fix(embed): extend #1717 model labeling to the embed-backfill stale path

src/core/embed-stale.ts (used by the embed-backfill minion handler) built
its merged ChunkInput without a model field, so every chunk on a touched
page — re-embedded AND preserved — was relabeled to the engine default on
each backfill pass. Mirror the embed.ts semantics: stamp the resolved
gateway label on re-embedded chunks, carry the existing label on untouched
ones. Pinned by a PGLite test that fails without the fix.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

src/commands/embed.ts

@@ -1,5 +1,5 @@
 import type { BrainEngine } from '../core/engine.ts';
-import { embedBatch, currentEmbeddingSignature } from '../core/embedding.ts';
+import { embedBatch, currentEmbeddingSignature, resolveEmbeddingModelLabel } from '../core/embedding.ts';
 import type { ChunkInput } from '../core/types.ts';
 import { chunkText } from '../core/chunkers/recursive.ts';
 import { createProgress, type ProgressReporter } from '../core/progress.ts';
@@ -581,11 +581,16 @@ async function embedPage(
   for (let j = 0; j < toEmbed.length; j++) {
     embeddingMap.set(toEmbed[j].chunk_index, embeddings[j]);
   }
+  // #1717: label each (re)embedded chunk with the model that actually
+  // produced its vector. Preserved chunks (not re-embedded this pass) keep
+  // their existing model so a mixed-model page isn't relabeled wholesale.
+  const embedModelLabel = resolveEmbeddingModelLabel();
   const updated: ChunkInput[] = chunks.map(c => ({
     chunk_index: c.chunk_index,
     chunk_text: c.chunk_text,
     chunk_source: c.chunk_source,
     embedding: embeddingMap.get(c.chunk_index),
+    model: embeddingMap.has(c.chunk_index) && embedModelLabel ? embedModelLabel : c.model,
     token_count: c.token_count || Math.ceil(c.chunk_text.length / 4),
   }));
 
@@ -717,12 +722,16 @@ async function embedAll(
       for (let j = 0; j < toEmbed.length; j++) {
         embeddingMap.set(toEmbed[j].chunk_index, embeddings[j]);
       }
+      // #1717: stamp the resolved embedding model on (re)embedded chunks;
+      // preserve the existing model on chunks left untouched.
+      const embedModelLabel = resolveEmbeddingModelLabel();
       // Preserve ALL chunks, only update embeddings for stale ones
       const updated: ChunkInput[] = chunks.map(c => ({
         chunk_index: c.chunk_index,
         chunk_text: c.chunk_text,
         chunk_source: c.chunk_source,
         embedding: embeddingMap.get(c.chunk_index) ?? undefined,
+        model: embeddingMap.has(c.chunk_index) && embedModelLabel ? embedModelLabel : c.model,
         token_count: c.token_count || Math.ceil(c.chunk_text.length / 4),
       }));
       await observed(pacer, () => engine.upsertChunks(page.slug, updated, pageOpts));
@@ -1012,11 +1021,15 @@ async function embedAllStale(
           for (let j = 0; j < stale.length; j++) {
             staleIdxToEmbedding.set(stale[j].chunk_index, embeddings[j]);
           }
+          // #1717: label the re-embedded (stale) chunks with the resolved
+          // model; preserve the existing model on the non-stale chunks.
+          const embedModelLabel = resolveEmbeddingModelLabel();
           const merged: ChunkInput[] = existing.map(c => ({
             chunk_index: c.chunk_index,
             chunk_text: c.chunk_text,
             chunk_source: c.chunk_source,
             embedding: staleIdxToEmbedding.get(c.chunk_index) ?? undefined,
+            model: staleIdxToEmbedding.has(c.chunk_index) && embedModelLabel ? embedModelLabel : c.model,
             token_count: c.token_count || Math.ceil(c.chunk_text.length / 4),
           }));
           await observed(pacer, () => engine.upsertChunks(slug, merged, { sourceId: keySourceId }));

src/commands/import.ts

@@ -170,14 +170,10 @@ 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, 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;
+  const { parseWorkers } = await import('../core/sync-concurrency.ts');
+  let workerCount: number;
   try {
-    workerCount = parseWorkers(workersArg ?? undefined);
+    workerCount = parseWorkers(workersArg ?? undefined) ?? 1;
   } catch (e) {
     console.error(e instanceof Error ? e.message : String(e));
     process.exit(1);
@@ -256,9 +252,8 @@ export async function runImport(
   }
   const files = resumeFilter(allFiles, dir, completed);
 
-  // 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);
+  // Determine actual worker count
+  const actualWorkers = workerCount > 1 ? workerCount : 1;
   if (actualWorkers > 1) {
     console.log(`Using ${actualWorkers} parallel workers`);
   }

src/core/ai/gateway.ts

@@ -1513,21 +1513,12 @@ 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 / 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,
-      )
+  // 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)
     : [truncated];
 
   const allEmbeddings: Float32Array[] = [];
@@ -1577,9 +1568,6 @@ 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.
  */
@@ -1587,17 +1575,15 @@ 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 || current.length >= maxCount)) {
+    if (current.length > 0 && currentTokens + estTokens > budgetTokens) {
       batches.push(current);
       current = [];
       currentTokens = 0;
@@ -1623,11 +1609,7 @@ 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) ||
-    // 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)
+    /max.*tokens.*per.*request/i.test(msg)
   );
 }
 

src/core/ai/recipes/dashscope.ts

@@ -31,10 +31,6 @@ 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.

src/core/ai/recipes/google.ts

@@ -16,15 +16,6 @@ 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'],

src/core/ai/recipes/index.ts

@@ -58,8 +58,5 @@ export function getRecipe(id: string): Recipe | undefined {
 }
 
 export function listRecipes(): Recipe[] {
-  // 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()];
+  return [...ALL];
 }

src/core/ai/types.ts

@@ -46,16 +46,6 @@ 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

src/core/embed-stale.ts

@@ -20,6 +20,7 @@
 import type { BrainEngine } from './engine.ts';
 import type { ChunkInput } from './types.ts';
 import { embedBatchWithBackoff } from '../commands/embed.ts';
+import { resolveEmbeddingModelLabel } from './embedding.ts';
 import { type DbPacer, createNoopPacer, observed } from './db-pacer.ts';
 import { AbortError } from './abort-check.ts';
 
@@ -200,11 +201,17 @@ export async function embedStaleForSource(
         for (let j = 0; j < stale.length; j++) {
           staleIdxToEmbedding.set(stale[j].chunk_index, embeddings[j]);
         }
+        // #1717: label re-embedded chunks with the model that produced the
+        // vector; preserved chunks keep their existing model. Without this,
+        // upsertChunks falls back to DEFAULT_EMBEDDING_MODEL for every chunk
+        // (the same mislabel the embed.ts paths fixed).
+        const embedModelLabel = resolveEmbeddingModelLabel();
         const merged: ChunkInput[] = existing.map((c) => ({
           chunk_index: c.chunk_index,
           chunk_text: c.chunk_text,
           chunk_source: c.chunk_source,
           embedding: staleIdxToEmbedding.get(c.chunk_index) ?? undefined,
+          model: staleIdxToEmbedding.has(c.chunk_index) && embedModelLabel ? embedModelLabel : c.model,
           token_count: c.token_count || Math.ceil(c.chunk_text.length / 4),
           // Carry through per-chunk metadata. upsertChunks writes these as
           // EXCLUDED.<col> (not COALESCE), so omitting them here resets image

src/core/embedding.ts

@@ -79,34 +79,15 @@ 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
- * owns progress-callback granularity and (#1818) bounded parallel dispatch
- * of the sub-batches — the embed-stale.ts worker-pool pattern, scoped down.
+ * is purely about progress-callback granularity.
  */
 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 = {},
@@ -122,47 +103,31 @@ export async function embedBatch(
   if (texts.length <= BATCH_SIZE && !options.onBatchComplete) {
     return gatewayEmbed(texts, gwOpts);
   }
-  // #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[] }> = [];
+  const results: Float32Array[] = [];
   for (let i = 0; i < texts.length; i += BATCH_SIZE) {
-    slices.push({ start: i, texts: texts.slice(i, 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);
   }
-  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;
 }
 
+/**
+ * Resolve the embedding model label (`provider:model`) to stamp onto
+ * `content_chunks.model`, so each chunk records the model that actually
+ * produced its vector instead of the engine's hardcoded default (#1717).
+ * Returns undefined if the gateway is unconfigured; callers then fall back
+ * to the chunk's existing model rather than mislabeling it.
+ */
+export function resolveEmbeddingModelLabel(): string | undefined {
+  try {
+    return gatewayGetModel();
+  } catch {
+    return undefined;
+  }
+}
+
 /** Currently-configured embedding model (short form without provider prefix). */
 export function getEmbeddingModelName(): string {
   return gatewayGetModel().split(':').slice(1).join(':') || 'text-embedding-3-large';

src/core/import-file.ts

@@ -8,7 +8,7 @@ import { chunkText } from './chunkers/recursive.ts';
 import { chunkCodeText, chunkCodeTextFull, detectCodeLanguage, CHUNKER_VERSION } from './chunkers/code.ts';
 import { findChunkForOffset } from './chunkers/edge-extractor.ts';
 import { extractCodeRefs, imageOfCandidates } from './link-extraction.ts';
-import { embedBatch, embedMultimodal, currentEmbeddingSignature } from './embedding.ts';
+import { embedBatch, embedMultimodal, currentEmbeddingSignature, resolveEmbeddingModelLabel } from './embedding.ts';
 import { slugifyPath, slugifyCodePath, isCodeFilePath } from './sync.ts';
 import type { ChunkInput, PageInput, PageType } from './types.ts';
 import { computeEffectiveDate } from './effective-date.ts';
@@ -716,8 +716,12 @@ export async function importFromContent(
       ? chunks.map((c) => wrapChunkForEmbedding(c.chunk_text, prefix, c.chunk_source))
       : chunks.map((c) => c.chunk_text);
     const embeddings = await embedBatch(wrappedTexts);
+    // #1717: label each chunk with the model that actually produced its
+    // vector, not the engine's hardcoded default.
+    const embedModelLabel = resolveEmbeddingModelLabel();
     for (let i = 0; i < chunks.length; i++) {
       chunks[i].embedding = embeddings[i];
+      if (embedModelLabel) chunks[i].model = embedModelLabel;
       // token_count tracks the wrapped string length so cost reporting
       // reflects what we actually sent to the embedder.
       chunks[i].token_count = Math.ceil(wrappedTexts[i].length / 4);
@@ -1141,7 +1145,10 @@ export async function importCodeFile(
     const matched = existingByKey.get(key);
     if (matched && matched.embedding) {
       // Reuse the existing embedding verbatim. No API call, no cost.
+      // #1717: carry the existing model label along with the reused vector
+      // so the upsert doesn't relabel it with the engine default.
       chunks[i]!.embedding = matched.embedding as Float32Array;
+      chunks[i]!.model = matched.model ?? undefined;
       chunks[i]!.token_count = matched.token_count ?? undefined;
     } else {
       needsEmbedIndexes.push(i);
@@ -1153,9 +1160,12 @@ export async function importCodeFile(
     try {
       const textsToEmbed = needsEmbedIndexes.map((i) => chunks[i]!.chunk_text);
       const embeddings = await embedBatch(textsToEmbed);
+      // #1717: stamp the model that produced these vectors.
+      const embedModelLabel = resolveEmbeddingModelLabel();
       for (let j = 0; j < needsEmbedIndexes.length; j++) {
         const i = needsEmbedIndexes[j]!;
         chunks[i]!.embedding = embeddings[j]!;
+        if (embedModelLabel) chunks[i]!.model = embedModelLabel;
         chunks[i]!.token_count = Math.ceil(chunks[i]!.chunk_text.length / 4);
       }
     } catch (e: unknown) {

test/ai/adaptive-embed-batch.test.ts

@@ -39,8 +39,6 @@ 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,
@@ -95,14 +93,6 @@ 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)', () => {
@@ -159,27 +149,6 @@ 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)', () => {
@@ -210,12 +179,6 @@ 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);
@@ -424,92 +387,26 @@ 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).
-      configureCapless();
+      configureGoogle();
       expect(warnings.length).toBe(firstCallCount);
     } finally {
       console.warn = original;
-      RECIPES.delete(caplessRecipe.id);
     }
 
     // The warning text should match the documented contract.
@@ -518,12 +415,11 @@ describe('startup warning for recipes missing max_batch_tokens', () => {
     );
     expect(contractMatch.length).toBe(1);
 
-    // 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.
+    // Voyage declares max_batch_tokens → suppressed. OpenAI is the
+    // canonical fast-path recipe → also suppressed by id. Both must be
+    // absent from the warnings.
     expect(warnings.find(w => w.includes('"voyage"'))).toBeUndefined();
     expect(warnings.find(w => w.includes('"openai"'))).toBeUndefined();
-    expect(warnings.find(w => w.includes('"google"'))).toBeUndefined();
-    expect(warnings.find(w => w.includes('"capless-test"'))).toBeDefined();
+    expect(warnings.find(w => w.includes('"google"'))).toBeDefined();
   });
 });

test/ai/no-batch-cap-suppression.serial.test.ts

@@ -52,7 +52,16 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
     }
   });
 
-  test('configureGateway does NOT warn for google now that it declares batch caps (#970)', () => {
+  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);
+
     warnSpy.mockClear();
     resetGateway();
     configureGateway({
@@ -60,20 +69,11 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
       embedding_dimensions: 768,
       env: { GOOGLE_GENERATIVE_AI_API_KEY: 'fake' },
     });
-    const messages = warnSpy.mock.calls.map(c => String(c[0] ?? ''));
+    messages = warnSpy.mock.calls.map(c => String(c[0] ?? ''));
     expect(
       messages.some(m => m.includes('"google"') && m.includes('without max_batch_tokens')),
-      '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);
+      'google should warn when configured because it has fixed-cap models',
+    ).toBe(true);
   });
 
   test('every recipe with empty models[] declares user_provided_models OR has openai-fast-path', () => {

test/ai/recipe-dashscope.test.ts

@@ -55,11 +55,6 @@ 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

test/embed-batch-concurrency.test.ts

@@ -1,161 +0,0 @@
-/**
- * #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);
-  });
-});

test/embed-stale.serial.test.ts

@@ -15,6 +15,7 @@ import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:tes
 import { PGLiteEngine } from '../src/core/pglite-engine.ts';
 import { resetPgliteState } from './helpers/reset-pglite.ts';
 import { embedStaleForSource } from '../src/core/embed-stale.ts';
+import { configureGateway, resetGateway } from '../src/core/ai/gateway.ts';
 import type { ChunkInput } from '../src/core/types.ts';
 
 let engine: PGLiteEngine;
@@ -276,4 +277,49 @@ describe('embedStaleForSource', () => {
     // The stale text row actually got its embedding.
     expect(txtRow.embedded_at).not.toBeNull();
   });
+
+  // #1717: the backfill path must label re-embedded chunks with the model
+  // that produced the vector, and preserve the existing label on chunks it
+  // did not touch (before the fix, both were reset to the engine default).
+  test('labels re-embedded chunks with the gateway model, preserves untouched labels (#1717)', async () => {
+    configureGateway({
+      embedding_model: 'openai:text-embedding-3-large',
+      env: { OPENAI_API_KEY: 'sk-test-embed-stale-1717' },
+    });
+    try {
+      await engine.putPage('notes/model-label', {
+        type: 'note',
+        title: 'model-label',
+        compiled_truth: '# model-label\n\nseeded',
+      });
+      await engine.upsertChunks('notes/model-label', [
+        {
+          chunk_index: 0,
+          chunk_text: 'already embedded elsewhere',
+          chunk_source: 'compiled_truth',
+          embedding: new Float32Array(1536).fill(0.01),
+          model: 'voyage:voyage-3',
+          token_count: 4,
+        },
+        {
+          chunk_index: 1,
+          chunk_text: 'stale chunk needing embed',
+          chunk_source: 'compiled_truth',
+          token_count: 5,
+          embedding: undefined, // stale
+        },
+      ]);
+
+      const result = await embedStaleForSource(engine, 'default', { embedFn: fakeEmbedFn });
+      expect(result.embedded).toBe(1);
+
+      const after = await engine.getChunks('notes/model-label');
+      const preserved = after.find((c) => c.chunk_index === 0)!;
+      const reembedded = after.find((c) => c.chunk_index === 1)!;
+      expect(reembedded.model).toBe('openai:text-embedding-3-large');
+      expect(preserved.model).toBe('voyage:voyage-3');
+    } finally {
+      resetGateway();
+    }
+  });
 });

test/embed.serial.test.ts

@@ -37,6 +37,8 @@ mock.module('../src/core/embedding.ts', () => ({
   // setPageEmbeddingSignature / invalidateStaleSignatureEmbeddings resolve to
   // null via the Proxy default, so the signature value is inert here.
   currentEmbeddingSignature: () => 'test:model:1536',
+  // #1717: embed paths stamp this label on (re)embedded chunks.
+  resolveEmbeddingModelLabel: () => 'openai:text-embedding-3-large',
 }));
 
 // Import AFTER mocking.
@@ -803,3 +805,34 @@ describe('embedAllStale --source threading (D7)', () => {
     expect((firstCallOpts as { sourceId?: string }).sourceId).toBe('media-corpus');
   });
 });
+
+// #1717: content_chunks.model must record the model that actually produced
+// each vector, not the gateway/engine default.
+describe('content_chunks.model labeling (#1717)', () => {
+  test('stamps the resolved embedding model on re-embedded chunks, preserves it on untouched chunks', async () => {
+    let upserted: any[] | undefined;
+    // Chunk 0 is stale (no embedded_at) → gets re-embedded this pass.
+    // Chunk 1 is already embedded with a DIFFERENT model → must be preserved,
+    // not relabeled to the current model.
+    const chunks = [
+      { chunk_index: 0, chunk_text: 'a', chunk_source: 'compiled_truth', embedded_at: null, model: 'zeroentropyai:zembed-1', token_count: 1 },
+      { chunk_index: 1, chunk_text: 'b', chunk_source: 'compiled_truth', embedded_at: '2026-01-01', embedding: new Float32Array(1536), model: 'voyage:voyage-3', token_count: 1 },
+    ];
+    const engine = mockEngine({
+      getPage: async () => ({ slug: 'notes/x', compiled_truth: 'a', timeline: '', source_id: 'default' }),
+      getChunks: async () => chunks,
+      upsertChunks: async (_slug: string, c: any[]) => { upserted = c; },
+      setPageEmbeddingSignature: async () => null,
+    });
+
+    await runEmbedCore(engine, { slugs: ['notes/x'] });
+
+    expect(upserted).toBeDefined();
+    const byIdx = Object.fromEntries(upserted!.map(c => [c.chunk_index, c]));
+    // Re-embedded chunk carries the model that produced its vector (was
+    // mislabeled with the default before the fix).
+    expect(byIdx[0].model).toBe('openai:text-embedding-3-large');
+    // Untouched chunk keeps its original model — no wholesale relabel.
+    expect(byIdx[1].model).toBe('voyage:voyage-3');
+  });
+});

test/helpers/legacy-embedding-preload.ts

@@ -19,7 +19,7 @@
  * overwrites this preload.
  */
 import { configureGateway, getEmbeddingDimensions } from '../../src/core/ai/gateway.ts';
-import { afterEach, beforeEach } from 'bun:test';
+import { 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. ✓
-function applyLegacyIfEmpty() {
+beforeEach(() => {
   try {
     // Only re-apply if the gateway was reset (or never configured).
     // Tests that explicitly configured a different model in their
@@ -62,28 +62,4 @@ function applyLegacyIfEmpty() {
   } 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);
+});

test/import-default-workers.test.ts

@@ -1,69 +0,0 @@
-/**
- * #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);
-  });
-});

test/import-signature-stamp.serial.test.ts

@@ -73,4 +73,21 @@ describe('importFromContent embedding_signature stamping (F1)', () => {
     await importFromContent(engine, 'concepts/unstamped', '# Unstamped\n\nbody content.', { noEmbed: true });
     expect(await signatureOf('concepts/unstamped')).toBeNull();
   });
+
+  // #1717: content_chunks.model must record the model that produced the
+  // vector (the configured gateway model), not the engine's hardcoded
+  // default. The gateway here is configured to openai:text-embedding-3-large,
+  // which differs from DEFAULT_EMBEDDING_MODEL — so this fails without the
+  // import-path model stamping.
+  test('inline embed labels content_chunks.model with the configured model (#1717)', async () => {
+    await importFromContent(engine, 'concepts/labeled', '# Labeled\n\nsome body content to chunk and embed.', {});
+    const rows = await engine.executeRaw<{ model: string }>(
+      `SELECT cc.model FROM content_chunks cc
+        JOIN pages p ON p.id = cc.page_id
+       WHERE p.slug = $1 AND p.source_id = 'default'`,
+      ['concepts/labeled'],
+    );
+    expect(rows.length).toBeGreaterThan(0);
+    for (const r of rows) expect(r.model).toBe('openai:text-embedding-3-large');
+  });
 });