fix(gateway): fall back to the pooler when the derived direct host is unreachable (#1641)

deriveDirectUrl() swaps the Supabase pooler host to db.<ref>.supabase.co:5432,
which is IPv6-only without the paid IPv4 add-on. On IPv4-only networks the
direct pool could never connect, and initDirectPool()'s throw killed
'gbrain init --url' and migrations with ENOTFOUND/ECONNREFUSED.

getDirectPool() now classifies network-unreachable errors (ENOTFOUND,
ECONNREFUSED, ENETUNREACH, EHOSTUNREACH, ETIMEDOUT, CONNECT_TIMEOUT) via the
new isNetworkUnreachableError(), self-activates the kill-switch, logs one
stderr line pointing at GBRAIN_DIRECT_DATABASE_URL / GBRAIN_DISABLE_DIRECT_POOL,
and returns the read pool. Auth/SQL errors still throw (misconfig, not
unreachability). The failed pool is ended via endPoolBounded so it can't
leak sockets into the now-continuing process.

Also surfaces the kill-switch + override envs in the init.ts IPv6 warnings
and docs/guides/live-sync.md (they were previously undocumented outside
connection-manager.ts).

Fixes #1641

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

docs/guides/live-sync.md

@@ -21,14 +21,17 @@ GBrain is tuned for the Supabase **Transaction pooler** (port 6543): it
 auto-disables prepared statements there and routes `engine.transaction()`
 (migrations, DDL, sync imports) to a derived **direct** connection
 (`db.<ref>.supabase.co:5432`). That direct host is IPv6-only, so on an
-IPv4-only host, reads work but sync **silently skips most pages**. This is the
-number one cause of "sync ran but nothing happened."
+IPv4-only host it is unreachable. When that happens gbrain now falls back to
+the pooler automatically (one stderr warning, then single-pool mode for the
+rest of the process) — but the pooler's ~2-min statement timeout can truncate
+very long migrations or bulk imports.
 
 Fix: make the direct connection reachable over IPv4. Either set
 `GBRAIN_DIRECT_DATABASE_URL` to the **Session pooler** string (port 5432 on the
-`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on. Verify by
-running `gbrain sync` and checking that the page count in `gbrain stats` matches
-the syncable file count in the repo.
+`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on.
+`GBRAIN_DISABLE_DIRECT_POOL=1` skips the direct pool (and the fallback warning)
+entirely. Verify by running `gbrain sync` and checking that the page count in
+`gbrain stats` matches the syncable file count in the repo.
 
 ### The Primitives
 

llms-full.txt

@@ -2720,14 +2720,17 @@ GBrain is tuned for the Supabase **Transaction pooler** (port 6543): it
 auto-disables prepared statements there and routes `engine.transaction()`
 (migrations, DDL, sync imports) to a derived **direct** connection
 (`db.<ref>.supabase.co:5432`). That direct host is IPv6-only, so on an
-IPv4-only host, reads work but sync **silently skips most pages**. This is the
-number one cause of "sync ran but nothing happened."
+IPv4-only host it is unreachable. When that happens gbrain now falls back to
+the pooler automatically (one stderr warning, then single-pool mode for the
+rest of the process) — but the pooler's ~2-min statement timeout can truncate
+very long migrations or bulk imports.
 
 Fix: make the direct connection reachable over IPv4. Either set
 `GBRAIN_DIRECT_DATABASE_URL` to the **Session pooler** string (port 5432 on the
-`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on. Verify by
-running `gbrain sync` and checking that the page count in `gbrain stats` matches
-the syncable file count in the repo.
+`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on.
+`GBRAIN_DISABLE_DIRECT_POOL=1` skips the direct pool (and the fallback warning)
+entirely. Verify by running `gbrain sync` and checking that the page count in
+`gbrain stats` matches the syncable file count in the repo.
 
 ### The Primitives
 

src/commands/embed.ts

@@ -1,5 +1,5 @@
 import type { BrainEngine } from '../core/engine.ts';
-import { embedBatch, currentEmbeddingSignature, resolveEmbeddingModelLabel } from '../core/embedding.ts';
+import { embedBatch, currentEmbeddingSignature } 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';
@@ -581,16 +581,11 @@ 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),
   }));
 
@@ -722,16 +717,12 @@ 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));
@@ -1021,15 +1012,11 @@ 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/init.ts

@@ -1078,6 +1078,9 @@ async function initPostgres(opts: {
     console.warn('  Direct connections are IPv6 only and fail in many environments.');
     console.warn('  Use the Transaction pooler connection string instead (port 6543):');
     console.warn('  Supabase Dashboard > Connect (top bar) > Connection String > Transaction pooler');
+    console.warn('  (With a pooler URL, gbrain derives a direct connection for DDL and falls back');
+    console.warn('  to the pooler automatically if that host is unreachable. Power users:');
+    console.warn('  GBRAIN_DIRECT_DATABASE_URL overrides the derived URL; GBRAIN_DISABLE_DIRECT_POOL=1 disables it.)');
     console.warn('');
   }
 
@@ -1091,6 +1094,9 @@ async function initPostgres(opts: {
       if (databaseUrl.includes('supabase.co') && (msg.includes('ECONNREFUSED') || msg.includes('ETIMEDOUT'))) {
         console.error('Connection failed. Supabase direct connections (db.*.supabase.co:5432) are IPv6 only.');
         console.error('Use the Transaction pooler connection string instead (port 6543).');
+        console.error('(gbrain derives its own direct connection from pooler URLs for DDL; if that host is');
+        console.error('unreachable it falls back to the pooler. GBRAIN_DIRECT_DATABASE_URL overrides the');
+        console.error('derived URL; GBRAIN_DISABLE_DIRECT_POOL=1 disables the direct pool entirely.)');
       }
       throw e;
     }

src/core/connection-manager.ts

@@ -167,6 +167,25 @@ export function deriveDirectUrl(url: string): string | null {
   }
 }
 
+/**
+ * Error codes that mean "the direct host is unreachable from this network"
+ * (#1641). The auto-derived db.<ref>.supabase.co host is IPv6-only without
+ * the paid IPv4 add-on, so ENOTFOUND/ECONNREFUSED here is expected on
+ * IPv4-only networks — we fall back to the pooler instead of failing init.
+ */
+const NETWORK_UNREACHABLE_CODES = [
+  'ENOTFOUND', 'ECONNREFUSED', 'ENETUNREACH', 'EHOSTUNREACH',
+  'ETIMEDOUT', 'CONNECT_TIMEOUT',
+];
+
+/** True when err looks like a network-unreachable failure (not auth/SQL). */
+export function isNetworkUnreachableError(err: unknown): boolean {
+  const code = (err as { code?: unknown } | null)?.code;
+  if (typeof code === 'string' && NETWORK_UNREACHABLE_CODES.includes(code)) return true;
+  const msg = err instanceof Error ? err.message : String(err);
+  return NETWORK_UNREACHABLE_CODES.some(c => msg.includes(c));
+}
+
 /**
  * Read kill-switch state from env. Subordinate to parent manager's state
  * when present (A2 inheritance).
@@ -319,7 +338,30 @@ export class ConnectionManager {
         throw err;
       });
     }
-    const pool = await this._directInit;
+    let pool: Sql | null;
+    try {
+      pool = await this._directInit;
+    } catch (err) {
+      // #1641: the derived direct host (db.<ref>.supabase.co) is IPv6-only
+      // without Supabase's IPv4 add-on. On IPv4-only networks the direct
+      // pool can never connect — permanently fall back to the read pool
+      // (self-activating kill-switch) instead of failing init/migrations.
+      // Non-network errors (auth, SQL) still throw: they mean misconfig,
+      // not unreachability.
+      if (isNetworkUnreachableError(err)) {
+        const alreadyWarned = this._killSwitch;
+        this._killSwitch = true;
+        const msg = err instanceof Error ? err.message : String(err);
+        if (!alreadyWarned) console.error(
+          `gbrain: direct connection to ${this._directUrl ? this.hostOnly(this._directUrl) : 'unknown host'} unreachable (${msg}); ` +
+          'falling back to the pooler for DDL/bulk (long migrations may hit the pooler statement timeout). ' +
+          'Set GBRAIN_DIRECT_DATABASE_URL to a reachable direct URL (e.g. the Session pooler, port 5432) or enable the Supabase IPv4 add-on; ' +
+          'GBRAIN_DISABLE_DIRECT_POOL=1 silences this.',
+        );
+        return this.getReadPool();
+      }
+      throw err;
+    }
     if (!pool) {
       // Defensive — initDirectPool should have thrown.
       throw new Error('connection-manager: direct pool init returned null');
@@ -350,8 +392,9 @@ export class ConnectionManager {
       },
     };
     const t0 = Date.now();
+    let pool: Sql | null = null;
     try {
-      const pool = postgres(this._directUrl, opts);
+      pool = postgres(this._directUrl, opts);
       // Probe to validate connectivity early.
       await pool`SELECT 1`;
       logConnectionEvent({
@@ -362,6 +405,9 @@ export class ConnectionManager {
       });
       return pool;
     } catch (err) {
+      // Don't leak the failed pool's sockets/timers (#1641 fallback keeps
+      // the process running afterward).
+      if (pool) await endPoolBounded(pool);
       logConnectionEvent({
         pool: 'ddl',
         op: 'error',

src/core/embed-stale.ts

@@ -20,7 +20,6 @@
 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';
 
@@ -201,17 +200,11 @@ 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

@@ -113,21 +113,6 @@ export async function embedBatch(
   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, resolveEmbeddingModelLabel } from './embedding.ts';
+import { embedBatch, embedMultimodal, currentEmbeddingSignature } from './embedding.ts';
 import { slugifyPath, slugifyCodePath, isCodeFilePath } from './sync.ts';
 import type { ChunkInput, PageInput, PageType } from './types.ts';
 import { computeEffectiveDate } from './effective-date.ts';
@@ -716,12 +716,8 @@ 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);
@@ -1145,10 +1141,7 @@ 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);
@@ -1160,12 +1153,9 @@ 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/connection-manager.serial.test.ts

@@ -3,6 +3,7 @@ import {
   isSupabasePoolerUrl,
   deriveDirectUrl,
   readKillSwitchEnv,
+  isNetworkUnreachableError,
   resolveDirectPoolSize,
   ConnectionManager,
   DEFAULT_DIRECT_POOL_SIZE,
@@ -238,3 +239,65 @@ describe('ConnectionManager — parent inheritance (A2)', () => {
     }
   });
 });
+
+describe('isNetworkUnreachableError (#1641)', () => {
+  test('classifies network codes as unreachable', () => {
+    for (const code of ['ENOTFOUND', 'ECONNREFUSED', 'ENETUNREACH', 'EHOSTUNREACH', 'ETIMEDOUT', 'CONNECT_TIMEOUT']) {
+      const err = Object.assign(new Error('connect failed'), { code });
+      expect(isNetworkUnreachableError(err)).toBe(true);
+    }
+  });
+
+  test('classifies by message when code absent', () => {
+    expect(isNetworkUnreachableError(new Error('getaddrinfo ENOTFOUND db.abc.supabase.co'))).toBe(true);
+  });
+
+  test('auth/SQL errors are NOT unreachable', () => {
+    expect(isNetworkUnreachableError(new Error('password authentication failed for user "postgres"'))).toBe(false);
+    expect(isNetworkUnreachableError(new Error('syntax error at or near "SELEC"'))).toBe(false);
+    expect(isNetworkUnreachableError(null)).toBe(false);
+  });
+});
+
+describe('ConnectionManager — direct-pool fallback on unreachable host (#1641)', () => {
+  let originalKillSwitch: string | undefined;
+  let originalError: typeof console.error;
+  let errLines: string[];
+  beforeEach(() => {
+    originalKillSwitch = process.env.GBRAIN_DISABLE_DIRECT_POOL;
+    delete process.env.GBRAIN_DISABLE_DIRECT_POOL;
+    originalError = console.error;
+    errLines = [];
+    console.error = (...args: unknown[]) => { errLines.push(args.join(' ')); };
+  });
+  afterEach(() => {
+    console.error = originalError;
+    if (originalKillSwitch === undefined) delete process.env.GBRAIN_DISABLE_DIRECT_POOL;
+    else process.env.GBRAIN_DISABLE_DIRECT_POOL = originalKillSwitch;
+  });
+
+  test('ddl() falls back to the read pool when the direct host is unreachable', async () => {
+    const cm = new ConnectionManager({
+      url: 'postgresql://postgres.abc:p@aws.pooler.supabase.com:6543/db',
+      // 127.0.0.1:9 (discard) → instant ECONNREFUSED, the IPv4-only-network shape.
+      directUrl: 'postgresql://postgres:p@127.0.0.1:9/db',
+    });
+    const fakeReadPool = {} as ReturnType<typeof ConnectionManager.prototype.read>;
+    cm.setReadPool(fakeReadPool);
+    expect(cm.isDualPoolActive()).toBe(true);
+
+    const pool = await cm.ddl(); // without the fix this throws ECONNREFUSED
+    expect(pool).toBe(fakeReadPool);
+    // Self-activating kill-switch: subsequent calls skip the direct pool.
+    expect(cm.isKillSwitchActive()).toBe(true);
+    expect(cm.isDualPoolActive()).toBe(false);
+    expect(cm.describeMode().mode).toBe('single (kill-switch)');
+    // One stderr line mentioning the power-user override.
+    const warning = errLines.filter(l => l.includes('GBRAIN_DIRECT_DATABASE_URL'));
+    expect(warning.length).toBe(1);
+
+    const again = await cm.ddl();
+    expect(again).toBe(fakeReadPool);
+    expect(errLines.filter(l => l.includes('GBRAIN_DIRECT_DATABASE_URL')).length).toBe(1);
+  }, 20000);
+});

test/embed-stale.serial.test.ts

@@ -15,7 +15,6 @@ 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;
@@ -277,49 +276,4 @@ 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

@@ -37,8 +37,6 @@ 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.
@@ -805,34 +803,3 @@ 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/import-signature-stamp.serial.test.ts

@@ -73,21 +73,4 @@ 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');
-  });
 });