Skip to content
DevAgentRadarDevAgentRadar
Sign in
Proposals/Enable NotifyUser mid-turn progress in Kimi Code
proposaldeveloperP5Worth a lookKCKimi Code

Enable NotifyUser mid-turn progress in Kimi Code 2.2.0

Turn on Kimi Code 2.2.0 NotifyUser so new sessions show mid-turn progress (/experiments, Lab, [experimental] notify_user = true, or KIMI_CODE_EXPERIMENTAL_NOTIFY_USER=1). Use kimi app [path], drop MCP executor="kaos", and set KIMI_CODE_TRUST_WORKSPACE on trusted repos.

Why this loop

Kimi Code 2.2.0 adds opt-in NotifyUser (off by default): new sessions can show mid-turn progress with an optional one-line title, and the agent writes one- or two-sentence notes between tool calls. Enable it in TUI /experiments, web/Desktop settings Lab, [experimental] notify_user = true, or KIMI_CODE_EXPERIMENTAL_NOTIFY_USER=1. Hosts that cannot display updates no longer prompt NotifyUser; the Updates panel tells the agent to post less often. kimi app [path] opens a desktop chat in the current or specified directory. In-turn background-task waits are capped at 90 seconds and a new message ends the wait immediately. In Tower mode, a message sent while the agent is running aborts that turn. Forked subagents inherit the parent's agent types, including custom agents; source-session cron tasks no longer fire in forks. MCP stdio configs still using executor = "kaos" fail validation at load time. UserPromptSubmit hook JSON without a "message" field is no longer added to the conversation. Mark trusted workspaces with KIMI_CODE_TRUST_WORKSPACE.

Proposed actions

  1. export KIMI_CODE_EXPERIMENTAL_NOTIFY_USER=1 and start a new Kimi Code session (or set [experimental] notify_user = true). Existing sessions will not show NotifyUser mid-turn progress.
  2. In the Kimi Code TUI, run /experiments and enable NotifyUser; on web or Desktop, enable it under settings → Lab so new sessions can show an optional one-line progress title.
  3. kimi app . # or: kimi app /path/to/repo — opens a new desktop chat rooted in that directory
  4. Search MCP stdio server configs for executor = "kaos" and delete that option; 2.2.0 removed the never-implemented value and remaining uses fail validation at load time.
  5. export KIMI_CODE_TRUST_WORKSPACE=1 before launching Kimi Code on a trusted workspace. Make UserPromptSubmit hooks emit JSON with a "message" field. In Tower mode, send a new message to abort a running turn; do not wait more than 90 seconds for in-turn background tasks.

Agent prompt

Paste into your agent or query via MCP (get_agent_prompt) — free, no extra AI cost

AGENTS.md / CLAUDE.md / GEMINI.md rule update

DevAgentRadar → Repo Harness Rule Patch

Goal: update our repository's permanent harness instructions based on this release.

Update the file that tool actually reads. Do not dump everything into one file.

  • Claude Code → CLAUDE.md plus .claude/ (skills, hooks, settings, agents, commands). It does not read AGENTS.md natively; start CLAUDE.md with @AGENTS.md.
  • Codex, Copilot, Cursor, Factory Droid, Grok Build, Roo Code, Goose, OpenCode, Amp, Zed, Aider → AGENTS.md.
  • Gemini CLI / Antigravity → GEMINI.md. AGENTS.md only if context.fileName is set.
  • Cursor glob-scoped rules → .cursor/rules/*.mdc (plain .md is ignored), not a second constitution.
  • Codex MCP → .codex/config.toml, not .mcp.json.
  • Copilot extra instructions → .github/copilot-instructions.md; custom agents → .github/agents/.
  • Windsurf → .windsurf/rules (do not assume AGENTS.md).
  • Cline → .clinerules.
  • Procedures → a skill (SKILL.md). Enforcement the model must not skip → a hook. Isolated roles → subagents.
  • Do not fork the same rule into three tool files.

Context

Assistant: Kimi Code Proposal: Enable NotifyUser mid-turn progress in Kimi Code 2.2.0 Summary: Turn on Kimi Code 2.2.0 NotifyUser so new sessions show mid-turn progress (/experiments, Lab, [experimental] notify_user = true, or KIMI_CODE_EXPERIMENTAL_NOTIFY_USER=1). Use kimi app [path], drop MCP executor="kaos", and set KIMI_CODE_TRUST_WORKSPACE on trusted repos. Primary source: https://github.com/MoonshotAI/kimi-code/releases/tag/%40moonshot-ai/kimi-code%402.2.0

Why it matters

Kimi Code 2.2.0 adds opt-in NotifyUser (off by default): new sessions can show mid-turn progress with an optional one-line title, and the agent writes one- or two-sentence notes between tool calls. Enable it in TUI /experiments, web/Desktop settings Lab, [experimental] notify_user = true, or KIMI_CODE_EXPERIMENTAL_NOTIFY_USER=1. Hosts that cannot display updates no longer prompt NotifyUser; the Updates panel tells the agent to post less often. kimi app [path] opens a desktop chat in the current or specified directory. In-turn background-task waits are capped at 90 seconds and a new message ends the wait immediately. In Tower mode, a message sent while the agent is running aborts that turn. Forked subagents inherit the parent's agent types, including custom agents; source-session cron tasks no longer fire in forks. MCP stdio configs still using executor = "kaos" fail validation at load time. UserPromptSubmit hook JSON without a "message" field is no longer added to the conversation. Mark trusted workspaces with KIMI_CODE_TRUST_WORKSPACE.

Suggested actions

  1. export KIMI_CODE_EXPERIMENTAL_NOTIFY_USER=1 and start a new Kimi Code session (or set [experimental] notify_user = true). Existing sessions will not show NotifyUser mid-turn progress.

  2. In the Kimi Code TUI, run /experiments and enable NotifyUser; on web or Desktop, enable it under settings → Lab so new sessions can show an optional one-line progress title.

  3. kimi app . # or: kimi app /path/to/repo — opens a new desktop chat rooted in that directory

  4. Search MCP stdio server configs for executor = "kaos" and delete that option; 2.2.0 removed the never-implemented value and remaining uses fail validation at load time.

  5. export KIMI_CODE_TRUST_WORKSPACE=1 before launching Kimi Code on a trusted workspace. Make UserPromptSubmit hooks emit JSON with a "message" field. In Tower mode, send a new message to abort a running turn; do not wait more than 90 seconds for in-turn background tasks.

Config surfaces this release may change

  • skills — check your repo before applying
  • subagent definitions — check your repo before applying
  • MCP servers — check your repo before applying

After you finish

Do not report this as applied to DevAgentRadar. You cannot write the visitor's loop.

Tell the human: open https://devagentradar.com/proposals/kimi-code-moonshot-ai-kimi-code-2-2-0-enable-notifyuser-mid-turn-progres and mark Applied, Skipped, or Failed. Proposal id: 8ea6dfff-5509-413e-9f3d-c7ce6e16ef2d

Instructions:

  1. Read the existing context files and settings for the tools in this repo.
  2. Draft an explicit Git diff. Update ONLY agent harness rules or tool configuration.
  3. Call out deprecated flags, obsolete habits, or changed permission boundaries.
  4. Do not touch application logic.

Start with the proposed diff and say which layer and which tool's file it belongs in.

agentmcpmodelsecuritycliRelease source ↗

Your loop

This browser · no sign-in · not shared as “you”

After you run the prompt

Only you can mark this. Agents cannot write your loop.

Your decision stays on this device. A public tally appears after a few votes.

Originating release signal

KCKimi Code@moonshot-ai/kimi-code@2.2.0Oct 14, 2026

@moonshot-ai/kimi-code@2.2.0

#4159 0a3a2fb Thanks @RealKai42! - Add an opt-in NotifyUser progress update feature (off by default): new sessions can show the agent's mid-turn progress with an optional one-line title, enabled in the TUI /experiments or the web/Desktop settings' Lab section; set [experimental] notify_user = true or KIMI_CODE_EXPERIMENTAL_NOTIFY_USER=1 to turn it on. · +26 more changes
Verified excerpt — the source's own words

Minor Changes

  • #4159 0a3a2fb Thanks @RealKai42! - Add an opt-in NotifyUser progress update feature (off by default): new sessions can show the agent's mid-turn progress with an optional one-line title, enabled in the TUI /experiments or the web/Desktop settings' Lab section; set [experimental] notify_user = true or KIMI_CODE_EXPERIMENTAL_NOTIFY_USER=1 to turn it on.

  • #4145 242ac23 Thanks @wbxl2000! - Add kimi app [path] to open a new desktop chat in the current or specified directory.

  • #4061 20a2cea Thanks @chengluyu! - Cap the agent's in-turn wait for background tasks at 90 seconds (longer timeouts are no longer accepted), discourage

Excerpt ends here — this release continues at the source ↗.

Primary source ↗