{ "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": "bfc97100-c9a8-4478-a42d-c6ce2bc2c384", "key": "AINGEST", "title": "Recover a partner telemetry ingestion pipeline", "field": "Data engineering", "summary": "Ingest compressed telemetry with explicit quarantine, lineage and replay.", "context": "A fictional energy dashboard receives hourly device batches. Corrupt archives and late corrections leave operators unsure which readings reached reports.", "stack": [ "Python", "PostgreSQL", "Object storage" ], "prerequisites": [ "Create synthetic device batches and local object-store fixtures.", "Understand checksums and bounded streaming." ], "developerValue": "Practice batch integrity, replay and data-quality boundaries.", "companyValue": "Review whether operational data can be traced, corrected and recovered.", "delivery": "Ten scoped tickets across three phases. Build a synthetic local service or select a ticket after recreating its prerequisites; estimates exclude setup.", "phases": [ { "id": "input", "title": "Validate batch boundaries", "goal": "Reject unsafe or ambiguous inputs before loading." }, { "id": "load", "title": "Load traceable records", "goal": "Preserve lineage and deterministic corrections." }, { "id": "recover", "title": "Recover ingestion gaps", "goal": "Reconcile committed batches and repair derived data." } ], "tickets": [ { "id": "dbe4c1e7-0a39-4017-aa04-855a89b29bf0", "key": "AINGEST-101", "title": "Record a manifest before decoding a telemetry batch", "type": "TASK", "priority": "MEDIUM", "difficulty": "FOUNDATIONAL", "estimateMinutes": 90, "phaseId": "input", "dependsOn": [], "scenario": "Operators see a failed file name but cannot identify the original bytes or the parser version used.", "acceptanceCriteria": [ "Record object version, byte hash and declared format.", "Bind each ingestion attempt to one manifest.", "Reject a changed object version on retry." ], "implementationNotes": [ "Use synthetic object metadata; avoid storing credentials in manifests." ], "verification": [ "Retry unchanged bytes against the same manifest.", "Replace bytes under the same object key and report identity mismatch." ], "deliverables": [ "Manifest schema and identity checks" ], "rollout": "Start manifests for new batches; retain earlier records as explicitly untracked.", "skills": [ "Lineage", "Checksums" ], "fieldMix": [ { "field": "Data engineering", "percentage": 60 }, { "field": "Storage systems", "percentage": 40 } ], "patterns": [] }, { "id": "1c4b8c6f-0a9e-49a6-a018-47666eb210a7", "key": "AINGEST-102", "title": "Cap decompressed telemetry bytes before archive expansion", "type": "BUG", "priority": "HIGH", "difficulty": "ADVANCED", "estimateMinutes": 180, "phaseId": "input", "dependsOn": [ "AINGEST-101" ], "scenario": "A tiny compressed batch expands far beyond the ingestion worker's memory budget.", "acceptanceCriteria": [ "Enforce compressed, expanded-byte and row limits.", "Stop streaming as soon as a bound is crossed.", "Quarantine with a reason without loading partial rows." ], "implementationNotes": [ "Do not unpack paths or execute files from archives." ], "verification": [ "Ingest a valid compressed synthetic batch.", "Exercise excessive expansion and path-like entry names without writing outside staging." ], "deliverables": [ "Bounded decoder and hostile archive fixtures" ], "rollout": "Enable bounded decoding before partner intake; keep rejected objects quarantined.", "skills": [ "Streaming", "Resource limits" ], "fieldMix": [ { "field": "Data engineering", "percentage": 40 }, { "field": "Performance engineering", "percentage": 30 }, { "field": "Security", "percentage": 30 } ], "patterns": [] }, { "id": "b5b1edec-a484-4f3b-bb4d-004abc509f0f", "key": "AINGEST-103", "title": "Normalize sensor units through a versioned conversion table", "type": "TASK", "priority": "MEDIUM", "difficulty": "INTERMEDIATE", "estimateMinutes": 150, "phaseId": "input", "dependsOn": [ "AINGEST-101" ], "scenario": "Two device models emit watt-hours and kilowatt-hours under the same field name.", "acceptanceCriteria": [ "Require a known unit and conversion version.", "Preserve raw numeric value and declared unit in lineage.", "Reject unsupported units and nonfinite measurements." ], "implementationNotes": [ "Use decimal arithmetic for documented conversions." ], "verification": [ "Convert synthetic Wh and kWh to equal canonical readings.", "Reject missing units and nonfinite input." ], "deliverables": [ "Unit conversion contract and cases" ], "rollout": "Publish conversion revisions for new runs; retain old mappings for replay.", "skills": [ "Data normalization", "Versioning" ], "fieldMix": [ { "field": "Data engineering", "percentage": 100 } ], "patterns": [] }, { "id": "8e01b627-5d45-47c7-95c0-883ccd390b12", "key": "AINGEST-104", "title": "Commit telemetry rows and the batch checkpoint atomically", "type": "STORY", "priority": "HIGH", "difficulty": "ADVANCED", "estimateMinutes": 240, "phaseId": "load", "dependsOn": [ "AINGEST-102", "AINGEST-103" ], "scenario": "A process dies after inserting rows but before marking the file complete; replay doubles reported usage.", "acceptanceCriteria": [ "Persist rows and committed checkpoint in one transaction.", "Use source reading identity to reject duplicate insertion.", "Retries return committed counts without adding readings." ], "implementationNotes": [ "Bound transaction size; larger batches require explicit sub-batch identities." ], "verification": [ "Kill the test process at modeled commit boundaries.", "Replay a completed sub-batch and compare row counts and totals." ], "deliverables": [ "Atomic batch loader and crash probe" ], "rollout": "Canary small batches; pause loading and inspect manifests if reconciliation diverges.", "skills": [ "Transactions", "Idempotency" ], "fieldMix": [ { "field": "Data engineering", "percentage": 50 }, { "field": "Database engineering", "percentage": 50 } ], "patterns": [] }, { "id": "9672c565-9395-4de8-be20-67bf9e01d74d", "key": "AINGEST-105", "title": "Quarantine malformed readings with usable row coordinates", "type": "STORY", "priority": "MEDIUM", "difficulty": "FOUNDATIONAL", "estimateMinutes": 90, "phaseId": "load", "dependsOn": [ "AINGEST-102", "AINGEST-103" ], "scenario": "A malformed timestamp makes the ingestion job fail with a stack trace and no indication of the source row.", "acceptanceCriteria": [ "Report manifest ID, row number and stable reason code.", "Keep rejected values out of generic logs.", "Publish accepted and rejected counts under the declared partial-load policy." ], "implementationNotes": [ "Choose and document all-or-nothing versus row quarantine for this dataset." ], "verification": [ "Load a batch containing valid rows under the chosen policy.", "Insert malformed timestamps and verify coordinates and count invariants." ], "deliverables": [ "Quarantine report and policy tests" ], "rollout": "Enable reports before changing load policy; replay corrected manifests as new attempts.", "skills": [ "Data quality", "Error reporting" ], "fieldMix": [ { "field": "Data engineering", "percentage": 100 } ], "patterns": [] }, { "id": "28a89991-18da-45dd-adf5-cb036ab83a8c", "key": "AINGEST-106", "title": "Apply corrected readings without overwriting source history", "type": "STORY", "priority": "MEDIUM", "difficulty": "EXPERT", "estimateMinutes": 300, "phaseId": "load", "dependsOn": [ "AINGEST-104", "AINGEST-105" ], "scenario": "A device sends a corrected cumulative reading two days late; a blind upsert destroys the value used in yesterday's report.", "acceptanceCriteria": [ "Append corrections linked to source reading and revision.", "Define the effective reading deterministically.", "Reject contradictory equal-revision corrections for review." ], "implementationNotes": [ "Preserve original ingestion time separately from measurement time." ], "verification": [ "Apply a higher revision and inspect both historical values.", "Submit equal revision with changed value and retain the last valid projection." ], "deliverables": [ "Correction model and conflict cases" ], "rollout": "Enable corrections for one synthetic device; rebuild projections from retained history on rollback.", "skills": [ "Temporal data", "Append-only design" ], "fieldMix": [ { "field": "Data engineering", "percentage": 70 }, { "field": "Database engineering", "percentage": 30 } ], "patterns": [] }, { "id": "888265ca-96f7-436b-9a1d-ccd6c538ecd4", "key": "AINGEST-107", "title": "Use event-time watermarks without discarding late telemetry silently", "type": "TASK", "priority": "MEDIUM", "difficulty": "ADVANCED", "estimateMinutes": 210, "phaseId": "load", "dependsOn": [ "AINGEST-106" ], "scenario": "The hourly aggregate closes by arrival time and quietly ignores a delayed batch from an offline device.", "acceptanceCriteria": [ "Define watermark advancement and allowed lateness.", "Route late readings to a visible correction path.", "Report aggregate revision when late data changes a result." ], "implementationNotes": [ "Test with a controlled clock and explicit event timestamps." ], "verification": [ "Deliver an in-window late reading and update the expected aggregate.", "Deliver beyond the lateness window and verify visible deferred correction." ], "deliverables": [ "Watermark logic and late-arrival fixtures" ], "rollout": "Run alongside the prior aggregate; switch readers only after discrepancy review.", "skills": [ "Event time", "Aggregation" ], "fieldMix": [ { "field": "Data engineering", "percentage": 70 }, { "field": "Real-time systems", "percentage": 30 } ], "patterns": [] }, { "id": "b4d16852-2af9-4ddc-805b-c11703ae73cc", "key": "AINGEST-108", "title": "Reconcile uploaded telemetry manifests against committed checkpoints", "type": "CHORE", "priority": "MEDIUM", "difficulty": "INTERMEDIATE", "estimateMinutes": 180, "phaseId": "recover", "dependsOn": [ "AINGEST-104", "AINGEST-107" ], "scenario": "Object storage contains yesterday's batches, but dashboard totals are low and no worker currently owns the missing jobs.", "acceptanceCriteria": [ "List missing, pending and committed manifests by bounded window.", "Schedule replay only for eligible uncommitted identities.", "Make repeated reconciliation produce no duplicate committed data." ], "implementationNotes": [ "Require explicit organization and time bounds." ], "verification": [ "Find a synthetic uploaded batch without a checkpoint.", "Rerun reconciliation after commit and schedule nothing additional." ], "deliverables": [ "Manifest reconciler and bounded replay command" ], "rollout": "Dry-run first; stop replay dispatch while preserving the discrepancy report.", "skills": [ "Reconciliation", "Operations" ], "fieldMix": [ { "field": "Data engineering", "percentage": 50 }, { "field": "Storage systems", "percentage": 30 }, { "field": "Site reliability", "percentage": 20 } ], "patterns": [] }, { "id": "01df221c-4c69-4a4b-9911-f61f1a45f241", "key": "AINGEST-109", "title": "Verify a telemetry backfill against immutable aggregate snapshots", "type": "TASK", "priority": "MEDIUM", "difficulty": "EXPERT", "estimateMinutes": 360, "phaseId": "recover", "dependsOn": [ "AINGEST-106", "AINGEST-107", "AINGEST-108" ], "scenario": "A conversion fix requires rebuilding a week of energy totals without obscuring what the previous dashboard showed.", "acceptanceCriteria": [ "Build a new aggregate generation from named manifests.", "Compare counts, units and totals against frozen previous output.", "Atomically select the generation only after review." ], "implementationNotes": [ "Use a synthetic seven-day corpus with declared correction cases." ], "verification": [ "Backfill the corpus and reconcile every changed aggregate.", "Interrupt before activation and keep previous dashboard reads consistent." ], "deliverables": [ "Backfill runner and generation difference report" ], "rollout": "Activate one synthetic tenant; restore the old generation pointer on discrepancy.", "skills": [ "Backfills", "Data reconciliation" ], "fieldMix": [ { "field": "Data engineering", "percentage": 80 }, { "field": "Database engineering", "percentage": 20 } ], "patterns": [] }, { "id": "fbd82c12-737c-45fa-9646-d863e0dc4d19", "key": "AINGEST-110", "title": "Add an ingestion freshness report that distinguishes missing data from zero", "type": "TASK", "priority": "MEDIUM", "difficulty": "FOUNDATIONAL", "estimateMinutes": 90, "phaseId": "recover", "dependsOn": [ "AINGEST-108", "AINGEST-109" ], "scenario": "A site with no recent readings is displayed as consuming zero energy, misleading dashboard consumers.", "acceptanceCriteria": [ "Show last event time and last committed arrival separately.", "Represent missing intervals as unknown rather than numeric zero.", "Define stale thresholds from a documented expected schedule." ], "implementationNotes": [ "Do not claim zero consumption without a reading." ], "verification": [ "Report a genuine zero reading as zero.", "Remove a scheduled batch and show unknown with stale status." ], "deliverables": [ "Freshness projection and missing-data cases" ], "rollout": "Introduce freshness beside existing totals; revert display wiring while preserving unknown semantics.", "skills": [ "Data semantics", "Observability" ], "fieldMix": [ { "field": "Data engineering", "percentage": 60 }, { "field": "Site reliability", "percentage": 40 } ], "patterns": [] } ] } ] }