siftlode/backend/app/routes/runs.py

"""Admin background-run history: read `job_runs`, a page at a time.

Admin-only and read-only — rows leave the table through the retention job
(`job_run_retention_days`). Filtered on the server and paged by `_keyset`, like the server log and
the audit log beside it on the activity page. A row names what a reader needs without a second
request: what a user's ad-hoc run worked on (the channel, the importing user), and how many log lines the run left (only
WARNING and up are stored, so most runs have none — the count says so before the click).
"""

from dataclasses import dataclass
from datetime import datetime
from typing import Literal

from fastapi import APIRouter, Depends, Query
from sqlalchemy import func, or_, select
from sqlalchemy.orm import Session

from app import scheduler
from app.auth import admin_user
from app.db import get_db
from app.models import JobRun, LogEvent, User
from app.catalog import queries as catalog_queries
from app.routes import _account as account
from app.routes._keyset import PAGE_MAX, accounts, older_than, page, utc
from app.runstatus import RunStatus
from app.utils import iso, like_escape

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

Facet = Literal["job", "status"]


def _serialize(run: JobRun, titles: dict[str, str], lines: dict[int, int]) -> dict:
    return {
        "id": run.id,
        "job": run.job,
        "trigger": run.trigger,
        "actor_id": run.actor_id,
        "target": run.target,
        "target_title": titles.get(run.target) if run.target is not None else None,
        "status": run.status,
        "started_at": iso(run.started_at),
        "finished_at": iso(run.finished_at),
        "summary": run.summary,
        "result": run.result,
        "error": run.error,
        "failure": run.failure,
        "quota_units": run.quota_units,
        "log_lines": lines.get(run.id, 0),
    }


@dataclass(frozen=True)
class RunFilters:
    job: str | None
    status: RunStatus | None
    actor: str | None
    q: str | None
    since: datetime | None
    until: datetime | None

    def conditions(self, skip: Facet | None = None) -> list:
        """The WHERE conditions, ANDed. `skip` leaves one menu's own filter out, so that menu counts
        its values under every other filter (the way back from a pick)."""
        out = []
        if self.job is not None and skip != "job":
            out.append(JobRun.job == self.job)
        if self.status is not None and skip != "status":
            out.append(JobRun.status == self.status)
        if self.actor is not None:
            out.append(account.condition(JobRun.actor_id, self.actor))
        if self.since is not None:
            out.append(JobRun.started_at >= utc(self.since))
        if self.until is not None:
            out.append(JobRun.started_at < utc(self.until))
        if self.q and self.q.strip():
            like = f"%{like_escape(self.q.strip())}%"
            out.append(
                or_(
                    JobRun.job.ilike(like),
                    JobRun.target.ilike(like),
                    JobRun.summary.ilike(like),
                    JobRun.error.ilike(like),
                )
            )
        return out


def run_filters(
    job: str | None = Query(default=None, max_length=40, pattern=r"^[a-z][a-z0-9_]*$"),
    status: RunStatus | None = None,
    user: str | None = Query(default=None, pattern=account.PATTERN),
    q: str | None = Query(default=None, max_length=200),
    since: datetime | None = None,
    until: datetime | None = None,
) -> RunFilters:
    return RunFilters(job, status, user, q, since, until)


@router.get("")
def list_runs(
    filters: RunFilters = Depends(run_filters),
    before: str | None = Query(default=None, max_length=200),
    limit: int = Query(default=100, ge=1, le=PAGE_MAX),
    _: User = Depends(admin_user),
    db: Session = Depends(get_db),
) -> dict:
    """One page of runs, newest first, matching every filter given; `before` continues from a
    previous page's `next_cursor`."""
    query = select(JobRun).where(*filters.conditions())
    if before is not None:
        query = query.where(older_than(JobRun.started_at, JobRun.id, before))
    order = (JobRun.started_at.desc(), JobRun.id.desc())
    runs, cursor = page(
        list(db.execute(query.order_by(*order).limit(limit + 1)).scalars().all()),
        limit,
        lambda r: r.started_at,
    )
    channels = {r.target for r in runs if r.job == scheduler.CHANNEL_BACKFILL and r.target}
    titles = catalog_queries.channel_titles(db, channels)
    for target in {r.target for r in runs if r.job == scheduler.TAKEOUT_IMPORT and r.target}:
        title = scheduler.ad_hoc_target_title(db, scheduler.TAKEOUT_IMPORT, target)
        if title is not None:
            titles[target] = title
    lines: dict[int, int] = {}
    if runs:
        counted = db.execute(
            select(LogEvent.run_id, func.count())
            .where(LogEvent.run_id.in_([r.id for r in runs]))
            .group_by(LogEvent.run_id)
        )
        lines = {rid: n for rid, n in counted.tuples() if rid is not None}
    return {
        "items": [_serialize(r, titles, lines) for r in runs],
        "accounts": accounts(db, {r.actor_id for r in runs if r.actor_id is not None}),
        "next_cursor": cursor,
    }


@router.get("/facets")
def run_facets(
    filters: RunFilters = Depends(run_filters),
    _: User = Depends(admin_user),
    db: Session = Depends(get_db),
) -> dict:
    """What the job menu and the status chips offer, each counted under every filter but its own."""

    def counts(col, skip: Facet) -> list[dict]:
        n = func.count().label("n")
        stmt = select(col, n).where(*filters.conditions(skip)).group_by(col).order_by(n.desc(), col)
        return [{"value": v, "count": c} for v, c in db.execute(stmt).all()]

    total = select(func.count()).select_from(JobRun).where(*filters.conditions("status"))
    return {
        "jobs": counts(JobRun.job, "job"),
        "statuses": counts(JobRun.status, "status"),
        "total": db.scalar(total) or 0,
    }