OpenClaw can talk to you on any chat app you already use. Each channel connects via the Gateway.

Text is supported everywhere; media and reactions vary by channel.

## Delivery notes

- Telegram replies that contain markdown image syntax, such as ``,

are converted into media replies on the final outbound path when possible.

- Slack multi-person DMs route as group chats, so group policy, mention

behavior, and group-session rules apply to MPIM conversations.

- WhatsApp setup is install-on-demand: onboarding can show the setup flow before

Baileys runtime dependencies are staged, and the Gateway loads the WhatsApp

runtime only when the channel is actually active.

## Supported channels

- [BlueBubbles](/channels/bluebubbles) — **Recommended for iMessage**; uses the BlueBubbles macOS server REST API with full feature support (bundled plugin; edit, unsend, effects, reactions, group management — edit currently broken on macOS 26 Tahoe).

The owner-only `gateway` runtime tool still refuses to rewrite

`tools.exec.ask` or `tools.exec.security`; legacy `tools.bash.*` aliases are

normalized to the same protected exec paths before the write.

Agent-driven `gateway config.apply` and `gateway config.patch` edits are

fail-closed by default: only a narrow set of prompt, model, and mention-gating

paths are agent-tunable. New sensitive config trees are therefore protected

unless they are deliberately added to the allowlist.

For any agent/surface that handles untrusted content, deny these by default:

paths, set `OPENCLAW_ALLOW_INSECURE_PRIVATE_WS=1` on the client process as

break-glass. This is intentionally process environment only, not an

`openclaw.json` config key.

Mobile pairing and Android manual or scanned gateway routes are stricter:

cleartext is accepted for loopback, but private-LAN, link-local, `.local`, and

dotless hostnames must use TLS unless you explicitly opt into the trusted

private-network cleartext path.

Local device pairing:

If `OPENCLAW_PLUGIN_STAGE_DIR` is not set, OpenClaw uses `$STATE_DIRECTORY` when

systemd provides it, then falls back to `~/.openclaw/plugin-runtime-deps`.

### Bundled plugin runtime dependencies

Packaged installs keep bundled plugin runtime dependencies out of the read-only

package tree. On startup and during `openclaw doctor --fix`, OpenClaw repairs

runtime dependencies only for bundled plugins that are active in config, active

through legacy channel config, or enabled by their bundled manifest default.

Explicit disablement wins. A disabled plugin or channel does not get its

runtime dependencies repaired just because it exists in the package. External

plugins and custom load paths still use `openclaw plugins install` or

`openclaw plugins update`.

## Auto-updater

The auto-updater is off by default. Enable it in `~/.openclaw/openclaw.json`:

OpenAI explicitly supports subscription OAuth usage in external tools and workflows like OpenClaw.

## Quick choice

| Goal | Use | Notes |

| --------------------------------------------- | -------------------------------------------------------- | ---------------------------------------------------------------------------- |

| Direct API-key billing | `openai/gpt-5.4` | Set `OPENAI_API_KEY` or run OpenAI API-key onboarding. |

| GPT-5.5 with ChatGPT/Codex subscription auth | `openai-codex/gpt-5.5` | Default PI route for Codex OAuth. Best first choice for subscription setups. |

| GPT-5.5 with native Codex app-server behavior | `openai/gpt-5.5` plus `embeddedHarness.runtime: "codex"` | Uses the Codex app-server harness, not the public OpenAI API route. |

| Image generation or editing | `openai/gpt-image-2` | Works with either `OPENAI_API_KEY` or OpenAI Codex OAuth. |

<Note>

GPT-5.5 is currently available in OpenClaw through subscription/OAuth routes:

`openai-codex/gpt-5.5` with the PI runner, or `openai/gpt-5.5` with the

Use `contextWindow` to declare native model metadata. Use `contextTokens` to limit the runtime context budget.

</Note>

### Catalog recovery

OpenClaw uses upstream Codex catalog metadata for `gpt-5.5` when it is

present. If live Codex discovery omits the `openai-codex/gpt-5.5` row while

the account is authenticated, OpenClaw synthesizes that OAuth model row so

cron, sub-agent, and configured default-model runs do not fail with

`Unknown model`.

</Tab>

</Tabs>

The agent calls `image_generate` automatically. No tool allow-listing needed — it's enabled by default when a provider is available.

## Common routes

| Goal | Model ref | Auth |

| ---------------------------------------------------- | -------------------------------------------------- | ------------------------------------ |

| OpenAI image generation with API billing | `openai/gpt-image-2` | `OPENAI_API_KEY` |

| OpenAI image generation with Codex subscription auth | `openai/gpt-image-2` | OpenAI Codex OAuth |

| OpenRouter image generation | `openrouter/google/gemini-3.1-flash-image-preview` | `OPENROUTER_API_KEY` |

| Google Gemini image generation | `google/gemini-3.1-flash-image-preview` | `GEMINI_API_KEY` or `GOOGLE_API_KEY` |

The same `image_generate` tool handles text-to-image and reference-image

editing. Use `image` for one reference or `images` for multiple references.

Provider-supported output hints such as `quality`, `outputFormat`, and

OpenAI-specific `background` are forwarded when available and reported as

ignored when a provider does not support them.

## Supported providers

| Provider | Default model | Edit support | Auth |

overrides. When a child genuinely needs the requester's current transcript, the agent can request

`context: "fork"` on that one spawn.

## Context modes

Native sub-agents start isolated unless the caller explicitly asks to fork the

current transcript.

| Mode | When to use it | Behavior |

| ---------- | -------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------- |

| `isolated` | Fresh research, independent implementation, slow tool work, or anything that can be briefed in the task text | Creates a clean child transcript. This is the default and keeps token use lower. |

| `fork` | Work that depends on the current conversation, prior tool results, or nuanced instructions already present in the requester transcript | Branches the requester transcript into the child session before the child starts. |

Use `fork` sparingly. It is for context-sensitive delegation, not a replacement

for writing a clear task prompt.

## Tool

Use `sessions_spawn`: