Follow Discord
Sweep 03 Nov 2026 · 22:27Z Build v2.1.318 536 read Stable v2.1.311 Latest v2.1.318 Next v2.1.318 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One change · claude-code

Deploy self-hosted environments to production changedself-hosted-environments-deploy

Upstream edited this page at 28 Oct 2026 19:51 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 28 Oct 2026 20:07 UTC.

Upstream edited
Recorded here
Lines+2added
Lines−0removed
From line 906 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits54to this page, all time

The whole hunk

from line 906, old and new numbered
/
lines
from line 906
906906 Before v2.1.274, the runner stopped retrying a failed fetch after a few attempts and waited for the next scheduled one. A failed turn didn't trigger a fetch, so every turn failed with a 401 until the next scheduled fetch.
907907* **A turn fails in claude.ai/code with `This model needs a newer version of Claude Code`**: the Claude Code version that your runners start sessions with is older than the session's model requires, so the API [rejects the request](https://code.claude.com/docs/en/errors.md#claude-code-does-not-support-this-model). Upgrade the runners to the version the message asks for, or a later one, as described in [Pin the version](#pin-the-version). Until then, people can pick a different model in the session.
908908* **Pod is killed mid-drain**: raise `terminationGracePeriodSeconds` to at least the value the runner logs at startup. See [Shutdown timing](#shutdown-timing).
909* **Runner logs a `[runner:log]` line ending `was paused or too slow`**: the runner kept running and needs no restart. Until the stdout or stderr stream named in the line was read again, the runner discarded all but that stream's newest 256 KiB of lines. If you passed [`--log-file`](https://code.claude.com/docs/en/self-hosted-environments-reference#runner-cli-flags), look there for the discarded lines.
910* **Runner logs `Nobody can read this process's stdout anymore`**: whatever read the runner's stdout is gone, so the runner stops writing there for the rest of its run and keeps running. While stderr is still open, this line and the runner's later status lines, `[runner:fatal]` lines included, go to stderr, so read them there.
909911 
910912Once logging is initialized, the runner writes its lifecycle log, including `[runner:fatal]` lines, to stdout, and debug output to stderr, all as plain-text lines rather than JSON. The base directory failures described in the troubleshooting entries above print to stderr before that point. Capture both streams with `--log-file`, which also lets `self-hosted-runner doctor` tail them, or with your platform's log collection.
911913 
Feedback