subagents all fail

Open

#498 opened on Jun 18, 2026 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty: 4/5
Estimated time: 3-5 days
Newbie friendliness: 35/100

Issue type: Bug
Clarity: Needs clarification
Activity status: Quiet
Tech stack: macos
Domain: ai, cli

Research direction

Start by reproducing the failure in Command Code v0.39.0 on macOS with a prompt that makes it explore a medium-sized project and spawn parallel subagents. Observe where the subagents report errors and when Command Code falls back to doing the work itself. Done means the subagents complete their work without repeated failures or fallback.

Written by the indexing model from the issue text.

Description

Summary

Error: Something went wrong. Please try again or contact support if the issue persists.

tried to use subagents in parallel, didn't work commandcode agent ended up doing the work itself

"Explore agents are down. Let me gather this info directly through reads and shell commands."

Expected Behavior

working subagents

Actual Behavior

error runnign subagents

Steps to reproduce the issue

open commandcode
give it prompt where ti ahs to explore decently sized project
itll spawn subagents theyll work for a bit then give an error.

commandcode tries to spawn more they run again then fail again
so commandcode has to do the work itself

Command Code Version

v0.39.0

Operating System

macOS

Terminal/IDE

No response

Shell

No response

Additional context

No response

Dominant language: No language data
Stars: 4k
Forks: 350
PR merge metrics: No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

Read the whole issue, then the project's contributing guide.
Comment on the issue to say you are picking it up — it saves two people doing the same work.
Fork the repository and make your change on a branch.
Open a pull request that references the issue number.

Similar issues

[Feature] Make RAG UPLOAD_EXTS configurable via environment variable Open

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

unslothai/unsloth#11385 · 1 comment · Opened Sep 20, 2026
[BUG] examples/tau2: _clean_messages(for_user=True) deletes the user simulator's own tool calls and results, breaking the telecom domain Open

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

areal-project/AReaL#1741 · Opened Sep 20, 2026
Past participle of “to be” becomes “was” instead of “been” Open

bug next-release

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

spencermountain/compromise#1226 · 1 comment · Opened Sep 20, 2026
Hindsight local_embedded: TypeError 'module' object is not callable in _new_embedded_client Open

area/memory comp/plugins P3 tool/memory type/bug

Difficulty 1/5 Under an hour Newbie friendliness 90/100

NousResearch/hermes-agent#117266 · 2 comments · Opened Sep 20, 2026
COMPACT-4: Where a round's results were sent as prose rather than in the API's own shape, by_round treats Open

bug spec-mismatch

Difficulty 2/5 1-3 hours Newbie friendliness 85/100

brave/bravebot#500 · Opened Sep 20, 2026

More AI Infra & Agents issues

subagents all fail

Assessment

Research direction

Description

Summary

Expected Behavior

Actual Behavior

Steps to reproduce the issue

Command Code Version

Operating System

Terminal/IDE

Shell

Additional context

Contributor guide

First steps

More from CommandCodeAI/command-code

Similar issues

Get new issues in your inbox