mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-31 04:07:52 +00:00
Garry TanandClaude Opus 5
683b7665f2
`detail` is result-affecting by design — it gates dedup, chunk-source filtering, and the compiled_truth boost — but was absent from knobsHash, the only thing that varies the query-cache key. A `--detail low` write (compiled-truth-only result set) was served to a default `medium` lookup for the whole TTL (3600s), silently, looking like a relevance problem. Same contamination class as [CDX-4], the v=2→3 floor_ratio/col/prov additions, and the v=9→10 relationalRetrieval fold. Fix: append `det=` to the knobsHash parts list (append-only, per the list's own convention) and bump KNOBS_HASH_VERSION 13→15. detail is a per-call SearchOpts value, not a mode knob, so it threads through KnobsHashContext the way col=/prov= do; hybridSearchCached passes the EFFECTIVE level (opts.detail ?? autoDetectDetail(query)) so an auto-detected `high` query keys like an explicit `high` one. Undefined falls back to 'medium' (the documented default). v=14 is claimed by in-flight PR #3514 (#3430); this lands as v=15 per the established D8 sequencing convention. All five KNOBS_HASH_VERSION pin sites updated. One-time cache cold-miss on upgrade, refills within cache.ttl_seconds — same as every prior bump. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
96 lines
3.8 KiB
TypeScript
96 lines
3.8 KiB
TypeScript
// v0.42 Type Unification (T32) — alias_resolved search boost stage.
|
|
//
|
|
// Coverage: pages whose slug is a canonical_slug in slug_aliases get 1.05x
|
|
// score multiplier; non-alias-canonical pages unchanged; stage stamps
|
|
// alias_resolved_boost field for --explain; KNOBS_HASH_VERSION bumped.
|
|
|
|
import { afterAll, beforeAll, beforeEach, describe, expect, it } from 'bun:test';
|
|
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
|
import { resetPgliteState } from './helpers/reset-pglite.ts';
|
|
import { runPostFusionStages, type PostFusionOpts } from '../src/core/search/hybrid.ts';
|
|
import { KNOBS_HASH_VERSION } from '../src/core/search/mode.ts';
|
|
import type { SearchResult } from '../src/core/types.ts';
|
|
|
|
let engine: PGLiteEngine;
|
|
|
|
beforeAll(async () => {
|
|
engine = new PGLiteEngine();
|
|
await engine.connect({});
|
|
await engine.initSchema();
|
|
});
|
|
|
|
afterAll(async () => {
|
|
await engine.disconnect();
|
|
});
|
|
|
|
beforeEach(async () => {
|
|
await resetPgliteState(engine);
|
|
});
|
|
|
|
const noopPostFusionOpts: PostFusionOpts = {
|
|
applyBacklinks: false,
|
|
salience: 'off',
|
|
recency: 'off',
|
|
graphSignalsEnabled: false,
|
|
};
|
|
|
|
describe('alias_resolved boost stage', () => {
|
|
it('applies 1.05x multiplier to pages that are canonicals of aliases', async () => {
|
|
// Insert an alias pointing at canonical-page
|
|
await engine.executeRaw(
|
|
`INSERT INTO slug_aliases (source_id, alias_slug, canonical_slug) VALUES ('default', 'old-name', 'canonical-page')`,
|
|
);
|
|
const results: SearchResult[] = [
|
|
{
|
|
slug: 'canonical-page', source_id: 'default', score: 1.0,
|
|
chunk_id: 1, page_id: 1, chunk_text: '', chunk_index: 0,
|
|
title: 'Canonical', type: 'concept' as never, slug_lower: 'canonical-page',
|
|
} as unknown as SearchResult,
|
|
{
|
|
slug: 'plain-page', source_id: 'default', score: 1.0,
|
|
chunk_id: 2, page_id: 2, chunk_text: '', chunk_index: 0,
|
|
title: 'Plain', type: 'concept' as never, slug_lower: 'plain-page',
|
|
} as unknown as SearchResult,
|
|
];
|
|
await runPostFusionStages(engine, results, noopPostFusionOpts);
|
|
// canonical-page gets 1.05x boost
|
|
expect(results[0].score).toBeCloseTo(1.05, 5);
|
|
expect(results[0].alias_resolved_boost).toBe(1.05);
|
|
// plain-page unchanged
|
|
expect(results[1].score).toBeCloseTo(1.0, 5);
|
|
expect(results[1].alias_resolved_boost).toBeUndefined();
|
|
});
|
|
|
|
it('does not boost when no aliases exist', async () => {
|
|
const results: SearchResult[] = [{
|
|
slug: 'plain', source_id: 'default', score: 1.0,
|
|
chunk_id: 1, page_id: 1, chunk_text: '', chunk_index: 0,
|
|
title: 'p', type: 'concept' as never, slug_lower: 'plain',
|
|
} as unknown as SearchResult];
|
|
await runPostFusionStages(engine, results, noopPostFusionOpts);
|
|
expect(results[0].score).toBeCloseTo(1.0, 5);
|
|
expect(results[0].alias_resolved_boost).toBeUndefined();
|
|
});
|
|
|
|
it('is source-scoped (F9): alias in source A does not boost in source B', async () => {
|
|
await engine.executeRaw(`INSERT INTO sources (id, name) VALUES ('alt', 'alt') ON CONFLICT DO NOTHING`);
|
|
await engine.executeRaw(
|
|
`INSERT INTO slug_aliases (source_id, alias_slug, canonical_slug) VALUES ('alt', 'old', 'shared')`,
|
|
);
|
|
// Same slug, different source — should NOT be boosted (alias is in 'alt')
|
|
const results: SearchResult[] = [{
|
|
slug: 'shared', source_id: 'default', score: 1.0,
|
|
chunk_id: 1, page_id: 1, chunk_text: '', chunk_index: 0,
|
|
title: 's', type: 'concept' as never, slug_lower: 'shared',
|
|
} as unknown as SearchResult];
|
|
await runPostFusionStages(engine, results, noopPostFusionOpts);
|
|
expect(results[0].alias_resolved_boost).toBeUndefined();
|
|
});
|
|
});
|
|
|
|
describe('KNOBS_HASH_VERSION', () => {
|
|
it('is 15 (13→15 detail fold makes detail-contaminated rows unreachable, #3515; v=14 claimed by in-flight #3514)', () => {
|
|
expect(KNOBS_HASH_VERSION).toBe(15);
|
|
});
|
|
});
|