Files
orca/src/main/codex/codex-structured-session-close.test.ts
T
Brennan BensonandMerge Sim 5868fdc9e3 feat(native-chat): report Codex background tasks in the chat strip (#19346)
* feat(native-chat): report Codex background tasks in the chat strip

The background-tasks strip works for Claude only; a structured Codex
session shows nothing in it. Feed it from the Codex app-server stream.

The strip stands for work that OUTLIVED a turn, which is what the
monitoring header, Claude's foreground suppression, and the conversation
command gate all already assume. Codex has no `is_backgrounded` flag, so
that fact is derived from the turn boundary: a `subAgentActivity` child or
a primary-thread `commandExecution` becomes visible once the turn it
belongs to completes and it is still unsettled.

`turn/completed` only reveals a task here, never settles one — measured on
`codex app-server` 0.153.4, a spawn_agent child reported `completed` 95.8s
after its parent turn ended. Only a child's own activity kind settles it.

Codex exposes no honest stop: `turn/interrupt` on a child ends its turn
without emitting a terminal activity item and leaves its shell running. So
the state carries a new optional `supportsStopAll: false`, the strip hides
a control that could not act, and the blocked-command message asks the user
to wait rather than to press a button that does not exist.

* refactor(codex): move session teardown out of the structured adapter

Merging main crossed the 300-line cap on
`codex-structured-session-adapter.ts`: the rewind backend (#19235) and this
branch's close-time strip clear both landed in it. The four close paths move
verbatim into `codex-structured-session-teardown.ts`, where they funnel
through one `settled` helper instead of repeating the notification-retry and
background-task cleanup at each call site. No ratchet bump.

Also normalize a background task's description once at receipt rather than on
every projection; the roster is re-projected on each observed frame.

* fix(codex): drop the shell row the journal already settles

A `commandExecution` still `inProgress` when its turn ends was reported as a
`command` task. But `settleCodexJournalTurn` writes exactly those items to the
journal as `state: 'failed'` on `turn/completed` and forgets them, so the strip
row would have claimed a shell was still running at the same instant Orca
recorded that it was not — two surfaces contradicting each other about the same
process.

A subagent is the opposite case and stays: the roster pointedly does not sweep
at a turn boundary, because children measurably outlive it. That leaves the
producer making exactly one claim — these spawn_agent children are still live
after their turn — which the durable roster row corroborates.

* fix(native-chat): track Codex background execution lifetimes

* fix(native-chat): keep running tool groups from claiming completion

* Fix runtime catalog and capability expectation

* fix(codex): keep a child's name on the command row that outlives it

A child agent's commands stay hidden behind its agent row while the child
works. Once the child's turn settles with a command still running, that
command surfaces as its own row labelled from the raw command string, so
'long_probe' became "/bin/zsh -lc 'ping -c 300 127.0.0.1 > /dev/null'"
at the moment that row was the only remaining signal for the work.

Qualify a child's command row with the child's label. Resolved on read,
so a label registered after the command still lands, and bounded by the
existing description cap so admission accounting stays valid. Primary-
thread commands are left unqualified: they have no child to name.

---------

Co-authored-by: Merge Sim <sim@local>
2026-09-09 00:13:20 -07:00

205 lines
7.0 KiB
TypeScript

import { describe, expect, it, vi } from 'vitest'
import type { AgentSessionJournalIdentity } from '../../shared/agent-session-journal-types'
import type {
CodexAppServerConnection,
CodexAppServerConnectionHandlers,
openCodexAppServerConnection
} from './codex-app-server-connection'
import {
CodexStructuredSessionAdapter,
type CodexStructuredSessionEvent
} from './codex-structured-session-adapter'
import { handleCodexSessionExit } from './codex-structured-session-close'
import { CodexBackgroundTaskTracker } from './codex-background-task-tracker'
import type { CodexSession } from './codex-structured-session-state'
import type { StructuredAgentSessionAdapter } from '../native-chat/agent-session-wire/structured-agent-session-adapter'
import { StructuredAgentSessionAdapterRouter } from '../native-chat/agent-session-wire/structured-agent-session-adapter-router'
const THREAD = 'thread-1'
function identity(sessionId: string): AgentSessionJournalIdentity {
return {
sessionId,
workspaceId: 'workspace-1',
hostId: 'host-1',
agent: 'codex',
providerHandle: { kind: 'codex', threadId: THREAD }
}
}
function adapterFixture() {
const connections: {
connection: CodexAppServerConnection
handlers: CodexAppServerConnectionHandlers
}[] = []
const events: CodexStructuredSessionEvent[] = []
let generation = 0
const openConnection = (async (_launch, handlers = {}) => {
const connection: CodexAppServerConnection = {
pid: 4321,
closed: false,
request: async (method) => (method === 'thread/start' ? { thread: { id: THREAD } } : {}),
notify: () => {},
respond: () => {},
respondWithError: () => {},
close: async () => true
}
connections.push({ connection, handlers })
return connection
}) as typeof openCodexAppServerConnection
const adapter = new CodexStructuredSessionAdapter({
resolveLaunch: async () => ({
command: 'codex',
args: ['app-server'],
cwd: '/workspace',
codexHome: null,
resumeThreadId: null
}),
openConnection,
readProcessStartTime: async () => 1_700_000_000_000,
mintAcquisitionGeneration: () => `generation-${++generation}`,
onEvent: (event) => events.push(event)
})
return { adapter, connections, events }
}
function claudeAdapterStub(): StructuredAgentSessionAdapter {
return {
acquire: vi.fn(async () => ({ process: { pid: 1 } }) as never),
dispatch: vi.fn(),
cancelTurn: vi.fn(),
answerPrompt: vi.fn(),
setOption: vi.fn()
}
}
describe('Codex structured session close lifecycle', () => {
it('forwards a one-shot exit when lifecycle admission is rejected', () => {
const connection: CodexAppServerConnection = {
pid: 4321,
closed: true,
request: async () => ({}),
notify: () => {},
respond: () => {},
respondWithError: () => {},
close: async () => true
}
const prompts = { clear: vi.fn() } as unknown as CodexSession['prompts']
const translator = {
handle: vi.fn().mockReturnValueOnce({ accepted: false, reason: 'backpressure' as const }),
dispose: vi.fn()
} as unknown as NonNullable<CodexSession['translator']>
const session = {
connection,
backgroundTasks: new CodexBackgroundTaskTracker('thread-1'),
ended: false,
requestedClose: false,
fence: 7,
acquisitionGeneration: 'generation-1',
threadId: THREAD,
historyPath: null,
prompts,
options: new Map(),
reportedOptions: {},
turnIdWaiters: [],
translator
} as CodexSession
const sessions = new Map([['session-1', session]])
const onEvent = vi.fn()
expect(
handleCodexSessionExit({
sessions,
sessionId: 'session-1',
connection,
error: new Error('provider exited'),
prompts,
onEvent
})
).toBe(true)
expect(session.ended).toBe(true)
expect(prompts.clear).toHaveBeenCalledOnce()
expect(onEvent).toHaveBeenCalledOnce()
expect(translator.dispose).toHaveBeenCalledOnce()
expect(onEvent.mock.calls[0]?.[0]).toMatchObject({
cause: 'unexpected-exit',
settlementRetryRequired: true
})
expect(translator.handle).toHaveBeenCalledOnce()
})
it('mints a distinct child generation even when acquisitions share one fence', async () => {
const { adapter } = adapterFixture()
const input = { identity: identity('session-1'), fence: 7, spawnToken: 'spawn-1' }
const first = await adapter.acquire(input)
const second = await adapter.acquire(input)
expect(first.acquisitionGeneration).toBe('generation-1')
expect(second.acquisitionGeneration).toBe('generation-2')
})
it('distinguishes an observed provider death from a requested close', async () => {
const { adapter, connections, events } = adapterFixture()
await adapter.acquire({ identity: identity('session-1'), fence: 7, spawnToken: 'spawn-1' })
connections[0]?.handlers.onExit?.(new Error('provider exited'))
await adapter.acquire({ identity: identity('session-2'), fence: 9, spawnToken: 'spawn-2' })
await adapter.closeSession('session-2')
expect(events.filter((event) => event.type === 'ended')).toMatchObject([
{
cause: 'unexpected-exit',
fence: 7,
acquisitionGeneration: 'generation-1'
},
{
cause: 'requested-close',
fence: 9,
acquisitionGeneration: 'generation-2'
}
])
})
it('force-close preserves unexpected-exit evidence when the adapter reports exit during close', async () => {
const { adapter, connections, events } = adapterFixture()
await adapter.acquire({ identity: identity('session-1'), fence: 7, spawnToken: 'spawn-1' })
const current = connections[0]
if (!current) {
throw new Error('missing connection')
}
current.connection.close = async () => {
current.handlers.onExit?.(new Error('sink failed'))
return true
}
await expect(adapter.forceCloseSession?.('session-1')).resolves.toBe(true)
expect(events.filter((event) => event.type === 'ended')).toMatchObject([
{ cause: 'unexpected-exit', reason: 'sink failed', fence: 7 }
])
})
it('routes Codex sink-failure recovery through force-close and preserves unexpected-exit settlement', async () => {
const { adapter, connections, events } = adapterFixture()
const router = new StructuredAgentSessionAdapterRouter(
{ claude: claudeAdapterStub(), codex: adapter },
async () => {}
)
await router.acquire({ identity: identity('session-1'), fence: 7, spawnToken: 'spawn-1' })
const current = connections[0]
if (!current) {
throw new Error('missing connection')
}
current.connection.close = async () => {
current.handlers.onExit?.(new Error('journal sink failed'))
return true
}
const forceCloseSession = router.forceCloseSession
await expect(forceCloseSession('session-1')).resolves.toBe(true)
expect(events.filter((event) => event.type === 'ended')).toMatchObject([
{ cause: 'unexpected-exit', reason: 'journal sink failed', fence: 7 }
])
})
})