Extend the cooperative shutdown-drain (Phase 2) to the long sweep and
full-load loops in scrape_pipeline.py so they stop CLEANLY on SIGTERM
instead of being hard-cancelled at the 80s _drain_inflight timeout.
At every between-unit checkpoint that already polls scrape_runs.is_cancelled
(user-cancel) we add an ALONGSIDE shutdown_requested() branch:
- anchor-loop sweeps (avito/yandex/cian city) + avito newbuilding +
domclick pre-SERP: update_heartbeat + mark_done(partial) + return;
- full-load on_bucket callbacks (cian/yandex/avito): raise a distinct
RuntimeError("shutdown") sentinel, handled next to the existing
"cancelled" sentinel -> mark_done(partial), skipping the detail phase;
- cian full-load detail loop: break -> existing post-loop mark_done.
Drain finalizes as mark_done(partial), NOT mark_cancelled (that stays
user-cancel only). is_cancelled -> user-cancel semantics are unchanged, and
behaviour is identical when shutdown_requested() is False. No resume_cursor
or paused status yet (Phase 3b, deferred): this is drain-coverage only.
Tests: tests/test_sweep_drain.py covers both structural variants -
run_avito_city_sweep / run_cian_city_sweep (anchor-loop) and
run_avito_full_load (on_bucket sentinel): shutdown flips True after the
first unit, asserting the sweep stops at the checkpoint, calls mark_done
with partial counters, never calls mark_cancelled, and does not process
later anchors/buckets/phases.
bot-backend
3320805723