Co-authored-by: Jason Woltje <jason@diversecanvas.com> Co-committed-by: Jason Woltje <jason@diversecanvas.com>
139 lines
4.6 KiB
TypeScript
139 lines
4.6 KiB
TypeScript
import { describe, it, expect, beforeEach, vi } from 'vitest';
|
|
import { RoutingService } from '../routing.service.js';
|
|
import type { ModelInfo } from '@mosaic/types';
|
|
|
|
const mockModels: ModelInfo[] = [
|
|
{
|
|
id: 'claude-3-haiku',
|
|
provider: 'anthropic',
|
|
name: 'Claude 3 Haiku',
|
|
reasoning: false,
|
|
contextWindow: 200_000,
|
|
maxTokens: 4096,
|
|
inputTypes: ['text', 'image'],
|
|
cost: { input: 0.25, output: 1.25, cacheRead: 0.03, cacheWrite: 0.3 },
|
|
},
|
|
{
|
|
id: 'claude-3-sonnet',
|
|
provider: 'anthropic',
|
|
name: 'Claude 3 Sonnet',
|
|
reasoning: true,
|
|
contextWindow: 200_000,
|
|
maxTokens: 8192,
|
|
inputTypes: ['text', 'image'],
|
|
cost: { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 3.75 },
|
|
},
|
|
{
|
|
id: 'llama3.2',
|
|
provider: 'ollama',
|
|
name: 'Llama 3.2',
|
|
reasoning: false,
|
|
contextWindow: 128_000,
|
|
maxTokens: 4096,
|
|
inputTypes: ['text'],
|
|
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
|
},
|
|
];
|
|
|
|
function createMockProviderService() {
|
|
return {
|
|
listAvailableModels: vi.fn().mockReturnValue(mockModels),
|
|
findModel: vi.fn(),
|
|
getDefaultModel: vi.fn(),
|
|
getRegistry: vi.fn(),
|
|
listProviders: vi.fn(),
|
|
registerCustomProvider: vi.fn(),
|
|
};
|
|
}
|
|
|
|
describe('RoutingService', () => {
|
|
let routingService: RoutingService;
|
|
let mockProviderService: ReturnType<typeof createMockProviderService>;
|
|
|
|
beforeEach(() => {
|
|
mockProviderService = createMockProviderService();
|
|
routingService = new RoutingService(mockProviderService as never);
|
|
});
|
|
|
|
it('returns a model when no criteria specified', () => {
|
|
const result = routingService.route();
|
|
expect(result).not.toBeNull();
|
|
expect(result!.provider).toBeDefined();
|
|
expect(result!.modelId).toBeDefined();
|
|
expect(result!.score).toBeGreaterThan(0);
|
|
});
|
|
|
|
it('returns null when no models available', () => {
|
|
mockProviderService.listAvailableModels.mockReturnValue([]);
|
|
const result = routingService.route();
|
|
expect(result).toBeNull();
|
|
});
|
|
|
|
it('selects preferred model when specified', () => {
|
|
const result = routingService.route({
|
|
preferredProvider: 'anthropic',
|
|
preferredModel: 'claude-3-sonnet',
|
|
});
|
|
expect(result).not.toBeNull();
|
|
expect(result!.provider).toBe('anthropic');
|
|
expect(result!.modelId).toBe('claude-3-sonnet');
|
|
expect(result!.score).toBe(100);
|
|
});
|
|
|
|
it('disqualifies models without reasoning when required', () => {
|
|
const result = routingService.route({ requireReasoning: true });
|
|
expect(result).not.toBeNull();
|
|
expect(result!.modelId).toBe('claude-3-sonnet');
|
|
});
|
|
|
|
it('disqualifies models without image input when required', () => {
|
|
const result = routingService.route({ requireImageInput: true });
|
|
expect(result).not.toBeNull();
|
|
// Llama doesn't support images, should be excluded
|
|
expect(result!.provider).toBe('anthropic');
|
|
});
|
|
|
|
it('respects minimum context window', () => {
|
|
const result = routingService.route({ minContextWindow: 150_000 });
|
|
expect(result).not.toBeNull();
|
|
// Only anthropic models have 200k context
|
|
expect(result!.provider).toBe('anthropic');
|
|
});
|
|
|
|
it('favors cheap models when costTier is cheap', () => {
|
|
const result = routingService.route({ costTier: 'cheap' });
|
|
expect(result).not.toBeNull();
|
|
// Ollama (free) and Haiku ($0.25/M) are cheap
|
|
expect(['ollama', 'anthropic'].includes(result!.provider)).toBe(true);
|
|
if (result!.provider === 'anthropic') {
|
|
expect(result!.modelId).toBe('claude-3-haiku');
|
|
}
|
|
});
|
|
|
|
it('ranks all models and returns sorted results', () => {
|
|
const ranked = routingService.rank({ taskType: 'coding' });
|
|
expect(ranked.length).toBeGreaterThan(0);
|
|
// Should be sorted by score descending
|
|
for (let i = 1; i < ranked.length; i++) {
|
|
expect(ranked[i]!.score).toBeLessThanOrEqual(ranked[i - 1]!.score);
|
|
}
|
|
});
|
|
|
|
it('gives reasoning bonus for coding tasks', () => {
|
|
const ranked = routingService.rank({ taskType: 'coding' });
|
|
const sonnet = ranked.find((r) => r.modelId === 'claude-3-sonnet');
|
|
const haiku = ranked.find((r) => r.modelId === 'claude-3-haiku');
|
|
expect(sonnet).toBeDefined();
|
|
expect(haiku).toBeDefined();
|
|
// Sonnet (reasoning) should score higher for coding than haiku (no reasoning)
|
|
expect(sonnet!.score).toBeGreaterThan(haiku!.score);
|
|
});
|
|
|
|
it('prefers specified provider', () => {
|
|
const ranked = routingService.rank({ preferredProvider: 'ollama' });
|
|
const ollamaModel = ranked.find((r) => r.provider === 'ollama');
|
|
expect(ollamaModel).toBeDefined();
|
|
expect(ollamaModel!.reasoning).toContain('preferred provider');
|
|
});
|
|
});
|