Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 c80b8b6757 fix(search): honor sources.config.federated in unqualified local CLI search/query (#2561)
A source registered with `gbrain sources add --federated` was invisible to
an unqualified `gbrain search`/`gbrain query`: the local CLI always emitted
a scalar {sourceId} scope, and nothing on the read path ever consulted
sources.config.federated — contradicting docs/guides/multi-source-brains.md
('Source participates in unqualified gbrain search results').

Fix, at the trusted-local boundary only:
- src/cli.ts makeContext resolves the source WITH its tier and, when the
  tier is non-explicit (local_path / brain_default / sole_non_default /
  seed_default), computes ctx.localFederatedSourceIds = [resolved source,
  ...other config.federated=true sources] (archived excluded).
- New federatedSearchScope (operations.ts) delegates to
  resolveRequestedScope, then widens an unqualified trusted-local scalar
  scope to that set. Used by the search + query handlers only.
- Expansion NEVER applies when ctx.remote !== false (fail-closed source
  isolation), when a per-call source_id/__all__ is passed, when an OAuth
  grant (allowedSources) is present, or when --source/GBRAIN_SOURCE/dotfile
  named the source explicitly.

Deliberately NOT inside sourceScopeOpts: code-intel ops reject multi-source
scopes (resolveCodeIntelScope) and non-search reads keep their scalar
behavior. Cache contamination is already handled — cacheScopeKey folds
sourceIds sets into the query-cache key.

Fixes #2561

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:43:36 -07:00
14 changed files with 279 additions and 168 deletions
+11 -2
View File
@@ -808,12 +808,20 @@ async function makeContext(engine: BrainEngine, params: Record<string, unknown>)
// 'default'. Wrapped in try/catch so a doctor / single-source brain that
// never set up sources still returns 'default' silently.
let sourceId: string | undefined;
// #2561: when the source resolved via a NON-explicit tier (path-match /
// brain default / sole-non-default / seed default), unqualified search-shaped
// reads span every `config.federated = true` source. Computed here (the
// trusted local boundary) and consumed by federatedSearchScope in
// operations.ts, which additionally gates on ctx.remote === false.
let localFederated: string[] | undefined;
try {
const { resolveSourceId } = await import('./core/source-resolver.ts');
const { resolveSourceWithTier, localFederatedSourceIds } = await import('./core/source-resolver.ts');
// params.source is set when a CLI flag was parsed for the op (rare; most
// CLI ops don't take --source). Falls through to env/dotfile/path-match.
const explicit = (params.source as string | undefined) ?? null;
sourceId = await resolveSourceId(engine, explicit);
const resolved = await resolveSourceWithTier(engine, explicit);
sourceId = resolved.source_id;
localFederated = await localFederatedSourceIds(engine, resolved.source_id, resolved.tier);
} catch {
// Source resolution failed (e.g. sources table doesn't exist on a fresh
// pre-init brain). Leave sourceId unset; engine read methods fall through
@@ -834,6 +842,7 @@ async function makeContext(engine: BrainEngine, params: Record<string, unknown>)
// table). Matches dispatch.ts's auto-fill so the contract holds across
// every transport.
sourceId: sourceId ?? 'default',
...(localFederated ? { localFederatedSourceIds: localFederated } : {}),
};
}
-4
View File
@@ -908,10 +908,6 @@ export const KNOWN_CONFIG_KEYS: readonly string[] = [
'facts.extraction_model',
// #2113: output-token cap for the per-turn facts extractor (default 4000).
'facts.extraction_max_tokens',
// Owner opt-in: let the local stdio MCP pipe read this owner's private facts
// (find_trajectory / recall). Default off; HTTP transport ignores it. See
// src/core/facts/reader-trust.ts.
'facts.trust_local_reads',
// Dream cycle config
'dream.synthesize.session_corpus_dir',
'dream.synthesize.meeting_transcripts_dir',
-2
View File
@@ -591,8 +591,6 @@ export interface TrajectoryOpts {
sourceIds?: string[];
/** When true, filters to visibility='world' only. Set by MCP layer from ctx.remote. */
remote?: boolean;
/** Owner opt-in: read private facts despite `remote`. See facts/reader-trust.ts. */
trustedFactReads?: boolean;
/** Metric filter. When set, only facts with this canonical metric label participate. */
metric?: string;
/**
+5 -8
View File
@@ -17,7 +17,6 @@
import type { OperationContext } from './../operations.ts';
import type { FactRow } from './../engine.ts';
import { effectiveConfidence } from './decay.ts';
import { readableFactVisibilities } from './reader-trust.ts';
const DEFAULT_TTL_MS = 30_000;
const DEFAULT_TOP_K = 10;
@@ -51,13 +50,7 @@ export async function getBrainHotMemoryMeta(
const sessionId = (ctx as { source_session?: string }).source_session
?? null;
const allowListHash = hashAllowList(ctx.takesHoldersAllowList);
// Visibility tier: untrusted remote → world-only; trusted local +
// owner-trusted reads → all rows. Folded into the cache key (the header's
// "cache entries don't bleed across tiers" invariant): trustedFactReads is
// re-read from config per call, so a mid-session opt-out must not keep
// serving a private-inclusive cached payload for the TTL window.
const visibility = readableFactVisibilities(ctx);
const cacheKey = `${sourceId}::${sessionId ?? '_'}::${allowListHash}::${visibility ? 'world' : 'all'}`;
const cacheKey = `${sourceId}::${sessionId ?? '_'}::${allowListHash}`;
const ttl = Math.max(1000, opts.ttlMs ?? DEFAULT_TTL_MS);
const topK = Math.max(1, Math.min(opts.topK ?? DEFAULT_TOP_K, 25));
@@ -68,6 +61,10 @@ export async function getBrainHotMemoryMeta(
return cached.payload;
}
// Build a fresh payload. Visibility tier: remote → world-only;
// local → all rows.
const visibility = ctx.remote === false ? undefined : ['world'] as ('world' | 'private')[];
let rows: FactRow[] = [];
if (sessionId) {
rows = await ctx.engine.listFactsBySession(sourceId, sessionId, {
-48
View File
@@ -1,48 +0,0 @@
/**
* Fact-read visibility trust.
*
* Fact rows are tagged `private` | `world`. Remote/untrusted callers
* (`remote === true`) see only `world` rows the posture that keeps a
* published or HTTP-served brain from leaking private claims to strangers.
*
* But the stdio MCP server is an unauthenticated LOCAL pipe: on a single-owner
* machine the caller IS the owner, yet it still defaults `remote: true` for
* safety, so the owner's own agent is denied the owner's own private facts
* (e.g. `find_trajectory` returns empty over MCP even though the facts exist).
*
* `trustedFactReads` is a narrow, READ-ONLY trust elevation, deliberately
* DECOUPLED from `remote` so every other remote protection file_upload
* confinement, source isolation, fence stripping, takes-holder scoping stays
* fully in force. The stdio MCP server sets it ONLY when the brain owner opts
* in via the `facts.trust_local_reads` config (default off). The HTTP/published
* transport never sets it, so a served brain stays world-only regardless.
*/
export interface FactReaderTrust {
/**
* Mirrors OperationContext.remote. FAIL-CLOSED: anything not strictly
* `false` is treated as remote/untrusted (CLAUDE.md trust invariant).
*/
remote?: boolean;
/** Owner opt-in: this remote caller may read private facts. */
trustedFactReads?: boolean;
}
/**
* True when the reader is restricted to `visibility = 'world'` rows.
* Fail-closed: an unset/undefined `remote` is untrusted only an explicit
* `remote: false` (trusted local CLI) or an explicit owner opt-in
* (`trustedFactReads: true`) reads private rows.
*/
export function factsWorldOnly(t: FactReaderTrust): boolean {
return t.remote !== false && t.trustedFactReads !== true;
}
/**
* Visibility filter for list-style fact reads: `['world']` when the reader is
* world-only, `undefined` (no filter all rows) when it is trusted.
*/
export function readableFactVisibilities(
t: FactReaderTrust,
): ('private' | 'world')[] | undefined {
return factsWorldOnly(t) ? ['world'] : undefined;
}
+68 -16
View File
@@ -18,7 +18,6 @@ import { captureEvalCandidate, isEvalCaptureEnabled, isEvalScrubEnabled } from '
import type { HybridSearchMeta } from './types.ts';
import { extractPageLinks, isAutoLinkEnabled, isAutoTimelineEnabled, isGlobalBasenameEnabled, parseTimelineEntries, makeResolver, type UnresolvedFrontmatterRef } from './link-extraction.ts';
import { isFactsBackstopEligible } from './facts/eligibility.ts';
import { readableFactVisibilities } from './facts/reader-trust.ts';
import { stripTakesFence } from './takes-fence.ts';
import { stripFactsFence } from './facts-fence.ts';
import { getContentFlag } from './quarantine.ts';
@@ -333,15 +332,6 @@ export interface OperationContext {
* remote/untrusted (defense in depth in case the type is bypassed via cast).
*/
remote: boolean;
/**
* Owner opt-in (`facts.trust_local_reads`): allow this remote caller to read
* `private` facts. A NARROW, read-only trust elevation decoupled from
* `remote` every other remote protection (file confinement, source
* isolation, fence stripping, takes scoping) stays in force. Set ONLY by the
* stdio MCP server when the config is on; the HTTP transport never sets it.
* Consulted via `src/core/facts/reader-trust.ts`.
*/
trustedFactReads?: boolean;
/**
* Subagent runtime context (v0.16+). Set by the subagent tool dispatcher when
* dispatching an op as a tool call from an LLM loop. Used to enforce per-op
@@ -434,6 +424,23 @@ export interface OperationContext {
* satisfied even on single-source brains.
*/
sourceId: string;
/**
* #2561 federated read scope for UNQUALIFIED local CLI reads.
*
* Set ONLY by the local CLI's context builder (src/cli.ts makeContext), and
* only when the source resolved via a non-explicit tier (local_path /
* brain_default / sole_non_default / seed_default NOT --source, NOT
* GBRAIN_SOURCE, NOT a .gbrain-source dotfile). Contains the resolved
* source first, then every other `config.federated = true` source, so an
* unqualified `gbrain search "X"` spans federated sources as
* docs/guides/multi-source-brains.md promises.
*
* Consumed exclusively by `federatedSearchScope` and ONLY when
* `ctx.remote === false` a remote caller's scope stays governed by
* `ctx.auth.allowedSources` / scalar `ctx.sourceId` (source-isolation
* invariant, fail-closed).
*/
localFederatedSourceIds?: string[];
}
/**
@@ -549,6 +556,45 @@ export function resolveRequestedScope(
return sourceScopeOpts(ctx);
}
/**
* #2561 source scope for the search-shaped read ops (`search`, `query`).
*
* Delegates to `resolveRequestedScope` (the single trust+grant resolver), then
* widens an UNQUALIFIED trusted-local scalar scope to the CLI-computed
* federated set (`ctx.localFederatedSourceIds`, resolved source first). This is
* what makes `sources add --federated` mean something for local search: a
* federated source participates in unqualified `gbrain search "X"` results.
*
* The expansion NEVER applies when:
* - the caller is not strictly trusted-local (`ctx.remote !== false`)
* remote scope stays grant-governed (fail-closed source isolation);
* - a per-call `source_id` was passed (explicit wins, including `__all__`);
* - the resolver already produced a federated array (OAuth grant);
* - the CLI resolved the source from an explicit signal (--source / env /
* dotfile) makeContext leaves `localFederatedSourceIds` unset then.
*
* Deliberately NOT inside `sourceScopeOpts`: code-intel ops collapse a
* multi-element scope to an error (`resolveCodeIntelScope`), and non-search
* reads (get_page, get_links, ) keep their long-standing scalar behavior.
*/
export function federatedSearchScope(
ctx: OperationContext,
sourceIdParam?: string,
): { sourceId?: string; sourceIds?: string[] } {
const scope = resolveRequestedScope(ctx, sourceIdParam);
if (
ctx.remote === false &&
sourceIdParam === undefined &&
scope.sourceId !== undefined &&
scope.sourceIds === undefined &&
ctx.localFederatedSourceIds !== undefined &&
ctx.localFederatedSourceIds.length > 1
) {
return { sourceIds: ctx.localFederatedSourceIds };
}
return scope;
}
/**
* Code-intel adapter for `resolveRequestedScope`. Graph traversal
* (code_callers/code_callees/code_blast/code_flow) is single-source by design
@@ -1458,7 +1504,8 @@ const search: Operation = {
const queryText = p.query as string;
const limit = (p.limit as number) || 20;
const offset = (p.offset as number) || 0;
const scope = sourceScopeOpts(ctx);
// #2561: unqualified trusted-local search spans federated sources.
const scope = federatedSearchScope(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
@@ -1620,7 +1667,9 @@ const query: Operation = {
// is spread into BOTH the image-similarity searchVector path and the text
// hybridSearch path below, so both honor the same grant.
const sourceIdParam = typeof p.source_id === 'string' ? p.source_id : undefined;
const querySourceScope = resolveRequestedScope(ctx, sourceIdParam);
// #2561: unqualified trusted-local query spans federated sources (per-call
// source_id / remote grants still resolve through resolveRequestedScope).
const querySourceScope = federatedSearchScope(ctx, sourceIdParam);
// v0.27.1: image-similarity branch. Bypasses hybridSearch (which is
// text-only); embeds the image via embedMultimodal and runs a direct
@@ -3639,7 +3688,6 @@ const find_trajectory: Operation = {
entitySlug: p.entity_slug,
...scope,
remote: ctx.remote === true,
trustedFactReads: ctx.trustedFactReads === true,
metric,
kind,
since,
@@ -4000,9 +4048,13 @@ const recall: Operation = {
const includeExpired = p.include_expired === true;
const grep = typeof p.grep === 'string' ? p.grep.toLowerCase() : null;
// Visibility filter: world-only for untrusted remote callers; all rows for
// trusted local CLI and owner-trusted reads (facts.trust_local_reads).
const visibility = readableFactVisibilities(ctx);
// Visibility filter: remote callers see world-only unless their token
// grants elevated visibility (future-proofing; v0.31 ships world-only
// for remote, all for local CLI).
const visibility =
ctx.remote === false
? undefined
: ['world'] as ('private' | 'world')[];
let rows: Awaited<ReturnType<typeof ctx.engine.listFactsByEntity>> = [];
+1 -5
View File
@@ -18,7 +18,6 @@ import type {
} from './engine.ts';
import { MAX_SEARCH_LIMIT, clampSearchLimit } from './engine.ts';
import { withRetry, BULK_RETRY_OPTS, resolveBulkRetryOpts, computeNextDelay, type BatchAuditSite } from './retry.ts';
import { factsWorldOnly } from './facts/reader-trust.ts';
import { logBatchRetry as auditLogBatchRetry, logBatchExhausted as auditLogBatchExhausted } from './audit/batch-retry-audit.ts';
import { runMigrations } from './migrate.ts';
import { PGLITE_SCHEMA_SQL, getPGLiteSchema } from './pglite-schema.ts';
@@ -4319,10 +4318,7 @@ export class PGLiteEngine implements BrainEngine {
const useArray = Array.isArray(opts.sourceIds) && opts.sourceIds.length > 0;
const sourceIds = useArray ? opts.sourceIds! : null;
const sourceId = opts.sourceId ?? 'default';
// Direct-engine contract: unset `remote` here means a trusted in-process
// caller (CLI/tests) — the fail-closed default lives in the op layer, which
// always passes explicit booleans. Normalize before the fail-closed helper.
const remoteFilter = factsWorldOnly({ remote: opts.remote === true, trustedFactReads: opts.trustedFactReads === true });
const remoteFilter = opts.remote === true;
// Build SQL dynamically. PGLite uses $N positional params; we
// assemble the WHERE clauses + params array in tandem to keep them
+1 -5
View File
@@ -14,7 +14,6 @@ import type {
SourceRow,
} from './engine.ts';
import { withRetry, BULK_RETRY_OPTS, resolveBulkRetryOpts, computeNextDelay, type BatchAuditSite } from './retry.ts';
import { factsWorldOnly } from './facts/reader-trust.ts';
import { logBatchRetry as auditLogBatchRetry, logBatchExhausted as auditLogBatchExhausted } from './audit/batch-retry-audit.ts';
import type {
DomainBankSampleOpts, CorpusSampleOpts, DomainBankRow,
@@ -4533,10 +4532,7 @@ export class PostgresEngine implements BrainEngine {
const useArray = Array.isArray(opts.sourceIds) && opts.sourceIds.length > 0;
const sourceIds = useArray ? opts.sourceIds! : null;
const sourceId = opts.sourceId ?? 'default';
// Direct-engine contract: unset `remote` here means a trusted in-process
// caller (CLI/tests) — the fail-closed default lives in the op layer, which
// always passes explicit booleans. Normalize before the fail-closed helper.
const remoteFilter = factsWorldOnly({ remote: opts.remote === true, trustedFactReads: opts.trustedFactReads === true });
const remoteFilter = opts.remote === true;
// Source-scope predicate: array path (federated) wins over scalar.
// Engine.ts contract: returns chronological points; regressions +
+39
View File
@@ -353,6 +353,45 @@ export async function resolveSourceWithTier(
return { source_id: 'default', tier: 'seed_default' };
}
/**
* #2561 compute the federated read scope for an UNQUALIFIED local CLI call.
*
* `sources add --federated` promises that a `config.federated = true` source
* "participates in unqualified `gbrain search` results"
* (docs/guides/multi-source-brains.md). This helper turns that promise into a
* scope: given the resolved source and WHICH tier resolved it, return
* `[resolvedSource, ...other federated source ids]` or `undefined` when the
* expansion must not apply:
*
* - explicit tiers (`flag` / `env` / `dotfile`): the user named a source;
* scalar scope stands (that IS the qualified case);
* - no other federated source exists: keep the scalar fast path unchanged.
*
* Archived sources are excluded (same rationale as pickSoleNonDefaultSource);
* the archived column is v34+, so fall back to the un-archived query on older
* brains. Callers put the result on `OperationContext.localFederatedSourceIds`
* consumed only by `federatedSearchScope` and only when `remote === false`.
*/
export async function localFederatedSourceIds(
engine: BrainEngine,
sourceId: string,
tier: SourceTier,
): Promise<string[] | undefined> {
if (tier === 'flag' || tier === 'env' || tier === 'dotfile') return undefined;
let rows: Array<{ id: string }>;
try {
rows = await engine.executeRaw<{ id: string }>(
`SELECT id FROM sources WHERE config->>'federated' = 'true' AND archived = false ORDER BY id`,
);
} catch {
rows = await engine.executeRaw<{ id: string }>(
`SELECT id FROM sources WHERE config->>'federated' = 'true' ORDER BY id`,
);
}
const ids = [sourceId, ...rows.map((r) => r.id).filter((id) => id !== sourceId)];
return ids.length > 1 ? ids : undefined;
}
/** Exposed for tests. */
export const __testing = {
readDotfileWalk,
-8
View File
@@ -30,13 +30,6 @@ export interface ToolResult {
export interface DispatchOpts {
/** Defaults to true (remote/untrusted). Local CLI callers (`gbrain call`) pass false. */
remote?: boolean;
/**
* Owner opt-in (`facts.trust_local_reads`): let this remote caller read
* `private` facts. Set ONLY by the stdio MCP server; the HTTP transport
* leaves it unset so a served brain stays world-only. See
* `src/core/facts/reader-trust.ts`.
*/
trustedFactReads?: boolean;
/** Override the default stderr logger (e.g. CLI uses console.* directly). */
logger?: OperationContext['logger'];
/**
@@ -210,7 +203,6 @@ export function buildOperationContext(
logger: opts.logger || stderrLogger,
dryRun: !!params.dry_run,
remote: opts.remote ?? true,
trustedFactReads: opts.trustedFactReads === true,
takesHoldersAllowList: opts.takesHoldersAllowList,
// v0.34 D4: sourceId is REQUIRED at the type level. Auto-fill 'default'
// for single-source brains and any caller who didn't resolve a sourceId.
-11
View File
@@ -35,16 +35,6 @@ export async function startMcpServer(engine: BrainEngine) {
// shape and cast through `any` (the SDK accepts it via the ServerResult union).
server.setRequestHandler(CallToolRequestSchema, async (request: any): Promise<any> => {
const { name, arguments: params } = request.params;
// Owner opt-in: the stdio pipe is local + unauthenticated, so on a
// single-owner machine its caller is the owner. When facts.trust_local_reads
// is on, let fact reads (find_trajectory / recall) see this owner's own
// private facts. Narrow + read-only — every other remote protection stays
// on (remote stays true). HTTP transport never sets this. Best-effort: a
// config read blip falls back to the safe world-only default.
let trustedFactReads = false;
try {
trustedFactReads = (await engine.getConfig('facts.trust_local_reads')) === 'true';
} catch { /* keep world-only default */ }
// v0.28: stdio MCP has no per-token auth (local pipe). Default the
// takes-holder allow-list to ['world'] so agent-facing callers don't
// see private hunches via takes_list / takes_search / query. Operators
@@ -52,7 +42,6 @@ export async function startMcpServer(engine: BrainEngine) {
// `gbrain call <op>` (sets remote=false in src/cli.ts).
return dispatchToolCall(engine, name, params, {
remote: true,
trustedFactReads,
takesHoldersAllowList: ['world'],
// v0.31: source defaults to 'default' for stdio (no per-token scope).
// Operators who want a different source on stdio MCP should set
-16
View File
@@ -165,22 +165,6 @@ describe('findTrajectory — visibility filter (D-CDX-1 / R6)', () => {
const all = await engine.findTrajectory({ entitySlug: 'traj-vis-default' });
expect(all.length).toBe(2);
});
test('remote=true + trustedFactReads bypasses world-only (owner-trusted reads)', async () => {
await insertTyped({ entity_slug: 'traj-vis-trusted', metric: 'mrr', value: 50000, visibility: 'private', valid_from: new Date('2026-01-15') });
await insertTyped({ entity_slug: 'traj-vis-trusted', metric: 'mrr', value: 99999, visibility: 'world', valid_from: new Date('2026-04-12') });
// Untrusted remote: world only.
const untrusted = await engine.findTrajectory({ entitySlug: 'traj-vis-trusted', remote: true });
expect(untrusted.length).toBe(1);
expect(untrusted[0].value).toBe(99999);
// Owner-trusted remote: sees the private point too. remote stays true — only
// fact-read visibility is elevated.
const trusted = await engine.findTrajectory({ entitySlug: 'traj-vis-trusted', remote: true, trustedFactReads: true });
expect(trusted.length).toBe(2);
expect(trusted.map(p => p.value).sort((a, b) => (a! - b!))).toEqual([50000, 99999]);
});
});
describe('findTrajectory — metric + since + until filters', () => {
-43
View File
@@ -1,43 +0,0 @@
import { describe, test, expect } from 'bun:test';
import {
factsWorldOnly,
readableFactVisibilities,
} from '../src/core/facts/reader-trust.ts';
describe('factsWorldOnly', () => {
test('FAIL-CLOSED: unset remote is untrusted (world-only)', () => {
expect(factsWorldOnly({})).toBe(true);
expect(factsWorldOnly({ remote: undefined })).toBe(true);
expect(factsWorldOnly({ trustedFactReads: false })).toBe(true);
});
test('explicit remote=false (trusted local CLI) sees all', () => {
expect(factsWorldOnly({ remote: false })).toBe(false);
expect(factsWorldOnly({ remote: false, trustedFactReads: false })).toBe(false);
});
test('untrusted remote callers are world-only', () => {
expect(factsWorldOnly({ remote: true })).toBe(true);
expect(factsWorldOnly({ remote: true, trustedFactReads: false })).toBe(true);
});
test('owner-trusted remote reads bypass the world-only filter', () => {
expect(factsWorldOnly({ remote: true, trustedFactReads: true })).toBe(false);
});
test('trustedFactReads is a no-op for an already-trusted local caller', () => {
expect(factsWorldOnly({ remote: false, trustedFactReads: true })).toBe(false);
});
});
describe('readableFactVisibilities', () => {
test("world-only readers get the ['world'] filter (incl. unset remote)", () => {
expect(readableFactVisibilities({ remote: true })).toEqual(['world']);
expect(readableFactVisibilities({})).toEqual(['world']);
});
test('trusted readers get undefined (no filter — all rows)', () => {
expect(readableFactVisibilities({ remote: false })).toBeUndefined();
expect(readableFactVisibilities({ remote: true, trustedFactReads: true })).toBeUndefined();
});
});
+154
View File
@@ -0,0 +1,154 @@
/**
* #2561 sources.config.federated participates in UNQUALIFIED local CLI
* search/query.
*
* Pre-fix: the local CLI always emitted a scalar `{sourceId}` scope (required
* field, auto-filled 'default'), so a source registered with
* `gbrain sources add --federated` was invisible to an unqualified
* `gbrain search "X"` contradicting docs/guides/multi-source-brains.md
* ("Source participates in unqualified `gbrain search` results").
*
* Fix: the CLI context builder computes `ctx.localFederatedSourceIds`
* (resolved source + every other federated source) whenever the source
* resolved via a NON-explicit tier; `federatedSearchScope` widens the scalar
* scope to that set for the `search` / `query` ops trusted-local only
* (`ctx.remote === false`), never for remote callers, never when a per-call
* `source_id` or an explicit --source/env/dotfile was given.
*/
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
import { localFederatedSourceIds } from '../src/core/source-resolver.ts';
import {
federatedSearchScope,
operations,
type OperationContext,
} from '../src/core/operations.ts';
let engine: PGLiteEngine;
const search = operations.find((o) => o.name === 'search')!;
function ctxOf(overrides: Partial<OperationContext> = {}): OperationContext {
return {
engine: engine as any,
config: {} as any,
logger: console as any,
dryRun: false,
remote: false,
sourceId: 'default',
...overrides,
};
}
beforeAll(async () => {
engine = new PGLiteEngine();
await engine.connect({});
await engine.initSchema();
// Seeded 'default' source is federated=true. Add:
// wiki — federated (must join unqualified search)
// private — NOT federated (must stay invisible unless explicitly named)
// oldnews — federated but archived (must stay excluded)
await engine.executeRaw(
`INSERT INTO sources (id, name, local_path, config) VALUES ('wiki', 'wiki', '/tmp/wiki', '{"federated": true}'::jsonb)`,
);
await engine.executeRaw(
`INSERT INTO sources (id, name, local_path, config) VALUES ('private', 'private', '/tmp/private', '{}'::jsonb)`,
);
await engine.executeRaw(
`INSERT INTO sources (id, name, local_path, config, archived) VALUES ('oldnews', 'oldnews', '/tmp/oldnews', '{"federated": true}'::jsonb, true)`,
);
const pages: Array<[slug: string, sourceId: string, where: string]> = [
['notes/home', 'default', 'default'],
['wiki/topic', 'wiki', 'wiki'],
['private/topic', 'private', 'private'],
['old/topic', 'oldnews', 'oldnews'],
];
for (const [slug, sourceId, where] of pages) {
await engine.putPage(slug, {
type: 'note', title: `Topic in ${where}`, compiled_truth: `the zebra telescope in ${where}`, frontmatter: {},
}, { sourceId });
await engine.upsertChunks(slug, [
{ chunk_index: 0, chunk_text: `the zebra telescope in ${where}`, chunk_source: 'compiled_truth' },
], { sourceId });
}
// Keyword-only search path: no embedding provider needed in tests.
await engine.setConfig('search.mcp_keyword_only', 'true');
}, 60_000);
afterAll(async () => {
if (engine) await engine.disconnect();
}, 60_000);
describe('localFederatedSourceIds — CLI-side scope computation', () => {
test('non-explicit tier: resolved source first, then other federated, archived excluded', async () => {
expect(await localFederatedSourceIds(engine, 'default', 'seed_default')).toEqual(['default', 'wiki']);
});
test('non-federated resolved source still joins its own scope', async () => {
expect(await localFederatedSourceIds(engine, 'private', 'brain_default')).toEqual(['private', 'default', 'wiki']);
});
test('explicit tiers (--source / env / dotfile) never expand', async () => {
expect(await localFederatedSourceIds(engine, 'default', 'flag')).toBeUndefined();
expect(await localFederatedSourceIds(engine, 'default', 'env')).toBeUndefined();
expect(await localFederatedSourceIds(engine, 'default', 'dotfile')).toBeUndefined();
});
test('single federated source (the resolved one) keeps the scalar fast path', async () => {
const solo = { executeRaw: async () => [{ id: 'default' }] } as any;
expect(await localFederatedSourceIds(solo, 'default', 'seed_default')).toBeUndefined();
});
});
describe('federatedSearchScope — trust + explicitness matrix', () => {
test('trusted local + unqualified widens to the federated set', () => {
const ctx = ctxOf({ localFederatedSourceIds: ['default', 'wiki'] });
expect(federatedSearchScope(ctx)).toEqual({ sourceIds: ['default', 'wiki'] });
});
test('remote caller NEVER widens (fail-closed), even if the field is set', () => {
const ctx = ctxOf({ remote: true, localFederatedSourceIds: ['default', 'wiki'] });
expect(federatedSearchScope(ctx)).toEqual({ sourceId: 'default' });
});
test('per-call source_id wins over the federated set', () => {
const ctx = ctxOf({ localFederatedSourceIds: ['default', 'wiki'] });
expect(federatedSearchScope(ctx, 'wiki')).toEqual({ sourceId: 'wiki' });
});
test('per-call __all__ keeps the whole-brain semantics for trusted local', () => {
const ctx = ctxOf({ localFederatedSourceIds: ['default', 'wiki'] });
expect(federatedSearchScope(ctx, '__all__')).toEqual({});
});
test('a federated OAuth grant wins over the local set', () => {
const ctx = ctxOf({
localFederatedSourceIds: ['default', 'wiki'],
auth: { allowedSources: ['a', 'b'] } as OperationContext['auth'],
});
expect(federatedSearchScope(ctx)).toEqual({ sourceIds: ['a', 'b'] });
});
test('no local federated set → unchanged scalar scope', () => {
expect(federatedSearchScope(ctxOf())).toEqual({ sourceId: 'default' });
});
});
describe('search op — unqualified local search spans federated sources', () => {
test('federated source results appear; non-federated + archived stay invisible', async () => {
const ctx = ctxOf({
localFederatedSourceIds: await localFederatedSourceIds(engine, 'default', 'seed_default'),
});
const results = (await search.handler(ctx, { query: 'zebra telescope' })) as Array<{ slug: string }>;
const slugs = results.map((r) => r.slug);
expect(slugs).toContain('notes/home');
expect(slugs).toContain('wiki/topic'); // pre-#2561 this was missing
expect(slugs).not.toContain('private/topic');
expect(slugs).not.toContain('old/topic');
});
test('explicit source resolution (no federated set on ctx) stays single-source', async () => {
const results = (await search.handler(ctxOf(), { query: 'zebra telescope' })) as Array<{ slug: string }>;
const slugs = results.map((r) => r.slug);
expect(slugs).toEqual(['notes/home']);
});
});