Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: apply repository naming contract

Browse Source 
Apply the accepted pre-release package, service, type, directory, and role renames as one repository-wide change.
This commit is contained in:
Tianyi Cui
2026-08-13 00:36:22 +08:00
parent 101df7cf58
commit a2d0f7f411
3281 changed files with 21730 additions and 21592 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
packages/subagent/tool-subagent/README.i18n.yaml
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/subagent/tool-subagent/README.md
README.md: cc872f3decc4c85f26bd997293c8dc4140eb221c
README.zh.md: bea9b212bf6d551446ba05c8f5b446a0347dd718
README.md: 9d7ed2e364f6a9dff26a1c9006535f898bdaabcc
README.zh.md: 8650ee35588c2615e4d6c016cb672030ee2e8194

8
packages/subagent/tool-subagent/README.md
View File

@@ -10,7 +10,7 @@ Each plugin instance binds one `provider` to one `toolName`; the model receives
A foreground call passes the execution signal through startup and execution, awaits `run.result`, and always awaits `run.dispose()` before returning. Only `completed` returns the canonical `{ kind: 'foreground', runId, output: JsonValue[] }`, rendered as the same final text; abort, refusal, token limit, and other failures become errored tool results whose message appends the child's preserved partial text (the `SubagentResult.output` selection) after the stop-reason headline, so a truncated answer is never reported as success yet never silently lost. If result collection and disposal both reject, the errored result preserves both diagnostics.
`backgroundMode` selects both the background route and the omitted `run_in_background` default. `one-shot` waits in the foreground by default; an explicit `true` registers a plain parent-owned Task and returns canonical `{ kind: 'background', taskId }`, rendered as `started background subagent task <id>`, even when the provider supports continuable children. Generic task tools own its later status, collection, cancellation, and notices. `continuable` runs in the background when the argument is omitted or `true`; an explicit `false` waits for the result in the foreground. Its background route requires a provider with the `prepareContinuable` capability, calls `ctx.subagents.startContinuable()`, and returns `{ kind: 'continuable', subagentId }`, rendered as `started subagent <childId>`. The route resolves at inbox acceptance: the child owns its own turns from there, so this call neither waits for nor collects a result. The child's transcript by that id remains the source of its detailed output, and the optional global `send_message` tool sends it more work. The continuation service delivers one settlement notice whenever the child's Activation ends, containing its outcome and any final assistant message independently of `report`. Starting continuable work does not require `send_message` to be loaded. See the [background subagent Agent Note](../../../.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md), the [continuable subagents Agent Note](../../../.agents/notes/implemented/feature/2026-07-28-continuable-subagent-conversations.md), and the [background-first delegation Agent Note](../../../.agents/notes/implemented/feature/2026-08-11-background-first-continuable-delegation.md).
`backgroundMode` selects both the background route and the omitted `run_in_background` default. `one-shot` waits in the foreground by default; an explicit `true` registers a plain parent-owned Task and returns canonical `{ kind: 'background', jobId }`, rendered as `started background subagent job <id>`, even when the provider supports continuable children. Generic task tools own its later status, collection, cancellation, and notices. `continuable` runs in the background when the argument is omitted or `true`; an explicit `false` waits for the result in the foreground. Its background route requires a provider with the `prepareContinuable` capability, calls `ctx.subagents.startContinuable()`, and returns `{ kind: 'continuable', subagentId }`, rendered as `started subagent <childId>`. The route resolves at inbox acceptance: the child owns its own turns from there, so this call neither waits for nor collects a result. The child's transcript by that id remains the source of its detailed output, and the optional global `send_message` tool sends it more work. The continuation service delivers one settlement notice whenever the child's Activation ends, containing its outcome and any final assistant message independently of `report`. Starting continuable work does not require `send_message` to be loaded. See the [background subagent Agent Note](../../../.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md), the [continuable subagents Agent Note](../../../.agents/notes/implemented/feature/2026-07-28-continuable-subagent-conversations.md), and the [background-first delegation Agent Note](../../../.agents/notes/implemented/feature/2026-08-11-background-first-continuable-delegation.md).
`toolFilter` changes the child's global tool layer but is not a parent-derived authority ceiling. See the [agent-scope security non-goal](../../../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-non-goals).
@@ -29,7 +29,7 @@ A foreground call passes the execution signal through startup and execution, awa
## Concurrency
Foreground and background calls are concurrency-safe: sibling delegations in one assistant message overlap under the loop's rolling pool (`maxParallelToolCalls`), and results still commit in model order. Children work in their own sessions and a run never mutates the parent session; the one-shot background form's one parent-owned write — registering a Task — is a synchronous, commutative insertion that tolerates concurrent dispatch, so overlapping background calls acquire their task ids in dispatch-race order. Coordinating sibling workspace effects belongs to the model, exactly as it already does for background and continuable children. See the [parallel subagent Agent Note](../../../.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.md) and the [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md).
Foreground and background calls are concurrency-safe: sibling delegations in one assistant message overlap under the loop's rolling pool (`maxParallelToolCalls`), and results still commit in model order. Children work in their own sessions and a run never mutates the parent session; the one-shot background form's one parent-owned write — registering a Task — is a synchronous, commutative insertion that tolerates concurrent dispatch, so overlapping background calls acquire their job ids in dispatch-race order. Coordinating sibling workspace effects belongs to the model, exactly as it already does for background and continuable children. See the [parallel subagent Agent Note](../../../.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.md) and the [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md).
## Model Experience
@@ -37,7 +37,7 @@ Foreground and background calls are concurrency-safe: sibling delegations in one
#### What the model sees
The generated default [`subagent` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-subagent) under this instance's configured name while its provider exists. Provider context inheritance changes the tool and prompt descriptions. Enabled background mode adds `run_in_background`: continuable mode documents its `true` default, runtime settlement notice, and explicit foreground override, while one-shot mode documents its `false` default and the task id collected with `task_output` or stopped with `task_kill`. While the tool is visible in an assembly's scope, a `tool:<toolName>` system-prompt section tells the model to start independent continuable delegations together, keep working while they run, and choose foreground only when its next action depends on the result; a tool restriction removes both its schema and this guidance.
The generated default [`subagent` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-subagent) under this instance's configured name while its provider exists. Provider context inheritance changes the tool and prompt descriptions. Enabled background mode adds `run_in_background`: continuable mode documents its `true` default, runtime settlement notice, and explicit foreground override, while one-shot mode documents its `false` default and the job id collected with `job_output` or stopped with `job_kill`. While the tool is visible in an assembly's scope, a `tool:<toolName>` system-prompt section tells the model to start independent continuable delegations together, keep working while they run, and choose foreground only when its next action depends on the result; a tool restriction removes both its schema and this guidance.
#### Token effect
@@ -65,7 +65,7 @@ Append-only; newly visible content follows the reusable request prefix and does
#### What the model sees
Start returns exactly `started subagent <childId>` in configured continuable mode, or `started background subagent task <id>` in configured one-shot mode. In one-shot mode the generic task surface provides later status, final output, cancellation responses, and notices. In continuable mode this tool returns no result of its own; the child's settlement reaches the parent as a [service-owned notice](../subagent/README.md#settlement-notice), an independently loaded `send_message` tool delivers follow-ups, and the child's transcript by its id is the source of its detailed output.
Start returns exactly `started subagent <childId>` in configured continuable mode, or `started background subagent job <id>` in configured one-shot mode. In one-shot mode the generic task surface provides later status, final output, cancellation responses, and notices. In continuable mode this tool returns no result of its own; the child's settlement reaches the parent as a [service-owned notice](../subagent/README.md#settlement-notice), an independently loaded `send_message` tool delivers follow-ups, and the child's transcript by its id is the source of its detailed output.
#### Token effect

8
packages/subagent/tool-subagent/README.zh.md
View File

@@ -10,7 +10,7 @@
前台调用会让执行信号贯穿启动和执行，等待 `run.result`，并且在返回前总会等待 `run.dispose()`。只有 `completed` 会返回规范值 `{ kind: 'foreground', runId, output: JsonValue[] }`，并渲染为相同的最终文本；中止、拒绝、token 上限和其他失败都会变成出错的工具结果，其消息在终止原因标题之后附带子 agent 保留下来的部分文本（即 `SubagentResult.output` 的选取结果）——被截断的回答不会被报告为成功，也绝不会被悄悄丢弃。如果结果收集与 dispose（资源释放）都 reject，出错的结果会保留两项诊断信息。
`backgroundMode` 同时选择后台路由与省略 `run_in_background` 时的默认行为。`one-shot` 默认在前台等待；显式传入 `true` 时，它会注册一个归父级所有的普通 Task，并返回规范值 `{ kind: 'background', taskId }`，渲染为 `started background subagent task <id>`，即使提供方支持可继续子 agent 也不例外。通用 Task 工具负责其后续状态、收集、取消和通知。`continuable` 在参数省略或为 `true` 时于后台运行；显式传入 `false` 时则在前台等待结果。其后台路由要求提供方具备 `prepareContinuable` 能力，调用 `ctx.subagents.startContinuable()`，并返回 `{ kind: 'continuable', subagentId }`，渲染为 `started subagent <childId>`。该路由在 inbox 接受时结算：子 agent 自此拥有自己的轮次，因此该调用既不等待也不收集结果。通过该 id 查看其 transcript（文本记录）仍是其详细输出的来源，可选的全局 `send_message` 工具则向其发送更多工作。每当子 agent 的 Activation 结束，继续执行服务都会投递一条结算通知，其中包含结束结果及可能存在的最终 assistant 消息，且这项投递不依赖 `report`。启动可继续工作不要求加载 `send_message`。见[后台 subagent Agent Note](../../../.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md)、[可继续的 subagent Agent Note](../../../.agents/notes/implemented/feature/2026-07-28-continuable-subagent-conversations.md)和[后台优先委派 Agent Note](../../../.agents/notes/implemented/feature/2026-08-11-background-first-continuable-delegation.md)。
`backgroundMode` 同时选择后台路由与省略 `run_in_background` 时的默认行为。`one-shot` 默认在前台等待；显式传入 `true` 时，它会注册一个归父级所有的普通 Task，并返回规范值 `{ kind: 'background', jobId }`，渲染为 `started background subagent job <id>`，即使提供方支持可继续子 agent 也不例外。通用 Task 工具负责其后续状态、收集、取消和通知。`continuable` 在参数省略或为 `true` 时于后台运行；显式传入 `false` 时则在前台等待结果。其后台路由要求提供方具备 `prepareContinuable` 能力，调用 `ctx.subagents.startContinuable()`，并返回 `{ kind: 'continuable', subagentId }`，渲染为 `started subagent <childId>`。该路由在 inbox 接受时结算：子 agent 自此拥有自己的轮次，因此该调用既不等待也不收集结果。通过该 id 查看其 transcript（文本记录）仍是其详细输出的来源，可选的全局 `send_message` 工具则向其发送更多工作。每当子 agent 的 Activation 结束，继续执行服务都会投递一条结算通知，其中包含结束结果及可能存在的最终 assistant 消息，且这项投递不依赖 `report`。启动可继续工作不要求加载 `send_message`。见[后台 subagent Agent Note](../../../.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md)、[可继续的 subagent Agent Note](../../../.agents/notes/implemented/feature/2026-07-28-continuable-subagent-conversations.md)和[后台优先委派 Agent Note](../../../.agents/notes/implemented/feature/2026-08-11-background-first-continuable-delegation.md)。
`toolFilter` 会改变子 agent 的全局工具层，但不是从父级派生的权限上限。见 [agent 作用域的安全非目标](../../../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-non-goals)。
@@ -29,7 +29,7 @@
## 并发
前台调用和后台调用均并发安全：同一条 assistant 消息中的同级委派会在循环的滚动池（`maxParallelToolCalls`）下重叠执行，结果仍按模型顺序提交。子 agent 在各自的会话中工作，一次运行绝不变更父会话；一次性后台形态对父级拥有状态的唯一写入是注册一个 Task——这是一次同步、可交换、能容忍并发分发的插入，因此重叠的后台调用按分发竞态顺序获得各自的 task id。协调同级工作区效果由模型负责，正如模型已经对后台和可继续子 agent 所承担的那样。见 [并行 subagent Agent Note](../../../.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.md) 和 [并行工具调用 Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md)。
前台调用和后台调用均并发安全：同一条 assistant 消息中的同级委派会在循环的滚动池（`maxParallelToolCalls`）下重叠执行，结果仍按模型顺序提交。子 agent 在各自的会话中工作，一次运行绝不变更父会话；一次性后台形态对父级拥有状态的唯一写入是注册一个 Task——这是一次同步、可交换、能容忍并发分发的插入，因此重叠的后台调用按分发竞态顺序获得各自的 job id。协调同级工作区效果由模型负责，正如模型已经对后台和可继续子 agent 所承担的那样。见 [并行 subagent Agent Note](../../../.agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.md) 和 [并行工具调用 Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md)。
## 模型体验
@@ -37,7 +37,7 @@
#### 模型看到的内容
当提供方存在时，以当前实例配置的名称公开已生成的默认 [`subagent` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-subagent)。提供方是否继承上下文会改变工具描述和提示词描述。启用后台模式会添加 `run_in_background`：可继续模式会记录其默认值为 `true`、运行时结算通知与显式前台覆盖；一次性模式会记录其默认值为 `false`，以及用 `task_output` 收集或用 `task_kill` 停止的 task id。当工具在本次组装的作用域中可见时，一个 `tool:<toolName>` 系统提示词 section 会指示模型同时启动相互独立的可继续委派、在它们运行时继续工作，并且仅当下一步动作依赖结果时选择前台；工具限制会同时移除其 schema 和这段指引。
当提供方存在时，以当前实例配置的名称公开已生成的默认 [`subagent` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-subagent)。提供方是否继承上下文会改变工具描述和提示词描述。启用后台模式会添加 `run_in_background`：可继续模式会记录其默认值为 `true`、运行时结算通知与显式前台覆盖；一次性模式会记录其默认值为 `false`，以及用 `job_output` 收集或用 `job_kill` 停止的 job id。当工具在本次组装的作用域中可见时，一个 `tool:<toolName>` 系统提示词 section 会指示模型同时启动相互独立的可继续委派、在它们运行时继续工作，并且仅当下一步动作依赖结果时选择前台；工具限制会同时移除其 schema 和这段指引。
#### Token 影响
@@ -65,7 +65,7 @@
#### 模型看到的内容
在配置的可继续模式下，启动时返回内容恰为 `started subagent <childId>`；在配置的一次性模式下，则返回 `started background subagent task <id>`。一次性模式下，通用 Task 接口提供后续状态、最终输出、取消响应和通知。可继续模式下，本工具不返回自己的结果；子 agent 的结算会以[服务负责的通知](../subagent/README.md#settlement-notice)到达父级，独立加载的 `send_message` 工具会投递后续消息，而通过其 id 查看子 agent 的 transcript 即是其详细输出来源。
在配置的可继续模式下，启动时返回内容恰为 `started subagent <childId>`；在配置的一次性模式下，则返回 `started background subagent job <id>`。一次性模式下，通用 Task 接口提供后续状态、最终输出、取消响应和通知。可继续模式下，本工具不返回自己的结果；子 agent 的结算会以[服务负责的通知](../subagent/README.md#settlement-notice)到达父级，独立加载的 `send_message` 工具会投递后续消息，而通过其 id 查看子 agent 的 transcript 即是其详细输出来源。
#### Token 影响

10
packages/subagent/tool-subagent/package.json
View File

@@ -37,7 +37,7 @@
"@deepseek-ai/dsh-llm": "workspace:^",
"@deepseek-ai/dsh-subagent": "workspace:^",
"@deepseek-ai/dsh-system-prompt": "workspace:^",
"@deepseek-ai/dsh-tasks": "workspace:^",
"@deepseek-ai/dsh-jobs": "workspace:^",
"@deepseek-ai/dsh-tools": "workspace:^",
"@deepseek-ai/cordis": "workspace:^"
},
@@ -53,11 +53,11 @@
"@deepseek-ai/dsh-session-persistence": "workspace:^",
"@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
"@deepseek-ai/dsh-subagent": "workspace:^",
"@deepseek-ai/dsh-subagent-spawn": "workspace:^",
"@deepseek-ai/dsh-subagent-spawn-in-process": "workspace:^",
"@deepseek-ai/dsh-system-prompt": "workspace:^",
"@deepseek-ai/dsh-tasks": "workspace:^",
"@deepseek-ai/dsh-tasks-local": "workspace:^",
"@deepseek-ai/dsh-tool-tasks": "workspace:^",
"@deepseek-ai/dsh-jobs": "workspace:^",
"@deepseek-ai/dsh-jobs-local": "workspace:^",
"@deepseek-ai/dsh-tool-jobs": "workspace:^",
"@deepseek-ai/dsh-tools": "workspace:^",
"@deepseek-ai/cordis": "workspace:^"
}

24
packages/subagent/tool-subagent/src/index.ts
View File

@@ -16,7 +16,7 @@ import type { ContentBlock } from '@deepseek-ai/dsh-llm'
import type { JsonValue } from '@deepseek-ai/dsh-session'
import { assertSubagentMaxDepth, settleRun } from '@deepseek-ai/dsh-subagent'
import type { SubagentProvider, SubagentResult, SubagentRun } from '@deepseek-ai/dsh-subagent'
import type { TaskOutcome } from '@deepseek-ai/dsh-tasks'
import type { JobOutcome } from '@deepseek-ai/dsh-jobs'
import type {} from '@deepseek-ai/dsh-system-prompt'
export const name = 'tool-subagent'
@@ -109,7 +109,7 @@ function outputValueText(values: JsonValue[]): string {
}
/** Settle pending startup without rejecting the task producer contract. */
async function settleStart(start: Promise<SubagentRun>, signal: AbortSignal): Promise<TaskOutcome> {
async function settleStart(start: Promise<SubagentRun>, signal: AbortSignal): Promise<JobOutcome> {
try {
return await settleRun(await start)
} catch (error: unknown) {
@@ -302,7 +302,7 @@ export function apply(ctx: Context, config: Config): void {
// continuable background path is reachable at all.
? continuable
? ' This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.'
: ' This call waits for the result by default. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.'
: ' This call waits for the result by default. Set `run_in_background: true` to return a job id; collect with `job_output` and stop with `job_kill`.'
: ' This call waits for the subagent and returns its result.'),
parameters: {
description: {
@@ -320,7 +320,7 @@ export function apply(ctx: Context, config: Config): void {
type: 'boolean' as const,
description: continuable
? 'Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it.'
: 'Whether to run as a background task and return its id. Defaults to false; collect with task_output or stop with task_kill.',
: 'Whether to run as a background job and return its id. Defaults to false; collect with job_output or stop with job_kill.',
},
} : {},
},
@@ -332,7 +332,7 @@ export function apply(ctx: Context, config: Config): void {
additionalProperties: false,
properties: {
kind: { type: 'string', required: true, const: 'background' },
taskId: { type: 'string', required: true },
jobId: { type: 'string', required: true },
},
},
{
@@ -357,7 +357,7 @@ export function apply(ctx: Context, config: Config): void {
render: (_args, value) => [{
type: 'text',
text: value.kind === 'background'
? `started background subagent task ${value.taskId}`
? `started background subagent task ${value.jobId}`
: value.kind === 'continuable'
? `started subagent ${value.subagentId}`
: outputValueText(value.output),
@@ -397,13 +397,13 @@ export function apply(ctx: Context, config: Config): void {
})
return { kind: 'continuable' as const, subagentId: started.childId }
}
const tasks = ctx.get('tasks')
if (tasks === undefined) {
throw new Error('background tasks unavailable: load @deepseek-ai/dsh-tasks and @deepseek-ai/dsh-tool-tasks')
const jobs = ctx.get('jobs')
if (jobs === undefined) {
throw new Error('background jobs unavailable: load @deepseek-ai/dsh-jobs and @deepseek-ai/dsh-tool-jobs')
}
// One-shot background child: task preflight finishes before the
// One-shot background child: job preflight finishes before the
// starter can spawn, and the task-owned signal covers startup.
const id = tasks.start({
const id = jobs.start({
kind: 'subagent',
label: args.description,
owner: parent,
@@ -419,7 +419,7 @@ export function apply(ctx: Context, config: Config): void {
}
},
})
return { kind: 'background' as const, taskId: id }
return { kind: 'background' as const, jobId: id }
}
const run: SubagentRun = await ctx.subagents.start(config.provider, {

6
packages/subagent/tool-subagent/tests/scripted-provider.spec.ts
View File

@@ -1,7 +1,7 @@
import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import { type Agent } from '@deepseek-ai/dsh-agent'
import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent'
import SubagentRuntime, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent'
import { SessionId } from '@deepseek-ai/dsh-session'
import * as scripted from './scripted-provider.ts'
@@ -21,7 +21,7 @@ function baseRequest(over: Partial<SubagentStartRequest> = {}): SubagentStartReq
async function mount(config: Partial<scripted.Config> = {}): Promise<Context> {
const ctx = new Context()
await ctx.plugin(SubagentService)
await ctx.plugin(SubagentRuntime)
await scripted.mountScriptedProvider(ctx, { name: 'mock', ...config })
return ctx
}
@@ -89,7 +89,7 @@ describe('scripted subagent provider fixture', () => {
it('unregisters with its owning fixture fiber', async () => {
const ctx = new Context()
await ctx.plugin(SubagentService)
await ctx.plugin(SubagentRuntime)
const fiber = await scripted.mountScriptedProvider(ctx, { name: 'mock' })
expect(ctx.subagents.list()).toEqual(['mock'])
await fiber.dispose()

170
packages/subagent/tool-subagent/tests/tool-subagent.spec.ts
View File

@@ -6,17 +6,17 @@ import { Context } from '@deepseek-ai/cordis'
import Loader from '@deepseek-ai/cordis-plugin-loader'
import { CallId } from '@deepseek-ai/dsh-llm'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { TOOL_ABORTED_BEFORE_DISPATCH } from '@deepseek-ai/dsh-tools'
import ToolRuntime, { TOOL_ABORTED_BEFORE_DISPATCH } from '@deepseek-ai/dsh-tools'
import { assembleContextFor, type Agent } from '@deepseek-ai/dsh-agent'
import AgentRegistry from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
import JsonlSessionPersistence from '@deepseek-ai/dsh-session-persistence-jsonl'
import SubagentService from '@deepseek-ai/dsh-subagent'
import SubagentRuntime from '@deepseek-ai/dsh-subagent'
import type { SubagentStartRequest } from '@deepseek-ai/dsh-subagent'
import LocalTaskService from '@deepseek-ai/dsh-tasks-local'
import * as SubagentSpawn from '@deepseek-ai/dsh-subagent-spawn'
import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks'
import LocalJobRegistry from '@deepseek-ai/dsh-jobs-local'
import * as SubagentSpawn from '@deepseek-ai/dsh-subagent-spawn-in-process'
import * as ToolTasks from '@deepseek-ai/dsh-tool-jobs'
import { MockAdapter, textResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
import * as mock from './scripted-provider.ts'
import * as tool from '../src/index.ts'
@@ -26,7 +26,7 @@ const testToolSignal = new AbortController().signal
/**
* Drives the REAL plugin body: mounts `dsh-tool-subagent` on a real
* `ToolRegistry` + `SubagentService`, with a package-local scripted child
* `ToolRuntime` + `SubagentRuntime`, with a package-local scripted child
* boundary, and invokes the registered `subagent` tool through
* `ctx.tools.execute`. Everything downstream of the child boundary is the
* shipping code path.
@@ -40,8 +40,8 @@ function fakeAgent(id = 'parent-1'): Agent {
async function setup(toolConfig: tool.Config, mockConfig: Partial<mock.Config> = {}) {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
await mock.mountScriptedProvider(ctx, { name: 'mock', ...mockConfig })
await ctx.plugin(tool, toolConfig)
return ctx
@@ -102,7 +102,7 @@ describe('dsh-tool-subagent', () => {
expect(schema).toBeDefined()
const props = (schema!.parameters as { properties?: Record<string, unknown> }).properties ?? {}
expect(Object.keys(props).sort()).toEqual(['description', 'prompt', 'run_in_background'])
expect(schema!.description).toContain('task_output')
expect(schema!.description).toContain('job_output')
})
it('omits run_in_background entirely when the instance disables it (schema and capability never disagree)', async () => {
@@ -110,7 +110,7 @@ describe('dsh-tool-subagent', () => {
const schema = ctx.tools.schemas().find(s => s.name === 'subagent')
const props = (schema!.parameters as { properties?: Record<string, unknown> }).properties ?? {}
expect(Object.keys(props).sort()).toEqual(['description', 'prompt'])
expect(schema!.description).not.toContain('task_output')
expect(schema!.description).not.toContain('job_output')
})
it('refuses a forced run_in_background at execution time when the instance disables it', async () => {
@@ -187,8 +187,8 @@ describe('dsh-tool-subagent', () => {
// names, so a configurable name is what makes this work.
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
await mock.mountScriptedProvider(ctx, { name: 'spawn', reply: 'from spawn' })
await mock.mountScriptedProvider(ctx, { name: 'acp', reply: 'from acp' })
await ctx.plugin(tool, { provider: 'spawn', toolName: 'subagent' })
@@ -208,8 +208,8 @@ describe('dsh-tool-subagent', () => {
// arm must treat an unrecognized terminal reason as a failure, not success.
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'weird',
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false },
@@ -234,8 +234,8 @@ describe('dsh-tool-subagent', () => {
let seen: { agentOptions?: { model?: string } } | undefined
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'capture',
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false },
@@ -264,8 +264,8 @@ describe('dsh-tool-subagent', () => {
let seen: { agentOptions?: unknown } | undefined
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'bare',
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false },
@@ -299,8 +299,8 @@ describe('dsh-tool-subagent', () => {
it('registers when the provider appears LATER — no load-order requirement (Loader starts siblings concurrently)', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
// Tool first: no provider yet — the tool must be absent, not broken.
// Direct apply (schema bypass): also covers the waiting-note's default
// toolName fallback, which validated config pre-fills.
@@ -316,8 +316,8 @@ describe('dsh-tool-subagent', () => {
it('keeps continuable guidance empty while its provider is absent', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
tool.apply(ctx, {
provider: 'later-continuable',
backgroundMode: 'continuable',
@@ -332,8 +332,8 @@ describe('dsh-tool-subagent', () => {
it('mirrors the provider lifecycle: gone on backend dispose, re-derived wording on re-registration', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
const backend = await mock.mountScriptedProvider(ctx, { name: 'mock' }) // fresh conversation (descriptor: false)
await ctx.plugin(tool, { provider: 'mock' })
expect(ctx.tools.schemas().find(s => s.name === 'subagent')!.description).toContain('does not see this conversation')
@@ -351,8 +351,8 @@ describe('dsh-tool-subagent', () => {
it('the tool PLUGIN fiber owns its lifecycle listeners: disposal unmounts, and a disposed fiber never zombie-mounts', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
// Arm 1: a mounted tool and its prompt section die with the plugin fiber;
// the provider survives.
@@ -387,8 +387,8 @@ describe('dsh-tool-subagent', () => {
it('ignores lifecycle events for OTHER providers', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
await mock.mountScriptedProvider(ctx, { name: 'mock' })
await ctx.plugin(tool, { provider: 'mock' })
// An unrelated provider registering (added-event with another name) and
@@ -423,8 +423,8 @@ describe('dsh-tool-subagent', () => {
const disposed = vi.fn()
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'spy',
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false },
@@ -446,8 +446,8 @@ describe('dsh-tool-subagent', () => {
const disposed = vi.fn()
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'spy',
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false },
@@ -470,8 +470,8 @@ describe('dsh-tool-subagent', () => {
const disposed = vi.fn()
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'spy',
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false },
@@ -498,8 +498,8 @@ describe('dsh-tool-subagent', () => {
it('reports a foreground disposal failure after a completed result', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'spy',
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false },
@@ -525,8 +525,8 @@ describe('dsh-tool-subagent', () => {
const cancelled = vi.fn()
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'spy',
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false },
@@ -564,8 +564,8 @@ describe('dsh-tool-subagent', () => {
const sawAborted = vi.fn()
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'spy',
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false },
@@ -591,8 +591,8 @@ describe('dsh-tool-subagent', () => {
it('tools depend on the service: no `subagent` tool without ctx.subagents', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
// No SubagentService mounted. The tool injects its three required services so its
await ctx.plugin(ToolRuntime)
// No SubagentRuntime mounted. The tool injects its three required services so its
// apply never runs; the tool is absent rather than half-registered.
let booted = true
try {
@@ -628,8 +628,8 @@ describe('dsh-tool-subagent', () => {
let seen: { persona?: string; toolFilter?: unknown; maxDepth?: number } | undefined
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'capture2',
capabilities: { outputSchema: false, depthLimit: true, toolFilter: true, persona: true },
@@ -685,8 +685,8 @@ describe('dsh-tool-subagent', () => {
let seen: { toolFilter?: { readonly allow?: readonly string[]; readonly deny?: readonly string[] } } | undefined
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'capture3',
capabilities: { outputSchema: false, depthLimit: false, toolFilter: true, persona: false },
@@ -715,8 +715,8 @@ describe('dsh-tool-subagent', () => {
let seen: { agentOptions?: unknown } | undefined
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'capture4',
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false },
@@ -740,8 +740,8 @@ describe('dsh-tool-subagent', () => {
it('an explicit empty toolFilter fails at plugin load, not at first delegation', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'p',
capabilities: { outputSchema: false, depthLimit: false, toolFilter: true, persona: false },
@@ -772,7 +772,7 @@ describe('dsh-tool-subagent background mode', () => {
async function backgroundSetup(toolConfig: tool.Config, mockConfig: Partial<mock.Config> = {}) {
const ctx = await setup(toolConfig, mockConfig)
await ctx.plugin(AgentRegistry)
await ctx.plugin(LocalTaskService)
await ctx.plugin(LocalJobRegistry)
await ctx.plugin(ToolTasks, {})
return ctx
}
@@ -818,21 +818,21 @@ describe('dsh-tool-subagent background mode', () => {
expect(prepareCalls).toBe(0)
})
it('returns a task id immediately and the answer is collected through task_output', async () => {
it('returns a job id immediately and the answer is collected through job_output', async () => {
const ctx = await backgroundSetup({ provider: 'mock', agentOptions: { model: 'child-model' } }, { reply: 'background answer' })
const parent = ownerAgent(ctx, 'sess-parent')
const start = await callSubagent(ctx, { description: 'deep research', prompt: 'dig in', run_in_background: true }, { agent: parent })
expect(start.isError).toBe(false)
if (start.isError) throw new Error('expected background subagent success')
expect(start.value).toEqual({ kind: 'background', taskId: 'subagent-1' })
expect(start.value).toEqual({ kind: 'background', jobId: 'subagent-1' })
expect(text(start)).toBe('started background subagent task subagent-1')
const collected = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('collect-1'),
name: 'task_output',
arguments: { task_id: 'subagent-1', wait: true },
name: 'job_output',
arguments: { job_id: 'subagent-1', wait: true },
agent: parent,
})
expect(text(collected)).toBe('background answer\n[status: completed]')
@@ -841,8 +841,8 @@ describe('dsh-tool-subagent background mode', () => {
const again = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('collect-2'),
name: 'task_output',
arguments: { task_id: 'subagent-1' },
name: 'job_output',
arguments: { job_id: 'subagent-1' },
agent: parent,
})
expect(text(again)).toBe('background answer\n[status: completed]')
@@ -852,7 +852,7 @@ describe('dsh-tool-subagent background mode', () => {
const ctx = await setup({ provider: 'mock' })
const result = await callSubagent(ctx, { description: 'd', prompt: 'p', run_in_background: true })
expect(result.isError).toBe(true)
expect(text(result)).toContain('background tasks unavailable: load @deepseek-ai/dsh-tasks')
expect(text(result)).toContain('background jobs unavailable: load @deepseek-ai/dsh-jobs')
})
it('skips background startup when the tool signal is already aborted', async () => {
@@ -891,8 +891,8 @@ describe('dsh-tool-subagent background mode', () => {
const output = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('broken-output'),
name: 'task_output',
arguments: { task_id: 'subagent-1', wait: true },
name: 'job_output',
arguments: { job_id: 'subagent-1', wait: true },
agent: parent,
})
expect(text(output)).toContain('[status: failed, Error: setup failed]')
@@ -921,21 +921,21 @@ describe('dsh-tool-subagent background mode', () => {
await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('pending-kill'),
name: 'task_kill',
arguments: { task_id: 'subagent-1', reason: 'no longer needed' },
name: 'job_kill',
arguments: { job_id: 'subagent-1', reason: 'no longer needed' },
agent: parent,
})
const output = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('pending-output'),
name: 'task_output',
arguments: { task_id: 'subagent-1', wait: true },
name: 'job_output',
arguments: { job_id: 'subagent-1', wait: true },
agent: parent,
})
expect(text(output)).toBe('(no new output)\n[status: killed]')
})
it('forwards task_kill reasons through the run signal (and defaults one when absent)', async () => {
it('forwards job_kill reasons through the run signal (and defaults one when absent)', async () => {
// Use a provider that remains live until its signal is aborted.
const ctx = await backgroundSetup({ provider: 'mock', agentOptions: { model: 'child-model' } })
const parent = ownerAgent(ctx, 'sess-parent')
@@ -969,14 +969,14 @@ describe('dsh-tool-subagent background mode', () => {
expect(text(startOne)).toBe('started background subagent task subagent-1')
expect(text(startTwo)).toBe('started background subagent task subagent-2')
const withReason = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('k1'), name: 'task_kill', arguments: { task_id: 'subagent-1', reason: 'superseded' }, agent: parent })
const withoutReason = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('k2'), name: 'task_kill', arguments: { task_id: 'subagent-2' }, agent: parent })
expect(text(withReason)).toBe('requested cancellation of task subagent-1')
expect(text(withoutReason)).toBe('requested cancellation of task subagent-2')
const withReason = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('k1'), name: 'job_kill', arguments: { job_id: 'subagent-1', reason: 'superseded' }, agent: parent })
const withoutReason = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('k2'), name: 'job_kill', arguments: { job_id: 'subagent-2' }, agent: parent })
expect(text(withReason)).toBe('requested cancellation of job subagent-1')
expect(text(withoutReason)).toBe('requested cancellation of job subagent-2')
expect(cancels).toEqual(['superseded', 'background subagent task killed'])
// The aborted children settle as killed tasks.
const killed = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('w1'), name: 'task_output', arguments: { task_id: 'subagent-1', wait: true }, agent: parent })
const killed = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('w1'), name: 'job_output', arguments: { job_id: 'subagent-1', wait: true }, agent: parent })
expect(text(killed)).toBe('(no new output)\n[status: killed]')
})
@@ -996,9 +996,9 @@ describe('dsh-tool-subagent continuable background mode', () => {
roots.push(root)
await ctx.plugin(JsonlSessionPersistence, { root })
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(SubagentService)
await ctx.plugin(SubagentRuntime)
await ctx.plugin(SubagentSpawn, { providerName: 'spawn' })
await ctx.plugin(LocalTaskService)
await ctx.plugin(LocalJobRegistry)
await ctx.plugin(ToolTasks, {})
await ctx.plugin(tool, { provider: 'spawn', backgroundMode: 'continuable' })
ctx.llm.registerAdapter(['mock'], new MockAdapter([
@@ -1022,8 +1022,8 @@ describe('dsh-tool-subagent continuable background mode', () => {
const { ctx, parent } = await continuableSetup()
const schema = ctx.tools.schemas().find(s => s.name === 'subagent')!
// Continuable delegation has no Task, so the schema promises no collection.
expect(schema.description).not.toContain('task_output')
expect(schema.description).not.toContain('task_kill')
expect(schema.description).not.toContain('job_output')
expect(schema.description).not.toContain('job_kill')
expect(schema.description).toContain('send_message')
expect(schema.description).toContain('runs in the background by default')
expect(schema.description).not.toContain('never poll or wait on it')
@@ -1046,7 +1046,7 @@ describe('dsh-tool-subagent continuable background mode', () => {
expect(match).not.toBeNull()
const [, childId] = match!
// No Task was created for the continuable child.
expect(ctx.tasks.list(parent)).toEqual([])
expect(ctx.jobs.list(parent)).toEqual([])
await vi.waitFor(() => {
expect(ctx.agents.get(SessionId(childId!))).toBeUndefined()
@@ -1077,7 +1077,7 @@ describe('dsh-tool-subagent continuable background mode', () => {
if (result.isError) throw new Error('expected foreground subagent success')
expect(result.value).toMatchObject({ kind: 'foreground' })
expect(text(result)).toBe('continuable answer')
expect(ctx.tasks.list(parent)).toEqual([])
expect(ctx.jobs.list(parent)).toEqual([])
})
it('isolates a cancelled continuable preparation from a concurrent sibling', async () => {
@@ -1147,10 +1147,10 @@ describe('dsh-tool-subagent continuable background mode', () => {
describe('background preflight failure (no orphaned child, by construction)', () => {
it('never starts the child when tasks.start preflight throws', async () => {
// With no task controller, preflight fails before the provider can spawn.
// With no job controller, preflight fails before the provider can spawn.
const ctx = await setup({ provider: 'mock' })
await ctx.plugin(AgentRegistry)
await ctx.plugin(LocalTaskService)
await ctx.plugin(LocalJobRegistry)
const scopeFiber = ctx.plugin(() => {})
const id = SessionId('sess-p')
const parent = {
@@ -1187,7 +1187,7 @@ describe('background preflight failure (no orphaned child, by construction)', ()
agent: parent,
})
expect(result.isError).toBe(true)
expect(text(result)).toContain('no task controller serves this agent')
expect(text(result)).toContain('no job controller serves this agent')
// Declare-then-execute: the failed preflight means no child ever existed.
expect(starts).toBe(0)
})
@@ -1199,8 +1199,8 @@ describe('depth budget configuration', () => {
const requests: SubagentStartRequest[] = []
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'capture',
capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: true },
@@ -1237,8 +1237,8 @@ describe('depth budget configuration', () => {
it('rejects a numeric maxDepth on a provider without the depthLimit capability at mount', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'no-depth',
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false },
@@ -1253,8 +1253,8 @@ describe('depth budget configuration', () => {
const requests: SubagentStartRequest[] = []
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(SubagentService)
await ctx.plugin(ToolRuntime)
await ctx.plugin(SubagentRuntime)
ctx.subagents.registerProvider({
name: 'external',
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false },

4
packages/subagent/tool-subagent/tsconfig.json
View File

@@ -33,10 +33,10 @@
"path": "../subagent"
},
{
"path": "../../tasks/tasks"
"path": "../../jobs/jobs"
},
{
"path": "../../support/invariants"
"path": "../../runtime-diagnostics/invariants"
}
]
}