Govern self-authored tools, skills, and reusable plans as capabilities
还没有人认领这个 Issue。
评估
- 难度
- 5/5
- 预计耗时
- 一周以上
- 新手友好度
- 25/100
- Issue 类型
- 功能
- 描述清晰度
- 需要澄清
- 活跃度
- 活跃
- 技术栈
- python
调研方向
该 issue 没有列出任何文件、测试或入口点,因此首先梳理 capabilities、authority manifests、qualification 和 invocation history 在 repository 中的表示位置。将验收标准作为 Definition of Done:隔离和独立 qualification、沙箱测试、拒绝扩大 authority、基于证据的撤销,以及可回放的审计历史。
由索引模型根据 Issue 内容生成。
描述
Origin
Deferred from the MVP proposed as a fresh realization of #485.
Goal
Allow agents to create, test, share, repair, and revoke tools, skills, and reusable plans safely.
Scope
- One immutable, versioned
Capabilitycontract for tools, skills, and reusable plans. - Lifecycle:
draft -> quarantined -> candidate -> trusted -> deprecated/revoked. - Input/output schemas, exact implementation hash, dependency lock, test/evidence bundle, ownership, and invocation history.
- Enforced authority manifests for network, filesystem, subprocess, secrets, cost, and side effects; child authority may narrow but never widen.
- Independent, use-based qualification; authors cannot approve their own capability.
- Bug reports linked to exact invocations and expected/observed artifacts.
- New-version repair and revocation rather than mutation or historical deletion.
- Idempotency and compensation declarations for external effects.
Acceptance criteria
- A run can author a capability in quarantine and cannot invoke it as trusted before independent qualification.
- Qualification executes real tests inside the declared sandbox.
- Authority widening is rejected and recorded.
- A failing invocation can trigger independent triage and evidence-based revocation.
- Historical runs remain replayable/auditable after revocation.
- 主要语言
- Python
- 星标
- 3
- 派生
- 2
- PR 合并指标
- 30 天内没有已合并 PR
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 没有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue,再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库,在一个分支上完成修改。
- 提交 Pull Request,并在描述里引用这个 Issue 编号。
ContextLab/orchestrator 的其他 Issue
-
Stop textually splicing variable values into expression source in ControlFlowAutoResolver._safe_eval未关闭architecture bug
难度 2/5 1-3 小时 新手友好度 85/100
ContextLab/orchestrator#427 ·
-
MVP: evidence-driven recursive agentic runtime可能已有人在做 @jeremymanning 于 59 天前认领。 未关闭architecture enhancement epic
难度 5/5 一周以上 新手友好度 25/100
ContextLab/orchestrator#492 ·
-
architecture enhancement
难度 5/5 一周以上 新手友好度 20/100
ContextLab/orchestrator#491 ·
-
architecture enhancement
难度 5/5 一周以上 新手友好度 28/100
ContextLab/orchestrator#490 ·
-
architecture enhancement
难度 5/5 一周以上 新手友好度 25/100
ContextLab/orchestrator#489 ·
查看 ContextLab/orchestrator 的全部 Issue
相似的 Issue
-
难度 1/5 1 小时以内 新手友好度 80/100
521xueweihan/HelloGitHub#4063 ·
-
难度 2/5 1-3 小时 新手友好度 78/100
-
难度 2/5 1-3 小时 新手友好度 62/100
Vanilla-OS/apx-gui#112 ·
-
Devstral and Voxtral: section 5 fails in us-east-1 with 400 "Model does not support audio modality"未关闭
难度 2/5 1-3 小时 新手友好度 76/100
aws-samples/sample-per-model-bedrock#409 ·
维护者通常 1 天内回复
-
DuckDB 2.0 breaks to_pyarrow_batches可能已有人在做 @DG47 今天认领。 未关闭
难度 2/5 1-3 小时 新手友好度 76/100
ibis-project/ibis#12196 ·
维护者通常 1 天内回复