term manually
+npx @kiyeonjeon21/datacontext glossary add "활성 사용자" "status가 1인 사용자" \
+  --sql "status = 1" \
+  --synonyms "active user,활성화된 사용자" \
+  --tables "users" \
+  --category "status"
 
-All knowledge is versioned with schema hashes to detect drift when your database changes.
+# Search for terms
+npx @kiyeonjeon21/datacontext glossary search "활성"
 
-## Safety Features
+# Generate terms with AI (requires ANTHROPIC_API_KEY)
+npx @kiyeonjeon21/datacontext glossary generate "최근 주문 = 30일 이내, VIP 고객 = 주문 10건 이상"
 
-DataContext is designed with safety as a priority:
+# Export to YAML/JSON
+npx @kiyeonjeon21/datacontext glossary export --output glossary.yaml
 
-- **Read-only Mode** - Enabled by default, blocks all DML/DDL
-- **Query Validation** - Blocks dangerous keywords and patterns
-- **Timeout Protection** - Default 30s query timeout
-- **Row Limits** - Default 1000 row limit on results
-- **Schema/Table Allowlist** - Restrict access to specific tables
-- **Audit Logging** - Local logs of all query attempts
+# Import from YAML/JSON
+npx @kiyeonjeon21/datacontext glossary import glossary.yaml
 
-## Configuration
+# Delete a term
+npx @kiyeonjeon21/datacontext glossary delete "활성 사용자"
+```
 
-### Environment Variables
+### Other Commands
 
 ```bash
-DATACONTEXT_CONNECTION=postgres://...  # Default connection string
-DATACONTEXT_SCHEMA=public              # Default schema
-DATACONTEXT_READ_ONLY=true             # Enable read-only mode
-DATACONTEXT_TIMEOUT=30000              # Query timeout (ms)
-DATACONTEXT_MAX_ROWS=1000              # Max result rows
+# Initialize configuration
+npx @kiyeonjeon21/datacontext init
 ```
 
-### Configuration File
+**Options:**
+- `--schema <name>` — Default schema (default: "public")
+- `--read-only` / `--no-read-only` — Read-only mode (default: true)
+- `--timeout <ms>` — Query timeout (default: 30000)
+- `--max-rows <n>` — Max rows to return (default: 1000)
+- `--port <n>` — REST API port (default: 3000)
 
-Create `.datacontext/config.json` in your project:
+**AI Features:** Set `ANTHROPIC_API_KEY` environment variable to enable AI-powered glossary generation.
 
-```json
-{
-  "version": "1.0.0",
-  "connection": "postgres://localhost/mydb",
-  "schema": "public",
-  "safety": {
-    "readOnly": true,
-    "timeoutMs": 30000,
-    "maxRows": 1000,
-    "allowedSchemas": ["public"],
-    "allowedTables": []
-  }
-}
-```
+---
 
 ## SDK Usage
 
-Use DataContext programmatically in your applications:
+Use DataContext directly in your application:
 
 ```typescript
 import { 
   createDataContextService,
   createPostgresAdapter,
-  KnowledgeStore 
+  createKnowledgeStore,
 } from '@kiyeonjeon21/datacontext';
 
 // Create service
-const adapter = createPostgresAdapter('postgres://user:pass@localhost:5432/mydb');
-const knowledge = new KnowledgeStore('mydb');
-await knowledge.load();
-
 const service = createDataContextService({
-  adapter,
-  knowledge,
-  safety: { readOnly: true, timeoutMs: 30000, maxRows: 1000 },
+  adapter: createPostgresAdapter('postgres://...'),
+  knowledge: createKnowledgeStore('mydb'),
+  safety: {
+    readOnly: true,
+    timeoutMs: 30000,
+    maxRows: 1000,
+  },
 });
 
-// Query with context
-const result = await service.query('SELECT * FROM users WHERE active = true');
-console.log(result);
+// Initialize
+await service.initialize();
 
-// Build AI context
-const context = service.buildContext(['users', 'orders']);
-console.log(context); // Returns descriptions, rules, examples for these tables
+// Query with context
+const result = await service.query('SELECT * FROM users WHERE status = 1');
+console.log(result.data);
+console.log('Context used:', result.contextUsed);
+
+// Add knowledge
+await service.setTableDescription('users', 'Core user accounts table');
+await service.addBusinessRule(
+  'active_users',
+  'Active users have status=1 and deleted_at IS NULL',
+  ['users']
+);
+
+// Cleanup
+await service.shutdown();
 ```
 
-See [docs/SDK.md](docs/SDK.md) for complete SDK documentation.
+---
 
-## Development
+## Documentation
 
-### Build from Source
+- [REST API Reference](./docs/API.md)
+- [SDK Integration Guide](./docs/SDK.md)
+- [VS Code Extension](./docs/VSCODE_EXTENSION.md)
+- [Architecture Overview](./docs/ARCHITECTURE.md)
+- [Contributing](./CONTRIBUTING.md)
 
-```bash
-git clone https://github.com/datacontext/datacontext-cli.git
-cd datacontext-cli
-npm install
-npm run build
-```
+---
 
-### Run Tests
+## Supported Databases
 
-```bash
-npm test
-```
+| Database | Status | Adapter |
+|----------|--------|---------|
+| PostgreSQL | ✅ Full | `postgres://` |
+| MySQL/MariaDB | ✅ Full | `mysql://` |
+| SQLite | ✅ Full | `./file.sqlite` |
+| BigQuery | 🔜 Planned | — |
+| Snowflake | 🔜 Planned | — |
 
-## Roadmap
-
-### Completed ✅
-- [x] Auto-Harvesting (DB COMMENT, indexes, FK collection)
-- [x] Cost Estimation (EXPLAIN-first analysis)
-- [x] Feedback Capture (SQL correction learning)
-- [x] Metrics Collection (success rates, guardrail stats)
-- [x] Platform-agnostic Core Service layer
-- [x] REST API layer for non-MCP clients
-- [x] SDK documentation
-- [x] MySQL adapter
-
-### In Progress 🚧
-- [ ] VS Code Extension
-- [ ] Cloud sync for team knowledge sharing
-
-### Planned 📋
-- [ ] SQLite adapter
-- [ ] BigQuery adapter
-- [ ] Snowflake adapter
-- [ ] JetBrains IDE plugin
-- [ ] Automatic rule suggestion from corrections
-- [ ] Drift detection and resolution workflows
+---
 
 ## License
 
-MIT License - see [LICENSE](LICENSE) for details.
-
-## Contributing
-
-Contributions are welcome! Please read our [Contributing Guide](CONTRIBUTING.md) for details.
+MIT © DataContext
 
 ---
 
-Made with ❤️ for developers who want AI to understand their data.
+<div align="center">
+
+**[Star on GitHub](https://github.com/vericontext/datacontext-cli)** · **[Report Bug](https://github.com/vericontext/datacontext-cli/issues)** · **[Request Feature](https://github.com/vericontext/datacontext-cli/issues)**
 
+</div>

package/dist/api/server.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"server.d.ts","sourceRoot":"","sources":["../../src/api/server.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,OAA4C,MAAM,SAAS,CAAC;AACnE,OAAO,IAAI,MAAM,MAAM,CAAC;AACxB,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAC;AAErE,MAAM,WAAW,eAAe;IAC9B,mCAAmC;IACnC,OAAO,EAAE,kBAAkB,CAAC;IAC5B,kBAAkB;IAClB,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,kBAAkB;IAClB,IAAI,CAAC,EAAE,OAAO,GAAG,IAAI,CAAC,WAAW,CAAC;IAClC,4CAA4C;IAC5C,MAAM,CAAC,EAAE,MAAM,CAAC;CACjB;AAED;;GAEG;AACH,wBAAgB,eAAe,CAAC,MAAM,EAAE,eAAe,GAAG,OAAO,CAAC,WAAW,CAwY5E;AAED;;GAEG;AACH,wBAAsB,cAAc,CAAC,MAAM,EAAE,eAAe,GAAG,OAAO,CAAC,IAAI,CAAC,CAW3E"}
+{"version":3,"file":"server.d.ts","sourceRoot":"","sources":["../../src/api/server.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,OAA4C,MAAM,SAAS,CAAC;AACnE,OAAO,IAAI,MAAM,MAAM,CAAC;AACxB,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAC;AAErE,MAAM,WAAW,eAAe;IAC9B,mCAAmC;IACnC,OAAO,EAAE,kBAAkB,CAAC;IAC5B,kBAAkB;IAClB,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,kBAAkB;IAClB,IAAI,CAAC,EAAE,OAAO,GAAG,IAAI,CAAC,WAAW,CAAC;IAClC,4CAA4C;IAC5C,MAAM,CAAC,EAAE,MAAM,CAAC;CACjB;AAED;;GAEG;AACH,wBAAgB,eAAe,CAAC,MAAM,EAAE,eAAe,GAAG,OAAO,CAAC,WAAW,CAwiB5E;AAED;;GAEG;AACH,wBAAsB,cAAc,CAAC,MAAM,EAAE,eAAe,GAAG,OAAO,CAAC,IAAI,CAAC,CAW3E"}