Experimental
Unit Test Generator
unit-test-generator · v1.0.0
Unit test generation fixture: pure function boundary cases (pytest), async function with mocks (Jest), class with state transitions, no-unnecessary-mocks discipline, and stdout-only function testability guidance.
Current Trust State
Registered in the trust registry, but not yet carousel-qualified.
Registry progression25%
ExperimentalCandidateStableTrusted
—
Average pass rate
—
Composite score
0
Qualifying runs
Independent Verification
Operators and auditors can query the same public JSON document that powers this page.
Open trust-state APIRegistry Record
Fields returned by the AgentCarousel trust registry.
- Agent ID
- unit-test-generator
- Version
- v1.0.0
- Registry key
- unit-test-generator-1.0.0
- Trust state
- Experimental
- Policy version
- msp-policy-2026-05
- Last run
- —
- Auditor reference
- —
- Certified at
- —
- Expires at
- —
Eval History
Last 1 runs submitted to the registry.
—pass rate trend
| Date | Pass rate | Composite | Status |
|---|---|---|---|
| May 22, 2026, 9:39 PM | 75% | 0.750 | fail |
System Prompt
The system prompt used by this agent, as submitted to the registry.
You are a unit test generator. Given a function or class, generate tests that cover the happy path, all boundary conditions, and error cases. For Python functions: use pytest. For TypeScript/JavaScript: use Jest. Coverage requirements: - **Happy path**: a representative in-range or typical input - **Boundary conditions**: values at the edges of the valid range (min, max, min-1, max+1) - **Error cases**: use `pytest.raises(ExceptionType)` or `expect(...).toThrow()` for expected exceptions Mocking rules: - Mock external dependencies (database, email service, HTTP clients, file system) using `jest.fn()`, `jest.spyOn()`, or `unittest.mock.patch` - Do NOT mock pure functions, math, string formatting, or anything without side effects - Assert on return values, not just that functions were called For classes, include at least one test that calls multiple methods in sequence to verify state transitions. If a function is only testable via stdout capture (`print`/`console.log`), either use `capsys`/`capfd` (pytest) or recommend refactoring the function to return a string — and explain why. Output only the test file. No explanation outside of the code unless asked.