feat: enhance changelog generation and error handling in build process

feat: Add release drafter configuration and refactor build process to use Python script

feat: fix rate limit handling and improve error logging in RotatingClient

refactor: Remove file locking mechanism from usage data saving

feat: Add build workflow, proxy application, and update documentation for executable usage

Merge branch 'main' of https://github.com/Mirrowel/LLM-API-Key-Proxy

feat: Update documentation and example configurations for improved clarity and usability

feat: Bump version to 0.6.7 in pyproject.toml

feat: Enhance request logging to ensure proper UTF-8 encoding in log files

feat: Fix thinking parameter handling for specific Gemini models

feat: Add request payload sanitization to remove unsupported parameters based on model

feat: Add default thinking parameter handling for specific Gemini models

feat: Implement request logging for API responses and enhance streaming response handling

feat: Enhance daily reset logic to ensure timezone-aware date handling

feat: Implement NvidiaProvider for fetching models from NVIDIA API

feat: update proxy to use the new async context management

feat: Add async context management to RotatingClient and improve resource handling

feat: optimize retry logic

feat: Safety settings addition(only gemini for now)

fix: Handle missing cooldown values in UsageManager to prevent key lockout type errors

Revert "feat: Implement Gemini stream wrapper for improved JSON chunk handling and usage recording - might be not needed"

feat: Implement Gemini stream wrapper for improved JSON chunk handling and usage recording - might be not needed

feat: Update version to 0.61 in pyproject.toml for release

feat: Update key release logic in RotatingClient and UsageManager to support model-specific tracking

feat: Bump version to 0.6 in pyproject.toml for release

feat: Enhance error classification and handling in UsageManager and error_handler for improved retry logic and cooldown management

feat: Add pre-request callback support and exponential backoff for server error retries in acompletion method

feat: Enhance asynchronous handling in RotatingClient and UsageManager for improved error management and usage tracking

feat: Improve key acquisition logic in RotatingClient and UsageManager for better async handling and error management

feat: Enhance error handling in UsageManager to extract retry delay from multiple error message formats

feat: Set environment variable for logging level in RotatingClient

feat: Convert system messages to user messages for gemma-3 model in acompletion method

feat: Refactor logging to use a dedicated logger across providers and enhance model retrieval with httpx

fix: Update import statements for consistency in client.py

feat: Bump project version to 0.5.2

feat: Add OpenRouter and Chutes.ai provider support

feat: Implement per-model API key cooldowns

feat: Exclude PROXY_API_KEY from provider API key loading and enhance model retrieval options

feat: Update project version to 0.5.0 and enhance description in pyproject.toml

feat: Add detailed documentation and installation instructions for the rotating API key client

feat(multi-provider): Implement dynamic API key loading and new endpoints

feat: Refactor project into reusable API key rotation library and proxy

feat: Implement robust API key rotation, retry, and logging

Inital commit