fix(embed): stop worker pool from dispatching new slices after a sub-batch failure

Review finding on #3130: when one sub-batch rejected, the surviving pool workers kept draining ALL remaining slices in the background after embedBatch had already rejected — real provider spend post-failure, onBatchComplete firing after the caller handled the error, and stacked 429 pressure when embedBatchWithBackoff retried while the failed run was still draining. A shared failed flag now stops further dispatch (in-flight sibling calls still settle, bounded by concurrency-1) and suppresses post-failure progress callbacks. Pinned by a new test: 10 slices / concurrency 2 / first call fails → no calls after rejection, no completions reported. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
test: fix CI red on #3130 — withEnv for batch-concurrency env + close resetGateway shard-order poison window
2026-08-14 17:02:19 +00:00 · 2026-07-22 11:52:30 -07:00 · 2026-07-22 11:08:07 -07:00 · 2026-07-21 14:39:33 -07:00
24 changed files with 563 additions and 365 deletions
@@ -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-CzLjRij_.js"></script>
+  <script type="module" crossorigin src="/admin/assets/index-CoGEje3-.js"></script>
  <link rel="stylesheet" crossorigin href="/admin/assets/index-GxkWX7v3.css">
 </head>
 <body>
@@ -39,7 +39,6 @@ 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 }) }),
@@ -23,16 +23,9 @@ 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;
@@ -95,7 +88,6 @@ 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>
@@ -116,9 +108,6 @@ 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>
@@ -268,29 +257,9 @@ 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' },
@@ -308,24 +277,11 @@ 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),
-          source_id: sourceId,
-          federated_read: federatedRead,
-          ...(uris.length > 0 ? { redirectUris: uris, grantTypes: ['authorization_code', 'refresh_token'] } : {}),
-        }),
+        body: JSON.stringify({ name: name.trim(), scopes: selectedScopes, tokenTtl: ttl === '0' ? 315360000 : Number(ttl) }),
      });
      if (!res.ok) throw new Error('Registration failed');
      const data = await res.json();
@@ -356,42 +312,6 @@ 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)}
@@ -608,8 +528,6 @@ 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),
  };

@@ -629,10 +547,6 @@ 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 2026-07-21.
+// Source: admin/dist/ at 2026-05-27.
 //
 // 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_CzLjRij__js from '../admin/dist/assets/index-CzLjRij_.js' with { type: 'file' };
+import A_0_assets_index_CoGEje3__js from '../admin/dist/assets/index-CoGEje3-.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-CzLjRij_.js": { path: A_0_assets_index_CzLjRij__js as unknown as string, mime: "application/javascript; charset=utf-8" },
+  "/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-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" },
 };
@@ -170,10 +170,14 @@ export async function runImport(
  // v0.22.13 (PR #490 Q2): shared parseWorkers helper rejects bad input
  // (--workers 0, -3, "foo") with a loud error instead of silently falling
  // through to 1. Mirrors sync.ts's flag handling.
-  const { parseWorkers } = await import('../core/sync-concurrency.ts');
-  let workerCount: number;
+  const { parseWorkers, autoConcurrency } = await import('../core/sync-concurrency.ts');
+  // #1207: undefined (no --workers flag) defers to autoConcurrency below —
+  // the shared sync/import policy (PGLite → 1, >100 files → 4) — instead of
+  // hardcoding serial. Large Postgres imports stop paying one embedding
+  // round-trip per file in sequence.
+  let workerCount: number | undefined;
  try {
-    workerCount = parseWorkers(workersArg ?? undefined) ?? 1;
+    workerCount = parseWorkers(workersArg ?? undefined);
  } catch (e) {
    console.error(e instanceof Error ? e.message : String(e));
    process.exit(1);
@@ -252,8 +256,9 @@ export async function runImport(
  }
  const files = resumeFilter(allFiles, dir, completed);

-  // Determine actual worker count
-  const actualWorkers = workerCount > 1 ? workerCount : 1;
+  // Determine actual worker count. Explicit --workers wins; otherwise the
+  // shared autoConcurrency policy decides from engine kind + file count.
+  const actualWorkers = autoConcurrency(engine, files.length, workerCount);
  if (actualWorkers > 1) {
    console.log(`Using ${actualWorkers} parallel workers`);
  }
@@ -39,7 +39,6 @@ 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,
@@ -1087,7 +1086,6 @@ 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,
@@ -1097,7 +1095,6 @@ 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,
@@ -1110,17 +1107,6 @@ 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.
@@ -1454,8 +1440,6 @@ 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 {
@@ -1486,23 +1470,8 @@ 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, sourceScope.sourceId, sourceScope.federatedRead, validatedAuthMethod,
+        name, grants, scopeString, uris, 'default', undefined, validatedAuthMethod,
      );
      // Set per-client TTL if specified
      if (tokenTtl && Number(tokenTtl) > 0) {
@@ -1,51 +0,0 @@
-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 };
-}
@@ -1513,12 +1513,21 @@ export async function embed(texts: string[], opts?: EmbedOpts): Promise<Float32A

  const embedding = recipe.touchpoints?.embedding;
  const maxBatchTokens = embedding?.max_batch_tokens;
+  const maxBatchCount = embedding?.max_batch_count;
  const charsPerToken = embedding?.chars_per_token ?? DEFAULT_CHARS_PER_TOKEN;

-  // Pre-split is gated on max_batch_tokens. Recipes without it (e.g. OpenAI)
-  // ride the fast path: one embedMany call, no recursion safety net.
-  const batches = maxBatchTokens
-    ? splitByTokenBudget(truncated, Math.floor(maxBatchTokens * effectiveSafetyFactor(recipe)), charsPerToken)
+  // Pre-split is gated on max_batch_tokens / max_batch_count. Recipes with
+  // neither (e.g. OpenAI) ride the fast path: one embedMany call, no
+  // recursion safety net.
+  const batches = (maxBatchTokens || maxBatchCount)
+    ? splitByTokenBudget(
+        truncated,
+        maxBatchTokens
+          ? Math.floor(maxBatchTokens * effectiveSafetyFactor(recipe))
+          : Number.MAX_SAFE_INTEGER,
+        charsPerToken,
+        maxBatchCount,
+      )
    : [truncated];

  const allEmbeddings: Float32Array[] = [];
@@ -1568,6 +1577,9 @@ export async function embed(texts: string[], opts?: EmbedOpts): Promise<Float32A
 *   responsible for applying any safety-factor shrink before passing in.
 * @param charsPerToken - Provider-specific character density. Defaults to
 *   `DEFAULT_CHARS_PER_TOKEN` (4) when omitted, matching OpenAI tiktoken.
+ * @param maxBatchCount - #1199: optional cap on INPUTS per sub-batch, for
+ *   providers that reject batches by count (DashScope: 10). When omitted,
+ *   only the token budget governs.
 *
 * @internal exported for tests; not part of the public gateway API.
 */
@@ -1575,15 +1587,17 @@ export function splitByTokenBudget(
  texts: string[],
  budgetTokens: number,
  charsPerToken: number = DEFAULT_CHARS_PER_TOKEN,
+  maxBatchCount?: number,
 ): string[][] {
  const ratio = charsPerToken > 0 ? charsPerToken : DEFAULT_CHARS_PER_TOKEN;
+  const maxCount = maxBatchCount !== undefined && maxBatchCount > 0 ? maxBatchCount : Infinity;
  const batches: string[][] = [];
  let current: string[] = [];
  let currentTokens = 0;

  for (const text of texts) {
    const estTokens = Math.ceil(text.length / ratio);
-    if (current.length > 0 && currentTokens + estTokens > budgetTokens) {
+    if (current.length > 0 && (currentTokens + estTokens > budgetTokens || current.length >= maxCount)) {
      batches.push(current);
      current = [];
      currentTokens = 0;
@@ -1609,7 +1623,11 @@ export function isTokenLimitError(err: unknown): boolean {
    /token.*limit.*exceeded/i.test(msg) ||
    // OpenAI embeddings: "Invalid 'input': maximum request size is 300000 tokens per request."
    /maximum request size.*tokens/i.test(msg) ||
-    /max.*tokens.*per.*request/i.test(msg)
+    /max.*tokens.*per.*request/i.test(msg) ||
+    // DashScope: "batch size is invalid, it should not be larger than 10." (#1199)
+    // Count-cap error, but recursive halving shrinks count too, so the same
+    // safety net converges.
+    /batch size is invalid/i.test(msg)
  );
 }

@@ -31,6 +31,10 @@ export const dashscope: Recipe = {
      // path. Conservative declaration so the gateway pre-splits before
      // hitting whatever undocumented server-side limit exists.
      max_batch_tokens: 8192,
+      // #1199: DashScope hard-caps embeddings at 10 inputs per request
+      // ("batch size is invalid, it should not be larger than 10"). The
+      // token budget alone admits far more than 10 short chunks per batch.
+      max_batch_count: 10,
      // text-embedding-v3 mixes English + CJK heavily; the tokenizer is
      // closer to Voyage density than OpenAI tiktoken for CJK-dominant
      // content. Conservative chars_per_token=2 leaves headroom.
@@ -16,6 +16,15 @@ export const google: Recipe = {
      dims_options: [768, 1536, 3072],
      cost_per_1m_tokens_usd: 0.15,
      price_last_verified: '2026-04-20',
+      // #970: Gemini's documented limits are per-INPUT (2048 tokens,
+      // silently truncated beyond) and per-REQUEST count (batchEmbedContents
+      // caps at 100 inputs). There is no separate per-request token cap, so
+      // the token budget is derived: 100 inputs × 2048 tokens. The count cap
+      // binds first for typical chunk sizes. Do NOT copy the 2048 per-input
+      // limit into max_batch_tokens — that would over-split 50×.
+      max_batch_tokens: 204_800,
+      chars_per_token: 4,
+      max_batch_count: 100,
    },
    expansion: {
      models: ['gemini-2.0-flash', 'gemini-2.0-flash-lite'],
@@ -58,5 +58,8 @@ export function getRecipe(id: string): Recipe | undefined {
 }

 export function listRecipes(): Recipe[] {
-  return [...ALL];
+  // Read the map (not ALL) so there is one source of truth — getRecipe,
+  // model-resolver, and listRecipes all see the same registry, and tests
+  // can inject a synthetic recipe via RECIPES to exercise registry walks.
+  return [...RECIPES.values()];
 }
@@ -46,6 +46,16 @@ export interface EmbeddingTouchpoint {
   * Only consulted when `max_batch_tokens` is also set.
   */
  chars_per_token?: number;
+  /**
+   * #1199: maximum number of INPUTS per embedding request, for providers
+   * that hard-cap batch size by count rather than (or in addition to)
+   * tokens — DashScope text-embedding-v3 rejects batches > 10 with
+   * `InvalidParameter`, Gemini batchEmbedContents caps at 100 requests.
+   * When set, the gateway's pre-split flushes a sub-batch at this count
+   * even if the token budget still has room. Independent of
+   * `max_batch_tokens`; either alone triggers the pre-split.
+   */
+  max_batch_count?: number;
  /**
   * Budget-utilization ceiling in (0, 1]. The gateway pre-splits at
   * `safety_factor × max_batch_tokens` to leave headroom for tokenizer
@@ -79,15 +79,34 @@ export interface EmbedBatchOptions {
   * and amplify rate-limit pressure.
   */
  maxRetries?: number;
+  /**
+   * #1818: bounded parallelism across BATCH_SIZE sub-batches. Defaults to
+   * `GBRAIN_EMBED_BATCH_CONCURRENCY` env, else 4. Results are
+   * index-addressed so output order always matches input order. Set 1 to
+   * force the pre-v0.42 serial dispatch.
+   */
+  concurrency?: number;
 }

 /**
 * Embed a batch of texts via the gateway. Sub-batches of 100 so upstream
 * progress callbacks fire incrementally on large imports. The gateway owns
 * adaptive batch splitting and per-recipe token-budget logic; this paginator
- * is purely about progress-callback granularity.
+ * owns progress-callback granularity and (#1818) bounded parallel dispatch
+ * of the sub-batches — the embed-stale.ts worker-pool pattern, scoped down.
 */
 const BATCH_SIZE = 100;
+const DEFAULT_EMBED_BATCH_CONCURRENCY = 4;
+
+function resolveEmbedBatchConcurrency(options: EmbedBatchOptions): number {
+  if (options.concurrency !== undefined) {
+    return Math.max(1, Math.floor(options.concurrency));
+  }
+  const env = Number(process.env.GBRAIN_EMBED_BATCH_CONCURRENCY);
+  if (Number.isFinite(env) && env >= 1) return Math.floor(env);
+  return DEFAULT_EMBED_BATCH_CONCURRENCY;
+}
+
 export async function embedBatch(
  texts: string[],
  options: EmbedBatchOptions = {},
@@ -103,13 +122,44 @@ export async function embedBatch(
  if (texts.length <= BATCH_SIZE && !options.onBatchComplete) {
    return gatewayEmbed(texts, gwOpts);
  }
-  const results: Float32Array[] = [];
+  // #1818: dispatch sub-batches through a bounded worker pool instead of a
+  // serial loop. Results are written into a preallocated index-addressed
+  // array so output order matches input order regardless of completion
+  // order; onBatchComplete reports a monotonic completed-embedding count.
+  const slices: Array<{ start: number; texts: string[] }> = [];
  for (let i = 0; i < texts.length; i += BATCH_SIZE) {
-    const slice = texts.slice(i, i + BATCH_SIZE);
-    const out = await gatewayEmbed(slice, gwOpts);
-    results.push(...out);
-    options.onBatchComplete?.(results.length, texts.length);
+    slices.push({ start: i, texts: texts.slice(i, i + BATCH_SIZE) });
  }
+  const results = new Array<Float32Array>(texts.length);
+  let next = 0;
+  let done = 0;
+  const numWorkers = Math.min(resolveEmbedBatchConcurrency(options), slices.length);
+  // Once any sub-batch fails, `failed` stops the surviving workers from
+  // dispatching FURTHER slices — the whole call is rejecting anyway, so
+  // continuing would burn real provider spend in the background and fire
+  // onBatchComplete after the caller already saw the failure (worst with
+  // embedBatchWithBackoff, whose 429 backoff assumes nothing is in flight).
+  // In-flight sibling calls still run to completion (bounded by numWorkers-1).
+  let failed = false;
+  const worker = async (): Promise<void> => {
+    while (!failed && next < slices.length) {
+      // NOTE: no local aborted-check here — an aborted signal makes the next
+      // gatewayEmbed call throw (SDK-side), which rejects the pool. Returning
+      // silently instead would resolve with holes in `results`.
+      const slice = slices[next++];
+      let out: Float32Array[];
+      try {
+        out = await gatewayEmbed(slice.texts, gwOpts);
+      } catch (err) {
+        failed = true;
+        throw err;
+      }
+      for (let j = 0; j < out.length; j++) results[slice.start + j] = out[j];
+      done += out.length;
+      if (!failed) options.onBatchComplete?.(done, texts.length);
+    }
+  };
+  await Promise.all(Array.from({ length: numWorkers }, () => worker()));
  return results;
 }

@@ -1,44 +0,0 @@
-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/);
-  });
-});
@@ -39,6 +39,8 @@ import {
  __getShrinkStateForTests,
 } from '../../src/core/ai/gateway.ts';
 import { AIConfigError, AITransientError } from '../../src/core/ai/errors.ts';
+import { RECIPES } from '../../src/core/ai/recipes/index.ts';
+import type { Recipe } from '../../src/core/ai/types.ts';

 // The last test in this file leaves the gateway configured with a remote
 // provider + fake key and a REAL embed transport. Without a final reset,
@@ -93,6 +95,14 @@ function configureGoogle(): void {
  });
 }

+function configureDashscope(): void {
+  configureGateway({
+    embedding_model: 'dashscope:text-embedding-v3',
+    embedding_dimensions: 1024,
+    env: { DASHSCOPE_API_KEY: 'sk-fake' },
+  });
+}
+
 // --------- 1. Pure helpers ---------

 describe('splitByTokenBudget (pure helper)', () => {
@@ -149,6 +159,27 @@ describe('splitByTokenBudget (pure helper)', () => {
    expect(splitByTokenBudget(texts, 96_000, 0)).toEqual(splitByTokenBudget(texts, 96_000, 4));
    expect(splitByTokenBudget(texts, 96_000, -1)).toEqual(splitByTokenBudget(texts, 96_000, 4));
  });
+
+  // #1199: count cap for providers that reject batches by input count.
+  test('max_batch_count flushes even when token budget has room', () => {
+    const texts = Array.from({ length: 25 }, (_, i) => `t${i}`);
+    const result = splitByTokenBudget(texts, 1_000_000, 4, 10);
+    expect(result.map(b => b.length)).toEqual([10, 10, 5]);
+    expect(result.flat()).toEqual(texts);
+  });
+
+  test('token budget still governs alongside max_batch_count', () => {
+    const texts = ['a'.repeat(50_000), 'b'.repeat(50_000), 'c'.repeat(50_000)];
+    const result = splitByTokenBudget(texts, 96_000, 1, 10);
+    expect(result).toHaveLength(3);
+  });
+
+  test('undefined / zero / negative max_batch_count is ignored', () => {
+    const texts = Array.from({ length: 25 }, () => 'x');
+    expect(splitByTokenBudget(texts, 1_000_000, 4, undefined)).toHaveLength(1);
+    expect(splitByTokenBudget(texts, 1_000_000, 4, 0)).toHaveLength(1);
+    expect(splitByTokenBudget(texts, 1_000_000, 4, -5)).toHaveLength(1);
+  });
 });

 describe('isTokenLimitError (pure helper)', () => {
@@ -179,6 +210,12 @@ describe('isTokenLimitError (pure helper)', () => {
    expect(isTokenLimitError(new Error('Exceeded 300000 max tokens per request'))).toBe(true);
  });

+  test('matches DashScope batch-count error (#1199)', () => {
+    expect(isTokenLimitError(new Error(
+      'InvalidParameter: batch size is invalid, it should not be larger than 10.',
+    ))).toBe(true);
+  });
+
  test('does not match unrelated errors', () => {
    expect(isTokenLimitError(new Error('Connection refused'))).toBe(false);
    expect(isTokenLimitError(new Error('Invalid API key'))).toBe(false);
@@ -387,26 +424,92 @@ describe('shrink-on-miss adaptive cache', () => {
  });
 });

+// --------- 8. Pre-split count cap through public embed() (#1199 / #970) ---------
+
+describe('embed() pre-split honors max_batch_count', () => {
+  beforeEach(() => resetGateway());
+  afterEach(() => __setEmbedTransportForTests(null));
+
+  test('dashscope never dispatches more than 10 inputs per call (#1199)', async () => {
+    configureDashscope();
+    const stub = mock(async ({ values }: { values: string[] }) => fakeEmbeddings(values, 1024));
+    __setEmbedTransportForTests(stub as any);
+
+    // 25 short texts fit trivially in the 8192-token budget; without the
+    // count cap they'd ship as ONE batch and DashScope would reject it.
+    const texts = Array.from({ length: 25 }, (_, i) => `short-${i}`);
+    const result = await embed(texts);
+
+    expect(result).toHaveLength(25);
+    const callLengths = stub.mock.calls.map(([arg]) => (arg as { values: string[] }).values.length);
+    expect(Math.max(...callLengths)).toBeLessThanOrEqual(10);
+    expect(callLengths.reduce((a, b) => a + b, 0)).toBe(25);
+    // Order preserved across sub-batches.
+    expect((stub.mock.calls[0][0] as { values: string[] }).values[0]).toBe('short-0');
+  });
+
+  test('google pre-splits at 100 inputs per batchEmbedContents call (#970)', async () => {
+    configureGoogle();
+    const stub = mock(async ({ values }: { values: string[] }) => fakeEmbeddings(values, 768));
+    __setEmbedTransportForTests(stub as any);
+
+    const texts = Array.from({ length: 250 }, (_, i) => `g${i}`);
+    const result = await embed(texts);
+
+    expect(result).toHaveLength(250);
+    const callLengths = stub.mock.calls.map(([arg]) => (arg as { values: string[] }).values.length);
+    expect(callLengths).toEqual([100, 100, 50]);
+  });
+});
+
 // --------- 7. Startup warning (D9-B) ---------

 describe('startup warning for recipes missing max_batch_tokens', () => {
  beforeEach(() => resetGateway());

+  // #970 closed google's missing cap, so no registered recipe is capless
+  // anymore. Inject a synthetic capless recipe to keep the warning path
+  // covered for the NEXT recipe that forgets the field.
+  const caplessRecipe: Recipe = {
+    id: 'capless-test',
+    name: 'Capless Test Provider',
+    tier: 'openai-compat',
+    implementation: 'openai-compatible',
+    base_url_default: 'https://example.invalid/v1',
+    auth_env: { required: [] },
+    touchpoints: {
+      embedding: { models: ['capless-embed-1'], default_dims: 768 },
+    },
+  };
+
+  function configureCapless(): void {
+    configureGateway({
+      embedding_model: 'capless-test:capless-embed-1',
+      embedding_dimensions: 768,
+      env: {},
+    });
+  }
+
  test('configured missing-cap recipe warns once; unrelated recipes stay quiet', () => {
    const warnings: string[] = [];
    const original = console.warn;
    console.warn = (msg: string) => warnings.push(String(msg));
+    RECIPES.set(caplessRecipe.id, caplessRecipe);
    try {
      configureOpenAI();
      expect(warnings.length).toBe(0);
+      // #970 regression: google now declares max_batch_tokens → quiet.
      configureGoogle();
+      expect(warnings.length).toBe(0);
+      configureCapless();
      const firstCallCount = warnings.length;
      // Reconfigure: the warning should NOT re-fire for the same recipes
      // within one process (we already told the operator).
-      configureGoogle();
+      configureCapless();
      expect(warnings.length).toBe(firstCallCount);
    } finally {
      console.warn = original;
+      RECIPES.delete(caplessRecipe.id);
    }

    // The warning text should match the documented contract.
@@ -415,11 +518,12 @@ describe('startup warning for recipes missing max_batch_tokens', () => {
    );
    expect(contractMatch.length).toBe(1);

-    // Voyage declares max_batch_tokens → suppressed. OpenAI is the
-    // canonical fast-path recipe → also suppressed by id. Both must be
-    // absent from the warnings.
+    // Voyage + google declare max_batch_tokens → suppressed. OpenAI is the
+    // canonical fast-path recipe → also suppressed by id. All must be
+    // absent from the warnings; only the synthetic capless recipe fires.
    expect(warnings.find(w => w.includes('"voyage"'))).toBeUndefined();
    expect(warnings.find(w => w.includes('"openai"'))).toBeUndefined();
-    expect(warnings.find(w => w.includes('"google"'))).toBeDefined();
+    expect(warnings.find(w => w.includes('"google"'))).toBeUndefined();
+    expect(warnings.find(w => w.includes('"capless-test"'))).toBeDefined();
  });
 });
@@ -52,16 +52,7 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
    }
  });

-  test('configureGateway warns for google only when google embedding is configured', () => {
-    warnSpy.mockClear();
-    resetGateway();
-    configureGateway({ env: {} });
-    let messages = warnSpy.mock.calls.map(c => String(c[0] ?? ''));
-    expect(
-      messages.some(m => m.includes('"google"') && m.includes('without max_batch_tokens')),
-      'google should not warn while OpenAI default is configured',
-    ).toBe(false);
-
+  test('configureGateway does NOT warn for google now that it declares batch caps (#970)', () => {
    warnSpy.mockClear();
    resetGateway();
    configureGateway({
@@ -69,11 +60,20 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
      embedding_dimensions: 768,
      env: { GOOGLE_GENERATIVE_AI_API_KEY: 'fake' },
    });
-    messages = warnSpy.mock.calls.map(c => String(c[0] ?? ''));
+    const messages = warnSpy.mock.calls.map(c => String(c[0] ?? ''));
    expect(
      messages.some(m => m.includes('"google"') && m.includes('without max_batch_tokens')),
-      'google should warn when configured because it has fixed-cap models',
-    ).toBe(true);
+      'google declares max_batch_tokens/max_batch_count since #970 — no warning',
+    ).toBe(false);
+  });
+
+  test('google recipe declares its derived batch caps (#970)', () => {
+    const e = getRecipe('google')!.touchpoints.embedding!;
+    // Count cap is the REAL Gemini limit (batchEmbedContents: 100 inputs);
+    // the token budget is derived (100 × 2048 per-input tokens), NOT the
+    // 2048 per-input limit — copying that verbatim would over-split 50×.
+    expect(e.max_batch_count).toBe(100);
+    expect(e.max_batch_tokens).toBe(204_800);
  });

  test('every recipe with empty models[] declares user_provided_models OR has openai-fast-path', () => {
@@ -55,6 +55,11 @@ describe('recipe: dashscope', () => {
    expect(r.touchpoints.embedding!.chars_per_token).toBeGreaterThan(0);
  });

+  test('declares max_batch_count: 10 — DashScope rejects larger batches (#1199)', () => {
+    const r = getRecipe('dashscope')!;
+    expect(r.touchpoints.embedding!.max_batch_count).toBe(10);
+  });
+
  test('dimsProviderOptions threads dimensions for text-embedding-v3 (Matryoshka)', async () => {
    // Codex finding #1: DashScope text-embedding-v3 is Matryoshka 64-1024.
    // Without `dimensions` on the wire, user-selected non-default dims are
@@ -0,0 +1,161 @@
+/**
+ * #1818: embedBatch dispatches its 100-input sub-batches through a bounded
+ * worker pool (the embed-stale.ts concurrency pattern) instead of a serial
+ * `for` loop. This file pins:
+ *
+ *   - output order matches input order regardless of completion order
+ *     (index-addressed results)
+ *   - parallelism actually happens (max in-flight > 1) and stays bounded
+ *     (max in-flight <= configured concurrency)
+ *   - concurrency: 1 restores the serial pre-#1818 dispatch
+ *   - GBRAIN_EMBED_BATCH_CONCURRENCY env is honored when the option is unset
+ *   - onBatchComplete reports a monotonic completed count ending at total
+ *
+ * Transport is stubbed via the gateway's __setEmbedTransportForTests seam
+ * (same pattern as test/ai/adaptive-embed-batch.test.ts). OpenAI recipe =
+ * fast path (no pre-split), so each embedBatch sub-batch is exactly one
+ * transport call.
+ */
+
+import { afterAll, afterEach, beforeEach, describe, expect, test } from 'bun:test';
+import {
+  configureGateway,
+  resetGateway,
+  __setEmbedTransportForTests,
+} from '../src/core/ai/gateway.ts';
+import { embedBatch } from '../src/core/embedding.ts';
+import { withEnv } from './helpers/with-env.ts';
+
+const DIMS = 1536;
+
+function configureOpenAI(): void {
+  configureGateway({
+    embedding_model: 'openai:text-embedding-3-large',
+    embedding_dimensions: DIMS,
+    env: { OPENAI_API_KEY: 'sk-fake' },
+  });
+}
+
+/**
+ * Install a transport whose returned embedding encodes the GLOBAL input
+ * index in dim 0 (texts are `t<N>`), so order can be asserted end-to-end.
+ * Tracks the max number of concurrently in-flight transport calls.
+ */
+function installTrackingTransport(delayMs = 5): { maxInFlight: () => number } {
+  let inFlight = 0;
+  let maxInFlight = 0;
+  __setEmbedTransportForTests((async ({ values }: { values: string[] }) => {
+    inFlight++;
+    maxInFlight = Math.max(maxInFlight, inFlight);
+    await new Promise(r => setTimeout(r, delayMs));
+    inFlight--;
+    return {
+      embeddings: values.map(v => {
+        const idx = Number(v.slice(1));
+        return Array.from({ length: DIMS }, (_, j) => (j === 0 ? idx : 0.1));
+      }),
+    };
+  }) as any);
+  return { maxInFlight: () => maxInFlight };
+}
+
+const texts = Array.from({ length: 250 }, (_, i) => `t${i}`);
+
+afterAll(() => resetGateway());
+
+describe('embedBatch bounded parallelism (#1818)', () => {
+  beforeEach(() => {
+    resetGateway();
+    configureOpenAI();
+  });
+  afterEach(() => {
+    __setEmbedTransportForTests(null);
+  });
+
+  test('default pool dispatches sub-batches in parallel, order preserved', async () => {
+    const tracker = installTrackingTransport();
+    const result = await embedBatch(texts, { onBatchComplete: () => {} });
+    expect(result).toHaveLength(250);
+    for (let i = 0; i < 250; i++) {
+      expect(result[i][0]).toBe(i);
+    }
+    // 250 texts → 3 sub-batches; default concurrency 4 → all 3 in flight.
+    expect(tracker.maxInFlight()).toBeGreaterThan(1);
+    expect(tracker.maxInFlight()).toBeLessThanOrEqual(4);
+  });
+
+  test('concurrency: 1 keeps the serial dispatch', async () => {
+    const tracker = installTrackingTransport();
+    const result = await embedBatch(texts, { concurrency: 1, onBatchComplete: () => {} });
+    expect(result).toHaveLength(250);
+    expect(tracker.maxInFlight()).toBe(1);
+  });
+
+  test('GBRAIN_EMBED_BATCH_CONCURRENCY env bounds the pool when option unset', async () => {
+    const tracker = installTrackingTransport();
+    await withEnv({ GBRAIN_EMBED_BATCH_CONCURRENCY: '2' }, async () => {
+      await embedBatch(texts, { onBatchComplete: () => {} });
+    });
+    expect(tracker.maxInFlight()).toBeGreaterThan(1);
+    expect(tracker.maxInFlight()).toBeLessThanOrEqual(2);
+  });
+
+  test('onBatchComplete reports a monotonic count ending at total', async () => {
+    installTrackingTransport();
+    const seen: number[] = [];
+    await embedBatch(texts, {
+      onBatchComplete: (done, total) => {
+        expect(total).toBe(250);
+        seen.push(done);
+      },
+    });
+    expect(seen).toHaveLength(3); // 100 + 100 + 50 sub-batches
+    for (let i = 1; i < seen.length; i++) {
+      expect(seen[i]).toBeGreaterThan(seen[i - 1]);
+    }
+    expect(seen[seen.length - 1]).toBe(250);
+  });
+
+  test('a failing sub-batch rejects the whole call', async () => {
+    let call = 0;
+    __setEmbedTransportForTests((async ({ values }: { values: string[] }) => {
+      call++;
+      if (call === 2) throw new Error('boom');
+      await new Promise(r => setTimeout(r, 2));
+      return { embeddings: values.map(() => Array.from({ length: DIMS }, () => 0.1)) };
+    }) as any);
+    await expect(embedBatch(texts, { onBatchComplete: () => {} })).rejects.toThrow();
+  });
+
+  test('after a failure, surviving workers stop dispatching new slices', async () => {
+    // 1000 texts → 10 slices, concurrency 2. First call fails immediately;
+    // without the `failed` flag the second worker would keep draining all
+    // 10 slices in the background AFTER embedBatch already rejected —
+    // burning provider spend and firing onBatchComplete post-rejection.
+    let calls = 0;
+    const completions: number[] = [];
+    __setEmbedTransportForTests((async ({ values }: { values: string[] }) => {
+      calls++;
+      if (calls === 1) throw new Error('boom');
+      await new Promise(r => setTimeout(r, 5));
+      return { embeddings: values.map(() => Array.from({ length: DIMS }, () => 0.1)) };
+    }) as any);
+    const many = Array.from({ length: 1000 }, (_, i) => `t${i}`);
+    await expect(
+      embedBatch(many, { concurrency: 2, onBatchComplete: d => completions.push(d) }),
+    ).rejects.toThrow('boom');
+    const callsAtRejection = calls;
+    await new Promise(r => setTimeout(r, 50)); // would-be background drain window
+    expect(calls).toBe(callsAtRejection); // no new dispatch after rejection
+    expect(calls).toBeLessThanOrEqual(2); // only the in-flight sibling ran
+    expect(completions).toHaveLength(0); // no progress reported after failure
+  });
+
+  test('single small batch without callback stays on the one-call fast path', async () => {
+    const tracker = installTrackingTransport(1);
+    const result = await embedBatch(['t0', 't1', 't2']);
+    expect(result).toHaveLength(3);
+    expect(result[1][0]).toBe(1);
+    expect(tracker.maxInFlight()).toBe(1);
+  });
+});
@@ -78,8 +78,6 @@ 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
@@ -89,7 +87,6 @@ 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
@@ -270,26 +267,3 @@ 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*\['authorization_code',\s*'refresh_token'\]/);
-  });
-});
@@ -19,7 +19,7 @@
 * overwrites this preload.
 */
 import { configureGateway, getEmbeddingDimensions } from '../../src/core/ai/gateway.ts';
-import { beforeEach } from 'bun:test';
+import { afterEach, beforeEach } from 'bun:test';

 const LEGACY_CONFIG = {
  embedding_model: 'openai:text-embedding-3-large',
@@ -52,7 +52,7 @@ applyLegacy();
 //   2. file-local beforeAll → may overwrite to ZE/1280
 // Since beforeAll runs once per file BEFORE the first beforeEach,
 // file-local beforeAll wins for that file's tests. ✓
-beforeEach(() => {
+function applyLegacyIfEmpty() {
  try {
    // Only re-apply if the gateway was reset (or never configured).
    // Tests that explicitly configured a different model in their
@@ -62,4 +62,28 @@ beforeEach(() => {
  } catch {
    applyLegacy();
  }
-});
+}
+
+beforeEach(applyLegacyIfEmpty);
+
+// PR #3130 shard-order fix: beforeEach alone leaves ONE window open — a file
+// whose LAST afterEach calls resetGateway() poisons the NEXT file's
+// beforeAll, which runs BEFORE any beforeEach fires. A beforeAll there that
+// does engine.initSchema() then sizes the embedding column from the gateway
+// DEFAULTS (zembed-1/1280d) instead of the pinned legacy 1536, and every
+// 1536-d Float32Array fixture in that file dies with
+// "expected 1280 dimensions, not 1536". Which file pair collides is a
+// function of shard composition, so adding/removing ANY test file can
+// surface it (that is exactly how it bit shard 9).
+//
+// Preload hooks are registered before any file-local hooks, and bun runs
+// after-hooks inside-out (file-local afterEach first, then this one), so
+// this repairs the empty slot immediately after the poisoning reset —
+// before the next file's beforeAll can observe it.
+//
+// Known remaining window: a file whose afterAll() resets the gateway (no
+// hook runs between its afterAll and the next file's beforeAll). Files
+// that reset in afterAll and can precede a schema-creating file should
+// re-apply their own config, or the victim file should configureGateway()
+// explicitly in its beforeAll.
+afterEach(applyLegacyIfEmpty);
@@ -0,0 +1,69 @@
+/**
+ * #1207: `gbrain import` without `--workers` used to hardcode workerCount=1,
+ * so a large Postgres import paid one serial embedding round-trip per file.
+ * runImport now routes the default through the shared autoConcurrency policy
+ * (PGLite → 1, >100 files on Postgres → DEFAULT_PARALLEL_WORKERS), while an
+ * explicit `--workers N` still wins.
+ *
+ * The engine here is a minimal postgres-kind stub with no database_url in
+ * config — runImport's parallel branch then falls back to serial processing
+ * (its PR #490 guard) but the WORKER-COUNT DECISION (the thing #1207 fixes)
+ * is still observable via the "Using N parallel workers" log line. Per-file
+ * imports fail against the stub engine and are swallowed by runImport's
+ * per-file catch; that's fine — this test pins the policy, not the import.
+ */
+
+import { afterEach, beforeEach, describe, expect, test } from 'bun:test';
+import { mkdtempSync, writeFileSync, mkdirSync, rmSync, realpathSync } from 'fs';
+import { tmpdir } from 'os';
+import { join } from 'path';
+import { withEnv } from './helpers/with-env.ts';
+import { runImport } from '../src/commands/import.ts';
+
+const fakePostgresEngine = {
+  kind: 'postgres',
+  executeRaw: async () => [],
+  logIngest: async () => {},
+  setConfig: async () => {},
+  getConfig: async () => null,
+} as any;
+
+let workspace: string;
+let brainDir: string;
+let logs: string[];
+const realLog = console.log;
+
+beforeEach(() => {
+  workspace = mkdtempSync(join(tmpdir(), 'gbrain-import-workers-home-'));
+  mkdirSync(join(workspace, '.gbrain'), { recursive: true });
+  brainDir = realpathSync(mkdtempSync(join(tmpdir(), 'gbrain-import-workers-brain-')));
+  // 101 files: one past AUTO_CONCURRENCY_FILE_THRESHOLD (100).
+  for (let i = 0; i < 101; i++) {
+    writeFileSync(join(brainDir, `page-${i}.md`), `# Page ${i}\n\nbody ${i}\n`);
+  }
+  logs = [];
+  console.log = (msg?: unknown) => logs.push(String(msg));
+});
+
+afterEach(() => {
+  console.log = realLog;
+  rmSync(workspace, { recursive: true, force: true });
+  rmSync(brainDir, { recursive: true, force: true });
+});
+
+describe('import default worker count (#1207)', () => {
+  test('no --workers flag → autoConcurrency picks 4 for >100 files on Postgres', async () => {
+    await withEnv({ GBRAIN_HOME: join(workspace, '.gbrain'), GBRAIN_SOURCE: undefined }, async () => {
+      await runImport(fakePostgresEngine, [brainDir, '--no-embed'], { sourceId: 'default' });
+    });
+    expect(logs.some(l => l.includes('Using 4 parallel workers'))).toBe(true);
+  });
+
+  test('explicit --workers 2 still wins over the auto policy', async () => {
+    await withEnv({ GBRAIN_HOME: join(workspace, '.gbrain'), GBRAIN_SOURCE: undefined }, async () => {
+      await runImport(fakePostgresEngine, [brainDir, '--no-embed', '--workers', '2'], { sourceId: 'default' });
+    });
+    expect(logs.some(l => l.includes('Using 2 parallel workers'))).toBe(true);
+    expect(logs.some(l => l.includes('Using 4 parallel workers'))).toBe(false);
+  });
+});
@@ -125,30 +125,6 @@ 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();