M5: implement RAGcore knowledge integration

KnowledgeProvider protocol with a deterministic TF-IDF-weighted extractive demo provider (never generative, always cites real excerpts) and a RAGcore HTTP adapter that degrades cleanly to unavailable. Knowledge nav + chat-style Q&A UI with source cards and honest grounded/insufficient/unavailable states. 57 backend tests passing, ruff clean. Fixed a real relevance bug (generic terms like "vehicle" crowding out distinctive matches) via IDF weighting, found by testing the actual S6 scenario. Verified end-to-end in the browser: grounded damage question cites both expected procedures; unrelated question honestly returns insufficient evidence with no fabrication.

frontend/src/api/types.ts

@@ -167,6 +167,32 @@ export interface MergeCustomersResult {
   rewired_bookings: number;
 }
 
+export interface SourceCard {
+  document_id: string;
+  title: string;
+  version: string;
+  section: string;
+  excerpt: string;
+}
+
+export interface GroundedAnswer {
+  answer: string;
+  evidence_state: "grounded" | "insufficient" | "unavailable";
+  sources: SourceCard[];
+  provider: string;
+  correlation_id: string;
+}
+
+export interface KnowledgeHealth {
+  provider: string;
+  available: boolean;
+  detail: string;
+  tenant: string;
+  workspace: string;
+  collection: string;
+  document_count: number;
+}
+
 export interface AuditEvent {
   id: string;
   actor_type: string;