refactor(embeddings): derive block options from the catalog; use shared helpers

Findings from a four-angle quality review.

Reuse: `splitByItemLimit` and `processWithConcurrency` were reimplementations of
`chunkArray` (`@sim/utils`) and `mapWithConcurrency`
(`@/lib/core/utils/concurrency`), so `lib/embeddings/batching.ts` is gone. That
helper's doc forbade a throwing mapper; embedding legitimately wants a failed
batch to fail the call, since a partial vector set is not a usable result, so the
contract is reworded to cover both intents rather than forked.

The block no longer hand-copies the catalog. Its model, task-type, and dimension
dropdowns are derived from `EMBEDDING_MODELS`, which deletes roughly 150 lines of
literals that had to be kept in step by a drift test. The comment claiming this
was impossible was wrong: `generate-docs.ts` only reads `subBlocks` looking for
an `id: 'operation'` entry, which this block does not have. Verified by
regenerating — `embeddings.mdx` and `integrations.json` come out byte-identical.

Single-sourced two maps that were stated twice: BYOK provider ids (which encode
the non-obvious gemini -> google mapping) and the per-provider default model.
The route previously took its default from `getModelsForProvider(provider)[0]`,
which silently depended on catalog key order.

Azure's `endpoint` and `apiVersion` are required on their own context type
instead of optional on the shared one, so the adapter can no longer be built
without them and emit an `undefined/...` URL.

Also: contract enums now `satisfies` the catalog unions so they cannot drift,
the barrel exports only what callers outside the module use, the redundant
`requestedDimensions` field is a parameter, the bare `getEmbeddingModelInfo()`
call is a named `assertKbEmbeddingModel`, and the route checks payload size
before scanning entries rather than copying the body first.

Author: waleedlatif1

apps/sim/app/api/tools/embeddings/route.ts

@@ -10,23 +10,26 @@ import { getValidationErrorMessage, parseRequest, validationErrorResponse } from
 import { checkInternalAuth } from '@/lib/auth/hybrid'
 import { withRouteHandler } from '@/lib/core/utils/with-route-handler'
 import {
+  DEFAULT_MODEL_BY_PROVIDER,
   embed,
   findEmbeddingModelInfo,
-  getModelsForProvider,
   resolveDimensions,
 } from '@/lib/embeddings'
 
 const logger = createLogger('EmbeddingsToolAPI')
 
 export const dynamic = 'force-dynamic'
 
-/** Accepts a single string, an array, or a JSON-encoded array from a reference expression. */
+/**
+ * Accepts a single string, an array, or a JSON-encoded array from a reference
+ * expression. Probes for the opening bracket with a regex rather than `trim()`,
+ * which would copy the whole payload just to read one character.
+ */
 function normalizeInput(input: string | string[]): string[] {
   if (Array.isArray(input)) return input
-  const trimmed = input.trim()
-  if (trimmed.startsWith('[')) {
+  if (/^\s*\[/.test(input)) {
     try {
-      const parsed = JSON.parse(trimmed)
+      const parsed = JSON.parse(input)
       if (Array.isArray(parsed) && parsed.every((entry) => typeof entry === 'string')) {
         return parsed
       }
@@ -84,13 +87,7 @@ export const POST = withRouteHandler(async (request: NextRequest) => {
       { status: 400 }
     )
   }
-  if (texts.some((text) => text.trim().length === 0)) {
-    return NextResponse.json(
-      { success: false, error: 'input entries cannot be empty' },
-      { status: 400 }
-    )
-  }
-
+  /** Size is checked before the per-entry scan so an oversized body is rejected without copying it. */
   const totalChars = texts.reduce((sum, text) => sum + text.length, 0)
   if (totalChars > MAX_EMBEDDING_TOTAL_CHARS) {
     return NextResponse.json(
@@ -102,7 +99,14 @@ export const POST = withRouteHandler(async (request: NextRequest) => {
     )
   }
 
-  const resolvedModel = model || getModelsForProvider(provider)[0]
+  if (texts.some((text) => !/\S/.test(text))) {
+    return NextResponse.json(
+      { success: false, error: 'input entries cannot be empty' },
+      { status: 400 }
+    )
+  }
+
+  const resolvedModel = model || DEFAULT_MODEL_BY_PROVIDER[provider]
   const info = findEmbeddingModelInfo(resolvedModel)
   if (!info) {
     return NextResponse.json(

apps/sim/blocks/blocks/embeddings.test.ts

@@ -2,18 +2,14 @@
  * @vitest-environment node
  */
 import { describe, expect, it } from 'vitest'
-import { EMBEDDING_MODELS } from '@/lib/embeddings/catalog'
-import {
-  DEFAULT_MODEL_BY_PROVIDER,
-  EmbeddingsBlock,
-  TOOL_ID_BY_PROVIDER,
-} from '@/blocks/blocks/embeddings'
+import { DEFAULT_MODEL_BY_PROVIDER, EMBEDDING_MODELS } from '@/lib/embeddings/catalog'
+import { EmbeddingsBlock, TOOL_ID_BY_PROVIDER } from '@/blocks/blocks/embeddings'
 
 /**
- * The block spells its model, task-type, and dimension options out as literals
- * because `scripts/generate-docs.ts` parses the block file as source text and
- * cannot see computed values. These tests are what stop those literals from
- * drifting away from the catalog that actually drives the runtime.
+ * The block derives its model, task-type, and dimension options from the
+ * catalog, so these assert the derivation still produces what the UI expects:
+ * one dropdown per provider/model, the catalog's own option sets, and the
+ * native size pre-selected. They also pin the provider-to-tool routing.
  */
 
 function subBlocksById(id: string) {