MiniMax-AI / MiniMax-AI/MiniMax-M3

[M3 Bug] ALLALLALL tags generation

Open
#20 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
No language data
Stars
487
Forks
59
PR merge metrics
No merged PRs in 30d

Description

Which inference path did you use?

MiniMax API

Inference parameters

No response

Prompt / input
When completing the task with the subagent, M3 reports that ALL tasks have been completed. Sometimes, this may lead to ALLALLALL... tags repeated thinking.
Expected behavior

The model decides that the task has been completed and closes the session.

Actual behavior
Image 2) Image
Image
Additional context

No response

Contributor guide

No contributing guide indexed for this repository

First steps

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

Research direction

The report names no repository file, test, or entry point; start by locating the MiniMax API inference and subagent session-completion handling. Reproduce the repeated ALL output with the supplied prompt, then verify that completion closes the session without repeated tags and add regression coverage for that behavior.

Written by the indexing model from the issue text.

Assessment

Domain
ai
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.