diff --git a/.changeset/prompt-auto-permission-docs.md b/.changeset/prompt-auto-permission-docs.md new file mode 100644 index 0000000000..c3eb67e7bf --- /dev/null +++ b/.changeset/prompt-auto-permission-docs.md @@ -0,0 +1,5 @@ +--- +"@moonshot-ai/kimi-code": patch +--- + +Document that `-p` / `--prompt` runs in auto permission mode, so tool calls are approved without prompting regardless of `default_permission_mode`. diff --git a/apps/kimi-code/src/cli/commands.ts b/apps/kimi-code/src/cli/commands.ts index 6ed5551939..c3e5ff59ed 100644 --- a/apps/kimi-code/src/cli/commands.ts +++ b/apps/kimi-code/src/cli/commands.ts @@ -57,7 +57,7 @@ export function createProgram( .addOption( new Option( '-p, --prompt ', - 'Run one prompt non-interactively and print the response.', + 'Run one prompt non-interactively and print the response. Runs in auto permission mode: tool calls are approved without prompting, except where a permission deny rule blocks them.', ), ) .addOption( diff --git a/docs/en/configuration/config-files.md b/docs/en/configuration/config-files.md index e8df6e99cf..cac4812575 100644 --- a/docs/en/configuration/config-files.md +++ b/docs/en/configuration/config-files.md @@ -98,7 +98,7 @@ Fields in the config file fall into two categories: **top-level scalars** that d | Field | Type | Default | Description | | --- | --- | --- | --- | | `default_model` | `string` | — | Default model alias; must be defined in `models` | -| `default_permission_mode` | `string` | `manual` | Default permission mode for new sessions; one of `manual` (prompt each time), `yolo` (auto-approve tool actions, but the agent may still ask questions), or `auto` (fully autonomous — the agent decides everything without asking) | +| `default_permission_mode` | `string` | `manual` | Default permission mode for new sessions; one of `manual` (prompt each time), `yolo` (auto-approve tool actions, but the agent may still ask questions), or `auto` (fully autonomous — the agent decides everything without asking). Non-interactive runs (`-p` / `--prompt`) always use `auto` regardless of this setting; `deny` rules still apply | | `default_plan_mode` | `boolean` | `false` | Whether new sessions start in Plan mode (produce a plan before executing) by default | | `merge_all_available_skills` | `boolean` | `true` | Whether to merge Agent Skills from all available directories | | `extra_skill_dirs` | `array` | — | Extra skill search directories, layered on top of the default directories | diff --git a/docs/en/configuration/overrides.md b/docs/en/configuration/overrides.md index 717b5d0dc5..a86ad652a2 100644 --- a/docs/en/configuration/overrides.md +++ b/docs/en/configuration/overrides.md @@ -59,14 +59,14 @@ Options passed at startup have the highest priority and apply only to the curren | `--auto` | Start in auto permission mode: fully autonomous, the agent will not ask questions | | `--plan` | Start in Plan mode | | `-m, --model ` | Use a specific model alias for this session | -| `-p, --prompt ` | Run in non-interactive mode: execute a single prompt and exit | +| `-p, --prompt ` | Run in non-interactive mode: execute a single prompt and exit. Runs in auto permission mode, so tool calls are approved without prompting regardless of `default_permission_mode`; `deny` rules in `[[permission.rules]]` still block | | `--output-format ` | Output format for `-p` mode: `text` or `stream-json` | | `--skills-dir ` | Replace auto-discovered Skills directories (repeatable; applies to this session only) | Mutual exclusion rules (startup fails if violated): - `--output-format` can only be used with `-p` -- `--prompt` cannot be combined with `--yolo` or `--plan` +- `--prompt` cannot be combined with `--yolo`, `--auto`, or `--plan` - `--continue` and `--session` cannot be used together - In non-prompt mode, `--yolo` and `--plan` cannot be combined with `--continue` or `--session` diff --git a/docs/zh/configuration/config-files.md b/docs/zh/configuration/config-files.md index be8757e99b..f906b9381c 100644 --- a/docs/zh/configuration/config-files.md +++ b/docs/zh/configuration/config-files.md @@ -98,7 +98,7 @@ timeout = 5 | 字段 | 类型 | 默认值 | 说明 | | --- | --- | --- | --- | | `default_model` | `string` | — | 默认模型别名，必须在 `models` 中定义 | -| `default_permission_mode` | `string` | `manual` | 新会话的默认权限模式，可选 `manual`（逐次询问）、`yolo`（自动批准工具操作，Agent 仍可能提问）、`auto`（完全自主，Agent 自己做决定，不再提问） | +| `default_permission_mode` | `string` | `manual` | 新会话的默认权限模式，可选 `manual`（逐次询问）、`yolo`（自动批准工具操作，Agent 仍可能提问）、`auto`（完全自主，Agent 自己做决定，不再提问）。非交互运行（`-p` / `--prompt`）始终使用 `auto`，不受该配置影响；`deny` 规则仍然生效 | | `default_plan_mode` | `boolean` | `false` | 新会话是否默认以 Plan 模式（先出计划再执行）启动 | | `merge_all_available_skills` | `boolean` | `true` | 是否合并所有目录中的 Agent Skills | | `extra_skill_dirs` | `array` | — | 额外 Skill 搜索目录，叠加到默认目录之上 | diff --git a/docs/zh/configuration/overrides.md b/docs/zh/configuration/overrides.md index 4194fe5214..f8e75381a0 100644 --- a/docs/zh/configuration/overrides.md +++ b/docs/zh/configuration/overrides.md @@ -59,14 +59,14 @@ Kimi Code CLI 有三个地方可以影响运行参数：配置文件、命令行 | `--auto` | 以 auto 权限模式启动：完全自主，Agent 不会向用户提问 | | `--plan` | 以 Plan 模式启动 | | `-m, --model ` | 指定本次使用的模型别名 | -| `-p, --prompt ` | 非交互模式：执行单条提示词后退出 | +| `-p, --prompt ` | 非交互模式：执行单条提示词后退出。以 auto 权限模式运行，工具调用会被自动批准，不受 `default_permission_mode` 影响；`[[permission.rules]]` 中的 `deny` 规则仍然生效 | | `--output-format ` | `-p` 模式的输出格式：`text` 或 `stream-json` | | `--skills-dir ` | 替换自动发现的 Skills 目录（可重复，仅本次生效） | 互斥规则（违反时启动报错）： - `--output-format` 只能配合 `-p` 使用 -- `--prompt` 不能同时用 `--yolo` 或 `--plan` +- `--prompt` 不能同时用 `--yolo`、`--auto` 或 `--plan` - `--continue` 和 `--session` 不能同时用 - 非 prompt 模式下，`--yolo` 和 `--plan` 不能配合 `--continue` 或 `--session`