openclaw-tools: fix browser_invoke tool description (act, not click/type)

The bridge advertised non-existent gateway actions ("click"/"type"), so Kimi
sent action="type" -> "Unknown action". Corrected to the real vocabulary:
interactions go through action="act" with args={kind, ref, text} (e.g.
{kind:"type", ref:"e59", text:"..."}, {kind:"click", ref}), plus the real
top-level actions (open/navigate/snapshot/screenshot/act/...). Verified Adolf
can now type/click in the browser.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014t8Qg9gi7H7HtT8MncoXAB

adolf/openclaw.json

@@ -22,7 +22,32 @@
       // /tools/invoke surface by default. The openclaw-tools MCP bridge
       // (P5) calls that surface for cron_create/cron_list/nodes_invoke, so
       // without this allow-list those tools 404 even with a valid token.
-      allow: ["cron", "nodes"],
+      // "browser" added (kb#64 follow-up) so Adolf can drive the OpenClaw
+      // browser via the openclaw-tools bridge for authenticated web access
+      // (e.g. the family wiki login form).
+      allow: ["cron", "nodes", "browser"],
+    },
+  },
+
+  // Browser tool — bundled plugin, off by default. Enables a dedicated,
+  // agent-only headless Chromium profile ("openclaw") driven through the
+  // gateway's loopback control service. Chromium is already in the image
+  // (playwright chromium-1228). Needs both this browser.enabled=true and the
+  // "browser" entry in gateway.tools.allow above.
+  browser: {
+    enabled: true,
+    // Chromium's setuid sandbox can't initialize inside this container (no
+    // unprivileged user namespaces), so run with --no-sandbox. Safe here: the
+    // browser profile is agent-only and isolated, and the container already
+    // drops NET_RAW/NET_ADMIN. Without this, `browser start` fails with
+    // "No usable sandbox".
+    noSandbox: true,
+    // The local *.alogins.net services resolve to the host gateway (private
+    // 172.17.0.1 via extra_hosts), so the browser's SSRF guard blocks them by
+    // default ("navigation blocked by policy"). Opt in for this trusted,
+    // self-owned network — same decision as channels.matrix.network above.
+    ssrfPolicy: {
+      dangerouslyAllowPrivateNetwork: true,
     },
   },
 

openai/docker-compose.yml

@@ -197,6 +197,14 @@ services:
       # same fix). Caddy on the host terminates TLS on :443 and proxies to
       # synapse:8008.
       - "mtx.alogins.net:host-gateway"
+      # Local *.alogins.net web services (family wiki / OtterWiki, РодоВики) —
+      # same hairpin-NAT dodge: the public A record can't loop back through the
+      # router from inside a container, so route the hostname to the host
+      # gateway where Caddy terminates TLS on :443 and proxies to the service.
+      # Lets Adolf's OpenClaw browser reach them with the real URL + the
+      # Vaultwarden creds. Add more *.alogins.net hosts here as needed.
+      - "family.alogins.net:host-gateway"
+      - "wiki.alogins.net:host-gateway"
     cap_drop:
       - NET_RAW
       - NET_ADMIN
@@ -242,6 +250,12 @@ services:
       # this compose project's network) via shared-mcp.json's "kanboard"
       # entry — same host-gateway trick used by adolf/cognee/pipecat above.
       - "host.docker.internal:host-gateway"
+      # Local *.alogins.net web services: the Kimi CLI's own web-fetch tool
+      # runs IN THIS container, so it needs the same hairpin-NAT dodge as the
+      # adolf gateway (the public A record can't loop back through the router).
+      # Route to the host gateway where Caddy terminates TLS on :443.
+      - "family.alogins.net:host-gateway"
+      - "wiki.alogins.net:host-gateway"
     restart: unless-stopped
 
   # hindsight — Adolf memory backend, replacing cognee/cognee-mcp/cognee-llm

openai/openclaw-tools/server.js

@@ -185,15 +185,21 @@ function buildServer() {
   // --- browser --------------------------------------------------------------
   server.registerTool('browser_invoke', {
     description:
-      'Generic pass-through to the OpenClaw gateway "browser" agent tool (agent-controlled Chrome/Brave/Edge ' +
-      'automation: tabs, snapshot, click, type, screenshot). Unlike cron/nodes, "browser" is NOT in the ' +
-      'gateway HTTP default hard-deny list, so this can work as soon as the gateway is up and its normal ' +
-      'tools.* policy allows "browser" for the caller — no special P6 HTTP-deny override needed. Args are ' +
-      'forwarded verbatim as the tool call payload; the exact action/argument vocabulary is defined by the ' +
-      'running gateway and needs live introspection once it exists (deferred to P6/P7).',
+      'Drive the OpenClaw gateway "browser" tool (a headless Chromium the agent controls). ' +
+      'TOP-LEVEL actions (the "action" arg): status, start, stop, profiles, tabs, open, navigate, ' +
+      'snapshot, screenshot, act, console, dialog, pdf, upload. ' +
+      'IMPORTANT: there is NO top-level "click"/"type"/"fill"/"evaluate" action — ALL page ' +
+      'interactions go through action="act" with args={kind, ref, ...}. ' +
+      'Typical flow: action="open" {url} -> action="snapshot" to get element refs (e.g. "e59") -> ' +
+      'action="act" to interact. Interaction args examples: ' +
+      'type text -> {kind:"type", ref:"e59", text:"hello"}; ' +
+      'click -> {kind:"click", ref:"e33"}; ' +
+      'fill -> {kind:"fill", ref:"e65", text:"secret"}; ' +
+      'also kind can be hover|select|press|scrollIntoView|drag|evaluate. ' +
+      'Refs go stale after navigation/DOM change — if an action reports "ref not found", re-snapshot.',
     inputSchema: {
-      action: z.string().describe('Browser tool action, e.g. "status", "open", "snapshot", "click", "type".'),
-      args: z.record(z.string(), z.unknown()).optional().describe('Action-specific parameters object.'),
+      action: z.string().describe('Top-level browser action: open | navigate | snapshot | screenshot | act | tabs | status | start | stop | profiles | console | dialog | pdf | upload. Use "act" for ALL page interactions (click/type/fill), never "click"/"type" directly.'),
+      args: z.record(z.string(), z.unknown()).optional().describe('Action params. action="open": {url, label?}. action="act": {kind:"type"|"click"|"fill"|"hover"|"select"|..., ref:"eN" from snapshot, text:"..." for type/fill}. action="snapshot": {refs:"aria"} for stable refs.'),
     },
   }, async ({ action, args }) => invokeGatewayTool('browser', action, args || {}));