{"version":"2.1.234","anchor":"startup-model-config-prefetch-switched-off","canonical_anchor":"startup-model-config-prefetch-switched-off","heading":"Startup model-config prefetch, switched off","tier":"soon","area":"Model Config","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.234\/e\/startup-model-config-prefetch-switched-off","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.234","markdown":"### Startup model-config prefetch, switched off\n\nStartup would prefetch your model's token limits, but the guard always returns false.\n\n**What**\n\nStartup now calls a step that would look up the chosen model through the API and cache its token limits before the first turn. Its guard returns false unconditionally in this build, so the call returns immediately and nothing is fetched.\n\n**Details**\n\n- When enabled it would log the resolved `max_input_tokens=` and `max_tokens=` values under a `[modelConfig]` prefix.\n- None of this code exists in v2.1.233.\n\n**Evidence**\n\n`[modelConfig] `\n\n- Area: Model Config\n- Tier: Nothing to try yet\n- Useful: 1\/5\n- Signal: 3\/5\n- Present in the build but not switched on"}