diff --git a/docs/tools/multi-agent-sandbox-tools.md b/docs/tools/multi-agent-sandbox-tools.md index a3711ed327e..48a6807854f 100644 --- a/docs/tools/multi-agent-sandbox-tools.md +++ b/docs/tools/multi-agent-sandbox-tools.md @@ -1,177 +1,176 @@ --- -summary: “Per-agent sandbox + tool restrictions, precedence, and examples” -title: Multi-agent sandbox & tools -read_when: “You want per-agent sandboxing or per-agent tool allow/deny policies in a multi-agent gateway.” +summary: "Per-agent sandbox + tool restrictions, precedence, and examples" +title: "Multi-agent sandbox and tools" +sidebarTitle: "Multi-agent sandbox and tools" +read_when: "You want per-agent sandboxing or per-agent tool allow/deny policies in a multi-agent gateway." status: active --- -# Multi-Agent Sandbox & Tools Configuration +Each agent in a multi-agent setup can override the global sandbox and tool policy. This page covers per-agent configuration, precedence rules, and examples. -Each agent in a multi-agent setup can override the global sandbox and tool -policy. This page covers per-agent configuration, precedence rules, and -examples. + + + Backends and modes — full sandbox reference. + + + Debug "why is this blocked?" + + + Elevated exec for trusted senders. + + -- **Sandbox backends and modes**: see [Sandboxing](/gateway/sandboxing). -- **Debugging blocked tools**: see [Sandbox vs Tool Policy vs Elevated](/gateway/sandbox-vs-tool-policy-vs-elevated) and `openclaw sandbox explain`. -- **Elevated exec**: see [Elevated Mode](/tools/elevated). - -Auth is per-agent: each agent reads from its own `agentDir` auth store at -`~/.openclaw/agents//agent/auth-profiles.json`. -Credentials are **not** shared between agents. Never reuse `agentDir` across agents. -If you want to share creds, copy `auth-profiles.json` into the other agent's `agentDir`. + +Auth is per-agent: each agent reads from its own `agentDir` auth store at `~/.openclaw/agents//agent/auth-profiles.json`. Credentials are **not** shared between agents. Never reuse `agentDir` across agents. If you want to share creds, copy `auth-profiles.json` into the other agent's `agentDir`. + --- -## Configuration Examples +## Configuration examples -### Example 1: Personal + Restricted Family Agent - -```json -{ - "agents": { - "list": [ - { - "id": "main", - "default": true, - "name": "Personal Assistant", - "workspace": "~/.openclaw/workspace", - "sandbox": { "mode": "off" } - }, - { - "id": "family", - "name": "Family Bot", - "workspace": "~/.openclaw/workspace-family", - "sandbox": { - "mode": "all", - "scope": "agent" - }, - "tools": { - "allow": ["read"], - "deny": ["exec", "write", "edit", "apply_patch", "process", "browser"] - } - } - ] - }, - "bindings": [ + + + ```json { - "agentId": "family", - "match": { - "provider": "whatsapp", - "accountId": "*", - "peer": { - "kind": "group", - "id": "120363424282127706@g.us" + "agents": { + "list": [ + { + "id": "main", + "default": true, + "name": "Personal Assistant", + "workspace": "~/.openclaw/workspace", + "sandbox": { "mode": "off" } + }, + { + "id": "family", + "name": "Family Bot", + "workspace": "~/.openclaw/workspace-family", + "sandbox": { + "mode": "all", + "scope": "agent" + }, + "tools": { + "allow": ["read"], + "deny": ["exec", "write", "edit", "apply_patch", "process", "browser"] + } + } + ] + }, + "bindings": [ + { + "agentId": "family", + "match": { + "provider": "whatsapp", + "accountId": "*", + "peer": { + "kind": "group", + "id": "120363424282127706@g.us" + } + } } + ] + } + ``` + + **Result:** + + - `main` agent: runs on host, full tool access. + - `family` agent: runs in Docker (one container per agent), only `read` tool. + + + + ```json + { + "agents": { + "list": [ + { + "id": "personal", + "workspace": "~/.openclaw/workspace-personal", + "sandbox": { "mode": "off" } + }, + { + "id": "work", + "workspace": "~/.openclaw/workspace-work", + "sandbox": { + "mode": "all", + "scope": "shared", + "workspaceRoot": "/tmp/work-sandboxes" + }, + "tools": { + "allow": ["read", "write", "apply_patch", "exec"], + "deny": ["browser", "gateway", "discord"] + } + } + ] } } - ] -} -``` + ``` + + + ```json + { + "tools": { "profile": "coding" }, + "agents": { + "list": [ + { + "id": "support", + "tools": { "profile": "messaging", "allow": ["slack"] } + } + ] + } + } + ``` -**Result:** + **Result:** -- `main` agent: Runs on host, full tool access -- `family` agent: Runs in Docker (one container per agent), only `read` tool + - default agents get coding tools. + - `support` agent is messaging-only (+ Slack tool). ---- - -### Example 2: Work Agent with Shared Sandbox - -```json -{ - "agents": { - "list": [ - { - "id": "personal", - "workspace": "~/.openclaw/workspace-personal", - "sandbox": { "mode": "off" } - }, - { - "id": "work", - "workspace": "~/.openclaw/workspace-work", - "sandbox": { - "mode": "all", - "scope": "shared", - "workspaceRoot": "/tmp/work-sandboxes" + + + ```json + { + "agents": { + "defaults": { + "sandbox": { + "mode": "non-main", + "scope": "session" + } }, - "tools": { - "allow": ["read", "write", "apply_patch", "exec"], - "deny": ["browser", "gateway", "discord"] - } + "list": [ + { + "id": "main", + "workspace": "~/.openclaw/workspace", + "sandbox": { + "mode": "off" + } + }, + { + "id": "public", + "workspace": "~/.openclaw/workspace-public", + "sandbox": { + "mode": "all", + "scope": "agent" + }, + "tools": { + "allow": ["read"], + "deny": ["exec", "write", "edit", "apply_patch"] + } + } + ] } - ] - } -} -``` + } + ``` + + --- -### Example 2b: Global coding profile + messaging-only agent - -```json -{ - "tools": { "profile": "coding" }, - "agents": { - "list": [ - { - "id": "support", - "tools": { "profile": "messaging", "allow": ["slack"] } - } - ] - } -} -``` - -**Result:** - -- default agents get coding tools -- `support` agent is messaging-only (+ Slack tool) - ---- - -### Example 3: Different Sandbox Modes per Agent - -```json -{ - "agents": { - "defaults": { - "sandbox": { - "mode": "non-main", // Global default - "scope": "session" - } - }, - "list": [ - { - "id": "main", - "workspace": "~/.openclaw/workspace", - "sandbox": { - "mode": "off" // Override: main never sandboxed - } - }, - { - "id": "public", - "workspace": "~/.openclaw/workspace-public", - "sandbox": { - "mode": "all", // Override: public always sandboxed - "scope": "agent" - }, - "tools": { - "allow": ["read"], - "deny": ["exec", "write", "edit", "apply_patch"] - } - } - ] - } -} -``` - ---- - -## Configuration Precedence +## Configuration precedence When both global (`agents.defaults.*`) and agent-specific (`agents.list[].*`) configs exist: -### Sandbox Config +### Sandbox config Agent-specific settings override global: @@ -185,139 +184,154 @@ agents.list[].sandbox.browser.* > agents.defaults.sandbox.browser.* agents.list[].sandbox.prune.* > agents.defaults.sandbox.prune.* ``` -**Notes:** + +`agents.list[].sandbox.{docker,browser,prune}.*` overrides `agents.defaults.sandbox.{docker,browser,prune}.*` for that agent (ignored when sandbox scope resolves to `"shared"`). + -- `agents.list[].sandbox.{docker,browser,prune}.*` overrides `agents.defaults.sandbox.{docker,browser,prune}.*` for that agent (ignored when sandbox scope resolves to `"shared"`). - -### Tool Restrictions +### Tool restrictions The filtering order is: -1. **Tool profile** (`tools.profile` or `agents.list[].tools.profile`) -2. **Provider tool profile** (`tools.byProvider[provider].profile` or `agents.list[].tools.byProvider[provider].profile`) -3. **Global tool policy** (`tools.allow` / `tools.deny`) -4. **Provider tool policy** (`tools.byProvider[provider].allow/deny`) -5. **Agent-specific tool policy** (`agents.list[].tools.allow/deny`) -6. **Agent provider policy** (`agents.list[].tools.byProvider[provider].allow/deny`) -7. **Sandbox tool policy** (`tools.sandbox.tools` or `agents.list[].tools.sandbox.tools`) -8. **Subagent tool policy** (`tools.subagents.tools`, if applicable) + + + `tools.profile` or `agents.list[].tools.profile`. + + + `tools.byProvider[provider].profile` or `agents.list[].tools.byProvider[provider].profile`. + + + `tools.allow` / `tools.deny`. + + + `tools.byProvider[provider].allow/deny`. + + + `agents.list[].tools.allow/deny`. + + + `agents.list[].tools.byProvider[provider].allow/deny`. + + + `tools.sandbox.tools` or `agents.list[].tools.sandbox.tools`. + + + `tools.subagents.tools`, if applicable. + + -Each level can further restrict tools, but cannot grant back denied tools from earlier levels. -If `agents.list[].tools.sandbox.tools` is set, it replaces `tools.sandbox.tools` for that agent. -If `agents.list[].tools.profile` is set, it overrides `tools.profile` for that agent. -Provider tool keys accept either `provider` (e.g. `google-antigravity`) or `provider/model` (e.g. `openai/gpt-5.4`). - -If any explicit allowlist in that chain leaves the run with no callable tools, -OpenClaw stops before submitting the prompt to the model. This is intentional: -an agent configured with a missing tool such as -`agents.list[].tools.allow: ["query_db"]` should fail loudly until the plugin -that registers `query_db` is enabled, not continue as a text-only agent. + + + - Each level can further restrict tools, but cannot grant back denied tools from earlier levels. + - If `agents.list[].tools.sandbox.tools` is set, it replaces `tools.sandbox.tools` for that agent. + - If `agents.list[].tools.profile` is set, it overrides `tools.profile` for that agent. + - Provider tool keys accept either `provider` (e.g. `google-antigravity`) or `provider/model` (e.g. `openai/gpt-5.4`). + + + If any explicit allowlist in that chain leaves the run with no callable tools, OpenClaw stops before submitting the prompt to the model. This is intentional: an agent configured with a missing tool such as `agents.list[].tools.allow: ["query_db"]` should fail loudly until the plugin that registers `query_db` is enabled, not continue as a text-only agent. + + Tool policies support `group:*` shorthands that expand to multiple tools. See [Tool groups](/gateway/sandbox-vs-tool-policy-vs-elevated#tool-groups-shorthands) for the full list. -Per-agent elevated overrides (`agents.list[].tools.elevated`) can further restrict elevated exec for specific agents. See [Elevated Mode](/tools/elevated) for details. +Per-agent elevated overrides (`agents.list[].tools.elevated`) can further restrict elevated exec for specific agents. See [Elevated mode](/tools/elevated) for details. --- -## Migration from Single Agent +## Migration from single agent -**Before (single agent):** - -```json -{ - "agents": { - "defaults": { - "workspace": "~/.openclaw/workspace", - "sandbox": { - "mode": "non-main" - } - } - }, - "tools": { - "sandbox": { + + + ```json + { + "agents": { + "defaults": { + "workspace": "~/.openclaw/workspace", + "sandbox": { + "mode": "non-main" + } + } + }, "tools": { - "allow": ["read", "write", "apply_patch", "exec"], - "deny": [] + "sandbox": { + "tools": { + "allow": ["read", "write", "apply_patch", "exec"], + "deny": [] + } + } } } - } -} -``` - -**After (multi-agent with different profiles):** - -```json -{ - "agents": { - "list": [ - { - "id": "main", - "default": true, - "workspace": "~/.openclaw/workspace", - "sandbox": { "mode": "off" } + ``` + + + ```json + { + "agents": { + "list": [ + { + "id": "main", + "default": true, + "workspace": "~/.openclaw/workspace", + "sandbox": { "mode": "off" } + } + ] } - ] - } -} -``` + } + ``` + + + Legacy `agent.*` configs are migrated by `openclaw doctor`; prefer `agents.defaults` + `agents.list` going forward. + --- -## Tool Restriction Examples +## Tool restriction examples -### Read-only Agent + + + ```json + { + "tools": { + "allow": ["read"], + "deny": ["exec", "write", "edit", "apply_patch", "process"] + } + } + ``` + + + ```json + { + "tools": { + "allow": ["read", "exec", "process"], + "deny": ["write", "edit", "apply_patch", "browser", "gateway"] + } + } + ``` + + + ```json + { + "tools": { + "sessions": { "visibility": "tree" }, + "allow": ["sessions_list", "sessions_send", "sessions_history", "session_status"], + "deny": ["exec", "write", "edit", "apply_patch", "read", "browser"] + } + } + ``` -```json -{ - "tools": { - "allow": ["read"], - "deny": ["exec", "write", "edit", "apply_patch", "process"] - } -} -``` + `sessions_history` in this profile still returns a bounded, sanitized recall view rather than a raw transcript dump. Assistant recall strips thinking tags, `` scaffolding, plain-text tool-call XML payloads (including `...`, `...`, `...`, `...`, and truncated tool-call blocks), downgraded tool-call scaffolding, leaked ASCII/full-width model control tokens, and malformed MiniMax tool-call XML before redaction/truncation. -### Safe Execution Agent (no file modifications) - -```json -{ - "tools": { - "allow": ["read", "exec", "process"], - "deny": ["write", "edit", "apply_patch", "browser", "gateway"] - } -} -``` - -### Communication-only Agent - -```json -{ - "tools": { - "sessions": { "visibility": "tree" }, - "allow": ["sessions_list", "sessions_send", "sessions_history", "session_status"], - "deny": ["exec", "write", "edit", "apply_patch", "read", "browser"] - } -} -``` - -`sessions_history` in this profile still returns a bounded, sanitized recall -view rather than a raw transcript dump. Assistant recall strips thinking tags, -`` scaffolding, plain-text tool-call XML payloads -(including `...`, -`...`, `...`, -`...`, and truncated tool-call blocks), -downgraded tool-call scaffolding, leaked ASCII/full-width model control -tokens, and malformed MiniMax tool-call XML before redaction/truncation. + + --- -## Common Pitfall: "non-main" +## Common pitfall: "non-main" -`agents.defaults.sandbox.mode: "non-main"` is based on `session.mainKey` (default `"main"`), -not the agent id. Group/channel sessions always get their own keys, so they -are treated as non-main and will be sandboxed. If you want an agent to never -sandbox, set `agents.list[].sandbox.mode: "off"`. + +`agents.defaults.sandbox.mode: "non-main"` is based on `session.mainKey` (default `"main"`), not the agent id. Group/channel sessions always get their own keys, so they are treated as non-main and will be sandboxed. If you want an agent to never sandbox, set `agents.list[].sandbox.mode: "off"`. + --- @@ -325,55 +339,55 @@ sandbox, set `agents.list[].sandbox.mode: "off"`. After configuring multi-agent sandbox and tools: -1. **Check agent resolution:** - - ```exec - openclaw agents list --bindings - ``` - -2. **Verify sandbox containers:** - - ```exec - docker ps --filter "name=openclaw-sbx-" - ``` - -3. **Test tool restrictions:** - - Send a message requiring restricted tools - - Verify the agent cannot use denied tools - -4. **Monitor logs:** - - ```exec - tail -f "${OPENCLAW_STATE_DIR:-$HOME/.openclaw}/logs/gateway.log" | grep -E "routing|sandbox|tools" - ``` + + + ```bash + openclaw agents list --bindings + ``` + + + ```bash + docker ps --filter "name=openclaw-sbx-" + ``` + + + - Send a message requiring restricted tools. + - Verify the agent cannot use denied tools. + + + ```bash + tail -f "${OPENCLAW_STATE_DIR:-$HOME/.openclaw}/logs/gateway.log" | grep -E "routing|sandbox|tools" + ``` + + --- ## Troubleshooting -### Agent not sandboxed despite `mode: "all"` - -- Check if there's a global `agents.defaults.sandbox.mode` that overrides it -- Agent-specific config takes precedence, so set `agents.list[].sandbox.mode: "all"` - -### Tools still available despite deny list - -- Check tool filtering order: global → agent → sandbox → subagent -- Each level can only further restrict, not grant back -- Verify with logs: `[tools] filtering tools for agent:${agentId}` - -### Container not isolated per agent - -- Set `scope: "agent"` in agent-specific sandbox config -- Default is `"session"` which creates one container per session + + + - Check if there's a global `agents.defaults.sandbox.mode` that overrides it. + - Agent-specific config takes precedence, so set `agents.list[].sandbox.mode: "all"`. + + + - Check tool filtering order: global → agent → sandbox → subagent. + - Each level can only further restrict, not grant back. + - Verify with logs: `[tools] filtering tools for agent:${agentId}`. + + + - Set `scope: "agent"` in agent-specific sandbox config. + - Default is `"session"` which creates one container per session. + + --- ## Related -- [Sandboxing](/gateway/sandboxing) -- full sandbox reference (modes, scopes, backends, images) -- [Sandbox vs Tool Policy vs Elevated](/gateway/sandbox-vs-tool-policy-vs-elevated) -- debugging "why is this blocked?" -- [Elevated Mode](/tools/elevated) -- [Multi-Agent Routing](/concepts/multi-agent) -- [Sandbox Configuration](/gateway/config-agents#agentsdefaultssandbox) -- [Session Management](/concepts/session) +- [Elevated mode](/tools/elevated) +- [Multi-agent routing](/concepts/multi-agent) +- [Sandbox configuration](/gateway/config-agents#agentsdefaultssandbox) +- [Sandbox vs tool policy vs elevated](/gateway/sandbox-vs-tool-policy-vs-elevated) — debugging "why is this blocked?" +- [Sandboxing](/gateway/sandboxing) — full sandbox reference (modes, scopes, backends, images) +- [Session management](/concepts/session)