Define the bounded research agent input contract

The accepted input remains: user question, KB search tool, max_steps, citation requirement. 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: search a local knowledge base then produce a cited answer within a step budget.

const budget={maxSteps:3, requireCitation:true};
if(budget.maxSteps<1) throw new Error('budget');
console.log(budget);

Expected evidence: agent budget contract. 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 bounded research agent so tightening the boundary does not over-reject. Document field names and types the way a teammate would need them on day two of agents-in-code—not as comments you plan to delete.

List every field in fixture KB with 4 notes + max_steps=3 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 bounded research agent.

Add one sentence about encoding, units, or timezones if relevant to user question, KB search tool, max_steps, citation requirement. Contracts that ignore units create “correct” programs that still ship wrong decisions when someone tries to search a local knowledge base then produce a cited answer within a step budget.

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 infinite tool loop, or final answer with no citations after search harder to confuse with a model or algorithm bug later.

At the data contract stage for agents-in-code, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about fixture KB with 4 notes + max_steps=3 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: single-shot LLM answer without search.

For this page specifically, success looks like malformed inputs rejected with field-named errors while still centering the user decision to search a local knowledge base then produce a cited answer within a step budget. If you cannot point to a file, command, or assertion that proves that for the bounded research agent, stay on this page instead of advancing.

Glossary: tool · Glossary: structured output · Cheatsheet: production ops signals

Previous · Next