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
2026-08-17 02:12:40 +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
26 changed files with 569 additions and 612 deletions
@@ -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.`);
@@ -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`);
  }
@@ -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;
  }
@@ -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
@@ -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,
@@ -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
@@ -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;
 }

@@ -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
@@ -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.
@@ -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)
@@ -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})
@@ -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.
@@ -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
@@ -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);
-  });
 }
@@ -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);
+  });
+});
@@ -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);
+  });
+});
@@ -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);
-  });
-});