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)

components/diagnostics-view.jsx

@@ -10,7 +10,9 @@ const ValidationIndicator = ({ status }) => {
     invalid: "❌ Validation failed",
   };
   return (
-    <div className={`flex items-center gap-2 ${styles[status] || "text-gray-500"}`}>
+    <div
+      className={`flex items-center gap-2 ${styles[status] || "text-gray-500"}`}
+    >
       <span className="font-medium">{labels[status] || status}</span>
     </div>
   );
@@ -29,8 +31,19 @@ export default function DiagnosticsView({ result }) {
     { label: "Model", value: result.modelName || "?" },
     { label: "Provider", value: "Ollama" },
     { label: "Prompt version", value: result.promptVersion || "?" },
-    { label: "Duration", value: result.responseDurationMs != null ? `${result.responseDurationMs}ms` : "?" },
-    { label: "Validation", value: <ValidationIndicator status={result.validationStatus || "invalid"} /> },
+    {
+      label: "Duration",
+      value:
+        result.responseDurationMs != null
+          ? `${result.responseDurationMs}ms`
+          : "?",
+    },
+    {
+      label: "Validation",
+      value: (
+        <ValidationIndicator status={result.validationStatus || "invalid"} />
+      ),
+    },
   ];
 
   return (
@@ -49,7 +62,8 @@ export default function DiagnosticsView({ result }) {
       {result.rawResponse && (
         <details className="mt-4">
           <summary className="cursor-pointer text-xs text-gray-500 underline hover:text-gray-700">
-            View raw model response ({(result.rawResponse?.length || 0).toLocaleString()} chars)
+            View raw model response (
+            {(result.rawResponse?.length || 0).toLocaleString()} chars)
           </summary>
           <pre className="mt-2 max-h-60 overflow-auto rounded bg-gray-900 px-3 py-2 text-xs leading-relaxed text-green-400">
             {result.rawResponse}

components/reconstruction-view.jsx

@@ -10,7 +10,9 @@ const confidenceColor = {
 };
 
 const ConfidenceBadge = ({ level }) => (
-  <span className={`inline-block rounded-full border px-2 py-0.5 text-xs font-medium ${confidenceColor[level] || "text-gray-600 bg-gray-100"}`}>
+  <span
+    className={`inline-block rounded-full border px-2 py-0.5 text-xs font-medium ${confidenceColor[level] || "text-gray-600 bg-gray-100"}`}
+  >
     {level}
   </span>
 );
@@ -42,17 +44,27 @@ const importanceLabels = {
 function ClassificationDisplay({ classification }) {
   if (!classification) return null;
   const p = classification.primaryType || classification.primary_type;
-  const sec = classification.secondaryTypes || classification.secondary_types || [];
-  const modes = classification.reasoningModes || classification.reasoning_modes || [];
+  const sec =
+    classification.secondaryTypes || classification.secondary_types || [];
+  const modes =
+    classification.reasoningModes || classification.reasoning_modes || [];
 
   // Normalize camelCase to snake_case for display if needed
-  const primaryLabel = String(p).replace(/_/g, " ").replace(/\b\w/g, (c) => c.toUpperCase());
-  const secLabels = sec.map((s) => s.replace(/_/g, " ").replace(/\b\w/g, (c) => c.toUpperCase()));
-  const modeLabels = modes.map((m) => m.replace(/_/g, " ").replace(/\b\w/g, (c) => c.toUpperCase()));
+  const primaryLabel = String(p)
+    .replace(/_/g, " ")
+    .replace(/\b\w/g, (c) => c.toUpperCase());
+  const secLabels = sec.map((s) =>
+    s.replace(/_/g, " ").replace(/\b\w/g, (c) => c.toUpperCase()),
+  );
+  const modeLabels = modes.map((m) =>
+    m.replace(/_/g, " ").replace(/\b\w/g, (c) => c.toUpperCase()),
+  );
 
   return (
     <div className="rounded-lg border border-blue-200 bg-blue-50 p-4">
-      <h3 className="mb-2 text-sm font-semibold text-blue-700">Input Classification</h3>
+      <h3 className="mb-2 text-sm font-semibold text-blue-700">
+        Input Classification
+      </h3>
       <dl className="grid grid-cols-[auto_1fr] gap-x-4 gap-y-1.5 text-sm">
         <dt className="text-blue-500">Primary type</dt>
         <dd className="font-medium">{primaryLabel}</dd>
@@ -69,9 +81,14 @@ function ClassificationDisplay({ classification }) {
           </>
         )}
         <dt className="text-blue-500 pt-1">Classification reason</dt>
-        <dd className="italic">{classification.classificationReason || classification.classification_reason}</dd>
+        <dd className="italic">
+          {classification.classificationReason ||
+            classification.classification_reason}
+        </dd>
         <dt className="text-blue-500 pt-1">Confidence</dt>
-        <dd><ConfidenceBadge level={classification.confidence} /></dd>
+        <dd>
+          <ConfidenceBadge level={classification.confidence} />
+        </dd>
       </dl>
     </div>
   );
@@ -83,7 +100,9 @@ function SummaryDisplay({ reconstruction }) {
   const summary = reconstruction.summary || reconstruction.Summary;
   return (
     <div className="rounded-lg border border-gray-200 bg-white p-4">
-      <h3 className="mb-2 text-sm font-semibold text-gray-600">Reconstruction Summary</h3>
+      <h3 className="mb-2 text-sm font-semibold text-gray-600">
+        Reconstruction Summary
+      </h3>
       <p className="text-sm leading-relaxed">{summary}</p>
     </div>
   );
@@ -98,15 +117,26 @@ function ItemList({ title, items, renderExtra }) {
 
   return (
     <div className="mb-4 rounded-lg border border-gray-200 bg-white p-4">
-      <h3 className="mb-2 text-sm font-semibold text-gray-600">{title} ({count})</h3>
+      <h3 className="mb-2 text-sm font-semibold text-gray-600">
+        {title} ({count})
+      </h3>
       <ul className="space-y-2">
         {itemsArr.map((item, idx) => (
-          <li key={item.id || `${title}-${idx}`} className="rounded border border-gray-200 bg-white px-3 py-2 text-sm">
+          <li
+            key={item.id || `${title}-${idx}`}
+            className="rounded border border-gray-200 bg-white px-3 py-2 text-sm"
+          >
             <div className="flex items-center gap-2">
-              {item.id && <span className="font-mono text-xs text-gray-400">#{item.id}</span>}
+              {item.id && (
+                <span className="font-mono text-xs text-gray-400">
+                  #{item.id}
+                </span>
+              )}
               {item.confidence && <ConfidenceBadge level={item.confidence} />}
               {item.importance && (
-                <span className={`inline-block rounded-full border px-2 py-0.5 text-xs font-medium ${importanceColors[item.importance] || "text-gray-600 bg-gray-100"}`}>
+                <span
+                  className={`inline-block rounded-full border px-2 py-0.5 text-xs font-medium ${importanceColors[item.importance] || "text-gray-600 bg-gray-100"}`}
+                >
                   {importanceLabels[item.importance]}
                 </span>
               )}
@@ -123,23 +153,38 @@ function ItemList({ title, items, renderExtra }) {
 // ── Plausible interpretations ───────────────────────
 function InterpretationsDisplay({ interpretations }) {
   if (!interpretations?.length) return null;
-  const arr = Array.isArray(interpretations) ? interpretations : [interpretations];
+  const arr = Array.isArray(interpretations)
+    ? interpretations
+    : [interpretations];
 
   return (
     <div className="mb-4 rounded-lg border border-indigo-200 bg-indigo-50 p-4">
-      <h3 className="mb-2 text-sm font-semibold text-indigo-700">Plausible Interpretations ({arr.length})</h3>
+      <h3 className="mb-2 text-sm font-semibold text-indigo-700">
+        Plausible Interpretations ({arr.length})
+      </h3>
       <ul className="space-y-3">
         {arr.map((interp, idx) => (
-          <li key={interp.id || `${idx}`} className="rounded border border-indigo-200 bg-white px-3 py-2.5 text-sm leading-relaxed">
+          <li
+            key={interp.id || `${idx}`}
+            className="rounded border border-indigo-200 bg-white px-3 py-2.5 text-sm leading-relaxed"
+          >
             <div className="flex items-center gap-2 mb-1">
-              <span className="font-medium text-indigo-600">{interp.description}</span>
-              {interp.confidence && <ConfidenceBadge level={interp.confidence} />}
+              <span className="font-medium text-indigo-600">
+                {interp.description}
+              </span>
+              {interp.confidence && (
+                <ConfidenceBadge level={interp.confidence} />
+              )}
             </div>
             {interp.supportingEvidenceIds?.length > 0 && (
-              <p className="text-xs text-gray-500">Supporting evidence: {interp.supportingEvidenceIds.join(", ")}</p>
+              <p className="text-xs text-gray-500">
+                Supporting evidence: {interp.supportingEvidenceIds.join(", ")}
+              </p>
             )}
             {interp.assumptionsRequired?.length > 0 && (
-              <p className="text-xs italic text-gray-500">Requires assumptions: {interp.assumptionsRequired.join("; ")}</p>
+              <p className="text-xs italic text-gray-500">
+                Requires assumptions: {interp.assumptionsRequired.join("; ")}
+              </p>
             )}
           </li>
         ))}
@@ -154,22 +199,37 @@ function NextQuestionDisplay({ question }) {
   const q = question.question || question.Question;
   const targets = question.targets || question.Targets || [];
   const reason = question.reason || question.Reason || "";
-  const value = question.expectedInformationValue || question.expected_information_value || "medium";
+  const value =
+    question.expectedInformationValue ||
+    question.expected_information_value ||
+    "medium";
 
-  const valueLabel = { low: "Low", medium: "Medium", high: "High" }[value] || "Medium";
-  const valueColor = { low: "bg-yellow-100 text-yellow-800", medium: "bg-blue-100 text-blue-800", high: "bg-green-100 text-green-800" }[value] || "";
+  const valueLabel =
+    { low: "Low", medium: "Medium", high: "High" }[value] || "Medium";
+  const valueColor =
+    {
+      low: "bg-yellow-100 text-yellow-800",
+      medium: "bg-blue-100 text-blue-800",
+      high: "bg-green-100 text-green-800",
+    }[value] || "";
 
   return (
     <div className="rounded-lg border-2 border-green-300 bg-green-50 p-5">
       <div className="flex items-center gap-2 mb-2">
         <h3 className="text-sm font-bold text-green-800">Next Question</h3>
-        <span className={`rounded-full px-2 py-0.5 text-xs font-medium ${valueColor}`}>{valueLabel} value</span>
+        <span
+          className={`rounded-full px-2 py-0.5 text-xs font-medium ${valueColor}`}
+        >
+          {valueLabel} value
+        </span>
       </div>
       <p className="mb-2 text-base font-medium text-gray-900">{q}</p>
       {targets.length > 0 && (
         <p className="text-sm text-gray-600">Targets: {targets.join(", ")}</p>
       )}
-      {reason && <p className="text-sm italic text-gray-500">Because: {reason}</p>}
+      {reason && (
+        <p className="text-sm italic text-gray-500">Because: {reason}</p>
+      )}
     </div>
   );
 }
@@ -189,13 +249,24 @@ function EvidenceDisplay({ evidence }) {
 
   return (
     <div className="mb-4 rounded-lg border border-gray-200 bg-white p-4">
-      <h3 className="mb-2 text-sm font-semibold text-gray-600">Supporting Evidence ({arr.length})</h3>
+      <h3 className="mb-2 text-sm font-semibold text-gray-600">
+        Supporting Evidence ({arr.length})
+      </h3>
       <ul className="space-y-2">
         {arr.map((item, idx) => (
-          <li key={item.id || `${idx}`} className="rounded border border-gray-200 bg-white px-3 py-2 text-sm leading-relaxed">
+          <li
+            key={item.id || `${idx}`}
+            className="rounded border border-gray-200 bg-white px-3 py-2 text-sm leading-relaxed"
+          >
             <div className="flex items-center gap-2 mb-0.5 flex-wrap">
-              {item.id && <span className="font-mono text-xs text-gray-400">#{item.id}</span>}
-              <span className={`inline-block rounded px-1.5 py-0.5 text-[10px] font-medium ${importanceColors[item.importance] || "text-gray-600 bg-gray-100"}`}>
+              {item.id && (
+                <span className="font-mono text-xs text-gray-400">
+                  #{item.id}
+                </span>
+              )}
+              <span
+                className={`inline-block rounded px-1.5 py-0.5 text-[10px] font-medium ${importanceColors[item.importance] || "text-gray-600 bg-gray-100"}`}
+              >
                 {importanceLabels[item.importance]}
               </span>
               <span className="inline-block rounded px-1.5 py-0.5 text-[10px] font-medium bg-gray-100 text-gray-700">
@@ -205,7 +276,9 @@ function EvidenceDisplay({ evidence }) {
             </div>
             <p className="text-sm">{item.description}</p>
             {(item.source || item.attribution) && (
-              <p className="mt-0.5 text-xs text-gray-400">Source: {item.source || item.attribution}</p>
+              <p className="mt-0.5 text-xs text-gray-400">
+                Source: {item.source || item.attribution}
+              </p>
             )}
           </li>
         ))}
@@ -222,7 +295,8 @@ export default function ReconstructionView({ reconstruction, partial }) {
   if (partial) {
     return (
       <div className="rounded-lg border border-yellow-300 bg-yellow-50 px-4 py-3 text-sm text-yellow-800">
-        ⚠ Partial result — some fields failed validation. Showing what was accepted.
+        ⚠ Partial result — some fields failed validation. Showing what was
+        accepted.
       </div>
     );
   }
@@ -241,60 +315,97 @@ export default function ReconstructionView({ reconstruction, partial }) {
 
       {/* Key differences */}
       {data.reconstruction?.differences && (
-        <ItemList title="Key Differences" items={data.reconstruction.differences} />
+        <ItemList
+          title="Key Differences"
+          items={data.reconstruction.differences}
+        />
       )}
 
       {/* Unexplained transitions */}
-      {data.reconstruction?.unexplainedTransitions && data.reconstruction.unexplainedTransitions.length > 0 && (
-        <ItemList title="Unexplained Transitions" items={data.reconstruction.unexplainedTransitions} renderExtra={(i) => (
-          i.entity && <p className="mt-1 text-xs text-gray-500">Entity: {i.entity}</p>
-        )} />
-      )}
+      {data.reconstruction?.unexplainedTransitions &&
+        data.reconstruction.unexplainedTransitions.length > 0 && (
+          <ItemList
+            title="Unexplained Transitions"
+            items={data.reconstruction.unexplainedTransitions}
+            renderExtra={(i) =>
+              i.entity && (
+                <p className="mt-1 text-xs text-gray-500">Entity: {i.entity}</p>
+              )
+            }
+          />
+        )}
 
       {/* Contradictions */}
-      {data.reconstruction?.contradictions && data.reconstruction.contradictions.length > 0 && (
-        <ItemList title="Contradictions" items={data.reconstruction.contradictions} />
-      )}
+      {data.reconstruction?.contradictions &&
+        data.reconstruction.contradictions.length > 0 && (
+          <ItemList
+            title="Contradictions"
+            items={data.reconstruction.contradictions}
+          />
+        )}
 
       {/* Important unknowns */}
-      {data.reconstruction?.importantUnknowns && data.reconstruction.importantUnknowns.length > 0 && (
-        <ItemList title="Important Unknowns" items={data.reconstruction.importantUnknowns} />
-      )}
+      {data.reconstruction?.importantUnknowns &&
+        data.reconstruction.importantUnknowns.length > 0 && (
+          <ItemList
+            title="Important Unknowns"
+            items={data.reconstruction.importantUnknowns}
+          />
+        )}
 
       {/* Plausible interpretations */}
-      {data.reconstruction?.plausibleInterpretations && data.reconstruction.plausibleInterpretations.length > 0 && (
-        <InterpretationsDisplay interpretations={data.reconstruction.plausibleInterpretations} />
-      )}
+      {data.reconstruction?.plausibleInterpretations &&
+        data.reconstruction.plausibleInterpretations.length > 0 && (
+          <InterpretationsDisplay
+            interpretations={data.reconstruction.plausibleInterpretations}
+          />
+        )}
 
       {/* Secondary reconstruction categories (actors, systems, etc.) */}
       {data.reconstruction?.actors && data.reconstruction.actors.length > 0 && (
         <ItemList title="Actors" items={data.reconstruction.actors} />
       )}
-      {data.reconstruction?.systemsOrObjects && data.reconstruction.systemsOrObjects.length > 0 && (
-        <ItemList title="Systems / Objects" items={data.reconstruction.systemsOrObjects} />
-      )}
-      {data.reconstruction?.expectedStates && data.reconstruction.expectedStates.length > 0 && (
-        <ItemList title="Expected States" items={data.reconstruction.expectedStates} />
-      )}
-      {data.reconstruction?.observedStates && data.reconstruction.observedStates.length > 0 && (
-        <ItemList title="Observed States" items={data.reconstruction.observedStates} />
-      )}
-      {data.reconstruction?.knownTransitions && data.reconstruction.knownTransitions.length > 0 && (
-        <ItemList title="Known Transitions" items={data.reconstruction.knownTransitions} renderExtra={(i) => (
-          <div className="mt-1 text-xs text-gray-500">
-            {i.entity && <span>Entity: {i.entity} · </span>}
-            From "{i.previousState}" → To "{i.currentState}" ({i.explanationStatus})
-          </div>
-        )} />
-      )}
+      {data.reconstruction?.systemsOrObjects &&
+        data.reconstruction.systemsOrObjects.length > 0 && (
+          <ItemList
+            title="Systems / Objects"
+            items={data.reconstruction.systemsOrObjects}
+          />
+        )}
+      {data.reconstruction?.expectedStates &&
+        data.reconstruction.expectedStates.length > 0 && (
+          <ItemList
+            title="Expected States"
+            items={data.reconstruction.expectedStates}
+          />
+        )}
+      {data.reconstruction?.observedStates &&
+        data.reconstruction.observedStates.length > 0 && (
+          <ItemList
+            title="Observed States"
+            items={data.reconstruction.observedStates}
+          />
+        )}
+      {data.reconstruction?.knownTransitions &&
+        data.reconstruction.knownTransitions.length > 0 && (
+          <ItemList
+            title="Known Transitions"
+            items={data.reconstruction.knownTransitions}
+            renderExtra={(i) => (
+              <div className="mt-1 text-xs text-gray-500">
+                {i.entity && <span>Entity: {i.entity} · </span>}
+                From "{i.previousState}" → To "{i.currentState}" (
+                {i.explanationStatus})
+              </div>
+            )}
+          />
+        )}
 
       {/* Next question — prominent */}
       <NextQuestionDisplay question={data.nextQuestion} />
 
       {/* Evidence */}
-      {data.evidence && (
-        <EvidenceDisplay evidence={data.evidence} />
-      )}
+      {data.evidence && <EvidenceDisplay evidence={data.evidence} />}
     </div>
   );
 }

components/scenario-form.jsx

@@ -48,7 +48,8 @@ export default function ScenarioForm() {
   const hasReconstruction = result?.reconstruction;
   const hasNextQuestion = result?.nextQuestion;
   const hasEvidence = result?.evidence && result.evidence.length > 0;
-  const hasMeaningfulContent = hasClassification || hasReconstruction || hasNextQuestion || hasEvidence;
+  const hasMeaningfulContent =
+    hasClassification || hasReconstruction || hasNextQuestion || hasEvidence;
 
   return (
     <div className="space-y-6">
@@ -62,7 +63,9 @@ export default function ScenarioForm() {
           className="w-full rounded-lg border border-gray-300 px-4 py-3 text-sm focus:border-gray-500 focus:outline-none focus:ring-2 focus:ring-gray-400"
         />
         <div className="flex items-center justify-between">
-          <span className="text-xs text-gray-400">{scenario.length}/{MAX_LENGTH}</span>
+          <span className="text-xs text-gray-400">
+            {scenario.length}/{MAX_LENGTH}
+          </span>
           <button
             type="submit"
             disabled={status === "loading" || !scenario.trim()}
@@ -84,7 +87,8 @@ export default function ScenarioForm() {
           {/* Show partial content even on validation failure */}
           {(hasClassification || hasReconstruction) && (
             <div className="rounded-lg border border-yellow-300 bg-yellow-50 px-4 py-2 text-sm text-yellow-800">
-              ⚠ Partial result — some fields failed validation. Showing what was accepted.
+              ⚠ Partial result — some fields failed validation. Showing what was
+              accepted.
             </div>
           )}
           {hasReconstruction && (
@@ -106,13 +110,17 @@ export default function ScenarioForm() {
       )}
 
       {status === "loading" && (
-        <div className="py-12 text-center text-sm text-gray-400">Waiting for model response...</div>
+        <div className="py-12 text-center text-sm text-gray-400">
+          Waiting for model response...
+        </div>
       )}
 
       {/* Empty state */}
       {status === "idle" && (
         <div className="rounded-lg border border-dashed border-gray-300 bg-gray-50 px-6 py-8 text-center">
-          <p className="text-sm text-gray-400">Enter a scenario above and click Analyse to begin.</p>
+          <p className="text-sm text-gray-400">
+            Enter a scenario above and click Analyse to begin.
+          </p>
         </div>
       )}