"""Internal control surface for the Go daemon (backend/daemon/).

The gateway bot and the recurring worker jobs moved out of this process into
`thermograph-daemon` — Go owns only the long-lived stateful I/O (the Discord
websocket, RESUME/heartbeat/backoff, interval timers). Anything that needs
*data* calls back in here, because grading depends on polars + the parquet
cache: reimplementing it out-of-process would let the bot's grades drift from
the API's, and the slash-command path deliberately shares one grade builder so
the two never drift. These routes hand the daemon finished answers, keeping it
entirely out of the grading contract.

Not publicly reachable: the deploy Caddyfile routes only /api/*, /digest and
/discord/interactions to this backend, so /internal/* never resolves through
the public domain. The shared-secret header is defence in depth on top of
that, not the only control — and it fails closed: with no token configured
the whole surface answers 404, never "open".

Deliberately NOT under BASE (same posture as /healthz): the daemon targets
THERMOGRAPH_API_BASE_INTERNAL directly and shouldn't need to know
THERMOGRAPH_BASE to construct a path.
"""
import hashlib
import hmac
import os
import threading

from fastapi import APIRouter, Depends, Header, HTTPException
from pydantic import BaseModel

_TOKEN_ENV = "THERMOGRAPH_INTERNAL_TOKEN"
_HEADER = "X-Thermograph-Internal-Token"

# Domain-separation label for the derived token. MUST match the Go daemon's
# internal/config constant byte-for-byte or every callback 401s.
_DERIVE_LABEL = b"thermograph/internal-api/v1"


def resolve_internal_token() -> str:
    """The shared secret guarding /internal/*, or "" if it can't be established.

    An explicit THERMOGRAPH_INTERNAL_TOKEN always wins. Otherwise it is DERIVED
    from THERMOGRAPH_AUTH_SECRET, which every environment already provisions, so
    standing up the daemon needs no new vault entry and no operator step -- one
    less secret to rotate, leak, or forget on a new host.

    HMAC with a distinct label rather than reusing AUTH_SECRET directly: that is
    ordinary domain separation, so a leak of this token can't be replayed as the
    session-signing key it was derived from, and the derivation is one-way.

    Deliberately reads THERMOGRAPH_AUTH_SECRET from the environment rather than
    users.py's effective value: users.py falls back to a random per-process
    secret when the env var is unset, and two processes would then derive two
    different tokens and fail every call in a way that looks like a bug rather
    than missing config. Unset env var => "" => the surface stays closed."""
    explicit = os.environ.get(_TOKEN_ENV, "").strip()
    if explicit:
        return explicit
    auth_secret = os.environ.get("THERMOGRAPH_AUTH_SECRET", "").strip()
    if not auth_secret:
        return ""
    return hmac.new(auth_secret.encode(), _DERIVE_LABEL, hashlib.sha256).hexdigest()


def _require_internal_token(
    x_thermograph_internal_token: str = Header(default=""),
) -> None:
    """Gate every internal route on the shared secret.

    Read from the environment per request (not at import) so the fail-closed
    behaviour is a property of the running config, not of import order — and so
    tests can exercise both states without re-importing the app. An unset/empty
    token means the surface was never provisioned: 404 (the route doesn't
    exist), matching the metrics endpoint's don't-reveal posture. A present but
    wrong header is a real auth failure: 401. compare_digest, not ==, so the
    comparison doesn't leak the token's prefix through response timing."""
    token = resolve_internal_token()
    if not token:
        raise HTTPException(status_code=404)
    if not hmac.compare_digest(x_thermograph_internal_token, token):
        raise HTTPException(status_code=401, detail="bad internal token")


# include_in_schema=False: an internal surface has no business in the public
# OpenAPI document, same as /api/v2/metrics.
router = APIRouter(prefix="/internal", include_in_schema=False,
                   dependencies=[Depends(_require_internal_token)])


# Every handler below is a plain `def`, not `async def`, on purpose: they all do
# blocking work (sync parquet/DB reads, grading math, upstream HTTP fetches).
# FastAPI runs sync handlers on its threadpool, so a slow grade or a long warm
# run never stalls the event loop the rest of the API is serving on — the same
# reason web/app.py wraps discord_interactions.handle in run_in_threadpool.


class _GradeBody(BaseModel):
    query: str


@router.post("/discord/grade")
def discord_grade(body: _GradeBody) -> dict:
    """The gateway-ready reply for one bot mention/DM: the same embed the /grade
    slash command builds, via the shared discord_interactions._grade_message —
    reusing one builder is what keeps the two paths from ever drifting. Local
    import for the same reason the in-process gateway bot used one: don't drag
    the interactions module's transitive deps into contexts that only mount the
    router."""
    from notifications import discord_interactions
    data = discord_interactions._grade_message(body.query)
    # Gateway messages can't be ephemeral — the flag is interactions-only, and
    # Discord rejects it outside an interaction response.
    data.pop("flags", None)
    return data


# One in-flight run per job, enforced here rather than trusted to the daemon's
# timers: warm_cities spends the Open-Meteo quota, so a stacked second run
# double-spends it, and a slow run must never let invocations pile up holding
# requests open. Non-blocking acquire => the loser answers 409 immediately.
_JOB_LOCKS: dict[str, threading.Lock] = {
    "warm-cities": threading.Lock(),
    "indexnow": threading.Lock(),
}


def _run_exclusive(job: str, fn) -> dict:
    lock = _JOB_LOCKS[job]
    if not lock.acquire(blocking=False):
        raise HTTPException(status_code=409, detail=f"{job} is already running")
    try:
        fn()
    finally:
        lock.release()
    return {"ok": True}


@router.post("/jobs/warm-cities")
def jobs_warm_cities() -> dict:
    """(Re-)warm the curated city set. The daemon owns the cadence (default
    daily — every already-cached city is a cheap skip); this endpoint just runs
    one pass. Local import: warm_cities is a script-style top-level module, so
    only the process that actually runs the job pays its import cost."""
    def _run():
        import warm_cities
        warm_cities.main()
    return _run_exclusive("warm-cities", _run)


@router.post("/jobs/indexnow")
def jobs_indexnow() -> dict:
    """Check whether the indexable URL set changed and, if so, ping IndexNow.
    submit_if_changed() is a cheap no-op when nothing changed, which is why the
    daemon can tick this more often than warm-cities without spending anything
    on most runs."""
    def _run():
        import indexnow
        indexnow.submit_if_changed()
    return _run_exclusive("indexnow", _run)