GitHub issue #75043 in anthropics/claude-code, opened 2026-07-07 by mof086999-code, records a report, based on a controlled experiment of 10+ orchestrator runs over two days, of three related failures when an agent spawned via the Agent tool spawns its own children via the Agent tool: children run detached regardless of run_in_background, child completion notifications reach the main conversation rather than the spawning subagent, and TaskStop fails with ownership errors after a SendMessage resume.
Verbatim Excerpts from Cited Records
“When an agent spawned via the `Agent` tool (an "orchestrator" subagent) spawns its own children via the `Agent` tool, three related failures occur reliably.”
·
anthropics/claude-code (issue 75043 opening body, Summary section)
·
2026-07-07T00:04:05Z
·GitHub Issue ↗
“Even when the orchestrator's `Agent` call does not set `run_in_background` (or sets it to false/null), the child runs detached: the orchestrator's turn does not block on it, no completion notification is delivered to the orchestrator, and the orchestrator is never auto-resumed.”
·
anthropics/claude-code (issue 75043 opening body, Summary section)
·
2026-07-07T00:04:05Z
·GitHub Issue ↗
“When the child finishes, its completion notification (task-notification) is delivered to the *main conversation* that spawned the orchestrator — not to the orchestrator that actually spawned the child.”
·
anthropics/claude-code (issue 75043 opening body, Summary section)
·
2026-07-07T00:04:05Z
·GitHub Issue ↗
Counter-record: Issue remains open as of 2026-10-28 with 25 comments. Surveyed comments show confirmations on other platforms and versions (Linux v2.1.195, Windows v2.1.207, and the code-review plugin internal fan-out). Anthropic collaborator bcherny re-tested on 2.1.233: in the 2026-08-15 re-test symptom 3 reproduced, while in the 2026-08-17 re-test symptom 1 appeared fixed, symptom 2 was confirmed still reproducing, and symptom 3 could not be reproduced in headless testing; the issue was kept open for item 2. Other commenters dispute the fix (vstratful on 2.1.234: items 1 and 3 still broken, item 2 works; taminomara on 2.1.226: item 2 fixed, item 3 not). The latest surveyed comment (grandmasteri, 2026-10-26) reports the behavior still reproducing on 2.1.310, with the depth-1 parent now woken. No maintainer resolution or author retraction appears in the surveyed thread; the claim documents the original report, not the current state of any symptom.
Falsification probe: If issue #75043 is deleted without archive, if the author edits the opening body so the quoted sentences no longer match verbatim, or if the author or maintainers post a definitive retraction showing the described behavior was mischaracterized, this claim drops to Withdrawn.
Audit verification: Verified 100% continuous verbatim substring against official GitHub REST API by
scripts/verify_claim_verbatim.py.