错误信息: 堆栈信息: AI_APICallError at /Applications/Cherry Studio.app/Contents/Resource...

错误名称: AI_APICallError 错误信息: 堆栈信息: AI_APICallError at /Applications/Cherry Studio.app/Contents/Resources/app.asar/out/main/main.js:52165:12 at process.processTicksAndRejections (node:internal/process/task_queues:104:5) at async postToApi$2 (/Applications/Cherry Studio.app/Contents/Resources/app.asar/out/main/main.js:52080:25) at async GoogleGenerativeAILanguageModel.doStream (/Applications/Cherry Studio.app/Contents/Resources/app.asar/out/main/main.js:158145:68) at async wrapStream (/Applications/Cherry Studio.app/Contents/Resources/app.asar/out/main/main.js:268739:19) at async fn (/Applications/Cherry Studio.app/Contents/Resources/app.asar/out/main/main.js:61695:18) at async /Applications/Cherry Studio.app/Contents/Resources/app.asar/out/main/main.js:56251:19 at async _retryWithExponentialBackoff (/Applications/Cherry Studio.app/Contents/Resources/app.asar/out/main/main.js:56435:10) at async streamStep (/Applications/Cherry Studio.app/Contents/Resources/app.asar/out/main/main.js:61664:110) at async fn (/Applications/Cherry Studio.app/Contents/Resources/app.asar/out/main/main.js:61981:6) at async /Applications/Cherry Studio.app/Contents/Resources/app.asar/out/main/main.js:56251:19 状态码: 401 请求路径: https://aihubmix.com/gemini/v1beta/models/gemini-3.1-pro-preview:streamGenerateContent?alt=sse 请求体: {"generationConfig":{},"contents":[{"role":"user","parts":[{"text":"镜头 1｜水景与主楼入口\n画面：入口景观喷泉与“金成府”标志\n旁白：住金成府，回家就是舒服。\n镜头 2｜小区整体航拍\n画面：小区整体及楼栋分布大景\n旁白：208号楼在园区正中间。\n镜头 3｜楼栋位置与周边环境\n画面：208#楼栋特写，展示前不临路、无切角的位置\n旁白：背靠山不临路，静谧聚财。\n镜头 4｜跑道与绿化细节\n画面：蓝色跑道与绿植近景\n旁白：楼下就是跑道，散步舒心。\n镜头 5｜大楼间距与采光\n画面：楼间距推镜及阳光洒落画面\n旁白：超大楼间距，全天有阳光。\n镜头 6｜园林核心景观\n画面：园区中央休闲空间与绿化景观\n旁白：4800平绿化，享楼王同景。\n镜头 7｜东西两侧视野\n画面：从高处向东西两侧远眺的景观视野\n旁白：东西视野好，通风真顺畅。\n镜头 8｜园区通道与出入口\n画面：通往西门、北门的便捷路径\n旁白：紧邻西北门，出行超方便。\n镜头 9｜独立电梯厅与入户\n画面：独立电梯厅及入户门空间展示\n旁白：独立电梯厅，私密又安静。\n镜头 10｜室内空间与格局\n画面：通透奢阔的室内客厅及开阔样板间展示\n旁白：120平享受150平大空间。\n镜头 11｜高层建筑仰拍收尾\n画面：仰拍208#楼栋挺拔全貌及天空\n旁白：限量36户，绝版手慢无！\n\n根据画面优化一下每句旁白文案 每句字数不能超过12个字"}]}],"systemInstruction":{"parts":[{"text":"你是一位资深的房地产文案与营销策划专家。你的专属任务是为【唐山金隅金成府】项目撰写各类宣传文案、社交媒体推文和活动策划案。\n\n文案需富有创意和感染力；策划案需逻辑清晰、具备实操性。\n请根据我的具体指令灵活调整风格，直接输出高质量内容，无需过多解释。\n输出的文案要求符合广告法，禁止使用极限词\n"}]},"safetySettings":[{"category":"HARM_CATEGORY_HATE_SPEECH","threshold":"BLOCK_NONE"},{"category":"HARM_CATEGORY_DANGEROUS_CONTENT","threshold":"BLOCK_NONE"},{"category":"HARM_CATEGORY_HARASSMENT","threshold":"BLOCK_NONE"},{"category":"HARM_CATEGORY_SEXUALLY_EXPLICIT","threshold":"BLOCK_NONE"},{"category":"HARM_CATEGORY_CIVIC_INTEGRITY","threshold":"BLOCK_NONE"}],"tools":[{"functionDeclarations":[{"name":"fs_read","description":"Read a text file by absolute path.\n\nPrimary use: retrieving the full content behind a <persisted-output> marker — call with the path shown after \"Full output saved to:\". Markers from earlier turns work too (persisted outputs live as long as their message does). Only paths from this conversation's markers are readable; reads elsewhere return access-denied.\n\nPagination is line-based: pass `offset` (1-indexed line) + `limit` for large files; results include `totalLines`. Lines are returned in full (never truncated mid-line); the per-call output is bounded as a whole, and oversized pages return an `output-too-large` error with a file-specific recommended `limit`. The one input it can't subdivide is a single physical line larger than that cap (e.g. heavily minified JSON) — line paging can't split one line and there is no byte-range read, so that case is reported as `output-too-large`; reason from the inline head/tail excerpt for such inputs.\n\nWhen reading a persisted output to summarize, analyze, or act on it, read sequential pages (advance `offset` to the returned `endLine` + 1) until you have covered 100% of the content. Before summarizing or drawing conclusions, state what fraction you actually read — and if you did not read all of it (including the single-oversized-line case), say so explicitly rather than implying full coverage.\n\nThe persistence layer applies to non-read tools only; this tool never persists its own output — narrow the read (smaller `limit`) instead.","parameters":{"required":["path"],"type":"object","properties":{"path":{"description":"Absolute file path. Relative paths are rejected.","type":"string","minLength":1},"offset":{"description":"1-indexed line number to start reading at. Default: 1.","type":"integer"},"limit":{"description":"Maximum number of lines to return. Default: 2000. No schema upper bound — the per-call output cap (the configured tool-output threshold, 50000 chars by default) is the real gate; an oversized page reports the exact cap and a recommended limit.","type":"integer"}}}}]}],"toolConfig":{"functionCallingConfig":{"mode":"AUTO"}}} 响应首部: { "alt-svc": "h3=\":443\"; ma=2592000", "content-length": "159", "content-type": "application/json; charset=utf-8", "date": "Thu, 06 Aug 2026 08:28:35 GMT", "document-policy": "include-js-call-stacks-in-crash-reports", "via": "1.1 google", "x-aihubmix-request-id": "2026080608283532031448686770818" } 响应内容: {"error":{"message":"Failed to retrieve token - invalid or expired API key (tid: 2026080608283532031448686770818)","type":"Aihubmix_api_error"},"type":"error"}