fix(google-meet): hide realtime alias from agent schema

CHANGELOG.md

@@ -42,6 +42,7 @@ Docs: https://docs.openclaw.ai
 ### Fixes
 
 - Diagnostics: keep webhook/message OTEL attributes and Prometheus delivery labels low-cardinality and omit raw chat/message IDs from spans, so progress-draft and message-tool modes do not leak high-cardinality messaging identifiers.
+- Google Meet: stop advertising legacy `mode: "realtime"` to agents and config UIs, while keeping it as a hidden compatibility alias for `mode: "agent"`, so new joins use the STT -> OpenClaw agent -> TTS path instead of selecting the direct realtime voice fallback.
 - Telegram: render shared interactive reply buttons in reply delivery so plugin approval messages show inline keyboards. (#76238) Thanks @keshavbotagent.
 - Agents/cli-runner: drop a saved `claude-cli` resume sessionId at preparation time when its on-disk transcript no longer exists in `~/.claude/projects/`, so a stale binding from a half-installed `update.run` cannot trap follow-up runs (auto-reply / Telegram direct) in a `claude --resume` timeout loop; the run starts fresh and the new sessionId is written back through the existing post-run flow. (#77030; refs #77011) Thanks @openperf.
 - Release validation: install the cross-OS TypeScript harness through Windows-safe Node/npm shims so native Windows package checks reach the OpenClaw smoke suites instead of exiting before artifact capture. Thanks @vincentkoc.

docs/plugins/google-meet.md

@@ -1,5 +1,5 @@
 ---
-summary: "Google Meet plugin: join explicit Meet URLs through Chrome or Twilio with realtime voice defaults"
+summary: "Google Meet plugin: join explicit Meet URLs through Chrome or Twilio with agent talk-back defaults"
 read_when:
   - You want an OpenClaw agent to join a Google Meet call
   - You want an OpenClaw agent to create a new Google Meet call
@@ -12,12 +12,12 @@ Google Meet participant support for OpenClaw — the plugin is explicit by desig
 - It only joins an explicit `https://meet.google.com/...` URL.
 - It can create a new Meet space through the Google Meet API, then join the
   returned URL.
-- `realtime` voice is the default mode.
-- Realtime voice can call back into the full OpenClaw agent when deeper
-  reasoning or tools are needed.
-- Agents choose the join behavior with `mode`: use `realtime` for live
-  listen/talk-back, or `transcribe` to join/control the browser without the
-  realtime voice bridge.
+- `agent` is the default talk-back mode: realtime transcription listens, the
+  configured OpenClaw agent answers, and regular OpenClaw TTS speaks into Meet.
+- `bidi` remains available as the fallback direct realtime voice model mode.
+- Agents choose the join behavior with `mode`: use `agent` for live
+  listen/talk-back, `bidi` for direct realtime voice fallback, or `transcribe`
+  to join/control the browser without the talk-back bridge.
 - Auth starts as personal Google OAuth or an already signed-in Chrome profile.
 - There is no automatic consent announcement.
 - The default Chrome audio backend is `BlackHole 2ch`.
@@ -29,9 +29,10 @@ Google Meet participant support for OpenClaw — the plugin is explicit by desig
 
 ## Quick start
 
-Install the local audio dependencies and configure a backend realtime voice
-provider. OpenAI is the default; Google Gemini Live also works with
-`realtime.provider: "google"`:
+Install the local audio dependencies and configure a realtime transcription
+provider plus regular OpenClaw TTS. OpenAI is the default transcription
+provider; Google Gemini Live also works with `realtime.provider: "google"` for
+`bidi` mode:
 
 ```bash
 brew install blackhole-2ch sox
@@ -130,7 +131,7 @@ participation.
 Create a new meeting and join it:
 
 ```bash
-openclaw googlemeet create --transport chrome-node --mode realtime
+openclaw googlemeet create --transport chrome-node --mode agent
 ```
 
 For API-created rooms, use Google Meet `SpaceConfig.accessType` when you want
@@ -138,7 +139,7 @@ the room's no-knock policy to be explicit instead of inherited from the Google
 account defaults:
 
 ```bash
-openclaw googlemeet create --access-type OPEN --transport chrome-node --mode realtime
+openclaw googlemeet create --access-type OPEN --transport chrome-node --mode agent
 ```
 
 `OPEN` lets anyone with the Meet URL join without knocking. `TRUSTED` lets the
@@ -177,15 +178,15 @@ can explain which path was used. `create` joins the new meeting by default and
 returns `joined: true` plus the join session. To only mint the URL, use
 `create --no-join` on the CLI or pass `"join": false` to the tool.
 
-Or tell an agent: "Create a Google Meet, join it with realtime voice, and send
-me the link." The agent should call `google_meet` with `action: "create"` and
-then share the returned `meetingUri`.
+Or tell an agent: "Create a Google Meet, join it with the agent talk-back mode,
+and send me the link." The agent should call `google_meet` with
+`action: "create"` and then share the returned `meetingUri`.
 
 ```json
 {
   "action": "create",
   "transport": "chrome-node",
-  "mode": "realtime"
+  "mode": "agent"
 }
 ```
 
@@ -818,7 +819,7 @@ Agents can also create an API-backed room with an explicit access policy:
 {
   "action": "create",
   "transport": "chrome-node",
-  "mode": "realtime",
+  "mode": "agent",
   "accessType": "OPEN"
 }
 ```
@@ -1000,8 +1001,8 @@ Set the plugin config under `plugins.entries.google-meet.config`:
 Defaults:
 
 - `defaultTransport: "chrome"`
-- `defaultMode: "agent"` (`"realtime"` is accepted as a compatibility alias for
-  `"agent"`)
+- `defaultMode: "agent"` (`"realtime"` is accepted only as a legacy
+  compatibility alias for `"agent"`; new tool calls should say `"agent"`)
 - `chromeNode.node`: optional node id/name/IP for `chrome-node`
 - `chrome.audioBackend: "blackhole-2ch"`
 - `chrome.guestName: "OpenClaw Agent"`: name used on the signed-out Meet guest
@@ -1011,7 +1012,7 @@ Defaults:
 - `chrome.reuseExistingTab: true`: activate an existing Meet tab instead of
   opening duplicates
 - `chrome.waitForInCallMs: 20000`: wait for the Meet tab to report in-call
-  before the realtime intro is triggered
+  before the talk-back intro is triggered
 - `chrome.audioFormat: "pcm16-24khz"`: command-pair audio format. Use
   `"g711-ulaw-8khz"` only for legacy/custom command pairs that still emit
   telephony audio.
@@ -1140,8 +1141,8 @@ Gateway host, so model credentials stay there. With the default `mode: "agent"`,
 the realtime transcription provider handles listening, the configured OpenClaw
 agent produces the answer, and regular OpenClaw TTS speaks it into Meet. Use
 `mode: "bidi"` when you want the realtime voice model to answer directly.
-`mode: "realtime"` remains accepted as a compatibility alias for
-`mode: "agent"`.
+Raw `mode: "realtime"` remains accepted as a legacy compatibility alias for
+`mode: "agent"`, but it is no longer advertised in the agent tool schema.
 
 Use `action: "status"` to list active sessions or inspect a session ID. Use
 `action: "speak"` with `sessionId` and `message` to make the realtime agent

extensions/google-meet/index.test.ts

@@ -386,6 +386,7 @@ describe("google-meet plugin", () => {
       oauth: {},
       auth: { provider: "google-oauth" },
     });
+    expect(resolveGoogleMeetConfig({ defaultMode: "realtime" }).defaultMode).toBe("agent");
     expect(resolveGoogleMeetConfig({}).realtime.instructions).toContain("openclaw_agent_consult");
   });
 
@@ -621,7 +622,7 @@ describe("google-meet plugin", () => {
           description: expect.stringContaining("recover_current_tab"),
         },
         transport: { type: "string", enum: ["chrome", "chrome-node", "twilio"] },
-        mode: { type: "string", enum: ["agent", "bidi", "realtime", "transcribe"] },
+        mode: { type: "string", enum: ["agent", "bidi", "transcribe"] },
       },
     });
   });
@@ -3154,7 +3155,12 @@ describe("google-meet plugin", () => {
       createdAt: "2026-04-27T00:00:00.000Z",
       updatedAt: "2026-04-27T00:00:00.000Z",
       participantIdentity: "signed-in Google Chrome profile",
-      realtime: { enabled: true, provider: "openai", toolPolicy: "safe-read-only" },
+      realtime: {
+        enabled: true,
+        strategy: "agent",
+        transcriptionProvider: "openai",
+        toolPolicy: "safe-read-only",
+      },
       chrome: {
         audioBackend: "blackhole-2ch",
         launched: true,

extensions/google-meet/index.ts

@@ -155,10 +155,14 @@ const googleMeetConfigSchema = {
       help: "Legacy realtime alias setting. Use mode=agent or mode=bidi for new Meet joins.",
     },
     "realtime.provider": {
-      label: "Realtime Provider",
-      help: "Defaults to OpenAI; uses OPENAI_API_KEY when no provider config is set.",
+      label: "Speech Provider",
+      help: "Agent mode uses this for realtime transcription. Bidi mode uses it as the realtime voice provider.",
+    },
+    "realtime.model": {
+      label: "Bidi Realtime Model",
+      help: "Only used by mode=bidi. Agent mode answers with the configured OpenClaw agent and regular TTS.",
+      advanced: true,
     },
-    "realtime.model": { label: "Realtime Model", advanced: true },
     "realtime.instructions": { label: "Realtime Instructions", advanced: true },
     "realtime.introMessage": {
       label: "Realtime Intro Message",
@@ -238,9 +242,9 @@ const GoogleMeetToolSchema = Type.Object({
   ),
   mode: Type.Optional(
     Type.String({
-      enum: ["agent", "bidi", "realtime", "transcribe"],
+      enum: ["agent", "bidi", "transcribe"],
       description:
-        "Join mode. agent uses realtime transcription, the configured OpenClaw agent, and regular TTS. bidi uses the realtime voice model directly. realtime is a compatibility alias for agent. transcribe joins observe-only.",
+        "Join mode. agent uses realtime transcription, the configured OpenClaw agent, and regular TTS. bidi uses the realtime voice model directly. transcribe joins observe-only.",
     }),
   ),
   dialInNumber: Type.Optional(

extensions/google-meet/openclaw.plugin.json

@@ -148,11 +148,12 @@
       "help": "Legacy realtime alias setting. Use mode=agent or mode=bidi for new Meet joins."
     },
     "realtime.provider": {
-      "label": "Realtime Provider",
-      "help": "Defaults to OpenAI; uses OPENAI_API_KEY when no provider config is set."
+      "label": "Speech Provider",
+      "help": "Agent mode uses this for realtime transcription. Bidi mode uses it as the realtime voice provider."
     },
     "realtime.model": {
-      "label": "Realtime Model",
+      "label": "Bidi Realtime Model",
+      "help": "Only used by mode=bidi. Agent mode answers with the configured OpenClaw agent and regular TTS.",
       "advanced": true
     },
     "realtime.instructions": {
@@ -227,7 +228,7 @@
       },
       "defaultMode": {
         "type": "string",
-        "enum": ["agent", "bidi", "realtime", "transcribe"],
+        "enum": ["agent", "bidi", "transcribe"],
         "default": "agent"
       },
       "chrome": {

extensions/google-meet/src/cli.ts

@@ -11,7 +11,7 @@ import {
   listGoogleMeetCalendarEvents,
   type GoogleMeetCalendarLookupResult,
 } from "./calendar.js";
-import type { GoogleMeetConfig, GoogleMeetMode, GoogleMeetTransport } from "./config.js";
+import type { GoogleMeetConfig, GoogleMeetModeInput, GoogleMeetTransport } from "./config.js";
 import { hasCreateSpaceConfigInput, resolveCreateSpaceConfig } from "./create.js";
 import {
   buildGoogleMeetPreflightReport,
@@ -37,7 +37,7 @@ import type { GoogleMeetRuntime } from "./runtime.js";
 
 type JoinOptions = {
   transport?: GoogleMeetTransport;
-  mode?: GoogleMeetMode;
+  mode?: GoogleMeetModeInput;
   message?: string;
   timeoutMs?: string;
   dialInNumber?: string;
@@ -134,7 +134,7 @@ export type GoogleMeetExportManifest = {
 
 type SetupOptions = {
   json?: boolean;
-  mode?: GoogleMeetMode;
+  mode?: GoogleMeetModeInput;
   transport?: GoogleMeetTransport;
 };
 
@@ -181,7 +181,7 @@ type CreateOptions = {
   entryPointAccess?: string;
   join?: boolean;
   transport?: GoogleMeetTransport;
-  mode?: GoogleMeetMode;
+  mode?: GoogleMeetModeInput;
   message?: string;
   dialInNumber?: string;
   pin?: string;
@@ -349,12 +349,17 @@ function writeDoctorStatus(status: Awaited<ReturnType<GoogleMeetRuntime["status"
     }
     writeStdoutLine("node: %s", session.chrome?.nodeId ?? "local/none");
     writeStdoutLine("audio bridge: %s", session.chrome?.audioBridge?.type ?? "none");
+    const bridgeProvider =
+      session.chrome?.audioBridge?.provider ??
+      session.realtime.transcriptionProvider ??
+      session.realtime.provider ??
+      "n/a";
     writeStdoutLine(
-      "provider: %s",
-      session.chrome?.audioBridge?.provider ?? session.realtime.provider ?? "n/a",
+      session.mode === "agent" ? "transcription provider: %s" : "provider: %s",
+      bridgeProvider,
     );
     if (session.realtime.enabled) {
-      writeStdoutLine("realtime strategy: %s", session.realtime.strategy ?? "agent");
+      writeStdoutLine("talk-back mode: %s", session.realtime.strategy ?? session.mode);
     }
     writeStdoutLine("in call: %s", formatBoolean(health?.inCall));
     writeStdoutLine("lobby waiting: %s", formatBoolean(health?.lobbyWaiting));
@@ -2268,7 +2273,7 @@ export function registerGoogleMeetCli(params: {
     .command("setup")
     .description("Show Google Meet transport setup status")
     .option("--transport <transport>", "Transport to check: chrome, chrome-node, or twilio")
-    .option("--mode <mode>", "Mode to check: realtime or transcribe")
+    .option("--mode <mode>", "Mode to check: agent, bidi, or transcribe")
     .option("--json", "Print JSON output", false)
     .action(async (options: SetupOptions) => {
       const rt = await params.ensureRuntime();

extensions/google-meet/src/runtime.ts

@@ -3,7 +3,12 @@ import type { OpenClawConfig } from "openclaw/plugin-sdk/config-types";
 import { formatErrorMessage } from "openclaw/plugin-sdk/error-runtime";
 import type { PluginRuntime, RuntimeLogger } from "openclaw/plugin-sdk/plugin-runtime";
 import { normalizeOptionalString } from "openclaw/plugin-sdk/text-runtime";
-import type { GoogleMeetConfig, GoogleMeetMode, GoogleMeetTransport } from "./config.js";
+import type {
+  GoogleMeetConfig,
+  GoogleMeetMode,
+  GoogleMeetModeInput,
+  GoogleMeetTransport,
+} from "./config.js";
 import { addGoogleMeetSetupCheck, getGoogleMeetSetupStatus } from "./setup.js";
 import { isSameMeetUrlForReuse, resolveChromeNodeInfo } from "./transports/chrome-browser-proxy.js";
 import { createMeetWithBrowserProxyOnNode } from "./transports/chrome-create.js";
@@ -60,8 +65,8 @@ function resolveTransport(input: GoogleMeetTransport | undefined, config: Google
   return input ?? config.defaultTransport;
 }
 
-function resolveMode(input: GoogleMeetMode | undefined, config: GoogleMeetConfig) {
-  return input ?? config.defaultMode;
+function resolveMode(input: GoogleMeetModeInput | undefined, config: GoogleMeetConfig) {
+  return input === "realtime" ? "agent" : (input ?? config.defaultMode);
 }
 
 function isGoogleMeetTalkBackMode(mode: GoogleMeetMode): boolean {
@@ -245,7 +250,7 @@ export class GoogleMeetRuntime {
   async setupStatus(
     options: {
       transport?: GoogleMeetTransport;
-      mode?: GoogleMeetMode;
+      mode?: GoogleMeetModeInput;
       dialInNumber?: string;
     } = {},
   ) {
@@ -397,8 +402,9 @@ export class GoogleMeetRuntime {
       realtime: {
         enabled: isGoogleMeetTalkBackMode(mode),
         strategy: mode === "bidi" ? "bidi" : "agent",
-        provider: this.params.config.realtime.provider,
-        model: this.params.config.realtime.model,
+        provider: mode === "bidi" ? this.params.config.realtime.provider : undefined,
+        model: mode === "bidi" ? this.params.config.realtime.model : undefined,
+        transcriptionProvider: mode === "agent" ? this.params.config.realtime.provider : undefined,
         toolPolicy: this.params.config.realtime.toolPolicy,
       },
       notes: [],
@@ -690,7 +696,8 @@ export class GoogleMeetRuntime {
     recentTranscript?: GoogleMeetChromeHealth["recentTranscript"];
     session: GoogleMeetSession;
   }> {
-    if (request.mode && isGoogleMeetTalkBackMode(request.mode)) {
+    const requestedMode = request.mode ? resolveMode(request.mode, this.params.config) : undefined;
+    if (requestedMode && isGoogleMeetTalkBackMode(requestedMode)) {
       throw new Error(
         "test_listen requires mode: transcribe; use test_speech for talk-back sessions.",
       );

extensions/google-meet/src/transports/types.ts

@@ -1,11 +1,11 @@
-import type { GoogleMeetMode, GoogleMeetTransport } from "../config.js";
+import type { GoogleMeetMode, GoogleMeetModeInput, GoogleMeetTransport } from "../config.js";
 
 type GoogleMeetSessionState = "active" | "ended";
 
 export type GoogleMeetJoinRequest = {
   url: string;
   transport?: GoogleMeetTransport;
-  mode?: GoogleMeetMode;
+  mode?: GoogleMeetModeInput;
   message?: string;
   timeoutMs?: number;
   dialInNumber?: string;
@@ -106,6 +106,7 @@ export type GoogleMeetSession = {
     strategy?: string;
     provider?: string;
     model?: string;
+    transcriptionProvider?: string;
     toolPolicy: string;
   };
   chrome?: {