mirror of
https://github.com/stablyai/orca.git
synced 2026-10-31 09:07:40 +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>
179 lines
6.4 KiB
TypeScript
179 lines
6.4 KiB
TypeScript
import { describe, expect, it } from 'vitest'
|
|
import type {
|
|
AgentJournalItemBody,
|
|
AgentJournalRenderItem,
|
|
AgentJournalTurnScope
|
|
} from './agent-session-journal-types'
|
|
import type { NativeChatMessage } from './native-chat-types'
|
|
import {
|
|
projectNativeChatTranscript,
|
|
projectNativeChatTranscriptMessages
|
|
} from './native-chat-transcript-projection'
|
|
|
|
let sequence = 0
|
|
|
|
function row(
|
|
id: string,
|
|
blocks: NativeChatMessage['blocks'],
|
|
overrides: Partial<NativeChatMessage> = {}
|
|
): NativeChatMessage {
|
|
sequence += 1
|
|
return {
|
|
id,
|
|
role: 'assistant',
|
|
blocks,
|
|
timestamp: 1,
|
|
source: 'transcript',
|
|
journalPosition: { sequence, index: 0 },
|
|
...overrides
|
|
}
|
|
}
|
|
|
|
const say = (value: string) => [{ type: 'text' as const, text: value }]
|
|
const call = (name: string) => [{ type: 'tool-call' as const, name, input: {} }]
|
|
const child = { agentId: 'task-1', producerKind: 'agent' as const }
|
|
|
|
/** A journal item as a host that states each row's turn writes it; `turnItemId` absent: none. */
|
|
function item(
|
|
itemId: string,
|
|
body: AgentJournalItemBody,
|
|
turnItemId?: string,
|
|
agentId?: string
|
|
): AgentJournalRenderItem {
|
|
const turnScope: AgentJournalTurnScope =
|
|
turnItemId === undefined ? { kind: 'thread' } : { kind: 'turn', turnItemId }
|
|
return {
|
|
itemId,
|
|
body,
|
|
sequence: 0,
|
|
observedAt: 0,
|
|
revision: 1,
|
|
turnScope,
|
|
...(agentId === undefined ? {} : { agentId })
|
|
}
|
|
}
|
|
const message = (role: 'user' | 'assistant'): AgentJournalItemBody => ({
|
|
kind: 'message',
|
|
role,
|
|
blocks: []
|
|
})
|
|
const turn = (turnId: string, userItemId: string): AgentJournalItemBody => ({
|
|
kind: 'turn',
|
|
turnId,
|
|
state: 'completed',
|
|
userItemId,
|
|
startedAt: 0
|
|
})
|
|
|
|
describe("a subagent's rows are not the conversation's", () => {
|
|
// The shape a background subagent leaves: its rows interleave with its parent's.
|
|
const transcript = [
|
|
row('ask', say('review the PR'), { role: 'user' }),
|
|
row('delegate', say('Delegating the review.')),
|
|
row('child-look', say('Looking at the diff.'), child),
|
|
row('parent-read', call('Read')),
|
|
row('child-grep', call('Grep'), child),
|
|
row('child-verdict', say('The PR is CLEAN.'), child),
|
|
row('answer', say('The review found nothing.'))
|
|
]
|
|
|
|
it("keeps the session's own rows as the conversation, and none of the subagent's", () => {
|
|
const { conversation, subagentRows } = projectNativeChatTranscript(transcript)
|
|
expect(conversation.map((message) => message.id)).toEqual(['ask', 'delegate', 'answer'])
|
|
expect(conversation[1]?.blocks).toEqual([...say('Delegating the review.'), ...call('Read')])
|
|
expect(
|
|
subagentRows.get('task-1')?.map(({ message, turnKey }) => [message.id, turnKey])
|
|
).toEqual([
|
|
['child-look', 'ask'],
|
|
['child-verdict', 'ask']
|
|
])
|
|
expect(projectNativeChatTranscriptMessages(transcript)).toEqual(conversation)
|
|
})
|
|
|
|
it("folds the subagent's calls into its own run however its parent's interleave", () => {
|
|
const [look] = projectNativeChatTranscript(transcript).subagentRows.get('task-1') ?? []
|
|
expect(look?.message.blocks).toEqual([...say('Looking at the diff.'), ...call('Grep')])
|
|
})
|
|
|
|
it('splits a subagent run at the turn it crossed, so each call stays in its own turn', () => {
|
|
const rows = projectNativeChatTranscript([
|
|
row('first', say('go'), { role: 'user' }),
|
|
row('child-start', say('Starting.'), child),
|
|
row('second', say('and then'), { role: 'user' }),
|
|
row('child-edit', call('Edit'), child)
|
|
]).subagentRows.get('task-1')
|
|
expect(rows?.map(({ message, turnKey }) => [message.id, turnKey])).toEqual([
|
|
['child-start', 'first'],
|
|
['child-edit', 'second']
|
|
])
|
|
})
|
|
|
|
// Turn records own rows; a mid-turn send cannot claim work before its own turn opens.
|
|
it("takes each row's turn from the journal's turn records, as the conversation's rows do", () => {
|
|
const rows = [
|
|
row('first', say('go'), { role: 'user' }),
|
|
row('child-start', say('Starting.'), child),
|
|
row('second', say('and then'), { role: 'user' }),
|
|
row('child-edit', call('Edit'), child),
|
|
row('child-woke', call('Write'), child)
|
|
]
|
|
const journal = {
|
|
items: [
|
|
item('first', message('user')),
|
|
item('turn-1', turn('1', 'first')),
|
|
item('child-start', message('assistant'), 'turn-1', 'task-1'),
|
|
item('second', message('user')),
|
|
item('child-edit', message('assistant'), 'turn-1', 'task-1'),
|
|
item('turn-2', turn('2', 'second')),
|
|
// Its opener is outside the loaded window, so the turn keys to its own record.
|
|
item('turn-3', turn('3', 'older-send')),
|
|
item('child-woke', message('assistant'), 'turn-3', 'task-1')
|
|
],
|
|
submissions: []
|
|
}
|
|
const projected = projectNativeChatTranscript(rows, undefined, journal).subagentRows.get(
|
|
'task-1'
|
|
)
|
|
expect(projected?.map(({ message, turnKey }) => [message.id, turnKey])).toEqual([
|
|
['child-start', 'first'],
|
|
['child-woke', 'turn-3']
|
|
])
|
|
expect(projected?.[0]?.message.blocks).toEqual([...say('Starting.'), ...call('Edit')])
|
|
})
|
|
|
|
it("never lets a subagent's own prompt open a conversation turn", () => {
|
|
const transcript = [
|
|
row('ask', say('go'), { role: 'user' }),
|
|
row('child-prompt', say('Review the diff.'), { ...child, role: 'user' }),
|
|
row('child-look', say('Looking.'), child)
|
|
]
|
|
const rows = projectNativeChatTranscript(transcript).subagentRows.get('task-1')
|
|
expect(rows?.every(({ turnKey }) => turnKey === 'ask')).toBe(true)
|
|
// A host that states turns scopes a prompt written after the turn ended to none.
|
|
const journal = {
|
|
items: [
|
|
item('ask', message('user')),
|
|
item('turn-1', turn('1', 'ask')),
|
|
item('child-prompt', message('user'), undefined, 'task-1'),
|
|
item('child-look', message('assistant'), 'turn-1', 'task-1')
|
|
],
|
|
submissions: []
|
|
}
|
|
const scoped = projectNativeChatTranscript(transcript, undefined, journal).subagentRows
|
|
expect(scoped.get('task-1')?.map(({ turnKey }) => turnKey)).toEqual([undefined, 'ask'])
|
|
})
|
|
|
|
it('projects a transcript that names no producer exactly as before', () => {
|
|
const plain = transcript.map(({ agentId: _agentId, producerKind: _kind, ...rest }) => rest)
|
|
const { conversation, subagentRows } = projectNativeChatTranscript(plain)
|
|
expect(subagentRows.size).toBe(0)
|
|
expect(conversation.map((message) => message.id)).toEqual([
|
|
'ask',
|
|
'delegate',
|
|
'child-look',
|
|
'child-verdict',
|
|
'answer'
|
|
])
|
|
})
|
|
})
|