feat: 添加选项必须检索长期记忆

.gitea/workflows/build.yaml

@@ -0,0 +1,32 @@
+name: Build and Push Docker Image
+
+on:
+  push:
+    branches:
+      - dev
+      - gitea
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Login to Docker Registry
+        uses: docker/login-action@v3
+        with:
+          registry: docker.gardel.top
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+      - name: Build and Push Docker Image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: ./Dockerfile
+          push: true
+          tags: docker.gardel.top/gardel/mofox:dev
+          build-args: |
+            BUILD_DATE=$(date -u +'%Y-%m-%dT%H:%M:%SZ')
+            VCS_REF=${{ github.sha }}

.github/workflows/docker-image.yml

@@ -1,149 +0,0 @@
-name: Docker Build and Push
-
-on:
-  push:
-    branches:
-      - master
-      - dev
-    tags:
-      - "v*.*.*"
-      - "v*"
-      - "*.*.*"
-      - "*.*.*-*"
-  workflow_dispatch: # 允许手动触发工作流
-
-# Workflow's jobs
-jobs:
-  build-amd64:
-    name: Build AMD64 Image
-    runs-on: ubuntu-24.04
-    outputs:
-      digest: ${{ steps.build.outputs.digest }}
-    steps:
-      - name: Check out git repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-        with:
-          buildkitd-flags: --debug
-
-      # Log in docker hub
-      - name: Log in to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      # Generate metadata for Docker images
-      - name: Docker meta
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ secrets.DOCKERHUB_USERNAME }}/mofox
-
-      # Build and push AMD64 image by digest
-      - name: Build and push AMD64
-        id: build
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          platforms: linux/amd64
-          labels: ${{ steps.meta.outputs.labels }}
-          file: ./Dockerfile
-          cache-from: type=registry,ref=${{ secrets.DOCKERHUB_USERNAME }}/mofox:amd64-buildcache
-          cache-to: type=registry,ref=${{ secrets.DOCKERHUB_USERNAME }}/mofox:amd64-buildcache,mode=max
-          outputs: type=image,name=${{ secrets.DOCKERHUB_USERNAME }}/mofox,push-by-digest=true,name-canonical=true,push=true
-          build-args: |
-            BUILD_DATE=$(date -u +'%Y-%m-%dT%H:%M:%SZ')
-            VCS_REF=${{ github.sha }}
-
-  build-arm64:
-    name: Build ARM64 Image
-    runs-on: ubuntu-24.04-arm
-    outputs:
-      digest: ${{ steps.build.outputs.digest }}
-    steps:
-      - name: Check out git repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-        with:
-          buildkitd-flags: --debug
-
-      # Log in docker hub
-      - name: Log in to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      # Generate metadata for Docker images
-      - name: Docker meta
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ secrets.DOCKERHUB_USERNAME }}/mofox
-
-      # Build and push ARM64 image by digest
-      - name: Build and push ARM64
-        id: build
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          platforms: linux/arm64/v8
-          labels: ${{ steps.meta.outputs.labels }}
-          file: ./Dockerfile
-          cache-from: type=registry,ref=${{ secrets.DOCKERHUB_USERNAME }}/mofox:arm64-buildcache
-          cache-to: type=registry,ref=${{ secrets.DOCKERHUB_USERNAME }}/mofox:arm64-buildcache,mode=max
-          outputs: type=image,name=${{ secrets.DOCKERHUB_USERNAME }}/mofox,push-by-digest=true,name-canonical=true,push=true
-          build-args: |
-            BUILD_DATE=$(date -u +'%Y-%m-%dT%H:%M:%SZ')
-            VCS_REF=${{ github.sha }}
-
-  create-manifest:
-    name: Create Multi-Arch Manifest
-    runs-on: ubuntu-24.04
-    needs:
-      - build-amd64
-      - build-arm64
-    steps:
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      # Log in docker hub
-      - name: Log in to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      # Generate metadata for Docker images
-      - name: Docker meta
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ secrets.DOCKERHUB_USERNAME }}/mofox
-          tags: |
-            type=ref,event=branch
-            type=ref,event=tag
-            type=raw,value=latest,enable=${{ github.ref == 'refs/heads/main' }}
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-            type=semver,pattern={{major}}
-            type=sha,prefix=${{ github.ref_name }}-,enable=${{ github.ref_type == 'branch' }}
-
-      - name: Create and Push Manifest
-        run: |
-          # 为每个标签创建多架构镜像
-          for tag in $(echo "${{ steps.meta.outputs.tags }}" | tr '\n' ' '); do
-            echo "Creating manifest for $tag"
-            docker buildx imagetools create -t $tag \
-              ${{ secrets.DOCKERHUB_USERNAME }}/mofox@${{ needs.build-amd64.outputs.digest }} \
-              ${{ secrets.DOCKERHUB_USERNAME }}/mofox@${{ needs.build-arm64.outputs.digest }}
-          done

Dockerfile

@@ -9,6 +9,10 @@ RUN apt-get update && apt-get install -y build-essential
 # 复制依赖列表和锁文件
 COPY pyproject.toml uv.lock ./
 
+COPY --from=mwader/static-ffmpeg:latest /ffmpeg /usr/local/bin/ffmpeg
+COPY --from=mwader/static-ffmpeg:latest /ffprobe /usr/local/bin/ffprobe
+RUN ldconfig && ffmpeg -version
+
 # 安装依赖（使用 --frozen 确保使用锁文件中的版本）
 RUN uv sync --frozen --no-dev
 

src/chat/emoji_system/emoji_manager.py

@@ -4,6 +4,7 @@ import binascii
 import hashlib
 import io
 import json
+import json_repair
 import os
 import random
 import re
@@ -1022,6 +1023,15 @@ class EmojiManager:
     -   必须是表情包，非普通截图。
     -   图中文字不超过5个。
 请确保你的最终输出是严格的JSON对象，不要添加任何额外解释或文本。
+输出格式:
+```json
+{{
+  "detailed_description": "",
+  "keywords": [],
+  "refined_sentence": "",
+  "is_compliant": true
+}}
+```
 """
 
                 image_data_for_vlm, image_format_for_vlm = image_base64, image_format
@@ -1041,16 +1051,14 @@ class EmojiManager:
                         if not vlm_response_str:
                             continue
 
-                        match = re.search(r"\{.*\}", vlm_response_str, re.DOTALL)
-                        if match:
-                            vlm_response_json = json.loads(match.group(0))
-                            description = vlm_response_json.get("detailed_description", "")
-                            emotions = vlm_response_json.get("keywords", [])
-                            refined_description = vlm_response_json.get("refined_sentence", "")
-                            is_compliant = vlm_response_json.get("is_compliant", False)
-                            if description and emotions and refined_description:
-                                logger.info("[VLM分析] 成功解析VLM返回的JSON数据。")
-                                break
+                        vlm_response_json = self._parse_json_response(vlm_response_str)
+                        description = vlm_response_json.get("detailed_description", "")
+                        emotions = vlm_response_json.get("keywords", [])
+                        refined_description = vlm_response_json.get("refined_sentence", "")
+                        is_compliant = vlm_response_json.get("is_compliant", False)
+                        if description and emotions and refined_description:
+                            logger.info("[VLM分析] 成功解析VLM返回的JSON数据。")
+                            break
                         logger.warning("[VLM分析] VLM返回的JSON数据不完整或格式错误，准备重试。")
                     except (json.JSONDecodeError, AttributeError) as e:
                         logger.error(f"VLM JSON解析失败 (第 {i+1}/3 次): {e}")
@@ -1195,6 +1203,29 @@ class EmojiManager:
                     logger.error(f"[错误] 删除异常处理文件时出错: {remove_error}")
             return False
 
+    @classmethod
+    def _parse_json_response(cls, response: str) -> dict[str, Any] | None:
+        """解析 LLM 的 JSON 响应"""
+        try:
+            # 尝试提取 JSON 代码块
+            json_match = re.search(r"```json\s*(.*?)\s*```", response, re.DOTALL)
+            if json_match:
+                json_str = json_match.group(1)
+            else:
+                # 尝试直接解析
+                json_str = response.strip()
+
+            # 移除可能的注释
+            json_str = re.sub(r"//.*", "", json_str)
+            json_str = re.sub(r"/\*.*?\*/", "", json_str, flags=re.DOTALL)
+
+            data = json_repair.loads(json_str)
+            return data
+
+        except json.JSONDecodeError as e:
+            logger.warning(f"JSON 解析失败: {e}, 响应: {response[:200]}")
+            return None
+
 
 emoji_manager = None
 

src/chat/replyer/default_generator.py

@@ -614,7 +614,7 @@ class DefaultReplyer:
             # 使用统一管理器的智能检索（Judge模型决策）
             search_result = await unified_manager.search_memories(
                 query_text=query_text,
-                use_judge=True,
+                use_judge=global_config.memory.use_judge,
                 recent_chat_history=chat_history,  # 传递最近聊天历史
             )
 
@@ -1799,8 +1799,9 @@ class DefaultReplyer:
             )
 
             if content:
-                # 移除 [SPLIT] 标记，防止消息被分割
-                content = content.replace("[SPLIT]", "")
+                if not global_config.response_splitter.enable or global_config.response_splitter.split_mode != 'llm':
+                    # 移除 [SPLIT] 标记，防止消息被分割
+                    content = content.replace("[SPLIT]", "")
 
                 # 应用统一的格式过滤器
                 from src.chat.utils.utils import filter_system_format_content

src/config/official_configs.py

@@ -508,6 +508,7 @@ class MemoryConfig(ValidatedConfigBase):
     short_term_decay_factor: float = Field(default=0.98, description="衰减因子")
 
     # 长期记忆层配置
+    use_judge: bool = Field(default=True, description="使用评判模型决定是否检索长期记忆")
     long_term_batch_size: int = Field(default=10, description="批量转移大小")
     long_term_decay_factor: float = Field(default=0.95, description="衰减因子")
     long_term_auto_transfer_interval: int = Field(default=60, description="自动转移间隔（秒）")

src/memory_graph/short_term_manager.py

@@ -11,6 +11,7 @@ import asyncio
 import json
 import re
 import uuid
+import json_repair
 from pathlib import Path
 from typing import Any
 
@@ -186,8 +187,8 @@ class ShortTermMemoryManager:
   "importance": 0.7,
   "attributes": {{
     "time": "时间信息",
-    "attribute1": "其他属性1"
-    "attribute2": "其他属性2"
+    "attribute1": "其他属性1",
+    "attribute2": "其他属性2",
     ...
   }}
 }}
@@ -530,7 +531,7 @@ class ShortTermMemoryManager:
             json_str = re.sub(r"//.*", "", json_str)
             json_str = re.sub(r"/\*.*?\*/", "", json_str, flags=re.DOTALL)
 
-            data = json.loads(json_str)
+            data = json_repair.loads(json_str)
             return data
 
         except json.JSONDecodeError as e:

src/plugins/built_in/kokoro_flow_chatter/context_builder.py

@@ -235,7 +235,7 @@ class KFCContextBuilder:
 
             search_result = await unified_manager.search_memories(
                 query_text=query_text,
-                use_judge=True,
+                use_judge=config.memory.use_judge,
                 recent_chat_history=chat_history,
             )
 

template/bot_config_template.toml

@@ -1,5 +1,5 @@
 [inner]
-version = "7.9.8"
+version = "7.9.9"
 
 #----以下是给开发人员阅读的，如果你只是部署了MoFox-Bot，不需要阅读----
 #如果你想要修改配置文件，请递增version的值
@@ -311,6 +311,7 @@ short_term_search_top_k = 5 # 搜索时返回的最大数量
 short_term_decay_factor = 0.98 # 衰减因子
 
 # 长期记忆层配置
+use_judge = true # 使用评判模型决定是否检索长期记忆
 long_term_batch_size = 10 # 批量转移大小
 long_term_decay_factor = 0.95 # 衰减因子
 long_term_auto_transfer_interval = 180 # 自动转移间隔（秒）