{"version":"2.1.274","anchor":"model-switch-suggestion-text-now-considers-config-sources-be","canonical_anchor":"usage-credits-1m-context-guidance-message-reworked-with-new","heading":"Smarter guidance when a model or 1M-context request can't be fulfilled","tier":"notice","area":"Model Settings","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.274\/e\/model-switch-suggestion-text-now-considers-config-sources-be","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.274","markdown":"### Smarter guidance when a model or 1M-context request can't be fulfilled\n\nMessages suggesting \/model, --model, or usage credits now adapt based on whether you're in an interactive session, self-hosted, or using the SDK\/CLI\/GitHub Action\n\n**What**\n\n- When 1M-context usage requires usage credits, the guidance message now checks whether the session is non-interactive or self-hosted-like, and whether the extra-usage-credits command is actually available (which itself depends on the `DISABLE_EXTRA_USAGE_COMMAND` setting). Depending on the result, the message either offers the `\/usage-credits` command or only mentions `\/model`.\n\n- Similarly, when a requested model isn't available, the suggestion of switching via `\/model` versus the `--model` flag now takes into account whether the session is interactive, and whether it's running in contexts like the SDK, CLI, or `claude-code-github-action`.\n\n**Why**\n\nPreviously these suggestions could point users toward commands or flags that don't actually work in their current context (for example, suggesting an interactive `\/model` command inside a non-interactive script or GitHub Action). The messages now match what's actually usable in the situation.\n\n- Area: Model Settings\n- Names: `\/model`, `--model`\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 1\/5"}