Preview a delegate (free)
kimi_delegate_dry_runPreview a delegate call's scope before paying: inspect baseline, prompt size, workspace, and deadline risks without invoking a model. Validate repo and task size to avoid failed or costly delegation.
Instructions
Preview what a kimi_delegate/kimi_delegate_async call would do — the
baseline it seeds from (HEAD commit, tracked file count/size, uncommitted and
untracked counts), the prompt size that would be sent, and the resolved
workspace/isolation. Free — no model call, no spend, no worktree created.
Use it before delegating to confirm scope and repo before committing to cost,
exactly as kimi_dry_run previews kimi_review_changes. Mirrors the real
delegate's zero-spend validation (workspace, isolation, task size, git repo), so
a failure here is a failure the paid call would also hit. The returned
tier/sandbox describe the previewed propose run, not this read-only preview;
the result echoes the effective model/reasoning_effort overrides the paid
call would send (unvalidated). deadline_advisory is non-null when size or
reasoning effort risks the synchronous deadline and names kimi_delegate_async
verbatim — the async counterpart of the previewed call, not of this dry-run tool.
A hint, not a refusal.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | The coding task you want Kimi to implement via a real kimi_delegate call; this dry run only previews the seeded baseline and prompt size — it does NOT call Kimi or return a diff. Must be non-blank: empty or whitespace-only is rejected here too, not previewed. | |
| model | No | The Kimi model slug the previewed paid call would use; defaults to the server default (MOONBRIDGE_MODEL) when unset, so the preview mirrors the paid call's resolution. This dry run does not call Kimi or validate the model. | |
| isolation | No | Which skills Kimi loads: 'inherit' (own user/project discovery) or 'ignore-skills' (empty dir). Built-ins load either way; this reduces loading, not isolation. Default: server-configured, per kimi_status. More: kimi://params. | |
| workspace_root | No | Absolute path to the target repo root — pass it to target the intended repo (MCP roots are unavailable); otherwise the call falls back to the server's own cwd and sets meta.workspace_warning. | |
| reasoning_effort | No | The reasoning effort the previewed paid call would send (as a `model_reasoning_effort` config override); defaults to the server default (MOONBRIDGE_REASONING_EFFORT) when unset, so the preview mirrors the paid call's resolution. This dry run does not call Kimi or validate the value beyond the paid params' shape bounds (no control or surrogate characters, ≤128 chars). |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ok | Yes |