Test Driven Execution

Test Driven Execution

Use tests as the feedback loop that shapes the implementation one vertical slice at a time.

Core Rules

• Test behavior through public interfaces.
• Prefer integration-style tests over implementation-coupled tests.
• Work in vertical slices, not horizontal batches.
• One failing test -> one minimal implementation -> repeat.
• Refactor only while green.

Workflow

1. Confirm the behavior to build or fix.
2. Identify the highest useful seam to test.
3. Write one failing test for one observable behavior.
4. Implement the minimum code to make it pass.
5. Repeat for the next behavior.
6. Refactor only after the slice is green.

For a diagnosed regression that needs durable proof, capture the exact same targeted command before and after with bug-evidence-protocol, then capture relevant broader checks. Do not infer FIX_PROVEN from a green targeted test alone.

Anti-Pattern

Do not write all tests first and all code later. That produces test suites for imagined behavior instead of validated behavior.

Good Tests

• name the user-visible behavior;
• survive internal refactors;
• avoid private methods and internal collaborator trivia;
• verify what the system does, not how it does it.

Planning Questions

• Which behaviors matter most?
• Which seams already exist?
• What should not be tested at this layer?
• What prior art already exists in the repo?

Final Report

Include the behaviors covered, the seams used, what remains untested, and any refactor opportunities exposed by the loop.