diff --git a/plugins.v2/lexiannot/__init__.py b/plugins.v2/lexiannot/__init__.py index 2843816..4034033 100644 --- a/plugins.v2/lexiannot/__init__.py +++ b/plugins.v2/lexiannot/__init__.py @@ -1,3 +1,4 @@ +import copy import os import json import queue @@ -31,7 +32,7 @@ from app.schemas.types import EventType from app.core.context import MediaInfo from app.chain.media import MediaChain -from .agenttool import VocabularyAnnotatingTool +from .agenttool import QueryAnnotationTasksTool, VocabularyAnnotatingTool from .lexicon import Lexicon from .schemas import ( IDGenerator, @@ -181,7 +182,7 @@ class LexiAnnot(_PluginBase): # 从字典中恢复队列 with self._tasks_lock: for task_id, task in self._tasks.items(): - if task.status == TaskStatus.PENDING: + if task.status in {TaskStatus.PENDING, TaskStatus.RUNNING}: self._task_queue.put(task) self._shutdown_event = threading.Event() @@ -361,26 +362,11 @@ class LexiAnnot(_PluginBase): "model": "annot_level", "label": "标注词汇的最低CEFR等级", "items": [ - { - "title": "B1", - "value": "B1", - }, - { - "title": "B2", - "value": "B2", - }, - { - "title": "C1", - "value": "C1", - }, - { - "title": "C2", - "value": "C2", - }, - { - "title": "C2+", - "value": "C2+", - }, + {"title": "B1", "value": "B1"}, + {"title": "B2", "value": "B2"}, + {"title": "C1", "value": "C1"}, + {"title": "C2", "value": "C2"}, + {"title": "C2+", "value": "C2+"}, ], }, } @@ -412,42 +398,15 @@ class LexiAnnot(_PluginBase): "chips": True, "multiple": True, "items": [ - { - "title": "四级", - "value": "CET-4", - }, - { - "title": "六级", - "value": "CET-6", - }, - { - "title": "考研", - "value": "NPEE", - }, - { - "title": "雅思", - "value": "IELTS", - }, - { - "title": "托福", - "value": "TOEFL", - }, - { - "title": "专四", - "value": "TEM-4", - }, - { - "title": "专八", - "value": "TEM-8", - }, - { - "title": "GRE", - "value": "GRE", - }, - { - "title": "PET", - "value": "PET", - }, + {"title": "四级", "value": "CET-4"}, + {"title": "六级", "value": "CET-6"}, + {"title": "考研", "value": "NPEE"}, + {"title": "雅思", "value": "IELTS"}, + {"title": "托福", "value": "TOEFL"}, + {"title": "专四", "value": "TEM-4"}, + {"title": "专八", "value": "TEM-8"}, + {"title": "GRE", "value": "GRE"}, + {"title": "PET", "value": "PET"}, ], }, } @@ -496,30 +455,12 @@ class LexiAnnot(_PluginBase): "model": "font_scaling", "label": "字体缩放", "items": [ - { - "title": "50%", - "value": "0.5", - }, - { - "title": "75%", - "value": "0.75", - }, - { - "title": "100%", - "value": "1", - }, - { - "title": "125%", - "value": "1.25", - }, - { - "title": "150%", - "value": "1.5", - }, - { - "title": "200%", - "value": "2", - }, + {"title": "50%", "value": "0.5"}, + {"title": "75%", "value": "0.75"}, + {"title": "100%", "value": "1"}, + {"title": "125%", "value": "1.25"}, + {"title": "150%", "value": "1.5"}, + {"title": "200%", "value": "2"} ], }, } @@ -549,26 +490,11 @@ class LexiAnnot(_PluginBase): "model": "opacity", "label": "透明度", "items": [ - { - "title": "0", - "value": "0", - }, - { - "title": "25%", - "value": "63", - }, - { - "title": "50%", - "value": "127", - }, - { - "title": "75%", - "value": "191", - }, - { - "title": "100%", - "value": "255", - }, + {"title": "0", "value": "0"}, + {"title": "25%", "value": "63"}, + {"title": "50%", "value": "127"}, + {"title": "75%", "value": "191"}, + {"title": "100%", "value": "255"}, ], }, } @@ -1100,7 +1026,7 @@ class LexiAnnot(_PluginBase): 获取插件智能体工具 返回工具类列表，每个工具类必须继承自 MoviePilotTool """ - return [VocabularyAnnotatingTool] + return [VocabularyAnnotatingTool, QueryAnnotationTasksTool] def stop_service(self): """ @@ -1170,7 +1096,12 @@ class LexiAnnot(_PluginBase): } self.save_data("tasks", tasks_dict) - def add_task(self, video_file: str, skip_existing=True): + def get_tasks(self) -> list[Task]: + return [copy.deepcopy(task) for task in self._tasks.values()] + + def add_task(self, video_file: str, skip_existing=True) -> bool: + if not self._enabled: + return False task = Task( video_path=video_file, add_time=datetime.now().strftime("%Y-%m-%d %H:%M:%S"), @@ -1181,6 +1112,7 @@ class LexiAnnot(_PluginBase): self._task_queue.put(task) self.save_tasks() logger.info(f"加入任务队列: {video_file}") + return True def add_media_file(self, path: str, skip_existing: bool = True): """ @@ -1193,10 +1125,7 @@ class LexiAnnot(_PluginBase): def delete_tasks(self, task_id: str | None): historical_status = { - TaskStatus.COMPLETED, - TaskStatus.FAILED, - TaskStatus.CANCELED, - TaskStatus.IGNORED, + TaskStatus.COMPLETED, TaskStatus.FAILED, TaskStatus.CANCELED, TaskStatus.IGNORED, } with self._tasks_lock: if task_id is None: @@ -1271,9 +1200,8 @@ class LexiAnnot(_PluginBase): if context and context.media_info and context.meta_info: media_info = context.media_info if media_info.type == MediaType.TV: - media_name = ( - f"{media_info.title_year} {context.meta_info.season_episode}" - ) + media_name = f"{media_info.title_year} {context.meta_info.season_episode}" + else: media_name = f"{media_info.title_year}" message = f"标题： {media_name}" @@ -1979,8 +1907,7 @@ class LexiAnnot(_PluginBase): segment=seg, lexi=lexi, spacy_worker=spacy_worker, - simple_level=simple_vocabulary, - exams=self._exam_tags, + simple_level=simple_vocabulary ) if self._gemini_available: if self._use_mp_agent: diff --git a/plugins.v2/lexiannot/agenttool.py b/plugins.v2/lexiannot/agenttool.py index 4bdc01f..abdf4d2 100644 --- a/plugins.v2/lexiannot/agenttool.py +++ b/plugins.v2/lexiannot/agenttool.py @@ -5,11 +5,11 @@ from pydantic import BaseModel from app.agent.tools.base import MoviePilotTool from app.core.plugin import PluginManager -from .schemas import VocabularyAnnotatingToolInput +from .schemas import VocabularyAnnotatingToolInput, QueryAnnotationTasksToolInput, Task class VocabularyAnnotatingTool(MoviePilotTool): - """自定义工具示例""" + """词汇标注工具""" # 工具名称 name: str = "vocabulary_annotating_tool" @@ -61,7 +61,74 @@ class VocabularyAnnotatingTool(MoviePilotTool): plugin_instance = plugins.get("LexiAnnot") if not plugin_instance: return "LexiAnnot 插件未运行" - await asyncio.to_thread( + res = await asyncio.to_thread( plugin_instance.add_task, video_file=video_path, skip_existing=skip_existing ) + if not res: + return "任务添加失败" return None + +class QueryAnnotationTasksTool(MoviePilotTool): + """词汇标注任务查询工具""" + + # 工具名称 + name: str = "query_annotation_tasks_tool" + # 工具描述 + description: str = ( + "Query the latest vocabulary annotation tasks from plugin LexiAnnot." + ) + # 输入参数模型 + args_schema: Type[BaseModel] = QueryAnnotationTasksToolInput + + def get_tool_message(self, **kwargs) -> Optional[str]: + """根据订阅参数生成友好的提示消息""" + count = kwargs.get("count", 5) + return f"正在查询最近的 {count} 条字幕标注任务" + + async def run(self, count: int, **kwargs) -> str: + """ + 实现工具的核心逻辑（异步方法） + + :param count: The max number of returned annotation tasks + :param kwargs: 其他参数，包含 explanation（工具使用说明） + :return: 工具执行结果，返回字符串格式 + """ + try: + # 执行工具逻辑 + plugins = PluginManager().running_plugins + plugin_instance = plugins.get("LexiAnnot") + if not plugin_instance: + return "LexiAnnot 插件未运行" + total: list[Task] = plugin_instance.get_tasks() + # Handle potential None in add_time + total.sort(key=lambda t: t.add_time or "", reverse=True) + + tasks = total[:count] + if not tasks: + return "未查询到相关任务" + + result_lines = [f"最近 {len(tasks)} 条标注任务:"] + for task in tasks: + status_val = ( + task.status.value + if hasattr(task.status, "value") + else str(task.status) + ) + + info = f"\n🎥 **{task.video_path}**" + info += f"\n ID: {task.task_id}" + info += f"\n Status: {status_val}" + info += f"\n Added: {task.add_time or 'N/A'}" + if task.complete_time: + info += f"\n Completed: {task.complete_time}" + if task.message: + info += f"\n Message: {task.message}" + if task.statistics: + info += f"\n Words: {task.statistics.total_words} | Segments: {task.statistics.total_segments}" + + result_lines.append(info) + + return "\n".join(result_lines) + + except Exception as e: + return f"执行失败: {str(e)}" diff --git a/plugins.v2/lexiannot/pipeline.py b/plugins.v2/lexiannot/pipeline.py index 9ca429a..6aac3e3 100644 --- a/plugins.v2/lexiannot/pipeline.py +++ b/plugins.v2/lexiannot/pipeline.py @@ -69,7 +69,7 @@ def initialize_llm( max_retries: int = 3, proxy: bool = False, ) -> BaseChatModel: - """初始化LLM模型""" + """初始化 LLM""" if provider == "google": if proxy: @@ -277,13 +277,8 @@ def _update_word_via_lexicon(word: Word, lexi: Lexicon) -> Word: return word -def extract_advanced_words( - segment: SubtitleSegment, - lexi: Lexicon, - spacy_worker: SpacyWorker, - simple_level: set[Cefr], - exams: list[str], -) -> list[Word]: +def extract_advanced_words(segment: SubtitleSegment, lexi: Lexicon, spacy_worker: SpacyWorker, + simple_level: set[Cefr]) -> list[Word]: text = segment.clean_text doc = spacy_worker.submit(text) last_end_pos = 0 @@ -331,9 +326,7 @@ def extract_advanced_words( return words -def _find_segment_by_word_id( - segments: list[SubtitleSegment], word_id: int -) -> SubtitleSegment | None: +def _find_segment_by_word_id(segments: list[SubtitleSegment], word_id: int) -> SubtitleSegment | None: for segment in segments: for word in segment.candidate_words: if word.meta.word_id == word_id: @@ -705,7 +698,7 @@ def llm_process_chain( 根据 LLM 的反馈更新字幕片段中的单词信息 :param lexi: 词典对象 - :param llm: 大语言模型对象 + :param llm: LLM 对象 :param segments: 字幕片段 :param shutdown_event: 关闭事件 :param context_window: 上下文窗口大小 diff --git a/plugins.v2/lexiannot/schemas.py b/plugins.v2/lexiannot/schemas.py index b01456d..aefd3e6 100644 --- a/plugins.v2/lexiannot/schemas.py +++ b/plugins.v2/lexiannot/schemas.py @@ -34,7 +34,7 @@ class UniversalPos(str, Enum): X = "X" # Other/unknown -class LexicalFeatures(str, Enum): +class LexicalFeatures(str, Enum): """Lexical features for words.""" FORMAL = "formal" @@ -335,7 +335,7 @@ class LlmWordEnrichment(BaseModel): class LlmEnrichmentResult(BaseModel): - enriched_words: list[LlmWordEnrichment] = Field(default_factory=list, description="List of enriched word data.") + enriched_words: list[LlmWordEnrichment] = Field(default_factory=list, description="List of enriched word data") class LlmSegmentTranslation(BaseModel): @@ -350,7 +350,12 @@ class LlmTranslationResult(BaseModel): class VocabularyAnnotatingToolInput(BaseModel): explanation: str = Field( ..., - description="This is a tool for adding a new vocabulary-annotating task to AnnotLexi.", + description="This is a tool for adding a new vocabulary-annotating task to AnnotLexi", ) video_path: str = Field(..., description="Path to the video file") skip_existing: bool = Field(default=True, description="Whether to skip existing subtitle files") + + +class QueryAnnotationTasksToolInput(BaseModel): + count: int = Field(default=5, description="The maximum number of returned annotation tasks") + explanation: str = Field(..., description="This is a tool for querying the latest annotation tasks in AnnotLexi")