Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix [Bug]: Non-main subagent mode:"run" ignores delegated task payload and returns generic handshake [1 comments, 2 participants]

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…
GitHub stats
openclaw/openclaw#78681•Fetched 2026-05-07 03:33:54
View on GitHub
Comments
1
Participants
2
Timeline
9
Reactions
2
Author
tonysamos1tonysamos1
Participants
clawsweeper[bot]clawsweeper[bot]tonysamos1tonysamos1
Timeline (top)
mentioned ×3subscribed ×3labeled ×2commented ×1

Non-main subagent runs for custom agent rom ignore exact delegated mode:"run" payloads and return a generic handshake; control runs with main execute correctly.

Root Cause

Non-main subagent runs for custom agent rom ignore exact delegated mode:"run" payloads and return a generic handshake; control runs with main execute correctly.

RAW_BUFFERClick to expand / collapse

Bug type

Regression (worked before, now fails)

Beta release blocker

No

Summary

Non-main subagent runs for custom agent rom ignore exact delegated mode:"run" payloads and return a generic handshake; control runs with main execute correctly.

Steps to reproduce

  1. Allow main to delegate to rom. 2) Spawn main with task Reply with exactly: TOKEN_MAIN_1421 (passes). 3) Spawn rom with task Reply with exactly: TOKEN_TEST_1412 (fails). 4) Inspect rom trajectory prompt/response.

Expected behavior

sessions_spawn(... agentId:"rom", mode:"run", task:"Reply with exactly: TOKEN_TEST_1412") should return exactly TOKEN_TEST_1412.

Actual behavior

ROM returns generic handshake text asking for input instead of returning TOKEN_TEST_1412. Reproduced repeatedly after restart/recreate/doctor --fix.

OpenClaw version

2026.5.4 (325df3e)

Operating system

Windows 11 10.0.26200 x64

Install method

No response

Model

openai-codex/gpt-5.3-codex

Provider / routing chain

openclaw gateway -> openai-codex

Additional provider/model setup details

No response

Logs, screenshots, and evidence

Impact and severity

No response

Additional information

No response

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…

FAQ

Expected behavior

sessions_spawn(... agentId:"rom", mode:"run", task:"Reply with exactly: TOKEN_TEST_1412") should return exactly TOKEN_TEST_1412.

#installation#tensor shape#autograd error#model save/load#optimization

Still need to ship something?

×6

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

Back to top recommendations

TRENDING

openclaw - 💡(How to fix) Fix [Bug]: Non-main subagent mode:"run" ignores delegated task payload and returns generic handshake [1 comments, 2 participants]