mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 22:15:33 +00:00
* feat(ai): add ZeroEntropy recipe + reranker touchpoint type
Widens `TouchpointKind` with `'reranker'`, adds `RerankerTouchpoint`
interface, extends `Recipe.touchpoints` and `AIGatewayConfig` to carry
reranker model state. Registers `zeroentropyai` recipe (zembed-1
embeddings + zerank-{2,1,1-small} rerankers) in the recipe registry.
Recipe declares the 7 Matryoshka dims (2560/1280/640/320/160/80/40),
Voyage-style dense-payload hedge (chars_per_token=1, safety_factor=0.5),
and 5MB rerank payload cap. Pinned by test/ai/zeroentropy-recipe.test.ts
including F1 regression (implementation literal is 'openai-compatible')
and F2 regression (base_url_default ends with /v1, no doubling).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(ai/dims): thread input_type 4th-arg + ZE flexible-dim allowlist
`dimsProviderOptions` gains an optional `inputType?: 'query' | 'document'`
4th param so asymmetric providers (ZE zembed-1, Voyage v3+) can route
query-side vs document-side encoding. Per-model filtering inside the
openai-compatible branch keeps `input_type` from leaking to symmetric
providers (OpenAI text-3, DashScope, Zhipu) that would 400 on it.
Adds `ZEROENTROPY_VALID_DIMS` allowlist (2560/1280/640/320/160/80/40),
`supportsZeroEntropyDimension(modelId)`, and `isValidZeroEntropyDim(dims)`.
Throws `AIConfigError` with paste-ready fix hint when zembed-1 is
configured with an invalid dim (most common: defaulting to 1536 from
DEFAULT_EMBEDDING_DIMENSIONS).
The 4th-arg is optional; existing call sites (1 production + N tests
across Voyage/OpenAI/DashScope/Zhipu/MiniMax) compile unchanged.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(ai/gateway): zeroEntropyCompatFetch + embedQuery + gateway.rerank()
Two seams land together because they share the same recipe + auth path.
zeroEntropyCompatFetch handles ZE's non-OpenAI-compatible wire shape:
- URL rewrite: SDK's `${base_url}/embeddings` -> `${base_url}/models/embed`
- Body inject: `input_type` (default 'document'; 'query' when threaded
via providerOptions) + explicit `encoding_format: 'float'`
- Response rewrite: `{results: [{embedding}]}` -> `{data: [{embedding,
index}]}` so the AI SDK's openai-compat schema validates
- `usage.prompt_tokens` injected from `total_tokens` (Voyage hit the
same SDK schema requirement at :655)
- Layer 1 (Content-Length) + Layer 2 (per-embedding size) OOM caps
via tagged `ZeroEntropyResponseTooLargeError` (kept separate from
`VoyageResponseTooLargeError` because the Voyage cap tests do
structural source-text greps pinning the Voyage name)
- Wired in `instantiateEmbedding()` via the existing
`recipe.id === 'voyage' ? voyageCompatFetch : ...` ternary pattern
embedQuery(text) routes `inputType: 'query'` through dimsProviderOptions
for the search hot path. Companion to embed(texts) which now takes an
optional 2nd-arg inputType (defaults to undefined -> 'document' for
asymmetric providers).
gateway.rerank() is the new native HTTP path (no AI-SDK reranking
abstraction). Resolves the configured reranker model via
`getRerankerModel()` (new accessor), parses + asserts the model is in
the recipe's touchpoint.reranker.models allowlist (CDX2-F11:
assertTouchpoint does not enforce allowlists for openai-compatible
recipes — rerank() does it directly). Posts to
`${recipe.base_url}/models/rerank` with bearer auth. Returns
`RerankResult[]` sorted by `relevanceScore`. Errors classify into
`RerankError.reason: 'auth' | 'rate_limit' | 'network' | 'timeout' |
'payload_too_large' | 'unknown'`. 5s default timeout. Pre-flight payload
guard rejects bodies over `recipe.max_payload_bytes` BEFORE any HTTP
call so applyReranker can fail-open without burning a round-trip.
`_rerankTransport` + `__setRerankTransportForTests` mirror the embed
test seam.
`AIGatewayConfig.reranker_model` + isAvailable('reranker') branch +
configureGateway / reconfigureGatewayWithEngine extensions thread the
reranker model through the same state path as embedding/expansion/chat.
`applyResolveAuth` + `defaultResolveAuth` widen the touchpoint param to
include `'reranker'`. `KnownTouchpointKey` + `getTouchpoint()` in
model-resolver widen to cover `'reranker'`.
Pinned by:
- test/ai/embedQuery.test.ts (8): returns single Float32Array, threads
input_type='query' for ZE, drops field for OpenAI text-3,
back-compat: legacy embed() callers without 4th arg keep their
previous Voyage no-input_type shape
- test/ai/rerank.test.ts (21): URL (F2 regression — no /v1/v1/), body
shape, bearer header, response parsing, error classification across
6 HTTP shapes, payload pre-flight (no transport call), allowlist
enforcement
- test/ai/zeroentropy-compat-fetch.test.ts (14): structural source
assertions for the shim that mirror test/voyage-response-cap.test.ts —
URL rewrite path, body injection, response rewrite, usage.prompt_tokens
injection, OOM caps Layer 1 + Layer 2 + instanceof rethrow,
instantiateEmbedding wiring branch
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(search): applyReranker + rerank-failure audit + hybrid wire-in
src/core/search/rerank.ts — the call-site abstraction. Slices the top
`opts.topNIn` deduped candidates, sends to gateway.rerank(), reorders by
relevanceScore desc, appends the un-reranked tail in its original RRF
order (recall protection). Fail-open on every RerankError.reason: logs
via `logRerankFailure` and returns the input array unchanged. Stamps
`rerank_score` onto reordered items. `topNOut: null` is the explicit
"don't truncate" signal — distinct from `undefined` (fall through to
mode bundle); pin in test (CDX2-F16).
src/core/rerank-audit.ts — failure-only JSONL audit at
`~/.gbrain/audit/rerank-failures-YYYY-Www.jsonl` (ISO-week rotation;
mirrors `src/core/audit-slug-fallback.ts`). Exports `logRerankFailure`
+ `readRecentRerankFailures(days)`. **No `logRerankSuccess`** — CDX2-F22
deliberately drops success-event logging: writing once per tokenmax
search is hot-path I/O churn AND success events leak query
volume + timing into a local audit. The doctor check reads
`search.reranker.enabled` first so "no events in window" gets
interpreted correctly (disabled -> healthy by definition; enabled ->
healthy because nothing failed). Query text is SHA-256-prefix-hashed
(8 hex chars) for privacy. Honors `GBRAIN_AUDIT_DIR`.
src/core/search/hybrid.ts — slots `applyReranker` between
`dedupResults()` and `enforceTokenBudget()` in the main RRF path.
Resolution: per-call `opts.reranker` overrides; otherwise pulled from
the resolved mode bundle (tokenmax -> enabled, others -> disabled in
commit 5). Cache rows store final reranked results; the bumped
knobsHash (commit 5) ensures rows can't leak across reranker configs.
src/core/types.ts — adds `SearchOpts.reranker` as a structural type so
callers can pass per-call overrides; runtime type lives in
src/core/search/rerank.ts (avoids circular import).
Tests:
- test/search/rerank.test.ts (14): reorder, tail preserve, fail-open on
every error class, topNOut null vs number, score stamping, empty +
enabled=false pass-through
- test/rerank-audit.test.ts (10): JSONL round-trip, error_summary
truncated to 200, corrupt rows skipped, missing dir -> [], ISO-week
rotation walks current + previous week, no logRerankSuccess export
(CDX2-F22 contract)
- test/search/hybrid-reranker-integration.test.ts (6): reranker fires
when enabled, doesn't when disabled, reorders correctly, preserves
tail, stamps rerank_score, fail-opens on rerankerFn throw — uses
PGLite + stubbed embed transport, no API keys
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(search/mode): reranker mode-bundle fields + KNOBS_HASH_VERSION v=2
Extends `ModeBundle` with five reranker fields: `reranker_enabled`,
`reranker_model`, `reranker_top_n_in`, `reranker_top_n_out`,
`reranker_timeout_ms`. Per-mode defaults:
- conservative -> enabled=false (cost-sensitive)
- balanced -> enabled=false (opt-in via search.reranker.enabled)
- tokenmax -> enabled=true (the high-cost-tolerant tier; ~$0.0003/query)
Defaults model to `zeroentropyai:zerank-2`, topNIn=30, topNOut=null
(no truncate by default; preserves tokenmax's searchLimit=50 end-to-end
per CDX2-F16), timeout_ms=5000.
`SearchKeyOverrides` + `SearchPerCallOpts` + `resolveSearchMode.pick`
all extend to thread the new fields through the resolution chain
(per-call -> per-key config -> mode bundle -> default).
`loadOverridesFromConfig` adds parsers for the five new
`search.reranker.*` config keys. `top_n_out` parsing distinguishes
three input shapes (CDX2-F15):
key absent -> undefined (fall through to mode bundle)
'null'|'none'|empty -> explicit null (no truncate)
positive integer -> that number
`SEARCH_MODE_CONFIG_KEYS` extends so `gbrain search modes --reset`
clears the reranker overrides too.
**KNOBS_HASH_VERSION bumps 1 -> 2** (CDX1-F14). Five new entries
appended to `parts[]` (append-only convention CDX2-F13; reordering
existing fields would silently rebuild every existing cache row).
Includes `reranker_timeout_ms` so a 5s -> 100ms change invalidates
stale rows (CDX2-F14: more fail-opens = different search behavior).
Mid-rolling-deploy note (CDX2-F12): v=1 and v=2 processes produce
distinct cacheRowIds for the same (source_id, query_text). Expect a
temporary hit-rate dip + cache-row doubling for hot queries. Clears
naturally within `cache.ttl_seconds` (default 3600s).
src/commands/search.ts extends `KNOB_DESCRIPTIONS` with five new
entries so `gbrain search modes` renders them. test/search-mode.test.ts
extends the three bundle fixtures and bumps the KNOBS_HASH_VERSION
expectation to 2.
Pinned by test/search/knobs-hash-reranker.test.ts (13): each of the 5
reranker fields independently flips the hash, top_n_out=null renders
stable, append-only convention enforced via source-position assertion.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(doctor): probeRerankerConfig + reranker_health check
`gbrain models doctor` gains two new probes:
- `probeRerankerConfig` (zero-network) validates that the configured
reranker model resolves through the recipe registry, that the recipe
declares a `reranker` touchpoint, and that the model is in
`touchpoint.models[]`. Direct allowlist check here — assertTouchpoint
does not enforce allowlists for openai-compatible recipes (CDX2-F11).
Surfaces paste-ready `gbrain config set search.reranker.model
<zerank-2|zerank-1|zerank-1-small>` fix hint.
- `probeRerankerReachability` (1-token-equivalent) sends a minimal
`{query: "probe", documents: ["probe"]}` rerank to verify auth + URL.
Failures classify via `classifyError` into auth/rate_limit/network/
unknown. Skipped silently when reranker is unconfigured.
Also extends `probeEmbeddingConfig` with a `providerId === 'zeroentropyai'`
branch that catches the silent-1536-default bug class for zembed-1
configurations (same posture as the existing Voyage branch).
`ProbeResult.touchpoint` widens to include `'reranker_config'`.
`gbrain doctor` adds `checkRerankerHealth` to both the abbreviated
(doctorReportRemote) and full (runDoctor) check sets. Logic:
1) Read `search.reranker.enabled` first. Disabled + no failures =>
'reranker disabled'. Enabled + no failures => healthy.
2) Walk last 7 days of ~/.gbrain/audit/rerank-failures-*.jsonl.
3) ANY auth failure warns (config-time problem the probe should have
caught — surface it).
4) ANY payload_too_large failure warns (workload mismatch).
5) Transient (network/timeout/rate_limit) warns at >=5 in window.
Below that they're noise; reranker fails open anyway.
CDX2-F21 blind-spot fix: reading enabled state first means "no events"
gets interpreted correctly — never confuses "never-used" with "success
logging broken" (the latter is impossible because there is no success
logging by design, CDX2-F22).
Engine-agnostic; file-based + one config-key read.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* test(e2e): ZeroEntropy live API round-trip + wire into Tier 2 CI
test/e2e/zeroentropy-live.test.ts exercises the full stack against the
real api.zeroentropy.dev: embed (default 2560-dim + flexible 1280),
embedQuery (asymmetric query side), batch embed (3 distinct vectors),
rerank (3 docs sorted by relevance score, photosynthesis-relevant docs
beat the irrelevant cat doc), rerank with topN truncation.
Gated on `ZEROENTROPY_API_KEY`: every test prints `[skip]` and returns
early without assertions when the env var is unset, so fork PRs and
contributor machines without a ZE account stay green.
CI wire-up: `.github/workflows/e2e.yml` Tier 2 step adds
`test/e2e/zeroentropy-live.test.ts` to its `bun test` invocation and
exposes `ZEROENTROPY_API_KEY: ${{ secrets.ZEROENTROPY_API_KEY }}` to
the runner. The secret is set on garrytan/gbrain at the repo scope
(separately from this commit — set via `gh secret set` so the value
never lands in source).
Tier 1 stays mechanical (no API keys); Tier 2 is the natural home for
provider-live tests because it's already the API-keyed lane.
Cost: each full run fires ~6 small HTTP calls totaling well under a
cent at the published $0.025/1M-token rate.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* v0.33.3.0 feat: ZeroEntropy zembed-1 + zerank-2 reranker
Release notes for the ZeroEntropy support wave: zembed-1 embeddings
(flexible-dim 2560/1280/640/320/160/80/40, asymmetric input_type) and
zerank-2 cross-encoder reranking land as a new openai-compatible recipe
alongside OpenAI/Voyage. Reranker defaults ON for tokenmax mode, OFF
for conservative/balanced (~$0.0003/query at tokenmax topNIn=30; rounding
error vs the tier's $700/mo Opus pairing per the CLAUDE.md cost matrix).
Search now ends with `RRF -> dedup -> reranker -> token-budget` when
reranker is enabled; fails open to RRF order on any error class
(audit-logged at ~/.gbrain/audit/rerank-failures-*.jsonl).
`KNOBS_HASH_VERSION` bumps 1 -> 2 to fold reranker config into the
query_cache row key. Rolling-deploy operators should expect a temporary
cache hit-rate dip + cache-row doubling for hot queries (clears
naturally within `cache.ttl_seconds`, default 3600s).
Files in this commit are pure docs / version bump:
- VERSION + package.json bump to 0.33.3.0
- CHANGELOG.md release-summary entry with "How to take advantage" block
- CLAUDE.md Key Files annotations for the new recipe + rerank.ts +
rerank-audit.ts + gateway extensions
- docs/ai-providers/zeroentropy.md one-pager (setup, knob reference,
failure observability, troubleshooting table)
- skills/migrations/v0.33.3.md (purely informational: no required user
action; reranker is opt-in everywhere, ZE embedding is opt-in)
- llms-full.txt regenerated to match CLAUDE.md
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
171 lines
5.8 KiB
TypeScript
171 lines
5.8 KiB
TypeScript
/**
|
|
* v0.35.0.0 — ZeroEntropy live E2E tests.
|
|
*
|
|
* Real HTTP round-trip against `api.zeroentropy.dev`. Gated on
|
|
* `ZEROENTROPY_API_KEY` — when absent, every test skips gracefully so
|
|
* `bun run test:e2e` stays green on contributor machines that don't have
|
|
* a ZE account.
|
|
*
|
|
* Pins (only meaningful when the env var is set):
|
|
* - POST /v1/models/embed returns float embeddings that round-trip
|
|
* through the AI-SDK adapter (after zeroEntropyCompatFetch's response
|
|
* rewrite).
|
|
* - dimensions parameter is honored: 2560 default → vector of length
|
|
* 2560; 1280 → 1280; etc.
|
|
* - asymmetric input_type plumbing reaches ZE: embedQuery() and embed()
|
|
* both succeed and return same-shape vectors (we can't easily inspect
|
|
* whether ZE actually produced asymmetric vectors without a reference
|
|
* corpus, but the request must succeed without HTTP 400).
|
|
* - POST /v1/models/rerank returns indices + relevance_scores that
|
|
* round-trip through gateway.rerank() into RerankResult[].
|
|
*
|
|
* Cost note: each test fires 1-2 HTTP requests. At $0.025/1M tokens and
|
|
* ~100 tokens per test, the full file costs well under a cent. Still
|
|
* gated by env so contributor PR CI doesn't spend.
|
|
*/
|
|
|
|
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
|
import {
|
|
configureGateway,
|
|
resetGateway,
|
|
embed,
|
|
embedQuery,
|
|
rerank,
|
|
} from '../../src/core/ai/gateway.ts';
|
|
|
|
const API_KEY = process.env.ZEROENTROPY_API_KEY;
|
|
|
|
// Skip the entire file when env is absent. `describe.skipIf` exists in
|
|
// modern bun:test; fall back to in-test guards for older runners.
|
|
const skipAll = !API_KEY;
|
|
|
|
beforeAll(() => {
|
|
if (skipAll) return;
|
|
configureGateway({
|
|
embedding_model: 'zeroentropyai:zembed-1',
|
|
embedding_dimensions: 2560,
|
|
reranker_model: 'zeroentropyai:zerank-2',
|
|
env: { ZEROENTROPY_API_KEY: API_KEY! },
|
|
});
|
|
});
|
|
|
|
afterAll(() => {
|
|
if (!skipAll) resetGateway();
|
|
});
|
|
|
|
describe('ZE live — embed round-trip', () => {
|
|
test('embed(["text"]) returns Float32Array[2560]', async () => {
|
|
if (skipAll) {
|
|
console.warn('[skip] ZEROENTROPY_API_KEY not set');
|
|
return;
|
|
}
|
|
const [v] = await embed(['hello world']);
|
|
expect(v).toBeInstanceOf(Float32Array);
|
|
expect(v.length).toBe(2560);
|
|
// Sanity: at least one non-zero element (otherwise the response
|
|
// rewrite probably dropped the payload).
|
|
const anyNonZero = Array.from(v).some(x => x !== 0);
|
|
expect(anyNonZero).toBe(true);
|
|
});
|
|
|
|
test('embedQuery("text") returns Float32Array[2560] (query side)', async () => {
|
|
if (skipAll) {
|
|
console.warn('[skip] ZEROENTROPY_API_KEY not set');
|
|
return;
|
|
}
|
|
const v = await embedQuery('what is foo');
|
|
expect(v).toBeInstanceOf(Float32Array);
|
|
expect(v.length).toBe(2560);
|
|
const anyNonZero = Array.from(v).some(x => x !== 0);
|
|
expect(anyNonZero).toBe(true);
|
|
});
|
|
|
|
test('embed batch of 3 returns 3 vectors in order', async () => {
|
|
if (skipAll) {
|
|
console.warn('[skip] ZEROENTROPY_API_KEY not set');
|
|
return;
|
|
}
|
|
const out = await embed(['one', 'two', 'three']);
|
|
expect(out.length).toBe(3);
|
|
for (const v of out) {
|
|
expect(v).toBeInstanceOf(Float32Array);
|
|
expect(v.length).toBe(2560);
|
|
}
|
|
// Different inputs → different vectors (sanity check; would fail
|
|
// hard if the response-rewriter accidentally returned the same
|
|
// vector for every input).
|
|
expect(out[0]).not.toEqual(out[1]);
|
|
expect(out[1]).not.toEqual(out[2]);
|
|
});
|
|
});
|
|
|
|
describe('ZE live — rerank round-trip', () => {
|
|
test('rerank({query, documents}) returns sorted RerankResult[]', async () => {
|
|
if (skipAll) {
|
|
console.warn('[skip] ZEROENTROPY_API_KEY not set');
|
|
return;
|
|
}
|
|
const out = await rerank({
|
|
query: 'how does photosynthesis work',
|
|
documents: [
|
|
'Photosynthesis is the process by which plants convert sunlight to energy.',
|
|
'My cat likes to eat tuna fish.',
|
|
'Chlorophyll absorbs red and blue light during photosynthesis.',
|
|
],
|
|
});
|
|
expect(out.length).toBe(3);
|
|
for (const r of out) {
|
|
expect(typeof r.index).toBe('number');
|
|
expect(typeof r.relevanceScore).toBe('number');
|
|
// ZE relevance scores are in [0, 1]. Pin the range so a future
|
|
// contract change is loud.
|
|
expect(r.relevanceScore).toBeGreaterThanOrEqual(0);
|
|
expect(r.relevanceScore).toBeLessThanOrEqual(1);
|
|
}
|
|
// Photosynthesis-relevant docs should score higher than the cat doc.
|
|
// We don't pin a specific order (zerank-2 may re-rank the two
|
|
// photosynthesis docs in either order depending on phrasing), but
|
|
// the cat doc must NOT be at the top.
|
|
const topIndex = out[0]!.index;
|
|
expect(topIndex).not.toBe(1); // index 1 is the cat doc
|
|
});
|
|
|
|
test('rerank with top_n=2 returns at most 2 results', async () => {
|
|
if (skipAll) {
|
|
console.warn('[skip] ZEROENTROPY_API_KEY not set');
|
|
return;
|
|
}
|
|
const out = await rerank({
|
|
query: 'photosynthesis',
|
|
documents: ['photosynthesis a', 'cats b', 'photosynthesis c'],
|
|
topN: 2,
|
|
});
|
|
expect(out.length).toBeLessThanOrEqual(2);
|
|
});
|
|
});
|
|
|
|
describe('ZE live — flexible dims', () => {
|
|
test('1280-dim embedding returns Float32Array[1280]', async () => {
|
|
if (skipAll) {
|
|
console.warn('[skip] ZEROENTROPY_API_KEY not set');
|
|
return;
|
|
}
|
|
resetGateway();
|
|
configureGateway({
|
|
embedding_model: 'zeroentropyai:zembed-1',
|
|
embedding_dimensions: 1280,
|
|
env: { ZEROENTROPY_API_KEY: API_KEY! },
|
|
});
|
|
const [v] = await embed(['1280 dim test']);
|
|
expect(v.length).toBe(1280);
|
|
// Restore 2560 for subsequent tests.
|
|
resetGateway();
|
|
configureGateway({
|
|
embedding_model: 'zeroentropyai:zembed-1',
|
|
embedding_dimensions: 2560,
|
|
reranker_model: 'zeroentropyai:zerank-2',
|
|
env: { ZEROENTROPY_API_KEY: API_KEY! },
|
|
});
|
|
});
|
|
});
|