What
The context report now carries a structured payload as well as the usual markdown table: model, total tokens, the model's raw maximum, percentage used, and breakdowns by category, MCP tool, memory file, agent and skill.
Details
- When you are over the window there is an extra section giving how many tokens over you are and which kind of limit was hit: the model's own believed limit, or the smaller window Claude Code compacts against.
- A matching schema with full descriptions was added to the stream-JSON type definitions. The schema shape existed before; the code that fills it in is new.
Evidence
Structured twin of the /context report, over_limit
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
Names in the bundle/context
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Added since
A small documentation edit on whats-new-fable-5-1 touched a line naming /context after this was published.
To keep thinking valid across a long session, treat the conversation as append-only. Add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) ([turn-s…models/fable-5-1/whats-new-fable-5-1 see the edit
Confirmed since
Anthropic's documentation has since written up /context, on How Claude Code uses prompt caching.
[Compaction](/docs/en/context-window#what-survives-compaction) replaces your message history with a summary. By design, this invalidates the conversation layer, since the next request has a new, shorter history that doesn't share a prefix …prompt-caching see the edit
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agrees
Anthropic's documentation has since written up /context, on How Claude Code uses prompt caching.