docs: update documentation for Ollama provider

- Add Ollama configuration instructions to README.md
- Update API usage section with Ollama examples
- Add Ollama to provider list in BACKEND_ARCHITECTURE.md
- All documentation now reflects complete Ollama support

BACKEND_ARCHITECTURE.md

@@ -30,7 +30,7 @@ The GopherGate backend is implemented in Go, focusing on high performance, clear
 ## Key Components
 
 ### 1. Provider Interface (`internal/providers/provider.go`)
-Standardized interface for all LLM backends. Implementations handle mapping between the unified format and provider-specific APIs (OpenAI, Gemini, DeepSeek, Grok).
+Standardized interface for all LLM backends. Implementations handle mapping between the unified format and provider-specific APIs (OpenAI, Gemini, DeepSeek, Grok, Moonshot, Ollama).
 
 ### 2. Model Registry & Pricing (`internal/utils/registry.go`)
 Integrates with `models.dev/api.json` to provide real-time model metadata and pricing. 

README.md

@@ -68,6 +68,10 @@ GopherGate is designed with security in mind:
    # OPENAI_API_KEY=sk-...
    # GEMINI_API_KEY=AIza...
    # MOONSHOT_API_KEY=...
+   # For Ollama (optional): Set base URL and enable
+   # LLM_PROXY__PROVIDERS__OLLAMA__BASE_URL=http://localhost:11434/v1
+   # LLM_PROXY__PROVIDERS__OLLAMA__ENABLED=true
+   # LLM_PROXY__PROVIDERS__OLLAMA__MODELS=llama3,gemma2,mistral
    ```
 
 3. Run the proxy:
@@ -120,6 +124,10 @@ Moonshot models are available through the same OpenAI-compatible endpoint. For
 example, use `kimi-k2.5` as the model name after setting `MOONSHOT_API_KEY` in
 your environment.
 
+Ollama models (like `llama3`, `gemma2`, `mistral`) are also available through the same
+endpoint after enabling Ollama in configuration and setting the base URL to your
+Ollama server (default: `http://localhost:11434/v1`).
+
 ### Python
 ```python
 from openai import OpenAI