Fix review findings: lifecycle containment, configurable tool name, coverage, type catalog
Address four findings from the first Codex review round: - Contain subagent/start|end listener throws (emitContainedStart/End): a thrown lifecycle listener could escape SubagentService.start() before the caller received the live run to dispose it (a leaked child), and a thrown subagent/end listener could surface as an unhandled rejection on the detached result-settle hook. Both emits now log-and-contain, mirroring the agent registry's agent/created|disposed containment. - Make the model-facing tool name configurable (Config.toolName, default subagent). The docs say to load dsh-tool-subagent once per provider to expose multiple transports, but the hardcoded name made the second load throw a duplicate-tool-name error; a distinct toolName per load is now required and documented. - Reach the per-file 100% coverage gate: tests for the subagent/end error branch, lifecycle-listener containment, every stopReasonError arm + the merge-extensible default, the multi-provider toolName path, agentOptions forwarding, and the direct-apply schema-bypass fallbacks. - Document the seam vocabulary in docs/core-data-structures/subagent.md with verbatim type-equiv blocks + manifest entries, and link it from core.md (a brand-new core/seam type the doc-sync gate cannot detect on its own).
This commit is contained in:
@@ -153,19 +153,51 @@ export class SubagentService extends Service {
|
||||
this.assertCapabilities(provider, request)
|
||||
|
||||
const run = provider.start(request)
|
||||
this.ctx.emit('subagent/start', { provider: name, id: run.id })
|
||||
// CONTAIN lifecycle-listener throws: the run is already live, so a throwing
|
||||
// `subagent/start` listener must NOT escape `start()` (the caller would
|
||||
// never receive the run to dispose it — a leaked child). Emit defensively
|
||||
// and log a thrown listener, mirroring the agent registry's `agent/created`
|
||||
// /`agent/disposed` containment.
|
||||
this.emitContainedStart({ provider: name, id: run.id })
|
||||
// Emit `subagent/end` when the run settles. The result promise does not
|
||||
// reject on a child-level failure (it resolves with stopReason 'error'),
|
||||
// so a rejection here is an infrastructure fault — surface its stop reason
|
||||
// as 'error' for the telemetry event without swallowing the rejection
|
||||
// (the consumer still observes it via `run.result`).
|
||||
// (the consumer still observes it via `run.result`). Containment also keeps
|
||||
// a thrown `subagent/end` listener from becoming an unhandled rejection on
|
||||
// this detached `.then`.
|
||||
void run.result.then(
|
||||
(result) => { this.ctx.emit('subagent/end', { provider: name, id: run.id, stopReason: result.stopReason }) },
|
||||
() => { this.ctx.emit('subagent/end', { provider: name, id: run.id, stopReason: 'error' }) },
|
||||
(result) => { this.emitContainedEnd({ provider: name, id: run.id, stopReason: result.stopReason }) },
|
||||
() => { this.emitContainedEnd({ provider: name, id: run.id, stopReason: 'error' }) },
|
||||
)
|
||||
return run
|
||||
}
|
||||
|
||||
/**
|
||||
* Emit `subagent/start`, containing a thrown listener (log, never propagate)
|
||||
* so one bad subscriber cannot strand the already-live run before the caller
|
||||
* receives it to dispose.
|
||||
*/
|
||||
private emitContainedStart(info: SubagentRunInfo): void {
|
||||
try {
|
||||
this.ctx.emit('subagent/start', info)
|
||||
} catch (error: unknown) {
|
||||
this.ctx.logger.warn(`subagent: subagent/start listener threw: ${String(error)}`)
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Emit `subagent/end`, containing a thrown listener so it cannot surface as an
|
||||
* unhandled rejection on the detached result-settle hook.
|
||||
*/
|
||||
private emitContainedEnd(info: SubagentRunEndInfo): void {
|
||||
try {
|
||||
this.ctx.emit('subagent/end', info)
|
||||
} catch (error: unknown) {
|
||||
this.ctx.logger.warn(`subagent: subagent/end listener threw: ${String(error)}`)
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Reject a request that needs a start-time capability the provider lacks.
|
||||
* Each optional request field maps to one {@link SubagentCapabilities} flag;
|
||||
|
||||
@@ -173,6 +173,60 @@ describe('SubagentService', () => {
|
||||
expect(ended).toHaveBeenCalledWith(expect.objectContaining({ provider: 'events', id: run.id, stopReason: 'completed' }))
|
||||
})
|
||||
|
||||
it('emits subagent/end with stopReason "error" when the run result promise rejects', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SubagentService)
|
||||
// A provider whose run.result REJECTS (an infrastructure fault — the seam
|
||||
// contract says child-level failures resolve with stopReason 'error', but a
|
||||
// rejection is still surfaced as an 'error' telemetry event).
|
||||
ctx.subagents.registerProvider({
|
||||
name: 'rejecter',
|
||||
capabilities: NO_CAPS,
|
||||
start: () => ({
|
||||
id: AgentId('rej-child'),
|
||||
result: Promise.reject(new Error('infra fault')),
|
||||
cancel() {},
|
||||
dispose: async () => {},
|
||||
}),
|
||||
})
|
||||
|
||||
const ended = vi.fn()
|
||||
ctx.on('subagent/end', ended)
|
||||
const run = ctx.subagents.start('rejecter', baseRequest())
|
||||
// Observe (and swallow) the rejection the consumer would see, then let the
|
||||
// detached `.then` settle the telemetry emit.
|
||||
await run.result.catch(() => {})
|
||||
await Promise.resolve()
|
||||
expect(ended).toHaveBeenCalledWith(expect.objectContaining({ provider: 'rejecter', id: run.id, stopReason: 'error' }))
|
||||
})
|
||||
|
||||
it('contains a throwing subagent/start listener so start() still returns the run', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SubagentService)
|
||||
ctx.subagents.registerProvider(new StubProvider('contain'))
|
||||
// A bad subscriber must not strand the live run: start() returns it anyway.
|
||||
ctx.on('subagent/start', () => { throw new Error('bad start listener') })
|
||||
|
||||
const run = ctx.subagents.start('contain', baseRequest())
|
||||
expect(run.id).toBeDefined()
|
||||
await expect(run.result).resolves.toMatchObject({ stopReason: 'completed' })
|
||||
})
|
||||
|
||||
it('contains a throwing subagent/end listener (no unhandled rejection on the settle hook)', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SubagentService)
|
||||
ctx.subagents.registerProvider(new StubProvider('contain-end'))
|
||||
ctx.on('subagent/end', () => { throw new Error('bad end listener') })
|
||||
|
||||
const run = ctx.subagents.start('contain-end', baseRequest())
|
||||
await run.result
|
||||
// Let the detached `.then` + the contained emit run; a thrown listener here
|
||||
// must be swallowed (logged), not escape as an unhandled rejection.
|
||||
await Promise.resolve()
|
||||
await Promise.resolve()
|
||||
expect(run.id).toBeDefined()
|
||||
})
|
||||
|
||||
it('SubagentError extends the shared HarnessError base', () => {
|
||||
const err = new SubagentError('boom', 'NO_PROVIDER')
|
||||
expect(err).toBeInstanceOf(HarnessError)
|
||||
|
||||
@@ -4,11 +4,12 @@ The model-facing `subagent` tool: delegate a self-contained task to a child agen
|
||||
|
||||
## Provider selection is config, not model-facing
|
||||
|
||||
This plugin binds to **exactly one** provider (`Config.provider`). The model sees only `{ description, prompt }` — there is no provider/type parameter in the schema. To expose more than one transport, load the plugin more than once, each bound to a different provider. Keeping selection in config (not the schema) is the deliberate split: the *service* holds a multi-provider registry; the *tool* picks one.
|
||||
This plugin binds to **exactly one** provider (`Config.provider`). The model sees only `{ description, prompt }` — there is no provider/type parameter in the schema. To expose more than one transport, load the plugin more than once, each bound to a different provider **and a distinct `toolName`** (the tool registry rejects a duplicate name, so a second load that kept the default `subagent` name would throw). Keeping selection in config (not the schema) is the deliberate split: the *service* holds a multi-provider registry; the *tool* picks one.
|
||||
|
||||
| Config key | Meaning |
|
||||
|---|---|
|
||||
| `provider` (required) | The `ctx.subagents` provider name to start runs on (`spawn`, `fork`, `acp`, …). |
|
||||
| `toolName` | The model-facing tool name to register (default `subagent`). Set a distinct value per load when exposing multiple providers, e.g. `subagent` + `subagent_acp`. |
|
||||
| `agentOptions` | Default per-child `{ model?, systemPrompt? }` applied to every spawned child. |
|
||||
|
||||
## Lifecycle (synchronous collect)
|
||||
|
||||
@@ -35,6 +35,14 @@ export const inject = ['tools', 'subagents']
|
||||
export interface Config {
|
||||
/** The `ctx.subagents` provider name to start runs on (e.g. `spawn`, `acp`). */
|
||||
provider: string
|
||||
/**
|
||||
* The model-facing tool name to register (default `subagent`). To expose more
|
||||
* than one transport, load this plugin once per provider — each load MUST set
|
||||
* a distinct `toolName` (the tool registry rejects a duplicate name), e.g.
|
||||
* `{ provider: 'spawn', toolName: 'subagent' }` and
|
||||
* `{ provider: 'acp', toolName: 'subagent_acp' }`.
|
||||
*/
|
||||
toolName?: string
|
||||
/**
|
||||
* Default per-child agent options (model, system prompt) applied to every
|
||||
* spawned child. Omitted fields fall back to the child loop's own defaults.
|
||||
@@ -44,6 +52,7 @@ export interface Config {
|
||||
|
||||
export const Config: z<Config> = z.object({
|
||||
provider: z.string().required(),
|
||||
toolName: z.string().default('subagent'),
|
||||
agentOptions: z.object({
|
||||
model: z.string(),
|
||||
systemPrompt: z.string(),
|
||||
@@ -85,7 +94,7 @@ function stopReasonError(result: SubagentResult): string | undefined {
|
||||
|
||||
export function apply(ctx: Context, config: Config): void {
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'subagent',
|
||||
name: config.toolName ?? 'subagent',
|
||||
description:
|
||||
'Delegate a self-contained task to a subagent (a separate agent that works in its own context) '
|
||||
+ 'and return its final result. Use this to offload focused, independent work — research, a scoped '
|
||||
|
||||
@@ -68,11 +68,121 @@ describe('dsh-tool-subagent', () => {
|
||||
expect(Object.keys(props).sort()).toEqual(['description', 'prompt'])
|
||||
})
|
||||
|
||||
it('maps a non-completed stop reason to an isError result (not partial success)', async () => {
|
||||
const ctx = await setup({ provider: 'mock' }, { stopReason: 'refusal' })
|
||||
it.each([
|
||||
{ stopReason: 'aborted' as const, fragment: 'cancelled' },
|
||||
{ stopReason: 'error' as const, fragment: 'failed' },
|
||||
{ stopReason: 'max-tokens' as const, fragment: 'token limit' },
|
||||
{ stopReason: 'refusal' as const, fragment: 'declined' },
|
||||
])('maps stop reason $stopReason to an isError result (not partial success)', async ({ stopReason, fragment }) => {
|
||||
const ctx = await setup({ provider: 'mock' }, { stopReason })
|
||||
const result = await callSubagent(ctx, { description: 'd', prompt: 'p' })
|
||||
expect(result.isError).toBe(true)
|
||||
expect(text(result)).toContain('declined')
|
||||
expect(text(result)).toContain(fragment)
|
||||
})
|
||||
|
||||
it('registers under a configurable toolName so multiple providers can coexist', async () => {
|
||||
// The defining multi-provider use case: two loads, two distinct tool names,
|
||||
// each bound to a different provider — the tool registry rejects duplicate
|
||||
// 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(mock, { name: 'spawn', reply: 'from spawn' })
|
||||
await ctx.plugin(mock, { name: 'acp', reply: 'from acp' })
|
||||
await ctx.plugin(tool, { provider: 'spawn', toolName: 'subagent' })
|
||||
await ctx.plugin(tool, { provider: 'acp', toolName: 'subagent_acp' })
|
||||
|
||||
const names = ctx.tools.schemas().map(s => s.name).filter(n => n.startsWith('subagent')).sort()
|
||||
expect(names).toEqual(['subagent', 'subagent_acp'])
|
||||
|
||||
const viaSpawn = await ctx.tools.execute({ callId: CallId('c-spawn'), name: 'subagent', arguments: { description: 'd', prompt: 'p' }, agent: fakeAgent() })
|
||||
const viaAcp = await ctx.tools.execute({ callId: CallId('c-acp'), name: 'subagent_acp', arguments: { description: 'd', prompt: 'p' }, agent: fakeAgent() })
|
||||
expect(text(viaSpawn)).toBe('from spawn')
|
||||
expect(text(viaAcp)).toBe('from acp')
|
||||
})
|
||||
|
||||
it('treats an unknown (plugin-added) stop reason as an isError result', async () => {
|
||||
// SubagentStopReason is merge-extensible; the tool's stopReasonError default
|
||||
// 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)
|
||||
ctx.subagents.registerProvider({
|
||||
name: 'weird',
|
||||
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false },
|
||||
start: () => ({
|
||||
id: AgentId('weird-child'),
|
||||
result: Promise.resolve({ output: [{ type: 'text', text: 'partial' }], stopReason: 'frobnicated' as never }),
|
||||
cancel() {},
|
||||
dispose: async () => {},
|
||||
}),
|
||||
})
|
||||
await ctx.plugin(tool, { provider: 'weird' })
|
||||
|
||||
const result = await callSubagent(ctx, { description: 'd', prompt: 'p' })
|
||||
expect(result.isError).toBe(true)
|
||||
expect(text(result)).toContain('abnormally')
|
||||
})
|
||||
|
||||
it('forwards configured agentOptions into the start request', async () => {
|
||||
// Cover the `config.agentOptions ? … : {}` spread: a provider that captures
|
||||
// the request lets us assert the agentOptions reached it.
|
||||
let seen: { agentOptions?: { model?: string } } | undefined
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(SubagentService)
|
||||
ctx.subagents.registerProvider({
|
||||
name: 'capture',
|
||||
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false },
|
||||
start: (request) => {
|
||||
seen = request
|
||||
return {
|
||||
id: AgentId('capture-child'),
|
||||
result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }),
|
||||
cancel() {},
|
||||
dispose: async () => {},
|
||||
}
|
||||
},
|
||||
})
|
||||
await ctx.plugin(tool, { provider: 'capture', agentOptions: { model: 'child-model', systemPrompt: 'be terse' } })
|
||||
|
||||
await callSubagent(ctx, { description: 'd', prompt: 'p' })
|
||||
expect(seen?.agentOptions).toEqual({ model: 'child-model', systemPrompt: 'be terse' })
|
||||
})
|
||||
|
||||
it('defaults toolName and omits agentOptions when apply() is called directly (schema bypass)', async () => {
|
||||
// `ctx.plugin` validates+defaults config first (toolName→'subagent', the
|
||||
// agentOptions object→{}), so the runtime `?? 'subagent'` fallback and the
|
||||
// no-agentOptions branch are only reachable via a direct apply() that
|
||||
// bypasses schemastery — the same pattern acp-agent uses for its defaults.
|
||||
let seen: { agentOptions?: unknown } | undefined
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(SubagentService)
|
||||
ctx.subagents.registerProvider({
|
||||
name: 'bare',
|
||||
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false },
|
||||
start: (request) => {
|
||||
seen = request
|
||||
return {
|
||||
id: AgentId('bare-child'),
|
||||
result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }),
|
||||
cancel() {},
|
||||
dispose: async () => {},
|
||||
}
|
||||
},
|
||||
})
|
||||
// Direct apply with only `provider` — no toolName, no agentOptions.
|
||||
tool.apply(ctx, { provider: 'bare' })
|
||||
await new Promise(r => setTimeout(r, 10))
|
||||
|
||||
expect(ctx.tools.schemas().some(s => s.name === 'subagent')).toBe(true)
|
||||
await callSubagent(ctx, { description: 'd', prompt: 'p' })
|
||||
expect(seen?.agentOptions).toBeUndefined()
|
||||
})
|
||||
|
||||
it('fails loud when invoked without a calling agent', async () => {
|
||||
|
||||
@@ -45,6 +45,12 @@ describe('dsh-subagent-mock', () => {
|
||||
await expect(run.result).resolves.toMatchObject({ structured: { answer: 42 } })
|
||||
})
|
||||
|
||||
it('defaults structured output to { reply } when outputSchema is requested but no structured value is configured', async () => {
|
||||
const ctx = await mount({ reply: 'fallback reply' })
|
||||
const run = ctx.subagents.start('mock', baseRequest({ outputSchema: { answer: { type: 'number' } } }))
|
||||
await expect(run.result).resolves.toMatchObject({ structured: { reply: 'fallback reply' } })
|
||||
})
|
||||
|
||||
it('omits structured output when outputSchema capability is off', async () => {
|
||||
const ctx = await mount({ capabilities: { outputSchema: false } })
|
||||
// The service rejects an outputSchema request against a no-cap provider, so
|
||||
|
||||
Reference in New Issue
Block a user