CommandCodeAI / CommandCodeAI/command-code

--yolo/bypass still asks for confirmation when model calls enter_plan_mode

Open
#771 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Summary

In --yolo/bypass mode, Command Code still prompts for confirmation when the model calls enter_plan_mode, which breaks expected non-interactive behavior.

Expected Behavior

When running with --yolo/bypass, there should be no interactive confirmation prompts for model-proposed mode switches (including enter_plan_mode), or there should be a clear option/flag for “never ask” behavior.

Actual Behavior

A confirmation prompt appears when the model calls enter_plan_mode, even with --yolo/bypass enabled. and just pauses

Steps to reproduce the issue
  1. Start Command Code with bypass enabled (--yolo).
  2. Run a prompt/task that causes the model to call enter_plan_mode. or just ask it say "plan differently"
  3. Observe a confirmation prompt asking to approve the mode switch.
Command Code Version

1.36.0

Operating System

Windows

Terminal/IDE

Unknown

Shell

cmd.exe

Session file (optional)

No response

Fix prompt (optional)

No response

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

Reproduce the issue by starting Command Code 1.36.0 with --yolo on Windows cmd.exe and asking for a plan that triggers enter_plan_mode. Trace the confirmation handling for model-proposed mode switches and compare it with bypass behavior. Done means enter_plan_mode does not pause for confirmation in bypass mode, or a clear never-ask option is provided.

Written by the indexing model from the issue text.

Assessment

Domain
cli
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.