better-ccflare 3.2.2 → 3.3.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -16,7 +16,7 @@ https://github.com/user-attachments/assets/c859872f-ca5e-4f8b-b6a0-7cc7461fe62a
16
16
  ## Why better-ccflare?
17
17
 
18
18
  - **🚀 Zero Rate Limit Errors** - Automatically distribute requests across multiple accounts
19
- - **🤖 Multi-Provider Support** - Claude OAuth, Claude API console, Vertex AI, AWS Bedrock, NanoGPT, z.ai, Minimax, Anthropic-compatible, and OpenAI-compatible providers
19
+ - **🤖 Multi-Provider Support** - Claude OAuth, Claude API console, Vertex AI, AWS Bedrock, NanoGPT, z.ai, Minimax, OpenRouter, Kilo, Anthropic-compatible, and OpenAI-compatible providers
20
20
  - **🔒 OAuth Token Health** - Real-time monitoring of OAuth token status with automatic refresh and health indicators
21
21
  - **🔗 Custom API Endpoints** - Configure custom endpoints for Anthropic accounts for enterprise deployments
22
22
  - **☁️ OpenAI-Compatible Support** - Use OpenAI-compatible providers like OpenRouter, Together AI, and more with Claude API format
@@ -36,7 +36,7 @@ This project builds upon the excellent foundation of [snipeship/ccflare](https:/
36
36
  **🎯 Core Improvements (v3.0.0):**
37
37
  - **Enhanced Security** - Critical fixes for authentication bypass, command injection, and PKCE implementation
38
38
  - **OAuth Token Health Monitoring** - Real-time status indicators and automatic token refresh with 30-minute buffer
39
- - **Extended Provider Support** - AWS Bedrock, NanoGPT (with dynamic pricing), Minimax, Anthropic-compatible, and OpenAI-compatible providers
39
+ - **Extended Provider Support** - AWS Bedrock, NanoGPT (with dynamic pricing), Minimax, OpenRouter, Kilo, Anthropic-compatible, and OpenAI-compatible providers
40
40
  - **Simplified Load Balancing** - Removed tier system for O(1) priority-based selection
41
41
  - **Real-time Analytics Dashboard** - Beautiful web UI with fixed request history (no disappearing requests)
42
42
  - **Package Distribution** - Available via npm and bun for easy installation
@@ -46,7 +46,7 @@ This project builds upon the excellent foundation of [snipeship/ccflare](https:/
46
46
  - **REST API** - Complete API for automation and integration
47
47
  - **Cross-Platform Binary** - Pre-compiled binary works with Node.js or Bun
48
48
  - **Comprehensive Logging** - Request/response tracking with searchable history
49
- - **Database Integration** - SQLite for persistent storage and analytics
49
+ - **Database Integration** - SQLite (default) or PostgreSQL for persistent storage and analytics, supporting Kubernetes multi-pod deployments
50
50
 
51
51
  **📦 Distribution & Updates:**
52
52
  - **npm/bun Registry** - Install with `npm install -g better-ccflare` or `bun install -g better-ccflare`
@@ -59,6 +59,7 @@ This project builds upon the excellent foundation of [snipeship/ccflare](https:/
59
59
  - **Performance Optimized** - <10ms overhead with request deduplication and caching
60
60
  - **Reliability** - Automatic error recovery, circuit breakers, and health monitoring
61
61
  - **Scalability** - Built for high-throughput production environments
62
+ - **PostgreSQL Support** - Set `DATABASE_URL=postgresql://...` to use PostgreSQL for Kubernetes multi-pod deployments where SQLite file-sharing is not feasible
62
63
 
63
64
  ## Quick Start
64
65
 
@@ -642,9 +643,11 @@ We recommend using one of the workarounds above until the npm bug is fixed.
642
643
  - **AWS Bedrock** - Native AWS Bedrock integration with SigV4 authentication, inference profile support (geographic/global/regional), and automatic credential chain resolution via AWS CLI profiles
643
644
  - **Vertex AI** - Google Cloud Vertex AI integration with service account authentication
644
645
  - **z.ai, Minimax** - API key based providers with pay-as-you-go model
646
+ - **OpenRouter** - OpenRouter integration with native API support and model mapping
647
+ - **Kilo** - Kilo API integration with usage tracking
645
648
  - **Anthropic-Compatible** - Custom Anthropic-compatible providers with pay-as-you-go model
646
- - **OpenAI-Compatible** - OpenAI-compatible providers (OpenRouter, Together AI, etc.) with Claude API format
647
- - **Universal API Format** - Use OpenAI-compatible providers (OpenRouter, Together AI, etc.) with Claude API format
649
+ - **OpenAI-Compatible** - OpenAI-compatible providers (Together AI, etc.) with Claude API format
650
+ - **Universal API Format** - Use OpenAI-compatible providers with Claude API format
648
651
  - **Automatic Format Conversion** - Seamless conversion between Anthropic and OpenAI request/response formats
649
652
  - **Model Mapping** - Map Claude models (Opus, Sonnet, Haiku) to equivalent OpenAI models
650
653
  - **Streaming Support** - Full support for streaming responses from OpenAI-compatible providers
Binary file
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "better-ccflare",
3
- "version": "3.2.2",
3
+ "version": "3.3.0",
4
4
  "description": "Load balancer proxy for Claude API with intelligent distribution across multiple OAuth accounts to avoid rate limiting",
5
5
  "license": "MIT",
6
6
  "repository": {