df242a7935
- Add comprehensive Moonshot AI provider with 11 models including: * Legacy moonshot-v1 series (8k, 32k, 128k context) * Latest Kimi K2 models (K2 Preview, Turbo, Thinking) * Vision-enabled models for multimodal capabilities * Auto-selecting model variants - Update xAI provider with latest Grok models: * Add Grok 4 (256K context) and Grok 4 (07-09) variant * Add Grok 3 Mini Beta and Mini Fast Beta variants * Update context limits to match actual model capabilities * Remove outdated grok-beta and grok-2-1212 models - Add MOONSHOT_API_KEY to environment configuration - Register Moonshot provider in service status monitoring - Full OpenAI-compatible API integration via api.moonshot.ai - Fix TypeScript errors in GitHub provider 🤖 Generated with [Claude Code](https://claude.ai/code) Co-authored-by: Claude <noreply@anthropic.com>
85 lines
2.1 KiB
TypeScript
85 lines
2.1 KiB
TypeScript
/*
|
|
* Maximum tokens for response generation (updated for modern model capabilities)
|
|
* This serves as a fallback when model-specific limits are unavailable
|
|
* Modern models like Claude 3.5, GPT-4o, and Gemini Pro support 128k+ tokens
|
|
*/
|
|
export const MAX_TOKENS = 128000;
|
|
|
|
/*
|
|
* Provider-specific default completion token limits
|
|
* Used as fallbacks when model doesn't specify maxCompletionTokens
|
|
*/
|
|
export const PROVIDER_COMPLETION_LIMITS: Record<string, number> = {
|
|
OpenAI: 4096, // Standard GPT models (o1 models have much higher limits)
|
|
Github: 4096, // GitHub Models use OpenAI-compatible limits
|
|
Anthropic: 64000, // Conservative limit for Claude 4 models (Opus: 32k, Sonnet: 64k)
|
|
Google: 8192, // Gemini 1.5 Pro/Flash standard limit
|
|
Cohere: 4000,
|
|
DeepSeek: 8192,
|
|
Groq: 8192,
|
|
HuggingFace: 4096,
|
|
Mistral: 8192,
|
|
Ollama: 8192,
|
|
OpenRouter: 8192,
|
|
Perplexity: 8192,
|
|
Together: 8192,
|
|
xAI: 8192,
|
|
LMStudio: 8192,
|
|
OpenAILike: 8192,
|
|
AmazonBedrock: 8192,
|
|
Hyperbolic: 8192,
|
|
};
|
|
|
|
/*
|
|
* Reasoning models that require maxCompletionTokens instead of maxTokens
|
|
* These models use internal reasoning tokens and have different API parameter requirements
|
|
*/
|
|
export function isReasoningModel(modelName: string): boolean {
|
|
const result = /^(o1|o3|gpt-5)/i.test(modelName);
|
|
|
|
// DEBUG: Test regex matching
|
|
console.log(`REGEX TEST: "${modelName}" matches reasoning pattern: ${result}`);
|
|
|
|
return result;
|
|
}
|
|
|
|
// limits the number of model responses that can be returned in a single request
|
|
export const MAX_RESPONSE_SEGMENTS = 2;
|
|
|
|
export interface File {
|
|
type: 'file';
|
|
content: string;
|
|
isBinary: boolean;
|
|
isLocked?: boolean;
|
|
lockedByFolder?: string;
|
|
}
|
|
|
|
export interface Folder {
|
|
type: 'folder';
|
|
isLocked?: boolean;
|
|
lockedByFolder?: string;
|
|
}
|
|
|
|
type Dirent = File | Folder;
|
|
|
|
export type FileMap = Record<string, Dirent | undefined>;
|
|
|
|
export const IGNORE_PATTERNS = [
|
|
'node_modules/**',
|
|
'.git/**',
|
|
'dist/**',
|
|
'build/**',
|
|
'.next/**',
|
|
'coverage/**',
|
|
'.cache/**',
|
|
'.vscode/**',
|
|
'.idea/**',
|
|
'**/*.log',
|
|
'**/.DS_Store',
|
|
'**/npm-debug.log*',
|
|
'**/yarn-debug.log*',
|
|
'**/yarn-error.log*',
|
|
'**/*lock.json',
|
|
'**/*lock.yml',
|
|
];
|