Define the CLI LLM summarizer input contract

The accepted input remains: non-empty text, model name, timeout, API key from environment. Keep parsing and normalization in functions that do not score, train, or call a model. That split lets a test fail the boundary without blaming the core logic. The user-facing decision stays: turn one user passage into a bounded one-sentence summary via an HTTP-shaped client.

function request(text){if(!text.trim()) throw new Error('text required'); return {model:'demo',messages:[{role:'system',content:'One sentence.'},{role:'user',content:text}],max_tokens:60};}
console.log(request('Vectors support retrieval.'));

Expected evidence: a request object with model, two roles, and max_tokens. If the contract is silent on a bad value, later debugging will look like an algorithm bug when it is really a data bug.

Write one assertion for a neighboring valid input to the CLI LLM summarizer so tightening the boundary does not over-reject. Document field names and types the way a teammate would need them on day two of llm-api-hello—not as comments you plan to delete.

List every field in system+user job object for an embeddings definition sentence and mark each as required, optional, or forbidden. Required fields must fail loudly when missing; optional fields need defaults you can quote in a test; forbidden fields (secrets, raw PII, path escapes) must never be accepted silently. This list is the contract for the CLI LLM summarizer.

Add one sentence about encoding, units, or timezones if relevant to non-empty text, model name, timeout, API key from environment. Contracts that ignore units create “correct” programs that still ship wrong decisions when someone tries to turn one user passage into a bounded one-sentence summary via an HTTP-shaped client.

Write the error string you want for the most likely bad input. Prefer ValueError('threshold out of range')-style messages over generic invalid input. The contract’s job is to make missing choices array treated as empty success, or retries on 400 harder to confuse with a model or algorithm bug later.

At the data contract stage for llm-api-hello, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about system+user job object for an embeddings definition sentence that later pages inherit without redefining success. Keep that fixture small enough to inspect by hand, keep outputs copy-pasteable as text, and refuse to narrate this baseline as if it were a production SLA: offline fake transport producing a fixed summary.

For this page specifically, success looks like malformed inputs rejected with field-named errors while still centering the user decision to turn one user passage into a bounded one-sentence summary via an HTTP-shaped client. If you cannot point to a file, command, or assertion that proves that for the CLI LLM summarizer, stay on this page instead of advancing.

API: chat completions · Glossary: API key

Previous · Next