ForexBot2/app_config.py

"""
app_config.py — deployment-settings overlay (config.json)
=========================================================

Loads the gitignored config.json at the repo root ONCE per process.
Deployment surface ONLY: Telegram credentials, data-provider selection
and API keys, scanned pairs/timeframes, per-pair base blocked hours,
alert-quality boot default, log level. Signal logic, weights,
thresholds and gates stay in config.py / pair_signals.

Precedence for every setting: env var → config.json → code default.
A repo-root .env file (gitignored) is loaded at import via setdefault,
so it behaves exactly like real environment variables except that a
real shell export always wins. Secrets have NO code default — with
neither env nor config.json the bot refuses to start
(telegram_bot.main) and data fetches fail with a named error
(data_provider).

Parity contract (test-enforced): with no config.json, or one holding
the config.json.example defaults, every produced PlatformConfig is
byte-identical to the pure-code defaults. apply_pair_overrides() runs
in the pair factory BEFORE the validated per-timeframe deltas, so the
bot, CLI and backtester all see the same overlay (live == backtest).

Spec: docs/superpowers/specs/2026-07-21-centralized-config-design.md
"""

import json
import logging
import os
from dataclasses import dataclass, field
from typing import Any, Dict, List, Optional

from config import PAIR_INFO, PlatformConfig, Timeframe, XAUUSD

logger = logging.getLogger(__name__)

CONFIG_PATH = os.path.join(
    os.path.dirname(os.path.abspath(__file__)), "config.json")
ENV_PATH = os.path.join(
    os.path.dirname(os.path.abspath(__file__)), ".env")


def load_dotenv(path: str = ENV_PATH) -> None:
    """Minimal .env loader (no python-dotenv dependency).

    KEY=VALUE lines land in os.environ via setdefault — a variable
    already exported in the shell always wins, keeping the
    env → config.json precedence intact (.env is just a convenient
    place to put env vars). Comments, blank lines, ``export `` prefixes
    and single/double quotes are handled; anything else is skipped.
    """
    try:
        with open(path, encoding="utf-8") as fh:
            lines = fh.read().splitlines()
    except OSError:
        return
    for line in lines:
        line = line.strip()
        if not line or line.startswith("#") or "=" not in line:
            continue
        if line.startswith("export "):
            line = line[len("export "):]
        key, _, value = line.partition("=")
        key, value = key.strip(), value.strip()
        if len(value) >= 2 and value[0] == value[-1] and value[0] in "\"'":
            value = value[1:-1]
        elif value[:1] not in "\"'":
            # Unquoted value: whitespace-then-# starts an inline comment
            # (KEY=abc  # prod). Quote the value to keep a literal " #".
            for sep in (" #", "\t#"):
                cut = value.find(sep)
                if cut != -1:
                    value = value[:cut].rstrip()
        if key:
            os.environ.setdefault(key, value)


# Module import == process boot, before any resolver can run.
load_dotenv()

_VALID_QUALITIES = ("A+", "A", "B", "C")
_VALID_LOG_LEVELS = ("DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL")
# Timeframes the bot's candle-boundary scheduler supports (must have
# AUTOSCAN_CONFIRMATIONS entries in telegram_bot.py).
_SCANNABLE_TFS = ("M5", "M15", "H1", "H4")

_KNOWN_TOP = {"telegram", "data_providers", "scanning", "pairs", "log_level"}
_KNOWN_TELEGRAM = {"token", "chat_id", "channel_id", "alert_min_quality"}
_KNOWN_SCANNING = {"pairs", "timeframes"}
_KNOWN_PAIR_KEYS = {"blocked_hours_utc"}


class AppConfigError(Exception):
    """config.json is present but invalid — fail fast at boot."""


@dataclass
class AppConfig:
    telegram_token: str = ""
    telegram_chat_id: str = ""
    telegram_channel_id: str = ""          # "" = channel feed disabled
    alert_min_quality: str = "C"
    active_provider: str = "twelve_data"
    provider_settings: Dict[str, Dict[str, Any]] = field(default_factory=dict)
    scan_pairs: List[str] = field(default_factory=lambda: [XAUUSD])
    scan_timeframes: List[Timeframe] = field(default_factory=lambda: [
        Timeframe.M5, Timeframe.M15, Timeframe.H1, Timeframe.H4])
    pair_overrides: Dict[str, Dict[str, Any]] = field(default_factory=dict)
    log_level: str = "INFO"


def _check_keys(section: Dict[str, Any], known: set, where: str) -> None:
    if not isinstance(section, dict):
        raise AppConfigError(f"config.json: {where} must be a JSON object")
    unknown = sorted(set(section) - known)
    if unknown:
        raise AppConfigError(
            f"config.json: unknown key(s) {unknown} in {where}; "
            f"known keys: {sorted(known)}")


def load_app_config(path: str = CONFIG_PATH) -> AppConfig:
    """Parse + validate config.json. Missing file → pure defaults."""
    app = AppConfig()
    if not os.path.exists(path):
        logger.warning(
            "config.json not found at %s — running on code defaults "
            "(secrets must come from environment variables)", path)
        return app
    try:
        with open(path, encoding="utf-8") as fh:
            raw = json.load(fh)
    except json.JSONDecodeError as e:
        raise AppConfigError(f"config.json is not valid JSON: {e}") from e
    if not isinstance(raw, dict):
        raise AppConfigError("config.json top level must be a JSON object")
    _check_keys(raw, _KNOWN_TOP, "top level")

    tg = raw.get("telegram", {})
    _check_keys(tg, _KNOWN_TELEGRAM, '"telegram"')
    app.telegram_token = str(tg.get("token", app.telegram_token))
    app.telegram_chat_id = str(tg.get("chat_id", app.telegram_chat_id))
    app.telegram_channel_id = str(
        tg.get("channel_id", app.telegram_channel_id))
    quality = tg.get("alert_min_quality", app.alert_min_quality)
    if quality not in _VALID_QUALITIES:
        raise AppConfigError(
            f'config.json: telegram.alert_min_quality "{quality}" '
            f"not in {_VALID_QUALITIES}")
    app.alert_min_quality = quality

    dp = raw.get("data_providers")
    if dp is not None:
        if not isinstance(dp, dict):
            raise AppConfigError('config.json: "data_providers" must be an object')
        app.active_provider = str(dp.get("active", app.active_provider))
        app.provider_settings = {}
        for name, block in dp.items():
            if name == "active":
                continue
            if not isinstance(block, dict):
                raise AppConfigError(
                    f'config.json: data_providers.{name} must be an object')
            app.provider_settings[name] = dict(block)
        if app.active_provider not in app.provider_settings:
            raise AppConfigError(
                f'config.json: data_providers.active "{app.active_provider}" '
                "has no matching provider block")

    scanning = raw.get("scanning", {})
    _check_keys(scanning, _KNOWN_SCANNING, '"scanning"')
    if "pairs" in scanning:
        pairs = scanning["pairs"]
        if not isinstance(pairs, list):
            raise AppConfigError('config.json: scanning.pairs must be a list')
        bad = [p for p in pairs if p not in PAIR_INFO]
        if bad:
            raise AppConfigError(
                f"config.json: unknown pair(s) {bad} in scanning.pairs; "
                f"known: {sorted(PAIR_INFO)}")
        app.scan_pairs = list(pairs)
    if "timeframes" in scanning:
        names = scanning["timeframes"]
        if not isinstance(names, list):
            raise AppConfigError(
                'config.json: scanning.timeframes must be a list')
        bad = [n for n in names if n not in _SCANNABLE_TFS]
        if bad:
            raise AppConfigError(
                f"config.json: unsupported timeframe(s) {bad} in "
                f"scanning.timeframes; supported: {list(_SCANNABLE_TFS)}")
        app.scan_timeframes = [Timeframe[n] for n in names]

    pair_section = raw.get("pairs", {})
    if not isinstance(pair_section, dict):
        raise AppConfigError('config.json: "pairs" must be a JSON object')
    for symbol, overrides in pair_section.items():
        if symbol not in PAIR_INFO:
            raise AppConfigError(
                f'config.json: unknown pair "{symbol}" in pairs; '
                f"known: {sorted(PAIR_INFO)}")
        _check_keys(overrides, _KNOWN_PAIR_KEYS, f'pairs."{symbol}"')
        if "blocked_hours_utc" in overrides:
            hours = overrides["blocked_hours_utc"]
            valid = isinstance(hours, list) and all(
                isinstance(h, int) and not isinstance(h, bool)
                and 0 <= h <= 23 for h in hours)
            if not valid:
                raise AppConfigError(
                    f'config.json: pairs."{symbol}".blocked_hours_utc must '
                    "be a list of integers in 0-23")
    app.pair_overrides = {s: dict(o) for s, o in pair_section.items()}

    level = raw.get("log_level", app.log_level)
    if level not in _VALID_LOG_LEVELS:
        raise AppConfigError(
            f'config.json: log_level "{level}" not in {_VALID_LOG_LEVELS}')
    app.log_level = level
    return app


# ── Process-wide singleton ────────────────────────────────────────────

_cached: Optional[AppConfig] = None


def get_app_config() -> AppConfig:
    global _cached
    if _cached is None:
        _cached = load_app_config()
    return _cached


def set_app_config(app: Optional[AppConfig]) -> None:
    """Override the process-wide AppConfig (tests/experiments).
    Pass None to re-enable lazy loading from CONFIG_PATH."""
    global _cached
    _cached = app


# ── Resolution helpers: env var → config.json → default ───────────────

def telegram_token(app: Optional[AppConfig] = None) -> str:
    app = app or get_app_config()
    return os.environ.get("TELEGRAM_TOKEN") or app.telegram_token


def telegram_chat_id(app: Optional[AppConfig] = None) -> str:
    app = app or get_app_config()
    return os.environ.get("TELEGRAM_CHAT_ID") or app.telegram_chat_id


def telegram_channel_id(app: Optional[AppConfig] = None) -> str:
    """Env set-but-empty ("") means "disable the feed" and beats JSON,
    so this checks None-ness, not truthiness."""
    app = app or get_app_config()
    env = os.environ.get("TELEGRAM_CHANNEL_ID")
    return env if env is not None else app.telegram_channel_id


def provider_api_key(app: Optional[AppConfig] = None) -> str:
    """API key for the ACTIVE provider. The env override is per-provider
    (TWELVE_DATA_API_KEY applies only when twelve_data is active)."""
    app = app or get_app_config()
    if app.active_provider == "twelve_data":
        env = os.environ.get("TWELVE_DATA_API_KEY")
        if env:
            return env
    block = app.provider_settings.get(app.active_provider, {})
    return str(block.get("api_key", ""))


# ── PlatformConfig overlay ────────────────────────────────────────────

def apply_pair_overrides(
    cfg: PlatformConfig, app: Optional[AppConfig] = None
) -> PlatformConfig:
    """Stamp deployment settings from config.json onto a PlatformConfig.

    Called by the pair factories BEFORE their validated per-timeframe
    deltas, so e.g. the M5 hour-9 append lands on top of the JSON base.
    The pair's base blocked_hours_utc is set on BOTH mirrored copies
    (xau_strategy + backtest) so they cannot drift.
    """
    app = app or get_app_config()
    overrides = app.pair_overrides.get(cfg.symbol, {})
    if "blocked_hours_utc" in overrides:
        hours = list(overrides["blocked_hours_utc"])
        cfg.xau_strategy.blocked_hours_utc = hours
        cfg.backtest.blocked_hours_utc = list(hours)
    cfg.scan_pairs = list(app.scan_pairs)
    cfg.scan_timeframes = list(app.scan_timeframes)
    return cfg