mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
docs(skill): document fail-closed frontmatter validation
This commit is contained in:
Tianyi Cui
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-28-skill-invocation-policy.md
|
||||
2026-07-28-skill-invocation-policy.md: 2010196c8373c89a49056a5d8acd41e2e4c307ce
|
||||
2026-07-28-skill-invocation-policy.zh.md: 129c5b7f62b14a0e9b9bc5ae6107ba946a5a54d7
|
||||
2026-07-28-skill-invocation-policy.md: 85fdec755d9f808b225e2bc5c4afbc303251099b
|
||||
2026-07-28-skill-invocation-policy.zh.md: 99d71ddda63214f763de992cd766edc52612492b
|
||||
|
||||
@@ -16,7 +16,7 @@ The local parser also exposed an internal camel-case spelling as frontmatter. Su
|
||||
|
||||
`ctx.skills.list()` returns every winning summary and no longer chooses an invocation surface. `isModelInvocable(skill)` and `isUserInvocable(skill)` read the matching positive field directly. `ctx.skills.get()` remains policy-neutral because trusted internal callers may need any definition, while a public consumer must enforce its own predicate before advertising or loading a skill.
|
||||
|
||||
The local provider accepts the exact kebab-case frontmatter keys `disable-model-invocation` and `user-invocable`. It accepts YAML booleans plus case-insensitive `true`/`false`, `yes`/`no`, `on`/`off`, and `1`/`0`, matching the practical boolean forms accepted by Claude skills. It maps `disable-model-invocation` to the inverse positive field and fills both positive fields from their defaults even when neither key is present. Camel-case external spellings are rejected with a targeted warning; this pre-release repository does not keep an on-disk compatibility alias.
|
||||
The local provider accepts the exact kebab-case frontmatter keys `disable-model-invocation` and `user-invocable`. It accepts YAML booleans plus case-insensitive `true`/`false`, `yes`/`no`, `on`/`off`, and `1`/`0`, matching the practical boolean forms accepted by Claude skills. It maps `disable-model-invocation` to the inverse positive field and fills both positive fields from their defaults even when neither key is present. A camel-case external spelling or non-boolean invocation value drops the entire skill from discovery with a targeted warning; this pre-release repository does not keep an on-disk compatibility alias. Invocation data fails closed because ignoring it would default to permission and could expose the skill on a disabled surface, while wrong-typed optional `whenToUse` and `metadata` values are omitted because they do not decide invocation.
|
||||
|
||||
The model-facing `dsh-tool-skill` catalog and loader enforce `isModelInvocable`. The TUI `/skill:` autocomplete and exact loader enforce the user field locally, so a user-only skill is visible and loadable there even when it is absent from model discovery, without turning the optional skill peer into a runtime import. The browser `skill.list` RPC serves a user-selected reference that still asks the model to load the skill, so it exposes the intersection of model- and user-invocable skills; no direct browser skill-loading RPC is added.
|
||||
|
||||
|
||||
@@ -16,7 +16,7 @@ skill 注册表最初将发现操作视为模型目录：`ctx.skills.list()` 会
|
||||
|
||||
`ctx.skills.list()` 返回所有胜出的摘要，不再替任何调用接口选择策略。`isModelInvocable(skill)` 和 `isUserInvocable(skill)` 分别直接读取对应的正向字段。`ctx.skills.get()` 保持策略无关，因为可信内部调用方可能需要任意定义；对外消费方则必须在展示或加载 skill 之前执行自身对应的判定函数。
|
||||
|
||||
本地提供方只接受拼写完全一致的 kebab-case frontmatter 键 `disable-model-invocation` 和 `user-invocable`。它接受 YAML 布尔值，以及不区分大小写的 `true`/`false`、`yes`/`no`、`on`/`off` 和 `1`/`0`，与 Claude skills 实际支持的布尔写法一致。它将 `disable-model-invocation` 映射为相反的正向字段，即使两个键都不存在，也会根据默认值填充两个正向字段。外部使用的驼峰式拼写会被拒绝，并产生有针对性的警告；本仓库尚处于发布前阶段，因此不为磁盘格式保留兼容别名。
|
||||
本地提供方只接受拼写完全一致的 kebab-case frontmatter 键 `disable-model-invocation` 和 `user-invocable`。它接受 YAML 布尔值，以及不区分大小写的 `true`/`false`、`yes`/`no`、`on`/`off` 和 `1`/`0`，与 Claude skills 实际支持的布尔写法一致。它将 `disable-model-invocation` 映射为相反的正向字段，即使两个键都不存在，也会根据默认值填充两个正向字段。若使用外部驼峰式拼写或提供非布尔调用值，发现流程会丢弃整个 skill，并给出有针对性的警告；本仓库尚处于发布前阶段，因此不为磁盘格式保留兼容别名。调用数据校验遵循失败时默认拒绝原则，因为忽略这类数据会默认授予权限，可能使 skill 暴露在已禁用的接口上；与之不同，类型错误的可选 `whenToUse` 和 `metadata` 值会被省略，因为它们不参与调用判定。
|
||||
|
||||
面向模型的 `dsh-tool-skill` 目录和 loader 执行 `isModelInvocable`。TUI 的 `/skill:` 自动补全与精确名称 loader 在本地执行用户字段，因此仅允许用户调用的 skill 即使不出现在模型发现结果中，仍会在此处显示并可加载，同时不会将可选的 skill peer 变成运行时导入。浏览器的 `skill.list` RPC 提供的是由用户选择、但仍要求模型加载的引用，因此只公开同时允许模型和用户调用的 skill；本次改动不新增让浏览器直接加载 skill 的 RPC。
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/skill/skill-local/README.md
|
||||
README.md: addabda98490b49736c1aa5053f5734978079a20
|
||||
README.zh.md: 1ab1a43d70d8393ba8c837f384e3a422cfdc1d3c
|
||||
README.md: 40666f8e56878260eeef13d378450273b950048d
|
||||
README.zh.md: edf3ef59539d85c903be788d063cfde74a5e16b2
|
||||
|
||||
@@ -38,7 +38,7 @@ When `ctx.fs` is available, discovery lists roots through `ctx.fs.listDir`, read
|
||||
|
||||
Skills can be single-level directory bundles (`<name>/SKILL.md`) or flat Markdown files (`<name>.md`). Nested `**/SKILL.md` discovery is intentionally not part of v1. Frontmatter is parsed as an open YAML object with the `yaml` package; this provider currently interprets required `name` and `description`, plus optional `whenToUse`, `metadata`, `disable-model-invocation`, and `user-invocable`. Names must be kebab-case.
|
||||
|
||||
The two invocation fields accept YAML booleans and the case-insensitive forms `true`/`false`, `yes`/`no`, `on`/`off`, and `1`/`0`. `disable-model-invocation: true` excludes the skill from model-facing catalogs and loaders; `user-invocable: false` excludes it from human-facing commands. Each omitted field defaults to permitting its surface, and the provider always emits both positive internal policy values, including when both keys are absent. The camel-case spellings `disableModelInvocation`, `modelInvocable`, and `userInvocable` are rejected with a warning instead of acting as compatibility aliases.
|
||||
The two invocation fields accept YAML booleans and the case-insensitive forms `true`/`false`, `yes`/`no`, `on`/`off`, and `1`/`0`. `disable-model-invocation: true` excludes the skill from model-facing catalogs and loaders; `user-invocable: false` excludes it from human-facing commands. Each omitted field defaults to permitting its surface, and the provider always emits both positive internal policy values, including when both keys are absent. A rejected camel-case spelling or a non-boolean invocation value drops the entire skill from discovery with a warning instead of discarding only that field or falling back to a permissive default. Invocation policy fails closed because ignoring invalid data could expose a skill on a disabled surface; wrong-typed optional `whenToUse` and `metadata` values are omitted because neither currently grants invocation.
|
||||
|
||||
## Model Experience
|
||||
|
||||
|
||||
@@ -38,7 +38,7 @@
|
||||
|
||||
Skill 可以是单层目录 bundle（`<name>/SKILL.md`），也可以是平铺 Markdown 文件（`<name>.md`）。v1 刻意不支持发现嵌套的 `**/SKILL.md`。Frontmatter 使用 `yaml` 包解析为开放的 YAML 对象；该提供方目前解析必填的 `name` 和 `description`，以及可选的 `whenToUse`、`metadata`、`disable-model-invocation` 和 `user-invocable`。名称必须使用 kebab-case。
|
||||
|
||||
这两个调用字段接受 YAML 布尔值，以及不区分大小写的 `true`/`false`、`yes`/`no`、`on`/`off` 和 `1`/`0`。`disable-model-invocation: true` 会从面向模型的目录和 loader 中排除该 skill；`user-invocable: false` 会从面向用户的命令中排除该 skill。每个省略的字段都默认为允许对应接口调用；提供方始终输出两个正向内部策略值，即使两个键都不存在也不例外。系统会拒绝驼峰形式的 `disableModelInvocation`、`modelInvocable` 和 `userInvocable` 并记录警告，而不会将其作为兼容别名。
|
||||
这两个调用字段接受 YAML 布尔值，以及不区分大小写的 `true`/`false`、`yes`/`no`、`on`/`off` 和 `1`/`0`。`disable-model-invocation: true` 会从面向模型的目录和 loader 中排除该 skill；`user-invocable: false` 会从面向用户的命令中排除该 skill。每个省略的字段都默认为允许对应接口调用；提供方始终输出两个正向内部策略值，即使两个键都不存在也不例外。若使用驼峰拼写或提供非布尔调用值，系统会记录警告并从发现结果中排除整个 skill，而不是只丢弃该字段或回退到宽松的默认值。调用策略校验遵循失败时默认拒绝原则，因为忽略无效数据可能会在已禁用的接口上暴露 skill；类型错误的可选 `whenToUse` 和 `metadata` 值则会被省略，因为这两个字段目前都不授予调用权限。
|
||||
|
||||
## 模型体验
|
||||
|
||||
|
||||
Reference in New Issue
Block a user