from __future__ import annotations
import os
import tomllib
from pathlib import Path
from pydantic import BaseModel, Field

REPO_ROOT = Path(__file__).resolve().parent.parent
DEFAULT_CONFIG = REPO_ROOT / "data" / "config.toml"
DEFAULT_DB = REPO_ROOT / "data" / "chat.db"

class Settings(BaseModel):
    featherless_api_key: str
    featherless_base_url: str = "https://api.featherless.ai/v1"
    narrative_model: str = "dphn/Dolphin-Mistral-24B-Venice-Edition"
    classifier_model: str = "NousResearch/Hermes-3-Llama-3.1-8B"
    classifier_fallbacks: list[str] = Field(
        default_factory=lambda: [
            "cognitivecomputations/dolphin-2.9.4-llama3-8b",
            "mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated",
        ]
    )
    ooc_marker: str = "(("
    retrieval_k: int = 4
    narrative_budget_hard: int = 8000
    narrative_budget_soft: int = 6000
    # Cap on each generated bot response. The asterisk-action format
    # (see ``_closing_instruction`` in chat/services/prompt.py) targets
    # 2-4 short interleaved action+dialogue beats; ~250 tokens fits that
    # without leaving room for the model to drift into multi-paragraph
    # inner-monologue prose. Bump back up if you want longer scenes;
    # drop to 150 for very terse banter.
    narrative_max_tokens: int = 250
    # Sampling temperature for narrative generation. 0.7 = grounded /
    # consistent; 0.85 = creative-but-in-character (default); 1.0 = wide
    # variety, can drift; >1.0 = often off-the-rails.
    narrative_temperature: float = 0.85
    classifier_budget_hard: int = 4000
    classifier_timeout_s: float = 30.0
    # Featherless free tier and lower paid tiers cap concurrent connections.
    # Set this to your account's max-concurrent-connections limit.
    featherless_max_concurrent: int = 2
    db_path: Path = DEFAULT_DB
    data_dir: Path = REPO_ROOT / "data"
    bind_host: str = "127.0.0.1"
    bind_port: int = 8000
    # Local MLX server (e.g. ``mlx-omni-server``) — serves any model
    # whose id starts with one of ``local_prefixes`` (default
    # ``"mlx-community/"``). The :class:`RoutedLLMClient` inspects the
    # ``model`` kwarg at call time: local-prefix -> local, else -> remote.
    # ``embed()`` always routes local.
    local_mlx_base_url: str = "http://127.0.0.1:10240/v1"
    local_mlx_max_concurrent: int = 1
    # Optional OpenRouter-style provider pinning for the classifier
    # client. Maps to the ``provider`` field on chat.completions.create
    # via ``extra_body``; the FeatherlessClient (which is just an
    # AsyncOpenAI wrapper) merges it into every call. Useful for forcing
    # Llama-3.1-8B classifier traffic onto Cerebras (~423 tok/s, 10x
    # the default Nebius). Empty list = no pin (provider is
    # OpenRouter's choice).
    classifier_provider_order: list[str] = Field(default_factory=list)
    # T112 (Phase 4.5): embedding model identifier. Default is the
    # deterministic local pseudo so fresh installs / tests don't need
    # any external infra. Override via config.toml to a real model id
    # (e.g. ``"mlx-community/bge-small-en-v1.5-bf16"``) once a local
    # MLX server is running.
    embedding_model: str = "pseudo-sha256-384"

def load_settings() -> Settings:
    config_path = Path(os.environ.get("CHAT_CONFIG_PATH", DEFAULT_CONFIG))
    raw: dict = {}
    if config_path.exists():
        raw = tomllib.loads(config_path.read_text())
    if "CHAT_DB_PATH" in os.environ:
        raw["db_path"] = Path(os.environ["CHAT_DB_PATH"])
    if "CHAT_DATA_DIR" in os.environ:
        raw["data_dir"] = Path(os.environ["CHAT_DATA_DIR"])
    elif "data_dir" not in raw and "db_path" in raw:
        # T31: when ``CHAT_DB_PATH`` is overridden (typical in tests) but
        # ``data_dir`` isn't, derive ``data_dir`` from the db's parent so
        # snapshot/auxiliary files stay alongside the test db rather than
        # leaking into the real repo data dir.
        raw["data_dir"] = Path(raw["db_path"]).parent
    return Settings(**raw)