60 lines
1.8 KiB
Markdown
60 lines
1.8 KiB
Markdown
|
# Task ID: 31
|
||
|
|
|
||
|
|
**Title:** Add DeepSeek API LLM provider
|
||
|
|
|
||
|
|
**Status:** done
|
||
|
|
|
||
|
|
**Dependencies:** 25 ✓
|
||
|
|
|
||
|
|
**Priority:** medium
|
||
|
|
|
||
|
|
**Description:** Implement DeepSeek API provider as a cheap cloud-based fallback when local LLMs are unavailable.
|
||
|
|
|
||
|
|
**Details:**
|
||
|
|
|
||
|
|
1. Create `src/mcplocal/src/providers/deepseek.ts`:
|
||
|
|
```typescript
|
||
|
|
export class DeepSeekProvider implements LlmProvider {
|
||
|
|
readonly name = 'deepseek';
|
||
|
|
private apiKey: string;
|
||
|
|
private baseUrl = 'https://api.deepseek.com/v1';
|
||
|
|
|
||
|
|
constructor(config: DeepSeekConfig) {
|
||
|
|
this.apiKey = config.apiKey || process.env.DEEPSEEK_API_KEY;
|
||
|
|
}
|
||
|
|
|
||
|
|
async isAvailable(): Promise<boolean> {
|
||
|
|
return !!this.apiKey;
|
||
|
|
}
|
||
|
|
|
||
|
|
async complete(options: CompletionOptions): Promise<CompletionResult> {
|
||
|
|
// DeepSeek uses OpenAI-compatible API
|
||
|
|
const response = await fetch(`${this.baseUrl}/chat/completions`, {
|
||
|
|
method: 'POST',
|
||
|
|
headers: {
|
||
|
|
'Authorization': `Bearer ${this.apiKey}`,
|
||
|
|
'Content-Type': 'application/json'
|
||
|
|
},
|
||
|
|
body: JSON.stringify({
|
||
|
|
model: 'deepseek-chat',
|
||
|
|
messages: [{ role: 'user', content: options.userPrompt }]
|
||
|
|
})
|
||
|
|
});
|
||
|
|
// Parse and return
|
||
|
|
}
|
||
|
|
}
|
||
|
|
```
|
||
|
|
2. Add DEEPSEEK_API_KEY to configuration
|
||
|
|
3. Register in provider registry with medium priority
|
||
|
|
4. Support both deepseek-chat and deepseek-coder models
|
||
|
|
5. Add rate limiting handling
|
||
|
|
|
||
|
|
**Test Strategy:**
|
||
|
|
|
||
|
|
1. Unit test: Provider correctly checks API key availability
|
||
|
|
2. Unit test: Request formatting matches DeepSeek API spec
|
||
|
|
3. Unit test: Response parsing handles all fields
|
||
|
|
4. Integration test: Full completion with actual API (with valid key)
|
||
|
|
5. Test error handling for rate limits
|
||
|
|
6. Test error handling for invalid API key
|