mcpctl/.taskmaster/tasks/task_030.md

Task ID: 30

Title: Add Gemini CLI LLM provider

Status: done

Dependencies: 25 ✓

Priority: medium

Description: Implement a new LLM provider that uses the Gemini CLI binary for local, free LLM inference as the preferred provider for pre-processing.

Details:

1. Create src/mcplocal/src/providers/gemini-cli.ts:

   import { spawn } from 'child_process';
   
   export class GeminiCliProvider implements LlmProvider {
     readonly name = 'gemini-cli';
     private binaryPath: string;
   
     constructor(config: GeminiCliConfig) {
       this.binaryPath = config.binaryPath || 'gemini';
     }
   
     async isAvailable(): Promise<boolean> {
       // Check if gemini binary exists and is executable
       try {
         await this.runCommand(['--version']);
         return true;
       } catch {
         return false;
       }
     }
   
     async complete(options: CompletionOptions): Promise<CompletionResult> {
       const input = this.formatPrompt(options);
       const output = await this.runCommand(['--prompt', input]);
       return { content: output, model: 'gemini-cli' };
     }
   
     private async runCommand(args: string[]): Promise<string> {
       // Spawn gemini CLI process and capture output
     }
   }
   

2. Research actual Gemini CLI interface and adjust implementation
3. Add to provider registry with high priority (prefer over API providers)
4. Add configuration: geminiCliBinaryPath
5. Handle timeout for slow inference
6. Add fallback to next provider if Gemini CLI fails

Test Strategy:

1. Unit test: Provider correctly detects CLI availability
2. Unit test: Prompt formatting is correct
3. Unit test: Output parsing handles various formats
4. Integration test: Full completion with actual Gemini CLI (if available)
5. Test timeout handling for slow responses
6. Test fallback when CLI is not installed