siftlode/backend/app/sysconfig.py

"""Admin-editable system configuration: a DB-override layer over the env/config defaults.

The registry (SPECS) is the single source of truth for which config keys can be overridden
from the admin Configuration page, plus each key's type, admin-UI group, env/config default,
bounds, and whether it's a secret. The resolver returns the DB override if one is set, else
``settings.<default_attr>`` (same DB-override-or-default pattern as app.state). Secrets are
stored Fernet-encrypted at rest (requires TOKEN_ENCRYPTION_KEY; without it, secrets can't be
stored in the DB and stay env-only).
"""
from dataclasses import dataclass

from sqlalchemy.orm import Session

from app import security
from app.config import settings
from app.models import SystemConfig


@dataclass(frozen=True)
class ConfigSpec:
    key: str
    type: str  # "int" | "str" | "bool"
    group: str  # admin-UI grouping (logically related keys stay together)
    default_attr: str  # attribute on `settings` holding the env/config default
    secret: bool = False
    min: int | None = None
    max: int | None = None
    allow_empty: bool = False  # str keys: a stored "" is an explicit empty value, not "unset"


# Registry of DB-overridable keys. Add a key here + wire its read through get_*() to move it
# off env into the admin UI; the admin page renders it automatically from this list.
SPECS: tuple[ConfigSpec, ...] = (
    # --- Email / SMTP (one logical group; the password is the only secret) ---
    ConfigSpec("smtp_host", "str", "email", "smtp_host"),
    ConfigSpec("smtp_port", "int", "email", "smtp_port", min=1, max=65535),
    ConfigSpec("smtp_user", "str", "email", "smtp_user", allow_empty=True),
    ConfigSpec("smtp_from", "str", "email", "smtp_from"),
    ConfigSpec("smtp_password", "str", "email", "smtp_password", secret=True),
    # --- Quota (shared YouTube Data API daily budget) ---
    ConfigSpec("quota_daily_budget", "int", "quota", "quota_daily_budget", min=1, max=1_000_000),
    ConfigSpec("backfill_quota_reserve", "int", "quota", "backfill_quota_reserve", min=0, max=1_000_000),
    ConfigSpec("search_daily_limit_per_user", "int", "quota", "search_daily_limit_per_user", min=0, max=100_000),
    # Live-search source: "scrape" (InnerTube, zero API quota) or "api" (search.list, 100u/page).
    ConfigSpec("search_source", "str", "quota", "search_source"),
    # --- Backfill (recent-first first pass per channel) ---
    ConfigSpec("backfill_recent_max_videos", "int", "backfill", "backfill_recent_max_videos", min=1, max=100_000),
    ConfigSpec("backfill_recent_max_days", "int", "backfill", "backfill_recent_max_days", min=1, max=36_500),
    # --- Shorts probe ---
    ConfigSpec("shorts_probe_max_seconds", "int", "shorts", "shorts_probe_max_seconds", min=1, max=3_600),
    ConfigSpec("shorts_probe_batch", "int", "shorts", "shorts_probe_batch", min=1, max=10_000),
    # --- Batch sizes ---
    ConfigSpec("enrich_batch_size", "int", "batch", "enrich_batch_size", min=1, max=50),
    ConfigSpec("autotag_title_sample", "int", "batch", "autotag_title_sample", min=1, max=1_000),
    # --- Discovery cleanup (search + explore ephemeral content) ---
    # Days an explored-but-unsubscribed channel is kept before the cleanup job purges it.
    ConfigSpec("explore_grace_days", "int", "explore", "explore_grace_days", min=0, max=3_650),
    # Days an un-kept live-search result video is kept before the cleanup job removes it.
    ConfigSpec("search_grace_days", "int", "explore", "search_grace_days", min=0, max=3_650),
    # --- YouTube Data API key (secret; optional — public reads prefer it over OAuth) ---
    ConfigSpec("youtube_api_key", "str", "youtube", "youtube_api_key", secret=True),
    # Optional egress proxy for YouTube API calls (fixed-IP host for an IP-restricted key).
    ConfigSpec("youtube_api_proxy", "str", "youtube", "youtube_api_proxy", allow_empty=True),
    # --- Google OAuth client (Sign in with Google; both encrypted, env fallback). Set from the
    #     install wizard / Configuration page so no restart is needed when the creds change. ---
    ConfigSpec("google_client_id", "str", "google", "google_client_id", secret=True),
    ConfigSpec("google_client_secret", "str", "google", "google_client_secret", secret=True),
    # --- Access / registration ---
    ConfigSpec("allow_registration", "bool", "access", "allow_registration"),
    # --- Download center (yt-dlp) — per-user defaults + retention/GC + layout ---
    ConfigSpec("download_total_max_bytes", "int", "downloads", "download_total_max_bytes", min=0),
    ConfigSpec("download_default_max_bytes", "int", "downloads", "download_default_max_bytes", min=0),
    ConfigSpec("download_default_max_concurrent", "int", "downloads", "download_default_max_concurrent", min=1, max=20),
    ConfigSpec("download_default_max_jobs", "int", "downloads", "download_default_max_jobs", min=1, max=100_000),
    ConfigSpec("download_retention_days", "int", "downloads", "download_retention_days", min=0, max=3_650),
    ConfigSpec("download_gc_grace_days", "int", "downloads", "download_gc_grace_days", min=0, max=3_650),
    ConfigSpec("download_layout", "str", "downloads", "download_layout"),
    ConfigSpec("download_worker_concurrency", "int", "downloads", "download_worker_concurrency", min=1, max=16),
    ConfigSpec("sponsorblock_default", "bool", "downloads", "sponsorblock_default"),
    # --- Plex integration (optional; local-file playback + Plex metadata) ---
    ConfigSpec("plex_enabled", "bool", "plex", "plex_enabled"),
    ConfigSpec("plex_server_url", "str", "plex", "plex_server_url"),
    ConfigSpec("plex_server_token", "str", "plex", "plex_server_token", secret=True),
    ConfigSpec("plex_path_map", "str", "plex", "plex_path_map"),
    ConfigSpec("plex_libraries", "str", "plex", "plex_libraries"),
    # (plex_sync_interval_min is tuned from the Scheduler dashboard, not here — it's a scheduler job.)
    ConfigSpec("plex_max_transcodes", "int", "plex", "plex_max_transcodes", min=0, max=16),
    # NOTE: plex_watch_sync_interval_min (config.py default) is surfaced here in Phase C, when the
    # incremental watch-sync scheduler job that reads it lands.
)

_BY_KEY: dict[str, ConfigSpec] = {s.key: s for s in SPECS}


def spec(key: str) -> ConfigSpec | None:
    return _BY_KEY.get(key)


def secrets_manageable() -> bool:
    """Secret values can only be stored when Fernet is configured (TOKEN_ENCRYPTION_KEY)."""
    return bool(settings.token_encryption_key)


def _default(s: ConfigSpec):
    return getattr(settings, s.default_attr)


def _coerce(s: ConfigSpec, raw: str):
    if s.type == "int":
        return int(raw)
    if s.type == "bool":
        return raw == "true"
    return raw


def _raw_override(db: Session, key: str) -> str | None:
    """Stored (decrypted) override string for `key`, or None if no override is set."""
    row = db.get(SystemConfig, key)
    if row is None or row.value is None:
        return None
    return security.decrypt(row.value) if row.encrypted else row.value


def get(db: Session, key: str):
    """Effective value: the DB override (typed) if set, else the env/config default."""
    s = _BY_KEY[key]
    raw = _raw_override(db, key)
    if raw is None:
        return _default(s)
    if raw == "" and not s.allow_empty:
        # For most keys an empty override means "fall back to the env default". Keys that opt
        # into allow_empty (e.g. smtp_user, youtube_api_proxy) treat "" as a real value — so an
        # admin can blank one to DISABLE it rather than being stuck with the env default.
        return _default(s)
    try:
        return _coerce(s, raw)
    except (TypeError, ValueError):
        return _default(s)


def get_str(db: Session, key: str) -> str:
    v = get(db, key)
    return "" if v is None else str(v)


def get_int(db: Session, key: str) -> int:
    return int(get(db, key))


def get_bool(db: Session, key: str) -> bool:
    return bool(get(db, key))


def set_value(db: Session, key: str, value) -> None:
    """Validate, coerce, and persist a DB override for `key`. Secrets are encrypted."""
    s = _BY_KEY[key]
    if s.type == "int":
        v = int(value)
        if s.min is not None and v < s.min:
            raise ValueError(f"{key} must be >= {s.min}")
        if s.max is not None and v > s.max:
            raise ValueError(f"{key} must be <= {s.max}")
        raw = str(v)
    elif s.type == "bool":
        raw = "true" if value else "false"
    else:
        raw = "" if value is None else str(value)

    stored, encrypted = raw, False
    if s.secret:
        if not secrets_manageable():
            raise RuntimeError("TOKEN_ENCRYPTION_KEY is not configured")
        stored, encrypted = security.encrypt(raw) or "", True

    row = db.get(SystemConfig, key)
    if row is None:
        row = SystemConfig(key=key)
        db.add(row)
    row.value = stored
    row.encrypted = encrypted
    db.commit()


def reset(db: Session, key: str) -> None:
    """Remove the DB override for `key` (fall back to the env/config default)."""
    row = db.get(SystemConfig, key)
    if row is not None:
        db.delete(row)
        db.commit()


def describe(db: Session) -> dict:
    """Admin-UI metadata + current values, grouped. Secret values are never echoed —
    only whether an override is set and whether an env default exists."""
    groups: dict[str, list[dict]] = {}
    for s in SPECS:
        is_set = db.get(SystemConfig, s.key) is not None
        item: dict = {
            "key": s.key,
            "type": s.type,
            "group": s.group,
            "secret": s.secret,
            "min": s.min,
            "max": s.max,
            "is_set": is_set,  # an override row exists
            "allow_empty": s.allow_empty,  # if true, the UI stores "" rather than deleting the row
        }
        if s.secret:
            item["default_is_set"] = bool(_default(s))
        else:
            item["value"] = get(db, s.key)
            item["default"] = _default(s)
        groups.setdefault(s.group, []).append(item)
    return {"groups": groups, "secrets_manageable": secrets_manageable()}