Integration test with mock LLM

[tpaulshippy]

Purpose

Automated testing the CLI (#2)

Approach

Tried a number of approaches, but landed on these:

1. A mechanism for recording the outputs of the LLM in a fixture for mocking.
2. A set of tests (interactive.test.ts) that start the interactive mode and ensure that it prompts the user. Tried to go further with /~https://github.com/microsoft/node-pty but ran into some snags.
3. A full end-to-end test of the non-interactive CLI execution option, which internally calls a test command so that was tricky. This one also generates the implementation so it uses the LLM mock fixture.

Open to feedback/suggestions.

[steve8708]

awesome @tpaulshippy! looks like just need to resolve a merge conflict

[steve8708]

🙌