merge: refresh against the advancing master
This commit is contained in:
Huanqi Cao
@@ -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/client/ui-goal/README.md
|
||||
README.md: 2c109ab1fbe0b566b8749a6af44ec5e0055fe3b2
|
||||
README.zh.md: b81113c67566fd834b3ddb10931d4ecc630aa2f9
|
||||
README.md: cfb54fd28044ed80e6ec05de0be057f5d4cfaf46
|
||||
README.zh.md: fd999cf1c4c9695d15cfaab3e83afdf475f40448
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
English | [中文](README.zh.md)
|
||||
|
||||
Goal surface plugin, browser half: the `GoalBar` strip is the first standalone card in the `conversation.input.dock` composer-context stack (order 0, before Todo and Queue). The live goal arrives through `useProjection('goal')` — the host-computed whole value seeded by the history tail page and updated by `session/projection` frames — so the plugin owns no store, no refresh chain, and no event listener. The slot inject face carries only the four mutation verbs (edit / pause / resume / clear over the `goal.*` wire domain — an active goal offers the pause action, a paused one resume); each reads the CAS ref from the session's current projected value at call time and surfaces the settled RPC error inline (the RPC's compare-and-set is the staleness guard — there is no client fence). Goal creation stays on the `/goal` host command; loading, absent, and completed goals render nothing.
|
||||
Goal surface plugin, browser half: the `GoalBar` strip is the first standalone card in the `conversation.input.dock` composer-context stack (order 0, before Todo and Queue). The live goal arrives through `useProjection('goal')` — the host-computed whole value seeded by the history tail page and updated by `session/projection` frames — so the plugin owns no domain store, refresh chain, or event listener. The slot inject face carries only the four mutation verbs (edit / pause / resume / clear over the `goal.*` wire domain — an active goal offers the pause action, a paused one resume); each reads the CAS ref from the session's current projected value at call time and surfaces the settled RPC error inline. The strip single-flights mutations synchronously because React's pending render cannot fence same-frame clicks; after a successful clear it immediately suppresses that exact goal id while the authoritative null projection catches up. Goal creation stays on the `/goal` host command; loading, absent, completed, and successfully cleared goals render nothing.
|
||||
|
||||
The `/client` export surface is the plugin body (`apply`/`inject`), the `GoalBar`/`GoalDock` components, and the injected verb face types.
|
||||
|
||||
@@ -17,4 +17,3 @@ None beyond the goal mutation's own context event, which appends to the log tail
|
||||
## Known Limitations and Deferred Work
|
||||
|
||||
- **Durable phase only** — the projection value deliberately omits process-local activation (armed/disarmed), so the strip cannot distinguish an active-but-disarmed goal from an armed one; resume re-arms through the RPC side. A host-live-value channel is deferred until a real consumer needs it.
|
||||
- **No keyless snapshot yet** — the assembled-application transcript (boot → projection → GoalBar) is deferred to the post-review cleanup pass recorded on the landing PR.
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
[English](README.md) | 中文
|
||||
|
||||
Goal 表面插件（浏览器半件）：`GoalBar` 条带是 `conversation.input.dock` composer 上下文堆栈中的第一张独立卡片（order 0，位于 Todo 和 Queue 之前）。活值经 `useProjection('goal')` 到达——host 计算的全量值由历史尾页播种、由 `session/projection` 帧更新——因此本插件不持有 store、不设刷新链、不挂事件监听。slot 注入面只携带四个变更动词（edit / pause / resume / clear，走 `goal.*` 协议域——active 的 goal 提供暂停动作，paused 的提供恢复）；每个动词在调用时从会话当前投影值读取 CAS ref，并把结算后的 RPC 错误内联呈现（RPC 的 compare-and-set 即陈旧性防护——客户端没有任何栅栏）。goal 的创建仍归 `/goal` host 命令；加载中、无 goal、已完成三种状态一律不渲染。
|
||||
Goal 表面插件（浏览器半件）：`GoalBar` 条带是 `conversation.input.dock` composer 上下文堆栈中的第一张独立卡片（order 0，位于 Todo 和 Queue 之前）。活值经 `useProjection('goal')` 到达——host 计算的全量值由历史尾页播种、由 `session/projection` 帧更新——因此本插件不持有领域 store、不设刷新链、不挂事件监听。slot 注入面只携带四个变更动词（edit / pause / resume / clear，走 `goal.*` 协议域——active 的 goal 提供暂停动作，paused 的提供恢复）；每个动词在调用时从会话当前投影值读取 CAS ref，并把结算后的 RPC 错误内联呈现。由于 React 的 pending 渲染无法拦住同一帧内的点击，横条会同步为变更建立 single-flight 防护；清除成功后，会立即抑制该 goal id 对应的目标显示，直到权威的 null 投影追上。goal 的创建仍归 `/goal` host 命令；加载中、无 goal、已完成和已成功清除的 goal 一律不渲染。
|
||||
|
||||
`/client` 出口面为插件本体（`apply`/`inject`）、`GoalBar`/`GoalDock` 组件与注入动词面类型。
|
||||
|
||||
@@ -17,4 +17,3 @@ Goal 表面插件（浏览器半件）：`GoalBar` 条带是 `conversation.input
|
||||
## Known Limitations and Deferred Work
|
||||
|
||||
- **只反映持久 phase** —— 投影值有意省略进程本地的 activation（armed/disarmed），条带无法区分 active-but-disarmed 与 armed 状态；resume 经 RPC 侧重新武装。host 活值通道待出现真实消费方后再议。
|
||||
- **暂缺 keyless 快照** —— 组装应用级 transcript（boot → 投影 → GoalBar）推迟到落地 PR 记录的评审后收口批次。
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
* the injected face.
|
||||
*/
|
||||
|
||||
import { useCallback, useEffect, useState } from 'react'
|
||||
import { useCallback, useEffect, useRef, useState } from 'react'
|
||||
import type { GoalSnapshot } from '@deepseek-ai/dsh-goal/client'
|
||||
import {
|
||||
IconCheckOutline16, IconCloseOutline16, IconEditOutline16, IconPauseOutline16, IconPlayOutline16, IconSparkle16, IconTrashOutline16,
|
||||
@@ -35,6 +35,8 @@ export function GoalBar({ goal, onEdit, onPause, onResume, onClear, t }: GoalBar
|
||||
const [draft, setDraft] = useState('')
|
||||
const [pending, setPending] = useState(false)
|
||||
const [actionError, setActionError] = useState<string | null>(null)
|
||||
const [clearedGoalId, setClearedGoalId] = useState<GoalSnapshot['id'] | null>(null)
|
||||
const pendingRef = useRef(false)
|
||||
|
||||
// A new goal identity (cleared/completed/replaced externally) invalidates the local edit
|
||||
// state: without the reset a surviving draft's Enter would write over the NEW goal.
|
||||
@@ -42,32 +44,37 @@ export function GoalBar({ goal, onEdit, onPause, onResume, onClear, t }: GoalBar
|
||||
useEffect(() => {
|
||||
setEditing(false)
|
||||
setActionError(null)
|
||||
setClearedGoalId(null)
|
||||
}, [goalId])
|
||||
|
||||
// React state disables the controls on the next render; the ref closes the
|
||||
// same-render window so rapid clicks cannot submit the same CAS twice.
|
||||
const runAction = useCallback(async (action: () => Promise<GoalActionResult>): Promise<GoalActionResult | undefined> => {
|
||||
if (pendingRef.current) return undefined
|
||||
pendingRef.current = true
|
||||
setPending(true)
|
||||
setActionError(null)
|
||||
const result = await action()
|
||||
pendingRef.current = false
|
||||
setPending(false)
|
||||
if (!result.ok) setActionError(`${result.error.message} (${result.error.code})`)
|
||||
return result
|
||||
}, [])
|
||||
|
||||
const handleEdit = useCallback(async () => {
|
||||
const trimmed = draft.trim()
|
||||
if (trimmed === '') return
|
||||
setPending(true)
|
||||
setActionError(null)
|
||||
const result = await onEdit(trimmed)
|
||||
setPending(false)
|
||||
if (result.ok) {
|
||||
setEditing(false)
|
||||
} else {
|
||||
setActionError(`${result.error.message} (${result.error.code})`)
|
||||
}
|
||||
}, [draft, onEdit])
|
||||
const result = await runAction(() => onEdit(trimmed))
|
||||
if (result?.ok) setEditing(false)
|
||||
}, [draft, onEdit, runAction])
|
||||
|
||||
const runAction = useCallback(async (action: () => Promise<GoalActionResult>) => {
|
||||
setPending(true)
|
||||
setActionError(null)
|
||||
const result = await action()
|
||||
setPending(false)
|
||||
if (!result.ok) setActionError(`${result.error.message} (${result.error.code})`)
|
||||
}, [])
|
||||
const handleClear = useCallback(async (clearedId: GoalSnapshot['id']) => {
|
||||
const result = await runAction(onClear)
|
||||
if (result?.ok) setClearedGoalId(clearedId)
|
||||
}, [onClear, runAction])
|
||||
|
||||
// Loading, absent, and complete goals have no strip at all.
|
||||
if (goal === undefined || goal === null || goal.phase === 'complete') return null
|
||||
if (goal === undefined || goal === null || goal.phase === 'complete' || goal.id === clearedGoalId) return null
|
||||
|
||||
if (editing) {
|
||||
return (
|
||||
@@ -142,7 +149,7 @@ export function GoalBar({ goal, onEdit, onPause, onResume, onClear, t }: GoalBar
|
||||
>
|
||||
<IconEditOutline16 />
|
||||
</button>
|
||||
<button type="button" className={css.iconBtn} disabled={pending} onClick={() => { void runAction(onClear) }} title={t('action.clear')} aria-label={t('action.clear')}>
|
||||
<button type="button" className={css.iconBtn} disabled={pending} onClick={() => { void handleClear(goal.id) }} title={t('action.clear')} aria-label={t('action.clear')}>
|
||||
<IconTrashOutline16 />
|
||||
</button>
|
||||
</div>
|
||||
|
||||
@@ -3,13 +3,13 @@
|
||||
// inline edit form, and resume/clear icon actions — driven purely through
|
||||
// props, no wire. Loading, absent, and complete goals render nothing.
|
||||
|
||||
import { cleanup, fireEvent, render, screen, waitFor } from '@testing-library/react'
|
||||
import { act, cleanup, fireEvent, render, screen, waitFor } from '@testing-library/react'
|
||||
import { afterEach, describe, expect, it, vi } from 'vitest'
|
||||
import type { GoalSnapshot } from '@deepseek-ai/dsh-goal/client'
|
||||
import { makeTranslate } from '@deepseek-ai/dsh-client-test-runtime'
|
||||
import { zh as commonZh } from '@deepseek-ai/dsh-client-locale/src/locales/zh.ts'
|
||||
import { GoalBar } from '../src/client/GoalBar.tsx'
|
||||
import type { GoalBarActions } from '../src/client/slots.ts'
|
||||
import type { GoalActionResult, GoalBarActions } from '../src/client/slots.ts'
|
||||
import { zh } from '../src/client/locales.ts'
|
||||
|
||||
// The framework-injected t seat, stubbed over the zh dictionaries (the default locale).
|
||||
@@ -61,6 +61,27 @@ describe('GoalBar', () => {
|
||||
expect(actions.onClear).toHaveBeenCalledTimes(1)
|
||||
})
|
||||
|
||||
it('single-flights rapid clear clicks and hides the committed goal before its projection catches up', async () => {
|
||||
const actions = makeActions()
|
||||
let resolveClear!: (result: GoalActionResult) => void
|
||||
actions.onClear.mockImplementation(() => new Promise((resolve) => { resolveClear = resolve }))
|
||||
const { container, rerender } = render(<GoalBar goal={makeGoal()} {...actions} t={t} />)
|
||||
const clear = screen.getByRole<HTMLButtonElement>('button', { name: '清除目标' })
|
||||
|
||||
act(() => {
|
||||
clear.click()
|
||||
clear.click()
|
||||
})
|
||||
expect(actions.onClear).toHaveBeenCalledTimes(1)
|
||||
expect(clear.disabled).toBe(true)
|
||||
|
||||
await act(async () => { resolveClear({ ok: true }) })
|
||||
expect(container.firstChild).toBeNull()
|
||||
|
||||
rerender(<GoalBar goal={makeGoal({ id: 'g2' as GoalSnapshot['id'], objective: 'Next goal' })} {...actions} t={t} />)
|
||||
expect(screen.getByText('Next goal')).toBeTruthy()
|
||||
})
|
||||
|
||||
it('edit swaps the strip for a prefilled form; Enter saves, empty stays disabled', async () => {
|
||||
const actions = makeActions()
|
||||
render(<GoalBar goal={makeGoal()} {...actions} t={t} />)
|
||||
@@ -180,5 +201,7 @@ describe('GoalBar', () => {
|
||||
fireEvent.click(screen.getByRole('button', { name: '清除目标' }))
|
||||
expect((await screen.findByRole('alert')).textContent).toBe('clear failed (agent-busy)')
|
||||
expect(screen.getByText('Ship the redesign')).toBeTruthy()
|
||||
fireEvent.click(screen.getByRole('button', { name: '清除目标' }))
|
||||
await waitFor(() => { expect(actions.onClear).toHaveBeenCalledTimes(2) })
|
||||
})
|
||||
})
|
||||
|
||||
@@ -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/app-boot/README.md
|
||||
README.md: ebd8e0842b934f6887e3c122e781c1d0f13bb5d3
|
||||
README.zh.md: ccd897d48178482aa74d0eb73505e26ec3a08d6c
|
||||
README.md: efc8c42e192a02ecf37f8ea1356aa22261c70d0e
|
||||
README.zh.md: 927d6d1fb493c404fcdbe14f1c668b1743412ea5
|
||||
|
||||
@@ -15,7 +15,7 @@ Shared boot glue for the app bins ([`dsh`](../../../apps/cli/README.md), [`dsh-c
|
||||
| `loadOverlayPatches(binName, file)` | Parse a required patch-list file with the same shape as personal config; read or parse failures throw a labelled error |
|
||||
| `boot(binName, absoluteConfigPath, patches?, prepare?)` | Create the root context, expose `dshHomePath(...segments)` to Loader `!!js` config expressions, install Loader, run optional host preparation before config-tree entries mount (`prepare` may use Loader and provide launcher-owned context slots such as [`MAIN_SESSION_ID_KEY`](../tui/README.md)), then mount and await the include tree, assert entries loaded and activated, and return the root context |
|
||||
| `renderConfigDump(binName, absoluteConfigPath, layers, warn?)` | Compose the base config and labeled overlay layers offline — the include's own parser and patch algorithm (`entryListSchema`/`applyEntryPatches`), so the result equals what `boot()` mounts — and render YAML with `!!js` expressions verbatim; each run of same-provenance rows is preceded by a `# ==` comment naming the contributing file and the layers that patched it, keeping the output one loadable document; a patch matching no row goes to `warn` with its layer label (default: one stderr line), read/parse/shape failures throw |
|
||||
| `addHarnessSourceSection(ctx, sourceRoot)` | Add a global `harness:source` prompt section (ordered just after the harness identity, before the persona) telling the agent the on-disk path to its own source checkout; a no-op returning `undefined` when the booted tree has no `systemPrompt` service. The section is registered against that service's fiber, so a dev HMR reload of the system prompt drops it until the next boot |
|
||||
| `addHarnessSourceSection(ctx, sourceRoot)` | Add a global `harness:source` prompt section (ordered just after the harness identity, before the persona) telling the agent the on-disk path to the DSH implementation checkout while warning it not to infer the current working directory from that path and to use `pwd` instead; a no-op returning `undefined` when the booted tree has no `systemPrompt` service. The section is registered against that service's fiber, so a dev HMR reload of the system prompt drops it until the next boot |
|
||||
| `HARNESS_SOURCE_SECTION` | The `'harness:source'` section name `addHarnessSourceSection` registers under |
|
||||
|
||||
Two Loader failure classes require separate guards because tree settlement propagates neither to its caller. A failed plugin import leaves a fiber-less entry that `assertEntriesLoaded` turns into a `boot()` rejection naming every unresolved plugin. A plugin callback or config failure leaves a failed fiber because `loader.await()` settles lifecycle tasks without propagating that error; `assertEntriesActivated` awaits the fiber explicitly and includes its original stack in the startup rejection. Before throwing, the audit marks those exact rejection reasons through one process checkpoint so `installFailLoud` coalesces Loader's duplicate notification while every unrelated unhandled rejection remains fatal.
|
||||
|
||||
@@ -15,7 +15,7 @@
|
||||
| `loadOverlayPatches(binName, file)` | 解析一份必需的 patch 列表文件，其形状与个人配置相同；读取或解析失败时抛出带标签的错误 |
|
||||
| `boot(binName, absoluteConfigPath, patches?, prepare?)` | 创建根上下文，向 Loader `!!js` 配置表达式暴露 `dshHomePath(...segments)` 并安装 Loader，在配置树条目挂载前执行可选的宿主准备操作（`prepare` 可以使用 Loader，也可以提供由启动器拥有的上下文插槽，例如 [`MAIN_SESSION_ID_KEY`](../tui/README.md)），再挂载并等待 include 树结算，断言所有条目均已加载并激活，最后返回根上下文 |
|
||||
| `renderConfigDump(binName, absoluteConfigPath, layers, warn?)` | 离线合成基础配置与带标签的覆盖层——使用 include 自己的解析器和补丁算法（`entryListSchema`/`applyEntryPatches`），因此结果与 `boot()` 挂载的内容一致——并渲染为 YAML，`!!js` 表达式原样保留；每段来源相同的连续行之前都有一条 `# ==` 注释，标明贡献该段的文件以及修补过它的层，输出仍是一份可加载的文档；未匹配到行的补丁连同其层标签交给 `warn`（默认：一行 stderr），读取／解析／形状失败则抛出 |
|
||||
| `addHarnessSourceSection(ctx, sourceRoot)` | 添加全局 `harness:source` 提示词段落（顺序紧随 harness 身份、位于 persona 之前），告知 agent（智能体）自身源代码 checkout 的磁盘路径；如果已启动树没有此项服务，则不执行操作并返回 `undefined`。这里的服务是 `systemPrompt`；该段落注册到它的 fiber，因此开发环境 HMR（热模块替换）重新加载系统提示词后，它会消失直至下次启动 |
|
||||
| `addHarnessSourceSection(ctx, sourceRoot)` | 添加全局 `harness:source` 提示词段落（顺序紧随 harness 身份、位于 persona 之前），告知 agent（智能体）DSH 实现代码 checkout 的磁盘路径，同时提醒它不得据此推断当前工作目录，而应使用 `pwd`；如果已启动树没有此项服务，则不执行操作并返回 `undefined`。这里的服务是 `systemPrompt`；该段落注册到它的 fiber，因此开发环境 HMR（热模块替换）重新加载系统提示词后，它会消失直至下次启动 |
|
||||
| `HARNESS_SOURCE_SECTION` | `'harness:source'` 段落名称，供 `addHarnessSourceSection` 注册使用 |
|
||||
|
||||
Loader 树结算不会向调用方传播两类故障，因此需要分别保护。插件导入失败会留下没有 fiber 的配置项，`assertEntriesLoaded` 将其转换为 `boot()` rejection，并列出每个未解析插件。插件回调或配置失败则会留下失败的 fiber，因为 `loader.await()` 只结算生命周期任务，不传播该错误；`assertEntriesActivated` 会显式等待该 fiber，并把原始错误堆栈写入启动 rejection。抛出错误前，审计会通过一个进程级检查点标记这些 rejection 的确切原因，从而让 `installFailLoud` 将 Loader 的重复通知合并为一次，而所有无关的未处理 rejection 仍然致命。
|
||||
|
||||
@@ -480,11 +480,11 @@ export async function boot(
|
||||
export const HARNESS_SOURCE_SECTION = 'harness:source'
|
||||
|
||||
/**
|
||||
* Add a global prompt section naming the on-disk path to the harness source
|
||||
* checkout the running bin was launched from, so the agent knows where its own
|
||||
* source lives (the self-referential `dsh-tool-cordis` toolset reads and edits
|
||||
* it). Call once on the settled boot context ({@link boot}); the section orders
|
||||
* just after the harness identity opener (`-100`) and before the deployment
|
||||
* Add a global prompt section naming the on-disk harness source checkout while
|
||||
* explicitly distinguishing it from the task workspace and current working
|
||||
* directory. The self-referential `dsh-tool-cordis` toolset reads and edits this
|
||||
* checkout. Call once on the settled boot context ({@link boot}); the section
|
||||
* orders just after the harness identity opener (`-100`) and before the deployment
|
||||
* persona (`0`). A booted tree with no `systemPrompt` service has no prompt to
|
||||
* augment, so this is then a no-op that returns `undefined`. The section is
|
||||
* registered against the `systemPrompt` service's fiber, so a dev HMR reload of
|
||||
@@ -499,6 +499,6 @@ export function addHarnessSourceSection(ctx: Context, sourceRoot: string): (() =
|
||||
return systemPrompt.section({
|
||||
name: HARNESS_SOURCE_SECTION,
|
||||
order: -99,
|
||||
text: `Your own source code is the checkout at ${sourceRoot}; you can read it there to learn how dsh works and how to extend it.`,
|
||||
text: `The DeepSeek Harness implementation checkout is at ${sourceRoot}. The checkout location and current working directory are separate values and may differ; never infer the working directory from this path. Use pwd to determine the current working directory. Use this checkout only to inspect or extend DSH itself.`,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -391,9 +391,9 @@ describe('boot', () => {
|
||||
|
||||
describe('addHarnessSourceSection', () => {
|
||||
const SOURCE_ROOT = `${sep}opt${sep}harness-src`
|
||||
const EXPECTED = `Your own source code is the checkout at ${SOURCE_ROOT}; you can read it there to learn how dsh works and how to extend it.`
|
||||
const EXPECTED = `The DeepSeek Harness implementation checkout is at ${SOURCE_ROOT}. The checkout location and current working directory are separate values and may differ; never infer the working directory from this path. Use pwd to determine the current working directory. Use this checkout only to inspect or extend DSH itself.`
|
||||
|
||||
it('adds the source path between the harness identity and the deployment persona', async () => {
|
||||
it('distinguishes the source path from the current workdir between identity and persona', async () => {
|
||||
const ctx = new Context()
|
||||
try {
|
||||
await ctx.plugin(SystemPrompt, { persona: 'You are a coding agent.' })
|
||||
|
||||
@@ -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: 20ad471faa707cce0e6f0ce4df2289a900f09b93
|
||||
README.zh.md: a7d918ba3239d3e6feaa2fb43181e4bcf33e1d89
|
||||
README.md: c81cac891403e5294c4456ce4d4048ecd74666ce
|
||||
README.zh.md: 01055619f4df460284564f0a1816de366d809e01
|
||||
|
||||
@@ -40,7 +40,7 @@ Selection repeats those checks and requires the current agent to be idle before
|
||||
|
||||
The exit line is launcher-owned, not configurable. A launcher provides `TUI_GOODBYE_MESSAGE_KEY` on the boot context — for the shipped `dsh`, the command that resumes this session — and exiting prints it verbatim after the terminal is released; absent, exiting prints nothing. Only the launcher knows how it was invoked, so only it can name a command that works. The TUI escapes terminal controls before rendering and never executes the text. A launcher that also supplies `MAIN_SESSION_ID_KEY` fixes which session the mounted app binds to, so resume survives any config-level patch.
|
||||
|
||||
A launcher can seed a fresh session's first turn by providing `INITIAL_SKILL_KEY` (the skill name) on the boot context; the TUI auto-invokes it exactly as a typed `/skill:<name>`, once the chat is live. The shipped `dsh migrate`/`dsh experimental-upgrade` set it and only for a fresh session, so a resumed session never re-invokes the skill; an unknown name is reported as a notice.
|
||||
A launcher can seed a fresh session's first turn by providing `INITIAL_SKILL_KEY` (the skill name) on the boot context; the TUI auto-invokes it exactly as a typed `/skill:<name>`, once the chat is live. The shipped `dsh migrate`/`dsh upgrade` set it and only for a fresh session, so a resumed session never re-invokes the skill; an unknown name is reported as a notice.
|
||||
|
||||
## Config
|
||||
|
||||
|
||||
@@ -40,7 +40,7 @@ Footer 将会话报告的用量汇总为 `↑<uncached input> ↓<output>`；任
|
||||
|
||||
退出时打印的行由启动器拥有，不可通过配置指定。启动器在启动上下文上提供 `TUI_GOODBYE_MESSAGE_KEY`（对于随附的 `dsh`，即恢复本会话的命令），释放终端后退出会原样打印它；未提供时退出不打印任何内容。只有启动器知道自己是如何被调用的，因此只有它能给出可用的命令。TUI 在渲染前会转义终端控制字符，且绝不执行该文本。若启动器同时提供 `MAIN_SESSION_ID_KEY`，则会固定已挂载应用绑定的会话，因此恢复功能不受配置层修补影响。
|
||||
|
||||
启动器可通过在启动上下文上提供 `INITIAL_SKILL_KEY`（skill 名称）来播种全新会话的首轮；聊天就绪后，TUI 会像用户手动键入 `/skill:<name>` 一样自动调用它。随附的 `dsh migrate`/`dsh experimental-upgrade` 会设置该键，且仅对全新会话设置，因此恢复的会话绝不会重复调用该 skill；未知名称会以通知形式报告。
|
||||
启动器可通过在启动上下文上提供 `INITIAL_SKILL_KEY`（skill 名称）来播种全新会话的首轮；聊天就绪后，TUI 会像用户手动键入 `/skill:<name>` 一样自动调用它。随附的 `dsh migrate`/`dsh upgrade` 会设置该键，且仅对全新会话设置，因此恢复的会话绝不会重复调用该 skill；未知名称会以通知形式报告。
|
||||
|
||||
## 配置
|
||||
|
||||
|
||||
@@ -122,7 +122,7 @@ export interface Config extends TuiConfig {
|
||||
/**
|
||||
* Skill name auto-invoked as this session's first user turn, exactly as if
|
||||
* the user typed `/skill:<name>`. Set only by a launcher for a fresh
|
||||
* skill-guided session (`dsh migrate`/`dsh experimental-upgrade`); absent
|
||||
* skill-guided session (`dsh migrate`/`dsh upgrade`); absent
|
||||
* leaves the first turn to the user.
|
||||
*/
|
||||
initialSkill?: string
|
||||
|
||||
@@ -227,7 +227,7 @@ export const TUI_GOODBYE_MESSAGE_KEY = 'tuiGoodbyeMessage'
|
||||
/**
|
||||
* Context key a launcher sets before any Loader entry mounts
|
||||
* (`ctx.provide(INITIAL_SKILL_KEY, name)`) to seed a fresh session's first user
|
||||
* turn with `/skill:<name>` — the `dsh migrate`/`dsh experimental-upgrade`
|
||||
* turn with `/skill:<name>` — the `dsh migrate`/`dsh upgrade`
|
||||
* guided-session entry. The launcher sets it only when minting a fresh session,
|
||||
* so it never re-fires on a resumed one. Absent leaves the first turn to the user.
|
||||
*/
|
||||
@@ -1690,7 +1690,7 @@ export function createTuiChat(
|
||||
})
|
||||
startBannerReveal()
|
||||
|
||||
// A launcher-seeded first turn (`dsh migrate`/`dsh experimental-upgrade`):
|
||||
// A launcher-seeded first turn (`dsh migrate`/`dsh upgrade`):
|
||||
// invoke the named skill exactly as a typed `/skill:<name>` would, once the
|
||||
// chat is live and the agent is idle. The launcher sets this only for a fresh
|
||||
// session, so there is no prior turn to collide with; invokeSkill reports an
|
||||
|
||||
Reference in New Issue
Block a user