mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-16 01:42:23 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
58683eb9ac |
-43
@@ -466,11 +466,6 @@ async function main() {
|
||||
const result = JSON.parse(JSON.stringify(rawResult, bigintToStringReplacer));
|
||||
const output = formatResult(op.name, result);
|
||||
if (output) process.stdout.write(output);
|
||||
// #1484 — invisible-miss hint: a bare query/search that hit zero results
|
||||
// on a multi-source brain tells the user (stderr) which source it
|
||||
// actually searched and how to widen the scope.
|
||||
const hint = await sourceScopeHint(op.name, params, ctx.sourceId, engine, result);
|
||||
if (hint) console.error(hint);
|
||||
} catch (e: unknown) {
|
||||
// v0.42.20.0 (codex D4): on error, set exitCode + return so the `finally`
|
||||
// STILL runs (drains every background-work sink + disconnects). A bare
|
||||
@@ -842,44 +837,6 @@ async function makeContext(engine: BrainEngine, params: Record<string, unknown>)
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* #1484 — a bare `gbrain query`/`search` silently scopes to the resolved
|
||||
* source (usually 'default'); on a multi-source brain a zero-hit run looks
|
||||
* identical to "the brain doesn't know this" even when the answer lives in
|
||||
* another source. Returns a stderr hint when (a) the op is query/search,
|
||||
* (b) it returned zero results, (c) the caller did NOT scope explicitly
|
||||
* (--source / --source-id / --all-sources), and (d) the brain has >1
|
||||
* registered source. Best-effort: any lookup failure returns null.
|
||||
*
|
||||
* Exported for tests (same import-safety contract as formatResult).
|
||||
*/
|
||||
export async function sourceScopeHint(
|
||||
opName: string,
|
||||
params: Record<string, unknown>,
|
||||
sourceId: string,
|
||||
engine: BrainEngine,
|
||||
result: unknown,
|
||||
): Promise<string | null> {
|
||||
if (opName !== 'query' && opName !== 'search') return null;
|
||||
if (!Array.isArray(result) || result.length > 0) return null;
|
||||
// Explicit scoping (flag tier) = user intent; don't second-guess it.
|
||||
if (params.source || params.source_id || params.all_sources) return null;
|
||||
if (sourceId === '__all__') return null;
|
||||
try {
|
||||
const rows = await engine.executeRaw<{ n: number }>(
|
||||
`SELECT count(*)::int AS n FROM sources`,
|
||||
);
|
||||
const n = Number(rows[0]?.n ?? 0);
|
||||
if (n <= 1) return null;
|
||||
return (
|
||||
`Hint: this brain has ${n} sources; you searched only "${sourceId}". ` +
|
||||
`Retry with --source-id __all__ (all sources) or --source-id <id>.`
|
||||
);
|
||||
} catch {
|
||||
return null; // hint is best-effort; never fail the query over it
|
||||
}
|
||||
}
|
||||
|
||||
// Exported for tests (same import-safety contract as cliAliases/printOpHelp).
|
||||
export function formatResult(opName: string, result: unknown): string {
|
||||
switch (opName) {
|
||||
|
||||
@@ -19,7 +19,7 @@
|
||||
*/
|
||||
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { runPhaseCalibrationProfile } from '../core/cycle/calibration-profile.ts';
|
||||
import { resolveCalibrationHolder, runPhaseCalibrationProfile } from '../core/cycle/calibration-profile.ts';
|
||||
import { sourceScopeOpts, type OperationContext } from '../core/operations.ts';
|
||||
import type { GBrainConfig } from '../core/config.ts';
|
||||
import { GBrainError } from '../core/types.ts';
|
||||
@@ -167,7 +167,7 @@ export async function runCalibration(
|
||||
config: GBrainConfig,
|
||||
): Promise<void> {
|
||||
const { opts } = parseArgs(args);
|
||||
const holder = opts.holder ?? 'garry';
|
||||
const holder = await resolveCalibrationHolder(engine, opts.holder);
|
||||
// Resolve --source / GBRAIN_SOURCE / .gbrain-source so the (now reachable, #2035)
|
||||
// calibration command targets the right source in a multi-source brain instead
|
||||
// of always reading `default`. No signal → 'default' (prior behavior).
|
||||
@@ -253,14 +253,14 @@ export async function getCalibrationProfileOp(
|
||||
ctx: OperationContext,
|
||||
params: { holder?: string },
|
||||
): Promise<CalibrationProfileRow | null> {
|
||||
const holder = params.holder ?? 'garry';
|
||||
if (typeof holder !== 'string' || holder.length === 0) {
|
||||
if (params.holder !== undefined && (typeof params.holder !== 'string' || params.holder.length === 0)) {
|
||||
throw new GBrainError(
|
||||
'INVALID_HOLDER',
|
||||
'get_calibration_profile.holder must be a non-empty string',
|
||||
'pass holder="<slug>" or omit to default to "garry"',
|
||||
'pass holder="<slug>" or omit to default to the calibration.user_holder config (then "garry")',
|
||||
);
|
||||
}
|
||||
const holder = await resolveCalibrationHolder(ctx.engine, params.holder);
|
||||
const scope = sourceScopeOpts(ctx);
|
||||
return getLatestProfile(ctx.engine, { holder, ...scope });
|
||||
}
|
||||
|
||||
+20
-49
@@ -1000,24 +1000,9 @@ const voyageCompatFetch = (async (input: RequestInfo | URL, init?: RequestInit)
|
||||
// Voyage diverges from OpenAI in two places that break the parser:
|
||||
// - `embedding` is a base64 string (SDK schema expects `number[]`)
|
||||
// - `usage` lacks `prompt_tokens` (SDK schema requires it when usage present)
|
||||
//
|
||||
// #1610: read the body ONCE via text() and JSON.parse it. The pre-fix
|
||||
// `await resp.clone().json()` truncated large bodies on bun < 1.1.27
|
||||
// (oven-sh/bun#6348) — the parse threw, the catch fell back to the raw
|
||||
// response, and multi-chunk pages died with "Invalid JSON response".
|
||||
// Every JSON return path below rebuilds the Response so a stale
|
||||
// Content-Length/Content-Encoding header from the original can't lie
|
||||
// about the rewritten body.
|
||||
const bodyText = await resp.text();
|
||||
const rebuild = (body: string) => {
|
||||
const headers = new Headers(resp.headers);
|
||||
headers.delete('content-length');
|
||||
headers.delete('content-encoding');
|
||||
return new Response(body, { status: resp.status, statusText: resp.statusText, headers });
|
||||
};
|
||||
try {
|
||||
const json: any = JSON.parse(bodyText);
|
||||
if (!json || typeof json !== 'object') return rebuild(bodyText);
|
||||
const json: any = await resp.clone().json();
|
||||
if (!json || typeof json !== 'object') return resp;
|
||||
let modified = false;
|
||||
if (Array.isArray(json.data)) {
|
||||
for (const item of json.data) {
|
||||
@@ -1052,19 +1037,22 @@ const voyageCompatFetch = (async (input: RequestInfo | URL, init?: RequestInit)
|
||||
: 0;
|
||||
modified = true;
|
||||
}
|
||||
if (!modified) return rebuild(bodyText);
|
||||
return rebuild(JSON.stringify(json));
|
||||
if (!modified) return resp;
|
||||
return new Response(JSON.stringify(json), {
|
||||
status: resp.status,
|
||||
statusText: resp.statusText,
|
||||
headers: resp.headers,
|
||||
});
|
||||
} catch (err) {
|
||||
// OOM-cap throws MUST propagate. The catch is here for "Voyage returned
|
||||
// JSON I can't reshape" (parse error, unexpected schema) — falling back
|
||||
// to the original body is correct in that case. Letting the
|
||||
// to the original response is correct in that case. Letting the
|
||||
// too-large response through here would defeat the entire purpose of
|
||||
// Layer 2 (the per-embedding cap that fires when Content-Length wasn't
|
||||
// available to Layer 1).
|
||||
if (err instanceof VoyageResponseTooLargeError) throw err;
|
||||
// If parsing/transformation fails, pass the original body through
|
||||
// (rebuilt — resp's body stream is already consumed by text()).
|
||||
return rebuild(bodyText);
|
||||
// If parsing/transformation fails, fall back to the original response.
|
||||
return resp;
|
||||
}
|
||||
}) as unknown as typeof fetch;
|
||||
|
||||
@@ -1204,21 +1192,9 @@ const zeroEntropyCompatFetch = (async (input: RequestInfo | URL, init?: RequestI
|
||||
// validates. Also map usage.total_tokens → prompt_tokens (SDK requires
|
||||
// prompt_tokens when `usage` is present — same divergence Voyage hit at
|
||||
// gateway.ts:655).
|
||||
//
|
||||
// #1610: read the body ONCE via text() + JSON.parse — `resp.clone().json()`
|
||||
// truncated large bodies on bun < 1.1.27 (oven-sh/bun#6348), so the parse
|
||||
// threw and the catch fell back to the RAW ZE `{results: ...}` shape, which
|
||||
// the AI SDK schema rejects → "Invalid JSON response" on multi-chunk pages.
|
||||
const bodyText = await resp.text();
|
||||
const rebuild = (body: string) => {
|
||||
const headers = new Headers(resp.headers);
|
||||
headers.delete('content-length');
|
||||
headers.delete('content-encoding');
|
||||
return new Response(body, { status: resp.status, statusText: resp.statusText, headers });
|
||||
};
|
||||
try {
|
||||
const json: any = JSON.parse(bodyText);
|
||||
if (!json || typeof json !== 'object') return rebuild(bodyText);
|
||||
const json: any = await resp.clone().json();
|
||||
if (!json || typeof json !== 'object') return resp;
|
||||
let modified = false;
|
||||
if (Array.isArray(json.results) && !Array.isArray(json.data)) {
|
||||
// Layer 2 OOM cap — per-embedding size. ZE returns float[] arrays,
|
||||
@@ -1252,25 +1228,20 @@ const zeroEntropyCompatFetch = (async (input: RequestInfo | URL, init?: RequestI
|
||||
// SDK also expects total_tokens; ZE provides it directly.
|
||||
modified = true;
|
||||
}
|
||||
if (!modified) return rebuild(bodyText);
|
||||
return rebuild(JSON.stringify(json));
|
||||
if (!modified) return resp;
|
||||
return new Response(JSON.stringify(json), {
|
||||
status: resp.status,
|
||||
statusText: resp.statusText,
|
||||
headers: resp.headers,
|
||||
});
|
||||
} catch (err) {
|
||||
// OOM-cap throws MUST propagate. Voyage's pattern: instanceof check on
|
||||
// its own tagged class. Same here — only rethrow our own cap class.
|
||||
if (err instanceof ZeroEntropyResponseTooLargeError) throw err;
|
||||
return rebuild(bodyText);
|
||||
return resp;
|
||||
}
|
||||
}) as unknown as typeof fetch;
|
||||
|
||||
/**
|
||||
* Test-only seams (#1610): the compat shims are module-private closures;
|
||||
* exporting them lets tests drive the response-rewrite paths behaviorally
|
||||
* (truncating clone(), stale Content-Length) without a live provider.
|
||||
* Same pattern as __getShrinkStateForTests.
|
||||
*/
|
||||
export const __voyageCompatFetchForTests = voyageCompatFetch;
|
||||
export const __zeroEntropyCompatFetchForTests = zeroEntropyCompatFetch;
|
||||
|
||||
/**
|
||||
* Generic asymmetric-embedding shim for openai-compatible recipes that
|
||||
* ship no compat fetch of their own (llama-server, litellm, ollama, ...).
|
||||
|
||||
@@ -928,6 +928,10 @@ export const KNOWN_CONFIG_KEYS: readonly string[] = [
|
||||
// Emotional weight (v0.29)
|
||||
'emotional_weight.high_tags',
|
||||
'emotional_weight.user_holder',
|
||||
// Calibration holder (#1726): persistent default for the nightly
|
||||
// calibration_profile phase + `gbrain calibration`, symmetric with
|
||||
// emotional_weight.user_holder. Falls back to 'garry' when unset.
|
||||
'calibration.user_holder',
|
||||
// Cycle phase config
|
||||
'cycle.grade_takes.write_gstack_learnings',
|
||||
// Content sanity (v0.41)
|
||||
|
||||
@@ -96,7 +96,7 @@ export type PatternStatementsGenerator = (input: {
|
||||
export type BiasTagsGenerator = (patterns: string[]) => Promise<string[]>;
|
||||
|
||||
export interface CalibrationProfileOpts extends BasePhaseOpts {
|
||||
/** Holder to generate the profile for. Default 'garry'. */
|
||||
/** Holder to generate the profile for. Default: `calibration.user_holder` config, then 'garry'. */
|
||||
holder?: string;
|
||||
/** Inject the patterns generator (tests). */
|
||||
patternsGenerator?: PatternStatementsGenerator;
|
||||
@@ -194,6 +194,26 @@ export function parseBiasTagsOutput(raw: string): string[] {
|
||||
.slice(0, 4);
|
||||
}
|
||||
|
||||
/**
|
||||
* #1726: resolve the calibration holder. Explicit param wins, then the
|
||||
* persistent `calibration.user_holder` config key (symmetric with
|
||||
* emotional_weight.user_holder), then the legacy 'garry' default. Fail-open:
|
||||
* a missing config table / mock engine without getConfig falls through.
|
||||
*/
|
||||
export async function resolveCalibrationHolder(
|
||||
engine: BrainEngine,
|
||||
explicit?: string,
|
||||
): Promise<string> {
|
||||
if (explicit) return explicit;
|
||||
try {
|
||||
const configured = await engine.getConfig('calibration.user_holder');
|
||||
if (configured && configured.trim().length > 0) return configured.trim();
|
||||
} catch {
|
||||
// Config unavailable — use the legacy default.
|
||||
}
|
||||
return 'garry';
|
||||
}
|
||||
|
||||
/** Pick the "loudest" pattern slot for the template fallback. */
|
||||
function pickFallbackSlots(scorecard: TakesScorecard): PatternStatementSlots {
|
||||
if (!scorecard || scorecard.resolved === 0) {
|
||||
@@ -227,7 +247,7 @@ class CalibrationProfilePhase extends BaseCyclePhase {
|
||||
_ctx: OperationContext,
|
||||
opts: CalibrationProfileOpts,
|
||||
): Promise<{ summary: string; details: Record<string, unknown>; status?: PhaseStatus }> {
|
||||
const holder = opts.holder ?? 'garry';
|
||||
const holder = await resolveCalibrationHolder(engine, opts.holder);
|
||||
const promptVersion = opts.promptVersion ?? CALIBRATION_PROFILE_PROMPT_VERSION;
|
||||
const modelId = opts.model ?? TIER_DEFAULTS.reasoning;
|
||||
const gradeCompletion = opts.gradeCompletion ?? 1.0;
|
||||
|
||||
@@ -68,11 +68,14 @@ export async function extractTimelineFromMeetings(
|
||||
// 1. Fetch all meeting pages (one round-trip).
|
||||
const sourceFilter = opts.sourceIdFilter ? `AND source_id = $1` : '';
|
||||
const meetingParams = opts.sourceIdFilter ? [opts.sourceIdFilter] : [];
|
||||
// #2109: gbrain-base-v2's unify-types catch-all retypes meeting pages to
|
||||
// `note` with frontmatter.legacy_type = 'meeting'. Match both spellings so
|
||||
// the extractor keeps working on migrated (v2) brains, not just v1 ones.
|
||||
const meetings = await engine.executeRaw<MeetingRow>(
|
||||
`SELECT slug, source_id, title, effective_date, updated_at,
|
||||
compiled_truth, COALESCE(timeline, '') AS timeline
|
||||
FROM pages
|
||||
WHERE type = 'meeting'
|
||||
WHERE (type = 'meeting' OR frontmatter ->> 'legacy_type' = 'meeting')
|
||||
AND deleted_at IS NULL
|
||||
${sourceFilter}
|
||||
ORDER BY effective_date DESC NULLS LAST, slug`,
|
||||
@@ -94,7 +97,7 @@ export async function extractTimelineFromMeetings(
|
||||
JOIN pages pf ON pf.id = l.from_page_id
|
||||
JOIN pages pt ON pt.id = l.to_page_id
|
||||
WHERE l.link_type = 'attended'
|
||||
AND pf.type = 'meeting'
|
||||
AND (pf.type = 'meeting' OR pf.frontmatter ->> 'legacy_type' = 'meeting')
|
||||
AND pf.deleted_at IS NULL
|
||||
AND pt.deleted_at IS NULL`,
|
||||
);
|
||||
|
||||
+6
-14
@@ -499,7 +499,7 @@ export function linkReadScopeOpts(ctx: OperationContext): { sourceId?: string; s
|
||||
* FAIL-CLOSED: anything not strictly `ctx.remote === false` is untrusted.
|
||||
*
|
||||
* This is the SINGLE resolver for every read op that accepts a per-call
|
||||
* `source_id` / `all_sources` parameter (query, search, code_callers, code_callees,
|
||||
* `source_id` / `all_sources` parameter (query, code_callers, code_callees,
|
||||
* get_page, search_by_image, code_blast, code_flow). Inlining the `__all__`
|
||||
* branch per handler is the bug class that leaked cross-source reads (#1924,
|
||||
* #1371): a remote client could pass `source_id: '__all__'` to opt out of its
|
||||
@@ -1442,24 +1442,13 @@ const search: Operation = {
|
||||
limit: { type: 'number', description: 'Max results (default 20)' },
|
||||
offset: { type: 'number', description: 'Skip first N results (for pagination)' },
|
||||
mode: { type: 'string', description: 'Search mode (conservative|balanced|tokenmax). Local callers only.' },
|
||||
source_id: {
|
||||
type: 'string',
|
||||
description:
|
||||
"Scope search to a single source. Defaults to OperationContext.sourceId. Pass '__all__' to span every source for trusted local callers; for remote callers '__all__' spans only your granted sources.",
|
||||
},
|
||||
all_sources: { type: 'boolean', description: "Span sources (equivalent to source_id=__all__): every source locally, your grant remotely." },
|
||||
},
|
||||
handler: async (ctx, p) => {
|
||||
const startedAt = Date.now();
|
||||
const queryText = p.query as string;
|
||||
const limit = (p.limit as number) || 20;
|
||||
const offset = (p.offset as number) || 0;
|
||||
// #1484 follow-up: route through the canonical fail-closed resolver so
|
||||
// `--source-id __all__` / `all_sources` behave the same as on `query`
|
||||
// (the zero-hit CLI hint advises exactly that retry). Without a per-call
|
||||
// param, `search` silently ignored --source-id — the retry looked like
|
||||
// a genuine miss.
|
||||
const scope = resolveRequestedScope(ctx, p.source_id as string | undefined, p.all_sources === true);
|
||||
const scope = sourceScopeOpts(ctx);
|
||||
|
||||
// T4/D5 — per-call mode honored ONLY for trusted/local callers so a remote
|
||||
// OAuth client can't escalate to the costly tokenmax bundle. Local + unknown
|
||||
@@ -4573,7 +4562,10 @@ const list_schema_packs: Operation = {
|
||||
const { existsSync, readdirSync } = await import('node:fs');
|
||||
const { join } = await import('node:path');
|
||||
const { gbrainPath } = await import('./config.ts');
|
||||
const bundled = ['gbrain-base', 'gbrain-recommended'];
|
||||
// #1726: derive from the locator's registry instead of a hand-copied
|
||||
// subset (which had frozen at 2 of 7 bundled packs).
|
||||
const { BUNDLED_PACKS } = await import('./schema-pack/load-active.ts');
|
||||
const bundled = [...BUNDLED_PACKS];
|
||||
const installedDir = gbrainPath('schema-packs');
|
||||
const installed: string[] = [];
|
||||
if (existsSync(installedDir)) {
|
||||
|
||||
@@ -41,6 +41,12 @@ migration_from:
|
||||
pack: gbrain-base
|
||||
version: "1.x"
|
||||
|
||||
# #2117 — cycle-phase participation. `phases:` is additive and pack-gated;
|
||||
# without this key extract_atoms is silently off on v2 brains even though
|
||||
# onboard + doctor recommend it (v2 declares the `atom` type it writes).
|
||||
phases:
|
||||
- extract_atoms
|
||||
|
||||
page_types:
|
||||
- name: person
|
||||
primitive: entity
|
||||
@@ -319,6 +325,10 @@ page_types:
|
||||
extractable: false
|
||||
expert_routing: false
|
||||
|
||||
# #2117 — inference rules ported from gbrain-base v1 so extract-ner keeps
|
||||
# working on v2 brains (it hard-skips with pack_unavailable when no
|
||||
# link_type declares an inference.regex). Same ReDoS-guarded sketch
|
||||
# regexes v1 ships; production matchers in link-extraction.ts still apply.
|
||||
link_types:
|
||||
- name: partner_of
|
||||
inverse: partner_of
|
||||
@@ -328,14 +338,24 @@ link_types:
|
||||
- name: discusses
|
||||
- name: founded
|
||||
inverse: founded_by
|
||||
inference:
|
||||
regex: \b(founded|founder of|co-?founded|started)\b
|
||||
- name: works_at
|
||||
inverse: employs
|
||||
inference:
|
||||
regex: \b(works? at|employed by|works? for|joined|hired by|ceo of|cto of|cmo of)\b
|
||||
- name: invested_in
|
||||
inverse: investor_of
|
||||
inference:
|
||||
regex: \b(invested in|backed|seeded|funded|wrote a check)\b
|
||||
- name: sourced_from
|
||||
- name: derived_from
|
||||
- name: supersedes
|
||||
- name: redirects_to
|
||||
# NOTE: v1's `attended` inference is page_type-bound to `meeting`, which
|
||||
# v2 does not declare (lint: link_types_undeclared_page_type). Meeting
|
||||
# pages retyped by unify-types are matched via frontmatter.legacy_type
|
||||
# in extract-timeline-from-meetings (#2109) instead.
|
||||
- name: attended
|
||||
inverse: attended_by
|
||||
- name: authored
|
||||
|
||||
@@ -91,29 +91,33 @@ export function _resetPackLocatorForTests(): void {
|
||||
* Returns null when the pack is not found. Callers handle null by
|
||||
* throwing UnknownPackError with a paste-ready install hint.
|
||||
*/
|
||||
// v0.39 T8 — bundled packs registry. gbrain-base + gbrain-recommended
|
||||
// ship in src/core/schema-pack/base/. Add a new entry here to bundle
|
||||
// additional canonical packs.
|
||||
//
|
||||
// v0.41 T4 — lens packs join the bundle: creator (atoms + concepts +
|
||||
// extract_atoms/synthesize_concepts phases), investor (theses + bet
|
||||
// resolution + 3 calibration domains), engineer (gstack-learnings bridge
|
||||
// + 3 calibration domains), everything (meta-pack stacking all three
|
||||
// via extends + borrow_from). Each ships as a real YAML at base/<name>.yaml.
|
||||
//
|
||||
// #1726: exported so reporting surfaces (list_schema_packs) derive from the
|
||||
// same list the locator resolves — no more hand-copied 2-of-7 subsets.
|
||||
export const BUNDLED_PACKS: ReadonlyArray<string> = [
|
||||
'gbrain-base',
|
||||
'gbrain-recommended',
|
||||
'gbrain-creator',
|
||||
'gbrain-investor',
|
||||
'gbrain-engineer',
|
||||
'gbrain-everything',
|
||||
// v0.42 type-unification: 15-type canonical successor to gbrain-base.
|
||||
// Ships as install default (Lane E T17) + via gbrain onboard pack
|
||||
// upgrade flow (the unify-types Minion handler).
|
||||
'gbrain-base-v2',
|
||||
];
|
||||
|
||||
function defaultPackLocator(name: string): string | null {
|
||||
// v0.39 T8 — bundled packs registry. gbrain-base + gbrain-recommended
|
||||
// ship in src/core/schema-pack/base/. Add a new entry here to bundle
|
||||
// additional canonical packs.
|
||||
//
|
||||
// v0.41 T4 — lens packs join the bundle: creator (atoms + concepts +
|
||||
// extract_atoms/synthesize_concepts phases), investor (theses + bet
|
||||
// resolution + 3 calibration domains), engineer (gstack-learnings bridge
|
||||
// + 3 calibration domains), everything (meta-pack stacking all three
|
||||
// via extends + borrow_from). Each ships as a real YAML at base/<name>.yaml.
|
||||
const BUNDLED: ReadonlyArray<string> = [
|
||||
'gbrain-base',
|
||||
'gbrain-recommended',
|
||||
'gbrain-creator',
|
||||
'gbrain-investor',
|
||||
'gbrain-engineer',
|
||||
'gbrain-everything',
|
||||
// v0.42 type-unification: 15-type canonical successor to gbrain-base.
|
||||
// Ships as install default (Lane E T17) + via gbrain onboard pack
|
||||
// upgrade flow (the unify-types Minion handler).
|
||||
'gbrain-base-v2',
|
||||
];
|
||||
if (BUNDLED.includes(name)) {
|
||||
if (BUNDLED_PACKS.includes(name)) {
|
||||
// Resolve bundled YAML relative to this source file. Works in both
|
||||
// direct-bun execution and bun --compile binaries.
|
||||
const here = dirname(fileURLToPath(import.meta.url));
|
||||
|
||||
@@ -1323,18 +1323,8 @@ export async function hybridSearch(
|
||||
if (effectiveModality === 'both' && imageVectorList !== null) {
|
||||
vectorLists = [...vectorLists, imageVectorList];
|
||||
}
|
||||
} catch (err) {
|
||||
// Embedding/vector failure is non-fatal — fall back to keyword-only —
|
||||
// but say WHY (#1626): this arm only runs when the embedding provider
|
||||
// probed available, so a throw here is a real failure (embed timeout,
|
||||
// transient pooler error on the searchVector fan-out). Pre-fix the bare
|
||||
// catch made a cross-source `--source __all__` run silently collapse to
|
||||
// keyword-only/"No results" with zero diagnostics.
|
||||
warnOncePerProcess(
|
||||
'hybrid-vector-arm-failed',
|
||||
`[gbrain] vector arm failed (fail-open, keyword-only fallback): ` +
|
||||
`${err instanceof Error ? err.message : String(err)}`,
|
||||
);
|
||||
} catch {
|
||||
// Embedding failure is non-fatal, fall back to keyword-only
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -1,115 +0,0 @@
|
||||
/**
|
||||
* #1610 — Voyage/ZeroEntropy compat shims must read the response body ONCE
|
||||
* via text() instead of `resp.clone().json()`.
|
||||
*
|
||||
* On bun < 1.1.27, Response.clone() truncates large bodies (oven-sh/bun#6348):
|
||||
* the clone().json() parse threw, the shim's catch fell back to the ORIGINAL
|
||||
* response — whose wire shape (ZE `{results: ...}`, Voyage base64 embeddings)
|
||||
* the AI SDK's openai-compatible Zod schema rejects — and multi-chunk pages
|
||||
* failed with "Invalid JSON response".
|
||||
*
|
||||
* These tests simulate the truncating clone() and assert the shims still
|
||||
* return the fully rewritten body. They also pin that the rewritten Response
|
||||
* does NOT carry the original (now stale) Content-Length header, which lied
|
||||
* about the rewritten body's size (gateway.ts previously copied
|
||||
* `headers: resp.headers` verbatim).
|
||||
*/
|
||||
|
||||
import { afterEach, describe, expect, test } from 'bun:test';
|
||||
import {
|
||||
__voyageCompatFetchForTests,
|
||||
__zeroEntropyCompatFetchForTests,
|
||||
} from '../../src/core/ai/gateway.ts';
|
||||
|
||||
const origFetch = globalThis.fetch;
|
||||
afterEach(() => {
|
||||
globalThis.fetch = origFetch;
|
||||
});
|
||||
|
||||
/** Build a Response whose clone() truncates the body (bun < 1.1.27 behavior). */
|
||||
function truncatingCloneResponse(body: string): Response {
|
||||
const headers = {
|
||||
'content-type': 'application/json',
|
||||
// Deliberately stale after any rewrite: the original wire body's length.
|
||||
'content-length': String(Buffer.byteLength(body)),
|
||||
};
|
||||
const resp = new Response(body, { status: 200, headers });
|
||||
(resp as any).clone = () =>
|
||||
new Response(body.slice(0, 32), { status: 200, headers });
|
||||
return resp;
|
||||
}
|
||||
|
||||
describe('voyageCompatFetch — single body read (#1610)', () => {
|
||||
test('rewrites base64 embeddings even when clone() truncates the body', async () => {
|
||||
const floats = new Float32Array([0.5, 0.25, -1]);
|
||||
const b64 = Buffer.from(floats.buffer).toString('base64');
|
||||
const wireBody = JSON.stringify({
|
||||
object: 'list',
|
||||
data: [{ object: 'embedding', embedding: b64, index: 0 }],
|
||||
model: 'voyage-3',
|
||||
usage: { total_tokens: 7 },
|
||||
});
|
||||
globalThis.fetch = (async () => truncatingCloneResponse(wireBody)) as unknown as typeof fetch;
|
||||
|
||||
const out = await __voyageCompatFetchForTests('https://api.voyageai.com/v1/embeddings', {
|
||||
method: 'POST',
|
||||
body: JSON.stringify({ input: ['hello'], model: 'voyage-3' }),
|
||||
headers: { 'content-type': 'application/json' },
|
||||
});
|
||||
|
||||
const json: any = await out.json();
|
||||
expect(Array.from(json.data[0].embedding)).toEqual([0.5, 0.25, -1]);
|
||||
expect(json.usage.prompt_tokens).toBe(7);
|
||||
// Stale Content-Length from the wire body must not survive the rewrite.
|
||||
expect(out.headers.get('content-length')).toBeNull();
|
||||
expect(out.headers.get('content-encoding')).toBeNull();
|
||||
});
|
||||
});
|
||||
|
||||
describe('zeroEntropyCompatFetch — single body read (#1610)', () => {
|
||||
test('rewrites {results} → {data} even when clone() truncates the body', async () => {
|
||||
const wireBody = JSON.stringify({
|
||||
results: [{ embedding: [0.1, 0.2] }, { embedding: [0.3, 0.4] }],
|
||||
usage: { total_bytes: 42, total_tokens: 9 },
|
||||
});
|
||||
let fetchedUrl = '';
|
||||
globalThis.fetch = (async (url: string | URL | Request) => {
|
||||
fetchedUrl = String(url);
|
||||
return truncatingCloneResponse(wireBody);
|
||||
}) as unknown as typeof fetch;
|
||||
|
||||
const out = await __zeroEntropyCompatFetchForTests('https://api.zeroentropy.dev/v1/embeddings', {
|
||||
method: 'POST',
|
||||
body: JSON.stringify({ input: ['hello'], model: 'zembed-1' }),
|
||||
headers: { 'content-type': 'application/json' },
|
||||
});
|
||||
|
||||
expect(fetchedUrl.endsWith('/v1/models/embed')).toBe(true);
|
||||
const json: any = await out.json();
|
||||
// The AI SDK schema requires {data: [{embedding, index}]} — the raw ZE
|
||||
// {results} fallback is exactly the pre-fix "Invalid JSON response".
|
||||
expect(json.results).toBeUndefined();
|
||||
expect(json.data).toHaveLength(2);
|
||||
expect(json.data[0]).toEqual({ object: 'embedding', embedding: [0.1, 0.2], index: 0 });
|
||||
expect(json.data[1].index).toBe(1);
|
||||
expect(json.usage.prompt_tokens).toBe(9);
|
||||
expect(out.headers.get('content-length')).toBeNull();
|
||||
});
|
||||
|
||||
test('non-JSON body falls back to the original bytes (rebuilt, still readable)', async () => {
|
||||
const wireBody = 'plain text, not json';
|
||||
globalThis.fetch = (async () =>
|
||||
new Response(wireBody, {
|
||||
status: 200,
|
||||
headers: { 'content-type': 'application/json' },
|
||||
})) as unknown as typeof fetch;
|
||||
|
||||
const out = await __zeroEntropyCompatFetchForTests('https://api.zeroentropy.dev/v1/embeddings', {
|
||||
method: 'POST',
|
||||
body: JSON.stringify({ input: ['hello'] }),
|
||||
});
|
||||
// Body was consumed by the shim's single read; the fallback must
|
||||
// rebuild a readable Response rather than return the drained original.
|
||||
expect(await out.text()).toBe(wireBody);
|
||||
});
|
||||
});
|
||||
@@ -98,18 +98,16 @@ describe('zeroEntropyCompatFetch — OOM caps', () => {
|
||||
expect(src).toMatch(/MAX_ZEROENTROPY_RESPONSE_BYTES\s*=\s*256\s*\*\s*1024\s*\*\s*1024/);
|
||||
});
|
||||
|
||||
test('Layer 1: Content-Length pre-check before the body is read', async () => {
|
||||
test('Layer 1: Content-Length pre-check before resp.clone().json()', async () => {
|
||||
const src = await Bun.file(GATEWAY_PATH).text();
|
||||
// Find the zeroEntropyCompatFetch block bounds, then assert ordering
|
||||
// within it (mirroring the voyage cap test pattern). #1610 moved the
|
||||
// body read from `resp.clone().json()` to a single `resp.text()` (bun
|
||||
// < 1.1.27 truncates clone()d bodies, oven-sh/bun#6348).
|
||||
// within it (mirroring the voyage cap test pattern).
|
||||
const zeFetchStart = src.indexOf('const zeroEntropyCompatFetch');
|
||||
expect(zeFetchStart).toBeGreaterThan(0);
|
||||
const block = src.slice(zeFetchStart, zeFetchStart + 9000);
|
||||
const block = src.slice(zeFetchStart, zeFetchStart + 8000);
|
||||
|
||||
const preCheckIdx = block.indexOf("resp.headers.get('content-length')");
|
||||
const jsonParseIdx = block.indexOf('const bodyText = await resp.text()');
|
||||
const jsonParseIdx = block.indexOf('await resp.clone().json()');
|
||||
expect(preCheckIdx).toBeGreaterThan(0);
|
||||
expect(jsonParseIdx).toBeGreaterThan(0);
|
||||
// The pre-check MUST appear before the JSON parse — Voyage's lesson
|
||||
|
||||
@@ -32,7 +32,7 @@ interface CapturedSql {
|
||||
params: unknown[];
|
||||
}
|
||||
|
||||
function buildMockEngine(opts: { scorecard: TakesScorecard }): {
|
||||
function buildMockEngine(opts: { scorecard: TakesScorecard; config?: Record<string, string> }): {
|
||||
engine: BrainEngine;
|
||||
captured: CapturedSql[];
|
||||
} {
|
||||
@@ -42,6 +42,9 @@ function buildMockEngine(opts: { scorecard: TakesScorecard }): {
|
||||
async getScorecard() {
|
||||
return opts.scorecard;
|
||||
},
|
||||
async getConfig(key: string) {
|
||||
return opts.config?.[key] ?? null;
|
||||
},
|
||||
async executeRaw<T>(sql: string, params?: unknown[]): Promise<T[]> {
|
||||
captured.push({ sql, params: params ?? [] });
|
||||
return [];
|
||||
@@ -241,6 +244,36 @@ describe('runPhaseCalibrationProfile — phase integration', () => {
|
||||
expect(insert!.params[11]).toEqual(['over-confident-geography']); // active_bias_tags
|
||||
});
|
||||
|
||||
test('#1726: calibration.user_holder config drives the holder when no explicit opt', async () => {
|
||||
const { engine, captured } = buildMockEngine({
|
||||
scorecard: ENOUGH_RESOLVED_SCORECARD,
|
||||
config: { 'calibration.user_holder': 'alice-example' },
|
||||
});
|
||||
await runPhaseCalibrationProfile(buildCtx(engine), {
|
||||
patternsGenerator: async () => ['You call early-stage tactics well — 8 of 10 held up.'],
|
||||
biasTagsGenerator: async () => [],
|
||||
voiceGateJudge: passJudge,
|
||||
});
|
||||
const insert = captured.find(c => c.sql.includes('INSERT INTO calibration_profiles'));
|
||||
expect(insert).toBeDefined();
|
||||
expect(insert!.params[1]).toBe('alice-example'); // holder from config
|
||||
});
|
||||
|
||||
test('#1726: explicit holder opt wins over calibration.user_holder config', async () => {
|
||||
const { engine, captured } = buildMockEngine({
|
||||
scorecard: ENOUGH_RESOLVED_SCORECARD,
|
||||
config: { 'calibration.user_holder': 'alice-example' },
|
||||
});
|
||||
await runPhaseCalibrationProfile(buildCtx(engine), {
|
||||
holder: 'charlie-example',
|
||||
patternsGenerator: async () => ['You call early-stage tactics well — 8 of 10 held up.'],
|
||||
biasTagsGenerator: async () => [],
|
||||
voiceGateJudge: passJudge,
|
||||
});
|
||||
const insert = captured.find(c => c.sql.includes('INSERT INTO calibration_profiles'));
|
||||
expect(insert!.params[1]).toBe('charlie-example');
|
||||
});
|
||||
|
||||
test('default model is a provider-prefixed id, persisted to model_id (#2451)', async () => {
|
||||
const { engine, captured } = buildMockEngine({ scorecard: ENOUGH_RESOLVED_SCORECARD });
|
||||
const patternsGenerator: PatternStatementsGenerator = async () => [
|
||||
|
||||
@@ -1,61 +0,0 @@
|
||||
/**
|
||||
* #1484 — invisible-miss hint. A bare `gbrain query` resolves to a single
|
||||
* source (usually 'default'); on a multi-source brain a zero-hit run gave no
|
||||
* signal that the answer might live in another source. sourceScopeHint
|
||||
* returns the stderr hint exactly when: query/search op + zero results +
|
||||
* no explicit scoping param + >1 registered source.
|
||||
*/
|
||||
|
||||
import { describe, expect, test } from 'bun:test';
|
||||
import { sourceScopeHint } from '../src/cli.ts';
|
||||
import type { BrainEngine } from '../src/core/engine.ts';
|
||||
|
||||
function fakeEngine(sourceCount: number, fail = false): BrainEngine {
|
||||
return {
|
||||
executeRaw: async () => {
|
||||
if (fail) throw new Error('sources table missing');
|
||||
return [{ n: sourceCount }];
|
||||
},
|
||||
} as unknown as BrainEngine;
|
||||
}
|
||||
|
||||
describe('sourceScopeHint (#1484)', () => {
|
||||
test('fires on a bare zero-hit query against a multi-source brain', async () => {
|
||||
const hint = await sourceScopeHint('query', {}, 'default', fakeEngine(3), []);
|
||||
expect(hint).toContain('3 sources');
|
||||
expect(hint).toContain('"default"');
|
||||
expect(hint).toContain('--source-id __all__');
|
||||
});
|
||||
|
||||
test('fires for search too', async () => {
|
||||
const hint = await sourceScopeHint('search', {}, 'wiki', fakeEngine(2), []);
|
||||
expect(hint).toContain('"wiki"');
|
||||
});
|
||||
|
||||
test('silent when results were found', async () => {
|
||||
expect(await sourceScopeHint('query', {}, 'default', fakeEngine(3), [{ slug: 'a' }])).toBeNull();
|
||||
});
|
||||
|
||||
test('silent when the caller scoped explicitly', async () => {
|
||||
expect(await sourceScopeHint('query', { source_id: 'wiki' }, 'wiki', fakeEngine(3), [])).toBeNull();
|
||||
expect(await sourceScopeHint('query', { source: 'wiki' }, 'wiki', fakeEngine(3), [])).toBeNull();
|
||||
expect(await sourceScopeHint('query', { all_sources: true }, '__all__', fakeEngine(3), [])).toBeNull();
|
||||
});
|
||||
|
||||
test('silent when the resolved scope is already __all__', async () => {
|
||||
expect(await sourceScopeHint('query', {}, '__all__', fakeEngine(3), [])).toBeNull();
|
||||
});
|
||||
|
||||
test('silent on a single-source brain', async () => {
|
||||
expect(await sourceScopeHint('query', {}, 'default', fakeEngine(1), [])).toBeNull();
|
||||
});
|
||||
|
||||
test('silent for non-search ops and non-array results', async () => {
|
||||
expect(await sourceScopeHint('get_stats', {}, 'default', fakeEngine(3), [])).toBeNull();
|
||||
expect(await sourceScopeHint('query', {}, 'default', fakeEngine(3), { rows: [] })).toBeNull();
|
||||
});
|
||||
|
||||
test('best-effort: sources lookup failure returns null, never throws', async () => {
|
||||
expect(await sourceScopeHint('query', {}, 'default', fakeEngine(3, true), [])).toBeNull();
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,106 @@
|
||||
// #2109 — gbrain-base-v2's unify-types retypes meeting pages to `note`
|
||||
// with frontmatter.legacy_type='meeting'. extract-timeline-from-meetings
|
||||
// used to hardcode type='meeting' and silently scan 0 meetings on migrated
|
||||
// brains. These tests fail without the legacy_type fallback in both SQL
|
||||
// sites (meeting walk + attended-edge join).
|
||||
|
||||
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 { extractTimelineFromMeetings } from '../src/core/extract-timeline-from-meetings.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);
|
||||
});
|
||||
|
||||
async function insertPage(opts: {
|
||||
slug: string;
|
||||
type: string;
|
||||
title: string;
|
||||
effectiveDate?: string;
|
||||
legacyType?: string;
|
||||
}): Promise<number> {
|
||||
const frontmatterLiteral = opts.legacyType
|
||||
? `'{"legacy_type": "${opts.legacyType}"}'::jsonb`
|
||||
: `'{}'::jsonb`;
|
||||
const rows = await engine.executeRaw<{ id: number }>(
|
||||
`INSERT INTO pages (slug, source_id, type, title, compiled_truth, timeline, effective_date, frontmatter)
|
||||
VALUES ($1, 'default', $2, $3, '', '', $4, ${frontmatterLiteral})
|
||||
RETURNING id`,
|
||||
[opts.slug, opts.type, opts.title, opts.effectiveDate ?? null],
|
||||
);
|
||||
return rows[0]!.id;
|
||||
}
|
||||
|
||||
describe('extractTimelineFromMeetings — legacy_type fallback (#2109)', () => {
|
||||
it('scans pages retyped to note with legacy_type=meeting and walks their attended edges', async () => {
|
||||
const meetingId = await insertPage({
|
||||
slug: 'meetings/2026-01-05',
|
||||
type: 'note', // post-unify-types shape on a gbrain-base-v2 brain
|
||||
legacyType: 'meeting',
|
||||
title: 'Weekly sync',
|
||||
effectiveDate: '2026-01-05',
|
||||
});
|
||||
const personId = await insertPage({
|
||||
slug: 'people/alice-example',
|
||||
type: 'person',
|
||||
title: 'Alice Example',
|
||||
});
|
||||
await engine.executeRaw(
|
||||
`INSERT INTO links (from_page_id, to_page_id, link_type) VALUES ($1, $2, 'attended')`,
|
||||
[meetingId, personId],
|
||||
);
|
||||
|
||||
const result = await extractTimelineFromMeetings(engine);
|
||||
expect(result.meetings_scanned).toBe(1);
|
||||
expect(result.entries_created).toBe(1);
|
||||
expect(result.entities_touched).toBe(1);
|
||||
expect(result.batch_errors).toBe(0);
|
||||
});
|
||||
|
||||
it('still scans pre-unify pages with type=meeting (v1 behavior preserved)', async () => {
|
||||
const meetingId = await insertPage({
|
||||
slug: 'meetings/2026-02-01',
|
||||
type: 'meeting',
|
||||
title: 'Board prep',
|
||||
effectiveDate: '2026-02-01',
|
||||
});
|
||||
const personId = await insertPage({
|
||||
slug: 'people/charlie-example',
|
||||
type: 'person',
|
||||
title: 'Charlie Example',
|
||||
});
|
||||
await engine.executeRaw(
|
||||
`INSERT INTO links (from_page_id, to_page_id, link_type) VALUES ($1, $2, 'attended')`,
|
||||
[meetingId, personId],
|
||||
);
|
||||
|
||||
const result = await extractTimelineFromMeetings(engine);
|
||||
expect(result.meetings_scanned).toBe(1);
|
||||
expect(result.entries_created).toBe(1);
|
||||
});
|
||||
|
||||
it('does not scan unrelated note pages without legacy_type=meeting', async () => {
|
||||
await insertPage({
|
||||
slug: 'notes/random',
|
||||
type: 'note',
|
||||
title: 'Random note',
|
||||
effectiveDate: '2026-03-01',
|
||||
});
|
||||
const result = await extractTimelineFromMeetings(engine);
|
||||
expect(result.meetings_scanned).toBe(0);
|
||||
expect(result.entries_created).toBe(0);
|
||||
});
|
||||
});
|
||||
@@ -1,77 +0,0 @@
|
||||
/**
|
||||
* #1626 — hybridSearch's text-vector arm must not fail DARK.
|
||||
*
|
||||
* The arm only runs when the embedding provider probed available, so a throw
|
||||
* inside it (embed timeout, transient pooler error on searchVector) is a real
|
||||
* failure. Pre-fix, a bare `catch {}` swallowed it and the run silently
|
||||
* collapsed to keyword-only — under `--source __all__` on a strained pooler
|
||||
* that read as a non-deterministic "No results". The fix logs the swallowed
|
||||
* reason via warnOncePerProcess while keeping the keyword fallback.
|
||||
*/
|
||||
|
||||
import { afterAll, beforeAll, describe, expect, test } from 'bun:test';
|
||||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||||
import { hybridSearch } from '../src/core/search/hybrid.ts';
|
||||
import {
|
||||
__setEmbedTransportForTests,
|
||||
configureGateway,
|
||||
resetGateway,
|
||||
} from '../src/core/ai/gateway.ts';
|
||||
import { _resetWarnOnceForTests } from '../src/core/utils.ts';
|
||||
|
||||
let engine: PGLiteEngine;
|
||||
const origWarn = console.warn;
|
||||
|
||||
beforeAll(async () => {
|
||||
// Pin the gateway to OpenAI with a stub key (put-page-provenance pattern):
|
||||
// embed() runs instantiateEmbedding — which requires OPENAI_API_KEY — BEFORE
|
||||
// the stubbed transport is reached. Without this, a keyless CI environment
|
||||
// throws the config error instead of the transport's, and the assertion on
|
||||
// the swallowed reason fails. The key never leaves the process.
|
||||
configureGateway({
|
||||
embedding_model: 'openai:text-embedding-3-large',
|
||||
embedding_dimensions: 1536,
|
||||
env: { ...process.env, OPENAI_API_KEY: process.env.OPENAI_API_KEY || 'sk-test-stub' },
|
||||
});
|
||||
engine = new PGLiteEngine();
|
||||
await engine.connect({});
|
||||
await engine.initSchema();
|
||||
await engine.putPage('people/alice-example', {
|
||||
type: 'person',
|
||||
title: 'Alice Example',
|
||||
compiled_truth: 'Alice Example is a test person for the vector-arm warn test.',
|
||||
});
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
console.warn = origWarn;
|
||||
__setEmbedTransportForTests(null);
|
||||
resetGateway();
|
||||
await engine.disconnect();
|
||||
});
|
||||
|
||||
describe('hybridSearch vector-arm failure telemetry (#1626)', () => {
|
||||
test('embed failure logs the swallowed reason and falls back to keyword', async () => {
|
||||
_resetWarnOnceForTests();
|
||||
// Installing a transport makes isAvailable('embedding') true (test-seam
|
||||
// fast path), so the vector arm RUNS — and then throws.
|
||||
__setEmbedTransportForTests(() => {
|
||||
throw new Error('pooler exploded mid-fanout');
|
||||
});
|
||||
const warnings: string[] = [];
|
||||
console.warn = (...args: unknown[]) => {
|
||||
warnings.push(args.map(String).join(' '));
|
||||
};
|
||||
try {
|
||||
const results = await hybridSearch(engine, 'alice');
|
||||
// Keyword fallback still returns results — fail-open preserved.
|
||||
expect(results.some((r) => r.slug === 'people/alice-example')).toBe(true);
|
||||
} finally {
|
||||
console.warn = origWarn;
|
||||
__setEmbedTransportForTests(null);
|
||||
}
|
||||
const armWarnings = warnings.filter((w) => w.includes('vector arm failed'));
|
||||
expect(armWarnings).toHaveLength(1);
|
||||
expect(armWarnings[0]).toContain('pooler exploded mid-fanout');
|
||||
});
|
||||
});
|
||||
@@ -152,6 +152,19 @@ describe('list_schema_packs', () => {
|
||||
expect(result.installed).toContain('mine');
|
||||
});
|
||||
});
|
||||
|
||||
it('reports the full bundled registry, not a hand-copied subset (#1726)', async () => {
|
||||
await withEnv({ GBRAIN_HOME: tmpDir }, async () => {
|
||||
const { BUNDLED_PACKS } = await import('../src/core/schema-pack/load-active.ts');
|
||||
const result = await operationsByName.list_schema_packs!.handler(ctxOf(), {}) as { bundled: string[] };
|
||||
expect(result.bundled.slice().sort()).toEqual([...BUNDLED_PACKS].sort());
|
||||
// The lens packs that declare extract_atoms/synthesize_concepts phases
|
||||
// were the ones dropped by the frozen 2-pack literal.
|
||||
for (const name of ['gbrain-creator', 'gbrain-everything', 'gbrain-base-v2']) {
|
||||
expect(result.bundled).toContain(name);
|
||||
}
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
// ── schema_stats ───────────────────────────────────────────────────────
|
||||
|
||||
@@ -0,0 +1,40 @@
|
||||
// #2117 — gbrain-base-v2 shipped with no `phases:` declaration and zero
|
||||
// link_types[].inference regexes, so extract_atoms was silently pack-gated
|
||||
// off and extract-ner returned pack_unavailable on the bundled default pack.
|
||||
// These assertions fail against the pre-fix yaml.
|
||||
|
||||
import { describe, expect, it } from 'bun:test';
|
||||
import { join } from 'node:path';
|
||||
import { loadPackFromFile } from '../src/core/schema-pack/loader.ts';
|
||||
import { linkTypesUndeclared } from '../src/core/schema-pack/lint-rules.ts';
|
||||
|
||||
const V2_PATH = join(import.meta.dir, '..', 'src', 'core', 'schema-pack', 'base', 'gbrain-base-v2.yaml');
|
||||
|
||||
describe('gbrain-base-v2 capability parity (#2117)', () => {
|
||||
const manifest = loadPackFromFile(V2_PATH);
|
||||
|
||||
it('declares the extract_atoms cycle phase', () => {
|
||||
expect(manifest.phases ?? []).toContain('extract_atoms');
|
||||
});
|
||||
|
||||
it('ships at least one link_type inference regex so extract-ner is not pack_unavailable', () => {
|
||||
// Mirrors the extract-ner hasRegex predicate exactly.
|
||||
const hasRegex = manifest.link_types.some(
|
||||
(lt) => lt.inference && typeof lt.inference === 'object' && 'regex' in lt.inference,
|
||||
);
|
||||
expect(hasRegex).toBe(true);
|
||||
});
|
||||
|
||||
it('ports the v1 inference verbs it declares link types for', () => {
|
||||
const withRegex = manifest.link_types
|
||||
.filter((lt) => lt.inference?.regex)
|
||||
.map((lt) => lt.name)
|
||||
.sort();
|
||||
expect(withRegex).toEqual(['founded', 'invested_in', 'works_at']);
|
||||
});
|
||||
|
||||
it('inference rules pass the undeclared-page-type lint (no meeting-bound inference)', async () => {
|
||||
const issues = await linkTypesUndeclared(manifest);
|
||||
expect(issues).toEqual([]);
|
||||
});
|
||||
});
|
||||
@@ -1,87 +0,0 @@
|
||||
/**
|
||||
* #1484 follow-up — the `search` op must honor per-call `source_id` /
|
||||
* `all_sources` through the canonical fail-closed resolver
|
||||
* (resolveRequestedScope), exactly like `query` does.
|
||||
*
|
||||
* Pre-fix, `search` had no source_id param at all: the zero-hit CLI hint
|
||||
* advised "retry with --source-id __all__", the flag parsed into params,
|
||||
* NOTHING consumed it, and the retry silently re-ran the same single-source
|
||||
* search — an invisible false negative (and the retry's params.source_id
|
||||
* suppressed the hint, so the user got no second warning).
|
||||
*/
|
||||
|
||||
import { describe, expect, test } from 'bun:test';
|
||||
import { operationsByName } from '../src/core/operations.ts';
|
||||
import type { OperationContext } from '../src/core/operations.ts';
|
||||
import type { BrainEngine } from '../src/core/engine.ts';
|
||||
|
||||
const searchOp = operationsByName['search'];
|
||||
|
||||
/** Fake engine: keyword-only config so the handler's scope goes straight to
|
||||
* searchKeyword, where we capture the opts it was called with. */
|
||||
function makeCtx(remote: boolean, allowedSources?: string[]) {
|
||||
const captured: { opts?: Record<string, unknown> } = {};
|
||||
const engine = {
|
||||
getConfig: async (key: string) => (key === 'search.mcp_keyword_only' ? 'true' : null),
|
||||
searchKeyword: async (_q: string, opts: Record<string, unknown>) => {
|
||||
captured.opts = opts;
|
||||
return [];
|
||||
},
|
||||
} as unknown as BrainEngine;
|
||||
const ctx = {
|
||||
engine,
|
||||
config: { engine: 'pglite' },
|
||||
logger: { info: () => {}, warn: () => {}, error: () => {} },
|
||||
dryRun: false,
|
||||
remote,
|
||||
sourceId: 'default',
|
||||
...(allowedSources ? { auth: { allowedSources } } : {}),
|
||||
} as unknown as OperationContext;
|
||||
return { ctx, captured };
|
||||
}
|
||||
|
||||
describe('search op per-call source scope (#1484 follow-up)', () => {
|
||||
test('op declares source_id + all_sources params (the CLI hint advises them)', () => {
|
||||
expect(searchOp.params.source_id).toBeDefined();
|
||||
expect(searchOp.params.all_sources).toBeDefined();
|
||||
});
|
||||
|
||||
test('default: scopes to ctx.sourceId', async () => {
|
||||
const { ctx, captured } = makeCtx(false);
|
||||
await searchOp.handler(ctx, { query: 'x' });
|
||||
expect(captured.opts?.sourceId).toBe('default');
|
||||
});
|
||||
|
||||
test("local + source_id '__all__' spans the whole brain (no source filter)", async () => {
|
||||
const { ctx, captured } = makeCtx(false);
|
||||
await searchOp.handler(ctx, { query: 'x', source_id: '__all__' });
|
||||
expect(captured.opts?.sourceId).toBeUndefined();
|
||||
expect(captured.opts?.sourceIds).toBeUndefined();
|
||||
});
|
||||
|
||||
test('local + all_sources=true spans the whole brain', async () => {
|
||||
const { ctx, captured } = makeCtx(false);
|
||||
await searchOp.handler(ctx, { query: 'x', all_sources: true });
|
||||
expect(captured.opts?.sourceId).toBeUndefined();
|
||||
expect(captured.opts?.sourceIds).toBeUndefined();
|
||||
});
|
||||
|
||||
test('explicit source_id wins over ctx.sourceId', async () => {
|
||||
const { ctx, captured } = makeCtx(false);
|
||||
await searchOp.handler(ctx, { query: 'x', source_id: 'wiki' });
|
||||
expect(captured.opts?.sourceId).toBe('wiki');
|
||||
});
|
||||
|
||||
test("remote + '__all__' collapses to the caller's grant (fail-closed)", async () => {
|
||||
const { ctx, captured } = makeCtx(true, ['wiki', 'essays']);
|
||||
await searchOp.handler(ctx, { query: 'x', source_id: '__all__' });
|
||||
expect(captured.opts?.sourceIds).toEqual(['wiki', 'essays']);
|
||||
});
|
||||
|
||||
test('remote + out-of-grant source_id is denied', async () => {
|
||||
const { ctx } = makeCtx(true, ['wiki']);
|
||||
await expect(searchOp.handler(ctx, { query: 'x', source_id: 'secrets' })).rejects.toThrow(
|
||||
/outside your granted sources/,
|
||||
);
|
||||
});
|
||||
});
|
||||
@@ -34,7 +34,7 @@ describe('v0.31.8 — voyage Content-Length pre-check + per-item cap', () => {
|
||||
expect(source).toMatch(/MAX_VOYAGE_RESPONSE_BYTES\s*=\s*256\s*\*\s*1024\s*\*\s*1024/);
|
||||
});
|
||||
|
||||
test('Layer 1: Content-Length pre-check fires BEFORE the body is read (D10 OOM defense)', async () => {
|
||||
test('Layer 1: Content-Length pre-check fires BEFORE resp.clone().json() (D10 OOM defense)', async () => {
|
||||
const source = await Bun.file(new URL('../src/core/ai/gateway.ts', import.meta.url)).text();
|
||||
// Anchor relative to the post-fetch handler block. The function declaration
|
||||
// contains an OUTBOUND request body section earlier; we want to verify
|
||||
@@ -47,10 +47,8 @@ describe('v0.31.8 — voyage Content-Length pre-check + per-item cap', () => {
|
||||
// doesn't pin to comment text.
|
||||
const preCheckIdx = inboundBlock.indexOf("resp.headers.get('content-length')");
|
||||
// Use the full lvalue assignment so the match doesn't accidentally hit
|
||||
// comment text that mentions the body read for context. (#1610 moved the
|
||||
// read from `resp.clone().json()` to a single `resp.text()` — bun <
|
||||
// 1.1.27 truncates clone()d bodies, oven-sh/bun#6348.)
|
||||
const jsonParseIdx = inboundBlock.indexOf('const bodyText = await resp.text()');
|
||||
// comment text that mentions `await resp.clone().json()` for context.
|
||||
const jsonParseIdx = inboundBlock.indexOf('const json: any = await resp.clone().json()');
|
||||
expect(preCheckIdx).toBeGreaterThan(0);
|
||||
expect(jsonParseIdx).toBeGreaterThan(0);
|
||||
// The pre-check MUST appear before the JSON parse — otherwise the OOM
|
||||
|
||||
Reference in New Issue
Block a user