Merge remote-tracking branch 'origin/master' into codex/pr335-merge-master-20260719

packages/subagent/README.md

@@ -12,6 +12,6 @@ The subagent seam: an agent delegating work to a child agent. Like the [bash](..
 | `subagent-acp/` | Out-of-process backend: a child agent in a spawned subprocess, driven over ACP | (registers on `ctx.subagents`) |
 | `tool-subagent/` | Model-facing `subagent` delegation tool over `ctx.subagents` | (registers on `ctx.tools`) |
 
-The interface lives at `subagent/subagent/`. The in-process `subagent-spawn` / `subagent-fork` backends share the `subagent-inprocess` driver (a library with no provider of its own — both depend on it, neither on the other), the out-of-process `subagent-acp` backend builds on the `subagent-subprocess` library (the credential env scrub, the dispose ladder, isolated config dirs) and ships alongside them here; the test-only `dsh-subagent-mock` (in [support](../support/README.md)) is separate. All **product** packages except the mock.
+The interface lives at `subagent/subagent/`. The in-process `subagent-spawn` / `subagent-fork` backends share the `subagent-inprocess` driver (a library with no provider of its own — both depend on it, neither on the other), and the out-of-process `subagent-acp` backend builds on the `subagent-subprocess` library (the credential env scrub, the dispose ladder, isolated config dirs). Tests replace only the child boundary with package-local fixtures.
 
 The proposal and design rationale: [docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md](../../docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md).

packages/subagent/tool-subagent/package.json

@@ -37,7 +37,6 @@
     "@deepseek-ai/dsh-agent": "workspace:^",
     "@deepseek-ai/dsh-llm": "workspace:^",
     "@deepseek-ai/dsh-subagent": "workspace:^",
-    "@deepseek-ai/dsh-subagent-mock": "workspace:^",
     "@deepseek-ai/dsh-system-prompt": "workspace:^",
     "@deepseek-ai/dsh-tasks": "workspace:^",
     "@deepseek-ai/dsh-tool-tasks": "workspace:^",

packages/subagent/tool-subagent/tests/scripted-provider.spec.ts

@@ -0,0 +1,98 @@
+import { describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import { type Agent } from '@deepseek-ai/dsh-agent'
+import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent'
+import { SessionId } from '@deepseek-ai/dsh-session'
+import * as scripted from './scripted-provider.ts'
+
+/** A minimal parent; the scripted provider only reads its id. */
+function fakeParent(id = 'parent-1'): Agent {
+  return { id: SessionId(id) } as unknown as Agent
+}
+
+function baseRequest(over: Partial<SubagentStartRequest> = {}): SubagentStartRequest {
+  return {
+    prompt: [{ type: 'text', text: 'task' }],
+    parent: fakeParent(),
+    signal: new AbortController().signal,
+    ...over,
+  }
+}
+
+async function mount(config: Partial<scripted.Config> = {}): Promise<Context> {
+  const ctx = new Context()
+  await ctx.plugin(SubagentService)
+  await scripted.mountScriptedProvider(ctx, { name: 'mock', ...config })
+  return ctx
+}
+
+describe('scripted subagent provider fixture', () => {
+  it('registers through the real service and returns the scripted reply', async () => {
+    const ctx = await mount({ reply: 'hello from fixture' })
+    expect(ctx.subagents.list()).toEqual(['mock'])
+
+    const run = await ctx.subagents.start('mock', baseRequest())
+    await expect(run.result).resolves.toEqual({
+      output: [{ type: 'text', text: 'hello from fixture' }],
+      structured: undefined,
+      stopReason: 'completed',
+    })
+    await run.dispose()
+  })
+
+  it('registers under a configurable name', async () => {
+    const ctx = await mount({ name: 'spawn' })
+    expect(ctx.subagents.list()).toEqual(['spawn'])
+  })
+
+  it('returns configured and default structured results', async () => {
+    const configured = await mount({ reply: 'r', structured: { answer: 42 } })
+    const schema = { type: 'object' as const, properties: { answer: { type: 'number' as const } } }
+    const configuredRun = await configured.subagents.start('mock', baseRequest({ outputSchema: schema }))
+    await expect(configuredRun.result).resolves.toMatchObject({ structured: { answer: 42 } })
+
+    const fallback = await mount({ reply: 'fallback reply' })
+    const fallbackRun = await fallback.subagents.start('mock', baseRequest({ outputSchema: schema }))
+    await expect(fallbackRun.result).resolves.toMatchObject({ structured: { reply: 'fallback reply' } })
+  })
+
+  it('omits structured output when no schema is requested', async () => {
+    const ctx = await mount({ capabilities: { outputSchema: false } })
+    const run = await ctx.subagents.start('mock', baseRequest())
+    expect(await run.result).not.toHaveProperty('structured')
+  })
+
+  it('honors configured and cancellation stop reasons', async () => {
+    const refused = await mount({ stopReason: 'refusal' })
+    const refusedRun = await refused.subagents.start('mock', baseRequest())
+    await expect(refusedRun.result).resolves.toMatchObject({ stopReason: 'refusal' })
+
+    const cancelled = await mount()
+    const controller = new AbortController()
+    const cancelledRun = await cancelled.subagents.start('mock', baseRequest({ signal: controller.signal }))
+    controller.abort()
+    await expect(cancelledRun.result).resolves.toMatchObject({ stopReason: 'aborted' })
+  })
+
+  it('rejects cancellation before or during asynchronous publication', async () => {
+    const ctx = await mount()
+    const alreadyAborted = new AbortController()
+    alreadyAborted.abort()
+    await expect(ctx.subagents.start('mock', baseRequest({ signal: alreadyAborted.signal })))
+      .rejects.toThrow('scripted subagent start aborted before publication')
+
+    const handoff = new AbortController()
+    const pending = ctx.subagents.start('mock', baseRequest({ signal: handoff.signal }))
+    handoff.abort()
+    await expect(pending).rejects.toThrow('scripted subagent start aborted before publication')
+  })
+
+  it('unregisters with its owning fixture fiber', async () => {
+    const ctx = new Context()
+    await ctx.plugin(SubagentService)
+    const fiber = await scripted.mountScriptedProvider(ctx, { name: 'mock' })
+    expect(ctx.subagents.list()).toEqual(['mock'])
+    await fiber.dispose()
+    expect(ctx.subagents.list()).toEqual([])
+  })
+})

packages/subagent/tool-subagent/tests/scripted-provider.ts

@@ -0,0 +1,104 @@
+/** Package-local scripted child boundary for deterministic tool-subagent tests. */
+
+import type { Context } from 'cordis'
+import type { ContentBlock } from '@deepseek-ai/dsh-llm'
+import { SessionId } from '@deepseek-ai/dsh-session'
+import type {
+  SubagentCapabilities,
+  SubagentProvider,
+  SubagentResult,
+  SubagentRun,
+  SubagentStartRequest,
+  SubagentStopReason,
+} from '@deepseek-ai/dsh-subagent'
+
+const DEFAULT_CAPABILITIES: SubagentCapabilities = {
+  outputSchema: true,
+  depthLimit: true,
+  toolFilter: true,
+  persona: true,
+}
+
+/** Options for one scripted provider fixture. */
+export interface Config {
+  /** Registry name to register under. */
+  name: string
+  /** Final text returned by the scripted child. */
+  reply?: string
+  /** Terminal result reason. */
+  stopReason?: SubagentStopReason
+  /** Start-time features advertised by the provider. */
+  capabilities?: Partial<SubagentCapabilities>
+  /** Whether tool descriptions say the child inherits completed turns. */
+  inheritsParentContext?: boolean
+  /** Structured value returned when the request asks for one. */
+  structured?: unknown
+}
+
+/** Scripted provider whose result aborts if its signal or disposer wins first. */
+class ScriptedSubagentProvider implements SubagentProvider {
+  readonly capabilities: SubagentCapabilities
+  readonly inheritsParentContext: boolean
+
+  constructor(
+    readonly name: string,
+    private readonly config: Config,
+  ) {
+    this.capabilities = { ...DEFAULT_CAPABILITIES, ...config.capabilities }
+    this.inheritsParentContext = config.inheritsParentContext ?? false
+  }
+
+  async start(request: SubagentStartRequest): Promise<SubagentRun> {
+    if (request.signal.aborted) throw new Error('scripted subagent start aborted before publication')
+    const reply = this.config.reply ?? 'scripted subagent reply'
+    const output: ContentBlock[] = [{ type: 'text', text: reply }]
+    const wantsStructured = request.outputSchema !== undefined && this.capabilities.outputSchema
+    const stopReason = this.config.stopReason ?? 'completed'
+    const state = { cancelled: false }
+    const onAbort = (): void => { state.cancelled = true }
+    request.signal.addEventListener('abort', onAbort, { once: true })
+    await Promise.resolve()
+    if (state.cancelled) {
+      request.signal.removeEventListener('abort', onAbort)
+      throw new Error('scripted subagent start aborted before publication')
+    }
+
+    const resultFor = (): SubagentResult => ({
+      output,
+      ...wantsStructured ? { structured: this.config.structured ?? { reply } } : {},
+      stopReason: state.cancelled ? 'aborted' : stopReason,
+    })
+    const result = new Promise<SubagentResult>((resolve) => {
+      setTimeout(() => { resolve(resultFor()) }, 0)
+    }).finally(() => {
+      request.signal.removeEventListener('abort', onAbort)
+    })
+
+    return {
+      id: SessionId(`scripted-subagent:${this.name}:${request.parent.id}`),
+      localAgent: undefined,
+      result,
+      dispose(): Promise<void> {
+        state.cancelled = true
+        request.signal.removeEventListener('abort', onAbort)
+        return Promise.resolve()
+      },
+    }
+  }
+}
+
+/**
+ * Mount one scripted provider through an effect-scoped local plugin.
+ * @param ctx - context carrying the real subagent registry.
+ * @param config - scripted provider identity and outcome.
+ * @returns the fixture plugin's disposable fiber.
+ */
+export function mountScriptedProvider(ctx: Context, config: Config) {
+  return ctx.plugin({
+    name: 'scripted-subagent-provider',
+    inject: ['subagents'],
+    apply(pluginCtx: Context): void {
+      pluginCtx.subagents.registerProvider(new ScriptedSubagentProvider(config.name, config))
+    },
+  })
+}

packages/subagent/tool-subagent/tests/tool-subagent.spec.ts

@@ -9,18 +9,17 @@ import AgentRegistry from '@deepseek-ai/dsh-agent'
 import SubagentService from '@deepseek-ai/dsh-subagent'
 import TaskService from '@deepseek-ai/dsh-tasks'
 import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks'
-import * as mock from '@deepseek-ai/dsh-subagent-mock'
+import * as mock from './scripted-provider.ts'
 import * as tool from '../src/index.ts'
 import { runOutcome, settleRun } from '../src/index.ts'
 import { SessionId } from '@deepseek-ai/dsh-session'
 
 /**
  * Drives the REAL plugin body: mounts `dsh-tool-subagent` on a real
- * `ToolRegistry` + `SubagentService`, with the real `dsh-subagent-mock` as the
- * backend, and invokes the registered `subagent` tool through
- * `ctx.tools.execute`. The mock is the genuine collaborator (we mock only the
- * "child agent", the expensive/non-deterministic boundary) — everything
- * downstream of the tool is the shipping code path.
+ * `ToolRegistry` + `SubagentService`, 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.
  */
 
 /** A minimal parent Agent — the tool reads `agent.id` for `parent`. */
@@ -33,7 +32,7 @@ async function setup(toolConfig: tool.Config, mockConfig: Partial<mock.Config> =
   await ctx.plugin(SystemPrompt)
   await ctx.plugin(ToolRegistry)
   await ctx.plugin(SubagentService)
-  await ctx.plugin(mock, { name: 'mock', ...mockConfig })
+  await mock.mountScriptedProvider(ctx, { name: 'mock', ...mockConfig })
   await ctx.plugin(tool, toolConfig)
   return ctx
 }
@@ -131,8 +130,8 @@ describe('dsh-tool-subagent', () => {
     await ctx.plugin(SystemPrompt)
     await ctx.plugin(ToolRegistry)
     await ctx.plugin(SubagentService)
-    await ctx.plugin(mock, { name: 'spawn', reply: 'from spawn' })
-    await ctx.plugin(mock, { name: 'acp', reply: 'from acp' })
+    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' })
     await ctx.plugin(tool, { provider: 'acp', toolName: 'subagent_acp' })
 
@@ -249,7 +248,7 @@ describe('dsh-tool-subagent', () => {
     tool.apply(ctx, { provider: 'mock' })
     expect(ctx.tools.schemas().some(s => s.name === 'subagent')).toBe(false)
     // Backend arrives (as a delayed sibling fiber would): the tool appears.
-    await ctx.plugin(mock, { name: 'mock', reply: 'late but fine' })
+    await mock.mountScriptedProvider(ctx, { name: 'mock', reply: 'late but fine' })
     expect(ctx.tools.schemas().some(s => s.name === 'subagent')).toBe(true)
     const result = await callSubagent(ctx, { description: 'd', prompt: 'p' })
     expect(text(result)).toBe('late but fine')
@@ -260,7 +259,7 @@ describe('dsh-tool-subagent', () => {
     await ctx.plugin(SystemPrompt)
     await ctx.plugin(ToolRegistry)
     await ctx.plugin(SubagentService)
-    const backend = await ctx.plugin(mock, { name: 'mock' }) // fresh conversation (descriptor: false)
+    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')
 
@@ -270,7 +269,7 @@ describe('dsh-tool-subagent', () => {
 
     // Backend reloads with a DIFFERENT conversation-history descriptor: the wording is re-derived
     // from the fresh provider, not served stale from the first mount.
-    await ctx.plugin(mock, { name: 'mock', inheritsParentContext: true })
+    await mock.mountScriptedProvider(ctx, { name: 'mock', inheritsParentContext: true })
     expect(ctx.tools.schemas().find(s => s.name === 'subagent')!.description).toContain('inherits this conversation')
   })
 
@@ -281,7 +280,7 @@ describe('dsh-tool-subagent', () => {
     await ctx.plugin(SubagentService)
 
     // Arm 1: a mounted tool dies with its plugin fiber; the provider survives.
-    await ctx.plugin(mock, { name: 'mock' })
+    await mock.mountScriptedProvider(ctx, { name: 'mock' })
     const mounted = await ctx.plugin(tool, { provider: 'mock' })
     expect(ctx.tools.schemas().some(s => s.name === 'subagent')).toBe(true)
     await mounted.dispose()
@@ -293,7 +292,7 @@ describe('dsh-tool-subagent', () => {
     // live plugin owns (the zombie mount).
     const waiting = await ctx.plugin(tool, { provider: 'later', toolName: 'subagent_later' })
     await waiting.dispose()
-    await ctx.plugin(mock, { name: 'later' })
+    await mock.mountScriptedProvider(ctx, { name: 'later' })
     expect(ctx.tools.schemas().some(s => s.name === 'subagent_later')).toBe(false)
   })
 
@@ -302,11 +301,11 @@ describe('dsh-tool-subagent', () => {
     await ctx.plugin(SystemPrompt)
     await ctx.plugin(ToolRegistry)
     await ctx.plugin(SubagentService)
-    await ctx.plugin(mock, { name: 'mock' })
+    await mock.mountScriptedProvider(ctx, { name: 'mock' })
     await ctx.plugin(tool, { provider: 'mock' })
     // An unrelated provider registering (added-event with another name) and
     // unregistering (removed-event with another name) must not touch the tool.
-    const other = await ctx.plugin(mock, { name: 'other', inheritsParentContext: true })
+    const other = await mock.mountScriptedProvider(ctx, { name: 'other', inheritsParentContext: true })
     expect(ctx.tools.schemas().filter(s => s.name === 'subagent')).toHaveLength(1)
     expect(ctx.tools.schemas().find(s => s.name === 'subagent')!.description).toContain('does not see this conversation')
     await other.dispose()