refactor(tools): let the terminal marker ride the nested result

The staged-promotion machinery (concludingParents keyed by parent token
plus a pendingParentConclusions staging map) spread one fact — this call
concluded the turn — across three registry-side collections with manual
cleanup. Align it with how additionalContexts already crosses the same
boundary: concludeTurn() marks only its own execution, the marker rides
that execution's successful result (ToolExecutionFailure types
concludesTurn as never, so a policy-converted failure sheds it with the
type), and the composite that owns the nested dispatch forwards it —
Code Mode's binding does so beside its existing context forwarding.

The registry loses both parent-keyed collections and the promotion
block; the propagation decision moves to the owning boundary; the
structured-output consumer's own two-phase commit is untouched.
This commit is contained in:
_Kerman
2026-07-26 21:24:16 +08:00
parent 39c09c9a49
commit 04f0435cc9
4 changed files with 68 additions and 34 deletions

View File

@@ -268,6 +268,12 @@ export function createRunCodeTool(registry: ToolRegistry, requireRuntime: () =>
for (const context of result.additionalContexts ?? []) {
exec.deferContext(context)
}
// Like the context forwarding above, cross-boundary facts travel on
// the nested result and the composite forwards them: only a
// successful nested result can carry the terminal marker
// (ToolExecutionFailure types it never), so a policy-converted
// failure cannot stop the turn through a recovering program.
if (result.concludesTurn) exec.concludeTurn()
exec.agent?.session.append('tool/code-dispatch', {
parentCallId: exec.callId,
subCallId,

View File

@@ -307,7 +307,14 @@ export interface ToolRunContext extends ToolExecution {
* are emitted in call order.
*/
deferContext(context: UserMessageData): void
/** Mark a successful final result as terminal for the current agent turn. */
/**
* Mark a successful final result as terminal for the current agent turn.
* The marker rides this execution's own result (`concludesTurn` exists only
* on {@link ToolExecutionSuccess}); a composite that dispatches nested
* calls forwards it from the nested result, exactly like
* `additionalContexts`, so only an authoritative nested success can
* conclude the enclosing run.
*/
concludeTurn(): void
}
@@ -653,16 +660,8 @@ export class ToolRegistry extends Service {
/** Context deferred by a running tool body, keyed by its scheduler-owned execution. */
private deferredContexts = new WeakMap<ToolRunContext, UserMessageData[]>()
/** Successful executions whose tool body declared the current turn complete. */
/** Executions whose tool body declared the current turn complete. */
private concludingExecutions = new WeakSet<ToolExecution>()
/** Enclosing transport tokens marked terminal by a successful nested call. */
private concludingParents = new Set<ToolExecutionToken>()
/**
* Nested conclusions staged until their call's final verdict: a post-execute
* policy may still convert the nested success into an error, and a failed
* terminal operation must not stop the turn through its composite.
*/
private pendingParentConclusions = new WeakMap<ToolRunContext, ToolExecutionToken>()
/** Original caller cancellation, kept outside the wrapper-mutable execution object. */
private cancellationStates = new WeakMap<ToolRunContext, ToolCancellationState>()
/** Definition-owned final content transform snapshotted before policy begins. */
@@ -985,7 +984,6 @@ export class ToolRegistry extends Service {
const definition = this.get(name, agent)
const finalizeContent = definition?.finalizeContent?.bind(definition)
const concludingExecutions = this.concludingExecutions
const pendingParentConclusions = this.pendingParentConclusions
const base = {
token,
callId,
@@ -997,10 +995,7 @@ export class ToolRegistry extends Service {
deferredContexts.push(context)
},
concludeTurn(): void {
if (parent === undefined) concludingExecutions.add(this as unknown as ToolExecution)
// Staged, not propagated: only this nested call's authoritative
// successful result promotes the marker onto its parent.
else pendingParentConclusions.set(this as unknown as ToolRunContext, parent)
concludingExecutions.add(this as unknown as ToolExecution)
},
}
try {
@@ -1214,16 +1209,7 @@ export class ToolRegistry extends Service {
} catch (error: unknown) {
finalResult = this.materializeFinalResult(toolErrorResult(error))
}
// Promote a staged nested conclusion only on the call's authoritative
// successful verdict — a policy-converted failure must not let the
// composite stop the turn on a failed terminal operation.
const stagedParent = this.pendingParentConclusions.get(exec)
if (stagedParent !== undefined) {
this.pendingParentConclusions.delete(exec)
if (!finalResult.isError) this.concludingParents.add(stagedParent)
}
this.notifyResult(exec, finalResult)
this.concludingParents.delete(exec.token)
return finalResult
}
@@ -1394,7 +1380,7 @@ export class ToolRegistry extends Service {
}
meta = snapshotProjection(tool.name, 'presentationMeta', projected)
}
const concludesTurn = this.concludingExecutions.has(exec) || this.concludingParents.has(exec.token)
const concludesTurn = this.concludingExecutions.has(exec)
return this.markCanonical(exec, this.materializeFinalResult({
isError: false,
value,

View File

@@ -417,6 +417,46 @@ describe('the run_code dispatch bridge', () => {
expect(result.content).toEqual([{ type: 'text', text: 'done' }])
})
it('forwards a nested terminal conclusion onto the successful run_code result', async () => {
const { ctx, runtime } = await setup({ mode: 'code' })
ctx.tools.register(defineTool({
name: 'finalize',
description: 'Terminal tool.',
parameters: {},
output: {
schema: { type: 'string' },
render: (_args, value) => [{ type: 'text', text: value }],
},
execute(_args, exec) {
exec.concludeTurn()
return Promise.resolve('done')
},
}))
runtime.behavior = async (request) => {
await request.bindings[0]!.functions.finalize!({})
return { logs: [], value: 'program complete' }
}
const concluded = await runCode(ctx, 'await tools.finalize({})')
expect(concluded.isError).toBe(false)
expect(concluded.concludesTurn).toBe(true)
// A policy that converts the nested success into an error strips the
// marker with the result type: the recovering program cannot conclude.
const veto = ctx.on('tools/post-execute', async (exec, _result, next): Promise<PostToolDecision> => {
if (exec.name !== 'finalize') return next()
return { kind: 'block', feedback: [{ type: 'text', text: 'terminal rejected' }] }
})
runtime.behavior = async (request) => {
await request.bindings[0]!.functions.finalize!({}).catch(() => undefined)
return { logs: [], value: 'recovered' }
}
const recovered = await runCode(ctx, 'await tools.finalize({}).catch(() => {})')
veto()
expect(recovered.isError).toBe(false)
expect(recovered.concludesTurn).toBeUndefined()
})
it('serializes Promise.all dispatches: tool executions never overlap, in submission order', async () => {
const { ctx, runtime } = await setup({ mode: 'code' })
const intervals: [string, string][] = []

View File

@@ -553,18 +553,20 @@ describe('ToolRegistry', () => {
expect(nested.isError ? undefined : nested.value).toBe('')
})
it('propagates a nested concludeTurn only when the nested verdict stays successful', async () => {
it('carries a nested conclusion on the nested result for its composite to forward', async () => {
const ctx = await setup()
ctx.tools.register({
...echoTool,
name: 'terminal-nested',
async execute(_args, exec) {
exec.concludeTurn()
return 'staged'
return 'terminal'
},
})
// A composite that swallows its nested failure and returns success — the
// Code Mode shape the staged propagation exists for.
// A composite that forwards the marker from the nested result — the Code
// Mode dispatch shape. A recovering composite (nested failure swallowed)
// has no marker to forward: ToolExecutionFailure types concludesTurn as
// never, so only an authoritative nested success can conclude the run.
let call = 0
ctx.tools.register({
...echoTool,
@@ -574,13 +576,13 @@ describe('ToolRegistry', () => {
const nested = await ctx.tools.execute({
signal: exec.signal, callId: CallId(`nested-${call}`), name: 'terminal-nested', arguments: {}, parent: exec.token,
})
if (nested.concludesTurn) exec.concludeTurn()
return nested.isError ? 'nested failed, composite recovered' : 'nested succeeded'
},
})
// A policy converts the nested success into an error: the staged
// conclusion must NOT reach the composite, or the loop would stop the
// turn on a failed terminal operation.
// A policy converts the nested success into an error: the failed result
// carries no marker, so the recovering composite does not conclude.
const veto = ctx.on('tools/post-execute', async (exec, _result, next): Promise<PostToolDecision> => {
if (exec.name !== 'terminal-nested') return next()
return { kind: 'block', feedback: [{ type: 'text', text: 'nested success rejected' }] }
@@ -592,8 +594,8 @@ describe('ToolRegistry', () => {
expect(recovered.concludesTurn).toBeUndefined()
veto()
// The same nested call succeeding promotes the marker: the composite's
// own successful result now carries concludesTurn.
// The same nested call succeeding carries the marker; the composite
// forwards it onto its own successful result.
const concluded = await ctx.tools.execute({
signal: testToolSignal, callId: CallId('composite-ok'), name: 'composite', arguments: {},
})