MoonshotAI / MoonshotAI/kimi-code
feat: expose thinkingEffort in the custom status line JSON snapshot
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 7.5k
- Forks
- 1.2k
- Avg merge
- 11h 53m
- Merged PRs (30d)
- 350
Description
Feature request
Add the current session's effective thinking effort to the JSON snapshot passed on stdin to a custom status line command ([status_line].command in tui.toml).
Current behavior (v0.30.0)
The snapshot contains only:
model, cwd, gitBranch, permissionMode, planMode, contextUsage, contextTokens, maxContextTokens, sessionId, version
The built-in footer renders the model slot as <model> thinking: <effort> from runtime state (state.thinkingEffort), so switching effort at runtime via /model is reflected immediately. A custom status line command cannot reproduce this:
thinkingEffortis not in the snapshot payload.- Runtime effort switches are not persisted to
config.toml([thinking].effortstays at its configured default), nor to any session file a script could read.
So with a custom status line configured, the effective effort becomes invisible — a regression versus the built-in layout.
Proposal
Add thinkingEffort (and ideally thinkingEnabled) to the status line payload, sourced from the same runtime state the built-in footer uses. This keeps custom status lines at feature parity with the built-in model slot.
Contributor guide
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.
Research direction
Start at the status line command snapshot generation for [status_line].command and trace the runtime state used by the built-in footer, especially state.thinkingEffort. Verify the stdin JSON reflects runtime changes made through /model, and consider whether thinkingEnabled belongs in the payload as well; done means custom commands can display the effective effort.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- cli
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 64/100