ABLITAI LAB — DRAFT PROTOCOL
PROPOSED STUDY — NO RESULTS

When coding clients expose model limits

Question
Does API compatibility produce a usable coding workflow?

Setup
Pin the client and API adapter versions, model identifier, context limit, output allowance and supported capabilities. Use an isolated fixture repository with no credentials or private data.

Proposed method
1. Start with a plain text response, then verify streaming completion and cancellation.
2. Run a harmless, clearly specified tool task only when both the client and server support tool calling.
3. Use a fixed multi-turn conversation to observe context accounting and compaction behavior.
4. Inspect actual API messages and final files. Distinguish executed tools from commands merely printed in the response.

Measures
- Plain text and streaming completion
- Tool-call structure and completion
- Compaction and repeated-response behavior
- Final task outcome and reproducibility

Limitations
Passing one harness does not establish compatibility with others. A client update, prompt change or different output allowance can change behavior. Chat-only mode must not be described as a fully supported coding agent.

Next step
Create the version-pinned fixture and acceptance checks before publishing a compatibility claim.