refactor(reasoning): enforce ClaimCoverage (Welt 1) vs ComplianceStatus (Welt 2) boundary [F1]

Architecture-validation finding: the implementation mode produced compliance-
flavored output ("teilweise erfüllt", "covered") from a mere customer claim,
blurring the line to the Execution layer. This is a design decision, not a text
fix — the reasoning layer judges only the customer's STATEMENT, never conformity.

- CoverageStatus -> ClaimCoverage; values are claim-relative + carry "potential":
  potentially_addresses / partially_addresses / does_not_address /
  insufficient_information.
- ImplementationAssessment -> ClaimObligationMapping (coverage_status ->
  claim_coverage); ImplementationResponse -> ImplementationReasoningResponse
  (assessments -> mappings, + explicit `disclaimer`); request renamed; engine
  entry assess_implementation -> reason_implementation_claim.
- Endpoint /reasoning/implementation-assessment -> /reasoning/implementation-reasoning.
- Summary/explanations reworded: "adressiert wahrscheinlich N Pflichten … für
  eine Bewertung der tatsächlichen Umsetzung sind Nachweise erforderlich (keine
  Konformitätsaussage)". No "erfüllt"/"abgedeckt" leaks.
- New guard test asserts no compliance verdict leaks (no "erfüllt"; disclaimer
  separates ClaimCoverage from ComplianceStatus). 23 tests green, mypy clean.

Discovery (scope/obligations) was already structurally claim-free and unaffected.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

backend-compliance/compliance/reasoning/__init__.py

@@ -13,7 +13,7 @@ only (spec §14).
 from __future__ import annotations
 
 from .claim_normalizer import normalize_claim
-from .implementation_engine import assess_implementation
+from .implementation_engine import reason_implementation_claim
 from .interpretation_engine import assess_interpretation
 from .obligation_engine import derive_obligations
 from .scope_engine import discover_scope
@@ -22,6 +22,6 @@ __all__ = [
     "discover_scope",
     "derive_obligations",
     "normalize_claim",
-    "assess_implementation",
+    "reason_implementation_claim",
     "assess_interpretation",
 ]