feat(core): add v3 lifecycle models, automation levels, subplan support, and security hardening

Implement multiple Stage A/B/E/SEC milestones for the v3 lifecycle system:
- Stage A5.3+A5.4: Add LifecycleActionModel and LifecyclePlanModel SQLAlchemy
  models with to_domain()/from_domain() conversion methods
- Stage A5.6: Implement ActionRepository with full CRUD, namespace/state
  queries, referential integrity checks, and retry decorator
- Stage E1: Add subplan domain models (ExecutionMode, SubplanMergeStrategy,
  SubplanConfig, SubplanStatus, SubplanAttempt, SubplanFailureHandler) with
  computed properties on Plan (is_subplan, is_root_plan, depth, has_subplans)
- Stage A6: Add AutomationLevel enum (MANUAL, REVIEW_BEFORE_APPLY,
  FULL_AUTOMATION), settings integration, PlanLifecycleService auto-progression,
  pause/resume, and CLI commands (--automation-level, set-automation-level)
- Stage SEC1: Remove eval()/exec() from stream_router.py, replace with named
  operation and transform registries; code blocks and unregistered transforms
  now raise StreamRoutingError
- Add langchain-anthropic dependency
- Update BDD tests for security changes and relax ADR directory requirement

features/architecture.feature

@@ -3,6 +3,10 @@ Feature: Architecture validation
   I want to verify the architecture follows our ADRs
   So that the codebase remains maintainable
 
+  Scenario: ADR directory is absent after cleanup
+    Given the ADR directory "docs/architecture/decisions" may be absent
+    Then the ADR check should be skipped when the directory is missing
+
   Scenario: Package structure follows layering ADR
     Given the source directory exists at "src/cleveragents"
     When I check the package structure