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.
Untrusted-data warnings on web fetch redirects are recalculated for each response.
What's wrong with this entry?
Anonymous. No account, no email.
What
The warning about untrusted data that gets attached to a web fetch redirect report is now computed for each response rather than once earlier in the call, so it reflects the agent context at the moment the redirect is handled.
Evidence
let F = wR(t.agentContext);
Strings lifted out of the shipped bundle, so the claim above can be checked against them.