重构语音能力配置与逻辑，统一音频输入输出开关并优化语音回复判断

app/agent/__init__.py

@@ -34,6 +34,7 @@ from app.chain import ChainBase
 from app.core.config import settings
 from app.db.transferhistory_oper import TransferHistoryOper
 from app.helper.llm import LLMHelper
+from app.helper.voice import VoiceHelper
 from app.log import logger
 from app.schemas import Notification, NotificationType
 from app.schemas.message import ChannelCapabilityManager, ChannelCapability
@@ -677,6 +678,22 @@ class MoviePilotAgent:
         """
         通过原渠道发送消息给用户
         """
+        voice_path = None
+        if (
+            self.reply_with_voice
+            and VoiceHelper.resolve_reply_mode(
+                channel=self.channel,
+                source=self.source,
+            )
+            == VoiceHelper.REPLY_MODE_NATIVE
+            and VoiceHelper.is_available("tts")
+        ):
+            # 当用户本轮发来语音且 Agent 未主动调用 send_voice_message 时，
+            # 这里补一层自动语音回复兜底，避免最终仍只返回纯文字。
+            voice_file = await asyncio.to_thread(VoiceHelper.synthesize_speech, message)
+            if voice_file:
+                voice_path = str(voice_file)
+
         await AgentChain().async_post_message(
             Notification(
                 channel=self.channel,
@@ -686,6 +703,12 @@ class MoviePilotAgent:
                 username=self.username,
                 title=title,
                 text=message,
+                voice_path=voice_path,
+                voice_caption=(
+                    message
+                    if voice_path and settings.AI_VOICE_REPLY_WITH_TEXT
+                    else None
+                ),
             )
         )
 

app/agent/prompt/__init__.py

@@ -335,7 +335,7 @@ class PromptManager:
         return (
             "- Current message context: The user sent a voice message.\n"
             "- Reply preference: Prioritize calling `send_voice_message` for the main user-facing reply.\n"
-            "- Fallback: If voice is unavailable on the current channel, `send_voice_message` will fall back to text.\n"
+            "- Fallback: If native voice is unavailable on the current channel, `send_voice_message` will fall back to text.\n"
             "- Do not repeat the same full reply again after calling `send_voice_message`."
         )
 

app/agent/tools/impl/send_voice_message.py

@@ -8,10 +8,8 @@ from pydantic import BaseModel, Field
 from app.agent.tools.base import MoviePilotTool, ToolChain
 from app.core.config import settings
 from app.helper.voice import VoiceHelper
-from app.helper.service import ServiceConfigHelper
 from app.log import logger
 from app.schemas import Notification, NotificationType
-from app.schemas.types import MessageChannel
 
 
 class SendVoiceMessageInput(BaseModel):
@@ -43,18 +41,6 @@ class SendVoiceMessageTool(MoviePilotTool):
             message = message[:40] + "..."
         return f"发送语音回复: {message}"
 
-    def _supports_real_voice_reply(self) -> bool:
-        channel = self._channel or ""
-        if channel == MessageChannel.Telegram.value:
-            return True
-        if channel != MessageChannel.Wechat.value:
-            return False
-        for config in ServiceConfigHelper.get_notification_configs():
-            if config.name != self._source:
-                continue
-            return (config.config or {}).get("WECHAT_MODE", "app") != "bot"
-        return False
-
     async def run(self, message: str, **kwargs) -> str:
         if not message:
             return "语音回复内容不能为空"
@@ -62,11 +48,23 @@ class SendVoiceMessageTool(MoviePilotTool):
         voice_path = None
         used_voice = False
         channel = self._channel or ""
-        if self._supports_real_voice_reply() and VoiceHelper.is_available("tts"):
+        reply_mode = VoiceHelper.resolve_reply_mode(
+            channel=channel,
+            source=self._source,
+        )
+        fallback_reason = "当前渠道不支持语音回复"
+        if not VoiceHelper.is_enabled():
+            fallback_reason = "当前未启用音频输入输出"
+        if (
+            reply_mode == VoiceHelper.REPLY_MODE_NATIVE
+            and VoiceHelper.is_available("tts")
+        ):
             voice_file = await asyncio.to_thread(VoiceHelper.synthesize_speech, message)
             if voice_file:
                 voice_path = str(voice_file)
                 used_voice = True
+        elif reply_mode == VoiceHelper.REPLY_MODE_NATIVE:
+            fallback_reason = "当前未配置可用的语音合成能力"
 
         logger.info(
             "执行工具: %s, channel=%s, use_voice=%s, text_len=%s",
@@ -85,7 +83,11 @@ class SendVoiceMessageTool(MoviePilotTool):
                 username=self._username,
                 text=message,
                 voice_path=voice_path,
-                voice_caption=message if settings.AI_VOICE_REPLY_WITH_TEXT else None,
+                voice_caption=(
+                    message
+                    if voice_path and settings.AI_VOICE_REPLY_WITH_TEXT
+                    else None
+                ),
             )
         )
         self._agent_context["user_reply_sent"] = True
@@ -93,4 +95,4 @@ class SendVoiceMessageTool(MoviePilotTool):
 
         if used_voice:
             return "语音回复已发送"
-        return "当前未使用语音通道，已自动回退为文字回复"
+        return f"{fallback_reason}，已自动回退为文字回复"