tatlock/src/core/config.py

"""
Global application configuration.
Following best practice of splitting config across domains.
"""
from enum import Enum
from functools import lru_cache
from pathlib import Path

from pydantic import Field, HttpUrl
from pydantic_settings import BaseSettings, SettingsConfigDict


def _get_version_from_pyproject() -> str:
    """
    Load version from pyproject.toml.

    Falls back to "unknown" if file cannot be read.
    """
    try:
        # Find pyproject.toml relative to this file
        config_dir = Path(__file__).parent
        pyproject_path = config_dir.parent.parent / "pyproject.toml"

        if pyproject_path.exists():
            content = pyproject_path.read_text()
            for line in content.splitlines():
                if line.strip().startswith("version"):
                    # Parse: version = "1.0.0"
                    return line.split("=", 1)[1].strip().strip('"').strip("'")
    except Exception:
        pass
    return "unknown"


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 = Field(default_factory=_get_version_from_pyproject)
    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"
    )

    # SearXNG Configuration
    SEARXNG_HOST: HttpUrl = Field(
        default="http://localhost:8087",
        description="SearXNG server URL"
    )
    SEARXNG_TIMEOUT: int = Field(
        default=30,
        description="SearXNG request timeout in seconds"
    )

    # Redis Configuration
    REDIS_HOST: str = Field(
        default="localhost",
        description="Redis server host"
    )
    REDIS_PORT: int = Field(
        default=6379,
        description="Redis server port"
    )
    REDIS_DB: int = Field(
        default=1,
        description="Redis database number"
    )
    REDIS_TIMEOUT: int = Field(
        default=5,
        description="Redis connection timeout in seconds"
    )

    # Library-Desk Configuration (The Librarian backend)
    LIBRARY_DESK_HOST: HttpUrl = Field(
        default="http://localhost:8089",
        description="Library-Desk API URL"
    )
    LIBRARY_DESK_API_KEY: str = Field(
        default="",
        description="API key for Library-Desk authentication"
    )
    LIBRARY_DESK_TIMEOUT: int = Field(
        default=60,
        description="Library-Desk request timeout in seconds"
    )

    # Qdrant Configuration (Memory vector storage)
    QDRANT_HOST: str = Field(
        default="localhost",
        description="Qdrant server host"
    )
    QDRANT_PORT: int = Field(
        default=6333,
        description="Qdrant server port"
    )
    QDRANT_EMBEDDING_DIM: int = Field(
        default=768,
        description="Embedding dimension (768 for nomic-embed-text)"
    )

    # Ollama Embedding Configuration
    OLLAMA_EMBEDDING_MODEL: str = Field(
        default="nomic-embed-text",
        description="Ollama model for embeddings"
    )

    # Redis Memory Database (separate from benchmarks)
    REDIS_MEMORY_DB: int = Field(
        default=2,
        description="Redis database number for memory cache"
    )
    REDIS_MEMORY_TTL_HOURS: int = Field(
        default=24,
        description="TTL for session context in hours"
    )

    # Logging
    LOG_LEVEL: str = Field(default="INFO", description="Logging level")
    ENABLE_BENCHMARKS: bool = Field(default=True, description="Enable performance benchmarking")

    # 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] = ["*"]

    @property
    def redis_url(self) -> str:
        """Construct Redis connection URL for benchmarks."""
        return f"redis://{self.REDIS_HOST}:{self.REDIS_PORT}/{self.REDIS_DB}"

    @property
    def redis_memory_url(self) -> str:
        """Construct Redis connection URL for memory cache."""
        return f"redis://{self.REDIS_HOST}:{self.REDIS_PORT}/{self.REDIS_MEMORY_DB}"

    @property
    def qdrant_url(self) -> str:
        """Construct Qdrant server URL."""
        return f"http://{self.QDRANT_HOST}:{self.QDRANT_PORT}"

    @property
    def log_format(self) -> str:
        """
        Determine log format based on environment.

        - production: JSON format for machine parsing
        - development/testing: Console format for human readability
        """
        return "json" if self.ENVIRONMENT == Environment.PRODUCTION else "console"


@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()