Merge branch 'master' of https://github.com/deepseek-harness/deepseek-harness into xtr/react-loop-simplification

# Conflicts:
#	.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml
#	docs/architecture.i18n.yaml
#	docs/cookbook/extension-cookbook.i18n.yaml
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/core.i18n.yaml
#	docs/core-data-structures/core.md
#	docs/core-data-structures/core.zh.md
#	docs/core-data-structures/llm-streaming.i18n.yaml
#	docs/core-data-structures/llm-streaming.md
#	docs/core-data-structures/llm-streaming.zh.md
#	docs/core-data-structures/session.i18n.yaml
#	docs/event-producer-consumer.md
#	docs/persistence-catalog.md
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/core/agent-loop/README.i18n.yaml
#	packages/core/agent-loop/src/agent.ts
#	packages/core/agent/README.i18n.yaml
#	packages/core/session/README.i18n.yaml
#	packages/core/session/src/types.ts
#	packages/llm/llm/README.i18n.yaml
#	packages/llm/llm/README.md
#	packages/llm/llm/README.zh.md
#	packages/llm/llm/src/index.ts
#	packages/llm/llm/tests/service.spec.ts
#	packages/sdk/sdk-client/README.i18n.yaml
#	packages/sdk/sdk-protocol/README.i18n.yaml
#	packages/sdk/sdk-protocol/README.md
#	packages/sdk/sdk-protocol/README.zh.md
#	packages/subagent/subagent-dsh-sdk/README.i18n.yaml
#	packages/ui/jsonrpc/README.i18n.yaml
#	packages/ui/jsonrpc/README.md
#	packages/ui/jsonrpc/README.zh.md
#	packages/ui/tui/src/index.ts
#	python/sdk/README.i18n.yaml
#	scripts/gen-cordis-catalog.ts
This commit is contained in:
_Kerman
2026-07-31 10:16:14 +08:00
1106 changed files with 33236 additions and 7168 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/ui/app-boot/README.md
README.md: 0282d3e9559d55c3fe5b07df133747750c06ebad
README.zh.md: b7121bbd288cd6e3f9ef2301de6018ceb380eb06
README.md: 1beffd6fbff2b84202683b010cd104f7c84297c7
README.zh.md: d9ce9774b9b492a98556bbd9aa4564b711dbe40e

View File

@@ -10,9 +10,10 @@ Shared boot glue for the app bins ([`dsh`](../../../apps/cli/README.md), [`dsh-c
| `loadEnv(binName, dir?, warn?)` | Load the gitignored `.env` (Node `process.loadEnvFile`); absent file is fine, an unloadable one warns a single labelled line (default: stderr) |
| `installFailLoud(binName, proc?)` | Turn a post-`boot()` unhandled Loader rejection into one labelled stderr line + `exit(1)`; returns the uninstaller (for tests) |
| `assertEntriesLoaded(ctx, binName)` | Throw when a settled tree holds an enabled entry with no fiber, reporting every unresolved plugin name as a Cordis startup failure |
| `assertEntriesActive(ctx, binName)` | Throw when a settled enabled fiber is not ACTIVE, including missing injected services for PENDING entries |
| `loadPersonalPatches(binName, dir?)` | Parse the optional `config.yaml` in the Harness home (default [`resolveDshHome()`](../../util/paths/README.md): `$DSH_HOME`, else `~/.dsh`) — a top-level YAML array of include `PatchOptions` (id-targeted config overrides, `insert` lists, `!!js` allowed); absent file → `undefined`, an unreadable/unparsable/non-array file throws |
| `boot(binName, absoluteConfigPath, patches?, prepare?)` | Create the root context, run optional host preparation before plugins mount (e.g. `ctx.provide(RESUME_SESSION_ID_KEY, id)`), then mount the Loader/include tree, await it, assert entries loaded, and return the root context |
| `RESUME_SESSION_ID_KEY` | Context key a bin sets through `boot`'s `prepare` hook to hand a resume session id to the booted config; the config reads it as the bare identifier `resumeSessionId` in a `!!js` expression, so resuming needs no environment variable |
| `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, 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 ACTIVE, and return the root context |
| `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 |
| `HARNESS_SOURCE_SECTION` | The `'harness:source'` section name `addHarnessSourceSection` registers under |
@@ -24,10 +25,10 @@ This package carries no loader hooks and no dev-mode surface. The [`dsh` app](..
## Personal config
A developer's machine-local preferences live outside every repository in the Harness home (default `~/.dsh`, overridable via `$DSH_HOME`; the single root [`resolveDshHome`](../../util/paths/README.md) resolves), consumed by the `dsh` CLI's TUI surface ([`apps/cli`](../../../apps/cli/README.md)); the demo bins boot their committed trees verbatim. Two optional files:
A developer's machine-local preferences live outside every repository in the Harness home (default `~/.dsh`, overridable via `$DSH_HOME`; the single root [`resolveDshHome`](../../util/paths/README.md) resolves), consumed by the official `dsh` surfaces ([`apps/cli`](../../../apps/cli/README.md)); the demo bins boot their committed trees verbatim. Two optional files:
- **`.env`** — loaded after the invoking directory's `.env`; `process.loadEnvFile` never overrides, so precedence is ambient environment > project `.env` > personal `.env`.
- **`config.yaml`** — loader overlay patches applied over the shipped default config, with the same semantics as an include entry's `patches` (the committed Code Mode overlay is the template): an id-targeted patch replaces the named entry's whole `config` (restate unchanged fields), `insert` adds entries, and `!!js` expressions interpolate at mount — so a personal `apiKey` can reference the personal `.env`. A patch naming an entry id absent from the booted tree is skipped with a loader warning. An empty or comments-only file throws (it parses to nothing, not to a list); disable the overlay with `[]` or by deleting the file.
- **`.env`** — the credential store of [`dsh-credentials-local`](../../credentials/credentials-local/README.md), read by that provider alone. No surface hoists it into `process.env`: doing so would make every stored key look like a read-only launch override on the next run, blocking rotation from the TUI and the web page. The environment layers are the ambient one and the invoking directory's `.env` (loaded by the bin; `process.loadEnvFile` never overrides), and a composition without the credential provider keeps resolving keys from those alone.
- **`config.yaml`** — loader overlay patches applied over the shipped default config, with the same semantics as the shipped surface overlays: an id-targeted patch replaces the named entry's whole `config` (restate unchanged fields), `insert` adds entries, and `!!js` expressions interpolate at mount. A patch naming an entry id absent from the booted tree is a silent no-op. An empty or comments-only file throws (it parses to nothing, not to a list); disable the overlay with `[]` or by deleting the file.
Subprocess test launchers point `DSH_HOME` at an isolated per-test directory so a developer's personal overlay can never leak into fixtures.
@@ -45,4 +46,3 @@ No direct invalidation from `boot()`; a consumer that calls `addHarnessSourceSec
- **Snapshot replay swapping is basename-specific** — only a config ending in `cordis.yml` or `cordis.yaml` maps to the sibling `cordis.snapshot.yml`; custom config names require caller-managed selection.
- **Environment loading is cwd-scoped and optional** — the helper loads one `.env` file and warns on failure; it does not search parents, merge profiles, or validate required variables.
- **Personal config is patch-shaped** — an id-targeted patch replaces the entry's whole `config` rather than deep-merging, so a personal override restates the base fields it keeps.
- **Personal patches see only the booted file's own entries** — an overlay leaf that reaches its base through a nested include entry (the Code Mode configs) resolves personal patch ids against the overlay's top-level entries, not the included subtree.

View File

@@ -10,9 +10,10 @@
| `loadEnv(binName, dir?, warn?)` | 加载已被 git 忽略的 `.env`(Node `process.loadEnvFile`);文件不存在不影响启动,文件无法加载时输出一行带标签的警告(默认写入 stderr) |
| `installFailLoud(binName, proc?)` | 将 `boot()` 之后未处理的 Loader rejection 转换为一行带标签的 stderr 消息并执行 `exit(1)`;返回卸载函数(供测试使用) |
| `assertEntriesLoaded(ctx, binName)` | 树结算后,如果其中存在已启用但没有 fiber 的条目,则抛出异常,并以 Cordis 启动故障的形式报告每个未解析插件的名称 |
| `assertEntriesActive(ctx, binName)` | 树结算后,如果已启用的 fiber 未处于 ACTIVE 状态,则抛出异常;对于 PENDING 条目还会列出缺失的注入服务 |
| `loadPersonalPatches(binName, dir?)` | 解析 Harness home 中可选的 `config.yaml`(默认使用 [`resolveDshHome()`](../../util/paths/README.md):先取 `$DSH_HOME`,否则取 `~/.dsh`):其顶层是一个 YAML 数组,内容为 include 的 `PatchOptions`(按 id 定位的配置覆盖、`insert` 列表,允许 `!!js`);文件不存在时返回 `undefined`,文件不可读、不可解析或内容不是数组时抛出异常 |
| `boot(binName, absoluteConfigPath, patches?, prepare?)` | 创建根上下文,在插件挂载前执行可选的宿主准备操作(例如 `ctx.provide(RESUME_SESSION_ID_KEY, id)`),再挂载 Loader/include 树并等待其结算,断言所有条目均已加载,最后返回根上下文 |
| `RESUME_SESSION_ID_KEY` | bin 通过 `boot` 的 `prepare` 钩子设置的上下文键,用于把要恢复的会话 id 交给已启动配置;配置以裸标识符 `resumeSessionId` 在 `!!js` 表达式中读取它,因此恢复操作无需环境变量 |
| `loadOverlayPatches(binName, file)` | 解析一份必需的 patch 列表文件,其形状与个人配置相同;读取或解析失败时抛出带标签的错误 |
| `boot(binName, absoluteConfigPath, patches?, prepare?)` | 创建根上下文并安装 Loader,在配置树条目挂载前执行可选的宿主准备操作(`prepare` 可以使用 Loader,也可以提供由启动器拥有的上下文插槽,例如 [`MAIN_SESSION_ID_KEY`](../tui/README.md)),再挂载并等待 include 树结算,断言所有条目均已加载且处于 ACTIVE 状态,最后返回根上下文 |
| `addHarnessSourceSection(ctx, sourceRoot)` | 添加全局 `harness:source` 提示词段落(顺序紧随 harness 身份、位于 persona 之前),告知 agent(智能体)自身源代码 checkout 的磁盘路径;如果已启动树没有此项服务,则不执行操作并返回 `undefined`。这里的服务是 `systemPrompt`;该段落注册到它的 fiber,因此开发环境 HMR(热模块替换)重新加载系统提示词后,它会消失直至下次启动 |
| `HARNESS_SOURCE_SECTION` | `'harness:source'` 段落名称,供 `addHarnessSourceSection` 注册使用 |
@@ -24,10 +25,10 @@
## 个人配置
开发者的机器本地偏好位于所有仓库之外的 Harness home 中(默认 `~/.dsh`,可由 `$DSH_HOME` 覆盖;统一由根级 [`resolveDshHome`](../../util/paths/README.md) 解析),并由 `dsh` CLI(命令行界面)的 TUI 界面([`apps/cli`](../../../apps/cli/README.md))使用;demo bin 会原样启动仓库中提交的树。这里有两个可选文件:
开发者的机器本地偏好位于所有仓库之外的 Harness home 中(默认 `~/.dsh`,可由 `$DSH_HOME` 覆盖;统一由根级 [`resolveDshHome`](../../util/paths/README.md) 解析),并由官方 `dsh` 界面([`apps/cli`](../../../apps/cli/README.md))使用;demo bin 会原样启动仓库中提交的树。这里有两个可选文件:
- **`.env`**:在调用目录的 `.env` 之后加载;`process.loadEnvFile` 从不覆盖已有值,因此优先级为环境中的值 > 项目 `.env` > 个人 `.env`。
- **`config.yaml`**:在发布的默认配置上应用 Loader overlay patch,语义与 include 条目的 `patches` 相同(以仓库提交的 Code Mode overlay 为模板):按 id 定位的 patch 会替换对应条目的整个 `config`(未改字段也要重述),`insert` 会添加条目,`!!js` 表达式则在挂载时插值,因此个人 `apiKey` 可以引用个人 `.env`。如果 patch 指定的条目 id 不在已启动树中,Loader 会发出警告并跳过。空文件或仅含注释的文件会抛出异常(其解析结果为空,而不是列表);如需禁用 overlay,请使用 `[]` 或删除该文件。
- **`.env`**:[`dsh-credentials-local`](../../credentials/credentials-local/README.md) 的凭据存储,只由该 provider 读取。没有任何表层会把它提升进 `process.env`:那样做会让每个已存密钥在下次运行时看起来都像只读的启动时覆盖,从而阻断从 TUI 与 Web 页面轮换密钥。环境层次由环境中的值与调用目录的 `.env` 构成(由 bin 加载;`process.loadEnvFile` 从不覆盖已有值),没有凭据 provider 的组合仍然只从这两者解析密钥。
- **`config.yaml`**:在发布的默认配置上应用 Loader overlay patch,语义与交付的 surface overlay 相同:按 id 定位的 patch 会替换对应条目的整个 `config`(未改字段也要重述),`insert` 会添加条目,`!!js` 表达式则在挂载时插值。如果 patch 指定的条目 id 不在已启动树中,则静默不执行任何操作。空文件或仅含注释的文件会抛出异常(其解析结果为空,而不是列表);如需禁用 overlay,请使用 `[]` 或删除该文件。
子进程测试 launcher 会把 `DSH_HOME` 指向逐测试隔离的目录,确保开发者的个人 overlay 不会泄漏到 fixture(测试前置数据)中。
@@ -45,4 +46,3 @@
- **快照回放替换仅识别特定 basename**:只有以 `cordis.yml` 或 `cordis.yaml` 结尾的配置会映射到同级 `cordis.snapshot.yml`;自定义配置名称需要调用方自行选择。
- **环境加载局限于 cwd 且为可选操作**:helper 只加载一个 `.env` 文件,并在失败时发出警告;它不会搜索父目录、合并 profile 或验证必需变量。
- **个人配置采用 patch 形式**:按 id 定位的 patch 会替换条目的整个 `config`,而不是深度合并,因此个人覆盖必须重述需要保留的基础字段。
- **个人 patch 只能看到已启动文件自身的条目**:如果 overlay 叶子通过嵌套 include 条目访问其基础配置(例如 Code Mode 配置),个人 patch id 只会在 overlay 的顶层条目中解析,不会进入被 include 的子树。

View File

@@ -10,7 +10,7 @@ import { pathToFileURL } from 'node:url'
import { readFileSync } from 'node:fs'
import { basename, dirname, join, resolve } from 'node:path'
import * as yaml from 'js-yaml'
import { Context } from 'cordis'
import { Context, type FiberState } from 'cordis'
import Loader from '@cordisjs/plugin-loader'
import Include, { type PatchOptions } from '@cordisjs/plugin-include'
import { resolveDshHome } from '@deepseek-ai/dsh-paths'
@@ -94,20 +94,56 @@ export function loadPersonalPatches(
if ((error as NodeJS.ErrnoException | null)?.code === 'ENOENT') return undefined
throw new Error(`${binName}: failed to read personal patches ${file}: ${String(error)}`)
}
return parsePatchList(binName, file, content, 'personal patches')
}
/**
* Load a required overlay patch list: a surface overlay (`tui.cordis.yml`) or a
* `--config <path>` overlay applied over the shared base. Same file format as
* {@link loadPersonalPatches}, but a missing file throws, because the caller
* named this file — its absence is a misconfiguration, not "no overlay".
* @param binName - the diagnostic prefix on the thrown error.
* @param file - absolute path of the overlay file.
* @returns the parsed patch list.
*/
export function loadOverlayPatches(binName: string, file: string): PatchOptions[] {
let content: string
try {
content = readFileSync(file, 'utf8')
} catch (error) {
throw new Error(`${binName}: failed to read overlay ${file}: ${String(error)}`)
}
return parsePatchList(binName, file, content, 'overlay')
}
/**
* Parse one loader patch list: a top-level YAML array of
* `@cordisjs/plugin-include` `PatchOptions` (id-targeted config overrides and
* `insert` lists, `!!js` expressions allowed). Every shape failure throws,
* because a patch file that cannot be applied at all is a misconfiguration; a
* single patch whose target row is absent stays a per-entry Loader warning, so
* one overlay shared across surfaces does not have to match every tree.
* @param binName - the diagnostic prefix on the thrown error.
* @param file - the source path, quoted in errors.
* @param content - the file's text.
* @param label - what to call this list in errors (`personal patches`, `overlay`).
* @returns the parsed patch list.
*/
function parsePatchList(
binName: string, file: string, content: string, label: string,
): PatchOptions[] {
let parsed: unknown
try {
parsed = yaml.load(content, { schema: personalPatchesSchema })
} catch (error) {
throw new Error(`${binName}: failed to parse personal patches ${file}: ${String(error)}`)
throw new Error(`${binName}: failed to parse ${label} ${file}: ${String(error)}`)
}
if (!Array.isArray(parsed)) {
throw new Error(`${binName}: personal patches ${file} must be a top-level YAML array of loader patch entries`)
throw new Error(`${binName}: ${label} ${file} must be a top-level YAML array of loader patch entries`)
}
// A present personal config that cannot apply is a misconfiguration and must
// fail loud here — the include only warns per entry at mount.
parsed.forEach((entry, index) => {
if (typeof entry !== 'object' || entry === null || Array.isArray(entry)) {
throw new Error(`${binName}: personal patches entry ${index + 1} in ${file} must be a mapping (a loader patch entry)`)
throw new Error(`${binName}: ${label} entry ${index + 1} in ${file} must be a mapping (a loader patch entry)`)
}
})
return parsed as PatchOptions[]
@@ -156,16 +192,30 @@ export function assertEntriesLoaded(ctx: Context, binName: string): void {
}
}
/** Runtime mirrors for Cordis's erased const-enum fiber states. */
const FIBER_ACTIVE = 2 as FiberState.ACTIVE
const FIBER_PENDING = 0 as FiberState.PENDING
/**
* Context key a bin sets through {@link boot}'s `prepare` hook to hand a resume
* session id to the booted config: `ctx.provide(RESUME_SESSION_ID_KEY, id)`
* makes `id` readable as the bare identifier `resumeSessionId` in a config
* `!!js` expression. The value is the bin's already-parsed id (or `undefined`),
* so resuming a session needs no environment variable. A bin that never
* provides it leaves the identifier undeclared, so configs read it defensively
* (`typeof resumeSessionId === 'string' ? resumeSessionId : undefined`).
* Reject enabled Loader entries whose fibers did not reach ACTIVE after settle.
* @param ctx - The settled application root.
* @param binName - Diagnostic prefix.
*/
export const RESUME_SESSION_ID_KEY = 'resumeSessionId'
export function assertEntriesActive(ctx: Context, binName: string): void {
const failures: string[] = []
for (const entry of ctx.loader.entries()) {
if (entry.fiber === undefined || entry.disabled || entry.fiber.state === FIBER_ACTIVE) continue
if (entry.fiber.state === FIBER_PENDING) {
const missing = Object.keys(entry.fiber.inject).filter(service => ctx.get(service) === undefined)
failures.push(`${entry.options.name}: pending (waiting for service${missing.length === 1 ? '' : 's'}: ${missing.join(', ') || 'unknown'})`)
} else {
failures.push(`${entry.options.name}: fiber state ${String(entry.fiber.state)}`)
}
}
if (failures.length > 0) {
throw new Error(`${binName}: ${String(failures.length)} entr${failures.length === 1 ? 'y' : 'ies'} did not activate\n${failures.join('\n')}`)
}
}
/**
* Boot the Loader against `absoluteConfigPath` and return only after the whole
@@ -183,8 +233,9 @@ export const RESUME_SESSION_ID_KEY = 'resumeSessionId'
* (see {@link resolveConfigPath}).
* @param patches - optional overlay patches applied over the included tree
* (see {@link loadPersonalPatches}); an empty list mounts none.
* @param prepare - optional host setup run against the root context before any Loader entry mounts.
* @returns the root context once every entry has started.
* @param prepare - optional host setup run after Loader installation and before any config-tree entry mounts.
* @returns the root context once every entry has started, or as soon as a
* surface disposed the tree while startup was still in flight.
*/
export async function boot(
binName: string,
@@ -193,10 +244,10 @@ export async function boot(
prepare?: (ctx: Context) => Promise<void> | void,
): Promise<Context> {
const ctx = new Context()
await prepare?.(ctx)
ctx.baseUrl = pathToFileURL(dirname(absoluteConfigPath)).href + '/'
await ctx.plugin(Loader)
ctx.loader.builtins.include = Include
await prepare?.(ctx)
await ctx.loader.create({
name: 'cordis:include',
config: {
@@ -205,7 +256,15 @@ export async function boot(
},
})
await ctx.loader.await()
// A surface can finish and dispose the whole tree while that await is still
// pending: the TUI renders as soon as its own fiber starts, so an `/exit`
// typed before the last entry settles tears the context down under us. The
// Loader service goes with it, and both assertions below describe a live
// tree — reading `ctx.loader` here would throw a TypeError over an app that
// exited exactly as asked.
if (ctx.get('loader') === undefined) return ctx
assertEntriesLoaded(ctx, binName)
assertEntriesActive(ctx, binName)
return ctx
}

View File

@@ -5,8 +5,8 @@ import { describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import SystemPrompt, { renderPrompt } from '@deepseek-ai/dsh-system-prompt'
import {
addHarnessSourceSection, assertEntriesLoaded, boot, HARNESS_SOURCE_SECTION,
installFailLoud, loadEnv, resolveConfigPath, type FailLoudProcess,
addHarnessSourceSection, assertEntriesActive, assertEntriesLoaded, boot, HARNESS_SOURCE_SECTION,
installFailLoud, loadEnv, loadOverlayPatches, resolveConfigPath, type FailLoudProcess,
} from '../src/index.ts'
const NAME = 'dsh-test-bin'
@@ -157,6 +157,25 @@ describe('assertEntriesLoaded', () => {
})
})
describe('loadOverlayPatches', () => {
it('loads expressions and rejects missing, malformed, non-array, and non-mapping overlays', () => {
const dir = tmp()
const valid = join(dir, 'valid.yml')
writeFileSync(valid, '- id: target\n config:\n value: !!js process.env.VALUE\n')
expect(loadOverlayPatches(NAME, valid)).toEqual([{ id: 'target', config: { value: { __jsExpr: 'process.env.VALUE' } } }])
expect(() => loadOverlayPatches(NAME, join(dir, 'missing.yml'))).toThrow(`${NAME}: failed to read overlay`)
const malformed = join(dir, 'malformed.yml')
writeFileSync(malformed, ': bad')
expect(() => loadOverlayPatches(NAME, malformed)).toThrow(`${NAME}: failed to parse overlay`)
const mapping = join(dir, 'mapping.yml')
writeFileSync(mapping, 'id: target\n')
expect(() => loadOverlayPatches(NAME, mapping)).toThrow('must be a top-level YAML array')
const scalar = join(dir, 'scalar.yml')
writeFileSync(scalar, '- scalar\n')
expect(() => loadOverlayPatches(NAME, scalar)).toThrow('entry 1')
})
})
describe('boot', () => {
it('boots a leaf config through the real Loader and settles the tree', async () => {
const dir = tmp()
@@ -176,7 +195,11 @@ describe('boot', () => {
writeFileSync(join(dir, 'noop.mjs'), 'export const name = "noop"\nexport function apply() {}\n')
writeFileSync(join(dir, 'cordis.yml'), '- id: noop\n name: ./noop.mjs\n')
const prepared: Context[] = []
const ctx = await boot(NAME, join(dir, 'cordis.yml'), undefined, (hostCtx) => { prepared.push(hostCtx) })
const ctx = await boot(NAME, join(dir, 'cordis.yml'), undefined, (hostCtx) => {
expect(hostCtx.loader).toBeDefined()
expect([...hostCtx.loader.entries()]).toEqual([])
prepared.push(hostCtx)
})
try {
expect(prepared).toEqual([ctx])
} finally {
@@ -184,11 +207,57 @@ describe('boot', () => {
}
})
it('returns instead of asserting over a tree a surface disposed mid-startup', async () => {
// What a TUI `/exit` does (ui-tui's disposeRootAndExit): dispose the root
// fiber, which lands while boot() is still awaiting the Loader whenever the
// surface renders before the last entry settles. The Loader service goes
// with the tree, so reading it for the post-boot assertions would crash an
// app that exited exactly as the user asked.
const dir = tmp()
writeFileSync(join(dir, 'exiting.mjs'), [
'export const name = "exiting"',
'export function apply(ctx) {',
' void ctx.root.fiber.dispose()',
'}',
'',
].join('\n'))
writeFileSync(join(dir, 'cordis.yml'), '- id: exiting\n name: ./exiting.mjs\n')
const ctx = await boot(NAME, join(dir, 'cordis.yml'))
expect(ctx.get('loader')).toBeUndefined()
})
it('rejects (never exits 0 half-empty) when a config names a plugin that cannot be imported', async () => {
const dir = tmp()
writeFileSync(join(dir, 'cordis.yml'), '- id: ghost\n name: ./missing.mjs\n')
await expect(boot(NAME, join(dir, 'cordis.yml'))).rejects.toThrow(`${NAME}: plugin(s) failed to load: ./missing.mjs`)
})
it('rejects a settled tree with a pending inject and names every missing service', async () => {
const dir = tmp()
writeFileSync(join(dir, 'waiting.mjs'), "export const inject = ['alpha', 'beta']\nexport function apply() {}\n")
writeFileSync(join(dir, 'cordis.yml'), '- id: waiting\n name: ./waiting.mjs\n')
await expect(boot(NAME, join(dir, 'cordis.yml'))).rejects.toThrow('./waiting.mjs: pending (waiting for services: alpha, beta)')
})
it('uses singular diagnostics for one missing pending dependency', () => {
const ctx = {
loader: { entries: () => [{ disabled: false, options: { name: 'waiting' }, fiber: { state: 0, inject: { alpha: {} } } }] },
get: () => undefined,
} as unknown as Context
expect(() =>{ assertEntriesActive(ctx, NAME) }).toThrow('waiting: pending (waiting for service: alpha)')
})
it('reports unknown pending dependencies and unexpected fiber states', () => {
const entries = [
{ disabled: false, options: { name: 'unknown' }, fiber: { state: 0, inject: {} } },
{ disabled: false, options: { name: 'failed' }, fiber: { state: 3, inject: {} } },
]
const ctx = {
loader: { entries: () => entries },
get: () => undefined,
} as unknown as Context
expect(() =>{ assertEntriesActive(ctx, NAME) }).toThrow(`${NAME}: 2 entries did not activate\nunknown: pending (waiting for services: unknown)\nfailed: fiber state 3`)
})
})
describe('addHarnessSourceSection', () => {

View File

@@ -126,3 +126,52 @@ describe('include refresh with overlay patches', () => {
}
})
})
describe('include patches layered over one base', () => {
it('lets a later patch configure or disable a row an earlier patch inserted', async () => {
// The surface/`--config`/personal composition: `dsh` includes one shared
// base and applies each source as its own patch list at the SAME include
// level, because patches never cross an include boundary. A later layer
// must therefore be able to reach a row an earlier layer inserted —
// otherwise every surface-only row (the whole TUI front door) would be
// invisible to the user's `~/.dsh/config.yaml`.
const dir = mkdtempSync(join(tmpdir(), 'dsh-config-layered-'))
writeFileSync(join(dir, 'noop.mjs'), NOOP_PLUGIN)
writeFileSync(join(dir, 'base.yml'), '- id: shared\n name: ./noop.mjs\n config:\n value: base\n')
writeFileSync(join(dir, 'cordis.yml'), [
'- id: base',
" name: 'cordis:include'",
' config:',
' path: ./base.yml',
' patches:',
// Layer 1 (a surface overlay): patch a base row and add two of its own.
' - id: shared',
' config:',
' value: surface',
' - insert:',
' - id: surface-kept',
' name: ./noop.mjs',
' config:',
' value: surface-default',
' - id: surface-dropped',
' name: ./noop.mjs',
// Layer 2 (the user): reconfigure one inserted row and disable the other.
' - id: surface-kept',
' config:',
' value: personal',
' - id: surface-dropped',
' disabled: true',
'',
].join('\n'))
const ctx = await boot(NAME, join(dir, 'cordis.yml'))
try {
expect(entryConfig(ctx, 'shared')).toEqual({ value: 'surface' })
expect(entryConfig(ctx, 'surface-kept')).toEqual({ value: 'personal' })
const dropped = [...ctx.loader.entries()].find(entry => entry.options.id === 'surface-dropped')
expect(dropped?.options.disabled).toBe(true)
expect(dropped?.fiber).toBeUndefined()
} finally {
await ctx.fiber.dispose()
}
})
})

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/ui/jsonrpc/README.md
README.md: 7eb0336a770397df280fbaf95a6ad88243d28944
README.zh.md: 993d227d464c460d2c1a3b309542a9c59d1fd18c
README.md: 9cd4876b52f9527745b27041eb2555408c73fabd
README.zh.md: f0b989658931132b118797526f3a3e0c98c6c19d

View File

@@ -6,7 +6,7 @@ The `jsonrpc` plugin serves newline-delimited JSON-RPC over stdio so out-of-proc
## Wiring
`inject: ['agents']`. The server gets or creates one agent per `sessionId`. It forwards subagent completions only when the service-snapshotted lifecycle `local` flag is true; provider names, child ids, and durable lineage never establish locality. A registered adapter wins, an unowned `deepseek` route mounts `dsh-llm-deepseek`, and any other unowned provider fails initialization. Other capabilities come from the surrounding `cordis.yml`.
`inject: ['agents']`. The server gets or creates one agent per `sessionId`. It forwards subagent completions only when the service-snapshotted lifecycle `local` flag is true; provider names, child ids, and durable lineage never establish locality. A registered adapter wins, an unowned `deepseek-official` route mounts `dsh-llm-deepseek`, and any other unowned provider fails initialization. Other capabilities come from the surrounding `cordis.yml`.
## Config
@@ -22,7 +22,7 @@ The plugin answers `shutdown`, flushes the response, disposes the root context s
## Wire notes
`initialize.serverInfo.name` is the wire-stable `deepseek-harness-sdk-runtime`. An optional positive `initialize.maxTokens` becomes the request output cap of each SDK-created agent and its in-process descendants; invalid values reject initialization, while omission sends no cap and preserves provider defaults. `session/prompt` queues one identified user message and immediately returns `{ messageId }`. The server streams every durable fact as `session.event` and every whole-agent lifecycle transition as `session.status`; it does not assign an assistant message or `turn/end` to that prompt. Independent requests may enqueue more work on the same session. Persistence roots and persona come from `cordis.yml`.
`initialize.serverInfo.name` is the wire-stable `deepseek-harness-sdk-runtime`. An optional positive `initialize.maxTokens` becomes the request output cap of each SDK-created agent and its in-process descendants; invalid values reject initialization, while omission sends no SDK cap and allows the selected adapter or provider route default to apply. `session/prompt` queues one identified user message and immediately returns `{ messageId }`. The server streams every durable fact as `session.event` and every whole-agent lifecycle transition as `session.status`; it does not assign an assistant message or `turn/end` to that prompt. Independent requests may enqueue more work on the same session. Persistence roots and persona come from `cordis.yml`.
## Model Experience

View File

@@ -6,7 +6,7 @@
## 组装
`inject: ['agents']`。服务器按 `sessionId` 获取或创建一个 agent。只有服务对生命周期建立快照时记录的 `local` 标志为 true,服务器才会转发 subagent 完成事件;提供方名称、子级 id 和持久化谱系均不能证明本地性。已注册的适配器优先;尚无适配器负责的 `deepseek` 路由会挂载 `dsh-llm-deepseek`,任何其他尚无适配器负责的提供方都会导致初始化失败。其他功能由外围 `cordis.yml` 提供。
`inject: ['agents']`。服务器按 `sessionId` 获取或创建一个 agent。只有服务对生命周期建立快照时记录的 `local` 标志为 true,服务器才会转发 subagent 完成事件;提供方名称、子级 id 和持久化谱系均不能证明本地性。已注册的适配器优先;尚无适配器负责的 `deepseek-official` 路由会挂载 `dsh-llm-deepseek`,任何其他尚无适配器负责的提供方都会导致初始化失败。其他功能由外围 `cordis.yml` 提供。
## 配置
@@ -22,7 +22,7 @@ Stdout 只承载 JSON-RPC 帧。部署不得组合 stdout logger;诊断应写
## 协议说明
`initialize.serverInfo.name` 的协议稳定值为 `deepseek-harness-sdk-runtime`。可选的正整数 `initialize.maxTokens` 会成为每个 SDK 创建的 agent 及其进程内后代的请求输出上限;非法值会使初始化失败,省略时则不发送上限并保留提供方默认值。`session/prompt` 将一条带标识的用户消息排入队列,并立即返回 `{ messageId }`。服务器将每个持久事实作为 `session.event` 流式发出,并将整个 agent 生命周期的每次状态转换作为 `session.status` 发出;它不会把某条助手消息或 `turn/end` 归属于该提示词。同一会话上的独立请求可以继续排入更多工作。持久化根目录和 persona 由 `cordis.yml` 提供。
`initialize.serverInfo.name` 的协议稳定值为 `deepseek-harness-sdk-runtime`。可选的正整数 `initialize.maxTokens` 会成为每个 SDK 创建的 agent 及其进程内后代的请求输出上限;非法值会使初始化失败,省略时则不发送 SDK 上限,并应用所选适配器或提供方路由的默认值。`session/prompt` 将一条带标识的用户消息排入队列,并立即返回 `{ messageId }`。服务器将每个持久事实作为 `session.event` 流式发出,并将整个 agent 生命周期的每次状态转换作为 `session.status` 发出;它不会把某条助手消息或 `turn/end` 归属于该提示词。同一会话上的独立请求可以继续排入更多工作。持久化根目录和 persona 由 `cordis.yml` 提供。
## 模型体验

View File

@@ -52,8 +52,8 @@ function successStatus(reason: string, options: HarnessSdkServerOptions): 'ok' |
*/
export class HarnessSdkServer {
private cwd = process.cwd()
private provider = 'deepseek'
private model = 'deepseek'
private provider = 'deepseek-official'
private model = 'deepseek-official'
private maxTokens: number | undefined
private llmFiber: { dispose(): Promise<void> } | undefined
private readonly sessions = new Map<string, SessionRecord>()
@@ -118,7 +118,7 @@ export class HarnessSdkServer {
this.model = params.model
this.maxTokens = params.maxTokens
if (!this.hasAdapterFor(this.provider)) {
if (this.provider !== 'deepseek') throw new Error(`no adapter registered for provider "${this.provider}"`)
if (this.provider !== 'deepseek-official') throw new Error(`no adapter registered for provider "${this.provider}"`)
this.llmFiber = await this.ctx.plugin(LlmDeepSeek, {})
}
return { serverInfo: { name: 'deepseek-harness-sdk-runtime', version: '0.0.1' } }

View File

@@ -155,7 +155,7 @@ describe('dsh-jsonrpc plugin apply', () => {
vi.stubEnv('DEEPSEEK_API_KEY', 'test-key')
const harness = await mountPlugin(storageDir)
try {
harness.send({ jsonrpc: '2.0', id: 'init-1', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'apply-model' } })
harness.send({ jsonrpc: '2.0', id: 'init-1', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek-official', model: 'apply-model' } })
const response = await harness.waitForFrame(frame => frame.id === 'init-1', 'initialize response')
expect(response).toEqual({
@@ -177,7 +177,7 @@ describe('dsh-jsonrpc plugin apply', () => {
vi.stubEnv('DEEPSEEK_BASE_URL', llmServer.url)
const harness = await mountPlugin(storageDir)
try {
harness.send({ jsonrpc: '2.0', id: 1, method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'dsagent-model' } })
harness.send({ jsonrpc: '2.0', id: 1, method: 'initialize', params: { cwd: storageDir, provider: 'deepseek-official', model: 'dsagent-model' } })
await harness.waitForFrame(frame => frame.id === 1, 'initialize response')
harness.send({
@@ -246,7 +246,7 @@ describe('dsh-jsonrpc plugin apply', () => {
expect(harness.events.filter(event => event.kind === 'root-disposed')).toHaveLength(1)
const before = harness.frames().length
harness.send({ jsonrpc: '2.0', id: 'after-exit', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'x' } })
harness.send({ jsonrpc: '2.0', id: 'after-exit', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek-official', model: 'x' } })
await settle()
expect(harness.frames().length).toBe(before)
} finally {
@@ -268,7 +268,7 @@ describe('dsh-jsonrpc plugin apply', () => {
expect(harness.outputErrors.map(error => error.message)).toEqual(['flush callback failed'])
const before = harness.frames().length
harness.send({ jsonrpc: '2.0', id: 'after-flush-failure', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'x' } })
harness.send({ jsonrpc: '2.0', id: 'after-flush-failure', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek-official', model: 'x' } })
await settle()
expect(harness.frames().length).toBe(before)
} finally {
@@ -293,7 +293,7 @@ describe('dsh-jsonrpc plugin apply', () => {
expect(harness.events.some(event => event.kind === 'root-disposed')).toBe(false)
const before = harness.frames().length
harness.send({ jsonrpc: '2.0', id: 'probe-2', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'x' } })
harness.send({ jsonrpc: '2.0', id: 'probe-2', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek-official', model: 'x' } })
await settle()
expect(harness.frames().length).toBe(before)
expect(harness.exits()).toEqual([])

View File

@@ -121,7 +121,7 @@ describe('HarnessSdkServer', () => {
const init = await server.handleRequest('initialize', {
cwd: storageDir,
provider: 'deepseek',
provider: 'deepseek-official',
model: 'dsagent-model',
maxTokens: 321,
}) as { serverInfo: { name: string } }
@@ -157,7 +157,7 @@ describe('HarnessSdkServer', () => {
const orphanHandle = await ctx.agents.create({
sessionId: SessionId('orphan-session'),
meta: { cwd: storageDir },
agentOptions: { provider: 'deepseek', model: 'dsagent-model' },
agentOptions: { provider: 'deepseek-official', model: 'dsagent-model' },
})
orphanHandle.agent.followup(createUserMessage({ content: [{ type: 'text', text: 'outside the sdk session map' }], source: { kind: 'user' } }))
await orphanHandle.agent.whenIdle()
@@ -304,7 +304,7 @@ describe('HarnessSdkServer', () => {
try {
const server = new HarnessSdkServer(ctx, new FakeTransport())
await server.initialize({ cwd: storageDir, provider: 'deepseek', model: 'plain-model' })
await server.initialize({ cwd: storageDir, provider: 'deepseek-official', model: 'plain-model' })
await server.prompt({
sessionId: 'plain',
contentBlocks: [{ type: 'text', text: 'hello' }],
@@ -328,20 +328,20 @@ describe('HarnessSdkServer', () => {
const parentHandle = await ctx.agents.create({
sessionId: SessionId('main'),
meta: { cwd: storageDir },
agentOptions: { provider: 'deepseek', model: 'deepseek' },
agentOptions: { provider: 'deepseek-official', model: 'deepseek-official' },
})
// A custom in-process provider may own its child at the provider/root
// scope while preserving durable parent lineage.
const handle = await ctx.agents.create({
sessionId: SessionId('child-session'),
meta: { cwd: storageDir, parentSession: SessionId('main') },
agentOptions: { provider: 'deepseek', model: 'deepseek' },
agentOptions: { provider: 'deepseek-official', model: 'deepseek-official' },
})
expect(ctx.agents.roots()).toContain(handle.agent)
const parentlessHandle = await parentHandle.agent.ctx.agents.create({
sessionId: SessionId('parentless-child-session'),
meta: { cwd: storageDir },
agentOptions: { model: 'deepseek' },
agentOptions: { model: 'deepseek-official' },
})
await settleSubagent(ctx, parentHandle.agent, {
provider: 'spawn',
@@ -398,12 +398,12 @@ describe('HarnessSdkServer', () => {
const parentHandle = await ctx.agents.create({
sessionId: SessionId('collision-parent'),
meta: { cwd: storageDir },
agentOptions: { model: 'deepseek' },
agentOptions: { model: 'deepseek-official' },
})
const collidingChild = await parentHandle.agent.ctx.agents.create({
sessionId: SessionId('remote-run-id'),
meta: { cwd: storageDir, parentSession: SessionId('collision-parent') },
agentOptions: { model: 'deepseek' },
agentOptions: { model: 'deepseek-official' },
})
await settleSubagent(ctx, parentHandle.agent, {
@@ -437,12 +437,12 @@ describe('HarnessSdkServer', () => {
const parentHandle = await ctx.agents.create({
sessionId: SessionId('continuation-parent'),
meta: { cwd: storageDir },
agentOptions: { model: 'deepseek' },
agentOptions: { model: 'deepseek-official' },
})
const childHandle = await parentHandle.agent.ctx.agents.create({
sessionId: SessionId('continuation-child'),
meta: { cwd: storageDir, parentSession: SessionId('continuation-parent') },
agentOptions: { model: 'deepseek' },
agentOptions: { model: 'deepseek-official' },
})
await settleSubagent(ctx, parentHandle.agent, {
@@ -482,12 +482,12 @@ describe('HarnessSdkServer', () => {
const oldParent = await ctx.agents.create({
sessionId: SessionId('old-parent'),
meta: { cwd: storageDir },
agentOptions: { model: 'deepseek' },
agentOptions: { model: 'deepseek-official' },
})
const oldChild = await oldParent.agent.ctx.agents.create({
sessionId: SessionId('reused-child'),
meta: { cwd: storageDir, parentSession: SessionId('old-parent') },
agentOptions: { model: 'deepseek' },
agentOptions: { model: 'deepseek-official' },
})
const first = Promise.withResolvers<SubagentResult>()
const sameLifetime = Promise.withResolvers<SubagentResult>()
@@ -523,12 +523,12 @@ describe('HarnessSdkServer', () => {
const newParent = await ctx.agents.create({
sessionId: SessionId('new-parent'),
meta: { cwd: storageDir },
agentOptions: { model: 'deepseek' },
agentOptions: { model: 'deepseek-official' },
})
const newChild = await newParent.agent.ctx.agents.create({
sessionId: SessionId('reused-child'),
meta: { cwd: storageDir, parentSession: SessionId('new-parent') },
agentOptions: { model: 'deepseek' },
agentOptions: { model: 'deepseek-official' },
})
currentLocalAgent = newChild.agent
const secondRun = await ctx.subagents.start('reused', {
@@ -581,12 +581,12 @@ describe('HarnessSdkServer', () => {
const parent = await ctx.agents.create({
sessionId: SessionId('provider-reuse-parent'),
meta: { cwd: storageDir },
agentOptions: { model: 'deepseek' },
agentOptions: { model: 'deepseek-official' },
})
const child = await parent.agent.ctx.agents.create({
sessionId: SessionId('provider-reuse-child'),
meta: { cwd: storageDir, parentSession: SessionId('provider-reuse-parent') },
agentOptions: { model: 'deepseek' },
agentOptions: { model: 'deepseek-official' },
})
const localResult = Promise.withResolvers<SubagentResult>()
const remoteResult = Promise.withResolvers<SubagentResult>()
@@ -674,18 +674,18 @@ describe('HarnessSdkServer', () => {
parentHandle = await ctx.agents.create({
sessionId: SessionId('fallback-parent'),
meta: { cwd: storageDir },
agentOptions: { provider: 'deepseek', model: 'deepseek' },
agentOptions: { provider: 'deepseek-official', model: 'deepseek-official' },
})
handle = await parentHandle.agent.ctx.agents.create({
sessionId: SessionId('fallback-child-session'),
meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') },
agentOptions: { provider: 'deepseek', model: 'deepseek' },
agentOptions: { provider: 'deepseek-official', model: 'deepseek-official' },
})
const fallbackChild = handle.agent
failedHandle = await parentHandle.agent.ctx.agents.create({
sessionId: SessionId('failed-child-session'),
meta: { cwd: storageDir },
agentOptions: { provider: 'deepseek', model: 'deepseek' },
agentOptions: { provider: 'deepseek-official', model: 'deepseek-official' },
})
const missedStartResult = Promise.withResolvers<SubagentResult>()
const disposeMissedStartProvider = ctx.subagents.registerProvider({
@@ -783,11 +783,11 @@ describe('HarnessSdkServer', () => {
const server = new HarnessSdkServer(ctx, new FakeTransport())
const inspect = server as unknown as { hasAdapterFor(provider: string): boolean }
expect(inspect.hasAdapterFor('deepseek')).toBe(true)
expect(inspect.hasAdapterFor('deepseek-official')).toBe(true)
expect(inspect.hasAdapterFor('missing-provider')).toBe(false)
await server.initialize({ cwd: storageDir, provider: 'deepseek', model: 'preinstalled-model' })
await server.initialize({ cwd: storageDir, provider: 'deepseek-official', model: 'preinstalled-model' })
expect(ctx.get('llm')?.listProviders().filter(provider => provider.id === 'deepseek')).toEqual([{ id: 'deepseek', name: 'DeepSeek' }])
expect(ctx.get('llm')?.listProviders().filter(provider => provider.id === 'deepseek-official')).toEqual([{ id: 'deepseek-official', name: 'DeepSeek' }])
await server.shutdown()
} finally {
await ctx.fiber.dispose()
@@ -806,7 +806,7 @@ describe('HarnessSdkServer', () => {
await expect(server.initialize({ cwd: storageDir, provider: 'private', model: 'new-model' }))
.rejects.toThrow('no adapter registered for provider "private"')
expect(ctx.get('llm')?.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }])
expect(ctx.get('llm')?.listProviders()).toEqual([{ id: 'deepseek-official', name: 'DeepSeek' }])
await server.shutdown()
} finally {
await ctx.fiber.dispose()
@@ -823,7 +823,7 @@ describe('HarnessSdkServer', () => {
const server = new HarnessSdkServer(ctx, new FakeTransport())
await expect(server.initialize({
cwd: storageDir,
provider: 'deepseek',
provider: 'deepseek-official',
model: 'model',
maxTokens,
})).rejects.toThrow('initialize maxTokens must be a positive safe integer')

View File

@@ -211,16 +211,19 @@ export class PermissionService extends Service {
name: 'permission',
description: 'Switch the permission preset (sandbox mode + approval policy)',
input: { hint: '<preset>' },
// No settlement text labels its value with this command's own name: a
// surface that renders `name · text` (the web command row) would
// otherwise read `permission · Permission preset: workspace-write.`
handler: ({ agent, rawInput }) => {
const name = rawInput.trim()
if (name === '') {
return { kind: 'success', text: `Current permission preset: ${this.current(agent.session.events)}. Available: ${this.names.join(', ')}.` }
return { kind: 'success', text: `current preset ${this.current(agent.session.events)} (available: ${this.names.join(', ')})` }
}
if (!this.names.includes(name)) {
return { kind: 'error', text: `unknown permission preset "${name}" (available: ${this.names.join(', ')})` }
return { kind: 'error', text: `unknown preset "${name}" (available: ${this.names.join(', ')})` }
}
this.set(agent.session, name)
return { kind: 'success', text: `Permission preset: ${name}.` }
return { kind: 'success', text: `preset ${name}` }
},
})
})

View File

@@ -89,7 +89,7 @@ describe('/permission command', () => {
const { ctx, session } = await harness()
const agent = await agentFor(ctx, session)
const execution = await ctx.commands.execute(agent, '/permission danger-full-access', new AbortController().signal)
expect(execution?.result).toEqual({ kind: 'success', text: 'Permission preset: danger-full-access.' })
expect(execution?.result).toEqual({ kind: 'success', text: 'preset danger-full-access' })
expect(ctx.permission.current(session.events)).toBe('danger-full-access')
const run = session.events.find(event => event.type === 'command/run')
expect(run?.data).toMatchObject({ name: 'permission', args: ' danger-full-access' })
@@ -101,7 +101,7 @@ describe('/permission command', () => {
const execution = await ctx.commands.execute(agent, '/permission', new AbortController().signal)
expect(execution?.result).toEqual({
kind: 'success',
text: 'Current permission preset: workspace-write. Available: workspace-write, danger-full-access.',
text: 'current preset workspace-write (available: workspace-write, danger-full-access)',
})
expect(session.events.filter(event => event.type === 'permission/preset')).toHaveLength(0)
})
@@ -110,7 +110,13 @@ describe('/permission command', () => {
const { ctx, session } = await harness()
const agent = await agentFor(ctx, session)
const execution = await ctx.commands.execute(agent, '/permission yolo', new AbortController().signal)
expect(execution?.result).toMatchObject({ kind: 'error' })
// The error text carries the same no-self-labelling rule as the success
// texts: `permission · unknown preset "yolo" (…)`, not `unknown permission
// preset`, which the row's own title already says.
expect(execution?.result).toEqual({
kind: 'error',
text: 'unknown preset "yolo" (available: workspace-write, danger-full-access)',
})
expect(session.events.filter(event => event.type !== 'command/run' && event.type !== 'command/done')).toHaveLength(0)
})
})

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/ui/tui/README.md
README.md: 99d76d21828bc6b1eb0220e11362885652b3cefd
README.zh.md: 71b3b0546fed70a89f34a2ca4eee423be5909afd
README.md: 63c888b1d51c02fa85a8f0cc1617874debd87c4e
README.zh.md: ca5efc9ae26a9833d271991f73a21c607d8fb09d

View File

@@ -12,7 +12,7 @@ This package owns interactive terminal presentation and input only. It injects `
After terminal startup succeeds, the package provides the terminal-local `ctx.tui` extension service. A plugin that injects it can call `openOverlay()` with a component factory and constrained layout options; the host exposes the viewport, semantic theme, display-text escaping, redraw, close, and a lifetime signal, but not the pi-tui tree, terminal, focus controller, or overlay handle. Plugin overlays, the model selector, and user questions share one FIFO modal queue. Each request is an effect of the calling plugin fiber, so unload removes queued work or closes visible work before cleanup settles; terminal shutdown unloads dependents before stopping pi-tui. Overlay state is not logged or replayed. Component code is trusted and may render ANSI styling, but must pass untrusted text through `host.display()`. The [interactive-extension Agent Note](../../../.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.md) owns the boundary and rejected alternatives.
The TUI rebuilds resumed history from the active session surface, renders Markdown responses and reasoning, applies each tool's `presentCall` / `presentResult` intent to terminal, diff, or generic cards, keeps the standing `todo/write` plan above the editor (cleared on the next `turn/start`), and presents `ctx.userInteraction` questions in a wide bottom-left keyboard panel with progress, numbered options, and aligned descriptions. The latest logged session title becomes the header subtitle, with `welcome` before a title exists, and the terminal window title becomes `<session title> — <configured title>`. A durable `llm/retry` event retracts the failed step's live chunks and renders the scheduled retry count, delay, and failure in the transcript; success, exhaustion, and cancellation then settle through ordinary session events. The footer totals each logged model step's usage once, including failed attempts, while treating committed-message usage as a fallback for logs without a usage chunk. Its idle view compares token-meter pressure with `ctx.llm.resolveModelInfo()` context for the current route, displays `context unknown` when the adapter has no capacity metadata, and also shows tool-card mode plus the current model and any explicitly selected reasoning effort; while the agent runs, an elapsed working indicator and `esc interrupt` replace that summary. Surface replacement events rebuild the transcript so compacted history does not reappear.
The TUI rebuilds resumed history from the append-origin session events, renders Markdown responses and reasoning, applies each tool's `presentCall` / `presentResult` intent to terminal, diff, or generic cards, keeps the standing `todo/write` plan above the editor (cleared on the next `turn/start`), and presents `ctx.userInteraction` questions in a wide bottom-left keyboard panel with progress, numbered options, and aligned descriptions. The latest logged session title becomes the header subtitle, with `welcome` before a title exists, and the terminal window title becomes `<session title> — <configured title>`. A durable `llm/retry` event retracts the failed step's live chunks and renders the scheduled retry count, delay, and failure in the transcript; success, exhaustion, and cancellation then settle through ordinary session events. The footer totals each logged model step's usage once, including failed attempts, while treating committed-message usage as a fallback for logs without a usage chunk. Its idle view compares token-meter pressure with `ctx.llm.resolveModelInfo()` context for the current route, displays `context unknown` when the adapter has no capacity metadata, and also shows tool-card mode plus the current model and any explicitly selected reasoning effort; while the agent runs, an elapsed working indicator and `esc interrupt` replace that summary. A surface replacement never rewrites the rendered transcript: the conversation it shadows stays readable, and a landed compaction checkpoint adds one dim `… earlier context was compacted …` marker at its log position, so the terminal reports where the model stopped seeing that history instead of erasing it. Model-only replacement copies — a pruned tool result, a regenerated assistant message — render nothing.
An embedding may provide `TuiRuntime.formatCwd` when its logical workspace label differs from the session's host directory. The override changes only the footer label; tools continue to use the session `cwd`.
@@ -75,7 +75,7 @@ A launcher can seed a fresh session's first turn by providing `INITIAL_SKILL_KEY
fileSearchExcludedDirectories: ['.git', 'node_modules', 'dist']
```
Startup fails before mounting when either process stream is not a TTY. The composing app must mount the TUI before its config-created agent so the front door can observe `agent-loop/config-start-failed`; a matching exact-session failure is written before fullscreen mode starts and exits with status 1 instead of leaving a blank terminal. Disposal stops extension admission, unloads the `ctx.tui` provider and its dependent plugins, aborts running commands, removes the TUI definitions, stops loaders, rejects pending questions, drains terminal input, restores terminal state, unregisters event listeners and the user-interaction provider, and never exits a replacement process during HMR.
Startup fails before mounting when either process stream is not a TTY. The composing app must mount the TUI before its config-created agent so the front door can observe `agent-loop/config-start-failed`; a matching exact-session failure is written before fullscreen mode starts and exits with status 1 instead of leaving a blank terminal. Disposal stops extension admission, unloads the `ctx.tui` provider and its dependent plugins, aborts running commands, removes the TUI definitions, stops loaders, rejects pending questions, drains terminal input, restores terminal state, unregisters event listeners and the user-interaction provider, and never exits a replacement process during HMR. A user exit disposes the application root so sibling resources close, then exits; a five-second fallback prevents one stuck disposer from trapping the process.
## Color

View File

@@ -12,7 +12,7 @@ DeepSeek Harness agent(智能体)的交互式终端入口,基于 [`@earend
终端成功启动后,本包会提供终端本地的 `ctx.tui` 扩展服务。注入该服务的插件可以使用组件工厂和受限布局选项调用 `openOverlay()`;宿主会公开 viewport、语义化主题、显示文本转义、重绘、关闭和生命周期信号,但不公开 pi-tui 树、终端、焦点控制器或 overlay 句柄。插件 overlay、模型选择器和用户问题共用一个 FIFO 模态队列。每个请求都是调用方插件 fiber 的 effect,因此卸载会移除排队工作,或在清理结算前关闭可见工作;终端关闭会先卸载依赖项,再停止 pi-tui。Overlay 状态不会记录或回放。组件代码受信任,可以渲染 ANSI 样式,但必须通过 `host.display()` 处理不受信任文本。[交互式扩展 Agent Note](../../../.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.md)持有该边界和未采用的替代方案。
TUI 从活跃会话表层重建已恢复历史,渲染 Markdown 响应与 reasoning,将每个工具的 `presentCall` / `presentResult` 意图应用到终端、diff 或通用卡片,把站立的 `todo/write` 计划保留在编辑器上方(下一个 `turn/start` 时清空),并在左下方宽键盘面板中展示 `ctx.userInteraction` 问题,包含进度、编号选项和对齐说明。最新记录的会话标题成为 header 副标题;标题不存在时使用 `welcome`,终端窗口标题则变为 `<session title> — <configured title>`。持久 `llm/retry` 事件会撤回失败步骤的实时 chunk,并在 transcript(文本记录)中渲染计划重试次数、延迟和失败;成功、耗尽与取消随后通过普通会话事件结算。Footer 会对每个已记录模型步骤的用量只计一次,包括失败尝试;对于没有用量 chunk 的日志,以已提交消息的用量回退。其空闲视图会将 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显示 `context unknown`,并显示工具卡片模式、当前模型,以及任何显式选择的推理强度。Agent 运行时,这些摘要会替换为已经过工作时间指示器和 `esc interrupt`。表层替换事件会重建 transcript,使经过压缩(compaction)的历史不会再次出现。
TUI 从追加来源的会话事件重建已恢复历史,渲染 Markdown 响应与 reasoning,将每个工具的 `presentCall` / `presentResult` 意图应用到终端、diff 或通用卡片,把站立的 `todo/write` 计划保留在编辑器上方(下一个 `turn/start` 时清空),并在左下方宽键盘面板中展示 `ctx.userInteraction` 问题,包含进度、编号选项和对齐说明。最新记录的会话标题成为 header 副标题;标题不存在时使用 `welcome`,终端窗口标题则变为 `<session title> — <configured title>`。持久 `llm/retry` 事件会撤回失败步骤的实时 chunk,并在 transcript(文本记录)中渲染计划重试次数、延迟和失败;成功、耗尽与取消随后通过普通会话事件结算。Footer 会对每个已记录模型步骤的用量只计一次,包括失败尝试;对于没有用量 chunk 的日志,以已提交消息的用量回退。其空闲视图会将 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显示 `context unknown`,并显示工具卡片模式、当前模型,以及任何显式选择的推理强度。Agent 运行时,这些摘要会替换为已经过工作时间指示器和 `esc interrupt`。表层替换从不重写已渲染的 transcript:被它遮蔽的对话仍可阅读,而已落地的压缩(compaction)检查点会在其日志位置添加一行暗色 `… earlier context was compacted …` 标记,因此终端报告的是模型从何处起不再看到那段历史,而不是把它抹掉。仅供模型使用的替换副本——被裁剪的工具结果、重新生成的 assistant 消息——不渲染任何内容。
如果逻辑工作区标签与会话宿主目录不同,嵌入方可以提供 `TuiRuntime.formatCwd`。该覆盖只改变 footer 标签;工具仍使用会话 `cwd`。
@@ -75,7 +75,7 @@ Footer 将会话报告的用量汇总为 `↑<uncached input> ↓<output>`;任
fileSearchExcludedDirectories: ['.git', 'node_modules', 'dist']
```
任一进程流不是 TTY 时,启动会在挂载前失败。组合 app 必须先挂载 TUI,再挂载由配置创建的 agent,使入口能够观察 `agent-loop/config-start-failed`;完全匹配会话的失败会在全屏模式启动前写出并以状态 1 退出,而不是留下空白终端。dispose(资源释放)会停止接收扩展请求,卸载 `ctx.tui` 提供方及其依赖插件,中止运行中的命令,移除 TUI 定义,停止 loader,拒绝待处理问题,排空终端输入,恢复终端状态,注销事件 listener 和用户交互提供方,并且绝不会在 HMR 期间退出替换进程。
任一进程流不是 TTY 时,启动会在挂载前失败。组合 app 必须先挂载 TUI,再挂载由配置创建的 agent,使入口能够观察 `agent-loop/config-start-failed`;完全匹配会话的失败会在全屏模式启动前写出并以状态 1 退出,而不是留下空白终端。dispose(资源释放)会停止接收扩展请求,卸载 `ctx.tui` 提供方及其依赖插件,中止运行中的命令,移除 TUI 定义,停止 loader,拒绝待处理问题,排空终端输入,恢复终端状态,注销事件 listener 和用户交互提供方,并且绝不会在 HMR 期间退出替换进程。用户退出会先 dispose 应用根上下文以关闭同级资源,再退出进程;五秒兜底可避免某个卡住的 disposer 困住进程。
## 颜色

View File

@@ -35,6 +35,7 @@
"@deepseek-ai/dsh-agent": "^0.0.1",
"@deepseek-ai/dsh-agent-loop": "^0.0.1",
"@deepseek-ai/dsh-commands": "^0.0.1",
"@deepseek-ai/dsh-compact": "^0.0.1",
"@deepseek-ai/dsh-invariants": "^0.0.1",
"@deepseek-ai/dsh-llm": "^0.0.1",
"@deepseek-ai/dsh-llm-retry": "^0.0.1",
@@ -74,6 +75,7 @@
"@deepseek-ai/dsh-agent-loop": "workspace:^",
"@deepseek-ai/dsh-goal": "workspace:^",
"@deepseek-ai/dsh-commands": "workspace:^",
"@deepseek-ai/dsh-compact": "workspace:^",
"@deepseek-ai/dsh-invariants": "workspace:^",
"@deepseek-ai/dsh-llm": "workspace:^",
"@deepseek-ai/dsh-llm-retry": "workspace:^",

View File

@@ -1,6 +1,6 @@
/**
* Zero-state helpers for the interactive chat channel: prompt-directory and
* Git-branch formatting, surface/tool-call derivations over the session log,
* Git-branch formatting, transcript/tool-call derivations over the session log,
* session-reference context cards, the placeholder editor, and banner-reveal
* timing constants. None of these close over channel state.
* @module @deepseek-ai/dsh-tui/chat/helpers
@@ -15,7 +15,9 @@ import {
truncateToWidth,
visibleWidth,
} from '@earendil-works/pi-tui'
import type { Session } from '@deepseek-ai/dsh-session'
import { isCompactCheckpointSource } from '@deepseek-ai/dsh-compact'
import { isAppendSurfaceEvent, isReplacementSurfaceEvent } from '@deepseek-ai/dsh-session'
import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
import { scrubbedParentEnv } from '@deepseek-ai/dsh-subprocess'
/** Editor that shows a placeholder without making it editable content. */
@@ -81,24 +83,16 @@ export function gitBranch(cwd: string): string | undefined {
}
/**
* Sequence numbers currently visible on the session surface.
* @param session - session whose surface nodes to read.
* @returns the set of visible event sequence numbers.
*/
export function activeSurfaceSeqs(session: Session): Set<number> {
return new Set(session.surface.nodes)
}
/**
* Tool-call ids whose owning assistant message is on the active surface.
* Tool-call ids whose owning assistant message is append-origin, so its tool
* cards stay paired in the transcript after a replacement shadowed the message
* on the model surface.
* @param session - session whose events to scan.
* @param active - sequence numbers currently on the surface.
* @returns the set of active tool-call ids.
* @returns the set of transcript tool-call ids.
*/
export function activeToolCallIds(session: Session, active: ReadonlySet<number>): Set<string> {
export function transcriptToolCallIds(session: Session): Set<string> {
const ids = new Set<string>()
for (const event of session.events) {
if (event.type !== 'assistant/message' || !active.has(event.seq)) continue
if (event.type !== 'assistant/message' || !isAppendSurfaceEvent(event)) continue
for (const block of event.data.message.content) {
if (block.type === 'tool-call') ids.add(block.id)
}
@@ -106,6 +100,26 @@ export function activeToolCallIds(session: Session, active: ReadonlySet<number>)
return ids
}
/**
* Whether an event is a landed compaction checkpoint. Recognition goes through
* {@link isCompactCheckpointSource} — the compaction seam's backend-independent
* contract for the source every backend stamps on its replacement user message —
* rather than the shape of the replacement. Other replacements (a pruned
* `tool/result`, a regenerated `assistant/message`) rewrite one node for the
* model and mark no boundary in the conversation.
*
* Both current call sites already test the replacement themselves. The check
* keeps the exported predicate true to its name for a third caller, rather than
* making that caller repeat it.
* @param event - event to test.
* @returns true when the event compacted a surface range.
*/
export function isCompactCheckpoint(event: SessionEvent): boolean {
return event.type === 'user/message'
&& isCompactCheckpointSource(event.data.source)
&& isReplacementSurfaceEvent(event)
}
/**
* Read a session-reference context card's display labels from an event source.
* @param source - event source to inspect.

View File

@@ -29,7 +29,13 @@ import type { ChannelNotice, ChatChannelDeps } from './channel.ts'
export interface ResumeControllerDeps extends ChatChannelDeps, ChannelNotice {
readonly agent: Agent
readonly runtime: TuiRuntime
readonly sessionQuery: SessionQueryService | undefined
/**
* The optional session-query service, re-read at each use. `sessionQuery` is
* mounted by an independent plugin, and a flat config tree gives no ordering
* guarantee between it and this front door, so a value captured once at
* construction can be `undefined` even though the service arrives moments later.
*/
readonly sessionQuery: (this: void) => SessionQueryService | undefined
readonly ui: TUI
readonly editor: HintEditor
/** Current agent status, re-read at each resume precondition point. */
@@ -74,9 +80,11 @@ export function createResumeController(deps: ResumeControllerDeps): ResumeContro
events: live.events.map(event => structuredClone(event)),
}
} else {
/* v8 ignore next -- caller checks the optional service before mapping records */
if (sessionQuery === undefined) throw new Error('session query is unavailable')
snapshot = await sessionQuery.readSession(record.header.id)
const readQuery = sessionQuery()
/* v8 ignore start -- caller proves the optional service before mapping records */
if (readQuery === undefined) throw new Error('session query is unavailable')
/* v8 ignore stop */
snapshot = await readQuery.readSession(record.header.id)
}
return summarizeResumeCandidate(
record,
@@ -104,11 +112,13 @@ export function createResumeController(deps: ResumeControllerDeps): ResumeContro
* resolve the exact identity and workspace the host will re-exec into.
*/
const preflightResume = async (sessionId: SessionId): Promise<{ id: SessionId; cwd: string }> => {
/* v8 ignore next -- only showResume can call this closure, after proving the optional service exists */
if (sessionQuery === undefined) throw new Error('Resume is unavailable: session query is not mounted.')
const query = sessionQuery()
/* v8 ignore start -- showResume alone calls this after proving the optional service exists */
if (query === undefined) throw new Error('Resume is unavailable: session query is not mounted.')
/* v8 ignore stop */
const initialStatus = deps.agentStatus()
if (initialStatus !== 'idle') throw new Error(`Resume requires an idle agent (status: ${initialStatus}).`)
const record = (await sessionQuery.listSessions()).find(candidate => candidate.header.id === sessionId)
const record = (await query.listSessions()).find(candidate => candidate.header.id === sessionId)
if (record === undefined) throw new Error(`Session "${sessionId}" is no longer available.`)
const candidate = await readResumeCandidate(
record,
@@ -177,13 +187,14 @@ export function createResumeController(deps: ResumeControllerDeps): ResumeContro
deps.appendNotice('Resume requires the current turn to finish or be cancelled first.', 'warning')
return
}
if (sessionQuery === undefined) {
const listQuery = sessionQuery()
if (listQuery === undefined) {
deps.appendNotice('Resume is not available: session query is not mounted.', 'warning')
return
}
const scan = ++resumeScan
void resumeOverlay?.close()
void sessionQuery.listSessions().then(async (records) => {
void listQuery.listSessions().then(async (records) => {
if (deps.isDisposed() || scan !== resumeScan) return
// Every workspace in the store is summarized; the picker owns the
// current-workspace/all-workspaces scope split over the whole set.

View File

@@ -389,10 +389,23 @@ export class ToolCardComponent implements Component {
const glyph = this.result === undefined ? '○' : '●'
const rawBody = this.renderBody()
const view = this.resultView ?? this.callView
const genericContent = view.card === 'generic' ? view.content ?? this.result?.content : undefined
const unknownXml = this.definition === undefined && genericContent !== undefined
// A generic card's own content, or a web card's fallback to the raw result
// content (the `web` view carries no `content` copy), both render as one dim
// Markdown block below, so links/lists/headings keep the unified dim styling
// rather than reading as bare text. Terminal and diff cards own their body
// styling, so they are excluded (mirrors renderBody's post-terminal/diff fallback).
const markdownContent = view.card === 'generic'
? view.content ?? this.result?.content
: view.card === 'web'
// A web resultView is only assigned alongside this.result (the result
// handler sets both) and the pending callView is never a web card, so
// the optional-chain undefined side is unreachable here.
/* v8 ignore next */
? this.result?.content
: undefined
const unknownXml = this.definition === undefined && markdownContent !== undefined
? renderUnknownXml(
displayText(contentText(genericContent)),
displayText(contentText(markdownContent)),
this.maxOutputLines,
this.visibility === 'expanded',
displayText,
@@ -405,7 +418,7 @@ export class ToolCardComponent implements Component {
// A generic card renders title and result as one Markdown document, so the
// document's own block spacing is preserved, then dims every row — the whole
// card body reads as one dim block under the status-colored header.
const body = unknownXml ?? (genericContent !== undefined && rawBody.lines.length > 0
const body = unknownXml ?? (markdownContent !== undefined && rawBody.lines.length > 0
? this.dimBody(rawBody, width)
: [...rawBody.prelude, ...rawBody.lines])
const visibleBody = unknownXml !== undefined || this.visibility === 'expanded'
@@ -502,7 +515,11 @@ export class ToolCardComponent implements Component {
// rather than under the dim result-output color.
return { prelude: [...hunks, footer], lines: [] }
}
const content = view.content ?? this.result?.content
// The web card carries no `content` copy, so a `web` result view falls back
// to the raw result content here (`view.card === 'generic'` narrows the
// generic union arm; a `web` card takes the same fallback, mirroring the
// `markdownContent` selection in render()).
const content = (view.card === 'generic' ? view.content : undefined) ?? this.result?.content
const prelude: string[] = []
const lines: string[] = []
// The presenter title headlines the body now that the header is a fixed

View File

@@ -5,8 +5,21 @@
* @module @deepseek-ai/dsh-tui
*/
import { CombinedAutocompleteProvider, Container, Key, Spacer, Text, TUI, ProcessTerminal, matchesKey, visibleWidth, type EditorTheme, type SlashCommand, type TerminalColorScheme } from '@earendil-works/pi-tui'
import { Service, type Context, type Fiber } from 'cordis'
import {
CombinedAutocompleteProvider,
Container,
Key,
Spacer,
Text,
TUI,
ProcessTerminal,
matchesKey,
visibleWidth,
type EditorTheme,
type SlashCommand,
type TerminalColorScheme,
} from '@earendil-works/pi-tui'
import { Service, type Context, type Fiber, type FiberState } from 'cordis'
import {
assembleContextFor,
installAgentLlmTarget,
@@ -22,6 +35,7 @@ import type { ContentBlock, MessageId } from '@deepseek-ai/dsh-llm'
import type {} from '@deepseek-ai/dsh-llm-retry'
import { renderPrompt } from '@deepseek-ai/dsh-system-prompt'
import {
isReplacementSurfaceEvent,
lastActivityTime,
SessionId,
type SessionEvent,
@@ -43,6 +57,7 @@ import {
TuiExtensionServiceImpl,
TuiOverlayManager,
} from './extension/overlay-manager.ts'
import {
parseTuiPromptTemplate,
renderTuiPromptTemplate,
@@ -106,14 +121,14 @@ import {
} from './chat/skill-invocation.ts'
import { ReferenceAutocompleteProvider } from './chat/autocomplete.ts'
import {
activeSurfaceSeqs,
activeToolCallIds,
BANNER_REVEAL_INTERVAL_MS,
BANNER_REVEAL_STEPS,
formatCwd,
gitBranch,
HintEditor,
isCompactCheckpoint,
sessionReferenceCard,
transcriptToolCallIds,
} from './chat/helpers.ts'
import {
createModelController,
@@ -158,6 +173,9 @@ export type {
TuiViewport,
} from './extension/types.ts'
/** First terminal Cordis state: FAILED, DISPOSED, and UNLOADING are unusable. */
const FIBER_FAILED = 3 as FiberState.FAILED
declare module 'cordis' {
interface Context {
/** Terminal-only interaction service, available only while a TUI is mounted. */
@@ -170,8 +188,6 @@ declare module 'cordis' {
tuiGoodbyeMessage: string | undefined
/** Skill the launcher wants auto-invoked as the fresh session's first turn; absent leaves it to the user. */
tuiInitialSkill: string | undefined
/** Launcher-owned session-store root the app bundle defaults to; absent keeps the bundle's project-local default. */
launcherSessionsRoot: string | undefined
}
}
@@ -216,16 +232,6 @@ export const TUI_GOODBYE_MESSAGE_KEY = 'tuiGoodbyeMessage'
*/
export const INITIAL_SKILL_KEY = 'tuiInitialSkill'
/**
* Context key a launcher sets before any Loader entry mounts
* (`ctx.provide(SESSIONS_ROOT_KEY, root)`) to supply its session-store root as
* the app bundle's default persistence root. Shared-store policy (one store
* across every cwd) belongs to the launcher — the dsh CLI resolves it under the
* Harness home — never to a plugin; a bundle without this slot keeps its own
* project-local default, and an explicit `persistenceRoot` config still wins.
*/
export const SESSIONS_ROOT_KEY = 'launcherSessionsRoot'
/**
* Optional terminal-local interaction service provided by one mounted TUI.
*
@@ -256,6 +262,13 @@ export const inject = ['agents', 'sessions', 'commands', 'userInteraction', 'too
/** Model guidance for path-only file references selected through the TUI. */
export const FILE_REFERENCE_PROMPT = 'Paths prefixed with @ are files explicitly referenced by the user. Use the read tool when their contents are needed; do not claim to have inspected a file before reading it.'
/**
* Transcript row standing in for one compacted range. The conversation the
* compaction replaced stays rendered above it: the marker reports where the
* model stopped seeing that history, not that the history is gone.
*/
const COMPACTION_MARKER = '… earlier context was compacted …'
interface RunningStatus {
turn: number | undefined
timer: ReturnType<typeof setInterval>
@@ -294,7 +307,6 @@ export function createTuiChat(
const sessionId = SessionId(config.sessionId ?? 'main')
const agent = ctx.agents.get(sessionId)
if (agent === undefined) throw new Error(`ui-tui: session "${sessionId}" is not running`)
const sessionQuery = ctx.get('sessionQuery')
const resolved = resolveTuiConfig(config)
const palette = createPalette(resolved.theme.color)
const mdTheme = markdownTheme(palette)
@@ -808,6 +820,23 @@ export function createTuiChat(
}
}
const renderCompactionMarker = (): void => {
chat.addChild(new Spacer(1))
chat.addChild(new Text(palette.dim(COMPACTION_MARKER), 0, 0))
}
/**
* Replay the human transcript from the append-only log. The model-visible
* surface shadows compacted ranges, so it is not the source here: every
* append-origin message stays rendered, and a replacement contributes at most
* the compaction marker at its own log position.
*
* The `tool/call` pairing check has no live counterpart, because only replay
* can meet an orphan: `tool/call` carries no `surfaceOp` of its own, so it
* inherits transcript membership from the `assistant/message` that advertised
* it, which the live listener has necessarily just rendered. A loaded log is a
* replay boundary, so the pairing is re-derived here instead of assumed.
*/
const rebuildTranscript = (populateHistory: boolean): void => {
chat.clear()
toolCards.clear()
@@ -815,15 +844,13 @@ export function createTuiChat(
contextCards.clear()
streaming = undefined
todo.update([])
const active = activeSurfaceSeqs(agent.session)
const activeCalls = activeToolCallIds(agent.session, active)
const transcriptCalls = transcriptToolCallIds(agent.session)
for (const event of agent.session.events) {
const isSurface = event.type === 'user/message'
|| event.type === 'assistant/message'
|| event.type === 'tool/result'
|| event.type === 'steering/message'
if (isSurface && !active.has(event.seq)) continue
if (event.type === 'tool/call' && !activeCalls.has(event.data.callId)) continue
if (isReplacementSurfaceEvent(event)) {
if (isCompactCheckpoint(event)) renderCompactionMarker()
continue
}
if (event.type === 'tool/call' && !transcriptCalls.has(event.data.callId)) continue
renderEvent(event, { addHistory: populateHistory, renderChunks: false })
}
requestRender()
@@ -845,7 +872,14 @@ export function createTuiChat(
resolved,
palette,
overlayManager,
sessionQuery,
// Optional and independently mounted. Cordis transiently leaves this sibling
// non-ACTIVE during command callbacks, so the non-strict read is intentional;
// terminal fiber states still exclude failed, closing, and closed providers.
sessionQuery: () => {
const implementation = ctx.reflect._getImpl('sessionQuery', false)
if (implementation === undefined || implementation.fiber.state >= FIBER_FAILED) return undefined
return ctx.get('sessionQuery', false)
},
ui,
editor,
appendNotice,
@@ -1482,8 +1516,11 @@ export function createTuiChat(
recordEventUsage(tokens, event)
if (event.type === 'turn/start' && runningStatus !== undefined) runningStatus.turn = event.data.turn
if (event.type === 'assistant/message' && streaming?.isSettled()) streaming = undefined
if ('surfaceOp' in event && typeof event.surfaceOp === 'object') {
rebuildTranscript(false)
// A replacement mutates only the model surface, so the rendered transcript
// keeps what it already showed; a landed summary checkpoint adds its marker.
if (isReplacementSurfaceEvent(event)) {
if (isCompactCheckpoint(event)) renderCompactionMarker()
requestRender()
return
}
renderEvent(event, { addHistory: false, renderChunks: true })
@@ -1658,9 +1695,35 @@ export function mountTui(ctx: Context, config: Config, runtime: TuiRuntime): voi
if (existing !== undefined) start(existing)
}
const ROOT_DISPOSE_TIMEOUT_MS = 5_000
/**
* Dispose the whole application before process exit, with a bounded fallback.
* @param ctx - The TUI plugin context whose root owns sibling resources.
* @param code - Process status to report.
* @param exit - Exit boundary, replaceable by tests.
*/
export function disposeRootAndExit(
ctx: Context,
code: number,
exit: (status: number) => void = (status) => { process.exit(status) },
): void {
let exited = false
const exitOnce = (): void => {
if (exited) return
exited = true
exit(code)
}
const timeout = setTimeout(exitOnce, ROOT_DISPOSE_TIMEOUT_MS)
void ctx.root.fiber.dispose().then(
() => { clearTimeout(timeout); exitOnce() },
() => { clearTimeout(timeout); exitOnce() },
)
}
/** Cordis entry point using the process terminal; explicit TUI composition requires a TTY pair. */
/* v8 ignore start -- production process wiring; fake-terminal tests cover mountTui/createTuiChat,
and the tui-agent PTY smoke covers the real entry */
and apps/cli PTY smokes cover the real entry */
export function apply(ctx: Context, config: Config): void {
if (!process.stdin.isTTY || !process.stdout.isTTY) {
throw new Error('ui-tui: both stdin and stdout must be TTYs; use the one-shot @deepseek-ai/dsh-cli-demo app for pipes')
@@ -1680,7 +1743,7 @@ export function apply(ctx: Context, config: Config): void {
initialSkill === undefined ? {} : { initialSkill },
), {
terminal: new ProcessTerminal(),
exit: code => process.exit(code),
exit: (code) => { disposeRootAndExit(ctx, code) },
...resumeHost === undefined ? {} : { handoffResume: (sessionId, cwd) => resumeHost.handoff(sessionId, cwd) },
...goodbyeMessage === undefined ? {} : { goodbyeMessage },
})

View File

@@ -102,10 +102,10 @@ export async function createTuiTestHarness<TerminalType extends Terminal, Exit e
await ctx.plugin(UserInteractionService)
await ctx.plugin(TuiPromptService)
const catalog = options.catalog ?? {
providers: [{ id: 'deepseek', name: 'DeepSeek' }],
providers: [{ id: 'deepseek-official', name: 'DeepSeek' }],
models: [
{ provider: 'deepseek', id: 'deepseek-v4-flash', name: 'DeepSeek V4 Flash' },
{ provider: 'deepseek', id: 'deepseek-v4-pro', name: 'DeepSeek V4 Pro' },
{ provider: 'deepseek-official', id: 'deepseek-v4-flash', name: 'DeepSeek V4 Flash' },
{ provider: 'deepseek-official', id: 'deepseek-v4-pro', name: 'DeepSeek V4 Pro' },
],
}
ctx.provide('tokenMeter', {
@@ -189,7 +189,7 @@ export async function createTuiTestHarness<TerminalType extends Terminal, Exit e
const cancelled: AgentCancelCause[] = []
const agent: FakeAgent = {
id: sessionId,
options: options.agentOptions ?? { provider: 'deepseek', model: 'deepseek-v4-flash' },
options: options.agentOptions ?? { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
session,
inbox: new Inbox(session),
status: options.status ?? 'idle',

View File

@@ -152,8 +152,8 @@ describe('TUI prompt values', () => {
describe('TUI prompt templates', () => {
it('interpolates values and removes separators around unavailable values', () => {
const tokens = parseTuiPromptTemplate('${cwd} ${git/worktree} :: ${missing} ${model}')
const values = new Map([['cwd', '/work'], ['model', 'deepseek']])
expect(renderTuiPromptTemplate(tokens, name => values.get(name))).toBe('/work :: deepseek')
const values = new Map([['cwd', '/work'], ['model', 'deepseek-official']])
expect(renderTuiPromptTemplate(tokens, name => values.get(name))).toBe('/work :: deepseek-official')
})
it('keeps a trailing literal after the last value', () => {

View File

@@ -36,9 +36,9 @@ buffer
14| " │ │ "
style 8-8 fg=bright-magenta
style 83-83 fg=bright-magenta
15| " │ → deepseek/deepseek-v4-pro DeepSeek V4 Pro │ "
15| " │ → deepseek-official/deepseek-v4- DeepSeek V4 Pro │ "
style 8-8 fg=bright-magenta
style 10-58 fg=bright-magenta inverse
style 10-41 fg=bright-magenta inverse
style 83-83 fg=bright-magenta
16| " │ │ "
style 8-8 fg=bright-magenta

View File

@@ -36,13 +36,13 @@ buffer
14| " │ │ "
style 8-8 fg=bright-magenta
style 83-83 fg=bright-magenta
15| " │ → deepseek/deepseek-v4-flash DeepSeek V4 Flash — current │ "
15| " │ → deepseek-official/deepseek-v4- DeepSeek V4 Flash — current │ "
style 8-8 fg=bright-magenta
style 10-70 fg=bright-magenta inverse
style 10-41 fg=bright-magenta inverse
style 83-83 fg=bright-magenta
16| " │ deepseek/deepseek-v4-pro DeepSeek V4 Pro │ "
16| " │ deepseek-official/deepseek-v4- DeepSeek V4 Pro │ "
style 8-8 fg=bright-magenta
style 36-58 dim
style 42-58 dim
style 83-83 fg=bright-magenta
17| " │ │ "
style 8-8 fg=bright-magenta

View File

@@ -16,8 +16,8 @@ buffer
5| "Model wait 0.0s "
style 0-14 dim
6| <blank>
7| "Model selected: deepseek/deepseek-v4-pro. New steps will use it. "
style 0-63 dim
7| "Model selected: deepseek-official/deepseek-v4-pro. New steps will use it. "
style 0-72 dim
8| <blank>
9| "/workspace/project (tui-staging) deepseek-v4-pro ↑0 ↓0 0% context"
style 0-17 fg=bright-magenta bold

View File

@@ -31,15 +31,15 @@ buffer
13| " unavailable: current session "
style 2-31 fg=yellow
14| " Other workspace work "
15| " 2024-02-02T00:00:08.000Z · turn 1: completed · deepseek/deepseek-v4-pro "
style 2-74 dim
15| " 2024-02-02T00:00:08.000Z · turn 1: completed · deepseek-official/deepseek-v4-pro "
style 2-83 dim
16| " persisted · elsewhere-session "
style 2-32 dim
17| " workspace /workspace/other "
style 2-29 dim
18| " Resume selector design "
19| " 2024-01-01T00:00:08.000Z · turn 1: completed · deepseek/deepseek-v4-pro "
style 2-74 dim
19| " 2024-01-01T00:00:08.000Z · turn 1: completed · deepseek-official/deepseek-v4-pro "
style 2-83 dim
20| " persisted · earlier-session "
style 2-30 dim
21| " workspace /workspace/project "

View File

@@ -29,8 +29,8 @@ buffer
12| " unavailable: current session "
style 2-31 fg=yellow
13| " Resume selector design "
14| " 2024-01-01T00:00:08.000Z · turn 1: completed · deepseek/deepseek-v4-pro "
style 2-74 dim
14| " 2024-01-01T00:00:08.000Z · turn 1: completed · deepseek-official/deepseek-v4-pro "
style 2-83 dim
15| " persisted · earlier-session "
style 2-30 dim
16| " "

View File

@@ -1,7 +1,7 @@
terminal 56x36 buffer=normal length=44 base=8 viewport=8
terminal 56x36 buffer=normal length=45 base=9 viewport=9
lifecycle started=1 stopped=0 progress=inactive
title "Inspect session diagnostics — DSH snapshot"
cursor hidden column=7 viewportRow=35 bufferRow=43
cursor hidden column=7 viewportRow=35 bufferRow=44
buffer
0| " DEEPSEEK HARNESS"
style 1-8 fg=bright-magenta bold
@@ -37,84 +37,87 @@ buffer
style 0-0 dim
style 3-12 dim
style 55-55 dim
15| "│ Model: deepseek/deepseek-v4-pro (effort │"
style 0-0 dim
style 3-12 dim
style 40-55 dim
16| "│ default; reasoning blocks shown) │"
style 0-0 dim
style 15-46 dim
style 55-55 dim
17| "│ │"
style 0-0 dim
style 55-55 dim
18| "│ Agent: idle · 8 events · 1 turn · 1 step · 1 │"
15| "│ Model: deepseek-official/deepseek-v4-pro │"
style 0-0 dim
style 3-12 dim
style 55-55 dim
19| "│ tool call │"
16| "│ (effort default; reasoning blocks │"
style 0-0 dim
style 15-55 dim
17| "│ shown) │"
style 0-0 dim
style 15-20 dim
style 55-55 dim
18| "│ │"
style 0-0 dim
style 55-55 dim
20| "│ │"
style 0-0 dim
style 55-55 dim
21| "│ Tokens: 1,250 input + 340 output │"
19| "│ Agent: idle · 8 events · 1 turn · 1 step · 1 │"
style 0-0 dim
style 3-12 dim
style 55-55 dim
22| "│ KV cache: [███████████░░░░░] 67% hit (3,000 read │"
20| "│ tool call │"
style 0-0 dim
style 55-55 dim
21| "│ │"
style 0-0 dim
style 55-55 dim
22| "│ Tokens: 1,250 input + 340 output │"
style 0-0 dim
style 3-12 dim
style 55-55 dim
23| "│ KV cache: [███████████░░░░░] 67% hit (3,000 read │"
style 0-0 dim
style 3-12 dim
style 15-15 dim
style 16-26 fg=bright-magenta
style 27-32 dim
style 55-55 dim
23| "│ + 250 write) │"
24| "│ + 250 write) │"
style 0-0 dim
style 55-55 dim
24| "│ Context: [█████░░░░░░░░░░░] 33% used (42,000 / │"
25| "│ Context: [█████░░░░░░░░░░░] 33% used (42,000 / │"
style 0-0 dim
style 3-12 dim
style 15-15 dim
style 16-20 fg=bright-magenta
style 21-32 dim
style 55-55 dim
25| "│ 128,000) │"
26| "│ 128,000) │"
style 0-0 dim
style 55-55 dim
26| "│ │"
27| "│ │"
style 0-0 dim
style 55-55 dim
27| "│ Created: 2026-07-22 09:10:11 UTC │"
28| "│ Created: 2026-07-22 09:10:11 UTC │"
style 0-0 dim
style 3-12 dim
style 55-55 dim
28| "│ Active: 2026-07-22 09:10:11 UTC │"
29| "│ Active: 2026-07-22 09:10:11 UTC │"
style 0-0 dim
style 3-12 dim
style 55-55 dim
29| "╰──────────────────────────────────────────────────────╯"
30| "╰──────────────────────────────────────────────────────╯"
style 0-55 dim
30| <blank>
31| "System prompt "
31| <blank>
32| "System prompt "
style 0-12 fg=bright-magenta bold
32| "You are an AI agent powered by the DeepSeek Harness SDK."
33| " "
34| "Paths prefixed with @ are files explicitly referenced by"
35| "the user. Use the read tool when their contents are "
36| "needed; do not claim to have inspected a file before "
37| "reading it. "
38| <blank>
39| "Registered tools "
33| "You are an AI agent powered by the DeepSeek Harness SDK."
34| " "
35| "Paths prefixed with @ are files explicitly referenced by"
36| "the user. Use the read tool when their contents are "
37| "needed; do not claim to have inspected a file before "
38| "reading it. "
39| <blank>
40| "Registered tools "
style 0-15 fg=bright-magenta bold
40| "read, write "
41| <blank>
42| "/workspace/project (tui-staging) deepseek-v4-pro ↑1.3k"
41| "read, write "
42| <blank>
43| "/workspace/project (tui-staging) deepseek-v4-pro ↑1.3k"
style 0-17 fg=bright-magenta bold
style 18-31 dim
style 34-48 dim
style 51-55 dim
43| " dsh > "
44| " dsh > "
style 1-3 fg=bright-magenta bold
style 5-6 dim
style 7-7 inverse

View File

@@ -21,68 +21,68 @@ buffer
style 0-2 fg=bright-magenta bold underline
9| "inspect this session "
10| <blank>
11| "╭─ Session status ───────────────────────────────────────────────────────────────╮"
11| "╭─ Session status ────────────────────────────────────────────────────────────────────────╮"
style 0-2 dim
style 3-16 fg=bright-magenta bold
style 17-81 dim
12| "│ Session: main-session │"
style 17-90 dim
12| "│ Session: main-session │"
style 0-0 dim
style 3-12 dim
style 81-81 dim
13| "│ Title: Inspect session diagnostics │"
style 90-90 dim
13| "│ Title: Inspect session diagnostics │"
style 0-0 dim
style 3-12 dim
style 81-81 dim
14| "│ Directory: /workspace/project │"
style 90-90 dim
14| "│ Directory: /workspace/project │"
style 0-0 dim
style 3-12 dim
style 81-81 dim
15| "│ Model: deepseek/deepseek-v4-pro (effort default; reasoning blocks shown) │"
style 90-90 dim
15| "│ Model: deepseek-official/deepseek-v4-pro (effort default; reasoning blocks shown) │"
style 0-0 dim
style 3-12 dim
style 40-79 dim
style 81-81 dim
16| "│ │"
style 49-88 dim
style 90-90 dim
16| "│ │"
style 0-0 dim
style 81-81 dim
17| "│ Agent: idle · 8 events · 1 turn · 1 step · 1 tool call │"
style 90-90 dim
17| "│ Agent: idle · 8 events · 1 turn · 1 step · 1 tool call │"
style 0-0 dim
style 3-12 dim
style 81-81 dim
18| "│ │"
style 90-90 dim
18| "│ │"
style 0-0 dim
style 81-81 dim
19| "│ Tokens: 1,250 input + 340 output │"
style 90-90 dim
19| "│ Tokens: 1,250 input + 340 output │"
style 0-0 dim
style 3-12 dim
style 81-81 dim
20| "│ KV cache: [███████████░░░░░] 67% hit (3,000 read + 250 write) │"
style 90-90 dim
20| "│ KV cache: [███████████░░░░░] 67% hit (3,000 read + 250 write) │"
style 0-0 dim
style 3-12 dim
style 15-15 dim
style 16-26 fg=bright-magenta
style 27-32 dim
style 81-81 dim
21| "│ Context: [█████░░░░░░░░░░░] 33% used (42,000 / 128,000) │"
style 90-90 dim
21| "│ Context: [█████░░░░░░░░░░░] 33% used (42,000 / 128,000) │"
style 0-0 dim
style 3-12 dim
style 15-15 dim
style 16-20 fg=bright-magenta
style 21-32 dim
style 81-81 dim
22| "│ │"
style 90-90 dim
22| "│ │"
style 0-0 dim
style 81-81 dim
23| "│ Created: 2026-07-22 09:10:11 UTC │"
style 90-90 dim
23| "│ Created: 2026-07-22 09:10:11 UTC │"
style 0-0 dim
style 3-12 dim
style 81-81 dim
24| "│ Active: 2026-07-22 09:10:11 UTC │"
style 90-90 dim
24| "│ Active: 2026-07-22 09:10:11 UTC │"
style 0-0 dim
style 3-12 dim
style 81-81 dim
25| "╰────────────────────────────────────────────────────────────────────────────────╯"
style 0-81 dim
style 90-90 dim
25| "╰─────────────────────────────────────────────────────────────────────────────────────────╯"
style 0-90 dim
26| <blank>
27| "System prompt "
style 0-12 fg=bright-magenta bold

View File

@@ -1,7 +1,7 @@
terminal 44x18 buffer=normal length=18 base=0 viewport=0
terminal 44x18 buffer=normal length=24 base=6 viewport=6
lifecycle started=1 stopped=0 progress=inactive
title "DSH snapshot"
cursor hidden column=7 viewportRow=14 bufferRow=14
cursor hidden column=7 viewportRow=17 bufferRow=23
buffer
0| " DEEPSEEK HARNESS"
style 1-8 fg=bright-magenta bold
@@ -13,25 +13,39 @@ buffer
3| <blank>
4| "Assistant "
style 0-8 fg=bright-magenta bold underline
5| "Model wait 0.0s "
5| <blank>
6| "You "
style 0-2 fg=bright-magenta bold underline
7| "Old prompt with a long line that exercises "
8| "wrapping and stays visible after compaction."
9| <blank>
10| "● Tool / bash / Run the coverage gate"
style 0-36 fg=green
11| "$ pnpm run test:coverage "
style 0-23 dim
12| "/workspace/project "
style 0-17 dim
13| "packages/ui/tui 100% "
style 0-19 dim
14| "… +1 lines (Ctrl+O to expand) "
style 0-28 dim
15| "1 test skipped "
style 0-13 dim
16| "coverage complete "
style 0-16 dim
17| "[exit 0] "
style 0-7 dim
18| "Model wait 0.0s "
style 0-14 dim
6| <blank>
7| "Context · workspace-context"
style 0-26 dim
8| "Additional instructions from: "
style 0-43 dim
9| "nested/AGENTS.md "
style 0-15 dim
10| " "
11| "Render workspace context XML clearly. "
style 0-36 dim
12| <blank>
13| "/workspace/project (tui-staging) deepseek-v"
19| <blank>
20| "… earlier context was compacted … "
style 0-32 dim
21| <blank>
22| "/workspace/project (tui-staging) deepseek-v"
style 0-17 fg=bright-magenta bold
style 18-31 dim
style 34-43 dim
14| " dsh > "
23| " dsh > "
style 1-3 fg=bright-magenta bold
style 5-6 dim
style 7-7 inverse
15-17| <blank>

View File

@@ -1,7 +1,7 @@
terminal 104x30 buffer=normal length=30 base=0 viewport=0
lifecycle started=1 stopped=0 progress=inactive
title "DSH snapshot"
cursor hidden column=7 viewportRow=13 bufferRow=13
cursor hidden column=7 viewportRow=22 bufferRow=22
buffer
0| " DEEPSEEK HARNESS"
style 1-8 fg=bright-magenta bold
@@ -13,25 +13,41 @@ buffer
3| <blank>
4| "Assistant "
style 0-8 fg=bright-magenta bold underline
5| "Model wait 0.0s "
5| <blank>
6| "You "
style 0-2 fg=bright-magenta bold underline
7| "Old prompt with a long line that exercises wrapping and stays visible after compaction. "
8| <blank>
9| "● Tool / bash / Run the coverage gate"
style 0-36 fg=green
10| "$ pnpm run test:coverage "
style 0-23 dim
11| "/workspace/project "
style 0-17 dim
12| "packages/ui/tui 100% "
style 0-19 dim
13| "… +1 lines (Ctrl+O to expand) "
style 0-28 dim
14| "1 test skipped "
style 0-13 dim
15| "coverage complete "
style 0-16 dim
16| "[exit 0] "
style 0-7 dim
17| "Model wait 0.0s "
style 0-14 dim
6| <blank>
7| "Context · workspace-context"
style 0-26 dim
8| "Additional instructions from: nested/AGENTS.md "
style 0-45 dim
9| " "
10| "Render workspace context XML clearly. "
style 0-36 dim
11| <blank>
12| "/workspace/project (tui-staging) deepseek-v4-flash ↑0 ↓0 0% context"
18| <blank>
19| "… earlier context was compacted … "
style 0-32 dim
20| <blank>
21| "/workspace/project (tui-staging) deepseek-v4-flash ↑0 ↓0 0% context"
style 0-17 fg=bright-magenta bold
style 18-31 dim
style 34-50 dim
style 53-57 dim
style 60-69 dim
13| " dsh > "
22| " dsh > "
style 1-3 fg=bright-magenta bold
style 5-6 dim
style 7-7 inverse
14-29| <blank>
23-29| <blank>

View File

@@ -1,7 +1,7 @@
terminal 80x24 buffer=normal length=24 base=0 viewport=0
lifecycle started=1 stopped=0 progress=inactive
title "DSH snapshot"
cursor hidden column=7 viewportRow=20 bufferRow=20
cursor hidden column=7 viewportRow=21 bufferRow=21
buffer
0| " DEEPSEEK HARNESS"
style 1-8 fg=bright-magenta bold
@@ -16,35 +16,36 @@ buffer
5| <blank>
6| "You "
style 0-2 fg=bright-magenta bold underline
7| "Old prompt with a long line that exercises wrapping before compaction. "
8| <blank>
9| "● Tool / bash / Run the coverage gate"
7| "Old prompt with a long line that exercises wrapping and stays visible after "
8| "compaction. "
9| <blank>
10| "● Tool / bash / Run the coverage gate"
style 0-36 fg=green
10| "$ pnpm run test:coverage "
11| "$ pnpm run test:coverage "
style 0-23 dim
11| "/workspace/project "
12| "/workspace/project "
style 0-17 dim
12| "packages/ui/tui 100% "
13| "packages/ui/tui 100% "
style 0-19 dim
13| "… +1 lines (Ctrl+O to expand) "
14| "… +1 lines (Ctrl+O to expand) "
style 0-28 dim
14| "1 test skipped "
15| "1 test skipped "
style 0-13 dim
15| "coverage complete "
16| "coverage complete "
style 0-16 dim
16| "[exit 0] "
17| "[exit 0] "
style 0-7 dim
17| "Model wait 0.0s "
18| "Model wait 0.0s "
style 0-14 dim
18| <blank>
19| "/workspace/project (tui-staging) deepseek-v4-flash ↑0 ↓0 0% context"
19| <blank>
20| "/workspace/project (tui-staging) deepseek-v4-flash ↑0 ↓0 0% context"
style 0-17 fg=bright-magenta bold
style 18-31 dim
style 34-50 dim
style 53-57 dim
style 60-69 dim
20| " dsh > "
21| " dsh > "
style 1-3 fg=bright-magenta bold
style 5-6 dim
style 7-7 inverse
21-23| <blank>
22-23| <blank>

View File

@@ -0,0 +1,53 @@
terminal 104x30 buffer=normal length=30 base=0 viewport=0
lifecycle started=1 stopped=0 progress=inactive
title "DSH snapshot"
cursor hidden column=7 viewportRow=22 bufferRow=22
buffer
0| " DEEPSEEK HARNESS"
style 1-8 fg=bright-magenta bold
style 10-16 bold
1| " Snapshot agent ready."
style 1-21 dim
2| " main-session"
style 1-12 dim
3| <blank>
4| "Assistant "
style 0-8 fg=bright-magenta bold underline
5| <blank>
6| "You "
style 0-2 fg=bright-magenta bold underline
7| "Old prompt with a long line that exercises wrapping and stays visible after compaction. "
8| <blank>
9| "● Tool / bash / Run the coverage gate"
style 0-36 fg=green
10| "$ pnpm run test:coverage "
style 0-23 dim
11| "/workspace/project "
style 0-17 dim
12| "packages/ui/tui 100% "
style 0-19 dim
13| "… +1 lines (Ctrl+O to expand) "
style 0-28 dim
14| "1 test skipped "
style 0-13 dim
15| "coverage complete "
style 0-16 dim
16| "[exit 0] "
style 0-7 dim
17| "Model wait 0.0s "
style 0-14 dim
18| <blank>
19| "… earlier context was compacted … "
style 0-32 dim
20| <blank>
21| "/workspace/project (tui-staging) deepseek-v4-flash ↑0 ↓0 0% context"
style 0-17 fg=bright-magenta bold
style 18-31 dim
style 34-50 dim
style 53-57 dim
style 60-69 dim
22| " dsh > "
style 1-3 fg=bright-magenta bold
style 5-6 dim
style 7-7 inverse
23-29| <blank>

View File

@@ -5,6 +5,7 @@ import { fileURLToPath } from 'node:url'
import { afterAll, describe, expect, it, vi } from 'vitest'
import type { Context } from 'cordis'
import { agentEvents } from '@deepseek-ai/dsh-agent'
import { COMPACT_CHECKPOINT_SOURCE } from '@deepseek-ai/dsh-compact'
import { createUserMessage, CallId, type ContentBlock , createMessage, createToolResultMessage } from '@deepseek-ai/dsh-llm'
import type {} from '@deepseek-ai/dsh-llm-retry'
import { SessionId, type JsonValue, type Session, type SessionEvent } from '@deepseek-ai/dsh-session'
@@ -50,6 +51,7 @@ const CHECKPOINTS = [
'surface-before-compaction',
'surface-after-compaction-narrow',
'surface-after-compaction-wide',
'surface-replayed-compaction',
'model-selector',
'model-selector-filtered',
'model-switching',
@@ -181,6 +183,67 @@ function appendToolResult(
}, { surfaceOp: 'append' })
}
/** Frozen clock for the compaction fixtures; see the live scenario for why. */
const COMPACTION_FIXTURE_TIME = new Date(2026, 6, 21, 14, 40, 0).getTime()
/** The surface range a compaction checkpoint replaces, with its provenance. */
interface CompactionRange {
start: number
end: number
sources: number[]
}
/**
* Append one prompt / tool-call / tool-result step, the history a compaction
* shadows on the model surface and the transcript must keep showing. The prompt
* text is rendered verbatim; the tool card's body comes from `bash`'s static
* presenter, so the fixtures pin that the shadowed step's card survives rather
* than the result content below.
*/
function appendPreCompactionLog(session: Session): CompactionRange {
const user = session.append('user/message', createUserMessage({
content: [{ type: 'text', text: 'Old prompt with a long line that exercises wrapping and stays visible after compaction.' }],
source: { kind: 'user' },
}), { surfaceOp: 'append' })
const assistant = session.append('assistant/message', {
turn: 1,
step: 1,
message: createMessage({
role: 'assistant',
content: [{ type: 'tool-call', id: CallId('old-tool'), name: 'bash', arguments: '{}' }],
source: {
kind: 'model',
...{ provider: 'mock', model: 'deepseek-v4-flash' },
},
}),
}, { surfaceOp: 'append' })
session.append('tool/call', { turn: 1, step: 1, callId: CallId('old-tool'), name: 'bash', arguments: '{}' })
const result = session.append('tool/result', {
turn: 1,
step: 1,
message: createToolResultMessage({
callId: CallId('old-tool'),
content: [{ type: 'text', text: 'shadowed step tool output' }],
isError: false,
}),
}, { surfaceOp: 'append' })
return { start: user.seq, end: result.seq, sources: [user.seq, assistant.seq, result.seq] }
}
/** Land a compaction: replace the range with the framed model-only checkpoint. */
function appendCompactionCheckpoint(session: Session, range: CompactionRange): void {
session.append('user/message', createUserMessage({
content: [{
type: 'text',
text: '<context_checkpoint>\nModel-only summary payload that must never reach the transcript.\n</context_checkpoint>',
}],
source: COMPACT_CHECKPOINT_SOURCE,
}), {
surfaceOp: { op: 'replace', start: range.start, end: range.end },
sourceEventSeqs: range.sources,
})
}
function visualTool(
name: string,
call: NonNullable<ToolDefinition['presentCall']>,
@@ -489,7 +552,7 @@ describe('TUI terminal-state snapshots', () => {
description: 'Audit terminal states from independent angles',
phases: [
{ title: 'Inspect', detail: 'Map renderer branches' },
{ title: 'Verify', detail: 'Challenge missing states', provider: 'deepseek', model: 'deepseek-v4-flash' },
{ title: 'Verify', detail: 'Challenge missing states', provider: 'deepseek-official', model: 'deepseek-v4-flash' },
],
},
args: { packages: ['ui/tui', 'workflow/tool-workflow'] },
@@ -682,61 +745,22 @@ describe('TUI terminal-state snapshots', () => {
await disposeSnapshot(harness)
})
it('pins compaction surface replacement and narrow-to-wide reflow', async () => {
it('pins preserved history, the compaction marker, and narrow-to-wide reflow', async () => {
// Freeze the clock: the timing header hides zero-duration buckets, so a
// real-clock millisecond tick between the fixture appends and the render
// would flip `Tools 0.0s` in and out of the pinned header.
const nowSpy = vi.spyOn(Date, 'now').mockReturnValue(new Date(2026, 6, 21, 14, 40, 0).getTime())
let replacementStart = 0
let replacementEnd = 0
let replacementSources: number[] = []
const nowSpy = vi.spyOn(Date, 'now').mockReturnValue(COMPACTION_FIXTURE_TIME)
// The awaited setup always invokes beforeMount, so the range the checkpoint
// replaces is assigned by the time the appends below need it.
let compacted!: CompactionRange
const harness = await setupSnapshot({
tools: ADVANCED_CARD_TOOLS,
beforeMount(session) {
const user = session.append('user/message', createUserMessage({
content: [{ type: 'text', text: 'Old prompt with a long line that exercises wrapping before compaction.' }],
source: { kind: 'user' },
}), { surfaceOp: 'append' })
const assistant = session.append('assistant/message', {
turn: 1,
step: 1,
message: createMessage({
role: 'assistant',
content: [{ type: 'tool-call', id: CallId('old-tool'), name: 'bash', arguments: '{}' }],
source: {
kind: 'model',
...{ provider: 'mock', model: 'deepseek-v4-flash' },
},
}),
}, { surfaceOp: 'append' })
session.append('tool/call', { turn: 1, step: 1, callId: CallId('old-tool'), name: 'bash', arguments: '{}' })
const result = session.append('tool/result', {
turn: 1,
step: 1,
message: createToolResultMessage({
callId: CallId('old-tool'),
content: [{ type: 'text', text: 'obsolete output that must disappear' }],
isError: false,
}),
}, { surfaceOp: 'append' })
replacementStart = user.seq
replacementEnd = result.seq
replacementSources = [user.seq, assistant.seq, result.seq]
},
beforeMount(session) { compacted = appendPreCompactionLog(session) },
}, { columns: 80, rows: 24 })
await checkpoint('surface-before-compaction', harness.terminal, { includeScrollback: true })
await renderAfter(harness, () => {
harness.session.append('user/message', createUserMessage({
content: [{
type: 'text',
text: '<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nRender workspace context XML clearly.\n</system-reminder>',
}],
source: { kind: 'plugin', plugin: 'workspace-context' },
}), {
surfaceOp: { op: 'replace', start: replacementStart, end: replacementEnd },
sourceEventSeqs: replacementSources,
})
appendCompactionCheckpoint(harness.session, compacted)
harness.terminal.resize(44, 18)
})
await checkpoint('surface-after-compaction-narrow', harness.terminal, { includeScrollback: true })
@@ -747,6 +771,23 @@ describe('TUI terminal-state snapshots', () => {
nowSpy.mockRestore()
})
// The resume path, which is what regressed for real users: the replacement is
// already stored when the terminal mounts, so the transcript comes from replay
// rather than from live appends. Pinned against the same log the live scenario
// ends on, at its wide size, so the two fixtures are directly comparable.
it('pins a stored compaction replayed at mount', async () => {
const nowSpy = vi.spyOn(Date, 'now').mockReturnValue(COMPACTION_FIXTURE_TIME)
const harness = await setupSnapshot({
tools: ADVANCED_CARD_TOOLS,
beforeMount(session) {
appendCompactionCheckpoint(session, appendPreCompactionLog(session))
},
}, { columns: 104, rows: 30 })
await checkpoint('surface-replayed-compaction', harness.terminal, { includeScrollback: true })
await disposeSnapshot(harness)
nowSpy.mockRestore()
})
it('pins wrapped and explicit multiline shell-prompt input', async () => {
const harness = await setupSnapshot({}, { columns: 44, rows: 18 })
await renderAfter(harness, () => {
@@ -826,13 +867,13 @@ describe('TUI terminal-state snapshots', () => {
{ type: 'turn/start', seq: 0, time: Date.parse(`${day}T00:00:01Z`), data: { turn: 1 } },
{ type: 'user/message', seq: 1, time: Date.parse(`${day}T00:00:02Z`), data: createUserMessage({ content: [{ type: 'text', text: 'restore the selector' }], source: { kind: 'user' } }), surfaceOp: 'append' },
{ type: 'step/start', seq: 2, time: Date.parse(`${day}T00:00:03Z`), data: { turn: 1, step: 1 } },
{ type: 'request/header', seq: 3, time: Date.parse(`${day}T00:00:04Z`), data: { header: { config: { provider: 'deepseek', model: 'deepseek-v4-pro' } }, reason: 'initial' } },
{ type: 'request/header', seq: 3, time: Date.parse(`${day}T00:00:04Z`), data: { header: { config: { provider: 'deepseek-official', model: 'deepseek-v4-pro' } }, reason: 'initial' } },
{ type: 'assistant/message', seq: 4, time: Date.parse(`${day}T00:00:05Z`), data: {
turn: 1, step: 1,
message: createMessage({
role: 'assistant',
content: [{ type: 'text', text: 'ready' }],
source: { kind: 'model', provider: 'deepseek', model: 'deepseek-v4-pro' },
source: { kind: 'model', provider: 'deepseek-official', model: 'deepseek-v4-pro' },
}),
}, surfaceOp: 'append' },
{ type: 'step/end', seq: 5, time: Date.parse(`${day}T00:00:06Z`), data: { turn: 1, step: 1 } },
@@ -873,7 +914,7 @@ describe('TUI terminal-state snapshots', () => {
const harness = await setupSnapshot({
contextWindow: 128_000,
contextTokens: 42_000,
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-pro' },
agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-pro' },
tools: {
read: {
name: 'read',

View File

@@ -9,6 +9,7 @@ import AgentRegistry, {
} from '@deepseek-ai/dsh-agent'
import { createUserMessage,
createToolResultMessage,
freezeMessage,
ReasoningEffortId,
type LlmCallConfig,
type LlmModelReasoningInfo,
@@ -16,6 +17,7 @@ import { createUserMessage,
} from '@deepseek-ai/dsh-llm'
import { GOAL_CHANGE_VERSION, GoalId, renderGoalChange, type GoalSnapshotChangeMeta } from '@deepseek-ai/dsh-goal'
import CommandService, { type CommandInvocation } from '@deepseek-ai/dsh-commands'
import { COMPACT_CHECKPOINT_SOURCE } from '@deepseek-ai/dsh-compact'
import SessionStore, { SessionId, type JsonValue, type SessionEvent, type SessionHeader, type TurnEndReason } from '@deepseek-ai/dsh-session'
import type { SessionRecord } from '@deepseek-ai/dsh-session-query'
import SkillService, { type SkillCatalogSnapshot, type SkillDefinition, type SkillProvider, type SkillSummary } from '@deepseek-ai/dsh-skill'
@@ -26,6 +28,7 @@ import SessionReferenceService, { formatSessionReferenceMention } from '@deepsee
import type {} from '@deepseek-ai/dsh-llm-retry'
import {
createTuiChat,
disposeRootAndExit,
FILE_REFERENCE_PROMPT,
mountTui,
renderSkillInvocation,
@@ -235,7 +238,7 @@ describe('goodbye message and /resume', () => {
({ version: 0, id: SessionId(id), createdAt, cwd })
const resumeEvents = (
title: string,
provider = 'deepseek',
provider = 'deepseek-official',
time = 100,
reason: TurnEndReason = { kind: 'completed' },
): SessionEvent[] => [
@@ -307,8 +310,8 @@ describe('goodbye message and /resume', () => {
sessionPersistence: {
list: async () => [older, newer, header('foreign-session', 3000, '/elsewhere')],
load: async id => id === newer.id
? { meta: newer, events: resumeEvents('Newer product work', 'deepseek', 300) }
: { meta: older, events: resumeEvents('Older investigation', 'deepseek', 100) },
? { meta: newer, events: resumeEvents('Newer product work', 'deepseek-official', 300) }
: { meta: older, events: resumeEvents('Older investigation', 'deepseek-official', 100) },
},
})
result.terminal.send('/resume')
@@ -407,7 +410,7 @@ describe('goodbye message and /resume', () => {
list: async () => targets,
load: async id => ({
meta: targets.find(target => target.id === id)!,
events: resumeEvents(`Paged ${id.slice('paged-'.length)}`, 'deepseek', 1000 - Number(id.slice('paged-'.length)) * 10),
events: resumeEvents(`Paged ${id.slice('paged-'.length)}`, 'deepseek-official', 1000 - Number(id.slice('paged-'.length)) * 10),
}),
},
})
@@ -463,7 +466,7 @@ describe('goodbye message and /resume', () => {
cwd: '/workspace',
sessionPersistence: {
list: async () => [target],
load: async () => ({ meta: target, events: resumeEvents(`Turn ${label}`, 'deepseek', 100, reason) }),
load: async () => ({ meta: target, events: resumeEvents(`Turn ${label}`, 'deepseek-official', 100, reason) }),
},
})
result.terminal.send('/resume')
@@ -492,6 +495,41 @@ describe('goodbye message and /resume', () => {
await dispose(result)
})
it('allows a transient session-query state but rejects a terminal state', async () => {
let queryCtx: Context | undefined
let listCalls = 0
const result = await setup({
cwd: '/workspace',
async configureContext(ctx) {
await ctx.plugin({
apply(child: Context) {
queryCtx = child
child.provide('sessionQuery', {
listSessions: async () => { listCalls++; return [] },
} as never)
},
})
},
})
if (queryCtx === undefined) throw new Error('query provider did not mount')
const activeState = queryCtx.fiber.state
queryCtx.fiber.state = 0
result.terminal.send('/resume')
result.terminal.send('\r')
await tick(); await tick()
expect(listCalls).toBe(1)
result.terminal.send('\u001B')
await tick()
queryCtx.fiber.state = 5
result.terminal.send('/resume')
result.terminal.send('\r')
await tick()
expect(result.terminal.output).toContain('session query is not mounted')
expect(listCalls).toBe(1)
queryCtx.fiber.state = activeState
await dispose(result)
})
it('keeps persisted query records readable without a persistence service', async () => {
const target = header('query-only-persisted', 10, '/workspace')
const result = await setup({
@@ -664,7 +702,7 @@ describe('goodbye message and /resume', () => {
it('falls back to assistant provenance and header creation time for sparse logs', async () => {
const assistantOnly = header('assistant-route', 20, '/workspace')
const empty = header('empty-log', 10, '/workspace')
const events = resumeEvents('Assistant route', 'deepseek')
const events = resumeEvents('Assistant route', 'deepseek-official')
.filter(event => event.type !== 'request/header')
.map((event, seq) => ({ ...event, seq })) as SessionEvent[]
const result = await setup({
@@ -679,7 +717,7 @@ describe('goodbye message and /resume', () => {
result.terminal.send('/resume')
result.terminal.send('\r')
await tick(); await tick()
expect(result.terminal.output).toContain('deepseek/model-1')
expect(result.terminal.output).toContain('deepseek-official/model-1')
expect(result.terminal.output).toContain(new Date(empty.createdAt).toISOString())
await dispose(result)
})
@@ -2316,7 +2354,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
contextWindow: 128_000,
contextTokens: 42_000,
config: { showReasoning: false },
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-pro' },
agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-pro' },
tools: {
read: {
name: 'read', description: 'Read a file', parameters: {},
@@ -2364,7 +2402,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
expect(result.terminal.output).toContain('main-session')
expect(result.terminal.output).toContain('Inspect status \\x1b]2;unsafe\\x07')
expect(result.terminal.output).toContain('/workspace/status')
expect(result.terminal.output).toContain('deepseek/deepseek-v4-pro (effort default; reasoning blocks')
expect(result.terminal.output).toContain('deepseek-official/deepseek-v4-pro (effort default; reasoning blocks')
expect(result.terminal.output).toContain('hidden)')
// 6 domain events + the /status invocation's own command/run (open turn: joined directly).
expect(result.terminal.output).toContain('running · 7 events · 1 turn · 1 step · 2 tool calls')
@@ -3486,7 +3524,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
const failed = await setup({
catalog: {
providers: [{ id: 'deepseek', name: 'DeepSeek' }],
providers: [{ id: 'deepseek-official', name: 'DeepSeek' }],
models: [],
listModels: () => Promise.reject(new Error('catalog offline')),
resolveModelInfo: () => Promise.reject(new Error('capacity offline')),
@@ -3502,8 +3540,8 @@ describe('pi-tui chat lifecycle and transcript', () => {
const reasoningFailed = await setup({
catalog: {
providers: [{ id: 'deepseek', name: 'DeepSeek' }],
models: [{ provider: 'deepseek', id: 'model-1', name: 'Model One' }],
providers: [{ id: 'deepseek-official', name: 'DeepSeek' }],
models: [{ provider: 'deepseek-official', id: 'model-1', name: 'Model One' }],
resolveModelInfo: () => Promise.reject(new Error('reasoning metadata offline')),
},
})
@@ -3519,7 +3557,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
const deferred = Promise.withResolvers<never[]>()
const result = await setup({
catalog: {
providers: [{ id: 'deepseek', name: 'DeepSeek' }],
providers: [{ id: 'deepseek-official', name: 'DeepSeek' }],
models: [],
listModels: () => deferred.promise,
},
@@ -3535,7 +3573,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
const rejected = Promise.withResolvers<never[]>()
const rejectedResult = await setup({
catalog: {
providers: [{ id: 'deepseek', name: 'DeepSeek' }],
providers: [{ id: 'deepseek-official', name: 'DeepSeek' }],
models: [],
listModels: () => rejected.promise,
},
@@ -3552,7 +3590,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
const contextResult = await setup({
contextTokens: 99,
catalog: {
providers: [{ id: 'deepseek', name: 'DeepSeek' }],
providers: [{ id: 'deepseek-official', name: 'DeepSeek' }],
models: [],
resolveModelInfo: () => context.promise.then(value => ({ context: value })),
},
@@ -4269,6 +4307,14 @@ describe('tool cards and surface replay', () => {
name: 'knownXml', description: '', parameters: {}, output: UNUSED_TOOL_OUTPUT, execute: async () => [],
presentCall: () => ({ card: 'generic', title: 'Known XML' }),
},
// A web card carries no `content` copy, so it falls back to the raw result
// content, which must still render through the dim Markdown path (bold
// markers stripped) rather than as bare text.
webCard: {
name: 'webCard', description: '', parameters: {}, output: UNUSED_TOOL_OUTPUT, execute: async () => [],
presentCall: () => ({ card: 'generic', title: 'Fetch page', kind: 'fetch' }),
presentResult: () => ({ card: 'web', kind: 'fetch', title: 'https://a.test', url: 'https://a.test', statusCode: 200, truncated: false }),
},
}
it('uses terminal, diff, generic, fallback, and collapsed tool presentations', async () => {
@@ -4289,6 +4335,7 @@ describe('tool cards and surface replay', () => {
['c11', 'terminalResult', '{}'],
['c12', 'symbolic', '{}'],
['c13', 'knownXml', '{}'],
['c16', 'webCard', '{}'],
] as const
appendAssistant(result.session, [
{ type: 'text', text: 'Calling tools' },
@@ -4382,6 +4429,14 @@ describe('tool cards and surface replay', () => {
isError: false,
}),
}, { surfaceOp: 'append' })
result.session.append('tool/result', {
turn: 1, step: 1,
message: createToolResultMessage({
callId: 'c16' as never,
content: [{ type: 'text', text: 'Fetched **body** text' }],
isError: false,
}),
}, { surfaceOp: 'append' })
result.session.append('tool/result', {
turn: 1,
step: 1,
@@ -4431,6 +4486,11 @@ describe('tool cards and surface replay', () => {
expect(output).toContain('Empty card')
expect(output).toContain('converted terminal')
expect(output).toContain('<known><value>literal</value></known>')
// A web card carries no `content` copy, so it falls back to the raw result
// content, which still renders through the dim Markdown path: the bold
// markers are stripped rather than shown literally.
expect(output).toContain('Fetched body text')
expect(output).not.toContain('Fetched **body** text')
expect(output).toContain('path: /tmp/a.txt')
expect(output).toContain('line (number="1"): hello')
expect(output).not.toContain('<result>')
@@ -4555,10 +4615,10 @@ describe('tool cards and surface replay', () => {
await dispose(result)
})
it('rebuilds after a surface replacement and hides shadowed tool calls', async () => {
it('keeps append-origin history and marks a landed compaction, live and on rebuild', async () => {
const result = await setup({ tools })
appendUser(result.session, 'old prompt')
const assistant = result.session.append('assistant/message', {
result.session.append('assistant/message', {
turn: 1,
step: 1,
message: createMessage({
@@ -4581,21 +4641,116 @@ describe('tool cards and surface replay', () => {
isError: false,
}),
}, { surfaceOp: 'append' })
const start = result.session.surface.nodes[0] as number
result.session.append('user/message', createUserMessage({
content: [{ type: 'text', text: 'summary replacement' }],
source: { kind: 'plugin', plugin: 'compact' },
}), {
surfaceOp: { op: 'replace', start, end: toolResult.seq },
sourceEventSeqs: [start, assistant.seq, toolResult.seq],
// Result pruning rewrites one node's content in place: model-only, and no
// boundary in the conversation, so the terminal keeps the full output.
const originalResult = toolResult.data.message.content[0]
result.session.append('tool/result', {
...toolResult.data,
message: freezeMessage({
...toolResult.data.message,
content: [{ ...originalResult, content: [{ type: 'text', text: 'pruned result copy' }] }] as [typeof originalResult],
}),
}, {
surfaceOp: { op: 'replace', start: toolResult.seq, end: toolResult.seq },
sourceEventSeqs: [toolResult.seq],
})
const nodes = [...result.session.surface.nodes]
const checkpoint = result.session.append('user/message', createUserMessage({
content: [{ type: 'text', text: '<context_checkpoint>model-only summary payload</context_checkpoint>' }],
source: COMPACT_CHECKPOINT_SOURCE,
}), {
surfaceOp: { op: 'replace', start: nodes[0] as number, end: nodes.at(-1) as number },
sourceEventSeqs: nodes,
})
// A regenerated assistant message replaces one node without summarizing
// anything, so it marks no boundary either.
const generic = result.session.append('assistant/message', {
turn: 1,
step: 1,
message: createMessage({
role: 'assistant',
content: [{ type: 'text', text: 'generic replacement copy' }],
source: {
kind: 'model',
...{ provider: 'mock', model: 'deepseek-v4-flash' },
},
}),
}, { surfaceOp: { op: 'replace', start: checkpoint.seq, end: checkpoint.seq }, sourceEventSeqs: [checkpoint.seq] })
// Only a checkpoint carrying the compaction seam's source marks a boundary:
// another plugin replacing a node is model-only.
result.session.append('user/message', createUserMessage({
content: [{ type: 'text', text: 'foreign plugin replacement copy' }],
source: { kind: 'plugin', plugin: 'other' },
}), { surfaceOp: { op: 'replace', start: generic.seq, end: generic.seq }, sourceEventSeqs: [generic.seq] })
await tick()
result.terminal.resize(89)
await tick()
const lastFullRender = result.terminal.output.slice(result.terminal.output.lastIndexOf('\x1b[2J'))
expect(lastFullRender).toContain('summary replacement')
expect(lastFullRender).not.toContain('old output')
const liveRender = result.terminal.output.slice(result.terminal.output.lastIndexOf('\x1b[2J'))
expect(liveRender).toContain('old prompt')
// The shadowed step keeps its card: one call row, one full result, no
// second card from the pruned copy.
expect(liveRender.split('$ printf hello')).toHaveLength(2)
expect(liveRender).toContain('third')
expect(liveRender.split('[exit 0]')).toHaveLength(2)
expect(liveRender.split('… earlier context was compacted …')).toHaveLength(2)
expect(liveRender).not.toContain('model-only summary payload')
expect(liveRender).not.toContain('generic replacement copy')
expect(liveRender).not.toContain('foreign plugin replacement copy')
// Ctrl+R toggles reasoning, which rebuilds the transcript from the log; the
// replayed projection matches what the live appends produced, including the
// shadowed assistant message's tool card.
result.terminal.send('\x12')
await tick()
result.terminal.resize(90)
await tick()
const replayRender = result.terminal.output.slice(result.terminal.output.lastIndexOf('\x1b[2J'))
expect(replayRender).toContain('old prompt')
expect(replayRender.split('$ printf hello')).toHaveLength(2)
expect(replayRender).toContain('third')
expect(replayRender.split('[exit 0]')).toHaveLength(2)
expect(replayRender.split('… earlier context was compacted …')).toHaveLength(2)
expect(replayRender).not.toContain('model-only summary payload')
expect(replayRender).not.toContain('generic replacement copy')
expect(replayRender).not.toContain('foreign plugin replacement copy')
await dispose(result)
})
it('replays a stored compaction as preserved history plus its marker', async () => {
const result = await setup({
beforeMount(session) {
appendUser(session, 'prompt before compaction')
session.append('assistant/message', {
turn: 1,
step: 1,
message: createMessage({
role: 'assistant',
content: [{ type: 'text', text: 'reply before compaction' }],
source: {
kind: 'model',
...{ provider: 'mock', model: 'deepseek-v4-flash' },
},
}),
}, { surfaceOp: 'append' })
const nodes = [...session.surface.nodes]
session.append('user/message', createUserMessage({
content: [{ type: 'text', text: '<context_checkpoint>stored model-only payload</context_checkpoint>' }],
source: COMPACT_CHECKPOINT_SOURCE,
}), {
surfaceOp: { op: 'replace', start: nodes[0] as number, end: nodes.at(-1) as number },
sourceEventSeqs: nodes,
})
},
})
result.terminal.resize(89)
await tick()
const mounted = result.terminal.output.slice(result.terminal.output.lastIndexOf('\x1b[2J'))
expect(mounted).toContain('prompt before compaction')
expect(mounted).toContain('reply before compaction')
expect(mounted.split('… earlier context was compacted …')).toHaveLength(2)
expect(mounted).not.toContain('stored model-only payload')
await dispose(result)
})
})
@@ -4892,6 +5047,59 @@ describe('TUI extension service', () => {
})
})
describe('application exit', () => {
it('disposes the root fiber rather than only the TUI child before exiting', async () => {
const rootDispose = vi.fn(() => Promise.resolve())
const childDispose = vi.fn(() => Promise.resolve())
const ctx = {
root: { fiber: { dispose: rootDispose } },
fiber: { dispose: childDispose },
} as unknown as Context
const exit = vi.fn()
disposeRootAndExit(ctx, 7, exit)
await Promise.resolve()
expect(rootDispose).toHaveBeenCalledOnce()
expect(childDispose).not.toHaveBeenCalled()
expect(exit).toHaveBeenCalledOnce()
expect(exit).toHaveBeenCalledWith(7)
})
it('forces exit when root disposal does not settle', async () => {
vi.useFakeTimers()
try {
let settle!: () => void
const disposal = new Promise<void>((resolve) => { settle = resolve })
const ctx = {
root: { fiber: { dispose: () => disposal } },
} as unknown as Context
const exit = vi.fn()
disposeRootAndExit(ctx, 9, exit)
await vi.advanceTimersByTimeAsync(4_999)
expect(exit).not.toHaveBeenCalled()
await vi.advanceTimersByTimeAsync(1)
expect(exit).toHaveBeenCalledOnce()
expect(exit).toHaveBeenCalledWith(9)
settle()
await disposal
await Promise.resolve()
expect(exit).toHaveBeenCalledOnce()
} finally {
vi.useRealTimers()
}
})
it('exits after a rejected root disposal without an unhandled rejection', async () => {
const ctx = {
root: { fiber: { dispose: () => Promise.reject(new Error('cleanup failed')) } },
} as unknown as Context
const exit = vi.fn()
disposeRootAndExit(ctx, 5, exit)
await Promise.resolve()
await Promise.resolve()
expect(exit).toHaveBeenCalledWith(5)
})
})
describe('terminal mounting', () => {
it('starts immediately when the configured agent already exists', async () => {
const ctx = new Context()

View File

@@ -53,6 +53,9 @@
{
"path": "../commands"
},
{
"path": "../../compact/compact"
},
{
"path": "../../skill/skill"
},

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/ui/user-interaction/README.md
README.md: d234d6677bdd772f1bbd2c979c0d41f90aef5c32
README.zh.md: c89210b6955a661313ca9e0e82e43da5a4d1db79
README.md: d62e75d110b8be339c5f9449b0834320f695ac99
README.zh.md: 55258e85e56df2375ed8f195fa0b3b731a9cb816

View File

@@ -13,14 +13,19 @@ Abstract user-interaction seam. It owns `ctx.userInteraction`, the service a mod
### Key Types
- `AskUserQuestionRequest` — `{ questions: [{ id, question, detail?, header?, options?, multiSelect? }], agent?, signal? }`; `detail` supplies supporting text that providers render with the question without turning it into an option label.
- `AskUserQuestionRequest` — `{ questions: [{ id, question, detail?, header?, options?, multiSelect?, intent? }], agent?, signal? }`; `detail` supplies supporting text that providers render with the question without turning it into an option label.
- `AskUserQuestionOption` — `{ label, description? }`.
- `AskUserQuestionIntent` — `{ kind: 'plan-review', approve }`; the tagged presentation intent below.
- `AskUserQuestionAnswer` — `{ answers: [{ id, selected, custom? }] }`.
- `UserInteractionProvider` — UI implementation with `ask(request)`.
- `UserInteractionError` — `HarnessError` subclass with codes such as `EMPTY_QUESTIONS`, `NO_PROVIDER`, `DUPLICATE_PROVIDER`, and `ASK_ABORTED`.
- `UserInteractionError` — `HarnessError` subclass with codes such as `EMPTY_QUESTIONS`, `BAD_INTENT`, `NO_PROVIDER`, `DUPLICATE_PROVIDER`, and `ASK_ABORTED`.
When an answer includes `custom`, `selected` is empty; custom text is an override rather than a supplement to selected choices. A UI may preserve a skipped item as `{ id, selected: [] }`, keeping the existing answer shape while retaining other answers in the batch.
### Presentation intent
`intent` declares that a question IS a decision of a known shape, so a UI that recognises the tag may present it as such — `plan-review` says `detail` is a plan under review, and `dsh-plan-mode` sets it on the `exit_plan_mode` question. An intent shapes presentation only: a UI honouring it answers with the same option labels a generic UI would send, and a UI that does not know the tag renders the generic option list, so callers read one answer shape either way. `approve` names the label that approves rather than relying on option order. `ask()` rejects with `BAD_INTENT` the two assertions no type can carry: an `approve` naming none of that question's own options, and an intent on a question with no `detail` — the thing it declares itself a review of.
## Role
This is the interface package. Model-facing consumers such as `@deepseek-ai/dsh-tool-ask-user` depend on this seam; `dsh-tui` and the host runtime provide interactive implementations. The loop stays unchanged: a tool call awaits a promise, and the tool result resumes the normal agent loop.

View File

@@ -13,14 +13,19 @@
### 关键类型
- `AskUserQuestionRequest`:`{ questions: [{ id, question, detail?, header?, options?, multiSelect? }], agent?, signal? }`;`detail` 提供辅助文本,提供方会将其随问题一起渲染,而不会将其变成选项标签。
- `AskUserQuestionRequest`:`{ questions: [{ id, question, detail?, header?, options?, multiSelect?, intent? }], agent?, signal? }`;`detail` 提供辅助文本,提供方会将其随问题一起渲染,而不会将其变成选项标签。
- `AskUserQuestionOption`:`{ label, description? }`。
- `AskUserQuestionIntent`:`{ kind: 'plan-review', approve }`;即下文的带标签呈现意图。
- `AskUserQuestionAnswer`:`{ answers: [{ id, selected, custom? }] }`。
- `UserInteractionProvider`:包含 `ask(request)` 的 UI 实现。
- `UserInteractionError`:`HarnessError` 的子类,包含 `EMPTY_QUESTIONS`、`NO_PROVIDER`、`DUPLICATE_PROVIDER` 和 `ASK_ABORTED` 等代码。
- `UserInteractionError`:`HarnessError` 的子类,包含 `EMPTY_QUESTIONS`、`BAD_INTENT`、`NO_PROVIDER`、`DUPLICATE_PROVIDER` 和 `ASK_ABORTED` 等代码。
当回答包含 `custom` 时,`selected` 为空;自定义文本是所选选项的替代,而不是补充。UI 可以把跳过的条目保留为 `{ id, selected: [] }`,既维持现有回答形态,也保留该批次中的其他回答。
### 呈现意图
`intent` 声明某个问题本身就是一次已知形状的决定,因此认识该标签的 UI 可以照此呈现 —— `plan-review` 表示 `detail` 是一份待审阅的计划,`dsh-plan-mode` 会在 `exit_plan_mode` 的问题上设置它。意图只塑造呈现:遵循它的 UI 回答的仍是通用 UI 会发送的那些选项标签,不认识该标签的 UI 渲染通用选项列表,因此调用方两种情况下读到的都是同一种回答形态。`approve` 指名表示批准的标签,而不依赖选项顺序。有两项断言是任何类型都承载不了的,`ask()` 会以 `BAD_INTENT` 拒绝它们:`approve` 未命中该问题自身的任一选项,以及意图落在没有 `detail` 的问题上 —— 而 `detail` 正是它自称在审阅的东西。
## 职责
这是接口包(package)。`@deepseek-ai/dsh-tool-ask-user` 等面向模型的消费方依赖此 seam;`dsh-tui` 和宿主运行时提供交互式实现。循环保持不变:工具调用等待 Promise,工具结果随后恢复正常的 agent loop(智能体循环)。

View File

@@ -20,7 +20,8 @@ declare module 'cordis' {
import type { AskUserQuestionAnswer, AskUserQuestionItem } from './types.ts'
export type {
AskUserQuestionAnswer, AskUserQuestionAnswerItem, AskUserQuestionItem, AskUserQuestionOption,
AskUserQuestionAnswer, AskUserQuestionAnswerItem, AskUserQuestionIntent, AskUserQuestionItem,
AskUserQuestionOption,
} from './types.ts'
/** Request for a human answer. */
@@ -86,6 +87,28 @@ export class UserInteractionService extends Service {
if (request.questions.length === 0) {
throw new UserInteractionError('ask_user_question requires at least one question', 'EMPTY_QUESTIONS')
}
// A presentation intent asserts two things the types cannot: that the
// named approve label is one of this question's own options, and that a
// plan-review carries the plan it is a review of. A UI honouring the
// intent answers with that label, and shows that detail as the plan, so
// either gap would put a choice the asker never offered — or an approval of
// something invisible — in front of the user. Caught at the asker, where
// the mistake is, rather than in each UI.
for (const question of request.questions) {
const intent = question.intent
if (intent === undefined) continue
if (!(question.options ?? []).some(option => option.label === intent.approve)) {
throw new UserInteractionError(
`question ${question.id} declares intent ${intent.kind} whose approve label `
+ `${JSON.stringify(intent.approve)} names none of its options`,
'BAD_INTENT')
}
if (question.detail === undefined) {
throw new UserInteractionError(
`question ${question.id} declares intent ${intent.kind} without the detail it reviews`,
'BAD_INTENT')
}
}
if (this.provider === undefined) {
throw new UserInteractionError('no user-interaction provider is registered', 'NO_PROVIDER')
}

View File

@@ -13,6 +13,24 @@ export interface AskUserQuestionOption {
description?: string
}
/**
* A caller-declared presentation intent: the question IS a decision of this
* shape, so a UI that recognises the tag may present it as such instead of as a
* generic option list. Tagged so further intents can be added; a UI that does
* not know a tag renders the generic flow, and the answer encoding is identical
* either way — an intent shapes presentation only, never the protocol.
*/
export type AskUserQuestionIntent = {
/** A plan submitted for review: `detail` is the plan markdown `ask()` requires, and the decision approves or declines it. */
kind: 'plan-review'
/**
* The option label that approves the plan; every other option declines it.
* Named rather than positional so no UI infers the verdict from option order.
* An `approve` naming no option of its own question is rejected at `ask()`.
*/
approve: string
}
/** One question in a user-interaction request. */
export interface AskUserQuestionItem {
/** Stable caller-provided question id, echoed in the answer. */
@@ -27,6 +45,8 @@ export interface AskUserQuestionItem {
options?: AskUserQuestionOption[]
/** Whether more than one option may be selected. Defaults to single-select. */
multiSelect?: boolean
/** Optional presentation intent for capable UIs; absent asks for the generic option list. */
intent?: AskUserQuestionIntent
}
/** Answer to one question. */

View File

@@ -83,4 +83,63 @@ describe('UserInteractionService', () => {
.rejects.toMatchObject({ name: 'UserInteractionError', code: 'EMPTY_QUESTIONS' })
expect(p.ask).not.toHaveBeenCalled()
})
it('rejects an intent whose approve label names none of its own options', async () => {
const ctx = new Context()
await ctx.plugin(UserInteractionService)
const p = { ask: vi.fn(async () => ({ answers: [] })) }
ctx.userInteraction.registerProvider(p)
const question = { id: 'plan-review', question: 'Approve?', detail: '# Plan' }
// A wrong label among offered options, and no options offered at all.
for (const options of [[{ label: 'Approve' }], undefined]) {
await expect(ctx.userInteraction.ask({
questions: [{
...question,
...(options === undefined ? {} : { options }),
intent: { kind: 'plan-review', approve: 'Ship it' },
}],
})).rejects.toMatchObject({ name: 'UserInteractionError', code: 'BAD_INTENT' })
}
expect(p.ask).not.toHaveBeenCalled()
})
it('rejects a plan-review intent on a question carrying no plan to review', async () => {
const ctx = new Context()
await ctx.plugin(UserInteractionService)
const p = { ask: vi.fn(async () => ({ answers: [] })) }
ctx.userInteraction.registerProvider(p)
// Detail IS the plan for this intent, so a UI honouring it would ask the
// user to approve something they cannot see.
await expect(ctx.userInteraction.ask({
questions: [{
id: 'plan-review', question: 'Approve?',
options: [{ label: 'Approve' }, { label: 'Keep planning' }],
intent: { kind: 'plan-review', approve: 'Approve' },
}],
})).rejects.toMatchObject({ name: 'UserInteractionError', code: 'BAD_INTENT' })
expect(p.ask).not.toHaveBeenCalled()
})
it('passes an intent through once its approve label names an offered option', async () => {
const ctx = new Context()
await ctx.plugin(UserInteractionService)
const p = provider('Approve')
ctx.userInteraction.registerProvider(p)
const intent = { kind: 'plan-review', approve: 'Approve' } as const
const result = await ctx.userInteraction.ask({
questions: [
{ id: 'plain', question: 'Proceed?' },
{
id: 'plan-review', question: 'Approve?', detail: '# Plan',
options: [{ label: 'Approve' }, { label: 'Keep planning' }], intent,
},
],
})
expect(result.answers).toEqual([{ id: 'plain', selected: ['Approve'] }])
expect(p.seen[0]?.questions[1]?.intent).toEqual(intent)
})
})