eaiadminandClaude Code
c1af86c934
按用户指示做**一包提交**，不按工作流拆分。本提交刻意混合了多条并行线：
· 本地 ASR 接管：audio 成为与 chat/embed/image/video 同等的路由类别
（IsLocalRoute 单一判据、audio 健康探测、default_audio_route、
auto 占位、GET /api/ai/routes/audio、回退云端时界面明示「音频已出网」）
· LLM 调用层：ctx 贯穿、ToolCall/ToolSchema、EmptyCompletionError /
TransientUpstreamError（按错误类型而非文案判重试）
· 编排 Agent：general_assistant orchestrate/persistence/spec_driver
· 联网搜索：internal/search（playwright）
· 网盘：backend + 前端
· 前端 UI：导航/路由/工作台若干页
· 交付文档：DELIVERY.md / AR04 / 部署文档的「无 Python」表述据实改写，
新增 eai_agentplatform-asr.service、asr.env、clonezilla-cleanup 清 ~/asr-poc
不分拆的原因：dev 早期，粒度不该打断工作节奏。且实测过——这些改动
**在编译上是同一个单元**（llm.go 的 ctx 签名变更牵动 12 个调用点，
chat_message.go 的 ctx 改动又与编排重写同处一个 hunk），拆出来的中间态编不过。
详见 TOP_CODING_RULES.md G14.5 与 bugs_and_errors.md E09。
Co-Authored-By: Claude Code <noreply@anthropic.com>
249 lines
10 KiB
JSON
249 lines
10 KiB
JSON
{
|
||
"agent_routes": {
|
||
"embed_gen": "embed_route_llamacpp_nomic",
|
||
"image_gen": "image_route_openrouter_gpt_image_2",
|
||
"video_gen": "video_route_openrouter_veo_3",
|
||
"path_coach": "chat_route_lmuai_deepseek_v4_flash",
|
||
"title_gen": "chat_route_lmuai_deepseek_v4_flash",
|
||
"audio_transcribe": "audio_route_auto",
|
||
"audio_transcribe_llm": "chat_route_lmuai_deepseek_v4_flash_doc"
|
||
},
|
||
"audio_routes": {
|
||
"audio_route_local_whisper": {
|
||
"base_url": "http://127.0.0.1:8090/v1",
|
||
"description": "语音转写 · 本机 faster-whisper large-v3 + pyannote 3.1（音频不出本机）。由 deploy/eai_agentplatform-asr.service 常驻在 127.0.0.1:8090；服务不在时 audio_route_auto 会改走 fallback_routes 里的云端路由，并在转写产物里标注「音频已出本机」。timeout 定在 840s 而不是一小时：前端 api/audioSkill.js 给这一步的上限是 15 分钟，后端必须在它之前自己收手（否则用户看到的是 axios 超时，而后端还在跑），同时 840s 里还留得下云端那 600s 的回退预算",
|
||
"endpoint": "/audio/transcriptions",
|
||
"model": "large-v3",
|
||
"provider": "local_asr",
|
||
"short_model_name": "whisper large-v3",
|
||
"short_route_name": "本地",
|
||
"supports_speakers": true,
|
||
"timeout_seconds": 840
|
||
},
|
||
"audio_route_siliconflow_diarize": {
|
||
"description": "语音转写 · SiliconFlow / XingChen ASR Diarize（云端，音频会出本机；本地服务不可用时的回退，也可由管理员手动指定）",
|
||
"endpoint": "/audio/transcriptions",
|
||
"model": "XingChenAGI/XingChenASR-Diarize-V3.0",
|
||
"provider": "siliconflow",
|
||
"short_model_name": "XingChen ASR Diarize",
|
||
"short_route_name": "SiliconFlow",
|
||
"supports_speakers": true,
|
||
"timeout_seconds": 600
|
||
},
|
||
"audio_route_siliconflow_qwen3": {
|
||
"description": "语音转写 · SiliconFlow / Qwen3-ASR（云端，音频会出公网；无说话人分离）",
|
||
"endpoint": "/audio/transcriptions",
|
||
"model": "Qwen/Qwen3-ASR-1.7B",
|
||
"provider": "siliconflow",
|
||
"short_model_name": "Qwen3 ASR",
|
||
"short_route_name": "SiliconFlow",
|
||
"supports_speakers": false,
|
||
"timeout_seconds": 600
|
||
}
|
||
},
|
||
"chat_routes": {
|
||
"chat_route_lmuai_deepseek_v4_flash": {
|
||
"description": "LMUAI / DeepSeek Flash。max_tokens 从 4096 提到 32768（2026-09-26）：4096 是当初只按「聊天」估的，但这条路由是 default_route，用户在对话框里选过模型后这个选择会被记进 localStorage 并**一路带到技能内部的加工步骤**（全仓库只有语音转写的第 3、4 步消费 ai_route_id，见 skills/api/audio_handlers.go 的 resolveAudioChatRoute）。于是它会顶掉技能自带的 _doc 路由，让「整理段落」在推理模型思考完之前就把预算耗光、正文 0 字。上限是天花板不是配额，模型写完就停，抬高不会让聊天变慢变贵（实测见 _doc 那条的说明）",
|
||
"endpoint": "/chat/completions",
|
||
"max_tokens": 32768,
|
||
"model": "deepseek-v4-flash",
|
||
"provider": "lmuai",
|
||
"short_model_name": "DeepSeek V4 Flash",
|
||
"short_route_name": "LMUAI",
|
||
"temperature": 0.7
|
||
},
|
||
"chat_route_lmuai_deepseek_v4_flash_doc": {
|
||
"description": "LMUAI / DeepSeek Flash（长文输出档，max_tokens=32768）· 供逐字稿整理这类要产出一整篇文档的技能使用。为什么不复用上面那条 4096 的：这是推理模型，思考与正文共用 max_tokens，而思考的长度跟输入几乎不成比例（实测 1200 字的输入，思考照样写到 7169 字）。4096 下正文一个字都写不出来（六次实测只有一次成功）。再说为什么是 32768 而不是 8192：纪要步骤最后要把各段结果**归并**成一份，那是全流程最长的一次输入（实测 8628 字），8192 下 finish_reason=length、正文 0 字，16384 才出稿、32768 又快又稳。上限提高**不会**让逐块调用变慢或变贵——上限是天花板不是配额，模型写完就停：实测同一批 11 段，8192 与 32768 两档的用时（18.6s / 19.2s）与 completion token（均 4928 / 5094）基本一致。调小这个值之前请先看 audio_transcribe/prompts.go 里的实测表",
|
||
"endpoint": "/chat/completions",
|
||
"max_tokens": 32768,
|
||
"model": "deepseek-v4-flash",
|
||
"provider": "lmuai",
|
||
"short_model_name": "DeepSeek V4 Flash（长文档）",
|
||
"short_route_name": "LMUAI",
|
||
"temperature": 0.7
|
||
},
|
||
"chat_route_ollama_qwen": {
|
||
"description": "本地对话 · llama.cpp / Qwen3.5 4B",
|
||
"endpoint": "/chat/completions",
|
||
"max_tokens": 512,
|
||
"model": "Qwen3.5-4B-Q4_K_M.gguf",
|
||
"provider": "llamacpp",
|
||
"short_model_name": "Qwen3.5 4B",
|
||
"short_route_name": "本地对话",
|
||
"temperature": 0.7,
|
||
"timeout_seconds": 90
|
||
},
|
||
"chat_route_ollama_qwen_fast": {
|
||
"description": "本地快聊 · llama.cpp / Qwen3.5 4B",
|
||
"endpoint": "/chat/completions",
|
||
"max_tokens": 512,
|
||
"model": "Qwen3.5-4B-Q4_K_M.gguf",
|
||
"provider": "llamacpp",
|
||
"short_model_name": "Qwen3.5 4B",
|
||
"short_route_name": "本地快聊",
|
||
"temperature": 0.3
|
||
},
|
||
"chat_route_openrouter_deepseek_v3": {
|
||
"description": "OpenRouter / DeepSeek V3.2",
|
||
"endpoint": "/chat/completions",
|
||
"max_tokens": 4096,
|
||
"model": "deepseek/deepseek-v3.2",
|
||
"provider": "openrouter",
|
||
"short_model_name": "DeepSeek V3.2",
|
||
"short_route_name": "OpenRouter",
|
||
"temperature": 0.6
|
||
},
|
||
"chat_route_openrouter_deepseek_v4_flash": {
|
||
"description": "OpenRouter / DeepSeek V4 Flash 0731",
|
||
"endpoint": "/chat/completions",
|
||
"max_tokens": 4096,
|
||
"model": "deepseek/deepseek-v4-flash-0731",
|
||
"provider": "openrouter",
|
||
"short_model_name": "DeepSeek V4 Flash 0731",
|
||
"short_route_name": "OpenRouter",
|
||
"temperature": 0.7
|
||
},
|
||
"chat_route_openrouter_gpt_5": {
|
||
"description": "OpenRouter / GPT 5.4",
|
||
"endpoint": "/chat/completions",
|
||
"max_tokens": 8192,
|
||
"model": "openai/gpt-5.4",
|
||
"provider": "openrouter",
|
||
"short_model_name": "GPT 5.4",
|
||
"short_route_name": "OpenRouter",
|
||
"temperature": 0.7
|
||
},
|
||
"chat_route_openrouter_grok_4": {
|
||
"description": "OpenRouter / Grok 4.20",
|
||
"endpoint": "/chat/completions",
|
||
"max_tokens": 4096,
|
||
"model": "x-ai/grok-4.20",
|
||
"provider": "openrouter",
|
||
"short_model_name": "Grok 4.20",
|
||
"short_route_name": "OpenRouter",
|
||
"temperature": 0.6
|
||
},
|
||
"chat_route_siliconflow_deepseek_v4_flash": {
|
||
"description": "SiliconFlow / DeepSeek V4 Flash",
|
||
"endpoint": "/chat/completions",
|
||
"max_tokens": 4096,
|
||
"model": "deepseek-ai/DeepSeek-V4-Flash",
|
||
"provider": "siliconflow",
|
||
"short_model_name": "DeepSeek V4 Flash",
|
||
"short_route_name": "SiliconFlow",
|
||
"temperature": 0.7
|
||
}
|
||
},
|
||
"default_audio_route": "audio_route_local_whisper",
|
||
"default_embed_route": "embed_route_llamacpp_nomic",
|
||
"default_route": "chat_route_lmuai_deepseek_v4_flash",
|
||
"description": "eai_agentplatform AI 路由配置 — 按场景分类定义多条路由，支持 provider/模型切换",
|
||
"embed_routes": {
|
||
"embed_route_llamacpp_nomic": {
|
||
"base_url": "http://127.0.0.1:8081/v1",
|
||
"description": "本地向量 · llama.cpp / Nomic Embed v1.5",
|
||
"endpoint": "/embeddings",
|
||
"model": "nomic-embed-text-v1.5.Q4_K_M.gguf",
|
||
"provider": "llamacpp",
|
||
"short_model_name": "Nomic Embed v1.5",
|
||
"short_route_name": "本地向量",
|
||
"timeout_seconds": 30
|
||
},
|
||
"embed_route_ollama_bge_m3": {
|
||
"description": "本地向量 · Ollama / BGE-M3",
|
||
"endpoint": "/embeddings",
|
||
"model": "bge-m3",
|
||
"provider": "ollama",
|
||
"short_model_name": "BGE-M3",
|
||
"short_route_name": "本地向量"
|
||
},
|
||
"embed_route_openrouter_text_v3": {
|
||
"description": "OpenRouter / text-embedding-3-small",
|
||
"endpoint": "/embeddings",
|
||
"model": "openai/text-embedding-3-small",
|
||
"provider": "openrouter",
|
||
"short_model_name": "text-embedding-3-small",
|
||
"short_route_name": "OpenRouter"
|
||
}
|
||
},
|
||
"fallback_routes": {
|
||
"chat_route_lmuai_deepseek_flash": [
|
||
"chat_route_ollama_qwen_fast",
|
||
"chat_route_ollama_qwen"
|
||
],
|
||
"chat_route_openrouter_deepseek_v3": [
|
||
"chat_route_openrouter_grok_4",
|
||
"chat_route_ollama_qwen"
|
||
],
|
||
"chat_route_openrouter_deepseek_v4_flash": [
|
||
"chat_route_openrouter_deepseek_v3",
|
||
"chat_route_openrouter_grok_4",
|
||
"chat_route_ollama_qwen"
|
||
],
|
||
"chat_route_openrouter_grok_4": [
|
||
"chat_route_ollama_qwen"
|
||
],
|
||
"chat_route_siliconflow_deepseek_v4_flash": [
|
||
"chat_route_ollama_qwen_fast",
|
||
"chat_route_ollama_qwen"
|
||
],
|
||
"audio_route_local_whisper": [
|
||
"audio_route_siliconflow_diarize"
|
||
],
|
||
"embed_route_llamacpp_nomic": [
|
||
"embed_route_openrouter_text_v3"
|
||
],
|
||
"embed_route_ollama_bge_m3": [
|
||
"embed_route_openrouter_text_v3"
|
||
],
|
||
"embed_route_openrouter_text_v3": [
|
||
"embed_route_ollama_bge_m3"
|
||
]
|
||
},
|
||
"image_routes": {
|
||
"image_route_ollama_llava": {
|
||
"description": "本地图像 · Ollama / LLaVA",
|
||
"endpoint": "/chat/completions",
|
||
"max_tokens": 2048,
|
||
"model": "llava",
|
||
"provider": "ollama",
|
||
"short_model_name": "LLaVA",
|
||
"short_route_name": "本地图像",
|
||
"temperature": 0.7
|
||
},
|
||
"image_route_openrouter_flux": {
|
||
"description": "OpenRouter / FLUX 1.1 Pro",
|
||
"endpoint": "/images/generations",
|
||
"max_tokens": 1024,
|
||
"model": "black-forest-labs/flux-1.1-pro",
|
||
"provider": "openrouter",
|
||
"short_model_name": "FLUX 1.1 Pro",
|
||
"short_route_name": "OpenRouter",
|
||
"temperature": 1
|
||
},
|
||
"image_route_openrouter_gpt_image_2": {
|
||
"description": "OpenRouter / GPT 5.4 Image 2",
|
||
"endpoint": "/images/generations",
|
||
"max_tokens": 4096,
|
||
"model": "openai/gpt-5.4-image-2",
|
||
"provider": "openrouter",
|
||
"short_model_name": "GPT 5.4 Image 2",
|
||
"short_route_name": "OpenRouter",
|
||
"temperature": 1
|
||
}
|
||
},
|
||
"video_routes": {
|
||
"video_route_openrouter_veo_3": {
|
||
"description": "OpenRouter / Google Veo 3",
|
||
"endpoint": "/videos/generations",
|
||
"model": "google/veo-3",
|
||
"max_tokens": 4096,
|
||
"provider": "openrouter",
|
||
"short_model_name": "Veo 3",
|
||
"short_route_name": "OpenRouter",
|
||
"temperature": 0.7
|
||
}
|
||
},
|
||
"version": "2.1.0"
|
||
}
|