CLI Reference

The lehuo CLI connects your local machine to lehuo Agents. It handles authentication, workspace management, issue tracking, and runs the agent daemon that executes AI tasks locally.

Agent Daemon

The daemon is the local agent runtime. It detects available AI CLIs on your machine, registers them with the lehuo Agents server, and executes tasks when agents are assigned work.

Start

lehuo daemon start

By default, the daemon runs in the background and logs to ~/.lehuo/daemon.log.

To run in the foreground (useful for debugging):

lehuo daemon start --foreground

Stop

lehuo daemon stop

Status

lehuo daemon status
lehuo daemon status --output json

Shows PID, uptime, detected agents, and watched workspaces.

Logs

lehuo daemon logs              # Last 50 lines
lehuo daemon logs -f           # Follow (tail -f)
lehuo daemon logs -n 100       # Last 100 lines

Supported Agents

The daemon auto-detects these AI CLIs on your PATH:

CLI	Command	Description
Claude Code	`claude`	Anthropic's coding agent
Codex	`codex`	OpenAI's coding agent
Gemini CLI	`gemini`	Google's coding agent
OpenCode	`opencode`	Open-source coding agent
OpenClaw	`openclaw`	Open-source coding agent
Hermes	`hermes`	Nous Research coding agent
Kimi	`kimi`	Moonshot coding agent
Kiro CLI	`kiro-cli`	Kiro ACP coding agent
Pi	`pi`	Inflection coding agent
Cursor Agent	`cursor-agent`	Cursor coding agent

You need at least one installed. The daemon registers each detected CLI as an available runtime.

How It Works

On start, the daemon detects installed agent CLIs and registers a runtime for each agent in each watched workspace
It polls the server at a configurable interval (default: 3s) for claimed tasks
When a task arrives, it creates an isolated workspace directory, spawns the agent CLI, and streams results back
Heartbeats are sent periodically (default: 15s) so the server knows the daemon is alive
On shutdown, all runtimes are deregistered

Configuration

Daemon behavior is configured via flags or environment variables:

Setting	Flag	Env Variable	Default
Poll interval	`--poll-interval`	`LEHUO_DAEMON_POLL_INTERVAL`	`3s`
Heartbeat interval	`--heartbeat-interval`	`LEHUO_DAEMON_HEARTBEAT_INTERVAL`	`15s`
Agent timeout	`--agent-timeout`	`LEHUO_AGENT_TIMEOUT`	`2h`
Max concurrent tasks	`--max-concurrent-tasks`	`LEHUO_DAEMON_MAX_CONCURRENT_TASKS`	`20`
Daemon ID	`--daemon-id`	`LEHUO_DAEMON_ID`	hostname
Device name	`--device-name`	`LEHUO_DAEMON_DEVICE_NAME`	hostname
Runtime name	`--runtime-name`	`LEHUO_AGENT_RUNTIME_NAME`	`Local Agent`
Workspaces root	—	`LEHUO_WORKSPACES_ROOT`	`~/lehuo_workspaces`

Agent-specific overrides:

Variable	Description
`LEHUO_CLAUDE_PATH`	Custom path to the `claude` binary
`LEHUO_CLAUDE_MODEL`	Override the Claude model used
`LEHUO_CODEX_PATH`	Custom path to the `codex` binary
`LEHUO_CODEX_MODEL`	Override the Codex model used
`LEHUO_OPENCODE_PATH`	Custom path to the `opencode` binary
`LEHUO_OPENCODE_MODEL`	Override the OpenCode model used
`LEHUO_OPENCLAW_PATH`	Custom path to the `openclaw` binary
`LEHUO_OPENCLAW_MODEL`	Override the OpenClaw model used
`LEHUO_HERMES_PATH`	Custom path to the `hermes` binary
`LEHUO_HERMES_MODEL`	Override the Hermes model used
`LEHUO_GEMINI_PATH`	Custom path to the `gemini` binary
`LEHUO_GEMINI_MODEL`	Override the Gemini model used
`LEHUO_PI_PATH`	Custom path to the `pi` binary
`LEHUO_PI_MODEL`	Override the Pi model used
`LEHUO_CURSOR_PATH`	Custom path to the `cursor-agent` binary
`LEHUO_CURSOR_MODEL`	Override the Cursor model used
`LEHUO_KIMI_PATH`	Custom path to the `kimi` binary
`LEHUO_KIMI_MODEL`	Override the Kimi model used
`LEHUO_KIRO_PATH`	Custom path to the `kiro-cli` binary
`LEHUO_KIRO_MODEL`	Override the Kiro model used

Self-Hosted Server

When connecting to a self-hosted lehuo Agents instance, point the CLI to your server before logging in:

export LEHUO_APP_URL=https://app.example.com
export LEHUO_SERVER_URL=wss://api.example.com/ws

lehuo login
lehuo daemon start

Or set them persistently:

lehuo config set app_url https://app.example.com
lehuo config set server_url wss://api.example.com/ws

Profiles

Profiles let you run multiple daemons on the same machine — for example, one for production and one for a staging server.

# Set up a staging profile
lehuo setup self-host --profile staging --server-url https://api-staging.example.com --app-url https://staging.example.com

# Start its daemon
lehuo daemon start --profile staging

# Default profile runs separately
lehuo daemon start

Each profile gets its own config directory (~/.lehuo/profiles/<name>/), daemon state, health port, and workspace root.

Workspaces

List Workspaces

lehuo workspace list

Watched workspaces are marked with *. The daemon only processes tasks for watched workspaces.

Watch / Unwatch

lehuo workspace watch <workspace-id>
lehuo workspace unwatch <workspace-id>

Get Details

lehuo workspace get <workspace-id>
lehuo workspace get <workspace-id> --output json

List Members

lehuo workspace member list <workspace-id>

Update Workspace

需要 admin 或 owner 权限。所有字段都是部分更新（PATCH 语义）：未传的字段保持不变。

lehuo workspace update <workspace-id> --name "Acme Eng"
lehuo workspace update <workspace-id> \
  --description "Engineering team workspace" \
  --issue-prefix ENG

长文本走 stdin（保留换行/反斜杠）：

cat <<'CTX' | lehuo workspace update <workspace-id> --context-stdin
我们是一支 5 人 AI-native 团队。
工作语言：中文 + 英文混合。
CTX

可编辑字段：--name、--description / --description-stdin、--context / --context-stdin、--issue-prefix。slug 创建后只读，不暴露在 CLI。--description 与 --description-stdin（以及 context 同名对）互斥。未传任何字段 flag 时命令拒绝执行，避免空 PATCH 触发无意义的 workspace 更新事件。--issue-prefix "" 也会被拒绝：当前后端在 prefix 为空时静默跳过该字段，CLI 在本地拦下避免“看似成功的 no-op”。

Issues

List Issues

lehuo issue list
lehuo issue list --status in_progress
lehuo issue list --priority urgent --assignee "Agent Name"
lehuo issue list --assignee-id 5fb87ac7-23b5-4a7a-81fa-ed295a54545d
lehuo issue list --full-id
lehuo issue list --limit 20 --output json

表格输出默认显示可直接复制到后续命令的 issue KEY（例如 MUL-123）；需要完整 UUID 时使用 --full-id。Available filters: --status, --priority, --assignee / --assignee-id, --project, --limit. 在重名 workspace 下用 --assignee-id <uuid> 可以精确锁定一个成员或 agent。

Get Issue

lehuo issue get MUL-123
lehuo issue get <uuid>
lehuo issue get <id> --output json

<id> 同时接受 issue key（lehuo issue list 表格里直接显示，例如 MUL-123）和完整 UUID（给 list 加 --full-id 可显示）。同样的规则适用于下面 update / assign / status / comment / subscriber / runs 等接受 <id> 的命令。

Create Issue

lehuo issue create --title "Fix login bug" --description "..." --priority high --assignee "Lambda"
lehuo issue create --title "Fix login bug" --assignee-id 5fb87ac7-23b5-4a7a-81fa-ed295a54545d

Flags: --title (required), --description, --status, --priority, --assignee / --assignee-id, --parent, --project, --due-date. 脚本里如果已经拿到了 UUID（例如来自 lehuo workspace member list --output json），传 --assignee-id <uuid>（与 --assignee 互斥）以精确锁定。

Update Issue

lehuo issue update <id> --title "New title" --priority urgent

Assign Issue

lehuo issue assign <id> --to "Lambda"
lehuo issue assign <id> --to-id 5fb87ac7-23b5-4a7a-81fa-ed295a54545d
lehuo issue assign <id> --unassign

--to-id <uuid>（与 --to 互斥）按 UUID 精确分配；适合重名 workspace 下脚本化场景。

Change Status

lehuo issue status <id> in_progress

Valid statuses: backlog, todo, in_progress, in_review, done, blocked, cancelled.

Comments

# List comments
lehuo issue comment list <issue-id>

# Add a comment
lehuo issue comment add <issue-id> --content "Looks good, merging now"

# Reply to a specific comment
lehuo issue comment add <issue-id> --parent <comment-id> --content "Thanks!"

# Delete a comment
lehuo issue comment delete <comment-id>

Execution History

# List all execution runs for an issue
lehuo issue runs <issue-id>
lehuo issue runs <issue-id> --full-id
lehuo issue runs <issue-id> --output json

# View messages for a specific execution run
lehuo issue run-messages <task-id>
lehuo issue run-messages <short-task-id> --issue <issue-id>
lehuo issue run-messages <task-id> --output json

# Incremental fetch (only messages after a given sequence number)
lehuo issue run-messages <task-id> --since 42 --output json

runs 的表格输出默认显示 task UUID 短前缀；需要完整 task UUID 时使用 --full-id。run-messages 可直接接受完整 task UUID；从 runs 表格复制短前缀时需要同时传 --issue <issue-id>，CLI 只会在该 issue 的 runs 内解析。

Projects

Projects group related issues (e.g. a sprint, an epic, a workstream). Every project belongs to a workspace and can optionally have a lead (member or agent).

List Projects

lehuo project list
lehuo project list --status in_progress
lehuo project list --output json

Available filters: --status.

Get Project

lehuo project get <id>
lehuo project get <id> --output json

Create Project

lehuo project create --title "2026 Week 16 Sprint" --icon "🏃" --lead "Lambda"

Flags: --title (required), --description, --status, --icon, --lead.

Update Project

lehuo project update <id> --title "New title" --status in_progress
lehuo project update <id> --lead "Lambda"

Flags: --title, --description, --status, --icon, --lead.

Change Status

lehuo project status <id> in_progress

Valid statuses: planned, in_progress, paused, completed, cancelled.

Delete Project

lehuo project delete <id>

Associating Issues with Projects

Use the --project flag on issue create / issue update to attach an issue to a project, or on issue list to filter issues by project:

lehuo issue create --title "Login bug" --project <project-id>
lehuo issue update <issue-id> --project <project-id>
lehuo issue list --project <project-id>

Configuration

View Config

lehuo config show

Shows config file path, server URL, app URL, and default workspace.

Set Values

lehuo config set server_url wss://api.example.com/ws
lehuo config set app_url https://app.example.com
lehuo config set workspace_id <workspace-id>

Other Commands

lehuo version              # Show CLI version and commit hash
lehuo update               # Update to latest version
lehuo agent list           # List agents in the current workspace

Output Formats

Most commands support --output with two formats:

table — human-readable table (default for list commands)
json — structured JSON (useful for scripting and automation)

lehuo issue list --output json
lehuo daemon status --output json

本页目录