feat(skill): add invocation controls
This commit is contained in:
Yichen Jiang
@@ -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/2026-07-05-skill-system.md
|
||||
2026-07-05-skill-system.md: 4fc621a9fdfa8042ebf3eb1975f0930cb1bf116c
|
||||
2026-07-05-skill-system.zh.md: 0dbebd211a1fa9e434d3f0a189c936f2b1c76574
|
||||
2026-07-05-skill-system.md: e90af985fc66dec93b3d71ce45d9aa0683cd5371
|
||||
2026-07-05-skill-system.zh.md: 4187f9bbb7f190a94b1fa1bc0dd331a040a114d5
|
||||
@@ -18,13 +18,13 @@ Provider plugins register synchronously during `apply()`. Provider membership is
|
||||
|
||||
The local provider scans cwd-sensitive project roots, custom roots, and user roots in first-wins rank order: project `.dsh`, project `.agents`, `customSkillDirs`, user `.dsh`, then user `.agents`. The user `.dsh/skills` scan skips `.system` so a system-owned directory is not treated as normal user content. DeepSeek Harness does not ship built-in system skills; embedded or remote providers supply additional skills when configured.
|
||||
|
||||
Each skill is either `<name>/SKILL.md` or `<name>.md` with YAML frontmatter. `name` and `description` are required; `whenToUse`, `disableModelInvocation`, and `metadata` are optional. Names are kebab-case. YAML frontmatter is parsed with the `yaml` package instead of `js-yaml` or a hand-written parser: `yaml` is the already-declared modern parser for this package's limited frontmatter needs, and a narrow parser would either reject valid YAML users expect to work or grow into an unreviewed YAML subset.
|
||||
Each skill is either `<name>/SKILL.md` or `<name>.md` with YAML frontmatter. `name` and `description` are required; `whenToUse`, `metadata`, `disable-model-invocation`, and `user-invocable` are optional. Names are kebab-case. The invocation fields project into a typed nested policy as defined by the [independent model and user invocation decision](2026-07-28-skill-invocation-policy.md); the parser rejects the old camel-case spellings. YAML frontmatter is parsed with the `yaml` package instead of `js-yaml` or a hand-written parser: `yaml` is the already-declared modern parser for this package's limited frontmatter needs, and a narrow parser would either reject valid YAML users expect to work or grow into an unreviewed YAML subset.
|
||||
|
||||
Local skill filesystem I/O goes through `ctx.fs` when a filesystem service is loaded: project-root lookup probes `.git` with `resolve` and `stat`, root discovery uses `listDir`, and skill reads use `readText`. The Node filesystem remains a fallback for minimal contexts that mount `dsh-skill-local` without the fs seam. Missing roots, unreadable or malformed skill files, and transient provider `list()` failures degrade to warn-and-skip so one bad source does not make every agent request fail; malformed candidates still fail fast because they are provider contract violations.
|
||||
|
||||
`dsh-tool-skill` injects one durable user-role `<system-reminder>` catalog as a sourced `user/message` at the session's first `agent/step`, and only when that agent's tool view resolves this plugin's exact `skill` registration. The catalog contains sorted skill name and description only; it excludes bodies, paths, sources, providers, and routing hints. Descriptions are whitespace-normalized, XML-escaped, and capped by `catalogDescriptionMaxLength`, whose default is `500` and minimum is `3`. Full skill bodies are never included in the catalog. (The catalog originally rode the request-only [session-prefix seam](../../archived/feature/2026-07-07-session-prefix.md), archived; the [unified sourced-message decision](../architecture/2026-07-22-unified-send-and-coalesced-user-messages.md) moved it into durable history.)
|
||||
|
||||
The `skill({ name })` tool loads one full skill for the current agent cwd and returns a tool result containing `<skill_content name="...">`, `<skill_resources>`, and `<skill_instructions>`. `resourceBase` supplies a directory, URL, or opaque provider-managed base for explicitly referenced scripts, references, and assets; resources load only as needed, without directory enumeration. An unresolved name reports that the skill is unknown or no longer available; invalid names and skills marked `disableModelInvocation` retain distinct tool errors. The tool result is the model-visible disclosure path.
|
||||
The registry's `list()` returns every winning summary, while model and user consumers apply the invocation predicates owned by the [independent invocation-policy decision](2026-07-28-skill-invocation-policy.md). The `skill({ name })` tool loads one model-invocable skill for the current agent cwd and returns a tool result containing `<skill_content name="...">`, `<skill_resources>`, and `<skill_instructions>`. `resourceBase` supplies a directory, URL, or opaque provider-managed base for explicitly referenced scripts, references, and assets; resources load only as needed, without directory enumeration. An unresolved name reports that the skill is unknown or no longer available; invalid names and skills marked `invocation.disableModelInvocation` retain distinct tool errors. The tool result is the model-visible disclosure path.
|
||||
|
||||
The data structures and catalog/tool contract are documented in [skills.md](../../../../docs/core-data-structures/skills.md), with service signatures in the generated [services catalog](../../../../docs/cordis-catalog/services.md).
|
||||
|
||||
@@ -52,4 +52,4 @@ The catalog is deterministic for a fixed root set and runtime registration revis
|
||||
|
||||
## Deferred
|
||||
|
||||
Forked skill contexts (`context: fork`), parameter declarations and hints (`arguments` and `argument-hint`), and per-skill tool constraints (`allowed-tools` and `disallowed-tools`) are outside the shipped contract. The registry, local provider, and model-facing tool do not parse, advertise, or enforce these fields, and the `user-invocable` frontmatter field is likewise unparsed. Direct user invocation itself ships as a consumer-side affordance instead: the TUI front door offers a manual `/skill:<name>` command over the registry's existing `list()` and `get()` methods, without a registry, provider, or tool contract change — see [the TUI skill slash command](2026-07-21-tui-skill-slash-command.md).
|
||||
Forked skill contexts (`context: fork`), parameter declarations and hints (`arguments` and `argument-hint`), and per-skill tool constraints (`allowed-tools` and `disallowed-tools`) are outside the shipped contract. The registry, local provider, and model-facing tool do not parse, advertise, or enforce these fields. Direct user invocation ships as a TUI affordance over the shared invocation policy and trusted `get()` primitive; see [the TUI skill slash command](2026-07-21-tui-skill-slash-command.md).
|
||||
@@ -18,13 +18,13 @@ DeepSeek Harness 使用同一原语，使项目特定的评审、插件编写和
|
||||
|
||||
本地提供方按先到先得的排名顺序扫描 cwd 敏感的项目根目录、自定义根目录和用户根目录：项目 `.dsh`、项目 `.agents`、`customSkillDirs`、用户 `.dsh`，然后是用户 `.agents`。用户 `.dsh/skills` 扫描跳过 `.system`，以免系统拥有的目录被当作普通用户内容处理。DeepSeek Harness 不随附内置系统 skill；嵌入式或远程提供方在配置后提供额外 skill。
|
||||
|
||||
每个 skill 是 `<name>/SKILL.md` 或带 YAML frontmatter 的 `<name>.md`。`name` 和 `description` 为必填；`whenToUse`、`disableModelInvocation` 和 `metadata` 为可选。名称采用 kebab-case。YAML frontmatter 使用 `yaml` 包（package）解析，而非 `js-yaml` 或手写解析器：`yaml` 是本包有限 frontmatter 需求已声明的现代解析器，窄解析器要么拒绝用户预期可用的合法 YAML，要么膨胀为一个未经评审的 YAML 子集。
|
||||
每个 skill 是 `<name>/SKILL.md` 或带 YAML frontmatter 的 `<name>.md`。`name` 和 `description` 为必填；`whenToUse`、`metadata`、`disable-model-invocation` 和 `user-invocable` 为可选。名称采用 kebab-case。调用字段会投影到类型化的嵌套策略中，具体由[模型与用户独立调用决策](2026-07-28-skill-invocation-policy.md)定义；解析器会拒绝旧的驼峰拼写。YAML frontmatter 使用 `yaml` 包（package）解析，而非 `js-yaml` 或手写解析器：`yaml` 是本包有限 frontmatter 需求已声明的现代解析器，窄解析器要么拒绝用户预期可用的合法 YAML，要么膨胀为一个未经评审的 YAML 子集。
|
||||
|
||||
本地 skill 的文件系统 I/O 在加载了文件系统服务时通过 `ctx.fs` 进行：项目根目录查找使用 `resolve` 和 `stat` 探测 `.git`，根目录发现使用 `listDir`，skill 读取使用 `readText`。Node 文件系统作为后备，供在不挂载 fs seam 的最小上下文中加载 `dsh-skill-local` 时使用。缺失的根目录、不可读或格式错误的 skill 文件、以及提供方 `list()` 的瞬态失败均降级为警告并跳过，使一个坏源不会导致所有 agent 请求失败；格式错误的候选项仍然快速失败，因为它们违反了提供方契约。
|
||||
|
||||
`dsh-tool-skill` 在会话的第一个 `agent/step` 注入一个持久化的 user-role `<system-reminder>` 目录，作为带来源的 `user/message`，且仅当该 agent 的工具视图解析到本插件精确的 `skill` 注册时才注入。该目录仅包含排序后的 skill 名称与描述；不包含正文、路径、来源、提供方和路由提示。描述经过空白规范化、XML 转义，并受 `catalogDescriptionMaxLength` 上限约束，其默认值为 `500`，最小值为 `3`。完整的 skill 正文从不包含在目录中。（目录最初通过仅请求的[会话前缀 seam](../../archived/feature/2026-07-07-session-prefix.md)（已归档）传递；[统一带来源消息的决策](../architecture/2026-07-22-unified-send-and-coalesced-user-messages.md)将其移入持久化历史。）
|
||||
|
||||
`skill({ name })` 工具为当前 agent cwd 加载一个完整 skill，返回包含 `<skill_content name="...">`、`<skill_resources>` 和 `<skill_instructions>` 的工具结果。`resourceBase` 提供一个目录、URL 或不透明的提供方管理的基路径，用于显式引用的脚本、参考资料和资产；资源仅按需加载，不进行目录枚举。无法解析的名称报告该 skill 未知或不再可用；无效名称和标记了 `disableModelInvocation` 的 skill 保留不同的工具错误。工具结果是面向模型的可见披露路径。
|
||||
注册表的 `list()` 返回全部胜出摘要，而模型与用户消费方应用[独立调用策略决策](2026-07-28-skill-invocation-policy.md)定义的调用判定。`skill({ name })` 工具为当前 agent cwd 加载一个模型可调用的 skill，返回包含 `<skill_content name="...">`、`<skill_resources>` 和 `<skill_instructions>` 的工具结果。`resourceBase` 提供一个目录、URL 或不透明的提供方管理的基路径，用于显式引用的脚本、参考资料和资产；资源仅按需加载，不进行目录枚举。无法解析的名称报告该 skill 未知或不再可用；无效名称和标记了 `invocation.disableModelInvocation` 的 skill 保留不同的工具错误。工具结果是面向模型的可见披露路径。
|
||||
|
||||
数据结构与目录/工具契约记录在 [skills.md](../../../../docs/core-data-structures/skills.md) 中，服务签名见生成的[服务目录](../../../../docs/cordis-catalog/services.md)。
|
||||
|
||||
@@ -52,4 +52,4 @@ agent-core 主干包含一个目录贡献者、一个本地提供方和一个面
|
||||
|
||||
## 延后
|
||||
|
||||
Fork 的 skill 上下文（`context: fork`）、参数声明与提示（`arguments` 和 `argument-hint`）、以及逐 skill 的工具约束（`allowed-tools` 和 `disallowed-tools`）不在已交付的契约范围内。注册表、本地提供方和面向模型的工具不解析、不广播、也不执行这些字段，`user-invocable` frontmatter 字段同样不会被解析。直接用户调用本身则作为消费方层面的能力交付：TUI 前门基于注册表现有的 `list()` 与 `get()` 方法提供手动 `/skill:<name>` 命令，无需变更注册表、提供方或工具契约——见 [TUI skill 斜杠命令](2026-07-21-tui-skill-slash-command.md)。
|
||||
Fork 的 skill 上下文（`context: fork`）、参数声明与提示（`arguments` 和 `argument-hint`）、以及逐 skill 的工具约束（`allowed-tools` 和 `disallowed-tools`）不在已交付的契约范围内。注册表、本地提供方和面向模型的工具不解析、不广播、也不执行这些字段。直接用户调用作为 TUI 功能交付，基于共享调用策略和受信的 `get()` 原语；见 [TUI skill 斜杠命令](2026-07-21-tui-skill-slash-command.md)。
|
||||
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# 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
|
||||
2026-07-21-tui-skill-slash-command.md: 8370ab61f552a6a60177b6da0b598dd142d21960
|
||||
2026-07-21-tui-skill-slash-command.zh.md: 66edec6ecd5c2a974b56e08bd9e924729302cc4a
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.md
|
||||
2026-07-21-tui-skill-slash-command.md: 872e1f109728731e0d55e81a538c81e794724856
|
||||
2026-07-21-tui-skill-slash-command.zh.md: 772e25745ea7ab25f715208a9c6b1d10cf0c6e65
|
||||
@@ -10,17 +10,17 @@ The [skill system](2026-07-05-skill-system.md) shipped with model-initiated load
|
||||
|
||||
## Decision
|
||||
|
||||
The [`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) front door owns a `/skill:<name> [instructions]` command. On submit it loads the named skill and delivers one text block as a user turn — sent with `agent.send()` while idle and `agent.steer()` while running, the same rule as ordinary editor input. The block is `renderSkillInvocation(skill, instructions)`: a `<skill name="…">` element wrapping the skill body, preceded by one resource-base line when the provider exposes one, with the user's trailing text appended after a blank line. The command is a TUI-only affordance; it adds no model-facing tool and changes no skill-system package contract.
|
||||
The [`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) front door owns a `/skill:<name> [instructions]` command. On submit it loads the named skill and delivers one text block as a user turn — sent with `agent.send()` while idle and `agent.steer()` while running, the same rule as ordinary editor input. The block is `renderSkillInvocation(skill, instructions)`: a `<skill name="…">` element wrapping the skill body, preceded by one resource-base line when the provider exposes one, with the user's trailing text appended after a blank line. The command is a TUI-only affordance; it adds no model-facing tool. Its visibility and loading policy comes from the shared [independent model and user skill invocation policy](2026-07-28-skill-invocation-policy.md).
|
||||
|
||||
The TUI reads the skill service through `ctx.get('skills')`, not a declared injection, because skills mount conditionally: a deployment without the registry keeps a working front door, and `/skill:` there reports that skills are unavailable rather than failing to mount. `createTuiChat` is synchronous while `ctx.skills.list()` is async, so autocomplete seeds the static slash commands immediately and rebuilds the provider with `skill:<name>` entries once the catalog resolves; a resolution that arrives after disposal is dropped, and a rejected lookup keeps the base commands.
|
||||
|
||||
Autocomplete lists only model-invocable skills — it is built from `list()`, which omits `disableModelInvocation` skills — while manual submission resolves through `get()`, which the skill registry documents as the trusted-caller path that returns disabled skills too. So a person can load any skill by typing its exact name, but the completion menu never advertises a skill the model is meant not to see. Each completion entry is labeled with its winning source's scope — `(project)` for the `project-` sources, `(user)` for every other source — in the slash-command argument-hint slot, which the menu shows but selection never inserts, so trailing instructions still follow the completed name. An unknown name, an empty name after the prefix, and a lookup failure each surface as a transcript notice without sending anything.
|
||||
Autocomplete filters the invocation-neutral `list()` result with `isUserInvocable`, and manual submission applies the same predicate after trusted `get()` resolves the definition. A user-only skill can therefore appear and load even when model invocation is disabled, while a user-disabled skill is neither advertised nor loadable by exact name. Each completion entry is labeled with its winning source's scope — `(project)` for the `project-` sources, `(user)` for every other source — in the slash-command argument-hint slot, which the menu shows but selection never inserts, so trailing instructions still follow the completed name. An unknown name, an empty name after the prefix, a user-disabled name, and a lookup failure each surface as a transcript notice without sending anything.
|
||||
|
||||
`renderSkillInvocation` and the resource-base line are the TUI's own, deliberately not reused from `dsh-tool-skill`'s `skill` tool result. The tool wraps a body in `<skill_content>`/`<skill_resources>`/`<skill_instructions>` for a *tool result*; a manual invocation is a *user turn*, and coupling the two renderers would force one model-facing shape to serve both surfaces. The cost is two renderers that both format a skill body; the benefit is that each surface's model-facing text evolves independently, and each is pinned where it is produced.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Add a `user-invocable` frontmatter field and enforce it in the registry.** Rejected for this change. The skill-system note defers that field, and manual invocation does not need it: the TUI is a trusted local caller, so `get()` already authorizes loading any skill, and autocomplete visibility keys off the existing `disableModelInvocation`. A new per-skill field would add a contract to the registry, local provider, and tool with no current consumer beyond visibility, which `disableModelInvocation` already covers.
|
||||
**Add a `user-invocable` frontmatter field only inside the original TUI change.** Rejected there because a TUI-only field would have changed the registry, provider, and tool contract without a shared invocation model. The later [independent invocation-policy decision](2026-07-28-skill-invocation-policy.md) adds it across every relevant consumer and preserves `get()` as a trusted primitive.
|
||||
|
||||
**Declare `skills` as a TUI injection.** Rejected because skills mount conditionally; a declared injection would make the front door require the registry and refuse to mount without it, contradicting the package's optional-service stance. `ctx.get('skills')` reads the global store and tolerates absence.
|
||||
|
||||
|
||||
@@ -10,17 +10,17 @@ Status: implemented
|
||||
|
||||
## Decision
|
||||
|
||||
[`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) 前门拥有一条 `/skill:<name> [instructions]` 命令。提交时它加载指定的 skill，并投递一个文本块作为用户轮次——空闲时用 `agent.send()` 发送、运行中用 `agent.steer()` 中途引导，与普通编辑器输入遵循同一规则。该文本块由 `renderSkillInvocation(skill, instructions)` 生成：一个包裹 skill 正文的 `<skill name="…">` 元素，当提供方暴露资源基址时在其前加一行资源基址行，用户尾随的文本在空行之后追加。该命令是 TUI 独有的能力；它不新增任何面向模型的工具，也不改动任何 skill 系统包的契约。
|
||||
[`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) 前门拥有一条 `/skill:<name> [instructions]` 命令。提交时它加载指定的 skill，并投递一个文本块作为用户轮次——空闲时用 `agent.send()` 发送、运行中用 `agent.steer()` 中途引导，与普通编辑器输入遵循同一规则。该文本块由 `renderSkillInvocation(skill, instructions)` 生成：一个包裹 skill 正文的 `<skill name="…">` 元素，当提供方暴露资源基址时在其前加一行资源基址行，用户尾随的文本在空行之后追加。该命令是 TUI 独有的功能；它不新增任何面向模型的工具。其可见性和加载策略来自共享的[模型与用户独立 skill 调用策略](2026-07-28-skill-invocation-policy.md)。
|
||||
|
||||
TUI 通过 `ctx.get('skills')` 读取 skill 服务，而非声明式注入，因为 skill 是条件挂载的：没有注册表的部署仍保有可用的前门，此时 `/skill:` 会报告 skill 不可用，而不是挂载失败。`createTuiChat` 是同步的，而 `ctx.skills.list()` 是异步的，所以自动补全先立即种入静态斜杠命令，待目录解析完成后再用 `skill:<name>` 条目重建 provider（提供方）；在 dispose（资源释放）之后才到达的解析结果会被丢弃，而被拒绝的查找会保留基础命令。
|
||||
|
||||
自动补全只列出模型可调用的 skill——它基于 `list()` 构建，而 `list()` 会略去 `disableModelInvocation` 的 skill——手动提交则通过 `get()` 解析，skill 注册表将其记录为返回被禁用 skill 的可信调用方路径。因此用户可以通过键入 skill 的确切名称加载任意 skill，但补全菜单绝不会宣传一个本不该让模型看见的 skill。每个补全条目都以其胜出来源的作用域为标签——`project-` 来源标为 `(project)`，其他一切来源标为 `(user)`——标签置于斜杠命令的参数提示位，菜单会显示它，但选中时绝不会插入，因此尾随指令仍然跟在补全后的名称之后。未知名称、前缀之后为空的名称、以及查找失败，都会各自呈现为 transcript（文本记录）中的一条通知，且不发送任何内容。
|
||||
自动补全使用 `isUserInvocable` 过滤与调用策略无关的 `list()` 结果；手动提交则在受信的 `get()` 解析定义后应用相同判定。因此，即使模型调用已禁用，仅供用户调用的 skill 仍会显示并可加载；用户禁用的 skill 既不会展示，也无法按精确名称加载。每个补全条目都以其胜出来源的作用域为标签——`project-` 来源标为 `(project)`，其他一切来源标为 `(user)`——标签置于斜杠命令的参数提示位，菜单会显示它，但选中时绝不会插入，因此尾随指令仍然跟在补全后的名称之后。未知名称、前缀之后为空的名称、用户禁用的名称以及查找失败，都会各自呈现为 transcript（文本记录）中的一条通知，且不发送任何内容。
|
||||
|
||||
`renderSkillInvocation` 及资源基址行是 TUI 自有的，刻意不复用 `dsh-tool-skill` 的 `skill` 工具结果。该工具把正文包进 `<skill_content>`/`<skill_resources>`/`<skill_instructions>` 是为了一个*工具结果*；而手动调用是一个*用户轮次*，把两个渲染器耦合起来会迫使一种面向模型的形态同时服务两个界面。代价是两个都在格式化 skill 正文的渲染器；收益是各界面面向模型的文本可以独立演进，且各自在其产出处被固定。
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**新增 `user-invocable` frontmatter 字段并在注册表中强制执行。** 本次改动否决。skill 系统 note 把该字段列为待办，而手动调用并不需要它：TUI 是可信的本地调用方，`get()` 已经授权加载任意 skill，自动补全的可见性以既有的 `disableModelInvocation` 为准。新增一个逐 skill 字段会给注册表、本地提供方和工具都加上一条契约，而除了可见性之外没有任何现有消费方，可见性又已由 `disableModelInvocation` 覆盖。
|
||||
**仅在最初的 TUI 变更内新增 `user-invocable` frontmatter 字段。** 当时未采纳，因为 TUI 独有的字段会在没有共享调用模型的情况下改变注册表、提供方和工具契约。后续的[独立调用策略决策](2026-07-28-skill-invocation-policy.md)将其扩展到每个相关消费方，并保留 `get()` 作为受信原语。
|
||||
|
||||
**把 `skills` 声明为 TUI 注入。** 否决，因为 skill 是条件挂载的；声明式注入会使前门必须依赖注册表，缺少它就拒绝挂载，与本包可选服务的立场相悖。`ctx.get('skills')` 读取全局存储并容忍其缺失。
|
||||
|
||||
|
||||
@@ -0,0 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# 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: e2c01c4343fec72ba285b13f78c1995b05dae928
|
||||
2026-07-28-skill-invocation-policy.zh.md: d5f9bac59fd3d21107ed3ffca52fa16038a63832
|
||||
@@ -0,0 +1,50 @@
|
||||
# Agent Note: Independent model and user skill invocation policy
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-28-skill-invocation-policy.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The skill registry originally treated discovery as a model catalog: `ctx.skills.list()` removed model-disabled skills, while `ctx.skills.get()` remained an unfiltered trusted loader. That was enough for model-initiated loading, but it could not represent Claude-compatible skills that are advertised only to a person, only to a model, to both, or to neither. The TUI compounded the mismatch by deriving user autocomplete from the model-filtered list and allowing every exact name through `get()`.
|
||||
|
||||
The local parser also exposed the internal camel-case `disableModelInvocation` spelling as frontmatter. Supporting the established `disable-model-invocation` and `user-invocable` fields requires a durable domain representation without turning every possible YAML key into an untyped cross-package contract.
|
||||
|
||||
## Decision
|
||||
|
||||
`SkillSummary` carries an optional typed `invocation: SkillInvocationPolicy` object. Its current fields are `disableModelInvocation?: boolean` and `userInvocable?: boolean`; future frontmatter keys remain outside the domain model until a consumer and enforcement contract exist. The local provider still parses frontmatter as an open `Record<string, unknown>`, then projects only recognized fields into the typed policy.
|
||||
|
||||
`ctx.skills.list()` returns every winning summary and no longer chooses an invocation surface. `isModelInvocable(skill)` excludes only `disableModelInvocation: true`; `isUserInvocable(skill)` excludes only `userInvocable: false`. Missing fields preserve model and user invocation. `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. The old camel-case spellings are rejected with a targeted warning; this pre-release repository does not keep an on-disk compatibility alias.
|
||||
|
||||
The model-facing `dsh-tool-skill` catalog and loader enforce `isModelInvocable`. The TUI `/skill:` autocomplete and exact loader enforce `isUserInvocable`, so a user-only skill is visible and loadable there even when it is absent from model discovery. 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.
|
||||
|
||||
These rules permit all four combinations:
|
||||
|
||||
| Policy | Model surface | User surface |
|
||||
|---|---|---|
|
||||
| defaults | included | included |
|
||||
| `userInvocable: false` | included | excluded |
|
||||
| `disableModelInvocation: true` | excluded | included |
|
||||
| both restrictive values | excluded | excluded |
|
||||
|
||||
This decision extends the [skill system](2026-07-05-skill-system.md) and supersedes the invocation-policy limitation recorded by the [TUI skill slash command](2026-07-21-tui-skill-slash-command.md).
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Store all frontmatter in a generic `Map` and read string keys in `isModelInvocable` / `isUserInvocable`.** Rejected because misspelled keys, non-boolean values, and consumer-specific coercion would cross package seams without type checking. The parser boundary remains open; the domain model is deliberately typed and narrow.
|
||||
|
||||
**Keep `ctx.skills.list()` model-filtered and add a second user list.** Rejected because discovery, duplicate resolution, caching, and ordering are surface-neutral work. One complete catalog plus explicit predicates prevents those mechanisms from drifting while making each consumer's policy visible at its boundary.
|
||||
|
||||
**Enforce invocation policy inside `ctx.skills.get()`.** Rejected because `get()` cannot know whether its caller is a model tool, a human command, or trusted orchestration. Filtering there would also make the both-disabled quadrant impossible to inspect or administer.
|
||||
|
||||
**Treat camel-case frontmatter as an alias.** Rejected because the external format is the kebab-case Claude skills contract and the repository has no released compatibility obligation. Failing loud avoids silently preserving a nonstandard spelling.
|
||||
|
||||
**Add a browser-side direct skill invocation RPC.** Rejected for this change because the existing browser flow inserts a model reference rather than a loaded instruction body. Its correct policy is therefore the intersection; a direct user-loading surface needs its own wire and logging design.
|
||||
|
||||
## Consequences
|
||||
|
||||
Providers and runtime registrations expose a small typed invocation contract, while local YAML remains extensible. Every new discovery consumer must consciously choose the model predicate, the user predicate, their intersection, or trusted unfiltered access; forgetting that choice is now review-visible rather than hidden in registry behavior.
|
||||
|
||||
The changed model catalog is pinned by the keyless ACP snapshot, which includes a model-only skill and excludes a user-only skill. TUI unit coverage exercises all four policy quadrants, and the real Loader/PTY smoke invokes a user-only local skill through `/skill:`. Registry, local-parser, model-tool, and API-proxy tests cover defaults, supported boolean forms, malformed values, legacy-key rejection, exact-load enforcement, and the browser intersection.
|
||||
@@ -0,0 +1,50 @@
|
||||
# Agent Note: 模型与用户彼此独立的 skill（技能）调用策略
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-28-skill-invocation-policy.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
skill 注册表最初将发现操作视为模型目录：`ctx.skills.list()` 会移除禁止模型调用的 skill，而 `ctx.skills.get()` 仍是不过滤内容的可信 loader。该设计足以支持由模型发起的加载，却无法表示与 Claude 兼容的四类 skill：仅向用户公开、仅向模型公开、同时向两者公开，或者两者均不公开。TUI 从面向模型过滤后的列表中生成用户自动补全，并允许通过 `get()` 加载任意精确名称，这进一步放大了两类调用策略不匹配的问题。
|
||||
|
||||
本地解析器还将内部使用的驼峰式 `disableModelInvocation` 拼写暴露为 frontmatter。若要支持既有的 `disable-model-invocation` 和 `user-invocable` 字段，需要建立持久的领域表示，同时避免把所有可能出现的 YAML 键都变成跨包的无类型契约。
|
||||
|
||||
## 决策
|
||||
|
||||
`SkillSummary` 包含一个可选且类型明确的 `invocation: SkillInvocationPolicy` 对象。该对象当前提供 `disableModelInvocation?: boolean` 和 `userInvocable?: boolean` 两个字段；未来的 frontmatter 键只有在具备消费方和执行契约后，才会进入领域模型。本地提供方仍将 frontmatter 解析为开放的 `Record<string, unknown>`，然后只把已识别字段投影到类型化策略中。
|
||||
|
||||
`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)` 只排除 `disableModelInvocation: true` 的 skill；`isUserInvocable(skill)` 只排除 `userInvocable: false` 的 skill。字段缺失时，模型和用户均可调用。`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。旧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。
|
||||
|
||||
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 执行 `isUserInvocable`，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。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。
|
||||
|
||||
这些规则允许以下四种组合：
|
||||
|
||||
| 策略 | 模型侧接口 | 用户侧接口 |
|
||||
|---|---|---|
|
||||
| 默认值 | 包含 | 包含 |
|
||||
| `userInvocable: false` | 包含 | 排除 |
|
||||
| `disableModelInvocation: true` | 排除 | 包含 |
|
||||
| 两个限制值同时存在 | 排除 | 排除 |
|
||||
|
||||
该决策扩展了 [skill 系统](2026-07-05-skill-system.md)，并取代 [TUI skill 斜杠命令](2026-07-21-tui-skill-slash-command.md)中记录的调用策略限制。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
**将所有 frontmatter 存入通用 `Map`，并在 `isModelInvocable` / `isUserInvocable` 中读取字符串键。** 不予采纳，因为拼写错误的键、非布尔值以及各消费方自行采用的类型转换都会越过包边界，且无法获得类型检查。解析器边界仍保持开放；领域模型则有意采用类型明确的窄接口。
|
||||
|
||||
**保持 `ctx.skills.list()` 仅返回允许模型调用的 skill，并另增一份用户列表。** 不予采纳，因为发现、重复项解析、缓存和排序都是与调用接口无关的工作。采用一份完整目录和显式判定函数，可以避免这些机制逐渐分化，并在各消费方边界清楚呈现其策略。
|
||||
|
||||
**在 `ctx.skills.get()` 内执行调用策略。** 不予采纳，因为 `get()` 无法判断调用方是模型工具、人类命令还是可信编排逻辑。在此处过滤还会使两个接口均禁止调用的组合无法被检查或管理。
|
||||
|
||||
**将驼峰式 frontmatter 作为别名处理。** 不予采纳，因为外部格式遵循采用 kebab-case 的 Claude skills 契约，而本仓库尚未发布，无需承担兼容义务。快速失败可以避免暗中保留不符合标准的拼写。
|
||||
|
||||
**增加由浏览器端直接调用 skill 的 RPC。** 本次改动不予采纳，因为现有浏览器流程插入的是模型引用，而非已经加载的指令正文。因此，该流程应当取模型与用户调用策略的交集；直接由用户加载的接口需要单独设计协议与日志记录方式。
|
||||
|
||||
## 后果
|
||||
|
||||
提供方与运行时注册对外提供小而类型明确的调用契约，同时本地 YAML 仍可扩展。每个新的发现消费方都必须明确选择模型判定函数、用户判定函数、两者的交集，或可信且不过滤的访问方式；如果遗漏这项选择，评审时可以直接看出问题，而不会再被注册表行为掩盖。
|
||||
|
||||
无密钥 ACP（Agent Client Protocol）快照固定了模型目录的变更：其中包含仅允许模型调用的 skill，并排除仅允许用户调用的 skill。TUI 单元测试覆盖全部四种策略组合，真实 Loader/PTY 冒烟测试则通过 `/skill:` 调用仅允许用户调用的本地 skill。注册表、本地解析器、模型工具和 API 代理测试覆盖默认值、支持的布尔写法、格式错误的值、旧键拒绝、精确名称加载时的策略执行，以及浏览器侧的策略交集。
|
||||
@@ -1187,7 +1187,7 @@ export interface Config {
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/skill/skill/src/index.ts:113`](../packages/skill/skill/src/index.ts)
|
||||
Source: [`packages/skill/skill/src/index.ts:139`](../packages/skill/skill/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-skill-local`
|
||||
|
||||
@@ -1207,7 +1207,7 @@ export interface Config {
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/skill/skill-local/src/index.ts:41`](../packages/skill/skill-local/src/index.ts)
|
||||
Source: [`packages/skill/skill-local/src/index.ts:42`](../packages/skill/skill-local/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-spill-local`
|
||||
|
||||
@@ -1666,7 +1666,7 @@ export interface Config {
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/skill/tool-skill/src/index.ts:20`](../packages/skill/tool-skill/src/index.ts)
|
||||
Source: [`packages/skill/tool-skill/src/index.ts:25`](../packages/skill/tool-skill/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tool-subagent`
|
||||
|
||||
|
||||
@@ -1434,11 +1434,12 @@ registerProvider(provider: SkillProvider): () => void
|
||||
register(skill: SkillRegistration): () => void
|
||||
|
||||
/**
|
||||
* List model-invocable skill summaries for a workspace. Lookup options and
|
||||
* provider candidates are readonly same-process values borrowed throughout
|
||||
* discovery.
|
||||
* List invocation-neutral skill summaries for a workspace. Consumers apply
|
||||
* model or user invocation policy at their operational boundary. Lookup
|
||||
* options and provider candidates are readonly same-process values borrowed
|
||||
* throughout discovery.
|
||||
* @param options - lookup options; `cwd` selects project roots and `signal` cancels discovery.
|
||||
* @returns sorted summaries, excluding skills disabled for model invocation.
|
||||
* @returns all sorted winning summaries.
|
||||
*/
|
||||
async list(options: SkillLookupOptions = {}): Promise<SkillSummary[]>
|
||||
|
||||
@@ -1455,7 +1456,7 @@ async get(name: string, options: SkillLookupOptions = {}): Promise<SkillDefiniti
|
||||
|
||||
Types: [SkillDefinition](../core-data-structures/skills.md) · [SkillLookupOptions](../core-data-structures/skills.md) · [SkillProvider](../core-data-structures/skills.md) · [SkillRegistration](../core-data-structures/skills.md) · [SkillSummary](../core-data-structures/skills.md)
|
||||
|
||||
Source: [`packages/skill/skill/src/index.ts:141`](../../packages/skill/skill/src/index.ts)
|
||||
Source: [`packages/skill/skill/src/index.ts:167`](../../packages/skill/skill/src/index.ts)
|
||||
|
||||
## `ctx.spillStore` — `SpillStore` (abstract seam)
|
||||
|
||||
@@ -1957,7 +1958,7 @@ The concrete provider retains pi-tui, focus, and terminal lifecycle state. Plugi
|
||||
abstract openOverlay(request: TuiOverlayRequest): TuiOverlaySession
|
||||
```
|
||||
|
||||
Source: [`packages/ui/tui/src/index.ts:188`](../../packages/ui/tui/src/index.ts)
|
||||
Source: [`packages/ui/tui/src/index.ts:191`](../../packages/ui/tui/src/index.ts)
|
||||
|
||||
## `ctx.userInteraction` — `UserInteractionService`
|
||||
|
||||
|
||||
@@ -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 docs/core-data-structures/skills.md
|
||||
skills.md: 2f47881ba5b694ab5affa43add60f340c4d17dbb
|
||||
skills.zh.md: b5a212f81cc17975cb203738f2636bd5f5695f4f
|
||||
skills.md: e641ffd578e52dcda8a1c191123c097333c6f238
|
||||
skills.zh.md: c5de8201c4e762438d15f12b169556543b6758b1
|
||||
@@ -62,19 +62,29 @@ type SkillSource = 'project-dsh' | 'project-agents' | 'runtime' | 'user-dsh' | '
|
||||
|
||||
## Summaries, candidates, and complete definitions
|
||||
|
||||
`SkillSummary` is the registry's model-invocable summary shape. Consumers choose which fields to render; the session catalog uses only `name` and `description`, never the body or absolute file path. `disableModelInvocation` hides a skill from model listings while allowing trusted code to load it by name.
|
||||
`SkillSummary` is the registry's invocation-neutral summary shape. Consumers choose which entries and fields to render; the model session catalog uses only model-invocable `name` and `description`, never the body or absolute file path. `SkillInvocationPolicy` keeps the two independent invocation controls typed without turning arbitrary frontmatter into the domain model.
|
||||
|
||||
```ts type-equiv
|
||||
/** Model-visible skill metadata returned by `ctx.skills.list()` and rendered into request guidance. */
|
||||
interface SkillSummary {
|
||||
/** Kebab-case identifier used with the `skill` tool. */
|
||||
readonly name: string
|
||||
/** Short routing description shown to the model. */
|
||||
readonly description: string
|
||||
/** Optional extra routing guidance shown to the model. */
|
||||
readonly whenToUse?: string
|
||||
/** Whether the skill is hidden from model listings while remaining loadable by trusted callers. */
|
||||
/** Invocation controls shared by skill discovery consumers. */
|
||||
interface SkillInvocationPolicy {
|
||||
/** Whether model-facing catalogs and loaders exclude this skill. */
|
||||
readonly disableModelInvocation?: boolean
|
||||
/** Whether human-facing command catalogs and loaders include this skill. */
|
||||
readonly userInvocable?: boolean
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Invocation-neutral skill metadata returned by `ctx.skills.list()`. */
|
||||
interface SkillSummary {
|
||||
/** Kebab-case identifier used to address the skill. */
|
||||
readonly name: string
|
||||
/** Short routing description shown by discovery consumers. */
|
||||
readonly description: string
|
||||
/** Optional extra routing guidance. */
|
||||
readonly whenToUse?: string
|
||||
/** Optional model and user invocation controls. */
|
||||
readonly invocation?: SkillInvocationPolicy
|
||||
/** Discovery source that produced this winning skill. */
|
||||
readonly source: SkillSource
|
||||
/** Provider that owns this skill body. */
|
||||
@@ -84,6 +94,8 @@ interface SkillSummary {
|
||||
}
|
||||
```
|
||||
|
||||
`ctx.skills.list()` preserves all four policy combinations. `isModelInvocable(skill)` excludes only `disableModelInvocation: true`, while `isUserInvocable(skill)` excludes only `userInvocable: false`; missing fields permit both surfaces. A model-only skill sets `userInvocable: false`, a user-only skill sets `disableModelInvocation: true`, and setting both restrictive values keeps the skill available only through trusted `ctx.skills.get()` callers. The local provider reads these values from the exact kebab-case frontmatter keys `disable-model-invocation` and `user-invocable`.
|
||||
|
||||
`SkillCandidate` is the provider-to-registry shape. `locator` is opaque provider state; the registry only stores it and gives it back to the winning provider's `get()`.
|
||||
|
||||
```ts type-equiv
|
||||
@@ -157,4 +169,4 @@ interface Config {
|
||||
|
||||
`dsh-tool-skill` injects a durable user-role `<system-reminder>` at the first `agent/step` of a live session. The catalog contains sorted skill `name` and normalized, XML-escaped `description` only; it omits bodies, paths, sources, providers, and routing hints. Discovery forwards the step's abort signal through `SkillLookupOptions`. `catalogDescriptionMaxLength` is the consumer config for the description bound, with default `500` and integer minimum `3`.
|
||||
|
||||
The model-facing `skill({ name })` tool validates the kebab-case name, loads the complete definition for the calling agent cwd, reports an unresolved skill as unknown or no longer available, rejects `disableModelInvocation` skills, and returns a tool result containing `<skill_content name="...">`, `<skill_resources>`, and `<skill_instructions>`. `resourceBase` resolves explicitly referenced scripts, references, and assets only as needed; the loaded result does not enumerate a skill directory. The tool result is the model-visible path for complete instructions.
|
||||
The model-facing `skill({ name })` tool validates the kebab-case name, filters its catalog with `isModelInvocable`, loads the complete definition for the calling agent cwd, reports an unresolved skill as unknown or no longer available, rechecks model invocation policy before returning content, and returns a tool result containing `<skill_content name="...">`, `<skill_resources>`, and `<skill_instructions>`. `resourceBase` resolves explicitly referenced scripts, references, and assets only as needed; the loaded result does not enumerate a skill directory. The tool result is the model-visible path for complete instructions.
|
||||
@@ -62,19 +62,29 @@ type SkillSource = 'project-dsh' | 'project-agents' | 'runtime' | 'user-dsh' | '
|
||||
|
||||
## 摘要、候选项与完整定义
|
||||
|
||||
`SkillSummary` 是注册表中可供模型调用的摘要形状。消费方自行选择渲染哪些字段；会话目录仅使用 `name` 和 `description`，从不使用 body 或绝对文件路径。`disableModelInvocation` 将 skill 从模型列表中隐藏，但允许受信代码按名称加载。
|
||||
`SkillSummary` 是注册表中与调用策略无关的摘要形状。消费方自行选择渲染哪些条目和字段；模型会话目录仅使用模型可调用 skill 的 `name` 和 `description`，从不使用正文或绝对文件路径。`SkillInvocationPolicy` 使两个独立调用控制保持类型化，而不会把任意 frontmatter 纳入领域模型。
|
||||
|
||||
```ts type-equiv
|
||||
/** Model-visible skill metadata returned by `ctx.skills.list()` and rendered into request guidance. */
|
||||
interface SkillSummary {
|
||||
/** Kebab-case identifier used with the `skill` tool. */
|
||||
readonly name: string
|
||||
/** Short routing description shown to the model. */
|
||||
readonly description: string
|
||||
/** Optional extra routing guidance shown to the model. */
|
||||
readonly whenToUse?: string
|
||||
/** Whether the skill is hidden from model listings while remaining loadable by trusted callers. */
|
||||
/** Invocation controls shared by skill discovery consumers. */
|
||||
interface SkillInvocationPolicy {
|
||||
/** Whether model-facing catalogs and loaders exclude this skill. */
|
||||
readonly disableModelInvocation?: boolean
|
||||
/** Whether human-facing command catalogs and loaders include this skill. */
|
||||
readonly userInvocable?: boolean
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Invocation-neutral skill metadata returned by `ctx.skills.list()`. */
|
||||
interface SkillSummary {
|
||||
/** Kebab-case identifier used to address the skill. */
|
||||
readonly name: string
|
||||
/** Short routing description shown by discovery consumers. */
|
||||
readonly description: string
|
||||
/** Optional extra routing guidance. */
|
||||
readonly whenToUse?: string
|
||||
/** Optional model and user invocation controls. */
|
||||
readonly invocation?: SkillInvocationPolicy
|
||||
/** Discovery source that produced this winning skill. */
|
||||
readonly source: SkillSource
|
||||
/** Provider that owns this skill body. */
|
||||
@@ -84,6 +94,8 @@ interface SkillSummary {
|
||||
}
|
||||
```
|
||||
|
||||
`ctx.skills.list()` 保留全部四种策略组合。`isModelInvocable(skill)` 仅排除 `disableModelInvocation: true`，`isUserInvocable(skill)` 仅排除 `userInvocable: false`；字段缺失时两个接口均允许调用。仅供模型调用的 skill 设置 `userInvocable: false`，仅供用户调用的 skill 设置 `disableModelInvocation: true`，同时设置两个限制值后，该 skill 只能由受信的 `ctx.skills.get()` 调用方获取。本地提供方从名称完全匹配的 kebab-case frontmatter 键 `disable-model-invocation` 和 `user-invocable` 读取这些值。
|
||||
|
||||
`SkillCandidate` 是提供方到注册表的形状。`locator` 是提供方的不透明状态；注册表只存储它并在调用获胜提供方的 `get()` 时传回。
|
||||
|
||||
```ts type-equiv
|
||||
@@ -157,4 +169,4 @@ interface Config {
|
||||
|
||||
`dsh-tool-skill` 在存活会话的第一个 `agent/step` 注入一条持久的 user-role `<system-reminder>`。目录只包含已排序的 skill `name` 和规范化、经 XML 转义的 `description`；不包含正文、路径、来源、提供方或路由提示。发现通过 `SkillLookupOptions` 转发该步骤的 abort signal。`catalogDescriptionMaxLength` 是消费方用于 description 上限的配置，默认值为 `500`，整数最小值为 `3`。
|
||||
|
||||
面向模型的 `skill({ name })` 工具校验 kebab-case 名称，为调用方 agent 的 cwd 加载完整定义，将未解析的 skill 报告为 unknown 或 no longer available，拒绝 `disableModelInvocation` 的 skill，并返回包含 `<skill_content name="...">`、`<skill_resources>` 和 `<skill_instructions>` 的工具结果。`resourceBase` 仅按需解析显式引用的脚本、参考资料和资产；加载结果不枚举 skill 目录。工具结果是模型获取完整指令的可见路径。
|
||||
面向模型的 `skill({ name })` 工具校验 kebab-case 名称，使用 `isModelInvocable` 过滤目录，为调用方 agent 的 cwd 加载完整定义，将未解析的 skill 报告为 unknown 或 no longer available，在返回内容前重新检查模型调用策略，并返回包含 `<skill_content name="...">`、`<skill_resources>` 和 `<skill_instructions>` 的工具结果。`resourceBase` 仅按需解析显式引用的脚本、参考资料和资产；加载结果不枚举 skill 目录。工具结果是模型获取完整指令的可见路径。
|
||||
@@ -2,7 +2,7 @@
|
||||
{"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":2,"time":1783654655603,"data":{"title":"Load the snapshot-skill skill with","messageSeqs":[1],"source":{"kind":"fallback"}}}
|
||||
{"type":"user/message","seq":3,"time":1784903324926,"data":{"content":[{"type":"text","text":"<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"dsh-tool-skill"}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":3,"time":1784903324926,"data":{"content":[{"type":"text","text":"<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `model-only-skill`: Prove user-disabled skills remain available to the model.\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"dsh-tool-skill"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":4,"time":1784903324927,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":5,"time":1784903324928,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
---
|
||||
name: model-only-skill
|
||||
description: Prove user-disabled skills remain available to the model.
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
Follow these model-only snapshot instructions.
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
---
|
||||
name: user-only-skill
|
||||
description: Prove model-disabled skills stay outside the model catalog.
|
||||
disable-model-invocation: true
|
||||
---
|
||||
|
||||
Follow these user-only snapshot instructions.
|
||||
@@ -219,6 +219,8 @@ describe('tui-agent keyless smoke (real Loader tree in a PTY)', () => {
|
||||
'---',
|
||||
'name: scripted-skill',
|
||||
'description: Keyless PTY proof that the skill command loads a local skill into the conversation.',
|
||||
'disable-model-invocation: true',
|
||||
'user-invocable: true',
|
||||
'---',
|
||||
'',
|
||||
'SCRIPTED SKILL BODY MARKER',
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# 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
|
||||
README.md: 4838be893c1d5422cc707cb0d7542a056be41fa7
|
||||
README.zh.md: 368171a43ef3a449049542cd227459f82ec43086
|
||||
# pnpm run verify-translation-pairing --write packages/client/ui-skill/README.md
|
||||
README.md: 2cb382f53466c07b977eef4d5a1ef2804c13abea
|
||||
README.zh.md: d7cfd96b8de49be7875e37dba4f06cd4bf3aa407
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
English | [中文](README.zh.md)
|
||||
|
||||
Skill reference source, browser half: registers the `/`-trigger `skill` source into `ctx.slash`. Candidates come from the `skill.list` RPC addressed by the per-call `ClientSessionContext` projection's `{sessionId}` — every session is agent-backed and the host resolves `cwd` from the session header. Catalogs cache per session with a single-flight fetch; the scope-birth `warm` hook prewarms the session's entry and `connection/reset` clears everything. Results filter by `startsWith(query)`; picking a candidate lands the literal `/name ` text through the slash pipeline (decision 21 plain-text reference), and the source `codec` owns the reference's two projections: `clipboardText` → `/name`, `serialize` → the model form `<skill>name</skill>` invoked at submit time. The RPC rides the plugin's root-context connection captured at registration — the source never reads services off a per-call argument. The source implements no `matchSpace`/`matchEnter` hooks — skill references never enter command adjudication and ride ordinary prompts into the default sink.
|
||||
Skill reference source, browser half: registers the `/`-trigger `skill` source into `ctx.slash`. Candidates come from the `skill.list` RPC addressed by the per-call `ClientSessionContext` projection's `{sessionId}` — every session is agent-backed and the host resolves `cwd` from the session header. The host returns the intersection of model-invocable and user-invocable skills because this browser path lets a user insert a model reference rather than loading the body directly. Catalogs cache per session with a single-flight fetch; the scope-birth `warm` hook prewarms the session's entry and `connection/reset` clears everything. Results filter by `startsWith(query)`; picking a candidate lands the literal `/name ` text through the slash pipeline (decision 21 plain-text reference), and the source `codec` owns the reference's two projections: `clipboardText` → `/name`, `serialize` → the model form `<skill>name</skill>` invoked at submit time. The RPC rides the plugin's root-context connection captured at registration — the source never reads services off a per-call argument. The source implements no `matchSpace`/`matchEnter` hooks — skill references never enter command adjudication and ride ordinary prompts into the default sink.
|
||||
|
||||
A failed `skill.list` throws from `candidates`, which the slash shell logs and folds into a silent menu-group drop — the menu shows only pending/ready states.
|
||||
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
[English](README.md) | 中文
|
||||
|
||||
skill（技能）引用 source 的浏览器半侧：把 `/` 触发的 `skill` source 注册进 `ctx.slash`。候选来自 `skill.list` RPC，以每次调用的 `ClientSessionContext` 投影中的 `{sessionId}` 寻址——每个会话恒为 agent-backed，host 从会话 header 解析 `cwd`。目录按会话缓存，拉取走 single-flight；scope 出生的 `warm` 钩子预热该会话的缓存项，`connection/reset` 清空全部缓存。结果按 `startsWith(query)` 过滤；pick 一个候选会把字面文本 `/name ` 经 slash 管线落进草稿（决策 21 的纯文本引用），source 的 `codec` 拥有该引用的两种投影：`clipboardText` → `/name`，`serialize` → 提交时生成的模型形式 `<skill>name</skill>`。RPC 使用插件注册时捕获的根上下文连接——source 绝不从每次调用的参数上读取服务。source 不实现 `matchSpace`／`matchEnter` 钩子——skill 引用永不进入命令裁决，随普通提示词落入 default sink。
|
||||
skill（技能）引用 source 的浏览器半侧：把 `/` 触发的 `skill` source 注册进 `ctx.slash`。候选来自 `skill.list` RPC，以每次调用的 `ClientSessionContext` 投影中的 `{sessionId}` 寻址——每个会话恒为 agent-backed，host 从会话 header 解析 `cwd`。宿主返回模型可调用与用户可调用 skill 的交集，因为该浏览器路径让用户插入模型引用，而不是直接加载正文。目录按会话缓存，拉取走 single-flight；scope 出生的 `warm` 钩子预热该会话的缓存项，`connection/reset` 清空全部缓存。结果按 `startsWith(query)` 过滤；pick 一个候选会把字面文本 `/name ` 经 slash 管线落进草稿（决策 21 的纯文本引用），source 的 `codec` 拥有该引用的两种投影：`clipboardText` → `/name`，`serialize` → 提交时生成的模型形式 `<skill>name</skill>`。RPC 使用插件注册时捕获的根上下文连接——source 绝不从每次调用的参数上读取服务。source 不实现 `matchSpace`／`matchEnter` 钩子——skill 引用永不进入命令裁决，随普通提示词落入 default sink。
|
||||
|
||||
`skill.list` 失败时 `candidates` 抛出异常，slash 壳层记录日志并折叠为静默的菜单组丢弃——菜单只显示 pending／ready 状态。
|
||||
|
||||
|
||||
@@ -684,7 +684,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
|
||||
},
|
||||
{
|
||||
signature: 'async list(options: SkillLookupOptions = {}): Promise<SkillSummary[]>',
|
||||
jsDoc: '/**\n * List model-invocable skill summaries for a workspace. Lookup options and\n * provider candidates are readonly same-process values borrowed throughout\n * discovery.\n * @param options - lookup options; `cwd` selects project roots and `signal` cancels discovery.\n * @returns sorted summaries, excluding skills disabled for model invocation.\n */',
|
||||
jsDoc: '/**\n * List invocation-neutral skill summaries for a workspace. Consumers apply\n * model or user invocation policy at their operational boundary. Lookup\n * options and provider candidates are readonly same-process values borrowed\n * throughout discovery.\n * @param options - lookup options; `cwd` selects project roots and `signal` cancels discovery.\n * @returns all sorted winning summaries.\n */',
|
||||
},
|
||||
{
|
||||
signature: 'async get(name: string, options: SkillLookupOptions = {}): Promise<SkillDefinition | undefined>',
|
||||
@@ -2201,6 +2201,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [
|
||||
name: 'SkillDefinition',
|
||||
declaration: 'export interface SkillDefinition extends SkillSummary {\n readonly content: string;\n readonly path?: string;\n readonly metadata?: Readonly<Record<string, unknown>>;\n}',
|
||||
},
|
||||
{
|
||||
name: 'SkillInvocationPolicy',
|
||||
declaration: 'export interface SkillInvocationPolicy {\n readonly disableModelInvocation?: boolean;\n readonly userInvocable?: boolean;\n}',
|
||||
},
|
||||
{
|
||||
name: 'SkillLookupOptions',
|
||||
declaration: 'export interface SkillLookupOptions {\n readonly cwd?: string | undefined;\n readonly signal?: AbortSignal | undefined;\n}',
|
||||
@@ -2223,7 +2227,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [
|
||||
},
|
||||
{
|
||||
name: 'SkillSummary',
|
||||
declaration: 'export interface SkillSummary {\n readonly name: string;\n readonly description: string;\n readonly whenToUse?: string;\n readonly disableModelInvocation?: boolean;\n readonly source: SkillSource;\n readonly provider: string;\n readonly resourceBase?: SkillResourceBase;\n}',
|
||||
declaration: 'export interface SkillSummary {\n readonly name: string;\n readonly description: string;\n readonly whenToUse?: string;\n readonly invocation?: SkillInvocationPolicy;\n readonly source: SkillSource;\n readonly provider: string;\n readonly resourceBase?: SkillResourceBase;\n}',
|
||||
},
|
||||
{
|
||||
name: 'SpillLocator',
|
||||
|
||||
@@ -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/host/apiproxy/README.md
|
||||
README.md: d6db9a9541b0727b61dbe501f7234564ffef139e
|
||||
README.zh.md: 4175c8fdb98aad2882718a2c95cd9e45825d787d
|
||||
README.md: 20c6e73628db160811f016a7c6df526edb172def
|
||||
README.zh.md: 131ead31de3c54b558ab7c07eb8cc6974c0b1484
|
||||
@@ -20,7 +20,7 @@ Workspace and Session lists are separate reconnect baselines. `workspace.create`
|
||||
|
||||
`session.history` pages on message boundaries, and its tail page (no `beforeSeq`) carries two session-level extras the page window cannot supply: the in-flight partial's chunk events, and `todos` — the latest `todo/write` whole-list projection over the full log. Older pages omit `todos` because the projection is session-level, not per-page; a tail response that omits it means the whole log holds no `todo/write`, so clients read the absent field as the empty plan rather than as unchanged state.
|
||||
|
||||
The `command.*` and `skill.*` domains expose the host command registry and skill catalog to clients. Every method addresses one session's agent by `sessionId` (a served session always has an Agent; `command.*` resumes cold sessions through the same path as `session.*`, while `skill.list` resolves the project root from the session header without touching the Agent registry). `command.execute` runs a slash-command line host-side and returns a detached result; the carrier's request signal cancels the running handler. `host/commands-changed` is the catalog invalidation frame: clients refetch `command.list` instead of diffing.
|
||||
The `command.*` and `skill.*` domains expose the host command registry and skill catalog to clients. Every method addresses one session's agent by `sessionId` (a served session always has an Agent; `command.*` resumes cold sessions through the same path as `session.*`, while `skill.list` resolves the project root from the session header without touching the Agent registry). `skill.list` serves the browser's user-selected model-reference path, so it returns only skills that are both model-invocable and user-invocable; this domain has no direct skill-loading RPC. `command.execute` runs a slash-command line host-side and returns a detached result; the carrier's request signal cancels the running handler. `host/commands-changed` is the catalog invalidation frame: clients refetch `command.list` instead of diffing.
|
||||
|
||||
## Carrier layer (`/client` + root)
|
||||
|
||||
|
||||
@@ -20,7 +20,7 @@ Workspace 列表与 Session 列表是相互独立的重连基线。`workspace.cr
|
||||
|
||||
`session.history` 按消息边界分页，其尾页（不带 `beforeSeq`）额外携带两项页窗口本身无法提供的会话级数据：进行中局部消息的 chunk 事件，以及 `todos`——整份日志上最后一次 `todo/write` 的整表投影。较早的页面不带 `todos`，因为该投影是会话级而非分页级的；尾页响应缺少该字段意味着整份日志中没有任何 `todo/write`，因此客户端要把缺失字段读作空计划，而不是读作「状态未变」。
|
||||
|
||||
`command.*` 与 `skill.*` 领域向客户端暴露宿主命令注册表和技能目录。每个方法都通过 `sessionId` 寻址一个会话的 Agent（被服务的会话必有 Agent；`command.*` 经由与 `session.*` 相同的路径恢复冷会话，而 `skill.list` 从会话头解析项目根目录，不触碰 Agent 注册表）。`command.execute` 在宿主侧运行一条斜杠命令行并返回脱耦结果；载体的请求信号可取消正在运行的处理器。`host/commands-changed` 是目录失效帧：客户端重新拉取 `command.list` 而不是做差分。
|
||||
`command.*` 与 `skill.*` 领域向客户端暴露宿主命令注册表和技能目录。每个方法都通过 `sessionId` 寻址一个会话的 Agent（被服务的会话必有 Agent；`command.*` 经由与 `session.*` 相同的路径恢复冷会话，而 `skill.list` 从会话头解析项目根目录，不触碰 Agent 注册表）。`skill.list` 服务于浏览器中由用户选择的模型引用路径，因此仅返回模型和用户均可调用的 skill；该领域没有直接加载 skill 的 RPC。`command.execute` 在宿主侧运行一条斜杠命令行并返回脱耦结果；载体的请求信号可取消正在运行的处理器。`host/commands-changed` 是目录失效帧：客户端重新拉取 `command.list` 而不是做差分。
|
||||
|
||||
## 载体层（`/client` + 根路径）
|
||||
|
||||
|
||||
@@ -17,6 +17,7 @@ import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm'
|
||||
import type { JsonValue, Session, SessionEvent, SessionHeader, SessionId, TodoItem } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionPersistence } from '@deepseek-ai/dsh-session-persistence'
|
||||
import { foldSessionTitle } from '@deepseek-ai/dsh-session-title'
|
||||
import { isModelInvocable, isUserInvocable } from '@deepseek-ai/dsh-skill'
|
||||
import type { Workspace, WorkspaceRecord } from '@deepseek-ai/dsh-workspace'
|
||||
import {
|
||||
workspaceDomainState, workspaceRecord, WorkspaceId as brandWorkspaceId,
|
||||
@@ -29,9 +30,8 @@ import type {
|
||||
MuxFrame, QuestionResponsePayload, SessionSummary, ToolEventView,
|
||||
WorkspaceId, WorkspaceView,
|
||||
} from './api/index.ts'
|
||||
// Type-only edges: resolve `ctx.get('commands')`, the `commands/change` event, and `ctx.get('skills')`.
|
||||
// Type-only edge: resolve `ctx.get('commands')` and the `commands/change` event.
|
||||
import type {} from '@deepseek-ai/dsh-commands'
|
||||
import type {} from '@deepseek-ai/dsh-skill'
|
||||
import { questionResponsePayloadSchema } from './api/questions.schema.ts'
|
||||
import type { ClientResponse, RpcError, RpcReceipt, RpcRequest, RpcResponse } from './api/rpc.ts'
|
||||
import { RpcId } from './api/rpc.ts'
|
||||
@@ -1082,7 +1082,8 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
return err(request, { code: 'internal', message: 'skill registry is absent: this deployment does not mount @deepseek-ai/dsh-skill in its composition (cordis.yml or explicit assembly)', details: {} })
|
||||
}
|
||||
try {
|
||||
const skills = await skillRegistry.list({ cwd })
|
||||
const skills = (await skillRegistry.list({ cwd }))
|
||||
.filter(skill => isModelInvocable(skill) && isUserInvocable(skill))
|
||||
return ok(request, {
|
||||
skills: skills.map(skill => ({
|
||||
name: skill.name,
|
||||
|
||||
@@ -20,6 +20,6 @@ export interface SkillEntry {
|
||||
|
||||
/** Skill-domain unary methods (the map key skill.* of RpcMethodMap). */
|
||||
export interface SkillsApi {
|
||||
/** Lists model-invocable skills for the addressed session's project root. */
|
||||
/** Lists skills usable by the browser's user-selected model-reference path. */
|
||||
list(request: RpcRequest<{ sessionId: SessionId }>): Promise<RpcResponse<{ skills: readonly SkillEntry[] }>>
|
||||
}
|
||||
@@ -175,10 +175,27 @@ describe('skill.list', () => {
|
||||
name: 'probe',
|
||||
list: (options) => {
|
||||
seenCwds.push(options.cwd)
|
||||
return Promise.resolve([{
|
||||
name: 'commit-helper', description: 'Git commits', whenToUse: 'when committing',
|
||||
source: 'custom', provider: 'probe', rank: 0, locator: null,
|
||||
}])
|
||||
return Promise.resolve([
|
||||
{
|
||||
name: 'commit-helper', description: 'Git commits', whenToUse: 'when committing',
|
||||
source: 'custom', provider: 'probe', rank: 0, locator: null,
|
||||
},
|
||||
{
|
||||
name: 'user-only', description: 'User-only',
|
||||
invocation: { disableModelInvocation: true },
|
||||
source: 'custom', provider: 'probe', rank: 0, locator: null,
|
||||
},
|
||||
{
|
||||
name: 'model-only', description: 'Model-only',
|
||||
invocation: { userInvocable: false },
|
||||
source: 'custom', provider: 'probe', rank: 0, locator: null,
|
||||
},
|
||||
{
|
||||
name: 'trusted-only', description: 'Trusted-only',
|
||||
invocation: { disableModelInvocation: true, userInvocable: false },
|
||||
source: 'custom', provider: 'probe', rank: 0, locator: null,
|
||||
},
|
||||
])
|
||||
},
|
||||
get: () => Promise.resolve(undefined),
|
||||
})
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# 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
|
||||
README.md: c488fdc4b1d97b5aa1113e41a470484063526ded
|
||||
README.zh.md: 796c814a3c4064d545a966465caf6f99e9dd8601
|
||||
# pnpm run verify-translation-pairing --write packages/skill/skill-local/README.md
|
||||
README.md: 56e19088e075f0ce9ad76eebdd23054e538174e4
|
||||
README.zh.md: 38caf2716240700aab4220783068651c9dd851f7
|
||||
@@ -36,7 +36,9 @@ When `ctx.fs` is available, discovery lists roots through `ctx.fs.listDir`, read
|
||||
|
||||
## Skill Format
|
||||
|
||||
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 YAML with the `yaml` package; it requires `name` and `description`, while `whenToUse`, `disableModelInvocation`, and `metadata` are optional. Names must be kebab-case.
|
||||
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. Omitted fields preserve both forms of invocation. The camel-case spellings `disableModelInvocation` and `userInvocable` are rejected with a warning instead of acting as compatibility aliases.
|
||||
|
||||
## Model Experience
|
||||
|
||||
|
||||
@@ -36,7 +36,9 @@
|
||||
|
||||
## Skill 格式
|
||||
|
||||
Skill 可以是单层目录 bundle（`<name>/SKILL.md`），也可以是平铺 Markdown 文件（`<name>.md`）。v1 刻意不包含嵌套 `**/SKILL.md` 发现。Frontmatter 使用 `yaml` 包解析为 YAML；它要求 `name` 和 `description`，而 `whenToUse`、`disableModelInvocation` 和 `metadata` 可选。名称必须使用 kebab-case。
|
||||
Skill 可以是单层目录 bundle（`<name>/SKILL.md`），也可以是平铺 Markdown 文件（`<name>.md`）。v1 刻意不包含嵌套 `**/SKILL.md` 发现。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加载器中排除该 skill；`user-invocable: false` 会从面向用户的命令中排除该 skill。省略字段时保留两种调用方式。系统会拒绝驼峰形式的 `disableModelInvocation` 和 `userInvocable` 并记录警告，而不会将其作为兼容别名。
|
||||
|
||||
## 模型体验
|
||||
|
||||
|
||||
@@ -22,6 +22,7 @@ import {
|
||||
isSkillName,
|
||||
type SkillCandidate,
|
||||
type SkillDefinition,
|
||||
type SkillInvocationPolicy,
|
||||
type SkillLookupOptions,
|
||||
type SkillProvider,
|
||||
type SkillSource,
|
||||
@@ -74,7 +75,7 @@ interface ParsedSkill {
|
||||
name: string
|
||||
description: string
|
||||
whenToUse?: string
|
||||
disableModelInvocation?: boolean
|
||||
invocation?: SkillInvocationPolicy
|
||||
metadata?: Record<string, unknown>
|
||||
content: string
|
||||
}
|
||||
@@ -136,7 +137,7 @@ export class LocalSkillProvider implements SkillProvider {
|
||||
name: parsed.name,
|
||||
description: parsed.description,
|
||||
...parsed.whenToUse !== undefined ? { whenToUse: parsed.whenToUse } : {},
|
||||
...parsed.disableModelInvocation !== undefined ? { disableModelInvocation: parsed.disableModelInvocation } : {},
|
||||
...parsed.invocation !== undefined ? { invocation: parsed.invocation } : {},
|
||||
source: candidate.source,
|
||||
provider: this.name,
|
||||
resourceBase: { kind: 'directory', path: locator.directory },
|
||||
@@ -184,7 +185,7 @@ async function discoverRoot(root: SkillRoot, ctx: Context): Promise<SkillCandida
|
||||
name: parsed.name,
|
||||
description: parsed.description,
|
||||
...parsed.whenToUse !== undefined ? { whenToUse: parsed.whenToUse } : {},
|
||||
...parsed.disableModelInvocation !== undefined ? { disableModelInvocation: parsed.disableModelInvocation } : {},
|
||||
...parsed.invocation !== undefined ? { invocation: parsed.invocation } : {},
|
||||
provider: 'local',
|
||||
source: root.source,
|
||||
rank: root.rank,
|
||||
@@ -263,11 +264,18 @@ async function parseSkillFile(path: string, ctx: Context, signal?: AbortSignal,
|
||||
ctx.logger.warn(`skill file ${path} ignored: invalid skill name "${name}"`)
|
||||
return undefined
|
||||
}
|
||||
let invocation
|
||||
try {
|
||||
invocation = parseInvocationPolicy(parsed.data)
|
||||
} catch (error) {
|
||||
ctx.logger.warn(`skill file ${path} ignored: invalid invocation frontmatter: ${errorMessage(error)}`)
|
||||
return undefined
|
||||
}
|
||||
return {
|
||||
name,
|
||||
description,
|
||||
...optionalString(parsed.data, 'whenToUse'),
|
||||
...optionalBoolean(parsed.data, 'disableModelInvocation'),
|
||||
...invocation === undefined ? {} : { invocation },
|
||||
...optionalMetadata(parsed.data),
|
||||
content: parsed.body.trim(),
|
||||
}
|
||||
@@ -420,9 +428,43 @@ function optionalString(data: Record<string, unknown>, key: string): { [K in typ
|
||||
return typeof value === 'string' && value.length > 0 ? { [key]: value } : {}
|
||||
}
|
||||
|
||||
function optionalBoolean(data: Record<string, unknown>, key: string): { [K in typeof key]?: boolean } {
|
||||
function parseInvocationPolicy(data: Record<string, unknown>): SkillInvocationPolicy | undefined {
|
||||
rejectLegacyInvocationKey(data, 'disableModelInvocation', 'disable-model-invocation')
|
||||
rejectLegacyInvocationKey(data, 'userInvocable', 'user-invocable')
|
||||
const disableModelInvocation = frontmatterBoolean(data, 'disable-model-invocation')
|
||||
const userInvocable = frontmatterBoolean(data, 'user-invocable')
|
||||
if (disableModelInvocation === undefined && userInvocable === undefined) return undefined
|
||||
return {
|
||||
...disableModelInvocation === undefined ? {} : { disableModelInvocation },
|
||||
...userInvocable === undefined ? {} : { userInvocable },
|
||||
}
|
||||
}
|
||||
|
||||
function rejectLegacyInvocationKey(data: Record<string, unknown>, legacy: string, canonical: string): void {
|
||||
if (Object.hasOwn(data, legacy)) {
|
||||
throw new Error(`frontmatter field "${legacy}" is unsupported; use "${canonical}"`)
|
||||
}
|
||||
}
|
||||
|
||||
function frontmatterBoolean(data: Record<string, unknown>, key: string): boolean | undefined {
|
||||
if (!Object.hasOwn(data, key)) return undefined
|
||||
const value = data[key]
|
||||
return typeof value === 'boolean' ? { [key]: value } : {}
|
||||
if (typeof value === 'boolean') return value
|
||||
if (value === 1 || value === '1') return true
|
||||
if (value === 0 || value === '0') return false
|
||||
if (typeof value === 'string') {
|
||||
switch (value.toLowerCase()) {
|
||||
case 'true':
|
||||
case 'yes':
|
||||
case 'on':
|
||||
return true
|
||||
case 'false':
|
||||
case 'no':
|
||||
case 'off':
|
||||
return false
|
||||
}
|
||||
}
|
||||
throw new TypeError(`frontmatter field "${key}" must be a boolean`)
|
||||
}
|
||||
|
||||
function optionalMetadata(data: Record<string, unknown>): { metadata?: Record<string, unknown> } {
|
||||
|
||||
@@ -200,7 +200,7 @@ describe('LocalSkillProvider', () => {
|
||||
expect((await ctx.skills.get('runtime-name', { cwd: project }))?.description).toBe('Runtime wins')
|
||||
})
|
||||
|
||||
it('parses flat skills and filters invalid or model-disabled skills from listing', async () => {
|
||||
it('parses flat skills and filters invalid skills from the invocation-neutral listing', async () => {
|
||||
const home = await tempDir('skill-flat')
|
||||
const root = join(home, '.dsh/skills')
|
||||
await writeFlatSkill(root, 'flat-skill', 'flat description', 'Flat instructions.')
|
||||
@@ -209,7 +209,8 @@ describe('LocalSkillProvider', () => {
|
||||
'name: rich-skill',
|
||||
'description: rich description',
|
||||
'whenToUse: For richer local parsing',
|
||||
'disableModelInvocation: false',
|
||||
'disable-model-invocation: off',
|
||||
'user-invocable: YES',
|
||||
'metadata:',
|
||||
' owner: tests',
|
||||
'---',
|
||||
@@ -225,8 +226,10 @@ describe('LocalSkillProvider', () => {
|
||||
await writeFile(join(root, 'no-trailing-body.md'), '---\nname: no-trailing-body\ndescription: No trailing body\n---')
|
||||
await writeFile(join(root, 'notes.txt'), 'ignored')
|
||||
await mkdir(join(root, 'not-a-skill'), { recursive: true })
|
||||
await writeSkill(root, 'hidden-skill', 'hidden description', 'Hidden.')
|
||||
await writeFile(join(root, 'hidden-skill/SKILL.md'), '---\nname: hidden-skill\ndescription: hidden description\ndisableModelInvocation: true\n---\n\nHidden.\n')
|
||||
await writeSkill(root, 'user-only-skill', 'user-only description', 'User-only.')
|
||||
await writeFile(join(root, 'user-only-skill/SKILL.md'), '---\nname: user-only-skill\ndescription: user-only description\ndisable-model-invocation: true\n---\n\nUser-only.\n')
|
||||
await writeSkill(root, 'model-only-skill', 'model-only description', 'Model-only.')
|
||||
await writeFile(join(root, 'model-only-skill/SKILL.md'), '---\nname: model-only-skill\ndescription: model-only description\nuser-invocable: false\n---\n\nModel-only.\n')
|
||||
|
||||
const ctx = await setupLocal(home)
|
||||
const listedBeforeDelete = await ctx.skills.list()
|
||||
@@ -234,17 +237,88 @@ describe('LocalSkillProvider', () => {
|
||||
if (flatSummary === undefined) throw new Error('expected flat-skill')
|
||||
await writeFile(join(root, 'flat-skill.md'), '')
|
||||
|
||||
expect(listedBeforeDelete.map(skill => skill.name)).toEqual(['flat-skill', 'no-trailing-body', 'rich-skill'])
|
||||
expect(listedBeforeDelete.map(skill => skill.name)).toEqual([
|
||||
'flat-skill',
|
||||
'model-only-skill',
|
||||
'no-trailing-body',
|
||||
'rich-skill',
|
||||
'user-only-skill',
|
||||
])
|
||||
expect(await ctx.skills.get('flat-skill')).toBeUndefined()
|
||||
expect((await ctx.skills.get('hidden-skill'))?.content).toContain('Hidden.')
|
||||
expect(await ctx.skills.get('user-only-skill')).toMatchObject({
|
||||
invocation: { disableModelInvocation: true },
|
||||
content: 'User-only.',
|
||||
})
|
||||
expect(await ctx.skills.get('model-only-skill')).toMatchObject({
|
||||
invocation: { userInvocable: false },
|
||||
content: 'Model-only.',
|
||||
})
|
||||
expect(await ctx.skills.get('rich-skill')).toMatchObject({
|
||||
whenToUse: 'For richer local parsing',
|
||||
disableModelInvocation: false,
|
||||
invocation: { disableModelInvocation: false, userInvocable: true },
|
||||
metadata: { owner: 'tests' },
|
||||
})
|
||||
expect(await ctx.skills.get('Bad_Name')).toBeUndefined()
|
||||
})
|
||||
|
||||
it('accepts the documented boolean spellings for invocation frontmatter', async () => {
|
||||
const home = await tempDir('skill-invocation-booleans')
|
||||
const root = join(home, '.dsh/skills')
|
||||
await mkdir(root, { recursive: true })
|
||||
const truthy = ['true', 'TRUE', 'yes', 'ON', '1', '"1"']
|
||||
const falsy = ['false', 'FALSE', 'no', 'OFF', '0', '"0"']
|
||||
for (const [index, value] of truthy.entries()) {
|
||||
await writeFile(join(root, `truthy-${index}.md`), [
|
||||
'---',
|
||||
`name: truthy-${index}`,
|
||||
`description: Truthy ${index}`,
|
||||
`disable-model-invocation: ${value}`,
|
||||
'---',
|
||||
'',
|
||||
'Truthy.',
|
||||
].join('\n'))
|
||||
}
|
||||
for (const [index, value] of falsy.entries()) {
|
||||
await writeFile(join(root, `falsy-${index}.md`), [
|
||||
'---',
|
||||
`name: falsy-${index}`,
|
||||
`description: Falsy ${index}`,
|
||||
`user-invocable: ${value}`,
|
||||
'---',
|
||||
'',
|
||||
'Falsy.',
|
||||
].join('\n'))
|
||||
}
|
||||
|
||||
const ctx = await setupLocal(home)
|
||||
|
||||
for (const [index] of truthy.entries()) {
|
||||
expect((await ctx.skills.get(`truthy-${index}`))?.invocation).toEqual({ disableModelInvocation: true })
|
||||
}
|
||||
for (const [index] of falsy.entries()) {
|
||||
expect((await ctx.skills.get(`falsy-${index}`))?.invocation).toEqual({ userInvocable: false })
|
||||
}
|
||||
})
|
||||
|
||||
it('rejects legacy and invalid invocation frontmatter without hiding valid siblings', async () => {
|
||||
const home = await tempDir('skill-invalid-invocation')
|
||||
const root = join(home, '.dsh/skills')
|
||||
await writeSkill(root, 'good-skill', 'Good skill')
|
||||
const invalid = [
|
||||
['legacy-model', 'disableModelInvocation: true'],
|
||||
['legacy-user', 'userInvocable: false'],
|
||||
['bad-string', 'disable-model-invocation: maybe'],
|
||||
['bad-value', 'user-invocable: null'],
|
||||
] as const
|
||||
for (const [name, field] of invalid) {
|
||||
await writeFile(join(root, `${name}.md`), `---\nname: ${name}\ndescription: ${name}\n${field}\n---\n\nBad.\n`)
|
||||
}
|
||||
|
||||
const ctx = await setupLocal(home)
|
||||
|
||||
expect((await ctx.skills.list()).map(skill => skill.name)).toEqual(['good-skill'])
|
||||
})
|
||||
|
||||
it('supports CRLF frontmatter and ignores delimiter-looking text inside YAML values', async () => {
|
||||
const home = await tempDir('skill-frontmatter-crlf')
|
||||
const root = join(home, '.dsh/skills')
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# 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
|
||||
README.md: 639616d0b75f960e9ccd48546d44db841372bbe2
|
||||
README.zh.md: 3afdd415397927ebf107d6f862422c711a51888b
|
||||
# pnpm run verify-translation-pairing --write packages/skill/skill/README.md
|
||||
README.md: 30e48b57cd33c50013f857c61e63cba74fd2cd62
|
||||
README.zh.md: 08b4a97a921565b5d69960e6f69d6ee6dd194986
|
||||
@@ -11,8 +11,8 @@ This package owns the `ctx.skills` interface. It does not know whether skills co
|
||||
### Public API
|
||||
|
||||
- `ctx.skills.registerProvider(provider): () => void` Registers a readonly provider by unique `provider.name`. Duplicate provider names throw, and `runtime` is reserved for `ctx.skills.register(...)`. The registry borrows the provider object and invokes its methods directly. The registration is effect-scoped and HMR-safe, and the exact Cordis disposer supports ordered composite teardown.
|
||||
- `ctx.skills.list({ cwd?, signal? })` Borrows the readonly lookup options, then returns model-invocable summaries for the current workspace, merged across providers and sorted by name.
|
||||
- `ctx.skills.get(name, { cwd?, signal? })` Uses the same readonly options and winning candidate for discovery and loading, rechecks cancellation after discovery or a cache hit, races provider loading against the signal, validates the loaded definition, then returns it, including disabled-for-model skills.
|
||||
- `ctx.skills.list({ cwd?, signal? })` Borrows the readonly lookup options, then returns every winning summary for the current workspace, merged across providers and sorted by name. The result is invocation-neutral; consumers apply `isModelInvocable(skill)` or `isUserInvocable(skill)` at their own boundary.
|
||||
- `ctx.skills.get(name, { cwd?, signal? })` Uses the same readonly options and winning candidate for discovery and loading, rechecks cancellation after discovery or a cache hit, races provider loading against the signal, validates the loaded definition, then returns it regardless of invocation policy.
|
||||
- `ctx.skills.register(skill): () => void` Registers a readonly runtime embedded skill, adding `provider: "runtime"` when omitted. Same-name runtime registrations are first-wins: a duplicate logs a warning and gets a no-op disposer. Successful registrations return the exact Cordis disposer for ordered composite teardown.
|
||||
|
||||
### Config
|
||||
@@ -21,6 +21,19 @@ This package owns the `ctx.skills` interface. It does not know whether skills co
|
||||
|---|---|---|
|
||||
| `collectCacheMaxEntries` | `128` | Maximum completed cwd/provider catalogs kept in memory. |
|
||||
|
||||
### Invocation policy
|
||||
|
||||
`SkillSummary.invocation` is a typed policy object with optional `disableModelInvocation` and `userInvocable` booleans. Missing values preserve the default model-and-user behavior. The registry keeps all four combinations so one discovery result can serve model-facing tools, human-facing commands, and trusted internal callers without conflating their catalogs.
|
||||
|
||||
| Policy | Model | User |
|
||||
|---|---|---|
|
||||
| neither field, or `false` / `true` | included | included |
|
||||
| `userInvocable: false` | included | excluded |
|
||||
| `disableModelInvocation: true` | excluded | included |
|
||||
| both restrictive values | excluded | excluded |
|
||||
|
||||
`isModelInvocable(skill)` returns false only for `disableModelInvocation: true`; `isUserInvocable(skill)` returns false only for `userInvocable: false`. `ctx.skills.get()` remains the trusted, policy-neutral loading primitive, so every user- or model-facing consumer must enforce the predicate that matches its surface before exposing or loading a skill.
|
||||
|
||||
## Provider Contract
|
||||
|
||||
A provider registers synchronously and performs remote setup, authentication, and discovery in its awaited `list(options)` call. Provider objects, lookup options, candidates, and definitions are borrowed readonly rather than cloned or rebound. Providers should honor `options.signal`; the registry also stops awaiting uncooperative discovery or loading after cancellation.
|
||||
|
||||
@@ -11,8 +11,8 @@
|
||||
### 公开 API
|
||||
|
||||
- `ctx.skills.registerProvider(provider): () => void` 使用唯一 `provider.name` 注册只读提供方。重复提供方名称会抛错，`runtime` 保留给 `ctx.skills.register(...)`。注册表借用提供方对象，并直接调用其方法。注册作用域绑定到 effect，可安全用于 HMR；精确的 Cordis disposer 支持有序组合拆卸。
|
||||
- `ctx.skills.list({ cwd?, signal? })` 借用只读查找选项，然后返回当前工作区中模型可调用的摘要；这些摘要跨提供方合并，并按名称排序。
|
||||
- `ctx.skills.get(name, { cwd?, signal? })` 在发现和加载中使用同一组只读选项和胜出候选项；在发现或缓存命中后重新检查取消，让提供方加载与信号竞速，验证已加载定义，然后将其返回，包括已对模型禁用的 skill。
|
||||
- `ctx.skills.list({ cwd?, signal? })` 借用只读查找选项，然后返回当前工作区中的全部胜出摘要；这些摘要跨提供方合并，并按名称排序。结果与调用策略无关；消费方在自身边界调用 `isModelInvocable(skill)` 或 `isUserInvocable(skill)`。
|
||||
- `ctx.skills.get(name, { cwd?, signal? })` 在发现和加载中使用同一组只读选项和胜出候选项；在发现或缓存命中后重新检查取消，让提供方加载与信号竞速，验证已加载定义，然后无论调用策略如何都将其返回。
|
||||
- `ctx.skills.register(skill): () => void` 注册只读运行时嵌入式 skill，省略时添加 `provider: "runtime"`。同名运行时注册使用先到先得：重复项会记录警告，并获得无操作 disposer。成功注册会返回精确的 Cordis disposer，以供有序组合拆卸。
|
||||
|
||||
### 配置
|
||||
@@ -21,6 +21,19 @@
|
||||
|---|---|---|
|
||||
| `collectCacheMaxEntries` | `128` | 内存中保留的最大已完成 cwd/提供方目录数。 |
|
||||
|
||||
### 调用策略
|
||||
|
||||
`SkillSummary.invocation` 是类型化策略对象，其中包含可选的布尔字段 `disableModelInvocation` 和 `userInvocable`。字段缺失时保留模型和用户均可调用的默认行为。注册表保留全部四种组合，使一次发现结果可以同时服务面向模型的工具、面向用户的命令和受信内部调用方，而不会混淆各自的目录。
|
||||
|
||||
| 策略 | 模型 | 用户 |
|
||||
|---|---|---|
|
||||
| 两个字段均未设置，或分别为 `false` / `true` | 包含 | 包含 |
|
||||
| `userInvocable: false` | 包含 | 排除 |
|
||||
| `disableModelInvocation: true` | 排除 | 包含 |
|
||||
| 两个限制值均已设置 | 排除 | 排除 |
|
||||
|
||||
`isModelInvocable(skill)` 仅在 `disableModelInvocation: true` 时返回 false；`isUserInvocable(skill)` 仅在 `userInvocable: false` 时返回 false。`ctx.skills.get()` 仍是受信且与策略无关的加载原语，因此每个面向用户或模型的消费方都必须先执行与自身接口匹配的判定，再暴露或加载 skill。
|
||||
|
||||
## 提供方契约
|
||||
|
||||
提供方同步注册，并在已等待的 `list(options)` 调用中执行远程设置、身份验证和发现。提供方对象、查找选项、候选项和定义都以只读方式借用，而不是克隆或重新绑定。提供方应遵守 `options.signal`；取消后，注册表也会停止等待不协作的发现或加载。
|
||||
|
||||
@@ -36,16 +36,24 @@ export type SkillResourceBase =
|
||||
| { readonly kind: 'url'; readonly url: string }
|
||||
| { readonly kind: 'opaque'; readonly description: string }
|
||||
|
||||
/** Model-visible skill metadata returned by `ctx.skills.list()` and rendered into request guidance. */
|
||||
export interface SkillSummary {
|
||||
/** Kebab-case identifier used with the `skill` tool. */
|
||||
readonly name: string
|
||||
/** Short routing description shown to the model. */
|
||||
readonly description: string
|
||||
/** Optional extra routing guidance shown to the model. */
|
||||
readonly whenToUse?: string
|
||||
/** Whether the skill is hidden from model listings while remaining loadable by trusted callers. */
|
||||
/** Invocation controls shared by skill discovery consumers. */
|
||||
export interface SkillInvocationPolicy {
|
||||
/** Whether model-facing catalogs and loaders exclude this skill. */
|
||||
readonly disableModelInvocation?: boolean
|
||||
/** Whether human-facing command catalogs and loaders include this skill. */
|
||||
readonly userInvocable?: boolean
|
||||
}
|
||||
|
||||
/** Invocation-neutral skill metadata returned by `ctx.skills.list()`. */
|
||||
export interface SkillSummary {
|
||||
/** Kebab-case identifier used to address the skill. */
|
||||
readonly name: string
|
||||
/** Short routing description shown by discovery consumers. */
|
||||
readonly description: string
|
||||
/** Optional extra routing guidance. */
|
||||
readonly whenToUse?: string
|
||||
/** Optional model and user invocation controls. */
|
||||
readonly invocation?: SkillInvocationPolicy
|
||||
/** Discovery source that produced this winning skill. */
|
||||
readonly source: SkillSource
|
||||
/** Provider that owns this skill body. */
|
||||
@@ -87,6 +95,24 @@ export interface SkillLookupOptions {
|
||||
readonly signal?: AbortSignal | undefined
|
||||
}
|
||||
|
||||
/**
|
||||
* Return whether a skill may be advertised to and loaded by a model.
|
||||
* @param skill - skill metadata carrying optional invocation controls.
|
||||
* @returns `false` only when model invocation is explicitly disabled.
|
||||
*/
|
||||
export function isModelInvocable(skill: Pick<SkillSummary, 'invocation'>): boolean {
|
||||
return skill.invocation?.disableModelInvocation !== true
|
||||
}
|
||||
|
||||
/**
|
||||
* Return whether a skill may be advertised to and loaded by a human-facing command.
|
||||
* @param skill - skill metadata carrying optional invocation controls.
|
||||
* @returns `false` only when user invocation is explicitly disabled.
|
||||
*/
|
||||
export function isUserInvocable(skill: Pick<SkillSummary, 'invocation'>): boolean {
|
||||
return skill.invocation?.userInvocable !== false
|
||||
}
|
||||
|
||||
/** Provider interface for one source of skills, such as local directories or a remote registry. */
|
||||
export interface SkillProvider {
|
||||
/** Unique provider name in the `ctx.skills` registry. */
|
||||
@@ -221,16 +247,16 @@ export class SkillService extends Service {
|
||||
}
|
||||
|
||||
/**
|
||||
* List model-invocable skill summaries for a workspace. Lookup options and
|
||||
* provider candidates are readonly same-process values borrowed throughout
|
||||
* discovery.
|
||||
* List invocation-neutral skill summaries for a workspace. Consumers apply
|
||||
* model or user invocation policy at their operational boundary. Lookup
|
||||
* options and provider candidates are readonly same-process values borrowed
|
||||
* throughout discovery.
|
||||
* @param options - lookup options; `cwd` selects project roots and `signal` cancels discovery.
|
||||
* @returns sorted summaries, excluding skills disabled for model invocation.
|
||||
* @returns all sorted winning summaries.
|
||||
*/
|
||||
async list(options: SkillLookupOptions = {}): Promise<SkillSummary[]> {
|
||||
return (await this.collect(options))
|
||||
.map(entry => entry.candidate)
|
||||
.filter(skill => skill.disableModelInvocation !== true)
|
||||
.map(toSummary)
|
||||
.sort(compareSkillSummary)
|
||||
}
|
||||
@@ -359,7 +385,7 @@ function runtimeCandidate(skill: SkillRegistration): SkillCandidate {
|
||||
name: skill.name,
|
||||
description: skill.description,
|
||||
...skill.whenToUse !== undefined ? { whenToUse: skill.whenToUse } : {},
|
||||
...skill.disableModelInvocation !== undefined ? { disableModelInvocation: skill.disableModelInvocation } : {},
|
||||
...skill.invocation !== undefined ? { invocation: skill.invocation } : {},
|
||||
source: skill.source,
|
||||
provider: skill.provider ?? RUNTIME_PROVIDER,
|
||||
...skill.resourceBase !== undefined ? { resourceBase: skill.resourceBase } : {},
|
||||
@@ -383,9 +409,7 @@ function validateCandidate(candidate: SkillCandidate, providerName: string): voi
|
||||
if (candidate.description.length === 0) {
|
||||
throw new Error(`skill provider "${providerName}" returned skill "${candidate.name}" without a description`)
|
||||
}
|
||||
if (candidate.disableModelInvocation !== undefined && typeof candidate.disableModelInvocation !== 'boolean') {
|
||||
throw new TypeError(`skill provider "${providerName}" returned skill "${candidate.name}" with a non-boolean disableModelInvocation`)
|
||||
}
|
||||
validateInvocation(candidate.invocation, `skill provider "${providerName}" returned skill "${candidate.name}"`)
|
||||
if (candidate.whenToUse !== undefined && typeof candidate.whenToUse !== 'string') {
|
||||
throw new TypeError(`skill provider "${providerName}" returned skill "${candidate.name}" with a non-string whenToUse`)
|
||||
}
|
||||
@@ -409,6 +433,7 @@ function validateCandidate(candidate: SkillCandidate, providerName: string): voi
|
||||
function validateRuntimeSkill(skill: SkillRegistration): void {
|
||||
if (!SKILL_NAME.test(skill.name)) throw new Error(`invalid skill name "${skill.name}"`)
|
||||
if (skill.description.length === 0) throw new Error(`skill "${skill.name}" requires a description`)
|
||||
validateInvocation(skill.invocation, `runtime skill "${skill.name}"`)
|
||||
}
|
||||
|
||||
/** Validate a definition loaded from a provider-controlled parser or remote source. */
|
||||
@@ -416,7 +441,7 @@ function validateDefinition(skill: SkillDefinition): void {
|
||||
const name = skill.name
|
||||
const description = skill.description
|
||||
const whenToUse = skill.whenToUse
|
||||
const disableModelInvocation = skill.disableModelInvocation
|
||||
const invocation = skill.invocation
|
||||
const source = skill.source
|
||||
const provider = skill.provider
|
||||
const content = skill.content
|
||||
@@ -425,9 +450,7 @@ function validateDefinition(skill: SkillDefinition): void {
|
||||
if (!SKILL_NAME.test(name)) throw new Error(`loaded skill has invalid name "${name}"`)
|
||||
if (typeof description !== 'string') throw new TypeError(`loaded skill "${name}" description must be a string`)
|
||||
if (description.length === 0) throw new Error(`loaded skill "${name}" requires a description`)
|
||||
if (disableModelInvocation !== undefined && typeof disableModelInvocation !== 'boolean') {
|
||||
throw new TypeError(`loaded skill "${name}" disableModelInvocation must be a boolean`)
|
||||
}
|
||||
validateInvocation(invocation, `loaded skill "${name}"`)
|
||||
if (whenToUse !== undefined && typeof whenToUse !== 'string') throw new TypeError(`loaded skill "${name}" whenToUse must be a string`)
|
||||
if (typeof source !== 'string') throw new TypeError(`loaded skill "${name}" source must be a string`)
|
||||
if (typeof provider !== 'string') throw new TypeError(`loaded skill "${name}" provider must be a string`)
|
||||
@@ -436,18 +459,32 @@ function validateDefinition(skill: SkillDefinition): void {
|
||||
}
|
||||
|
||||
function toSummary(skill: SkillDefinition | SkillCandidate): SkillSummary {
|
||||
const { name, description, whenToUse, disableModelInvocation, source, provider, resourceBase } = skill
|
||||
const { name, description, whenToUse, invocation, source, provider, resourceBase } = skill
|
||||
return {
|
||||
name,
|
||||
description,
|
||||
...whenToUse !== undefined ? { whenToUse } : {},
|
||||
...disableModelInvocation !== undefined ? { disableModelInvocation } : {},
|
||||
...invocation !== undefined ? { invocation } : {},
|
||||
source,
|
||||
provider,
|
||||
...resourceBase !== undefined ? { resourceBase } : {},
|
||||
}
|
||||
}
|
||||
|
||||
function validateInvocation(invocation: unknown, subject: string): void {
|
||||
if (invocation === undefined) return
|
||||
if (typeof invocation !== 'object' || invocation === null || Array.isArray(invocation)) {
|
||||
throw new TypeError(`${subject} with a non-object invocation policy`)
|
||||
}
|
||||
const policy = invocation as Record<string, unknown>
|
||||
if (policy.disableModelInvocation !== undefined && typeof policy.disableModelInvocation !== 'boolean') {
|
||||
throw new TypeError(`${subject} with a non-boolean invocation.disableModelInvocation`)
|
||||
}
|
||||
if (policy.userInvocable !== undefined && typeof policy.userInvocable !== 'boolean') {
|
||||
throw new TypeError(`${subject} with a non-boolean invocation.userInvocable`)
|
||||
}
|
||||
}
|
||||
|
||||
function compareSkillSummary(left: SkillSummary, right: SkillSummary): number {
|
||||
return compareCodePoints(left.name, right.name)
|
||||
}
|
||||
|
||||
@@ -1,6 +1,13 @@
|
||||
import { describe, expect, it, vi } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import SkillService, { type SkillCandidate, type SkillDefinition, type SkillLookupOptions, type SkillProvider } from '@deepseek-ai/dsh-skill'
|
||||
import SkillService, {
|
||||
isModelInvocable,
|
||||
isUserInvocable,
|
||||
type SkillCandidate,
|
||||
type SkillDefinition,
|
||||
type SkillLookupOptions,
|
||||
type SkillProvider,
|
||||
} from '@deepseek-ai/dsh-skill'
|
||||
|
||||
function memorySkill(name: string, description: string, rank: number, body = `${name} body.`): SkillCandidate {
|
||||
return {
|
||||
@@ -107,6 +114,32 @@ describe('SkillService registry', () => {
|
||||
expect((await ctx.skills.list()).map(skill => skill.name)).toEqual(['same-rank-skill', 'shadowed'])
|
||||
})
|
||||
|
||||
it('returns an invocation-neutral catalog and resolves model and user policy independently', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SkillService)
|
||||
const registrations = [
|
||||
{ name: 'both', invocation: undefined },
|
||||
{ name: 'model-only', invocation: { userInvocable: false } },
|
||||
{ name: 'user-only', invocation: { disableModelInvocation: true } },
|
||||
{ name: 'trusted-only', invocation: { disableModelInvocation: true, userInvocable: false } },
|
||||
] as const
|
||||
for (const registration of registrations) {
|
||||
ctx.skills.register({
|
||||
name: registration.name,
|
||||
description: registration.name,
|
||||
source: 'runtime',
|
||||
...registration.invocation === undefined ? {} : { invocation: registration.invocation },
|
||||
content: `${registration.name} body.`,
|
||||
})
|
||||
}
|
||||
|
||||
const listed = await ctx.skills.list()
|
||||
expect(listed.map(skill => skill.name)).toEqual(['both', 'model-only', 'trusted-only', 'user-only'])
|
||||
expect(listed.filter(isModelInvocable).map(skill => skill.name)).toEqual(['both', 'model-only'])
|
||||
expect(listed.filter(isUserInvocable).map(skill => skill.name)).toEqual(['both', 'user-only'])
|
||||
expect(await ctx.skills.get('trusted-only')).toMatchObject({ content: 'trusted-only body.' })
|
||||
})
|
||||
|
||||
it('validates parsed candidate fields', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SkillService)
|
||||
@@ -117,7 +150,7 @@ describe('SkillService registry', () => {
|
||||
...memorySkill('bad-candidate', 'placeholder', 1),
|
||||
provider: 'bad-candidate',
|
||||
description: badDescription as unknown as string,
|
||||
disableModelInvocation: 'false' as unknown as boolean,
|
||||
invocation: { disableModelInvocation: 'false' as unknown as boolean },
|
||||
}]),
|
||||
get: () => Promise.resolve(undefined),
|
||||
})
|
||||
@@ -130,11 +163,11 @@ describe('SkillService registry', () => {
|
||||
list: () => Promise.resolve([{
|
||||
...memorySkill('bad-boolean', 'Bad boolean', 1),
|
||||
provider: 'bad-boolean',
|
||||
disableModelInvocation: 'false' as unknown as boolean,
|
||||
invocation: { disableModelInvocation: 'false' as unknown as boolean },
|
||||
}]),
|
||||
get: () => Promise.resolve(undefined),
|
||||
})
|
||||
await expect(badBoolean.skills.list()).rejects.toThrow('non-boolean disableModelInvocation')
|
||||
await expect(badBoolean.skills.list()).rejects.toThrow('non-boolean invocation.disableModelInvocation')
|
||||
})
|
||||
|
||||
it('rejects non-array provider results and every malformed candidate scalar', async () => {
|
||||
@@ -163,7 +196,7 @@ describe('SkillService registry', () => {
|
||||
name: `candidate-${index}`,
|
||||
description: 'Candidate',
|
||||
whenToUse: 'Use this candidate.',
|
||||
disableModelInvocation: false,
|
||||
invocation: { disableModelInvocation: false, userInvocable: true },
|
||||
provider: providerName,
|
||||
source: 'test',
|
||||
rank: 1,
|
||||
@@ -320,11 +353,12 @@ describe('SkillService registry', () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SkillService)
|
||||
const locator = { id: 'provider-owned' }
|
||||
const invocation = { disableModelInvocation: false, userInvocable: true }
|
||||
const candidate: SkillCandidate = {
|
||||
name: 'stable-skill',
|
||||
description: 'Stable description',
|
||||
whenToUse: 'When stability matters.',
|
||||
disableModelInvocation: false,
|
||||
invocation,
|
||||
provider: 'detached',
|
||||
source: 'test',
|
||||
resourceBase: { kind: 'opaque', description: 'candidate resources' },
|
||||
@@ -337,7 +371,7 @@ describe('SkillService registry', () => {
|
||||
name: 'stable-skill',
|
||||
description: 'Stable description',
|
||||
whenToUse: 'When stability matters.',
|
||||
disableModelInvocation: false,
|
||||
invocation,
|
||||
provider: 'detached',
|
||||
source: 'test',
|
||||
resourceBase: { kind: 'opaque', description: 'definition resources' },
|
||||
@@ -366,6 +400,7 @@ describe('SkillService registry', () => {
|
||||
resourceBase: { kind: 'opaque', description: 'candidate resources' },
|
||||
})])
|
||||
expect(listed[0]?.resourceBase).toBe(candidate.resourceBase)
|
||||
expect(listed[0]?.invocation).toBe(invocation)
|
||||
expect(listCalls).toBe(1)
|
||||
|
||||
const loaded = await ctx.skills.get('stable-skill')
|
||||
@@ -379,11 +414,12 @@ describe('SkillService registry', () => {
|
||||
await ctx.plugin(SkillService)
|
||||
const resourceBase = { kind: 'opaque' as const, description: 'runtime resources' }
|
||||
const metadata = { owner: 'runtime' }
|
||||
const invocation = { disableModelInvocation: false, userInvocable: true }
|
||||
const registration = {
|
||||
name: 'runtime-skill',
|
||||
description: 'Runtime',
|
||||
whenToUse: 'When runtime data is needed.',
|
||||
disableModelInvocation: false,
|
||||
invocation,
|
||||
source: 'runtime',
|
||||
resourceBase,
|
||||
metadata,
|
||||
@@ -399,6 +435,7 @@ describe('SkillService registry', () => {
|
||||
const listed = await ctx.skills.list()
|
||||
const loaded = await ctx.skills.get('runtime-skill')
|
||||
expect(listed[0]?.resourceBase).toBe(resourceBase)
|
||||
expect(listed[0]?.invocation).toBe(invocation)
|
||||
expect(loaded?.resourceBase).toBe(resourceBase)
|
||||
expect(loaded?.metadata).toBe(metadata)
|
||||
expect(loaded?.provider).toBe('runtime')
|
||||
@@ -410,7 +447,15 @@ describe('SkillService registry', () => {
|
||||
{ patch: { name: 'Bad_Name' }, expected: 'loaded skill has invalid name' },
|
||||
{ patch: { description: { value: 'description' } as unknown as string }, expected: 'description must be a string' },
|
||||
{ patch: { description: '' }, expected: 'requires a description' },
|
||||
{ patch: { disableModelInvocation: 'false' as unknown as boolean }, expected: 'disableModelInvocation must be a boolean' },
|
||||
{ patch: { invocation: null as never }, expected: 'non-object invocation policy' },
|
||||
{
|
||||
patch: { invocation: { disableModelInvocation: 'false' as unknown as boolean } },
|
||||
expected: 'invocation.disableModelInvocation',
|
||||
},
|
||||
{
|
||||
patch: { invocation: { userInvocable: 'true' as unknown as boolean } },
|
||||
expected: 'invocation.userInvocable',
|
||||
},
|
||||
{ patch: { whenToUse: 1 as unknown as string }, expected: 'whenToUse must be a string' },
|
||||
{ patch: { source: { value: 'source' } as unknown as string }, expected: 'source must be a string' },
|
||||
{ patch: { provider: { value: 'provider' } as unknown as string }, expected: 'provider must be a string' },
|
||||
@@ -436,7 +481,7 @@ describe('SkillService registry', () => {
|
||||
name: skillName,
|
||||
description: 'Definition',
|
||||
whenToUse: 'Use this definition.',
|
||||
disableModelInvocation: false,
|
||||
invocation: { disableModelInvocation: false, userInvocable: true },
|
||||
provider: providerName,
|
||||
source: 'test',
|
||||
content: 'Definition body.',
|
||||
@@ -668,6 +713,13 @@ describe('SkillService registry', () => {
|
||||
await ctx.plugin(SkillService)
|
||||
expect(() => ctx.skills.register({ name: 'Bad_Name', description: 'Bad', source: 'runtime', content: 'bad' })).toThrow('invalid skill name')
|
||||
expect(() => ctx.skills.register({ name: 'no-description', description: '', source: 'runtime', content: 'bad' })).toThrow('requires a description')
|
||||
expect(() => ctx.skills.register({
|
||||
name: 'bad-invocation',
|
||||
description: 'Bad invocation',
|
||||
source: 'runtime',
|
||||
invocation: [] as never,
|
||||
content: 'bad',
|
||||
})).toThrow('non-object invocation policy')
|
||||
expect(await ctx.skills.get('missing-skill')).toBeUndefined()
|
||||
expect(await ctx.skills.get('Bad_Name')).toBeUndefined()
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# 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
|
||||
README.md: 6b0af04a15bfda985be3e04868f18b9af702eae7
|
||||
README.zh.md: 4ca0ccd7734848d5774e92910e916bdf71c88c13
|
||||
# pnpm run verify-translation-pairing --write packages/skill/tool-skill/README.md
|
||||
README.md: 37cda665b74e186d26129c74401b4d8b24c9b7c3
|
||||
README.zh.md: 849e44513c69ed11c311a1437c8a9a4af03a03f0
|
||||
@@ -22,7 +22,7 @@ Execution uses the calling agent's `session.header.cwd` so workspace-sensitive p
|
||||
|
||||
Resource guidance resolves only paths or URLs explicitly referenced by the instructions against `resourceBase`; scripts, references, and assets load on demand, and the result does not enumerate a skill directory. Local providers may supply a directory, while remote or embedded providers may supply a URL or opaque loading guidance.
|
||||
|
||||
An unresolved name reports that the skill is unknown or no longer available. Invalid names and `disableModelInvocation: true` skills produce distinct error results.
|
||||
An unresolved name reports that the skill is unknown or no longer available. Invalid names and skills whose `invocation.disableModelInvocation` is `true` produce distinct error results. `invocation.userInvocable` does not restrict this model-facing surface.
|
||||
|
||||
The tool does not call `agent.inject()` in v1. Its result is already recorded as the tool result and becomes available to the next model step without duplicating the content as synthetic context.
|
||||
|
||||
|
||||
@@ -22,7 +22,7 @@
|
||||
|
||||
资源指引只会根据 `resourceBase` 解析指令显式引用的路径或 URL；脚本、参考资料和产物按需加载，结果不会列举 skill 目录。本地提供方可以提供目录，而远程或嵌入式提供方可以提供 URL 或不透明加载指引。
|
||||
|
||||
无法解析的名称会报告 skill 未知或已不可用。无效名称和 `disableModelInvocation: true` skill 产生不同的错误结果。
|
||||
无法解析的名称会报告 skill 未知或已不可用。无效名称和 `invocation.disableModelInvocation` 为 `true` 的 skill 会产生不同的错误结果。`invocation.userInvocable` 不限制这个面向模型的接口。
|
||||
|
||||
该工具在 v1 中不调用 `agent.inject()`。其结果已作为工具结果记录，并在下一个模型步骤可用，无需将内容重复为合成上下文。
|
||||
|
||||
|
||||
@@ -9,7 +9,12 @@ import z from 'schemastery'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import { defineTool } from '@deepseek-ai/dsh-tools'
|
||||
import { assertNever, type Message } from '@deepseek-ai/dsh-llm'
|
||||
import { isSkillName, type SkillDefinition, type SkillSummary } from '@deepseek-ai/dsh-skill'
|
||||
import {
|
||||
isModelInvocable,
|
||||
isSkillName,
|
||||
type SkillDefinition,
|
||||
type SkillSummary,
|
||||
} from '@deepseek-ai/dsh-skill'
|
||||
|
||||
export const name = 'tool-skill'
|
||||
export const inject = ['tools', 'skills']
|
||||
@@ -91,7 +96,7 @@ export function apply(ctx: Context, config: Config = {}): void {
|
||||
if (!skill) {
|
||||
throw new Error(`skill "${args.name}" is unknown or no longer available`)
|
||||
}
|
||||
if (skill.disableModelInvocation === true) {
|
||||
if (!isModelInvocable(skill)) {
|
||||
throw new Error(`skill "${args.name}" is not available for model invocation`)
|
||||
}
|
||||
return {
|
||||
@@ -123,7 +128,8 @@ export function apply(ctx: Context, config: Config = {}): void {
|
||||
catalogLoaded.add(agent.session)
|
||||
return
|
||||
}
|
||||
const skills = await ctx.skills.list({ cwd: agent.session.header.cwd, signal })
|
||||
const skills = (await ctx.skills.list({ cwd: agent.session.header.cwd, signal }))
|
||||
.filter(isModelInvocable)
|
||||
if (skills.length > 0) {
|
||||
const catalog = renderCatalogMessage(skills, catalogDescriptionMaxLength)
|
||||
agent.inject({ content: catalog.content, source: { kind: 'plugin', plugin: 'dsh-tool-skill' } })
|
||||
|
||||
@@ -143,6 +143,20 @@ describe('dsh-tool-skill', () => {
|
||||
provider: 'runtime',
|
||||
content: 'A body.',
|
||||
})
|
||||
ctx.skills.register({
|
||||
name: 'model-only-skill',
|
||||
description: 'Model-only skill.',
|
||||
invocation: { userInvocable: false },
|
||||
source: 'runtime',
|
||||
content: 'Model-only body.',
|
||||
})
|
||||
ctx.skills.register({
|
||||
name: 'user-only-skill',
|
||||
description: 'User-only skill.',
|
||||
invocation: { disableModelInvocation: true },
|
||||
source: 'runtime',
|
||||
content: 'User-only body.',
|
||||
})
|
||||
ctx.on('agent/step', (agent) => {
|
||||
agent.inject({ content: [{ type: 'text', text: 'later contribution' }], source: { kind: 'plugin', plugin: 'later-contribution' } })
|
||||
})
|
||||
@@ -160,6 +174,7 @@ describe('dsh-tool-skill', () => {
|
||||
'',
|
||||
'<available_skills>',
|
||||
'- `a-skill`: Use {{placeholder}} <safely> & carefully.',
|
||||
'- `model-only-skill`: Model-only skill.',
|
||||
'- `z-skill`: Long description Long description Long descript...',
|
||||
'</available_skills>',
|
||||
'',
|
||||
@@ -175,12 +190,20 @@ describe('dsh-tool-skill', () => {
|
||||
expect(rendered).not.toContain('secret-source')
|
||||
expect(rendered).not.toContain('/secret/path')
|
||||
expect(rendered).not.toContain('Secret body')
|
||||
expect(rendered).not.toContain('user-only-skill')
|
||||
expect(renderPrompt(await ctx.systemPrompt.assemble({ agent: agentForCwd('/workspace') }))).not.toContain('<available_skills>')
|
||||
})
|
||||
|
||||
it('does not inject a catalog when no skills are available', async () => {
|
||||
it('does not inject a catalog when no model-invocable skills are available', async () => {
|
||||
const home = await tempDir('tool-empty-catalog')
|
||||
const ctx = await setup(home)
|
||||
ctx.skills.register({
|
||||
name: 'user-only-skill',
|
||||
description: 'User-only skill',
|
||||
invocation: { disableModelInvocation: true },
|
||||
source: 'runtime',
|
||||
content: 'User-only body.',
|
||||
})
|
||||
|
||||
expect(await composePrefix(ctx, '/workspace')).toEqual([])
|
||||
})
|
||||
@@ -333,16 +356,25 @@ describe('dsh-tool-skill', () => {
|
||||
it('returns isError for unknown, invalid, and model-disabled skills', async () => {
|
||||
const home = await tempDir('tool-errors')
|
||||
await writeSkill(join(home, '.dsh/skills'), 'hidden-skill', 'Hidden skill', 'Hidden instructions.')
|
||||
await writeFile(join(home, '.dsh/skills/hidden-skill/SKILL.md'), '---\nname: hidden-skill\ndescription: Hidden skill\ndisableModelInvocation: true\n---\n\nHidden instructions.\n')
|
||||
await writeFile(join(home, '.dsh/skills/hidden-skill/SKILL.md'), '---\nname: hidden-skill\ndescription: Hidden skill\ndisable-model-invocation: true\n---\n\nHidden instructions.\n')
|
||||
const ctx = await setup(home)
|
||||
ctx.skills.register({
|
||||
name: 'model-only-skill',
|
||||
description: 'Model-only skill',
|
||||
invocation: { userInvocable: false },
|
||||
source: 'runtime',
|
||||
content: 'Model-only instructions.',
|
||||
})
|
||||
|
||||
const unknown = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('c1'), name: 'skill', arguments: { name: 'missing' } })
|
||||
const invalid = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('c2'), name: 'skill', arguments: { name: 'Bad_Name' } })
|
||||
const disabled = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('c3'), name: 'skill', arguments: { name: 'hidden-skill' } })
|
||||
const modelOnly = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('c4'), name: 'skill', arguments: { name: 'model-only-skill' } })
|
||||
|
||||
expect(unknown.isError).toBe(true)
|
||||
expect(invalid.isError).toBe(true)
|
||||
expect(disabled.isError).toBe(true)
|
||||
expect(modelOnly.isError).toBe(false)
|
||||
const unknownBlock = unknown.content[0]
|
||||
if (unknownBlock?.type !== 'text') throw new Error('expected text tool result')
|
||||
expect(unknownBlock.text).toContain('skill "missing" is unknown or no longer available')
|
||||
|
||||
@@ -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/ui/tui/README.md
|
||||
README.md: 528daef773635451ceb198ab3231c2dd87cb9413
|
||||
README.zh.md: ed19023334389e3f64b8a2f3821307f1540876f2
|
||||
README.md: 76d7f09d8b69123705f0d30c203b01989afe605c
|
||||
README.zh.md: 61fe34fc09ffea6d81442bcd23c99a340c1e0ac0
|
||||
@@ -26,7 +26,7 @@ While the agent is running, ordinary editor submissions call `agent.steer()`; ot
|
||||
|
||||
`/model` opens the advisory `ctx.llm` catalog as a keyboard selector: Up/Down moves, Shift+Tab cycles the focused model's adapter-advertised reasoning efforts in display order, Enter selects the model and effort, and Escape closes it. When an adapter does not advertise a default effort, the cycle also includes `provider default`, which clears an explicit selection; models without selectable effort metadata ignore Shift+Tab. The selector renders the exact advertised effort list—including `off` when present—and does not synthesize, clamp, or transfer an effort between models. `/model <model>` still selects an unambiguous model id directly, while `/model <provider>/<model>` selects an exact target and uses its adapter default when one exists. The configured target or latest logged request header initializes the selector, and an unlisted current model remains visible because catalogs are advisory. Selection is local to this TUI session. Prompt assembly snapshots the target for one step, replaces `{{provider}}` and `{{model}}`, and applies the same provider/model/reasoning-effort target through `agent/request`; a switch during assembly therefore starts with a later step. The request header durably records targets that reach the model, while an unused selection remains process-local.
|
||||
|
||||
`/reload` (EXPERIMENTAL, dev-only) re-reads every file-backed loader config tree and applies the diff to the running app — the HMR watcher's config path, invoked manually; it needs the cordis Loader in the context and degrades to a warning without one, runs only while the agent is idle, and refuses re-entry while a reload is in flight. Module-source hot reload remains watcher-owned. When a `skills` service is mounted, `/skill:<name> [instructions]` loads that skill's instructions into the conversation as a user turn; autocomplete lists the model-invocable skills, and any skill (including a model-disabled one) is loadable by its exact name.
|
||||
`/reload` (EXPERIMENTAL, dev-only) re-reads every file-backed loader config tree and applies the diff to the running app — the HMR watcher's config path, invoked manually; it needs the cordis Loader in the context and degrades to a warning without one, runs only while the agent is idle, and refuses re-entry while a reload is in flight. Module-source hot reload remains watcher-owned. When a `skills` service is mounted, `/skill:<name> [instructions]` loads that skill's instructions into the conversation as a user turn; autocomplete lists user-invocable skills, and exact invocation rejects a skill whose user policy disables it.
|
||||
|
||||
The footer sums the session's reported usage as `↑<uncached input> ↓<output>`, followed by `cache <rate>%` once any input has been billed — the share of billed prompt tokens (uncached input plus cache reads and writes) served from the provider cache, rounded to a percent. It also compares token-meter pressure with `ctx.llm.resolveModelInfo()` context for the current route (omitting the context share when the adapter has no capacity metadata) and shows the current model and tool-card mode; the right side clips first when the footer is narrow.
|
||||
|
||||
@@ -130,7 +130,7 @@ Changing provider or model enters that target's cache domain; no cache reuse acr
|
||||
|
||||
#### What the model sees
|
||||
|
||||
A `/skill:<name> [instructions]` submission loads the named skill and delivers one text block: a `<skill name="…">` element wrapping the skill's instructions — preceded, when the provider exposes a resource base, by a line locating the skill's relative resources — followed by any trailing instructions the user typed. Delivery follows the same followup-while-idle / steer-while-running rule as ordinary input. The command, not the model, chooses the skill; model-disabled skills are omitted from autocomplete but stay loadable by exact name.
|
||||
A `/skill:<name> [instructions]` submission loads the named skill and delivers one text block: a `<skill name="…">` element wrapping the skill's instructions — preceded, when the provider exposes a resource base, by a line locating the skill's relative resources — followed by any trailing instructions the user typed. Delivery follows the same followup-while-idle / steer-while-running rule as ordinary input. The command, not the model, chooses the skill: autocomplete and exact invocation apply `userInvocable`, while `disableModelInvocation` does not restrict this surface. A user-disabled skill produces a warning and no user turn.
|
||||
|
||||
#### Token effect
|
||||
|
||||
|
||||
@@ -26,7 +26,7 @@ Agent 运行时，普通编辑器提交会调用 `agent.steer()`；其他时候
|
||||
|
||||
`/model` 将建议性的 `ctx.llm` catalog 打开为键盘选择器：Up/Down 移动，Shift+Tab 按显示顺序循环切换适配器为焦点模型公布的推理强度，Enter 选择模型和推理强度，Escape 关闭。适配器未公布默认推理强度时，循环还会包含 `provider default`，该项会清除显式选择；没有可选推理强度元数据的模型会忽略 Shift+Tab。选择器会原样呈现公布的推理强度列表（包括存在时的 `off`），不会合成、自动调整或在模型之间转移推理强度。`/model <model>` 仍可直接选择无歧义的模型 id，`/model <provider>/<model>` 则选择精确目标，并在存在时使用其适配器默认值。已配置目标或最新记录的请求 header 会初始化选择器；由于 catalog 仅提供建议，未列出的当前模型仍会显示。选择仅对本 TUI 会话有效。提示词组装会为一个步骤建立目标快照，替换 `{{provider}}` 和 `{{model}}`，并通过 `agent/request` 应用同一个提供方／模型／推理强度目标；因此组装期间的切换会从后续步骤开始生效。请求 header 会持久记录真正到达模型的目标，未使用的选择则只存在于进程本地。
|
||||
|
||||
`/reload`（实验性，仅开发环境）会重新读取所有基于文件的 loader 配置树，并把 diff 应用到运行中 app：它手动调用 HMR（热模块替换）watcher 的配置路径；上下文中必须有 cordis Loader，否则退化为警告。它只在 agent 空闲时运行，并拒绝 reload 进行期间的再次进入。模块源代码热重载仍由 watcher 持有。挂载 `skills` 服务后，`/skill:<name> [instructions]` 会把该 skill 的指令作为一个 user 轮次加载到会话中；自动补全列出模型可调用的 skill，任何 skill（包括模型禁用的 skill）都可通过精确名称加载。
|
||||
`/reload`（实验性，仅开发环境）会重新读取所有基于文件的 loader 配置树，并把 diff 应用到运行中 app：它手动调用 HMR（热模块替换）watcher 的配置路径；上下文中必须有 cordis Loader，否则退化为警告。它只在 agent 空闲时运行，并拒绝 reload 进行期间的再次进入。模块源代码热重载仍由 watcher 持有。挂载 `skills` 服务后，`/skill:<name> [instructions]` 会把该 skill 的指令作为一个 user 轮次加载到会话中；自动补全列出用户可调用的 skill，按精确名称调用时也会拒绝用户策略禁用的 skill。
|
||||
|
||||
Footer 将会话报告的用量汇总为 `↑<uncached input> ↓<output>`；任何输入计费后，后面会显示 `cache <rate>%`，表示提供方缓存服务的已计费提示词 token 占比（未缓存输入加缓存读写），并四舍五入为百分比。它还会将 token-meter 压力与 `ctx.llm.resolveModelInfo()` 为当前路由返回的上下文容量进行比较（适配器没有容量元数据时省略上下文占比），并显示当前模型和工具卡片模式；footer 过窄时，右侧会优先裁剪。
|
||||
|
||||
@@ -130,7 +130,7 @@ Paths prefixed with @ are files explicitly referenced by the user. Use the read
|
||||
|
||||
#### 模型看到的内容
|
||||
|
||||
提交 `/skill:<name> [instructions]` 会加载具名 skill，并交付一个文本块：用 `<skill name="…">` 元素包装 skill 指令；提供方公开资源基准时，会先添加一行定位 skill 相对资源；最后附上用户输入的尾随指令。交付遵循普通输入同样的空闲时 followup、运行时 steer 规则。选择 skill 的是命令而非模型；模型禁用的 skill 不出现在自动补全中，但仍可按精确名称加载。
|
||||
提交 `/skill:<name> [instructions]` 会加载具名 skill，并交付一个文本块：用 `<skill name="…">` 元素包装 skill 指令；提供方公开资源基准时，会先添加一行定位 skill 相对资源；最后附上用户输入的尾随指令。交付遵循普通输入同样的空闲时 followup、运行时 steer 规则。选择 skill 的是命令而非模型：自动补全和按精确名称调用都应用 `userInvocable`，`disableModelInvocation` 不限制这个接口。用户禁用的 skill 会产生一条警告，不会产生用户轮次。
|
||||
|
||||
#### Token 影响
|
||||
|
||||
|
||||
@@ -49,7 +49,10 @@ import { foldSessionTitle } from '@deepseek-ai/dsh-session-title'
|
||||
// Type import also declaration-merges the optional `sessionPersistence`
|
||||
// service onto `Context` so `ctx.get('sessionPersistence')` is typed.
|
||||
import type {} from '@deepseek-ai/dsh-session-persistence'
|
||||
import type { SkillService } from '@deepseek-ai/dsh-skill'
|
||||
import {
|
||||
isUserInvocable,
|
||||
type SkillService,
|
||||
} from '@deepseek-ai/dsh-skill'
|
||||
// Type import declaration-merges the `userInteraction` service onto `Context`;
|
||||
// the ask-user-question queue is registered by ./chat/questions.
|
||||
import type {} from '@deepseek-ai/dsh-user-interaction'
|
||||
@@ -969,9 +972,7 @@ export function createTuiChat(
|
||||
}
|
||||
|
||||
// Skill listing is async while `createTuiChat` is synchronous, so the
|
||||
// completions rebuild once the catalog resolves. Disabled-for-model skills
|
||||
// are absent from `list()`, so they never appear as completions; a user can
|
||||
// still invoke one by typing its exact name.
|
||||
// completions rebuild once the invocation-neutral catalog resolves.
|
||||
let skillCommands: SlashCommand[] = []
|
||||
const refreshCommandAutocomplete = (): void => {
|
||||
const base = new CombinedAutocompleteProvider(
|
||||
@@ -999,13 +1000,14 @@ export function createTuiChat(
|
||||
const loadSkillCommands = (service: SkillService): void => {
|
||||
service.list({ cwd, signal: skillAbort.signal }).then(
|
||||
(summaries) => {
|
||||
if (disposed || summaries.length === 0) return
|
||||
const invocable = summaries.filter(isUserInvocable)
|
||||
if (disposed || invocable.length === 0) return
|
||||
// The argument-hint slot shows in the menu but is never inserted on
|
||||
// selection, so it carries the skill's scope instead of an
|
||||
// instructions placeholder. `SkillSource` is open-ended; every
|
||||
// non-project source (user, custom, bundled, runtime, …) collapses
|
||||
// to `(user)`.
|
||||
skillCommands = summaries.map(skill => ({
|
||||
skillCommands = invocable.map(skill => ({
|
||||
name: `skill:${skill.name}`,
|
||||
description: skill.description,
|
||||
argumentHint: skill.source.startsWith('project-') ? '(project)' : '(user)',
|
||||
@@ -1211,6 +1213,10 @@ export function createTuiChat(
|
||||
appendNotice(`Unknown skill: ${name}`, 'warning')
|
||||
return
|
||||
}
|
||||
if (!isUserInvocable(skill)) {
|
||||
appendNotice(`Skill "${name}" is not available for user invocation.`, 'warning')
|
||||
return
|
||||
}
|
||||
deliver(renderSkillInvocation(skill, instructions))
|
||||
},
|
||||
(error: unknown) => {
|
||||
|
||||
@@ -3542,10 +3542,30 @@ describe('skill slash command', () => {
|
||||
if (skills === undefined) throw new Error('skills service not mounted')
|
||||
skills.register({ name: 'demo-skill', description: 'Demo skill for tests', source: 'runtime', provider: 'runtime', content: 'Demo instructions body.' })
|
||||
skills.register({ name: 'project-skill', description: 'Project skill for tests', source: 'project-dsh', provider: 'runtime', content: 'Project instructions body.' })
|
||||
skills.register({ name: 'hidden-skill', description: 'Model-hidden skill', source: 'runtime', provider: 'runtime', content: 'Hidden instructions body.', disableModelInvocation: true })
|
||||
skills.register({
|
||||
name: 'user-only-skill',
|
||||
description: 'User-only skill',
|
||||
invocation: { disableModelInvocation: true },
|
||||
source: 'runtime',
|
||||
content: 'User-only instructions body.',
|
||||
})
|
||||
skills.register({
|
||||
name: 'model-only-skill',
|
||||
description: 'Model-only skill',
|
||||
invocation: { userInvocable: false },
|
||||
source: 'runtime',
|
||||
content: 'Model-only instructions body.',
|
||||
})
|
||||
skills.register({
|
||||
name: 'trusted-only-skill',
|
||||
description: 'Trusted-only skill',
|
||||
invocation: { disableModelInvocation: true, userInvocable: false },
|
||||
source: 'runtime',
|
||||
content: 'Trusted-only instructions body.',
|
||||
})
|
||||
}
|
||||
|
||||
it('labels slash completions by scope and hides model-disabled skills', async () => {
|
||||
it('labels slash completions by scope and applies user invocation policy', async () => {
|
||||
const result = await setup({ configureContext: withSkills })
|
||||
result.terminal.send('/skill')
|
||||
await tick()
|
||||
@@ -3553,8 +3573,10 @@ describe('skill slash command', () => {
|
||||
expect(result.terminal.output).toContain('(user)')
|
||||
expect(result.terminal.output).toContain('project-skill')
|
||||
expect(result.terminal.output).toContain('(project)')
|
||||
expect(result.terminal.output).toContain('user-only-skill')
|
||||
expect(result.terminal.output).not.toContain('[instructions]')
|
||||
expect(result.terminal.output).not.toContain('hidden-skill')
|
||||
expect(result.terminal.output).not.toContain('model-only-skill')
|
||||
expect(result.terminal.output).not.toContain('trusted-only-skill')
|
||||
await dispose(result)
|
||||
})
|
||||
|
||||
@@ -3573,12 +3595,26 @@ describe('skill slash command', () => {
|
||||
await dispose(result)
|
||||
})
|
||||
|
||||
it('invokes a model-disabled skill by its exact name', async () => {
|
||||
it('invokes a user-only skill by its exact name', async () => {
|
||||
const result = await setup({ configureContext: withSkills })
|
||||
result.terminal.send('/skill:hidden-skill')
|
||||
result.terminal.send('/skill:user-only-skill')
|
||||
result.terminal.send('\r')
|
||||
await tick()
|
||||
expect(result.agent.sent).toEqual([[{ type: 'text', text: '<skill name="hidden-skill">\nHidden instructions body.\n</skill>' }]])
|
||||
expect(result.agent.sent).toEqual([[{ type: 'text', text: '<skill name="user-only-skill">\nUser-only instructions body.\n</skill>' }]])
|
||||
await dispose(result)
|
||||
})
|
||||
|
||||
it('rejects exact invocation of skills disabled for users', async () => {
|
||||
const result = await setup({ configureContext: withSkills })
|
||||
result.terminal.send('/skill:model-only-skill')
|
||||
result.terminal.send('\r')
|
||||
await tick()
|
||||
result.terminal.send('/skill:trusted-only-skill')
|
||||
result.terminal.send('\r')
|
||||
await tick()
|
||||
expect(result.agent.sent).toEqual([])
|
||||
expect(result.terminal.output).toContain('Skill "model-only-skill" is not available for user invocation.')
|
||||
expect(result.terminal.output).toContain('Skill "trusted-only-skill" is not available for user invocation.')
|
||||
await dispose(result)
|
||||
})
|
||||
|
||||
|
||||
@@ -979,6 +979,11 @@
|
||||
"symbol": "SkillResourceBase",
|
||||
"source": "packages/skill/skill/src/index.ts"
|
||||
},
|
||||
{
|
||||
"doc": "docs/core-data-structures/skills.md",
|
||||
"symbol": "SkillInvocationPolicy",
|
||||
"source": "packages/skill/skill/src/index.ts"
|
||||
},
|
||||
{
|
||||
"doc": "docs/core-data-structures/skills.md",
|
||||
"symbol": "SkillSummary",
|
||||
|
||||
Reference in New Issue
Block a user