Compare commits

..
Author SHA1 Message Date
1b45023dba fix(admin): source scoping + redirect URIs in admin OAuth registration
Takeover of #1558 (rebased onto master, admin/dist + admin-embedded
regenerated so asset hashes match; source changes salvaged intact):

- /admin/api/register-client now accepts source_id + federated_read
  (snake and camel case), validated fail-closed against the registered
  source list via the new normalizeAdminClientSourceScope
  (src/core/admin-source-scope.ts) before reaching
  registerClientManual — unknown or malformed ids are a 400, never a
  silently-hardcoded 'default'. Fixes #1490.
- New requireAdmin-gated GET /admin/api/sources feeds the Register
  Agent form; the form now has a Write Source select + Read Sources
  checkboxes, and the agents table/drawer show each client's scope.
- #1036: the Register Agent form now has a Redirect URIs textarea
  (one per line). When present, the POST carries redirectUris plus
  the authorization_code + refresh_token grants, mirroring the CLI's
  --redirect-uri grant-inference convention (src/commands/auth.ts).
  Backend plumbing already existed; this was UI-only.

Tests: test/admin-source-scope.test.ts (normalization matrix),
test/oauth.test.ts (registerClientManual persists source scope into
AuthInfo), test/fix-wave-structural.test.ts (endpoint + form pins for
#1490 and #1036).

Co-authored-by: flamerged <flamerged@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 15:09:32 -07:00
24 changed files with 394 additions and 635 deletions
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
+1 -1
View File
@@ -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>
+1
View File
@@ -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 }) }),
+87 -1
View File
@@ -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>
+3 -3
View File
@@ -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" },
};
+13 -43
View File
@@ -1,7 +1,6 @@
import type { BrainEngine } from '../core/engine.ts';
import { embedBatch, currentEmbeddingSignature } from '../core/embedding.ts';
import type { ChunkInput, ResolvedColumn } from '../core/types.ts';
import { resolveWriteColumnForEngine } from '../core/search/embedding-column.ts';
import type { ChunkInput } from '../core/types.ts';
import { chunkText } from '../core/chunkers/recursive.ts';
import { createProgress, type ProgressReporter } from '../core/progress.ts';
import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
@@ -184,13 +183,8 @@ export class EmbeddingDimMismatchError extends Error {
* fresh-install bug class at the very first invocation instead of letting
* the worker pool hammer N pages with raw 22000 errors.
*/
async function preflightDimMismatch(engine: BrainEngine, dryRun: boolean, embeddingColumn?: ResolvedColumn): Promise<void> {
async function preflightDimMismatch(engine: BrainEngine, dryRun: boolean): Promise<void> {
if (dryRun) return; // dry-run never embeds, no risk
// #1262: an alt-column brain writes to `embeddingColumn`, not the legacy
// `embedding` column — the legacy column's dims are irrelevant, and the
// registry entry (validated at resolve time) pins the target's dims. Only
// the legacy default path needs the schema-vs-gateway dim comparison.
if (embeddingColumn && embeddingColumn.name !== 'embedding') return;
const { readContentChunksEmbeddingDim, embeddingMismatchMessage } = await import('../core/embedding-dim-check.ts');
const { getEmbeddingDimensions, getEmbeddingModel } = await import('../core/ai/gateway.ts');
let existing;
@@ -244,12 +238,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
// v0.37.11.0 (Lane D.2): pre-flight dim-mismatch check. Catches the headline
// fresh-install bug class before the worker pool spends 20 parallel calls
// hitting raw Postgres dimension errors.
// #1262: resolve the write-side embedding column ONCE at the boundary
// (merged config + gateway model) and thread the descriptor through every
// upsertChunks / stale-scan below. undefined => legacy `embedding` column.
const embeddingColumn = await resolveWriteColumnForEngine(engine);
await preflightDimMismatch(engine, !!opts.dryRun, embeddingColumn);
await preflightDimMismatch(engine, !!opts.dryRun);
const result: EmbedResult = {
embedded: 0,
@@ -264,7 +253,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
for (const s of opts.slugs) {
if (isAborted(opts.signal)) break; // #1737: stop the per-slug loop on abort
try {
await embedPage(engine, s, !!opts.dryRun, result, opts.sourceId, opts.signal, embeddingColumn);
await embedPage(engine, s, !!opts.dryRun, result, opts.sourceId, opts.signal);
} catch (e: unknown) {
serr(` Error embedding ${s}: ${e instanceof Error ? e.message : e}`);
}
@@ -358,7 +347,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
catchUp: opts.catchUp,
pacer,
paceMaxConcurrency,
}, opts.signal, embeddingColumn);
}, opts.signal);
} finally {
// E1: surface pacing telemetry (human + structured) when pacing was on.
const snap = pacer.snapshot();
@@ -387,7 +376,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
return result;
}
if (opts.slug) {
await embedPage(engine, opts.slug, !!opts.dryRun, result, opts.sourceId, opts.signal, embeddingColumn);
await embedPage(engine, opts.slug, !!opts.dryRun, result, opts.sourceId, opts.signal);
return result;
}
throw new Error('No embed target specified. Pass { slug }, { slugs }, { all }, or { stale }.');
@@ -532,13 +521,8 @@ async function embedPage(
result: EmbedResult,
sourceId?: string,
signal?: AbortSignal,
embeddingColumn?: ResolvedColumn,
) {
const opts = sourceId ? { sourceId } : undefined;
// #1262: write-side descriptor rides only on WRITE calls (upsertChunks).
const chunkOpts = (sourceId || embeddingColumn)
? { ...(sourceId && { sourceId }), ...(embeddingColumn && { embeddingColumn }) }
: undefined;
const page = await engine.getPage(slug, opts);
if (!page) {
throw new Error(`Page not found: ${slug}`);
@@ -570,7 +554,7 @@ async function embedPage(
}
if (inputs.length > 0) {
await engine.upsertChunks(slug, inputs, chunkOpts);
await engine.upsertChunks(slug, inputs, opts);
chunks = await engine.getChunks(slug, opts);
}
}
@@ -605,7 +589,7 @@ async function embedPage(
token_count: c.token_count || Math.ceil(c.chunk_text.length / 4),
}));
await engine.upsertChunks(slug, updated, chunkOpts);
await engine.upsertChunks(slug, updated, opts);
// v0.41.31: stamp provenance so a later model/dims swap is detectable as
// stale. embedPage is the per-slug path used by `gbrain embed <slug>` AND
// by `gbrain sync`'s post-import embed step (runEmbedCore({slugs})).
@@ -638,7 +622,6 @@ async function embedAll(
paceMaxConcurrency?: number;
},
signal?: AbortSignal,
embeddingColumn?: ResolvedColumn,
) {
// v0.41.31: current embedding provenance signature. Stamped onto pages
// when their chunks are (re)embedded so a later model/dimension swap is
@@ -661,7 +644,7 @@ async function embedAll(
// D7: thread sourceId so `gbrain embed --stale --source X` actually scopes.
// v0.41.18.0 (A13): thread batchSize/priority/catchUp into the stale path.
// #1737: thread the external abort signal so the cycle embed phase bails.
return await embedAllStale(engine, sourceId, dryRun, result, onProgress, staleOpts, signature, signal, embeddingColumn);
return await embedAllStale(engine, sourceId, dryRun, result, onProgress, staleOpts, signature, signal);
}
// --all path: pacer (no-op when off). E-1: lower the worker count to the
@@ -742,10 +725,7 @@ async function embedAll(
embedding: embeddingMap.get(c.chunk_index) ?? undefined,
token_count: c.token_count || Math.ceil(c.chunk_text.length / 4),
}));
await observed(pacer, () => engine.upsertChunks(page.slug, updated, {
...(pageSourceId && { sourceId: pageSourceId }),
...(embeddingColumn && { embeddingColumn }),
}));
await observed(pacer, () => engine.upsertChunks(page.slug, updated, pageOpts));
// v0.41.31: stamp embedding provenance so a later model swap is
// detectable as stale.
await observed(pacer, () =>
@@ -825,16 +805,10 @@ async function embedAllStale(
},
signature?: string,
externalSignal?: AbortSignal,
embeddingColumn?: ResolvedColumn,
) {
// D7: thread sourceId so source-scoped runs only count + visit
// that source's NULL embeddings.
// #1262: the stale predicate follows the write-side column — without it an
// alt-column brain would perpetually re-select (and re-pay for) chunks whose
// target column is already populated.
const sourceOpt = (sourceId || embeddingColumn)
? { ...(sourceId && { sourceId }), ...(embeddingColumn && { embeddingColumn }) }
: undefined;
const sourceOpt = sourceId ? { sourceId } : undefined;
// v0.41.31: re-embed pages whose embedding_signature drifted (model/dims
// swap). dry-run must NOT mutate, so it counts signature-stale via the
@@ -993,7 +967,6 @@ async function embedAllStale(
afterUpdatedAt,
}),
...(sourceId && { sourceId }),
...(embeddingColumn && { embeddingColumn }),
}),
);
if (batch.length === 0) {
@@ -1046,10 +1019,7 @@ async function embedAllStale(
embedding: staleIdxToEmbedding.get(c.chunk_index) ?? undefined,
token_count: c.token_count || Math.ceil(c.chunk_text.length / 4),
}));
await observed(pacer, () => engine.upsertChunks(slug, merged, {
sourceId: keySourceId,
...(embeddingColumn && { embeddingColumn }),
}));
await observed(pacer, () => engine.upsertChunks(slug, merged, { sourceId: keySourceId }));
// v0.41.31: stamp provenance after the page's chunks are embedded —
// but only when EVERY chunk was stale (fully re-embedded this pass).
// A partially-stale page keeps preserved chunks of unknown/old
@@ -1120,7 +1090,7 @@ async function embedAllStale(
// as a clean run — re-running won't help until the underlying failure is fixed.
if (staleOpts?.catchUp && !effectiveSignal.aborted && embedFailures > 0) {
const remaining = await engine.countStaleChunks(
signature ? { signature, ...sourceOpt } : sourceOpt,
signature ? { signature, ...(sourceId ? { sourceId } : {}) } : (sourceId ? { sourceId } : undefined),
);
if (remaining > 0) {
serr(`\n [embed] catch-up finished but ${remaining} chunk(s) remain stale after ${embedFailures} embed failure(s). These are not embeddable as-is; re-running won't clear them until the underlying error is resolved.`);
+32 -1
View File
@@ -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) {
+1 -8
View File
@@ -576,16 +576,9 @@ async function runInlineCostGate(
// Stale backlog: cheap single SQL; fail-open to 0 so a transient DB hiccup
// never blocks the sync. Signature-aware (model/dims swap surfaces here).
// #1262: follow the write-side embedding column — otherwise an alt-column
// brain's fully-embedded corpus counts as phantom backlog on every gate.
let staleChars = 0;
try {
const { resolveWriteColumnForEngine } = await import('../core/search/embedding-column.ts');
const embeddingColumn = await resolveWriteColumnForEngine(engine);
staleChars = await engine.sumStaleChunkChars({
signature: currentEmbeddingSignature(),
...(embeddingColumn && { embeddingColumn }),
});
staleChars = await engine.sumStaleChunkChars({ signature: currentEmbeddingSignature() });
} catch {
staleChars = 0;
}
+51
View File
@@ -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 };
}
-5
View File
@@ -61,7 +61,6 @@ import {
type SynopsisFailureKind,
} from './audit-synopsis.ts';
import type { BrainEngine } from './engine.ts';
import { resolveWriteColumnForEngine } from './search/embedding-column.ts';
import type { ChunkInput, CRMode, Page } from './types.ts';
import type { SourceRow } from './sources-ops.ts';
@@ -287,13 +286,9 @@ export async function reembedPageWithContextualRetrieval(
// ── PHASE 2: single DB transaction ───────────────────────────
try {
// #1262: contextual re-embeds write TEXT embeddings — thread the
// caller-resolved write column like every other embed path.
const embeddingColumn = await resolveWriteColumnForEngine(args.engine);
await args.engine.transaction(async (tx) => {
await tx.upsertChunks(args.pageSlug, phase1.embeddedChunks, {
sourceId: args.sourceId,
...(embeddingColumn && { embeddingColumn }),
});
await tx.updatePageContextualRetrievalState(
args.pageSlug,
+2 -13
View File
@@ -18,7 +18,7 @@
*/
import type { BrainEngine } from './engine.ts';
import type { ChunkInput, ResolvedColumn } from './types.ts';
import type { ChunkInput } from './types.ts';
import { embedBatchWithBackoff } from '../commands/embed.ts';
import { type DbPacer, createNoopPacer, observed } from './db-pacer.ts';
import { AbortError } from './abort-check.ts';
@@ -61,13 +61,6 @@ export interface EmbedStaleOpts {
* Omit to keep the legacy `embedding IS NULL`-only behavior.
*/
embeddingSignature?: string;
/**
* #1262: caller-resolved write-side embedding column. Threaded into BOTH
* listStaleChunks (staleness predicate) and upsertChunks (write target) so
* an alt-column brain converges instead of re-selecting embedded rows.
* Resolve at the boundary via `resolveWriteColumnForEngine()`.
*/
embeddingColumn?: ResolvedColumn;
/**
* DB-contention pacer (paced-backfill). When enabled it (a) supplies the
* worker count via the caller passing `concurrency = bundle.maxConcurrency`
@@ -163,7 +156,6 @@ export async function embedStaleForSource(
afterPageId,
afterChunkIndex,
sourceId,
...(opts.embeddingColumn && { embeddingColumn: opts.embeddingColumn }),
}),
);
if (batch.length === 0) {
@@ -231,10 +223,7 @@ export async function embedStaleForSource(
doc_comment: c.doc_comment ?? undefined,
symbol_name_qualified: c.symbol_name_qualified ?? undefined,
}));
await observed(pacer, () => engine.upsertChunks(slug, merged, {
sourceId: keySourceId,
...(opts.embeddingColumn && { embeddingColumn: opts.embeddingColumn }),
}));
await observed(pacer, () => engine.upsertChunks(slug, merged, { sourceId: keySourceId }));
// v0.41.31: stamp provenance only when EVERY chunk was stale (fully
// re-embedded this pass) — a partially-stale page keeps preserved
// chunks of unknown provenance, so don't claim current. After the
+3 -22
View File
@@ -12,7 +12,6 @@ import type {
BrainStats, BrainHealth,
IngestLogEntry, IngestLogInput,
EngineConfig,
ResolvedColumn,
CodeEdgeInput, CodeEdgeResult,
EvalCandidate, EvalCandidateInput,
EvalCaptureFailure, EvalCaptureFailureReason,
@@ -988,13 +987,8 @@ export interface BrainEngine {
* Postgres rolls back automatically on conn drop, so commit-ambiguous
* failure replays to the same end state. Callers MUST NOT wrap externally;
* see {@link BatchOpts} retry-contract block.
*
* `opts.embeddingColumn` (optional) selects the content_chunks column that
* receives TEXT embeddings (#1262). The caller resolves the descriptor at
* the import/embed boundary via `resolveWriteColumn()`; engines never read
* config or choose columns themselves. Omitted => legacy `embedding`.
*/
upsertChunks(slug: string, chunks: ChunkInput[], opts?: { sourceId?: string; embeddingColumn?: ResolvedColumn } & BatchOpts): Promise<void>;
upsertChunks(slug: string, chunks: ChunkInput[], opts?: { sourceId?: string } & BatchOpts): Promise<void>;
/**
* Read every chunk for a page. `opts.sourceId` source-scopes the page
* lookup; without it, multi-source brains return chunks from every
@@ -1011,13 +1005,8 @@ export interface BrainEngine {
* counts across every source in the brain. Operators running
* `gbrain embed --stale --source media-corpus` expect only that
* source's NULLs touched; the caller threads `sourceId` here.
*
* `opts.embeddingColumn` switches the staleness predicate from the legacy
* `embedding` column to the resolved write-side column, so alt-column
* brains do not perpetually re-select rows whose target column is already
* populated (#1262). Must match the eventual upsertChunks target.
*/
countStaleChunks(opts?: { sourceId?: string; signature?: string; embeddingColumn?: ResolvedColumn }): Promise<number>;
countStaleChunks(opts?: { sourceId?: string; signature?: string }): Promise<number>;
/**
* Sum of LENGTH(chunk_text) over stale chunks the character-count
* backlog the embed phase / embed-backfill will process. Sibling of
@@ -1031,13 +1020,8 @@ export interface BrainEngine {
* model signature (a model/dims swap). NULL signature is GRANDFATHERED
* (never counted) so the post-migration corpus isn't flagged en masse.
* Omit `signature` for the legacy `embedding IS NULL`-only count.
*
* `opts.embeddingColumn` switches the staleness predicate to the resolved
* write-side column (#1262) same contract as countStaleChunks so the
* sync cost gate doesn't count an alt-column brain's fully-embedded corpus
* as phantom backlog.
*/
sumStaleChunkChars(opts?: { sourceId?: string; signature?: string; embeddingColumn?: ResolvedColumn }): Promise<number>;
sumStaleChunkChars(opts?: { sourceId?: string; signature?: string }): Promise<number>;
/**
* Stamp `pages.embedding_signature = signature` for one page. Called after
* a page's chunks are (re)embedded so a later model swap can detect it as
@@ -1085,9 +1069,6 @@ export interface BrainEngine {
// both round-trip TIMESTAMPTZ as Date | string; ISO string is the
// common denominator on the wire).
afterUpdatedAt?: string | null;
// #1262: staleness predicate targets this column when set (must match
// countStaleChunks and the eventual upsertChunks write target).
embeddingColumn?: ResolvedColumn;
}): Promise<StaleChunkRow[]>;
/**
* Delete every chunk for a page. Internal page-id lookup is sourceId-scoped
+4 -25
View File
@@ -10,8 +10,7 @@ import { findChunkForOffset } from './chunkers/edge-extractor.ts';
import { extractCodeRefs, imageOfCandidates } from './link-extraction.ts';
import { embedBatch, embedMultimodal, currentEmbeddingSignature } from './embedding.ts';
import { slugifyPath, slugifyCodePath, isCodeFilePath } from './sync.ts';
import type { ChunkInput, PageInput, PageType, ResolvedColumn } from './types.ts';
import { resolveWriteColumnForEngine } from './search/embedding-column.ts';
import type { ChunkInput, PageInput, PageType } from './types.ts';
import { computeEffectiveDate } from './effective-date.ts';
import { MARKDOWN_CHUNKER_VERSION } from './chunkers/recursive.ts';
import { logSlugFallback } from './audit-slug-fallback.ts';
@@ -741,14 +740,6 @@ export async function importFromContent(
// schema DEFAULT — required for multi-source brains; harmless ('default')
// for single-source callers.
const txOpts = sourceId ? { sourceId } : undefined;
// #1262: resolve the write-side embedding column once (merged config +
// gateway model) BEFORE the transaction; the descriptor rides only on
// upsertChunks so text embeddings land in the registered column.
const chunkWriteColumn = await resolveWriteColumnForEngine(engine);
const chunkOpts: { sourceId?: string; embeddingColumn?: ResolvedColumn } | undefined =
(sourceId || chunkWriteColumn)
? { ...(sourceId && { sourceId }), ...(chunkWriteColumn && { embeddingColumn: chunkWriteColumn }) }
: undefined;
await engine.transaction(async (tx) => {
if (existing) await tx.createVersion(slug, txOpts);
@@ -833,7 +824,7 @@ export async function importFromContent(
}
if (chunks.length > 0) {
await tx.upsertChunks(slug, chunks, chunkOpts);
await tx.upsertChunks(slug, chunks, txOpts);
// v0.41.31: stamp embedding provenance when this import actually
// embedded (not --no-embed), so a later model/dims swap is detectable
// as stale via embed --stale. The deferred/backfill + per-slug embed
@@ -1073,12 +1064,6 @@ export async function importCodeFile(
const title = `${relativePath} (${lang})`;
const sourceId = opts.sourceId;
const txOpts = sourceId ? { sourceId } : undefined;
// #1262: write-side embedding column descriptor (rides only on upsertChunks).
const chunkWriteColumn = await resolveWriteColumnForEngine(engine);
const chunkOpts: { sourceId?: string; embeddingColumn?: ResolvedColumn } | undefined =
(sourceId || chunkWriteColumn)
? { ...(sourceId && { sourceId }), ...(chunkWriteColumn && { embeddingColumn: chunkWriteColumn }) }
: undefined;
const byteLength = Buffer.byteLength(content, 'utf-8');
if (byteLength > MAX_FILE_SIZE) {
@@ -1198,7 +1183,7 @@ export async function importCodeFile(
await tx.addTag(slug, lang, txOpts);
if (chunks.length > 0) {
await tx.upsertChunks(slug, chunks, chunkOpts);
await tx.upsertChunks(slug, chunks, txOpts);
// v0.41.31: stamp embedding provenance ONLY when every chunk was
// freshly embedded with the current model this call (no reuse-by-hash
// carrying old-model vectors). Mixed pages stay unstamped rather than
@@ -1347,12 +1332,6 @@ export async function withImportTransaction(
): Promise<void> {
const sourceId = spec.sourceId ?? 'default';
const txOpts = spec.sourceId ? { sourceId: spec.sourceId } : undefined;
// #1262: write-side embedding column descriptor (rides only on upsertChunks).
const chunkWriteColumn = await resolveWriteColumnForEngine(engine);
const chunkOpts: { sourceId?: string; embeddingColumn?: ResolvedColumn } | undefined =
(spec.sourceId || chunkWriteColumn)
? { ...(spec.sourceId && { sourceId: spec.sourceId }), ...(chunkWriteColumn && { embeddingColumn: chunkWriteColumn }) }
: undefined;
await engine.transaction(async (tx) => {
if (spec.hadExisting) await tx.createVersion(spec.slug, txOpts);
await tx.putPage(spec.slug, spec.page, txOpts);
@@ -1368,7 +1347,7 @@ export async function withImportTransaction(
}
if (spec.chunks !== undefined) {
if (spec.chunks.length > 0) {
await tx.upsertChunks(spec.slug, spec.chunks, chunkOpts);
await tx.upsertChunks(spec.slug, spec.chunks, txOpts);
} else {
await tx.deleteChunks(spec.slug, txOpts);
}
@@ -35,7 +35,6 @@ import { tryAcquireDbLock } from '../../db-lock.ts';
import { BudgetTracker, BudgetExhausted } from '../../budget/budget-tracker.ts';
import { withBudgetTracker } from '../../ai/gateway.ts';
import { embedStaleForSource } from '../../embed-stale.ts';
import { resolveWriteColumnForEngine } from '../../search/embedding-column.ts';
import { currentEmbeddingSignature } from '../../embedding.ts';
import { type DbPacer, createDbPacer, createNoopPacer } from '../../db-pacer.ts';
import { resolvePaceMode, loadPaceModeConfig, readPaceEnv } from '../../pace-mode.ts';
@@ -165,16 +164,12 @@ export function makeEmbedBackfillHandler(engine: BrainEngine) {
// the supervisor, so pacing it is the headline win.
const { pacer, concurrency } = await resolveBackfillPacer(engine, job.data);
// #1262: resolve the write-side embedding column once at the job boundary.
const embeddingColumn = await resolveWriteColumnForEngine(engine);
try {
const result = await withBudgetTracker(tracker, async () =>
embedStaleForSource(engine, sourceId, {
batchSize,
signal: job.signal,
pacer,
...(embeddingColumn && { embeddingColumn }),
...(concurrency !== undefined && { concurrency }),
// v0.41.31: re-embed pages whose model signature drifted + stamp
// provenance as chunks land.
+22 -42
View File
@@ -40,7 +40,6 @@ import type {
BrainStats, BrainHealth,
IngestLogEntry, IngestLogInput,
EngineConfig,
ResolvedColumn,
EvalCandidate, EvalCandidateInput,
EvalCaptureFailure, EvalCaptureFailureReason,
SalienceOpts, SalienceResult, AnomaliesOpts, AnomalyResult,
@@ -2231,20 +2230,12 @@ export class PGLiteEngine implements BrainEngine {
}
// Chunks
async upsertChunks(slug: string, chunks: ChunkInput[], opts?: { sourceId?: string; embeddingColumn?: ResolvedColumn } & BatchOpts): Promise<void> {
async upsertChunks(slug: string, chunks: ChunkInput[], opts?: { sourceId?: string } & BatchOpts): Promise<void> {
return this.batchRetry(opts?.auditSite ?? 'upsertChunks', opts?.signal, () => this._upsertChunksOnce(slug, chunks, opts), chunks.length);
}
private async _upsertChunksOnce(slug: string, chunks: ChunkInput[], opts?: { sourceId?: string; embeddingColumn?: ResolvedColumn }): Promise<void> {
private async _upsertChunksOnce(slug: string, chunks: ChunkInput[], opts?: { sourceId?: string }): Promise<void> {
const sourceId = opts?.sourceId ?? 'default';
// #1262: caller-resolved write target for TEXT embeddings. Descriptor
// names are identifier-validated + quoted by buildVectorCastFragment;
// omitted => legacy `embedding vector`. Mirrors postgres-engine.ts.
const targetFragment = opts?.embeddingColumn
? buildVectorCastFragment(opts.embeddingColumn)
: undefined;
const targetCol = targetFragment?.col ?? 'embedding';
const embeddingCast = targetFragment?.castSql.replace('$1::', '') ?? 'vector';
// Source-scope the page-id lookup so duplicate slugs in different sources
// do not return multiple rows or target the wrong page.
@@ -2279,7 +2270,7 @@ export class PGLiteEngine implements BrainEngine {
// list. Image chunks pass embedding=null + embedding_image=Float32Array
// (1024-dim Voyage). Text/code chunks pass embedding=Float32Array +
// embedding_image=null. Default modality='text' when omitted.
const cols = `(page_id, chunk_index, chunk_text, chunk_source, ${targetCol}, model, token_count, embedded_at, language, symbol_name, symbol_type, start_line, end_line, parent_symbol_path, doc_comment, symbol_name_qualified, modality, embedding_image)`;
const cols = '(page_id, chunk_index, chunk_text, chunk_source, embedding, model, token_count, embedded_at, language, symbol_name, symbol_type, start_line, end_line, parent_symbol_path, doc_comment, symbol_name_qualified, modality, embedding_image)';
const rowParts: string[] = [];
const params: unknown[] = [];
let paramIdx = 1;
@@ -2297,7 +2288,7 @@ export class PGLiteEngine implements BrainEngine {
const modality = chunk.modality ?? 'text';
// Inline ::vector NULL literals to avoid a per-branch placeholder.
const embeddingPh = embeddingStr ? `$${paramIdx++}::${embeddingCast}` : 'NULL';
const embeddingPh = embeddingStr ? `$${paramIdx++}::vector` : 'NULL';
const embeddedAtPh = embeddingStr ? 'now()' : 'NULL';
const embeddingImagePh = embeddingImageStr ? `$${paramIdx++}::vector` : 'NULL';
@@ -2336,19 +2327,19 @@ export class PGLiteEngine implements BrainEngine {
ON CONFLICT (page_id, chunk_index) DO UPDATE SET
chunk_text = EXCLUDED.chunk_text,
chunk_source = EXCLUDED.chunk_source,
${targetCol} = CASE
WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.${targetCol}
WHEN content_chunks.${targetCol} IS NULL THEN EXCLUDED.${targetCol}
embedding = CASE
WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.embedding
WHEN content_chunks.embedding IS NULL THEN EXCLUDED.embedding
WHEN EXCLUDED.embedded_at IS NOT NULL
AND (content_chunks.embedded_at IS NULL OR EXCLUDED.embedded_at > content_chunks.embedded_at)
THEN EXCLUDED.${targetCol}
ELSE content_chunks.${targetCol}
THEN EXCLUDED.embedding
ELSE content_chunks.embedding
END,
model = COALESCE(EXCLUDED.model, content_chunks.model),
token_count = EXCLUDED.token_count,
embedded_at = CASE
WHEN EXCLUDED.chunk_text != content_chunks.chunk_text AND EXCLUDED.${targetCol} IS NULL THEN NULL
WHEN content_chunks.${targetCol} IS NULL AND EXCLUDED.${targetCol} IS NOT NULL THEN EXCLUDED.embedded_at
WHEN EXCLUDED.chunk_text != content_chunks.chunk_text AND EXCLUDED.embedding IS NULL THEN NULL
WHEN content_chunks.embedding IS NULL AND EXCLUDED.embedding IS NOT NULL THEN EXCLUDED.embedded_at
WHEN EXCLUDED.embedded_at IS NOT NULL
AND (content_chunks.embedded_at IS NULL OR EXCLUDED.embedded_at > content_chunks.embedded_at)
THEN EXCLUDED.embedded_at
@@ -2386,19 +2377,14 @@ export class PGLiteEngine implements BrainEngine {
* drift (NULL grandfathered never stale). Shared by countStaleChunks +
* sumStaleChunkChars so they can't drift.
*/
private buildStaleChunkWhere(opts?: { sourceId?: string; signature?: string; embeddingColumn?: ResolvedColumn }): { where: string; params: unknown[] } {
// #1262: staleness targets the caller-resolved write column when set
// (identifier-validated + quoted); legacy `embedding` otherwise.
const staleCol = opts?.embeddingColumn
? buildVectorCastFragment(opts.embeddingColumn).col
: 'embedding';
private buildStaleChunkWhere(opts?: { sourceId?: string; signature?: string }): { where: string; params: unknown[] } {
const params: unknown[] = [];
const conds: string[] = [];
if (opts?.signature !== undefined) {
params.push(opts.signature);
conds.push(`(cc.${staleCol} IS NULL OR (p.embedding_signature IS NOT NULL AND p.embedding_signature <> $${params.length}))`);
conds.push(`(cc.embedding IS NULL OR (p.embedding_signature IS NOT NULL AND p.embedding_signature <> $${params.length}))`);
} else {
conds.push(`cc.${staleCol} IS NULL`);
conds.push(`cc.embedding IS NULL`);
}
conds.push(`NOT (COALESCE(p.frontmatter, '{}'::jsonb) ? 'embed_skip')`);
if (opts?.sourceId !== undefined) {
@@ -2408,7 +2394,7 @@ export class PGLiteEngine implements BrainEngine {
return { where: conds.join(' AND '), params };
}
async countStaleChunks(opts?: { sourceId?: string; signature?: string; embeddingColumn?: ResolvedColumn }): Promise<number> {
async countStaleChunks(opts?: { sourceId?: string; signature?: string }): Promise<number> {
// D7: source-scoped count for `gbrain embed --stale --source X`. Always
// JOIN pages so embed-skip + signature predicates apply. PGLite is
// PostgreSQL 17.5 in WASM and supports the full JSONB operator set.
@@ -2424,7 +2410,7 @@ export class PGLiteEngine implements BrainEngine {
return Number(count);
}
async sumStaleChunkChars(opts?: { sourceId?: string; signature?: string; embeddingColumn?: ResolvedColumn }): Promise<number> {
async sumStaleChunkChars(opts?: { sourceId?: string; signature?: string }): Promise<number> {
// Sibling of countStaleChunks: same stale predicate, summing chunk_text
// length for the sync cost preview. ::bigint guards int4 overflow.
const { where, params } = this.buildStaleChunkWhere(opts);
@@ -2477,17 +2463,11 @@ export class PGLiteEngine implements BrainEngine {
sourceId?: string;
orderBy?: 'page_id' | 'updated_desc';
afterUpdatedAt?: string | null;
embeddingColumn?: ResolvedColumn;
}): Promise<StaleChunkRow[]> {
const limit = opts?.batchSize ?? 2000;
const afterPid = opts?.afterPageId ?? 0;
const afterIdx = opts?.afterChunkIndex ?? -1;
const orderBy = opts?.orderBy ?? 'page_id';
// #1262: staleness follows the caller-resolved write column (validated +
// quoted identifier); legacy `embedding` otherwise.
const staleCol = opts?.embeddingColumn
? buildVectorCastFragment(opts.embeddingColumn).col
: 'embedding';
// v0.41.18.0 (A13, codex #9): --priority recent path. See postgres-engine
// sibling for full rationale. Same composite cursor + ORDER BY.
@@ -2501,7 +2481,7 @@ export class PGLiteEngine implements BrainEngine {
p.updated_at
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE cc.${staleCol} IS NULL
WHERE cc.embedding IS NULL
AND NOT (COALESCE(p.frontmatter, '{}'::jsonb) ? 'embed_skip')
ORDER BY p.updated_at DESC NULLS LAST, p.id ASC, cc.chunk_index ASC
LIMIT $1`,
@@ -2512,7 +2492,7 @@ export class PGLiteEngine implements BrainEngine {
p.updated_at
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE cc.${staleCol} IS NULL
WHERE cc.embedding IS NULL
AND NOT (COALESCE(p.frontmatter, '{}'::jsonb) ? 'embed_skip')
AND (
p.updated_at < $1::timestamptz
@@ -2531,7 +2511,7 @@ export class PGLiteEngine implements BrainEngine {
p.updated_at
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE cc.${staleCol} IS NULL
WHERE cc.embedding IS NULL
AND p.source_id = $1
AND NOT (COALESCE(p.frontmatter, '{}'::jsonb) ? 'embed_skip')
ORDER BY p.updated_at DESC NULLS LAST, p.id ASC, cc.chunk_index ASC
@@ -2543,7 +2523,7 @@ export class PGLiteEngine implements BrainEngine {
p.updated_at
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE cc.${staleCol} IS NULL
WHERE cc.embedding IS NULL
AND p.source_id = $1
AND NOT (COALESCE(p.frontmatter, '{}'::jsonb) ? 'embed_skip')
AND (
@@ -2568,7 +2548,7 @@ export class PGLiteEngine implements BrainEngine {
cc.model, cc.token_count, p.source_id, cc.page_id
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE cc.${staleCol} IS NULL
WHERE cc.embedding IS NULL
AND NOT (COALESCE(p.frontmatter, '{}'::jsonb) ? 'embed_skip')
AND (cc.page_id, cc.chunk_index) > ($1, $2)
ORDER BY cc.page_id, cc.chunk_index
@@ -2582,7 +2562,7 @@ export class PGLiteEngine implements BrainEngine {
cc.model, cc.token_count, p.source_id, cc.page_id
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE cc.${staleCol} IS NULL
WHERE cc.embedding IS NULL
AND p.source_id = $1
AND NOT (COALESCE(p.frontmatter, '{}'::jsonb) ? 'embed_skip')
AND (cc.page_id, cc.chunk_index) > ($2, $3)
+22 -43
View File
@@ -50,7 +50,6 @@ import type {
BrainStats, BrainHealth,
IngestLogEntry, IngestLogInput,
EngineConfig,
ResolvedColumn,
EvalCandidate, EvalCandidateInput,
EvalCaptureFailure, EvalCaptureFailureReason,
SalienceOpts, SalienceResult, AnomaliesOpts, AnomalyResult,
@@ -2381,21 +2380,13 @@ export class PostgresEngine implements BrainEngine {
}
// Chunks
async upsertChunks(slug: string, chunks: ChunkInput[], opts?: { sourceId?: string; embeddingColumn?: ResolvedColumn } & BatchOpts): Promise<void> {
async upsertChunks(slug: string, chunks: ChunkInput[], opts?: { sourceId?: string } & BatchOpts): Promise<void> {
return this.batchRetry(opts?.auditSite ?? 'upsertChunks', opts?.signal, () => this._upsertChunksOnce(slug, chunks, opts), chunks.length);
}
private async _upsertChunksOnce(slug: string, chunks: ChunkInput[], opts?: { sourceId?: string; embeddingColumn?: ResolvedColumn }): Promise<void> {
private async _upsertChunksOnce(slug: string, chunks: ChunkInput[], opts?: { sourceId?: string }): Promise<void> {
const sql = this.sql;
const sourceId = opts?.sourceId ?? 'default';
// #1262: caller-resolved write target for TEXT embeddings. Descriptor
// names are identifier-validated + quoted by buildVectorCastFragment;
// omitted => legacy `embedding vector`.
const targetFragment = opts?.embeddingColumn
? buildVectorCastFragment(opts.embeddingColumn)
: undefined;
const targetCol = targetFragment?.col ?? 'embedding';
const embeddingCast = targetFragment?.castSql.replace('$1::', '') ?? 'vector';
// Source-scope the page-id lookup. Without this filter, multi-source
// brains where the slug exists in 2+ sources return >1 row and the
@@ -2422,7 +2413,7 @@ export class PostgresEngine implements BrainEngine {
// scope metadata through upserts.
// v0.27.1 (Phase 8): added `modality` + `embedding_image` to the column
// list. Image chunks pass embedding=null + embedding_image=Float32Array.
const cols = `(page_id, chunk_index, chunk_text, chunk_source, ${targetCol}, model, token_count, embedded_at, language, symbol_name, symbol_type, start_line, end_line, parent_symbol_path, doc_comment, symbol_name_qualified, modality, embedding_image)`;
const cols = '(page_id, chunk_index, chunk_text, chunk_source, embedding, model, token_count, embedded_at, language, symbol_name, symbol_type, start_line, end_line, parent_symbol_path, doc_comment, symbol_name_qualified, modality, embedding_image)';
const rows: string[] = [];
const params: unknown[] = [];
let paramIdx = 1;
@@ -2439,7 +2430,7 @@ export class PostgresEngine implements BrainEngine {
: null;
const modality = chunk.modality ?? 'text';
const embeddingPh = embeddingStr ? `$${paramIdx++}::${embeddingCast}` : 'NULL';
const embeddingPh = embeddingStr ? `$${paramIdx++}::vector` : 'NULL';
const embeddedAtPh = embeddingStr ? 'now()' : 'NULL';
const embeddingImagePh = embeddingImageStr ? `$${paramIdx++}::vector` : 'NULL';
@@ -2487,19 +2478,19 @@ export class PostgresEngine implements BrainEngine {
ON CONFLICT (page_id, chunk_index) DO UPDATE SET
chunk_text = EXCLUDED.chunk_text,
chunk_source = EXCLUDED.chunk_source,
${targetCol} = CASE
WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.${targetCol}
WHEN content_chunks.${targetCol} IS NULL THEN EXCLUDED.${targetCol}
embedding = CASE
WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.embedding
WHEN content_chunks.embedding IS NULL THEN EXCLUDED.embedding
WHEN EXCLUDED.embedded_at IS NOT NULL
AND (content_chunks.embedded_at IS NULL OR EXCLUDED.embedded_at > content_chunks.embedded_at)
THEN EXCLUDED.${targetCol}
ELSE content_chunks.${targetCol}
THEN EXCLUDED.embedding
ELSE content_chunks.embedding
END,
model = COALESCE(EXCLUDED.model, content_chunks.model),
token_count = EXCLUDED.token_count,
embedded_at = CASE
WHEN EXCLUDED.chunk_text != content_chunks.chunk_text AND EXCLUDED.${targetCol} IS NULL THEN NULL
WHEN content_chunks.${targetCol} IS NULL AND EXCLUDED.${targetCol} IS NOT NULL THEN EXCLUDED.embedded_at
WHEN EXCLUDED.chunk_text != content_chunks.chunk_text AND EXCLUDED.embedding IS NULL THEN NULL
WHEN content_chunks.embedding IS NULL AND EXCLUDED.embedding IS NOT NULL THEN EXCLUDED.embedded_at
WHEN EXCLUDED.embedded_at IS NOT NULL
AND (content_chunks.embedded_at IS NULL OR EXCLUDED.embedded_at > content_chunks.embedded_at)
THEN EXCLUDED.embedded_at
@@ -2539,19 +2530,14 @@ export class PostgresEngine implements BrainEngine {
* embedding_signature drift (NULL grandfathered). Shared by
* countStaleChunks + sumStaleChunkChars (parity with the PGLite sibling).
*/
private buildStaleChunkWhere(opts?: { sourceId?: string; signature?: string; embeddingColumn?: ResolvedColumn }): { where: string; params: unknown[] } {
// #1262: staleness targets the caller-resolved write column when set
// (identifier-validated + quoted); legacy `embedding` otherwise.
const staleCol = opts?.embeddingColumn
? buildVectorCastFragment(opts.embeddingColumn).col
: 'embedding';
private buildStaleChunkWhere(opts?: { sourceId?: string; signature?: string }): { where: string; params: unknown[] } {
const params: unknown[] = [];
const conds: string[] = [];
if (opts?.signature !== undefined) {
params.push(opts.signature);
conds.push(`(cc.${staleCol} IS NULL OR (p.embedding_signature IS NOT NULL AND p.embedding_signature <> $${params.length}))`);
conds.push(`(cc.embedding IS NULL OR (p.embedding_signature IS NOT NULL AND p.embedding_signature <> $${params.length}))`);
} else {
conds.push(`cc.${staleCol} IS NULL`);
conds.push(`cc.embedding IS NULL`);
}
conds.push(`NOT (COALESCE(p.frontmatter, '{}'::jsonb) ? 'embed_skip')`);
if (opts?.sourceId !== undefined) {
@@ -2561,7 +2547,7 @@ export class PostgresEngine implements BrainEngine {
return { where: conds.join(' AND '), params };
}
async countStaleChunks(opts?: { sourceId?: string; signature?: string; embeddingColumn?: ResolvedColumn }): Promise<number> {
async countStaleChunks(opts?: { sourceId?: string; signature?: string }): Promise<number> {
// Always JOIN pages so the embed_skip + signature predicates apply.
// D7: source_id scoping. v0.41.31: optional signature widens staleness
// to embedding_signature drift (NULL grandfathered).
@@ -2579,7 +2565,7 @@ export class PostgresEngine implements BrainEngine {
});
}
async sumStaleChunkChars(opts?: { sourceId?: string; signature?: string; embeddingColumn?: ResolvedColumn }): Promise<number> {
async sumStaleChunkChars(opts?: { sourceId?: string; signature?: string }): Promise<number> {
// Sibling of countStaleChunks: same stale predicate, summing chunk_text
// length for the sync cost preview. ::bigint guards int4 overflow.
const { where, params } = this.buildStaleChunkWhere(opts);
@@ -2632,18 +2618,11 @@ export class PostgresEngine implements BrainEngine {
sourceId?: string;
orderBy?: 'page_id' | 'updated_desc';
afterUpdatedAt?: string | null;
embeddingColumn?: ResolvedColumn;
}): Promise<StaleChunkRow[]> {
const limit = opts?.batchSize ?? 2000;
const afterPid = opts?.afterPageId ?? 0;
const afterIdx = opts?.afterChunkIndex ?? -1;
const orderBy = opts?.orderBy ?? 'page_id';
// #1262: staleness follows the caller-resolved write column (validated +
// quoted identifier); legacy `embedding` otherwise. Interpolated below as
// an unsafe FRAGMENT (identifiers can't be bound parameters).
const staleCol = opts?.embeddingColumn
? buildVectorCastFragment(opts.embeddingColumn).col
: 'embedding';
// RLS scope binding (opt-in via GBRAIN_RLS_SCOPE_BINDING).
return await this.withScopedReadTransaction(undefined, opts?.sourceId, async (tx) => {
@@ -2660,7 +2639,7 @@ export class PostgresEngine implements BrainEngine {
p.updated_at
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE ${tx.unsafe(`cc.${staleCol} IS NULL`)}
WHERE cc.embedding IS NULL
AND NOT (COALESCE(p.frontmatter, '{}'::jsonb) ? 'embed_skip')
ORDER BY p.updated_at DESC NULLS LAST, p.id ASC, cc.chunk_index ASC
LIMIT ${limit}
@@ -2670,7 +2649,7 @@ export class PostgresEngine implements BrainEngine {
p.updated_at
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE ${tx.unsafe(`cc.${staleCol} IS NULL`)}
WHERE cc.embedding IS NULL
AND NOT (COALESCE(p.frontmatter, '{}'::jsonb) ? 'embed_skip')
AND (
p.updated_at < ${afterUpdated}::timestamptz
@@ -2688,7 +2667,7 @@ export class PostgresEngine implements BrainEngine {
p.updated_at
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE ${tx.unsafe(`cc.${staleCol} IS NULL`)}
WHERE cc.embedding IS NULL
AND p.source_id = ${opts.sourceId}
AND NOT (COALESCE(p.frontmatter, '{}'::jsonb) ? 'embed_skip')
ORDER BY p.updated_at DESC NULLS LAST, p.id ASC, cc.chunk_index ASC
@@ -2699,7 +2678,7 @@ export class PostgresEngine implements BrainEngine {
p.updated_at
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE ${tx.unsafe(`cc.${staleCol} IS NULL`)}
WHERE cc.embedding IS NULL
AND p.source_id = ${opts.sourceId}
AND NOT (COALESCE(p.frontmatter, '{}'::jsonb) ? 'embed_skip')
AND (
@@ -2719,7 +2698,7 @@ export class PostgresEngine implements BrainEngine {
cc.model, cc.token_count, p.source_id, cc.page_id
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE ${tx.unsafe(`cc.${staleCol} IS NULL`)}
WHERE cc.embedding IS NULL
AND NOT (COALESCE(p.frontmatter, '{}'::jsonb) ? 'embed_skip')
AND (cc.page_id, cc.chunk_index) > (${afterPid}, ${afterIdx})
ORDER BY cc.page_id, cc.chunk_index
@@ -2732,7 +2711,7 @@ export class PostgresEngine implements BrainEngine {
cc.model, cc.token_count, p.source_id, cc.page_id
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE ${tx.unsafe(`cc.${staleCol} IS NULL`)}
WHERE cc.embedding IS NULL
AND p.source_id = ${opts.sourceId}
AND NOT (COALESCE(p.frontmatter, '{}'::jsonb) ? 'embed_skip')
AND (cc.page_id, cc.chunk_index) > (${afterPid}, ${afterIdx})
-74
View File
@@ -443,80 +443,6 @@ export function resolveEmbeddingColumn(
};
}
/**
* Resolves the WRITE-side embedding column for the currently configured
* embedding model (#1262). The read-side resolver above answers "which
* column does this query search?"; this one answers "which column should
* newly produced text embeddings land in?".
*
* Unlike read-side search, writes take no per-call column override. The
* import/embed boundary resolves once from merged config + gateway state
* and passes the descriptor into `engine.upsertChunks`; engines stay
* config-free (same contract as the read-side descriptor).
*
* Behavior:
* - no user-declared `embedding_columns` => undefined (legacy brain,
* writes keep targeting the default `embedding` column)
* - a user-declared entry whose `provider` matches the current
* embedding model => that entry's descriptor
* - no provider match => undefined (fall back to legacy `embedding`)
*
* Only USER-declared entries are consulted never the cfg-derived
* builtins. The `embedding_image` builtin's provider is the multimodal
* model; matching it here would misroute text embeddings into the image
* column. The no-match fallback is intentional: switching models before
* registering a matching column must not silently write vectors into an
* arbitrary column.
*/
export function resolveWriteColumn(cfg: GBrainConfig): ResolvedColumn | undefined {
const userColumns = cfg.embedding_columns;
if (
!userColumns ||
typeof userColumns !== 'object' ||
Array.isArray(userColumns) ||
Object.keys(userColumns).length === 0
) {
return undefined;
}
// Same model-resolution chain as the registry builtin: cfg > gateway > default.
let gwModel: string | undefined;
try {
const gw = require('../ai/gateway.ts') as typeof import('../ai/gateway.ts');
gwModel = gw.getEmbeddingModel();
} catch {
// Gateway unconfigured — fall through to the canonical default.
}
const currentModel = cfg.embedding_model ?? gwModel ?? DEFAULT_EMBEDDING_MODEL;
for (const [name, entry] of Object.entries(userColumns)) {
if (!entry) continue;
validateColumnKey(name);
validateColumnConfig(name, entry);
if (entry.provider !== currentModel) continue;
return {
name,
type: entry.type,
dimensions: entry.dimensions,
embeddingModel: entry.provider,
};
}
return undefined;
}
/**
* Engine-boundary convenience: merged config (file/env + DB plane)
* resolveWriteColumn. Dynamic import keeps config.ts out of this module's
* static graph (mirrors the gateway require above).
*/
export async function resolveWriteColumnForEngine(
engine: { getConfig(key: string): Promise<string | null | undefined> },
): Promise<ResolvedColumn | undefined> {
const { loadConfigWithEngine } = await import('../config.ts');
const cfg = await loadConfigWithEngine(engine);
return cfg ? resolveWriteColumn(cfg) : undefined;
}
/**
* True when the resolved column is the default `embedding` name.
* Name-based check; does not compare embedding space.
+44
View File
@@ -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/);
});
});
-133
View File
@@ -241,136 +241,3 @@ describe('buildVectorCastFragment — engine SQL composer (D3)', () => {
expect(castSql).toBe('$1::halfvec(2560)');
});
});
describe('PGLite engine: upsertChunks write-side ResolvedColumn descriptor (#1262)', () => {
test('halfvec descriptor writes the text embedding to the alternate column, not legacy embedding', async () => {
await engine.putPage('docs/write-alt-pglite', {
type: 'concept',
title: 'Write alt column PGLite',
compiled_truth: 'PGLite write-side alternate embedding column test.',
});
const descriptor: ResolvedColumn = {
name: 'embedding_ze',
type: 'halfvec',
dimensions: 2560,
embeddingModel: 'zeroentropyai:zembed-1',
};
await engine.upsertChunks('docs/write-alt-pglite', [
{
chunk_index: 0,
chunk_text: 'PGLite write-side alternate embedding column test.',
chunk_source: 'compiled_truth',
embedding: new Float32Array(2560).fill(0.25),
},
], { embeddingColumn: descriptor });
const rows = await engine.executeRaw<{
has_default: boolean;
has_ze: boolean;
has_embedded_at: boolean;
}>(
`SELECT embedding IS NOT NULL AS has_default,
embedding_ze IS NOT NULL AS has_ze,
embedded_at IS NOT NULL AS has_embedded_at
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE p.slug = 'docs/write-alt-pglite'`,
);
expect(rows.length).toBe(1);
expect(rows[0].has_default).toBe(false);
expect(rows[0].has_ze).toBe(true);
expect(rows[0].has_embedded_at).toBe(true);
});
test('text-unchanged re-upsert without a vector preserves the alternate-column embedding', async () => {
const descriptor: ResolvedColumn = {
name: 'embedding_ze',
type: 'halfvec',
dimensions: 2560,
embeddingModel: 'zeroentropyai:zembed-1',
};
// Same chunk_text, no embedding: the ON CONFLICT CASE must keep the
// existing alternate-column vector (D24 semantics follow the column).
await engine.upsertChunks('docs/write-alt-pglite', [
{
chunk_index: 0,
chunk_text: 'PGLite write-side alternate embedding column test.',
chunk_source: 'compiled_truth',
},
], { embeddingColumn: descriptor });
const rows = await engine.executeRaw<{ has_ze: boolean }>(
`SELECT embedding_ze IS NOT NULL AS has_ze
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE p.slug = 'docs/write-alt-pglite'`,
);
expect(rows).toEqual([{ has_ze: true }]);
});
});
describe('PGLite: embed --stale converges on an alt-column brain (#1262)', () => {
test('boundary resolves the write column; stale scan does not re-select embedded rows', async () => {
const { runEmbedCore } = await import('../../src/commands/embed.ts');
const local = new PGLiteEngine();
const previousHome = process.env.GBRAIN_HOME;
process.env.GBRAIN_HOME = `/tmp/gbrain-write-col-stale-${Date.now()}`;
try {
await local.connect({});
await local.initSchema();
await (local as any).db.exec(
`ALTER TABLE content_chunks ADD COLUMN IF NOT EXISTS embedding_ze halfvec(2560)`,
);
const descriptor: ResolvedColumn = {
name: 'embedding_ze',
type: 'halfvec',
dimensions: 2560,
embeddingModel: 'zeroentropyai:zembed-1',
};
await local.setConfig('embedding_columns', JSON.stringify({
embedding_ze: { provider: 'zeroentropyai:zembed-1', dimensions: 2560, type: 'halfvec' },
}));
configureGateway({
embedding_model: 'zeroentropyai:zembed-1',
embedding_dimensions: 2560,
env: {},
});
await local.putPage('docs/stale-alt-pglite', {
type: 'concept',
title: 'Dynamic stale column',
compiled_truth: 'A chunk that is embedded only in the dynamic column.',
});
await local.upsertChunks('docs/stale-alt-pglite', [
{
chunk_index: 0,
chunk_text: 'A chunk that is embedded only in the dynamic column.',
chunk_source: 'compiled_truth',
embedding: new Float32Array(2560).fill(0.25),
},
], { embeddingColumn: descriptor });
// Engine-level contrast: legacy predicate still sees the row as stale;
// the alt-column predicate does not.
expect(await local.countStaleChunks()).toBe(1);
expect(await local.countStaleChunks({ embeddingColumn: descriptor })).toBe(0);
// sumStaleChunkChars feeds the sync cost gate — same predicate contract.
expect(await local.sumStaleChunkChars()).toBeGreaterThan(0);
expect(await local.sumStaleChunkChars({ embeddingColumn: descriptor })).toBe(0);
expect(await local.listStaleChunks({ embeddingColumn: descriptor, batchSize: 100 })).toHaveLength(0);
expect(await local.listStaleChunks({ batchSize: 100 })).toHaveLength(1);
// Boundary-level: `embed --stale --dry-run` resolves the write column
// from merged config + gateway and reports NOTHING to embed. Without
// the fix this reports 1 (perpetual re-embed loop).
const result = await runEmbedCore(local, { stale: true, dryRun: true });
expect(result.would_embed).toBe(0);
} finally {
await local.disconnect();
if (previousHome === undefined) delete process.env.GBRAIN_HOME;
else process.env.GBRAIN_HOME = previousHome;
resetGateway();
}
});
});
@@ -224,54 +224,4 @@ if (!dbUrl) {
await engine.executeRaw(`UPDATE content_chunks SET embedding_voyage = '${v}'::vector WHERE id = ${dogId}`);
});
});
describe('Postgres: upsertChunks write-side ResolvedColumn descriptor (#1262)', () => {
const descriptor: ResolvedColumn = {
name: 'embedding_ze',
type: 'halfvec',
dimensions: 2560,
embeddingModel: 'zeroentropyai:zembed-1',
};
test('halfvec descriptor writes the text embedding to the alternate column, not legacy embedding', async () => {
await engine.putPage('docs/write-alt-postgres', {
type: 'concept',
title: 'Write alt column Postgres',
compiled_truth: 'Postgres write-side alternate embedding column test.',
});
await engine.upsertChunks('docs/write-alt-postgres', [
{
chunk_index: 0,
chunk_text: 'Postgres write-side alternate embedding column test.',
chunk_source: 'compiled_truth',
embedding: new Float32Array(2560).fill(0.25),
},
], { embeddingColumn: descriptor });
const rows = await engine.executeRaw<{
has_default: boolean;
has_ze: boolean;
}>(
`SELECT embedding IS NOT NULL AS has_default,
embedding_ze IS NOT NULL AS has_ze
FROM content_chunks cc
JOIN pages p ON p.id = cc.page_id
WHERE p.slug = 'docs/write-alt-postgres'`,
);
expect(rows.length).toBe(1);
expect(rows[0].has_default).toBe(false);
expect(rows[0].has_ze).toBe(true);
}, 30_000);
test('stale scan follows the write-side column (count + list parity with the write target)', async () => {
// Legacy predicate: cat/dog/write-alt rows all have embedding NULL.
expect(await engine.countStaleChunks()).toBeGreaterThan(0);
// Alt-column predicate: every chunk has embedding_ze populated.
expect(await engine.countStaleChunks({ embeddingColumn: descriptor })).toBe(0);
expect(await engine.listStaleChunks({ embeddingColumn: descriptor, batchSize: 100 })).toHaveLength(0);
expect((await engine.listStaleChunks({ batchSize: 100 })).length).toBeGreaterThan(0);
// updated_desc arm uses the same predicate.
expect(await engine.listStaleChunks({ embeddingColumn: descriptor, orderBy: 'updated_desc', batchSize: 100 })).toHaveLength(0);
}, 30_000);
});
}
+26
View File
@@ -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*\['authorization_code',\s*'refresh_token'\]/);
});
});
+24
View File
@@ -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();
+1 -110
View File
@@ -13,10 +13,9 @@
* throw on unknown string.
*/
import { describe, test, expect, afterAll, afterEach } from 'bun:test';
import { describe, test, expect } from 'bun:test';
import {
resolveEmbeddingColumn,
resolveWriteColumn,
getEmbeddingColumnRegistry,
buildVectorCastFragment,
quoteIdentifier,
@@ -35,28 +34,6 @@ import {
} from '../../src/core/search/embedding-column.ts';
import type { GBrainConfig } from '../../src/core/config.ts';
import type { ResolvedColumn } from '../../src/core/types.ts';
import { configureGateway, resetGateway } from '../../src/core/ai/gateway.ts';
/**
* Teardown: reset AND re-apply the legacy preload config
* (test/helpers/legacy-embedding-preload.ts). A bare resetGateway() would
* leave the slot empty for the NEXT file's beforeAll (the preload's
* per-test beforeEach only fires before tests, not before beforeAll), which
* would make sibling PGLite fixtures initSchema at the 1280 default instead
* of the legacy 1536 their seed vectors assume.
*/
function restorePreloadGateway() {
resetGateway();
configureGateway({
embedding_model: 'openai:text-embedding-3-large',
embedding_dimensions: 1536,
env: { ...process.env },
});
}
afterAll(() => {
restorePreloadGateway();
});
function cfg(overrides: Partial<GBrainConfig> = {}): GBrainConfig {
return { engine: 'pglite', ...overrides };
@@ -545,89 +522,3 @@ describe('codex /ship #4 — isCacheSafe (embedding-space-based skip)', () => {
expect(isCacheSafe(r, cfg())).toBe(true);
});
});
describe('resolveWriteColumn — write-side boundary resolution (#1262)', () => {
afterEach(() => {
restorePreloadGateway();
});
test('no registry / empty registry returns undefined (legacy single-column brain)', () => {
expect(resolveWriteColumn(cfg())).toBeUndefined();
expect(resolveWriteColumn(cfg({ embedding_columns: {} }))).toBeUndefined();
});
test('provider match via cfg.embedding_model returns the descriptor', () => {
const r = resolveWriteColumn(cfg({
embedding_model: 'voyage:voyage-3-large',
embedding_dimensions: 1024,
embedding_columns: {
embedding_voyage: { provider: 'voyage:voyage-3-large', dimensions: 1024, type: 'vector' },
},
}));
expect(r).toEqual({
name: 'embedding_voyage',
type: 'vector',
dimensions: 1024,
embeddingModel: 'voyage:voyage-3-large',
});
});
test('provider match via gateway state (cfg.embedding_model unset) returns descriptor', () => {
configureGateway({
embedding_model: 'zeroentropyai:zembed-1',
embedding_dimensions: 2560,
env: {},
});
const r = resolveWriteColumn(cfg({
embedding_columns: {
embedding_ze: { provider: 'zeroentropyai:zembed-1', dimensions: 2560, type: 'halfvec' },
},
}));
expect(r).toEqual({
name: 'embedding_ze',
type: 'halfvec',
dimensions: 2560,
embeddingModel: 'zeroentropyai:zembed-1',
});
});
test('no provider match returns undefined instead of guessing a column', () => {
configureGateway({
embedding_model: 'zeroentropyai:zembed-1',
embedding_dimensions: 2560,
env: {},
});
const r = resolveWriteColumn(cfg({
embedding_columns: {
embedding_voyage: { provider: 'voyage:voyage-3-large', dimensions: 1024, type: 'vector' },
},
}));
expect(r).toBeUndefined();
});
test('only USER-declared columns are consulted — multimodal builtin never captures text writes', () => {
// Current model equals the embedding_image BUILTIN's provider; a registry
// walk that consulted builtins would misroute text writes into the image
// column. resolveWriteColumn must return undefined here.
configureGateway({
embedding_model: 'voyage:voyage-multimodal-3',
embedding_dimensions: 1024,
env: {},
});
const r = resolveWriteColumn(cfg({
embedding_columns: {
embedding_other: { provider: 'openai:text-embedding-3-large', dimensions: 1536, type: 'vector' },
},
}));
expect(r).toBeUndefined();
});
test('malformed registry entry throws loud (same validation as the read side)', () => {
expect(() => resolveWriteColumn(cfg({
embedding_model: 'voyage:voyage-3-large',
embedding_columns: {
'bad"col': { provider: 'voyage:voyage-3-large', dimensions: 1024, type: 'vector' },
} as never,
}))).toThrow(EmbeddingColumnConfigError);
});
});