feat(interpretation-in-map): judge a customer interpretation within the map (step 5)

Thin adapter — it judges the customer's reading WITHIN the already-built
RegulatoryMap, it does not assess abstract legal questions and it is not RCI.

- Reuses the existing assess_interpretation (no new legal reasoning); the 6
  verdicts (plausible/too_narrow/too_broad/partially_correct/unsupported/uncertain)
  pass through unchanged.
- Restricts affected_regulations/affected_obligations to those present in the map
  (intersection); links to the map's uncertain regulations.
- Touched unsupported domains (wastewater/chemicals/...) are reported as
  future_corpus_domains (future_corpus_needed) — never pseudo-evaluated.
- Customer-readable explanation ("Ihre Interpretation ist wahrscheinlich zu eng. …
  Betroffen in Ihrer Map: CRA.").
- POST /reasoning/interpretation-in-map (renders the map, then interprets).
- 7 tests; 63 green (existing reasoning MVP stays green), mypy clean, LOC ok.

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

backend-compliance/compliance/api/reasoning_routes.py

@@ -9,12 +9,18 @@ pure deterministic rule evaluation.
     POST /reasoning/interpretation-assessment  -> verdict on a customer interpretation
     POST /reasoning/product-scope              -> gate on facts, else run discover_scope once
     POST /reasoning/regulatory-map             -> customer-readable read-model over the scope
+    POST /reasoning/interpretation-in-map      -> judge a customer interpretation within the map
 """
 
 from __future__ import annotations
 
 from fastapi import APIRouter
 
+from compliance.interpretation_map import (
+    InterpretationInMapRequest,
+    InterpretationInMapResult,
+    interpret_in_map,
+)
 from compliance.product_scope import (
     ProductScopeRequest,
     ProductScopeResponse,
@@ -71,6 +77,12 @@ def regulatory_map(req: RegulatoryMapRequest) -> RegulatoryMap:
     return render_regulatory_map(req.product_profile)
 
 
+@router.post("/interpretation-in-map", response_model=InterpretationInMapResult)
+def interpretation_in_map(req: InterpretationInMapRequest) -> InterpretationInMapResult:
+    reg_map = render_regulatory_map(req.product_profile)
+    return interpret_in_map(reg_map, req.customer_interpretation)
+
+
 @router.post("/interpretation-assessment", response_model=InterpretationResponse)
 def interpretation_assessment(req: InterpretationRequest) -> InterpretationResponse:
     result = assess_interpretation(req.customer_interpretation, req.product_profile)