Repository navigation
Description
Summary
Follow-up to #811 (which fixed .get() in v3.0.1).
We hit a related failure on client.actor(actor_id).call(...) against v3.0.0 — every call raises 11 validation errors for ActorResponse before returning, so 100% of actor executions fail. We pinned to >=2.5,<3 to unblock production and have not retested against v3.0.1 yet, so this issue is to confirm whether the same fix in v3.0.1 also covered .call(), or whether there is a remaining gap.
Versions
- apify-client v3.0.0 — confirmed broken
- apify-client v3.0.1 — unverified (please confirm)
- apify-client v2.5.1 — works as expected (current production pin)
Failure mode (v3.0.0)
from apify_client import ApifyClient
client = ApifyClient(token=API_TOKEN)
run = client.actor("apify/instagram-profile-scraper").call(
run_input={"directUrls": ["https://www.instagram.com/example/"]},
timeout_secs=300,
)
# Raises: 11 validation errors for ActorResponseRequired fields on the nested Actor model that real API responses don't include
id, user_id, name, username, is_public, created_at, modified_at, stats, versions, default_run_options
Production impact for us
- Sprint #2195 migrated to v3 on 2026-05-22T09:51Z (deploy SHA
933d3d0f). - First post-deploy scrape (23:33Z): 0 successful / 471 failed out of 533 attempted (Instagram profile scraping pipeline).
- 82h scrape-freshness lag before we identified the root cause and pinned to v2.5 on 2026-05-23.
Workaround
- apify-client>=3.0,<4
+ apify-client>=2.5,<3This preserves the dict-based .call() return shape (no Pydantic strict validation on the response) and keeps timeout_secs: int | None parity.
Ask
- Has v3.0.1's fix also been applied to the
.call()path'sActorResponsemodel, or is there a separate OpenAPI-spec discrepancy still affecting.call()? - If still broken, would you like a minimal repro against v3.0.1? Happy to attach one once I've validated it in an isolated venv.
Related
- 3.0.0: client.actor(...).get() fails with validation errors #811 (closed in v3.0.1) — same root cause, different surface (
.get())
Thanks for the great library and the rapid v3.0.1 turnaround on #811.
Activity
vdusek commentedon May 25, 2026
Hi @hardik562,
Yes, this should be fixed in v3.0.1 - it has the same root cause as #811 (pricing-tier fields on the nested Actor model). The
.call()path failed because it transitively callsactor.get(), so the same model relaxations cover it. Closing as a duplicate of #811. Please give v3.0.1 a try in your workflow, and feel free to reopen if you still hit anything. Thank you.hardik562 commentedon May 25, 2026
Thanks for the fast confirmation — that's a clean answer (since
.call()transitively calls.get(), the v3.0.1 model relaxations cover both paths). Closing the loop here. We'll plan a careful re-attempt at v3.0.1 in our pipeline after a stabilization period, and re-open if anything resurfaces. Appreciate the responsive maintenance!