src/config.py

"""Application configuration for imageO_v3."""

from __future__ import annotations

import os
from typing import Optional

from pydantic import Field
from pydantic_settings import BaseSettings, SettingsConfigDict


# Cache defaults are set only when they are not already configured.
os.environ.setdefault("XDG_CACHE_HOME", "/app/.cache")
os.environ.setdefault("HF_HOME", "/app/.cache/huggingface")
os.environ.setdefault("NUMBA_DISABLE_CACHE", "1")


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

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

    app_env: str = Field(default="development", description="Runtime environment")
    log_level: str = Field(default="INFO", description="Logger minimum level")
    model_version: str = Field(default="v3.0.0", description="Service model version")

    redis_url: str = Field(default="", description="Redis connection URL")

    hf_token: str = Field(default="", description="Hugging Face token for gated model access")
    replay_attack_ttl_s: int = Field(default=60, description="HMAC timestamp TTL")
    prediction_cache_ttl_s: int = Field(default=300, description="Prediction cache TTL")
    max_image_size_mb: int = Field(default=16, description="Maximum upload size in MB")

    model_checkpoint_path: str = Field(
        default="",
        alias="MODEL_CHECKPOINT_PATH",
        description="Local path to ABMIL .pt when ABMIL_HF_REPO_ID is unset; ignored when Hub repo id is set",
    )

    abmil_hf_repo_id: Optional[str] = Field(
        default=None,
        description="Hugging Face Hub repo id (e.g. org/private-repo). If set, ABMIL checkpoint is fetched via hf_hub_download.",
    )
    abmil_hf_filename: str = Field(
        default="production_model.pt",
        description="Checkpoint filename inside the Hub repo (top level or under ABMIL_HF_SUBFOLDER)",
    )
    abmil_hf_revision: Optional[str] = Field(
        default=None,
        description="Optional Hub revision: branch, tag, or commit SHA (pin in production)",
    )
    abmil_hf_subfolder: Optional[str] = Field(
        default=None,
        description="Optional folder inside the repo containing ABMIL_HF_FILENAME",
    )
    abmil_hf_local_files_only: bool = Field(
        default=False,
        description="If true, Hub resolution uses only local HF cache (no network)",
    )

    dinov3_model_id: str = Field(
        default="facebook/dinov3-vitb16-pretrain-lvd1689m",
        description="Hugging Face model id for DINOv3 backbone",
    )
    embedding_batch_size: int = Field(default=16, description="Batch size for tile embedding")
    embedding_device: Optional[str] = Field(
        default=None,
        description="Optional device override (cpu/cuda)",
    )
    embedding_dtype: Optional[str] = Field(
        default=None,
        description="Optional dtype for DINO model loading (auto/float16/float32/bfloat16)",
    )
    dinov3_local_files_only: bool = Field(
        default=False,
        description="If true, do not fetch model files from Hugging Face",
    )

    tile_size: int = Field(default=128, description="Preprocessing tile size")
    tile_overlap_ratio: float = Field(default=0.25, description="Preprocessing tile overlap ratio")
    tile_shrink_factor: float = Field(default=0.92, description="ROI shrink factor")

    abmil_attn_dim: int = Field(default=256, description="Fallback ABMIL attention dimension")
    abmil_classifier_hidden: int = Field(
        default=256,
        description="Fallback ABMIL classifier hidden size",
    )
    abmil_attn_hidden: int = Field(default=128, description="Fallback gated attention hidden size")
    abmil_dropout: float = Field(default=0.40, description="Fallback ABMIL dropout")
    abmil_threshold: float = Field(default=0.5, description="Fallback positive class threshold")


settings = Settings()