fix(prometheus, syslog): a target or pattern pauses with a Pause/Resume button, not an "on" tick box in its form (#6419)
CI / lint (push) Successful in 2s
CI / unit (push) Failing after 1m42s
CI / integration (push) Successful in 1m45s
CI / publish (push) Skipped

Monitors, schedules and maintenance plans already pause with a
Pause/Resume button and say "Paused" where they're listed. Prometheus
targets and syslog patterns only had a tick box inside the edit form,
so a target refused by its endpoint couldn't be stopped from its page.

- Both get a Pause/Resume button (target page and list; patterns list)
  posting to /toggle, recorded in the audit log, and a Paused badge.
- The forms lose the tick box. A new one starts running; an edit keeps
  whether it is paused.
- A target's "off" state is now "paused", in its pages and MCP tools.
  A resumed target reads "not scraped yet" until its next scrape, and its
  counter rates start over.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-25 17:48:31 -04:00
co-authored by Claude Opus 5.5
parent 0b787a0676
commit d20d78498e
15 changed files with 104 additions and 51 deletions
+25 -4
View File
@@ -25,7 +25,7 @@ from .service import (OWN_METRICS, SOURCE, FormError, fold_states, form_values,
prometheus_bp = Blueprint("prometheus", __name__, template_folder="templates")
_REACH_ORDER = {"down": 0, "stale": 1, "pending": 2, "up": 3, "off": 4}
_REACH_ORDER = {"down": 0, "stale": 1, "pending": 2, "up": 3, "paused": 4}
def _actor() -> tuple[str | None, str]:
@@ -40,7 +40,8 @@ def view(target: PrometheusTarget, own: dict, now: datetime) -> dict:
"""What a page says about a target: its state in words and the numbers
from its newest scrape."""
state = target_state(target, now)
return {"id": target.id, "name": target.name, "url": target.url, "reach": state.reach,
return {"id": target.id, "name": target.name, "url": target.url, "enabled": target.enabled,
"reach": state.reach,
"says": state.says, "scraped_at": target.last_scraped_at, "ok_at": target.last_ok_at,
"interval": target.interval_seconds, "kept": target.last_kept,
"dropped": target.last_dropped, "capped": target.last_capped, "cap": target.series_cap,
@@ -79,8 +80,7 @@ def _typed(form, target: PrometheusTarget | None = None) -> dict:
return {"name": form.get("name", ""), "url": form.get("url", ""),
"interval_seconds": form.get("interval_seconds", ""), "series_cap": form.get("series_cap", ""),
"keep": form.get("keep", ""), "drop": form.get("drop", ""),
"verify_tls": bool(form.get("verify_tls")), "enabled": bool(form.get("enabled")),
"has_token": bool(target and target.token)}
"verify_tls": bool(form.get("verify_tls")), "has_token": bool(target and target.token)}
async def _name_taken(db, name: str, other_than: str | None = None) -> bool:
@@ -176,6 +176,27 @@ async def save_target(target_id: str):
return redirect(f"/plugins/prometheus/targets/{target_id}")
@prometheus_bp.post("/targets/<target_id>/toggle")
@require_role(UserRole.admin)
async def toggle_target(target_id: str):
"""Pause a target, or resume a paused one, from its page or the list."""
async with current_app.db_sessionmaker() as db:
async with db.begin():
target = await _target_or_404(db, target_id)
target.enabled = not target.enabled
if target.enabled:
# Resumed: it reads "not scraped yet" until the next scrape,
# rather than stale from before the pause.
target.last_scraped_at = target.last_error = None
enabled, name = target.enabled, target.name
# A rate needs two readings in a row; one from before the pause isn't one.
from . import scheduler
scheduler.RATES.forget(target_id)
await log_audit(current_app, *_actor(), "prometheus.target_resumed" if enabled else "prometheus.target_paused",
entity_type="prometheus_target", entity_id=target_id, detail={"name": name})
return redirect(request.referrer or f"/plugins/prometheus/targets/{target_id}")
@prometheus_bp.post("/targets/<target_id>/delete")
@require_role(UserRole.admin)
async def delete_target(target_id: str):