Follow Discord
Sweep 23 Oct 2026 · 21:48Z Build v2.1.310 529 read Stable v2.1.308 Latest v2.1.310 Next v2.1.310 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeReleasesv2.1.310entry #237

Claude Code v2.1.310 ·

Self-hosted runner sessions now take their own path for the artifacts MCP laptop entry

Sessions started by a self-hosted runner are no longer handled like other remote sessions when Claude Code sets up the artifacts MCP laptop entry

Under the hood Internal Changes
JSON All of v2.1.310
Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
Self-Hosted RunnersArea: what it touches
Internal ChangesKind: in v2.1.310,
Internal ChangesSection of the release

Unclear Whether self-hosted runner sessions now get the artifacts laptop entry or still go without it is not shown.

What

Claude Code has a step that sets up a laptop entry for the artifacts MCP server (MCP is a standard way to connect extra tools). In remote sessions, flagged by CLAUDE_CODE_REMOTE or CLAUDE_CODE_REMOTE_SESSION_ID, it leaves that entry out.

Sessions started by a self-hosted runner (a machine you run yourself that starts Claude Code sessions) are now checked first and take their own path, before that remote-session check.

Why

If you run Claude Code through a self-hosted runner, these sessions now behave differently from other remote sessions at this step.

Read from
Names in the bundleCLAUDE_CODE_REMOTECLAUDE_CODE_REMOTE_SESSION_ID
What the documentation says
Documented inclaude-code/cloud-environments
How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtWhether self-hosted runner sessions now get the artifacts laptop entry or still go without it is not shown.

See this entry in the whole of v2.1.310 →

Feedback