code/core/src/telemetry/detect-agent.test.ts (1)

5-64: Tests are well-structured but rely on std-env's internal behavior.

The tests correctly use vi.stubEnv() for environment variable stubbing and properly clean up with vi.unstubAllEnvs() in afterEach. However, these tests are effectively integration tests that depend on std-env's internal mapping of environment variables to agent names.

If std-env changes how it maps environment variables (e.g., CLAUDECODE → claude), these tests would fail even though detectAgent() itself works correctly. Consider whether adding a unit test that mocks std-env directly would provide more stable coverage:

vi.mock('std-env', { spy: true });
// Then in beforeEach: vi.mocked(stdEnvDetectAgent).mockReturnValue({ name: 'claude' });

This is not blocking since the current approach validates the full integration path.

🤖 Prompt for AI Agents

Verify each finding against the current code and only fix it if needed.

In `@code/core/src/telemetry/detect-agent.test.ts` around lines 5 - 64, Tests rely
on std-env's mapping of env vars to agent names causing brittle integration
tests; change the tests in detect-agent.test.ts to mock the 'std-env' module
directly instead of stubbing process envs: use vi.mock('std-env', { spy: true })
and in each test (or beforeEach) set vi.mocked(<imported std-env
function>).mockReturnValue(...) to return the expected agent object (e.g., {
name: 'claude' }) for each scenario, keep the existing detectAgent() assertions,
and restore mocks/unmock in afterEach so tests no longer depend on std-env
implementation details.