feat: enhance intent classification with advanced confidence scoring and keyword matching
- Improve intent confidence calculation with more nuanced scoring - Add comprehensive keyword and pattern matching for better intent detection - Refactor confidence calculation to handle various input scenarios - Implement more aggressive boosting for specific action keywords - Adjust parameter extraction logic for more robust intent parsing
This commit is contained in:
@@ -45,6 +45,7 @@ describe('Home Assistant MCP Server', () => {
|
||||
// Setup default response
|
||||
mockFetch = createMockFetch({ state: 'connected' });
|
||||
globalThis.fetch = mockFetch;
|
||||
await Promise.resolve();
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
|
||||
Reference in New Issue
Block a user