Files
FabledSteward/plugins/prometheus/scraper.py
T
bvandeusenandClaude Opus 5.5 66a5dd12fd
CI / lint (push) Successful in 2s
CI / unit (push) Successful in 1m36s
CI / integration (push) Successful in 1m55s
CI / publish (push) Successful in 20s
fix(prometheus): a refused token stops the scraping, as Home Assistant bans an address after a few refusals (#6355)
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>
2026-11-01 09:41:53 -05:00

64 lines
2.7 KiB
Python

# plugins/prometheus/scraper.py
"""Fetching one /metrics endpoint. Every failure comes back as one sentence
a page can show, never a stack trace."""
from __future__ import annotations
import httpx
from steward.core import prometheus
TIMEOUT_SECONDS = 10.0
# A /metrics page past this is not one to store a series of; reading stops.
MAX_BYTES = 20 * 1024 * 1024
ACCEPT = "text/plain;version=0.0.4;q=1,*/*;q=0.1"
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."""
headers = {"Accept": ACCEPT}
if token:
headers["Authorization"] = f"Bearer {token}"
try:
async with httpx.AsyncClient(timeout=TIMEOUT_SECONDS, verify=verify_tls,
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 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()
async for chunk in response.aiter_bytes():
body.extend(chunk)
if len(body) > MAX_BYTES:
raise ScrapeError(f"The page is over {MAX_BYTES // (1024 * 1024)} MB; "
"is this a /metrics address?")
except ScrapeError:
raise
except httpx.TimeoutException:
raise ScrapeError(f"No answer within {TIMEOUT_SECONDS:.0f} s.") from None
except httpx.ConnectError as exc:
raise ScrapeError(f"Couldn't connect: {_reason(exc)}.") from None
except httpx.HTTPError as exc:
raise ScrapeError(f"The request failed: {_reason(exc)}.") from None
families = prometheus.parse(body.decode("utf-8", errors="replace"))
if not families:
raise ScrapeError("It answered, but with no metrics in Prometheus format.")
return families
def _reason(exc: Exception) -> str:
text = str(exc).strip() or type(exc).__name__
return text.rstrip(".")