Typed Service Contracts (Spec & Handler Pattern)

This skill defines a Vertical Slice Architecture backed by Design by Contract (DbC) principles. It treats application logic as rigorously defined Units of Work where inputs are parsed (not just validated) and errors are treated as values (Result Pattern) rather than exceptions.

When to use this skill

• Building CLIs or Libraries: When you need strict boundaries between user input and system logic.
• Complex Validation: When inputs require transformation (parsing) before being useful (e.g., ensuring a string is a valid file path).
• High-Reliability Requirements: When you cannot afford unhandled runtime exceptions and need exhaustive error handling.
• Testing Focus: When you want to separate data validation tests from business logic tests.

Architecture Components

1. The Spec (spec.ts)

The "Contract" or "Port". It defines the What. It must contain:

• Input Schema: A Zod schema that parses raw input into a valid DTO.
• Output Schema: A Zod schema defining the successful data structure.
• Error Schema: A discriminated union of specific failure modes (not generic errors).
• Result Type: A DiscriminatedUnion of Success | Failure.
• Interface: The capability definition (e.g., interface ConfigureSpec).

2. The Handler (handler.ts)

The "Implementation" or "Adapter". It defines the How. It must:

• Implement the Interface defined in the Spec.
• Be an "Impure" class that handles side effects (File System, API calls).
• NEVER throw exceptions. It must catch internal errors and map them to the Result type.

How to use it

Step 1: Define the Contract (spec.ts)

Follow this template to define the boundaries.

typescript
1import { z } from 'zod';
2
3// 1. VALIDATION HELPERS (Reusable Refinements)
4export const SafePathSchema = z.string()
5  .min(1)
6  .refine(p => !p.includes('..'), "No traversal allowed");
7
8// 2. INPUT (The Command) - "Parse, don't validate"
9export const MyTaskInputSchema = z.object({
10  path: SafePathSchema,
11  force: z.boolean().default(false),
12});
13export type MyTaskInput = z.infer<typeof MyTaskInputSchema>;
14
15// 3. ERROR CODES (Exhaustive)
16export const MyTaskErrorCode = z.enum([
17  'FILE_NOT_FOUND',
18  'PERMISSION_DENIED', 
19  'UNKNOWN_ERROR'
20]);
21
22// 4. RESULT (The Monad)
23export const MyTaskSuccess = z.object({
24  success: z.literal(true),
25  data: z.string(), // The output payload
26});
27
28export const MyTaskFailure = z.object({
29  success: z.literal(false),
30  error: z.object({
31    code: MyTaskErrorCode,
32    message: z.string(),
33    suggestion: z.string().optional(),
34    recoverable: z.boolean(),
35  })
36});
37
38export type MyTaskResult = 
39  | z.infer<typeof MyTaskSuccess> 
40  | z.infer<typeof MyTaskFailure>;
41
42// 5. INTERFACE (The Capability)
43export interface MyTaskSpec {
44  execute(input: MyTaskInput): Promise<MyTaskResult>;
45}
46

Step 2: Implement the Handler (handler.ts)

Follow this template to implement the logic.

typescript
1import { MyTaskSpec, MyTaskInput, MyTaskResult } from './spec.js';
2import * as fs from 'fs';
3
4export class MyTaskHandler implements MyTaskSpec {
5  async execute(input: MyTaskInput): Promise<MyTaskResult> {
6    try {
7      // 1. Business Logic
8      if (!fs.existsSync(input.path)) {
9        // 2. Explicit Error Return (No Throwing)
10        return {
11          success: false,
12          error: {
13            code: 'FILE_NOT_FOUND',
14            message: `Path does not exist: ${input.path}`,
15            recoverable: true
16          }
17        };
18      }
19
20      // 3. Success Return
21      return {
22        success: true,
23        data: 'Operation complete'
24      };
25
26    } catch (error) {
27      // 4. Safety Net: Catch unknown runtime errors
28      return {
29        success: false,
30        error: {
31          code: 'UNKNOWN_ERROR',
32          message: error instanceof Error ? error.message : String(error),
33          recoverable: false
34        }
35      };
36    }
37  }
38}
39

Step 3: Testing Strategy

Do not write monolithic tests. Split them into Contract Tests and Logic Tests.

A. Contract Tests (Schema)

Test the Bouncer. Ensure invalid data is rejected before it reaches the handler.

• Focus: Edge cases, validation rules, Zod refinements.
• Style: Data-driven (Table tests).

typescript
1// spec.test.ts
2import { MyTaskInputSchema } from './spec';
3
4const invalidCases = [
5  { val: '../etc/passwd', err: 'No traversal allowed' },
6  { val: '', err: 'min(1)' },
7];
8
9test.each(invalidCases)('validates paths', ({ val, err }) => {
10  const result = MyTaskInputSchema.safeParse({ path: val });
11  expect(result.success).toBe(false);
12});
13

B. Logic Tests (Handler)

Test the Chef. Mock external dependencies (fs, network) and assert the Result Object.

• Focus: Business logic flow, error mapping, success states.
• Style: Mocked unit tests or Scenario Runners.

typescript
1// handler.test.ts
2import { MyTaskHandler } from './handler';
3import { vi } from 'vitest'; // or jest
4
5test('returns FILE_NOT_FOUND if path missing', async () => {
6  // MOCK
7  vi.mocked(fs.existsSync).mockReturnValue(false);
8  
9  // EXECUTE
10  const handler = new MyTaskHandler();
11  const result = await handler.execute({ path: '/fake' });
12
13  // ASSERT (Check the Result Object)
14  expect(result.success).toBe(false);
15  if (!result.success) {
16    expect(result.error.code).toBe('FILE_NOT_FOUND');
17  }
18});
19