chore: establish clean v0.2 baseline

Include only the working reconstruction prototype with Ollama integration: - double-wrapping fix (lib/llm/provider.js) - explicit v0.2 JSON output schema (prompts/reconstruct-v0.2.md) - Zod validation layer (lib/reconstruction/schema.js) - shared core analysis path (lib/analysis.js) - prompt versioning infrastructure (lib/reconstruction/prompt.js) - provider abstraction - functioning Ollama provider path - updated API route with centralized analysis - UI components displaying v0.2 data and validation errors - .gitignore rules for generated evaluation artifacts Exclude: evaluator experiments, diagnostic tests, debug scripts, generated artifacts, comparison findings, test data tied to evaluator.
2026-08-01 14:45:06 +01:00
parent a2f9e472ea
commit d72c7c5465
11 changed files with 1048 additions and 172 deletions
@@ -34,3 +34,8 @@ Thumbs.db
 npm-debug.log*
 yarn-debug.log*
 yarn-error.log*
+
+# Generated evaluation artifacts (regenerated each run)
+evaluation-results/
+provider-debug-results/
+tests-results/
@@ -1,101 +1,49 @@
-import { getConfig } from "@/lib/config";
-import { getProvider } from "@/lib/llm/provider";
-import { reconstructionSchema } from "@/lib/reconstruction/schema";
-
-const MAX_SCENARIO_LENGTH = 10000;
+import {
+  analyseScenario,
+  PROMPT_VERSIONS,
+  DEFAULT_PROMPT_VERSION,
+} from "@/lib/analysis";

 export async function POST(request) {
-  const startTime = Date.now();
-  let rawResponse = null;
-  
  try {
    const body = await request.json();

    if (!body.scenario || typeof body.scenario !== "string") {
      return Response.json(
        { error: "Request must include a 'scenario' string field" },
-        { status: 400 }
+        { status: 400 },
      );
    }

-    const trimmed = body.scenario.trim();
+    // Optional prompt version override
+    let promptVersion = DEFAULT_PROMPT_VERSION;
+    if (body.promptVersion && PROMPT_VERSIONS.includes(body.promptVersion)) {
+      promptVersion = body.promptVersion;
+    }

-    if (trimmed.length === 0) {
+    const result = await analyseScenario(body.scenario, { promptVersion });
+
+    if (!result.success) {
      return Response.json(
-        { error: "Scenario cannot be empty" },
-        { status: 400 }
+        { ...result, reconstruction: result.reconstruction || null },
+        { status: Number(result.statusCode) || 500 },
      );
    }

-    if (trimmed.length > MAX_SCENARIO_LENGTH) {
-      return Response.json(
-        { error: `Scenario must be under ${MAX_SCENARIO_LENGTH} characters` },
-        { status: 400 }
-      );
-    }
-
-    const configResult = getConfig();
-    if (!configResult.ok) {
-      return Response.json(
-        { error: "Invalid server configuration" },
-        { status: 500 }
-      );
-    }
-
-    const { OLLAMA_BASE_URL, OLLAMA_MODEL } = configResult.config;
-    const provider = getProvider();
-
-    // Attempt parse to capture raw for debugging
-    let reconstruction;
-    try {
-      reconstruction = await provider.generateReconstruction(trimmed, OLLAMA_MODEL);
-    } catch (e) {
-      return Response.json(
-        { 
-          error: e.message || "Unknown server error", 
-          responseDurationMs: Date.now() - startTime,
-          modelName: OLLAMA_MODEL,
-          validationStatus: "invalid",
-        },
-        { status: 500 }
-      );
-    }
-    
-    // Try to stringify for rawResponse display (safe even if it's already an object)
-    try {
-      rawResponse = JSON.stringify(reconstruction);
-    } catch {
-      rawResponse = String(reconstruction).slice(0, 2000);
-    }
-
-    const duration = Date.now() - startTime;
-
-    // Validate with Zod schema
-    const validationResult = reconstructionSchema.safeParse(reconstruction);
-
-    if (!validationResult.success) {
-      return Response.json({
-        reconstruction: null,
-        modelName: OLLAMA_MODEL,
-        responseDurationMs: duration,
-        validationStatus: "invalid",
-        rawResponse: rawResponse?.slice(0, 2000),
-        errors: validationResult.error.issues.map((i) => `${i.path.join(".")}: ${i.message}`),
-      });
-    }
-
    return Response.json({
-      reconstruction: validationResult.data,
-      modelName: OLLAMA_MODEL,
-      responseDurationMs: duration,
-      validationStatus: "valid",
-      rawResponse: rawResponse?.slice(0, 2000),
+      inputClassification: result.inputClassification,
+      reconstruction: result.reconstruction,
+      evidence: result.evidence,
+      nextQuestion: result.nextQuestion,
+      modelName: result.modelName,
+      responseDurationMs: result.responseDurationMs,
+      validationStatus: result.validationStatus,
+      promptVersion: result.promptVersion,
    });
  } catch (e) {
-    const duration = Date.now() - startTime;
    return Response.json(
-      { error: e.message || "Unknown server error", responseDurationMs: duration },
-      { status: 500 }
+      { error: e.message || "Unknown server error", responseDurationMs: 0 },
+      { status: 500 },
    );
  }
 }
@@ -10,17 +10,40 @@ 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>
  );
 };

+const validationIcons = {
+  valid: "✅",
+  partial: "⚠️",
+  invalid: "❌",
+};
+
 export default function DiagnosticsView({ result }) {
+  if (!result) return null;
+
  const metrics = [
    { label: "Model", value: result.modelName || "?" },
-    { label: "Duration", value: result.responseDurationMs != null ? `${result.responseDurationMs}ms` : "?" },
-    { label: "Validation", value: <ValidationIndicator status={result.validationStatus || "invalid"} /> },
+    { label: "Provider", value: "Ollama" },
+    { label: "Prompt version", value: result.promptVersion || "?" },
+    {
+      label: "Duration",
+      value:
+        result.responseDurationMs != null
+          ? `${result.responseDurationMs}ms`
+          : "?",
+    },
+    {
+      label: "Validation",
+      value: (
+        <ValidationIndicator status={result.validationStatus || "invalid"} />
+      ),
+    },
  ];

  return (
@@ -35,16 +58,32 @@ export default function DiagnosticsView({ result }) {
        ))}
      </dl>

+      {/* Collapsed raw output for debugging */}
      {result.rawResponse && (
        <details className="mt-4">
          <summary className="cursor-pointer text-xs text-gray-500 underline hover:text-gray-700">
-            View raw model response
+            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}
          </pre>
        </details>
      )}
+
+      {/* Errors if present */}
+      {result.errors && result.errors.length > 0 && (
+        <details className="mt-3">
+          <summary className="cursor-pointer text-xs text-red-500 underline hover:text-red-700">
+            Validation errors ({result.errors.length})
+          </summary>
+          <ul className="mt-1 space-y-0.5 text-xs text-red-600">
+            {result.errors.map((err, i) => (
+              <li key={i}>{err}</li>
+            ))}
+          </ul>
+        </details>
+      )}
    </div>
  );
 }
@@ -1,15 +1,8 @@
-const categoryLabels = {
-  observations: "Direct Observations",
-  reportedClaims: "Reported Claims",
-  assumptions: "Unsupported Assumptions",
-  entities: "Entities",
-  transitions: "Transitions",
-  expectedButMissing: "Expected But Missing",
-  presentButUnexpected: "Present But Unexpected",
-  contradictions: "Contradictions",
-  openUncertainties: "Open Uncertainties",
-};
+"use client";

+import { useMemo } from "react";
+
+// ── Confidence badge (shared) ────────────────────────
 const confidenceColor = {
  low: "text-red-600 bg-red-50 border-red-200",
  medium: "text-yellow-700 bg-yellow-50 border-yellow-200",
@@ -17,54 +10,401 @@ 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>
 );

-function ItemList({ items, renderExtra }) {
-  if (!items?.length) return <p className="text-sm italic text-gray-400">None identified</p>;
+// ── Evidence type labels (shared) ───────────────────
+const evidenceTypeLabels = {
+  direct_observation: "Direct Observation",
+  reported_statement: "Reported Statement",
+  interpretation: "Interpretation",
+  assumption: "Assumption",
+  inferred_relationship: "Inferred Relationship",
+};
+
+const importanceColors = {
+  incidental: "text-gray-500 bg-gray-50 border-gray-200",
+  supporting: "text-blue-700 bg-blue-50 border-blue-200",
+  important: "text-orange-700 bg-orange-50 border-orange-200",
+  critical: "text-red-800 bg-red-50 border-red-300 font-semibold",
+};
+
+const importanceLabels = {
+  incidental: "Incidental",
+  supporting: "Supporting",
+  important: "Important",
+  critical: "Critical",
+};
+
+// ── Input classification display ────────────────────
+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 || [];
+
+  // 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()),
+  );

  return (
-    <ul className="space-y-2">
-      {items.map((item) => (
-        <li key={item.id} className="rounded border border-gray-200 bg-white px-3 py-2 text-sm">
-          <div className="flex items-center gap-2">
-            <span className="font-mono text-xs text-gray-400">#{item.id}</span>
-            <ConfidenceBadge level={item.confidence} />
-          </div>
-          <p className="mt-1">{item.description}</p>
-          {renderExtra && renderExtra(item)}
-        </li>
-      ))}
-    </ul>
+    <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>
+      <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>
+        {secLabels.length > 0 && (
+          <>
+            <dt className="text-blue-500 pt-1">Secondary types</dt>
+            <dd>{secLabels.join(" · ")}</dd>
+          </>
+        )}
+        {modeLabels.length > 0 && (
+          <>
+            <dt className="text-blue-500 pt-1">Reasoning modes</dt>
+            <dd>{modeLabels.join(" · ")}</dd>
+          </>
+        )}
+        <dt className="text-blue-500 pt-1">Classification reason</dt>
+        <dd className="italic">
+          {classification.classificationReason ||
+            classification.classification_reason}
+        </dd>
+        <dt className="text-blue-500 pt-1">Confidence</dt>
+        <dd>
+          <ConfidenceBadge level={classification.confidence} />
+        </dd>
+      </dl>
+    </div>
  );
 }

+// ── Reconstruction summary ──────────────────────────
+function SummaryDisplay({ reconstruction }) {
+  if (!reconstruction?.summary) return null;
+  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>
+      <p className="text-sm leading-relaxed">{summary}</p>
+    </div>
+  );
+}
+
+// ── Generic item list (used for multiple sections) ──
+function ItemList({ title, items, renderExtra }) {
+  const count = items?.length;
+  if (!count) return null; // hide empty sections entirely
+
+  const itemsArr = Array.isArray(items) ? items : [items];
+
+  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>
+      <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"
+          >
+            <div className="flex items-center gap-2">
+              {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 ${importanceColors[item.importance] || "text-gray-600 bg-gray-100"}`}
+                >
+                  {importanceLabels[item.importance]}
+                </span>
+              )}
+            </div>
+            <p className="mt-1">{item.description}</p>
+            {renderExtra && renderExtra(item)}
+          </li>
+        ))}
+      </ul>
+    </div>
+  );
+}
+
+// ── Plausible interpretations ───────────────────────
+function InterpretationsDisplay({ interpretations }) {
+  if (!interpretations?.length) return null;
+  const arr = Array.isArray(interpretations)
+    ? interpretations
+    : [interpretations];
+
+  return (
+    <div className="mb-4 rounded-lg border border-indigo-200 bg-indigo-50 p-4">
+      <h3 className="mb-2 text-sm font-semibold text-indigo-700">
+        Plausible Interpretations ({arr.length})
+      </h3>
+      <ul className="space-y-3">
+        {arr.map((interp, idx) => (
+          <li
+            key={interp.id || `${idx}`}
+            className="rounded border border-indigo-200 bg-white px-3 py-2.5 text-sm leading-relaxed"
+          >
+            <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} />
+              )}
+            </div>
+            {interp.supportingEvidenceIds?.length > 0 && (
+              <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>
+            )}
+          </li>
+        ))}
+      </ul>
+    </div>
+  );
+}
+
+// ── Next question (prominent) ───────────────────────
+function NextQuestionDisplay({ question }) {
+  if (!question?.question) return null;
+  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 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 ${valueColor}`}
+        >
+          {valueLabel} value
+        </span>
+      </div>
+      <p className="mb-2 text-base font-medium text-gray-900">{q}</p>
+      {targets.length > 0 && (
+        <p className="text-sm text-gray-600">Targets: {targets.join(", ")}</p>
+      )}
+      {reason && (
+        <p className="text-sm italic text-gray-500">Because: {reason}</p>
+      )}
+    </div>
+  );
+}
+
+// ── Evidence list ───────────────────────────────────
+function EvidenceDisplay({ evidence }) {
+  if (!evidence?.length) return null;
+  const arr = Array.isArray(evidence) ? evidence : [evidence];
+
+  const evidenceLabels = {
+    direct_observation: "👁 Direct Observation",
+    reported_statement: "🗣 Reported Statement",
+    interpretation: "💡 Interpretation",
+    assumption: "❓ Assumption",
+    inferred_relationship: "🔗 Inferred Relationship",
+  };
+
+  return (
+    <div className="mb-4 rounded-lg border border-gray-200 bg-white p-4">
+      <h3 className="mb-2 text-sm font-semibold text-gray-600">
+        Supporting Evidence ({arr.length})
+      </h3>
+      <ul className="space-y-2">
+        {arr.map((item, idx) => (
+          <li
+            key={item.id || `${idx}`}
+            className="rounded border border-gray-200 bg-white px-3 py-2 text-sm leading-relaxed"
+          >
+            <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"}`}
+              >
+                {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">
+                {evidenceLabels[item.evidenceType] || item.evidenceType}
+              </span>
+              {item.confidence && <ConfidenceBadge level={item.confidence} />}
+            </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>
+            )}
+          </li>
+        ))}
+      </ul>
+    </div>
+  );
+}
+
+// ── Main component ──────────────────────────────────
 export default function ReconstructionView({ reconstruction, partial }) {
+  // Handle both v0.2 direct object and wrapped result formats
+  const data = reconstruction;
+
  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>
    );
  }

-  const categories = Object.entries(categoryLabels).map(([key, label]) => ({
-    key,
-    label,
-    items: reconstruction[key],
-  }));
-
  return (
-    <div className="space-y-1">
-      <h2 className="mb-3 text-lg font-semibold">Reconstruction</h2>
-      {categories.map(({ key, label, items }) => (
-        <div key={key} className="mb-4 rounded border border-gray-200 bg-white p-4">
-          <h3 className="mb-2 text-sm font-medium text-gray-600">{label}</h3>
-          <ItemList items={items} />
-        </div>
-      ))}
+    <div className="space-y-4">
+      {/* Classification first */}
+      {data.inputClassification && (
+        <ClassificationDisplay classification={data.inputClassification} />
+      )}
+
+      {/* Summary */}
+      {data.reconstruction?.summary && (
+        <SummaryDisplay reconstruction={data.reconstruction} />
+      )}
+
+      {/* Key differences */}
+      {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>
+              )
+            }
+          />
+        )}
+
+      {/* 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}
+          />
+        )}
+
+      {/* Plausible interpretations */}
+      {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 &ldquo;{i.previousState}&rdquo; → To &ldquo;{i.currentState}&rdquo; (&quot;{i.explanationStatus}&quot;)
+              </div>
+            )}
+          />
+        )}
+
+      {/* Next question — prominent */}
+      <NextQuestionDisplay question={data.nextQuestion} />
+
+      {/* Evidence */}
+      {data.evidence && <EvidenceDisplay evidence={data.evidence} />}
    </div>
  );
 }
@@ -8,7 +8,7 @@ const MAX_LENGTH = 10000;

 export default function ScenarioForm() {
  const [scenario, setScenario] = useState("");
-  const [status, setStatus] = useState("idle"); // idle | loading | error | success
+  const [status, setStatus] = useState("idle"); // idle | loading | error | success | partial
  const [result, setResult] = useState(null);
  const textareaRef = useRef(null);

@@ -29,6 +29,10 @@ export default function ScenarioForm() {
      if (res.ok && data.validationStatus === "valid") {
        setStatus("success");
        setResult(data);
+      } else if (data.success) {
+        // Success in analysis but validation may be partial
+        setStatus("success");
+        setResult(data);
      } else {
        setStatus("error");
        setResult(data);
@@ -39,8 +43,13 @@ export default function ScenarioForm() {
    }
  };

-  // Always show diagnostics when there's a result (even if validation failed)
-  const hasDiagnostics = result && (result.reconstruction || result.modelName || result.responseDurationMs !== undefined);
+  // Determine if we have meaningful content to display
+  const hasClassification = result?.inputClassification;
+  const hasReconstruction = result?.reconstruction;
+  const hasNextQuestion = result?.nextQuestion;
+  const hasEvidence = result?.evidence && result.evidence.length > 0;
+  const hasMeaningfulContent =
+    hasClassification || hasReconstruction || hasNextQuestion || hasEvidence;

  return (
    <div className="space-y-6">
@@ -54,7 +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()}
@@ -65,6 +76,7 @@ export default function ScenarioForm() {
        </div>
      </form>

+      {/* Error state */}
      {status === "error" && (
        <div className="space-y-3">
          {result?.error && (
@@ -72,35 +84,51 @@ export default function ScenarioForm() {
              Error: {result.error}
            </div>
          )}
-          {hasDiagnostics && result?.modelName && (
-            <dl className="grid grid-cols-[auto_1fr] gap-x-4 gap-y-1.5 text-sm">
-              <dt className="text-gray-500">Model</dt>
-              <dd>{result.modelName}</dd>
-              <dt className="text-gray-500">Duration</dt>
-              <dd>{result.responseDurationMs != null ? `${result.responseDurationMs}ms` : "?"}</dd>
-            </dl>
+          {/* 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.
+            </div>
+          )}
+          {hasReconstruction && (
+            <ReconstructionView reconstruction={result} partial />
          )}
        </div>
      )}

-      {status === "success" && result?.reconstruction && (
+      {/* Success state */}
+      {status === "success" && hasMeaningfulContent && (
        <div className="space-y-4">
-          <ReconstructionView reconstruction={result.reconstruction} />
-          <DiagnosticsView result={result} />
+          <ReconstructionView reconstruction={result} />
        </div>
      )}

-      {status === "error" && result?.reconstruction && (
-        <div className="space-y-3">
-          <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.
-          </div>
-          <ReconstructionView reconstruction={result.reconstruction} partial />
-        </div>
+      {/* Always show diagnostics when we have any result */}
+      {(hasClassification || hasReconstruction || hasNextQuestion) && (
+        <DiagnosticsView result={result} />
      )}

      {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>
+        </div>
+      )}
+
+      {/* Invalid result with no partial data */}
+      {status === "error" && !result?.error && !hasMeaningfulContent && (
+        <div className="rounded-lg border border-yellow-300 bg-yellow-50 px-4 py-2 text-sm text-yellow-800">
+          Validation failed — no structured output was produced.
+        </div>
      )}
    </div>
  );
@@ -0,0 +1,182 @@
+/**
+ * Core analysis pipeline — shared by API routes and evaluation harness.
+ * Calls the provider, parses output, validates against Zod schemas (v0.2 first, v0.1 fallback).
+ */
+
+import { getConfig } from "../lib/config.js";
+import { getProvider } from "../lib/llm/provider.js";
+import { buildPrompt, PROMPT_VERSIONS } from "../lib/reconstruction/prompt.js";
+import {
+  reconstructionV2Schema,
+  reconstructionSchema as reconstructionV1Schema,
+} from "../lib/reconstruction/schema.js";
+
+const MAX_SCENARIO_LENGTH = 10000;
+const DEFAULT_PROMPT_VERSION = "v0.2";
+
+/**
+ * Analyse a scenario string through the full pipeline.
+ * @param {string} scenario - The scenario text to analyse
+ * @param {object} [opts]
+ * @param {"v0.1" | "v0.2"} [opts.promptVersion="v0.2"] - Prompt version to use
+ * @returns {Promise<object>} Analysis result with diagnostics
+ */
+export async function analyseScenario(scenario, opts = {}) {
+  const startTime = Date.now();
+
+  // ── Input validation ───────────────────────────────
+  if (typeof scenario !== "string") {
+    return buildErrorResponse("Input must be a string", startTime);
+  }
+
+  const trimmed = scenario.trim();
+  if (trimmed.length === 0) {
+    return buildErrorResponse("Scenario cannot be empty", startTime);
+  }
+  if (trimmed.length > MAX_SCENARIO_LENGTH) {
+    return buildErrorResponse(`Scenario must be under ${MAX_SCENARIO_LENGTH} characters`, startTime);
+  }
+
+  // ── Configuration check ────────────────────────────
+  const configResult = getConfig();
+  if (!configResult.ok) {
+    return buildErrorResponse("Invalid server configuration", startTime, "500");
+  }
+
+  const { OLLAMA_BASE_URL: _ignored, OLLAMA_MODEL } = configResult.config;
+  const promptVersion = opts.promptVersion || DEFAULT_PROMPT_VERSION;
+
+  // ── Build prompt ───────────────────────────────────
+  let promptObj;
+  try {
+    promptObj = await buildPrompt(trimmed, promptVersion);
+  } catch (e) {
+    return buildErrorResponse(`Failed to build prompt: ${e.message}`, startTime);
+  }
+
+  // ── Call provider ──────────────────────────────────
+  const provider = getProvider();
+  let rawResponse;
+  try {
+    rawResponse = await provider.generateReconstruction(promptObj.prompt, OLLAMA_MODEL);
+  } catch (e) {
+    return buildErrorResponse(
+      e.message || "Provider error during analysis",
+      Date.now() - startTime
+    );
+  }
+
+  const duration = Date.now() - startTime;
+
+  // Try to capture raw response for diagnostics
+  let rawResponseStr;
+  try {
+    rawResponseStr = JSON.stringify(rawResponse);
+  } catch {
+    rawResponseStr = String(rawResponse).slice(0, 2000);
+  }
+
+  // ── Validate against v0.2 schema (preferred) ──────
+  const resultV2 = tryValidateAgainstSchema(rawResponse, reconstructionV2Schema);
+  if (resultV2.valid) {
+    return buildSuccessResultV2(resultV2.data, OLLAMA_MODEL, duration, promptVersion);
+  }
+
+  // ── Fallback to v0.1 schema ────────────────────────
+  const resultV1 = tryValidateAgainstSchema(rawResponse, reconstructionV1Schema);
+  if (resultV1.valid) {
+    return buildSuccessResultV1(resultV1.data, OLLAMA_MODEL, duration, promptVersion);
+  }
+
+  // ── Neither schema matched — partial failure ───────
+  return buildPartialResult(
+    rawResponseStr?.slice(0, 2000),
+    resultV2.error ?? resultV1.error,
+    OLLAMA_MODEL,
+    duration,
+    promptVersion
+  );
+}
+
+/** Attempt validation against a Zod schema */
+function tryValidateAgainstSchema(data, schema) {
+  if (!schema.safeParse) {
+    return { valid: false, error: new Error("Schema does not support safeParse") };
+  }
+  const result = schema.safeParse(data);
+  return result.success ? { valid: true, data: result.data } : { valid: false, error: result.error };
+}
+
+// ── Result builders ──────────────────────────────────
+
+function buildErrorResponse(message, elapsed, statusCode = 500) {
+  return {
+    success: false,
+    error: message,
+    modelName: null,
+    responseDurationMs: elapsed,
+    validationStatus: "invalid",
+    rawResponse: null,
+    promptVersion: null,
+    statusCode,
+  };
+}
+
+function buildSuccessResultV2(data, model, duration, version) {
+  return {
+    success: true,
+    validationStatus: "valid",
+    modelName: model,
+    responseDurationMs: duration,
+    rawResponse: JSON.stringify(data).slice(0, 3000),
+    promptVersion: version,
+    inputClassification: data.inputClassification,
+    reconstruction: data.reconstruction,
+    evidence: data.evidence,
+    nextQuestion: data.nextQuestion,
+    errors: undefined,
+  };
+}
+
+function buildSuccessResultV1(data, model, duration, version) {
+  return {
+    success: true,
+    validationStatus: "valid",
+    modelName: model,
+    responseDurationMs: duration,
+    rawResponse: JSON.stringify(data).slice(0, 3000),
+    promptVersion: version,
+    inputClassification: null,
+    reconstruction: data,
+    evidence: undefined,
+    nextQuestion: undefined,
+    errors: undefined,
+  };
+}
+
+function buildPartialResult(rawResp, error, model, duration, version) {
+  let errors = [];
+  if (error && typeof error.flatten === "function") {
+    errors = error.flatten().fieldErrors
+      ? Object.entries(error.flatten().fieldErrors).flatMap(([k, v]) => [`${k}: ${v.join(", ")}`])
+      : [String(error)];
+  } else if (error) {
+    errors = [String(error).slice(0, 500)];
+  }
+
+  return {
+    success: false,
+    validationStatus: "invalid",
+    modelName: model,
+    responseDurationMs: duration,
+    rawResponse: rawResp?.slice(0, 2000),
+    promptVersion: version,
+    inputClassification: null,
+    reconstruction: null,
+    evidence: undefined,
+    nextQuestion: undefined,
+    errors,
+  };
+}
+
+export { PROMPT_VERSIONS, DEFAULT_PROMPT_VERSION };
@@ -93,11 +93,9 @@ async function detectChatSupport(baseUrl) {

 class OllamaLlmProvider {
  async generateReconstruction(scenario, modelName) {
-    const { buildPrompt } = await import("@/lib/reconstruction/prompt");
-    
-    let rawPrompt = buildPrompt(scenario);
-    // Stronger JSON hint since we can't use format:json on older Ollama
-    const prompt = rawPrompt + `\n\nReturn ONLY a valid JSON object starting with { and ending with }. Do NOT include any text before the opening brace or after the closing brace. Do NOT wrap in markdown backticks.`;
+    // scenario is ALREADY a fully-built prompt text (built by analyseScenario).
+    // Do NOT call buildPrompt() again — that would double-wrap the prompt.
+    const prompt = scenario;

    const baseUrl = process.env.OLLAMA_BASE_URL;
    if (!baseUrl) throw new Error("OLLAMA_BASE_URL is not set");
@@ -1,4 +1,16 @@
-export function buildPrompt(scenario) {
+import { promises as fs } from "node:fs";
+import { fileURLToPath } from "node:url";
+import { dirname, join } from "node:path";
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = dirname(__filename);
+const PROMPTS_DIR = join(__dirname, "../../prompts");
+
+/** Available prompt versions */
+export const PROMPT_VERSIONS = ["v0.1", "v0.2"];
+
+/** Build a v0.1 (extraction-only) prompt inline for backward compatibility */
+function buildV1Prompt(scenario) {
  return `You are a neutral analyst performing an evidence-based reconstruction of the following scenario.

 Rules:
@@ -29,3 +41,38 @@ Return valid JSON matching this structure exactly:

 Return ONLY the JSON object. No markdown, no explanation, no preamble.`;
 }
+
+/** Load a versioned prompt from disk and substitute {{SCENARIO}} */
+async function buildV2Prompt(scenario) {
+  try {
+    const content = await fs.readFile(
+      join(PROMPTS_DIR, "reconstruct-v0.2.md"),
+      "utf-8",
+    );
+    return content.replace("{{SCENARIO}}", scenario);
+  } catch {
+    // Fall back to v0.1 prompt if v0.2 file is missing
+    return buildV1Prompt(scenario);
+  }
+}
+
+/**
+ * Build an analysis prompt for the given version.
+ * @param {"v0.1" | "v0.2"} [version="v0.2"]
+ * @returns {Promise<{prompt: string, version: string}>}
+ */
+export async function buildPrompt(scenario, version = "v0.2") {
+  let prompt;
+  switch (version) {
+    case "v0.1":
+      prompt = buildV1Prompt(scenario);
+      break;
+    default: // v0.2
+      prompt = await buildV2Prompt(scenario);
+      break;
+  }
+
+  const strongJsonHint =
+    "\n\nReturn ONLY a valid JSON object starting with { and ending with }. Do NOT include any text before the opening brace or after the closing brace. Do NOT wrap in markdown backticks.";
+  return { prompt: prompt + strongJsonHint, version };
+}
@@ -1,38 +1,59 @@
 import { z } from "zod";

-const confidenceEnum = z.enum(["low", "medium", "high"]);
+// ──────────────────────────────────────────────
+// Shared enums (v0.1 & v0.2)
+// ──────────────────────────────────────────────

-const itemSchema = z.object({
+export const confidenceEnum = z.enum(["low", "medium", "high"]);
+const importanceEnum = z.enum([
+  "incidental",
+  "supporting",
+  "important",
+  "critical",
+]);
+const expectedInfoValueEnum = z.enum(["low", "medium", "high"]);
+
+// ──────────────────────────────────────────────
+// v0.1 — extraction-only schema (preserved)
+// ──────────────────────────────────────────────
+
+const confidenceEnumV1 = z.enum(["low", "medium", "high"]);
+
+const itemSchemaV1 = z.object({
  id: z.string().min(1),
  description: z.string().min(1),
-  confidence: confidenceEnum,
+  confidence: confidenceEnumV1,
 });

 export const reconstructionSchema = z.object({
-  observations: z.array(itemSchema),
+  observations: z.array(itemSchemaV1),
  reportedClaims: z.array(
-    itemSchema.extend({
-      attributedTo: z.union([z.string().min(1), z.null()]).optional().nullable(),
-    })
+    itemSchemaV1.extend({
+      attributedTo: z
+        .union([z.string().min(1), z.null()])
+        .optional()
+        .nullable(),
+    }),
  ),
-  assumptions: z.array(itemSchema),
-  entities: z.array(itemSchema),
+  assumptions: z.array(itemSchemaV1),
+  entities: z.array(itemSchemaV1),
  transitions: z.array(
-    itemSchema.extend({
+    itemSchemaV1.extend({
      entity: z.string().min(1),
      previousState: z.string().min(1),
      currentState: z.string().min(1),
      explanationStatus: z.string().min(1),
-    })
+    }),
  ),
-  expectedButMissing: z.array(itemSchema),
-  presentButUnexpected: z.array(itemSchema),
-  contradictions: z.array(itemSchema),
-  openUncertainties: z.array(itemSchema),
+  expectedButMissing: z.array(itemSchemaV1),
+  presentButUnexpected: z.array(itemSchemaV1),
+  contradictions: z.array(itemSchemaV1),
+  openUncertainties: z.array(itemSchemaV1),
 });

+// v0.1 analyse response (used internally)
 export const analyseResponseSchema = z.object({
-  reconstruction: reconstructionSchema,
+  reconstruction: z.union([reconstructionSchema, z.null()]),
  modelName: z.string(),
  responseDurationMs: z.number(),
  validationStatus: z.enum(["valid", "partial", "invalid"]),
@@ -48,6 +69,141 @@ export const healthResponseSchema = z.object({
  error: z.string().nullable(),
 });

+// ──────────────────────────────────────────────
+// v0.2 — reasoning classification + reconstruction
+// ──────────────────────────────────────────────
+
+export const inputTypes =
+  /** @type {z.ZodType<typeof import("@/lib/reconstruction/schema").INPUT_TYPE_VALUE>} */ (
+    z.enum([
+      "observed_problem",
+      "unexplained_change",
+      "contradiction",
+      "decision_request",
+      "causal_claim",
+      "reported_claim",
+      "fault_report",
+      "ambiguous_statement",
+      "question",
+      "desired_outcome",
+      "insufficient_context",
+      "other",
+    ])
+  );
+
+export const reasoningModes =
+  /** @type {z.ZodType<typeof import("@/lib/reconstruction/schema").REASONING_MODE_VALUE>} */ (
+    z.enum([
+      "establish_baseline",
+      "identify_difference",
+      "reconstruct_transition",
+      "decompose_aggregate",
+      "validate_measurement",
+      "validate_claim",
+      "investigate_contradiction",
+      "clarify_meaning",
+      "decision_support",
+      "fault_investigation",
+      "identify_missing_information",
+      "test_possible_explanations",
+      "other",
+    ])
+  );
+
+const evidenceRecordSchema = z.object({
+  id: z.string().min(1),
+  description: z.string().min(1),
+  evidenceType: z.enum([
+    "direct_observation",
+    "reported_statement",
+    "interpretation",
+    "assumption",
+    "inferred_relationship",
+  ]),
+  source: z.string().optional(),
+  attribution: z.string().nullable().optional(),
+  confidence: confidenceEnum,
+  importance: importanceEnum,
+});
+
+const reconstructionSchemaV2 = z.object({
+  summary: z.string().min(1),
+  actors: z.array(itemSchemaV1),
+  systemsOrObjects: z.array(itemSchemaV1),
+  expectedStates: z.array(itemSchemaV1),
+  observedStates: z.array(itemSchemaV1),
+  differences: z.array(itemSchemaV1),
+  knownTransitions: z.array(
+    itemSchemaV1.extend({
+      entity: z.string().min(1),
+      previousState: z.string().min(1),
+      currentState: z.string().min(1),
+      explanationStatus: z.string().min(1),
+    }),
+  ),
+  unexplainedTransitions: z.array(
+    itemSchemaV1.extend({
+      entity: z.string().min(1).optional(),
+      previousState: z.string().min(1).optional(),
+      currentState: z.string().min(1).optional(),
+    }),
+  ),
+  contradictions: z.array(itemSchemaV1),
+  importantUnknowns: z.array(itemSchemaV1),
+  plausibleInterpretations: z.array(
+    z.object({
+      id: z.string().min(1),
+      description: z.string().min(1),
+      supportingEvidenceIds: z.array(z.string()),
+      assumptionsRequired: z.array(z.string()).optional().default([]),
+      confidence: confidenceEnum,
+    }),
+  ),
+});
+
+const inputClassificationSchema = z.object({
+  primaryType: inputTypes,
+  secondaryTypes: z.array(inputTypes).optional().default([]),
+  reasoningModes: z.array(reasoningModes).optional().default([]),
+  classificationReason: z.string().min(1),
+  confidence: confidenceEnum,
+});
+
+const nextQuestionSchema = z.object({
+  id: z.string().min(1),
+  question: z.string().min(1),
+  targets: z.array(z.string()),
+  reason: z.string().min(1),
+  expectedInformationValue: expectedInfoValueEnum,
+  reasoningMode: reasoningModes.optional().default("other"),
+});
+
+// v0.2 complete analysis response (what the model produces)
+export const reconstructionV2Schema = z.object({
+  inputClassification: inputClassificationSchema,
+  reconstruction: reconstructionSchemaV2,
+  evidence: z.array(evidenceRecordSchema),
+  nextQuestion: nextQuestionSchema,
+});
+
+// Outer wrapper for API return (includes diagnostics + v0.2 data)
+export const analyseResponseV2Schema = z.object({
+  inputClassification: inputClassificationSchema.optional(),
+  reconstruction: reconstructionSchemaV2.optional().nullable(),
+  evidence: z.array(evidenceRecordSchema).optional(),
+  nextQuestion: nextQuestionSchema.optional(),
+  modelName: z.string(),
+  responseDurationMs: z.number(),
+  validationStatus: z.enum(["valid", "partial", "invalid"]),
+  rawResponse: z.string().optional(),
+  errors: z.array(z.string()).optional(),
+  promptVersion: z.string().optional(),
+});
+
+// ──────────────────────────────────────────────
+// Parsing helpers
+// ──────────────────────────────────────────────
+
 export function parseReconstruction(raw) {
  if (typeof raw === "string") {
    try {
@@ -58,3 +214,14 @@ export function parseReconstruction(raw) {
  }
  return reconstructionSchema.parse(raw);
 }
+
+export function parseReconstructionV2(raw) {
+  if (typeof raw === "string") {
+    try {
+      raw = JSON.parse(raw);
+    } catch {
+      throw new SyntaxError("Model response is not valid JSON");
+    }
+  }
+  return reconstructionV2Schema.parse(raw);
+}
@@ -1,7 +1,7 @@
 {
  "type": "module",
  "name": "confidence-engine",
-  "version": "0.1.0",
+  "version": "0.2.0-experimental",
  "private": true,
  "description": "Experimental prototype for evidence-based situation reconstruction using local LLMs",
  "scripts": {
@@ -0,0 +1,122 @@
+You are a neutral analyst performing evidence-based situation reconstruction.
+
+## Rules
+
+1. Do NOT invent facts, context or causes. Only include information present in the scenario or clearly implied.
+2. First determine what kind of input has been supplied. Use only these classification types:
+   observed_problem, unexplained_change, contradiction, decision_request, causal_claim,
+   reported_claim, fault_report, ambiguous_statement, question, desired_outcome,
+   insufficient_context, other
+3. Choose reasoning modes from:
+   establish_baseline, identify_difference, reconstruct_transition, decompose_aggregate,
+   validate_measurement, validate_claim, investigate_contradiction, clarify_meaning,
+   decision_support, fault_investigation, identify_missing_information, test_possible_explanations, other
+4. Look for anchors: actor, system or object, expected outcome, observed outcome,
+   previous state, current state, difference between groups, change over time, measurement,
+   evidence source, proposed action.
+5. Identify meaningful differences (e.g., some succeed while others fail; revenue rises while cash falls).
+6. Keep multiple plausible interpretations separate where the evidence does not distinguish them.
+7. Distinguish: what was said / what it may mean / why it may have been said.
+8. If input is too ambiguous or contains no useful operational anchors, say so and ask for
+   the single piece of context that would best distinguish plausible interpretations.
+
+## Confidence scale
+
+- low — weak evidence, speculation, or missing information
+- medium — reasonable inference from available evidence
+- high — strong evidence, direct observation, or confirmed fact
+
+## Importance scale (evidence records)
+
+- incidental — minor detail, unlikely to affect conclusions
+- supporting — adds context but not critical
+- important — materially affects understanding of the situation
+- critical — essential to resolving the situation; without it conclusions cannot be drawn
+
+## Expected information value (next question)
+
+- low — marginally useful even if answered
+- medium — meaningfully clarifies the situation
+- high — would significantly distinguish between plausible explanations or fill a gap in understanding
+
+## Next question selection criteria
+
+Prefer questions that:
+- clarify a major difference
+- establish a baseline
+- explain an important transition
+- test an unsupported claim
+- distinguish between plausible explanations
+- request measurable evidence
+- identify who or what is affected
+- establish timing
+
+Avoid questions that:
+- have already been answered
+- assume a cause
+- jump to a solution
+- ask about motive before the observable situation is understood
+- focus on incidental wording
+- are too broad to produce useful information
+- combine many unrelated questions
+
+## Output format — return this exact JSON structure
+
+Return a JSON object with exactly these four top-level keys (use **camelCase**):
+
+```json
+{
+  "inputClassification": {
+    "primaryType": "<one of: observed_problem, unexplained_change, contradiction, decision_request, causal_claim, reported_claim, fault_report, ambiguous_statement, question, desired_outcome, insufficient_context, other>",
+    "secondaryTypes": ["<optional additional types from the same list>"],
+    "reasoningModes": ["<one or more of: establish_baseline, identify_difference, reconstruct_transition, decompose_aggregate, validate_measurement, validate_claim, investigate_contradiction, clarify_meaning, decision_support, fault_investigation, identify_missing_information, test_possible_explanations, other>"],
+    "classificationReason": "<brief explanation of why you chose the primary type>",
+    "confidence": "<low | medium | high>"
+  },
+  "reconstruction": {
+    "summary": "<one-sentence overview of the situation>",
+    "actors": [{"id": "<any unique string>", "description": "...", "confidence": "<low|medium|high>"}],
+    "systemsOrObjects": [{"id": "<any unique string>", "description": "...", "confidence": "<low|medium|high>"}],
+    "expectedStates": [{"id": "...", "description": "...", "confidence": "<low|medium|high>"}],
+    "observedStates": [{"id": "...", "description": "...", "confidence": "<low|medium|high>"}],
+    "differences": [{"id": "...", "description": "...", "confidence": "<low|medium|high>"}],
+    "knownTransitions": [{"id": "...", "description": "...", "confidence": "<low|medium|high>", "entity": "...", "previousState": "...", "currentState": "...", "explanationStatus": "..."}],
+    "unexplainedTransitions": [{"id": "...", "description": "...", "confidence": "<low|medium|high>", "entity": "...", "previousState": "...", "currentState": "..."}],
+    "contradictions": [{"id": "...", "description": "...", "confidence": "<low|medium|high>"}],
+    "importantUnknowns": [{"id": "...", "description": "...", "confidence": "<low|medium|high>"}],
+    "plausibleInterpretations": [{"id": "...", "description": "...", "supportingEvidenceIds": ["<ids that support this interpretation>"], "assumptionsRequired": [], "confidence": "<low|medium|high>"}]
+  },
+  "evidence": [
+    {
+      "id": "<any unique string>",
+      "description": "...",
+      "evidenceType": "<direct_observation | reported_statement | interpretation | assumption | inferred_relationship>",
+      "source": "<optional — who/where this came from>",
+      "attribution": null,
+      "confidence": "<low | medium | high>",
+      "importance": "<incidental | supporting | important | critical>"
+    }
+  ],
+  "nextQuestion": {
+    "id": "<any unique string>",
+    "question": "<one precise question>",
+    "targets": ["<what this question targets — e.g. 'actor', 'system', 'expectedOutcome'>"],
+    "reason": "<why answering this is important>",
+    "expectedInformationValue": "<low | medium | high>",
+    "reasoningMode": "<optional reasoning mode from the list above>"
+  }
+}
+```
+
+CRITICAL RULES for JSON output:
+1. Use **exactly** the key names shown above (camelCase, no snake_case).
+2. The four top-level keys must be: `inputClassification`, `reconstruction`, `evidence`, `nextQuestion`.
+3. Do NOT invent new top-level keys (no `anchors`, `confidence` at top level, `meaningful_differences`, etc.).
+4. Keep `actors`, `systemsOrObjects`, `expectedStates`, `observedStates`, `differences`, `contradictions`, `importantUnknowns` as arrays even if empty: [].
+5. Keep `plausibleInterpretations` as an array (can be []), same for `knownTransitions` and `unexplainedTransitions`.
+6. Each object in arrays must have at least `id`, `description`, `confidence`.
+
+Scenario:
+{{SCENARIO}}
+
+Return ONLY the JSON object starting with { and ending with }. Do NOT include any text before the opening brace or after the closing brace. Do NOT wrap in markdown backticks.