mirror of
https://github.com/stablyai/orca.git
synced 2026-11-02 10:08:13 +00:00
* [comment audit] Align legacy failure-read counts with cached display * [comment audit] Condense shared provider lifecycle and browser recovery comments [skip ci] * [comment audit] Condense shared generation, path and preview comments [skip ci] * [comment audit] Condense host, file and Git contract rationale [skip ci] * [comment audit] Tighten Git lifecycle and provider contract comments [skip ci] * [comment audit] Clarify shared host authority and launch isolation [skip ci] * [comment audit] simplify local access mobile and native chat contracts [skip ci] * [comment audit] simplify native chat presentation and state contracts [skip ci] * [comment audit] simplify native runtime and provider contracts [skip ci] * [comment audit] simplify migration and orchestration contracts [skip ci] * [comment audit] simplify plugin trust and process capture rationale [skip ci] * [comment audit] simplify terminal delivery and remote compatibility rationale [skip ci] * [comment audit] clarify remote recovery and launch wire rationale [skip ci] * [comment audit] shorten shared RPC compatibility and runtime evidence comments [skip ci] * [comment audit] simplify secure storage shell startup and sidebar rationale [skip ci] * [comment audit] clarify sidebar, skill and SSH invariants [skip ci] * [comment audit] condense structured chat delivery and timing rationale [skip ci] * [comment audit] condense terminal replay and telemetry invariants [skip ci] * [comment audit] clarify launch permission and terminal delivery rationale [skip ci] * [comment audit] clarify workspace ownership and layout contracts [skip ci] * [comment audit] wait for fitted and painted SSH terminal links * [comment audit] clarify layout persistence and session ownership [skip ci] * [comment audit] clarify host routing and workspace lifecycle contracts [skip ci] * [comment audit] clarify startup persistence and app lifetime comments [skip ci] * [comment audit] clarify recovery and activity boundaries [skip ci] * [comment audit] condense activity and artifact invariants [skip ci] * [comment audit] condense automation authority contracts [skip ci] * [comment audit] simplify automation scheduling and history contracts [skip ci] * [comment audit] clarify browser chrome and annotation lifecycles [skip ci] * [comment audit] clarify browser routing and retained guest ownership [skip ci] * [comment audit] clarify browser recovery and document ownership comments [skip ci] * [comment audit] restore hosted runners required by native IME fixtures * [comment audit] shorten preview, palette and dashboard invariants [skip ci] * [comment audit] clarify terminal preview, dashboard and retention comments [skip ci] * [comment audit] clarify diff-note recovery and editor lifecycle comments [skip ci] * [comment audit] shorten rich-text and combined-diff ownership comments [skip ci] * [comment audit] shorten autosave, draft recovery and model ownership comments [skip ci] * [comment audit] shorten save-queue, notebook and Markdown constraints [skip ci] * [comment audit] shorten Monaco, PDF and rich Markdown safeguards [skip ci] * [comment audit] clarify rich Markdown source and selection safeguards [skip ci] * [comment audit] clarify editor loading and emulator stream lifetimes [skip ci] * [comment audit] trim emulator and feature tour narration [skip ci] * [comment audit] clarify floating workspace and GitHub cache ownership [skip ci] * [comment audit] trim provider controls and Linear filter explanations [skip ci] * [comment audit] clarify pairing and chat resume lifetimes [skip ci] * [comment audit] clarify chat delivery and transcript lifetimes [skip ci] * [comment audit] clarify session options and host-owned status [skip ci] * [comment audit] clarify draft durability and live-status precedence [skip ci] * [comment audit] Trim chat send and model ownership explanations [skip ci] * [comment audit] Shorten transcript ownership and send recovery comments [skip ci] * [comment audit] Simplify native chat composer and transcript hook comments [skip ci] * [comment audit] Shorten native chat scroll and structured session explanations [skip ci] * [comment audit] Trim workspace picker and onboarding commentary [skip ci] * [comment audit] Simplify pet rendering, review cache and quick open comments [skip ci] * [comment audit] Trim sidebar and session history explanations [skip ci] * [comment audit] Condense session resume and review checks comments [skip ci] * [comment audit] Shorten checks state and file explorer refresh comments [skip ci] * [comment audit] Trim plugin bridge and source-control action rationale [skip ci] * [comment audit] Trim source-control listing and review rationale [skip ci] * [comment audit] Shorten sidebar lifecycle and explorer safeguards [skip ci] * [comment audit] Condense Settings account and appearance rationale [skip ci] * [comment audit] Trim pairing and repository Settings explanations [skip ci] * [comment audit] Condense Settings search SSH and terminal safeguards [skip ci] * [comment audit] Shorten Settings voice and provider ownership comments [skip ci] * [comment audit] Condense Settings draft persistence and host-state rationale [skip ci] * [comment audit] Trim Settings hooks and sidebar setup rationale [skip ci] * [comment audit] Condense sidebar deletion and board-filter safeguards [skip ci] * [comment audit] Condense worktree cards, host ownership and Markdown contracts [skip ci] * [comment audit] Condense sidebar drag, folder and filtering contracts [skip ci] * [comment audit] Condense sidebar parity, sleep and host ownership contracts [skip ci] * [comment audit] Prune focus-read baseline after comment cleanup * [comment audit] Clarify sidebar visibility, board drops and agent evidence [skip ci] * [comment audit] Tighten sidebar listing, drag and reveal contracts [skip ci] * [comment audit] Clarify viewport geometry and skill update safeguards [skip ci] * [comment audit] Tighten skill inventory, usage and host status comments [skip ci] * [comment audit] Clarify usage ownership and resource kill safeguards [skip ci] * [comment audit] Tighten tab selection, rename and search contracts [skip ci] * [comment audit] Tighten tab-strip geometry and drag ownership comments [skip ci] * [comment audit] Tighten Tasks recovery, pagination and mutation comments [skip ci] * [comment audit] Tighten provider loading and terminal recovery comments [skip ci] * [comment audit] Tighten completion, cadence and PTY ownership comments [skip ci] * [comment audit] Clarify terminal restore and parked-pane boundaries [skip ci] * [comment audit] Tighten PTY startup and replay explanations [skip ci] * [comment audit] Clarify PTY identity and delivery ownership [skip ci] * [comment audit] Shorten remote reconnect and input replay rationale [skip ci] * [comment audit] Condense terminal parking clipboard and file link comments [skip ci] * [comment audit] Clarify IME ownership and trim trace history [skip ci] * [comment audit] Shorten pane recovery and parked watcher explanations [skip ci] * [comment audit] Condense snapshot replay and visibility recovery rationale [skip ci] * [comment audit] Shorten terminal parking and keyboard ownership rationale [skip ci] * [comment audit] Trim renderer lifecycle and menu rationale [skip ci] * [comment audit] Condense workspace cleanup ownership and settlement notes [skip ci] * [comment audit] Clarify renderer hook evidence and source ownership [skip ci] * [comment audit] Tighten IPC ownership and reconnect explanations [skip ci] * [comment audit] Trim renderer focus, paste and attention comments [skip ci] * [comment audit] Shorten scroll, locale and agent lifecycle comments [skip ci] * [comment audit] Trim agent launch, resume and ownership commentary [skip ci] * [comment audit] Shorten account, browser and editor comments [skip ci] * [comment audit] Clarify host-mirror waits, previews and input ownership [skip ci] * [comment audit] Condense launch recovery and editor tokenization comments [skip ci] * [comment audit] Condense workspace selection and terminal pane rationale [skip ci] * [comment audit] Condense terminal fitting and rendering recovery comments [skip ci] * [comment audit] Condense terminal input and host routing explanations [skip ci] * [comment audit] Condense ownership and sleeping-session recovery rationale [skip ci] * [comment audit] Condense structured launch and terminal link explanations [skip ci] * [comment audit] Condense terminal ownership and workspace file routing rationale [skip ci] * [comment audit] Condense session persistence and workspace activation rationale [skip ci] * [comment audit] Condense workspace routing and browser ownership rationale [skip ci] * [comment audit] Condense mirror recovery and layout authority rationale [skip ci] * [comment audit] Condense runtime transport and file safety rationale [skip ci] * [comment audit] Condense runtime graph and structured session rationale [skip ci] * [comment audit] Condense browser creation and remote tab recovery rationale [skip ci] * [comment audit] Condense snapshot authority and publisher recovery rationale [skip ci] * [comment audit] Condense frame, startup and provider cache rationale [skip ci] * [comment audit] Condense host twin and agent lifecycle rationale [skip ci] * [comment audit] Condense browser authority and editor cleanup rationale [skip ci] * [comment audit] Condense editor buffer identity and review cache rationale [skip ci] * [comment audit] Condense provider lifetime and repository ownership rationale [skip ci] * [comment audit] Condense reconnect, hydration and terminal retirement rationale [skip ci] * [comment audit] Condense recovery, reconciliation and persistence rationale [skip ci] * [comment audit] Condense cleanup ownership and listing admission rationale [skip ci] * [comment audit] Condense teardown ordering and terminal ownership rationale [skip ci] * [comment audit] Condense recovery ledger and web host-boundary rationale [skip ci] * [comment audit] Condense web reconnect and credential lifecycle rationale [skip ci] * [comment audit] Condense cloud rollout and assignment safety rationale [skip ci] * [comment audit] Condense relay session and database recovery rationale [skip ci] * [comment audit] Condense relay placement and protocol compatibility rationale [skip ci] * [comment audit] Condense build and packaging constraints [skip ci] * [comment audit] Condense CI gates and validation isolation rationale [skip ci] * [comment audit] Condense catalog identity and browser validation rationale [skip ci] * [comment audit] Condense mobile browser and frame-budget rationale [skip ci] * [comment audit] Shorten mobile route and browser test explanations [skip ci] * [comment audit] Condense editor and session seam test rationale [skip ci] * [comment audit] Trim session and terminal closure history [skip ci] * [comment audit] Shorten terminal browser and census explanations [skip ci] * [comment audit] Preserve root-only E2E diagnostic baseline * [comment audit] Condense mobile seam and HTML preview test rationale [skip ci] * [comment audit] Condense preview instrumentation and render harness rationale [skip ci] * [comment audit] Condense bundle contracts and native-build constraints [skip ci] * [comment audit] Shorten native packaging and CI routing rationale [skip ci] * [comment audit] Condense release tooling and benchmark constraints [skip ci] * [comment audit] Condense packaging and platform gate rationale [skip ci] * [comment audit] Shorten mobile route and history rationale [skip ci] * [comment audit] Condense mobile browser and component rationale [skip ci] * [comment audit] Shorten drawer and workspace-form rationale [skip ci] * [comment audit] Trim mobile review and editor-document explanations [skip ci] * [comment audit] Condense editor lifecycle and Markdown explanations [skip ci] * [comment audit] Trim mobile file, diagnostics and dictation commentary [skip ci] * [comment audit] Simplify mobile host-list and workspace-view explanations [skip ci] * [comment audit] Clarify mobile shell lifetime and bridge delivery constraints [skip ci] * [comment audit] Condense bridge stream, native request and audio rationale [skip ci] * [comment audit] Reduce bridge schema and page-client commentary [skip ci] * [comment audit] Tighten mobile page bridge contracts [skip ci] * [comment audit] Clarify mobile cache and session constraints [skip ci] * [comment audit] Condense mobile route and lifecycle rationale [skip ci] * [comment audit] Tighten mobile shell hook timing rationale [skip ci] * [comment audit] Clarify route handoff and notification compatibility [skip ci] * [comment audit] Clarify push registration and dictation cleanup constraints [skip ci] * [comment audit] Condense keyboard geometry and native media ownership rationale [skip ci] * [comment audit] Tighten mobile chat scroll and composer concurrency rationale [skip ci] * [comment audit] Condense mobile reply compatibility and upload ownership rationale [skip ci] * [comment audit] Condense optimistic echo and scroll ownership rationale [skip ci] * [comment audit] Tighten stream replay and queued session ownership rationale [skip ci] * [comment audit] Condense mobile composer and reply-schema constraints [skip ci] * [comment audit] Clarify mobile transcript recovery and session ownership [skip ci] * [comment audit] Clarify mobile queue and source-control compatibility [skip ci] * [comment audit] Condense storage and task launch constraints [skip ci] * [comment audit] Clarify task schemas and terminal document ownership [skip ci] * [comment audit] Tighten terminal input and viewport rationale [skip ci] * [comment audit] Shorten terminal and RPC recorder contracts [skip ci] * [comment audit] Condense recorder engine and connection contracts [skip ci] * [comment audit] Shorten host credential and relay recovery comments [skip ci] * [comment audit] Tighten pairing recovery and bundle transport rationale [skip ci] * [comment audit] Clarify RPC delivery and workspace catalog boundaries [skip ci] * [comment audit] Condense catalog and relay entry contracts [skip ci] * [comment audit] Shorten shutdown and SSH relay delivery contracts [skip ci] * [comment audit] Condense WSL relay and E2E regression rationale [skip ci] * [comment audit] Shorten cross-version harness and renderer fixture explanations [skip ci] * [comment audit] Condense paired-host and E2E lifecycle rationale [skip ci] * [comment audit] Shorten layout oracle and regression explanations [skip ci] * [comment audit] Condense paired recovery and ownership regression contracts [skip ci] * [comment audit] Shorten restart, sidebar and SSH lifecycle contracts [skip ci] * [comment audit] Condense terminal rendering and IME regression rationale [skip ci] * [comment audit] Shorten terminal recovery and benchmark contracts [skip ci] * [comment audit] Condense tooling and Windows lifecycle proof rationale [skip ci] * [comment audit] Condense workflow routing and release rationale [skip ci] * [comment audit] Condense mobile security and installer contracts [skip ci] * [comment audit] Shorten native rationale and stylesheet workarounds [skip ci] * [comment audit] Shorten Windows visibility probe rationale [skip ci] * [comment audit] Condense embedded release and signing rationale [skip ci] * [comment audit] Retain current main test behavior in final reconciliation [skip ci] * [comment audit] Complete final comment review across current source inventory * [comment audit] Handle consolidated audit reports before final CI * [comment audit] Preserve credential storage census detail [skip ci] * [comment audit] Scale broad changed E2E selections with verified timing shards * [comment audit] Align E2E assertions with browser close and settled session metadata * [comment audit] Match existing E2Es to current resource and windowing contracts * [comment audit] Observe the shared server outage notice in reconnect coverage * [comment audit] Make existing renderer probes measure settled tab and PTY work * [comment audit] Align palette E2E selector with task search * [comment audit] Refresh remaining palette search selectors * [comment audit] Keep selector correction within selected audit specs * [comment audit] Await emoji fixture settings inside renderer evaluation * [comment audit] Cancel fixture fit retries between terminal tests --------- Co-authored-by: OrcaWin <293788423+OrcaWin@users.noreply.github.com>
417 lines
14 KiB
TypeScript
417 lines
14 KiB
TypeScript
import { describe, expect, it } from 'vitest'
|
|
import type { AgentJournalRenderItem } from './agent-session-journal-types'
|
|
import { selectNativeChatTurnStatuses } from './native-chat-turn-status'
|
|
import {
|
|
completedStructuredAgentTurnSeconds,
|
|
selectStructuredAgentRunningTurnTiming,
|
|
selectStructuredAgentSettledTurns,
|
|
selectStructuredAgentTurnTimings,
|
|
structuredAgentTurnLocalStartedAt
|
|
} from './structured-agent-session-turn-timing'
|
|
|
|
let sequence = 0
|
|
function user(itemId: string): AgentJournalRenderItem {
|
|
sequence += 1
|
|
return {
|
|
itemId,
|
|
revision: 0,
|
|
sequence,
|
|
observedAt: 1_000 + sequence,
|
|
body: { kind: 'message', role: 'user', blocks: [{ type: 'text', text: itemId }] }
|
|
}
|
|
}
|
|
function lifecycle(
|
|
turnId: string,
|
|
lifecycle: Partial<
|
|
NonNullable<AgentJournalRenderItem['body'] & { kind: 'status' }>['turnLifecycle']
|
|
>,
|
|
observedAt = 1_000 + sequence + 1
|
|
): AgentJournalRenderItem {
|
|
sequence += 1
|
|
return {
|
|
itemId: `legacy:codex:s:turn-lifecycle%3A${turnId}`,
|
|
revision: 1,
|
|
sequence,
|
|
observedAt,
|
|
body: {
|
|
kind: 'status',
|
|
text: 'Codex is working…',
|
|
turnLifecycle: { turnId, state: 'running', ...lifecycle }
|
|
}
|
|
}
|
|
}
|
|
function assistant(): AgentJournalRenderItem {
|
|
sequence += 1
|
|
return {
|
|
itemId: `a${sequence}`,
|
|
revision: 0,
|
|
sequence,
|
|
observedAt: 1_000 + sequence,
|
|
body: { kind: 'message', role: 'assistant', blocks: [{ type: 'text', text: 'ok' }] }
|
|
}
|
|
}
|
|
|
|
describe('selectStructuredAgentTurnTimings', () => {
|
|
it('keys each timed lifecycle row by the user message that opened the turn', () => {
|
|
const items = [
|
|
user('u1'),
|
|
lifecycle('t1', { state: 'completed', startedAt: 10_000, completedAt: 197_500 }),
|
|
assistant(),
|
|
user('u2'),
|
|
lifecycle('t2', { state: 'running', startedAt: 300_000 })
|
|
]
|
|
const timings = selectStructuredAgentTurnTimings(items)
|
|
expect(timings.get('u1')).toMatchObject({
|
|
state: 'completed',
|
|
startedAt: 10_000,
|
|
completedAt: 197_500
|
|
})
|
|
expect(timings.get('u2')).toMatchObject({ state: 'running', startedAt: 300_000 })
|
|
expect(timings.get('u2')?.completedAt).toBeUndefined()
|
|
})
|
|
|
|
it('skips lifecycle rows that carry no start (older hosts, conversation commands)', () => {
|
|
const items = [user('u1'), lifecycle('compact:1', {})]
|
|
expect(selectStructuredAgentTurnTimings(items).size).toBe(0)
|
|
})
|
|
|
|
it('gives a prompt folded into a running turn no timing of its own', () => {
|
|
const items = [
|
|
user('u1'),
|
|
lifecycle('t1', { state: 'completed', startedAt: 5_000, completedAt: 9_000 }),
|
|
user('u2-steer'),
|
|
assistant()
|
|
]
|
|
const timings = selectStructuredAgentTurnTimings(items)
|
|
expect([...timings.keys()]).toEqual(['u1'])
|
|
})
|
|
|
|
it('drops an end that precedes its start', () => {
|
|
const items = [
|
|
user('u1'),
|
|
lifecycle('t1', { state: 'completed', startedAt: 9_000, completedAt: 5_000 })
|
|
]
|
|
expect(selectStructuredAgentTurnTimings(items).get('u1')?.completedAt).toBeUndefined()
|
|
})
|
|
})
|
|
|
|
describe('completedStructuredAgentTurnSeconds', () => {
|
|
it('floors whole seconds for completed and interrupted turns', () => {
|
|
expect(
|
|
completedStructuredAgentTurnSeconds({
|
|
state: 'completed',
|
|
startedAt: 1_000,
|
|
completedAt: 188_900,
|
|
observedAt: 1_000
|
|
})
|
|
).toBe(187)
|
|
expect(
|
|
completedStructuredAgentTurnSeconds({
|
|
state: 'interrupted',
|
|
startedAt: 1_000,
|
|
completedAt: 4_999,
|
|
observedAt: 1_000
|
|
})
|
|
).toBe(3)
|
|
})
|
|
|
|
it('claims nothing for running or unverifiable turns', () => {
|
|
expect(
|
|
completedStructuredAgentTurnSeconds({ state: 'running', startedAt: 1_000, observedAt: 1_000 })
|
|
).toBeNull()
|
|
expect(
|
|
completedStructuredAgentTurnSeconds({
|
|
state: 'unverifiable',
|
|
startedAt: 1_000,
|
|
observedAt: 1_000
|
|
})
|
|
).toBeNull()
|
|
expect(completedStructuredAgentTurnSeconds(undefined)).toBeNull()
|
|
})
|
|
})
|
|
|
|
describe('structuredAgentTurnLocalStartedAt', () => {
|
|
it('moves the local first sighting back by the host-side append lag only', () => {
|
|
const timing = { state: 'running' as const, startedAt: 50_000, observedAt: 52_500 }
|
|
// Client clock is 1h ahead of the host: the anchor must not inherit that skew.
|
|
expect(structuredAgentTurnLocalStartedAt(timing, 3_600_000 + 60_000)).toBe(3_600_000 + 57_500)
|
|
})
|
|
|
|
it('never moves the anchor forward when the row predates its own start', () => {
|
|
expect(
|
|
structuredAgentTurnLocalStartedAt(
|
|
{ state: 'running', startedAt: 50_000, observedAt: 40_000 },
|
|
100
|
|
)
|
|
).toBe(100)
|
|
})
|
|
})
|
|
|
|
describe('host-settled turns override local observation', () => {
|
|
it('wins per turn and leaves locally observed turns from an older host intact', () => {
|
|
const settled = selectStructuredAgentSettledTurns([
|
|
user('u1'),
|
|
lifecycle('t1', { state: 'completed', startedAt: 10_000, completedAt: 197_000 })
|
|
])
|
|
const statuses = selectNativeChatTurnStatuses(
|
|
{ u0: { startedAt: 500, workedSeconds: 4 }, u1: { startedAt: 900, workedSeconds: 2 } },
|
|
{
|
|
activeTurnKey: 'u1',
|
|
isWorking: false,
|
|
thinking: false,
|
|
settledByTurn: settled
|
|
}
|
|
)
|
|
expect(statuses.completedByTurn.u1?.workedSeconds).toBe(187)
|
|
expect(statuses.completedByTurn.u0?.workedSeconds).toBe(4)
|
|
expect(statuses.active?.workedSeconds).toBe(187)
|
|
})
|
|
})
|
|
|
|
describe('selectStructuredAgentRunningTurnTiming', () => {
|
|
it('finds the live turn by id and returns null for an older host row without a start', () => {
|
|
const items = [user('u1'), lifecycle('t1', { state: 'running', startedAt: 7_000 }, 7_250)]
|
|
expect(selectStructuredAgentRunningTurnTiming(items, 't1')).toEqual({
|
|
state: 'running',
|
|
startedAt: 7_000,
|
|
observedAt: 7_250
|
|
})
|
|
expect(selectStructuredAgentRunningTurnTiming(items, 'other')).toBeNull()
|
|
expect(
|
|
selectStructuredAgentRunningTurnTiming([user('u2'), lifecycle('t2', {})], 't2')
|
|
).toBeNull()
|
|
})
|
|
})
|
|
|
|
describe('explicit user-item attribution', () => {
|
|
const submission = (clientMessageId: string, providerItemId: string | null) => ({
|
|
clientMessageId,
|
|
fence: 1,
|
|
payloadFingerprint: 'fp',
|
|
dispatchState: 'accepted' as const,
|
|
providerItemId,
|
|
reason: null,
|
|
submittedAt: 1,
|
|
resolvedAt: 2
|
|
})
|
|
|
|
it('resolves a submission through its provider alias instead of journal order', () => {
|
|
const items = [
|
|
user('orca:first'),
|
|
user('orca:second'),
|
|
lifecycle('t1', {
|
|
state: 'completed',
|
|
userItemId: 'codex:thread:t1:0',
|
|
startedAt: 1_000,
|
|
completedAt: 5_000
|
|
})
|
|
]
|
|
const timings = selectStructuredAgentTurnTimings(items, [
|
|
submission('first', 'codex:thread:t1:0'),
|
|
submission('second', null)
|
|
])
|
|
expect([...timings.keys()]).toEqual(['orca:first'])
|
|
})
|
|
|
|
it('uses the key directly when the user item is journaled under it', () => {
|
|
const items = [
|
|
user('claude:s:u1'),
|
|
lifecycle('u1', {
|
|
state: 'completed',
|
|
userItemId: 'claude:s:u1',
|
|
startedAt: 1_000,
|
|
completedAt: 2_000
|
|
})
|
|
]
|
|
expect([...selectStructuredAgentTurnTimings(items).keys()]).toEqual(['claude:s:u1'])
|
|
})
|
|
|
|
it('anchors to the record itself when a keyed row names a user item nobody journaled', () => {
|
|
const items = [
|
|
user('orca:first'),
|
|
lifecycle('auto', {
|
|
state: 'completed',
|
|
userItemId: 'codex:thread:auto:0',
|
|
startedAt: 1_000,
|
|
completedAt: 2_000
|
|
})
|
|
]
|
|
// Provider-opened turns anchor themselves; preceding prompts did not open them.
|
|
expect([...selectStructuredAgentTurnTimings(items).keys()]).toEqual([
|
|
'legacy:codex:s:turn-lifecycle%3Aauto'
|
|
])
|
|
})
|
|
|
|
it('falls back to journal order only for rows without a key (older hosts)', () => {
|
|
const items = [
|
|
user('orca:first'),
|
|
lifecycle('t1', { state: 'completed', startedAt: 1_000, completedAt: 2_000 })
|
|
]
|
|
expect([...selectStructuredAgentTurnTimings(items).keys()]).toEqual(['orca:first'])
|
|
})
|
|
})
|
|
|
|
describe('provider-measured duration', () => {
|
|
it('outranks an unattributed host interval and floors to seconds', () => {
|
|
expect(
|
|
completedStructuredAgentTurnSeconds({
|
|
state: 'completed',
|
|
startedAt: 1_000,
|
|
completedAt: 9_999,
|
|
durationMs: 7_172,
|
|
observedAt: 1_000
|
|
})
|
|
).toBe(7)
|
|
})
|
|
|
|
it('is ignored while the turn is not settled', () => {
|
|
expect(
|
|
completedStructuredAgentTurnSeconds({
|
|
state: 'running',
|
|
startedAt: 1_000,
|
|
durationMs: 7_172,
|
|
observedAt: 1_000
|
|
})
|
|
).toBeNull()
|
|
})
|
|
})
|
|
|
|
describe('coalesced sends and canonical rows', () => {
|
|
const accepted = (clientMessageId: string, providerItemId: string) => ({
|
|
clientMessageId,
|
|
fence: 1,
|
|
payloadFingerprint: 'fp',
|
|
dispatchState: 'accepted' as const,
|
|
providerItemId,
|
|
reason: null,
|
|
submittedAt: 1,
|
|
resolvedAt: 2
|
|
})
|
|
|
|
it('gives a turn shared by two accepted sends to the prompt that opened it', () => {
|
|
const items = [
|
|
user('orca:first'),
|
|
user('orca:second'),
|
|
lifecycle('t1', {
|
|
state: 'completed',
|
|
userItemId: 'codex:thread:t1:0',
|
|
startedAt: 1_000,
|
|
completedAt: 5_000
|
|
})
|
|
]
|
|
const timings = selectStructuredAgentTurnTimings(items, [
|
|
accepted('first', 'codex:thread:t1:0'),
|
|
accepted('second', 'codex:thread:t1:0')
|
|
])
|
|
expect([...timings.keys()]).toEqual(['orca:first'])
|
|
})
|
|
|
|
it('reads a canonical turn item exactly like the legacy carrier', () => {
|
|
sequence += 1
|
|
const canonical: AgentJournalRenderItem = {
|
|
itemId: 'legacy:codex:s:turn-lifecycle%3At9',
|
|
revision: 2,
|
|
sequence,
|
|
observedAt: 1_000,
|
|
body: {
|
|
kind: 'turn',
|
|
turnId: 't9',
|
|
state: 'completed',
|
|
userItemId: 'orca:u9',
|
|
startedAt: 1_000,
|
|
completedAt: 9_000,
|
|
durationMs: 7_172
|
|
}
|
|
}
|
|
const timings = selectStructuredAgentTurnTimings([user('orca:u9'), canonical])
|
|
expect(timings.get('orca:u9')).toMatchObject({ state: 'completed', durationMs: 7_172 })
|
|
expect(selectStructuredAgentSettledTurns([user('orca:u9'), canonical]).get('orca:u9')).toEqual({
|
|
startedAt: 1_000,
|
|
workedSeconds: 7
|
|
})
|
|
expect(selectStructuredAgentRunningTurnTiming([canonical], 't9')?.startedAt).toBe(1_000)
|
|
})
|
|
})
|
|
|
|
describe('structuredAgentTurnLocalStartedAt with the host clock', () => {
|
|
it('counts a mid-turn attach from the real start, not from first sight', () => {
|
|
const timing = { state: 'running' as const, startedAt: 50_000, observedAt: 50_000 }
|
|
// Host says the turn has run 40s; client clock is arbitrary.
|
|
expect(structuredAgentTurnLocalStartedAt(timing, 3_600_000, 90_000)).toBe(3_600_000 - 40_000)
|
|
expect(structuredAgentTurnLocalStartedAt(timing, 3_600_000, 40_000)).toBe(3_600_000)
|
|
})
|
|
})
|
|
|
|
describe('a rejected send', () => {
|
|
const rejected = (clientMessageId: string) => ({
|
|
clientMessageId,
|
|
fence: 5,
|
|
payloadFingerprint: 'fp',
|
|
dispatchState: 'rejected' as const,
|
|
providerItemId: null,
|
|
reason: 'provider_write_failed: claude: not signed in',
|
|
submittedAt: 1,
|
|
resolvedAt: 2
|
|
})
|
|
|
|
// Local send timestamps cannot imply a zero-duration turn when the host proves the message never reached the provider.
|
|
it('opened no turn, whatever the local clock observed', () => {
|
|
const settled = selectStructuredAgentSettledTurns([user('orca:dead')], [rejected('dead')])
|
|
expect(settled.get('orca:dead')).toBeNull()
|
|
|
|
const statuses = selectNativeChatTurnStatuses(
|
|
{ 'orca:dead': { startedAt: 900, workedSeconds: 0 } },
|
|
{ activeTurnKey: 'orca:dead', isWorking: false, thinking: false, settledByTurn: settled }
|
|
)
|
|
expect(statuses.completedByTurn['orca:dead']).toBeUndefined()
|
|
expect(statuses.active).toBeNull()
|
|
})
|
|
|
|
it('keeps the duration of a turn the journal does record for it', () => {
|
|
const settled = selectStructuredAgentSettledTurns(
|
|
[
|
|
user('orca:ran'),
|
|
lifecycle('t1', {
|
|
state: 'interrupted',
|
|
userItemId: 'orca:ran',
|
|
startedAt: 10_000,
|
|
completedAt: 14_000
|
|
})
|
|
],
|
|
[rejected('ran')]
|
|
)
|
|
expect(settled.get('orca:ran')).toEqual({
|
|
startedAt: 10_000,
|
|
workedSeconds: 4,
|
|
verdict: 'interruption'
|
|
})
|
|
})
|
|
|
|
// The folded header reads the verdict: a crash nobody asked for, versus a user's stop.
|
|
it('carries how a settled turn ended, so its header can say a crash cut it off', () => {
|
|
const ended = (userItemId: string, turn: Parameters<typeof lifecycle>[1]) => [
|
|
user(userItemId),
|
|
lifecycle(userItemId, { userItemId, startedAt: 10_000, completedAt: 22_000, ...turn })
|
|
]
|
|
const settled = selectStructuredAgentSettledTurns([
|
|
...ended('orca:crashed', { state: 'interrupted' }),
|
|
...ended('orca:stopped', { state: 'interrupted', outcome: 'cancellation' }),
|
|
...ended('orca:finished', { state: 'completed', outcome: 'success' }),
|
|
...ended('orca:unjudged', { state: 'completed' })
|
|
])
|
|
expect(settled.get('orca:crashed')).toEqual({
|
|
startedAt: 10_000,
|
|
workedSeconds: 12,
|
|
verdict: 'interruption'
|
|
})
|
|
expect(settled.get('orca:stopped')).toMatchObject({ verdict: 'cancellation' })
|
|
expect(settled.get('orca:finished')).toMatchObject({ verdict: 'success' })
|
|
expect(settled.get('orca:unjudged')).toEqual({ startedAt: 10_000, workedSeconds: 12 })
|
|
const statuses = selectNativeChatTurnStatuses(
|
|
{},
|
|
{ activeTurnKey: 'orca:crashed', isWorking: false, thinking: false, settledByTurn: settled }
|
|
)
|
|
expect(statuses.active).toMatchObject({ workedSeconds: 12, verdict: 'interruption' })
|
|
})
|
|
})
|