docs: add AGENTS.md for project structure and development guidelines

* 📦 chore: update vite to v6.4.1

* 📦 chore: update @playwright/test to v1.56.1

AGENTS.md

@@ -0,0 +1,233 @@
+# LibreChat AGENTS.md
+
+LibreChat is a multi-provider AI chat platform featuring agents, tools, and multimodal interactions. This file provides guidance for AI coding agents working on the codebase.
+
+## Project Overview
+
+LibreChat is a monorepo-based full-stack application providing a unified interface for multiple AI models and providers (OpenAI, Anthropic, Google Gemini, Azure, AWS Bedrock, Groq, Mistral, and more).
+
+## Workspace Structure
+
+LibreChat uses npm workspaces to organize code into distinct packages with clear responsibilities:
+
+```
+LibreChat/
+├── api/                          # Express.js backend (CJS, transitioning to TypeScript)
+├── client/                       # React/Vite frontend application
+└── packages/
+    ├── api/                      # @librechat/api - Backend TypeScript package
+    ├── client/                   # @librechat/client - Frontend shared components
+    ├── data-provider/            # librechat-data-provider - Shared frontend/backend
+    └── data-schemas/             # @librechat/data-schemas - Backend schemas & models
+```
+
+### Workspace Responsibilities
+
+#### `/api` - Express.js Backend
+- **Language**: CommonJS JavaScript (transitioning to TypeScript via shared packages)
+- **Purpose**: Main Express.js server, routes, middleware, legacy services
+- **Note**: Legacy workspace; **new backend logic should go in `packages/api` instead**
+- **Uses**: `librechat-data-provider`, `@librechat/api`, `@librechat/data-schemas`
+
+#### `/client` - React Frontend Application
+- **Language**: TypeScript + React
+- **Purpose**: Main web application UI
+- **Uses**: `librechat-data-provider`, `@librechat/client`
+
+#### `/packages/api` - `@librechat/api`
+- **Language**: TypeScript (full support)
+- **Purpose**: Backend-only package for all new backend logic
+- **Used by**: `/api` workspace and potentially other backend projects
+- **Key Modules**: Agents, MCP, tools, file handling, endpoints, authentication, caching, middleware
+- **Critical**: **All new backend logic should be coded here first and foremost for full TypeScript support**
+- **Depends on**: `@librechat/data-schemas`
+
+#### `/packages/client` - `@librechat/client`
+- **Language**: TypeScript + React
+- **Purpose**: Reusable React components, hooks, and utilities
+- **Used by**: `/client` workspace and other LibreChat team frontend repositories
+- **Exports**: Common components, hooks, SVG icons, theme utilities, localization
+
+#### `/packages/data-provider` - `librechat-data-provider`
+- **Language**: TypeScript
+- **Purpose**: **App-wide shared package** used by both frontend and backend
+- **Scope**: Universal - used everywhere
+- **Exports**: Data services, API endpoints, type definitions, utilities, React Query hooks
+- **Note**: Foundation package that all other workspaces depend on
+
+#### `/packages/data-schemas` - `@librechat/data-schemas`
+- **Language**: TypeScript
+- **Purpose**: Backend-only schemas, models, and data validation
+- **Used by**: Backend workspaces only (`@librechat/api`, `/api`)
+- **Exports**: Mongoose models, Zod schemas, database utilities, configuration schemas
+
+## Build System & Dependencies
+
+### Build Order
+
+The build system has a specific dependency chain that must be followed:
+
+```bash
+# Full frontend build command:
+npm run frontend
+```
+
+**Execution order:**
+1. `librechat-data-provider` - Foundation package (all depend on this)
+2. `@librechat/data-schemas` - Required by `@librechat/api`
+3. `@librechat/api` - Backend TypeScript package
+4. `@librechat/client` - Frontend shared components
+5. `/client` - Final frontend compilation
+
+### Individual Build Commands
+
+Packages can be built separately as needed:
+
+```bash
+npm run build:data-provider      # Build librechat-data-provider
+npm run build:data-schemas       # Build @librechat/data-schemas
+npm run build:api                # Build @librechat/api
+npm run build:client-package     # Build @librechat/client
+npm run build:client             # Build /client frontend app
+npm run build:packages           # Build all packages (excludes /client app)
+```
+
+**Note**: Not all packages need rebuilding for every change - only rebuild when files in that specific workspace are modified.
+
+## Development Workflow
+
+### Running Development Servers
+
+```bash
+# Backend
+npm run backend:dev              # Runs /api workspace with nodemon
+
+# Frontend  
+npm run frontend:dev             # Runs /client with Vite dev server
+
+# Both (not recommended for active development)
+npm run dev
+```
+
+### Where to Place New Code
+
+#### Backend Logic
+- **Primary location**: `/packages/api/src/` - Full TypeScript support
+- **Legacy location**: `/api/` - Only for modifying existing CJS code
+- **Strategy**: Prefer `@librechat/api` for all new features, utilities, and services
+
+#### Frontend Components
+- **Reusable components**: `/packages/client/src/components/`
+- **App-specific components**: `/client/src/components/`
+- **Strategy**: If it could be reused in other frontend projects, put it in `@librechat/client`
+
+#### Shared Types & Utilities
+- **Universal (frontend + backend)**: `/packages/data-provider/src/`
+- **Backend-only**: `/packages/data-schemas/src/` or `/packages/api/src/`
+- **Frontend-only**: `/packages/client/src/`
+
+#### Database Models & Schemas
+- **Always**: `/packages/data-schemas/src/models/` or `/packages/data-schemas/src/schema/`
+
+## Technology Stack
+
+### Backend
+- **Runtime**: Node.js
+- **Framework**: Express.js
+- **Database**: MongoDB with Mongoose ODM
+- **Authentication**: Passport.js (OAuth2, OpenID, LDAP, SAML, JWT)
+- **AI Integration**: LangChain, direct SDK integrations
+- **Streaming**: Server-Sent Events (SSE)
+
+### Frontend
+- **Framework**: React 18
+- **Build Tool**: Vite
+- **State Management**: Recoil
+- **Styling**: TailwindCSS
+- **UI Components**: Radix UI, Headless UI
+- **Data Fetching**: TanStack Query (React Query)
+- **HTTP Client**: Axios
+
+### Package Manager
+- **Primary**: npm (workspaces)
+- **Alternative**: pnpm (compatible), bun (experimental scripts available)
+
+## Configuration
+
+### Environment Variables
+- `.env` - Local development (never commit)
+- `docker-compose.override.yml.example` - Example for Docker environment configuration
+- Validate on server startup
+
+### librechat.yaml
+Main configuration for:
+- AI provider endpoints
+- Model configurations
+- Agent and tool settings
+- Authentication options
+
+## Code Quality & Standards
+
+### General Guidelines
+- Use TypeScript for all new code (especially in `packages/`)
+- Follow existing ESLint/Prettier configurations (formatting issues will be fixed manually)
+- Keep functions focused and modular
+- Handle errors appropriately with proper HTTP status codes
+
+### File Naming
+- React components: `PascalCase.tsx` (e.g., `ChatInterface.tsx`)
+- Utilities: `camelCase.ts` (e.g., `formatMessage.ts`)
+- Test files: `*.spec.ts` or `*.test.ts`
+
+## Key Architectural Patterns
+
+### Multi-Provider Pattern
+Abstract AI provider implementations to support multiple services uniformly:
+- Provider services implement common interfaces
+- Handle streaming via SSE
+- Support both completion and chat endpoints
+
+### Agent System
+- Built on LangChain
+- Agent definitions in `packages/api/src/agents/`
+- Tools in `packages/api/src/tools/`
+- MCP (Model Context Protocol) support in `packages/api/src/mcp/`
+
+### Data Layer
+- `librechat-data-provider` provides unified data access
+- React Query for frontend data fetching
+- Backend services use Mongoose models from `@librechat/data-schemas`
+
+## Testing
+
+```bash
+npm run test:api                 # Backend tests
+npm run test:client              # Frontend tests
+npm run e2e                      # Playwright E2E tests
+```
+
+## Common Pitfalls
+
+1. **Wrong workspace for backend code**: New backend logic belongs in `/packages/api`, not `/api`
+  - The `/api` workspace is still necessary as it's used to run the Express.js server, but all new logic should be written in TypeScript in `/packages/api` as much as possible. Existing logic should also be converted to TypeScript if possible.
+2. **Build order matters**: Can't build `@librechat/api` before `@librechat/data-schemas`
+3. **Unnecessary rebuilds**: Only rebuild packages when their source files change
+4. **Import paths**: Use package names (`@librechat/api`) not relative paths across workspaces
+5. **TypeScript vs CJS**: `/api` is still CJS; use `packages/api` for TypeScript
+
+## Getting Help
+
+- **Documentation**: https://docs.librechat.ai
+- **Discord**: Active community support
+- **GitHub Issues**: Bug reports and feature requests
+- **Discussions**: General questions and ideas
+
+---
+
+**Remember**: The monorepo structure exists to enforce separation of concerns. Respect workspace boundaries and build dependencies. When in doubt about where code should live, consider:
+- Is it backend logic? → `packages/api/src/`
+- Is it a database model? → `packages/data-schemas/src/`
+- Is it shared between frontend/backend? → `packages/data-provider/src/`
+- Is it a reusable React component? → `packages/client/src/`
+- Is it app-specific UI? → `client/src/`
+

api/models/tx.js

@@ -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;

api/models/tx.spec.js

@@ -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([]);
+  });
+});

api/package.json

@@ -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": "^2.4.86",
     "@librechat/api": "*",
     "@librechat/data-schemas": "*",
     "@microsoft/microsoft-graph-client": "^3.0.7",

api/server/controllers/AuthController.js

@@ -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) {

api/server/services/Endpoints/agents/agent.js

@@ -143,7 +143,7 @@ const initializeAgent = async ({
   const agentMaxContextTokens = optionalChainWithEmptyCheck(
     maxContextTokens,
     getModelMaxTokens(tokensModel, providerEndpointMap[provider], options.endpointTokenConfig),
-    4096,
+    18000,
   );
 
   if (

api/utils/tokens.spec.js

@@ -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', () => {

client/package.json

@@ -149,7 +149,7 @@
     "tailwindcss": "^3.4.1",
     "ts-jest": "^29.2.5",
     "typescript": "^5.3.3",
-    "vite": "^6.3.6",
+    "vite": "^6.4.1",
     "vite-plugin-compression2": "^2.2.1",
     "vite-plugin-node-polyfills": "^0.23.0",
     "vite-plugin-pwa": "^0.21.2"

client/src/App.jsx

@@ -1,3 +1,4 @@
+import { useEffect } from 'react';
 import { RecoilRoot } from 'recoil';
 import { DndProvider } from 'react-dnd';
 import { RouterProvider } from 'react-router-dom';
@@ -8,6 +9,7 @@ import { Toast, ThemeProvider, ToastProvider } from '@librechat/client';
 import { QueryClient, QueryClientProvider, QueryCache } from '@tanstack/react-query';
 import { ScreenshotProvider, useApiErrorBoundary } from './hooks';
 import { getThemeFromEnv } from './utils/getThemeFromEnv';
+import { initializeFontSize } from '~/store/fontSize';
 import { LiveAnnouncer } from '~/a11y';
 import { router } from './routes';
 
@@ -24,6 +26,10 @@ const App = () => {
     }),
   });
 
+  useEffect(() => {
+    initializeFontSize();
+  }, []);
+
   // Load theme from environment variables if available
   const envTheme = getThemeFromEnv();
 

client/src/components/Agents/AgentDetail.tsx

@@ -11,9 +11,9 @@ import {
   AgentListResponse,
 } from 'librechat-data-provider';
 import type t from 'librechat-data-provider';
+import { renderAgentAvatar, clearMessagesCache } from '~/utils';
 import { useLocalize, useDefaultConvo } from '~/hooks';
 import { useChatContext } from '~/Providers';
-import { renderAgentAvatar } from '~/utils';
 
 interface SupportContact {
   name?: string;
@@ -56,10 +56,7 @@ const AgentDetail: React.FC<AgentDetailProps> = ({ agent, isOpen, onClose }) =>
 
       localStorage.setItem(`${LocalStorageKeys.AGENT_ID_PREFIX}0`, agent.id);
 
-      queryClient.setQueryData<t.TMessage[]>(
-        [QueryKeys.messages, conversation?.conversationId ?? Constants.NEW_CONVO],
-        [],
-      );
+      clearMessagesCache(queryClient, conversation?.conversationId);
       queryClient.invalidateQueries([QueryKeys.messages]);
 
       /** Template with agent configuration */

client/src/components/Agents/Marketplace.tsx

@@ -4,7 +4,7 @@ import { useOutletContext } from 'react-router-dom';
 import { useQueryClient } from '@tanstack/react-query';
 import { useSearchParams, useParams, useNavigate } from 'react-router-dom';
 import { TooltipAnchor, Button, NewChatIcon, useMediaQuery } from '@librechat/client';
-import { PermissionTypes, Permissions, QueryKeys, Constants } from 'librechat-data-provider';
+import { PermissionTypes, Permissions, QueryKeys } from 'librechat-data-provider';
 import type t from 'librechat-data-provider';
 import type { ContextType } from '~/common';
 import { useDocumentTitle, useHasAccess, useLocalize, TranslationKeys } from '~/hooks';
@@ -13,11 +13,11 @@ import MarketplaceAdminSettings from './MarketplaceAdminSettings';
 import { SidePanelProvider, useChatContext } from '~/Providers';
 import { SidePanelGroup } from '~/components/SidePanel';
 import { OpenSidebar } from '~/components/Chat/Menus';
+import { cn, clearMessagesCache } from '~/utils';
 import CategoryTabs from './CategoryTabs';
 import AgentDetail from './AgentDetail';
 import SearchBar from './SearchBar';
 import AgentGrid from './AgentGrid';
-import { cn } from '~/utils';
 import store from '~/store';
 
 interface AgentMarketplaceProps {
@@ -224,10 +224,7 @@ const AgentMarketplace: React.FC<AgentMarketplaceProps> = ({ className = '' }) =
       window.open('/c/new', '_blank');
       return;
     }
-    queryClient.setQueryData<t.TMessage[]>(
-      [QueryKeys.messages, conversation?.conversationId ?? Constants.NEW_CONVO],
-      [],
-    );
+    clearMessagesCache(queryClient, conversation?.conversationId);
     queryClient.invalidateQueries([QueryKeys.messages]);
     newConversation();
   };

client/src/components/Chat/Menus/HeaderNewChat.tsx

@@ -1,8 +1,8 @@
+import { QueryKeys } from 'librechat-data-provider';
 import { useQueryClient } from '@tanstack/react-query';
-import { QueryKeys, Constants } from 'librechat-data-provider';
 import { TooltipAnchor, Button, NewChatIcon } from '@librechat/client';
-import type { TMessage } from 'librechat-data-provider';
 import { useChatContext } from '~/Providers';
+import { clearMessagesCache } from '~/utils';
 import { useLocalize } from '~/hooks';
 
 export default function HeaderNewChat() {
@@ -15,10 +15,7 @@ export default function HeaderNewChat() {
       window.open('/c/new', '_blank');
       return;
     }
-    queryClient.setQueryData<TMessage[]>(
-      [QueryKeys.messages, conversation?.conversationId ?? Constants.NEW_CONVO],
-      [],
-    );
+    clearMessagesCache(queryClient, conversation?.conversationId);
     queryClient.invalidateQueries([QueryKeys.messages]);
     newConversation();
   };

client/src/components/Chat/Messages/MessageParts.tsx

@@ -1,10 +1,12 @@
 import React, { useMemo } from 'react';
+import { useAtomValue } from 'jotai';
 import { useRecoilValue } from 'recoil';
 import type { TMessageContentParts } from 'librechat-data-provider';
 import type { TMessageProps, TMessageIcon } from '~/common';
 import { useMessageHelpers, useLocalize, useAttachments } from '~/hooks';
 import MessageIcon from '~/components/Chat/Messages/MessageIcon';
 import ContentParts from './Content/ContentParts';
+import { fontSizeAtom } from '~/store/fontSize';
 import SiblingSwitch from './SiblingSwitch';
 import MultiMessage from './MultiMessage';
 import HoverButtons from './HoverButtons';
@@ -36,7 +38,7 @@ export default function Message(props: TMessageProps) {
     regenerateMessage,
   } = useMessageHelpers(props);
 
-  const fontSize = useRecoilValue(store.fontSize);
+  const fontSize = useAtomValue(fontSizeAtom);
   const maximizeChatSpace = useRecoilValue(store.maximizeChatSpace);
   const { children, messageId = null, isCreatedByUser } = message ?? {};
 

client/src/components/Chat/Messages/MessagesView.tsx

@@ -1,10 +1,12 @@
 import { useState } from 'react';
+import { useAtomValue } from 'jotai';
 import { useRecoilValue } from 'recoil';
 import { CSSTransition } from 'react-transition-group';
 import type { TMessage } from 'librechat-data-provider';
 import { useScreenshot, useMessageScrolling, useLocalize } from '~/hooks';
 import ScrollToBottom from '~/components/Messages/ScrollToBottom';
 import { MessagesViewProvider } from '~/Providers';
+import { fontSizeAtom } from '~/store/fontSize';
 import MultiMessage from './MultiMessage';
 import { cn } from '~/utils';
 import store from '~/store';
@@ -15,7 +17,7 @@ function MessagesViewContent({
   messagesTree?: TMessage[] | null;
 }) {
   const localize = useLocalize();
-  const fontSize = useRecoilValue(store.fontSize);
+  const fontSize = useAtomValue(fontSizeAtom);
   const { screenshotTargetRef } = useScreenshot();
   const scrollButtonPreference = useRecoilValue(store.showScrollButton);
   const [currentEditId, setCurrentEditId] = useState<number | string | null>(-1);

client/src/components/Chat/Messages/SearchMessage.tsx

@@ -1,10 +1,12 @@
 import { useMemo } from 'react';
+import { useAtomValue } from 'jotai';
 import { useRecoilValue } from 'recoil';
 import { useAuthContext, useLocalize } from '~/hooks';
 import type { TMessageProps, TMessageIcon } from '~/common';
 import MinimalHoverButtons from '~/components/Chat/Messages/MinimalHoverButtons';
 import Icon from '~/components/Chat/Messages/MessageIcon';
 import SearchContent from './Content/SearchContent';
+import { fontSizeAtom } from '~/store/fontSize';
 import SearchButtons from './SearchButtons';
 import SubRow from './SubRow';
 import { cn } from '~/utils';
@@ -34,8 +36,8 @@ const MessageBody = ({ message, messageLabel, fontSize }) => (
 );
 
 export default function SearchMessage({ message }: Pick<TMessageProps, 'message'>) {
+  const fontSize = useAtomValue(fontSizeAtom);
   const UsernameDisplay = useRecoilValue<boolean>(store.UsernameDisplay);
-  const fontSize = useRecoilValue(store.fontSize);
   const { user } = useAuthContext();
   const localize = useLocalize();
 

client/src/components/Chat/Messages/ui/MessageRender.tsx

@@ -1,4 +1,5 @@
 import React, { useCallback, useMemo, memo } from 'react';
+import { useAtomValue } from 'jotai';
 import { useRecoilValue } from 'recoil';
 import { type TMessage } from 'librechat-data-provider';
 import type { TMessageProps, TMessageIcon } from '~/common';
@@ -9,6 +10,7 @@ import HoverButtons from '~/components/Chat/Messages/HoverButtons';
 import MessageIcon from '~/components/Chat/Messages/MessageIcon';
 import { Plugin } from '~/components/Messages/Content';
 import SubRow from '~/components/Chat/Messages/SubRow';
+import { fontSizeAtom } from '~/store/fontSize';
 import { MessageContext } from '~/Providers';
 import { useMessageActions } from '~/hooks';
 import { cn, logger } from '~/utils';
@@ -58,8 +60,8 @@ const MessageRender = memo(
       isMultiMessage,
       setCurrentEditId,
     });
+    const fontSize = useAtomValue(fontSizeAtom);
     const maximizeChatSpace = useRecoilValue(store.maximizeChatSpace);
-    const fontSize = useRecoilValue(store.fontSize);
 
     const handleRegenerateMessage = useCallback(() => regenerateMessage(), [regenerateMessage]);
     const hasNoChildren = !(msg?.children?.length ?? 0);

client/src/components/Messages/ContentRender.tsx

@@ -1,5 +1,6 @@
-import { useRecoilValue } from 'recoil';
 import { useCallback, useMemo, memo } from 'react';
+import { useAtomValue } from 'jotai';
+import { useRecoilValue } from 'recoil';
 import type { TMessage, TMessageContentParts } from 'librechat-data-provider';
 import type { TMessageProps, TMessageIcon } from '~/common';
 import ContentParts from '~/components/Chat/Messages/Content/ContentParts';
@@ -9,6 +10,7 @@ import HoverButtons from '~/components/Chat/Messages/HoverButtons';
 import MessageIcon from '~/components/Chat/Messages/MessageIcon';
 import { useAttachments, useMessageActions } from '~/hooks';
 import SubRow from '~/components/Chat/Messages/SubRow';
+import { fontSizeAtom } from '~/store/fontSize';
 import { cn, logger } from '~/utils';
 import store from '~/store';
 
@@ -60,8 +62,8 @@ const ContentRender = memo(
       isMultiMessage,
       setCurrentEditId,
     });
+    const fontSize = useAtomValue(fontSizeAtom);
     const maximizeChatSpace = useRecoilValue(store.maximizeChatSpace);
-    const fontSize = useRecoilValue(store.fontSize);
 
     const handleRegenerateMessage = useCallback(() => regenerateMessage(), [regenerateMessage]);
     const isLast = useMemo(

client/src/components/Nav/MobileNav.tsx

@@ -5,6 +5,7 @@ import { QueryKeys, Constants } from 'librechat-data-provider';
 import type { TMessage } from 'librechat-data-provider';
 import type { Dispatch, SetStateAction } from 'react';
 import { useLocalize, useNewConvo } from '~/hooks';
+import { clearMessagesCache } from '~/utils';
 import store from '~/store';
 
 export default function MobileNav({
@@ -57,10 +58,7 @@ export default function MobileNav({
         aria-label={localize('com_ui_new_chat')}
         className="m-1 inline-flex size-10 items-center justify-center rounded-full hover:bg-surface-hover"
         onClick={() => {
-          queryClient.setQueryData<TMessage[]>(
-            [QueryKeys.messages, conversation?.conversationId ?? Constants.NEW_CONVO],
-            [],
-          );
+          clearMessagesCache(queryClient, conversation?.conversationId);
           queryClient.invalidateQueries([QueryKeys.messages]);
           newConversation();
         }}

client/src/components/Nav/NewChat.tsx

@@ -5,6 +5,7 @@ import { QueryKeys, Constants } from 'librechat-data-provider';
 import { TooltipAnchor, NewChatIcon, MobileSidebar, Sidebar, Button } from '@librechat/client';
 import type { TMessage } from 'librechat-data-provider';
 import { useLocalize, useNewConvo } from '~/hooks';
+import { clearMessagesCache } from '~/utils';
 import store from '~/store';
 
 export default function NewChat({
@@ -33,10 +34,7 @@ export default function NewChat({
         window.open('/c/new', '_blank');
         return;
       }
-      queryClient.setQueryData<TMessage[]>(
-        [QueryKeys.messages, conversation?.conversationId ?? Constants.NEW_CONVO],
-        [],
-      );
+      clearMessagesCache(queryClient, conversation?.conversationId);
       queryClient.invalidateQueries([QueryKeys.messages]);
       newConvo();
       navigate('/c/new', { state: { focusChat: true } });

client/src/components/Nav/SettingsTabs/Chat/FontSizeSelector.tsx

@@ -1,15 +1,14 @@
-import { useRecoilState } from 'recoil';
-import { Dropdown, applyFontSize } from '@librechat/client';
+import { useAtom } from 'jotai';
+import { Dropdown } from '@librechat/client';
+import { fontSizeAtom } from '~/store/fontSize';
 import { useLocalize } from '~/hooks';
-import store from '~/store';
 
 export default function FontSizeSelector() {
-  const [fontSize, setFontSize] = useRecoilState(store.fontSize);
   const localize = useLocalize();
+  const [fontSize, setFontSize] = useAtom(fontSizeAtom);
 
   const handleChange = (val: string) => {
     setFontSize(val);
-    applyFontSize(val);
   };
 
   const options = [

client/src/components/Share/Message.tsx

@@ -1,4 +1,4 @@
-import { useRecoilValue } from 'recoil';
+import { useAtomValue } from 'jotai';
 import type { TMessageProps } from '~/common';
 import MinimalHoverButtons from '~/components/Chat/Messages/MinimalHoverButtons';
 import MessageContent from '~/components/Chat/Messages/Content/MessageContent';
@@ -6,16 +6,16 @@ import SearchContent from '~/components/Chat/Messages/Content/SearchContent';
 import SiblingSwitch from '~/components/Chat/Messages/SiblingSwitch';
 import { Plugin } from '~/components/Messages/Content';
 import SubRow from '~/components/Chat/Messages/SubRow';
+import { fontSizeAtom } from '~/store/fontSize';
 import { MessageContext } from '~/Providers';
 import { useAttachments } from '~/hooks';
 
 import MultiMessage from './MultiMessage';
 import { cn } from '~/utils';
-import store from '~/store';
 
 import Icon from './MessageIcon';
 export default function Message(props: TMessageProps) {
-  const fontSize = useRecoilValue(store.fontSize);
+  const fontSize = useAtomValue(fontSizeAtom);
   const {
     message,
     siblingIdx,

client/src/hooks/Chat/__tests__/useFocusChatEffect.spec.tsx

@@ -21,8 +21,8 @@ describe('useFocusChatEffect', () => {
     (useNavigate as jest.Mock).mockReturnValue(mockNavigate);
 
     // Mock window.matchMedia
-    window.matchMedia = jest.fn().mockImplementation(() => ({
-      matches: false,
+    window.matchMedia = jest.fn().mockImplementation((query) => ({
+      matches: query === '(hover: hover)', // Desktop has hover capability
       media: '',
       onchange: null,
       addListener: jest.fn(),
@@ -83,8 +83,8 @@ describe('useFocusChatEffect', () => {
     });
 
     test('should not focus textarea on touchscreen devices', () => {
-      window.matchMedia = jest.fn().mockImplementation(() => ({
-        matches: true, // This indicates a touchscreen
+      window.matchMedia = jest.fn().mockImplementation((query) => ({
+        matches: query === '(pointer: coarse)', // Touchscreen has coarse pointer
         media: '',
         onchange: null,
         addListener: jest.fn(),

client/src/hooks/Conversations/useNavigateToConvo.tsx

@@ -3,7 +3,13 @@ import { useNavigate } from 'react-router-dom';
 import { useQueryClient } from '@tanstack/react-query';
 import { QueryKeys, Constants, dataService } from 'librechat-data-provider';
 import type { TConversation, TEndpointsConfig, TModelsConfig } from 'librechat-data-provider';
-import { buildDefaultConvo, getDefaultEndpoint, getEndpointField, logger } from '~/utils';
+import {
+  getDefaultEndpoint,
+  clearMessagesCache,
+  buildDefaultConvo,
+  getEndpointField,
+  logger,
+} from '~/utils';
 import store from '~/store';
 
 const useNavigateToConvo = (index = 0) => {
@@ -80,7 +86,7 @@ const useNavigateToConvo = (index = 0) => {
       });
     }
     clearAllConversations(true);
-    queryClient.setQueryData([QueryKeys.messages, currentConvoId], []);
+    clearMessagesCache(queryClient, currentConvoId);
     if (convo.conversationId !== Constants.NEW_CONVO && convo.conversationId) {
       queryClient.invalidateQueries([QueryKeys.conversation, convo.conversationId]);
       fetchFreshData(convo);

client/src/locales/zh-Hans/translation.json

@@ -365,6 +365,7 @@
   "com_error_files_process": "处理文件时发生错误",
   "com_error_files_upload": "上传文件时发生错误",
   "com_error_files_upload_canceled": "文件上传请求已取消。注意：文件上传可能仍在进行中，需要手动删除。",
+  "com_error_files_upload_too_large": "文件过大，请上传小于 {{0}} MB 的文件",
   "com_error_files_validation": "验证文件时出错。",
   "com_error_google_tool_conflict": "内置的 Google 工具与外部工具不兼容。请禁用内置工具或外部工具。",
   "com_error_heic_conversion": "将 HEIC 图片转换为 JPEG 失败。请尝试手动转换图像或使用其他格式。",
@@ -560,6 +561,7 @@
   "com_nav_setting_balance": "余额",
   "com_nav_setting_chat": "对话",
   "com_nav_setting_data": "数据管理",
+  "com_nav_setting_delay": "延迟（秒）",
   "com_nav_setting_general": "通用",
   "com_nav_setting_mcp": "MCP 设置",
   "com_nav_setting_personalization": "个性化",
@@ -759,6 +761,7 @@
   "com_ui_client_secret": "Client Secret",
   "com_ui_close": "关闭",
   "com_ui_close_menu": "关闭菜单",
+  "com_ui_close_settings": "关闭设置",
   "com_ui_close_window": "关闭窗口",
   "com_ui_code": "代码",
   "com_ui_collapse_chat": "收起对话",
@@ -857,6 +860,7 @@
   "com_ui_edit_editing_image": "编辑图片",
   "com_ui_edit_mcp_server": "编辑 MCP 服务器",
   "com_ui_edit_memory": "编辑记忆",
+  "com_ui_editor_instructions": "拖动图片调整位置 • 使用缩放滑块或按钮调整大小",
   "com_ui_empty_category": "-",
   "com_ui_endpoint": "端点",
   "com_ui_endpoint_menu": "LLM 端点菜单",
@@ -891,6 +895,7 @@
   "com_ui_feedback_tag_unjustified_refusal": "无故拒绝回答",
   "com_ui_field_max_length": "{{field}} 最多 {{length}} 个字符",
   "com_ui_field_required": "此字段为必填项",
+  "com_ui_file_input_avatar_label": "上传文件用作头像",
   "com_ui_file_size": "文件大小",
   "com_ui_file_token_limit": "文件词元数限制",
   "com_ui_file_token_limit_desc": "为文件处理设定最大词元数限制，以控制成本和资源使用",
@@ -953,11 +958,13 @@
   "com_ui_import_conversation_file_type_error": "不支持的导入类型",
   "com_ui_import_conversation_info": "从 JSON 文件导入对话",
   "com_ui_import_conversation_success": "对话导入成功",
+  "com_ui_import_conversation_upload_error": "上传文件时出错，请重试。",
   "com_ui_include_shadcnui": "包含 shadcn/ui 组件指令",
   "com_ui_initializing": "初始化中...",
   "com_ui_input": "输入",
   "com_ui_instructions": "指令",
   "com_ui_key": "键",
+  "com_ui_key_required": "API Key 为必填项",
   "com_ui_late_night": "夜深了",
   "com_ui_latest_footer": "Every AI for Everyone.",
   "com_ui_latest_production_version": "最新在用版本",
@@ -972,6 +979,7 @@
   "com_ui_manage": "管理",
   "com_ui_marketplace": "市场",
   "com_ui_marketplace_allow_use": "允许使用市场",
+  "com_ui_max_file_size": "PNG、JPG 或 JPEG（最大 {{0}}）",
   "com_ui_max_tags": "最多允许 {{0}} 个，用最新值。",
   "com_ui_mcp_authenticated_success": "MCP 服务器 “{{0}}” 认证成功",
   "com_ui_mcp_configure_server": "配置 {{0}}",
@@ -1066,6 +1074,7 @@
   "com_ui_privacy_policy": "隐私政策",
   "com_ui_privacy_policy_url": "隐私政策链接",
   "com_ui_prompt": "提示词",
+  "com_ui_prompt_groups": "提示词组列表",
   "com_ui_prompt_name": "提示词名称",
   "com_ui_prompt_name_required": "提示词名称为必填项",
   "com_ui_prompt_preview_not_shared": "作者未允许对此提示词进行协作。",
@@ -1095,6 +1104,8 @@
   "com_ui_rename_failed": "重命名对话失败",
   "com_ui_rename_prompt": "重命名 Prompt",
   "com_ui_requires_auth": "需要认证",
+  "com_ui_reset": "重置",
+  "com_ui_reset_adjustments": "重置调整",
   "com_ui_reset_var": "重置 {{0}}",
   "com_ui_reset_zoom": "重置缩放",
   "com_ui_resource": "资源",
@@ -1103,6 +1114,8 @@
   "com_ui_revoke_info": "撤销所有用户提供的凭据",
   "com_ui_revoke_key_confirm": "您确定要撤销此密钥吗？",
   "com_ui_revoke_key_endpoint": "撤销 {{0}} 的密钥",
+  "com_ui_revoke_key_error": "撤销 API Key 失败，请重试。",
+  "com_ui_revoke_key_success": "API Key 撤销成功",
   "com_ui_revoke_keys": "撤销密钥",
   "com_ui_revoke_keys_confirm": "您确定要撤销所有密钥吗？",
   "com_ui_role": "角色",
@@ -1116,11 +1129,15 @@
   "com_ui_role_viewer": "查看者",
   "com_ui_role_viewer_desc": "可以查看和使用智能体，但无法修改智能体",
   "com_ui_roleplay": "角色扮演",
+  "com_ui_rotate": "旋转",
+  "com_ui_rotate_90": "旋转 90 度",
   "com_ui_run_code": "运行代码",
   "com_ui_run_code_error": "代码运行出错",
   "com_ui_save": "保存",
   "com_ui_save_badge_changes": "保存徽章更改？",
   "com_ui_save_changes": "保存修改",
+  "com_ui_save_key_error": "保存 API Key 失败，请重试。",
+  "com_ui_save_key_success": "API Key 保存成功",
   "com_ui_save_submit": "保存并提交",
   "com_ui_saved": "保存成功！",
   "com_ui_saving": "保存中...",
@@ -1217,6 +1234,7 @@
   "com_ui_update_mcp_success": "已成功创建或更新 MCP",
   "com_ui_upload": "上传",
   "com_ui_upload_agent_avatar": "成功更新智能体头像",
+  "com_ui_upload_avatar_label": "上传头像图片",
   "com_ui_upload_code_files": "上传代码解释器文件",
   "com_ui_upload_delay": "上传 “{{0}}” 时比预期花了更长时间。文件正在进行检索索引，请稍候。",
   "com_ui_upload_error": "上传文件错误",
@@ -1228,6 +1246,7 @@
   "com_ui_upload_invalid": "上传的文件无效。必须是图片，且不得超过大小限制",
   "com_ui_upload_invalid_var": "上传的文件无效。必须是图片，且不得超过 {{0}} MB。",
   "com_ui_upload_ocr_text": "作为文本上传",
+  "com_ui_upload_provider": "上传至提供商",
   "com_ui_upload_success": "上传文件成功",
   "com_ui_upload_type": "选择上传类型",
   "com_ui_usage": "用量",
@@ -1267,6 +1286,8 @@
   "com_ui_web_search_scraper": "抓取器",
   "com_ui_web_search_scraper_firecrawl": "Firecrawl API",
   "com_ui_web_search_scraper_firecrawl_key": "获取您的 Firecrawl API Key",
+  "com_ui_web_search_scraper_serper": "Serper Scrape API",
+  "com_ui_web_search_scraper_serper_key": "获取您的 Serper API Key",
   "com_ui_web_search_searxng_api_key": "输入 SearXNG API Key（可选）",
   "com_ui_web_search_searxng_instance_url": "SearXNG 实例 URL",
   "com_ui_web_searching": "正在搜索网络",
@@ -1276,5 +1297,8 @@
   "com_ui_x_selected": "{{0}} 已选择",
   "com_ui_yes": "是的",
   "com_ui_zoom": "缩放",
+  "com_ui_zoom_in": "放大",
+  "com_ui_zoom_level": "缩放级别",
+  "com_ui_zoom_out": "缩小",
   "com_user_message": "您"
 }

client/src/store/fontSize.ts

@@ -0,0 +1,54 @@
+import { atom } from 'jotai';
+import { atomWithStorage } from 'jotai/utils';
+import { applyFontSize } from '@librechat/client';
+
+const DEFAULT_FONT_SIZE = 'text-base';
+
+/**
+ * Base storage atom for font size
+ */
+const fontSizeStorageAtom = atomWithStorage<string>('fontSize', DEFAULT_FONT_SIZE, undefined, {
+  getOnInit: true,
+});
+
+/**
+ * Derived atom that applies font size changes to the DOM
+ * Read: returns the current font size
+ * Write: updates storage and applies the font size to the DOM
+ */
+export const fontSizeAtom = atom(
+  (get) => get(fontSizeStorageAtom),
+  (get, set, newValue: string) => {
+    set(fontSizeStorageAtom, newValue);
+    if (typeof window !== 'undefined' && typeof document !== 'undefined') {
+      applyFontSize(newValue);
+    }
+  },
+);
+
+/**
+ * Initialize font size on app load
+ */
+export const initializeFontSize = () => {
+  if (typeof window === 'undefined' || typeof document === 'undefined') {
+    return;
+  }
+
+  const savedValue = localStorage.getItem('fontSize');
+
+  if (savedValue !== null) {
+    try {
+      const parsedValue = JSON.parse(savedValue);
+      applyFontSize(parsedValue);
+    } catch (error) {
+      console.error(
+        'Error parsing localStorage key "fontSize", resetting to default. Error:',
+        error,
+      );
+      localStorage.setItem('fontSize', JSON.stringify(DEFAULT_FONT_SIZE));
+      applyFontSize(DEFAULT_FONT_SIZE);
+    }
+  } else {
+    applyFontSize(DEFAULT_FONT_SIZE);
+  }
+};

client/src/store/settings.ts

@@ -21,7 +21,6 @@ const localStorageAtoms = {
   // General settings
   autoScroll: atomWithLocalStorage('autoScroll', false),
   hideSidePanel: atomWithLocalStorage('hideSidePanel', false),
-  fontSize: atomWithLocalStorage('fontSize', 'text-base'),
   enableUserMsgMarkdown: atomWithLocalStorage<boolean>(
     LocalStorageKeys.ENABLE_USER_MSG_MARKDOWN,
     true,

client/src/utils/messages.ts

@@ -1,5 +1,6 @@
-import { ContentTypes } from 'librechat-data-provider';
+import { ContentTypes, QueryKeys, Constants } from 'librechat-data-provider';
 import type { TMessage, TMessageContentParts } from 'librechat-data-provider';
+import type { QueryClient } from '@tanstack/react-query';
 
 export const TEXT_KEY_DIVIDER = '|||';
 
@@ -146,3 +147,26 @@ export const scrollToEnd = (callback?: () => void) => {
     }
   }
 };
+
+/**
+ * Clears messages for both the specified conversation ID and the NEW_CONVO query key.
+ * This ensures that messages are properly cleared in all contexts, preventing stale data
+ * from persisting in the NEW_CONVO cache.
+ *
+ * @param queryClient - The React Query client instance
+ * @param conversationId - The conversation ID to clear messages for
+ */
+export const clearMessagesCache = (
+  queryClient: QueryClient,
+  conversationId: string | undefined | null,
+): void => {
+  const convoId = conversationId ?? Constants.NEW_CONVO;
+
+  // Clear messages for the current conversation
+  queryClient.setQueryData<TMessage[]>([QueryKeys.messages, convoId], []);
+
+  // Also clear NEW_CONVO messages if we're not already on NEW_CONVO
+  if (convoId !== Constants.NEW_CONVO) {
+    queryClient.setQueryData<TMessage[]>([QueryKeys.messages, Constants.NEW_CONVO], []);
+  }
+};

client/vite.config.ts

@@ -1,4 +1,5 @@
 import react from '@vitejs/plugin-react';
+// @ts-ignore
 import path from 'path';
 import type { Plugin } from 'vite';
 import { defineConfig } from 'vite';
@@ -7,19 +8,23 @@ import { nodePolyfills } from 'vite-plugin-node-polyfills';
 import { VitePWA } from 'vite-plugin-pwa';
 
 // https://vitejs.dev/config/
+const backendPort = process.env.BACKEND_PORT && Number(process.env.BACKEND_PORT) || 3080;
+const backendURL = process.env.HOST ? `http://${process.env.HOST}:${backendPort}` : `http://localhost:${backendPort}`;
+
 export default defineConfig(({ command }) => ({
   base: '',
   server: {
-    host: 'localhost',
-    port: 3090,
+    allowedHosts: process.env.VITE_ALLOWED_HOSTS && process.env.VITE_ALLOWED_HOSTS.split(',') || [],
+    host: process.env.HOST || 'localhost',
+    port: process.env.PORT && Number(process.env.PORT) || 3090,
     strictPort: false,
     proxy: {
       '/api': {
-        target: 'http://localhost:3080',
+        target: backendURL,
         changeOrigin: true,
       },
       '/oauth': {
-        target: 'http://localhost:3080',
+        target: backendURL,
         changeOrigin: true,
       },
     },
@@ -259,6 +264,7 @@ export default defineConfig(({ command }) => ({
 interface SourcemapExclude {
   excludeNodeModules?: boolean;
 }
+
 export function sourcemapExclude(opts?: SourcemapExclude): Plugin {
   return {
     name: 'sourcemap-exclude',

package-lock.json

@@ -19,7 +19,7 @@
         "@eslint/eslintrc": "^3.2.0",
         "@eslint/js": "^9.20.0",
         "@microsoft/eslint-formatter-sarif": "^3.1.0",
-        "@playwright/test": "^1.50.1",
+        "@playwright/test": "^1.56.1",
         "@types/react-virtualized": "^9.22.0",
         "caniuse-lite": "^1.0.30001741",
         "cross-env": "^7.0.3",
@@ -64,7 +64,7 @@
         "@langchain/google-genai": "^0.2.13",
         "@langchain/google-vertexai": "^0.2.13",
         "@langchain/textsplitters": "^0.1.0",
-        "@librechat/agents": "^2.4.85",
+        "@librechat/agents": "^2.4.86",
         "@librechat/api": "*",
         "@librechat/data-schemas": "*",
         "@microsoft/microsoft-graph-client": "^3.0.7",
@@ -2768,7 +2768,7 @@
         "tailwindcss": "^3.4.1",
         "ts-jest": "^29.2.5",
         "typescript": "^5.3.3",
-        "vite": "^6.3.6",
+        "vite": "^6.4.1",
         "vite-plugin-compression2": "^2.2.1",
         "vite-plugin-node-polyfills": "^0.23.0",
         "vite-plugin-pwa": "^0.21.2"
@@ -4305,6 +4305,24 @@
         "node": ">=6"
       }
     },
+    "client/node_modules/fdir": {
+      "version": "6.5.0",
+      "resolved": "https://registry.npmjs.org/fdir/-/fdir-6.5.0.tgz",
+      "integrity": "sha512-tIbYtZbucOs0BRGqPJkshJUYdL+SDH7dVM8gjy+ERp3WAUjLEFJE+02kanyHtwjWOnwrKYBiwAmM0p4kLJAnXg==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=12.0.0"
+      },
+      "peerDependencies": {
+        "picomatch": "^3 || ^4"
+      },
+      "peerDependenciesMeta": {
+        "picomatch": {
+          "optional": true
+        }
+      }
+    },
     "client/node_modules/framer-motion": {
       "version": "11.18.2",
       "resolved": "https://registry.npmjs.org/framer-motion/-/framer-motion-11.18.2.tgz",
@@ -4358,6 +4376,19 @@
       "dev": true,
       "license": "MIT"
     },
+    "client/node_modules/picomatch": {
+      "version": "4.0.3",
+      "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
+      "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=12"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/jonschlinkert"
+      }
+    },
     "client/node_modules/react-is": {
       "version": "17.0.2",
       "resolved": "https://registry.npmjs.org/react-is/-/react-is-17.0.2.tgz",
@@ -4453,6 +4484,81 @@
         "browserslist": ">= 4.21.0"
       }
     },
+    "client/node_modules/vite": {
+      "version": "6.4.1",
+      "resolved": "https://registry.npmjs.org/vite/-/vite-6.4.1.tgz",
+      "integrity": "sha512-+Oxm7q9hDoLMyJOYfUYBuHQo+dkAloi33apOPP56pzj+vsdJDzr+j1NISE5pyaAuKL4A3UD34qd0lx5+kfKp2g==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "esbuild": "^0.25.0",
+        "fdir": "^6.4.4",
+        "picomatch": "^4.0.2",
+        "postcss": "^8.5.3",
+        "rollup": "^4.34.9",
+        "tinyglobby": "^0.2.13"
+      },
+      "bin": {
+        "vite": "bin/vite.js"
+      },
+      "engines": {
+        "node": "^18.0.0 || ^20.0.0 || >=22.0.0"
+      },
+      "funding": {
+        "url": "https://github.com/vitejs/vite?sponsor=1"
+      },
+      "optionalDependencies": {
+        "fsevents": "~2.3.3"
+      },
+      "peerDependencies": {
+        "@types/node": "^18.0.0 || ^20.0.0 || >=22.0.0",
+        "jiti": ">=1.21.0",
+        "less": "*",
+        "lightningcss": "^1.21.0",
+        "sass": "*",
+        "sass-embedded": "*",
+        "stylus": "*",
+        "sugarss": "*",
+        "terser": "^5.16.0",
+        "tsx": "^4.8.1",
+        "yaml": "^2.4.2"
+      },
+      "peerDependenciesMeta": {
+        "@types/node": {
+          "optional": true
+        },
+        "jiti": {
+          "optional": true
+        },
+        "less": {
+          "optional": true
+        },
+        "lightningcss": {
+          "optional": true
+        },
+        "sass": {
+          "optional": true
+        },
+        "sass-embedded": {
+          "optional": true
+        },
+        "stylus": {
+          "optional": true
+        },
+        "sugarss": {
+          "optional": true
+        },
+        "terser": {
+          "optional": true
+        },
+        "tsx": {
+          "optional": true
+        },
+        "yaml": {
+          "optional": true
+        }
+      }
+    },
     "client/node_modules/vite-plugin-pwa": {
       "version": "0.21.2",
       "resolved": "https://registry.npmjs.org/vite-plugin-pwa/-/vite-plugin-pwa-0.21.2.tgz",
@@ -21531,9 +21637,9 @@
       }
     },
     "node_modules/@librechat/agents": {
-      "version": "2.4.85",
-      "resolved": "https://registry.npmjs.org/@librechat/agents/-/agents-2.4.85.tgz",
-      "integrity": "sha512-t6h5f6ApnoEC+x8kqBlke1RR6BPzT+9BvlkA8VxvQVJtYIt5Ey4BOTRDGjdilDoXUcLui11PbjCd17EbjPkTcA==",
+      "version": "2.4.86",
+      "resolved": "https://registry.npmjs.org/@librechat/agents/-/agents-2.4.86.tgz",
+      "integrity": "sha512-Z3v+vMfFEyrDWrlPvgY9dUlhzYvtLXYYULEzkxUM1QpITuI3DsXr3xb1kXHAYOx3NmBGxiN9R/gjZN0tGBEo1g==",
       "license": "MIT",
       "dependencies": {
         "@langchain/anthropic": "^0.3.26",
@@ -22902,12 +23008,12 @@
       }
     },
     "node_modules/@playwright/test": {
-      "version": "1.50.1",
-      "resolved": "https://registry.npmjs.org/@playwright/test/-/test-1.50.1.tgz",
-      "integrity": "sha512-Jii3aBg+CEDpgnuDxEp/h7BimHcUTDlpEtce89xEumlJ5ef2hqepZ+PWp1DDpYC/VO9fmWVI1IlEaoI5fK9FXQ==",
+      "version": "1.56.1",
+      "resolved": "https://registry.npmjs.org/@playwright/test/-/test-1.56.1.tgz",
+      "integrity": "sha512-vSMYtL/zOcFpvJCW71Q/OEGQb7KYBPAdKh35WNSkaZA75JlAO8ED8UN6GUNTm3drWomcbcqRPFqQbLae8yBTdg==",
       "license": "Apache-2.0",
       "dependencies": {
-        "playwright": "1.50.1"
+        "playwright": "1.56.1"
       },
       "bin": {
         "playwright": "cli.js"
@@ -43042,12 +43148,12 @@
       }
     },
     "node_modules/playwright": {
-      "version": "1.50.1",
-      "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.50.1.tgz",
-      "integrity": "sha512-G8rwsOQJ63XG6BbKj2w5rHeavFjy5zynBA9zsJMMtBoe/Uf757oG12NXz6e6OirF7RCrTVAKFXbLmn1RbL7Qaw==",
+      "version": "1.56.1",
+      "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.56.1.tgz",
+      "integrity": "sha512-aFi5B0WovBHTEvpM3DzXTUaeN6eN0qWnTkKx4NQaH4Wvcmc153PdaY2UBdSYKaGYw+UyWXSVyxDUg5DoPEttjw==",
       "license": "Apache-2.0",
       "dependencies": {
-        "playwright-core": "1.50.1"
+        "playwright-core": "1.56.1"
       },
       "bin": {
         "playwright": "cli.js"
@@ -43060,9 +43166,9 @@
       }
     },
     "node_modules/playwright-core": {
-      "version": "1.50.1",
-      "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.50.1.tgz",
-      "integrity": "sha512-ra9fsNWayuYumt+NiM069M6OkcRb1FZSK8bgi66AtpFoWkg2+y0bJSNmkFrWhMbEBbVKC/EruAHH3g0zmtwGmQ==",
+      "version": "1.56.1",
+      "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.56.1.tgz",
+      "integrity": "sha512-hutraynyn31F+Bifme+Ps9Vq59hKuUCz7H1kDOcBs+2oGguKkWTU50bBWrtz34OUWmIwpBTWDxaRPXrIXkgvmQ==",
       "license": "Apache-2.0",
       "bin": {
         "playwright-core": "cli.js"
@@ -49973,6 +50079,7 @@
       "integrity": "sha512-0msEVHJEScQbhkbVTb/4iHZdJ6SXp/AvxL2sjwYQFfBqleHtnCqv1J3sa9zbWz/6kW1m9Tfzn92vW+kZ1WV6QA==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "esbuild": "^0.25.0",
         "fdir": "^6.4.4",
@@ -50076,6 +50183,7 @@
       "integrity": "sha512-tIbYtZbucOs0BRGqPJkshJUYdL+SDH7dVM8gjy+ERp3WAUjLEFJE+02kanyHtwjWOnwrKYBiwAmM0p4kLJAnXg==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "engines": {
         "node": ">=12.0.0"
       },
@@ -50094,6 +50202,7 @@
       "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "engines": {
         "node": ">=12"
       },
@@ -51337,7 +51446,7 @@
         "@azure/storage-blob": "^12.27.0",
         "@keyv/redis": "^4.3.3",
         "@langchain/core": "^0.3.62",
-        "@librechat/agents": "^2.4.85",
+        "@librechat/agents": "^2.4.86",
         "@librechat/data-schemas": "*",
         "@modelcontextprotocol/sdk": "^1.17.1",
         "axios": "^1.12.1",

package.json

@@ -100,7 +100,7 @@
     "@eslint/eslintrc": "^3.2.0",
     "@eslint/js": "^9.20.0",
     "@microsoft/eslint-formatter-sarif": "^3.1.0",
-    "@playwright/test": "^1.50.1",
+    "@playwright/test": "^1.56.1",
     "@types/react-virtualized": "^9.22.0",
     "caniuse-lite": "^1.0.30001741",
     "cross-env": "^7.0.3",

packages/api/package.json

@@ -80,7 +80,7 @@
     "@azure/storage-blob": "^12.27.0",
     "@keyv/redis": "^4.3.3",
     "@langchain/core": "^0.3.62",
-    "@librechat/agents": "^2.4.85",
+    "@librechat/agents": "^2.4.86",
     "@librechat/data-schemas": "*",
     "@modelcontextprotocol/sdk": "^1.17.1",
     "axios": "^1.12.1",

packages/api/src/utils/tokens.ts

@@ -40,10 +40,10 @@ const openAIModels = {
   'gpt-5': 400000,
   'gpt-5-mini': 400000,
   'gpt-5-nano': 400000,
+  'gpt-5-pro': 400000,
   'gpt-4o': 127500, // -500 from max
   'gpt-4o-mini': 127500, // -500 from max
   'gpt-4o-2024-05-13': 127500, // -500 from max
-  'gpt-4o-2024-08-06': 127500, // -500 from max
   'gpt-4-turbo': 127500, // -500 from max
   'gpt-4-vision': 127500, // -500 from max
   'gpt-3.5-turbo': 16375, // -10 from max
@@ -60,9 +60,11 @@ const mistralModels = {
   'mistral-7b': 31990, // -10 from max
   'mistral-small': 31990, // -10 from max
   'mixtral-8x7b': 31990, // -10 from max
+  'mixtral-8x22b': 65536,
   'mistral-large': 131000,
   'mistral-large-2402': 127500,
   'mistral-large-2407': 127500,
+  'mistral-nemo': 131000,
   'pixtral-large': 131000,
   'mistral-saba': 32000,
   codestral: 256000,
@@ -75,6 +77,7 @@ const cohereModels = {
   'command-light-nightly': 8182, // -10 from max
   command: 4086, // -10 from max
   'command-nightly': 8182, // -10 from max
+  'command-text': 4086, // -10 from max
   'command-r': 127500, // -500 from max
   'command-r-plus': 127500, // -500 from max
 };
@@ -127,14 +130,17 @@ const anthropicModels = {
   'claude-3.7-sonnet': 200000,
   'claude-3-5-sonnet-latest': 200000,
   'claude-3.5-sonnet-latest': 200000,
+  'claude-haiku-4-5': 200000,
   'claude-sonnet-4': 1000000,
   'claude-opus-4': 200000,
   'claude-4': 200000,
 };
 
 const deepseekModels = {
-  'deepseek-reasoner': 128000,
   deepseek: 128000,
+  'deepseek-reasoner': 128000,
+  'deepseek-r1': 128000,
+  'deepseek-v3': 128000,
   'deepseek.r1': 128000,
 };
 
@@ -200,32 +206,57 @@ const metaModels = {
   'llama2:70b': 4000,
 };
 
-const ollamaModels = {
+const qwenModels = {
+  qwen: 32000,
   'qwen2.5': 32000,
+  'qwen-turbo': 1000000,
+  'qwen-plus': 131000,
+  'qwen-max': 32000,
+  'qwq-32b': 32000,
+  // Qwen3 models
+  qwen3: 40960, // Qwen3 base pattern (using qwen3-4b context)
+  'qwen3-8b': 128000,
+  'qwen3-14b': 40960,
+  'qwen3-30b-a3b': 40960,
+  'qwen3-32b': 40960,
+  'qwen3-235b-a22b': 40960,
+  // Qwen3 VL (Vision-Language) models
+  'qwen3-vl-8b-thinking': 256000,
+  'qwen3-vl-8b-instruct': 262144,
+  'qwen3-vl-30b-a3b': 262144,
+  'qwen3-vl-235b-a22b': 131072,
+  // Qwen3 specialized models
+  'qwen3-max': 256000,
+  'qwen3-coder': 262144,
+  'qwen3-coder-30b-a3b': 262144,
+  'qwen3-coder-plus': 128000,
+  'qwen3-coder-flash': 128000,
+  'qwen3-next-80b-a3b': 262144,
 };
 
 const ai21Models = {
-  'ai21.j2-mid-v1': 8182, // -10 from max
-  'ai21.j2-ultra-v1': 8182, // -10 from max
-  'ai21.jamba-instruct-v1:0': 255500, // -500 from max
+  'j2-mid': 8182, // -10 from max
+  'j2-ultra': 8182, // -10 from max
+  'jamba-instruct': 255500, // -500 from max
 };
 
 const amazonModels = {
-  'amazon.titan-text-lite-v1': 4000,
-  'amazon.titan-text-express-v1': 8000,
-  'amazon.titan-text-premier-v1:0': 31500, // -500 from max
+  // Amazon Titan models
+  'titan-text-lite': 4000,
+  'titan-text-express': 8000,
+  'titan-text-premier': 31500, // -500 from max
+  // Amazon Nova models
   // https://aws.amazon.com/ai/generative-ai/nova/
-  'amazon.nova-micro-v1:0': 127000, // -1000 from max,
-  'amazon.nova-lite-v1:0': 295000, // -5000 from max,
-  'amazon.nova-pro-v1:0': 295000, // -5000 from max,
-  'amazon.nova-premier-v1:0': 995000, // -5000 from max,
+  'nova-micro': 127000, // -1000 from max
+  'nova-lite': 295000, // -5000 from max
+  'nova-pro': 295000, // -5000 from max
+  'nova-premier': 995000, // -5000 from max
 };
 
 const bedrockModels = {
   ...anthropicModels,
   ...mistralModels,
   ...cohereModels,
-  ...ollamaModels,
   ...deepseekModels,
   ...metaModels,
   ...ai21Models,
@@ -254,6 +285,7 @@ const aggregateModels = {
   ...googleModels,
   ...bedrockModels,
   ...xAIModels,
+  ...qwenModels,
   // misc.
   kimi: 131000,
   // GPT-OSS
@@ -289,6 +321,7 @@ export const modelMaxOutputs = {
   'gpt-5': 128000,
   'gpt-5-mini': 128000,
   'gpt-5-nano': 128000,
+  'gpt-5-pro': 128000,
   'gpt-oss-20b': 131000,
   'gpt-oss-120b': 131000,
   system_default: 32000,
@@ -299,6 +332,7 @@ const anthropicMaxOutputs = {
   'claude-3-haiku': 4096,
   'claude-3-sonnet': 4096,
   'claude-3-opus': 4096,
+  'claude-haiku-4-5': 64000,
   'claude-opus-4': 32000,
   'claude-sonnet-4': 64000,
   'claude-3.5-sonnet': 8192,