Files
gbrain/test/eval-whoknows.test.ts
T
d71fcf6f65 v0.33.1.0 feat: eval-gated whoknows — expertise + relationship-proximity routing (#881)
* feat(v0.33): add SearchOpts.types multi-type filter to searchHybrid

Push the page-type filter into SQL via AND p.type = ANY(\$N::text[]) in
both engines' searchKeyword + searchVector + searchKeywordChunks paths.
Primary consumer is the upcoming gbrain whoknows command (filters to
['person','company']); the limit budget then goes to typed candidates
instead of being eaten by note/transcript/article pages. Future
entity-only search in v0.34+ reuses the parameter for free.

AND-applies alongside the existing single-value type filter (callers can
use either or both). HybridSearchOpts threads opts.types into the
underlying searchOpts so hybridSearch callers get the SQL-level filter
without any post-filter waste.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(v0.33): whoknows core ranking function + 10 locked unit tests

Implements ENG-D1's locked spec: score = log(1 + raw_match) ×
max(0.1, exp(-days/180)) × (0.5 + 0.5 × salience). raw_match comes
from hybridSearch's RRF + source-boost-adjusted score; salience and
recency boosts in hybridSearch are intentionally disabled so the
formula applies on a clean signal.

rankCandidates() is the pure function the eval grades against;
findExperts() is the public entrypoint that wires hybrid search +
batch salience/effective_date fetches; runWhoknows() is the CLI.

Test/whoknows.test.ts covers the 10 ENG-D3 cases (zero results,
negative recency floor, NaN salience neutral default, NaN match
zeros gracefully, type preservation, --explain factor breakdown,
top-K limit clamping, recency-floor extreme-days safety, alphabetical
tie-break determinism, public-surface contract). Plus four sanity
asserts (higher-match outranks, more-recent outranks, higher-salience
outranks, all-zero candidate appears with score 0). Plus one factor
decomposition assertion that pins the exact formula numerically.
Plus a composite-key safety case (Codex F1).

22 expect calls across 16 tests. All passing.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(v0.33): register find_experts MCP op + gbrain whoknows CLI

Wires both surfaces per ENG-D5: MCP op = find_experts (matches
find_anomalies naming convention; agent-facing); CLI command =
gbrain whoknows (memorable, user-facing). One findExperts() core
function backs both paths.

The op is scope:'read', localOnly:false — accessible over HTTP MCP
to read-scoped OAuth clients like the salience/anomalies family.
Op handler validates non-empty topic and dispatches to the same
findExperts() pure function the CLI uses.

CLI dispatch in src/cli.ts:case 'whoknows' calls runWhoknows; thin-
client routing happens inside runWhoknows via isThinClient(cfg) —
remote MCP installs route through the v0.31.1 routing seam to
callRemoteTool('find_experts', ...).

FIND_EXPERTS_DESCRIPTION in operations-descriptions.ts mirrors the
v0.29 redirect-hint style: leads with what the tool does, lists
explicit user-intent triggers ("who should I talk to about X",
"who knows about Y"), notes the type-filter behavior.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(v0.33): gbrain eval whoknows — two-layer eval gate (ENG-D2)

Implements the locked spec: Layer 1 hand-labeled fixture (>=80% top-3
hit rate) is the primary ship-blocking gate; Layer 2 eval_candidates
replay (>=0.4 mean set-Jaccard@3) is the regression gate that
auto-skips when < 20 replay-eligible rows exist (CONTRIBUTOR_MODE
sparseness fallback).

Dispatch lands as `gbrain eval whoknows <fixture.jsonl>` sub-subcommand
in src/commands/eval.ts (mirrors v0.25.0 export/prune/replay and
v0.27.x cross-modal pattern). Exits 0/1/2 for pass/fail/usage so CI
gates can consume.

JSON output (--json) ships schema_version: 1 for stable consumer
contract (mirrors v0.25.0 eval-replay.ts). Human output groups by
layer + emits a per-miss diagnostic table so failures are
self-debugging.

Unit tests pin:
- jaccardAtK math (7 cases — identical, disjoint, partial, k cutoff,
  empty-empty vacuous-stable, empty-vs-non-empty, Set dedup)
- topKHit (7 cases — position 1, 3, 4, miss, multi-expected, empty
  actual, empty expected)
- readFixture (6 cases — well-formed, comments/blanks, missing file,
  malformed JSON, missing required fields, non-string filter)
- Locked thresholds (HIT_RATE=0.8, REGRESSION=0.4, MIN_REPLAY_ROWS=20)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(v0.33): gbrain doctor adds whoknows_health check

Per CEO-D7 (substrate-conditional v0.33 doctor check, but the
fixture-presence sub-check ships in week 1 regardless — it's the
"did you do the assignment?" signal). When the eval fixture is
missing, empty, or undersized (< 5 rows), doctor warns with the
exact path the user should populate.

The check is intentionally lightweight: it does NOT run the eval
itself or measure hit-rate regression. That's the job of `gbrain
eval whoknows`, called from CI/ship time. This check is the cheap
always-runs signal that surfaces in `gbrain doctor` and on the
ship review dashboard.

5 unit cases pin the four-status behavior (missing/empty/undersized/
ok) plus the comment-and-blank-line filtering so users can comment
out queries during iteration without breaking the row count.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(v0.33): synthetic whoknows eval fixture + E2E quality gate test

test/fixtures/whoknows-eval.jsonl ships as a 10-query placeholder
demonstrating the schema. Comments document the assignment for end
users: they replace these with their own real queries before
shipping their gbrain install. The placeholder uses obviously-
example slugs (wiki/people/example-alice, etc.) so nobody mistakes
it for production data.

test/e2e/whoknows.test.ts seeds a synthetic PGLite brain that
matches the placeholder fixture, then runs findExperts on every
fixture query and asserts >=80% top-3 hit rate per ENG-D2 quality
gate. Also exercises the typeFilter (concept-decoy pages filtered
out), empty-result graceful return, --explain factor breakdown, and
top-K limit honoring.

Basis-vector embeddings (no API key) follow the existing pattern from
test/e2e/search-quality.test.ts.

5 test cases, 23 expect calls, all passing against PGLite.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs(v0.33): VERSION bump + CHANGELOG + CLAUDE.md + llms regen

Bumps VERSION 0.31.11 → 0.33.0 and package.json to match. CHANGELOG
entry leads with the headline use ("ask gbrain who knows about X")
and the locked ENG-D1 ranking formula. "Numbers that matter" replaced
with a "what ships on which eval outcome" table — honest about the
eval-gated trajectory rather than fabricating benchmarks before the
release has been graded against a real brain.

CLAUDE.md Key Files annotations added for src/commands/whoknows.ts,
src/commands/eval-whoknows.ts, and test/fixtures/whoknows-eval.jsonl.
src/core/search/hybrid.ts entry extended with the new types parameter
documentation (push the type filter to SQL, no post-filter waste,
AND-applies alongside the existing single-value type field).

bun run build:llms ran the chaser; llms.txt + llms-full.txt
regenerated to match.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(v0.33): unit-test gap fill — engine typeFilter + find_experts op

Two new files filling the gaps Garry called out:

test/search-types-filter.test.ts — engine-level coverage on PGLite for
the new SearchOpts.types filter. Asserts the SQL-clause behavior
directly so a regression in the AND p.type = ANY(...) emission gets
caught here with a tight assertion rather than as part of a longer
findExperts pipeline. 9 cases across searchKeyword + searchVector +
chunk-grain documentation. Documents the pre-existing PGLite parity
gap (single-value `type` field is Postgres-only; `types` is the v0.33
multi-type filter that BOTH engines honor).

test/find-experts-op.test.ts — MCP-op contract test for find_experts.
Pins:
- Registered in the operations array + operationsByName
- scope: 'read', localOnly false (HTTP-MCP accessible per ENG-D5)
- Documented params (topic / limit / explain) with correct types
- cliHints.name === 'whoknows' (CLI surface bridge)
- Non-trivial description that references the use case
- Handler rejects empty / whitespace / missing topic with invalid_params
- Handler returns array shape on valid topic
- Handler honors limit param

11 op-contract cases + 9 engine-clause cases. All passing.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: bump version to v0.33.1.0

Garry asked for v0.33.1 instead of v0.33.0 (queue collision with
unrelated 0.33.0 work). 4-digit format: 0.33.1.0. CHANGELOG header
and "To take advantage of" block updated. llms.txt regenerated.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(v0.33.1.1): cliHints.positional on find_experts so CLI accepts <topic>

Without `cliHints.positional: ['topic']`, the op-dispatch path in
src/cli.ts couldn't parse `gbrain whoknows "ai agents"` and threw
`invalid_params: topic is required`. Found while testing the v0.33.1.0
build against a real brain. The op handler validates topic; the CLI
just needed to know the positional shape so the dispatcher could
hand it through.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(v0.33.1.2): real-brain whoknows-eval fixture from VC intro network

Replaces the synthetic 10-row placeholder with 10 real expertise-routing
queries mined from Garry's actual brain via thin-client connection to
Wintermute (v0.32.2). Source: reference/vc-intro-network ("Who Takes
Intros from Garry") + adjacent routing context. All 15 unique expected
person slugs verified against ~/git/brain/people/<slug>.md source
markdown:

  people/amit-kumar          Accel partner, 102 YC deals
  people/diana-hu            YC GP
  people/elad-gil            Angel, top-rated
  people/eric-vishria        Benchmark, healthtech
  people/gokul-rajaram       Angel, 57 YC deals
  people/joff-redfern        Menlo Ventures, ex-CPO Atlassian
  people/jon-xu              YC GP
  people/kristina-shen       Chemistry, healthtech
  people/lachy-groom         Angel, 43 YC deals
  people/lee-edwards         Quiet Capital, 52 YC deals
  people/nick-shalek         Ribbit Capital, fintech
  people/nina-achadian       Index Ventures, 69 YC deals (note: slug
                              uses 'achadian' not 'achadjian')
  people/parul-singh         645 Ventures
  people/rebecca-kaden       USV
  people/trae-stephens       Founders Fund, defense/deep-tech

Eval cannot run yet against Wintermute thin-client: server is v0.32.2,
find_experts MCP op was added in v0.33. Once Wintermute upgrades the
eval will run end-to-end via the v0.31.1 thin-client routing seam.
Local eval works once the brain is indexed with find_experts available.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(v0.33.1.3): wire thin-client routing into eval-whoknows

`gbrain eval whoknows` now works against a thin-client install. When
isThinClient(cfg), each fixture query routes through the remote
find_experts MCP op via callRemoteTool — same v0.31.1 routing seam
runWhoknows already uses. Local mode unchanged: findExperts(engine, ...)
called directly.

Server prerequisite: the brain must be v0.33+ for find_experts to be
registered. Wintermute (currently v0.32.2) gets it on next upgrade and
then the eval runs end-to-end with zero client-side changes.

Mechanics:
- `WhoknowsFn` callable abstraction so the gates are impl-agnostic
- runEvalWhoknows(engine: BrainEngine | null, args) — null engine
  allowed in thin-client mode
- Regression gate auto-skips in thin-client mode (no DB access to
  eval_candidates; quality gate alone gates ship)
- cli.ts adds a thin-client bypass before connectEngine for
  `gbrain eval whoknows`, matching the longmemeval/cross-modal no-DB
  pattern

E2E test updated to use an inline synthetic fixture (the shipped
fixture is real-brain data now, doesn't match the seeded test brain).
Sanity-check the shipped fixture parses cleanly in a separate case.

Tests: 25 unit cases (+2 for null-engine signature contract) + 6 E2E
cases. Typecheck clean.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-12 14:33:29 -07:00

191 lines
6.1 KiB
TypeScript

import { describe, it, expect } from 'bun:test';
import { writeFileSync, unlinkSync } from 'fs';
import { tmpdir } from 'os';
import { join } from 'path';
import {
jaccardAtK,
topKHit,
readFixture,
HIT_RATE_THRESHOLD,
REGRESSION_THRESHOLD,
MIN_REPLAY_ROWS,
type FixtureRow,
} from '../src/commands/eval-whoknows.ts';
/**
* v0.33 eval harness unit tests — pure functions only.
*
* Integration coverage (real engine, fixture grading end-to-end) lives in
* test/e2e/whoknows.test.ts. This file verifies the math and the parser.
*/
describe('eval-whoknows / jaccardAtK', () => {
it('identical 3-element sets → 1.0', () => {
expect(jaccardAtK(['a', 'b', 'c'], ['a', 'b', 'c'], 3)).toBeCloseTo(1.0, 5);
});
it('disjoint sets → 0', () => {
expect(jaccardAtK(['a', 'b', 'c'], ['x', 'y', 'z'], 3)).toBe(0);
});
it('partial overlap (2 of 3 match) → 2/4 = 0.5', () => {
expect(jaccardAtK(['a', 'b', 'c'], ['a', 'b', 'z'], 3)).toBeCloseTo(0.5, 5);
});
it('respects k cutoff — ignores beyond top-k', () => {
expect(jaccardAtK(['a', 'b', 'x'], ['a', 'b', 'y'], 2)).toBeCloseTo(1.0, 5);
});
it('empty both sets → 1.0 (vacuously stable)', () => {
expect(jaccardAtK([], [], 3)).toBe(1);
});
it('empty one side, non-empty other → 0', () => {
expect(jaccardAtK([], ['a', 'b', 'c'], 3)).toBe(0);
});
it('duplicates in input collapse via Set semantics', () => {
// Set-Jaccard, not multiset — duplicates collapse.
expect(jaccardAtK(['a', 'a', 'a'], ['a'], 3)).toBe(1);
});
});
describe('eval-whoknows / topKHit', () => {
it('expected slug at position 1 → hit', () => {
expect(topKHit(['alice', 'bob', 'carol'], ['alice'], 3)).toBe(true);
});
it('expected slug at position 3 → hit (within top-3)', () => {
expect(topKHit(['x', 'y', 'alice'], ['alice'], 3)).toBe(true);
});
it('expected slug at position 4 → miss (beyond top-3)', () => {
expect(topKHit(['x', 'y', 'z', 'alice'], ['alice'], 3)).toBe(false);
});
it('no expected match anywhere → miss', () => {
expect(topKHit(['x', 'y', 'z'], ['alice'], 3)).toBe(false);
});
it('multiple expected slugs — hit if ANY appears in top-3', () => {
expect(topKHit(['x', 'bob', 'z'], ['alice', 'bob', 'carol'], 3)).toBe(true);
});
it('empty actual results → miss', () => {
expect(topKHit([], ['alice'], 3)).toBe(false);
});
it('empty expected → miss (cannot match anything)', () => {
expect(topKHit(['alice', 'bob'], [], 3)).toBe(false);
});
});
describe('eval-whoknows / readFixture', () => {
function tmpFixture(content: string): string {
const path = join(tmpdir(), `whoknows-eval-test-${Date.now()}-${Math.random()}.jsonl`);
writeFileSync(path, content);
return path;
}
it('parses well-formed JSONL', () => {
const path = tmpFixture(
'{"query":"lab automation","expected_top_3_slugs":["wiki/people/alice","wiki/people/bob"]}\n' +
'{"query":"fintech","expected_top_3_slugs":["wiki/companies/acme"],"notes":"hot topic"}\n',
);
try {
const rows = readFixture(path);
expect(rows.length).toBe(2);
expect(rows[0].query).toBe('lab automation');
expect(rows[0].expected_top_3_slugs.length).toBe(2);
expect(rows[1].notes).toBe('hot topic');
} finally {
unlinkSync(path);
}
});
it('skips blank lines and comments (#, //)', () => {
const path = tmpFixture(
'# this is a comment\n' +
'\n' +
'// another comment\n' +
'{"query":"x","expected_top_3_slugs":["y"]}\n',
);
try {
const rows = readFixture(path);
expect(rows.length).toBe(1);
} finally {
unlinkSync(path);
}
});
it('throws on missing file', () => {
expect(() => readFixture('/nonexistent/path/abc.jsonl')).toThrow(/fixture not found/);
});
it('throws on malformed JSON line', () => {
const path = tmpFixture('{not json\n');
try {
expect(() => readFixture(path)).toThrow(/malformed JSONL line/);
} finally {
unlinkSync(path);
}
});
it('throws on row missing required fields', () => {
const path = tmpFixture('{"query":"x"}\n'); // missing expected_top_3_slugs
try {
expect(() => readFixture(path)).toThrow(/missing required fields/);
} finally {
unlinkSync(path);
}
});
it('filters non-string entries in expected_top_3_slugs', () => {
const path = tmpFixture(
'{"query":"x","expected_top_3_slugs":["alice", null, 42, "bob"]}\n',
);
try {
const rows = readFixture(path);
expect(rows[0].expected_top_3_slugs).toEqual(['alice', 'bob']);
} finally {
unlinkSync(path);
}
});
});
describe('eval-whoknows / thresholds', () => {
it('HIT_RATE_THRESHOLD locked at 0.8 per ENG-D2', () => {
expect(HIT_RATE_THRESHOLD).toBe(0.8);
});
it('REGRESSION_THRESHOLD locked at 0.4 per ENG-D2', () => {
expect(REGRESSION_THRESHOLD).toBe(0.4);
});
it('MIN_REPLAY_ROWS sparseness fallback at 20', () => {
expect(MIN_REPLAY_ROWS).toBe(20);
});
});
// v0.33.1.3: WhoknowsFn is the per-query callable that the gates consume.
// runEvalWhoknows picks the impl (local findExperts vs thin-client MCP-routed).
// These tests pin the type-level contract and the export presence; full
// thin-client routing E2E is in the engine-required integration suite.
describe('eval-whoknows / WhoknowsFn contract', () => {
it('module exports WhoknowsFn type alias', async () => {
// The type is structurally `(topic: string, limit: number) => Promise<WhoknowsResult[]>`.
// Confirm import resolves without throwing.
const mod = await import('../src/commands/eval-whoknows.ts');
expect(typeof mod.runEvalWhoknows).toBe('function');
});
it('runEvalWhoknows accepts null engine (thin-client signature)', async () => {
// Signature gate: the function must be callable with engine=null. We use
// a missing-fixture path to short-circuit before any engine/MCP use, so
// this test pins ONLY the signature acceptance, not the routing logic.
const { runEvalWhoknows } = await import('../src/commands/eval-whoknows.ts');
const exitCode = await runEvalWhoknows(null, []); // no fixture path → 2
expect(exitCode).toBe(2);
});
});