Merge branch 'codex/canonical-tool-output' into codex/code-mode-typed-results
# Conflicts: # 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/event-producer-consumer.md # packages/core/tools/tests/code-mode.spec.ts
This commit is contained in:
@@ -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' }])
|
||||
@@ -657,6 +659,7 @@ 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 },
|
||||
@@ -669,6 +672,7 @@ 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 },
|
||||
@@ -701,6 +705,7 @@ 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' },
|
||||
@@ -709,6 +714,7 @@ 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 },
|
||||
@@ -739,6 +745,7 @@ 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' },
|
||||
@@ -747,6 +754,7 @@ 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 },
|
||||
@@ -781,6 +789,7 @@ 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 },
|
||||
@@ -791,6 +800,7 @@ 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), {})
|
||||
|
||||
Reference in New Issue
Block a user