Files
awoooi/docs/operations/ai-technology-radar-readback.snapshot.json
Your Name 889b7b4229
Some checks failed
Code Review / ai-code-review (push) Successful in 15s
CD Pipeline / tests (push) Successful in 1m42s
CD Pipeline / build-and-deploy (push) Successful in 3m58s
CD Pipeline / post-deploy-checks (push) Has been cancelled
Ansible / Reboot Recovery Contract / validate (push) Has been cancelled
feat(governance): refresh AI agent market radar
2026-06-26 11:55:21 +08:00

608 lines
24 KiB
JSON
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"blocked_gates": [
"sdk_installation_approved=false",
"paid_api_calls_approved=false",
"production_routing_approved=false",
"telegram_send_approved=false",
"model_provider_switch_approved=false",
"host_write_approved=false",
"openclaw_replacement_approved=false",
"replay_shadow_canary_gate_required=true",
"cost_and_data_boundary_review_required=true"
],
"generated_at": "2026-06-26T03:43:13.171222+00:00",
"high_priority_review_queue": [
{
"display_name": "Model Context Protocol SDK",
"evaluation_priority": "p0",
"gate_status": "scorecard_required_before_integration",
"next_gate": "刷新 scorecard若涉及 SDK/API/route/Telegram/host write 則送人工審核。",
"requires_cost_approval": false,
"requires_dependency_approval": true,
"requires_security_review": true,
"technology_area": "mcp_and_a2a",
"technology_id": "modelcontextprotocol_sdk"
},
{
"display_name": "Agent2Agent Protocol",
"evaluation_priority": "p1",
"gate_status": "scorecard_required_before_integration",
"next_gate": "刷新 scorecard若涉及 SDK/API/route/Telegram/host write 則送人工審核。",
"requires_cost_approval": false,
"requires_dependency_approval": true,
"requires_security_review": true,
"technology_area": "mcp_and_a2a",
"technology_id": "a2a_protocol"
},
{
"display_name": "Anthropic Claude Platform",
"evaluation_priority": "p0",
"gate_status": "scorecard_required_before_integration",
"next_gate": "刷新 scorecard若涉及 SDK/API/route/Telegram/host write 則送人工審核。",
"requires_cost_approval": true,
"requires_dependency_approval": false,
"requires_security_review": true,
"technology_area": "model_providers",
"technology_id": "anthropic_claude_platform"
},
{
"display_name": "Langfuse",
"evaluation_priority": "p1",
"gate_status": "scorecard_required_before_integration",
"next_gate": "刷新 scorecard若涉及 SDK/API/route/Telegram/host write 則送人工審核。",
"requires_cost_approval": true,
"requires_dependency_approval": true,
"requires_security_review": true,
"technology_area": "evaluation_and_observability",
"technology_id": "langfuse_observability"
}
],
"integration_candidates": [
{
"awoooi_role": "協調者、handoff、tool tracing、guardrail 候選",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "OpenAI Agents SDK",
"integration_surface": "agent_handoff_tracing_guardrails",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "agent_frameworks",
"technology_id": "openai_agents_sdk"
},
{
"awoooi_role": "NemoTron replay / evaluator / synthetic data gate",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "NVIDIA Nemotron + NeMo Agent Toolkit",
"integration_surface": "offline_replay_evaluator_smoke_gate",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "agent_frameworks",
"technology_id": "nvidia_nemotron_nemo"
},
{
"awoooi_role": "事件處理與可恢復 workflow kernel 候選",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "LangGraph",
"integration_surface": "durable_workflow_human_in_loop",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "agent_frameworks",
"technology_id": "langgraph_runtime"
},
{
"awoooi_role": "Gemini/Vertex agent stack watch-only 候選",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "Google Agent Development Kit",
"integration_surface": "gemini_enterprise_agent_stack",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "agent_frameworks",
"technology_id": "google_adk_stack"
},
{
"awoooi_role": "MCP/A2A enterprise workflow watch-only 候選",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "Microsoft Agent Framework",
"integration_surface": "enterprise_mcp_a2a_workflow",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "agent_frameworks",
"technology_id": "microsoft_agent_framework"
},
{
"awoooi_role": "快速 prototype / non-production 評估候選",
"changed": true,
"decision": "changed_requires_replay_readiness_review",
"display_name": "CrewAI Flows + Crews",
"integration_surface": "multi_agent_prototype",
"recommended_actions": [
"refresh_ai_technology_scorecard",
"classify_business_applicability",
"prepare_no_install_integration_note",
"route_high_risk_items_to_human_review"
],
"technology_area": "agent_frameworks",
"technology_id": "crewai_flows"
},
{
"awoooi_role": "read-only tool registry / MCP adapter 候選",
"changed": true,
"decision": "changed_requires_replay_readiness_review",
"display_name": "Model Context Protocol SDK",
"integration_surface": "tool_registry_interoperability",
"recommended_actions": [
"refresh_ai_technology_scorecard",
"classify_business_applicability",
"prepare_no_install_integration_note",
"route_high_risk_items_to_human_review"
],
"technology_area": "mcp_and_a2a",
"technology_id": "modelcontextprotocol_sdk"
},
{
"awoooi_role": "跨 Agent 溝通協定 watch-only 候選",
"changed": true,
"decision": "changed_requires_replay_readiness_review",
"display_name": "Agent2Agent Protocol",
"integration_surface": "agent_to_agent_interop",
"recommended_actions": [
"refresh_ai_technology_scorecard",
"classify_business_applicability",
"prepare_no_install_integration_note",
"route_high_risk_items_to_human_review"
],
"technology_area": "mcp_and_a2a",
"technology_id": "a2a_protocol"
},
{
"awoooi_role": "Agent / LLM / MCP trace 欄位標準與日週月報可觀測基礎",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "OpenTelemetry GenAI Semantic Conventions",
"integration_surface": "agent_llm_trace_semantic_conventions",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "evaluation_and_observability",
"technology_id": "opentelemetry_genai_semconv"
},
{
"awoooi_role": "模型能力、成本與 routing scorecard 來源",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "OpenAI Model Platform",
"integration_surface": "model_capability_cost_routing",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "model_providers",
"technology_id": "openai_model_platform"
},
{
"awoooi_role": "Claude model / coding agent / remediation watch source",
"changed": true,
"decision": "changed_requires_replay_readiness_review",
"display_name": "Anthropic Claude Platform",
"integration_surface": "model_capability_cost_routing",
"recommended_actions": [
"refresh_ai_technology_scorecard",
"classify_business_applicability",
"prepare_no_install_integration_note",
"route_high_risk_items_to_human_review"
],
"technology_area": "model_providers",
"technology_id": "anthropic_claude_platform"
},
{
"awoooi_role": "Gemini model capability / cost watch source",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "Google Gemini Platform",
"integration_surface": "model_capability_cost_routing",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "model_providers",
"technology_id": "google_gemini_platform"
},
{
"awoooi_role": "RAG ingestion / indexing / connector watch source",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "LlamaIndex",
"integration_surface": "rag_indexing_connectors",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "rag_and_vector",
"technology_id": "llamaindex_rag"
},
{
"awoooi_role": "LLM app integration connector watch source",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "LangChain",
"integration_surface": "llm_app_runtime_connectors",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "rag_and_vector",
"technology_id": "langchain_runtime"
},
{
"awoooi_role": "現有 Postgres/pgvector 能力與版本 freshness 來源",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "pgvector",
"integration_surface": "postgres_vector_index",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "rag_and_vector",
"technology_id": "pgvector_vector_store"
},
{
"awoooi_role": "專用 vector DB 候選,只能 sandbox 評估",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "Qdrant",
"integration_surface": "dedicated_vector_database",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "rag_and_vector",
"technology_id": "qdrant_vector_store"
},
{
"awoooi_role": "本機 / sandbox vector store 候選",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "ChromaDB",
"integration_surface": "local_vector_database",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "rag_and_vector",
"technology_id": "chromadb_vector_store"
},
{
"awoooi_role": "RAG / LLM app evaluation metrics 候選",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "Ragas",
"integration_surface": "rag_eval_metrics",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "evaluation_and_observability",
"technology_id": "ragas_eval"
},
{
"awoooi_role": "LLM trace / prompt / eval observability 候選",
"changed": true,
"decision": "changed_requires_replay_readiness_review",
"display_name": "Langfuse",
"integration_surface": "llm_observability_tracing",
"recommended_actions": [
"refresh_ai_technology_scorecard",
"classify_business_applicability",
"prepare_no_install_integration_note",
"route_high_risk_items_to_human_review"
],
"technology_area": "evaluation_and_observability",
"technology_id": "langfuse_observability"
},
{
"awoooi_role": "自託管模型 serving 能力與版本 freshness 來源",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "Hugging Face Text Generation Inference",
"integration_surface": "self_hosted_model_serving",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "model_serving",
"technology_id": "huggingface_tgi"
},
{
"awoooi_role": "自託管 LLM inference 候選,需 GPU/成本/安全 gate",
"changed": false,
"decision": "watch_only_no_change",
"display_name": "vLLM",
"integration_surface": "self_hosted_llm_inference",
"recommended_actions": [
"keep_watch_only_status"
],
"technology_area": "model_serving",
"technology_id": "vllm_serving"
}
],
"policy": {
"host_write_approved": false,
"model_provider_switch_approved": false,
"openclaw_replacement_approved": false,
"paid_api_calls_approved": false,
"production_routing_approved": false,
"raw_chat_history_synced": false,
"read_only": true,
"sdk_installation_approved": false,
"telegram_send_approved": false
},
"primary_source_alignment": [
{
"agent_assignment": "OpenClaw 負責 policy guardMarketRadar 追版本Hermes 產審核包。",
"awoooi_gate": "sandbox_orchestration_no_write",
"practice": "OpenAI Agents SDK專家協作、tool execution、approvals、state 由產品掌控",
"source": "https://developers.openai.com/api/docs/guides/agents"
},
{
"agent_assignment": "NemoTron 只做離線 replay / evaluator / smoke gate不接 production routing。",
"awoooi_gate": "nemotron_replay_evaluator_only",
"practice": "NVIDIA Nemotron 3 Ultra / NeMo長任務 Agent、profiling、evaluation、MCP / A2A 互通",
"source": "https://developer.nvidia.com/blog/nvidia-nemotron-3-ultra-powers-faster-more-efficient-reasoning-for-long-running-agents/"
},
{
"agent_assignment": "OpenClaw 仲裁狀態轉移Hermes 記錄 replay 證據與交接原因。",
"awoooi_gate": "incident_workflow_kernel_replay_first",
"practice": "LangGraphdurable execution、human-in-the-loop、stateful workflow runtime",
"source": "https://docs.langchain.com/oss/python/langgraph/overview"
},
{
"agent_assignment": "MarketRadar 監控 SDK / specCritic 檢查資料權限與 tool safety。",
"awoooi_gate": "read_only_tool_registry_before_write_adapter",
"practice": "MCP標準化 agent-to-tool / resource / prompt 連接,且需明確 user consent",
"source": "https://modelcontextprotocol.io/specification/2025-06-18"
},
{
"agent_assignment": "OpenClaw 設定協作邊界Hermes 彙整 handoff 記錄NemoTron 比對輸出。",
"awoooi_gate": "agent_to_agent_interop_watch_only",
"practice": "A2A跨框架 Agent 溝通、委派與互通MCP 處理工具、A2A 處理 Agent 對 Agent",
"source": "https://a2a-protocol.org/latest/"
},
{
"agent_assignment": "Critic 定義稽核欄位MarketRadar 追語意規範版本Hermes 產日週月報。",
"awoooi_gate": "trace_semconv_mapping_before_runtime_export",
"practice": "OpenTelemetry GenAIAgent / LLM / MCP trace 語意慣例,支援可觀測與稽核",
"source": "https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/"
}
],
"priority_workplan": [
{
"automation_mode": "agent_auto_read_only",
"done_definition": "API、snapshot、Markdown、schema、測試與 production readback 都能顯示技術領域、來源與 Gate。",
"order": 1,
"priority": "P0",
"work_item": "AI 技術雷達 primary source 監控產品化"
},
{
"automation_mode": "agent_auto_schedule_read_only",
"done_definition": "每 6 小時可跑 watch失敗來源會進日報不會自動整合。",
"order": 2,
"priority": "P0",
"work_item": "近即時版本 / release / docs 變更偵測"
},
{
"automation_mode": "agent_auto_read_model_human_review_for_write",
"done_definition": "每個 Agent 的角色、輸出、學習寫回與限制都能被前端讀回。",
"order": 3,
"priority": "P0",
"work_item": "OpenClaw / Hermes / NemoTron / MarketRadar 專業分工與成長紀錄"
},
{
"automation_mode": "agent_propose_owner_review",
"done_definition": "高優先級變更先進 scorecard再進 no-cost/no-write sandbox 或 replay 計畫。",
"order": 4,
"priority": "P1",
"work_item": "AI 技術 scorecard 與 sandbox / replay 優先級"
},
{
"automation_mode": "blocked_until_telegram_send_gate",
"done_definition": "低中風險只告警回報;高風險需 owner approval 後才可發送或執行。",
"order": 5,
"priority": "P1",
"work_item": "Telegram Bot 報告與高風險審核橋接"
},
{
"automation_mode": "agent_auto_discover_human_classify",
"done_definition": "GitHub topic / package registry / 官方 blog 可提出候選,但加入正式 watchlist 前需審核。",
"order": 6,
"priority": "P2",
"work_item": "新 AI 技術探索與 watchlist 擴充"
}
],
"professional_agent_roles": [
{
"agent": "OpenClaw",
"auto_scope": "維持現有 production baseline、讀取 replay / shadow 評分、拒絕無證據替換",
"professional_role": "生產決策仲裁者、風險分級與最後 policy guard",
"review_boundary": "任何取代、降級、生產路由切換都必須通過 replay / shadow / canary 與人工批准。"
},
{
"agent": "NemoTron",
"auto_scope": "只讀 request pack、比對候選輸出、產生 replay scorecard 草稿",
"professional_role": "離線回放評估者、模型能力比較、合約輸出 smoke gate",
"review_boundary": "不得自行呼叫外部 NIM/API、不得讀 labels 作答、不得進生產路由。"
},
{
"agent": "Hermes",
"auto_scope": "整理 primary source 摘要、建立 no-send 日週月報、準備人審包",
"professional_role": "知識管理、RAG 整理、報告草稿與長期技能庫維護",
"review_boundary": "不得同步 raw chat history、不得保存 secret、不得直接發 Telegram live report。"
},
{
"agent": "MarketRadar",
"auto_scope": "每 6 小時只讀 primary sources、產生 freshness / review queue",
"professional_role": "AI 技術市場雷達、版本監控、來源失敗偵測",
"review_boundary": "不得自動新增 SDK、不得自動修改 provider route 或 workflow 行為。"
},
{
"agent": "Critic / Reviewer",
"auto_scope": "檢查政策旗標、來源可靠性、成本與資安風險",
"professional_role": "獨立審核、反例檢查、整合風險評分",
"review_boundary": "只能輸出 blocked / candidate / owner_review不得直接執行寫入。"
}
],
"report_contract": {
"agent_auto_allowed_for": [
"官方來源只讀監控",
"版本與文件 hash 比對",
"審核佇列分類",
"繁中 no-send 報告草稿",
"離線 replay fixture 準備",
"低風險文件與讀回 snapshot 更新提案"
],
"api_endpoint": "/api/v1/agents/ai-technology-radar-readback",
"daily": "每日彙整變更、來源失敗、審核佇列與可自動處理項目。",
"frontend_target": "/zh-TW/governance?tab=agent-market",
"human_review_required_for": [
"新 SDK / package / MCP server 安裝",
"付費 API 或 token 上限變更",
"模型 provider / 生產路由切換",
"Telegram Bot 即時發送或審批按鈕策略變更",
"主機、K8s、workflow、Nginx、secret 或資料層寫入",
"OpenClaw 生產決策核心替換、拆分或降級"
],
"monthly": "每月進行策略 review決定納入 roadmap、維持 watch-only 或移出監控。",
"near_real_time": "每 6 小時讀取 primary sources偵測主流 AI 技術版本、文件與 release 變更。",
"schedule_cron_utc": "0 */6 * * *",
"schedule_enabled": true,
"schedule_workflow": ".gitea/workflows/ai-technology-watch.yaml",
"weekly": "每週做技術 scorecard決定 sandbox / replay / adapter design 優先級。"
},
"rolling_update_controls": [
{
"agent_auto_action": "讀取官方文件、PyPI、npm、GitHub release、primary source hash。",
"cadence": "每 6 小時",
"cadence_source": "每 6 小時執行一次只讀 primary-source 檢查,偵測主流 AI 技術版本、文件與 release 變更。",
"gate": "read_only_only",
"output": "AI 技術 watch report、來源失敗清單、review queue。"
},
{
"agent_auto_action": "依 business applicability、成本、依賴、資安、AWOOOI fit 分類。",
"cadence": "每日",
"cadence_source": "每日彙整變更技術,依商業適用性、依賴風險、成本風險與資安風險分組。",
"gate": "no_send_report_until_delivery_gate",
"output": "日報摘要與中低風險自動處理建議。"
},
{
"agent_auto_action": "刷新 scorecard決定 sandbox / replay / adapter design 優先級。",
"cadence": "每週",
"cadence_source": "每週刷新技術 scorecard判斷是否值得進入 sandbox、offline replay 或 adapter design。",
"gate": "scorecard_required_before_replay",
"output": "週報、優先序、候選整合審查包。"
},
{
"agent_auto_action": "彙整趨勢,提出 roadmap / watch-only / retire 建議。",
"cadence": "每月",
"cadence_source": "每月策略檢討,決定技術應納入 roadmap、維持 watch-only 或從監控清單移除。",
"gate": "human_review_for_strategy_or_production_change",
"output": "月報與策略審核包。"
}
],
"schema_version": "ai_technology_radar_readback_v1",
"source_scope": {
"agent_market_radar_readback": "docs/operations/ai-agent-market-radar-readback.snapshot.json",
"gitea_main_evidence_basis_commit": "61cf5024",
"scope_note": "本讀回只整合已提交的只讀來源監控、AI Agent 市場雷達與治理 gate不包含 raw chat history、secret、session 或本機工作視窗內容。",
"technology_source_registry": "docs/ai/ai-technology-watch-sources.v1.json",
"technology_watch_report": "docs/evaluations/ai_technology_watch_report_2026-06-25.json"
},
"summary": {
"ai_technology_radar_completion_percent": 100.0,
"changed_technologies": 5,
"high_priority_count": 15,
"overall_completion_percent": 42.2,
"review_queue_count": 5,
"rolling_update_status": "near_real_time_watch_ready_integration_gated",
"source_count": 52,
"source_failures": 0,
"technology_area_count": 6,
"technology_count": 21
},
"technology_area_counts": {
"agent_frameworks": 6,
"evaluation_and_observability": 3,
"mcp_and_a2a": 2,
"model_providers": 3,
"model_serving": 2,
"rag_and_vector": 5
},
"technology_domains": [
{
"changed_count": 1,
"high_priority_count": 5,
"representative_technologies": [
"OpenAI Agents SDK",
"NVIDIA Nemotron + NeMo Agent Toolkit",
"LangGraph",
"Google Agent Development Kit"
],
"technology_area": "agent_frameworks",
"technology_count": 6
},
{
"changed_count": 1,
"high_priority_count": 3,
"representative_technologies": [
"OpenTelemetry GenAI Semantic Conventions",
"Ragas",
"Langfuse"
],
"technology_area": "evaluation_and_observability",
"technology_count": 3
},
{
"changed_count": 2,
"high_priority_count": 2,
"representative_technologies": [
"Model Context Protocol SDK",
"Agent2Agent Protocol"
],
"technology_area": "mcp_and_a2a",
"technology_count": 2
},
{
"changed_count": 1,
"high_priority_count": 3,
"representative_technologies": [
"OpenAI Model Platform",
"Anthropic Claude Platform",
"Google Gemini Platform"
],
"technology_area": "model_providers",
"technology_count": 3
},
{
"changed_count": 0,
"high_priority_count": 0,
"representative_technologies": [
"Hugging Face Text Generation Inference",
"vLLM"
],
"technology_area": "model_serving",
"technology_count": 2
},
{
"changed_count": 0,
"high_priority_count": 2,
"representative_technologies": [
"LlamaIndex",
"LangChain",
"pgvector",
"Qdrant"
],
"technology_area": "rag_and_vector",
"technology_count": 5
}
]
}