feat: add comprehensive OpenAI and Anthropic provider support

- Add complete OpenAI template with 35 models including GPT-5, GPT-4.1, o1/o3/o4 series, DALL-E, Whisper, TTS, and embeddings
- Add comprehensive Anthropic template with 8 Claude models (Opus 4.1, Opus 4, Sonnet 4, 3.7 Sonnet, 3.5 Sonnet variants, Haiku)
- Implement intelligent multi-pattern matching system via 'match' arrays for handling versioned model IDs
- Add auto-configuration for unmatched API models with smart capability detection
- Support template-based fallback when no API key is provided
- Update configuration examples with OpenAI and Anthropic provider settings
- Enhance model fetching to handle 65+ OpenAI models and 8 Anthropic models
- Add comprehensive logging for matched vs auto-configured models

The new matching system resolves API model ID variations (e.g., gpt-5-nano-2025-08-07 → gpt-5-nano template)
while providing intelligent defaults for unknown models, significantly improving coverage and reliability.

Author: zerob13

.gitignore

@@ -18,7 +18,6 @@ Thumbs.db
 
 # Logs
 *.log
-samples/*.json
 
 # Configuration files (may contain sensitive API keys)
 config/providers.toml

config/providers.toml.example

@@ -50,6 +50,24 @@ api_url = "https://tokenflux.ai/v1/models"
 rate_limit = 10
 timeout = 30
 
+[providers.openai]
+api_url = "https://api.openai.com/v1/models"
+# Option 1: Use environment variable (recommended for security)
+api_key_env = "OPENAI_API_KEY"
+# Option 2: Direct API key (not recommended for production)
+# api_key = "your-openai-key-here"
+rate_limit = 10
+timeout = 30
+
+[providers.anthropic]
+api_url = "https://api.anthropic.com/v1/models"
+# Option 1: Use environment variable (recommended for security)
+api_key_env = "ANTHROPIC_API_KEY"
+# Option 2: Direct API key (not recommended for production)
+# api_key = "your-anthropic-key-here"
+rate_limit = 10
+timeout = 30
+
 [providers.groq]
 api_url = "https://api.groq.com/openai/v1/models"
 # Option 1: Use environment variable (recommended for security)
@@ -73,6 +91,8 @@ timeout = 60  # Web scraping might take longer
 # - Vercel: Uses public AI Gateway API, no key required
 # - GitHub AI: Uses public model listing API, no key required
 # - Tokenflux: Uses public API, no key required
+# - OpenAI: Requires API key for access
+# - Anthropic: Requires API key for access
 # - Gemini: Optional API key for complete model list
 # - Groq: Requires API key for access
 # - DeepSeek: Uses web scraping from documentation, no key required