library-desk/src/config.py

"""
Application configuration using Pydantic Settings.
Following best practices: modular settings, environment-based config.
"""

from functools import lru_cache
from pathlib import Path
from pydantic import Field
from pydantic_settings import BaseSettings, SettingsConfigDict

# Read version from pyproject.toml
try:
    import tomllib
    _pyproject_path = Path(__file__).parent.parent / "pyproject.toml"
    with open(_pyproject_path, "rb") as f:
        _pyproject = tomllib.load(f)
    __version__ = _pyproject["project"]["version"]
except Exception:
    __version__ = "0.0.0"  # Fallback if pyproject.toml not found


class Settings(BaseSettings):
    """Application settings loaded from environment variables."""

    model_config = SettingsConfigDict(
        env_file=".env",
        env_file_encoding="utf-8",
        case_sensitive=False,
        extra="ignore",
    )

    # API Configuration
    library_api_key: str = Field(..., description="API key for authentication")

    # Neo4j Configuration
    neo4j_uri: str = Field(default="bolt://neo4j:7687", description="Neo4j Bolt URI")
    neo4j_user: str = Field(default="neo4j", description="Neo4j username")
    neo4j_password: str = Field(..., description="Neo4j password")

    # Qdrant Configuration
    qdrant_host: str = Field(default="qdrant", description="Qdrant host")
    qdrant_port: int = Field(default=6333, description="Qdrant port")
    qdrant_timeout: int = Field(default=30, ge=1, le=300, description="Qdrant client timeout in seconds")

    # Wiki.js Configuration
    wikijs_url: str = Field(default="http://wiki:3000", description="Wiki.js URL")
    wiki_graphql_api: str = Field(default="", description="Wiki.js GraphQL API token (optional - API may be open)")
    # Legacy auth fields - kept for backwards compatibility but deprecated
    wikijs_username: str = Field(default="", description="Wiki.js username (deprecated, use wiki_graphql_api)")
    wikijs_password: str = Field(default="", description="Wiki.js password (deprecated, use wiki_graphql_api)")

    # Wiki.js Database Configuration (for change listener)
    wikijs_db_host: str = Field(default="postgres-shared", description="Wiki.js PostgreSQL host")
    wikijs_db_port: int = Field(default=5432, description="Wiki.js PostgreSQL port")
    wikijs_db_name: str = Field(default="library", description="Wiki.js database name")
    wikijs_db_user: str = Field(default="library_desk_listener", description="Wiki.js database user (read-only)")
    wikijs_db_password: str = Field(..., description="Wiki.js database password")
    wikijs_change_listener_debounce_seconds: int = Field(
        default=5,
        ge=1,
        le=60,
        description="Debounce duration to prevent processing duplicate notifications"
    )

    # SearXNG Configuration
    searxng_url: str = Field(default="http://searxng:8080", description="SearXNG URL")

    # Ollama Configuration
    ollama_url: str = Field(default="http://ollama:11434", description="Ollama URL")
    # Named ollama_llm_model (env: OLLAMA_LLM_MODEL) to avoid collision with the
    # OLLAMA_MODEL container env var, which is used for the embedding model.
    ollama_llm_model: str = Field(default="gemma4:e2b", description="Ollama LLM model for generation (keyword extraction, re-ranking, consolidation)")
    ollama_embedding_model: str = Field(default="nomic-embed-text", description="Ollama embedding model")

    # HybridRAG Configuration
    reranker_enabled: bool = Field(default=True, description="Enable LLM re-ranking")
    hybrid_rag_vector_limit: int = Field(default=10, ge=1, le=50, description="Vector search limit")
    hybrid_rag_graph_limit: int = Field(default=10, ge=1, le=50, description="Graph search limit")
    hybrid_rag_web_limit: int = Field(default=5, ge=1, le=20, description="Web search limit")
    vector_similarity_threshold: float = Field(default=0.7, ge=0.0, le=1.0, description="Minimum similarity score for vector results")

    # Entity Linking Fuzzy Matching Configuration
    entity_linking_min_confidence: float = Field(default=0.70, ge=0.0, le=1.0, description="Minimum confidence for entity-document matching")
    entity_linking_min_entity_length: int = Field(default=5, ge=1, le=50, description="Minimum entity name length for matching")
    entity_linking_min_containment_ratio: float = Field(default=0.30, ge=0.0, le=1.0, description="Minimum containment ratio for substring matching")
    entity_linking_min_token_overlap: float = Field(default=0.60, ge=0.0, le=1.0, description="Minimum token overlap ratio for matching")

    # Redis Configuration (for job tracking - separate DB from wiki)
    redis_host: str = Field(default="redis-shared", description="Redis host")
    redis_port: int = Field(default=6379, description="Redis port")
    redis_db: int = Field(default=4, description="Redis database number (4 for library-desk jobs)")

    # Application
    app_name: str = Field(default="Library Desk", description="Application name")
    app_version: str = Field(default=__version__, description="Application version")
    debug: bool = Field(default=False, description="Debug mode")

    # CORS: comma-separated list of allowed browser origins. The default "*"
    # is only acceptable because allow_credentials is disabled (see main.py).
    cors_allow_origins: str = Field(
        default="*",
        description="Comma-separated CORS allowed origins (credentials are never allowed)"
    )

    @property
    def cors_allow_origins_list(self) -> list[str]:
        """cors_allow_origins parsed into a list for CORSMiddleware."""
        return [o.strip() for o in self.cors_allow_origins.split(",") if o.strip()]

    # RAG Search Configuration
    search_cache_ttl: int = Field(default=300, ge=0, le=3600, description="Search cache TTL in seconds")
    search_timeout: int = Field(default=10, ge=1, le=60, description="SearXNG timeout in seconds")
    search_default_limit: int = Field(default=10, ge=1, le=20, description="Default number of search results")

    # Content Extraction Configuration
    content_extraction_timeout: int = Field(default=5, ge=1, le=30, description="Trafilatura per-URL timeout in seconds")
    content_max_length: int = Field(default=2000, ge=500, le=10000, description="Max extracted content length per result")

    # Paperless-ngx Configuration
    paperless_url: str = Field(default="http://paperless:8000", description="Paperless-ngx URL")
    paperless_token: str = Field(default="", description="Paperless-ngx API token")
    paperless_timeout: int = Field(default=30, ge=5, le=120, description="Paperless API timeout in seconds")

    # Document Store Configuration
    document_store_enabled: bool = Field(default=True, description="Enable document store feature")
    document_catalog_path_prefix: str = Field(default="docs", description="Wiki path prefix for catalog pages")

    # Volatile Cache Configuration
    volatile_cache_enabled: bool = Field(default=True, description="Enable volatile cache feature")
    volatile_default_ttl: int = Field(default=3600, ge=60, le=86400, description="Default TTL in seconds")
    volatile_weather_ttl: int = Field(default=1800, ge=60, le=7200, description="Weather data TTL in seconds")
    volatile_news_ttl: int = Field(default=7200, ge=300, le=86400, description="News data TTL in seconds")
    volatile_financial_ttl: int = Field(default=300, ge=60, le=3600, description="Financial data TTL in seconds")

    # Maintenance Configuration
    maintenance_orphan_cleanup_enabled: bool = Field(default=True, description="Enable automatic orphan cleanup")
    maintenance_cleanup_batch_size: int = Field(default=100, ge=10, le=1000, description="Cleanup batch size")

    # Central Settings Database (Tatlock-wide)
    system_settings_host: str = Field(default="postgres-shared", description="System settings PostgreSQL host")
    system_settings_port: int = Field(default=5432, description="System settings PostgreSQL port")
    system_settings_db: str = Field(default="system_settings", description="System settings database name")
    system_settings_user: str = Field(default="settings", description="System settings database user")
    system_settings_password: str = Field(default="", description="System settings database password")

    # Scheduler Service
    scheduler_url: str = Field(default="http://scheduler:8090", description="Scheduler service URL")
    scheduler_api_key: str = Field(
        default="",
        description=(
            "Bearer key for the Scheduler's auth-guarded task-management API; "
            "required for runtime prefetch task registration"
        ),
    )

    @property
    def qdrant_url(self) -> str:
        """Computed Qdrant URL."""
        return f"http://{self.qdrant_host}:{self.qdrant_port}"

    @property
    def redis_url(self) -> str:
        """Computed Redis URL."""
        return f"redis://{self.redis_host}:{self.redis_port}/{self.redis_db}"

    @property
    def system_settings_dsn(self) -> str:
        """Computed System Settings PostgreSQL DSN."""
        if not self.system_settings_password:
            return ""
        return (
            f"postgresql://{self.system_settings_user}:{self.system_settings_password}"
            f"@{self.system_settings_host}:{self.system_settings_port}/{self.system_settings_db}"
        )


@lru_cache
def get_settings() -> Settings:
    """
    Get cached settings instance.
    Uses lru_cache to ensure single instance across app.
    """
    return Settings()