vellum 0.2.0 → 0.2.2

package/src/__tests__/call-orchestrator.test.ts

@@ -0,0 +1,454 @@
+import { describe, test, expect, beforeEach, afterAll, mock, type Mock } from 'bun:test';
+import { mkdtempSync, rmSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+import { EventEmitter } from 'node:events';
+
+const testDir = mkdtempSync(join(tmpdir(), 'call-orchestrator-test-'));
+
+// ── Platform + logger mocks (must come before any source imports) ────
+
+mock.module('../util/platform.js', () => ({
+  getDataDir: () => testDir,
+  isMacOS: () => process.platform === 'darwin',
+  isLinux: () => process.platform === 'linux',
+  isWindows: () => process.platform === 'win32',
+  getSocketPath: () => join(testDir, 'test.sock'),
+  getPidPath: () => join(testDir, 'test.pid'),
+  getDbPath: () => join(testDir, 'test.db'),
+  getLogPath: () => join(testDir, 'test.log'),
+  ensureDataDir: () => {},
+}));
+
+mock.module('../util/logger.js', () => ({
+  getLogger: () =>
+    new Proxy({} as Record<string, unknown>, {
+      get: () => () => {},
+    }),
+}));
+
+// ── Config mock ─────────────────────────────────────────────────────
+
+mock.module('../config/loader.js', () => ({
+  getConfig: () => ({
+    apiKeys: { anthropic: 'test-key' },
+    calls: {
+      enabled: true,
+      provider: 'twilio',
+      maxDurationSeconds: 12 * 60,
+      userConsultTimeoutSeconds: 90,
+      userConsultationTimeoutSeconds: 90,
+      silenceTimeoutSeconds: 30,
+      disclosure: { enabled: false, text: '' },
+      safety: { denyCategories: [] },
+    },
+  }),
+}));
+
+// ── Helpers for building mock streaming responses ───────────────────
+
+/**
+ * Creates a mock Anthropic stream object that emits 'text' events
+ * for each token and resolves `finalMessage()` with the full response.
+ */
+function createMockStream(tokens: string[]) {
+  const emitter = new EventEmitter();
+  const fullText = tokens.join('');
+
+  const stream = {
+    on: (event: string, handler: (...args: unknown[]) => void) => {
+      emitter.on(event, handler);
+      return stream;
+    },
+    finalMessage: () => {
+      // Emit tokens synchronously so the on('text') handler has fired
+      // before finalMessage resolves.
+      for (const token of tokens) {
+        emitter.emit('text', token);
+      }
+      return Promise.resolve({
+        content: [{ type: 'text', text: fullText }],
+      });
+    },
+  };
+
+  return stream;
+}
+
+// ── Anthropic SDK mock ──────────────────────────────────────────────
+
+let mockStreamFn: Mock<(...args: unknown[]) => unknown>;
+
+mock.module('@anthropic-ai/sdk', () => {
+  mockStreamFn = mock((..._args: unknown[]) => createMockStream(['Hello', ' there']));
+  return {
+    default: class MockAnthropic {
+      messages = {
+        stream: (...args: unknown[]) => mockStreamFn(...args),
+      };
+    },
+  };
+});
+
+// ── Import source modules after all mocks are registered ────────────
+
+import { initializeDb, getDb, resetDb } from '../memory/db.js';
+import { conversations } from '../memory/schema.js';
+import {
+  createCallSession,
+  getCallSession,
+  getPendingQuestion,
+  updateCallSession,
+} from '../calls/call-store.js';
+import {
+  getCallOrchestrator,
+} from '../calls/call-state.js';
+import { CallOrchestrator } from '../calls/call-orchestrator.js';
+import type { RelayConnection } from '../calls/relay-server.js';
+
+initializeDb();
+
+afterAll(() => {
+  resetDb();
+  try {
+    rmSync(testDir, { recursive: true });
+  } catch {
+    /* best effort */
+  }
+});
+
+// ── RelayConnection mock factory ────────────────────────────────────
+
+interface MockRelay extends RelayConnection {
+  sentTokens: Array<{ token: string; last: boolean }>;
+  endCalled: boolean;
+  endReason: string | undefined;
+}
+
+function createMockRelay(): MockRelay {
+  const state = {
+    sentTokens: [] as Array<{ token: string; last: boolean }>,
+    _endCalled: false,
+    _endReason: undefined as string | undefined,
+  };
+
+  return {
+    get sentTokens() { return state.sentTokens; },
+    get endCalled() { return state._endCalled; },
+    get endReason() { return state._endReason; },
+    sendTextToken(token: string, last: boolean) {
+      state.sentTokens.push({ token, last });
+    },
+    endSession(reason?: string) {
+      state._endCalled = true;
+      state._endReason = reason;
+    },
+  } as unknown as MockRelay;
+}
+
+// ── Helpers ─────────────────────────────────────────────────────────
+
+let ensuredConvIds = new Set<string>();
+function ensureConversation(id: string): void {
+  if (ensuredConvIds.has(id)) return;
+  const db = getDb();
+  const now = Date.now();
+  db.insert(conversations).values({
+    id,
+    title: `Test conversation ${id}`,
+    createdAt: now,
+    updatedAt: now,
+  }).run();
+  ensuredConvIds.add(id);
+}
+
+function resetTables() {
+  const db = getDb();
+  db.run('DELETE FROM call_pending_questions');
+  db.run('DELETE FROM call_events');
+  db.run('DELETE FROM call_sessions');
+  db.run('DELETE FROM conversations');
+  ensuredConvIds = new Set();
+}
+
+/**
+ * Create a call session and an orchestrator wired to a mock relay.
+ */
+function setupOrchestrator(task?: string) {
+  ensureConversation('conv-orch-test');
+  const session = createCallSession({
+    conversationId: 'conv-orch-test',
+    provider: 'twilio',
+    fromNumber: '+15551111111',
+    toNumber: '+15552222222',
+    task,
+  });
+  updateCallSession(session.id, { status: 'in_progress' });
+  const relay = createMockRelay();
+  const orchestrator = new CallOrchestrator(session.id, relay as unknown as RelayConnection, task ?? null);
+  return { session, relay, orchestrator };
+}
+
+describe('call-orchestrator', () => {
+  beforeEach(() => {
+    resetTables();
+    // Reset the stream mock to default behaviour
+    mockStreamFn.mockImplementation(() => createMockStream(['Hello', ' there']));
+  });
+
+  // ── handleCallerUtterance ─────────────────────────────────────────
+
+  test('handleCallerUtterance: streams tokens via sendTextToken', async () => {
+    mockStreamFn.mockImplementation(() => createMockStream(['Hi', ', how', ' are you?']));
+    const { relay, orchestrator } = setupOrchestrator();
+
+    await orchestrator.handleCallerUtterance('Hello');
+
+    // Verify tokens were sent to the relay
+    const nonEmptyTokens = relay.sentTokens.filter((t) => t.token.length > 0);
+    expect(nonEmptyTokens.length).toBeGreaterThan(0);
+    // The last token should have last=true (empty string token signaling end)
+    const lastToken = relay.sentTokens[relay.sentTokens.length - 1];
+    expect(lastToken.last).toBe(true);
+
+    orchestrator.destroy();
+  });
+
+  test('handleCallerUtterance: sends last=true at end of turn', async () => {
+    mockStreamFn.mockImplementation(() => createMockStream(['Simple response.']));
+    const { relay, orchestrator } = setupOrchestrator();
+
+    await orchestrator.handleCallerUtterance('Test');
+
+    // Find the final empty-string token that marks end of turn
+    const endMarkers = relay.sentTokens.filter((t) => t.last === true);
+    expect(endMarkers.length).toBeGreaterThanOrEqual(1);
+
+    orchestrator.destroy();
+  });
+
+  test('handleCallerUtterance: includes speaker context in model message', async () => {
+    mockStreamFn.mockImplementation((...args: unknown[]) => {
+      const firstArg = args[0] as { messages: Array<{ role: string; content: string }> };
+      const userMessage = firstArg.messages.find((m) => m.role === 'user');
+      expect(userMessage?.content).toContain('[SPEAKER id="speaker-1" label="Aaron" source="provider" confidence="0.91"]');
+      expect(userMessage?.content).toContain('Can you summarize this meeting?');
+      return createMockStream(['Sure, here is a summary.']);
+    });
+
+    const { orchestrator } = setupOrchestrator();
+
+    await orchestrator.handleCallerUtterance('Can you summarize this meeting?', {
+      speakerId: 'speaker-1',
+      speakerLabel: 'Aaron',
+      speakerConfidence: 0.91,
+      source: 'provider',
+    });
+
+    orchestrator.destroy();
+  });
+
+  // ── ASK_USER pattern ──────────────────────────────────────────────
+
+  test('ASK_USER pattern: detects pattern, creates pending question, enters waiting_on_user', async () => {
+    mockStreamFn.mockImplementation(() =>
+      createMockStream(['Let me check on that. ', '[ASK_USER: What date works best?]']),
+    );
+    const { session, relay, orchestrator } = setupOrchestrator('Book appointment');
+
+    await orchestrator.handleCallerUtterance('I need to schedule something');
+
+    // Verify a pending question was created
+    const question = getPendingQuestion(session.id);
+    expect(question).not.toBeNull();
+    expect(question!.questionText).toBe('What date works best?');
+    expect(question!.status).toBe('pending');
+
+    // Verify session status was updated to waiting_on_user
+    const updatedSession = getCallSession(session.id);
+    expect(updatedSession!.status).toBe('waiting_on_user');
+
+    // The ASK_USER marker text should NOT appear in the relay tokens
+    const allText = relay.sentTokens.map((t) => t.token).join('');
+    expect(allText).not.toContain('[ASK_USER:');
+
+    orchestrator.destroy();
+  });
+
+  // ── END_CALL pattern ──────────────────────────────────────────────
+
+  test('END_CALL pattern: detects marker, calls endSession, updates status to completed', async () => {
+    mockStreamFn.mockImplementation(() =>
+      createMockStream(['Thank you for calling, goodbye! ', '[END_CALL]']),
+    );
+    const { session, relay, orchestrator } = setupOrchestrator();
+
+    await orchestrator.handleCallerUtterance('That is all, thanks');
+
+    // endSession should have been called
+    expect(relay.endCalled).toBe(true);
+
+    // Session status should be completed
+    const updatedSession = getCallSession(session.id);
+    expect(updatedSession!.status).toBe('completed');
+    expect(updatedSession!.endedAt).not.toBeNull();
+
+    // The END_CALL marker text should NOT appear in the relay tokens
+    const allText = relay.sentTokens.map((t) => t.token).join('');
+    expect(allText).not.toContain('[END_CALL]');
+
+    orchestrator.destroy();
+  });
+
+  // ── handleUserAnswer ──────────────────────────────────────────────
+
+  test('handleUserAnswer: returns true immediately and fires LLM asynchronously', async () => {
+    // First utterance triggers ASK_USER
+    mockStreamFn.mockImplementation(() =>
+      createMockStream(['Hold on. [ASK_USER: Preferred time?]']),
+    );
+    const { relay, orchestrator } = setupOrchestrator();
+
+    await orchestrator.handleCallerUtterance('I need an appointment');
+
+    // Now provide the answer — reset mock for second LLM call
+    mockStreamFn.mockImplementation((...args: unknown[]) => {
+      // Verify the messages include the USER_ANSWERED marker
+      const firstArg = args[0] as { messages: Array<{ role: string; content: string }> };
+      const lastUserMsg = firstArg.messages.filter((m: { role: string }) => m.role === 'user').pop();
+      expect(lastUserMsg?.content).toContain('[USER_ANSWERED: 3pm tomorrow]');
+      return createMockStream(['Great, I have scheduled for 3pm tomorrow.']);
+    });
+
+    const accepted = await orchestrator.handleUserAnswer('3pm tomorrow');
+    expect(accepted).toBe(true);
+
+    // handleUserAnswer fires runLlm without awaiting, so give the
+    // microtask queue a tick to let the async LLM work complete.
+    await new Promise((r) => setTimeout(r, 50));
+
+    // Should have streamed a response for the answer
+    const tokensAfterAnswer = relay.sentTokens.filter((t) => t.token.includes('3pm'));
+    expect(tokensAfterAnswer.length).toBeGreaterThan(0);
+
+    orchestrator.destroy();
+  });
+
+  // ── Full mid-call question flow ──────────────────────────────────
+
+  test('mid-call question flow: unavailable time → ask user → user confirms → resumed call', async () => {
+    // Step 1: Caller says "7:30" but it's unavailable. The LLM asks the user.
+    mockStreamFn.mockImplementation(() =>
+      createMockStream(['I\'m sorry, 7:30 is not available. ', '[ASK_USER: Is 8:00 okay instead?]']),
+    );
+
+    const { session, relay, orchestrator } = setupOrchestrator('Schedule a haircut');
+
+    await orchestrator.handleCallerUtterance('Can I book for 7:30?');
+
+    // Verify we're in waiting_on_user state
+    expect(orchestrator.getState()).toBe('waiting_on_user');
+    const question = getPendingQuestion(session.id);
+    expect(question).not.toBeNull();
+    expect(question!.questionText).toBe('Is 8:00 okay instead?');
+
+    // Verify session status
+    const midSession = getCallSession(session.id);
+    expect(midSession!.status).toBe('waiting_on_user');
+
+    // Step 2: User answers "Yes, 8:00 works"
+    mockStreamFn.mockImplementation(() =>
+      createMockStream(['Great, I\'ve booked you for 8:00. See you then! ', '[END_CALL]']),
+    );
+
+    const accepted = await orchestrator.handleUserAnswer('Yes, 8:00 works for me');
+    expect(accepted).toBe(true);
+
+    // Give the fire-and-forget LLM call time to complete
+    await new Promise((r) => setTimeout(r, 50));
+
+    // Step 3: Verify call completed
+    const endSession = getCallSession(session.id);
+    expect(endSession!.status).toBe('completed');
+    expect(endSession!.endedAt).not.toBeNull();
+
+    // Verify the END_CALL marker triggered endSession on relay
+    expect(relay.endCalled).toBe(true);
+
+    orchestrator.destroy();
+  });
+
+  // ── Provider / LLM failure paths ───────────────────────────────
+
+  test('LLM error: sends error message to caller and returns to idle', async () => {
+    // Make the stream throw an error on finalMessage
+    mockStreamFn.mockImplementation(() => {
+      const emitter = new EventEmitter();
+      return {
+        on: (event: string, handler: (...args: unknown[]) => void) => {
+          emitter.on(event, handler);
+          return { on: () => ({ on: () => ({}) }) };
+        },
+        finalMessage: () => Promise.reject(new Error('API rate limit exceeded')),
+      };
+    });
+
+    const { relay, orchestrator } = setupOrchestrator();
+
+    await orchestrator.handleCallerUtterance('Hello');
+
+    // Should have sent an error recovery message
+    const errorTokens = relay.sentTokens.filter((t) =>
+      t.token.includes('technical issue'),
+    );
+    expect(errorTokens.length).toBeGreaterThan(0);
+
+    // State should return to idle after error
+    expect(orchestrator.getState()).toBe('idle');
+
+    orchestrator.destroy();
+  });
+
+  test('handleUserAnswer: returns false when not in waiting_on_user state', async () => {
+    const { orchestrator } = setupOrchestrator();
+
+    // Orchestrator starts in idle state
+    const result = await orchestrator.handleUserAnswer('some answer');
+    expect(result).toBe(false);
+
+    orchestrator.destroy();
+  });
+
+  // ── handleInterrupt ───────────────────────────────────────────────
+
+  test('handleInterrupt: resets state to idle', () => {
+    const { orchestrator } = setupOrchestrator();
+
+    // Calling handleInterrupt should not throw
+    orchestrator.handleInterrupt();
+
+    orchestrator.destroy();
+  });
+
+  // ── destroy ───────────────────────────────────────────────────────
+
+  test('destroy: unregisters orchestrator', () => {
+    const { session, orchestrator } = setupOrchestrator();
+
+    // Orchestrator should be registered
+    expect(getCallOrchestrator(session.id)).toBeDefined();
+
+    orchestrator.destroy();
+
+    // After destroy, orchestrator should be unregistered
+    expect(getCallOrchestrator(session.id)).toBeUndefined();
+  });
+
+  test('destroy: can be called multiple times without error', () => {
+    const { orchestrator } = setupOrchestrator();
+
+    orchestrator.destroy();
+    // Second destroy should not throw
+    expect(() => orchestrator.destroy()).not.toThrow();
+  });
+});