Source Intelligence

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.

All of v2.1.236 Home All releases olderv2.1.235 v2.1.237newer
Claude Code v2.1.236

Per-model reminder text delivered from server config

Not switched on
Useful2 Signal4
Conversation Notable not in their notes

Reminder text can be latched into a conversation once per model from server config or an env var.

A per-model reminder attachment reads a server-supplied model-pattern map or CLAUDE_CODE_TOASTY_THIMBLE; with neither, nothing is injected.

CLAUDE_CODE_TOASTY_THIMBLE
What

The reminder described above is a new attachment type that latches into a conversation once per model, taking its text from a server-supplied map of model pattern to reminder text or from CLAUDE_CODE_TOASTY_THIMBLE. With neither present, nothing is injected.

Details
  • Injection is reported with the model name and whether the text came from the environment or the server.
  • It writes a marker entry into the transcript when sent.
  • The reminder is filtered out of the prompt when the turn is not a human turn.
  • None of this machinery existed in the previous release.
Evidence

tengu_toasty_thimble_applied

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

See this entry in the whole of v2.1.236 →