test: verify Phase 2 — routing + coord tests (P2-007) (#79)

Co-authored-by: Jason Woltje <jason@diversecanvas.com>
Co-committed-by: Jason Woltje <jason@diversecanvas.com>

apps/gateway/src/agent/__tests__/routing.service.test.ts

@@ -0,0 +1,138 @@
+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');
+  });
+});

docs/TASKS.md

@@ -27,8 +27,8 @@
 | P2-003 | done        | Phase 2   | Agent routing engine — cost/capability matrix                 | #75 | #21   |
 | P2-004 | done        | Phase 2   | Tool registration — brain, queue, memory tools                | #76 | #22   |
 | P2-005 | done        | Phase 2   | @mosaic/coord — migrate from v0, gateway integration          | #77 | #23   |
-| P2-006 | in-progress | Phase 2   | Agent session management — tmux + monitoring                  | —   | #24   |
-| P2-007 | not-started | Phase 2   | Verify Phase 2 — multi-provider routing works                 | —   | #25   |
+| P2-006 | done        | Phase 2   | Agent session management — tmux + monitoring                  | #78 | #24   |
+| P2-007 | in-progress | Phase 2   | Verify Phase 2 — multi-provider routing works                 | —   | #25   |
 | P3-001 | not-started | Phase 3   | apps/web scaffold — Next.js 16 + BetterAuth + Tailwind        | —   | #26   |
 | P3-002 | not-started | Phase 3   | Auth pages — login, registration, SSO redirect                | —   | #27   |
 | P3-003 | not-started | Phase 3   | Chat UI — conversations, messages, streaming                  | —   | #28   |
@@ -63,6 +63,6 @@
 | P7-006 | not-started | Phase 7   | Documentation — user guide, admin guide, dev guide            | —   | #57   |
 | P7-007 | not-started | Phase 7   | Bare-metal deployment docs + .env.example                     | —   | #58   |
 | P7-008 | not-started | Phase 7   | Beta release gate — v0.1.0 tag                                | —   | #59   |
-| FIX-01 | not-started | Backlog   | Call piSession.dispose() in AgentService.destroySession       | —   | #62   |
+| FIX-01 | done        | Backlog   | Call piSession.dispose() in AgentService.destroySession       | #78 | #62   |
 | FIX-02 | not-started | Backlog   | TUI agent:end — fix React state updater side-effect           | —   | #63   |
 | FIX-03 | not-started | Backlog   | Agent session — cwd sandbox, system prompt, tool restrictions | —   | #64   |

packages/coord/src/__tests__/tasks-file.test.ts

@@ -0,0 +1,102 @@
+import { describe, it, expect } from 'vitest';
+import { parseTasksFile, writeTasksFile } from '../tasks-file.js';
+import type { MissionTask } from '../types.js';
+
+const SAMPLE_TASKS_MD = `# Tasks — MVP
+
+> Single-writer: orchestrator only. Workers read but never modify.
+
+| id     | status      | milestone | description                                | pr  | notes |
+| ------ | ----------- | --------- | ------------------------------------------ | --- | ----- |
+| P0-001 | done        | Phase 0   | Scaffold monorepo                          | #60 | #1    |
+| P0-002 | done        | Phase 0   | @mosaic/types — migrate and extend         | #65 | #2    |
+| P1-001 | in-progress | Phase 1   | apps/gateway scaffold                      | #61 | #10   |
+| P2-001 | not-started | Phase 2   | @mosaic/agent — Pi SDK integration         | —   | #19   |
+| P2-002 | blocked     | Phase 2   | Multi-provider support                     | —   | #20   |
+`;
+
+describe('parseTasksFile', () => {
+  it('parses a valid TASKS.md into MissionTask[]', () => {
+    const tasks = parseTasksFile(SAMPLE_TASKS_MD);
+    expect(tasks).toHaveLength(5);
+  });
+
+  it('extracts task IDs correctly', () => {
+    const tasks = parseTasksFile(SAMPLE_TASKS_MD);
+    expect(tasks.map((t) => t.id)).toEqual(['P0-001', 'P0-002', 'P1-001', 'P2-001', 'P2-002']);
+  });
+
+  it('extracts statuses correctly', () => {
+    const tasks = parseTasksFile(SAMPLE_TASKS_MD);
+    expect(tasks.map((t) => t.status)).toEqual([
+      'done',
+      'done',
+      'in-progress',
+      'not-started',
+      'blocked',
+    ]);
+  });
+
+  it('extracts milestones correctly', () => {
+    const tasks = parseTasksFile(SAMPLE_TASKS_MD);
+    expect(tasks[0]!.milestone).toBe('Phase 0');
+    expect(tasks[2]!.milestone).toBe('Phase 1');
+    expect(tasks[3]!.milestone).toBe('Phase 2');
+  });
+
+  it('extracts PR references', () => {
+    const tasks = parseTasksFile(SAMPLE_TASKS_MD);
+    expect(tasks[0]!.pr).toBe('#60');
+    expect(tasks[3]!.pr).toBe('—');
+  });
+
+  it('returns empty array for empty content', () => {
+    expect(parseTasksFile('')).toEqual([]);
+    expect(parseTasksFile('# No table here')).toEqual([]);
+  });
+
+  it('handles legacy status values', () => {
+    const content = `| id | status | description |
+|----|--------|-------------|
+| T1 | completed | Task one |
+| T2 | pending | Task two |
+| T3 | failed | Task three |
+`;
+    const tasks = parseTasksFile(content);
+    expect(tasks[0]!.status).toBe('done');
+    expect(tasks[1]!.status).toBe('not-started');
+    expect(tasks[2]!.status).toBe('blocked');
+  });
+});
+
+describe('writeTasksFile', () => {
+  it('generates valid markdown table', () => {
+    const tasks: MissionTask[] = [
+      {
+        id: 'T-001',
+        title: 'Test task',
+        status: 'done',
+        dependencies: [],
+        milestone: 'Phase 1',
+        pr: '#42',
+        notes: '#1',
+      },
+    ];
+
+    const output = writeTasksFile(tasks);
+    expect(output).toContain('| T-001 | done | Phase 1 | Test task | #42 | #1 |');
+    expect(output).toContain('# Tasks');
+  });
+
+  it('roundtrips parse/write', () => {
+    const tasks = parseTasksFile(SAMPLE_TASKS_MD);
+    const output = writeTasksFile(tasks);
+    const reparsed = parseTasksFile(output);
+    expect(reparsed).toHaveLength(tasks.length);
+    for (let i = 0; i < tasks.length; i++) {
+      expect(reparsed[i]!.id).toBe(tasks[i]!.id);
+      expect(reparsed[i]!.status).toBe(tasks[i]!.status);
+      expect(reparsed[i]!.title).toBe(tasks[i]!.title);
+    }
+  });
+});