From 0b5cc9636243574c4212e969621ea65f03e7e88a Mon Sep 17 00:00:00 2001
From: Abhi <43648792+abhipatel12@users.noreply.github.com>
Date: Sun, 27 Jul 2025 17:40:55 -0400
Subject: (model) - Use Flash Lite For Next Speaker Checks (#4991)

---
 packages/core/src/config/models.ts                 | 1 +
 packages/core/src/core/tokenLimits.ts              | 1 +
 packages/core/src/utils/nextSpeakerChecker.test.ts | 4 ++--
 packages/core/src/utils/nextSpeakerChecker.ts      | 4 ++--
 4 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'packages/core/src')

diff --git a/packages/core/src/config/models.ts b/packages/core/src/config/models.ts
index 07e0e051..e879268b 100644
--- a/packages/core/src/config/models.ts
+++ b/packages/core/src/config/models.ts
@@ -6,4 +6,5 @@
 
 export const DEFAULT_GEMINI_MODEL = 'gemini-2.5-pro';
 export const DEFAULT_GEMINI_FLASH_MODEL = 'gemini-2.5-flash';
+export const DEFAULT_GEMINI_FLASH_LITE_MODEL = 'gemini-2.5-flash-lite';
 export const DEFAULT_GEMINI_EMBEDDING_MODEL = 'gemini-embedding-001';
diff --git a/packages/core/src/core/tokenLimits.ts b/packages/core/src/core/tokenLimits.ts
index 1c7fbde9..d238cdb3 100644
--- a/packages/core/src/core/tokenLimits.ts
+++ b/packages/core/src/core/tokenLimits.ts
@@ -21,6 +21,7 @@ export function tokenLimit(model: Model): TokenCount {
     case 'gemini-2.5-pro':
     case 'gemini-2.5-flash-preview-05-20':
     case 'gemini-2.5-flash':
+    case 'gemini-2.5-flash-lite':
     case 'gemini-2.0-flash':
       return 1_048_576;
     case 'gemini-2.0-flash-preview-image-generation':
diff --git a/packages/core/src/utils/nextSpeakerChecker.test.ts b/packages/core/src/utils/nextSpeakerChecker.test.ts
index 9141105f..70d6023f 100644
--- a/packages/core/src/utils/nextSpeakerChecker.test.ts
+++ b/packages/core/src/utils/nextSpeakerChecker.test.ts
@@ -6,7 +6,7 @@
 
 import { describe, it, expect, vi, beforeEach, Mock, afterEach } from 'vitest';
 import { Content, GoogleGenAI, Models } from '@google/genai';
-import { DEFAULT_GEMINI_FLASH_MODEL } from '../config/models.js';
+import { DEFAULT_GEMINI_FLASH_LITE_MODEL } from '../config/models.js';
 import { GeminiClient } from '../core/client.js';
 import { Config } from '../config/config.js';
 import { checkNextSpeaker, NextSpeakerResponse } from './nextSpeakerChecker.js';
@@ -248,6 +248,6 @@ describe('checkNextSpeaker', () => {
     expect(mockGeminiClient.generateJson).toHaveBeenCalled();
     const generateJsonCall = (mockGeminiClient.generateJson as Mock).mock
       .calls[0];
-    expect(generateJsonCall[3]).toBe(DEFAULT_GEMINI_FLASH_MODEL);
+    expect(generateJsonCall[3]).toBe(DEFAULT_GEMINI_FLASH_LITE_MODEL);
   });
 });
diff --git a/packages/core/src/utils/nextSpeakerChecker.ts b/packages/core/src/utils/nextSpeakerChecker.ts
index 9d428887..c75bf645 100644
--- a/packages/core/src/utils/nextSpeakerChecker.ts
+++ b/packages/core/src/utils/nextSpeakerChecker.ts
@@ -5,7 +5,7 @@
  */
 
 import { Content, SchemaUnion, Type } from '@google/genai';
-import { DEFAULT_GEMINI_FLASH_MODEL } from '../config/models.js';
+import { DEFAULT_GEMINI_FLASH_LITE_MODEL } from '../config/models.js';
 import { GeminiClient } from '../core/client.js';
 import { GeminiChat } from '../core/geminiChat.js';
 import { isFunctionResponse } from './messageInspectors.js';
@@ -132,7 +132,7 @@ export async function checkNextSpeaker(
       contents,
       RESPONSE_SCHEMA,
       abortSignal,
-      DEFAULT_GEMINI_FLASH_MODEL,
+      DEFAULT_GEMINI_FLASH_LITE_MODEL,
     )) as unknown as NextSpeakerResponse;
 
     if (
-- 
cgit v1.2.3