fix(chunkers): fix log message and add missing month abbreviations

- Fix regex fallback log: "character splitting" → "word-boundary splitting" - Add Jun and Jul to sentence chunker abbreviation list
simstudioai · waleedlatif1 · Apr 11, 2026 · Apr 11, 2026 · Apr 11, 2026 · Apr 11, 2026
commit e391efa11d8c300c3accfb7fdffd6e4f164267a3
diff --git a/apps/sim/lib/chunkers/regex-chunker.ts b/apps/sim/lib/chunkers/regex-chunker.ts
@@ -84,7 +84,7 @@ export class RegexChunker {
     const segments = cleaned.split(this.regex).filter((s) => s.trim().length > 0)
 
     if (segments.length <= 1) {
-      logger.warn('Regex pattern did not produce any splits, falling back to character splitting')
+      logger.warn('Regex pattern did not produce any splits, falling back to word-boundary splitting')
       const chunkSizeChars = tokensToChars(this.chunkSize)
       let chunks = splitAtWordBoundaries(cleaned, chunkSizeChars)
       if (this.chunkOverlap > 0) {

diff --git a/apps/sim/lib/chunkers/sentence-chunker.ts b/apps/sim/lib/chunkers/sentence-chunker.ts
@@ -28,7 +28,7 @@ export class SentenceChunker {
   private splitSentences(text: string): string[] {
     return text
       .split(
-        /(?<!\b(?:Mr|Mrs|Ms|Dr|Prof|Sr|Jr|St|Rev|Gen|Sgt|Capt|Lt|Col|Maj|No|Fig|Vol|Ch|vs|etc|Inc|Ltd|Corp|Co|approx|dept|est|govt|Ave|Blvd|Rd|Jan|Feb|Mar|Apr|Aug|Sep|Oct|Nov|Dec|i\.e|e\.g)\.)(?<![A-Z]\.)(?<!\.\.)(?<!\d\.)(?<=[.!?])\s+/
+        /(?<!\b(?:Mr|Mrs|Ms|Dr|Prof|Sr|Jr|St|Rev|Gen|Sgt|Capt|Lt|Col|Maj|No|Fig|Vol|Ch|vs|etc|Inc|Ltd|Corp|Co|approx|dept|est|govt|Ave|Blvd|Rd|Jan|Feb|Mar|Apr|Jun|Jul|Aug|Sep|Oct|Nov|Dec|i\.e|e\.g)\.)(?<![A-Z]\.)(?<!\.\.)(?<!\d\.)(?<=[.!?])\s+/
       )
       .filter((s) => s.trim().length > 0)
   }