[{"data":1,"prerenderedAt":1238},["ShallowReactive",2],{"content-/ai/context-awareness":3,"related-ai":1208},{"_path":4,"_dir":5,"_draft":6,"_partial":6,"_locale":7,"title":8,"description":9,"keywords":10,"author":11,"date":12,"category":13,"image":14,"body":15,"_type":1202,"_id":1203,"_source":1204,"_file":1205,"_stem":1206,"_extension":1207},"/ai/context-awareness","ai",false,"","全域上下文感知系统","构建跨越时间、空间与语义维度的智能上下文理解架构","上下文感知, 知识图谱, 长期记忆, 意图推理, 个性化推荐, HTMLPAGE","HTMLPAGE","2025-11-27","AI 技术","/content-images/ai/ai.jpg",{"type":16,"children":17,"toc":1180},"root",[18,26,33,39,44,226,231,236,245,575,581,586,591,616,621,626,640,646,651,656,689,694,717,723,728,733,741,770,775,780,1075,1081,1086,1091,1124,1130,1161,1165,1174],{"type":19,"tag":20,"props":21,"children":22},"element","p",{},[23],{"type":24,"value":25},"text","HTMLPAGE 的全域上下文感知系统（Omni-Context Awareness System）是 AI 引擎的\"大脑皮层\"。它不仅关注当前的对话窗口，更能够跨越时间（历史交互）、空间（项目环境）和语义（行业知识）维度，构建一个立体的上下文模型，从而实现真正\"懂你\"的智能生成。",{"type":19,"tag":27,"props":28,"children":30},"h2",{"id":29},"上下文记忆架构",[31],{"type":24,"value":32},"🧠 上下文记忆架构",{"type":19,"tag":34,"props":35,"children":37},"h3",{"id":36},"双层记忆模型",[38],{"type":24,"value":36},{"type":19,"tag":20,"props":40,"children":41},{},[42],{"type":24,"value":43},"我们借鉴人类的认知心理学模型，构建了短期工作记忆和长期语义记忆相结合的双层架构。",{"type":19,"tag":45,"props":46,"children":50},"pre",{"className":47,"code":48,"language":49,"meta":7,"style":7},"language-mermaid shiki shiki-themes github-dark github-dark","graph TD\n    A[用户输入] --> B{上下文管理器}\n    \n    subgraph \"短期工作记忆 (Session)\"\n        C[当前对话窗口]\n        D[临时变量池]\n        E[即时意图栈]\n    end\n    \n    subgraph \"长期语义记忆 (Profile)\"\n        F[用户画像库]\n        G[项目知识库]\n        H[行业领域图谱]\n    end\n    \n    B \u003C--> C\n    B \u003C--> F\n    C -.->|归档与摘要| F\n    F -.->|检索增强| C\n","mermaid",[51],{"type":19,"tag":52,"props":53,"children":54},"code",{"__ignoreMap":7},[55,67,76,85,94,103,112,121,130,138,147,156,165,174,182,190,199,208,217],{"type":19,"tag":56,"props":57,"children":60},"span",{"class":58,"line":59},"line",1,[61],{"type":19,"tag":56,"props":62,"children":64},{"style":63},"--shiki-default:#E1E4E8;--shiki-dark:#E1E4E8",[65],{"type":24,"value":66},"graph TD\n",{"type":19,"tag":56,"props":68,"children":70},{"class":58,"line":69},2,[71],{"type":19,"tag":56,"props":72,"children":73},{"style":63},[74],{"type":24,"value":75},"    A[用户输入] --> B{上下文管理器}\n",{"type":19,"tag":56,"props":77,"children":79},{"class":58,"line":78},3,[80],{"type":19,"tag":56,"props":81,"children":82},{"style":63},[83],{"type":24,"value":84},"    \n",{"type":19,"tag":56,"props":86,"children":88},{"class":58,"line":87},4,[89],{"type":19,"tag":56,"props":90,"children":91},{"style":63},[92],{"type":24,"value":93},"    subgraph \"短期工作记忆 (Session)\"\n",{"type":19,"tag":56,"props":95,"children":97},{"class":58,"line":96},5,[98],{"type":19,"tag":56,"props":99,"children":100},{"style":63},[101],{"type":24,"value":102},"        C[当前对话窗口]\n",{"type":19,"tag":56,"props":104,"children":106},{"class":58,"line":105},6,[107],{"type":19,"tag":56,"props":108,"children":109},{"style":63},[110],{"type":24,"value":111},"        D[临时变量池]\n",{"type":19,"tag":56,"props":113,"children":115},{"class":58,"line":114},7,[116],{"type":19,"tag":56,"props":117,"children":118},{"style":63},[119],{"type":24,"value":120},"        E[即时意图栈]\n",{"type":19,"tag":56,"props":122,"children":124},{"class":58,"line":123},8,[125],{"type":19,"tag":56,"props":126,"children":127},{"style":63},[128],{"type":24,"value":129},"    end\n",{"type":19,"tag":56,"props":131,"children":133},{"class":58,"line":132},9,[134],{"type":19,"tag":56,"props":135,"children":136},{"style":63},[137],{"type":24,"value":84},{"type":19,"tag":56,"props":139,"children":141},{"class":58,"line":140},10,[142],{"type":19,"tag":56,"props":143,"children":144},{"style":63},[145],{"type":24,"value":146},"    subgraph \"长期语义记忆 (Profile)\"\n",{"type":19,"tag":56,"props":148,"children":150},{"class":58,"line":149},11,[151],{"type":19,"tag":56,"props":152,"children":153},{"style":63},[154],{"type":24,"value":155},"        F[用户画像库]\n",{"type":19,"tag":56,"props":157,"children":159},{"class":58,"line":158},12,[160],{"type":19,"tag":56,"props":161,"children":162},{"style":63},[163],{"type":24,"value":164},"        G[项目知识库]\n",{"type":19,"tag":56,"props":166,"children":168},{"class":58,"line":167},13,[169],{"type":19,"tag":56,"props":170,"children":171},{"style":63},[172],{"type":24,"value":173},"        H[行业领域图谱]\n",{"type":19,"tag":56,"props":175,"children":177},{"class":58,"line":176},14,[178],{"type":19,"tag":56,"props":179,"children":180},{"style":63},[181],{"type":24,"value":129},{"type":19,"tag":56,"props":183,"children":185},{"class":58,"line":184},15,[186],{"type":19,"tag":56,"props":187,"children":188},{"style":63},[189],{"type":24,"value":84},{"type":19,"tag":56,"props":191,"children":193},{"class":58,"line":192},16,[194],{"type":19,"tag":56,"props":195,"children":196},{"style":63},[197],{"type":24,"value":198},"    B \u003C--> C\n",{"type":19,"tag":56,"props":200,"children":202},{"class":58,"line":201},17,[203],{"type":19,"tag":56,"props":204,"children":205},{"style":63},[206],{"type":24,"value":207},"    B \u003C--> F\n",{"type":19,"tag":56,"props":209,"children":211},{"class":58,"line":210},18,[212],{"type":19,"tag":56,"props":213,"children":214},{"style":63},[215],{"type":24,"value":216},"    C -.->|归档与摘要| F\n",{"type":19,"tag":56,"props":218,"children":220},{"class":58,"line":219},19,[221],{"type":19,"tag":56,"props":222,"children":223},{"style":63},[224],{"type":24,"value":225},"    F -.->|检索增强| C\n",{"type":19,"tag":34,"props":227,"children":229},{"id":228},"向量化记忆存储",[230],{"type":24,"value":228},{"type":19,"tag":20,"props":232,"children":233},{},[234],{"type":24,"value":235},"所有的上下文信息都被转化为高维向量（Embeddings），存储在向量数据库（Vector DB）中，支持毫秒级的语义检索。",{"type":19,"tag":20,"props":237,"children":238},{},[239],{"type":19,"tag":240,"props":241,"children":242},"strong",{},[243],{"type":24,"value":244},"上下文检索代码示例",{"type":19,"tag":45,"props":246,"children":250},{"className":247,"code":248,"language":249,"meta":7,"style":7},"language-python shiki shiki-themes github-dark github-dark","class ContextMemorySystem:\n    def __init__(self):\n        self.vector_db = MilvusClient()\n        self.embedding_model = OpenAIEmbeddings()\n    \n    def retrieve_relevant_context(self, query, user_id, project_id):\n        query_vec = self.embedding_model.embed_query(query)\n        \n        # 混合检索策略\n        results = self.vector_db.search(\n            collection_name=\"context_memory\",\n            data=[query_vec],\n            filter=f\"user_id == {user_id} && (project_id == {project_id} || scope == 'global')\",\n            limit=5\n        )\n        \n        return self.synthesize_context(results)\n","python",[251],{"type":19,"tag":52,"props":252,"children":253},{"__ignoreMap":7},[254,274,293,316,337,344,361,383,391,400,421,445,462,526,543,551,558],{"type":19,"tag":56,"props":255,"children":256},{"class":58,"line":59},[257,263,269],{"type":19,"tag":56,"props":258,"children":260},{"style":259},"--shiki-default:#F97583;--shiki-dark:#F97583",[261],{"type":24,"value":262},"class",{"type":19,"tag":56,"props":264,"children":266},{"style":265},"--shiki-default:#B392F0;--shiki-dark:#B392F0",[267],{"type":24,"value":268}," ContextMemorySystem",{"type":19,"tag":56,"props":270,"children":271},{"style":63},[272],{"type":24,"value":273},":\n",{"type":19,"tag":56,"props":275,"children":276},{"class":58,"line":69},[277,282,288],{"type":19,"tag":56,"props":278,"children":279},{"style":259},[280],{"type":24,"value":281},"    def",{"type":19,"tag":56,"props":283,"children":285},{"style":284},"--shiki-default:#79B8FF;--shiki-dark:#79B8FF",[286],{"type":24,"value":287}," __init__",{"type":19,"tag":56,"props":289,"children":290},{"style":63},[291],{"type":24,"value":292},"(self):\n",{"type":19,"tag":56,"props":294,"children":295},{"class":58,"line":78},[296,301,306,311],{"type":19,"tag":56,"props":297,"children":298},{"style":284},[299],{"type":24,"value":300},"        self",{"type":19,"tag":56,"props":302,"children":303},{"style":63},[304],{"type":24,"value":305},".vector_db ",{"type":19,"tag":56,"props":307,"children":308},{"style":259},[309],{"type":24,"value":310},"=",{"type":19,"tag":56,"props":312,"children":313},{"style":63},[314],{"type":24,"value":315}," MilvusClient()\n",{"type":19,"tag":56,"props":317,"children":318},{"class":58,"line":87},[319,323,328,332],{"type":19,"tag":56,"props":320,"children":321},{"style":284},[322],{"type":24,"value":300},{"type":19,"tag":56,"props":324,"children":325},{"style":63},[326],{"type":24,"value":327},".embedding_model ",{"type":19,"tag":56,"props":329,"children":330},{"style":259},[331],{"type":24,"value":310},{"type":19,"tag":56,"props":333,"children":334},{"style":63},[335],{"type":24,"value":336}," OpenAIEmbeddings()\n",{"type":19,"tag":56,"props":338,"children":339},{"class":58,"line":96},[340],{"type":19,"tag":56,"props":341,"children":342},{"style":63},[343],{"type":24,"value":84},{"type":19,"tag":56,"props":345,"children":346},{"class":58,"line":105},[347,351,356],{"type":19,"tag":56,"props":348,"children":349},{"style":259},[350],{"type":24,"value":281},{"type":19,"tag":56,"props":352,"children":353},{"style":265},[354],{"type":24,"value":355}," retrieve_relevant_context",{"type":19,"tag":56,"props":357,"children":358},{"style":63},[359],{"type":24,"value":360},"(self, query, user_id, project_id):\n",{"type":19,"tag":56,"props":362,"children":363},{"class":58,"line":114},[364,369,373,378],{"type":19,"tag":56,"props":365,"children":366},{"style":63},[367],{"type":24,"value":368},"        query_vec ",{"type":19,"tag":56,"props":370,"children":371},{"style":259},[372],{"type":24,"value":310},{"type":19,"tag":56,"props":374,"children":375},{"style":284},[376],{"type":24,"value":377}," self",{"type":19,"tag":56,"props":379,"children":380},{"style":63},[381],{"type":24,"value":382},".embedding_model.embed_query(query)\n",{"type":19,"tag":56,"props":384,"children":385},{"class":58,"line":123},[386],{"type":19,"tag":56,"props":387,"children":388},{"style":63},[389],{"type":24,"value":390},"        \n",{"type":19,"tag":56,"props":392,"children":393},{"class":58,"line":132},[394],{"type":19,"tag":56,"props":395,"children":397},{"style":396},"--shiki-default:#6A737D;--shiki-dark:#6A737D",[398],{"type":24,"value":399},"        # 混合检索策略\n",{"type":19,"tag":56,"props":401,"children":402},{"class":58,"line":140},[403,408,412,416],{"type":19,"tag":56,"props":404,"children":405},{"style":63},[406],{"type":24,"value":407},"        results ",{"type":19,"tag":56,"props":409,"children":410},{"style":259},[411],{"type":24,"value":310},{"type":19,"tag":56,"props":413,"children":414},{"style":284},[415],{"type":24,"value":377},{"type":19,"tag":56,"props":417,"children":418},{"style":63},[419],{"type":24,"value":420},".vector_db.search(\n",{"type":19,"tag":56,"props":422,"children":423},{"class":58,"line":149},[424,430,434,440],{"type":19,"tag":56,"props":425,"children":427},{"style":426},"--shiki-default:#FFAB70;--shiki-dark:#FFAB70",[428],{"type":24,"value":429},"            collection_name",{"type":19,"tag":56,"props":431,"children":432},{"style":259},[433],{"type":24,"value":310},{"type":19,"tag":56,"props":435,"children":437},{"style":436},"--shiki-default:#9ECBFF;--shiki-dark:#9ECBFF",[438],{"type":24,"value":439},"\"context_memory\"",{"type":19,"tag":56,"props":441,"children":442},{"style":63},[443],{"type":24,"value":444},",\n",{"type":19,"tag":56,"props":446,"children":447},{"class":58,"line":158},[448,453,457],{"type":19,"tag":56,"props":449,"children":450},{"style":426},[451],{"type":24,"value":452},"            data",{"type":19,"tag":56,"props":454,"children":455},{"style":259},[456],{"type":24,"value":310},{"type":19,"tag":56,"props":458,"children":459},{"style":63},[460],{"type":24,"value":461},"[query_vec],\n",{"type":19,"tag":56,"props":463,"children":464},{"class":58,"line":167},[465,470,474,479,484,489,494,499,504,508,513,517,522],{"type":19,"tag":56,"props":466,"children":467},{"style":426},[468],{"type":24,"value":469},"            filter",{"type":19,"tag":56,"props":471,"children":472},{"style":259},[473],{"type":24,"value":310},{"type":19,"tag":56,"props":475,"children":476},{"style":259},[477],{"type":24,"value":478},"f",{"type":19,"tag":56,"props":480,"children":481},{"style":436},[482],{"type":24,"value":483},"\"user_id == ",{"type":19,"tag":56,"props":485,"children":486},{"style":284},[487],{"type":24,"value":488},"{",{"type":19,"tag":56,"props":490,"children":491},{"style":63},[492],{"type":24,"value":493},"user_id",{"type":19,"tag":56,"props":495,"children":496},{"style":284},[497],{"type":24,"value":498},"}",{"type":19,"tag":56,"props":500,"children":501},{"style":436},[502],{"type":24,"value":503}," && (project_id == ",{"type":19,"tag":56,"props":505,"children":506},{"style":284},[507],{"type":24,"value":488},{"type":19,"tag":56,"props":509,"children":510},{"style":63},[511],{"type":24,"value":512},"project_id",{"type":19,"tag":56,"props":514,"children":515},{"style":284},[516],{"type":24,"value":498},{"type":19,"tag":56,"props":518,"children":519},{"style":436},[520],{"type":24,"value":521}," || scope == 'global')\"",{"type":19,"tag":56,"props":523,"children":524},{"style":63},[525],{"type":24,"value":444},{"type":19,"tag":56,"props":527,"children":528},{"class":58,"line":176},[529,534,538],{"type":19,"tag":56,"props":530,"children":531},{"style":426},[532],{"type":24,"value":533},"            limit",{"type":19,"tag":56,"props":535,"children":536},{"style":259},[537],{"type":24,"value":310},{"type":19,"tag":56,"props":539,"children":540},{"style":284},[541],{"type":24,"value":542},"5\n",{"type":19,"tag":56,"props":544,"children":545},{"class":58,"line":184},[546],{"type":19,"tag":56,"props":547,"children":548},{"style":63},[549],{"type":24,"value":550},"        )\n",{"type":19,"tag":56,"props":552,"children":553},{"class":58,"line":192},[554],{"type":19,"tag":56,"props":555,"children":556},{"style":63},[557],{"type":24,"value":390},{"type":19,"tag":56,"props":559,"children":560},{"class":58,"line":201},[561,566,570],{"type":19,"tag":56,"props":562,"children":563},{"style":259},[564],{"type":24,"value":565},"        return",{"type":19,"tag":56,"props":567,"children":568},{"style":284},[569],{"type":24,"value":377},{"type":19,"tag":56,"props":571,"children":572},{"style":63},[573],{"type":24,"value":574},".synthesize_context(results)\n",{"type":19,"tag":27,"props":576,"children":578},{"id":577},"️-知识图谱集成",[579],{"type":24,"value":580},"🕸️ 知识图谱集成",{"type":19,"tag":34,"props":582,"children":584},{"id":583},"实体链接与消歧",[585],{"type":24,"value":583},{"type":19,"tag":20,"props":587,"children":588},{},[589],{"type":24,"value":590},"当用户提到\"苹果\"时，系统需要根据上下文判断是指\"水果\"还是\"科技公司\"。我们通过实体链接（Entity Linking）技术，将文本映射到知识图谱中的具体节点。",{"type":19,"tag":592,"props":593,"children":594},"ul",{},[595,606],{"type":19,"tag":596,"props":597,"children":598},"li",{},[599,604],{"type":19,"tag":240,"props":600,"children":601},{},[602],{"type":24,"value":603},"技术栈识别",{"type":24,"value":605},"：识别 \"Vue\", \"React\", \"Tailwind\" 等技术名词，自动关联其最佳实践和依赖关系。",{"type":19,"tag":596,"props":607,"children":608},{},[609,614],{"type":19,"tag":240,"props":610,"children":611},{},[612],{"type":24,"value":613},"行业术语解析",{"type":24,"value":615},"：识别 \"SaaS\", \"B2B\", \"ROI\" 等商业术语，自动调整生成内容的专业度。",{"type":19,"tag":34,"props":617,"children":619},{"id":618},"关系推理",[620],{"type":24,"value":618},{"type":19,"tag":20,"props":622,"children":623},{},[624],{"type":24,"value":625},"知识图谱不仅存储实体，还存储实体间的关系。系统利用这些关系进行逻辑推理。",{"type":19,"tag":627,"props":628,"children":629},"blockquote",{},[630],{"type":19,"tag":20,"props":631,"children":632},{},[633,638],{"type":19,"tag":240,"props":634,"children":635},{},[636],{"type":24,"value":637},"推理示例",{"type":24,"value":639},":\n用户输入: \"我想做一个类似 Airbnb 的网站。\"\n系统推理: Airbnb -> 属于 \"短租平台\" -> 核心功能包括 \"房源搜索\", \"地图模式\", \"预订系统\", \"评价系统\" -> 自动推荐包含这些模块的页面结构。",{"type":19,"tag":27,"props":641,"children":643},{"id":642},"环境与情境感知",[644],{"type":24,"value":645},"🌍 环境与情境感知",{"type":19,"tag":34,"props":647,"children":649},{"id":648},"设备与网络感知",[650],{"type":24,"value":648},{"type":19,"tag":20,"props":652,"children":653},{},[654],{"type":24,"value":655},"系统会自动检测用户的设备环境，并据此调整生成策略。",{"type":19,"tag":592,"props":657,"children":658},{},[659,669,679],{"type":19,"tag":596,"props":660,"children":661},{},[662,667],{"type":19,"tag":240,"props":663,"children":664},{},[665],{"type":24,"value":666},"设备类型",{"type":24,"value":668},"：如果是移动设备访问，优先生成 Mobile-First 的布局，并简化交互逻辑。",{"type":19,"tag":596,"props":670,"children":671},{},[672,677],{"type":19,"tag":240,"props":673,"children":674},{},[675],{"type":24,"value":676},"网络状况",{"type":24,"value":678},"：检测到弱网环境时，自动生成轻量级的图片（WebP/AVIF）和精简的 CSS/JS 代码。",{"type":19,"tag":596,"props":680,"children":681},{},[682,687],{"type":19,"tag":240,"props":683,"children":684},{},[685],{"type":24,"value":686},"深色模式",{"type":24,"value":688},"：检测系统主题设置，自动生成适配 Dark Mode 的配色方案。",{"type":19,"tag":34,"props":690,"children":692},{"id":691},"时间与地域感知",[693],{"type":24,"value":691},{"type":19,"tag":592,"props":695,"children":696},{},[697,707],{"type":19,"tag":596,"props":698,"children":699},{},[700,705],{"type":19,"tag":240,"props":701,"children":702},{},[703],{"type":24,"value":704},"时区适配",{"type":24,"value":706},"：根据用户时区，自动调整生成内容中的时间格式和问候语。",{"type":19,"tag":596,"props":708,"children":709},{},[710,715],{"type":19,"tag":240,"props":711,"children":712},{},[713],{"type":24,"value":714},"地域文化",{"type":24,"value":716},"：根据 IP 地址推断用户所在地区，自动适配货币单位、度量衡和文化习俗（如：美国用户使用 MM/DD/YYYY 日期格式）。",{"type":19,"tag":27,"props":718,"children":720},{"id":719},"意图追踪与预测",[721],{"type":24,"value":722},"🎯 意图追踪与预测",{"type":19,"tag":34,"props":724,"children":726},{"id":725},"隐式意图推断",[727],{"type":24,"value":725},{"type":19,"tag":20,"props":729,"children":730},{},[731],{"type":24,"value":732},"用户往往不会直接说出所有需求。系统通过分析用户的行为序列，推断其隐式意图。",{"type":19,"tag":20,"props":734,"children":735},{},[736],{"type":19,"tag":240,"props":737,"children":738},{},[739],{"type":24,"value":740},"行为序列分析",{"type":19,"tag":742,"props":743,"children":744},"ol",{},[745,750,755,760],{"type":19,"tag":596,"props":746,"children":747},{},[748],{"type":24,"value":749},"用户生成了一个\"产品介绍页\"。",{"type":19,"tag":596,"props":751,"children":752},{},[753],{"type":24,"value":754},"用户修改了\"价格表\"组件。",{"type":19,"tag":596,"props":756,"children":757},{},[758],{"type":24,"value":759},"用户点击了\"导出代码\"。",{"type":19,"tag":596,"props":761,"children":762},{},[763,768],{"type":19,"tag":240,"props":764,"children":765},{},[766],{"type":24,"value":767},"系统推断",{"type":24,"value":769},"：用户可能正在准备上线一个新产品的落地页，下一步可能需要\"支付集成\"或\"SEO 优化\"。",{"type":19,"tag":34,"props":771,"children":773},{"id":772},"动态目标规划",[774],{"type":24,"value":772},{"type":19,"tag":20,"props":776,"children":777},{},[778],{"type":24,"value":779},"系统维护一个动态的目标栈（Goal Stack），跟踪当前任务的完成进度。",{"type":19,"tag":45,"props":781,"children":785},{"className":782,"code":783,"language":784,"meta":7,"style":7},"language-typescript shiki shiki-themes github-dark github-dark","interface GoalState {\n  primaryGoal: string; // e.g., \"Create Landing Page\"\n  subGoals: [\n    { id: 1, name: \"Header Design\", status: \"completed\" },\n    { id: 2, name: \"Feature Section\", status: \"in-progress\" },\n    { id: 3, name: \"Footer\", status: \"pending\" }\n  ];\n  currentFocus: number; // 2\n}\n","typescript",[786],{"type":19,"tag":52,"props":787,"children":788},{"__ignoreMap":7},[789,807,835,852,916,974,1033,1041,1067],{"type":19,"tag":56,"props":790,"children":791},{"class":58,"line":59},[792,797,802],{"type":19,"tag":56,"props":793,"children":794},{"style":259},[795],{"type":24,"value":796},"interface",{"type":19,"tag":56,"props":798,"children":799},{"style":265},[800],{"type":24,"value":801}," GoalState",{"type":19,"tag":56,"props":803,"children":804},{"style":63},[805],{"type":24,"value":806}," {\n",{"type":19,"tag":56,"props":808,"children":809},{"class":58,"line":69},[810,815,820,825,830],{"type":19,"tag":56,"props":811,"children":812},{"style":426},[813],{"type":24,"value":814},"  primaryGoal",{"type":19,"tag":56,"props":816,"children":817},{"style":259},[818],{"type":24,"value":819},":",{"type":19,"tag":56,"props":821,"children":822},{"style":284},[823],{"type":24,"value":824}," string",{"type":19,"tag":56,"props":826,"children":827},{"style":63},[828],{"type":24,"value":829},"; ",{"type":19,"tag":56,"props":831,"children":832},{"style":396},[833],{"type":24,"value":834},"// e.g., \"Create Landing Page\"\n",{"type":19,"tag":56,"props":836,"children":837},{"class":58,"line":78},[838,843,847],{"type":19,"tag":56,"props":839,"children":840},{"style":426},[841],{"type":24,"value":842},"  subGoals",{"type":19,"tag":56,"props":844,"children":845},{"style":259},[846],{"type":24,"value":819},{"type":19,"tag":56,"props":848,"children":849},{"style":63},[850],{"type":24,"value":851}," [\n",{"type":19,"tag":56,"props":853,"children":854},{"class":58,"line":87},[855,860,865,869,874,879,884,888,893,897,902,906,911],{"type":19,"tag":56,"props":856,"children":857},{"style":63},[858],{"type":24,"value":859},"    { ",{"type":19,"tag":56,"props":861,"children":862},{"style":426},[863],{"type":24,"value":864},"id",{"type":19,"tag":56,"props":866,"children":867},{"style":259},[868],{"type":24,"value":819},{"type":19,"tag":56,"props":870,"children":871},{"style":284},[872],{"type":24,"value":873}," 1",{"type":19,"tag":56,"props":875,"children":876},{"style":63},[877],{"type":24,"value":878},", ",{"type":19,"tag":56,"props":880,"children":881},{"style":426},[882],{"type":24,"value":883},"name",{"type":19,"tag":56,"props":885,"children":886},{"style":259},[887],{"type":24,"value":819},{"type":19,"tag":56,"props":889,"children":890},{"style":436},[891],{"type":24,"value":892}," \"Header Design\"",{"type":19,"tag":56,"props":894,"children":895},{"style":63},[896],{"type":24,"value":878},{"type":19,"tag":56,"props":898,"children":899},{"style":426},[900],{"type":24,"value":901},"status",{"type":19,"tag":56,"props":903,"children":904},{"style":259},[905],{"type":24,"value":819},{"type":19,"tag":56,"props":907,"children":908},{"style":436},[909],{"type":24,"value":910}," \"completed\"",{"type":19,"tag":56,"props":912,"children":913},{"style":63},[914],{"type":24,"value":915}," },\n",{"type":19,"tag":56,"props":917,"children":918},{"class":58,"line":96},[919,923,927,931,936,940,944,948,953,957,961,965,970],{"type":19,"tag":56,"props":920,"children":921},{"style":63},[922],{"type":24,"value":859},{"type":19,"tag":56,"props":924,"children":925},{"style":426},[926],{"type":24,"value":864},{"type":19,"tag":56,"props":928,"children":929},{"style":259},[930],{"type":24,"value":819},{"type":19,"tag":56,"props":932,"children":933},{"style":284},[934],{"type":24,"value":935}," 2",{"type":19,"tag":56,"props":937,"children":938},{"style":63},[939],{"type":24,"value":878},{"type":19,"tag":56,"props":941,"children":942},{"style":426},[943],{"type":24,"value":883},{"type":19,"tag":56,"props":945,"children":946},{"style":259},[947],{"type":24,"value":819},{"type":19,"tag":56,"props":949,"children":950},{"style":436},[951],{"type":24,"value":952}," \"Feature Section\"",{"type":19,"tag":56,"props":954,"children":955},{"style":63},[956],{"type":24,"value":878},{"type":19,"tag":56,"props":958,"children":959},{"style":426},[960],{"type":24,"value":901},{"type":19,"tag":56,"props":962,"children":963},{"style":259},[964],{"type":24,"value":819},{"type":19,"tag":56,"props":966,"children":967},{"style":436},[968],{"type":24,"value":969}," \"in-progress\"",{"type":19,"tag":56,"props":971,"children":972},{"style":63},[973],{"type":24,"value":915},{"type":19,"tag":56,"props":975,"children":976},{"class":58,"line":105},[977,981,985,989,994,998,1002,1006,1011,1015,1019,1023,1028],{"type":19,"tag":56,"props":978,"children":979},{"style":63},[980],{"type":24,"value":859},{"type":19,"tag":56,"props":982,"children":983},{"style":426},[984],{"type":24,"value":864},{"type":19,"tag":56,"props":986,"children":987},{"style":259},[988],{"type":24,"value":819},{"type":19,"tag":56,"props":990,"children":991},{"style":284},[992],{"type":24,"value":993}," 3",{"type":19,"tag":56,"props":995,"children":996},{"style":63},[997],{"type":24,"value":878},{"type":19,"tag":56,"props":999,"children":1000},{"style":426},[1001],{"type":24,"value":883},{"type":19,"tag":56,"props":1003,"children":1004},{"style":259},[1005],{"type":24,"value":819},{"type":19,"tag":56,"props":1007,"children":1008},{"style":436},[1009],{"type":24,"value":1010}," \"Footer\"",{"type":19,"tag":56,"props":1012,"children":1013},{"style":63},[1014],{"type":24,"value":878},{"type":19,"tag":56,"props":1016,"children":1017},{"style":426},[1018],{"type":24,"value":901},{"type":19,"tag":56,"props":1020,"children":1021},{"style":259},[1022],{"type":24,"value":819},{"type":19,"tag":56,"props":1024,"children":1025},{"style":436},[1026],{"type":24,"value":1027}," \"pending\"",{"type":19,"tag":56,"props":1029,"children":1030},{"style":63},[1031],{"type":24,"value":1032}," }\n",{"type":19,"tag":56,"props":1034,"children":1035},{"class":58,"line":114},[1036],{"type":19,"tag":56,"props":1037,"children":1038},{"style":63},[1039],{"type":24,"value":1040},"  ];\n",{"type":19,"tag":56,"props":1042,"children":1043},{"class":58,"line":123},[1044,1049,1053,1058,1062],{"type":19,"tag":56,"props":1045,"children":1046},{"style":426},[1047],{"type":24,"value":1048},"  currentFocus",{"type":19,"tag":56,"props":1050,"children":1051},{"style":259},[1052],{"type":24,"value":819},{"type":19,"tag":56,"props":1054,"children":1055},{"style":284},[1056],{"type":24,"value":1057}," number",{"type":19,"tag":56,"props":1059,"children":1060},{"style":63},[1061],{"type":24,"value":829},{"type":19,"tag":56,"props":1063,"children":1064},{"style":396},[1065],{"type":24,"value":1066},"// 2\n",{"type":19,"tag":56,"props":1068,"children":1069},{"class":58,"line":132},[1070],{"type":19,"tag":56,"props":1071,"children":1072},{"style":63},[1073],{"type":24,"value":1074},"}\n",{"type":19,"tag":27,"props":1076,"children":1078},{"id":1077},"️-隐私与隔离",[1079],{"type":24,"value":1080},"🛡️ 隐私与隔离",{"type":19,"tag":34,"props":1082,"children":1084},{"id":1083},"上下文隔离机制",[1085],{"type":24,"value":1083},{"type":19,"tag":20,"props":1087,"children":1088},{},[1089],{"type":24,"value":1090},"为了保护用户隐私，我们实施了严格的上下文隔离策略。",{"type":19,"tag":592,"props":1092,"children":1093},{},[1094,1104,1114],{"type":19,"tag":596,"props":1095,"children":1096},{},[1097,1102],{"type":19,"tag":240,"props":1098,"children":1099},{},[1100],{"type":24,"value":1101},"租户隔离",{"type":24,"value":1103},"：不同企业/团队的数据在物理存储上是隔离的。",{"type":19,"tag":596,"props":1105,"children":1106},{},[1107,1112],{"type":19,"tag":240,"props":1108,"children":1109},{},[1110],{"type":24,"value":1111},"项目隔离",{"type":24,"value":1113},"：不同项目之间的上下文默认不共享，防止信息串扰。",{"type":19,"tag":596,"props":1115,"children":1116},{},[1117,1122],{"type":19,"tag":240,"props":1118,"children":1119},{},[1120],{"type":24,"value":1121},"敏感信息过滤",{"type":24,"value":1123},"：在将上下文发送给 LLM 之前，自动识别并掩盖（Mask）手机号、邮箱、API Key 等敏感信息。",{"type":19,"tag":27,"props":1125,"children":1127},{"id":1126},"相关技术文档",[1128],{"type":24,"value":1129},"🔗 相关技术文档",{"type":19,"tag":592,"props":1131,"children":1132},{},[1133,1143,1152],{"type":19,"tag":596,"props":1134,"children":1135},{},[1136],{"type":19,"tag":1137,"props":1138,"children":1140},"a",{"href":1139},"/ai/semantic-understanding.md",[1141],{"type":24,"value":1142},"语义理解系统",{"type":19,"tag":596,"props":1144,"children":1145},{},[1146],{"type":19,"tag":1137,"props":1147,"children":1149},{"href":1148},"/ai/requirement-understanding.md",[1150],{"type":24,"value":1151},"需求理解机制",{"type":19,"tag":596,"props":1153,"children":1154},{},[1155],{"type":19,"tag":1137,"props":1156,"children":1158},{"href":1157},"/ai/prompt-elements.md",[1159],{"type":24,"value":1160},"提示词工程",{"type":19,"tag":1162,"props":1163,"children":1164},"hr",{},[],{"type":19,"tag":20,"props":1166,"children":1167},{},[1168],{"type":19,"tag":1169,"props":1170,"children":1171},"em",{},[1172],{"type":24,"value":1173},"上下文是智能的基石。HTMLPAGE 通过全域上下文感知，让 AI 不再是冷冰冰的工具，而是懂你、识你、助你的智能伙伴。",{"type":19,"tag":1175,"props":1176,"children":1177},"style",{},[1178],{"type":24,"value":1179},"html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"title":7,"searchDepth":78,"depth":78,"links":1181},[1182,1186,1190,1194,1198,1201],{"id":29,"depth":69,"text":32,"children":1183},[1184,1185],{"id":36,"depth":78,"text":36},{"id":228,"depth":78,"text":228},{"id":577,"depth":69,"text":580,"children":1187},[1188,1189],{"id":583,"depth":78,"text":583},{"id":618,"depth":78,"text":618},{"id":642,"depth":69,"text":645,"children":1191},[1192,1193],{"id":648,"depth":78,"text":648},{"id":691,"depth":78,"text":691},{"id":719,"depth":69,"text":722,"children":1195},[1196,1197],{"id":725,"depth":78,"text":725},{"id":772,"depth":78,"text":772},{"id":1077,"depth":69,"text":1080,"children":1199},[1200],{"id":1083,"depth":78,"text":1083},{"id":1126,"depth":69,"text":1129},"markdown","content:ai:context-awareness.md","content","ai/context-awareness.md","ai/context-awareness","md",[1209,1220,1229],{"_path":1210,"_dir":5,"_draft":6,"_partial":6,"_locale":7,"title":1211,"description":1212,"keywords":1213,"schemaType":1214,"author":11,"date":1215,"image":1216,"_type":1202,"_id":1217,"_source":1204,"_file":1218,"_stem":1219,"_extension":1207},"/ai/architecture-overview","AI架构概述 - HTMLPAGE智能网页生成系统","HTMLPAGE AI系统架构深度解析，了解多智能体协作、实时流式生成、模块化组装等核心技术，探索AI如何革新网页设计流程。","AI网页生成, 多智能体系统, 实时流式AI, 智能网页设计, AI架构, 机器学习","TechArticle","2025-11-24","/content-images/ai/architecture-overview.jpg","content:ai:architecture-overview.md","ai/architecture-overview.md","ai/architecture-overview",{"_path":1221,"_dir":5,"_draft":6,"_partial":6,"_locale":7,"title":1222,"description":1223,"keywords":1224,"author":11,"date":12,"category":1225,"image":14,"_type":1202,"_id":1226,"_source":1204,"_file":1227,"_stem":1228,"_extension":1207},"/ai/batch-creation","批量页面创建","模板 + 提示词模式组合进行多页面高效率生成","批量页面创建, 批量生成, 提示词模板, HTMLPAGE","应用场景","content:ai:batch-creation.md","ai/batch-creation.md","ai/batch-creation",{"_path":1230,"_dir":5,"_draft":6,"_partial":6,"_locale":7,"title":1231,"description":1232,"keywords":1233,"author":11,"date":12,"category":1234,"image":14,"_type":1202,"_id":1235,"_source":1204,"_file":1236,"_stem":1237,"_extension":1207},"/ai/case-studies","AI 案例研究","HTMLPAGE AI 在不同行业和场景中的成功应用案例","AI 案例研究, 成功案例, 页面生成, HTMLPAGE","案例研究","content:ai:case-studies.md","ai/case-studies.md","ai/case-studies",1774945280298]