1B: autonomous door config — level=full + claude_cli text-only note

Set the tool-free risk profile to level="full" so ZeroClaw raises no in-channel
approval (the human is removed; the Clawmates door auto-governs). Document that
claude_cli is text-only (claude -p doesn't surface tool calls), so agents that
ACT through the door need a tool-capable provider (groq/anthropic) — with a
commented actor-agent example.

Validated live: a groq-brained actor agent at full autonomy emitted
clawmates__email_send with no approval prompt; the door executed it (outbox +
agent|door.executed audit). No human in the loop.

Co-Authored-By: Claude Opus 4.8 <[email protected]>

deploy/clawmates-runtime/agent.config.example.toml

@@ -19,12 +19,13 @@ quickstart_completed = true
 [providers.models.claude_cli.default]
 model = "haiku"
 
-# §15 door (Step 1A): a tool-free profile — agents can only reason, no native
+# Tool-free profile — agents can only reason + call the MCP door (tools inject
-# outbound tools. Step 1B adds an MCP client bundle (the Clawmates gated door),
+# AFTER this allowlist filter). `level = "full"` removes ZeroClaw's OWN approval
-# whose tools are injected AFTER this allowlist filter, so a tool-free agent can
+# prompts so the agent is autonomous; governance happens at the Clawmates door
-# still call ONLY the gated Clawmates tools.
+# (auto-policy, no human — "agents control their destiny"). Use "supervised" if
+# you want ZeroClaw to also gate sensitive calls with an in-channel approval.
 [risk_profiles.toolfree]
-level = "supervised"
+level = "full"
 allowed_tools = []
 excluded_tools = ["shell", "file_read", "file_write", "http_request", "browser", "composio"]
 
@@ -76,3 +77,14 @@ headers = { Authorization = "Bearer REPLACE_WITH_DOOR_TOKEN" }
 
 [mcp_bundles.clawmates_door]
 servers = ["clawmates"]
+
+# NOTE: `claude_cli` is a TEXT-ONLY provider — `claude -p` doesn't surface
+# tool-calls back to ZeroClaw, so claude_cli agents reason but can't invoke the
+# door. An agent that ACTS through the door needs a tool-capable provider
+# (groq/anthropic/openai). Example actor agent (uncomment + provide groq creds
+# via env ZEROCLAW_providers__models__groq__default__{model,api_key}):
+# [providers.models.groq.default]
+# [agents.actor]
+# model_provider = "groq.default"
+# risk_profile = "toolfree"
+# mcp_bundles = ["clawmates_door"]