Files
gbrain/test/balanced-reranker-default.test.ts
T
cdba533a04 v0.36.2.0 feat: ZeroEntropy as default + zero-based README rewrite (#1136)
* 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>
2026-05-18 21:11:02 -07:00

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');
});
});