Issue Station
Sign In
Tools hereToolbox

claude-code - 💡(How to fix) Fix [Bug] Opus 4.8: parallel Bash siblings stuck on Waiting… and render out of order behind a long-running call

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Error Message

Likely shares a root cause with #63881 (also Opus 4.8, parallel Bash batches; reportedly absent on 4.7). That issue covers cascade-cancellation on non-zero exit; this one is the out-of-order / stuck-Waiting… rendering variant with no error involved.

Root Cause

Likely shares a root cause with #63881 (also Opus 4.8, parallel Bash batches; reportedly absent on 4.7). That issue covers cascade-cancellation on non-zero exit; this one is the out-of-order / stuck-Waiting… rendering variant with no error involved.

Fix Action

Fix / Workaround

On claude-opus-4-8, when a batch of parallel Bash calls includes one long-running command, its sibling calls get stuck displaying Waiting… indefinitely, while Bash calls dispatched afterward complete and render normally — producing out-of-order tool output in the TUI.

The trivial n1–n4 calls never leave Waiting…, yet p1–p5 (dispatched later) finish and render. Expected: all calls complete and render in a consistent order.

Code Example

● Bash(echo done-flush)        ⎿  done-flush
● Bash(W="…"; cd "$W"; py -c…)  ⎿  Running… (3s)
● Bash(echo n1)                ⎿  Waiting…
● Bash(echo n2)                ⎿  Waiting…
● Bash(echo n3)                ⎿  Waiting…
● Bash(echo n4)                ⎿  Waiting…
● Bash(echo p1)                ⎿  p1
● Bash(echo p2)                ⎿  p2
● Bash(echo p3)                ⎿  p3
● Bash(echo p4)                ⎿  p4
● Bash(echo p5)                ⎿  p5
RAW_BUFFERClick to expand / collapse

Bug Description

On claude-opus-4-8, when a batch of parallel Bash calls includes one long-running command, its sibling calls get stuck displaying Waiting… indefinitely, while Bash calls dispatched afterward complete and render normally — producing out-of-order tool output in the TUI.

Observed output:

● Bash(echo done-flush)        ⎿  done-flush
● Bash(W="…"; cd "$W"; py -c…)  ⎿  Running… (3s)
● Bash(echo n1)                ⎿  Waiting…
● Bash(echo n2)                ⎿  Waiting…
● Bash(echo n3)                ⎿  Waiting…
● Bash(echo n4)                ⎿  Waiting…
● Bash(echo p1)                ⎿  p1
● Bash(echo p2)                ⎿  p2
● Bash(echo p3)                ⎿  p3
● Bash(echo p4)                ⎿  p4
● Bash(echo p5)                ⎿  p5

The trivial n1–n4 calls never leave Waiting…, yet p1–p5 (dispatched later) finish and render. Expected: all calls complete and render in a consistent order.

Environment

  • Model: claude-opus-4-8
  • Platform: win32 (Windows 11)
  • CLI version: 2.1.158

Related

Likely shares a root cause with #63881 (also Opus 4.8, parallel Bash batches; reportedly absent on 4.7). That issue covers cascade-cancellation on non-zero exit; this one is the out-of-order / stuck-Waiting… rendering variant with no error involved.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

claude-code - 💡(How to fix) Fix [Bug] Opus 4.8: parallel Bash siblings stuck on Waiting… and render out of order behind a long-running call