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.
A new internal summarization mechanism emits a background summary after each assistant turn, with a summarizes_uuid field pointing to the message being summarized. This infrastructure supports future conversation intelligence features.
Evidence
Post-turn summary (search for "Background post-turn summary")
Strings lifted out of the shipped bundle, so the claim above can be checked against them.