Build the first working tool registry runtime

Build only what the claim requires: unknown tools are rejected; calculator and lookup return typed results. Prefer boring, deterministic code over frameworks you cannot yet explain. Run the path twice; identical output on this fixture is a feature, not a lack of creativity.

export async function run(input: unknown, deps: Dependencies) {
  const started = performance.now();
  const validated = deps.parseInput(input);
  const raw = await deps.execute(validated); // dispatch model tool calls through a local Map instead of evaluating generated code
  const value = deps.parseOutput(raw);
  return { value, durationMs: Math.round(performance.now() - started) };
}

Expected evidence: duplicate names, stale schemas, timeouts, oversized results, and unsafe side effects. Read each printed intermediate as part of the argument that the path works—not as decoration.

Narrate the journey from raw input to result for a single example from registry with calc and kb.lookup. If you cannot name an intermediate, the implementation is still too opaque for this lab. Only after this path is solid should you generalize data sources or UI.

While implementing the tool registry runtime, print or log at least three intermediates that map to the claim (unknown tools are rejected; calculator and lookup return typed results). Good intermediates are values a teammate could recompute with a calculator or diff. Bad intermediates are framework traces you cannot explain.

Re-run with registry with calc and kb.lookup twice. If the second run differs, either the path is nondeterministic (document the seed) or you have hidden global state—both are lab bugs until named.

Stop adding features once the path supports route model tool requests through a registry that validates names and args. Extra UI, extra tools, or extra models belong in later chapters. The mastery bar for this page is simply: a deterministic end-to-end path with intermediates.

At the implementation stage for tools-in-code, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about registry with calc and kb.lookup 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: inline if/else tool routing without schemas.

For this page specifically, success looks like a deterministic path with printed intermediates while still centering the user decision to route model tool requests through a registry that validates names and args. If you cannot point to a file, command, or assertion that proves that for the tool registry runtime, stay on this page instead of advancing.

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

Previous · Next