robbond
956fc2e31e
Two bugs were causing the model to return {"status":"ok"} / {"status":"ready"}
instead of structured reconstruction data, resulting in POST /api/analyse 500:
1. DOUBLE-WRAPPING BUG (lib/llm/provider.js):
generateReconstruction() called buildPrompt(scenario) on input that was
already a fully-built prompt string from analyseScenario(). This wrapped the
v0.1 prompt (~5000+ chars) in another template layer, producing incomprehensible
output that the model could not parse as structured JSON.
Fix: Pass scenario through directly (it is ALREADY a built prompt).
2. MISSING JSON SPEC (prompts/reconstruct-v0.2.md):
The v0.2 prompt template said 'matching the structure exactly' but never
defined what that structure was. The model invented its own field names
(input_classification, reasoning_mode, anchors) with snake_case instead of
camelCase, which failed Zod validation -> 500 errors.
Fix: Added explicit JSON schema section with exact key names, enum values,
and nested structure matching the Zod validation layer.
Additionally:
- Refactored route to use analyseScenario from lib/analysis (centralized)
- Added lib/analysis.js with shared analysis logic
- Updated components to display promptVersion and validation errors
- Added lib/reconstruction/prompt.js v0.1/v0.2 versioning
- Added lib/reconstruction/schema.js v0.2 Zod schemas
- Added debug tool scripts, evaluation results, and comparison findings
76 lines
2.5 KiB
React
76 lines
2.5 KiB
React
const ValidationIndicator = ({ status }) => {
|
|
const styles = {
|
|
valid: "text-green-600",
|
|
partial: "text-yellow-600",
|
|
invalid: "text-red-600",
|
|
};
|
|
const labels = {
|
|
valid: "✅ Validation passed",
|
|
partial: "⚠️ Partial validation",
|
|
invalid: "❌ Validation failed",
|
|
};
|
|
return (
|
|
<div className={`flex items-center gap-2 ${styles[status] || "text-gray-500"}`}>
|
|
<span className="font-medium">{labels[status] || status}</span>
|
|
</div>
|
|
);
|
|
};
|
|
|
|
const validationIcons = {
|
|
valid: "✅",
|
|
partial: "⚠️",
|
|
invalid: "❌",
|
|
};
|
|
|
|
export default function DiagnosticsView({ result }) {
|
|
if (!result) return null;
|
|
|
|
const metrics = [
|
|
{ label: "Model", value: result.modelName || "?" },
|
|
{ label: "Provider", value: "Ollama" },
|
|
{ label: "Prompt version", value: result.promptVersion || "?" },
|
|
{ label: "Duration", value: result.responseDurationMs != null ? `${result.responseDurationMs}ms` : "?" },
|
|
{ label: "Validation", value: <ValidationIndicator status={result.validationStatus || "invalid"} /> },
|
|
];
|
|
|
|
return (
|
|
<div className="rounded border border-gray-200 bg-gray-50 p-4">
|
|
<h2 className="mb-3 text-sm font-semibold text-gray-500">Diagnostics</h2>
|
|
<dl className="grid grid-cols-[auto_1fr] gap-x-4 gap-y-1.5 text-sm">
|
|
{metrics.map(({ label, value }) => (
|
|
<div key={label}>
|
|
<dt className="text-gray-500">{label}</dt>
|
|
<dd>{value}</dd>
|
|
</div>
|
|
))}
|
|
</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 ({(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>
|
|
);
|
|
}
|