Follow Discord
Sweep 10 Nov 2026 · 02:18Z Build v2.1.322 539 read Stable v2.1.311 Latest v2.1.322 Next v2.1.322 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Code CLI 9 Nov 2026
One change · claude-code

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

Nearest release: v2.1.321, published an hour before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Upstream edited this page at 9 Nov 2026 21:00 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 9 Nov 2026 21:07 UTC.

Upstream edited
Recorded here
Lines+6added
Lines−0removed
From line 938 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits58to this page, all time

The whole hunk

from line 938, old and new numbered
/
lines
from line 938
938938 If every call starts failing about 30 minutes into a session, a wrapper script has likely severed the session's stdin, so token rotations can't reach it; see [Keep stdin and file descriptor 3 attached](https://code.claude.com/docs/en/self-hosted-environments-configuration.md#keep-stdin-and-file-descriptor-3-attached).
939939 
940940 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.
941* **A session shows `The server has refused to renew this session's access to the model`**: the session's [`CLAUDE_CODE_OAUTH_TOKEN`](https://code.claude.com/docs/en/self-hosted-environments-configuration#wrapper-scripts) has expired, and the runner has received HTTP 400 in answer to its requests for a new token. The runner logs `the server has refused to renew the inference_token`. Turns in that session fail. The runner keeps requesting a new token for as long as the session's process runs:
942 
943 * **A request succeeds**: a session that showed the warning then shows `The server renewed this session's access to the model`
944 * **Turns keep failing**: the process eventually exits, and the session shows a failure such as `The session process exited with code 1`
945 
946 To keep working without waiting for a new token, start a new session. If a new session fails too, check whether a proxy or gateway of yours gave the HTTP 400 answer. If none did, [contact your Anthropic account team](#report-an-issue) with the first session's ID.
941947* **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.
942948* **Pod is killed mid-drain**: raise `terminationGracePeriodSeconds` to at least the value the runner logs at startup. See [Shutdown timing](#shutdown-timing).
943949* **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.
Feedback