{"version":"2.1.281","anchor":"context-low-warning-passes-the-model-through-a-normalizer","canonical_anchor":"context-low-warning-passes-the-model-through-a-normalizer","heading":"Context-low warning passes the model through a normalizer","tier":null,"area":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281\/e\/context-low-warning-passes-the-model-through-a-normalizer","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281","markdown":"### Context-low warning passes the model through a normalizer\n\nThe low-context warning now normalizes the model before working out its warning level and auto-compact threshold\n\n**Unclear.** The finding does not say what the helper does to the model, so it is unclear for which models the numbers change.\n\n**What**\n\nThe \"Context low\" warning and the \"% until auto-compact\" footer now run the current model through a helper first. From the result they work out three things: the warning level, the usable context size and the point where auto-compact starts. Context is how much of the conversation the model can hold at once. Auto-compact is when Claude Code shortens the conversation to make room. The wording of the warning is unchanged.\n\n**Why**\n\nThe warning's numbers now come from the model after this extra step, so the percentage shown can differ for some models even though the text looks the same."}