docs: document google meet consult agent

This commit is contained in:
Peter Steinberger
2026-04-27 07:52:50 +01:00
parent 729a4498d9
commit 83da0b01b8
4 changed files with 15 additions and 2 deletions

View File

@@ -28,6 +28,7 @@ Docs: https://docs.openclaw.ai
- Voice Call: allow SecretRef-backed Twilio auth tokens and call-specific OpenAI/ElevenLabs TTS API keys through the plugin config surface. Fixes #68690. Thanks @joshavant.
- Google Meet: clean stale chrome-node realtime audio bridges by URL before rejoining, expose active node bridge inspection, and tolerate transient node input pull failures instead of dropping the Meet session. Fixes #72371. (#72372) Thanks @BsnizND.
- Google Meet: clear queued Gemini Live playback when realtime interruptions arrive, restart Chrome command-pair audio output after clears, and expose Google Live interruption/VAD config knobs for Meet and Voice Call realtime bridges. Fixes #72523. (#72524) Thanks @BsnizND.
- Google Meet: add `realtime.agentId` so live meeting consults can target a named OpenClaw agent instead of always using `main`. (#72381) Thanks @BsnizND.
- Matrix/E2EE: stabilize recovery and broken-device QA flows while avoiding Matrix device-cleanup sync races that could leave shutdown-time crypto work running. Thanks @gumadeiras.
- Cron: treat isolated run-level agent failures as job errors even when no reply payload is produced, synthesizing a safe error payload so model/provider failures increment error counters and trigger failure notifications instead of clearing as successful. Fixes #43604; carries forward #43631. Thanks @SPFAdvisors.
- Cron: preserve exact `NO_REPLY` tool results from isolated jobs with empty final assistant turns as quiet successes instead of surfacing incomplete-turn errors. Fixes #68452; carries forward #68453. Thanks @anyech.

View File

@@ -897,6 +897,8 @@ Defaults:
`openclaw_agent_consult` for deeper answers
- `realtime.introMessage`: short spoken readiness check when the realtime bridge
connects; set it to `""` to join silently
- `realtime.agentId`: optional OpenClaw agent id for
`openclaw_agent_consult`; defaults to `main`
Optional overrides:
@@ -915,6 +917,7 @@ Optional overrides:
},
realtime: {
provider: "google",
agentId: "jay",
toolPolicy: "owner",
introMessage: "Say exactly: I'm here.",
providers: {
@@ -1001,6 +1004,10 @@ meeting transcript context and returns a concise spoken answer to the realtime
voice session. The voice model can then speak that answer back into the meeting.
It uses the same shared realtime consult tool as Voice Call.
By default, consults run against the `main` agent. Set `realtime.agentId` when a
Meet lane should consult a dedicated OpenClaw agent workspace, model defaults,
tool policy, memory, and session history.
`realtime.toolPolicy` controls the consult run:
- `safe-read-only`: expose the consult tool and limit the regular agent to

View File

@@ -120,6 +120,11 @@ const googleMeetConfigSchema = {
label: "Realtime Intro Message",
help: "Spoken once when the realtime bridge is ready. Set to an empty string to join silently.",
},
"realtime.agentId": {
label: "Realtime Consult Agent",
help: 'OpenClaw agent id used by openclaw_agent_consult. Defaults to "main".',
advanced: true,
},
"realtime.toolPolicy": {
label: "Realtime Tool Policy",
help: "Safe read-only tools are available by default; owner requests can unlock broader tools.",

View File

@@ -131,7 +131,7 @@
},
"realtime.agentId": {
"label": "Realtime Consult Agent",
"help": "OpenClaw agent id to consult when realtime.toolPolicy exposes openclaw_agent_consult.",
"help": "OpenClaw agent id used by openclaw_agent_consult. Defaults to \"main\".",
"advanced": true
},
"realtime.toolPolicy": {
@@ -360,7 +360,7 @@
},
"agentId": {
"type": "string",
"description": "OpenClaw agent id to consult when realtime.toolPolicy exposes openclaw_agent_consult."
"description": "OpenClaw agent id used by openclaw_agent_consult. Defaults to \"main\"."
},
"toolPolicy": {
"type": "string",