Breaking change: openrouter_models.json -> custom_models.json

* Support for Custom URLs and custom models, including locally hosted models such as ollama
* Support for native + openrouter + local models (i.e. dozens of models) means you can start delegating sub-tasks to particular models or work to local models such as localizations or other boring work etc.
* Several tests added
* precommit to also include untracked (new) files
* Logfile auto rollover
* Improved logging

server.py

@@ -24,6 +24,7 @@ import os
 import sys
 import time
 from datetime import datetime
+from logging.handlers import RotatingFileHandler
 from typing import Any
 
 from mcp.server import Server
@@ -79,16 +80,17 @@ logging.basicConfig(
 for handler in logging.getLogger().handlers:
     handler.setFormatter(LocalTimeFormatter(log_format))
 
-# Add file handler for Docker log monitoring
+# Add rotating file handler for Docker log monitoring
 try:
-    file_handler = logging.FileHandler("/tmp/mcp_server.log")
+    # Main server log with rotation (10MB max, keep 2 files)
+    file_handler = RotatingFileHandler("/tmp/mcp_server.log", maxBytes=10 * 1024 * 1024, backupCount=2)
     file_handler.setLevel(getattr(logging, log_level, logging.INFO))
     file_handler.setFormatter(LocalTimeFormatter(log_format))
     logging.getLogger().addHandler(file_handler)
 
-    # Create a special logger for MCP activity tracking
+    # Create a special logger for MCP activity tracking with rotation
     mcp_logger = logging.getLogger("mcp_activity")
-    mcp_file_handler = logging.FileHandler("/tmp/mcp_activity.log")
+    mcp_file_handler = RotatingFileHandler("/tmp/mcp_activity.log", maxBytes=10 * 1024 * 1024, backupCount=2)
     mcp_file_handler.setLevel(logging.INFO)
     mcp_file_handler.setFormatter(LocalTimeFormatter("%(asctime)s - %(message)s"))
     mcp_logger.addHandler(mcp_file_handler)
@@ -128,6 +130,7 @@ def configure_providers():
     """
     from providers import ModelProviderRegistry
     from providers.base import ProviderType
+    from providers.custom import CustomProvider
     from providers.gemini import GeminiModelProvider
     from providers.openai import OpenAIModelProvider
     from providers.openrouter import OpenRouterProvider
@@ -135,6 +138,7 @@ def configure_providers():
     valid_providers = []
     has_native_apis = False
     has_openrouter = False
+    has_custom = False
 
     # Check for Gemini API key
     gemini_key = os.getenv("GEMINI_API_KEY")
@@ -157,31 +161,68 @@ def configure_providers():
         has_openrouter = True
         logger.info("OpenRouter API key found - Multiple models available via OpenRouter")
 
-    # Register providers - native APIs first to ensure they take priority
+    # Check for custom API endpoint (Ollama, vLLM, etc.)
+    custom_url = os.getenv("CUSTOM_API_URL")
+    if custom_url:
+        # IMPORTANT: Always read CUSTOM_API_KEY even if empty
+        # - Some providers (vLLM, LM Studio, enterprise APIs) require authentication
+        # - Others (Ollama) work without authentication (empty key)
+        # - DO NOT remove this variable - it's needed for provider factory function
+        custom_key = os.getenv("CUSTOM_API_KEY", "")  # Default to empty (Ollama doesn't need auth)
+        custom_model = os.getenv("CUSTOM_MODEL_NAME", "llama3.2")
+        valid_providers.append(f"Custom API ({custom_url})")
+        has_custom = True
+        logger.info(f"Custom API endpoint found: {custom_url} with model {custom_model}")
+        if custom_key:
+            logger.debug("Custom API key provided for authentication")
+        else:
+            logger.debug("No custom API key provided (using unauthenticated access)")
+
+    # Register providers in priority order:
+    # 1. Native APIs first (most direct and efficient)
     if has_native_apis:
         if gemini_key and gemini_key != "your_gemini_api_key_here":
             ModelProviderRegistry.register_provider(ProviderType.GOOGLE, GeminiModelProvider)
         if openai_key and openai_key != "your_openai_api_key_here":
             ModelProviderRegistry.register_provider(ProviderType.OPENAI, OpenAIModelProvider)
 
-    # Register OpenRouter last so native APIs take precedence
+    # 2. Custom provider second (for local/private models)
+    if has_custom:
+        # Factory function that creates CustomProvider with proper parameters
+        def custom_provider_factory(api_key=None):
+            # api_key is CUSTOM_API_KEY (can be empty for Ollama), base_url from CUSTOM_API_URL
+            base_url = os.getenv("CUSTOM_API_URL", "")
+            return CustomProvider(api_key=api_key or "", base_url=base_url)  # Use provided API key or empty string
+
+        ModelProviderRegistry.register_provider(ProviderType.CUSTOM, custom_provider_factory)
+
+    # 3. OpenRouter last (catch-all for everything else)
     if has_openrouter:
         ModelProviderRegistry.register_provider(ProviderType.OPENROUTER, OpenRouterProvider)
 
     # Require at least one valid provider
     if not valid_providers:
         raise ValueError(
-            "At least one API key is required. Please set either:\n"
+            "At least one API configuration is required. Please set either:\n"
             "- GEMINI_API_KEY for Gemini models\n"
             "- OPENAI_API_KEY for OpenAI o3 model\n"
-            "- OPENROUTER_API_KEY for OpenRouter (multiple models)"
+            "- OPENROUTER_API_KEY for OpenRouter (multiple models)\n"
+            "- CUSTOM_API_URL for local models (Ollama, vLLM, etc.)"
         )
 
     logger.info(f"Available providers: {', '.join(valid_providers)}")
 
-    # Log provider priority if both are configured
-    if has_native_apis and has_openrouter:
-        logger.info("Provider priority: Native APIs (Gemini, OpenAI) will be checked before OpenRouter")
+    # Log provider priority
+    priority_info = []
+    if has_native_apis:
+        priority_info.append("Native APIs (Gemini, OpenAI)")
+    if has_custom:
+        priority_info.append("Custom endpoints")
+    if has_openrouter:
+        priority_info.append("OpenRouter (catch-all)")
+
+    if len(priority_info) > 1:
+        logger.info(f"Provider priority: {' → '.join(priority_info)}")
 
 
 @server.list_tools()
@@ -536,7 +577,7 @@ async def handle_get_version() -> list[TextContent]:
     if ModelProviderRegistry.get_provider(ProviderType.OPENAI):
         configured_providers.append("OpenAI (o3, o3-mini)")
     if ModelProviderRegistry.get_provider(ProviderType.OPENROUTER):
-        configured_providers.append("OpenRouter (configured via conf/openrouter_models.json)")
+        configured_providers.append("OpenRouter (configured via conf/custom_models.json)")
 
     # Format the information in a human-readable way
     text = f"""Zen MCP Server v{__version__}