fix(prometheus): a refused token stops the scraping, as Home Assistant bans an address after a few refusals (#6355)
CI / lint (push) Successful in 2s
CI / unit (push) Successful in 1m36s
CI / integration (push) Successful in 1m55s
CI / publish (push) Successful in 20s

Also names the Home Assistant connection by its address in the audit log and
timeline, where its id showed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-11-01 09:41:53 -05:00
co-authored by Claude Opus 5.5
parent a1dfa7b821
commit 66a5dd12fd
11 changed files with 94 additions and 11 deletions
@@ -0,0 +1,23 @@
"""A target whose token was refused stops being scraped until it is saved
Revision ID: prometheus_003_refused
Revises: prometheus_002_templates
Create Date: 2026-11-01
"""
from typing import Sequence, Union
import sqlalchemy as sa
from alembic import op
revision: str = "prometheus_003_refused"
down_revision: Union[str, None] = "prometheus_002_templates"
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
op.add_column("prometheus_targets", sa.Column("refused", sa.Boolean, nullable=False, server_default=sa.false()))
def downgrade() -> None:
op.drop_column("prometheus_targets", "refused")
+3 -1
View File
@@ -17,7 +17,8 @@ class PrometheusTarget(Base):
patterns ("fabledarchives_*") an admin chooses: Steward does the
filtering, the endpoint serves everything. The last_* columns are the
newest scrape's outcome, written by the scraper, so a page can say why a
target isn't answering without asking it.
target isn't answering without asking it. `refused` says its token was
refused, which stops the scraping until the target is saved or resumed.
"""
__tablename__ = "prometheus_targets"
@@ -31,6 +32,7 @@ class PrometheusTarget(Base):
drop: Mapped[list] = mapped_column(JSON, nullable=False, default=list)
series_cap: Mapped[int] = mapped_column(Integer, nullable=False, default=1000)
enabled: Mapped[bool] = mapped_column(Boolean, nullable=False, default=True)
refused: Mapped[bool] = mapped_column(Boolean, nullable=False, default=False)
created_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), nullable=False, default=lambda: datetime.now(timezone.utc))
last_scraped_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
+2
View File
@@ -153,6 +153,7 @@ async def save_target(target_id: str):
# Where it is or what is kept may have changed: the last outcome no
# longer describes it, so the page says "not scraped yet" until the next scrape.
target.last_scraped_at = target.last_ok_at = target.last_error = None
target.refused = False
target.last_kept = target.last_dropped = target.last_capped = 0
if old_name != target.name:
# Its history is stored under its name, and its labelled series
@@ -188,6 +189,7 @@ async def toggle_target(target_id: str):
# 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
target.refused = False
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
+3 -2
View File
@@ -40,7 +40,7 @@ def make_scrape_task(app: "Quart") -> ScheduledTask:
def is_due(target, now: datetime) -> bool:
"""Whether a target's interval has elapsed since its last scrape, with
half a tick of slack so tick jitter doesn't push it back a whole tick."""
if not target.enabled:
if not target.enabled or target.refused:
return False
if target.last_scraped_at is None:
return True
@@ -115,7 +115,7 @@ async def record(app: "Quart", targets, results, now: datetime) -> None:
from steward.core.alerts import MetricBatch
from .models import PrometheusTarget
from .scraper import ScrapeError
from .scraper import ScrapeError, TokenRefused
from .service import (IS_UP, OWN_METRICS, SCRAPE_MS, SERIES_CAPPED, SERIES_KEPT, SOURCE,
map_families)
@@ -132,6 +132,7 @@ async def record(app: "Quart", targets, results, now: datetime) -> None:
if not isinstance(result, ScrapeError):
logger.warning("Prometheus scrape of %s failed: %r", target.name, result)
row.last_error = str(result) or "The scrape failed."
row.refused = isinstance(result, TokenRefused)
batch.add(source_module=SOURCE, resource_name=row.name, metric_name=IS_UP,
value=0.0, recorded_at=now)
continue
+7 -2
View File
@@ -18,6 +18,11 @@ class ScrapeError(Exception):
"""Why a scrape got nothing, said to the person."""
class TokenRefused(ScrapeError):
"""The endpoint refused the token. Asking again won't change that, and
Home Assistant, for one, bans an address after a few refusals."""
async def scrape(url: str, token: str = "", verify_tls: bool = True,
transport: httpx.AsyncBaseTransport | None = None) -> dict[str, prometheus.Family]:
"""The endpoint's families. `transport` stands in for the network in tests."""
@@ -29,8 +34,8 @@ async def scrape(url: str, token: str = "", verify_tls: bool = True,
transport=transport, follow_redirects=False) as client:
async with client.stream("GET", url, headers=headers) as response:
if response.status_code in (401, 403):
raise ScrapeError(f"Answered {response.status_code}: the token was refused. "
"Check the token, or make a new one on the service.")
raise TokenRefused(f"Answered {response.status_code}: the token was refused. "
"Check the token, or make a new one on the service.")
if response.status_code != 200:
raise ScrapeError(f"Answered {response.status_code} {response.reason_phrase}, not metrics.")
body = bytearray()
+3
View File
@@ -271,6 +271,9 @@ class TargetState:
def target_state(target: PrometheusTarget, now: datetime) -> TargetState:
if not target.enabled:
return TargetState("paused", "Paused: not scraped until it's resumed.")
if target.refused:
return TargetState("down", f"{target.last_error} Steward stopped asking, as some services ban an "
"address after a few refusals. Save a new token to start again.")
if target.last_scraped_at is None:
return TargetState("pending", "Not scraped yet.")
if (now - target.last_scraped_at).total_seconds() > STALE_SCRAPES * max(target.interval_seconds, 1):