DevRunbook-Public/content/playbooks/playwright-critical-flows/playbook.yaml

apiVersion: devrunbook.io/v1alpha1
kind: Playbook
metadata:
  id: testing.playwright-critical-flows
  slug: playwright-critical-flows
  version: 1.0.0
  title: Add Playwright Critical-Flow Tests
  summary: Cover selected end-to-end user journeys with resilient selectors, deterministic setup and useful failure artifacts.
  category: testing
  tags:
  - playwright
  - e2e
  - frontend
  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: run-pack
  intent:
    problem: Development work around add playwright critical-flow tests is often underspecified, inconsistently executed or
      reported without enough evidence.
    outcome: Cover selected end-to-end user journeys with resilient selectors, deterministic setup and useful failure artifacts.
    whenToUse:
    - Use this playbook when the repository needs a bounded add playwright critical-flow tests 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: criticalFlows
    label: Critical flows
    description: List the highest-value user or system flows that must be covered.
    type: string-list
    required: true
    sensitive: false
    includeInOutput: true
  - key: browserTargets
    label: Browser targets
    description: Select the browser engines required for the end-to-end suite.
    type: multiselect
    required: true
    sensitive: false
    includeInOutput: true
    default:
    - chromium
    options:
    - chromium
    - firefox
    - webkit
  compatibility:
    repositoryRequired: true
    languages: []
    frameworks: []
    packageManagers: []
    databases: []
    deploymentTypes: []
    requiredProfileCapabilities:
    - dev-start-command
    incompatibleConditions: []
  guardrails:
  - id: guardrail-1
    severity: blocking
    text: Use resilient user-facing selectors and avoid arbitrary sleep-based timing.
  - id: guardrail-2
    severity: blocking
    text: Do not depend on mutable production data or external services without controlled fixtures.
  - id: guardrail-3
    severity: blocking
    text: Capture traces or screenshots on failure without including secrets or private content.
  workflow:
  - id: map-flows
    title: Map critical flows
    instruction: Define preconditions, roles, test data, success states and failure states for each selected flow.
    required: true
  - id: configure-playwright
    title: Configure Playwright
    instruction: Add compatible browser, base URL, server startup, retries and artifact settings.
    required: true
  - id: build-fixtures
    title: Build test fixtures
    instruction: Create isolated deterministic data setup and teardown that supports parallel or repeated execution.
    required: true
  - id: implement-flows
    title: Implement flow tests
    instruction: Exercise behavior through accessible user interactions and assert meaningful outcomes.
    required: true
  - id: stabilize
    title: Stabilize tests
    instruction: Replace timing assumptions with state-based waits and investigate flakiness through traces.
    required: true
  - id: ci-integration
    title: Integrate with CI
    instruction: Add an appropriate CI job, browser dependencies and artifact retention.
    required: true
  - id: verify
    title: Verify repeatedly
    instruction: Run selected browsers repeatedly and confirm the suite fails for meaningful regressions.
    required: true
  validation:
    commandRoles:
    - dev-start
    - end-to-end-test
    - build
    checks:
    - id: check-1
      type: assertion
      description: Critical flows pass repeatedly without arbitrary delays.
      blocking: true
      evidence: Referenced files, command results or explicit review notes.
    - id: check-2
      type: assertion
      description: Failure artifacts are useful and safely redacted.
      blocking: true
      evidence: Referenced files, command results or explicit review notes.
    - id: command-dev-start
      type: command
      description: Run the resolved dev-start command when the repository profile provides it and record the result.
      blocking: true
      evidence: Resolved command, exit status and concise result summary.
    - id: command-end-to-end-test
      type: command
      description: Run the resolved end-to-end-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.
  completion:
    criteria:
    - Critical flows pass from clean setup.
    - Failures capture actionable evidence and avoid brittle timing.
    - 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: true
    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:
  - playwright-critical-flows.static-structure