apiVersion: devrunbook.io/v1alpha1
kind: Playbook
metadata:
  id: release-operations.health-readiness
  slug: health-readiness
  version: 1.0.0
  title: Implement Health and Readiness Checks
  summary: Add accurate liveness, readiness and dependency health without hiding partial outages.
  category: release-operations
  tags:
  - healthcheck
  - operations
  - reliability
  lifecycle: reviewed
  riskTier: moderate
  authors:
  - name: DevRunbook Core Team
  license: MIT
package:
  files:
  - path: prompt.md
    role: template
    digest: true
    exportByDefault: false
  - path: README.md
    role: documentation
    digest: true
    exportByDefault: false
  - path: CHANGELOG.md
    role: changelog
    digest: true
    exportByDefault: false
  - path: examples/minimal.yaml
    role: example
    digest: true
    exportByDefault: false
  - path: evaluations/static-structure.yaml
    role: evaluation
    digest: true
    exportByDefault: false
spec:
  type: guided
  intent:
    problem: Development work around implement health and readiness checks is often underspecified, inconsistently executed
      or reported without enough evidence.
    outcome: Add accurate liveness, readiness and dependency health without hiding partial outages.
    whenToUse:
    - Use this playbook when the repository needs a bounded implement health and readiness checks task with explicit evidence
      and completion criteria.
    - Use it when Codex should follow a repeatable workflow rather than improvise from a one-line request.
    whenNotToUse:
    - Do not use it when the desired outcome or authority boundaries are still materially undecided.
    - Do not use it to access unavailable production credentials, bypass safeguards or claim validation that cannot be performed.
  modes:
  - guided
  - execute
  - recovery
  defaultMode: execute
  autonomy:
    min: implement
    max: repair
    default: verify
  inputs:
  - key: requiredDependencies
    label: Required dependencies
    description: List dependencies that determine readiness and their failure semantics.
    type: string-list
    required: true
    sensitive: false
    includeInOutput: true
  - key: degradedComponents
    label: Degraded components
    description: List optional components that may fail without making the whole service unready.
    type: string-list
    required: false
    sensitive: false
    includeInOutput: true
    default: []
  compatibility:
    repositoryRequired: true
    languages: []
    frameworks: []
    packageManagers: []
    databases: []
    deploymentTypes: []
    requiredProfileCapabilities: []
    incompatibleConditions: []
  guardrails:
  - id: guardrail-1
    severity: blocking
    text: Keep liveness independent from optional downstream availability.
  - id: guardrail-2
    severity: blocking
    text: Do not expose secrets, topology details or raw dependency errors in public health responses.
  - id: guardrail-3
    severity: blocking
    text: Avoid health checks that create load or mutate external systems.
  workflow:
  - id: classify-dependencies
    title: Classify dependencies
    instruction: Separate process health, required readiness dependencies and optional degraded components.
    required: true
  - id: define-contract
    title: Define endpoint contract
    instruction: Specify status codes, response shape, timeouts, caching and authentication/exposure.
    required: true
  - id: implement-checks
    title: Implement checks
    instruction: Add bounded checks and aggregate them with clear required/degraded semantics.
    required: true
  - id: integrate-runtime
    title: Integrate runtime
    instruction: Configure container healthchecks and startup/shutdown behavior.
    required: true
  - id: add-observability
    title: Add observability
    instruction: Emit safe structured logs and metrics for state transitions.
    required: true
  - id: test-failures
    title: Test failure matrix
    instruction: Simulate required and optional dependency failures and recovery.
    required: true
  - id: document
    title: Document operations
    instruction: Explain how orchestrators and operators should use each endpoint.
    required: true
  validation:
    commandRoles:
    - lint
    - typecheck
    - unit-test
    - integration-test
    - build
    - smoke-test
    checks:
    - id: check-1
      type: assertion
      description: Required dependency failure changes readiness without killing liveness.
      blocking: true
      evidence: Referenced files, command results or explicit review notes.
    - id: check-2
      type: assertion
      description: Optional component failure is visible as degraded according to policy.
      blocking: true
      evidence: Referenced files, command results or explicit review notes.
    - id: command-lint
      type: command
      description: Run the resolved lint command when the repository profile provides it and record the result.
      blocking: true
      evidence: Resolved command, exit status and concise result summary.
    - id: command-typecheck
      type: command
      description: Run the resolved typecheck command when the repository profile provides it and record the result.
      blocking: true
      evidence: Resolved command, exit status and concise result summary.
    - id: command-unit-test
      type: command
      description: Run the resolved unit-test command when the repository profile provides it and record the result.
      blocking: true
      evidence: Resolved command, exit status and concise result summary.
    - id: command-integration-test
      type: command
      description: Run the resolved integration-test command when the repository profile provides it and record the result.
      blocking: true
      evidence: Resolved command, exit status and concise result summary.
    - id: command-build
      type: command
      description: Run the resolved build command when the repository profile provides it and record the result.
      blocking: true
      evidence: Resolved command, exit status and concise result summary.
    - id: command-smoke-test
      type: command
      description: Run the resolved smoke-test command when the repository profile provides it and record the result.
      blocking: true
      evidence: Resolved command, exit status and concise result summary.
  completion:
    criteria:
    - Orchestrator behavior matches documented semantics.
    - Optional integration outages do not misreport total failure.
    - Validation evidence and unresolved limitations are reported honestly.
  failurePolicy:
    onValidationFailure: Investigate failures caused by the current work, repair them when they remain within scope, rerun
      affected validation and report any genuine blocker without claiming success.
    onAmbiguity: Use repository evidence and existing conventions for minor reversible choices. Preserve current behavior
      and stop before any material irreversible decision that the specification does not resolve.
    onMissingContext: Inspect the repository for missing non-sensitive context. Never invent commands, credentials, production
      behavior or validation results; report what remains unavailable.
    onOutOfScopeCause: Explain the evidenced out-of-scope cause, avoid unrelated changes and provide the smallest safe follow-up
      recommendation.
    onExternalDependencyUnavailable: Use an approved local substitute or fixture only when it preserves the behavior under
      test. Otherwise record the blocked validation and do not claim the external path succeeded.
    onUnableToReproduce: Record attempted reproduction, environment and observed evidence. Do not apply speculative production
      changes; provide the narrowest next diagnostic action.
  reporting:
    sections:
    - id: outcome
      title: Outcome
      required: true
      description: State the delivered result or audit conclusion without overstating evidence.
    - id: evidence
      title: Evidence and scope
      required: true
      description: List inspected or changed areas and the evidence supporting the result.
    - id: validation
      title: Validation
      required: true
      description: Report commands, manual checks and their actual outcomes.
    - id: risks
      title: Risks and limitations
      required: true
      description: State residual risk, inaccessible evidence and untested conditions.
    - id: follow-up
      title: Recommended follow-up
      required: true
      description: List the smallest useful next actions or state None.
  template:
    main: prompt.md
    partials: []
  exports:
    prompt: true
    markdown: true
    runPack: false
    agentsSuggestion: false
quality:
  reviewStatus: editorial-reviewed
  testedStacks: []
  knownLimitations:
  - Repository-specific effectiveness depends on the accuracy of the selected profile and the evidence available to Codex.
  evaluationCaseIds:
  - health-readiness.static-structure