Merge remote-tracking branch 'origin/v2' into v2

app/agent/__init__.py

@@ -1,7 +1,6 @@
 """MoviePilot AI智能体实现"""
 
 import asyncio
-import threading
 from typing import Dict, List, Any
 
 from langchain.agents import AgentExecutor, create_openai_tools_agent
@@ -21,9 +20,6 @@ from app.helper.message import MessageHelper
 from app.log import logger
 from app.schemas import Notification
 
-# 用于保护环境变量修改的线程锁
-_env_lock = threading.Lock()
-
 
 class AgentChain(ChainBase):
     pass
@@ -75,36 +71,21 @@ class MoviePilotAgent:
         api_key = settings.LLM_API_KEY
 
         if provider == "google":
-            import os
-            from contextlib import contextmanager
-            from langchain_google_genai import ChatGoogleGenerativeAI
-
-            # 使用线程锁保护的临时环境变量配置
-            @contextmanager
-            def _temp_proxy_env():
-                """线程安全的临时设置代理环境变量的上下文管理器"""
-                with _env_lock:
-                    old_http = os.environ.get("HTTP_PROXY")
-                    old_https = os.environ.get("HTTPS_PROXY")
-                    try:
-                        if settings.PROXY_HOST:
-                            os.environ["HTTP_PROXY"] = settings.PROXY_HOST
-                            os.environ["HTTPS_PROXY"] = settings.PROXY_HOST
-                        yield
-                    finally:
-                        # 恢复原始环境变量
-                        if old_http is not None:
-                            os.environ["HTTP_PROXY"] = old_http
-                        elif "HTTP_PROXY" in os.environ:
-                            del os.environ["HTTP_PROXY"]
-
-                        if old_https is not None:
-                            os.environ["HTTPS_PROXY"] = old_https
-                        elif "HTTPS_PROXY" in os.environ:
-                            del os.environ["HTTPS_PROXY"]
-
-            # 在临时环境变量中初始化 ChatGoogleGenerativeAI
-            with _temp_proxy_env():
+            if settings.PROXY_HOST:
+                from langchain_openai import ChatOpenAI
+                return ChatOpenAI(
+                    model=settings.LLM_MODEL,
+                    api_key=api_key,
+                    max_retries=3,
+                    base_url="https://generativelanguage.googleapis.com/v1beta/openai",
+                    temperature=settings.LLM_TEMPERATURE,
+                    streaming=True,
+                    callbacks=[self.callback_handler],
+                    stream_usage=True,
+                    openai_proxy=settings.PROXY_HOST
+                )
+            else:
+                from langchain_google_genai import ChatGoogleGenerativeAI
                 return ChatGoogleGenerativeAI(
                     model=settings.LLM_MODEL,
                     google_api_key=api_key,

app/agent/tools/factory.py

@@ -21,6 +21,8 @@ from app.agent.tools.impl.query_popular_subscribes import QueryPopularSubscribes
 from app.agent.tools.impl.query_subscribe_history import QuerySubscribeHistoryTool
 from app.agent.tools.impl.delete_subscribe import DeleteSubscribeTool
 from app.agent.tools.impl.search_media import SearchMediaTool
+from app.agent.tools.impl.search_person import SearchPersonTool
+from app.agent.tools.impl.search_person_credits import SearchPersonCreditsTool
 from app.agent.tools.impl.recognize_media import RecognizeMediaTool
 from app.agent.tools.impl.scrape_metadata import ScrapeMetadataTool
 from app.agent.tools.impl.query_episode_schedule import QueryEpisodeScheduleTool
@@ -53,6 +55,8 @@ class MoviePilotToolFactory:
         tools = []
         tool_definitions = [
             SearchMediaTool,
+            SearchPersonTool,
+            SearchPersonCreditsTool,
             RecognizeMediaTool,
             ScrapeMetadataTool,
             QueryEpisodeScheduleTool,

app/agent/tools/impl/add_subscribe.py

@@ -33,6 +33,8 @@ class AddSubscribeInput(BaseModel):
                                   description="Effect filter as regular expression (optional, e.g., 'HDR|DV|SDR')")
     filter_groups: Optional[List[str]] = Field(None,
                                                description="List of filter rule group names to apply (optional, use query_rule_groups tool to get available rule groups)")
+    sites: Optional[List[int]] = Field(None,
+                                       description="List of site IDs to search from (optional, use query_sites tool to get available site IDs)")
 
 
 class AddSubscribeTool(MoviePilotTool):
@@ -61,12 +63,13 @@ class AddSubscribeTool(MoviePilotTool):
                   season: Optional[int] = None, tmdb_id: Optional[str] = None,
                   start_episode: Optional[int] = None, total_episode: Optional[int] = None,
                   quality: Optional[str] = None, resolution: Optional[str] = None,
-                  effect: Optional[str] = None, filter_groups: Optional[List[str]] = None, **kwargs) -> str:
+                  effect: Optional[str] = None, filter_groups: Optional[List[str]] = None,
+                  sites: Optional[List[int]] = None, **kwargs) -> str:
         logger.info(
             f"执行工具: {self.name}, 参数: title={title}, year={year}, media_type={media_type}, "
             f"season={season}, tmdb_id={tmdb_id}, start_episode={start_episode}, "
             f"total_episode={total_episode}, quality={quality}, resolution={resolution}, "
-            f"effect={effect}, filter_groups={filter_groups}")
+            f"effect={effect}, filter_groups={filter_groups}, sites={sites}")
 
         try:
             subscribe_chain = SubscribeChain()
@@ -92,6 +95,8 @@ class AddSubscribeTool(MoviePilotTool):
                 subscribe_kwargs['effect'] = effect
             if filter_groups:
                 subscribe_kwargs['filter_groups'] = filter_groups
+            if sites:
+                subscribe_kwargs['sites'] = sites
 
             sid, message = await subscribe_chain.async_add(
                 mtype=MediaType(media_type),
@@ -118,6 +123,8 @@ class AddSubscribeTool(MoviePilotTool):
                         params.append(f"特效过滤: {effect}")
                     if filter_groups:
                         params.append(f"规则组: {', '.join(filter_groups)}")
+                    if sites:
+                        params.append(f"站点: {', '.join(map(str, sites))}")
                     if params:
                         result_msg += f"\n配置参数: {', '.join(params)}"
                 return result_msg

app/agent/tools/impl/query_media_library.py

@@ -1,7 +1,7 @@
 """查询媒体库工具"""
 
 import json
-from typing import Optional, List, Type
+from typing import Optional, Type
 
 from pydantic import BaseModel, Field
 
@@ -9,7 +9,6 @@ from app.agent.tools.base import MoviePilotTool
 from app.chain.mediaserver import MediaServerChain
 from app.core.context import MediaInfo
 from app.log import logger
-from app.schemas import MediaServerItem
 from app.schemas.types import MediaType
 
 

app/agent/tools/impl/search_person.py

@@ -0,0 +1,83 @@
+"""搜索人物工具"""
+
+import json
+from typing import Optional, Type
+
+from pydantic import BaseModel, Field
+
+from app.agent.tools.base import MoviePilotTool
+from app.chain.media import MediaChain
+from app.log import logger
+
+
+class SearchPersonInput(BaseModel):
+    """搜索人物工具的输入参数模型"""
+    explanation: str = Field(..., description="Clear explanation of why this tool is being used in the current context")
+    name: str = Field(..., description="The name of the person to search for (e.g., 'Tom Hanks', '周杰伦')")
+
+
+class SearchPersonTool(MoviePilotTool):
+    name: str = "search_person"
+    description: str = "Search for person information including actors, directors, etc. Supports searching by name. Returns detailed person information from TMDB, Douban, or Bangumi database."
+    args_schema: Type[BaseModel] = SearchPersonInput
+
+    def get_tool_message(self, **kwargs) -> Optional[str]:
+        """根据搜索参数生成友好的提示消息"""
+        name = kwargs.get("name", "")
+        return f"正在搜索人物: {name}"
+
+    async def run(self, name: str, **kwargs) -> str:
+        logger.info(f"执行工具: {self.name}, 参数: name={name}")
+
+        try:
+            media_chain = MediaChain()
+            # 使用 MediaChain.async_search_persons 方法搜索人物
+            persons = await media_chain.async_search_persons(name=name)
+
+            if persons:
+                # 限制最多30条结果
+                total_count = len(persons)
+                limited_persons = persons[:30]
+                # 精简字段，只保留关键信息
+                simplified_results = []
+                for person in limited_persons:
+                    simplified = {
+                        "name": person.name,
+                        "id": person.id,
+                        "source": person.source,
+                        "profile_path": person.profile_path,
+                        "original_name": person.original_name,
+                        "known_for_department": person.known_for_department,
+                        "popularity": person.popularity,
+                        "biography": person.biography[:200] + "..." if person.biography and len(person.biography) > 200 else person.biography,
+                        "birthday": person.birthday,
+                        "deathday": person.deathday,
+                        "place_of_birth": person.place_of_birth,
+                        "gender": person.gender,
+                        "imdb_id": person.imdb_id,
+                        "also_known_as": person.also_known_as[:5] if person.also_known_as else [],  # 限制别名数量
+                    }
+                    # 添加豆瓣特有字段
+                    if person.source == "douban":
+                        simplified["url"] = person.url
+                        simplified["avatar"] = person.avatar
+                        simplified["latin_name"] = person.latin_name
+                        simplified["roles"] = person.roles[:5] if person.roles else []  # 限制角色数量
+                    # 添加Bangumi特有字段
+                    if person.source == "bangumi":
+                        simplified["career"] = person.career
+                        simplified["relation"] = person.relation
+                    
+                    simplified_results.append(simplified)
+                
+                result_json = json.dumps(simplified_results, ensure_ascii=False, indent=2)
+                # 如果结果被裁剪，添加提示信息
+                if total_count > 30:
+                    return f"注意：搜索结果共找到 {total_count} 条，为节省上下文空间，仅显示前 30 条结果。\n\n{result_json}"
+                return result_json
+            else:
+                return f"未找到相关人物信息: {name}"
+        except Exception as e:
+            error_message = f"搜索人物失败: {str(e)}"
+            logger.error(f"搜索人物失败: {e}", exc_info=True)
+            return error_message

app/agent/tools/impl/search_person_credits.py

@@ -0,0 +1,85 @@
+"""搜索演员参演作品工具"""
+
+import json
+from typing import Optional, Type
+
+from pydantic import BaseModel, Field
+
+from app.agent.tools.base import MoviePilotTool
+from app.chain.douban import DoubanChain
+from app.chain.tmdb import TmdbChain
+from app.chain.bangumi import BangumiChain
+from app.log import logger
+
+
+class SearchPersonCreditsInput(BaseModel):
+    """搜索演员参演作品工具的输入参数模型"""
+    explanation: str = Field(..., description="Clear explanation of why this tool is being used in the current context")
+    person_id: int = Field(..., description="The ID of the person/actor to search for credits (e.g., 31 for Tom Hanks in TMDB)")
+    source: str = Field(..., description="The data source: 'tmdb' for TheMovieDB, 'douban' for Douban, 'bangumi' for Bangumi")
+    page: Optional[int] = Field(1, description="Page number for pagination (default: 1)")
+
+
+class SearchPersonCreditsTool(MoviePilotTool):
+    name: str = "search_person_credits"
+    description: str = "Search for films and TV shows that a person/actor has appeared in (filmography). Supports searching by person ID from TMDB, Douban, or Bangumi database. Returns a list of media works the person has participated in."
+    args_schema: Type[BaseModel] = SearchPersonCreditsInput
+
+    def get_tool_message(self, **kwargs) -> Optional[str]:
+        """根据搜索参数生成友好的提示消息"""
+        person_id = kwargs.get("person_id", "")
+        source = kwargs.get("source", "")
+        return f"正在搜索人物参演作品: {source} ID {person_id}"
+
+    async def run(self, person_id: int, source: str, page: Optional[int] = 1, **kwargs) -> str:
+        logger.info(f"执行工具: {self.name}, 参数: person_id={person_id}, source={source}, page={page}")
+
+        try:
+            # 根据source选择相应的chain
+            if source.lower() == "tmdb":
+                tmdb_chain = TmdbChain()
+                medias = await tmdb_chain.async_person_credits(person_id=person_id, page=page)
+            elif source.lower() == "douban":
+                douban_chain = DoubanChain()
+                medias = await douban_chain.async_person_credits(person_id=person_id, page=page)
+            elif source.lower() == "bangumi":
+                bangumi_chain = BangumiChain()
+                medias = await bangumi_chain.async_person_credits(person_id=person_id)
+            else:
+                return f"不支持的数据源: {source}。支持的数据源: tmdb, douban, bangumi"
+
+            if medias:
+                # 限制最多30条结果
+                total_count = len(medias)
+                limited_medias = medias[:30]
+                # 精简字段，只保留关键信息
+                simplified_results = []
+                for media in limited_medias:
+                    simplified = {
+                        "title": media.title,
+                        "en_title": media.en_title,
+                        "year": media.year,
+                        "type": media.type.value if media.type else None,
+                        "season": media.season,
+                        "tmdb_id": media.tmdb_id,
+                        "imdb_id": media.imdb_id,
+                        "douban_id": media.douban_id,
+                        "overview": media.overview[:200] + "..." if media.overview and len(media.overview) > 200 else media.overview,
+                        "vote_average": media.vote_average,
+                        "poster_path": media.poster_path,
+                        "backdrop_path": media.backdrop_path,
+                        "detail_link": media.detail_link
+                    }
+                    simplified_results.append(simplified)
+                
+                result_json = json.dumps(simplified_results, ensure_ascii=False, indent=2)
+                # 如果结果被裁剪，添加提示信息
+                if total_count > 30:
+                    return f"注意：搜索结果共找到 {total_count} 条，为节省上下文空间，仅显示前 30 条结果。\n\n{result_json}"
+                return result_json
+            else:
+                return f"未找到人物 ID {person_id} ({source}) 的参演作品"
+        except Exception as e:
+            error_message = f"搜索演员参演作品失败: {str(e)}"
+            logger.error(f"搜索演员参演作品失败: {e}", exc_info=True)
+            return error_message

app/agent/tools/impl/search_web.py

@@ -64,7 +64,8 @@ class SearchWebTool(MoviePilotTool):
             logger.error(f"搜索网络内容失败: {e}", exc_info=True)
             return error_message
 
-    async def _search_duckduckgo_api(self, query: str, max_results: int) -> list:
+    @staticmethod
+    async def _search_duckduckgo_api(query: str, max_results: int) -> list:
         """
         使用DuckDuckGo API进行搜索
         
@@ -143,7 +144,8 @@ class SearchWebTool(MoviePilotTool):
             logger.warning(f"DuckDuckGo API搜索失败: {e}")
             return []
 
-    def _format_and_truncate_results(self, results: list, max_results: int) -> dict:
+    @staticmethod
+    def _format_and_truncate_results(results: list, max_results: int) -> dict:
         """
         格式化并裁剪搜索结果以避免占用过多上下文