Follow Discord
Sweep 03 Oct 2026 · 20:28Z Build v2.1.289 510 read Stable v2.1.285 Latest v2.1.289 Next v2.1.289 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Code CLI 3 Oct 2026
One change · claude-code

Create custom subagents changedsub-agents

Nearest release: v2.1.288, published 6 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Upstream edited this page at 3 Oct 2026 01:12 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 3 Oct 2026 01:37 UTC.

Upstream edited
Recorded here
Lines+2added
Lines−2removed
From line 926 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits65to this page, all time

The whole hunk

from line 926, old and new numbered
/
lines
from line 926
926926 
927927When something [cuts off a subagent's response mid-stream](/docs/en/errors#the-response-above-may-be-incomplete), and the partial response contains text but no tool calls, Claude Code prompts the subagent to continue rather than ending the run. This happens in interactive sessions too. The run ends on the error only once those continuations are used up.
928928 
929As of v2.1.199, a subagent whose run ends on an API error, such as a usage limit or a repeated server error, reports that failure back to Claude instead of returning the error text as if it were the subagent's findings. What Claude receives depends on where the subagent ran:
929A subagent whose run ends on an API error, such as a usage limit or a repeated server error, reports that failure back to Claude. What Claude receives depends on where the subagent ran:
930930 
931931* **Foreground**: if a rate limit, overload, or server error cuts off a subagent that already produced text output, the Agent tool returns that partial output with a note that the subagent was cut off and didn't finish its task. A subagent that produced nothing, or whose only output was tool calls, fails with [`Agent terminated early due to an API error`](/docs/en/errors#agent-terminated-early-due-to-an-api-error), followed by the error detail. In v2.1.199, a rate limit, overload, or server error that cut off the tool-calls-only shape returned an empty partial result containing only the cut-off note instead.
932932* **Background**: the subagent is marked failed, and the message Claude receives when it ends names the API error and includes the subagent's last output, so partial work isn't lost.
from line 1106
11061106 
11071107Resuming starts a new run of the agent under the same ID, so a subagent that had already failed or completed shows as running again in the task list and in the Agent SDK's task events. Before v2.1.205, it kept showing its earlier failed or completed status while the resumed run was working.
11081108 
1109As of v2.1.199, `SendMessage` checks that a name still refers to the same agent it reached earlier in the conversation. If a newer agent has taken the name, such as a re-spawned background agent that reused it, Claude Code refuses the send rather than delivering it to the wrong agent, and the error reports which agent the name now reaches so Claude can retarget. To reach the earlier agent while it's still running, Claude addresses it by the agent ID it received when it spawned that agent. The check is scoped to the current conversation and resets on `/clear`.
1109`SendMessage` checks that a name still refers to the same agent it reached earlier in the conversation. If a newer agent has taken the name, such as a re-spawned background agent that reused it, Claude Code refuses the send rather than delivering it to the wrong agent, and the error reports which agent the name now reaches so Claude can retarget. To reach the earlier agent while it's still running, Claude addresses it by the agent ID it received when it spawned that agent. The check is scoped to the current conversation and resets on `/clear`.
11101110 
11111111A subagent treats messages from the agent that launched it as normal task direction, including mid-task course corrections, and acts on them within its own permission settings. Two limits hold regardless of who sent the message: no message from any agent counts as your approval for a pending permission prompt, and no agent message can change a subagent's permission settings, `CLAUDE.md`, or configuration. Only the permission system or your own messages can grant approval.
11121112 
Feedback