RAG/backend/app/core/config.py

"""Typed runtime configuration loaded from non-secret environment values."""

from functools import lru_cache
from pathlib import Path
from typing import Literal, Self
from urllib.parse import urlsplit

from pydantic import Field, field_validator, model_validator
from pydantic_settings import BaseSettings, SettingsConfigDict
from sqlalchemy import URL

from app.core.secrets import read_secret_file


class Settings(BaseSettings):
    """Application settings; secret values stay in mounted files."""

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

    app_env: Literal["development", "test", "production"] = "development"
    app_name: str = "geological-rag"
    app_secret_key_file: Path = Path("/run/secrets/app_secret_key")

    postgres_host: str = "db"
    postgres_port: int = Field(default=5432, ge=1, le=65535)
    postgres_db: str = "geological_rag"
    postgres_user: str = "geological_rag_app"
    postgres_password_file: Path = Path("/run/secrets/postgres_app_password")

    upload_root: Path = Path("/data/uploads")
    max_upload_mb: int = Field(default=100, ge=1, le=2048)

    model_gateway_base_url: str = "http://model-gateway:8000"
    model_gateway_token_file: Path = Path("/run/secrets/model_gateway_api_token")
    model_gateway_caller: Literal["api", "worker"] = "api"
    model_gateway_timeout_seconds: float = Field(default=120, gt=0, le=600)

    bailian_openai_base_url: str = (
        "https://<workspace-id>.cn-beijing.maas.aliyuncs.com/compatible-mode/v1"
    )
    bailian_native_base_url: str = "https://<workspace-id>.cn-beijing.maas.aliyuncs.com/api/v1"
    bailian_rerank_base_url: str = (
        "https://<workspace-id>.cn-beijing.maas.aliyuncs.com/compatible-api/v1"
    )
    dashscope_api_key_file: Path = Path("/run/secrets/bailian_api_key")

    embedding_model: str = "text-embedding-v4"
    embedding_dimension: Literal[1024] = 1024
    rerank_model: str = "qwen3-rerank"
    llm_model: str = "deepseek-v4-flash"

    chunk_target_tokens: int = Field(default=512, ge=120, le=800)
    chunk_max_tokens: int = Field(default=800, ge=120, le=4000)
    chunk_overlap_tokens: int = Field(default=64, ge=0, le=256)
    vector_top_k: int = Field(default=50, ge=1, le=500)
    rerank_top_n: int = Field(default=10, ge=1, le=500)
    context_top_n: int = Field(default=8, ge=1, le=50)
    max_context_tokens: int = Field(default=10_000, ge=1, le=100_000)

    model_timeout_seconds: float = Field(default=90, gt=0, le=600)
    model_max_retries: int = Field(default=3, ge=0, le=10)
    model_max_concurrency: int = Field(default=4, ge=1, le=100)
    worker_capabilities: str = "document_parse,embedding,rerank,evaluation"

    @field_validator(
        "bailian_openai_base_url",
        "bailian_native_base_url",
        "bailian_rerank_base_url",
    )
    @classmethod
    def normalize_base_url(cls, value: str) -> str:
        return value.rstrip("/")

    @field_validator("model_gateway_base_url")
    @classmethod
    def validate_model_gateway_base_url(cls, value: str) -> str:
        normalized = value.rstrip("/")
        parsed = urlsplit(normalized)
        if (
            parsed.scheme != "http"
            or parsed.hostname != "model-gateway"
            or parsed.port != 8000
            or parsed.path not in ("", "/")
            or parsed.username is not None
            or parsed.password is not None
            or parsed.query
            or parsed.fragment
        ):
            raise ValueError("MODEL_GATEWAY_BASE_URL must be the fixed internal service URL")
        return normalized

    @field_validator("embedding_dimension", mode="before")
    @classmethod
    def parse_embedding_dimension(cls, value: object) -> int:
        """Accept Compose's string representation without widening the contract."""
        if value == "1024" or (
            isinstance(value, int) and not isinstance(value, bool) and value == 1024
        ):
            return 1024
        raise ValueError("EMBEDDING_DIMENSION must be exactly 1024")

    @model_validator(mode="after")
    def validate_rag_limits(self) -> Self:
        if self.chunk_overlap_tokens >= self.chunk_target_tokens:
            raise ValueError("CHUNK_OVERLAP_TOKENS must be smaller than CHUNK_TARGET_TOKENS")
        if self.chunk_target_tokens > self.chunk_max_tokens:
            raise ValueError("CHUNK_TARGET_TOKENS must not exceed CHUNK_MAX_TOKENS")
        if self.context_top_n > self.rerank_top_n:
            raise ValueError("CONTEXT_TOP_N must not exceed RERANK_TOP_N")
        if self.rerank_top_n > self.vector_top_k:
            raise ValueError("RERANK_TOP_N must not exceed VECTOR_TOP_K")
        return self

    def bailian_api_key(self) -> str:
        self.validate_live_bailian_endpoints()
        return read_secret_file(self.dashscope_api_key_file)

    def validate_live_bailian_endpoints(self) -> str:
        endpoints = {
            self.bailian_openai_base_url: "/compatible-mode/v1",
            self.bailian_rerank_base_url: "/compatible-api/v1",
        }
        hosts: set[str] = set()
        for endpoint, expected_path in endpoints.items():
            parsed = urlsplit(endpoint)
            host = parsed.hostname or ""
            if (
                parsed.scheme != "https"
                or parsed.path.rstrip("/") != expected_path
                or parsed.username is not None
                or parsed.password is not None
                or parsed.query
                or parsed.fragment
                or "<" in endpoint
                or not host.endswith(".cn-beijing.maas.aliyuncs.com")
            ):
                raise ValueError("Bailian endpoint is not an approved Beijing MaaS URL")
            hosts.add(host)
        if len(hosts) != 1:
            raise ValueError("Bailian endpoints must use the same workspace host")
        return hosts.pop()

    def database_url(self) -> URL:
        return URL.create(
            drivername="postgresql+psycopg",
            username=self.postgres_user,
            password=read_secret_file(self.postgres_password_file),
            host=self.postgres_host,
            port=self.postgres_port,
            database=self.postgres_db,
        )


@lru_cache(maxsize=1)
def get_settings() -> Settings:
    return Settings()