DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.
What changed: Context warnings now adapt based on the model's maximum context size Impact: Users with 1M context models won't receive premature "low context" warnings when they still have substantial tokens remaining, improving the experience for long-form conversations
