Isolate unexpected fetch failures and harden task durability (T2)

fetch_feed had no time limit and no handling for anything beyond the
network/parse errors fetch_and_ingest already catches internally — an
unexpected exception (a parser/sanitizer bug, a DB error) crashed the
task with no error recorded on the Feed, the claim left held for the
full CLAIM_STALE_MINUTES, and no visibility beyond a bare traceback.
fetch_feed now catches that, records it the same way a handled failure
would be (reusing fetcher.record_fetch_error, promoted from a private
helper), clears the claim, and re-raises so Celery still marks the task
FAILED. soft_time_limit/time_limit bound a single fetch that somehow
outruns FETCH_TIMEOUT_SECONDS + ssrf_guard's response cap during
parsing/ingestion.

Also: a worker process killed mid-task (OOM, deploy restart, crash)
previously lost that task silently — Celery's default is to ack a
message the moment a worker *starts* it. CELERY_TASK_ACKS_LATE +
CELERY_TASK_REJECT_ON_WORKER_LOST (config/settings/base.py) make the
message redeliverable instead, and CELERY_WORKER_PREFETCH_MULTIPLIER=1
keeps a worker from grabbing a batch of tasks it could lose all at once.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
ksmithandClaude Sonnet 5 committed 2026-10-31 12:46:29 -06:00
1 parent 0466ccc334
commit 64f25789f5
4 files changed
+104 -10

No files matched your search

+28 -7
View File
@@ -31,6 +31,15 @@ FETCH_TIMEOUT_SECONDS = 15
MAX_BACKOFF_MINUTES = 24 * 60
USER_AGENT = "Evection/0.1 (+https://github.com/; self-hosted RSS reader)"
# ssrf_guard.MAX_RESPONSE_BYTES already bounds the raw download; these
# bound what a single poll does *with* that response — a feed within the
# byte cap can still carry an unreasonable number of entries, or one
# entry with an unreasonably large body, and both cost real CPU/DB time
# (nh3 sanitization, an Article row/UPDATE) per entry processed.
MAX_ENTRIES_PER_POLL = 200
MAX_CONTENT_HTML_INPUT_CHARS = 200_000 # bounds sanitizer cost, not just storage
MAX_CONTENT_HTML_CHARS = 50_000 # bounds what's actually stored/rendered
ALLOWED_TAGS = {
"a",
"p",
@@ -83,7 +92,9 @@ class FetchResult:
def sanitize_html(raw_html: str) -> str:
if not raw_html:
return ""
return nh3.clean(raw_html, tags=ALLOWED_TAGS, attributes=ALLOWED_ATTRIBUTES, link_rel=None)
bounded = raw_html[:MAX_CONTENT_HTML_INPUT_CHARS]
cleaned = nh3.clean(bounded, tags=ALLOWED_TAGS, attributes=ALLOWED_ATTRIBUTES, link_rel=None)
return cleaned[:MAX_CONTENT_HTML_CHARS]
def _content_hash(title: str, content_html: str) -> str:
@@ -144,10 +155,10 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
response = safe_get(feed.feed_url, headers=headers, timeout=FETCH_TIMEOUT_SECONDS)
except SSRFBlocked as exc:
feed.last_fetched_at = timezone.now()
return _record_error(feed, f"Refused to fetch: {exc}")
return record_fetch_error(feed, f"Refused to fetch: {exc}")
except requests.RequestException as exc:
feed.last_fetched_at = timezone.now()
return _record_error(feed, f"Request failed: {exc}")
return record_fetch_error(feed, f"Request failed: {exc}")
feed.last_fetched_at = timezone.now()
@@ -159,12 +170,12 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
)
if response.status_code >= 400:
return _record_error(feed, f"HTTP {response.status_code}")
return record_fetch_error(feed, f"HTTP {response.status_code}")
parsed = feedparser.parse(response.content)
if parsed.bozo and not parsed.entries:
return _record_error(feed, f"Unparseable feed: {parsed.get('bozo_exception')}")
return record_fetch_error(feed, f"Unparseable feed: {parsed.get('bozo_exception')}")
if parsed.bozo:
logger.warning(
@@ -186,7 +197,17 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
new_ids: list[int] = []
updated_ids: list[int] = []
for entry in parsed.entries:
entries = parsed.entries
if len(entries) > MAX_ENTRIES_PER_POLL:
logger.warning(
"Feed %s: %d entries in one poll, only processing the first %d",
feed.feed_url,
len(entries),
MAX_ENTRIES_PER_POLL,
)
entries = entries[:MAX_ENTRIES_PER_POLL]
for entry in entries:
guid = _entry_guid(entry)
title = (getattr(entry, "title", "") or "")[:1000]
content_html = sanitize_html(_entry_content_html(entry))
@@ -220,7 +241,7 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
)
def _record_error(feed: Feed, message: str) -> FetchResult:
def record_fetch_error(feed: Feed, message: str) -> FetchResult:
feed.last_fetch_status = Feed.STATUS_ERROR
feed.last_error_message = message[:2000]
feed.fetch_error_count += 1