Fix validating bulk insert assigning same ID to all items (#929)

KyleAMathews · claude · web-flow · commit 5f474f1eabd5 · 2025-11-28T07:23:23.000-07:00
fix(db): detect duplicate keys within same bulk insert batch

Previously, when inserting multiple items with the same key in a single
bulk insert operation, later items would silently overwrite earlier ones.
This fix adds tracking of keys already processed within the current batch,
throwing a DuplicateKeyError when duplicate keys are detected.

Co-authored-by: Claude &lt;noreply@anthropic.com&gt;
diff --git a/.changeset/fix-bulk-insert-duplicate-keys.md b/.changeset/fix-bulk-insert-duplicate-keys.md
@@ -0,0 +1,5 @@
+---
+"@tanstack/db": patch
+---
+
+Fix bulk insert not detecting duplicate keys within the same batch. Previously, when inserting multiple items with the same key in a single bulk insert operation, later items would silently overwrite earlier ones. Now, a `DuplicateKeyError` is thrown when duplicate keys are detected within the same batch.
diff --git a/packages/db/src/collection/mutations.ts b/packages/db/src/collection/mutations.ts
@@ -163,17 +163,19 @@ export class CollectionMutationsManager<
 
     const items = Array.isArray(data) ? data : [data]
     const mutations: Array<PendingMutation<TOutput>> = []
+    const keysInCurrentBatch = new Set<TKey>()
 
     // Create mutations for each item
     items.forEach((item) => {
       // Validate the data against the schema if one exists
       const validatedData = this.validateData(item, `insert`)
 
-      // Check if an item with this ID already exists in the collection
+      // Check if an item with this ID already exists in the collection or in the current batch
       const key = this.config.getKey(validatedData)
-      if (this.state.has(key)) {
+      if (this.state.has(key) || keysInCurrentBatch.has(key)) {
         throw new DuplicateKeyError(key)
       }
+      keysInCurrentBatch.add(key)
       const globalKey = this.generateGlobalKey(key, item)
 
       const mutation: PendingMutation<TOutput, `insert`> = {
diff --git a/packages/db/tests/collection.test.ts b/packages/db/tests/collection.test.ts
@@ -567,6 +567,51 @@ describe(`Collection`, () => {
     }).not.toThrow()
   })
 
+  it(`should not allow bulk inserting documents with duplicate IDs in the same batch`, async () => {
+    const collection = createCollection<{ id: number; value: string }>({
+      id: `bulk-duplicate-id-test`,
+      getKey: (item) => item.id,
+      startSync: true,
+      sync: {
+        sync: ({ begin, commit, markReady }) => {
+          begin()
+          commit()
+          markReady()
+        },
+      },
+    })
+
+    await collection.stateWhenReady()
+
+    const mutationFn = async () => {}
+    const tx = createTransaction({ mutationFn })
+
+    // Try to bulk insert documents with duplicate IDs within the same batch
+    expect(() => {
+      tx.mutate(() =>
+        collection.insert([
+          { id: 1, value: `first` },
+          { id: 1, value: `second` }, // Same ID - should throw
+        ])
+      )
+    }).toThrow(DuplicateKeyError)
+
+    // Should be able to bulk insert documents with different IDs
+    const tx2 = createTransaction({ mutationFn })
+    expect(() => {
+      tx2.mutate(() =>
+        collection.insert([
+          { id: 2, value: `first` },
+          { id: 3, value: `second` },
+        ])
+      )
+    }).not.toThrow()
+
+    // Verify both items were inserted
+    expect(collection.state.get(2)).toEqual({ id: 2, value: `first` })
+    expect(collection.state.get(3)).toEqual({ id: 3, value: `second` })
+  })
+
   it(`should support operation handler functions`, async () => {
     // Create mock handler functions
     const onInsertMock = vi.fn()

-Original file line number
+Diff line change
@@ @@ -0,0 +1,5 @@ @@
 +---
 +"@tanstack/db": patch
 +---
++
 +Fix bulk insert not detecting duplicate keys within the same batch. Previously, when inserting multiple items with the same key in a single bulk insert operation, later items would silently overwrite earlier ones. Now, a `DuplicateKeyError` is thrown when duplicate keys are detected within the same batch.