merge: integrate remote speech capabilities into feature/N7Web

apps/web-console/app.js

@@ -7556,18 +7556,21 @@ function naturalLanguageRequestBody(
   {
     executionMode = state.executionMode,
     clientType = "web_console",
+    provider = state.provider,
+    speechUtteranceId = null,
   } = {},
 ) {
   const driverOnlyCh1 = isDriverOnlyCh1Runtime();
   return {
     utterance,
     client_type: clientType,
-    provider: state.provider,
+    provider,
     conversation_id: state.conversationId,
     vehicle_id: state.vehicleId || state.runtime?.default_vehicle_id,
     execution_mode: executionMode,
     control_transport: state.controlTransport,
-    ...(state.provider === "openai" ? { reasoning_effort: state.reasoningEffort } : {}),
+    ...(provider === "openai" ? { reasoning_effort: state.reasoningEffort } : {}),
+    ...(speechUtteranceId ? { speech_utterance_id: speechUtteranceId } : {}),
     ...(executionMode === "hardware"
       && state.controlTransport !== "wireless_mqtt"
       && !driverOnlyCh1
@@ -7584,6 +7587,8 @@ async function requestNaturalLanguageControl(
   {
     executionMode = state.executionMode,
     clientType = "web_console",
+    provider = state.provider,
+    speechUtteranceId = null,
     previewOnly = false,
     onControlPhaseEvent = null,
     onPreview = null,
@@ -7593,8 +7598,10 @@ async function requestNaturalLanguageControl(
   const requestBody = naturalLanguageRequestBody(utterance, {
     executionMode,
     clientType,
+    provider,
+    speechUtteranceId,
   });
-  const usePreview = previewOnly || state.provider === "openai";
+  const usePreview = previewOnly || provider === "openai";
   if (!usePreview) {
     const payload = await postControlPhase(
       "/api/requests",
@@ -7623,7 +7630,7 @@ async function requestNaturalLanguageControl(
       `/api/requests/${preview.request_id}/supplement`,
       {
         client_type: clientType,
-        provider: state.provider,
+        provider,
         reasoning_effort: state.reasoningEffort,
         ...(executionMode === "hardware"
           && state.controlTransport !== "wireless_mqtt"
@@ -7712,7 +7719,14 @@ async function executeCanCommands(canCommands, { deviceName = "车辆设备" } =
 
 async function submitRequest(event) {
   event.preventDefault();
-  const utterance = $("#utterance").value.trim();
+  const utteranceInput = $("#utterance");
+  const utterance = utteranceInput.value.trim();
+  const speechSubmission = (
+    utteranceInput.dataset.speechExecutionEligible === "true"
+    && utteranceInput.dataset.speechValue === utterance
+    && Boolean(utteranceInput.dataset.speechUtteranceId)
+  );
+  const requestProvider = speechSubmission ? "local" : state.provider;
   const submittedModeProfileId = state.pendingModeProfileId;
   state.pendingModeProfileId = null;
   if (!utterance) {
@@ -7720,6 +7734,20 @@ async function submitRequest(event) {
     showToast("请输入车舱控制请求");
     return;
   }
+  if (
+    utteranceInput.dataset.speechExecutionEligible === "false"
+    && utteranceInput.dataset.speechValue === utterance
+  ) {
+    if (submittedModeProfileId) setModeExecutionState(submittedModeProfileId, "failed");
+    const speechStatus = utteranceInput.dataset.speechSemanticStatus;
+    const message = speechStatus === "recognized_unsupported"
+      ? "语音意图已识别，但当前车辆能力不支持执行"
+      : speechStatus === "incomplete"
+        ? "语音控制参数不完整，请补充后再执行"
+        : "语音结果存在歧义，请修改确认后再执行";
+    showToast(message);
+    return;
+  }
   const driverOnlyCh1 = isDriverOnlyCh1Runtime();
   if (state.executionMode === "hardware"
     && state.controlTransport !== "wireless_mqtt"
@@ -7757,6 +7785,10 @@ async function submitRequest(event) {
     const { payload, supplementWarning } = await requestNaturalLanguageControl(
       utterance,
       {
+        provider: requestProvider,
+        speechUtteranceId: speechSubmission
+          ? utteranceInput.dataset.speechUtteranceId
+          : null,
         onControlPhaseEvent,
         onPreview: (preview) => {
           renderResult(preview);
@@ -7771,6 +7803,13 @@ async function submitRequest(event) {
     if (!payload) return;
     renderResult(payload);
     completedResult = payload;
+    if (speechSubmission) {
+      delete utteranceInput.dataset.speechUtteranceId;
+      delete utteranceInput.dataset.speechExecutionEligible;
+      delete utteranceInput.dataset.speechSemanticStatus;
+      delete utteranceInput.dataset.speechValue;
+      delete utteranceInput.dataset.speechUncertain;
+    }
     const peripheralRoute = String(payload.orchestration_route || "")
       .startsWith("nfc_peripheral");
     if (state.executionMode === "hardware" && !peripheralRoute) {