feat: add embedding rate limiting to prevent API quota exhaustion

- Add EMBEDDING_CALL_DELAY_MS constant (100ms) to prevent rate limiting
- Implement delays after embedding calls in file-watcher.ts
- Implement delays after embedding calls in scanner.ts
- Helps prevent HTTP 429 errors during code indexing operations

Author: SatoshiReport

src/services/code-index/constants/index.ts

@@ -28,3 +28,6 @@ export const BATCH_PROCESSING_CONCURRENCY = 10
 
 /**Gemini Embedder */
 export const GEMINI_MAX_ITEM_TOKENS = 2048
+
+/**Embedding Rate Limiting */
+export const EMBEDDING_CALL_DELAY_MS = 100 // Pause between embedding API calls to prevent rate limiting

src/services/code-index/processors/file-watcher.ts

@@ -5,6 +5,7 @@ import {
 	BATCH_SEGMENT_THRESHOLD,
 	MAX_BATCH_RETRIES,
 	INITIAL_RETRY_DELAY_MS,
+	EMBEDDING_CALL_DELAY_MS,
 } from "../constants"
 import { createHash } from "crypto"
 import { RooIgnoreController } from "../../../core/ignore/RooIgnoreController"
@@ -542,6 +543,9 @@ export class FileWatcher implements IFileWatcher {
 			if (this.embedder && blocks.length > 0) {
 				const texts = blocks.map((block) => block.content)
 				const { embeddings } = await this.embedder.createEmbeddings(texts)
+				
+				// Add pause between embedding calls to prevent rate limiting
+				await new Promise(resolve => setTimeout(resolve, EMBEDDING_CALL_DELAY_MS))
 
 				pointsToUpsert = blocks.map((block, index) => {
 					const normalizedAbsolutePath = generateNormalizedAbsolutePath(block.file_path, this.workspacePath)

src/services/code-index/processors/scanner.ts

@@ -23,6 +23,7 @@ import {
 	INITIAL_RETRY_DELAY_MS,
 	PARSING_CONCURRENCY,
 	BATCH_PROCESSING_CONCURRENCY,
+	EMBEDDING_CALL_DELAY_MS,
 } from "../constants"
 import { isPathInIgnoredDirectory } from "../../glob/ignore-utils"
 import { TelemetryService } from "@roo-code/telemetry"
@@ -344,6 +345,9 @@ export class DirectoryScanner implements IDirectoryScanner {
 
 				// Create embeddings for batch
 				const { embeddings } = await this.embedder.createEmbeddings(batchTexts)
+				
+				// Add pause between embedding calls to prevent rate limiting
+				await new Promise(resolve => setTimeout(resolve, EMBEDDING_CALL_DELAY_MS))
 
 				// Prepare points for Qdrant
 				const points = batchBlocks.map((block, index) => {