feat(web): 用户侧体验补齐——思维链/工具卡数据源 + 图片附件 + 语音上行 + home/vision/voice 真表现

- 打通 thinking/tool_call 运行时数据源：openai 发 thinking_*(reasoning_content)/tool_call_*
  (delta.tool_calls 累积重新组装 Args 非 JSON 串)；anthropic_stream 发 thinking_*(content_block
  thinking start/delta/stop)。ws_bridge 已映射 thinking.*/tool_call.*，前端渲染活。
- 前端消息模型 + 附件：ChatMessage 加 image?；ChatInput 加附件按钮(file→base64)、预览/移除、
  image-aware onSend(text,image)；VisionMessageBody 升级图像卡+识别 chip；VoiceMessageBody
  升级通话控制卡(live2D预留/波形/静音/挂断)；HomeMessageBody 读真实 deviceUpdates(去掉
  sampleDevices 猜)。
- 激活 voice_input：ChatShell onVoice 不再 no-op → sendUp voice_input + 切 voice mode。
- addTool 改按工具名 upsert(修复 tool_call.start/end 重复卡)；ws_mode_switch 应用 agent 驱动
  mode；addUserMessage/beginAssistant 带 image/mode；chatStream/useChat.send 带 image。
- 新增 image/phone 图标。

已知限制(标注)：图片仅前端收集(后端 chatRequest 无 image 字段未接真推理)；流式工具卡无真实
工具名(StreamEvent 只带 ID，回退 tool_<id前缀>)；mode 由 agent 驱动但后端未逐消息下发 mode
(mode_switch 回显+默认当前 mode 兜底)；voice 为 UI+voice_input 上行(真实通话后置)。
go build/vet/test + 前端 tsc 绿。

frontend/web/src/modes/ChatShell.tsx

@@ -1,6 +1,8 @@
 import { useEffect, useRef } from "react";
 import { useAppStore } from "../store/useAppStore";
+import { useModeStore } from "../store/useModeStore";
 import { useSendChat } from "../lib/useChat";
+import { sendUp } from "../lib/ws";
 import { MessageBubble } from "../components/chat";
 import { ChatInput } from "../components/ChatInput";
 import { EmptyState } from "../components/primitives";
@@ -37,7 +39,17 @@ export function ChatShell(): React.ReactNode {
           <div ref={bottomRef} />
         </div>
       </div>
-      <ChatInput onSend={(t) => void send(t)} sending={sending} onVoice={() => { /* voice handled by agent */ }} />
+      <ChatInput
+        onSend={(t, image) => void send(t, image)}
+        sending={sending}
+        onVoice={() => {
+          // Voice is not wired to a live pipeline yet (real call deferred). Activate
+          // the voice_input uplink and switch the shell to voice mode so the agent
+          // (or the demo) reflects a voice session.
+          useModeStore.getState().setMode("voice");
+          sendUp({ type: "voice_input", data: { mode: "voice" } });
+        }}
+      />
     </div>
   );
 }