mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-16 09:52:22 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
c80b8b6757 |
@@ -21,17 +21,14 @@ GBrain is tuned for the Supabase **Transaction pooler** (port 6543): it
|
||||
auto-disables prepared statements there and routes `engine.transaction()`
|
||||
(migrations, DDL, sync imports) to a derived **direct** connection
|
||||
(`db.<ref>.supabase.co:5432`). That direct host is IPv6-only, so on an
|
||||
IPv4-only host it is unreachable. When that happens gbrain now falls back to
|
||||
the pooler automatically (one stderr warning, then single-pool mode for the
|
||||
rest of the process) — but the pooler's ~2-min statement timeout can truncate
|
||||
very long migrations or bulk imports.
|
||||
IPv4-only host, reads work but sync **silently skips most pages**. This is the
|
||||
number one cause of "sync ran but nothing happened."
|
||||
|
||||
Fix: make the direct connection reachable over IPv4. Either set
|
||||
`GBRAIN_DIRECT_DATABASE_URL` to the **Session pooler** string (port 5432 on the
|
||||
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on.
|
||||
`GBRAIN_DISABLE_DIRECT_POOL=1` skips the direct pool (and the fallback warning)
|
||||
entirely. Verify by running `gbrain sync` and checking that the page count in
|
||||
`gbrain stats` matches the syncable file count in the repo.
|
||||
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on. Verify by
|
||||
running `gbrain sync` and checking that the page count in `gbrain stats` matches
|
||||
the syncable file count in the repo.
|
||||
|
||||
### The Primitives
|
||||
|
||||
|
||||
+5
-8
@@ -2720,17 +2720,14 @@ GBrain is tuned for the Supabase **Transaction pooler** (port 6543): it
|
||||
auto-disables prepared statements there and routes `engine.transaction()`
|
||||
(migrations, DDL, sync imports) to a derived **direct** connection
|
||||
(`db.<ref>.supabase.co:5432`). That direct host is IPv6-only, so on an
|
||||
IPv4-only host it is unreachable. When that happens gbrain now falls back to
|
||||
the pooler automatically (one stderr warning, then single-pool mode for the
|
||||
rest of the process) — but the pooler's ~2-min statement timeout can truncate
|
||||
very long migrations or bulk imports.
|
||||
IPv4-only host, reads work but sync **silently skips most pages**. This is the
|
||||
number one cause of "sync ran but nothing happened."
|
||||
|
||||
Fix: make the direct connection reachable over IPv4. Either set
|
||||
`GBRAIN_DIRECT_DATABASE_URL` to the **Session pooler** string (port 5432 on the
|
||||
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on.
|
||||
`GBRAIN_DISABLE_DIRECT_POOL=1` skips the direct pool (and the fallback warning)
|
||||
entirely. Verify by running `gbrain sync` and checking that the page count in
|
||||
`gbrain stats` matches the syncable file count in the repo.
|
||||
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on. Verify by
|
||||
running `gbrain sync` and checking that the page count in `gbrain stats` matches
|
||||
the syncable file count in the repo.
|
||||
|
||||
### The Primitives
|
||||
|
||||
|
||||
+11
-2
@@ -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 } : {}),
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
@@ -1078,9 +1078,6 @@ async function initPostgres(opts: {
|
||||
console.warn(' Direct connections are IPv6 only and fail in many environments.');
|
||||
console.warn(' Use the Transaction pooler connection string instead (port 6543):');
|
||||
console.warn(' Supabase Dashboard > Connect (top bar) > Connection String > Transaction pooler');
|
||||
console.warn(' (With a pooler URL, gbrain derives a direct connection for DDL and falls back');
|
||||
console.warn(' to the pooler automatically if that host is unreachable. Power users:');
|
||||
console.warn(' GBRAIN_DIRECT_DATABASE_URL overrides the derived URL; GBRAIN_DISABLE_DIRECT_POOL=1 disables it.)');
|
||||
console.warn('');
|
||||
}
|
||||
|
||||
@@ -1094,9 +1091,6 @@ async function initPostgres(opts: {
|
||||
if (databaseUrl.includes('supabase.co') && (msg.includes('ECONNREFUSED') || msg.includes('ETIMEDOUT'))) {
|
||||
console.error('Connection failed. Supabase direct connections (db.*.supabase.co:5432) are IPv6 only.');
|
||||
console.error('Use the Transaction pooler connection string instead (port 6543).');
|
||||
console.error('(gbrain derives its own direct connection from pooler URLs for DDL; if that host is');
|
||||
console.error('unreachable it falls back to the pooler. GBRAIN_DIRECT_DATABASE_URL overrides the');
|
||||
console.error('derived URL; GBRAIN_DISABLE_DIRECT_POOL=1 disables the direct pool entirely.)');
|
||||
}
|
||||
throw e;
|
||||
}
|
||||
|
||||
@@ -167,25 +167,6 @@ export function deriveDirectUrl(url: string): string | null {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Error codes that mean "the direct host is unreachable from this network"
|
||||
* (#1641). The auto-derived db.<ref>.supabase.co host is IPv6-only without
|
||||
* the paid IPv4 add-on, so ENOTFOUND/ECONNREFUSED here is expected on
|
||||
* IPv4-only networks — we fall back to the pooler instead of failing init.
|
||||
*/
|
||||
const NETWORK_UNREACHABLE_CODES = [
|
||||
'ENOTFOUND', 'ECONNREFUSED', 'ENETUNREACH', 'EHOSTUNREACH',
|
||||
'ETIMEDOUT', 'CONNECT_TIMEOUT',
|
||||
];
|
||||
|
||||
/** True when err looks like a network-unreachable failure (not auth/SQL). */
|
||||
export function isNetworkUnreachableError(err: unknown): boolean {
|
||||
const code = (err as { code?: unknown } | null)?.code;
|
||||
if (typeof code === 'string' && NETWORK_UNREACHABLE_CODES.includes(code)) return true;
|
||||
const msg = err instanceof Error ? err.message : String(err);
|
||||
return NETWORK_UNREACHABLE_CODES.some(c => msg.includes(c));
|
||||
}
|
||||
|
||||
/**
|
||||
* Read kill-switch state from env. Subordinate to parent manager's state
|
||||
* when present (A2 inheritance).
|
||||
@@ -338,30 +319,7 @@ export class ConnectionManager {
|
||||
throw err;
|
||||
});
|
||||
}
|
||||
let pool: Sql | null;
|
||||
try {
|
||||
pool = await this._directInit;
|
||||
} catch (err) {
|
||||
// #1641: the derived direct host (db.<ref>.supabase.co) is IPv6-only
|
||||
// without Supabase's IPv4 add-on. On IPv4-only networks the direct
|
||||
// pool can never connect — permanently fall back to the read pool
|
||||
// (self-activating kill-switch) instead of failing init/migrations.
|
||||
// Non-network errors (auth, SQL) still throw: they mean misconfig,
|
||||
// not unreachability.
|
||||
if (isNetworkUnreachableError(err)) {
|
||||
const alreadyWarned = this._killSwitch;
|
||||
this._killSwitch = true;
|
||||
const msg = err instanceof Error ? err.message : String(err);
|
||||
if (!alreadyWarned) console.error(
|
||||
`gbrain: direct connection to ${this._directUrl ? this.hostOnly(this._directUrl) : 'unknown host'} unreachable (${msg}); ` +
|
||||
'falling back to the pooler for DDL/bulk (long migrations may hit the pooler statement timeout). ' +
|
||||
'Set GBRAIN_DIRECT_DATABASE_URL to a reachable direct URL (e.g. the Session pooler, port 5432) or enable the Supabase IPv4 add-on; ' +
|
||||
'GBRAIN_DISABLE_DIRECT_POOL=1 silences this.',
|
||||
);
|
||||
return this.getReadPool();
|
||||
}
|
||||
throw err;
|
||||
}
|
||||
const pool = await this._directInit;
|
||||
if (!pool) {
|
||||
// Defensive — initDirectPool should have thrown.
|
||||
throw new Error('connection-manager: direct pool init returned null');
|
||||
@@ -392,9 +350,8 @@ export class ConnectionManager {
|
||||
},
|
||||
};
|
||||
const t0 = Date.now();
|
||||
let pool: Sql | null = null;
|
||||
try {
|
||||
pool = postgres(this._directUrl, opts);
|
||||
const pool = postgres(this._directUrl, opts);
|
||||
// Probe to validate connectivity early.
|
||||
await pool`SELECT 1`;
|
||||
logConnectionEvent({
|
||||
@@ -405,9 +362,6 @@ export class ConnectionManager {
|
||||
});
|
||||
return pool;
|
||||
} catch (err) {
|
||||
// Don't leak the failed pool's sockets/timers (#1641 fallback keeps
|
||||
// the process running afterward).
|
||||
if (pool) await endPoolBounded(pool);
|
||||
logConnectionEvent({
|
||||
pool: 'ddl',
|
||||
op: 'error',
|
||||
|
||||
+61
-2
@@ -424,6 +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[];
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -539,6 +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 —
|
||||
@@ -1448,7 +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
|
||||
@@ -1610,7 +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
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -3,7 +3,6 @@ import {
|
||||
isSupabasePoolerUrl,
|
||||
deriveDirectUrl,
|
||||
readKillSwitchEnv,
|
||||
isNetworkUnreachableError,
|
||||
resolveDirectPoolSize,
|
||||
ConnectionManager,
|
||||
DEFAULT_DIRECT_POOL_SIZE,
|
||||
@@ -239,65 +238,3 @@ describe('ConnectionManager — parent inheritance (A2)', () => {
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('isNetworkUnreachableError (#1641)', () => {
|
||||
test('classifies network codes as unreachable', () => {
|
||||
for (const code of ['ENOTFOUND', 'ECONNREFUSED', 'ENETUNREACH', 'EHOSTUNREACH', 'ETIMEDOUT', 'CONNECT_TIMEOUT']) {
|
||||
const err = Object.assign(new Error('connect failed'), { code });
|
||||
expect(isNetworkUnreachableError(err)).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
test('classifies by message when code absent', () => {
|
||||
expect(isNetworkUnreachableError(new Error('getaddrinfo ENOTFOUND db.abc.supabase.co'))).toBe(true);
|
||||
});
|
||||
|
||||
test('auth/SQL errors are NOT unreachable', () => {
|
||||
expect(isNetworkUnreachableError(new Error('password authentication failed for user "postgres"'))).toBe(false);
|
||||
expect(isNetworkUnreachableError(new Error('syntax error at or near "SELEC"'))).toBe(false);
|
||||
expect(isNetworkUnreachableError(null)).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe('ConnectionManager — direct-pool fallback on unreachable host (#1641)', () => {
|
||||
let originalKillSwitch: string | undefined;
|
||||
let originalError: typeof console.error;
|
||||
let errLines: string[];
|
||||
beforeEach(() => {
|
||||
originalKillSwitch = process.env.GBRAIN_DISABLE_DIRECT_POOL;
|
||||
delete process.env.GBRAIN_DISABLE_DIRECT_POOL;
|
||||
originalError = console.error;
|
||||
errLines = [];
|
||||
console.error = (...args: unknown[]) => { errLines.push(args.join(' ')); };
|
||||
});
|
||||
afterEach(() => {
|
||||
console.error = originalError;
|
||||
if (originalKillSwitch === undefined) delete process.env.GBRAIN_DISABLE_DIRECT_POOL;
|
||||
else process.env.GBRAIN_DISABLE_DIRECT_POOL = originalKillSwitch;
|
||||
});
|
||||
|
||||
test('ddl() falls back to the read pool when the direct host is unreachable', async () => {
|
||||
const cm = new ConnectionManager({
|
||||
url: 'postgresql://postgres.abc:p@aws.pooler.supabase.com:6543/db',
|
||||
// 127.0.0.1:9 (discard) → instant ECONNREFUSED, the IPv4-only-network shape.
|
||||
directUrl: 'postgresql://postgres:p@127.0.0.1:9/db',
|
||||
});
|
||||
const fakeReadPool = {} as ReturnType<typeof ConnectionManager.prototype.read>;
|
||||
cm.setReadPool(fakeReadPool);
|
||||
expect(cm.isDualPoolActive()).toBe(true);
|
||||
|
||||
const pool = await cm.ddl(); // without the fix this throws ECONNREFUSED
|
||||
expect(pool).toBe(fakeReadPool);
|
||||
// Self-activating kill-switch: subsequent calls skip the direct pool.
|
||||
expect(cm.isKillSwitchActive()).toBe(true);
|
||||
expect(cm.isDualPoolActive()).toBe(false);
|
||||
expect(cm.describeMode().mode).toBe('single (kill-switch)');
|
||||
// One stderr line mentioning the power-user override.
|
||||
const warning = errLines.filter(l => l.includes('GBRAIN_DIRECT_DATABASE_URL'));
|
||||
expect(warning.length).toBe(1);
|
||||
|
||||
const again = await cm.ddl();
|
||||
expect(again).toBe(fakeReadPool);
|
||||
expect(errLines.filter(l => l.includes('GBRAIN_DIRECT_DATABASE_URL')).length).toBe(1);
|
||||
}, 20000);
|
||||
});
|
||||
|
||||
@@ -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']);
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user