| { |
| "name": "Deploy verifier", |
| "objective": "Watch a rollout after deployment, compare live signals against release expectations, and escalate quickly when anomalies appear.", |
| "trigger": { |
| "type": "event", |
| "cadence_or_event": "Deployment starts, canary advances, feature flag flips, or release tag is created; then poll every 5-15 minutes during the rollout window." |
| }, |
| "intake": { |
| "sources": ["release notes", "dashboards", "logs", "traces", "synthetic checks", "feature flag state"], |
| "selection_rule": "Compare only signals named in the release expectations and rollback criteria against the pre-rollout baseline." |
| }, |
| "workspace": { |
| "isolation": "Read-only access to observability systems; no production mutation surface.", |
| "allowed_actions": ["read metrics, logs, and traces", "write rollout status updates", "create issues"], |
| "disallowed_actions": ["rollback", "config change", "traffic shifting", "database action", "incident declaration"] |
| }, |
| "context": { |
| "required_files": ["release notes", "rollout checklist"], |
| "runtime_sources": ["baseline metric window", "current dashboards", "synthetic check results", "feature flag state"] |
| }, |
| "agents": [ |
| { |
| "role": "Observer", |
| "responsibility": "Gather metrics, logs, traces, and check status on the polling cadence." |
| }, |
| { |
| "role": "Comparator", |
| "responsibility": "Compare observed signals against release expectations, thresholds, and baseline." |
| }, |
| { |
| "role": "Reporter", |
| "responsibility": "Write concise rollout status: stable, degraded, blocked, or unknown." |
| } |
| ], |
| "verification": { |
| "gates": ["synthetic checks pass", "error rate, latency, and saturation stay within thresholds", "no new dominant failure mode in logs or traces", "deployment phase matches expectations"], |
| "receipts": ["dashboards checked", "baseline window", "anomalies with evidence links", "status decisions with timestamps"] |
| }, |
| "state": { |
| "artifacts": ["rollout status report", "checked-signal log"], |
| "update_rule": "Record release version, rollout phase, signals checked, anomalies, and decisions after every polling interval." |
| }, |
| "budget": { |
| "max_retries": 2, |
| "max_runtime_minutes": 120 |
| }, |
| "escalation": { |
| "conditions": ["threshold breach", "missing telemetry", "migration errors", "customer-impacting regression", "rollback criteria met"], |
| "destination": "On-call channel with evidence links and the rollback checklist" |
| }, |
| "exit": { |
| "success": "The rollout window completes with all signals stable.", |
| "stop_without_success": "The deploy is rolled back, paused, or handed to an incident owner." |
| } |
| } |
|
|
