Unified error handling for AI providers with retry logic and HTTP mapping
// Source: https://github.com/majiayu000/litellm-rs | License: MIT | Copyright 2024 Rust LiteLLM Gateway Contributors // Provided via justclaw.it.com; keep this notice with the code. //! Unified Provider Error Handling //! //! Single error type for all providers - optimized design for simplicity and performance //! //! This module provides a unified error handling system for all AI providers. //! //! ## Core Components //! //! ### `ProviderError` Enum //! A comprehensive error type that covers all possible failure scenarios across different AI providers. //! //! | Variant | Purpose | HTTP Status | Retryable | //! |------|------|------------|--------| //! | Authentication | Authentication failed | 401 | No | //! | RateLimit | Rate limit exceeded | 429 | Yes (after delay) | //! | ModelNotFou ... (truncated -- full source via MCP)
See the full source, get the GitHub permalink, and search for more like it.
Get a free API key