MoonshotAI / MoonshotAI/kimi-cli

[Bug] Kimi Work tab: "Daimon control WS not ready" + infinite reload at 99%

Open
#2,435 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
11.4k
Forks
1.3k
Avg merge
9h 47m
Merged PRs (30d)
2

Description

Description

The Work tab in kimi web is completely unusable due to a WebSocket daemon initialization failure and an infinite reload loop. The UI shows a persistent error and restarts loading at 99% continuously.

Environment

  • OS: Windows 10/11
  • Kimi CLI version: 1.41.0 (initial) → 1.47.0 (after reinstall)
  • uv version: 0.11.7
  • Python: 3.13

Steps to Reproduce

  1. Run kimi web in terminal
  2. Open browser at http://127.0.0.1:5494
  3. Click on the Work tab (next to Chat)
  4. Observe the error banner and loading behavior

Expected Behavior

The Work tab should load successfully, showing:

  • New Task button
  • Skills section
  • Scheduled Tasks
  • WebBridge

Actual Behavior

Error 1: Daemon WebSocket not ready

A red error banner appears immediately:
Daimon control WS not ready (status=idle)

Error 2: Session Error

After attempting to load, a popup shows:
ERROR | threading:run | GitHub MCP Server running on stdio ERROR | threading:run | Context7 Documentation MCP Server v3.1.0 running on stdio ERROR | threading:run | Starting MCP server 'notebooklm' with transport 'stdio'

This cycle repeats continuously, suggesting the entire backend process is crashing and restarting.

What I've Tried

  1. ✅ Restarted kimi web (browser + terminal)
  2. ✅ Reinstalled Kimi CLI completely (1.41.0 → 1.47.0)
  3. ✅ Killed all residual processes and cleaned cache
  4. ✅ Same bug persists after clean reinstall

Additional Context

  • The Chat tab works perfectly fine
  • All CLI functionality works normally in terminal
  • The bug appears to be isolated to the Work tab's daemon initialization
  • The WebSocket for "Daimon control" never reaches ready state, remaining idle

Labels

bug, web-ui

Contributor guide

Open the contributing guide

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 on Windows by running kimi web, opening http://127.0.0.1:5494, and selecting Work. Start by tracing Daimon control WebSocket initialization and the backend restart cycle, including the MCP server messages. Done means the WebSocket reaches ready, loading completes without reloading, and the Work tab shows its task and skills sections.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend, cli, web-dev
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.