fix(import): normalize mixed-case slugs before chunk upsert (#430)

putPage lowercases slugs via validateSlug, but upsertChunks queried
pages by the caller's raw slug — so a mixed-case slug through
importFromContent created the page row, then failed the chunk upsert
with 'Page not found' and rolled back the whole import.

Normalize via validateSlug at importFromContent entry and inside
_upsertChunksOnce on BOTH engines (postgres + pglite parity).

Takeover of #855, rebased onto current master shapes (batchRetry
wrapper / _upsertChunksOnce, rewritten importFromContent opts block).

Co-authored-by: Kage18 <Kage18@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

src/core/import-file.ts

@@ -36,7 +36,7 @@ import {
 } from './embedding-context.ts';
 import { loadSearchModeConfig, resolveSearchMode } from './search/mode.ts';
 import { normalizeAliasList } from './search/alias-normalize.ts';
-import { isUndefinedTableError, warnOncePerProcess } from './utils.ts';
+import { isUndefinedTableError, warnOncePerProcess, validateSlug } from './utils.ts';
 import { computeCorpusGeneration } from './contextual-retrieval-service.ts';
 import { runGuardrails } from './guardrails.ts';
 
@@ -295,6 +295,12 @@ export async function importFromContent(
     remote?: boolean;
   } = {},
 ): Promise<ImportResult> {
+  // Normalize BEFORE any tx write: putPage lowercases via validateSlug but
+  // upsertChunks used to query by the caller's raw slug, so a mixed-case slug
+  // created the page row then failed the chunk upsert with "Page not found",
+  // rolling back the whole import (#430).
+  slug = validateSlug(slug);
+
   // v0.18.0+ multi-source: when caller is syncing under a non-default source,
   // every per-page tx call must carry `sourceId` so writes target the right
   // (source_id, slug) row. Pre-fix, putPage relied on the schema DEFAULT and

src/core/pglite-engine.ts

@@ -2235,6 +2235,9 @@ export class PGLiteEngine implements BrainEngine {
   }
 
   private async _upsertChunksOnce(slug: string, chunks: ChunkInput[], opts?: { sourceId?: string }): Promise<void> {
+    // Normalize the same way putPage does — pages.slug is stored lowercased,
+    // so a raw mixed-case slug here would miss the row it just wrote (#430).
+    slug = validateSlug(slug);
     const sourceId = opts?.sourceId ?? 'default';
 
     // Source-scope the page-id lookup so duplicate slugs in different sources

src/core/postgres-engine.ts

@@ -2385,6 +2385,9 @@ export class PostgresEngine implements BrainEngine {
   }
 
   private async _upsertChunksOnce(slug: string, chunks: ChunkInput[], opts?: { sourceId?: string }): Promise<void> {
+    // Normalize the same way putPage does — pages.slug is stored lowercased,
+    // so a raw mixed-case slug here would miss the row it just wrote (#430).
+    slug = validateSlug(slug);
     const sql = this.sql;
     const sourceId = opts?.sourceId ?? 'default';
 

test/pglite-engine.test.ts

@@ -6,6 +6,7 @@
 
 import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:test';
 import { PGLiteEngine } from '../src/core/pglite-engine.ts';
+import { importFromContent } from '../src/core/import-file.ts';
 import type { BrainEngine } from '../src/core/engine.ts';
 import type { PageInput, ChunkInput } from '../src/core/types.ts';
 
@@ -181,6 +182,24 @@ describe('PGLiteEngine: Pages', () => {
     const page = await engine.putPage('Test/UPPER', testPage);
     expect(page.slug).toBe('test/upper');
   });
+
+  test('importFromContent normalizes mixed-case slugs before all tx writes (#430)', async () => {
+    const result = await importFromContent(
+      engine,
+      'TestNamespace/Page-Name',
+      '---\ntype: note\ntitle: Mixed Case\n---\n\nbody text',
+      { noEmbed: true },
+    );
+    expect(result.status).toBe('imported');
+    expect(result.slug).toBe('testnamespace/page-name');
+
+    const page = await engine.getPage('testnamespace/page-name');
+    expect(page).not.toBeNull();
+    expect(page!.title).toBe('Mixed Case');
+
+    const chunks = await engine.getChunks('testnamespace/page-name');
+    expect(chunks.length).toBeGreaterThan(0);
+  });
 });
 
 // ─────────────────────────────────────────────────────────────────
@@ -364,6 +383,17 @@ describe('PGLiteEngine: Chunks', () => {
     expect(chunks[1].chunk_text).toBe('Chunk one');
   });
 
+  test('upsertChunks normalizes mixed-case slugs like putPage (#430)', async () => {
+    await engine.putPage('Test/ChunkCase', testPage);
+    await engine.upsertChunks('Test/ChunkCase', [
+      { chunk_index: 0, chunk_text: 'Mixed-case chunk', chunk_source: 'compiled_truth' },
+    ]);
+
+    const chunks = await engine.getChunks('test/chunkcase');
+    expect(chunks.length).toBe(1);
+    expect(chunks[0].chunk_text).toBe('Mixed-case chunk');
+  });
+
   test('upsertChunks removes orphan chunks', async () => {
     await engine.putPage('test/orphan', testPage);
     await engine.upsertChunks('test/orphan', [