mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-15 09:22:18 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
1b45023dba |
Vendored
-56
File diff suppressed because one or more lines are too long
Vendored
+57
File diff suppressed because one or more lines are too long
Vendored
+1
-1
@@ -7,7 +7,7 @@
|
||||
<link rel="preconnect" href="https://fonts.googleapis.com" />
|
||||
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
|
||||
<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600&family=JetBrains+Mono:wght@400;500&display=swap" rel="stylesheet" />
|
||||
<script type="module" crossorigin src="/admin/assets/index-CoGEje3-.js"></script>
|
||||
<script type="module" crossorigin src="/admin/assets/index-CzLjRij_.js"></script>
|
||||
<link rel="stylesheet" crossorigin href="/admin/assets/index-GxkWX7v3.css">
|
||||
</head>
|
||||
<body>
|
||||
|
||||
@@ -39,6 +39,7 @@ export const api = {
|
||||
stats: () => apiFetch('/admin/api/stats'),
|
||||
health: () => apiFetch('/admin/api/health-indicators'),
|
||||
agents: () => apiFetch('/admin/api/agents'),
|
||||
sources: () => apiFetch('/admin/api/sources'),
|
||||
requests: (page = 1, qs = '') => apiFetch(`/admin/api/requests?page=${page}${qs}`),
|
||||
apiKeys: () => apiFetch('/admin/api/api-keys'),
|
||||
createApiKey: (name: string) => apiFetch('/admin/api/api-keys', { method: 'POST', body: JSON.stringify({ name }) }),
|
||||
|
||||
@@ -23,9 +23,16 @@ interface Agent {
|
||||
total_requests: number;
|
||||
requests_today: number;
|
||||
token_ttl: number | null;
|
||||
source_id: string | null;
|
||||
federated_read: string[] | null;
|
||||
status: 'active' | 'revoked';
|
||||
}
|
||||
|
||||
interface SourceOption {
|
||||
id: string;
|
||||
name: string | null;
|
||||
}
|
||||
|
||||
interface ApiKey {
|
||||
id: string;
|
||||
name: string;
|
||||
@@ -88,6 +95,7 @@ export function AgentsPage() {
|
||||
<th>Name</th>
|
||||
<th>Type</th>
|
||||
<th>Scopes</th>
|
||||
<th>Source</th>
|
||||
<th>Status</th>
|
||||
<th>Requests</th>
|
||||
<th>Last Used</th>
|
||||
@@ -108,6 +116,9 @@ export function AgentsPage() {
|
||||
<span key={s} className={`badge badge-${s}`} style={{ marginRight: 4 }}>{s}</span>
|
||||
))}
|
||||
</td>
|
||||
<td className="mono" style={{ fontSize: 12, color: 'var(--text-secondary)' }}>
|
||||
{a.auth_type === 'oauth' ? (a.source_id || 'default') : 'all'}
|
||||
</td>
|
||||
<td>
|
||||
<span className={`badge ${a.status === 'active' ? 'badge-success' : 'badge-danger'}`}>{a.status}</span>
|
||||
</td>
|
||||
@@ -257,9 +268,29 @@ function RegisterModal({ onClose, onRegistered }: {
|
||||
Object.fromEntries(ALLOWED_SCOPES_LIST.map(s => [s, s === 'read'])) as Record<Scope, boolean>,
|
||||
);
|
||||
const [ttl, setTtl] = useState('86400'); // 24h default
|
||||
const [redirectUris, setRedirectUris] = useState('');
|
||||
const [sources, setSources] = useState<SourceOption[]>([{ id: 'default', name: 'default' }]);
|
||||
const [sourceId, setSourceId] = useState('default');
|
||||
const [readSources, setReadSources] = useState<Record<string, boolean>>({ default: true });
|
||||
const [loading, setLoading] = useState(false);
|
||||
const [error, setError] = useState('');
|
||||
|
||||
useEffect(() => {
|
||||
api.sources()
|
||||
.then((rows: SourceOption[]) => {
|
||||
const nextSources = rows.length > 0 ? rows : [{ id: 'default', name: 'default' }];
|
||||
const nextSourceId = nextSources.some(s => s.id === sourceId) ? sourceId : nextSources[0].id;
|
||||
setSources(nextSources);
|
||||
setSourceId(nextSourceId);
|
||||
setReadSources(prev => {
|
||||
const next = Object.fromEntries(nextSources.map(s => [s.id, Boolean(prev[s.id])])) as Record<string, boolean>;
|
||||
next[nextSourceId] = true;
|
||||
return next;
|
||||
});
|
||||
})
|
||||
.catch(() => {});
|
||||
}, []);
|
||||
|
||||
const ttlOptions = [
|
||||
{ label: '1 hour', value: '3600' },
|
||||
{ label: '24 hours', value: '86400' },
|
||||
@@ -277,11 +308,24 @@ function RegisterModal({ onClose, onRegistered }: {
|
||||
try {
|
||||
// Use the CLI registration endpoint (POST to admin API)
|
||||
const selectedScopes = Object.entries(scopes).filter(([, v]) => v).map(([k]) => k).join(' ');
|
||||
const federatedRead = sources.map(s => s.id).filter(id => readSources[id]);
|
||||
if (federatedRead.length === 0) { setError('Select at least one read source'); setLoading(false); return; }
|
||||
// #1036: redirect URIs, one per line. Mirrors the CLI convention
|
||||
// (src/commands/auth.ts): presence of redirect URIs implies
|
||||
// authorization_code + refresh_token grants unless the user had none.
|
||||
const uris = redirectUris.split('\n').map(u => u.trim()).filter(Boolean);
|
||||
const res = await fetch('/admin/api/register-client', {
|
||||
method: 'POST',
|
||||
credentials: 'same-origin',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify({ name: name.trim(), scopes: selectedScopes, tokenTtl: ttl === '0' ? 315360000 : Number(ttl) }),
|
||||
body: JSON.stringify({
|
||||
name: name.trim(),
|
||||
scopes: selectedScopes,
|
||||
tokenTtl: ttl === '0' ? 315360000 : Number(ttl),
|
||||
source_id: sourceId,
|
||||
federated_read: federatedRead,
|
||||
...(uris.length > 0 ? { redirectUris: uris, grantTypes: ['authorization_code', 'refresh_token'] } : {}),
|
||||
}),
|
||||
});
|
||||
if (!res.ok) throw new Error('Registration failed');
|
||||
const data = await res.json();
|
||||
@@ -312,6 +356,42 @@ function RegisterModal({ onClose, onRegistered }: {
|
||||
))}
|
||||
</div>
|
||||
</div>
|
||||
<div style={{ marginBottom: 16 }}>
|
||||
<label>Write Source</label>
|
||||
<select value={sourceId} onChange={e => {
|
||||
const id = e.target.value;
|
||||
setSourceId(id);
|
||||
setReadSources(p => ({ ...p, [id]: true }));
|
||||
}}
|
||||
style={{ width: '100%', background: 'var(--bg-secondary)', color: 'var(--text-primary)', border: '1px solid var(--border)', borderRadius: 6, padding: '6px 10px', fontSize: 14 }}>
|
||||
{sources.map(s => <option key={s.id} value={s.id}>{s.name && s.name !== s.id ? `${s.id} (${s.name})` : s.id}</option>)}
|
||||
</select>
|
||||
</div>
|
||||
<div style={{ marginBottom: 16 }}>
|
||||
<label>Read Sources</label>
|
||||
<div className="checkbox-group">
|
||||
{sources.map(s => (
|
||||
<label key={s.id} className="checkbox-label">
|
||||
<input
|
||||
type="checkbox"
|
||||
checked={Boolean(readSources[s.id])}
|
||||
onChange={e => setReadSources(p => ({ ...p, [s.id]: e.target.checked }))}
|
||||
/>
|
||||
{s.name && s.name !== s.id ? `${s.id} (${s.name})` : s.id}
|
||||
</label>
|
||||
))}
|
||||
</div>
|
||||
</div>
|
||||
<div style={{ marginBottom: 16 }}>
|
||||
<label>Redirect URIs <span style={{ color: 'var(--text-secondary)', fontWeight: 400 }}>(optional, one per line — enables authorization_code flow)</span></label>
|
||||
<textarea
|
||||
placeholder={'https://example.com/callback'}
|
||||
value={redirectUris}
|
||||
onChange={e => setRedirectUris(e.target.value)}
|
||||
rows={2}
|
||||
style={{ width: '100%', background: 'var(--bg-secondary)', color: 'var(--text-primary)', border: '1px solid var(--border)', borderRadius: 6, padding: '6px 10px', fontSize: 13, fontFamily: 'inherit', resize: 'vertical' }}
|
||||
/>
|
||||
</div>
|
||||
<div style={{ marginBottom: 20 }}>
|
||||
<label>Token Lifetime</label>
|
||||
<select value={ttl} onChange={e => setTtl(e.target.value)}
|
||||
@@ -528,6 +608,8 @@ function AgentDrawer({ agent, onClose, onRevoked }: { agent: Agent; onClose: ()
|
||||
client_name: agentName,
|
||||
auth_type: agent.auth_type,
|
||||
scope: agent.scope,
|
||||
source_id: agent.source_id,
|
||||
federated_read: agent.federated_read,
|
||||
}, null, 2),
|
||||
};
|
||||
|
||||
@@ -547,6 +629,10 @@ function AgentDrawer({ agent, onClose, onRevoked }: { agent: Agent; onClose: ()
|
||||
<span>{(agent.scope || '').split(' ').filter(Boolean).map(s => (
|
||||
<span key={s} className={`badge badge-${s}`} style={{ marginRight: 4 }}>{s}</span>
|
||||
))}</span>
|
||||
<span style={{ color: 'var(--text-secondary)' }}>Write Source</span>
|
||||
<span className="mono">{agent.source_id || (isOAuth ? 'default' : 'all')}</span>
|
||||
<span style={{ color: 'var(--text-secondary)' }}>Read Sources</span>
|
||||
<span className="mono">{isOAuth ? (agent.federated_read && agent.federated_read.length > 0 ? agent.federated_read.join(', ') : (agent.source_id || 'default')) : 'all'}</span>
|
||||
<span style={{ color: 'var(--text-secondary)' }}>Registered</span>
|
||||
<span>{new Date(agent.created_at).toLocaleDateString()}</span>
|
||||
<span style={{ color: 'var(--text-secondary)' }}>Token TTL</span>
|
||||
|
||||
@@ -1,13 +1,13 @@
|
||||
// AUTO-GENERATED — do not edit by hand.
|
||||
// Run `bun run scripts/build-admin-embedded.ts` to regenerate.
|
||||
// Source: admin/dist/ at 2026-05-27.
|
||||
// Source: admin/dist/ at 2026-07-21.
|
||||
//
|
||||
// Bun resolves the file: imports to a path that works at runtime even
|
||||
// inside a compiled binary (`bun build --compile`). The manifest maps
|
||||
// the request path the express handler sees to (resolved-path, mime).
|
||||
|
||||
// @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
|
||||
import A_0_assets_index_CoGEje3__js from '../admin/dist/assets/index-CoGEje3-.js' with { type: 'file' };
|
||||
import A_0_assets_index_CzLjRij__js from '../admin/dist/assets/index-CzLjRij_.js' with { type: 'file' };
|
||||
// @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
|
||||
import A_1_assets_index_GxkWX7v3_css from '../admin/dist/assets/index-GxkWX7v3.css' with { type: 'file' };
|
||||
// @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
|
||||
@@ -19,7 +19,7 @@ export interface AdminAsset {
|
||||
}
|
||||
|
||||
export const ADMIN_ASSETS: Record<string, AdminAsset> = {
|
||||
"/admin/assets/index-CoGEje3-.js": { path: A_0_assets_index_CoGEje3__js as unknown as string, mime: "application/javascript; charset=utf-8" },
|
||||
"/admin/assets/index-CzLjRij_.js": { path: A_0_assets_index_CzLjRij__js as unknown as string, mime: "application/javascript; charset=utf-8" },
|
||||
"/admin/assets/index-GxkWX7v3.css": { path: A_1_assets_index_GxkWX7v3_css as unknown as string, mime: "text/css; charset=utf-8" },
|
||||
"/admin/index.html": { path: A_2_index_html as unknown as string, mime: "text/html; charset=utf-8" },
|
||||
};
|
||||
|
||||
@@ -820,10 +820,6 @@ export async function doctorReportRemote(engine: BrainEngine): Promise<DoctorRep
|
||||
// v0.42.x (#1794, 4A): pool-budget nudge when GBRAIN_MAX_CONNECTIONS is set.
|
||||
checks.push(await checkPoolBudget(engine));
|
||||
|
||||
// #2552: warn when an explicit embed-concurrency override fans out against
|
||||
// a local single-slot embedding endpoint (silent backfill starvation).
|
||||
checks.push(await checkEmbedConcurrency());
|
||||
|
||||
// v0.42.7 (#1696): link-extraction lag. Strictly SQL (single indexed COUNT),
|
||||
// safe on the thin-client/remote path — remote operators on checkout-less
|
||||
// Postgres brains are exactly who can't otherwise see the extraction backlog.
|
||||
@@ -3819,61 +3815,6 @@ export function computePoolBudgetCheck(
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* #2552: warn when an explicit GBRAIN_EMBED_CONCURRENCY override fans out
|
||||
* against a local single-slot embedding endpoint (Ollama / llama-server /
|
||||
* localhost base URL). Requests serialize on the one loaded model, so N
|
||||
* parallel pages multiply latency xN and can exceed the fetch timeout with
|
||||
* no surfaced error — the backfill silently starves. (When the env var is
|
||||
* unset, embed auto-caps at LOCAL_EMBED_CONCURRENCY_CAP and this check
|
||||
* reports ok.) Pure; exported for tests.
|
||||
*/
|
||||
export function computeEmbedConcurrencyCheck(
|
||||
isLocalEndpoint: boolean,
|
||||
envValue: string | undefined,
|
||||
localCap: number,
|
||||
): Check {
|
||||
const name = 'embed_concurrency';
|
||||
if (!isLocalEndpoint) {
|
||||
return { name, status: 'ok', message: 'Embedding endpoint is not a local inference server — cloud concurrency defaults apply.' };
|
||||
}
|
||||
const parsed = envValue ? parseInt(envValue, 10) : NaN;
|
||||
if (envValue && Number.isFinite(parsed) && parsed > localCap) {
|
||||
return {
|
||||
name,
|
||||
status: 'warn',
|
||||
message:
|
||||
`GBRAIN_EMBED_CONCURRENCY=${parsed} against a local embedding endpoint. ` +
|
||||
`Local inference servers serialize requests, so ${parsed} parallel pages multiply ` +
|
||||
`latency x${parsed} and can exceed the fetch timeout — the embed backfill stalls ` +
|
||||
`with no error. Unset GBRAIN_EMBED_CONCURRENCY (auto-caps at ${localCap}) or set it <= ${localCap}.`,
|
||||
};
|
||||
}
|
||||
return {
|
||||
name,
|
||||
status: 'ok',
|
||||
message: `Local embedding endpoint detected; embed concurrency capped at ${envValue ? parsed : localCap}.`,
|
||||
};
|
||||
}
|
||||
|
||||
/** Thin gateway/env wrapper over `computeEmbedConcurrencyCheck`. */
|
||||
export async function checkEmbedConcurrency(): Promise<Check> {
|
||||
try {
|
||||
const { isLocalEmbeddingEndpoint, LOCAL_EMBED_CONCURRENCY_CAP } = await import('../core/ai/gateway.ts');
|
||||
return computeEmbedConcurrencyCheck(
|
||||
isLocalEmbeddingEndpoint(),
|
||||
process.env.GBRAIN_EMBED_CONCURRENCY,
|
||||
LOCAL_EMBED_CONCURRENCY_CAP,
|
||||
);
|
||||
} catch (err) {
|
||||
return {
|
||||
name: 'embed_concurrency',
|
||||
status: 'ok',
|
||||
message: `Skipped (${err instanceof Error ? err.message : String(err)})`,
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
/** Thin env/engine wrapper over `computePoolBudgetCheck`. */
|
||||
export async function checkPoolBudget(_engine: BrainEngine): Promise<Check> {
|
||||
try {
|
||||
|
||||
+8
-30
@@ -1,6 +1,5 @@
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { embedBatch, currentEmbeddingSignature } from '../core/embedding.ts';
|
||||
import { isLocalEmbeddingEndpoint, LOCAL_EMBED_CONCURRENCY_CAP } from '../core/ai/gateway.ts';
|
||||
import type { ChunkInput } from '../core/types.ts';
|
||||
import { chunkText } from '../core/chunkers/recursive.ts';
|
||||
import { createProgress, type ProgressReporter } from '../core/progress.ts';
|
||||
@@ -177,31 +176,6 @@ export class EmbeddingDimMismatchError extends Error {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* #2552: resolve the bulk-embed worker count. Env override or the
|
||||
* cloud-tuned default of 20 — but when the operator did NOT set
|
||||
* GBRAIN_EMBED_CONCURRENCY and the embedding endpoint is a local inference
|
||||
* server (Ollama / llama-server / localhost base URL), cap at
|
||||
* LOCAL_EMBED_CONCURRENCY_CAP: 20 parallel pages against a single-slot
|
||||
* server serialize on the one loaded model, multiply latency x20 past the
|
||||
* fetch timeout, and starve the backfill with no surfaced error. An
|
||||
* explicit env value always wins (`gbrain doctor` warns instead).
|
||||
* Pacing only ever LOWERS concurrency (Codex P2).
|
||||
*/
|
||||
export function resolveEmbedConcurrency(paceMaxConcurrency?: number): number {
|
||||
const envSet = !!process.env.GBRAIN_EMBED_CONCURRENCY;
|
||||
const base = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
|
||||
let resolved = base;
|
||||
if (!envSet && isLocalEmbeddingEndpoint() && base > LOCAL_EMBED_CONCURRENCY_CAP) {
|
||||
resolved = LOCAL_EMBED_CONCURRENCY_CAP;
|
||||
serr(
|
||||
`[embed] local embedding endpoint detected — capping concurrency at ` +
|
||||
`${LOCAL_EMBED_CONCURRENCY_CAP} (set GBRAIN_EMBED_CONCURRENCY to override)`,
|
||||
);
|
||||
}
|
||||
return paceMaxConcurrency ? Math.min(resolved, paceMaxConcurrency) : resolved;
|
||||
}
|
||||
|
||||
/**
|
||||
* Pre-flight check: read the actual schema column dim and compare to the
|
||||
* gateway's resolved dim. Throws `EmbeddingDimMismatchError` on mismatch
|
||||
@@ -703,8 +677,10 @@ async function embedAll(
|
||||
// Paced runs lower this to the resolved cap (the real lever vs pooler-slot
|
||||
// starvation); unpaced keeps the env/default 20. Codex P2: only ever LOWER —
|
||||
// never raise above an operator's existing env cap.
|
||||
// #2552: local endpoints auto-cap — see resolveEmbedConcurrency.
|
||||
const CONCURRENCY = resolveEmbedConcurrency(staleOpts?.paceMaxConcurrency);
|
||||
const BASE_CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
|
||||
const CONCURRENCY = staleOpts?.paceMaxConcurrency
|
||||
? Math.min(BASE_CONCURRENCY, staleOpts.paceMaxConcurrency)
|
||||
: BASE_CONCURRENCY;
|
||||
|
||||
async function embedOnePage(page: typeof pages[number]) {
|
||||
// #1737: bail before doing any work for this page if the run was aborted.
|
||||
@@ -879,8 +855,10 @@ async function embedAllStale(
|
||||
// Paced runs lower concurrency to the resolved cap (E-1: worker count IS the
|
||||
// lever on this single pool, no separate permit). Codex P2: pacing only ever
|
||||
// LOWERS concurrency — never raise above an operator's existing env cap.
|
||||
// #2552: local endpoints auto-cap — see resolveEmbedConcurrency.
|
||||
const CONCURRENCY = resolveEmbedConcurrency(staleOpts?.paceMaxConcurrency);
|
||||
const BASE_CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
|
||||
const CONCURRENCY = staleOpts?.paceMaxConcurrency
|
||||
? Math.min(BASE_CONCURRENCY, staleOpts.paceMaxConcurrency)
|
||||
: BASE_CONCURRENCY;
|
||||
const pacer = staleOpts?.pacer ?? createNoopPacer();
|
||||
|
||||
// D3 + D3a + D8: wall-clock budget. 30 min default; env override.
|
||||
|
||||
@@ -39,6 +39,7 @@ import * as db from '../core/db.ts';
|
||||
import { sqlQueryForEngine, executeRawJsonb } from '../core/sql-query.ts';
|
||||
import { MinionQueue } from '../core/minions/queue.ts';
|
||||
import { isRetryableError } from '../core/retry-matcher.ts';
|
||||
import { normalizeAdminClientSourceScope } from '../core/admin-source-scope.ts';
|
||||
import {
|
||||
computeContentHash,
|
||||
validateIngestionEvent,
|
||||
@@ -1086,6 +1087,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
|
||||
const oauthClients = await sql`
|
||||
SELECT c.client_id as id, c.client_name as name, 'oauth' as auth_type,
|
||||
c.grant_types, c.scope, c.created_at, c.token_ttl,
|
||||
c.source_id, c.federated_read,
|
||||
CASE WHEN c.deleted_at IS NOT NULL THEN 'revoked' ELSE 'active' END as status,
|
||||
(SELECT max(created_at) FROM mcp_request_log WHERE token_name = c.client_id) as last_used_at,
|
||||
(SELECT count(*)::int FROM mcp_request_log WHERE token_name = c.client_id) as total_requests,
|
||||
@@ -1095,6 +1097,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
|
||||
const legacyKeys = await sql`
|
||||
SELECT a.id, a.name, 'api_key' as auth_type,
|
||||
'{"bearer"}' as grant_types, 'read write admin' as scope, a.created_at, null as token_ttl,
|
||||
null as source_id, null as federated_read,
|
||||
CASE WHEN a.revoked_at IS NOT NULL THEN 'revoked' ELSE 'active' END as status,
|
||||
a.last_used_at,
|
||||
(SELECT count(*)::int FROM mcp_request_log WHERE token_name = a.name) as total_requests,
|
||||
@@ -1107,6 +1110,17 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
|
||||
}
|
||||
});
|
||||
|
||||
app.get('/admin/api/sources', requireAdmin, async (_req: Request, res: Response) => {
|
||||
try {
|
||||
const sources = await engine.listAllSources({ includeArchived: false });
|
||||
const options = sources.map(s => ({ id: s.id, name: s.name }));
|
||||
if (!options.some(s => s.id === 'default')) options.unshift({ id: 'default', name: 'default' });
|
||||
res.json(options);
|
||||
} catch (e) {
|
||||
res.status(503).json({ error: 'service_unavailable' });
|
||||
}
|
||||
});
|
||||
|
||||
// v0.38 Slice 4 — per-OAuth-client agent spend viewer. Pre-computes today's
|
||||
// spend (committed + pending reservations) per client so the Agents tab
|
||||
// can render a "$X / $Y today" cell. Read-side endpoint only — no mutation.
|
||||
@@ -1440,6 +1454,8 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
|
||||
// missing, empty) and rejects the rest with a structured 400.
|
||||
const { name, tokenTtl, grantTypes, redirectUris, tokenEndpointAuthMethod } = req.body;
|
||||
const rawScopes = (req.body as Record<string, unknown>).scopes ?? (req.body as Record<string, unknown>).scope;
|
||||
const rawSourceId = (req.body as Record<string, unknown>).source_id ?? (req.body as Record<string, unknown>).sourceId;
|
||||
const rawFederatedRead = (req.body as Record<string, unknown>).federated_read ?? (req.body as Record<string, unknown>).federatedRead;
|
||||
if (!name) { res.status(400).json({ error: 'Name required' }); return; }
|
||||
let scopeString: string;
|
||||
try {
|
||||
@@ -1470,8 +1486,23 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
|
||||
});
|
||||
return;
|
||||
}
|
||||
let sourceScope: ReturnType<typeof normalizeAdminClientSourceScope>;
|
||||
try {
|
||||
const sources = await engine.listAllSources({ includeArchived: false });
|
||||
sourceScope = normalizeAdminClientSourceScope(
|
||||
rawSourceId,
|
||||
rawFederatedRead,
|
||||
sources.map(s => s.id),
|
||||
);
|
||||
} catch (e) {
|
||||
res.status(400).json({
|
||||
error: 'invalid_source_scope',
|
||||
message: e instanceof Error ? e.message : String(e),
|
||||
});
|
||||
return;
|
||||
}
|
||||
const result = await oauthProvider.registerClientManual(
|
||||
name, grants, scopeString, uris, 'default', undefined, validatedAuthMethod,
|
||||
name, grants, scopeString, uris, sourceScope.sourceId, sourceScope.federatedRead, validatedAuthMethod,
|
||||
);
|
||||
// Set per-client TTL if specified
|
||||
if (tokenTtl && Number(tokenTtl) > 0) {
|
||||
|
||||
@@ -0,0 +1,51 @@
|
||||
import { isValidSourceId } from './source-id.ts';
|
||||
|
||||
export interface AdminClientSourceScope {
|
||||
sourceId: string;
|
||||
federatedRead: string[];
|
||||
}
|
||||
|
||||
function parseFederatedReadInput(raw: unknown, sourceId: string): string[] {
|
||||
if (raw === undefined || raw === null) return [sourceId];
|
||||
if (typeof raw === 'string') {
|
||||
const values = raw.split(',').map(s => s.trim()).filter(Boolean);
|
||||
return values.length > 0 ? values : [sourceId];
|
||||
}
|
||||
if (Array.isArray(raw)) {
|
||||
if (!raw.every(v => typeof v === 'string')) {
|
||||
throw new Error('federated_read must be an array of source ids');
|
||||
}
|
||||
const values = raw.map(v => v.trim()).filter(Boolean);
|
||||
return values.length > 0 ? values : [sourceId];
|
||||
}
|
||||
throw new Error('federated_read must be a string or array');
|
||||
}
|
||||
|
||||
export function normalizeAdminClientSourceScope(
|
||||
rawSourceId: unknown,
|
||||
rawFederatedRead: unknown,
|
||||
availableSourceIds: string[],
|
||||
): AdminClientSourceScope {
|
||||
const knownSources = new Set(availableSourceIds);
|
||||
const fallbackSourceId = knownSources.has('default') ? 'default' : (availableSourceIds[0] ?? 'default');
|
||||
const sourceId = rawSourceId === undefined || rawSourceId === null || rawSourceId === ''
|
||||
? fallbackSourceId
|
||||
: rawSourceId;
|
||||
if (!isValidSourceId(sourceId)) {
|
||||
throw new Error(`Invalid source_id: ${JSON.stringify(sourceId)}`);
|
||||
}
|
||||
if (knownSources.size > 0 && !knownSources.has(sourceId)) {
|
||||
throw new Error(`Unknown source_id: ${sourceId}`);
|
||||
}
|
||||
|
||||
const federatedRead = Array.from(new Set(parseFederatedReadInput(rawFederatedRead, sourceId)));
|
||||
for (const id of federatedRead) {
|
||||
if (!isValidSourceId(id)) {
|
||||
throw new Error(`Invalid federated_read source_id: ${JSON.stringify(id)}`);
|
||||
}
|
||||
if (knownSources.size > 0 && !knownSources.has(id)) {
|
||||
throw new Error(`Unknown federated_read source_id: ${id}`);
|
||||
}
|
||||
}
|
||||
return { sourceId, federatedRead };
|
||||
}
|
||||
@@ -683,33 +683,6 @@ export function getEmbeddingDimensions(): number {
|
||||
return requireConfig().embedding_dimensions ?? DEFAULT_EMBEDDING_DIMENSIONS;
|
||||
}
|
||||
|
||||
/**
|
||||
* #2552: cap for parallel bulk-embed workers against a local inference
|
||||
* server. A single-slot Ollama/llama-server serializes requests, so the
|
||||
* cloud-tuned 20-worker fan-out multiplies latency x20 and blows past the
|
||||
* fetch timeout with no surfaced error (the backfill silently starves).
|
||||
*/
|
||||
export const LOCAL_EMBED_CONCURRENCY_CAP = 2;
|
||||
|
||||
/**
|
||||
* #2552: true when the configured embedding model routes to a local
|
||||
* inference server — the `ollama` / `llama-server` recipes, or any recipe
|
||||
* whose base URL was explicitly pointed at localhost. Bulk callers use this
|
||||
* to pick CPU-safe concurrency defaults; `gbrain doctor` uses it to warn
|
||||
* about an explicit cloud-sized override. Fail-open: unconfigured or
|
||||
* unresolvable gateway → false (cloud behavior, the historical default).
|
||||
*/
|
||||
export function isLocalEmbeddingEndpoint(): boolean {
|
||||
try {
|
||||
const { recipe } = resolveRecipe(getEmbeddingModel());
|
||||
if (recipe.id === 'ollama' || recipe.id === 'llama-server') return true;
|
||||
const base = requireConfig().base_urls?.[recipe.id] ?? '';
|
||||
return /\/\/(localhost|127\.0\.0\.1|\[::1\])(:|\/|$)/i.test(base);
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* v0.28.11: returns the configured multimodal embedding model when set,
|
||||
* or undefined if the brain falls back to `embedding_model` for multimodal
|
||||
|
||||
@@ -29,17 +29,9 @@ export const ollama: Recipe = {
|
||||
trust_custom_dims: true, // #2271: local models carry varied native dims
|
||||
cost_per_1m_tokens_usd: 0,
|
||||
price_last_verified: '2026-04-20',
|
||||
// #2552: Ollama's true batch capacity depends on the locally loaded
|
||||
// model + OLLAMA_NUM_PARALLEL, but the previous `no_batch_cap: true`
|
||||
// meant a whole page went out in ONE request — on a CPU-only box that
|
||||
// multiplies latency past the fetch timeout and the backfill starves
|
||||
// with no surfaced error. Ollama doesn't return a recognizable
|
||||
// token-limit error either, so the recursive-halving safety net never
|
||||
// fires; a conservative static pre-split cap is the only guard.
|
||||
// 4096 tokens x 2 chars/token ~= 8K chars per request (code-dense
|
||||
// pages run ~2 chars/token, not the tiktoken-ish 4).
|
||||
max_batch_tokens: 4096,
|
||||
chars_per_token: 2,
|
||||
// Ollama's batch capacity depends on the locally loaded model + the
|
||||
// OLLAMA_NUM_PARALLEL config; no static cap to declare. v0.32 (#779).
|
||||
no_batch_cap: true,
|
||||
},
|
||||
},
|
||||
setup_hint: 'Install Ollama from https://ollama.ai, then `ollama pull nomic-embed-text` and `ollama serve`.',
|
||||
|
||||
@@ -141,7 +141,6 @@ export const OPS_CHECK_NAMES: ReadonlySet<string> = new Set([
|
||||
'pgbouncer_prepare',
|
||||
'pgvector',
|
||||
'pool_budget',
|
||||
'embed_concurrency',
|
||||
'progressive_batch_audit_health',
|
||||
'queue_health',
|
||||
'reranker_health',
|
||||
|
||||
@@ -56,7 +56,7 @@ import { GBrainError, PAGE_SORT_SQL, ENRICH_ORDER_SQL } from './types.ts';
|
||||
import { finalizeLastSeen } from './chronicle/last-seen.ts';
|
||||
import { computeAnomaliesFromBuckets } from './cycle/anomaly.ts';
|
||||
import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
|
||||
import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery, buildWebsearchQueryExpr } from './search/sql-ranking.ts';
|
||||
import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
|
||||
import {
|
||||
normalizeEngineColumn,
|
||||
buildVectorCastFragment,
|
||||
@@ -1591,8 +1591,6 @@ export class PGLiteEngine implements BrainEngine {
|
||||
}
|
||||
|
||||
// v0.20.0 Cathedral II Layer 10 C1/C2: language + symbol-kind filters.
|
||||
// #2380: slash-bearing queries match both the split-word and literal
|
||||
// slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
|
||||
const params: unknown[] = [query, innerLimit, limit, offset];
|
||||
let extraFilter = '';
|
||||
if (opts?.language) {
|
||||
@@ -1632,7 +1630,6 @@ export class PGLiteEngine implements BrainEngine {
|
||||
// FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
|
||||
// — safe to interpolate into raw SQL.
|
||||
const ftsLang = getFtsLanguage();
|
||||
const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
|
||||
|
||||
const keywordSql =
|
||||
`WITH ranked AS (
|
||||
@@ -1640,14 +1637,14 @@ export class PGLiteEngine implements BrainEngine {
|
||||
p.slug, p.id as page_id, p.title, p.type, p.source_id,
|
||||
p.effective_date, p.effective_date_source,
|
||||
cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
|
||||
ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
|
||||
ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
|
||||
CASE WHEN p.updated_at < (
|
||||
SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
|
||||
) THEN true ELSE false END AS stale
|
||||
FROM content_chunks cc
|
||||
JOIN pages p ON p.id = cc.page_id
|
||||
JOIN sources s ON s.id = p.source_id
|
||||
WHERE cc.search_vector @@ ${ftsQueryExpr} ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
|
||||
WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
|
||||
-- v0.27.1: hide image rows from default text-keyword search so
|
||||
-- OCR text doesn't drown text-page hits. Image-similarity queries
|
||||
-- run a separate vector path on embedding_image.
|
||||
@@ -1715,10 +1712,7 @@ export class PGLiteEngine implements BrainEngine {
|
||||
// FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
|
||||
// — safe to interpolate into raw SQL.
|
||||
const ftsLang = getFtsLanguage();
|
||||
const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
|
||||
|
||||
// #2380: slash-bearing queries match both the split-word and literal
|
||||
// slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
|
||||
const params: unknown[] = [query, limit, offset];
|
||||
let extraFilter = '';
|
||||
if (opts?.type) {
|
||||
@@ -1766,7 +1760,7 @@ export class PGLiteEngine implements BrainEngine {
|
||||
COALESCE(rep.chunk_index, 0) as chunk_index,
|
||||
COALESCE(rep.chunk_text, '') as chunk_text,
|
||||
COALESCE(rep.chunk_source, 'compiled_truth') as chunk_source,
|
||||
ts_rank_cd(p.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
|
||||
ts_rank_cd(p.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
|
||||
CASE WHEN p.updated_at < (
|
||||
SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
|
||||
) THEN true ELSE false END AS stale
|
||||
@@ -1781,7 +1775,7 @@ export class PGLiteEngine implements BrainEngine {
|
||||
ORDER BY (cc.chunk_source = 'compiled_truth') DESC, cc.chunk_index ASC
|
||||
LIMIT 1
|
||||
) rep ON true
|
||||
WHERE p.search_vector @@ ${ftsQueryExpr}
|
||||
WHERE p.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
|
||||
${extraFilter} ${hardExcludeClause} ${visibilityClause}
|
||||
ORDER BY score DESC, p.id ASC
|
||||
LIMIT $2 OFFSET $3`;
|
||||
@@ -1968,8 +1962,6 @@ export class PGLiteEngine implements BrainEngine {
|
||||
});
|
||||
}
|
||||
|
||||
// #2380: slash-bearing queries match both the split-word and literal
|
||||
// slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
|
||||
const params: unknown[] = [query, limit, offset];
|
||||
let extraFilter = '';
|
||||
if (opts?.language) {
|
||||
@@ -2004,21 +1996,20 @@ export class PGLiteEngine implements BrainEngine {
|
||||
// FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
|
||||
// — safe to interpolate into raw SQL.
|
||||
const ftsLang = getFtsLanguage();
|
||||
const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
|
||||
|
||||
const { rows } = await this.db.query(
|
||||
`SELECT
|
||||
p.slug, p.id as page_id, p.title, p.type, p.source_id,
|
||||
p.effective_date, p.effective_date_source,
|
||||
cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
|
||||
ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
|
||||
ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
|
||||
CASE WHEN p.updated_at < (
|
||||
SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
|
||||
) THEN true ELSE false END AS stale
|
||||
FROM content_chunks cc
|
||||
JOIN pages p ON p.id = cc.page_id
|
||||
JOIN sources s ON s.id = p.source_id
|
||||
WHERE cc.search_vector @@ ${ftsQueryExpr} ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
|
||||
WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
|
||||
ORDER BY score DESC
|
||||
LIMIT $2 OFFSET $3`,
|
||||
params
|
||||
|
||||
@@ -64,7 +64,7 @@ import { ConnectionManager } from './connection-manager.ts';
|
||||
import { logConnectionEvent } from './connection-audit.ts';
|
||||
import { validateSlug, contentHash, rowToPage, rowToStalePage, rowToChunk, rowToSearchResult, parseEmbedding, tryParseEmbedding, takeRowToTake, takeHitRowToHit, isUndefinedTableError, warnOncePerProcess } from './utils.ts';
|
||||
import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
|
||||
import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery, buildWebsearchQueryExpr } from './search/sql-ranking.ts';
|
||||
import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
|
||||
import { DEFAULT_EMBEDDING_MODEL, DEFAULT_EMBEDDING_DIMENSIONS } from './ai/defaults.ts';
|
||||
import { DELETE_BATCH_SIZE } from './engine-constants.ts';
|
||||
|
||||
@@ -1691,8 +1691,6 @@ export class PostgresEngine implements BrainEngine {
|
||||
const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
|
||||
const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
|
||||
|
||||
// #2380: slash-bearing queries match both the split-word and literal
|
||||
// slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
|
||||
const params: unknown[] = [query];
|
||||
let typeClause = '';
|
||||
if (type) {
|
||||
@@ -1763,7 +1761,6 @@ export class PostgresEngine implements BrainEngine {
|
||||
// FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
|
||||
// — safe to interpolate into raw SQL.
|
||||
const ftsLang = getFtsLanguage();
|
||||
const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
|
||||
|
||||
const rawQuery = `
|
||||
WITH ranked_chunks AS (
|
||||
@@ -1771,11 +1768,11 @@ export class PostgresEngine implements BrainEngine {
|
||||
p.slug, p.id as page_id, p.title, p.type, p.source_id,
|
||||
p.effective_date, p.effective_date_source,
|
||||
cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
|
||||
ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score
|
||||
ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score
|
||||
FROM content_chunks cc
|
||||
JOIN pages p ON p.id = cc.page_id
|
||||
JOIN sources s ON s.id = p.source_id
|
||||
WHERE cc.search_vector @@ ${ftsQueryExpr}
|
||||
WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
|
||||
${typeClause}
|
||||
${typesClause}
|
||||
${excludeSlugsClause}
|
||||
@@ -1866,10 +1863,7 @@ export class PostgresEngine implements BrainEngine {
|
||||
// FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
|
||||
// — safe to interpolate into raw SQL.
|
||||
const ftsLang = getFtsLanguage();
|
||||
const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
|
||||
|
||||
// #2380: slash-bearing queries match both the split-word and literal
|
||||
// slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
|
||||
const params: unknown[] = [query];
|
||||
let typeClause = '';
|
||||
if (opts?.type) {
|
||||
@@ -1929,7 +1923,7 @@ export class PostgresEngine implements BrainEngine {
|
||||
COALESCE(rep.chunk_index, 0) as chunk_index,
|
||||
COALESCE(rep.chunk_text, '') as chunk_text,
|
||||
COALESCE(rep.chunk_source, 'compiled_truth') as chunk_source,
|
||||
ts_rank_cd(p.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
|
||||
ts_rank_cd(p.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
|
||||
false AS stale
|
||||
FROM pages p
|
||||
JOIN sources s ON s.id = p.source_id
|
||||
@@ -1942,7 +1936,7 @@ export class PostgresEngine implements BrainEngine {
|
||||
ORDER BY (cc.chunk_source = 'compiled_truth') DESC, cc.chunk_index ASC
|
||||
LIMIT 1
|
||||
) rep ON true
|
||||
WHERE p.search_vector @@ ${ftsQueryExpr}
|
||||
WHERE p.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
|
||||
${typeClause}
|
||||
${typesClause}
|
||||
${excludeSlugsClause}
|
||||
@@ -2006,8 +2000,6 @@ export class PostgresEngine implements BrainEngine {
|
||||
const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
|
||||
const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
|
||||
|
||||
// #2380: slash-bearing queries match both the split-word and literal
|
||||
// slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
|
||||
const params: unknown[] = [query];
|
||||
let typeClause = '';
|
||||
if (type) {
|
||||
@@ -2068,19 +2060,18 @@ export class PostgresEngine implements BrainEngine {
|
||||
// FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
|
||||
// — safe to interpolate into raw SQL.
|
||||
const ftsLang = getFtsLanguage();
|
||||
const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
|
||||
|
||||
const rawQuery = `
|
||||
SELECT
|
||||
p.slug, p.id as page_id, p.title, p.type, p.source_id,
|
||||
p.effective_date, p.effective_date_source,
|
||||
cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
|
||||
ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
|
||||
ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
|
||||
false AS stale
|
||||
FROM content_chunks cc
|
||||
JOIN pages p ON p.id = cc.page_id
|
||||
JOIN sources s ON s.id = p.source_id
|
||||
WHERE cc.search_vector @@ ${ftsQueryExpr}
|
||||
WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
|
||||
${typeClause}
|
||||
${typesClause}
|
||||
${excludeSlugsClause}
|
||||
|
||||
@@ -251,28 +251,6 @@ export function buildOrFallbackWebsearchQuery(query: string): string | null {
|
||||
return tokens.join(' OR ');
|
||||
}
|
||||
|
||||
/**
|
||||
* #2380: FTS query expression for slash-bearing queries. Postgres' default
|
||||
* text-search parser classifies `foo/bar` as a single `file`-alias lexeme —
|
||||
* on BOTH the query side and the index side. So a raw `foo/bar` query only
|
||||
* matched documents carrying the identical joined lexeme (literal paths),
|
||||
* and a slash-split query only matches documents whose text had the words
|
||||
* separated. Neither form alone covers both document shapes; OR the two
|
||||
* parses so a slash query matches prose ("foo and bar", stemmed, AND
|
||||
* semantics) AND literal slash forms ("src/core/x.ts") alike.
|
||||
*
|
||||
* Slash-free queries return the plain single-parse expression — byte-
|
||||
* identical SQL and identical ts_rank to the historical behavior.
|
||||
*
|
||||
* `ftsLang` is validated by getFtsLanguage() (safe to interpolate);
|
||||
* `param` is a `$N` placeholder, never user text.
|
||||
*/
|
||||
export function buildWebsearchQueryExpr(ftsLang: string, param: string, query: string): string {
|
||||
const plain = `websearch_to_tsquery('${ftsLang}', ${param})`;
|
||||
if (!query.includes('/')) return plain;
|
||||
return `(websearch_to_tsquery('${ftsLang}', translate(${param}, '/', ' ')) || ${plain})`;
|
||||
}
|
||||
|
||||
// ============================================================
|
||||
// v0.29.1 — Recency component SQL builder
|
||||
// ============================================================
|
||||
|
||||
@@ -0,0 +1,44 @@
|
||||
import { describe, expect, test } from 'bun:test';
|
||||
import { normalizeAdminClientSourceScope } from '../src/core/admin-source-scope.ts';
|
||||
|
||||
describe('admin register-client source scope normalization', () => {
|
||||
const sources = ['default', 'team-a', 'team-b'];
|
||||
|
||||
test('defaults write and read scope to default source', () => {
|
||||
expect(normalizeAdminClientSourceScope(undefined, undefined, sources)).toEqual({
|
||||
sourceId: 'default',
|
||||
federatedRead: ['default'],
|
||||
});
|
||||
});
|
||||
|
||||
test('accepts snake-case body fields with multiple read sources', () => {
|
||||
expect(normalizeAdminClientSourceScope('team-a', ['team-a', 'team-b'], sources)).toEqual({
|
||||
sourceId: 'team-a',
|
||||
federatedRead: ['team-a', 'team-b'],
|
||||
});
|
||||
});
|
||||
|
||||
test('accepts comma-separated federated_read for API callers', () => {
|
||||
expect(normalizeAdminClientSourceScope('team-a', 'team-b, default,team-b', sources)).toEqual({
|
||||
sourceId: 'team-a',
|
||||
federatedRead: ['team-b', 'default'],
|
||||
});
|
||||
});
|
||||
|
||||
test('falls back to selected write source when federated_read is empty', () => {
|
||||
expect(normalizeAdminClientSourceScope('team-b', [], sources)).toEqual({
|
||||
sourceId: 'team-b',
|
||||
federatedRead: ['team-b'],
|
||||
});
|
||||
});
|
||||
|
||||
test('rejects malformed source ids before registration', () => {
|
||||
expect(() => normalizeAdminClientSourceScope('../secret', undefined, sources)).toThrow(/Invalid source_id/);
|
||||
expect(() => normalizeAdminClientSourceScope('team-a', ['snake_case'], sources)).toThrow(/Invalid federated_read/);
|
||||
});
|
||||
|
||||
test('rejects valid-looking but unregistered source ids', () => {
|
||||
expect(() => normalizeAdminClientSourceScope('ghost', undefined, sources)).toThrow(/Unknown source_id/);
|
||||
expect(() => normalizeAdminClientSourceScope('team-a', ['ghost'], sources)).toThrow(/Unknown federated_read/);
|
||||
});
|
||||
});
|
||||
@@ -28,8 +28,8 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
|
||||
resetGateway();
|
||||
});
|
||||
|
||||
test('LiteLLM and llama-server declare no_batch_cap: true', () => {
|
||||
for (const id of ['litellm', 'llama-server']) {
|
||||
test('Ollama, LiteLLM, llama-server all declare no_batch_cap: true', () => {
|
||||
for (const id of ['ollama', 'litellm', 'llama-server']) {
|
||||
const r = getRecipe(id);
|
||||
expect(r, `${id} not registered`).toBeDefined();
|
||||
expect(
|
||||
@@ -39,18 +39,6 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
|
||||
}
|
||||
});
|
||||
|
||||
test('#2552: Ollama declares a conservative static batch cap, not no_batch_cap', () => {
|
||||
// A CPU-only Ollama box wedges when a whole page ships in one request;
|
||||
// Ollama never returns a token-limit error so the recursive-halving
|
||||
// safety net can't fire. The pre-split cap is the only guard.
|
||||
const r = getRecipe('ollama');
|
||||
expect(r).toBeDefined();
|
||||
const e = r!.touchpoints.embedding!;
|
||||
expect(e.no_batch_cap).toBeUndefined();
|
||||
expect(e.max_batch_tokens).toBe(4096);
|
||||
expect(e.chars_per_token).toBe(2);
|
||||
});
|
||||
|
||||
test('configureGateway does NOT warn for ollama/litellm/llama-server', () => {
|
||||
warnSpy.mockClear();
|
||||
resetGateway();
|
||||
|
||||
@@ -1,118 +0,0 @@
|
||||
/**
|
||||
* #2552: cloud-tuned embedding defaults silently wedge CPU-only local
|
||||
* endpoints (Ollama). Three-part fix under test:
|
||||
*
|
||||
* 1. `isLocalEmbeddingEndpoint()` — gateway helper detecting local
|
||||
* inference servers (ollama / llama-server recipes, localhost base URL).
|
||||
* 2. `resolveEmbedConcurrency()` — embed auto-caps the 20-worker fan-out
|
||||
* at LOCAL_EMBED_CONCURRENCY_CAP for local endpoints unless the
|
||||
* operator set GBRAIN_EMBED_CONCURRENCY explicitly.
|
||||
* 3. `computeEmbedConcurrencyCheck()` — doctor warns when an explicit env
|
||||
* override fans out against a local endpoint.
|
||||
*
|
||||
* Serial: mutates process.env and the module-global gateway config.
|
||||
*/
|
||||
|
||||
import { afterAll, afterEach, describe, expect, test } from 'bun:test';
|
||||
import {
|
||||
configureGateway,
|
||||
resetGateway,
|
||||
isLocalEmbeddingEndpoint,
|
||||
LOCAL_EMBED_CONCURRENCY_CAP,
|
||||
} from '../src/core/ai/gateway.ts';
|
||||
import { resolveEmbedConcurrency } from '../src/commands/embed.ts';
|
||||
import { computeEmbedConcurrencyCheck } from '../src/commands/doctor.ts';
|
||||
|
||||
const SAVED_ENV = process.env.GBRAIN_EMBED_CONCURRENCY;
|
||||
|
||||
afterEach(() => {
|
||||
resetGateway();
|
||||
if (SAVED_ENV === undefined) delete process.env.GBRAIN_EMBED_CONCURRENCY;
|
||||
else process.env.GBRAIN_EMBED_CONCURRENCY = SAVED_ENV;
|
||||
});
|
||||
|
||||
afterAll(() => {
|
||||
resetGateway();
|
||||
});
|
||||
|
||||
describe('#2552 isLocalEmbeddingEndpoint', () => {
|
||||
test('false when the gateway is not configured (fail-open to cloud behavior)', () => {
|
||||
resetGateway();
|
||||
expect(isLocalEmbeddingEndpoint()).toBe(false);
|
||||
});
|
||||
|
||||
test('true for the ollama recipe', () => {
|
||||
configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
|
||||
expect(isLocalEmbeddingEndpoint()).toBe(true);
|
||||
});
|
||||
|
||||
test('true for the llama-server recipe', () => {
|
||||
configureGateway({ embedding_model: 'llama-server:my-gguf', env: {} });
|
||||
expect(isLocalEmbeddingEndpoint()).toBe(true);
|
||||
});
|
||||
|
||||
test('false for a cloud recipe', () => {
|
||||
configureGateway({
|
||||
embedding_model: 'openai:text-embedding-3-small',
|
||||
env: { OPENAI_API_KEY: 'fake' },
|
||||
});
|
||||
expect(isLocalEmbeddingEndpoint()).toBe(false);
|
||||
});
|
||||
|
||||
test('true when a cloud recipe base URL is explicitly pointed at localhost', () => {
|
||||
configureGateway({
|
||||
embedding_model: 'openai:text-embedding-3-small',
|
||||
env: { OPENAI_API_KEY: 'fake' },
|
||||
base_urls: { openai: 'http://localhost:8080/v1' },
|
||||
});
|
||||
expect(isLocalEmbeddingEndpoint()).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe('#2552 resolveEmbedConcurrency', () => {
|
||||
test('caps at LOCAL_EMBED_CONCURRENCY_CAP for a local endpoint when env is unset', () => {
|
||||
delete process.env.GBRAIN_EMBED_CONCURRENCY;
|
||||
configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
|
||||
expect(resolveEmbedConcurrency()).toBe(LOCAL_EMBED_CONCURRENCY_CAP);
|
||||
});
|
||||
|
||||
test('explicit env override always wins, even against a local endpoint', () => {
|
||||
process.env.GBRAIN_EMBED_CONCURRENCY = '10';
|
||||
configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
|
||||
expect(resolveEmbedConcurrency()).toBe(10);
|
||||
});
|
||||
|
||||
test('cloud endpoints keep the historical default of 20', () => {
|
||||
delete process.env.GBRAIN_EMBED_CONCURRENCY;
|
||||
configureGateway({ env: { OPENAI_API_KEY: 'fake' } });
|
||||
expect(resolveEmbedConcurrency()).toBe(20);
|
||||
});
|
||||
|
||||
test('pacing only ever lowers concurrency', () => {
|
||||
delete process.env.GBRAIN_EMBED_CONCURRENCY;
|
||||
configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
|
||||
expect(resolveEmbedConcurrency(1)).toBe(1);
|
||||
expect(resolveEmbedConcurrency(16)).toBe(LOCAL_EMBED_CONCURRENCY_CAP);
|
||||
});
|
||||
});
|
||||
|
||||
describe('#2552 computeEmbedConcurrencyCheck (doctor)', () => {
|
||||
test('ok for non-local endpoints', () => {
|
||||
expect(computeEmbedConcurrencyCheck(false, '20', 2).status).toBe('ok');
|
||||
});
|
||||
|
||||
test('warn when an explicit override exceeds the local cap', () => {
|
||||
const check = computeEmbedConcurrencyCheck(true, '20', 2);
|
||||
expect(check.status).toBe('warn');
|
||||
expect(check.message).toContain('GBRAIN_EMBED_CONCURRENCY=20');
|
||||
});
|
||||
|
||||
test('ok when env is unset against a local endpoint (auto-cap applies)', () => {
|
||||
expect(computeEmbedConcurrencyCheck(true, undefined, 2).status).toBe('ok');
|
||||
});
|
||||
|
||||
test('ok when the override is at or under the cap', () => {
|
||||
expect(computeEmbedConcurrencyCheck(true, '2', 2).status).toBe('ok');
|
||||
expect(computeEmbedConcurrencyCheck(true, '1', 2).status).toBe('ok');
|
||||
});
|
||||
});
|
||||
@@ -78,6 +78,8 @@ describe('v0.36.1.x #1077 — admin register-client supports PKCE public clients
|
||||
// (under either name) from req.body. Pin the fallback pattern so the
|
||||
// PKCE-fix regression contract stays load-bearing.
|
||||
expect(src).toMatch(/req\.body[^;]*scopes\s*\?\?\s*[^;]*scope\b/);
|
||||
expect(src).toMatch(/req\.body[^;]*source_id\s*\?\?\s*[^;]*sourceId\b/);
|
||||
expect(src).toMatch(/req\.body[^;]*federated_read\s*\?\?\s*[^;]*federatedRead\b/);
|
||||
// v0.41.3 (T4 atomicity fix, codex F4): admin endpoint now validates
|
||||
// tokenEndpointAuthMethod via the shared validator and passes it to
|
||||
// registerClientManual as a positional arg. Pre-v0.41.3 the route did
|
||||
@@ -87,6 +89,7 @@ describe('v0.36.1.x #1077 — admin register-client supports PKCE public clients
|
||||
// UPDATE block (the regex deliberately asserts the post-insert UPDATE
|
||||
// is GONE).
|
||||
expect(src).toMatch(/validateTokenEndpointAuthMethod\(tokenEndpointAuthMethod\)/);
|
||||
expect(src).toMatch(/normalizeAdminClientSourceScope\(/);
|
||||
expect(src).toMatch(/registerClientManual\([^)]*validatedAuthMethod[^)]*\)/);
|
||||
// Regression guard: post-insert UPDATE flipping client_secret_hash to
|
||||
// NULL based on a runtime check is exactly the non-atomic pattern T4
|
||||
@@ -267,3 +270,26 @@ describe('v0.42.43.0 #2095 — volunteer-events sink + cycle purge wiring (struc
|
||||
expect(src).toMatch(/purged_volunteer_events_count/);
|
||||
});
|
||||
});
|
||||
|
||||
describe('#1490 + #1036 — admin Register Agent form exposes source scope + redirect URIs', () => {
|
||||
test('Agents.tsx RegisterModal sends source_id + federated_read in the POST body (#1490)', () => {
|
||||
const src = readFileSync('admin/src/pages/Agents.tsx', 'utf8');
|
||||
expect(src).toMatch(/source_id:\s*sourceId/);
|
||||
expect(src).toMatch(/federated_read:\s*federatedRead/);
|
||||
// The source list comes from the requireAdmin-gated endpoint, not a hardcoded 'default'.
|
||||
expect(src).toMatch(/api\.sources\(\)/);
|
||||
});
|
||||
|
||||
test('serve-http.ts serves /admin/api/sources behind requireAdmin (#1490)', () => {
|
||||
const src = readFileSync('src/commands/serve-http.ts', 'utf8');
|
||||
expect(src).toMatch(/app\.get\('\/admin\/api\/sources',\s*requireAdmin/);
|
||||
});
|
||||
|
||||
test('Agents.tsx RegisterModal sends redirectUris + authorization_code grants when URIs are entered (#1036)', () => {
|
||||
const src = readFileSync('admin/src/pages/Agents.tsx', 'utf8');
|
||||
// One-per-line textarea split into an array...
|
||||
expect(src).toMatch(/redirectUris\.split\('\\n'\)/);
|
||||
// ...included in the body with the CLI's grant-type inference convention.
|
||||
expect(src).toMatch(/redirectUris:\s*uris,\s*grantTypes:\s*\['authorization_code',\s*'refresh_token'\]/);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -125,6 +125,30 @@ describe('client registration', () => {
|
||||
expect(client!.client_name).toBe('test-agent');
|
||||
});
|
||||
|
||||
test('registerClientManual persists source_id and federated_read into AuthInfo', async () => {
|
||||
await sql`
|
||||
INSERT INTO sources (id, name) VALUES (${'team-a'}, ${'Team A'}), (${'team-b'}, ${'Team B'})
|
||||
ON CONFLICT DO NOTHING
|
||||
`;
|
||||
const { clientId, clientSecret } = await provider.registerClientManual(
|
||||
'source-scoped-test',
|
||||
['client_credentials'],
|
||||
'read write',
|
||||
[],
|
||||
'team-a',
|
||||
['team-a', 'team-b'],
|
||||
);
|
||||
|
||||
const tokens = await provider.exchangeClientCredentials(clientId, clientSecret!, 'read');
|
||||
const authInfo = await provider.verifyAccessToken(tokens.access_token) as {
|
||||
sourceId?: string;
|
||||
allowedSources?: string[];
|
||||
};
|
||||
|
||||
expect(authInfo.sourceId).toBe('team-a');
|
||||
expect(authInfo.allowedSources).toEqual(['team-a', 'team-b']);
|
||||
});
|
||||
|
||||
test('getClient returns undefined for unknown client', async () => {
|
||||
const client = await provider.clientsStore.getClient('nonexistent');
|
||||
expect(client).toBeUndefined();
|
||||
|
||||
@@ -216,67 +216,6 @@ describe('PGLiteEngine: Search', () => {
|
||||
expect(results.length).toBe(0);
|
||||
});
|
||||
|
||||
// Regression (#2380): queries containing `/` used to bypass FTS AND
|
||||
// semantics. Postgres' default text-search parser classifies `foo/bar` as
|
||||
// a `file`-alias token mapped to the `simple` dictionary, so it became a
|
||||
// single un-stemmed lexeme `'foo/bar'` that never matches indexed text —
|
||||
// the primary FTS pass returned 0 and the OR fallback took over, matching
|
||||
// pages that contain EITHER term. searchKeyword/searchTitles now normalize
|
||||
// `/` to whitespace before websearch_to_tsquery parses, so the primary
|
||||
// AND pass matches directly.
|
||||
test('searchKeyword: slash query matches with AND semantics, not OR fallback', async () => {
|
||||
// Decoy shares only ONE of the two query terms ('enterprise').
|
||||
await engine.putPage('concepts/enterprise-pricing', {
|
||||
type: 'concept', title: 'Widget Pricing',
|
||||
compiled_truth: 'Enterprise pricing for widgets.',
|
||||
});
|
||||
await engine.upsertChunks('concepts/enterprise-pricing', [
|
||||
{ chunk_index: 0, chunk_text: 'Enterprise pricing for widgets', chunk_source: 'compiled_truth' },
|
||||
]);
|
||||
|
||||
// Both terms co-occur only in the novamind chunk. Pre-fix this returned
|
||||
// BOTH pages (primary pass zero-hit → OR fallback); post-fix the primary
|
||||
// AND pass returns exactly the co-occurrence page.
|
||||
const results = await engine.searchKeyword('NovaMind/enterprise');
|
||||
expect(results.length).toBe(1);
|
||||
expect(results[0].slug).toBe('companies/novamind');
|
||||
});
|
||||
|
||||
test('searchTitles: slash query matches with AND semantics, not OR fallback', async () => {
|
||||
await engine.putPage('companies/novamind-enterprise', {
|
||||
type: 'company', title: 'NovaMind Enterprise Platform',
|
||||
compiled_truth: 'Placeholder body.',
|
||||
});
|
||||
await engine.putPage('guides/enterprise-sales', {
|
||||
type: 'concept', title: 'Enterprise Sales Guide',
|
||||
compiled_truth: 'Placeholder body.',
|
||||
});
|
||||
|
||||
// Pre-fix: `NovaMind/Enterprise` parsed as one file-alias lexeme → the
|
||||
// primary title pass returned 0 and the OR fallback matched BOTH titles.
|
||||
const results = await engine.searchTitles('NovaMind/Enterprise');
|
||||
expect(results.length).toBe(1);
|
||||
expect(results[0].slug).toBe('companies/novamind-enterprise');
|
||||
});
|
||||
|
||||
test('searchKeyword: slash query still matches the literal slash form (file paths)', async () => {
|
||||
// The INDEX side also emits the joined file-alias lexeme for literal
|
||||
// `foo/bar` text, so a query normalized to split words alone would go
|
||||
// blind to documents containing the literal slash form (paths, URLs).
|
||||
// buildWebsearchQueryExpr ORs both parses; this pins the raw arm.
|
||||
await engine.putPage('runbooks/widget-deploy', {
|
||||
type: 'concept', title: 'Widget Deploy Runbook',
|
||||
compiled_truth: 'Runbook for the acme/widget deployment pipeline.',
|
||||
});
|
||||
await engine.upsertChunks('runbooks/widget-deploy', [
|
||||
{ chunk_index: 0, chunk_text: 'Runbook for the acme/widget deployment pipeline', chunk_source: 'compiled_truth' },
|
||||
]);
|
||||
|
||||
const results = await engine.searchKeyword('acme/widget');
|
||||
expect(results.length).toBe(1);
|
||||
expect(results[0].slug).toBe('runbooks/widget-deploy');
|
||||
});
|
||||
|
||||
test('tsvector trigger populates search_vector on insert', async () => {
|
||||
// Verify the PL/pgSQL trigger fires and content_chunks.search_vector is
|
||||
// populated from chunk_text. v0.20.0 Cathedral II Layer 3 moved FTS from
|
||||
|
||||
Reference in New Issue
Block a user