Agent status is read from their own text, recognising phrases like "needs input:" and "blocked:".
What's wrong with this entry?
Background and managed agents are now classified by scanning their output for state lines. Recognised prefixes are needs input:, failed:, blocked: and I'm blocked:, each accepting a colon, em dash or en dash, and a separate detector matches "Giving up" and "The task is not actionable" to mark an agent as having stopped.
- Matching is case-insensitive and captures 3 to 200 characters of the reason up to the end of the line.
/(?:^|\n)\sneeds input\s[:\u2014\u2013-]\s*(.{3,200}?)(?=\n|$)/gi
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.
-
v2.1.235
Question options with identical text are no longer confused with each other
Both mention agent
-
v2.1.236
Teammate messages whose summary swallowed the body are split back apart
Both mention agent
-
v2.1.238
Claude is told to stay in a worktree even when it did not create one
Both mention agent