feat: Enhance Reply chain handling for Record components (#8527)

* Enhance Reply chain handling for Record components

Added processing for Record components within Reply chains, including WAV conversion and STT functionality.

* Refactor STT processing for Record components

* Add STT record function for voice-to-text processing

* Update stage.py

* Update stage.py

* Update stage.py

Author: tjc6666666666666

astrbot/core/pipeline/preprocess_stage/stage.py

@@ -4,7 +4,7 @@
 from collections.abc import AsyncGenerator
 
 from astrbot.core import logger
-from astrbot.core.message.components import Image, Plain, Record
+from astrbot.core.message.components import Image, Plain, Record, Reply
 from astrbot.core.platform.astr_message_event import AstrMessageEvent
 from astrbot.core.utils.media_utils import ensure_wav
 
@@ -80,6 +80,24 @@ async def process(
                 except Exception as e:
                     logger.warning(f"Voice processing failed: {e}")
 
+        # Also process Record components inside Reply chains (wav conversion)
+        for component in event.get_messages():
+            if isinstance(component, Reply) and component.chain:
+                for idx, reply_comp in enumerate(component.chain):
+                    if isinstance(reply_comp, Record):
+                        try:
+                            original_path = await reply_comp.convert_to_file_path()
+                            record_path = await ensure_wav(original_path)
+                            if record_path != original_path:
+                                event.track_temporary_local_file(record_path)
+                            reply_comp.file = record_path
+                            reply_comp.path = record_path
+                            component.chain[idx] = reply_comp
+                        except Exception as e:
+                            logger.warning(
+                                f"Voice processing in reply chain failed: {e}"
+                            )
+
         # STT
         if self.stt_settings.get("enable", False):
             # TODO: 独立
@@ -90,27 +108,53 @@ async def process(
                     f"会话 {event.unified_msg_origin} 未配置语音转文本模型。",
                 )
                 return
+
+            async def _stt_record(record_comp: Record, is_reply: bool = False):
+                """对单个 Record 组件执行语音转文本，成功返回 Plain，失败返回 None。"""
+                prefix = "引用消息" if is_reply else ""
+                try:
+                    path = await record_comp.convert_to_file_path()
+                except Exception as e:
+                    logger.warning(f"获取{prefix}语音路径失败: {e}")
+                    return None
+
+                retry = 5
+                for i in range(retry):
+                    try:
+                        result = await stt_provider.get_text(audio_url=path)
+                        if result:
+                            suffix = "(引用消息)" if is_reply else ""
+                            logger.info(f"语音转文本{suffix}结果: " + result)
+                            return Plain(result)
+                        break
+                    except FileNotFoundError:
+                        # napcat workaround: file may not be ready immediately
+                        logger.debug(f"文件尚未就绪 ({path})，重试 {i + 1}/{retry}")
+                        await asyncio.sleep(0.5)
+                        continue
+                    except BaseException as e:
+                        logger.error(traceback.format_exc())
+                        suffix = "(引用消息)" if is_reply else ""
+                        logger.error(f"语音转文本{suffix}失败: {e}")
+                        break
+                return None
+
             message_chain = event.get_messages()
             for idx, component in enumerate(message_chain):
                 if isinstance(component, Record):
-                    path = await component.convert_to_file_path()
-                    retry = 5
-                    for i in range(retry):
-                        try:
-                            result = await stt_provider.get_text(audio_url=path)
-                            if result:
-                                logger.info("语音转文本结果: " + result)
-                                message_chain[idx] = Plain(result)
-                                event.message_str += result
-                                event.message_obj.message_str += result
-                            break
-                        except FileNotFoundError as e:
-                            # napcat workaround
-                            logger.warning(e)
-                            logger.warning(f"重试中: {i + 1}/{retry}")
-                            await asyncio.sleep(0.5)
-                            continue
-                        except BaseException as e:
-                            logger.error(traceback.format_exc())
-                            logger.error(f"语音转文本失败: {e}")
-                            break
+                    plain_comp = await _stt_record(component)
+                    if plain_comp:
+                        message_chain[idx] = plain_comp
+                        event.message_str += plain_comp.text
+                        event.message_obj.message_str += plain_comp.text
+
+            # Also STT for Record components inside Reply chains
+            for component in event.get_messages():
+                if isinstance(component, Reply) and component.chain:
+                    for idx, reply_comp in enumerate(component.chain):
+                        if isinstance(reply_comp, Record):
+                            plain_comp = await _stt_record(reply_comp, is_reply=True)
+                            if plain_comp:
+                                component.chain[idx] = plain_comp
+                                event.message_str += plain_comp.text
+                                event.message_obj.message_str += plain_comp.text