{"version":"2.1.267","anchor":"headless-served-model-catalog-fetch-now-backs-off-exponentia","canonical_anchor":"headless-served-model-catalog-fetch-now-backs-off-exponentia","heading":"Headless served-model-catalog fetch now backs off exponentially after failures","tier":"notice","area":"Model Catalog","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.267\/e\/headless-served-model-catalog-fetch-now-backs-off-exponentia","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.267","markdown":"### Headless served-model-catalog fetch now backs off exponentially after failures\n\nHeadless mode now backs off from re-fetching the model catalog after a recent failure instead of retrying every time\n\n**What**\n\nWhen Claude Code starts in headless (non-interactive, scripted) mode, it fetches a catalog of available models over the network. Now, before doing that fetch, it checks a saved marker recording whether a recent headless fetch failed. If a failure was recorded recently, it skips the network call entirely and falls back to the built-in model list, recording the reason as `headless_held_off`.\n\nSuccess and failure are tracked in a new `.headless-failed.json` marker file, and repeated failures make Claude Code wait longer before trying again (exponential backoff).\n\n**Why**\n\nThis avoids repeatedly hitting a failing network endpoint on every headless run, which previously could slow down or delay each invocation. If the model catalog can't be reached, headless runs now fail fast and fall back to a known-good default list instead of retrying every time.\n\n- Area: Model Catalog\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 1\/5"}