{ "policy": { "version": 5, "patterns": { "version": 1, "method": "CURATED_PRACTICE_TOPIC", "notice": "Pattern topics identify design choices to practice. Read the ticket's acceptance criteria and justify the simplest suitable approach. Tags are not capability or ownership evidence; an untagged ticket has no curated pattern topic assigned." }, "fieldMix": { "version": 1, "method": "CURATED_ESTIMATE", "notice": "Field percentages are editorial estimates of the ticket's engineering focus. They total 100%; they are not measured time, proficiency scores, or ownership evidence." }, "contentStatus": "PRACTICE_BRIEF", "assessmentStatus": "NOT_QUALIFIED", "evidenceUse": "NONE", "aiPolicy": "AI tools are welcome during implementation. Record assumptions, review the result, and verify its behavior.", "notice": "Fictional engineering practice briefs. Starter repositories, fixtures, automated grading, and verified ownership are not included.", "outcomeEvidence": "Tests, patches, and runbooks are requested deliverables. They become Outcome Evidence only through a qualified Mission and immutable Evidence IDs.", "ownershipEvidence": "Independent adaptation must be observed under a declared verification policy and cite immutable Evidence IDs. Completing a planning ticket establishes no Ownership Evidence." }, "patternTopics": [ { "id": "factory-method", "label": "Factory Method", "group": "Creational" }, { "id": "abstract-factory", "label": "Abstract Factory", "group": "Creational" }, { "id": "builder", "label": "Builder", "group": "Creational" }, { "id": "prototype", "label": "Prototype", "group": "Creational" }, { "id": "singleton", "label": "Singleton", "group": "Creational" }, { "id": "adapter", "label": "Adapter", "group": "Structural" }, { "id": "bridge", "label": "Bridge", "group": "Structural" }, { "id": "composite", "label": "Composite", "group": "Structural" }, { "id": "decorator", "label": "Decorator", "group": "Structural" }, { "id": "facade", "label": "Facade", "group": "Structural" }, { "id": "flyweight", "label": "Flyweight", "group": "Structural" }, { "id": "proxy", "label": "Proxy", "group": "Structural" }, { "id": "chain-of-responsibility", "label": "Chain of Responsibility", "group": "Behavioral" }, { "id": "command", "label": "Command", "group": "Behavioral" }, { "id": "interpreter", "label": "Interpreter", "group": "Behavioral" }, { "id": "iterator", "label": "Iterator", "group": "Behavioral" }, { "id": "mediator", "label": "Mediator", "group": "Behavioral" }, { "id": "memento", "label": "Memento", "group": "Behavioral" }, { "id": "observer", "label": "Observer", "group": "Behavioral" }, { "id": "state", "label": "State", "group": "Behavioral" }, { "id": "strategy", "label": "Strategy", "group": "Behavioral" }, { "id": "template-method", "label": "Template Method", "group": "Behavioral" }, { "id": "visitor", "label": "Visitor", "group": "Behavioral" }, { "id": "ports-and-adapters", "label": "Ports and Adapters", "group": "Architectural" }, { "id": "cqrs", "label": "CQRS", "group": "Architectural" }, { "id": "strangler-fig", "label": "Strangler Fig", "group": "Architectural" }, { "id": "saga", "label": "Saga", "group": "Distributed and reliability" }, { "id": "transactional-outbox", "label": "Transactional Outbox", "group": "Distributed and reliability" }, { "id": "circuit-breaker", "label": "Circuit Breaker", "group": "Distributed and reliability" }, { "id": "bulkhead", "label": "Bulkhead", "group": "Distributed and reliability" } ], "projects": [ { "id": "f1a43d6a-7c9b-4238-9fdd-c8584780644a", "key": "BINCIDENT", "title": "Queue backlog incident response", "field": "Site reliability", "summary": "Diagnose and recover delayed background work without duplicating effects.", "context": "A fictional document service has a rising processing backlog. Operators cannot tell whether arrivals, worker failures, or a slow dependency is responsible.", "stack": [ "TypeScript", "BullMQ", "Redis" ], "prerequisites": [ "Create a bounded local queue simulation with synthetic jobs and controllable worker/dependency failures." ], "developerValue": "Practice incident timelines, queue diagnosis, and measured recovery.", "companyValue": "Produce a repeatable response that preserves work integrity and exposes customer delay.", "delivery": "Deliver local incident instrumentation, recovery controls, and a tabletop report.", "phases": [ { "id": "observe", "title": "Observe backlog", "goal": "Separate queue age, throughput, and failure symptoms." }, { "id": "contain", "title": "Contain safely", "goal": "Control arrivals and retries while preserving job identity." }, { "id": "recover", "title": "Recover and learn", "goal": "Drain work and validate recovery decisions." } ], "tickets": [ { "id": "132f5f91-367b-419e-9187-8c0346612078", "key": "BINCIDENT-101", "title": "Report oldest eligible job age alongside queue depth", "type": "TASK", "priority": "MEDIUM", "difficulty": "FOUNDATIONAL", "estimateMinutes": 60, "phaseId": "observe", "dependsOn": [], "scenario": "A shallow queue can still contain a single customer job stuck for hours.", "acceptanceCriteria": [ "Measure oldest eligible age separately from count.", "Exclude scheduled future work from overdue age.", "Show missing timestamp records explicitly." ], "implementationNotes": [ "Use bounded job-type labels only." ], "verification": [ "Measure a known delayed fixture.", "Keep future-scheduled jobs out of overdue calculations." ], "deliverables": [ "Backlog age metric." ], "rollout": "Add read-only metrics before changing worker behavior.", "skills": [ "Queue observability" ], "fieldMix": [ { "field": "Site reliability", "percentage": 80 }, { "field": "Platform engineering", "percentage": 20 } ], "patterns": [] }, { "id": "3e4b7de0-a6a4-4786-9248-2a5a42215167", "key": "BINCIDENT-102", "title": "Separate arrival rate from successful service rate", "type": "TASK", "priority": "MEDIUM", "difficulty": "INTERMEDIATE", "estimateMinutes": 120, "phaseId": "observe", "dependsOn": [ "BINCIDENT-101" ], "scenario": "The dashboard counts retries as new incoming customer work.", "acceptanceCriteria": [ "Track logical arrivals, attempts, and completions separately.", "Use consistent measurement windows.", "Expose worker concurrency with throughput." ], "implementationNotes": [ "Do not infer capacity from a single peak sample." ], "verification": [ "Reconcile a fixture with repeated attempts.", "Detect growing backlog despite high attempt throughput." ], "deliverables": [ "Queue flow dashboard." ], "rollout": "Compare against synthetic queue inventory before relying on alerts.", "skills": [ "Metrics", "Capacity analysis" ], "fieldMix": [ { "field": "Site reliability", "percentage": 60 }, { "field": "Performance engineering", "percentage": 40 } ], "patterns": [] }, { "id": "94197340-77d5-486a-a40c-0ef9de7bcfcf", "key": "BINCIDENT-103", "title": "Identify poison jobs without starving unrelated work", "type": "BUG", "priority": "HIGH", "difficulty": "ADVANCED", "estimateMinutes": 180, "phaseId": "contain", "dependsOn": [ "BINCIDENT-102" ], "scenario": "One malformed document repeatedly consumes the first worker slot.", "acceptanceCriteria": [ "Bound attempts by failure category.", "Move exhausted jobs to an inspectable terminal holding state.", "Allow unrelated valid jobs to continue." ], "implementationNotes": [ "Keep payload contents out of generic incident logs." ], "verification": [ "Quarantine a deterministic poison job.", "Process a valid neighboring job and preserve its identity." ], "deliverables": [ "Poison-job containment." ], "rollout": "Enable per job type; retain held work for reviewed correction.", "skills": [ "Retries", "Queue design" ], "fieldMix": [ { "field": "Platform engineering", "percentage": 60 }, { "field": "Site reliability", "percentage": 40 } ], "patterns": [] }, { "id": "bed818de-b4ef-4677-8183-ff690a51ba12", "key": "BINCIDENT-104", "title": "Pause selected producers while preserving accepted work", "type": "TASK", "priority": "HIGH", "difficulty": "ADVANCED", "estimateMinutes": 180, "phaseId": "contain", "dependsOn": [ "BINCIDENT-102" ], "scenario": "Operators stop every producer even though only one import path overloads the queue.", "acceptanceCriteria": [ "Scope pause controls to declared producer classes.", "Reject new work with explicit retry guidance.", "Preserve previously accepted job records." ], "implementationNotes": [ "Privileged pause changes require an audit entry." ], "verification": [ "Pause the synthetic import producer.", "Verify another producer works and unauthorized pause is denied." ], "deliverables": [ "Scoped admission control." ], "rollout": "Start with one producer switch; restore intake gradually after backlog age recovers.", "skills": [ "Admission control", "Authorization" ], "fieldMix": [ { "field": "Site reliability", "percentage": 50 }, { "field": "Platform engineering", "percentage": 30 }, { "field": "Security", "percentage": 20 } ], "patterns": [] }, { "id": "3f380235-9c75-4802-8726-3a31c66fe0fa", "key": "BINCIDENT-105", "title": "Recover expired worker leases without concurrent duplicate effects", "type": "BUG", "priority": "HIGH", "difficulty": "ADVANCED", "estimateMinutes": 210, "phaseId": "contain", "dependsOn": [ "BINCIDENT-103" ], "scenario": "A worker crashes after producing output but before acknowledging completion.", "acceptanceCriteria": [ "Use stable job operation identity.", "Reclaim only expired ownership.", "Adopt existing completed output before repeating effects." ], "implementationNotes": [ "Mock effects must be idempotent and locally scoped." ], "verification": [ "Crash after effect acceptance and reclaim.", "Race two reclaimers and observe one terminal outcome." ], "deliverables": [ "Lease recovery behavior." ], "rollout": "Reclaim in bounded batches; stop on conflicting output identities.", "skills": [ "Leases", "Idempotency" ], "fieldMix": [ { "field": "Distributed systems", "percentage": 50 }, { "field": "Platform engineering", "percentage": 30 }, { "field": "Site reliability", "percentage": 20 } ], "patterns": [] }, { "id": "e9de9fc1-cff1-433c-8989-3db9130ff37f", "key": "BINCIDENT-106", "title": "Tune retry delay for a throttled dependency", "type": "TASK", "priority": "HIGH", "difficulty": "INTERMEDIATE", "estimateMinutes": 150, "phaseId": "contain", "dependsOn": [ "BINCIDENT-103", "BINCIDENT-104" ], "scenario": "Immediate retries amplify the dependency's temporary throttling.", "acceptanceCriteria": [ "Respect bounded retry-after guidance.", "Apply jitter with reproducible test control.", "Cap total attempts and elapsed time." ], "implementationNotes": [ "Never retry permanent validation or authorization failures." ], "verification": [ "Recover after a temporary throttle.", "Exhaust a persistent outage without a retry storm." ], "deliverables": [ "Dependency retry policy." ], "rollout": "Trial on one job class; pause dispatch if throttling remains sustained.", "skills": [ "Backoff", "Resilience" ], "fieldMix": [ { "field": "Site reliability", "percentage": 60 }, { "field": "Integrations", "percentage": 40 } ], "patterns": [] }, { "id": "5e3e5a35-2214-4c97-b5f2-a20ff4972b7f", "key": "BINCIDENT-107", "title": "Estimate backlog drain time under explicit capacity assumptions", "type": "TASK", "priority": "MEDIUM", "difficulty": "ADVANCED", "estimateMinutes": 180, "phaseId": "recover", "dependsOn": [ "BINCIDENT-102", "BINCIDENT-106" ], "scenario": "Support promises a completion time using queue depth divided by the busiest worker's speed.", "acceptanceCriteria": [ "Use measured successful service and arrival rates.", "Report assumptions and uncertainty bounds.", "Return no finite estimate when arrivals meet or exceed service." ], "implementationNotes": [ "Use synthetic measurements and avoid general capacity claims." ], "verification": [ "Estimate a controlled draining workload.", "Show an unstable workload as non-draining." ], "deliverables": [ "Drain-time estimator." ], "rollout": "Publish estimates with their observation window; retract stale estimates.", "skills": [ "Queueing", "Capacity planning" ], "fieldMix": [ { "field": "Performance engineering", "percentage": 60 }, { "field": "Site reliability", "percentage": 40 } ], "patterns": [] }, { "id": "bf808a7a-5d59-4411-968a-e212a1d66b4c", "key": "BINCIDENT-108", "title": "Rehearse backlog recovery with a constrained worker budget", "type": "TASK", "priority": "HIGH", "difficulty": "EXPERT", "estimateMinutes": 300, "phaseId": "recover", "dependsOn": [ "BINCIDENT-104", "BINCIDENT-105", "BINCIDENT-107" ], "scenario": "Adding workers may increase database contention and make recovery slower.", "acceptanceCriteria": [ "Compare two bounded concurrency settings under identical arrivals.", "Measure completion age, dependency pressure, and duplicate-effect checks.", "Choose a recovery setting with stated tradeoffs." ], "implementationNotes": [ "Record machine limits; do not extrapolate local capacity to production." ], "verification": [ "Drain the synthetic incident workload.", "Demonstrate a setting that worsens contention or violates limits." ], "deliverables": [ "Recovery experiment report." ], "rollout": "Raise concurrency in measured steps; revert when dependency or integrity thresholds fail.", "skills": [ "Performance experiments", "Incident response" ], "fieldMix": [ { "field": "Performance engineering", "percentage": 60 }, { "field": "Site reliability", "percentage": 40 } ], "patterns": [] }, { "id": "ba55f9ec-cb8f-48ef-abad-0c468c0fc0c5", "key": "BINCIDENT-109", "title": "Create an incident timeline from control and queue events", "type": "STORY", "priority": "MEDIUM", "difficulty": "INTERMEDIATE", "estimateMinutes": 120, "phaseId": "recover", "dependsOn": [ "BINCIDENT-108" ], "scenario": "The post-incident discussion relies on memory of when pauses and retries changed.", "acceptanceCriteria": [ "Record control actions with actor and UTC time.", "Link changes to observed backlog metrics.", "Separate observations from causal hypotheses." ], "implementationNotes": [ "Exclude customer payloads and personal operator commentary." ], "verification": [ "Reconstruct the synthetic incident.", "Show a missing observation as a gap rather than inventing timing." ], "deliverables": [ "Incident timeline exporter." ], "rollout": "Preserve original event records; append corrections to the timeline.", "skills": [ "Auditability", "Incident analysis" ], "fieldMix": [ { "field": "Site reliability", "percentage": 80 }, { "field": "Data engineering", "percentage": 20 } ], "patterns": [] }, { "id": "95ee50ea-fc4b-4fbe-bc39-42b52dcfad77", "key": "BINCIDENT-110", "title": "Write a queue handoff with explicit resume conditions", "type": "CHORE", "priority": "LOW", "difficulty": "FOUNDATIONAL", "estimateMinutes": 60, "phaseId": "recover", "dependsOn": [ "BINCIDENT-109" ], "scenario": "The next on-call engineer inherits paused intake without knowing when to reopen it.", "acceptanceCriteria": [ "List active controls and held job counts.", "Specify measurable intake-resume conditions.", "Document safe rollback of each temporary control." ], "implementationNotes": [ "Commands target the local incident fixture only." ], "verification": [ "Resume intake using the handoff.", "Keep intake paused when dependency health remains unknown." ], "deliverables": [ "On-call handoff runbook." ], "rollout": "Require a handoff whenever containment outlives the current operator.", "skills": [ "Runbooks" ], "fieldMix": [ { "field": "Site reliability", "percentage": 100 } ], "patterns": [] } ] } ] }