{"version":"2.1.286","anchor":"self-hosted-runner-can-force-an-inference-token-refresh","canonical_anchor":"self-hosted-runner-can-force-an-inference-token-refresh","heading":"Self-hosted runners can ask for a fresh model token right away","tier":"notice","area":"Elsewhere","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.286\/e\/self-hosted-runner-can-force-an-inference-token-refresh","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.286","markdown":"### Self-hosted runners can ask for a fresh model token right away\n\nOn self-hosted runners, Claude Code can now request a fresh inference token immediately instead of waiting for the next scheduled refresh\n\n**Unclear.** What triggers an immediate refresh is not shown.\n\n**What**\n\nOn a self-hosted runner, meaning a machine you run yourself that carries out remote Claude Code sessions, the part that keeps the inference token fresh can now be asked to refresh straight away. The inference token is the credential the runner uses to make requests to the model. A request to refresh now ends in one of these ways:\n\n- a refresh is started\n\n- a refresh is already under way\n\n- it is skipped because one happened very recently\n\n- it is dropped because the session is ending\n\nEach refresh also now reports when its `\/remote` call begins.\n\n**Why**\n\nThis makes it less likely that an expired token holds up a turn on a self-hosted runner.\n\n- Area: Elsewhere\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5"}