docs: rescan rebased documentation hierarchy

This commit is contained in:
Turtle
2026-08-05 12:46:38 +08:00
parent 012bb0a549
commit 8af3babaea
304 changed files with 1091 additions and 1983 deletions

View File

@@ -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/goal/command-goal/README.md
README.md: 8e1a5b417467c8701ea935e25acfece11c5a70d4
README.zh.md: ddb11d09d4a4d560af05b05ad7b586c1b0d365f9
README.md: b7626f3ff14a563407c7a60dd057c9c8616fe994
README.zh.md: f4c3c16b963ad16b1430efb25c91bd27fc75638f

View File

@@ -2,7 +2,7 @@
English | [中文](README.zh.md)
Human-facing `/goal` control over [`ctx.goals`](../goal/README.md). The plugin registers one global command through [`ctx.commands`](../../ui/commands/README.md), so every composed command adapter discovers it; the shipped TUI executes it without a model turn. The [human goal-command Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-human-goal-command.md) owns the UX and composition decisions.
Human-facing `/goal` control over [`ctx.goals`](../goal/README.md). The plugin registers one global command through [`ctx.commands`](../../ui/commands/README.md), so every composed command adapter discovers and executes it without a model turn. The [human goal-command Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-human-goal-command.md) owns the UX and composition decisions.
## Command contract
@@ -32,7 +32,7 @@ The producer injects `commands` and `goals`. A custom app mounts their owners pl
name: '@deepseek-ai/dsh-command-goal'
```
The TUI app enables the complete persisted-goal stack and this command by default. The ACP automation app enables the domain and model tools without mounting the command registry; `goals: false` removes that stack. The UI-less `agent-spine-demo` requires an explicit `goals: {}` so headless one-shot callers do not silently change from one physical turn to a multi-round operation.
The shipped `dsh` base enables the persisted-goal stack and this command; the Web client provides its interactive adapter. The ACP automation app enables the domain and model tools without a command adapter; `goals: false` removes that stack. The UI-less `agent-spine-demo` requires an explicit `goals: {}` so headless one-shot callers do not silently change from one physical turn to a multi-round operation.
## Model Experience
@@ -55,4 +55,4 @@ Command discovery and direct output do not affect the cache. A mutation appends
- **Plain-text interaction only** — the generic command registry has no modal edit form or replacement-confirmation callback; inline edit and explicit clear keep destructive intent deterministic across adapters.
- **No per-command round-cap argument** — `defaultMaxGoalRounds` remains deployment config, while a direct human request may ask the model to edit `max_goal_rounds` through the separately authorized goal tool.
- **No continuous status widget** — bare `/goal` is the portable observation surface; adapter-specific badges and reconnectable command output remain future UI work.
- **TUI only in the shipped apps** — the headless CLI, ACP automation, and JSON-RPC adapters do not consume `ctx.commands`. Ordinary prompts can still authorize model-facing goal tools when those are composed.
- **Web command adapter only in the shipped apps** — headless, ACP automation, and JSON-RPC adapters do not consume `ctx.commands`. Ordinary prompts can still authorize model-facing goal tools when those are composed.

View File

@@ -2,7 +2,7 @@
[English](README.md) | 中文
面向用户的 `/goal` 控制,基于 [`ctx.goals`](../goal/README.md) 实现。该插件通过 [`ctx.commands`](../../ui/commands/README.md) 注册一个全局命令,因此每个已组合的命令适配器都能发现它;随附 TUI 无需模型轮次即可执行。[用户 goal 命令 Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-human-goal-command.md) 负责用户体验与组合决策。
面向用户的 `/goal` 控制,基于 [`ctx.goals`](../goal/README.md) 实现。该插件通过 [`ctx.commands`](../../ui/commands/README.md) 注册一个全局命令,因此每个已组合的命令适配器都能发现并执行它,无需模型轮次。[用户 goal 命令 Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-human-goal-command.md)负责用户体验与组合决策。
## 命令契约
@@ -32,7 +32,7 @@
name: '@deepseek-ai/dsh-command-goal'
```
TUI 应用默认启用完整的持久 goal 栈和此命令。ACP(Agent Client Protocol)自动化应用会启用领域与模型工具,但不挂载命令注册表;`goals: false` 会移除该栈。无 UI 的 `agent-spine-demo` 必须显式配置 `goals: {}`,避免无头单次调用方在不知情时从一个物理轮次变为包含多个 Round 的操作。
随附 `dsh` 基础配置启用持久 goal 栈和此命令;Web 客户端提供其交互适配器。ACP(Agent Client Protocol)自动化应用启用领域与模型工具,但不挂载命令适配器;`goals: false` 会移除该栈。无 UI 的 `agent-spine-demo` 必须显式配置 `goals: {}`,避免无头单次调用方在不知情时从一个物理轮次变为包含多个 Round 的操作。
## 模型体验
@@ -55,4 +55,4 @@ TUI 应用默认启用完整的持久 goal 栈和此命令。ACP(Agent Client
- **仅纯文本交互**:通用命令注册表没有模态编辑表单或替换确认回调;内联 edit 与显式 clear 能在不同适配器中保持明确且一致的破坏性意图。
- **没有逐命令 Round 上限参数**:`defaultMaxGoalRounds` 仍是部署配置;用户直接请求时,可以要求模型通过另行授权的 goal 工具编辑 `max_goal_rounds`。
- **没有持续状态组件**:裸 `/goal` 是可移植的观察接口;适配器专用徽标和重连后可恢复的命令输出仍属于未来 UI 工作。
- **随附应用中只有 TUI 使用此命令**:无头 CLI(命令行界面)、ACP 自动化和 JSON-RPC 适配器不消费 `ctx.commands`。如果组合中包含面向模型的 goal 工具,普通提示词仍能授权它们。
- **随附应用中只有 Web 命令适配器使用此命令**:无头、ACP 自动化和 JSON-RPC 适配器不消费 `ctx.commands`。如果组合中包含面向模型的 goal 工具,普通提示词仍能授权它们。

View File

@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write packages/goal/goal-session/README.md
README.md: 6a1c3b9455c93762c2458109c753588ce9a08d9a
README.zh.md: 7e8b04f46f0345bce026ccd8c663882f27e036ab
README.zh.md: 6101d4e3724aea99875613c96bc9c004feb38ad3

View File

@@ -21,7 +21,7 @@
## Round 契约
当对应的活跃 agent 实例处于 idle 状态,且目标 phase 为 active、已启用续行并有剩余容量时,驱动器先为待处理 goal 变更创建检查点,再预留 `roundsStarted + 1`,对应当前 `{ goalId, revision }`。它会排入一条 `<goal_round>` 提示词,并携带 `GoalMessageSource`。通过 `agent/prompt-submit` 准入时,会在下游提示词钩子前后验证完整的排队记录与当前 goal;只有被接受的 `user/message` 才会增加 `roundsStarted`。因陈旧而被拒绝的预留不会消耗 Round 编号。
当对应的活跃 agent(智能体)实例处于 idle 状态,且目标 phase 为 active、已启用续行并有剩余容量时,驱动器先为待处理 goal 变更创建检查点,再预留 `roundsStarted + 1`,对应当前 `{ goalId, revision }`。它会排入一条 `<goal_round>` 提示词,并携带 `GoalMessageSource`。通过 `agent/prompt-submit` 准入时,会在下游提示词钩子前后验证完整的排队记录与当前 goal;只有被接受的 `user/message` 才会增加 `roundsStarted`。因陈旧而被拒绝的预留不会消耗 Round 编号。
一个 Goal Round 对应一个普通会话轮次,该轮次可以包含多个模型/工具步骤。驱动器只会把预留与 `message` 轮次配对,且该轮次必须携带完全相同的 `GoalMessageSource`;可通过声明合并扩展的插件轮次触发器不会准入或替换该预留。用户消息仍是普通轮次,不消耗 goal 上限。如果用户工作在预留前进入 inbox,或加入预留的待处理批次,自动工作会让行,直到用户工作结算;混合批次中的待处理自动提示词会被拒绝,只有 agent 再次 idle 后才重新预留。