ATOCore/src/atocore/config.py

"""AtoCore configuration via environment variables."""

from pathlib import Path

from pydantic_settings import BaseSettings


class Settings(BaseSettings):
    env: str = "development"
    debug: bool = False
    log_level: str = "INFO"
    data_dir: Path = Path("./data")
    db_dir: Path | None = None
    chroma_dir: Path | None = None
    cache_dir: Path | None = None
    tmp_dir: Path | None = None
    vault_source_dir: Path = Path("./sources/vault")
    drive_source_dir: Path = Path("./sources/drive")
    source_vault_enabled: bool = True
    source_drive_enabled: bool = True
    log_dir: Path = Path("./logs")
    backup_dir: Path = Path("./backups")
    run_dir: Path = Path("./run")
    project_registry_path: Path = Path("./config/project-registry.json")
    assets_dir: Path | None = None
    assets_max_upload_bytes: int = 20 * 1024 * 1024  # 20 MB per upload
    host: str = "127.0.0.1"
    port: int = 8100
    db_busy_timeout_ms: int = 5000

    # Embedding
    embedding_model: str = (
        "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
    )

    # Chunking
    chunk_max_size: int = 800
    chunk_overlap: int = 100
    chunk_min_size: int = 50

    # Context
    context_budget: int = 3000
    context_top_k: int = 15

    # Retrieval ranking weights (tunable per environment).
    # All multipliers default to the values used since Wave 1; tighten or
    # loosen them via ATOCORE_* env vars without touching code.
    rank_project_match_boost: float = 2.0
    rank_query_token_step: float = 0.08
    rank_query_token_cap: float = 1.32
    rank_path_high_signal_boost: float = 1.18
    rank_path_low_signal_penalty: float = 0.72

    model_config = {"env_prefix": "ATOCORE_"}

    @property
    def db_path(self) -> Path:
        legacy_path = self.resolved_data_dir / "atocore.db"
        if self.db_dir is not None:
            return self.resolved_db_dir / "atocore.db"
        if legacy_path.exists():
            return legacy_path
        return self.resolved_db_dir / "atocore.db"

    @property
    def chroma_path(self) -> Path:
        return self._resolve_path(self.chroma_dir or (self.resolved_data_dir / "chroma"))

    @property
    def cache_path(self) -> Path:
        return self._resolve_path(self.cache_dir or (self.resolved_data_dir / "cache"))

    @property
    def tmp_path(self) -> Path:
        return self._resolve_path(self.tmp_dir or (self.resolved_data_dir / "tmp"))

    @property
    def resolved_data_dir(self) -> Path:
        return self._resolve_path(self.data_dir)

    @property
    def resolved_assets_dir(self) -> Path:
        return self._resolve_path(self.assets_dir or (self.resolved_data_dir / "assets"))

    @property
    def resolved_db_dir(self) -> Path:
        return self._resolve_path(self.db_dir or (self.resolved_data_dir / "db"))

    @property
    def resolved_vault_source_dir(self) -> Path:
        return self._resolve_path(self.vault_source_dir)

    @property
    def resolved_drive_source_dir(self) -> Path:
        return self._resolve_path(self.drive_source_dir)

    @property
    def resolved_log_dir(self) -> Path:
        return self._resolve_path(self.log_dir)

    @property
    def resolved_backup_dir(self) -> Path:
        return self._resolve_path(self.backup_dir)

    @property
    def resolved_run_dir(self) -> Path:
        if self.run_dir == Path("./run"):
            return self._resolve_path(self.resolved_data_dir.parent / "run")
        return self._resolve_path(self.run_dir)

    @property
    def resolved_project_registry_path(self) -> Path:
        """Path to the project registry JSON file.

        If ``ATOCORE_PROJECT_REGISTRY_DIR`` env var is set, the registry
        lives at ``<that dir>/project-registry.json``. Otherwise falls
        back to the configured ``project_registry_path`` field.

        This lets Docker deployments point at a mounted volume via env
        var without the ephemeral in-image ``/app/config/`` getting
        wiped on every rebuild.
        """
        import os

        registry_dir = os.environ.get("ATOCORE_PROJECT_REGISTRY_DIR", "").strip()
        if registry_dir:
            return Path(registry_dir) / "project-registry.json"
        return self._resolve_path(self.project_registry_path)

    @property
    def machine_dirs(self) -> list[Path]:
        return [
            self.db_path.parent,
            self.chroma_path,
            self.cache_path,
            self.tmp_path,
            self.resolved_log_dir,
            self.resolved_backup_dir,
            self.resolved_run_dir,
            self.resolved_project_registry_path.parent,
            self.resolved_assets_dir,
        ]

    @property
    def source_specs(self) -> list[dict[str, object]]:
        return [
            {
                "name": "vault",
                "enabled": self.source_vault_enabled,
                "path": self.resolved_vault_source_dir,
                "read_only": True,
            },
            {
                "name": "drive",
                "enabled": self.source_drive_enabled,
                "path": self.resolved_drive_source_dir,
                "read_only": True,
            },
        ]

    @property
    def source_dirs(self) -> list[Path]:
        return [spec["path"] for spec in self.source_specs if spec["enabled"]]

    def _resolve_path(self, path: Path) -> Path:
        return path.expanduser().resolve(strict=False)


settings = Settings()


def ensure_runtime_dirs() -> None:
    """Create writable runtime directories for machine state and logs.

    Source directories are intentionally excluded because they are treated as
    read-only ingestion inputs by convention.
    """
    for directory in settings.machine_dirs:
        directory.mkdir(parents=True, exist_ok=True)