fix: make behaviour evaluation authoritative

Core fix: For cases with expectedBehaviours, reasoningQuality.status is now
set exclusively from behaviour evaluation results (required behaviour pass/fail).
Legacy concept checks remain visible as diagnostic-only metrics and do not
influence the authoritative result.

Key changes:
- Behaviour-based scoring determines reasoning status (passed/failed)
  instead of legacy concept literal matching
- Schema failure correctly forces not_evaluated (no vacuous truth)
- Saved live results re-evaluator preserves provenance metadata
- Classification tolerance map works bidirectionally for interchangeable types
- normalise() treats underscores as word characters, hyphens as spaces

Tests: 74 passing across both evaluator test suites
- tests/evaluator-behaviour-authoritative.test.mjs (47 tests, new)
- tests/evaluator-semantic.test.mjs (27 tests)

app/api/analyse/route.js

@@ -1,4 +1,8 @@
-import { analyseScenario, PROMPT_VERSIONS, DEFAULT_PROMPT_VERSION } from "@/lib/analysis";
+import {
+  analyseScenario,
+  PROMPT_VERSIONS,
+  DEFAULT_PROMPT_VERSION,
+} from "@/lib/analysis";
 
 export async function POST(request) {
   try {
@@ -7,7 +11,7 @@ export async function POST(request) {
     if (!body.scenario || typeof body.scenario !== "string") {
       return Response.json(
         { error: "Request must include a 'scenario' string field" },
-        { status: 400 }
+        { status: 400 },
       );
     }
 
@@ -22,7 +26,7 @@ export async function POST(request) {
     if (!result.success) {
       return Response.json(
         { ...result, reconstruction: result.reconstruction || null },
-        { status: Number(result.statusCode) || 500 }
+        { status: Number(result.statusCode) || 500 },
       );
     }
 
@@ -39,7 +43,7 @@ export async function POST(request) {
   } catch (e) {
     return Response.json(
       { error: e.message || "Unknown server error", responseDurationMs: 0 },
-      { status: 500 }
+      { status: 500 },
     );
   }
 }