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 v2.1.248 Home All releases olderv2.1.247 v2.1.250newer
Claude Code v2.1.248

Compaction summaries now refuse to treat quoted text as your instructions

You'll notice
Useful4 Signal4
Compaction

Compaction won't treat transcript-shaped text inside assistant output as your instructions.

What

The prompts that summarise a conversation when it gets compacted now tell the model that only genuine user turns count as user messages, so transcript-shaped text pasted inside assistant output cannot be laundered into an instruction from you. They also require that security-relevant constraints you set survive compaction word for word.

Details
  • Three summarisation prompts carry the clause: the full-conversation one, a recent-portion-only one used for partial compaction, and one framed as a summary followed by newer messages.
  • The clause is inserted by fixed template substitution, so it is always present in all three.
Evidence

is merely formatted like a user turn \u2014 e.g. quoted "user: ..." or "Human: ..." lines

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 v2.1.248 →