Instrument the research-critique coordinator

Instrument the research+critique coordinator so a run records enough structure to debug offline: counts, latency if relevant, pass/fail of veto rate, and a stable stage name. Redact secrets and raw credentials from every event.

const event={stage:'coordinator', veto:true, unsupported_after_merge:0, steps:3};
console.log(JSON.stringify(event));

Expected evidence: coordinator telemetry. Prefer JSON or structured text you can grep in CI over prose logs for multi-agent-in-code.

Turn one historical failure—especially workers sharing mutable state—into a test that fails if the signal disappears for the research-critique coordinator. Observability without a failing test is optional decoration; observability with a test is part of the multi-agent-in-code artifact.

Draft a three-field event for the research-critique coordinator: stage, ok, and one domain field derived from veto rate; unsupported claim count after merge; total step budget. Add fixture_id or docs_version when content can change. Explicitly list fields that must never appear (tokens, passwords, raw prompts) because critique worker receiving secrets from research scratchpad logs is in scope for this lab.

Wire one assertion that fails if the research-critique coordinator event is missing after a run. Observability that cannot fail a test will not survive contact with a busy multi-agent-in-code repository.

Imagine a teammate opens only your event stream after a bad deploy. Could they tell whether two workers with separate step budgets was wrong, whether workers sharing mutable state, or coordinator ignoring critique veto returned, or whether critique worker receiving secrets from research scratchpad logs slipped through? If not, rename fields until those three stories are distinguishable.

At the testing and observability stage for multi-agent-in-code, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about two workers with separate step budgets 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 agent without critique pass.

For this page specifically, success looks like a structured event schema locked by a test while still centering the user decision to delegate research and critique to two bounded workers, then merge under a coordinator policy. If you cannot point to a file, command, or assertion that proves that for the research-critique coordinator, stay on this page instead of advancing.

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

Previous · Next