ACP Agents: Run External Coding Harnesses via ACP Backend

Agent Client Protocol (ACP) sessions let OpenClaw run external coding harnesses (Claude Code, Cursor, Copilot, Droid, OpenClaw ACP, OpenCode, Gemini CLI, and other supported ACPX harnesses) through an ACP backend plugin. Each spawn is tracked as a background task.

Note

ACP is the external-harness path, not the default Codex path. The native Codex app-server plugin owns /codex ... controls and the default openai/gpt-* embedded runtime for agent turns; ACP owns /acp ... controls and sessions_spawn({ runtime: "acp" }) sessions.

To let Codex or Claude Code connect as an external MCP client directly to existing OpenClaw channel conversations, use openclaw mcp serve instead of ACP.

Which page do I want?

Does this work out of the box?

Yes, after installing the official ACP runtime plugin:

openclaw plugins install @openclaw/acpx
openclaw config set plugins.entries.acpx.enabled true

Source checkouts can use the local extensions/acpx workspace plugin after pnpm install. Run /acp doctor for a readiness check.

OpenClaw only teaches agents about ACP spawning when ACP is truly usable: ACP must be enabled, dispatch must not be disabled, the current session must not be sandbox-blocked, and a runtime backend must be loaded and healthy. If any condition fails, ACP skills and sessions_spawn ACP guidance stay hidden so the agent does not suggest an unavailable backend.

First-run gotchas

• If plugins.allow is set, it is a restrictive plugin inventory and must include acpx, or the installed ACP backend is intentionally blocked (/acp doctor reports the missing allowlist entry).
• The Codex ACP adapter ships with the acpx plugin and launches locally when possible.
• Codex ACP runs with an isolated CODEX_HOME. OpenClaw copies trusted project trust entries plus safe model/provider routing config (model, model_provider, model_reasoning_effort, sandbox_mode, and safe model_providers.<name> fields) from the host Codex config; auth, notifications, and hooks stay on the host config only.
• Other target harness adapters may be fetched on demand with npx on first use.
• Vendor auth must already exist on the host for that harness.
• If the host has no npm or network access, first-run adapter fetches fail until caches are pre-warmed or the adapter is installed another way.

Runtime prerequisites

ACP launches a real external harness process. OpenClaw owns routing, background-task state, delivery, bindings, and policy; the harness owns its provider login, model catalog, filesystem behavior, and native tools.

Before blaming OpenClaw, verify:

• /acp doctor reports an enabled, healthy backend.
• The target id is allowed by acp.allowedAgents when that allowlist is set.
• The harness command can start on the Gateway host.
• Provider auth is present for that harness (claude, codex, gemini, opencode, droid, etc.).
• The selected model exists for that harness - model ids are not portable across harnesses.
• The requested cwd exists and is accessible, or omit cwd and let the backend use its default.
• Permission mode matches the work. Non-interactive sessions cannot click native permission prompts, so write/exec-heavy coding runs usually need an ACPX permission profile that can proceed headlessly.

OpenClaw plugin tools and built-in OpenClaw tools are not exposed to ACP harnesses by default. Enable the explicit MCP bridges in ACP agents - setup only when the harness should call those tools directly.

Supported harness targets

With the acpx backend, use these ids as /acp spawn <id> or sessions_spawn({ runtime: "acp", agentId: "<id>" }) targets:

pi (pi-acp) is also registered in the acpx backend but is not a coding harness in the same sense as the others above.

Custom acpx agent aliases can be configured in acpx itself, but OpenClaw policy still checks acp.allowedAgents and any agents.entries.*.runtime.acp.agent mapping before dispatch.

Operator runbook

Quick /acp flow from chat:

Spawn

/acp spawn claude --bind here, /acp spawn gemini --mode persistent --thread auto, or explicit /acp spawn codex --bind here.

Work

Continue in the bound conversation or thread (or target the session key explicitly).

Check state

/acp status

Tune

/acp model <provider/model>, /acp permissions <profile>, /acp timeout <seconds>.

Steer

Without replacing context: /acp steer tighten logging and continue.

Stop

/acp cancel (current turn) or /acp close (session + bindings).

Lifecycle details

• Spawn creates or resumes an ACP runtime session, records ACP metadata in the OpenClaw session store, and may create a background task when the run is parent-owned.
• Parent-owned ACP sessions are treated as background work even when the runtime session is persistent; completion and cross-surface delivery go through the parent task notifier rather than acting like a normal user-facing chat session.
• Task maintenance closes terminal or orphaned parent-owned one-shot ACP sessions. Persistent ACP sessions are preserved while an active conversation binding remains; stale persistent sessions without an active binding are closed so they cannot be silently resumed after the owning task is done or its task record is gone.
• Bound follow-up messages go directly to the ACP session until the binding is closed, unfocused, reset, or expired.
• Gateway commands stay local. /acp ..., /status, and /unfocus are never sent as normal prompt text to a bound ACP harness.
• cancel aborts the active turn when the backend supports cancellation; it does not delete the binding or session metadata.
• close ends the ACP session from OpenClaw's point of view and removes the binding. A harness may still keep its own upstream history if it supports resume.
• The acpx plugin cleans up OpenClaw-owned wrapper and adapter process trees after close, and reaps stale OpenClaw-owned ACPX orphans during Gateway startup.
• Idle runtime workers are eligible for cleanup after the built-in idle period; stored session metadata remains available for /acp sessions.

Native Codex routing rules

When the native Codex plugin is active, these natural language triggers should route to it:

• "Bind this Discord channel to Codex."
• "Attach this chat to Codex thread <id>."
• "Show Codex threads, then bind this one."

The default path for chat control is native Codex conversation binding. OpenClaw dynamic tools still run through OpenClaw, while Codex native tools like shell/apply-patch execute inside Codex. For Codex native tool events, OpenClaw injects a per turn native hook relay so plugin hooks can block before_tool_call, observe after_tool_call, and route Codex PermissionRequest events through OpenClaw approvals. Codex Stop hooks are relayed to OpenClaw before_agent_finalize, where plugins can request one more model pass before Codex finalizes its answer. The relay stays deliberately conservative: it does not mutate Codex native tool arguments or rewrite Codex thread records. Use explicit ACP only when you want the ACP runtime/session model. The embedded Codex support boundary is documented in the Codex harness v1 support contract.

Model / provider / runtime selection cheat sheet

• legacy Codex model refs - legacy Codex OAuth/subscription model route repaired by doctor.
• openai/* - native Codex app server embedded runtime for OpenAI agent turns.
• /codex ... - native Codex conversation control.
• /acp ... or runtime: "acp" - explicit ACP/acpx control.

ACP-routing natural-language triggers

These triggers should route to the ACP runtime:

• "Run this as a one-shot Claude Code ACP session and summarize the result."
• "Use Gemini CLI for this task in a thread, then keep follow-ups in that same thread."
• "Run Codex through ACP in a background thread."

OpenClaw picks runtime: "acp", resolves the harness agentId, binds to the current conversation or thread when supported, and routes follow-ups to that session until close/expiry. Codex only follows this path when ACP/acpx is explicit or the native Codex plugin is unavailable for the requested operation.

For sessions_spawn, runtime: "acp" is advertised only when ACP is enabled, the requester is not sandboxed, and an ACP runtime backend is loaded. acp.dispatch.enabled=false pauses automatic ACP thread dispatch but does not hide or block explicit sessions_spawn({ runtime: "acp" }) calls. It targets ACP harness ids such as codex, claude, droid, gemini, or opencode. Do not pass a normal OpenClaw config agent id from agents_list unless that entry is explicitly configured with agents.entries.*.runtime.type="acp"; otherwise use the default sub-agent runtime. When an OpenClaw agent is configured with runtime.type="acp", OpenClaw uses runtime.acp.agent as the underlying harness id.

ACP versus sub-agents

Use ACP when you want an external harness runtime. Use native Codex app-server for Codex conversation binding/control when the codex plugin is enabled. Use sub-agents when you want OpenClaw native delegated runs.

See also Sub-agents.

How ACP runs Claude Code

For Claude Code through ACP, the stack is:

1. OpenClaw ACP session control plane.
2. Official @openclaw/acpx runtime plugin.
3. Claude ACP adapter.
4. Claude side runtime/session machinery.

ACP Claude is a harness session with ACP controls, session resume, background task tracking, and optional conversation/thread binding.

CLI backends are separate text only local fallback runtimes - see CLI Backends.

For operators, the practical rule is:

• Want /acp spawn, bindable sessions, runtime controls, or persistent harness work? Use ACP.
• Want simple local text fallback through the raw CLI? Use CLI backends.

Bound sessions

Mental model

• Chat surface - where people keep talking (Discord channel, Telegram topic, iMessage chat).
• ACP session - the durable Codex/Claude/Gemini runtime state OpenClaw routes to.
• Child thread/topic - an optional extra messaging surface created only by --thread ....
• Runtime workspace - the filesystem location (cwd, repo checkout, backend workspace) where the harness runs. Independent of the chat surface.

Current-conversation binds

/acp spawn <harness> --bind here pins the current conversation to the spawned ACP session - no child thread, same chat surface. OpenClaw keeps owning transport, auth, safety, and delivery. Follow-up messages in that conversation route to the same session; /new and /reset reset the session in place; /acp close removes the binding.

Examples:

/codex bind                                              # native Codex bind, route future messages here
/codex model gpt-5.4                                     # tune the bound native Codex thread
/codex stop                                              # control the active native Codex turn
/acp spawn codex --bind here                             # explicit ACP fallback for Codex
/acp spawn codex --thread auto                           # may create a child thread/topic and bind there
/acp spawn codex --bind here --cwd /workspace/repo       # same chat binding, Codex runs in /workspace/repo

Binding rules and exclusivity

• --bind here and --thread ... are mutually exclusive.
• --bind here only works on channels that advertise current conversation binding; OpenClaw returns a clear unsupported message otherwise. Bindings persist across gateway restarts.
• On Discord, spawnSessions gates child thread creation for --thread auto|here - not --bind here.
• If you spawn to a different ACP agent without --cwd, OpenClaw inherits the target agent's workspace by default. Missing inherited paths (ENOENT/ENOTDIR) fall back to the backend default; other access errors (e.g. EACCES) surface as spawn errors.
• Gateway management commands stay local in bound conversations - /acp ... commands are handled by OpenClaw even when normal follow-up text routes to the bound ACP session; /status and /unfocus also stay local whenever command handling is enabled for that surface.

Thread-bound sessions

When thread bindings are enabled for a channel adapter:

• OpenClaw binds a thread to a target ACP session.
• Follow-up messages in that thread route to the bound ACP session.
• ACP output is delivered back to the same thread.
• Unfocus/close/archive/idle-timeout or max-age expiry removes the binding.
• /acp close, /acp cancel, /acp status, /status, and /unfocus are Gateway commands, not prompts to the ACP harness.

Required feature flags for thread bound ACP:

• acp.enabled=true
• acp.dispatch.enabled is on by default (set false to pause automatic ACP thread dispatch; explicit sessions_spawn({ runtime: "acp" }) calls still work).
• Channel adapter thread session spawns enabled (default: true):
  • Discord/Telegram: session.threadBindings.spawnSessions=true

Thread binding support is adapter specific. If the active channel adapter does not support thread bindings, OpenClaw returns a clear unsupported/unavailable message.

Thread-supporting channels

• Any channel adapter that exposes session/thread binding capability.
• Current built-in support: Discord threads/channels, Telegram topics (forum topics in groups/supergroups and DM topics).
• Plugin channels can add support through the same binding interface.

Persistent channel bindings

For non ephemeral workflows, configure persistent ACP bindings in top-level bindings[] entries.

Binding model

• bindings[].type (acp), Marks a persistent ACP conversation binding.

• bindings[].match (object), Identifies the target conversation. Per channel shapes: - Discord channel/thread: match.channel="discord" + match.peer.id="<channelOrThreadId>" - Slack channel/DM: match.channel="slack" + match.peer.id="<channelId|channel:<channelId>|#<channelId>|userId|user:<userId>|slack:<userId>|<@userId>>". Prefer stable Slack ids; channel bindings also match replies inside that channel's threads. - Telegram forum topic: match.channel="telegram" + match.peer.id="<chatId>:topic:<topicId>" - WhatsApp DM/group: match.channel="whatsapp" + match.peer.id="<E.164|group JID>". Use E.164 numbers such as +15555550123 for direct chats and WhatsApp group JIDs such as 120363424282127706@g.us for groups. - iMessage DM/group: match.channel="imessage" + match.peer.id="<handle|chat_id:*|chat_guid:*|chat_identifier:*>". Prefer chat_id:* for stable group bindings.

• bindings[].agentId (string), The owning OpenClaw agent id.

• bindings[].acp.mode (persistent" | "oneshot), Optional ACP override.

• bindings[].acp.label (string), Optional operator facing label.

• bindings[].acp.cwd (string), Optional runtime working directory.

• bindings[].acp.backend (string), Optional backend override.

Runtime defaults per agent

Use agents.entries.*.runtime to define ACP defaults once per agent:

• agents.entries.*.runtime.type="acp"
• agents.entries.*.runtime.acp.agent (harness id, e.g. codex or claude)
• agents.entries.*.runtime.acp.backend
• agents.entries.*.runtime.acp.mode
• agents.entries.*.runtime.acp.cwd

Override precedence for ACP bound sessions:

1. bindings[].acp.*
2. agents.entries.*.runtime.acp.*
3. Global ACP defaults (e.g. acp.backend)

Example

{
  agents: {
    list: [
      {
        id: "codex",
        runtime: {
          type: "acp",
          acp: {
            agent: "codex",
            backend: "acpx",
            mode: "persistent",
            cwd: "/workspace/openclaw",
          },
        },
      },
      {
        id: "claude",
        runtime: {
          type: "acp",
          acp: { agent: "claude", backend: "acpx", mode: "persistent" },
        },
      },
    ],
  },
  bindings: [
    {
      type: "acp",
      agentId: "codex",
      match: {
        channel: "discord",
        accountId: "default",
        peer: { kind: "channel", id: "222222222222222222" },
      },
      acp: { label: "codex-main" },
    },
    {
      type: "acp",
      agentId: "claude",
      match: {
        channel: "telegram",
        accountId: "default",
        peer: { kind: "group", id: "-1001234567890:topic:42" },
      },
      acp: { cwd: "/workspace/repo-b" },
    },
    {
      type: "route",
      agentId: "main",
      match: { channel: "discord", accountId: "default" },
    },
    {
      type: "route",
      agentId: "main",
      match: { channel: "telegram", accountId: "default" },
    },
  ],
  channels: {
    discord: {
      guilds: {
        "111111111111111111": {
          channels: {
            "222222222222222222": { requireMention: false },
          },
        },
      },
    },
    telegram: {
      groups: {
        "-1001234567890": {
          topics: { "42": { requireMention: false } },
        },
      },
    },
  },
}

Behavior

• OpenClaw ensures the configured ACP session exists after channel specific admission and before use.
• Messages in that channel, topic, or chat route to the configured ACP session.
• Configured ACP bindings own their session route. Channel broadcast fan-out does not replace the configured ACP session for a matched binding.
• In bound conversations, /new and /reset reset the same ACP session key in place.
• Temporary runtime bindings (for example created by thread focus flows) still apply where present.
• For cross agent ACP spawns without an explicit cwd, OpenClaw inherits the target agent workspace from agent config.
• Missing inherited workspace paths fall back to the backend default cwd; non missing access failures surface as spawn errors.

Start ACP sessions

Two methods exist for launching an ACP session:

From sessions_spawn

Use runtime: "acp" to launch an ACP session from an agent turn or tool call.

{
  "task": "Open the repo and summarize failing tests",
  "runtime": "acp",
  "agentId": "codex",
  "thread": true,
  "mode": "session"
}

Note

runtime defaults to subagent, so set runtime: "acp" explicitly for ACP sessions. If agentId is omitted, OpenClaw uses acp.defaultAgent when configured. mode: "session" requires thread: true to keep a persistent bound conversation.

From /acp command

Use /acp spawn for direct operator control from chat.

/acp spawn codex --mode persistent --thread auto
/acp spawn codex --mode oneshot --thread off
/acp spawn codex --bind here
/acp spawn codex --thread here

Key flags:

• --mode persistent|oneshot
• --bind here|off
• --thread auto|here|off
• --cwd <absolute-path>
• --label <name>

See Slash commands.

sessions_spawn parameters

• task (string, required), The initial prompt sent to the ACP session.

• runtime (acp, required), Must be "acp" for ACP sessions.

• agentId (string), ACP target harness id. Falls back to acp.defaultAgent if set.

• thread (boolean, default: false), Request thread binding flow where supported.

• mode (run" | "session, default: run), "run" is one-shot; "session" is persistent. If thread: true and mode is omitted, OpenClaw may default to persistent behaviour per runtime path. mode: "session" requires thread: true.

• cwd (string), Requested runtime working directory (validated by backend/runtime policy). If omitted, ACP spawn inherits the target agent workspace when configured; missing inherited paths fall back to backend defaults, while real access errors are returned.

• label (string), Operator-facing label used in session/banner text.

• resumeSessionId (string), Resume an existing ACP session instead of creating a new one. The agent replays its conversation history via session/load. Requires runtime: "acp".

• streamTo (parent), "parent" streams initial ACP run progress summaries back to the requester session as system events. OpenClaw records the full relay history in the child agent's SQLite state and removes it with the child session. Parent progress streams show assistant commentary and ACP status progress by default unless streaming.progress.commentary=false. Discord also defaults parent previews to progress mode when no stream mode is configured. Status progress still honors acp.stream.tagVisibility, so tags such as plan remain hidden unless explicitly enabled.

ACP sessions_spawn runs use agents.defaults.subagents.runTimeoutSeconds for their default child turn limit. The tool does not accept per-call timeout overrides (runTimeoutSeconds/timeoutSeconds are rejected with a config-the-default error).

• model (string), Explicit model override for the ACP child session. Codex ACP spawns normalize OpenAI refs such as openai/gpt-5.4 to Codex ACP startup config before session/new; slash forms such as openai/gpt-5.4/high also set Codex ACP reasoning effort. When omitted, sessions_spawn({ runtime: "acp" }) uses existing subagent model defaults (agents.defaults.subagents.model or agents.entries.*.subagents.model) when configured; otherwise it lets the ACP harness use its own default model. Other harnesses must advertise ACP models and support session/set_model; otherwise OpenClaw/acpx fails clearly instead of silently falling back to the target agent default.

• thinking (string), Explicit thinking/reasoning effort. For Codex ACP, minimal maps to low effort, low/medium/high/xhigh map directly, and off omits the reasoning-effort startup override. When omitted, ACP spawns use existing subagent thinking defaults and per-model agents.defaults.models["provider/model"].params.thinking for the selected model.

Spawn bind and thread modes

--bind here|off

Notes:

• --bind here is the simplest operator path for "make this channel or chat Codex-backed."
• --bind here does not create a child thread.
• --bind here is only available on channels that expose current-conversation binding support.
• --bind and --thread cannot be combined in the same /acp spawn call.

--thread auto|here|off

Notes:

• On non-thread binding surfaces, default behavior is effectively off.
• Thread-bound spawn requires channel policy support:
  • Discord/Telegram: session.threadBindings.spawnSessions=true
• Use --bind here when you want to pin the current conversation without creating a child thread.

Delivery model

ACP sessions can be either interactive workspaces or parent-owned background work. The delivery path depends on that shape.

Interactive ACP sessions

Interactive sessions are meant to keep talking on a visible chat surface:

• /acp spawn ... --bind here binds the current conversation to the ACP session.
• /acp spawn ... --thread ... binds a channel thread/topic to the ACP session.
• Persistent configured bindings[].type="acp" route matching conversations to the same ACP session.

Follow-up messages in the bound conversation route directly to the ACP session, and ACP output is delivered back to that same channel/thread/topic.

What OpenClaw sends to the harness:

• Normal bound follow-ups are sent as prompt text, plus attachments only when the harness/backend supports them.
• /acp management commands and local Gateway commands are intercepted before ACP dispatch.
• Runtime-generated completion events are materialized per target. OpenClaw agents get OpenClaw's internal runtime-context envelope; external ACP harnesses get a plain prompt with the child result and instruction. The raw <<<BEGIN_OPENCLAW_INTERNAL_CONTEXT>>> envelope should never be sent to external harnesses or persisted as ACP user transcript text.
• ACP transcript entries use the user-visible trigger text or the plain completion prompt. Internal event metadata stays structured in OpenClaw where possible and is not treated as user-authored chat content.

Parent-owned one-shot ACP sessions

One-shot ACP sessions spawned by another agent run are background children, similar to sub-agents:

• The parent asks for work with sessions_spawn({ runtime: "acp", mode: "run" }).
• The child runs in its own ACP harness session.
• Child turns run on the same background lane used by native sub-agent spawns, so a slow ACP harness does not block unrelated main-session work.
• Completion reports back through the task-completion announce path. OpenClaw converts internal completion metadata into a plain ACP prompt before sending it to an external harness, so harnesses do not see OpenClaw-only runtime context markers.
• The parent rewrites the child result in normal assistant voice when a user-facing reply is useful.

Do not treat this path as a peer-to-peer chat between parent and child. The child already has a completion channel back to the parent.

sessions_send and A2A delivery

sessions_send can target another session after spawn. For normal peer sessions, OpenClaw uses an agent-to-agent (A2A) follow-up path after injecting the message:

• Wait for the target session's reply.
• Optionally let requester and target exchange a bounded number of follow-up turns.
• Ask the target to produce an announce message.
• Deliver that announce to the visible channel or thread.

That A2A path is a fallback for peer sends where the sender needs a visible follow-up. It stays enabled when an unrelated session can see and message an ACP target, for example under broad tools.sessions.visibility settings.

OpenClaw skips the A2A follow-up only when the requester is the parent of its own parent-owned one-shot ACP child. In that case, running A2A on top of task completion can wake the parent with the child's result, forward the parent's reply back into the child, and create a parent/child echo loop. The sessions_send result reports delivery.status="skipped" for that owned-child case because the completion path is already responsible for the result.

Resume an existing session

Use resumeSessionId to continue a previous ACP session instead of starting fresh. The agent replays its conversation history via session/load, so it picks up with full context of what came before.

{
  "task": "Continue where we left off - fix the remaining test failures",
  "runtime": "acp",
  "agentId": "codex",
  "resumeSessionId": "<previous-session-id>"
}

Common use cases:

• Hand off a Codex session from your laptop to your phone - tell your agent to pick up where you left off.
• Continue a coding session you started interactively in the CLI, now headlessly through your agent.
• Pick up work that was interrupted by a gateway restart or idle timeout.

Notes:

• resumeSessionId only takes effect when runtime: "acp" is set; the default sub-agent runtime ignores this ACP-only field.
• streamTo only applies when runtime: "acp" is active; the default sub-agent runtime ignores this ACP-only field.
• resumeSessionId is a host-local ACP/harness resume identifier, not an OpenClaw channel session key. OpenClaw still checks ACP spawn policy and target agent policy before dispatching, while the ACP backend or harness handles authorization for loading that upstream id.
• resumeSessionId restores the upstream ACP conversation history. thread and mode still apply normally to the new OpenClaw session you are creating, so mode: "session" still requires thread: true.
• The target agent must support session/load (Codex and Claude Code do).
• If the session id is not found, the spawn fails with a clear error. There is no silent fallback to a new session.

Post-deploy smoke test

After deploying a gateway, run a live end-to-end check instead of relying on unit tests:

1. Confirm the deployed gateway version and commit on the target host.
2. Open a temporary ACPX bridge session to a live agent.
3. Ask that agent to call sessions_spawn with runtime: "acp", agentId: "codex", mode: "run", and task Reply with exactly LIVE-ACP-SPAWN-OK.
4. Verify accepted=yes, a real childSessionKey, and no validator error.
5. Tear down the temporary bridge session.

Keep the gate on mode: "run" and skip streamTo: "parent". Thread-bound mode: "session" and stream-relay paths are separate, more thorough integration passes.

Sandbox compatibility

ACP sessions currently run on the host runtime, not inside the OpenClaw sandbox.

Warning

Security boundary:

• The external harness can read and write according to its own CLI permissions and the selected cwd.
• OpenClaw's sandbox policy does not wrap ACP harness execution.
• OpenClaw still enforces ACP feature gates, allowed agents, session ownership, channel bindings, and Gateway delivery policy.
• Use runtime: "subagent" for sandbox-enforced OpenClaw-native work.

Current limitations:

• If the requester session is sandboxed, ACP spawns are blocked for both sessions_spawn({ runtime: "acp" }) and /acp spawn.
• sessions_spawn with runtime: "acp" does not support sandbox: "require".

Session target resolution

Most /acp actions accept an optional session target (session-key, session-id, or session-label).

Resolution order:

1. Explicit target argument (or --session for /acp steer)
   • tries key
   • then UUID-shaped session id
   • then label
2. Current thread binding (if this conversation or thread is bound to an ACP session).
3. Current requester session fallback.

Current-conversation bindings and thread bindings both participate in step 2.

If no target resolves, OpenClaw returns a clear error (Unable to resolve session target: ...).

ACP controls

Runtime controls (spawn, cancel, steer, close, status, set-mode, set, cwd, permissions, timeout, model, and reset-options) require owner identity from external channels and operator.admin from internal Gateway clients. Authorized non-owner senders can still use sessions, doctor, install, and help. For non-owner senders, /acp sessions lists only the current bound or requester session. Owner identity and operator.admin clients see all recent sessions.

/acp status shows the effective runtime options plus runtime-level and backend-level session identifiers. Unsupported-control errors surface clearly when a backend lacks a capability. Commands that accept target tokens (session-key, session-id, or session-label) resolve them through gateway session discovery, including custom per-agent session.store roots. /acp sessions does not accept a target token.

Runtime options mapping

/acp has convenience commands and a generic setter. Equivalent operations:

acpx harness, plugin setup, and permissions

For acpx harness configuration (Claude Code, Codex, Gemini CLI aliases), the plugin-tools and OpenClaw-tools MCP bridges, and ACP permission modes, see ACP agents - setup.

Troubleshooting

Note

Command blocked by PreToolUse hook: Native hook relay unavailable is part of the native Codex hook relay, not ACP or acpx. In a bound Codex chat, begin a new session with /new or /reset. If it works once and then fails on the next native tool call, restart the Codex app-server or OpenClaw Gateway rather than repeating /new. Refer to Codex harness troubleshooting.

Related

• ACP agents - setup
• Agent send
• CLI Backends
• Codex harness
• Codex harness runtime
• Multi-agent sandbox tools
• openclaw acp (bridge mode)
• Sub-agents