Complete production implementation with shell+adapter architecture, 13 MCP tools, SQLite FTS5 search, and multi-source ingestion pipeline. Ingestion fetches from UCI mirror, UNODC SHERLOC PDFs, and Knesset mobile PDFs (135 provisions, 33 definitions). 3 acts with full text, 7 acts metadata-only due to gov.il/nevo.co.il access restrictions. Knesset OData API used for metadata enrichment. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
86 lines
2.3 KiB
TypeScript
86 lines
2.3 KiB
TypeScript
#!/usr/bin/env tsx
|
|
/**
|
|
* Drift detection for Israel Law MCP.
|
|
*
|
|
* Checks if upstream Knesset/gov.il content has changed since last ingestion.
|
|
* Uses the golden-hashes.json fixture to verify content integrity.
|
|
*/
|
|
|
|
import { readFileSync } from 'fs';
|
|
import { join, dirname } from 'path';
|
|
import { fileURLToPath } from 'url';
|
|
|
|
const __dirname = dirname(fileURLToPath(import.meta.url));
|
|
const hashesPath = join(__dirname, '../fixtures/golden-hashes.json');
|
|
|
|
interface GoldenHash {
|
|
id: string;
|
|
description: string;
|
|
upstream_url: string;
|
|
expected_sha256: string;
|
|
expected_snippet: string;
|
|
}
|
|
|
|
interface HashFixture {
|
|
version: string;
|
|
provisions: GoldenHash[];
|
|
}
|
|
|
|
async function main(): Promise<void> {
|
|
console.log('Israel Law MCP -- Drift Detection');
|
|
console.log('=================================\n');
|
|
|
|
const fixture: HashFixture = JSON.parse(readFileSync(hashesPath, 'utf-8'));
|
|
console.log(`Checking ${fixture.provisions.length} provisions...\n`);
|
|
|
|
let passed = 0;
|
|
let failed = 0;
|
|
let skipped = 0;
|
|
|
|
for (const hash of fixture.provisions) {
|
|
if (hash.expected_sha256 === 'COMPUTE_ON_FIRST_INGEST') {
|
|
console.log(` SKIP ${hash.id}: Not yet ingested`);
|
|
skipped++;
|
|
continue;
|
|
}
|
|
|
|
try {
|
|
const response = await fetch(hash.upstream_url, {
|
|
headers: { 'User-Agent': 'Israel-Law-MCP/1.0 drift-detect' },
|
|
});
|
|
|
|
if (response.status !== 200) {
|
|
console.log(` WARN ${hash.id}: HTTP ${response.status}`);
|
|
failed++;
|
|
continue;
|
|
}
|
|
|
|
const body = await response.text();
|
|
|
|
if (hash.expected_snippet && body.toLowerCase().includes(hash.expected_snippet.toLowerCase())) {
|
|
console.log(` OK ${hash.id}: Snippet found`);
|
|
passed++;
|
|
} else {
|
|
console.log(` DRIFT ${hash.id}: Expected snippet "${hash.expected_snippet}" not found`);
|
|
failed++;
|
|
}
|
|
} catch (error) {
|
|
const msg = error instanceof Error ? error.message : String(error);
|
|
console.log(` ERROR ${hash.id}: ${msg}`);
|
|
failed++;
|
|
}
|
|
}
|
|
|
|
console.log(`\nResults: ${passed} passed, ${failed} failed, ${skipped} skipped`);
|
|
|
|
if (failed > 0) {
|
|
console.log('\nDrift detected! Data may need re-ingestion.');
|
|
process.exit(1);
|
|
}
|
|
}
|
|
|
|
main().catch(error => {
|
|
console.error('Fatal error:', error);
|
|
process.exit(1);
|
|
});
|