Add an LLM fact-check pass over the generated briefing

After summarisation the report is verified against the collected
payload (numbers, directions, unsupported claims) by a second LLM call
with a Verification JSON schema. Major issues trigger one revision and
a re-check; minor-only verdicts are normalized to ok. Failures never
block delivery. The verdict is stored in the result JSON and shown on
the dashboard (badge + 검증 메모). Disable with US2KR_VERIFY_ENABLED.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

us2kr/llm/base.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 from typing import Protocol
 
-from us2kr.models import MarketPayload, Report
+from us2kr.models import MarketPayload, Report, Verification, VerificationIssue
 
 
 class LLMError(RuntimeError):
@@ -15,3 +15,13 @@ class LLMProvider(Protocol):
     def summarize(self, payload: MarketPayload) -> tuple[Report, str]:
         """Return (validated Report, model id that produced it). Raise LLMError on total failure."""
         ...
+
+    def verify(self, payload: MarketPayload, report: Report) -> tuple[Verification, str]:
+        """Fact-check `report` against the payload. Raise LLMError on total failure."""
+        ...
+
+    def revise(
+        self, payload: MarketPayload, report: Report, issues: list[VerificationIssue]
+    ) -> tuple[Report, str]:
+        """Return a corrected Report addressing `issues`. Raise LLMError on total failure."""
+        ...