siftlode/backend/app/routes/scheduler.py

"""Admin Scheduler dashboard: a live view of what the background scheduler is doing —
per-job run activity (from the in-process scheduler), the work still queued (DB-derived),
and the shared quota picture."""

from fastapi import APIRouter, Depends
from pydantic import BaseModel
from sqlalchemy.orm import Session

from app import audit, quota, state, sysconfig
from app.audit import AuditAction
from app.auth import admin_user
from app.config import settings
from app.db import get_db
from app.models import User
from app.catalog import queries as catalog_queries
from app.scheduler import (
    JOB_INTERVALS,
    MAX_INTERVAL,
    MIN_INTERVAL,
    reschedule,
    scheduler_snapshot,
    stage_interval,
    trigger_all,
    trigger_job,
)
from app.sync.runner import estimate_deep_backfill
from app.routes._common import not_found
from app.refusal import refused
from app.refusal import setting_refused

router = APIRouter(prefix="/api/admin/scheduler", tags=["admin"])


class JobIntervalIn(BaseModel):
    interval_minutes: int


@router.patch("/jobs/{job_id}")
def set_job_interval(
    job_id: str,
    body: JobIntervalIn,
    admin: User = Depends(admin_user),
    db: Session = Depends(get_db),
) -> dict:
    """Change how often a scheduler job runs (minutes). Stored as an override together with its
    audit row, then applied to the live scheduler."""
    if job_id not in JOB_INTERVALS:
        raise not_found("job")
    minutes = body.interval_minutes
    if not (MIN_INTERVAL <= minutes <= MAX_INTERVAL):
        raise refused(400, "invalid_interval", min=MIN_INTERVAL, max=MAX_INTERVAL)
    applied = stage_interval(db, job_id, minutes)
    audit.record(
        db,
        admin.id,
        AuditAction.SCHEDULER_INTERVAL,
        target_type="job",
        target_id=job_id,
        summary=f"{job_id} → {applied} min/run",
        after={"interval_minutes": applied},
    )
    db.commit()
    reschedule(job_id, applied)
    return {"ok": True, "id": job_id, "interval_minutes": applied}


@router.post("/jobs/{job_id}/run")
def run_job_now(
    job_id: str,
    user: User = Depends(admin_user),
) -> dict:
    """Trigger a job to run immediately (in a background thread), independent of its
    interval. 409 if it's already running, 404 for an unknown job. On completion the
    triggering admin gets an inbox notification with the result."""
    try:
        result = trigger_job(job_id, actor_id=user.id)
    except KeyError:
        raise not_found("job") from None
    if result == "already_running":
        raise refused(409, "job_running")
    return {"ok": True, "id": job_id, "started": True}


@router.post("/run-all")
def run_all_now(user: User = Depends(admin_user)) -> dict:
    """Trigger every job that isn't already running. Returns the ids actually started."""
    return {"ok": True, "started": trigger_all(actor_id=user.id)}


class MaintenanceSettingsIn(BaseModel):
    revalidate_batch: int


@router.patch("/maintenance")
def set_maintenance_settings(
    body: MaintenanceSettingsIn,
    admin: User = Depends(admin_user),
    db: Session = Depends(get_db),
) -> dict:
    """Admin-tune the maintenance job's rolling re-validation batch (videos re-checked per
    run). Persisted via sysconfig; the job reads it each run."""
    # set_value validates against the spec's min/max (one source of bounds), mirroring the config PATCH.
    try:
        sysconfig.set_value(db, "maintenance_revalidate_batch", body.revalidate_batch)
    except sysconfig.InvalidSetting as exc:
        raise setting_refused(exc) from None
    new = sysconfig.get_int(db, "maintenance_revalidate_batch")
    audit.record(
        db,
        admin.id,
        AuditAction.MAINTENANCE_TUNE,
        summary=f"revalidate batch = {new}",
        after={"revalidate_batch": new},
    )
    db.commit()
    return {"ok": True, "revalidate_batch": new}


@router.get("")
def get_scheduler(_: User = Depends(admin_user), db: Session = Depends(get_db)) -> dict:
    snap = scheduler_snapshot(db)

    # Work still queued (shared catalog, so these are instance-wide, not per-user).
    deep_eta = estimate_deep_backfill(db, catalog_queries.deep_backlog(db))
    queue = catalog_queries.work_queue(db)
    # The whole opted-in BACKLOG, deliberately not `run_deep_backfill`'s next-pass selection
    # (which also wants `recent_synced_at`): the same figure /api/sync/my-status shows the user,
    # and a channel missing its recent pull is one the same job tick fetches first, not one the
    # job will never touch. Narrowing it here would under-report work that is genuinely queued.
    queue["channels_deep_pending"] = deep_eta["channels_pending"]
    queue["deep_eta_seconds"] = deep_eta["eta_seconds"]

    used = quota.units_used_today(db)
    quota_info = {
        "used_today": used,
        "remaining_today": quota.remaining_today(db),
        "daily_budget": sysconfig.get_int(db, "quota_daily_budget"),
        "backfill_reserve": sysconfig.get_int(db, "backfill_quota_reserve"),
    }
    maint = sysconfig.spec("maintenance_revalidate_batch")

    return {
        **snap,
        "paused": state.is_sync_paused(db),
        "queue": queue,
        "quota": quota_info,
        "maintenance": {
            "revalidate_batch": sysconfig.get_int(db, "maintenance_revalidate_batch"),
            "revalidate_batch_default": settings.maintenance_revalidate_batch,
            "min": maint.min,
            "max": maint.max,
        },
    }