What
The /context command now attaches machine-readable usage data to its message alongside the text, so the context report carries exact numbers rather than only rendered output.
Details
- The payload includes the model,
total_tokens,raw_max_tokens, a percentage, and an optional over-limit block giving how many tokens over and of what kind. - Separate breakdowns for categories, MCP tools, memory files and agents.
- Each category is classified by a new helper as free, buffer, deferred or used.
- The field flows through to the transcript and to the assistant message yielded to the caller. No such field existed in the previous build.
Evidence
raw_max_tokens
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.