Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2026-01-24 03:06:12 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'main' into feature/entra-id-azure-integration

Browse source
This commit is contained in:
victorbjorkgren 2025-10-31 13:16:16 +01:00
commit 23ac2556da
193 changed files with 3845 additions and 692 deletions
Download patch file Download diff file Expand all files Collapse all files

40
api/app/clients/OllamaClient.js
View file

@ -2,7 +2,7 @@ const { z } = require('zod');
const axios = require('axios');
const { Ollama } = require('ollama');
const { sleep } = require('@librechat/agents');
const { logAxiosError } = require('@librechat/api');
const { resolveHeaders } = require('@librechat/api');
const { logger } = require('@librechat/data-schemas');
const { Constants } = require('librechat-data-provider');
const { deriveBaseURL } = require('~/utils');
@ -44,6 +44,7 @@ class OllamaClient {
constructor(options = {}) {
const host = deriveBaseURL(options.baseURL ?? 'http://localhost:11434');
this.streamRate = options.streamRate ?? Constants.DEFAULT_STREAM_RATE;
this.headers = options.headers ?? {};
/** @type {Ollama} */
this.client = new Ollama({ host });
}
@ -51,27 +52,32 @@ class OllamaClient {
/**
* Fetches Ollama models from the specified base API path.
* @param {string} baseURL
* @param {Object} [options] - Optional configuration
* @param {Partial<IUser>} [options.user] - User object for header resolution
* @param {Record<string, string>} [options.headers] - Headers to include in the request
* @returns {Promise<string[]>} The Ollama models.
* @throws {Error} Throws if the Ollama API request fails
*/
static async fetchModels(baseURL) {
let models = [];
static async fetchModels(baseURL, options = {}) {
if (!baseURL) {
return models;
}
try {
const ollamaEndpoint = deriveBaseURL(baseURL);
/** @type {Promise<AxiosResponse<OllamaListResponse>>} */
const response = await axios.get(`${ollamaEndpoint}/api/tags`, {
timeout: 5000,
});
models = response.data.models.map((tag) => tag.name);
return models;
} catch (error) {
const logMessage =
"Failed to fetch models from Ollama API. If you are not using Ollama directly, and instead, through some aggregator or reverse proxy that handles fetching via OpenAI spec, ensure the name of the endpoint doesn't start with `ollama` (case-insensitive).";
logAxiosError({ message: logMessage, error });
return [];
}
const ollamaEndpoint = deriveBaseURL(baseURL);
const resolvedHeaders = resolveHeaders({
headers: options.headers,
user: options.user,
});
/** @type {Promise<AxiosResponse<OllamaListResponse>>} */
const response = await axios.get(`${ollamaEndpoint}/api/tags`, {
headers: resolvedHeaders,
timeout: 5000,
});
const models = response.data.models.map((tag) => tag.name);
return models;
}
/**

12
api/app/clients/tools/structured/OpenAIImageTools.js
View file

@ -5,6 +5,7 @@ const FormData = require('form-data');
const { ProxyAgent } = require('undici');
const { tool } = require('@langchain/core/tools');
const { logger } = require('@librechat/data-schemas');
const { HttpsProxyAgent } = require('https-proxy-agent');
const { logAxiosError, oaiToolkit } = require('@librechat/api');
const { ContentTypes, EImageOutputType } = require('librechat-data-provider');
const { getStrategyFunctions } = require('~/server/services/Files/strategies');
@ -348,16 +349,7 @@ Error Message: ${error.message}`);
};
if (process.env.PROXY) {
try {
const url = new URL(process.env.PROXY);
axiosConfig.proxy = {
host: url.hostname.replace(/^\[|\]$/g, ''),
port: url.port ? parseInt(url.port, 10) : undefined,
protocol: url.protocol.replace(':', ''),
};
} catch (error) {
logger.error('Error parsing proxy URL:', error);
}
axiosConfig.httpsAgent = new HttpsProxyAgent(process.env.PROXY);
}
if (process.env.IMAGE_GEN_OAI_AZURE_API_VERSION && process.env.IMAGE_GEN_OAI_BASEURL) {

25
api/models/Agent.js
View file

@ -62,25 +62,37 @@ const getAgents = async (searchParameter) => await Agent.find(searchParameter).l
*
* @param {Object} params
* @param {ServerRequest} params.req
* @param {string} params.spec
* @param {string} params.agent_id
* @param {string} params.endpoint
* @param {import('@librechat/agents').ClientOptions} [params.model_parameters]
* @returns {Promise<Agent|null>} The agent document as a plain object, or null if not found.
*/
const loadEphemeralAgent = async ({ req, agent_id, endpoint, model_parameters: _m }) => {
const loadEphemeralAgent = async ({ req, spec, agent_id, endpoint, model_parameters: _m }) => {
const { model, ...model_parameters } = _m;
const modelSpecs = req.config?.modelSpecs?.list;
/** @type {TModelSpec | null} */
let modelSpec = null;
if (spec != null && spec !== '') {
modelSpec = modelSpecs?.find((s) => s.name === spec) || null;
}
/** @type {TEphemeralAgent | null} */
const ephemeralAgent = req.body.ephemeralAgent;
const mcpServers = new Set(ephemeralAgent?.mcp);
if (modelSpec?.mcpServers) {
for (const mcpServer of modelSpec.mcpServers) {
mcpServers.add(mcpServer);
}
}
/** @type {string[]} */
const tools = [];
if (ephemeralAgent?.execute_code === true) {
if (ephemeralAgent?.execute_code === true || modelSpec?.executeCode === true) {
tools.push(Tools.execute_code);
}
if (ephemeralAgent?.file_search === true) {
if (ephemeralAgent?.file_search === true || modelSpec?.fileSearch === true) {
tools.push(Tools.file_search);
}
if (ephemeralAgent?.web_search === true) {
if (ephemeralAgent?.web_search === true || modelSpec?.webSearch === true) {
tools.push(Tools.web_search);
}
@ -122,17 +134,18 @@ const loadEphemeralAgent = async ({ req, agent_id, endpoint, model_parameters: _
*
* @param {Object} params
* @param {ServerRequest} params.req
* @param {string} params.spec
* @param {string} params.agent_id
* @param {string} params.endpoint
* @param {import('@librechat/agents').ClientOptions} [params.model_parameters]
* @returns {Promise<Agent|null>} The agent document as a plain object, or null if not found.
*/
const loadAgent = async ({ req, agent_id, endpoint, model_parameters }) => {
const loadAgent = async ({ req, spec, agent_id, endpoint, model_parameters }) => {
if (!agent_id) {
return null;
}
if (agent_id === EPHEMERAL_AGENT_ID) {
return await loadEphemeralAgent({ req, agent_id, endpoint, model_parameters });
return await loadEphemeralAgent({ req, spec, agent_id, endpoint, model_parameters });
}
const agent = await getAgent({
id: agent_id,

258
api/models/tx.js
View file

@ -1,4 +1,4 @@
const { matchModelName } = require('@librechat/api');
const { matchModelName, findMatchingPattern } = require('@librechat/api');
const defaultRate = 6;
/**
@ -6,44 +6,58 @@ const defaultRate = 6;
* source: https://aws.amazon.com/bedrock/pricing/
* */
const bedrockValues = {
// Basic llama2 patterns
// Basic llama2 patterns (base defaults to smallest variant)
llama2: { prompt: 0.75, completion: 1.0 },
'llama-2': { prompt: 0.75, completion: 1.0 },
'llama2-13b': { prompt: 0.75, completion: 1.0 },
'llama2:13b': { prompt: 0.75, completion: 1.0 },
'llama2:70b': { prompt: 1.95, completion: 2.56 },
'llama2-70b': { prompt: 1.95, completion: 2.56 },
// Basic llama3 patterns
// Basic llama3 patterns (base defaults to smallest variant)
llama3: { prompt: 0.3, completion: 0.6 },
'llama-3': { prompt: 0.3, completion: 0.6 },
'llama3-8b': { prompt: 0.3, completion: 0.6 },
'llama3:8b': { prompt: 0.3, completion: 0.6 },
'llama3-70b': { prompt: 2.65, completion: 3.5 },
'llama3:70b': { prompt: 2.65, completion: 3.5 },
// llama3-x-Nb pattern
// llama3-x-Nb pattern (base defaults to smallest variant)
'llama3-1': { prompt: 0.22, completion: 0.22 },
'llama3-1-8b': { prompt: 0.22, completion: 0.22 },
'llama3-1-70b': { prompt: 0.72, completion: 0.72 },
'llama3-1-405b': { prompt: 2.4, completion: 2.4 },
'llama3-2': { prompt: 0.1, completion: 0.1 },
'llama3-2-1b': { prompt: 0.1, completion: 0.1 },
'llama3-2-3b': { prompt: 0.15, completion: 0.15 },
'llama3-2-11b': { prompt: 0.16, completion: 0.16 },
'llama3-2-90b': { prompt: 0.72, completion: 0.72 },
'llama3-3': { prompt: 2.65, completion: 3.5 },
'llama3-3-70b': { prompt: 2.65, completion: 3.5 },
// llama3.x:Nb pattern
// llama3.x:Nb pattern (base defaults to smallest variant)
'llama3.1': { prompt: 0.22, completion: 0.22 },
'llama3.1:8b': { prompt: 0.22, completion: 0.22 },
'llama3.1:70b': { prompt: 0.72, completion: 0.72 },
'llama3.1:405b': { prompt: 2.4, completion: 2.4 },
'llama3.2': { prompt: 0.1, completion: 0.1 },
'llama3.2:1b': { prompt: 0.1, completion: 0.1 },
'llama3.2:3b': { prompt: 0.15, completion: 0.15 },
'llama3.2:11b': { prompt: 0.16, completion: 0.16 },
'llama3.2:90b': { prompt: 0.72, completion: 0.72 },
'llama3.3': { prompt: 2.65, completion: 3.5 },
'llama3.3:70b': { prompt: 2.65, completion: 3.5 },
// llama-3.x-Nb pattern
// llama-3.x-Nb pattern (base defaults to smallest variant)
'llama-3.1': { prompt: 0.22, completion: 0.22 },
'llama-3.1-8b': { prompt: 0.22, completion: 0.22 },
'llama-3.1-70b': { prompt: 0.72, completion: 0.72 },
'llama-3.1-405b': { prompt: 2.4, completion: 2.4 },
'llama-3.2': { prompt: 0.1, completion: 0.1 },
'llama-3.2-1b': { prompt: 0.1, completion: 0.1 },
'llama-3.2-3b': { prompt: 0.15, completion: 0.15 },
'llama-3.2-11b': { prompt: 0.16, completion: 0.16 },
'llama-3.2-90b': { prompt: 0.72, completion: 0.72 },
'llama-3.3': { prompt: 2.65, completion: 3.5 },
'llama-3.3-70b': { prompt: 2.65, completion: 3.5 },
'mistral-7b': { prompt: 0.15, completion: 0.2 },
'mistral-small': { prompt: 0.15, completion: 0.2 },
@ -52,15 +66,19 @@ const bedrockValues = {
'mistral-large-2407': { prompt: 3.0, completion: 9.0 },
'command-text': { prompt: 1.5, completion: 2.0 },
'command-light': { prompt: 0.3, completion: 0.6 },
'ai21.j2-mid-v1': { prompt: 12.5, completion: 12.5 },
'ai21.j2-ultra-v1': { prompt: 18.8, completion: 18.8 },
'ai21.jamba-instruct-v1:0': { prompt: 0.5, completion: 0.7 },
'amazon.titan-text-lite-v1': { prompt: 0.15, completion: 0.2 },
'amazon.titan-text-express-v1': { prompt: 0.2, completion: 0.6 },
'amazon.titan-text-premier-v1:0': { prompt: 0.5, completion: 1.5 },
'amazon.nova-micro-v1:0': { prompt: 0.035, completion: 0.14 },
'amazon.nova-lite-v1:0': { prompt: 0.06, completion: 0.24 },
'amazon.nova-pro-v1:0': { prompt: 0.8, completion: 3.2 },
// AI21 models
'j2-mid': { prompt: 12.5, completion: 12.5 },
'j2-ultra': { prompt: 18.8, completion: 18.8 },
'jamba-instruct': { prompt: 0.5, completion: 0.7 },
// Amazon Titan models
'titan-text-lite': { prompt: 0.15, completion: 0.2 },
'titan-text-express': { prompt: 0.2, completion: 0.6 },
'titan-text-premier': { prompt: 0.5, completion: 1.5 },
// Amazon Nova models
'nova-micro': { prompt: 0.035, completion: 0.14 },
'nova-lite': { prompt: 0.06, completion: 0.24 },
'nova-pro': { prompt: 0.8, completion: 3.2 },
'nova-premier': { prompt: 2.5, completion: 12.5 },
'deepseek.r1': { prompt: 1.35, completion: 5.4 },
};
@ -71,100 +89,136 @@ const bedrockValues = {
*/
const tokenValues = Object.assign(
{
// Legacy token size mappings (generic patterns - check LAST)
'8k': { prompt: 30, completion: 60 },
'32k': { prompt: 60, completion: 120 },
'4k': { prompt: 1.5, completion: 2 },
'16k': { prompt: 3, completion: 4 },
// Generic fallback patterns (check LAST)
'claude-': { prompt: 0.8, completion: 2.4 },
deepseek: { prompt: 0.28, completion: 0.42 },
command: { prompt: 0.38, completion: 0.38 },
gemma: { prompt: 0.02, completion: 0.04 }, // Base pattern (using gemma-3n-e4b pricing)
gemini: { prompt: 0.5, completion: 1.5 },
'gpt-oss': { prompt: 0.05, completion: 0.2 },
// Specific model variants (check FIRST - more specific patterns at end)
'gpt-3.5-turbo-1106': { prompt: 1, completion: 2 },
'o4-mini': { prompt: 1.1, completion: 4.4 },
'o3-mini': { prompt: 1.1, completion: 4.4 },
o3: { prompt: 2, completion: 8 },
'o1-mini': { prompt: 1.1, completion: 4.4 },
'o1-preview': { prompt: 15, completion: 60 },
o1: { prompt: 15, completion: 60 },
'gpt-3.5-turbo-0125': { prompt: 0.5, completion: 1.5 },
'gpt-4-1106': { prompt: 10, completion: 30 },
'gpt-4.1': { prompt: 2, completion: 8 },
'gpt-4.1-nano': { prompt: 0.1, completion: 0.4 },
'gpt-4.1-mini': { prompt: 0.4, completion: 1.6 },
'gpt-4.1': { prompt: 2, completion: 8 },
'gpt-4.5': { prompt: 75, completion: 150 },
'gpt-4o-mini': { prompt: 0.15, completion: 0.6 },
'gpt-5': { prompt: 1.25, completion: 10 },
'gpt-5-mini': { prompt: 0.25, completion: 2 },
'gpt-5-nano': { prompt: 0.05, completion: 0.4 },
'gpt-4o': { prompt: 2.5, completion: 10 },
'gpt-4o-2024-05-13': { prompt: 5, completion: 15 },
'gpt-4-1106': { prompt: 10, completion: 30 },
'gpt-3.5-turbo-0125': { prompt: 0.5, completion: 1.5 },
'claude-3-opus': { prompt: 15, completion: 75 },
'gpt-4o-mini': { prompt: 0.15, completion: 0.6 },
'gpt-5': { prompt: 1.25, completion: 10 },
'gpt-5-nano': { prompt: 0.05, completion: 0.4 },
'gpt-5-mini': { prompt: 0.25, completion: 2 },
'gpt-5-pro': { prompt: 15, completion: 120 },
o1: { prompt: 15, completion: 60 },
'o1-mini': { prompt: 1.1, completion: 4.4 },
'o1-preview': { prompt: 15, completion: 60 },
o3: { prompt: 2, completion: 8 },
'o3-mini': { prompt: 1.1, completion: 4.4 },
'o4-mini': { prompt: 1.1, completion: 4.4 },
'claude-instant': { prompt: 0.8, completion: 2.4 },
'claude-2': { prompt: 8, completion: 24 },
'claude-2.1': { prompt: 8, completion: 24 },
'claude-3-haiku': { prompt: 0.25, completion: 1.25 },
'claude-3-sonnet': { prompt: 3, completion: 15 },
'claude-3-opus': { prompt: 15, completion: 75 },
'claude-3-5-haiku': { prompt: 0.8, completion: 4 },
'claude-3.5-haiku': { prompt: 0.8, completion: 4 },
'claude-3-5-sonnet': { prompt: 3, completion: 15 },
'claude-3.5-sonnet': { prompt: 3, completion: 15 },
'claude-3-7-sonnet': { prompt: 3, completion: 15 },
'claude-3.7-sonnet': { prompt: 3, completion: 15 },
'claude-3-5-haiku': { prompt: 0.8, completion: 4 },
'claude-3.5-haiku': { prompt: 0.8, completion: 4 },
'claude-3-haiku': { prompt: 0.25, completion: 1.25 },
'claude-sonnet-4': { prompt: 3, completion: 15 },
'claude-haiku-4-5': { prompt: 1, completion: 5 },
'claude-opus-4': { prompt: 15, completion: 75 },
'claude-2.1': { prompt: 8, completion: 24 },
'claude-2': { prompt: 8, completion: 24 },
'claude-instant': { prompt: 0.8, completion: 2.4 },
'claude-': { prompt: 0.8, completion: 2.4 },
'command-r-plus': { prompt: 3, completion: 15 },
'claude-sonnet-4': { prompt: 3, completion: 15 },
'command-r': { prompt: 0.5, completion: 1.5 },
'command-r-plus': { prompt: 3, completion: 15 },
'command-text': { prompt: 1.5, completion: 2.0 },
'deepseek-reasoner': { prompt: 0.28, completion: 0.42 },
deepseek: { prompt: 0.28, completion: 0.42 },
/* cohere doesn't have rates for the older command models,
so this was from https://artificialanalysis.ai/models/command-light/providers */
command: { prompt: 0.38, completion: 0.38 },
gemma: { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
'gemma-2': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
'gemma-3': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
'gemma-3-27b': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
'gemini-2.0-flash-lite': { prompt: 0.075, completion: 0.3 },
'deepseek-r1': { prompt: 0.4, completion: 2.0 },
'deepseek-v3': { prompt: 0.2, completion: 0.8 },
'gemma-2': { prompt: 0.01, completion: 0.03 }, // Base pattern (using gemma-2-9b pricing)
'gemma-3': { prompt: 0.02, completion: 0.04 }, // Base pattern (using gemma-3n-e4b pricing)
'gemma-3-27b': { prompt: 0.09, completion: 0.16 },
'gemini-1.5': { prompt: 2.5, completion: 10 },
'gemini-1.5-flash': { prompt: 0.15, completion: 0.6 },
'gemini-1.5-flash-8b': { prompt: 0.075, completion: 0.3 },
'gemini-2.0': { prompt: 0.1, completion: 0.4 }, // Base pattern (using 2.0-flash pricing)
'gemini-2.0-flash': { prompt: 0.1, completion: 0.4 },
'gemini-2.0': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
'gemini-2.5-pro': { prompt: 1.25, completion: 10 },
'gemini-2.0-flash-lite': { prompt: 0.075, completion: 0.3 },
'gemini-2.5': { prompt: 0.3, completion: 2.5 }, // Base pattern (using 2.5-flash pricing)
'gemini-2.5-flash': { prompt: 0.3, completion: 2.5 },
'gemini-2.5-flash-lite': { prompt: 0.1, completion: 0.4 },
'gemini-2.5': { prompt: 0, completion: 0 }, // Free for a period of time
'gemini-1.5-flash-8b': { prompt: 0.075, completion: 0.3 },
'gemini-1.5-flash': { prompt: 0.15, completion: 0.6 },
'gemini-1.5': { prompt: 2.5, completion: 10 },
'gemini-2.5-pro': { prompt: 1.25, completion: 10 },
'gemini-pro-vision': { prompt: 0.5, completion: 1.5 },
gemini: { prompt: 0.5, completion: 1.5 },
'grok-2-vision-1212': { prompt: 2.0, completion: 10.0 },
'grok-2-vision-latest': { prompt: 2.0, completion: 10.0 },
'grok-2-vision': { prompt: 2.0, completion: 10.0 },
grok: { prompt: 2.0, completion: 10.0 }, // Base pattern defaults to grok-2
'grok-beta': { prompt: 5.0, completion: 15.0 },
'grok-vision-beta': { prompt: 5.0, completion: 15.0 },
'grok-2': { prompt: 2.0, completion: 10.0 },
'grok-2-1212': { prompt: 2.0, completion: 10.0 },
'grok-2-latest': { prompt: 2.0, completion: 10.0 },
'grok-2': { prompt: 2.0, completion: 10.0 },
'grok-3-mini-fast': { prompt: 0.6, completion: 4 },
'grok-3-mini': { prompt: 0.3, completion: 0.5 },
'grok-3-fast': { prompt: 5.0, completion: 25.0 },
'grok-2-vision': { prompt: 2.0, completion: 10.0 },
'grok-2-vision-1212': { prompt: 2.0, completion: 10.0 },
'grok-2-vision-latest': { prompt: 2.0, completion: 10.0 },
'grok-3': { prompt: 3.0, completion: 15.0 },
'grok-3-fast': { prompt: 5.0, completion: 25.0 },
'grok-3-mini': { prompt: 0.3, completion: 0.5 },
'grok-3-mini-fast': { prompt: 0.6, completion: 4 },
'grok-4': { prompt: 3.0, completion: 15.0 },
'grok-beta': { prompt: 5.0, completion: 15.0 },
'mistral-large': { prompt: 2.0, completion: 6.0 },
'pixtral-large': { prompt: 2.0, completion: 6.0 },
'mistral-saba': { prompt: 0.2, completion: 0.6 },
codestral: { prompt: 0.3, completion: 0.9 },
'ministral-8b': { prompt: 0.1, completion: 0.1 },
'ministral-3b': { prompt: 0.04, completion: 0.04 },
// GPT-OSS models
'gpt-oss': { prompt: 0.05, completion: 0.2 },
'ministral-8b': { prompt: 0.1, completion: 0.1 },
'mistral-nemo': { prompt: 0.15, completion: 0.15 },
'mistral-saba': { prompt: 0.2, completion: 0.6 },
'pixtral-large': { prompt: 2.0, completion: 6.0 },
'mistral-large': { prompt: 2.0, completion: 6.0 },
'mixtral-8x22b': { prompt: 0.65, completion: 0.65 },
kimi: { prompt: 0.14, completion: 2.49 }, // Base pattern (using kimi-k2 pricing)
// GPT-OSS models (specific sizes)
'gpt-oss:20b': { prompt: 0.05, completion: 0.2 },
'gpt-oss-20b': { prompt: 0.05, completion: 0.2 },
'gpt-oss:120b': { prompt: 0.15, completion: 0.6 },
'gpt-oss-120b': { prompt: 0.15, completion: 0.6 },
// GLM models (Zhipu AI)
// GLM models (Zhipu AI) - general to specific
glm4: { prompt: 0.1, completion: 0.1 },
'glm-4': { prompt: 0.1, completion: 0.1 },
'glm-4-32b': { prompt: 0.1, completion: 0.1 },
'glm-4.5': { prompt: 0.35, completion: 1.55 },
'glm-4.5v': { prompt: 0.6, completion: 1.8 },
'glm-4.5-air': { prompt: 0.14, completion: 0.86 },
'glm-4.5v': { prompt: 0.6, completion: 1.8 },
'glm-4.6': { prompt: 0.5, completion: 1.75 },
// Qwen models
qwen: { prompt: 0.08, completion: 0.33 }, // Qwen base pattern (using qwen2.5-72b pricing)
'qwen2.5': { prompt: 0.08, completion: 0.33 }, // Qwen 2.5 base pattern
'qwen-turbo': { prompt: 0.05, completion: 0.2 },
'qwen-plus': { prompt: 0.4, completion: 1.2 },
'qwen-max': { prompt: 1.6, completion: 6.4 },
'qwq-32b': { prompt: 0.15, completion: 0.4 },
// Qwen3 models
qwen3: { prompt: 0.035, completion: 0.138 }, // Qwen3 base pattern (using qwen3-4b pricing)
'qwen3-8b': { prompt: 0.035, completion: 0.138 },
'qwen3-14b': { prompt: 0.05, completion: 0.22 },
'qwen3-30b-a3b': { prompt: 0.06, completion: 0.22 },
'qwen3-32b': { prompt: 0.05, completion: 0.2 },
'qwen3-235b-a22b': { prompt: 0.08, completion: 0.55 },
// Qwen3 VL (Vision-Language) models
'qwen3-vl-8b-thinking': { prompt: 0.18, completion: 2.1 },
'qwen3-vl-8b-instruct': { prompt: 0.18, completion: 0.69 },
'qwen3-vl-30b-a3b': { prompt: 0.29, completion: 1.0 },
'qwen3-vl-235b-a22b': { prompt: 0.3, completion: 1.2 },
// Qwen3 specialized models
'qwen3-max': { prompt: 1.2, completion: 6 },
'qwen3-coder': { prompt: 0.22, completion: 0.95 },
'qwen3-coder-30b-a3b': { prompt: 0.06, completion: 0.25 },
'qwen3-coder-plus': { prompt: 1, completion: 5 },
'qwen3-coder-flash': { prompt: 0.3, completion: 1.5 },
'qwen3-next-80b-a3b': { prompt: 0.1, completion: 0.8 },
},
bedrockValues,
);
@ -195,67 +249,39 @@ const cacheTokenValues = {
* @returns {string|undefined} The key corresponding to the model name, or undefined if no match is found.
*/
const getValueKey = (model, endpoint) => {
if (!model || typeof model !== 'string') {
return undefined;
}
// Use findMatchingPattern directly against tokenValues for efficient lookup
if (!endpoint || (typeof endpoint === 'string' && !tokenValues[endpoint])) {
const matchedKey = findMatchingPattern(model, tokenValues);
if (matchedKey) {
return matchedKey;
}
}
// Fallback: use matchModelName for edge cases and legacy handling
const modelName = matchModelName(model, endpoint);
if (!modelName) {
return undefined;
}
// Legacy token size mappings and aliases for older models
if (modelName.includes('gpt-3.5-turbo-16k')) {
return '16k';
} else if (modelName.includes('gpt-3.5-turbo-0125')) {
return 'gpt-3.5-turbo-0125';
} else if (modelName.includes('gpt-3.5-turbo-1106')) {
return 'gpt-3.5-turbo-1106';
} else if (modelName.includes('gpt-3.5')) {
return '4k';
} else if (modelName.includes('o4-mini')) {
return 'o4-mini';
} else if (modelName.includes('o4')) {
return 'o4';
} else if (modelName.includes('o3-mini')) {
return 'o3-mini';
} else if (modelName.includes('o3')) {
return 'o3';
} else if (modelName.includes('o1-preview')) {
return 'o1-preview';
} else if (modelName.includes('o1-mini')) {
return 'o1-mini';
} else if (modelName.includes('o1')) {
return 'o1';
} else if (modelName.includes('gpt-4.5')) {
return 'gpt-4.5';
} else if (modelName.includes('gpt-4.1-nano')) {
return 'gpt-4.1-nano';
} else if (modelName.includes('gpt-4.1-mini')) {
return 'gpt-4.1-mini';
} else if (modelName.includes('gpt-4.1')) {
return 'gpt-4.1';
} else if (modelName.includes('gpt-4o-2024-05-13')) {
return 'gpt-4o-2024-05-13';
} else if (modelName.includes('gpt-5-nano')) {
return 'gpt-5-nano';
} else if (modelName.includes('gpt-5-mini')) {
return 'gpt-5-mini';
} else if (modelName.includes('gpt-5')) {
return 'gpt-5';
} else if (modelName.includes('gpt-4o-mini')) {
return 'gpt-4o-mini';
} else if (modelName.includes('gpt-4o')) {
return 'gpt-4o';
} else if (modelName.includes('gpt-4-vision')) {
return 'gpt-4-1106';
} else if (modelName.includes('gpt-4-1106')) {
return 'gpt-4-1106';
return 'gpt-4-1106'; // Alias for gpt-4-vision
} else if (modelName.includes('gpt-4-0125')) {
return 'gpt-4-1106';
return 'gpt-4-1106'; // Alias for gpt-4-0125
} else if (modelName.includes('gpt-4-turbo')) {
return 'gpt-4-1106';
return 'gpt-4-1106'; // Alias for gpt-4-turbo
} else if (modelName.includes('gpt-4-32k')) {
return '32k';
} else if (modelName.includes('gpt-4')) {
return '8k';
} else if (tokenValues[modelName]) {
return modelName;
}
return undefined;

594
api/models/tx.spec.js
View file

@ -1,3 +1,4 @@
const { maxTokensMap } = require('@librechat/api');
const { EModelEndpoint } = require('librechat-data-provider');
const {
defaultRate,
@ -113,6 +114,14 @@ describe('getValueKey', () => {
expect(getValueKey('gpt-5-nano-2025-01-30-0130')).toBe('gpt-5-nano');
});
it('should return "gpt-5-pro" for model type of "gpt-5-pro"', () => {
expect(getValueKey('gpt-5-pro-2025-01-30')).toBe('gpt-5-pro');
expect(getValueKey('openai/gpt-5-pro')).toBe('gpt-5-pro');
expect(getValueKey('gpt-5-pro-0130')).toBe('gpt-5-pro');
expect(getValueKey('gpt-5-pro-2025-01-30-0130')).toBe('gpt-5-pro');
expect(getValueKey('gpt-5-pro-preview')).toBe('gpt-5-pro');
});
it('should return "gpt-4o" for model type of "gpt-4o"', () => {
expect(getValueKey('gpt-4o-2024-08-06')).toBe('gpt-4o');
expect(getValueKey('gpt-4o-2024-08-06-0718')).toBe('gpt-4o');
@ -288,6 +297,20 @@ describe('getMultiplier', () => {
);
});
it('should return the correct multiplier for gpt-5-pro', () => {
const valueKey = getValueKey('gpt-5-pro-2025-01-30');
expect(getMultiplier({ valueKey, tokenType: 'prompt' })).toBe(tokenValues['gpt-5-pro'].prompt);
expect(getMultiplier({ valueKey, tokenType: 'completion' })).toBe(
tokenValues['gpt-5-pro'].completion,
);
expect(getMultiplier({ model: 'gpt-5-pro-preview', tokenType: 'prompt' })).toBe(
tokenValues['gpt-5-pro'].prompt,
);
expect(getMultiplier({ model: 'openai/gpt-5-pro', tokenType: 'completion' })).toBe(
tokenValues['gpt-5-pro'].completion,
);
});
it('should return the correct multiplier for gpt-4o', () => {
const valueKey = getValueKey('gpt-4o-2024-08-06');
expect(getMultiplier({ valueKey, tokenType: 'prompt' })).toBe(tokenValues['gpt-4o'].prompt);
@ -471,6 +494,249 @@ describe('AWS Bedrock Model Tests', () => {
});
});
describe('Amazon Model Tests', () => {
describe('Amazon Nova Models', () => {
it('should return correct pricing for nova-premier', () => {
expect(getMultiplier({ model: 'nova-premier', tokenType: 'prompt' })).toBe(
tokenValues['nova-premier'].prompt,
);
expect(getMultiplier({ model: 'nova-premier', tokenType: 'completion' })).toBe(
tokenValues['nova-premier'].completion,
);
expect(getMultiplier({ model: 'amazon.nova-premier-v1:0', tokenType: 'prompt' })).toBe(
tokenValues['nova-premier'].prompt,
);
expect(getMultiplier({ model: 'amazon.nova-premier-v1:0', tokenType: 'completion' })).toBe(
tokenValues['nova-premier'].completion,
);
});
it('should return correct pricing for nova-pro', () => {
expect(getMultiplier({ model: 'nova-pro', tokenType: 'prompt' })).toBe(
tokenValues['nova-pro'].prompt,
);
expect(getMultiplier({ model: 'nova-pro', tokenType: 'completion' })).toBe(
tokenValues['nova-pro'].completion,
);
expect(getMultiplier({ model: 'amazon.nova-pro-v1:0', tokenType: 'prompt' })).toBe(
tokenValues['nova-pro'].prompt,
);
expect(getMultiplier({ model: 'amazon.nova-pro-v1:0', tokenType: 'completion' })).toBe(
tokenValues['nova-pro'].completion,
);
});
it('should return correct pricing for nova-lite', () => {
expect(getMultiplier({ model: 'nova-lite', tokenType: 'prompt' })).toBe(
tokenValues['nova-lite'].prompt,
);
expect(getMultiplier({ model: 'nova-lite', tokenType: 'completion' })).toBe(
tokenValues['nova-lite'].completion,
);
expect(getMultiplier({ model: 'amazon.nova-lite-v1:0', tokenType: 'prompt' })).toBe(
tokenValues['nova-lite'].prompt,
);
expect(getMultiplier({ model: 'amazon.nova-lite-v1:0', tokenType: 'completion' })).toBe(
tokenValues['nova-lite'].completion,
);
});
it('should return correct pricing for nova-micro', () => {
expect(getMultiplier({ model: 'nova-micro', tokenType: 'prompt' })).toBe(
tokenValues['nova-micro'].prompt,
);
expect(getMultiplier({ model: 'nova-micro', tokenType: 'completion' })).toBe(
tokenValues['nova-micro'].completion,
);
expect(getMultiplier({ model: 'amazon.nova-micro-v1:0', tokenType: 'prompt' })).toBe(
tokenValues['nova-micro'].prompt,
);
expect(getMultiplier({ model: 'amazon.nova-micro-v1:0', tokenType: 'completion' })).toBe(
tokenValues['nova-micro'].completion,
);
});
it('should match both short and full model names to the same pricing', () => {
const models = ['nova-micro', 'nova-lite', 'nova-pro', 'nova-premier'];
const fullModels = [
'amazon.nova-micro-v1:0',
'amazon.nova-lite-v1:0',
'amazon.nova-pro-v1:0',
'amazon.nova-premier-v1:0',
];
models.forEach((shortModel, i) => {
const fullModel = fullModels[i];
const shortPrompt = getMultiplier({ model: shortModel, tokenType: 'prompt' });
const fullPrompt = getMultiplier({ model: fullModel, tokenType: 'prompt' });
const shortCompletion = getMultiplier({ model: shortModel, tokenType: 'completion' });
const fullCompletion = getMultiplier({ model: fullModel, tokenType: 'completion' });
expect(shortPrompt).toBe(fullPrompt);
expect(shortCompletion).toBe(fullCompletion);
expect(shortPrompt).toBe(tokenValues[shortModel].prompt);
expect(shortCompletion).toBe(tokenValues[shortModel].completion);
});
});
});
describe('Amazon Titan Models', () => {
it('should return correct pricing for titan-text-premier', () => {
expect(getMultiplier({ model: 'titan-text-premier', tokenType: 'prompt' })).toBe(
tokenValues['titan-text-premier'].prompt,
);
expect(getMultiplier({ model: 'titan-text-premier', tokenType: 'completion' })).toBe(
tokenValues['titan-text-premier'].completion,
);
expect(getMultiplier({ model: 'amazon.titan-text-premier-v1:0', tokenType: 'prompt' })).toBe(
tokenValues['titan-text-premier'].prompt,
);
expect(
getMultiplier({ model: 'amazon.titan-text-premier-v1:0', tokenType: 'completion' }),
).toBe(tokenValues['titan-text-premier'].completion);
});
it('should return correct pricing for titan-text-express', () => {
expect(getMultiplier({ model: 'titan-text-express', tokenType: 'prompt' })).toBe(
tokenValues['titan-text-express'].prompt,
);
expect(getMultiplier({ model: 'titan-text-express', tokenType: 'completion' })).toBe(
tokenValues['titan-text-express'].completion,
);
expect(getMultiplier({ model: 'amazon.titan-text-express-v1', tokenType: 'prompt' })).toBe(
tokenValues['titan-text-express'].prompt,
);
expect(
getMultiplier({ model: 'amazon.titan-text-express-v1', tokenType: 'completion' }),
).toBe(tokenValues['titan-text-express'].completion);
});
it('should return correct pricing for titan-text-lite', () => {
expect(getMultiplier({ model: 'titan-text-lite', tokenType: 'prompt' })).toBe(
tokenValues['titan-text-lite'].prompt,
);
expect(getMultiplier({ model: 'titan-text-lite', tokenType: 'completion' })).toBe(
tokenValues['titan-text-lite'].completion,
);
expect(getMultiplier({ model: 'amazon.titan-text-lite-v1', tokenType: 'prompt' })).toBe(
tokenValues['titan-text-lite'].prompt,
);
expect(getMultiplier({ model: 'amazon.titan-text-lite-v1', tokenType: 'completion' })).toBe(
tokenValues['titan-text-lite'].completion,
);
});
it('should match both short and full model names to the same pricing', () => {
const models = ['titan-text-lite', 'titan-text-express', 'titan-text-premier'];
const fullModels = [
'amazon.titan-text-lite-v1',
'amazon.titan-text-express-v1',
'amazon.titan-text-premier-v1:0',
];
models.forEach((shortModel, i) => {
const fullModel = fullModels[i];
const shortPrompt = getMultiplier({ model: shortModel, tokenType: 'prompt' });
const fullPrompt = getMultiplier({ model: fullModel, tokenType: 'prompt' });
const shortCompletion = getMultiplier({ model: shortModel, tokenType: 'completion' });
const fullCompletion = getMultiplier({ model: fullModel, tokenType: 'completion' });
expect(shortPrompt).toBe(fullPrompt);
expect(shortCompletion).toBe(fullCompletion);
expect(shortPrompt).toBe(tokenValues[shortModel].prompt);
expect(shortCompletion).toBe(tokenValues[shortModel].completion);
});
});
});
});
describe('AI21 Model Tests', () => {
describe('AI21 J2 Models', () => {
it('should return correct pricing for j2-mid', () => {
expect(getMultiplier({ model: 'j2-mid', tokenType: 'prompt' })).toBe(
tokenValues['j2-mid'].prompt,
);
expect(getMultiplier({ model: 'j2-mid', tokenType: 'completion' })).toBe(
tokenValues['j2-mid'].completion,
);
expect(getMultiplier({ model: 'ai21.j2-mid-v1', tokenType: 'prompt' })).toBe(
tokenValues['j2-mid'].prompt,
);
expect(getMultiplier({ model: 'ai21.j2-mid-v1', tokenType: 'completion' })).toBe(
tokenValues['j2-mid'].completion,
);
});
it('should return correct pricing for j2-ultra', () => {
expect(getMultiplier({ model: 'j2-ultra', tokenType: 'prompt' })).toBe(
tokenValues['j2-ultra'].prompt,
);
expect(getMultiplier({ model: 'j2-ultra', tokenType: 'completion' })).toBe(
tokenValues['j2-ultra'].completion,
);
expect(getMultiplier({ model: 'ai21.j2-ultra-v1', tokenType: 'prompt' })).toBe(
tokenValues['j2-ultra'].prompt,
);
expect(getMultiplier({ model: 'ai21.j2-ultra-v1', tokenType: 'completion' })).toBe(
tokenValues['j2-ultra'].completion,
);
});
it('should match both short and full model names to the same pricing', () => {
const models = ['j2-mid', 'j2-ultra'];
const fullModels = ['ai21.j2-mid-v1', 'ai21.j2-ultra-v1'];
models.forEach((shortModel, i) => {
const fullModel = fullModels[i];
const shortPrompt = getMultiplier({ model: shortModel, tokenType: 'prompt' });
const fullPrompt = getMultiplier({ model: fullModel, tokenType: 'prompt' });
const shortCompletion = getMultiplier({ model: shortModel, tokenType: 'completion' });
const fullCompletion = getMultiplier({ model: fullModel, tokenType: 'completion' });
expect(shortPrompt).toBe(fullPrompt);
expect(shortCompletion).toBe(fullCompletion);
expect(shortPrompt).toBe(tokenValues[shortModel].prompt);
expect(shortCompletion).toBe(tokenValues[shortModel].completion);
});
});
});
describe('AI21 Jamba Models', () => {
it('should return correct pricing for jamba-instruct', () => {
expect(getMultiplier({ model: 'jamba-instruct', tokenType: 'prompt' })).toBe(
tokenValues['jamba-instruct'].prompt,
);
expect(getMultiplier({ model: 'jamba-instruct', tokenType: 'completion' })).toBe(
tokenValues['jamba-instruct'].completion,
);
expect(getMultiplier({ model: 'ai21.jamba-instruct-v1:0', tokenType: 'prompt' })).toBe(
tokenValues['jamba-instruct'].prompt,
);
expect(getMultiplier({ model: 'ai21.jamba-instruct-v1:0', tokenType: 'completion' })).toBe(
tokenValues['jamba-instruct'].completion,
);
});
it('should match both short and full model names to the same pricing', () => {
const shortPrompt = getMultiplier({ model: 'jamba-instruct', tokenType: 'prompt' });
const fullPrompt = getMultiplier({
model: 'ai21.jamba-instruct-v1:0',
tokenType: 'prompt',
});
const shortCompletion = getMultiplier({ model: 'jamba-instruct', tokenType: 'completion' });
const fullCompletion = getMultiplier({
model: 'ai21.jamba-instruct-v1:0',
tokenType: 'completion',
});
expect(shortPrompt).toBe(fullPrompt);
expect(shortCompletion).toBe(fullCompletion);
expect(shortPrompt).toBe(tokenValues['jamba-instruct'].prompt);
expect(shortCompletion).toBe(tokenValues['jamba-instruct'].completion);
});
});
});
describe('Deepseek Model Tests', () => {
const deepseekModels = ['deepseek-chat', 'deepseek-coder', 'deepseek-reasoner', 'deepseek.r1'];
@ -502,6 +768,187 @@ describe('Deepseek Model Tests', () => {
});
});
describe('Qwen3 Model Tests', () => {
describe('Qwen3 Base Models', () => {
it('should return correct pricing for qwen3 base pattern', () => {
expect(getMultiplier({ model: 'qwen3', tokenType: 'prompt' })).toBe(
tokenValues['qwen3'].prompt,
);
expect(getMultiplier({ model: 'qwen3', tokenType: 'completion' })).toBe(
tokenValues['qwen3'].completion,
);
});
it('should return correct pricing for qwen3-4b (falls back to qwen3)', () => {
expect(getMultiplier({ model: 'qwen3-4b', tokenType: 'prompt' })).toBe(
tokenValues['qwen3'].prompt,
);
expect(getMultiplier({ model: 'qwen3-4b', tokenType: 'completion' })).toBe(
tokenValues['qwen3'].completion,
);
});
it('should return correct pricing for qwen3-8b', () => {
expect(getMultiplier({ model: 'qwen3-8b', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-8b'].prompt,
);
expect(getMultiplier({ model: 'qwen3-8b', tokenType: 'completion' })).toBe(
tokenValues['qwen3-8b'].completion,
);
});
it('should return correct pricing for qwen3-14b', () => {
expect(getMultiplier({ model: 'qwen3-14b', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-14b'].prompt,
);
expect(getMultiplier({ model: 'qwen3-14b', tokenType: 'completion' })).toBe(
tokenValues['qwen3-14b'].completion,
);
});
it('should return correct pricing for qwen3-235b-a22b', () => {
expect(getMultiplier({ model: 'qwen3-235b-a22b', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-235b-a22b'].prompt,
);
expect(getMultiplier({ model: 'qwen3-235b-a22b', tokenType: 'completion' })).toBe(
tokenValues['qwen3-235b-a22b'].completion,
);
});
it('should handle model name variations with provider prefixes', () => {
const models = [
{ input: 'qwen3', expected: 'qwen3' },
{ input: 'qwen3-4b', expected: 'qwen3' },
{ input: 'qwen3-8b', expected: 'qwen3-8b' },
{ input: 'qwen3-32b', expected: 'qwen3-32b' },
];
models.forEach(({ input, expected }) => {
const withPrefix = `alibaba/${input}`;
expect(getMultiplier({ model: withPrefix, tokenType: 'prompt' })).toBe(
tokenValues[expected].prompt,
);
expect(getMultiplier({ model: withPrefix, tokenType: 'completion' })).toBe(
tokenValues[expected].completion,
);
});
});
});
describe('Qwen3 VL (Vision-Language) Models', () => {
it('should return correct pricing for qwen3-vl-8b-thinking', () => {
expect(getMultiplier({ model: 'qwen3-vl-8b-thinking', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-vl-8b-thinking'].prompt,
);
expect(getMultiplier({ model: 'qwen3-vl-8b-thinking', tokenType: 'completion' })).toBe(
tokenValues['qwen3-vl-8b-thinking'].completion,
);
});
it('should return correct pricing for qwen3-vl-8b-instruct', () => {
expect(getMultiplier({ model: 'qwen3-vl-8b-instruct', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-vl-8b-instruct'].prompt,
);
expect(getMultiplier({ model: 'qwen3-vl-8b-instruct', tokenType: 'completion' })).toBe(
tokenValues['qwen3-vl-8b-instruct'].completion,
);
});
it('should return correct pricing for qwen3-vl-30b-a3b', () => {
expect(getMultiplier({ model: 'qwen3-vl-30b-a3b', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-vl-30b-a3b'].prompt,
);
expect(getMultiplier({ model: 'qwen3-vl-30b-a3b', tokenType: 'completion' })).toBe(
tokenValues['qwen3-vl-30b-a3b'].completion,
);
});
it('should return correct pricing for qwen3-vl-235b-a22b', () => {
expect(getMultiplier({ model: 'qwen3-vl-235b-a22b', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-vl-235b-a22b'].prompt,
);
expect(getMultiplier({ model: 'qwen3-vl-235b-a22b', tokenType: 'completion' })).toBe(
tokenValues['qwen3-vl-235b-a22b'].completion,
);
});
});
describe('Qwen3 Specialized Models', () => {
it('should return correct pricing for qwen3-max', () => {
expect(getMultiplier({ model: 'qwen3-max', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-max'].prompt,
);
expect(getMultiplier({ model: 'qwen3-max', tokenType: 'completion' })).toBe(
tokenValues['qwen3-max'].completion,
);
});
it('should return correct pricing for qwen3-coder', () => {
expect(getMultiplier({ model: 'qwen3-coder', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-coder'].prompt,
);
expect(getMultiplier({ model: 'qwen3-coder', tokenType: 'completion' })).toBe(
tokenValues['qwen3-coder'].completion,
);
});
it('should return correct pricing for qwen3-coder-plus', () => {
expect(getMultiplier({ model: 'qwen3-coder-plus', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-coder-plus'].prompt,
);
expect(getMultiplier({ model: 'qwen3-coder-plus', tokenType: 'completion' })).toBe(
tokenValues['qwen3-coder-plus'].completion,
);
});
it('should return correct pricing for qwen3-coder-flash', () => {
expect(getMultiplier({ model: 'qwen3-coder-flash', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-coder-flash'].prompt,
);
expect(getMultiplier({ model: 'qwen3-coder-flash', tokenType: 'completion' })).toBe(
tokenValues['qwen3-coder-flash'].completion,
);
});
it('should return correct pricing for qwen3-next-80b-a3b', () => {
expect(getMultiplier({ model: 'qwen3-next-80b-a3b', tokenType: 'prompt' })).toBe(
tokenValues['qwen3-next-80b-a3b'].prompt,
);
expect(getMultiplier({ model: 'qwen3-next-80b-a3b', tokenType: 'completion' })).toBe(
tokenValues['qwen3-next-80b-a3b'].completion,
);
});
});
describe('Qwen3 Model Variations', () => {
it('should handle all qwen3 models with provider prefixes', () => {
const models = ['qwen3', 'qwen3-8b', 'qwen3-max', 'qwen3-coder', 'qwen3-vl-8b-instruct'];
const prefixes = ['alibaba', 'qwen', 'openrouter'];
models.forEach((model) => {
prefixes.forEach((prefix) => {
const fullModel = `${prefix}/${model}`;
expect(getMultiplier({ model: fullModel, tokenType: 'prompt' })).toBe(
tokenValues[model].prompt,
);
expect(getMultiplier({ model: fullModel, tokenType: 'completion' })).toBe(
tokenValues[model].completion,
);
});
});
});
it('should handle qwen3-4b falling back to qwen3 base pattern', () => {
const testCases = ['qwen3-4b', 'alibaba/qwen3-4b', 'qwen/qwen3-4b-preview'];
testCases.forEach((model) => {
expect(getMultiplier({ model, tokenType: 'prompt' })).toBe(tokenValues['qwen3'].prompt);
expect(getMultiplier({ model, tokenType: 'completion' })).toBe(
tokenValues['qwen3'].completion,
);
});
});
});
});
describe('getCacheMultiplier', () => {
it('should return the correct cache multiplier for a given valueKey and cacheType', () => {
expect(getCacheMultiplier({ valueKey: 'claude-3-5-sonnet', cacheType: 'write' })).toBe(
@ -914,6 +1361,37 @@ describe('Claude Model Tests', () => {
);
});
it('should return correct prompt and completion rates for Claude Haiku 4.5', () => {
expect(getMultiplier({ model: 'claude-haiku-4-5', tokenType: 'prompt' })).toBe(
tokenValues['claude-haiku-4-5'].prompt,
);
expect(getMultiplier({ model: 'claude-haiku-4-5', tokenType: 'completion' })).toBe(
tokenValues['claude-haiku-4-5'].completion,
);
});
it('should handle Claude Haiku 4.5 model name variations', () => {
const modelVariations = [
'claude-haiku-4-5',
'claude-haiku-4-5-20250420',
'claude-haiku-4-5-latest',
'anthropic/claude-haiku-4-5',
'claude-haiku-4-5/anthropic',
'claude-haiku-4-5-preview',
];
modelVariations.forEach((model) => {
const valueKey = getValueKey(model);
expect(valueKey).toBe('claude-haiku-4-5');
expect(getMultiplier({ model, tokenType: 'prompt' })).toBe(
tokenValues['claude-haiku-4-5'].prompt,
);
expect(getMultiplier({ model, tokenType: 'completion' })).toBe(
tokenValues['claude-haiku-4-5'].completion,
);
});
});
it('should handle Claude 4 model name variations with different prefixes and suffixes', () => {
const modelVariations = [
'claude-sonnet-4',
@ -991,3 +1469,119 @@ describe('Claude Model Tests', () => {
});
});
});
describe('tokens.ts and tx.js sync validation', () => {
it('should resolve all models in maxTokensMap to pricing via getValueKey', () => {
const tokensKeys = Object.keys(maxTokensMap[EModelEndpoint.openAI]);
const txKeys = Object.keys(tokenValues);
const unresolved = [];
tokensKeys.forEach((key) => {
// Skip legacy token size mappings (e.g., '4k', '8k', '16k', '32k')
if (/^\d+k$/.test(key)) return;
// Skip generic pattern keys (end with '-' or ':')
if (key.endsWith('-') || key.endsWith(':')) return;
// Try to resolve via getValueKey
const resolvedKey = getValueKey(key);
// If it resolves and the resolved key has pricing, success
if (resolvedKey && txKeys.includes(resolvedKey)) return;
// If it resolves to a legacy key (4k, 8k, etc), also OK
if (resolvedKey && /^\d+k$/.test(resolvedKey)) return;
// If we get here, this model can't get pricing - flag it
unresolved.push({
key,
resolvedKey: resolvedKey || 'undefined',
context: maxTokensMap[EModelEndpoint.openAI][key],
});
});
if (unresolved.length > 0) {
console.log('\nModels that cannot resolve to pricing via getValueKey:');
unresolved.forEach(({ key, resolvedKey, context }) => {
console.log(` - '${key}' → '${resolvedKey}' (context: ${context})`);
});
}
expect(unresolved).toEqual([]);
});
it('should not have redundant dated variants with same pricing and context as base model', () => {
const txKeys = Object.keys(tokenValues);
const redundant = [];
txKeys.forEach((key) => {
// Check if this is a dated variant (ends with -YYYY-MM-DD)
if (key.match(/.*-\d{4}-\d{2}-\d{2}$/)) {
const baseKey = key.replace(/-\d{4}-\d{2}-\d{2}$/, '');
if (txKeys.includes(baseKey)) {
const variantPricing = tokenValues[key];
const basePricing = tokenValues[baseKey];
const variantContext = maxTokensMap[EModelEndpoint.openAI][key];
const baseContext = maxTokensMap[EModelEndpoint.openAI][baseKey];
const samePricing =
variantPricing.prompt === basePricing.prompt &&
variantPricing.completion === basePricing.completion;
const sameContext = variantContext === baseContext;
if (samePricing && sameContext) {
redundant.push({
key,
baseKey,
pricing: `${variantPricing.prompt}/${variantPricing.completion}`,
context: variantContext,
});
}
}
}
});
if (redundant.length > 0) {
console.log('\nRedundant dated variants found (same pricing and context as base):');
redundant.forEach(({ key, baseKey, pricing, context }) => {
console.log(` - '${key}' → '${baseKey}' (pricing: ${pricing}, context: ${context})`);
console.log(` Can be removed - pattern matching will handle it`);
});
}
expect(redundant).toEqual([]);
});
it('should have context windows in tokens.ts for all models with pricing in tx.js (openAI catch-all)', () => {
const txKeys = Object.keys(tokenValues);
const missingContext = [];
txKeys.forEach((key) => {
// Skip legacy token size mappings (4k, 8k, 16k, 32k)
if (/^\d+k$/.test(key)) return;
// Check if this model has a context window defined
const context = maxTokensMap[EModelEndpoint.openAI][key];
if (!context) {
const pricing = tokenValues[key];
missingContext.push({
key,
pricing: `${pricing.prompt}/${pricing.completion}`,
});
}
});
if (missingContext.length > 0) {
console.log('\nModels with pricing but missing context in tokens.ts:');
missingContext.forEach(({ key, pricing }) => {
console.log(` - '${key}' (pricing: ${pricing})`);
console.log(` Add to tokens.ts openAIModels/bedrockModels/etc.`);
});
}
expect(missingContext).toEqual([]);
});
});

4
api/package.json
View file

@ -1,6 +1,6 @@
{
"name": "@librechat/backend",
"version": "v0.8.0",
"version": "v0.8.1-rc1",
"description": "",
"scripts": {
"start": "echo 'please run this from the root directory'",
@ -48,7 +48,7 @@
"@langchain/google-genai": "^0.2.13",
"@langchain/google-vertexai": "^0.2.13",
"@langchain/textsplitters": "^0.1.0",
"@librechat/agents": "^2.4.85",
"@librechat/agents": "^2.4.90",
"@librechat/api": "*",
"@librechat/data-schemas": "*",
"@microsoft/microsoft-graph-client": "^3.0.7",

14
api/server/controllers/AuthController.js
View file

@ -116,11 +116,15 @@ const refreshController = async (req, res) => {
const token = await setAuthTokens(userId, res, session);
// trigger OAuth MCP server reconnection asynchronously (best effort)
void getOAuthReconnectionManager()
.reconnectServers(userId)
.catch((err) => {
logger.error('Error reconnecting OAuth MCP servers:', err);
});
try {
void getOAuthReconnectionManager()
.reconnectServers(userId)
.catch((err) => {
logger.error('[refreshController] Error reconnecting OAuth MCP servers:', err);
});
} catch (err) {
logger.warn(`[refreshController] Cannot attempt OAuth MCP servers reconnection:`, err);
}
res.status(200).send({ token, user });
} else if (req?.query?.retry) {

8
api/server/controllers/agents/client.js
View file

@ -8,6 +8,7 @@ const {
Tokenizer,
checkAccess,
logAxiosError,
sanitizeTitle,
resolveHeaders,
getBalanceConfig,
memoryInstructions,
@ -775,6 +776,7 @@ class AgentClient extends BaseClient {
const agentsEConfig = appConfig.endpoints?.[EModelEndpoint.agents];
config = {
runName: 'AgentRun',
configurable: {
thread_id: this.conversationId,
last_agent_index: this.agentConfigs?.size ?? 0,
@ -1233,6 +1235,10 @@ class AgentClient extends BaseClient {
handleLLMEnd,
},
],
configurable: {
thread_id: this.conversationId,
user_id: this.user ?? this.options.req.user?.id,
},
},
});
@ -1270,7 +1276,7 @@ class AgentClient extends BaseClient {
);
});
return titleResult.title;
return sanitizeTitle(titleResult.title);
} catch (err) {
logger.error('[api/server/controllers/agents/client.js #titleConvo] Error', err);
return;

36
api/server/controllers/agents/client.test.js
View file

@ -10,6 +10,10 @@ jest.mock('@librechat/agents', () => ({
}),
}));
jest.mock('@librechat/api', () => ({
...jest.requireActual('@librechat/api'),
}));
describe('AgentClient - titleConvo', () => {
let client;
let mockRun;
@ -252,6 +256,38 @@ describe('AgentClient - titleConvo', () => {
expect(result).toBe('Generated Title');
});
it('should sanitize the generated title by removing think blocks', async () => {
const titleWithThinkBlock = '<think>reasoning about the title</think> User Hi Greeting';
mockRun.generateTitle.mockResolvedValue({
title: titleWithThinkBlock,
});
const text = 'Test conversation text';
const abortController = new AbortController();
const result = await client.titleConvo({ text, abortController });
// Should remove the <think> block and return only the clean title
expect(result).toBe('User Hi Greeting');
expect(result).not.toContain('<think>');
expect(result).not.toContain('</think>');
});
it('should return fallback title when sanitization results in empty string', async () => {
const titleOnlyThinkBlock = '<think>only reasoning no actual title</think>';
mockRun.generateTitle.mockResolvedValue({
title: titleOnlyThinkBlock,
});
const text = 'Test conversation text';
const abortController = new AbortController();
const result = await client.titleConvo({ text, abortController });
// Should return the fallback title since sanitization would result in empty string
expect(result).toBe('Untitled Conversation');
});
it('should handle errors gracefully and return undefined', async () => {
mockRun.generateTitle.mockRejectedValue(new Error('Title generation failed'));

4
api/server/services/Config/loadConfigModels.js
View file

@ -57,7 +57,7 @@ async function loadConfigModels(req) {
for (let i = 0; i < customEndpoints.length; i++) {
const endpoint = customEndpoints[i];
const { models, name: configName, baseURL, apiKey } = endpoint;
const { models, name: configName, baseURL, apiKey, headers: endpointHeaders } = endpoint;
const name = normalizeEndpointName(configName);
endpointsMap[name] = endpoint;
@ -76,6 +76,8 @@ async function loadConfigModels(req) {
apiKey: API_KEY,
baseURL: BASE_URL,
user: req.user.id,
userObject: req.user,
headers: endpointHeaders,
direct: endpoint.directEndpoint,
userIdQuery: models.userIdQuery,
});

12
api/server/services/Endpoints/agents/agent.js
View file

@ -134,16 +134,16 @@ const initializeAgent = async ({
});
const tokensModel =
agent.provider === EModelEndpoint.azureOpenAI ? agent.model : modelOptions.model;
const maxTokens = optionalChainWithEmptyCheck(
modelOptions.maxOutputTokens,
modelOptions.maxTokens,
agent.provider === EModelEndpoint.azureOpenAI ? agent.model : options.llmConfig?.model;
const maxOutputTokens = optionalChainWithEmptyCheck(
options.llmConfig?.maxOutputTokens,
options.llmConfig?.maxTokens,
0,
);
const agentMaxContextTokens = optionalChainWithEmptyCheck(
maxContextTokens,
getModelMaxTokens(tokensModel, providerEndpointMap[provider], options.endpointTokenConfig),
4096,
18000,
);
if (
@ -203,7 +203,7 @@ const initializeAgent = async ({
userMCPAuthMap,
toolContextMap,
useLegacyContent: !!options.useLegacyContent,
maxContextTokens: Math.round((agentMaxContextTokens - maxTokens) * 0.9),
maxContextTokens: Math.round((agentMaxContextTokens - maxOutputTokens) * 0.9),
};
};

4
api/server/services/Endpoints/agents/build.js
View file

@ -3,9 +3,10 @@ const { isAgentsEndpoint, removeNullishValues, Constants } = require('librechat-
const { loadAgent } = require('~/models/Agent');
const buildOptions = (req, endpoint, parsedBody, endpointType) => {
const { spec, iconURL, agent_id, instructions, ...model_parameters } = parsedBody;
const { spec, iconURL, agent_id, ...model_parameters } = parsedBody;
const agentPromise = loadAgent({
req,
spec,
agent_id: isAgentsEndpoint(endpoint) ? agent_id : Constants.EPHEMERAL_AGENT_ID,
endpoint,
model_parameters,
@ -20,7 +21,6 @@ const buildOptions = (req, endpoint, parsedBody, endpointType) => {
endpoint,
agent_id,
endpointType,
instructions,
model_parameters,
agent: agentPromise,
});

51
api/server/services/Endpoints/custom/initialize.js
View file

@ -1,4 +1,3 @@
const { Providers } = require('@librechat/agents');
const {
resolveHeaders,
isUserProvided,
@ -143,39 +142,27 @@ const initializeClient = async ({ req, res, endpointOption, optionsOnly, overrid
if (optionsOnly) {
const modelOptions = endpointOption?.model_parameters ?? {};
if (endpoint !== Providers.OLLAMA) {
clientOptions = Object.assign(
{
modelOptions,
},
clientOptions,
);
clientOptions.modelOptions.user = req.user.id;
const options = getOpenAIConfig(apiKey, clientOptions, endpoint);
if (options != null) {
options.useLegacyContent = true;
options.endpointTokenConfig = endpointTokenConfig;
}
if (!clientOptions.streamRate) {
return options;
}
options.llmConfig.callbacks = [
{
handleLLMNewToken: createHandleLLMNewToken(clientOptions.streamRate),
},
];
clientOptions = Object.assign(
{
modelOptions,
},
clientOptions,
);
clientOptions.modelOptions.user = req.user.id;
const options = getOpenAIConfig(apiKey, clientOptions, endpoint);
if (options != null) {
options.useLegacyContent = true;
options.endpointTokenConfig = endpointTokenConfig;
}
if (!clientOptions.streamRate) {
return options;
}
if (clientOptions.reverseProxyUrl) {
modelOptions.baseUrl = clientOptions.reverseProxyUrl.split('/v1')[0];
delete clientOptions.reverseProxyUrl;
}
return {
useLegacyContent: true,
llmConfig: modelOptions,
};
options.llmConfig.callbacks = [
{
handleLLMNewToken: createHandleLLMNewToken(clientOptions.streamRate),
},
];
return options;
}
const client = new OpenAIClient(apiKey, clientOptions);

2
api/server/services/Endpoints/openAI/initialize.js
View file

@ -159,7 +159,7 @@ const initializeClient = async ({
modelOptions.model = modelName;
clientOptions = Object.assign({ modelOptions }, clientOptions);
clientOptions.modelOptions.user = req.user.id;
const options = getOpenAIConfig(apiKey, clientOptions);
const options = getOpenAIConfig(apiKey, clientOptions, endpoint);
if (options != null && serverless === true) {
options.useLegacyContent = true;
}

24
api/server/services/Files/Audio/getCustomConfigSpeech.js
View file

@ -42,18 +42,26 @@ async function getCustomConfigSpeech(req, res) {
settings.advancedMode = speechTab.advancedMode;
}
if (speechTab.speechToText) {
for (const key in speechTab.speechToText) {
if (speechTab.speechToText[key] !== undefined) {
settings[key] = speechTab.speechToText[key];
if (speechTab.speechToText !== undefined) {
if (typeof speechTab.speechToText === 'boolean') {
settings.speechToText = speechTab.speechToText;
} else {
for (const key in speechTab.speechToText) {
if (speechTab.speechToText[key] !== undefined) {
settings[key] = speechTab.speechToText[key];
}
}
}
}
if (speechTab.textToSpeech) {
for (const key in speechTab.textToSpeech) {
if (speechTab.textToSpeech[key] !== undefined) {
settings[key] = speechTab.textToSpeech[key];
if (speechTab.textToSpeech !== undefined) {
if (typeof speechTab.textToSpeech === 'boolean') {
settings.textToSpeech = speechTab.textToSpeech;
} else {
for (const key in speechTab.textToSpeech) {
if (speechTab.textToSpeech[key] !== undefined) {
settings[key] = speechTab.textToSpeech[key];
}
}
}
}

21
api/server/services/Files/process.js
View file

@ -598,11 +598,22 @@ const processAgentFileUpload = async ({ req, res, metadata }) => {
if (shouldUseOCR && !(await checkCapability(req, AgentCapabilities.ocr))) {
throw new Error('OCR capability is not enabled for Agents');
} else if (shouldUseOCR) {
const { handleFileUpload: uploadOCR } = getStrategyFunctions(
appConfig?.ocr?.strategy ?? FileSources.mistral_ocr,
);
const { text, bytes, filepath: ocrFileURL } = await uploadOCR({ req, file, loadAuthValues });
return await createTextFile({ text, bytes, filepath: ocrFileURL });
try {
const { handleFileUpload: uploadOCR } = getStrategyFunctions(
appConfig?.ocr?.strategy ?? FileSources.mistral_ocr,
);
const {
text,
bytes,
filepath: ocrFileURL,
} = await uploadOCR({ req, file, loadAuthValues });
return await createTextFile({ text, bytes, filepath: ocrFileURL });
} catch (ocrError) {
logger.error(
`[processAgentFileUpload] OCR processing failed for file "${file.originalname}", falling back to text extraction:`,
ocrError,
);
}
}
const shouldUseSTT = fileConfig.checkType(

47
api/server/services/GraphApiService.js
View file

@ -159,7 +159,7 @@ const searchEntraIdPrincipals = async (accessToken, sub, query, type = 'all', li
/**
* Get current user's Entra ID group memberships from Microsoft Graph
* Uses /me/memberOf endpoint to get groups the user is a member of
* Uses /me/getMemberGroups endpoint to get transitive groups the user is a member of
* @param {string} accessToken - OpenID Connect access token
* @param {string} sub - Subject identifier
* @returns {Promise<Array<string>>} Array of group ID strings (GUIDs)
@ -167,10 +167,12 @@ const searchEntraIdPrincipals = async (accessToken, sub, query, type = 'all', li
const getUserEntraGroups = async (accessToken, sub) => {
try {
const graphClient = await createGraphClient(accessToken, sub);
const response = await graphClient
.api('/me/getMemberGroups')
.post({ securityEnabledOnly: false });
const groupsResponse = await graphClient.api('/me/memberOf').select('id').get();
return (groupsResponse.value || []).map((group) => group.id);
const groupIds = Array.isArray(response?.value) ? response.value : [];
return [...new Set(groupIds.map((groupId) => String(groupId)))];
} catch (error) {
logger.error('[getUserEntraGroups] Error fetching user groups:', error);
return [];
@ -187,13 +189,22 @@ const getUserEntraGroups = async (accessToken, sub) => {
const getUserOwnedEntraGroups = async (accessToken, sub) => {
try {
const graphClient = await createGraphClient(accessToken, sub);
const allGroupIds = [];
let nextLink = '/me/ownedObjects/microsoft.graph.group';
const groupsResponse = await graphClient
.api('/me/ownedObjects/microsoft.graph.group')
.select('id')
.get();
while (nextLink) {
const response = await graphClient.api(nextLink).select('id').top(999).get();
const groups = response?.value || [];
allGroupIds.push(...groups.map((group) => group.id));
return (groupsResponse.value || []).map((group) => group.id);
nextLink = response['@odata.nextLink']
? response['@odata.nextLink']
.replace(/^https:\/\/graph\.microsoft\.com\/v1\.0/, '')
.trim() || null
: null;
}
return allGroupIds;
} catch (error) {
logger.error('[getUserOwnedEntraGroups] Error fetching user owned groups:', error);
return [];
@ -211,21 +222,27 @@ const getUserOwnedEntraGroups = async (accessToken, sub) => {
const getGroupMembers = async (accessToken, sub, groupId) => {
try {
const graphClient = await createGraphClient(accessToken, sub);
const allMembers = [];
let nextLink = `/groups/${groupId}/members`;
const allMembers = new Set();
let nextLink = `/groups/${groupId}/transitiveMembers`;
while (nextLink) {
const membersResponse = await graphClient.api(nextLink).select('id').top(999).get();
const members = membersResponse.value || [];
allMembers.push(...members.map((member) => member.id));
const members = membersResponse?.value || [];
members.forEach((member) => {
if (typeof member?.id === 'string' && member['@odata.type'] === '#microsoft.graph.user') {
allMembers.add(member.id);
}
});
nextLink = membersResponse['@odata.nextLink']
? membersResponse['@odata.nextLink'].split('/v1.0')[1]
? membersResponse['@odata.nextLink']
.replace(/^https:\/\/graph\.microsoft\.com\/v1\.0/, '')
.trim() || null
: null;
}
return allMembers;
return Array.from(allMembers);
} catch (error) {
logger.error('[getGroupMembers] Error fetching group members:', error);
return [];

118
api/server/services/GraphApiService.spec.js
View file

@ -73,6 +73,7 @@ describe('GraphApiService', () => {
header: jest.fn().mockReturnThis(),
top: jest.fn().mockReturnThis(),
get: jest.fn(),
post: jest.fn(),
};
Client.init.mockReturnValue(mockGraphClient);
@ -514,31 +515,33 @@ describe('GraphApiService', () => {
});
describe('getUserEntraGroups', () => {
it('should fetch user groups from memberOf endpoint', async () => {
it('should fetch user groups using getMemberGroups endpoint', async () => {
const mockGroupsResponse = {
value: [
{
id: 'group-1',
},
{
id: 'group-2',
},
],
value: ['group-1', 'group-2'],
};
mockGraphClient.get.mockResolvedValue(mockGroupsResponse);
mockGraphClient.post.mockResolvedValue(mockGroupsResponse);
const result = await GraphApiService.getUserEntraGroups('token', 'user');
expect(mockGraphClient.api).toHaveBeenCalledWith('/me/memberOf');
expect(mockGraphClient.select).toHaveBeenCalledWith('id');
expect(mockGraphClient.api).toHaveBeenCalledWith('/me/getMemberGroups');
expect(mockGraphClient.post).toHaveBeenCalledWith({ securityEnabledOnly: false });
expect(result).toEqual(['group-1', 'group-2']);
});
it('should deduplicate returned group ids', async () => {
mockGraphClient.post.mockResolvedValue({
value: ['group-1', 'group-2', 'group-1'],
});
const result = await GraphApiService.getUserEntraGroups('token', 'user');
expect(result).toHaveLength(2);
expect(result).toEqual(['group-1', 'group-2']);
});
it('should return empty array on error', async () => {
mockGraphClient.get.mockRejectedValue(new Error('API error'));
mockGraphClient.post.mockRejectedValue(new Error('API error'));
const result = await GraphApiService.getUserEntraGroups('token', 'user');
@ -550,7 +553,7 @@ describe('GraphApiService', () => {
value: [],
};
mockGraphClient.get.mockResolvedValue(mockGroupsResponse);
mockGraphClient.post.mockResolvedValue(mockGroupsResponse);
const result = await GraphApiService.getUserEntraGroups('token', 'user');
@ -558,7 +561,7 @@ describe('GraphApiService', () => {
});
it('should handle missing value property', async () => {
mockGraphClient.get.mockResolvedValue({});
mockGraphClient.post.mockResolvedValue({});
const result = await GraphApiService.getUserEntraGroups('token', 'user');
@ -566,6 +569,89 @@ describe('GraphApiService', () => {
});
});
describe('getUserOwnedEntraGroups', () => {
it('should fetch owned groups with pagination support', async () => {
const firstPage = {
value: [
{
id: 'owned-group-1',
},
],
'@odata.nextLink':
'https://graph.microsoft.com/v1.0/me/ownedObjects/microsoft.graph.group?$skiptoken=xyz',
};
const secondPage = {
value: [
{
id: 'owned-group-2',
},
],
};
mockGraphClient.get.mockResolvedValueOnce(firstPage).mockResolvedValueOnce(secondPage);
const result = await GraphApiService.getUserOwnedEntraGroups('token', 'user');
expect(mockGraphClient.api).toHaveBeenNthCalledWith(
1,
'/me/ownedObjects/microsoft.graph.group',
);
expect(mockGraphClient.api).toHaveBeenNthCalledWith(
2,
'/me/ownedObjects/microsoft.graph.group?$skiptoken=xyz',
);
expect(mockGraphClient.top).toHaveBeenCalledWith(999);
expect(mockGraphClient.get).toHaveBeenCalledTimes(2);
expect(result).toEqual(['owned-group-1', 'owned-group-2']);
});
it('should return empty array on error', async () => {
mockGraphClient.get.mockRejectedValue(new Error('API error'));
const result = await GraphApiService.getUserOwnedEntraGroups('token', 'user');
expect(result).toEqual([]);
});
});
describe('getGroupMembers', () => {
it('should fetch transitive members and include only users', async () => {
const firstPage = {
value: [
{ id: 'user-1', '@odata.type': '#microsoft.graph.user' },
{ id: 'child-group', '@odata.type': '#microsoft.graph.group' },
],
'@odata.nextLink':
'https://graph.microsoft.com/v1.0/groups/group-id/transitiveMembers?$skiptoken=abc',
};
const secondPage = {
value: [{ id: 'user-2', '@odata.type': '#microsoft.graph.user' }],
};
mockGraphClient.get.mockResolvedValueOnce(firstPage).mockResolvedValueOnce(secondPage);
const result = await GraphApiService.getGroupMembers('token', 'user', 'group-id');
expect(mockGraphClient.api).toHaveBeenNthCalledWith(1, '/groups/group-id/transitiveMembers');
expect(mockGraphClient.api).toHaveBeenNthCalledWith(
2,
'/groups/group-id/transitiveMembers?$skiptoken=abc',
);
expect(mockGraphClient.top).toHaveBeenCalledWith(999);
expect(result).toEqual(['user-1', 'user-2']);
});
it('should return empty array on error', async () => {
mockGraphClient.get.mockRejectedValue(new Error('API error'));
const result = await GraphApiService.getGroupMembers('token', 'user', 'group-id');
expect(result).toEqual([]);
});
});
describe('testGraphApiAccess', () => {
beforeEach(() => {
jest.clearAllMocks();

12
api/server/services/ModelService.js
View file

@ -39,6 +39,8 @@ const { openAIApiKey, userProvidedOpenAI } = require('./Config/EndpointService')
* @param {boolean} [params.userIdQuery=false] - Whether to send the user ID as a query parameter.
* @param {boolean} [params.createTokenConfig=true] - Whether to create a token configuration from the API response.
* @param {string} [params.tokenKey] - The cache key to save the token configuration. Uses `name` if omitted.
* @param {Record<string, string>} [params.headers] - Optional headers for the request.
* @param {Partial<IUser>} [params.userObject] - Optional user object for header resolution.
* @returns {Promise<string[]>} A promise that resolves to an array of model identifiers.
* @async
*/
@ -52,6 +54,8 @@ const fetchModels = async ({
userIdQuery = false,
createTokenConfig = true,
tokenKey,
headers,
userObject,
}) => {
let models = [];
const baseURL = direct ? extractBaseURL(_baseURL) : _baseURL;
@ -65,7 +69,13 @@ const fetchModels = async ({
}
if (name && name.toLowerCase().startsWith(Providers.OLLAMA)) {
return await OllamaClient.fetchModels(baseURL);
try {
return await OllamaClient.fetchModels(baseURL, { headers, user: userObject });
} catch (ollamaError) {
const logMessage =
'Failed to fetch models from Ollama API. Attempting to fetch via OpenAI-compatible endpoint.';
logAxiosError({ message: logMessage, error: ollamaError });
}
}
try {

56
api/server/services/ModelService.spec.js
View file

@ -1,5 +1,5 @@
const axios = require('axios');
const { logger } = require('@librechat/data-schemas');
const { logAxiosError, resolveHeaders } = require('@librechat/api');
const { EModelEndpoint, defaultModels } = require('librechat-data-provider');
const {
@ -18,6 +18,8 @@ jest.mock('@librechat/api', () => {
processModelData: jest.fn((...args) => {
return originalUtils.processModelData(...args);
}),
logAxiosError: jest.fn(),
resolveHeaders: jest.fn((options) => options?.headers || {}),
};
});
@ -277,12 +279,51 @@ describe('fetchModels with Ollama specific logic', () => {
expect(models).toEqual(['Ollama-Base', 'Ollama-Advanced']);
expect(axios.get).toHaveBeenCalledWith('https://api.ollama.test.com/api/tags', {
headers: {},
timeout: 5000,
});
});
it('should handle errors gracefully when fetching Ollama models fails', async () => {
axios.get.mockRejectedValue(new Error('Network error'));
it('should pass headers and user object to Ollama fetchModels', async () => {
const customHeaders = {
'Content-Type': 'application/json',
Authorization: 'Bearer custom-token',
};
const userObject = {
id: 'user789',
email: 'test@example.com',
};
resolveHeaders.mockReturnValueOnce(customHeaders);
const models = await fetchModels({
user: 'user789',
apiKey: 'testApiKey',
baseURL: 'https://api.ollama.test.com',
name: 'ollama',
headers: customHeaders,
userObject,
});
expect(models).toEqual(['Ollama-Base', 'Ollama-Advanced']);
expect(resolveHeaders).toHaveBeenCalledWith({
headers: customHeaders,
user: userObject,
});
expect(axios.get).toHaveBeenCalledWith('https://api.ollama.test.com/api/tags', {
headers: customHeaders,
timeout: 5000,
});
});
it('should handle errors gracefully when fetching Ollama models fails and fallback to OpenAI-compatible fetch', async () => {
axios.get.mockRejectedValueOnce(new Error('Ollama API error'));
axios.get.mockResolvedValueOnce({
data: {
data: [{ id: 'fallback-model-1' }, { id: 'fallback-model-2' }],
},
});
const models = await fetchModels({
user: 'user789',
apiKey: 'testApiKey',
@ -290,8 +331,13 @@ describe('fetchModels with Ollama specific logic', () => {
name: 'OllamaAPI',
});
expect(models).toEqual([]);
expect(logger.error).toHaveBeenCalled();
expect(models).toEqual(['fallback-model-1', 'fallback-model-2']);
expect(logAxiosError).toHaveBeenCalledWith({
message:
'Failed to fetch models from Ollama API. Attempting to fetch via OpenAI-compatible endpoint.',
error: expect.any(Error),
});
expect(axios.get).toHaveBeenCalledTimes(2);
});
it('should return an empty array if no baseURL is provided', async () => {

14
api/strategies/openidStrategy.js
View file

@ -357,16 +357,18 @@ async function setupOpenId() {
};
const appConfig = await getAppConfig();
if (!isEmailDomainAllowed(userinfo.email, appConfig?.registration?.allowedDomains)) {
/** Azure AD sometimes doesn't return email, use preferred_username as fallback */
const email = userinfo.email || userinfo.preferred_username || userinfo.upn;
if (!isEmailDomainAllowed(email, appConfig?.registration?.allowedDomains)) {
logger.error(
`[OpenID Strategy] Authentication blocked - email domain not allowed [Email: ${userinfo.email}]`,
`[OpenID Strategy] Authentication blocked - email domain not allowed [Email: ${email}]`,
);
return done(null, false, { message: 'Email domain not allowed' });
}
const result = await findOpenIDUser({
findUser,
email: claims.email,
email: email,
openidId: claims.sub,
idOnTheSource: claims.oid,
strategyName: 'openidStrategy',
@ -433,7 +435,7 @@ async function setupOpenId() {
provider: 'openid',
openidId: userinfo.sub,
username,
email: userinfo.email || '',
email: email || '',
emailVerified: userinfo.email_verified || false,
name: fullName,
idOnTheSource: userinfo.oid,
@ -447,8 +449,8 @@ async function setupOpenId() {
user.username = username;
user.name = fullName;
user.idOnTheSource = userinfo.oid;
if (userinfo.email && userinfo.email !== user.email) {
user.email = userinfo.email;
if (email && email !== user.email) {
user.email = email;
user.emailVerified = userinfo.email_verified || false;
}
}

180
api/utils/tokens.spec.js
View file

@ -186,6 +186,19 @@ describe('getModelMaxTokens', () => {
);
});
test('should return correct tokens for gpt-5-pro matches', () => {
expect(getModelMaxTokens('gpt-5-pro')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-5-pro']);
expect(getModelMaxTokens('gpt-5-pro-preview')).toBe(
maxTokensMap[EModelEndpoint.openAI]['gpt-5-pro'],
);
expect(getModelMaxTokens('openai/gpt-5-pro')).toBe(
maxTokensMap[EModelEndpoint.openAI]['gpt-5-pro'],
);
expect(getModelMaxTokens('gpt-5-pro-2025-01-30')).toBe(
maxTokensMap[EModelEndpoint.openAI]['gpt-5-pro'],
);
});
test('should return correct tokens for Anthropic models', () => {
const models = [
'claude-2.1',
@ -469,7 +482,7 @@ describe('getModelMaxTokens', () => {
test('should return correct max output tokens for GPT-5 models', () => {
const { getModelMaxOutputTokens } = require('@librechat/api');
['gpt-5', 'gpt-5-mini', 'gpt-5-nano'].forEach((model) => {
['gpt-5', 'gpt-5-mini', 'gpt-5-nano', 'gpt-5-pro'].forEach((model) => {
expect(getModelMaxOutputTokens(model)).toBe(maxOutputTokensMap[EModelEndpoint.openAI][model]);
expect(getModelMaxOutputTokens(model, EModelEndpoint.openAI)).toBe(
maxOutputTokensMap[EModelEndpoint.openAI][model],
@ -582,6 +595,13 @@ describe('matchModelName', () => {
expect(matchModelName('gpt-5-nano-2025-01-30')).toBe('gpt-5-nano');
});
it('should return the closest matching key for gpt-5-pro matches', () => {
expect(matchModelName('openai/gpt-5-pro')).toBe('gpt-5-pro');
expect(matchModelName('gpt-5-pro-preview')).toBe('gpt-5-pro');
expect(matchModelName('gpt-5-pro-2025-01-30')).toBe('gpt-5-pro');
expect(matchModelName('gpt-5-pro-2025-01-30-0130')).toBe('gpt-5-pro');
});
// Tests for Google models
it('should return the exact model name if it exists in maxTokensMap - Google models', () => {
expect(matchModelName('text-bison-32k', EModelEndpoint.google)).toBe('text-bison-32k');
@ -832,6 +852,49 @@ describe('Claude Model Tests', () => {
);
});
it('should return correct context length for Claude Haiku 4.5', () => {
expect(getModelMaxTokens('claude-haiku-4-5', EModelEndpoint.anthropic)).toBe(
maxTokensMap[EModelEndpoint.anthropic]['claude-haiku-4-5'],
);
expect(getModelMaxTokens('claude-haiku-4-5')).toBe(
maxTokensMap[EModelEndpoint.anthropic]['claude-haiku-4-5'],
);
});
it('should handle Claude Haiku 4.5 model name variations', () => {
const modelVariations = [
'claude-haiku-4-5',
'claude-haiku-4-5-20250420',
'claude-haiku-4-5-latest',
'anthropic/claude-haiku-4-5',
'claude-haiku-4-5/anthropic',
'claude-haiku-4-5-preview',
];
modelVariations.forEach((model) => {
const modelKey = findMatchingPattern(model, maxTokensMap[EModelEndpoint.anthropic]);
expect(modelKey).toBe('claude-haiku-4-5');
expect(getModelMaxTokens(model, EModelEndpoint.anthropic)).toBe(
maxTokensMap[EModelEndpoint.anthropic]['claude-haiku-4-5'],
);
});
});
it('should match model names correctly for Claude Haiku 4.5', () => {
const modelVariations = [
'claude-haiku-4-5',
'claude-haiku-4-5-20250420',
'claude-haiku-4-5-latest',
'anthropic/claude-haiku-4-5',
'claude-haiku-4-5/anthropic',
'claude-haiku-4-5-preview',
];
modelVariations.forEach((model) => {
expect(matchModelName(model, EModelEndpoint.anthropic)).toBe('claude-haiku-4-5');
});
});
it('should handle Claude 4 model name variations with different prefixes and suffixes', () => {
const modelVariations = [
'claude-sonnet-4',
@ -924,6 +987,121 @@ describe('Kimi Model Tests', () => {
});
});
describe('Qwen3 Model Tests', () => {
describe('getModelMaxTokens', () => {
test('should return correct tokens for Qwen3 base pattern', () => {
expect(getModelMaxTokens('qwen3')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3']);
});
test('should return correct tokens for qwen3-4b (falls back to qwen3)', () => {
expect(getModelMaxTokens('qwen3-4b')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3']);
});
test('should return correct tokens for Qwen3 base models', () => {
expect(getModelMaxTokens('qwen3-8b')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3-8b']);
expect(getModelMaxTokens('qwen3-14b')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3-14b']);
expect(getModelMaxTokens('qwen3-32b')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3-32b']);
expect(getModelMaxTokens('qwen3-235b-a22b')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-235b-a22b'],
);
});
test('should return correct tokens for Qwen3 VL (Vision-Language) models', () => {
expect(getModelMaxTokens('qwen3-vl-8b-thinking')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-vl-8b-thinking'],
);
expect(getModelMaxTokens('qwen3-vl-8b-instruct')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-vl-8b-instruct'],
);
expect(getModelMaxTokens('qwen3-vl-30b-a3b')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-vl-30b-a3b'],
);
expect(getModelMaxTokens('qwen3-vl-235b-a22b')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-vl-235b-a22b'],
);
});
test('should return correct tokens for Qwen3 specialized models', () => {
expect(getModelMaxTokens('qwen3-max')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3-max']);
expect(getModelMaxTokens('qwen3-coder')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-coder'],
);
expect(getModelMaxTokens('qwen3-coder-30b-a3b')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-coder-30b-a3b'],
);
expect(getModelMaxTokens('qwen3-coder-plus')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-coder-plus'],
);
expect(getModelMaxTokens('qwen3-coder-flash')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-coder-flash'],
);
expect(getModelMaxTokens('qwen3-next-80b-a3b')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-next-80b-a3b'],
);
});
test('should handle Qwen3 models with provider prefixes', () => {
expect(getModelMaxTokens('alibaba/qwen3')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3']);
expect(getModelMaxTokens('alibaba/qwen3-4b')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3'],
);
expect(getModelMaxTokens('qwen/qwen3-8b')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-8b'],
);
expect(getModelMaxTokens('openrouter/qwen3-max')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-max'],
);
expect(getModelMaxTokens('alibaba/qwen3-vl-8b-instruct')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-vl-8b-instruct'],
);
expect(getModelMaxTokens('qwen/qwen3-coder')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-coder'],
);
});
test('should handle Qwen3 models with suffixes', () => {
expect(getModelMaxTokens('qwen3-preview')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3']);
expect(getModelMaxTokens('qwen3-4b-preview')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3'],
);
expect(getModelMaxTokens('qwen3-8b-latest')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-8b'],
);
expect(getModelMaxTokens('qwen3-max-2024')).toBe(
maxTokensMap[EModelEndpoint.openAI]['qwen3-max'],
);
});
});
describe('matchModelName', () => {
test('should match exact Qwen3 model names', () => {
expect(matchModelName('qwen3')).toBe('qwen3');
expect(matchModelName('qwen3-4b')).toBe('qwen3');
expect(matchModelName('qwen3-8b')).toBe('qwen3-8b');
expect(matchModelName('qwen3-vl-8b-thinking')).toBe('qwen3-vl-8b-thinking');
expect(matchModelName('qwen3-max')).toBe('qwen3-max');
expect(matchModelName('qwen3-coder')).toBe('qwen3-coder');
});
test('should match Qwen3 model variations with provider prefixes', () => {
expect(matchModelName('alibaba/qwen3')).toBe('qwen3');
expect(matchModelName('alibaba/qwen3-4b')).toBe('qwen3');
expect(matchModelName('qwen/qwen3-8b')).toBe('qwen3-8b');
expect(matchModelName('openrouter/qwen3-max')).toBe('qwen3-max');
expect(matchModelName('alibaba/qwen3-vl-8b-instruct')).toBe('qwen3-vl-8b-instruct');
expect(matchModelName('qwen/qwen3-coder')).toBe('qwen3-coder');
});
test('should match Qwen3 model variations with suffixes', () => {
expect(matchModelName('qwen3-preview')).toBe('qwen3');
expect(matchModelName('qwen3-4b-preview')).toBe('qwen3');
expect(matchModelName('qwen3-8b-latest')).toBe('qwen3-8b');
expect(matchModelName('qwen3-max-2024')).toBe('qwen3-max');
expect(matchModelName('qwen3-coder-v1')).toBe('qwen3-coder');
});
});
});
describe('GLM Model Tests (Zhipu AI)', () => {
describe('getModelMaxTokens', () => {
test('should return correct tokens for GLM models', () => {