mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 21:19:18 +00:00
* feat(dims): OpenAI text-embedding-3 Matryoshka range validation (D13) dimsProviderOptions now fail-loud at the embed boundary when the configured embedding_dimensions is outside the model's native range (1..1536 for -small, 1..3072 for -large). Paste-ready fix hint in the AIConfigError.fix field. Closes the silent-HTTP-400 path that would have bit OpenAI-fallback users on v0.36.0.0 ZE-default installs. 16 new test cases in test/ai/dims-openai.test.ts pinning the contract across native-openai and openai-compatible adapter paths. * feat(ai): flip defaults to ZeroEntropy zembed-1 1280d + zerank-2 reranker Default embedding model is now zeroentropyai:zembed-1 at 1280d via Matryoshka. Real-corpus benchmark: 2.2x faster than OpenAI, 2.6x cheaper at regular pricing, wins 11/20 head-to-head queries. 1280 is the closest valid ZE Matryoshka step to the prior OpenAI 1536d default (valid set: 2560/1280/640/320/160/80/40). 1024 (Voyage's step) is NOT on ZE's list — pinned by AIConfigError fail-loud in dims.ts. balanced mode bundle now defaults reranker_enabled=true. zerank-2 reshuffles 60% of top-1 results in benchmarks. Missing-key fail-open contract in src/core/search/rerank.ts handles unauthenticated cases. Opt out with: gbrain config set search.reranker.enabled false Existing tests updated (gateway.test.ts, search-mode.test.ts) and a new test/balanced-reranker-default.test.ts (10 cases) pins the fail- open invariants. * feat(retrieval-upgrade): RetrievalUpgradePlanner + interactive prompt UX New src/core/retrieval-upgrade-planner.ts is the consolidated planner that computes the brain's pending retrieval-upgrade work (chunker bumps + ZE switch) in one pass and applies the schema transition + config updates atomically. Tagged-union ApplyResult enum (D15): 'applied' | 'skipped_already_ applied' | 'skipped_no_work' | 'declined' | 'planned' | 'failed'. No string-parsing reasons. Three config keys (D12): ze_switch_prompt_shown (UI state), ze_switch_requested (user intent), ze_switch_applied (work done). Plus ze_switch_previous_snapshot (JSON, full prior config for --undo per D16) and ze_switch_declined_at (90-day re-ask window). Schema transition (D18) is atomic: DROP indexes + ALTER COLUMN + CREATE INDEX inside a single engine.transaction(). HNSW recreation is part of the same transaction — no silent slow-search window. C3 eligibility logic: ze_switch_offered iff NOT on ZE + NOT declined recently + NOT applied + (legacy default OR >100 pages). C4 cost math: MAX(chunker_pending, dim_pending) not SUM — one re-embed pass invalidates both surfaces simultaneously. New src/core/retrieval-upgrade-prompt.ts wires the planner to a TTY-only interactive prompt with two-line cost split (D10) and privacy callout for the reranker flip. Tests: test/retrieval-upgrade-planner.test.ts (24 cases) pins the state machine. test/asymmetric-encoding-contract.test.ts (6 cases) pins D17: search read path uses gateway.embedQuery() not embed(), asserted via __setEmbedTransportForTests mock. * feat(cli): gbrain ze-switch — manual lever for the ZE switch New gbrain ze-switch CLI with --dry-run, --json, --resume, --force, --undo, --non-interactive, --confirm-reembed, --ignore-missing-key flags. Mirrors the upgrade prompt's UX symmetry: --undo presents a cost-warning before re-embedding back to the prior width. src/cli.ts: dispatch case + CLI_ONLY entry. ze-switch owns its own engine lifecycle (mirrors the doctor pattern). test/ze-switch-cli.test.ts (11 cases): --help, --dry-run, --json, --non-interactive, --ignore-missing-key, --resume, --undo, --confirm-reembed. Uses captureExit harness to test process.exit() paths without breaking the test process. * feat(doctor): ze_embedding_health + embedding_width_consistency checks Two new doctor checks (D-A5): ze_embedding_health: when embedding_model starts with zeroentropyai:, verify ZEROENTROPY_API_KEY is set (env or config). Paste-ready setup hint with the signup URL on failure. embedding_width_consistency: cross-check that the configured embedding_dimensions matches the actual vector(N) column width on content_chunks.embedding. Catches the half-applied switch state (schema migrated but config write crashed) with a paste-ready gbrain ze-switch --resume hint. Wired into runDoctor between reranker_health and the existing sync_freshness checks. Both checks gracefully no-op on non-ZE embedding configs. test/doctor-ze-checks.test.ts (8 cases) pins both checks across happy + missing-key + missing-config + drift paths. Uses withEnv() helper to clear ZEROENTROPY_API_KEY for the no-key path so tests are hermetic against contributor env state. test/e2e/v0_28_5-fix-wave.test.ts + test/openai-compat-multimodal.test.ts: updated to explicit-configure the gateway when the test depends on specific dims that diverge from the v0.36.0.0 default (1280d). * docs: README zero-based rewrite (884 -> 139 lines) + new docs files Strip 4 months of accreted "New in v0.X.Y" hero blocks and reorganize around what gbrain does today. 33 H2s -> 8. The Commands section (136 lines duplicating gbrain --help) moved out; the 6-table skills enumeration collapsed to a one-paragraph capability description with a link to skills/RESOLVER.md. Hero retains load-bearing facts: OpenClaw + Hermes credit, production numbers (17,888 pages / 4,383 people / 723 companies), BrainBench numbers (P@5 49.1% / R@5 97.9% / +31.4 lift), ZE comparison numbers, 30-min install claim. Adds one paragraph announcing the v0.36.0.0 ZE default with the explicit gbrain config set escape for OpenAI/Voyage users. New files: - docs/INSTALL.md: every install path consolidated (agent platform, CLI standalone, MCP server). Thin-client mode covered. - docs/architecture/RETRIEVAL.md: why the hybrid + graph stack works. BrainBench numbers, why each strategy alone fails, the source-aware ranking + intent classification + multi-query expansion story. - docs/ethos/ORIGIN.md: origin story lifted from the old README so the front door stays factual + concrete. test/readme-hero-anchors.test.ts (5 cases) is the D9 regression guard. Five load-bearing strings: OpenClaw, Hermes, ZE, production-numbers regex, P@5/R@5. Light anchors that let voice/ structure evolve but block accidental loss of headline facts. scripts/check-test-real-names.sh: allowlist entries for OpenClaw + Hermes literals in the anchor test (it explicitly asserts those strings appear in README). * chore: bump version and changelog (v0.36.0.0) ZeroEntropy as the new default for embedding (zembed-1 at 1280d via Matryoshka) and reranker (zerank-2 cross-encoder, on by default in balanced mode bundle). README zero-based rewrite (884 -> 139 lines). 3 new docs files. Two new doctor checks. New gbrain ze-switch CLI with --undo for symmetric reversibility. skills/migrations/v0.36.0.0.md tells the agent how to surface the retrieval-upgrade prompt post-upgrade. llms-full.txt regenerated via bun run build:llms. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(docs): scrub Wintermute from RETRIEVAL.md per privacy rule * chore: rebump version 0.36.0.0 → 0.36.2.0 (queue collision) Three open PRs were claiming v0.36.0.0 (#1130 skillpack, #1139 hindsight, #1136 this PR). Ship-aware queue allocator says this branch lands at v0.36.2.0. Trio audit: VERSION 0.36.2.0 package.json 0.36.2.0 CHANGELOG ## [0.36.2.0] - 2026-05-17 Updates: VERSION, package.json, CHANGELOG header + body refs, README "New default in v0.36.2.0" announcement + credit line, skills/migrations/v0.36.0.0.md renamed to v0.36.2.0.md with frontmatter + body refs updated. llms-full.txt regenerated. * fix(test): pin gateway dim=1536 in cross-file-stateful PGLite tests CI shard 1 reported 10 failures across `query-cache.test.ts` (6) and `consolidate-valid-until.test.ts` (4). Both files hardcode 1536-dim vectors but rely on `PGLiteEngine.initSchema()` to size `vector(__EMBEDDING_DIMS__)` at the right width. Root cause: v0.36.2.0 flipped DEFAULT_EMBEDDING_DIMENSIONS from 1536 to 1280 (ZE Matryoshka step). The gateway module is process-singleton; when ANOTHER test file in the same shard's bun-test process configures the gateway before us, `pglite-engine.ts:216` reads `getEmbeddingDimensions() === 1280` and sizes the schema columns at vector(1280). The hardcoded 1536-dim INSERTs then fail with "expected 1280 dimensions, not 1536". Locally these tests pass in isolation because the gateway falls back through the try/catch at pglite-engine.ts:218 (1536 default). CI runs multiple test files in one process, so cross-file state poisons the schema width. Fix: explicit `resetGateway()` + `configureGateway({embedding_dimensions: 1536, ...})` at the top of `beforeAll`, plus `resetGateway()` in `afterAll`. Pins the schema width regardless of cross-file state. --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
159 lines
5.3 KiB
TypeScript
159 lines
5.3 KiB
TypeScript
/**
|
|
* v0.36.0.0 (D6 + C2) — balanced mode bundle now defaults reranker_enabled=true.
|
|
*
|
|
* Pins:
|
|
* - MODE_BUNDLES.balanced.reranker_enabled === true (the flip)
|
|
* - applyReranker honors the flag (calls injected rerankerFn)
|
|
* - Fail-open contract: missing key / network error returns input unchanged
|
|
* - rerankerFn is called with input_type-equivalent shape for the query path
|
|
*/
|
|
|
|
import { describe, test, expect } from 'bun:test';
|
|
import { MODE_BUNDLES } from '../src/core/search/mode.ts';
|
|
import { applyReranker, type RerankerOpts } from '../src/core/search/rerank.ts';
|
|
import type { SearchResult } from '../src/core/types.ts';
|
|
import { RerankError } from '../src/core/ai/gateway.ts';
|
|
|
|
describe('Mode bundle defaults (D6)', () => {
|
|
test('balanced.reranker_enabled is true (the v0.36.0.0 flip)', () => {
|
|
expect(MODE_BUNDLES.balanced.reranker_enabled).toBe(true);
|
|
});
|
|
|
|
test('balanced reranker model is zeroentropyai:zerank-2', () => {
|
|
expect(MODE_BUNDLES.balanced.reranker_model).toBe('zeroentropyai:zerank-2');
|
|
});
|
|
|
|
test('conservative reranker stays off (cheap tier)', () => {
|
|
expect(MODE_BUNDLES.conservative.reranker_enabled).toBe(false);
|
|
});
|
|
|
|
test('tokenmax reranker still on', () => {
|
|
expect(MODE_BUNDLES.tokenmax.reranker_enabled).toBe(true);
|
|
});
|
|
});
|
|
|
|
function makeResults(n: number): SearchResult[] {
|
|
const out: SearchResult[] = [];
|
|
for (let i = 0; i < n; i++) {
|
|
out.push({
|
|
slug: `doc/${i}`,
|
|
page_id: i + 1,
|
|
title: `Doc ${i}`,
|
|
type: 'note',
|
|
chunk_text: `This is doc ${i}, an example chunk text for rerank testing.`,
|
|
chunk_source: 'compiled_truth',
|
|
chunk_id: i + 100,
|
|
chunk_index: 0,
|
|
score: 1 / (i + 1),
|
|
stale: false,
|
|
});
|
|
}
|
|
return out;
|
|
}
|
|
|
|
describe('applyReranker — fail-open contract (D6 + R8)', () => {
|
|
test('reranker disabled: passthrough', async () => {
|
|
const results = makeResults(5);
|
|
const opts: RerankerOpts = {
|
|
enabled: false,
|
|
topNIn: 30,
|
|
topNOut: null,
|
|
rerankerFn: async () => { throw new Error('should not be called'); },
|
|
};
|
|
const out = await applyReranker('test query', results, opts);
|
|
expect(out).toEqual(results);
|
|
});
|
|
|
|
test('reranker enabled + thrown error: returns input order unchanged', async () => {
|
|
const results = makeResults(5);
|
|
const opts: RerankerOpts = {
|
|
enabled: true,
|
|
topNIn: 30,
|
|
topNOut: null,
|
|
rerankerFn: async () => {
|
|
throw new RerankError('missing ZEROENTROPY_API_KEY', 'auth');
|
|
},
|
|
};
|
|
const out = await applyReranker('test query', results, opts);
|
|
// Fail-open: original order preserved.
|
|
expect(out.map(r => r.slug)).toEqual(results.map(r => r.slug));
|
|
});
|
|
|
|
test('reranker enabled + happy path: reorders by relevance_score', async () => {
|
|
const results = makeResults(3);
|
|
const opts: RerankerOpts = {
|
|
enabled: true,
|
|
topNIn: 30,
|
|
topNOut: null,
|
|
rerankerFn: async () => {
|
|
// Reverse the order: doc/2 first, doc/0 last.
|
|
return [
|
|
{ index: 2, relevanceScore: 0.95 },
|
|
{ index: 1, relevanceScore: 0.50 },
|
|
{ index: 0, relevanceScore: 0.10 },
|
|
];
|
|
},
|
|
};
|
|
const out = await applyReranker('test query', results, opts);
|
|
expect(out.map(r => r.slug)).toEqual(['doc/2', 'doc/1', 'doc/0']);
|
|
});
|
|
|
|
test('empty results: passthrough (no upstream call)', async () => {
|
|
let called = false;
|
|
const opts: RerankerOpts = {
|
|
enabled: true,
|
|
topNIn: 30,
|
|
topNOut: null,
|
|
rerankerFn: async () => { called = true; return []; },
|
|
};
|
|
const out = await applyReranker('test query', [], opts);
|
|
expect(out).toEqual([]);
|
|
expect(called).toBe(false);
|
|
});
|
|
|
|
test('preserves un-reranked tail past topNIn (recall protection)', async () => {
|
|
const results = makeResults(10);
|
|
const opts: RerankerOpts = {
|
|
enabled: true,
|
|
topNIn: 3, // only rerank top 3
|
|
topNOut: null,
|
|
rerankerFn: async () => [
|
|
{ index: 2, relevanceScore: 0.99 },
|
|
{ index: 0, relevanceScore: 0.50 },
|
|
{ index: 1, relevanceScore: 0.10 },
|
|
],
|
|
};
|
|
const out = await applyReranker('test query', results, opts);
|
|
// Head: reranked. Tail: original positions 3-9 in order.
|
|
expect(out.slice(0, 3).map(r => r.slug)).toEqual(['doc/2', 'doc/0', 'doc/1']);
|
|
expect(out.slice(3).map(r => r.slug)).toEqual([
|
|
'doc/3', 'doc/4', 'doc/5', 'doc/6', 'doc/7', 'doc/8', 'doc/9',
|
|
]);
|
|
});
|
|
});
|
|
|
|
describe('Reranker invocation receives query + documents', () => {
|
|
test('rerankerFn called with query + document texts from top N', async () => {
|
|
const results = makeResults(5);
|
|
let received: { query: string; documents: string[] } | null = null;
|
|
const opts: RerankerOpts = {
|
|
enabled: true,
|
|
topNIn: 3,
|
|
topNOut: null,
|
|
rerankerFn: async (input) => {
|
|
received = { query: input.query, documents: input.documents };
|
|
return [
|
|
{ index: 0, relevanceScore: 0.9 },
|
|
{ index: 1, relevanceScore: 0.5 },
|
|
{ index: 2, relevanceScore: 0.1 },
|
|
];
|
|
},
|
|
};
|
|
await applyReranker('what is foo?', results, opts);
|
|
expect(received).not.toBeNull();
|
|
expect(received!.query).toBe('what is foo?');
|
|
expect(received!.documents.length).toBe(3);
|
|
expect(received!.documents[0]).toContain('doc 0');
|
|
});
|
|
});
|