Commit Graph

2 Commits

Author SHA1 Message Date
freemo 583e6b7ea2 feat(correcting-plans): implement Predictive Error Prevention (Layer 4) with Error Pattern Database
Implement spec-mandated Layer 4 Predictive Error Prevention system:

- ErrorPattern domain model with pattern text, historical failures,
  preventive checks, frequency tracking, and keyword-based matching.
- ErrorPatternRepository with in-memory CRUD + context-matching query.
- ErrorPatternService with record_failure(), match_patterns(), and
  get_statistics() methods.
- Wire into plan execution via plan_lifecycle_service pre-execution hook.
- Add error pattern statistics to CLI diagnostics output.

Behave BDD: 11 scenarios covering recording, matching, formatting, stats.
Robot Framework: 3 integration smoke tests.
ASV benchmarks: pattern matching performance.

ISSUES CLOSED: #571
2026-03-08 21:53:21 -04:00
freemo 4ca4874c4d feat(correction): implement cross-plan correction cascading with child plan state handling
Add CrossPlanCorrectionService that implements the four child-plan-state-
dependent behaviours from the specification when a correction's affected
subtree includes child plans:

- Not yet started → cancel the child plan
- In progress → cancel + rollback sandbox to pre-child-plan state
- Completed but not applied → cancel + rollback sandbox
- Already applied → reject the correction (CorrectionRejection)

Key additions:
- ChildPlanState enum classifying child plans into 4 states
- CorrectionRejection result type with reason and affected applied plan IDs
- CascadeAction/CascadeResult models for cascade operation tracking
- CorrectionStatus.REJECTED for rejected corrections
- Atomic cascade-or-rollback: all child plan actions succeed or the
  entire cascade is rolled back
- Protocol-based dependency injection (ChildPlanLookup, ChildPlanCanceller,
  SandboxRollbacker) for testability
- execute_correction_with_cascade() integrates with CorrectionService flow

Testing:
- 24 Behave BDD scenarios in cross_plan_correction.feature
- 8 Robot Framework end-to-end smoke tests
- ASV benchmarks for cascade performance with varying child plan counts

ISSUES CLOSED: #547
2026-03-04 21:20:47 +00:00