openbkn-ai

为 BKN 对象匹配 Vega resource，输出绑定决议。

基于对象资源绑定结果判定关系类型，绑定 backing resource（indirect 类型）。

BKN 全生命周期编排入口。按需读取 OpenBKN SDK / CLI 操作参考。 凡涉及创建 BKN、从 PRD/文档提取对象关系、 生成或更新 `.bkn`、做数据视图绑定、环境检查、测试集生成、校验与推送时， 优先使用 bkn-creator 进行流程路由、阶段门禁、子 skill 编排与结果回执。 适用于 BKN 的 create/read/update/delete/extract/copy/validate 场景， 技能包能力补齐/skill 草案生成场景，…

将绑定/映射结果写回 .bkn 文件。

将确认后的建模清单生成 .bkn 文件。

BKN 执行前环境就绪检查与 bootstrap 判定。

属性到字段映射 + 覆盖率计算 + 完备性放行。

OpenBKN SDK / CLI 操作参考层。 覆盖认证、平台业务域（config）、知识网络管理与查询、Agent CRUD 与对话、 数据源管理、数据视图、Skill 注册、Vega 可观测、context-loader 语义搜索、通用 API 调用。 仅由 bkn-creator pipeline 内部读取，不独立注册到宿主 skill 系统。

Use when performing BOM-level production schedule backward planning (齐套倒排), material need-by dates, A/B delay classification, or supply-status diagnosis against a demand end date on knowledge network supply_ontology_hand.

Use when analyzing how many finished units can be sold now (成品仓 + 理论可产) on knowledge network supply_ontology_hand. Not a delivery-date promise.

Use when checking whether multiple new product demands can be accepted together on knowledge network supply_ontology_hand, including shared-BOM structure, kitting net demand, and shared-material contention.

Use when a user asks whether a product demand (an existing forecast or a new order) can be delivered on knowledge network supply_942_verify: locate the forecast, read the inventory metric, run the kitting / net-demand function, and, only after explicit user…

Deploy or upgrade OpenBKN on a customer-authorized Linux server through the repository's deploy scripts, with preflight checks, explicit confirmation, secret handling, and post-deployment verification.

操作 BKN（Business Knowledge Network）平台的统一 CLI `openbkn` —— 知识网络 构建/查询（Schema：对象/关系/行动类型、指标、概念组；实例与语义搜索； push/pull/validate；从 Vega Catalog 或 CSV 建网）、资源、Vega Catalog 与 索引构建任务、Context Loader（MCP 检索）、模型工厂（大模型/小模型 CRUD、OpenAI 兼容对话/embedding/ rerank）、Skill 注册（zip…

Guides creation of BKN (Business Knowledge Network) definition files following v2.0.1 spec. Covers network, object_type, relation_type, action_type, concept_group. Use when creating knowledge networks, BKN files, object types, relation types, action types,…

Execution factory E2E skill fixture