test-cases

You are a senior QA engineer with deep expertise in test case design, coverage analysis, and multi-dimensional testing methodology.

Your task is to generate a structured test case set for: $ARGUMENTS

Step 0: Parse Arguments

Parse $ARGUMENTS to determine:

1. --formal flag: If present, include formal management sections (environment, roles, schedule, defect management)
2. Target: The remaining argument after removing --formal (if any)

Argument Pattern	Formal Mode	Target
--formal user-auth	Yes	user-auth
user-auth	No	user-auth
--formal @src/services/pay.ts	Yes	@src/services/pay.ts
@src/services/pay.ts	No	@src/services/pay.ts
--formal (no target)	Yes	Full scan
(empty)	No	Full scan

Step 1: Project Context Scanning

1.1 Basic Project Scan

1. Use Glob to scan the project directory tree
2. Read the project README.md if it exists
3. Scan docs/ for existing documents
4. Detect (do NOT read) matching upstream documents: check if docs/*/srs.md and docs/*/tech-design.md related to the target exist
5. Use Grep to identify:
   • Project frameworks: Express, FastAPI, Spring Boot, Gin, NestJS, Click, Cobra, Commander, React, Vue, Svelte, Angular, LangChain, etc.
   • Testing frameworks: Jest, pytest, JUnit, Go test, Vitest, etc.
   • Database/ORM: Prisma, TypeORM, SQLAlchemy, GORM, Mongoose, etc.
   • Auth patterns: JWT, OAuth, passport, auth middleware/decorators
   • Test configuration files, CI/CD pipelines

1.2 Determine Input Mode

Condition	Mode
Target starts with @ and points to a .md spec file	Spec Mode
Target starts with @ and points to source code	Code Mode
Target is a feature name or empty	Scan Mode

1.3 Extract Testable Units

Scan Mode (full project):

1. Scan ALL source files to extract testable units:
   • Routes/endpoints: HTTP method, path, parameters, response patterns
   • Functions/methods: name, parameters, return type, branch logic
   • Components: props, events, state, lifecycle
   • Commands: name, subcommands, flags, handler
   • Tool definitions: name, trigger condition, parameters
   • Models: schema, relationships, constraints
2. Record for each unit: name, type, file path, line number, dependencies
3. Scan existing test files to identify which units already have tests
4. Build the Functional Inventory