feat: support torrent description filtering (#6172)

app/agent/tools/impl/_torrent_search_utils.py

@@ -127,8 +127,19 @@ def filter_contexts(items: List[Context],
     return filtered_items
 
 
-def simplify_search_result(context: Context, index: int) -> dict:
-    """精简单条搜索结果"""
+def simplify_search_result(
+    context: Context,
+    index: int,
+    include_description: bool = False,
+) -> dict:
+    """
+    精简单条搜索结果
+
+    :param context: 搜索结果上下文
+    :param index: 搜索结果在原始缓存中的序号
+    :param include_description: 是否返回种子简介
+    :return: 精简后的搜索结果
+    """
     simplified = {}
     torrent_info = context.torrent_info
     meta_info = context.meta_info
@@ -147,6 +158,8 @@ def simplify_search_result(context: Context, index: int) -> dict:
             "freedate_diff": torrent_info.freedate_diff,
             "pubdate": torrent_info.pubdate,
         }
+        if include_description:
+            simplified["torrent_info"]["description"] = torrent_info.description
 
     if media_info:
         simplified["media_info"] = {

app/agent/tools/impl/get_search_results.py

@@ -34,6 +34,14 @@ class GetSearchResultsInput(BaseModel):
         None,
         description="Regular expression pattern to filter torrent titles (e.g., '4K|2160p|UHD', '1080p.*BluRay')",
     )
+    content_pattern: Optional[str] = Field(
+        None,
+        description="Regular expression pattern to filter torrent titles, descriptions, and labels (e.g., '特效字幕|国语|DIY')",
+    )
+    include_description: Optional[bool] = Field(
+        False,
+        description="Whether to include torrent descriptions in returned results",
+    )
     show_filter_options: Optional[bool] = Field(
         False,
         description="Whether to return only optional filter options for re-checking available conditions",
@@ -45,6 +53,8 @@ class GetSearchResultsInput(BaseModel):
 
 
 class GetSearchResultsTool(MoviePilotTool):
+    """获取并筛选最近一次种子搜索结果"""
+
     name: str = "get_search_results"
     tags: list[str] = [
         ToolTag.Read,
@@ -54,6 +64,7 @@ class GetSearchResultsTool(MoviePilotTool):
     args_schema: Type[BaseModel] = GetSearchResultsInput
 
     def get_tool_message(self, **kwargs) -> Optional[str]:
+        """返回工具执行提示"""
         return "获取搜索结果"
 
     async def run(
@@ -66,13 +77,33 @@ class GetSearchResultsTool(MoviePilotTool):
         resolution: Optional[List[str]] = None,
         release_group: Optional[List[str]] = None,
         title_pattern: Optional[str] = None,
+        content_pattern: Optional[str] = None,
+        include_description: bool = False,
         show_filter_options: bool = False,
         page: Optional[int] = 1,
         **kwargs,
     ) -> str:
+        """
+        获取并筛选最近一次种子搜索结果
+
+        :param site: 站点名称筛选项
+        :param season: 季集筛选项
+        :param free_state: 促销状态筛选项
+        :param video_code: 视频编码筛选项
+        :param edition: 制作版本筛选项
+        :param resolution: 分辨率筛选项
+        :param release_group: 发布组筛选项
+        :param title_pattern: 仅匹配种子标题的正则表达式
+        :param content_pattern: 匹配种子标题、简介和标签的正则表达式
+        :param include_description: 是否在结果中返回种子简介
+        :param show_filter_options: 是否只返回可用筛选项
+        :param page: 分页页码
+        :param kwargs: 工具框架附加参数
+        :return: JSON 格式的搜索结果或错误提示
+        """
         page = max(1, page or 1)
         logger.info(
-            f"执行工具: {self.name}, 参数: site={site}, season={season}, free_state={free_state}, video_code={video_code}, edition={edition}, resolution={resolution}, release_group={release_group}, title_pattern={title_pattern}, show_filter_options={show_filter_options}, page={page}"
+            f"执行工具: {self.name}, 参数: site={site}, season={season}, free_state={free_state}, video_code={video_code}, edition={edition}, resolution={resolution}, release_group={release_group}, title_pattern={title_pattern}, content_pattern={content_pattern}, include_description={include_description}, show_filter_options={show_filter_options}, page={page}"
         )
 
         try:
@@ -87,14 +118,22 @@ class GetSearchResultsTool(MoviePilotTool):
                 }
                 return json.dumps(payload, ensure_ascii=False, indent=2)
 
-            regex_pattern = None
+            title_regex_pattern = None
             if title_pattern:
                 try:
-                    regex_pattern = re.compile(title_pattern, re.IGNORECASE)
+                    title_regex_pattern = re.compile(title_pattern, re.IGNORECASE)
                 except re.error as e:
                     logger.warning(f"正则表达式编译失败: {title_pattern}, 错误: {e}")
                     return f"正则表达式格式错误: {str(e)}"
 
+            content_regex_pattern = None
+            if content_pattern:
+                try:
+                    content_regex_pattern = re.compile(content_pattern, re.IGNORECASE)
+                except re.error as e:
+                    logger.warning(f"正则表达式编译失败: {content_pattern}, 错误: {e}")
+                    return f"正则表达式格式错误: {str(e)}"
+
             filtered_items = filter_contexts(
                 items=items,
                 site=site,
@@ -105,14 +144,29 @@ class GetSearchResultsTool(MoviePilotTool):
                 resolution=resolution,
                 release_group=release_group,
             )
-            if regex_pattern:
+            if title_regex_pattern:
                 filtered_items = [
                     item
                     for item in filtered_items
                     if item.torrent_info
                     and item.torrent_info.title
-                    and regex_pattern.search(item.torrent_info.title)
+                    and title_regex_pattern.search(item.torrent_info.title)
                 ]
+            if content_regex_pattern:
+                content_filtered_items = []
+                for item in filtered_items:
+                    torrent_info = item.torrent_info
+                    if not torrent_info:
+                        continue
+                    content_values = [torrent_info.title, torrent_info.description]
+                    content_values.extend(torrent_info.labels or [])
+                    if any(
+                        content_regex_pattern.search(str(value))
+                        for value in content_values
+                        if value
+                    ):
+                        content_filtered_items.append(item)
+                filtered_items = content_filtered_items
             if not filtered_items:
                 return "没有符合筛选条件的搜索结果，请调整筛选条件"
 
@@ -135,7 +189,11 @@ class GetSearchResultsTool(MoviePilotTool):
                 return f"第 {page} 页没有数据，共 {total_count} 条结果，共 {(total_count + page_size - 1) // page_size} 页。"
 
             results = [
-                simplify_search_result(item, index)
+                simplify_search_result(
+                    item,
+                    index,
+                    include_description=include_description,
+                )
                 for item, index in zip(page_items, page_indices)
             ]
             total_pages = (total_count + page_size - 1) // page_size

docs/mcp-api.md

@@ -214,6 +214,8 @@ AniList 榜单、探索、详情、人物和推荐接口优先通过 `anilist-ch
 
 媒体相关 MCP 工具（如 `query_media_detail`、`search_torrents`、`query_library_exists`、`add_subscribe`、`transfer_file`）接受 `tmdb_id`/`tmdbid`、`douban_id`/`doubanid`、`bangumi_id`/`bangumiid`、`anilist_id`/`anilistid`，也接受 `media_source` + `media_id`。工具返回的媒体、订阅、下载和整理记录会同步带回可用的四种专用 ID 及通用主身份。
 
+`get_search_results` 可使用 `title_pattern` 对种子标题执行正则筛选，也可使用 `content_pattern` 联合匹配种子标题、简介和标签。`title_pattern` 保持仅匹配标题的兼容语义；需要在结果中查看种子简介时，传入 `include_description=true`。两种正则参数与站点、分辨率等结构化筛选条件同时传入时按 AND 关系组合。
+
 #### Agent 自主定时任务工具
 
 以下工具用于管理会在指定时间重新唤醒 Agent 的持久化任务，均为管理员级工具：

skills/moviepilot-cli/SKILL.md

@@ -99,6 +99,9 @@ Filter values must come from the `filter_options` returned by `search_torrents`
 Fetch results with selected filters:
 `moviepilot tool run get_search_results resolution='1080p,2160p' free_state='免费,50%'`
 
+To filter subtitle, audio, DIY, translation, or release notes that may appear outside the title, use `content_pattern`. It matches the torrent title, description, and labels while `title_pattern` continues to match the title only. Set `include_description=true` when the description is needed to explain why a result matched:
+`moviepilot tool run get_search_results content_pattern='特效字幕|国语|DIY' include_description=true`
+
 If empty, tell the user which filter to relax and ask before retrying.
 
 #### 4. Present results as a numbered list

tests/test_agent_get_search_results_tool.py

@@ -0,0 +1,100 @@
+import asyncio
+import json
+from unittest.mock import AsyncMock, MagicMock, patch
+
+from app.agent.tools.impl._torrent_search_utils import simplify_search_result
+from app.agent.tools.impl.get_search_results import GetSearchResultsTool
+from app.core.context import Context, TorrentInfo
+
+
+def _build_context(
+    title: str,
+    *,
+    description: str = None,
+    labels: list = None,
+    index: int = 1,
+) -> Context:
+    """构造种子搜索结果上下文。"""
+    return Context(
+        torrent_info=TorrentInfo(
+            title=title,
+            description=description,
+            labels=labels or [],
+            enclosure=f"https://example.com/download/{index}",
+            size=1024,
+            seeders=index,
+            site_name="测试站点",
+        )
+    )
+
+
+def _run_tool(items: list[Context], **kwargs) -> str:
+    """使用指定缓存结果运行搜索结果工具。"""
+    search_chain = MagicMock()
+    search_chain.async_last_search_results = AsyncMock(return_value=items)
+    with patch(
+        "app.agent.tools.impl.get_search_results.SearchChain",
+        return_value=search_chain,
+    ):
+        return asyncio.run(
+            GetSearchResultsTool(session_id="session-1", user_id="10001").run(
+                **kwargs
+            )
+        )
+
+
+def test_simplify_search_result_only_includes_description_when_requested():
+    """精简结果应按参数控制简介输出，避免默认增加上下文长度。"""
+    context = _build_context("Movie.2026.1080p", description="简繁特效字幕")
+
+    default_result = simplify_search_result(context, 1)
+    detailed_result = simplify_search_result(context, 1, include_description=True)
+
+    assert "description" not in default_result["torrent_info"]
+    assert detailed_result["torrent_info"]["description"] == "简繁特效字幕"
+
+
+def test_content_pattern_matches_title_description_and_labels():
+    """内容正则应联合匹配标题、简介和标签，并可返回命中的简介。"""
+    items = [
+        _build_context("Movie.Special.Effect.2026", description="普通字幕", index=1),
+        _build_context("Movie.2026.1080p", description="简繁特效字幕", index=2),
+        _build_context("Movie.2026.2160p", description="国语音轨", labels=["官译"], index=3),
+        _build_context("Movie.2026.WEB-DL", description="英文字幕", index=4),
+    ]
+
+    result = _run_tool(
+        items,
+        content_pattern="Special.Effect|特效字幕|官译",
+        include_description=True,
+    )
+    payload = json.loads(result)
+
+    assert payload["total_count"] == 3
+    assert [item["torrent_info"]["description"] for item in payload["results"]] == [
+        "普通字幕",
+        "简繁特效字幕",
+        "国语音轨",
+    ]
+
+
+def test_title_pattern_keeps_title_only_matching_semantics():
+    """标题正则不应因新增内容筛选而匹配简介或标签。"""
+    items = [
+        _build_context("Movie.特效.2026", description="普通字幕", index=1),
+        _build_context("Movie.2026.1080p", description="简繁特效字幕", index=2),
+        _build_context("Movie.2026.2160p", labels=["特效"], index=3),
+    ]
+
+    result = _run_tool(items, title_pattern="特效", include_description=True)
+    payload = json.loads(result)
+
+    assert payload["total_count"] == 1
+    assert payload["results"][0]["torrent_info"]["title"] == "Movie.特效.2026"
+
+
+def test_invalid_content_pattern_returns_validation_message():
+    """非法内容正则应返回明确错误，不进入搜索结果筛选。"""
+    result = _run_tool([_build_context("Movie.2026")], content_pattern="[")
+
+    assert result.startswith("正则表达式格式错误:")