Function calling in code
Instrument the order-status tool caller
Page 6 adds signals that distinguish bad input from component failure in the order-status function-calling assistant.
1Learn the idea
Read
Emit stage signals
Instrument the order-status function-calling assistant so a run records enough structure to debug offline: counts, latency if relevant, pass/fail of tool-call validity rate, and a stable stage name. Redact secrets and raw credentials from every event.
Read
Emit and assert
const event={stage:'tool-call', tool:'get_order_status', valid:true, grounded:true};
console.log(JSON.stringify(event));
Expected evidence: tool-call telemetry. Prefer JSON or structured text you can grep in CI over prose logs for function-calling-code.
Read
Lock signals with a regression test
Turn one historical failure—especially executing a hallucinated tool name—into a test that fails if the signal disappears for the order-status tool caller. Observability without a failing test is optional decoration; observability with a test is part of the function-calling-code artifact.
Read
Lab notebook: signal schema
Draft a three-field event for the order-status tool caller: stage, ok, and one domain field derived from tool-call validity rate; grounded status answers vs fabricated ones. Add fixture_id or docs_version when content can change. Explicitly list fields that must never appear (tokens, passwords, raw prompts) because allowing a write tool (refund/cancel) in the same registry is in scope for this lab.
Wire one assertion that fails if the order-status tool caller event is missing after a run. Observability that cannot fail a test will not survive contact with a busy function-calling-code repository.
Read
Worked judgment
Imagine a teammate opens only your event stream after a bad deploy. Could they tell whether orders map + tool schema for get_order_status was wrong, whether executing a hallucinated tool name, or answering status without a tool call returned, or whether allowing a write tool (refund/cancel) in the same registry slipped through? If not, rename fields until those three stories are distinguishable.
Read
Why this stage matters for the order-status tool caller
At the testing and observability stage for function-calling-code, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about orders map + tool schema for get_order_status 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: assistant that answers without tools on the same prompts.
For this page specifically, success looks like a structured event schema locked by a test while still centering the user decision to let the model request a read-only get_order_status tool, then answer from the tool result. If you cannot point to a file, command, or assertion that proves that for the order-status tool caller, stay on this page instead of advancing.
Glossary: tool · Glossary: structured output · Cheatsheet: production ops signals
Go deeper
Before you start
Why this matters
Write the single log line or metric event that would tell you whether a bad result came from input vs implementation for the order-status tool caller. If your line could not tell them apart, redesign it before coding.
In the wild
See how this idea shows up as a product and a company — then come back to the lesson. Skills transfer across vendors.
Related lessons
Check your understanding
Page assessment
Answer from memory. Completion is saved from this evidence, not from opening the next page.
All responses are required.