# Task ID: 49

**Title:** Implement read_prompts tool for ongoing retrieval

**Status:** done

**Dependencies:** 48 ✓

**Priority:** high

**Description:** Create the read_prompts MCP tool that allows clients to request additional context by keywords after the session is ungated.

**Details:**

1. Add read_prompts tool definition:
   ```typescript
   private getReadPromptsTool(): Tool {
     return {
       name: 'read_prompts',
       description: 'Request additional project context by keywords. Use this whenever you need guidelines, policies, or conventions related to your current work.',
       inputSchema: {
         type: 'object',
         properties: {
           tags: {
             type: 'array',
             items: { type: 'string' },
             description: 'Keywords describing what context you need'
           }
         },
         required: ['tags']
       }
     };
   }
   ```

2. Implement read_prompts handler:
   - Always use keyword matching (not LLM) for precision
   - Exclude already-retrieved prompts from response
   - Add newly retrieved prompts to session state
   - Include reminder about more prompts available

3. Response format:
   ```
   [Matched prompt content - deduplicated]
   
   Remember: you can request more prompts at any time with read_prompts({ tags: [...] }).
   The project may have additional guidelines relevant to your current approach.
   ```

**Test Strategy:**

- Unit test: read_prompts returns matched prompts by keyword
- Unit test: Already retrieved prompts excluded from response
- Unit test: Newly retrieved prompts added to session state
- Unit test: Response includes reminder text
- Unit test: read_prompts while gated returns error
- Unit test: Empty tags returns empty response
- Unit test: Uses keyword matching not LLM