Add core configuration and base models

Implement global application configuration and custom Pydantic models
following FastAPI best practices.

Core Configuration (src/core/config.py):
- BaseSettings with environment variable support
- Split configuration by domain (following best practices)
- Ollama connection settings (host, model, timeouts)
- API configuration (host, port, prefix)
- CORS settings
- 20-second streaming timeout per turn
- Cached configuration with @lru_cache

Custom Base Models (src/core/models.py):
- CustomBaseModel for consistent serialization
- ISO datetime formatting
- Alias population support
- Enum value serialization
- Validation on assignment
- serializable_dict() for logging/debugging

Exception Handling (src/core/exceptions.py):
- Base AppException with status codes
- OllamaConnectionError (503)
- OllamaTimeoutError (504)
- ModelNotFoundError (404)
- ValidationError (422)
- OpenAI-compatible error structure

Benefits:
- Consistent configuration across domains
- Type-safe settings with validation
- Easy environment override via .env
- Predictable error responses
- Better debugging with serializable models

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

src/core/config.py

@@ -0,0 +1,86 @@
+"""
+Global application configuration.
+Following best practice of splitting config across domains.
+"""
+from enum import Enum
+from functools import lru_cache
+
+from pydantic import Field, HttpUrl
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+
+class Environment(str, Enum):
+    """Application environment."""
+    DEVELOPMENT = "development"
+    PRODUCTION = "production"
+    TESTING = "testing"
+
+
+class Config(BaseSettings):
+    """
+    Global application configuration.
+    
+    Loads from environment variables and .env file.
+    Domain-specific configs should be in their respective modules.
+    """
+    model_config = SettingsConfigDict(
+        env_file=".env",
+        env_file_encoding="utf-8",
+        case_sensitive=True,
+        extra="ignore",
+    )
+    
+    # Application
+    APP_NAME: str = "OpenAI-Compatible API"
+    APP_VERSION: str = "0.1.0"
+    ENVIRONMENT: Environment = Environment.DEVELOPMENT
+    DEBUG: bool = Field(default=False, description="Debug mode")
+    
+    # API Configuration
+    API_HOST: str = Field(default="0.0.0.0", description="API host")
+    API_PORT: int = Field(default=8000, description="API port")
+    API_PREFIX: str = Field(default="/v1", description="API route prefix")
+    
+    # Ollama Configuration
+    OLLAMA_HOST: HttpUrl = Field(
+        default="http://localhost:11434",
+        description="Ollama server URL"
+    )
+    OLLAMA_DEFAULT_MODEL: str = Field(
+        default="mistral-nemo:latest",
+        description="Default Ollama model"
+    )
+    OLLAMA_TIMEOUT: int = Field(
+        default=120,
+        description="Ollama request timeout in seconds"
+    )
+    STREAM_TIMEOUT: int = Field(
+        default=20,
+        description="Timeout for each streaming turn in seconds"
+    )
+
+    # Logging
+    LOG_LEVEL: str = Field(default="INFO", description="Logging level")
+    
+    # CORS
+    CORS_ORIGINS: list[str] = Field(
+        default=["*"],
+        description="Allowed CORS origins"
+    )
+    CORS_ALLOW_CREDENTIALS: bool = True
+    CORS_ALLOW_METHODS: list[str] = ["*"]
+    CORS_ALLOW_HEADERS: list[str] = ["*"]
+
+
+@lru_cache
+def get_config() -> Config:
+    """
+    Get cached configuration instance.
+    
+    Uses lru_cache to ensure config is loaded once and reused.
+    """
+    return Config()
+
+
+# Global config instance
+config = get_config()