fix: support photo client tool in debug preview

backend/routes/voice_webrtc.py

@@ -13,7 +13,7 @@ import json
 from collections.abc import Coroutine
 from typing import Any
 
-from fastapi import APIRouter, Body, Depends, Request, WebSocket
+from fastapi import APIRouter, Body, Depends, HTTPException, Request, WebSocket
 from loguru import logger
 from models import AssistantConfig, SignalingOffer
 from services.auth import require_admin, require_admin_websocket
@@ -35,6 +35,7 @@ _active_connections = realtime_lifecycle.active_connections
 _pipeline_tasks = realtime_lifecycle.pipeline_tasks
 _connection_tasks = realtime_lifecycle.connection_tasks
 PIPELINE_CLOSE_GRACE_SECONDS = 10.0
+MAX_CLIENT_TOOL_NAME_LENGTH = 64
 
 
 def _start_pipeline_task(
@@ -69,6 +70,53 @@ async def shutdown_active_sessions() -> None:
     )
 
 
+def _decode_client_tool_names(encoded: str | None) -> list[str] | None:
+    """Decode client capabilities carried outside the WebRTC SDP body.
+
+    Pipecat's browser transport replaces the body of a ``Request`` endpoint
+    with its SDP offer and drops ``APIRequest.requestData``. Request headers are
+    preserved, so they are the authoritative metadata channel for this path.
+    ``None`` means the header was absent and callers should use the legacy body.
+    """
+
+    if encoded is None:
+        return None
+    try:
+        padding = "=" * (-len(encoded) % 4)
+        value = json.loads(
+            base64.urlsafe_b64decode(encoded + padding).decode("utf-8")
+        )
+    except (ValueError, UnicodeDecodeError, json.JSONDecodeError) as exc:
+        raise HTTPException(
+            status_code=400,
+            detail="客户端工具能力请求头格式无效",
+        ) from exc
+    if not isinstance(value, list):
+        raise HTTPException(
+            status_code=400,
+            detail="客户端工具能力必须是函数名列表",
+        )
+
+    names: list[str] = []
+    seen: set[str] = set()
+    for item in value:
+        if not isinstance(item, str):
+            raise HTTPException(
+                status_code=400,
+                detail="客户端工具函数名必须是字符串",
+            )
+        name = item.strip()
+        if not name or len(name) > MAX_CLIENT_TOOL_NAME_LENGTH:
+            raise HTTPException(
+                status_code=400,
+                detail="客户端工具函数名为空或过长",
+            )
+        if name not in seen:
+            names.append(name)
+            seen.add(name)
+    return names
+
+
 @router.get("/api/webrtc/ice-servers", dependencies=[Depends(require_admin)])
 async def ice_servers():
     """Browser fetches STUN/TURN config (with ephemeral TURN creds when configured)."""
@@ -86,12 +134,22 @@ async def http_offer(request: Request, payload: dict = Body(...)):
         header_variables = json.loads(
             base64.urlsafe_b64decode(encoded_variables + padding).decode("utf-8")
         )
+    header_client_tools = _decode_client_tool_names(
+        request.headers.get("x-pipecat-client-tools")
+    )
+    client_tool_names = (
+        header_client_tools
+        if header_client_tools is not None
+        else request_data.get("client_tool_names") or []
+    )
+    logger.debug(f"WebRTC 客户端工具上报: {client_tool_names or '<none>'}")
     offer_payload = {
         **payload,
         "assistant_id": request.headers.get("x-pipecat-assistant-id"),
         "dynamic_variables": header_variables,
-        "client_tool_names": request_data.get("client_tool_names") or [],
         **request_data,
+        # Keep header metadata authoritative when both paths are present.
+        "client_tool_names": client_tool_names,
     }
     answer = await _handle_offer_payload(offer_payload, _http_peers)
     return answer

backend/tests/test_voice_webrtc_lifecycle.py

@@ -1,16 +1,87 @@
 from __future__ import annotations
 
 import asyncio
+import base64
+import json
 import unittest
-from unittest.mock import patch
+from unittest.mock import AsyncMock, patch
 
+from fastapi import HTTPException
 from routes import voice_webrtc
+from starlette.requests import Request
 
 
 class FakeConnection:
     pc_id = "pc_test"
 
 
+def encoded_header_json(value: object) -> str:
+    payload = json.dumps(value).encode("utf-8")
+    return base64.urlsafe_b64encode(payload).decode("ascii").rstrip("=")
+
+
+def offer_request(*, client_tools: object | None = None) -> Request:
+    headers = []
+    if client_tools is not None:
+        headers.append(
+            (
+                b"x-pipecat-client-tools",
+                encoded_header_json(client_tools).encode("ascii"),
+            )
+        )
+    return Request({"type": "http", "method": "POST", "headers": headers})
+
+
+class WebRTCOfferMetadataTest(unittest.IsolatedAsyncioTestCase):
+    async def test_client_tool_header_survives_request_endpoint_body_replacement(self):
+        request = offer_request(
+            client_tools=["set_photo_button_visible", "show_message"]
+        )
+        payload = {"sdp": "offer", "type": "offer"}
+
+        with patch.object(
+            voice_webrtc,
+            "_handle_offer_payload",
+            new=AsyncMock(return_value={"type": "answer"}),
+        ) as handle_offer:
+            await voice_webrtc.http_offer(request, payload)
+
+        forwarded = handle_offer.await_args.args[0]
+        self.assertEqual(
+            forwarded["client_tool_names"],
+            ["set_photo_button_visible", "show_message"],
+        )
+
+    async def test_client_tool_request_data_remains_a_compatibility_fallback(self):
+        request = offer_request()
+        payload = {
+            "sdp": "offer",
+            "type": "offer",
+            "requestData": {"client_tool_names": ["show_message"]},
+        }
+
+        with patch.object(
+            voice_webrtc,
+            "_handle_offer_payload",
+            new=AsyncMock(return_value={"type": "answer"}),
+        ) as handle_offer:
+            await voice_webrtc.http_offer(request, payload)
+
+        forwarded = handle_offer.await_args.args[0]
+        self.assertEqual(forwarded["client_tool_names"], ["show_message"])
+
+    async def test_invalid_client_tool_header_is_rejected(self):
+        request = offer_request(client_tools={"name": "show_message"})
+
+        with self.assertRaises(HTTPException) as raised:
+            await voice_webrtc.http_offer(
+                request,
+                {"sdp": "offer", "type": "offer"},
+            )
+
+        self.assertEqual(raised.exception.status_code, 400)
+
+
 class WebRTCPipelineLifecycleTest(unittest.IsolatedAsyncioTestCase):
     async def asyncTearDown(self):
         tasks = list(voice_webrtc._pipeline_tasks)

frontend/src/components/assistant-editor/debug-preview.tsx

@@ -5,6 +5,7 @@ import { useCallback, useEffect, useLayoutEffect, useRef, useState } from "react
 import {
   AudioLines,
   Braces,
+  Camera,
   Check,
   Copy,
   ImageIcon,
@@ -13,7 +14,6 @@ import {
   Mic,
   Orbit,
   PhoneOff,
-  ScanLine,
   Send,
   Smartphone,
   Sparkles,
@@ -1674,7 +1674,10 @@ function DebugPhotoCaptureButton({
   onCapture: () => Promise<void>;
 }) {
   return (
-    <div className="absolute bottom-4 left-1/2 z-20 flex -translate-x-1/2 flex-col items-center gap-2">
+    <div className="absolute bottom-4 left-1/2 z-20 flex -translate-x-1/2 animate-in flex-col items-center gap-2 fade-in-0 slide-in-from-bottom-2 duration-200">
+      <span className="sr-only" role="status" aria-live="polite">
+        拍照按钮已开启
+      </span>
       {error && (
         <div className="max-w-xs rounded-full border border-destructive/20 bg-background/90 px-3 py-1 text-xs text-destructive shadow-sm backdrop-blur">
           {error}
@@ -1682,18 +1685,19 @@ function DebugPhotoCaptureButton({
       )}
       <Button
         type="button"
-        size="icon"
+        size="sm"
         onClick={() => void onCapture()}
         disabled={capturing || !enabled}
         aria-label={capturing ? "正在提交照片" : "拍照并发送"}
         title={capturing ? "正在提交照片" : "拍照并发送"}
-        className="size-12 rounded-full shadow-lg"
+        className="h-10 shrink-0 gap-2 rounded-full px-5 shadow-lg ring-1 ring-black/10"
       >
         {capturing ? (
           <Loader2 className="size-5 animate-spin" />
         ) : (
-          <ScanLine className="size-5" />
+          <Camera className="size-5" />
         )}
+        <span>{capturing ? "正在拍照" : "拍照"}</span>
       </Button>
     </div>
   );

frontend/src/hooks/use-voice-preview.ts

@@ -826,6 +826,10 @@ export function useVoicePreview(
       setVideoStream(localVideo ? new MediaStream([localVideo]) : null);
       void refreshDevices();
 
+      // SmallWebRTCTransport discards APIRequest.requestData when endpoint is a
+      // Request object. Keep capabilities in a header as the reliable path;
+      // requestData remains below for compatibility with other transports.
+      const clientToolNames = Array.from(clientToolHandlersRef.current.keys());
       const request = new Request(`${API_BASE}/api/webrtc/offer`, {
         method: "POST",
         headers: {
@@ -834,6 +838,7 @@ export function useVoicePreview(
           "X-Pipecat-Dynamic-Variables": encodeHeaderJson(
             options.dynamicVariables ?? {},
           ),
+          "X-Pipecat-Client-Tools": encodeHeaderJson(clientToolNames),
         },
         credentials: "include",
       });
@@ -844,9 +849,7 @@ export function useVoicePreview(
             assistant_id: assistantId,
             vision_enabled: Boolean(options.visionEnabled),
             dynamic_variables: options.dynamicVariables ?? {},
-            client_tool_names: Array.from(
-              clientToolHandlersRef.current.keys(),
-            ),
+            client_tool_names: clientToolNames,
           },
         },
       });