Tool host output arrives as its own system message in stream-json, easier to script against.
What's wrong with this entry?
Output from a tool host (a separate process that runs a tool on Claude Code's behalf) now arrives as its own system message in --output-format stream-json, so scripts can read it directly instead of parsing it out of an attachment.
- The message carries the
tool_use_id, the host name and its working directory, an optional disposition and label, anunverifiedflag, and the output lines. - No flag gates it; it is emitted whenever the underlying attachment appears.
tool_host_result
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.
-
v2.1.234
Permission mode changes are announced on the stream-json output
Both mention output format stream json
-
v2.1.224
Compact summaries are flagged as synthetic in SDK output
Both mention output stream json
-
v2.1.229
Injected stream-json user messages no longer count as human turns
Both mention stream json