fix(agent-loop): log tool/result under the originating call.id (P1-7)

The loop passed the authoritative call.id into ctx.tools.execute() but then
appended tool/result using result.callId — the value a tools/execute waterfall
listener returns — with no check. A listener returning a mismatched id silently
recorded the result under the wrong call. callId is the model-transcript
correlation id: deriveMessages() turns it into the tool-result block's
toolCallId, which must pair with the assistant tool-call block; a wrong id
orphans that pairing in the next model request.

Append tool/result with callId: call.id (the loop's authoritative id). A
listener-internal id, if ever worth keeping, belongs in a separate diagnostic
field — never overloaded onto callId.

Test: a tools/execute listener returns a wrong callId; assert the logged
tool/result.callId equals call.id AND deriveMessages() yields a tool-result
block whose toolCallId equals call.id (not the wrong returned id). Verified the
test fails on the pre-fix result.callId behavior.
This commit is contained in:
Tianyi Cui
2026-06-15 01:06:13 +08:00
parent 22e9152d8b
commit 37576ade6a
2 changed files with 55 additions and 1 deletions
+7 -1
View File
@@ -420,7 +420,13 @@ async function runStep(
})
session.append('tool/result', {
turn, step,
callId: result.callId,
// The correlation id MUST be the loop's authoritative call.id (the
// model-transcript id that deriveMessages turns into toolCallId), NOT
// result.callId — a tools/execute waterfall listener returning a
// mismatched id would otherwise orphan the call↔result pairing in the
// next model request. A listener-internal id, if ever needed, belongs in
// a separate diagnostic field, never overloaded onto callId.
callId: call.id,
content: result.content,
isError: result.isError,
...result.error ? { error: result.error } : {},
@@ -887,3 +887,51 @@ describe('P1-5: a started turn (and any open step) is always closed on a boundar
expect(boundaryCounts(agent).turnEnd).toBe(2)
})
})
describe('P1-7: tool/result is logged under the originating call.id, not result.callId', () => {
it('a tools/execute listener returning a mismatched callId cannot orphan the call↔result pairing', async () => {
// Model emits a tool-call with id "c1", then a final text turn.
const adapter = new MockAdapter([
toolCallResponse('c1', 'echo', { x: 1 }),
textResponse('done'),
])
const ctx = await harness(adapter)
ctx.tools.register(defineTool({
name: 'echo',
description: 'echo',
parameters: { x: { type: 'number' } },
async execute() { return [{ type: 'text', text: 'ok' }] },
}))
// A waterfall listener short-circuits with a result carrying the WRONG
// callId (a listener-internal/proxy id). The loop must still record the
// tool/result under the model's authoritative call.id.
ctx.on('tools/execute', (exec) => {
expect(exec.callId).toBe(CallId('c1')) // the loop passed the real id in
return Promise.resolve({ callId: CallId('wrong-proxy-id'), content: [{ type: 'text', text: 'ok' }], isError: false })
}, { prepend: true })
const agent = ctx.agentLoop.create('a-callid', { model: 'mock' })
send(agent, 'use tool')
await waitForIdle(ctx, agent)
// The logged tool/result.callId is the originating call.id, NOT the
// listener's wrong id.
const resultEvent = [...agent.session.events].find(e => e.type === 'tool/result')
expect(resultEvent?.type).toBe('tool/result')
if (resultEvent?.type === 'tool/result') {
expect(resultEvent.data.callId).toBe(CallId('c1'))
}
// And deriveMessages pairs the tool-result with the assistant tool-call:
// the derived tool-result block's toolCallId equals the original call.id.
const messages = agent.session.deriveMessages()
const toolResultBlock = messages
.flatMap(m => m.content)
.find(b => b.type === 'tool-result')
expect(toolResultBlock?.type).toBe('tool-result')
if (toolResultBlock?.type === 'tool-result') {
expect(toolResultBlock.toolCallId).toBe(CallId('c1'))
}
})
})