"""HTTP lifespan composition; standalone backend services remain opt-in owners."""

from contextlib import asynccontextmanager
import asyncio
import logging
import os
import threading

from fastapi import FastAPI
from hermes_cli.pty_session import run_reaper

logger = logging.getLogger("hermes_cli.web_server")


def _unlink_pty_markers(app: FastAPI) -> None:
    """Second pass after ``PTY_REGISTRY.close_all()``: drop channel markers left in app state,
    including stale paths from sessions reaped earlier (``PtySession.close()`` only removes
    markers owned by live registry sessions)."""
    from hermes_cli.web_server import _get_pty_active_session_files

    for marker in set(_get_pty_active_session_files(app).values()):
        try:
            marker.unlink(missing_ok=True)
        except OSError:
            pass


@asynccontextmanager
async def standalone_lifespan(app: "FastAPI"):
    from hermes_cli.web_server import (
        _eager_reconcile_own_session_db, _warm_gateway_module,
        _start_desktop_cron_ticker, _dashboard_selftest_loop,
        _auto_archive_ticker_loop, _terminate_desktop_managed_gateway,
    )
    from hermes_cli.web_server_chat import PTY_REGISTRY

    app.state.event_channels = {}  # dict[str, set]
    app.state.event_lock = asyncio.Lock()
    app.state.pty_active_session_files = {}  # dict[str, Path]
    # Serializes chat-argv resolution so concurrent /api/pty connections don't
    # overlap ``npm install`` / ``npm run build``. Locks live on app.state (not
    # module globals) so they bind to the running loop, not the import-time one.
    app.state.chat_argv_lock = asyncio.Lock()

    # Bring state.db schema current BEFORE the first session-list poll
    # (#79531/#80037): a store left behind by `hermes update` otherwise 500s
    # every poll until its owner completes schema reconciliation.
    # Off-thread so a locked store never delays the socket (Desktop
    # ready-probe times out at 10s, GH-73083). NOT a daemon, and joined at
    # shutdown: its sqlite connection must be closed by the thread that is
    # stepping it. A daemon copy that outlived the lifespan had its
    # connection closed from the main thread mid-probe (pytest's leaked-DB
    # sweep) and segfaulted the interpreter. The worker is time-bounded by
    # SessionDB's lock patience, so the join cannot hang shutdown.
    eager_reconcile_thread = threading.Thread(
        target=_eager_reconcile_own_session_db,
        name="statedb-eager-reconcile",
    )
    eager_reconcile_thread.start()

    # Import hermes_cli.gateway *before* the yield: on Windows + 3.11 the
    # import holds the GIL, so run_in_executor still froze the loop 15-22s and
    # the Desktop's 10s ready-probe timed out (GH-73083).
    _warm_gateway_module()

    # Snapshot the checkout revision so lazy-import paths (model picker) can
    # refuse with "restart required" after `hermes update` replaced the code
    # (#86207); the update flow does not reliably restart the dashboard.
    from gateway.code_skew import record_boot_fingerprint

    record_boot_fingerprint()

    # Hosted Bot rooms belong to the backend process. Recovery may need a
    # contended state.db migration, so keep it off the pre-yield path: Group
    # Chat must degrade on its own rather than block every Desktop feature.
    from tui_gateway import methods_groups as _hosted_groups
    import tui_gateway.server

    try:
        tui_gateway.server.install_tui_message_injector()
    except Exception:
        logger.warning("TUI message injector did not install", exc_info=True)

    hosted_room_start_cancel = threading.Event()

    def _start_hosted_rooms() -> None:
        try:
            _hosted_groups.start_hosted_room_service()
        except Exception:
            logger.exception("Hosted Group Chat recovery failed during backend startup")
        finally:
            if hosted_room_start_cancel.is_set():
                _hosted_groups.stop_hosted_room_service(timeout=1.0)

    hosted_room_start_thread = threading.Thread(
        target=_start_hosted_rooms,
        daemon=True,
        name="hosted-room-startup",
    )
    hosted_room_start_thread.start()

    # Desktop-spawned backends fire cron jobs themselves, since the app has no
    # gateway running the scheduler. Server `hermes dashboard` is unaffected —
    # it relies on its own gateway.
    from hermes_cli.process_identity import is_desktop_owned_backend
    cron_stop: threading.Event | None = None
    cron_thread: threading.Thread | None = None
    desktop_owned = is_desktop_owned_backend()
    if desktop_owned:
        # Reap an orphaned gateway from an abnormal previous exit (reparented to
        # launchd, still holding the platform WebSocket) before forking a fresh
        # one that would race the same credential (#77276). Runs
        # unconditionally; protection of a healthy standalone gateway lives
        # INSIDE the reaper (registration probed with cleanup_stale=False).
        # Startup grace: spare a gateway still claiming gateway.pid/lock (#122533).
        try:
            from hermes_cli.dashboard_procs import _REAP_MIN_AGE_SECONDS
            from hermes_cli.gateway import _reap_unsupervised_gateway_orphans

            _reap_unsupervised_gateway_orphans(min_age_s=_REAP_MIN_AGE_SECONDS)
        except Exception:
            logger.exception("Desktop startup: orphan gateway reap failed")

        cron_stop = threading.Event()
        cron_thread = threading.Thread(
            target=_start_desktop_cron_ticker,
            args=(cron_stop,),
            daemon=True,
            name="desktop-cron-ticker",
        )
        cron_thread.start()

    # Reap idle/dead keep-alive PTY sessions (30-min TTL).
    pty_reaper_task = asyncio.create_task(run_reaper(PTY_REGISTRY))
    # Periodic authenticated self-test feeding the ``dashboard`` component on /api/status.
    selftest_task = asyncio.create_task(_dashboard_selftest_loop())
    # Live auto-archive timer, independent of list requests.
    auto_archive_task = asyncio.create_task(_auto_archive_ticker_loop())

    # Managed local runtime (local_runtime.enabled): bring llama-server back so a
    # restart doesn't strand a llamacpp main model. Off-thread and best-effort;
    # failure falls back to cloud providers like a cold start. Server only —
    # models load on first inference (an empty router holds no VRAM).
    def _boot_local_runtime():
        try:
            from hermes_cli.config import load_config
            from hermes_cli.local_runtime.bootstrap import ensure_local_runtime

            ensure_local_runtime(load_config())
        except Exception as exc:
            logging.getLogger(__name__).warning("local runtime boot failed: %s", exc)

    threading.Thread(target=_boot_local_runtime, daemon=True, name="local-runtime-boot").start()

    # Records who carries inference for setup.status / free_tier.status and broadcasts `setup.ready`
    # (no identity is created at boot). Off-thread; the desktop's first setup.status waits on the
    # record (bounded) instead.
    from hermes_cli.free_tier_bootstrap import start_background_bootstrap

    start_background_bootstrap()

    try:
        yield
    finally:
        try:
            tui_gateway.server.clear_tui_message_injector()
        except Exception:
            logger.debug("TUI message injector clear skipped", exc_info=True)
        hosted_room_start_cancel.set()
        _hosted_groups.stop_hosted_room_service(timeout=5.0)
        hosted_room_start_thread.join(timeout=1.0)
        if cron_stop is not None:
            cron_stop.set()
        pty_reaper_task.cancel()
        selftest_task.cancel()
        auto_archive_task.cancel()
        eager_reconcile_thread.join()
        await PTY_REGISTRY.close_all()

        # PtySession.close() removes markers owned by live registry sessions.
        # This second pass cleans any channel markers left in app state,
        # including stale paths from sessions reaped earlier.
        _unlink_pty_markers(app)

        # Stop the managed llama-server with its parent (an orphan pins VRAM).
        try:
            from hermes_cli.local_runtime.bootstrap import shutdown_local_runtime

            shutdown_local_runtime()
        except Exception:
            # Shutdown boundary: a supervisor that fails to stop must not skip the
            # managed-gateway teardown below; log it so the orphan is diagnosable.
            logger.warning("managed local runtime shutdown failed", exc_info=True)
        if desktop_owned:
            _terminate_desktop_managed_gateway()


@asynccontextmanager
async def http_lifespan(app: FastAPI):
    """The gateway already owns schema, rooms, scheduler and model services."""
    from hermes_cli.web_server import _dashboard_selftest_loop
    from hermes_cli.web_server_chat import PTY_REGISTRY

    app.state.event_channels = {}
    app.state.event_lock = asyncio.Lock()
    app.state.pty_active_session_files = {}
    app.state.chat_argv_lock = asyncio.Lock()
    tasks = [
        asyncio.create_task(run_reaper(PTY_REGISTRY), name="gateway-api-pty-reaper"),
        asyncio.create_task(_dashboard_selftest_loop(), name="gateway-api-selftest"),
    ]
    try:
        yield
    finally:
        for task in tasks:
            task.cancel()
        await asyncio.gather(*tasks, return_exceptions=True)
        await PTY_REGISTRY.close_all()
        _unlink_pty_markers(app)


@asynccontextmanager
async def app_lifespan(app: FastAPI):
    lifespan = http_lifespan if getattr(app.state, "gateway_runner", None) is not None else standalone_lifespan
    async with lifespan(app):
        yield