Files
confidence-engine/app/api/analyse/route.js
T
robbond a0bcb12792 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)
2026-08-01 13:39:01 +01:00

50 lines
1.4 KiB
JavaScript

import {
analyseScenario,
PROMPT_VERSIONS,
DEFAULT_PROMPT_VERSION,
} from "@/lib/analysis";
export async function POST(request) {
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 },
);
}
// Optional prompt version override
let promptVersion = DEFAULT_PROMPT_VERSION;
if (body.promptVersion && PROMPT_VERSIONS.includes(body.promptVersion)) {
promptVersion = body.promptVersion;
}
const result = await analyseScenario(body.scenario, { promptVersion });
if (!result.success) {
return Response.json(
{ ...result, reconstruction: result.reconstruction || null },
{ status: Number(result.statusCode) || 500 },
);
}
return Response.json({
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) {
return Response.json(
{ error: e.message || "Unknown server error", responseDurationMs: 0 },
{ status: 500 },
);
}
}