- Agents: surface concise default-visible warnings when `exec`/`bash` tool calls fail after the assistant claims success, while keeping raw stderr hidden unless verbose details are enabled. Fixes #60497. (#80003) Thanks @jbetala7.

- Auto-reply/TUI: keep fallback timeout recovery deliverable after a primary model lifecycle error by emitting fallback progress and deferring terminal TUI errors until recovery has a chance to finish. Fixes #80000. (#80009) Thanks @TurboTheTurtle.

- CLI/agent: let `openclaw agent --model` use the backend/admin Gateway scope without cached device-token scopes silently downscoping the request. (#78837) Thanks @VACInc.

- CLI/help: keep help and version invocations configless while improving shared port, channel, plugin, task, session, message, pairing, and auth recovery text.

- Ollama: keep DeepSeek V4 cloud models thinking-capable even when Ollama Cloud `/api/show` omits the `thinking` capability, so `/think high` no longer rejects `ollama/deepseek-v4-*:cloud`.

- ACPX/Claude ACP: keep foreground prompts waiting for their own result when autonomous task-notification results arrive during the same session, and retarget the patch for Claude Agent ACP `0.33.1`.

- WhatsApp: keep Baileys media uploads from passing non-Dispatcher agents to undici in `7.0.0-rc10`, and patch the bundled Baileys declaration so the latest tsdown build stays warning-clean.

- account ids per selected channel

- optional display names for those accounts

- `Bind configured channel accounts to agents now?`

- `Route these channel accounts to agents now?`

If you confirm bind now, the wizard asks which agent should own each configured channel account and writes account-scoped routing bindings.

# `openclaw configure`

Interactive prompt to set up credentials, devices, and agent defaults.

Interactive prompt for targeted changes to an existing setup: credentials, devices, agent defaults, gateway, channels, plugins, skills, and health checks.

Use `openclaw onboard` for the full guided first-run journey, `openclaw setup` for the baseline config/workspace only, and `openclaw channels add` when you only need channel account setup.

<Note>

The **Model** section includes a multi-select for the `agents.defaults.models` allowlist (what shows up in `/model` and the model picker). Provider-scoped setup choices merge their selected models into the existing allowlist instead of replacing unrelated providers already in the config.

index lists the commands, the global flags, and the output styling rules that

apply across the CLI.

Use the setup commands by intent:

- `openclaw setup` creates the baseline config and workspace without walking the full guided onboarding flow.

- `openclaw onboard` is the full guided first-run path for gateway, model auth, workspace, channels, skills, and health.

- `openclaw configure` changes targeted parts of an existing setup, such as model auth, gateway, channels, plugins, or skills.

- `openclaw channels add` configures channel accounts after the baseline exists; run it without flags for guided channel setup or with channel-specific flags for scripts.

## Command pages

| Area | Commands |

# `openclaw onboard`

Interactive onboarding for local or remote Gateway setup.

Full guided onboarding for local or remote Gateway setup. Use this when you want OpenClaw to walk through model auth, workspace, gateway, channels, skills, and health in one flow.

## Related guides

## Common follow-up commands

```bash

openclaw channels add

openclaw configure

openclaw agents add <name>

```

Use `openclaw setup` instead when you only need the baseline config/workspace. Use `openclaw configure` later for targeted changes and `openclaw channels add` for channel-only setup.

<Note>

`--json` does not imply non-interactive mode. Use `--non-interactive` for scripts.

</Note>

# `openclaw setup`

Initialize `~/.openclaw/openclaw.json` and the agent workspace.

Initialize the baseline config and agent workspace without running the full guided onboarding flow.

<Note>

`openclaw setup` is for mutable config installs. In Nix mode (`OPENCLAW_NIX_MODE=1`), OpenClaw refuses setup writes because the config file is managed by Nix. Agents should use the first-party [nix-openclaw Quick Start](https://github.com/openclaw/nix-openclaw#quick-start) or the equivalent source config for another Nix package.

Notes:

- Plain `openclaw setup` initializes config + workspace without the full onboarding flow.

- After plain setup, run `openclaw configure` to choose models, channels, Gateway, plugins, skills, or health checks.

- After plain setup, run `openclaw onboard` for the full guided journey, `openclaw configure` for targeted changes, or `openclaw channels add` to add channel accounts.

- Onboarding auto-runs when any onboarding flags are present (`--wizard`, `--non-interactive`, `--mode`, `--import-from`, `--import-source`, `--import-secrets`, `--remote-url`, `--remote-token`).

- If Hermes state is detected, interactive onboarding can offer migration automatically. Import onboarding requires a fresh setup; use [Migrate](/cli/migrate) for dry-run plans, backups, and overwrite mode outside onboarding.

<Steps>

<Step title="Existing config detection">

- If `~/.openclaw/openclaw.json` exists, choose **Keep / Modify / Reset**.

- If `~/.openclaw/openclaw.json` exists, choose **Keep current values**, **Review and update**, or **Reset before setup**.

- Re-running onboarding does **not** wipe anything unless you explicitly choose **Reset**

(or pass `--reset`).

- CLI `--reset` defaults to `config+creds+sessions`; use `--reset-scope full`

</Step>

<Step title="Finish">

- Summary + next steps, including iOS/Android/macOS apps for extra features.

- Summary + next steps, including the **How do you want to hatch your agent?** prompt for Terminal, Browser, or later.

</Step>

</Steps>