{ "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": "4cbe8d74-12ed-43d2-9bca-6503851d91a7", "key": "QUEUE", "title": "Bring document processing back under control", "field": "Platform engineering", "summary": "Operate an asynchronous document pipeline through retries, poison jobs, worker loss, and tenant bursts.", "context": "A fictional internal document portal creates previews through a trusted mock renderer. Large batches crowd out small teams, failed documents retry forever, and operators lack a safe replay command. This exercise never executes uploaded code or real document macros.", "stack": [ "TypeScript", "BullMQ", "Redis", "PostgreSQL", "Object storage" ], "prerequisites": [ "Queue semantics", "Database transactions", "Operational metrics" ], "developerValue": "Practice asynchronous lifecycle control, fair scheduling, bounded retries, and artifact recovery with a deterministic provider.", "companyValue": "See how an engineer accounts for accepted work and reduces operational toil without granting operators broad data access.", "delivery": "Ten tickets in intake, resilience, and operations phases; use only synthetic document metadata and a trusted deterministic renderer.", "phases": [ { "id": "intake", "title": "Account for accepted work", "goal": "Create traceable jobs with bounded inputs." }, { "id": "resilience", "title": "Handle failures deliberately", "goal": "Control retries, concurrency, cancellation, and worker loss." }, { "id": "operations", "title": "Make recovery routine", "goal": "Expose useful lag signals and safe repair operations." } ], "tickets": [ { "id": "430c0420-821f-4e1a-86a5-38b5c0a1a9e0", "key": "QUEUE-101", "title": "Expose a document job's current phase and terminal reason", "type": "STORY", "priority": "MEDIUM", "difficulty": "FOUNDATIONAL", "estimateMinutes": 90, "phaseId": "intake", "dependsOn": [], "scenario": "The portal shows Processing for both queued and permanently rejected documents. Support cannot tell whether a file is waiting, rendering, or never going to finish.", "acceptanceCriteria": [ "Expose QUEUED, RUNNING, SUCCEEDED, FAILED, and CANCELLED through an allowlisted projection.", "Include a stable terminal reason code and last transition time.", "Deny jobs owned by another tenant." ], "implementationNotes": [ "Only service transition methods may update lifecycle state; logs are not the source of truth." ], "verification": [ "Read queued and failed fixture jobs with distinct explanations.", "Reject foreign-tenant lookup and ensure renderer payloads are absent." ], "deliverables": [ "Job status contract and authorized read endpoint" ], "rollout": "Switch status reads for synthetic jobs first; retain historical transition records if the view is reverted.", "skills": [ "State projection", "Tenant isolation", "API design" ], "fieldMix": [ { "field": "API design", "percentage": 40 }, { "field": "Platform engineering", "percentage": 30 }, { "field": "Backend", "percentage": 30 } ], "patterns": [] }, { "id": "371a4f08-25c9-43c8-bac3-e6e1dddbde08", "key": "QUEUE-102", "title": "Reject oversized document batches before accepting work", "type": "TASK", "priority": "HIGH", "difficulty": "FOUNDATIONAL", "estimateMinutes": 90, "phaseId": "intake", "dependsOn": [], "scenario": "A client submits 50,000 document references in one call. Validation exhausts API memory before the queue sees a single job.", "acceptanceCriteria": [ "Enforce a documented request byte limit and a maximum of 100 document references.", "Reject duplicate references within the batch with a clear validation reason.", "Create no jobs when batch validation fails." ], "implementationNotes": [ "Validate metadata only; the API must not download or render document contents." ], "verification": [ "Accept a valid 100-reference synthetic batch.", "Reject 101 references, excessive bytes, and duplicate references without partial jobs." ], "deliverables": [ "Bounded batch contract and boundary cases" ], "rollout": "Publish limits before enforcing them on the test client; rollback client batching rather than raising limits without measurement.", "skills": [ "Input limits", "Resource bounds", "Contract testing" ], "fieldMix": [ { "field": "Platform engineering", "percentage": 50 }, { "field": "Performance engineering", "percentage": 30 }, { "field": "API design", "percentage": 20 } ], "patterns": [] }, { "id": "fa3b1d74-b9f5-4d75-8357-4d4523e8539f", "key": "QUEUE-103", "title": "Commit job acceptance and dispatch intent together", "type": "BUG", "priority": "HIGH", "difficulty": "ADVANCED", "estimateMinutes": 210, "phaseId": "intake", "dependsOn": [ "QUEUE-101", "QUEUE-102" ], "scenario": "The portal returns 202 after storing a job, then loses Redis connectivity before enqueueing it. The job stays QUEUED forever with no delivery attempt.", "acceptanceCriteria": [ "Commit accepted job records and durable dispatch intents atomically.", "Dispatch retries use deterministic job identities.", "A failed database transaction cannot return accepted status." ], "implementationNotes": [ "Queue messages contain identifiers and bounded metadata, not document bytes." ], "verification": [ "Lose Redis after acceptance and recover every job when dispatch resumes.", "Fail the database commit and assert neither job nor dispatch intent exists." ], "deliverables": [ "Outbox-backed acceptance and recovery reproduction" ], "rollout": "Drain synthetic pending intents through the new dispatcher; pause dispatch without deleting accepted work to rollback.", "skills": [ "Transactional outbox", "Durable acceptance", "Idempotency" ], "fieldMix": [ { "field": "Distributed systems", "percentage": 40 }, { "field": "Database engineering", "percentage": 30 }, { "field": "Platform engineering", "percentage": 30 } ], "patterns": [ { "pattern": "transactional-outbox", "activity": "APPLY", "focus": "Commit acceptance and dispatch intent in one transaction, then demonstrate recovery after the queue is unavailable or the process stops before dispatch." } ] }, { "id": "e3cb7c2c-1160-4aed-9af8-3df3c25fb6d1", "key": "QUEUE-104", "title": "Stop retrying unsupported document formats", "type": "BUG", "priority": "HIGH", "difficulty": "INTERMEDIATE", "estimateMinutes": 150, "phaseId": "resilience", "dependsOn": [ "QUEUE-103" ], "scenario": "The trusted mock renderer returns UNSUPPORTED_FORMAT for a fixture file. The worker retries it every minute, consuming the same capacity as a temporary storage timeout.", "acceptanceCriteria": [ "Classify unsupported format as terminal and storage timeout as retryable.", "Apply a bounded attempt count and backoff policy to retryable failures.", "Record each attempt and the final exhaustion reason without replacing earlier failures." ], "implementationNotes": [ "Unknown provider errors need an explicit conservative policy; do not retry forever." ], "verification": [ "Retry a transient failure that succeeds on its third attempt.", "Verify unsupported format runs once and persistent timeout reaches a bounded terminal state." ], "deliverables": [ "Failure classification table and retry policy" ], "rollout": "Apply new classification to future attempts; stop scheduling exhausted jobs without erasing their attempt history.", "skills": [ "Retry policy", "Error taxonomy", "Failure budgets" ], "fieldMix": [ { "field": "Platform engineering", "percentage": 60 }, { "field": "Site reliability", "percentage": 40 } ], "patterns": [] }, { "id": "ef2da24e-e945-4621-beb0-1d580d78bb6f", "key": "QUEUE-105", "title": "Keep one team's bulk import from occupying every worker", "type": "STORY", "priority": "HIGH", "difficulty": "ADVANCED", "estimateMinutes": 240, "phaseId": "resilience", "dependsOn": [ "QUEUE-103", "QUEUE-104" ], "scenario": "A synthetic tenant uploads 10,000 documents. A second tenant's single preview waits behind the entire batch although the renderer has spare concurrency slots between completions.", "acceptanceCriteria": [ "Enforce configured global and per-tenant active-job limits.", "Allow eligible tenants to make progress while a bulk tenant has backlog.", "Release capacity after success, terminal failure, cancellation, or expired execution lease." ], "implementationNotes": [ "Do not create an unbounded queue or metric family per tenant; explain the fairness policy." ], "verification": [ "Run one bulk tenant and two small tenants and measure their wait times.", "Crash a worker while holding capacity and prove another eligible tenant eventually progresses." ], "deliverables": [ "Fair dispatch policy and controlled-load report" ], "rollout": "Start with conservative synthetic limits; disable new intake and drain leases if accounting diverges.", "skills": [ "Fair scheduling", "Concurrency limits", "Capacity accounting" ], "fieldMix": [ { "field": "Platform engineering", "percentage": 50 }, { "field": "Performance engineering", "percentage": 30 }, { "field": "Distributed systems", "percentage": 20 } ], "patterns": [] }, { "id": "04530a6b-1191-4a5e-b627-b75324118e3f", "key": "QUEUE-106", "title": "Fence a late worker after its rendering lease expires", "type": "BUG", "priority": "HIGH", "difficulty": "EXPERT", "estimateMinutes": 300, "phaseId": "resilience", "dependsOn": [ "QUEUE-104", "QUEUE-105" ], "scenario": "Worker A pauses long enough to lose its lease. Worker B completes the same preview, then A resumes and overwrites B's artifact pointer with stale output.", "acceptanceCriteria": [ "Associate each execution attempt with a monotonic fencing identity.", "Accept completion only from the current authorized lease holder.", "Keep rejected late completions observable and prevent them from changing terminal job state." ], "implementationNotes": [ "Lease expiration alone does not stop a process; the persistence boundary must reject stale writes." ], "verification": [ "Expire A, complete through B, then submit A's completion and inspect unchanged output.", "Replay B's completion and assert one terminal transition and artifact reference." ], "deliverables": [ "Fenced completion operation and paused-worker reproduction" ], "rollout": "Introduce fencing before extending concurrency; rollback dispatch while retaining fencing checks on completions.", "skills": [ "Fencing tokens", "Worker leases", "Concurrency", "Artifact consistency" ], "fieldMix": [ { "field": "Distributed systems", "percentage": 60 }, { "field": "Platform engineering", "percentage": 40 } ], "patterns": [] }, { "id": "6502461a-e612-4d91-9fa6-cf8134370266", "key": "QUEUE-107", "title": "Cancel queued work without racing a completed preview", "type": "STORY", "priority": "MEDIUM", "difficulty": "ADVANCED", "estimateMinutes": 180, "phaseId": "resilience", "dependsOn": [ "QUEUE-106" ], "scenario": "A user cancels a batch just as one preview finishes. The portal reports Cancelled while retaining an accessible success artifact, and a retry renders it again.", "acceptanceCriteria": [ "Make cancellation an authorized state transition with documented running-job semantics.", "Resolve cancellation and completion races to one terminal result.", "Prevent cancelled jobs from being newly dispatched or retried." ], "implementationNotes": [ "For the mock renderer, cancellation can be cooperative; disclose work that cannot stop immediately." ], "verification": [ "Cancel queued work and prove the renderer is never called.", "Race running completion and cancellation, then replay both commands and inspect stable state." ], "deliverables": [ "Cancellation contract and race regression" ], "rollout": "Enable queued cancellation first, then running cancellation after the race cases pass; retain terminal records on rollback.", "skills": [ "Cancellation", "State transitions", "Race handling" ], "fieldMix": [ { "field": "Backend", "percentage": 50 }, { "field": "Platform engineering", "percentage": 30 }, { "field": "Distributed systems", "percentage": 20 } ], "patterns": [] }, { "id": "50c5f8de-f4b3-4723-b536-69305c0b8e70", "key": "QUEUE-108", "title": "Measure oldest runnable work instead of queue size alone", "type": "CHORE", "priority": "MEDIUM", "difficulty": "INTERMEDIATE", "estimateMinutes": 120, "phaseId": "operations", "dependsOn": [ "QUEUE-104", "QUEUE-105" ], "scenario": "The queue contains only ten jobs, but the oldest eligible preview has waited 40 minutes. A queue-depth alert never fires, while scheduled retries inflate another dashboard.", "acceptanceCriteria": [ "Measure oldest eligible-job age separately from delayed retries and running age.", "Expose attempt exhaustion and stale-lease counts with bounded labels.", "Alert when eligible wait exceeds the fixture's ten-minute budget for two observations." ], "implementationNotes": [ "Exclude document IDs and tenant IDs from metric label sets." ], "verification": [ "Advance a controlled clock and trigger runnable-age paging.", "Keep a future retry delayed and verify it does not inflate eligible wait." ], "deliverables": [ "Queue age metrics and diagnosis-oriented alert" ], "rollout": "Compare alerts with the synthetic workload trace in report-only mode before paging.", "skills": [ "Queue observability", "Metric semantics", "Alert design" ], "fieldMix": [ { "field": "Site reliability", "percentage": 70 }, { "field": "Platform engineering", "percentage": 30 } ], "patterns": [] }, { "id": "c9a69594-abdc-4f09-8121-2b43536a302a", "key": "QUEUE-109", "title": "Replay a failed preview through an audited repair command", "type": "TASK", "priority": "HIGH", "difficulty": "INTERMEDIATE", "estimateMinutes": 150, "phaseId": "operations", "dependsOn": [ "QUEUE-104", "QUEUE-106" ], "scenario": "Operators repair failed jobs by deleting Redis keys. That loses failure history and can replay work for the wrong tenant when a copied ID is mistaken.", "acceptanceCriteria": [ "Allow an authorized operator to create a linked repair attempt for a terminal failure.", "Require tenant scope, expected job revision, and a reason.", "Preserve original failure history and make duplicate repair requests idempotent." ], "implementationNotes": [ "Do not reopen the failed record in place or expose a general queue-management console." ], "verification": [ "Repair one terminal fixture failure and follow the linked attempts.", "Reject a foreign tenant, stale revision, and repair of a successful job." ], "deliverables": [ "Scoped repair command and audit projection" ], "rollout": "Grant repair permission to a synthetic operator role; revoke command access while retaining read-only audit history.", "skills": [ "Operational APIs", "Audit trails", "Least privilege" ], "fieldMix": [ { "field": "Platform engineering", "percentage": 40 }, { "field": "Backend", "percentage": 30 }, { "field": "Security", "percentage": 30 } ], "patterns": [] }, { "id": "ca2316a5-d93a-4bd0-849b-ad157c8a0d63", "key": "QUEUE-110", "title": "Collect orphaned preview artifacts without deleting live output", "type": "TASK", "priority": "MEDIUM", "difficulty": "ADVANCED", "estimateMinutes": 210, "phaseId": "operations", "dependsOn": [ "QUEUE-106", "QUEUE-107", "QUEUE-109" ], "scenario": "A worker writes an artifact then loses its lease before committing the pointer. Storage grows with orphaned previews, but a naive age-based cleanup can delete an output still being committed.", "acceptanceCriteria": [ "Separate temporary attempt artifacts from committed output references.", "Delete only unreferenced artifacts beyond a documented grace period with no active lease.", "Make cleanup resumable and record bounded deletion outcomes." ], "implementationNotes": [ "Use synthetic objects; an artifact listing alone cannot prove an object is unreferenced." ], "verification": [ "Collect an abandoned attempt artifact after its grace period.", "Race cleanup with a valid completion and prove committed output survives." ], "deliverables": [ "Orphan collector, race fixture, and dry-run manifest" ], "rollout": "Review deletion manifests in dry-run mode, then enable cleanup for the synthetic storage prefix only.", "skills": [ "Object lifecycle", "Garbage collection", "Race prevention", "Recovery" ], "fieldMix": [ { "field": "Storage systems", "percentage": 50 }, { "field": "Platform engineering", "percentage": 30 }, { "field": "Distributed systems", "percentage": 20 } ], "patterns": [] } ] } ] }