feat：maisak正确解析图片原始数据，reply信息

src/chat/image_system/image_manager.py

@@ -44,6 +44,12 @@ class ImageManager:
 
         logger.info("图片管理器初始化完成")
 
+    def _get_image_record(self, image_hash: str) -> Optional[Images]:
+        """根据哈希获取图片记录。"""
+        with get_db_session() as session:
+            statement = select(Images).filter_by(image_hash=image_hash, image_type=ImageType.IMAGE).limit(1)
+            return session.exec(statement).first()
+
     async def get_image_description(
         self,
         *,
@@ -76,9 +82,8 @@ class ImageManager:
             hash_str = hashlib.sha256(image_bytes).hexdigest()
 
         try:
-            with get_db_session() as session:
-                statement = select(Images).filter_by(image_hash=hash_str, image_type=ImageType.IMAGE).limit(1)
-                if record := session.exec(statement).first():
+            if record := self._get_image_record(hash_str):
+                if record.vlm_processed and record.description:
                     return record.description
         except Exception as e:
             logger.error(f"查询图片描述时发生错误: {e}")
@@ -86,12 +91,17 @@ class ImageManager:
         if not image_bytes:
             logger.warning("图片哈希值未找到，且未提供图片字节数据，返回无描述")
             return ""
+        try:
+            await self.ensure_image_saved(image_bytes)
+        except Exception as e:
+            logger.error(f"保存图片文件时发生错误: {e}")
+            return ""
         if not wait_for_build:
             self._schedule_description_build(hash_str, image_bytes)
             return ""
         logger.info(f"图片描述未找到，哈希值: {hash_str}，准备生成新描述")
         try:
-            image = await self.save_image_and_process(image_bytes)
+            image = await self.build_image_description(image_bytes)
             return image.description
         except Exception as e:
             logger.error(f"生成图片描述时发生错误: {e}")
@@ -120,7 +130,7 @@ class ImageManager:
         """
         try:
             logger.info(f"图片描述后台构建已开始，哈希值: {image_hash}")
-            await self.save_image_and_process(image_bytes)
+            await self.build_image_description(image_bytes)
             logger.info(f"图片描述后台构建完成，哈希值: {image_hash}")
         except Exception as exc:
             logger.warning(f"图片描述后台构建失败，哈希值: {image_hash}，错误: {exc}")
@@ -201,6 +211,7 @@ class ImageManager:
                     return False
                 record.description = image.description
                 record.last_used_time = datetime.now()
+                record.vlm_processed = image.vlm_processed
                 session.add(record)
                 logger.info(f"成功更新图片描述: {image.file_hash}，新描述: {image.description}")
         except Exception as e:
@@ -239,22 +250,13 @@ class ImageManager:
             return False
         return True
 
-    async def save_image_and_process(self, image_bytes: bytes) -> MaiImage:
-        """
-        保存图片并生成描述
-
-        Args:
-            image_bytes (bytes): 图片的字节数据
-        Returns:
-            return (MaiImage): 包含图片信息的 MaiImage 对象
-        Raises:
-            Exception: 如果在保存或处理过程中发生错误
-        """
+    async def ensure_image_saved(self, image_bytes: bytes) -> MaiImage:
+        """先保存图片记录，确保后续可以按哈希回填图片内容。"""
         hash_str = hashlib.sha256(image_bytes).hexdigest()
 
         try:
             with get_db_session() as session:
-                statement = select(Images).filter_by(image_hash=hash_str).limit(1)
+                statement = select(Images).filter_by(image_hash=hash_str, image_type=ImageType.IMAGE).limit(1)
                 if record := session.exec(statement).first():
                     logger.info(f"图片已存在于数据库中，哈希值: {hash_str}")
                     record.last_used_time = datetime.now()
@@ -270,18 +272,38 @@ class ImageManager:
         tmp_file_path = IMAGE_DIR / f"{hash_str}.tmp"
         with tmp_file_path.open("wb") as f:
             f.write(image_bytes)
-        mai_image = MaiImage(full_path=(IMAGE_DIR / f"{hash_str}.tmp"), image_bytes=image_bytes)
+        mai_image = MaiImage(full_path=tmp_file_path, image_bytes=image_bytes)
         await mai_image.calculate_hash_format()
+        if not self.register_image_to_db(mai_image):
+            raise RuntimeError(f"保存图片记录到数据库失败: {hash_str}")
+        return mai_image
+
+    async def build_image_description(self, image_bytes: bytes) -> MaiImage:
+        """在图片已保存的前提下生成或补齐图片描述。"""
+        mai_image = await self.ensure_image_saved(image_bytes)
+        if mai_image.vlm_processed and mai_image.description:
+            return mai_image
+
         desc = await self._generate_image_description(image_bytes, mai_image.image_format)
         mai_image.description = desc
         mai_image.vlm_processed = True
-        try:
-            self.register_image_to_db(mai_image)
-        except Exception as e:
-            logger.error(f"保存新图片记录到数据库时发生错误: {e}")
-            raise e
+        if not self.update_image_description(mai_image):
+            raise RuntimeError(f"更新图片描述失败: {mai_image.file_hash}")
         return mai_image
 
+    async def save_image_and_process(self, image_bytes: bytes) -> MaiImage:
+        """
+        保存图片并生成描述
+
+        Args:
+            image_bytes (bytes): 图片的字节数据
+        Returns:
+            return (MaiImage): 包含图片信息的 MaiImage 对象
+        Raises:
+            Exception: 如果在保存或处理过程中发生错误
+        """
+        return await self.build_image_description(image_bytes)
+
     def cleanup_invalid_descriptions_in_db(self):
         """
         清理数据库中无效的图片记录

src/chat/message_receive/bot.py

@@ -1,7 +1,6 @@
 """聊天消息入口与主链路调度。"""
 
 from contextlib import suppress
-from copy import deepcopy
 from typing import Any, Dict, List, Optional
 
 import os
@@ -550,9 +549,9 @@ class ChatBot:
             # if await self.handle_notice_message(message):
             #     pass
 
-            # 处理消息内容，识别表情包等二进制数据并转化为文本描述
-            if global_config.maisaka.direct_image_input:
-                message.maisaka_original_raw_message = deepcopy(message.raw_message)  # type: ignore[attr-defined]
+            # 处理消息内容，识别表情包等二进制数据并转化为文本描述。
+            # 如果 Maisaka 需要直接消费图片，会在后续构建 prompt 时按需回填图片二进制数据，
+            # 这里不再复制整条原始消息。
             # 入站主链优先保证消息尽快入队，避免图片、表情包、语音分析阻塞适配器超时。
             await message.process(
                 enable_heavy_media_analysis=False,

src/chat/message_receive/message.py

@@ -1,11 +1,10 @@
+import asyncio
 from asyncio import Task
 from typing import Dict, List, Sequence, Tuple
 
 from rich.traceback import install
 from sqlmodel import select
 
-import asyncio
-
 from src.common.logger import get_logger
 from src.common.database.database import get_db_session
 from src.common.database.database_model import Messages
@@ -36,6 +35,102 @@ class MsgIDMapping:
 
 
 class SessionMessage(MaiMessage):
+    
+    #便于调试的打印函数
+    def __str__(self) -> str:
+        """返回适合日志输出的消息摘要。"""
+        return self.to_debug_string()
+
+    def __repr__(self) -> str:
+        """返回适合调试场景的消息摘要。"""
+        return self.to_debug_string()
+
+    def to_debug_string(self) -> str:
+        """构建包含引用信息的调试字符串。
+
+        Returns:
+            str: 适合记录日志的消息摘要。
+        """
+        user_info = self.message_info.user_info
+        group_info = self.message_info.group_info
+        chat_type = "group" if group_info else "private"
+        group_id = group_info.group_id if group_info else None
+        group_name = group_info.group_name if group_info else None
+        component_summaries = [self._summarize_component(component) for component in self.raw_message.components]
+        raw_components = ", ".join(component_summaries) if component_summaries else "empty"
+
+        return (
+            "SessionMessage("
+            f"message_id={self.message_id!r}, "
+            f"platform={self.platform!r}, "
+            f"chat_type={chat_type!r}, "
+            f"group_id={group_id!r}, "
+            f"group_name={group_name!r}, "
+            f"user_id={user_info.user_id!r}, "
+            f"user_nickname={user_info.user_nickname!r}, "
+            f"user_cardname={user_info.user_cardname!r}, "
+            f"reply_to={self.reply_to!r}, "
+            f"processed_plain_text={self._truncate_text(self.processed_plain_text)}, "
+            f"raw_components=[{raw_components}]"
+            ")"
+        )
+
+    @staticmethod
+    def _truncate_text(text: str | None, max_length: int = 120) -> str:
+        """截断较长文本，避免日志过长。
+
+        Args:
+            text: 原始文本。
+            max_length: 最大保留长度。
+
+        Returns:
+            str: 截断后的文本表示。
+        """
+        if text is None:
+            return "None"
+        normalized_text = text.replace("\r", "\\r").replace("\n", "\\n")
+        if len(normalized_text) <= max_length:
+            return repr(normalized_text)
+        return repr(f"{normalized_text[:max_length]}...")
+
+    def _summarize_component(self, component: StandardMessageComponents) -> str:
+        """生成单个消息组件的调试摘要。
+
+        Args:
+            component: 消息组件对象。
+
+        Returns:
+            str: 组件摘要文本。
+        """
+        if isinstance(component, TextComponent):
+            return f"Text(text={self._truncate_text(component.text, 80)})"
+        if isinstance(component, ImageComponent):
+            return f"Image(content={self._truncate_text(component.content or None, 60)})"
+        if isinstance(component, EmojiComponent):
+            return f"Emoji(content={self._truncate_text(component.content or None, 60)})"
+        if isinstance(component, AtComponent):
+            target_name = component.target_user_cardname or component.target_user_nickname or component.target_user_id
+            return f"At(target={target_name!r})"
+        if isinstance(component, VoiceComponent):
+            return f"Voice(content={self._truncate_text(component.content or None, 60)})"
+        if isinstance(component, ReplyComponent):
+            sender_name = (
+                component.target_message_sender_cardname
+                or component.target_message_sender_nickname
+                or component.target_message_sender_id
+            )
+            return (
+                "Reply("
+                f"target_message_id={component.target_message_id!r}, "
+                f"target_sender={sender_name!r}, "
+                f"target_content={self._truncate_text(component.target_message_content, 80)}"
+                ")"
+            )
+        if isinstance(component, ForwardNodeComponent):
+            return f"ForwardNode(count={len(component.forward_components)})"
+        return f"{component.__class__.__name__}"
+    #便于调试的打印函数end
+
     async def process(
         self,
         *,

src/chat/replyer/group_generator.py

@@ -35,7 +35,7 @@ from src.services import llm_service as llm_api
 
 from src.chat.logger.plan_reply_logger import PlanReplyLogger
 from src.memory_system.memory_retrieval import init_memory_retrieval_sys, build_memory_retrieval_prompt
-from src.learners.jargon_explainer_old import explain_jargon_in_context, retrieve_concepts_with_jargon
+from src.learners.jargon_explainer_old import explain_jargon_in_context
 from src.chat.utils.common_utils import TempMethodsExpression
 
 init_memory_retrieval_sys()

src/chat/utils/statistic.py

@@ -15,7 +15,6 @@ from src.common.database.database import get_db_session
 from src.common.database.database_model import Messages, ModelUsage, OnlineTime, ToolRecord
 from src.manager.async_task_manager import AsyncTask
 from src.manager.local_store_manager import local_storage
-from src.config.config import global_config
 
 logger = get_logger("maibot_statistic")