Merge branch 'codex/tool-json-schema-dsl' into codex/canonical-tool-output
# Conflicts: # .agents/notes/implemented/feature/2026-06-30-interception-seams.md # docs/config-catalog.md # docs/cookbook/adding-a-tool.i18n.yaml # docs/cookbook/adding-a-tool.md # docs/cookbook/adding-a-tool.zh.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/tools.md # docs/event-producer-consumer.md # docs/persistence-catalog.md # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl # packages/bash/tool-bash/src/index.ts # packages/core/agent-loop/src/tool-calls.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/core/agent-loop/tests/tool-calls.spec.ts # packages/core/tools/README.md # packages/core/tools/src/index.ts # packages/core/tools/tests/code-mode.spec.ts # packages/core/tools/tests/tools.spec.ts # packages/fs/tool-fs-search/tests/integration.spec.ts # packages/fs/tool-fs-search/tests/tools.spec.ts # packages/fs/tool-fs/tests/integration.spec.ts # packages/mcp/mcp-client/src/tools.ts # packages/timeout/timeout-policy/tests/timeout-policy.spec.ts # packages/web/tool-web/tests/integration.spec.ts # packages/web/tool-web/tests/tool-web.spec.ts
This commit is contained in:
Tianyi Cui
@@ -135,7 +135,7 @@ export async function startInProcessRun(
|
||||
|
||||
const onAbort = (): void => {
|
||||
flags.cancelled = true
|
||||
child.cancel('subagent request aborted')
|
||||
child.cancel({ kind: 'parent' })
|
||||
}
|
||||
request.signal.addEventListener('abort', onAbort, { once: true })
|
||||
|
||||
|
||||
@@ -105,7 +105,7 @@ export function attachStructuredRuntime(childCtx: Context, schema: ObjectJsonSch
|
||||
// Stop the child's turn once its output is captured. This monotonic serial
|
||||
// checkpoint runs after the ordinary continuation waterfall, its reason,
|
||||
// and late-steering folding, so no ordering trick can resume a finished run.
|
||||
childCtx.on('agent/turn-stop', function (this: unknown): ContinuationStop | undefined {
|
||||
childCtx.on('agent/turn-stop', function (this: unknown, _agent, _turn, _signal): ContinuationStop | undefined {
|
||||
return captured === undefined ? undefined : { action: 'stop' }
|
||||
})
|
||||
|
||||
|
||||
@@ -19,6 +19,8 @@ import {
|
||||
STRUCTURED_OUTPUT_TOOL,
|
||||
} from '../src/structured.ts'
|
||||
|
||||
const testToolSignal = new AbortController().signal
|
||||
|
||||
type Script = ConstructorParameters<typeof MockAdapter>[0]
|
||||
|
||||
async function mountInvariants(ctx: Context): Promise<void> {
|
||||
@@ -230,7 +232,7 @@ describe('in-process structured output', () => {
|
||||
ctx.on('agent/session-start', (child) => {
|
||||
if (child === parent) return
|
||||
wrapperInstalled = true
|
||||
child.ctx.on('agent/turn-continuation', async (_subject, _turn, _decision, next): Promise<ContinuationDecision> => {
|
||||
child.ctx.on('agent/turn-continuation', async (_subject, _turn, _decision, _signal, next): Promise<ContinuationDecision> => {
|
||||
const downstream = await next()
|
||||
expect(downstream).toEqual({ action: 'stop' })
|
||||
return { action: 'continue' }
|
||||
@@ -256,7 +258,7 @@ describe('in-process structured output', () => {
|
||||
const run = await ctx.subagents.start('spawn', structuredRequest(parent))
|
||||
ctx.on('agent/session-start', (child) => {
|
||||
if (child.id !== run.id) return
|
||||
child.ctx.on('agent/turn-continuation', async (subject, _turn, _decision, next): Promise<ContinuationDecision> => {
|
||||
child.ctx.on('agent/turn-continuation', async (subject, _turn, _decision, _signal, next): Promise<ContinuationDecision> => {
|
||||
const downstream = await next()
|
||||
expect(downstream).toEqual({ action: 'stop' })
|
||||
subject.steer([{ type: 'text', text: 'late steering after downstream stop' }])
|
||||
@@ -655,6 +657,7 @@ describe('in-process structured output', () => {
|
||||
it('a structured_output call from an agent WITHOUT a structured run is UNKNOWN_TOOL (the tool does not exist for it)', async () => {
|
||||
const { ctx, parent } = await setup([])
|
||||
const result = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: 'x' as never,
|
||||
name: STRUCTURED_OUTPUT_TOOL,
|
||||
arguments: { answer: 1 },
|
||||
@@ -667,6 +670,7 @@ describe('in-process structured output', () => {
|
||||
it('a structured_output call with NO calling agent at all is UNKNOWN_TOOL', async () => {
|
||||
const { ctx } = await setup([])
|
||||
const result = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: 'x' as never,
|
||||
name: STRUCTURED_OUTPUT_TOOL,
|
||||
arguments: { answer: 1 },
|
||||
@@ -699,6 +703,7 @@ describe('in-process structured output', () => {
|
||||
// …and a LATER invalid call (its own body staged nothing) must not
|
||||
// resurrect c1's discarded value: drive the pipeline directly.
|
||||
const invalid = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: 'c2' as never,
|
||||
name: STRUCTURED_OUTPUT_TOOL,
|
||||
arguments: { answer: 'not-a-number' },
|
||||
@@ -707,6 +712,7 @@ describe('in-process structured output', () => {
|
||||
expect(invalid.isError).toBe(true)
|
||||
// A fresh valid call still captures ITS OWN value.
|
||||
const valid = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: 'c3' as never,
|
||||
name: STRUCTURED_OUTPUT_TOOL,
|
||||
arguments: { answer: 9 },
|
||||
@@ -737,6 +743,7 @@ describe('in-process structured output', () => {
|
||||
// (invalid args throw before the stage): the discarded value must not ride
|
||||
// its acceptance.
|
||||
const reused = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: 'c1' as never,
|
||||
name: STRUCTURED_OUTPUT_TOOL,
|
||||
arguments: { answer: 'not-a-number' },
|
||||
@@ -745,6 +752,7 @@ describe('in-process structured output', () => {
|
||||
expect(reused.isError).toBe(true)
|
||||
// Nothing was ever committed: a fresh valid call is still required.
|
||||
const valid = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: 'c1' as never,
|
||||
name: STRUCTURED_OUTPUT_TOOL,
|
||||
arguments: { answer: 5 },
|
||||
@@ -779,6 +787,7 @@ describe('in-process structured output', () => {
|
||||
return undefined as never
|
||||
}, { prepend: true })
|
||||
const denied = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: 'c1' as never,
|
||||
name: STRUCTURED_OUTPUT_TOOL,
|
||||
arguments: { answer: 2 },
|
||||
@@ -789,6 +798,7 @@ describe('in-process structured output', () => {
|
||||
// The discarded value was never promoted: a fresh valid call is required
|
||||
// (and succeeds, proving the runtime is not wedged).
|
||||
const valid = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: 'c1' as never,
|
||||
name: STRUCTURED_OUTPUT_TOOL,
|
||||
arguments: { answer: 5 },
|
||||
|
||||
@@ -27,9 +27,10 @@ async function setup(script: Script) {
|
||||
await mountInvariants(ctx)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
await ctx.plugin(SubagentService)
|
||||
ctx.llm.registerAdapter(['mock'], new MockAdapter(script))
|
||||
const adapter = new MockAdapter(script)
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
const parent = ctx.agentLoop.create(SessionId('parent'), { provider: 'mock', model: 'mock' })
|
||||
return { ctx, parent }
|
||||
return { ctx, parent, adapter }
|
||||
}
|
||||
|
||||
function request(parent: Agent, signal = new AbortController().signal) {
|
||||
@@ -133,12 +134,16 @@ describe('startInProcessRun', () => {
|
||||
})
|
||||
|
||||
it('uses the request signal after publication and dispose as cancellation paths', async () => {
|
||||
const { parent } = await setup(['hang', 'hang'])
|
||||
const { parent, adapter } = await setup(['hang', 'hang'])
|
||||
const controller = new AbortController()
|
||||
const signalled = await startInProcessRun(request(parent, controller.signal), {})
|
||||
await new Promise(resolve => setTimeout(resolve, 30))
|
||||
controller.abort('stop child')
|
||||
await expect(signalled.result).resolves.toMatchObject({ stopReason: 'aborted' })
|
||||
expect(adapter.requests[0]?.signal?.reason).toEqual({ kind: 'parent' })
|
||||
const child = parent.ctx.agents.get(signalled.id)
|
||||
const turnEnd = child?.session.events.findLast(event => event.type === 'turn/end')
|
||||
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'aborted' })
|
||||
await signalled.dispose()
|
||||
|
||||
const disposed = await startInProcessRun(request(parent), {})
|
||||
|
||||
@@ -325,9 +325,6 @@ export function apply(ctx: Context, config: Config): void {
|
||||
if (tasks === undefined) {
|
||||
throw new Error('background tasks unavailable: load @deepseek-ai/dsh-tasks and @deepseek-ai/dsh-tool-tasks')
|
||||
}
|
||||
// Reject cancellation before spawning; after return, the task-owned
|
||||
// signal covers both pending startup and the ready child.
|
||||
if (exec.signal?.aborted) throw new Error('subagent delegation aborted')
|
||||
// Task preflight finishes before the starter can spawn a child.
|
||||
const id = tasks.start({
|
||||
kind: 'subagent',
|
||||
@@ -355,7 +352,7 @@ export function apply(ctx: Context, config: Config): void {
|
||||
config,
|
||||
args.prompt,
|
||||
parent,
|
||||
exec.signal ?? new AbortController().signal,
|
||||
exec.signal,
|
||||
)
|
||||
|
||||
const run: SubagentRun = await ctx.subagents.start(config.provider, request)
|
||||
|
||||
@@ -3,7 +3,7 @@ import { Context } from 'cordis'
|
||||
import Loader from '@cordisjs/plugin-loader'
|
||||
import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
||||
import ToolRegistry, { TOOL_ABORTED_BEFORE_DISPATCH } from '@deepseek-ai/dsh-tools'
|
||||
import { type Agent } from '@deepseek-ai/dsh-agent'
|
||||
import AgentRegistry from '@deepseek-ai/dsh-agent'
|
||||
import SubagentService from '@deepseek-ai/dsh-subagent'
|
||||
@@ -15,6 +15,8 @@ import * as tool from '../src/index.ts'
|
||||
import { runOutcome, settleRun } from '../src/index.ts'
|
||||
import { SessionId } from '@deepseek-ai/dsh-session'
|
||||
|
||||
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
|
||||
@@ -45,6 +47,7 @@ function callSubagent(ctx: Context, args: unknown, over: { agent?: Agent | undef
|
||||
// exactOptionalPropertyTypes the key is omitted rather than set to undefined.
|
||||
const agent = 'agent' in over ? over.agent : fakeAgent()
|
||||
return ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId(`call-${++callCounter}`),
|
||||
name: 'subagent',
|
||||
arguments: args,
|
||||
@@ -106,11 +109,13 @@ describe('dsh-tool-subagent', () => {
|
||||
it('keeps foreground and background calls exclusive', async () => {
|
||||
const ctx = await setup({ provider: 'mock' })
|
||||
expect(ctx.tools.executionMode({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('subagent-foreground'),
|
||||
name: 'subagent',
|
||||
arguments: { description: 'do work', prompt: 'Reply OK' },
|
||||
})).toEqual({ kind: 'exclusive' })
|
||||
expect(ctx.tools.executionMode({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('subagent-background'),
|
||||
name: 'subagent',
|
||||
arguments: { description: 'do work', prompt: 'Reply OK', run_in_background: true },
|
||||
@@ -145,8 +150,8 @@ describe('dsh-tool-subagent', () => {
|
||||
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() })
|
||||
const viaSpawn = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('c-spawn'), name: 'subagent', arguments: { description: 'd', prompt: 'p' }, agent: fakeAgent() })
|
||||
const viaAcp = await ctx.tools.execute({ signal: testToolSignal, 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')
|
||||
})
|
||||
@@ -424,7 +429,7 @@ describe('dsh-tool-subagent', () => {
|
||||
expect(result.isError).toBe(true)
|
||||
})
|
||||
|
||||
it('passes an already-aborted signal so provider startup rejects', async () => {
|
||||
it('skips provider startup for an already-aborted signal', async () => {
|
||||
const sawAborted = vi.fn()
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
@@ -444,8 +449,12 @@ describe('dsh-tool-subagent', () => {
|
||||
const controller = new AbortController()
|
||||
controller.abort() // already aborted BEFORE the tool runs
|
||||
const result = await callSubagent(ctx, { description: 'd', prompt: 'p' }, { signal: controller.signal })
|
||||
expect(sawAborted).toHaveBeenCalledTimes(1)
|
||||
expect(sawAborted).not.toHaveBeenCalled()
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.error).toEqual({
|
||||
message: 'tool call aborted before dispatch',
|
||||
info: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH },
|
||||
})
|
||||
})
|
||||
|
||||
it('tools depend on the service: no `subagent` tool without ctx.subagents', async () => {
|
||||
@@ -648,6 +657,7 @@ describe('dsh-tool-subagent background mode', () => {
|
||||
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 },
|
||||
@@ -657,6 +667,7 @@ describe('dsh-tool-subagent background mode', () => {
|
||||
|
||||
// Final-output reads are idempotent (not consumed).
|
||||
const again = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('collect-2'),
|
||||
name: 'task_output',
|
||||
arguments: { task_id: 'subagent-1' },
|
||||
@@ -672,14 +683,18 @@ describe('dsh-tool-subagent background mode', () => {
|
||||
expect(text(result)).toContain('background tasks unavailable: load @deepseek-ai/dsh-tasks')
|
||||
})
|
||||
|
||||
it('refuses to start when the tool signal is already aborted', async () => {
|
||||
it('skips background startup when the tool signal is already aborted', async () => {
|
||||
const ctx = await backgroundSetup({ provider: 'mock' })
|
||||
const parent = ownerAgent(ctx, 'sess-parent')
|
||||
const controller = new AbortController()
|
||||
controller.abort()
|
||||
const result = await callSubagent(ctx, { description: 'd', prompt: 'p', run_in_background: true }, { agent: parent, signal: controller.signal })
|
||||
expect(result.isError).toBe(true)
|
||||
expect(text(result)).toContain('subagent delegation aborted')
|
||||
expect(result.error).toEqual({
|
||||
message: 'tool call aborted before dispatch',
|
||||
info: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH },
|
||||
})
|
||||
expect(text(result)).toBe('Error: tool call aborted before dispatch')
|
||||
})
|
||||
|
||||
it('settles an asynchronous provider-start failure as a failed task', async () => {
|
||||
@@ -694,6 +709,7 @@ describe('dsh-tool-subagent background mode', () => {
|
||||
tool.apply(ctx, { provider: 'broken-start', toolName: 'subagent_broken' })
|
||||
|
||||
const started = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('broken-start'),
|
||||
name: 'subagent_broken',
|
||||
arguments: { description: 'broken', prompt: 'p', run_in_background: true },
|
||||
@@ -701,6 +717,7 @@ describe('dsh-tool-subagent background mode', () => {
|
||||
})
|
||||
expect(text(started)).toBe('started background subagent task subagent-1')
|
||||
const output = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('broken-output'),
|
||||
name: 'task_output',
|
||||
arguments: { task_id: 'subagent-1', wait: true },
|
||||
@@ -723,18 +740,21 @@ describe('dsh-tool-subagent background mode', () => {
|
||||
tool.apply(ctx, { provider: 'pending-start', toolName: 'subagent_pending' })
|
||||
|
||||
await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('pending-start'),
|
||||
name: 'subagent_pending',
|
||||
arguments: { description: 'pending', prompt: 'p', run_in_background: true },
|
||||
agent: parent,
|
||||
})
|
||||
await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('pending-kill'),
|
||||
name: 'task_kill',
|
||||
arguments: { task_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 },
|
||||
@@ -772,19 +792,19 @@ describe('dsh-tool-subagent background mode', () => {
|
||||
// Direct apply preserves omitted agentOptions instead of applying schema defaults.
|
||||
tool.apply(ctx, { provider: 'hanging', toolName: 'subagent_hang' })
|
||||
|
||||
const startOne = await ctx.tools.execute({ callId: CallId('h1'), name: 'subagent_hang', arguments: { description: 'one', prompt: 'p', run_in_background: true }, agent: parent })
|
||||
const startTwo = await ctx.tools.execute({ callId: CallId('h2'), name: 'subagent_hang', arguments: { description: 'two', prompt: 'p', run_in_background: true }, agent: parent })
|
||||
const startOne = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('h1'), name: 'subagent_hang', arguments: { description: 'one', prompt: 'p', run_in_background: true }, agent: parent })
|
||||
const startTwo = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('h2'), name: 'subagent_hang', arguments: { description: 'two', prompt: 'p', run_in_background: true }, agent: parent })
|
||||
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({ callId: CallId('k1'), name: 'task_kill', arguments: { task_id: 'subagent-1', reason: 'superseded' }, agent: parent })
|
||||
const withoutReason = await ctx.tools.execute({ callId: CallId('k2'), name: 'task_kill', arguments: { task_id: 'subagent-2' }, agent: parent })
|
||||
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')
|
||||
expect(cancels).toEqual(['superseded', 'background subagent task killed'])
|
||||
|
||||
// The aborted children settle as killed tasks.
|
||||
const killed = await ctx.tools.execute({ 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: 'task_output', arguments: { task_id: 'subagent-1', wait: true }, agent: parent })
|
||||
expect(text(killed)).toBe('(no new output)\n[status: killed]')
|
||||
})
|
||||
|
||||
@@ -878,6 +898,7 @@ describe('background preflight failure (no orphaned child, by construction)', ()
|
||||
tool.apply(ctx, { provider: 'probe', toolName: 'subagent_probe' })
|
||||
|
||||
const result = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('probe-1'),
|
||||
name: 'subagent_probe',
|
||||
arguments: { description: 'd', prompt: 'p', run_in_background: true },
|
||||
|
||||
Reference in New Issue
Block a user