Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-12-17 00:40:14 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

🤖 feat: Gemini 3 Support (#10584)

Browse source 
* feat: Add support for  model in token configurations and tests

* chore: Update @librechat/agents to version 3.0.26 in package.json and package-lock.json
This commit is contained in:
Danny Avila 2025-11-19 15:05:37 -05:00 • committed by GitHub
parent 4c2719a37e
commit 8b9afd5965
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 14 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

1
api/models/tx.js
View file

@ -156,6 +156,7 @@ const tokenValues = Object.assign(
'gemini-2.5-flash': { prompt: 0.3, completion: 2.5 }, 'gemini-2.5-flash': { prompt: 0.3, completion: 2.5 },
'gemini-2.5-flash-lite': { prompt: 0.1, completion: 0.4 }, 'gemini-2.5-flash-lite': { prompt: 0.1, completion: 0.4 },
'gemini-2.5-pro': { prompt: 1.25, completion: 10 }, 'gemini-2.5-pro': { prompt: 1.25, completion: 10 },
'gemini-3': { prompt: 2, completion: 12 },
'gemini-pro-vision': { prompt: 0.5, completion: 1.5 }, 'gemini-pro-vision': { prompt: 0.5, completion: 1.5 },
grok: { prompt: 2.0, completion: 10.0 }, // Base pattern defaults to grok-2 grok: { prompt: 2.0, completion: 10.0 }, // Base pattern defaults to grok-2
'grok-beta': { prompt: 5.0, completion: 15.0 }, 'grok-beta': { prompt: 5.0, completion: 15.0 },

2
api/models/tx.spec.js
View file

@ -1040,6 +1040,7 @@ describe('getCacheMultiplier', () => {
describe('Google Model Tests', () => { describe('Google Model Tests', () => {
const googleModels = [ const googleModels = [
'gemini-3',
'gemini-2.5-pro', 'gemini-2.5-pro',
'gemini-2.5-flash', 'gemini-2.5-flash',
'gemini-2.5-flash-lite', 'gemini-2.5-flash-lite',
@ -1083,6 +1084,7 @@ describe('Google Model Tests', () => {
it('should map to the correct model keys', () => { it('should map to the correct model keys', () => {
const expected = { const expected = {
'gemini-3': 'gemini-3',
'gemini-2.5-pro': 'gemini-2.5-pro', 'gemini-2.5-pro': 'gemini-2.5-pro',
'gemini-2.5-flash': 'gemini-2.5-flash', 'gemini-2.5-flash': 'gemini-2.5-flash',
'gemini-2.5-flash-lite': 'gemini-2.5-flash-lite', 'gemini-2.5-flash-lite': 'gemini-2.5-flash-lite',

2
api/package.json
View file

@ -47,7 +47,7 @@
"@langchain/google-genai": "^0.2.13", "@langchain/google-genai": "^0.2.13",
"@langchain/google-vertexai": "^0.2.13", "@langchain/google-vertexai": "^0.2.13",
"@langchain/textsplitters": "^0.1.0", "@langchain/textsplitters": "^0.1.0",
"@librechat/agents": "^3.0.25", "@librechat/agents": "^3.0.26",
"@librechat/api": "*", "@librechat/api": "*",
"@librechat/data-schemas": "*", "@librechat/data-schemas": "*",
"@microsoft/microsoft-graph-client": "^3.0.7", "@microsoft/microsoft-graph-client": "^3.0.7",

3
api/utils/tokens.spec.js
View file

@ -275,6 +275,9 @@ describe('getModelMaxTokens', () => {
expect(getModelMaxTokens('gemini-1.5-pro-preview-0409', EModelEndpoint.google)).toBe( expect(getModelMaxTokens('gemini-1.5-pro-preview-0409', EModelEndpoint.google)).toBe(
maxTokensMap[EModelEndpoint.google]['gemini-1.5'], maxTokensMap[EModelEndpoint.google]['gemini-1.5'],
); );
expect(getModelMaxTokens('gemini-3', EModelEndpoint.google)).toBe(
maxTokensMap[EModelEndpoint.google]['gemini-3'],
);
expect(getModelMaxTokens('gemini-2.5-pro', EModelEndpoint.google)).toBe( expect(getModelMaxTokens('gemini-2.5-pro', EModelEndpoint.google)).toBe(
maxTokensMap[EModelEndpoint.google]['gemini-2.5-pro'], maxTokensMap[EModelEndpoint.google]['gemini-2.5-pro'],
); );

10
package-lock.json generated
View file

@ -63,7 +63,7 @@
"@langchain/google-genai": "^0.2.13", "@langchain/google-genai": "^0.2.13",
"@langchain/google-vertexai": "^0.2.13", "@langchain/google-vertexai": "^0.2.13",
"@langchain/textsplitters": "^0.1.0", "@langchain/textsplitters": "^0.1.0",
"@librechat/agents": "^3.0.25", "@librechat/agents": "^3.0.26",
"@librechat/api": "*", "@librechat/api": "*",
"@librechat/data-schemas": "*", "@librechat/data-schemas": "*",
"@microsoft/microsoft-graph-client": "^3.0.7", "@microsoft/microsoft-graph-client": "^3.0.7",
@ -16426,9 +16426,9 @@
} }
}, },
"node_modules/@librechat/agents": { "node_modules/@librechat/agents": {
"version": "3.0.25", "version": "3.0.26",
"resolved": "https://registry.npmjs.org/@librechat/agents/-/agents-3.0.25.tgz", "resolved": "https://registry.npmjs.org/@librechat/agents/-/agents-3.0.26.tgz",
"integrity": "sha512-2TQETX++K75TEEG/30KZdwsPzUljH1MCrKkh55UcHM7OWvUNZCIRlgiWqov731NPwp1bCI3fbXoncbnWzL8NDA==", "integrity": "sha512-ALJQlry68RjxHE6Jq1S7l8M3bmBTrikkT5C6NhN8SRgq1DFoov383wDiHqOs7WwxG29Zh2FmBEGKd23bkjiTcw==",
"license": "MIT", "license": "MIT",
"dependencies": { "dependencies": {
"@langchain/anthropic": "^0.3.26", "@langchain/anthropic": "^0.3.26",
@ -47440,7 +47440,7 @@
"@azure/storage-blob": "^12.27.0", "@azure/storage-blob": "^12.27.0",
"@keyv/redis": "^4.3.3", "@keyv/redis": "^4.3.3",
"@langchain/core": "^0.3.79", "@langchain/core": "^0.3.79",
"@librechat/agents": "^3.0.25", "@librechat/agents": "^3.0.26",
"@librechat/data-schemas": "*", "@librechat/data-schemas": "*",
"@modelcontextprotocol/sdk": "^1.21.0", "@modelcontextprotocol/sdk": "^1.21.0",
"axios": "^1.12.1", "axios": "^1.12.1",

2
packages/api/package.json
View file

@ -84,7 +84,7 @@
"@azure/storage-blob": "^12.27.0", "@azure/storage-blob": "^12.27.0",
"@keyv/redis": "^4.3.3", "@keyv/redis": "^4.3.3",
"@langchain/core": "^0.3.79", "@langchain/core": "^0.3.79",
"@librechat/agents": "^3.0.25", "@librechat/agents": "^3.0.26",
"@librechat/data-schemas": "*", "@librechat/data-schemas": "*",
"@modelcontextprotocol/sdk": "^1.21.0", "@modelcontextprotocol/sdk": "^1.21.0",
"axios": "^1.12.1", "axios": "^1.12.1",

1
packages/api/src/utils/tokens.ts
View file

@ -91,6 +91,7 @@ const googleModels = {
gemini: 30720, // -2048 from max gemini: 30720, // -2048 from max
'gemini-pro-vision': 12288, 'gemini-pro-vision': 12288,
'gemini-exp': 2000000, 'gemini-exp': 2000000,
'gemini-3': 1000000, // 1M input tokens, 64k output tokens
'gemini-2.5': 1000000, // 1M input tokens, 64k output tokens 'gemini-2.5': 1000000, // 1M input tokens, 64k output tokens
'gemini-2.5-pro': 1000000, 'gemini-2.5-pro': 1000000,
'gemini-2.5-flash': 1000000, 'gemini-2.5-flash': 1000000,