feat: add live Codex research chat and reusable deck sources
This commit is contained in:
@@ -0,0 +1,435 @@
|
||||
// @vitest-environment node
|
||||
import { expect, it, vi } from 'vitest'
|
||||
import type { Connection } from '../connections/model'
|
||||
import type { Deck } from '../decks/model'
|
||||
import type { ResearchPost } from '../platforms/types'
|
||||
import { createResearchTools } from './agent-tools.server'
|
||||
|
||||
const savedDecks = vi.hoisted(() => ({ list: vi.fn(), load: vi.fn() }))
|
||||
vi.mock('../decks/repository.server', () => ({
|
||||
listDecks: savedDecks.list,
|
||||
loadDeck: savedDecks.load,
|
||||
}))
|
||||
|
||||
const account: Connection = {
|
||||
id: 'selected',
|
||||
platform: 'twitter',
|
||||
origin: 'https://relay.invalid',
|
||||
accountId: null,
|
||||
displayName: 'Selected',
|
||||
status: 'connected',
|
||||
}
|
||||
const mastodon: Connection = {
|
||||
...account,
|
||||
id: 'mastodon',
|
||||
platform: 'mastodon',
|
||||
origin: 'https://mastodon.invalid',
|
||||
}
|
||||
const column = {
|
||||
id: 'column',
|
||||
title: 'Research',
|
||||
connectionId: account.id,
|
||||
source: { kind: 'search', query: 'WebMCP' },
|
||||
}
|
||||
const post: ResearchPost = {
|
||||
key: 'twitter:1',
|
||||
platform: 'twitter',
|
||||
nativeId: '1',
|
||||
url: 'https://x.com/alice/status/1',
|
||||
text: 'Evidence from a public post',
|
||||
author: { name: 'Alice', handle: 'alice' },
|
||||
}
|
||||
const open = { title: 'Research', columns: [column] }
|
||||
|
||||
it('publishes JSON tool definitions and only the explicitly selected public account fields', async () => {
|
||||
const tools = createResearchTools(
|
||||
[{ ...account, token: 'not-public' } as Connection],
|
||||
vi.fn(),
|
||||
vi.fn(),
|
||||
)
|
||||
expect(tools.definitions.map((tool) => tool.name)).toEqual([
|
||||
'list_connections',
|
||||
'list_lists',
|
||||
'list_decks',
|
||||
'get_deck',
|
||||
'open_temporary_deck',
|
||||
'fetch_column_posts',
|
||||
])
|
||||
const definition = tools.definitions.find(
|
||||
(tool) => tool.name === 'open_temporary_deck',
|
||||
)
|
||||
expect(JSON.parse(JSON.stringify(definition?.inputSchema))).toMatchObject({
|
||||
type: 'object',
|
||||
additionalProperties: false,
|
||||
})
|
||||
expect(await tools.execute('list_connections', {})).toEqual({
|
||||
ok: true,
|
||||
connections: [account],
|
||||
})
|
||||
expect(await tools.execute('save_deck', {})).toMatchObject({
|
||||
ok: false,
|
||||
error: { code: 'unknown-tool' },
|
||||
})
|
||||
})
|
||||
|
||||
it('opens a validated temporary mixed-platform deck and forwards it to the host callback', async () => {
|
||||
const onDeck = vi.fn()
|
||||
const tools = createResearchTools([account, mastodon], onDeck, vi.fn())
|
||||
const result = await tools.execute('open_temporary_deck', {
|
||||
title: 'Mixed',
|
||||
columns: [
|
||||
column,
|
||||
{
|
||||
title: 'Tag',
|
||||
connectionId: mastodon.id,
|
||||
source: { platform: 'mastodon', kind: 'hashtag', target: 'WebMCP' },
|
||||
},
|
||||
],
|
||||
})
|
||||
expect(result).toMatchObject({
|
||||
ok: true,
|
||||
persisted: false,
|
||||
deck: {
|
||||
title: 'Mixed',
|
||||
columns: [
|
||||
{
|
||||
id: 'column',
|
||||
source: { platform: 'twitter', product: 'Latest', following: false },
|
||||
},
|
||||
{ connectionId: 'mastodon' },
|
||||
],
|
||||
},
|
||||
})
|
||||
expect(onDeck).toHaveBeenCalledTimes(1)
|
||||
expect(tools.evidenceCount).toBe(0)
|
||||
})
|
||||
|
||||
it('updates the same temporary deck and keeps explicitly reused column IDs', async () => {
|
||||
const views: Deck[] = []
|
||||
const tools = createResearchTools(
|
||||
[account],
|
||||
(deck) => views.push(deck),
|
||||
vi.fn(),
|
||||
)
|
||||
await tools.execute('open_temporary_deck', open)
|
||||
await tools.execute('open_temporary_deck', {
|
||||
title: 'Refined research',
|
||||
columns: [
|
||||
{ ...column, source: { kind: 'search', query: 'WebMCP testing' } },
|
||||
],
|
||||
})
|
||||
expect(views).toHaveLength(2)
|
||||
expect(views[1]).toMatchObject({
|
||||
id: views[0]?.id,
|
||||
title: 'Refined research',
|
||||
columns: [{ id: 'column', source: { query: 'WebMCP testing' } }],
|
||||
})
|
||||
})
|
||||
|
||||
it('lists and reads saved decks only within the selected account scope', async () => {
|
||||
const deck: Deck = {
|
||||
...open,
|
||||
id: 'saved',
|
||||
columns: [
|
||||
{
|
||||
...column,
|
||||
source: {
|
||||
platform: 'twitter',
|
||||
kind: 'search',
|
||||
query: 'WebMCP',
|
||||
product: 'Latest',
|
||||
following: false,
|
||||
},
|
||||
},
|
||||
],
|
||||
}
|
||||
const record = { ...deck, revision: 3, createdAt: 1, updatedAt: 2 }
|
||||
const outside = {
|
||||
...record,
|
||||
id: 'outside',
|
||||
columns: [{ ...deck.columns[0], connectionId: 'not-selected' }],
|
||||
}
|
||||
savedDecks.list.mockReturnValue([record, outside])
|
||||
savedDecks.load.mockReturnValue(record)
|
||||
const onDeck = vi.fn()
|
||||
const tools = createResearchTools([account], onDeck, vi.fn())
|
||||
expect(await tools.execute('list_decks', {})).toEqual({
|
||||
ok: true,
|
||||
decks: [{ id: 'saved', title: 'Research', revision: 3, columnCount: 1 }],
|
||||
})
|
||||
expect(await tools.execute('get_deck', { deckId: 'saved' })).toEqual({
|
||||
ok: true,
|
||||
persisted: true,
|
||||
revision: 3,
|
||||
deck,
|
||||
})
|
||||
expect(onDeck).not.toHaveBeenCalled()
|
||||
savedDecks.load.mockReturnValue(outside)
|
||||
expect(await tools.execute('get_deck', { deckId: 'outside' })).toMatchObject({
|
||||
ok: false,
|
||||
error: { code: 'deck-unavailable' },
|
||||
})
|
||||
})
|
||||
|
||||
it('fetches the current context directly and creates a separate temporary view when changed', async () => {
|
||||
const context: Deck = {
|
||||
...open,
|
||||
id: 'saved',
|
||||
columns: [
|
||||
{
|
||||
...column,
|
||||
source: {
|
||||
platform: 'twitter',
|
||||
kind: 'search',
|
||||
query: 'WebMCP',
|
||||
product: 'Latest',
|
||||
following: false,
|
||||
},
|
||||
},
|
||||
],
|
||||
}
|
||||
const fetchPage = vi.fn().mockResolvedValue({ posts: [post] })
|
||||
const views: Deck[] = []
|
||||
const tools = createResearchTools(
|
||||
[account],
|
||||
(deck) => views.push(deck),
|
||||
fetchPage,
|
||||
{ contextDeck: context },
|
||||
)
|
||||
expect(
|
||||
await tools.execute('fetch_column_posts', { columnId: 'column' }),
|
||||
).toMatchObject({ ok: true, posts: [{ key: post.key }] })
|
||||
expect(fetchPage).toHaveBeenCalledWith(context.columns[0], undefined)
|
||||
expect(views).toHaveLength(0)
|
||||
await tools.execute('open_temporary_deck', { ...open, title: 'Refined' })
|
||||
expect(views[0]?.id).not.toBe('saved')
|
||||
expect(context.title).toBe('Research')
|
||||
expect(views[0]?.columns[0]?.id).toBe('column')
|
||||
})
|
||||
|
||||
it('accepts a mixed context but fetches only columns in the selected account scope', async () => {
|
||||
const fetchPage = vi.fn().mockResolvedValue({ posts: [post] })
|
||||
const tools = createResearchTools([account], vi.fn(), fetchPage, {
|
||||
contextDeck: {
|
||||
...open,
|
||||
id: 'saved',
|
||||
columns: [
|
||||
{
|
||||
...column,
|
||||
source: {
|
||||
platform: 'twitter',
|
||||
kind: 'search',
|
||||
query: 'WebMCP',
|
||||
product: 'Latest',
|
||||
following: false,
|
||||
},
|
||||
},
|
||||
{
|
||||
id: 'mastodon-column',
|
||||
title: 'Mastodon',
|
||||
connectionId: mastodon.id,
|
||||
source: { platform: 'mastodon', kind: 'hashtag', target: 'WebMCP' },
|
||||
},
|
||||
],
|
||||
},
|
||||
})
|
||||
expect(await tools.execute('list_connections', {})).toEqual({
|
||||
ok: true,
|
||||
connections: [account],
|
||||
})
|
||||
expect(
|
||||
await tools.execute('fetch_column_posts', { columnId: 'mastodon-column' }),
|
||||
).toMatchObject({ ok: false, error: { code: 'account-unavailable' } })
|
||||
expect(fetchPage).not.toHaveBeenCalled()
|
||||
expect(
|
||||
await tools.execute('fetch_column_posts', { columnId: 'column' }),
|
||||
).toMatchObject({ ok: true, posts: [{ key: post.key }] })
|
||||
expect(fetchPage).toHaveBeenCalledTimes(1)
|
||||
})
|
||||
|
||||
it('continues updating the generated view while fetching the newly selected context', async () => {
|
||||
const context: Deck = {
|
||||
id: 'another-saved-deck',
|
||||
title: 'Another source',
|
||||
columns: [
|
||||
{
|
||||
...column,
|
||||
id: 'another-column',
|
||||
source: {
|
||||
platform: 'twitter',
|
||||
kind: 'search',
|
||||
query: 'Mastodon',
|
||||
product: 'Latest',
|
||||
following: false,
|
||||
},
|
||||
},
|
||||
],
|
||||
}
|
||||
const fetchPage = vi.fn().mockResolvedValue({ posts: [] })
|
||||
const views: Deck[] = []
|
||||
const tools = createResearchTools(
|
||||
[account],
|
||||
(deck) => views.push(deck),
|
||||
fetchPage,
|
||||
{
|
||||
contextDeck: context,
|
||||
temporaryDeckId: 'previous-generated-plan',
|
||||
},
|
||||
)
|
||||
await tools.execute('fetch_column_posts', { columnId: 'another-column' })
|
||||
expect(fetchPage).toHaveBeenCalledWith(context.columns[0], undefined)
|
||||
await tools.execute('open_temporary_deck', open)
|
||||
expect(views[0]?.id).toBe('previous-generated-plan')
|
||||
expect(context.id).toBe('another-saved-deck')
|
||||
expect(context.columns[0]?.id).toBe('another-column')
|
||||
})
|
||||
|
||||
it.each([
|
||||
{ deckId: 'saved' },
|
||||
{ expectedRevision: 1 },
|
||||
{ columns: [{ ...column, connectionId: 'not-selected' }] },
|
||||
])('rejects saved deck mutations and unselected accounts', async (extra) => {
|
||||
const onDeck = vi.fn()
|
||||
const tools = createResearchTools([account], onDeck, vi.fn())
|
||||
expect(
|
||||
await tools.execute('open_temporary_deck', { ...open, ...extra }),
|
||||
).toMatchObject({ ok: false, error: { code: 'invalid-input' } })
|
||||
expect(onDeck).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
it('fetches with the current account binding, filters private fields and caps returned posts at20', async () => {
|
||||
const fetchPage = vi.fn().mockResolvedValue({
|
||||
posts: Array.from({ length: 25 }, (_, index) => ({
|
||||
...post,
|
||||
key: `twitter:${index}`,
|
||||
token: 'secret',
|
||||
_raw: { token: 'secret' },
|
||||
html: '<script>untrusted()</script>',
|
||||
})),
|
||||
nextCursor: 'next',
|
||||
})
|
||||
const tools = createResearchTools([account], vi.fn(), fetchPage)
|
||||
await tools.execute('open_temporary_deck', open)
|
||||
const result = await tools.execute('fetch_column_posts', {
|
||||
columnId: 'column',
|
||||
})
|
||||
expect(fetchPage).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
connectionId: account.id,
|
||||
source: {
|
||||
platform: 'twitter',
|
||||
kind: 'search',
|
||||
query: 'WebMCP',
|
||||
product: 'Latest',
|
||||
following: false,
|
||||
},
|
||||
}),
|
||||
undefined,
|
||||
)
|
||||
expect(result).toMatchObject({
|
||||
ok: true,
|
||||
truncated: true,
|
||||
nextCursor: 'next',
|
||||
fetchesRemaining: 11,
|
||||
})
|
||||
expect(JSON.stringify(result)).not.toContain('secret')
|
||||
expect(JSON.stringify(result)).not.toContain('<script>')
|
||||
expect(tools.evidenceCount).toBe(20)
|
||||
})
|
||||
|
||||
it('rejects arbitrary and cross-column cursors while allowing the returned continuation', async () => {
|
||||
const fetchPage = vi
|
||||
.fn()
|
||||
.mockResolvedValueOnce({ posts: [post], nextCursor: 'first-next' })
|
||||
.mockResolvedValueOnce({ posts: [post] })
|
||||
const tools = createResearchTools([account], vi.fn(), fetchPage)
|
||||
await tools.execute('open_temporary_deck', {
|
||||
...open,
|
||||
columns: [column, { ...column, id: 'other' }],
|
||||
})
|
||||
expect(
|
||||
await tools.execute('fetch_column_posts', {
|
||||
columnId: 'column',
|
||||
cursor: 'invented',
|
||||
}),
|
||||
).toMatchObject({ ok: false, error: { code: 'cursor-invalid' } })
|
||||
await tools.execute('fetch_column_posts', { columnId: 'column' })
|
||||
expect(
|
||||
await tools.execute('fetch_column_posts', {
|
||||
columnId: 'other',
|
||||
cursor: 'first-next',
|
||||
}),
|
||||
).toMatchObject({ ok: false, error: { code: 'cursor-invalid' } })
|
||||
expect(
|
||||
await tools.execute('fetch_column_posts', {
|
||||
columnId: 'column',
|
||||
cursor: 'first-next',
|
||||
}),
|
||||
).toMatchObject({ ok: true, hasMore: false })
|
||||
expect(
|
||||
await tools.execute('fetch_column_posts', { columnId: 'column' }),
|
||||
).toMatchObject({ ok: false, error: { code: 'cursor-invalid' } })
|
||||
expect(fetchPage).toHaveBeenCalledTimes(2)
|
||||
expect(tools.evidenceCount).toBe(1)
|
||||
})
|
||||
|
||||
it('caps all upstream calls including failures and does not expose diagnostic secrets', async () => {
|
||||
const fetchPage = vi
|
||||
.fn()
|
||||
.mockRejectedValue(new Error('authorization: Bearer secret-token'))
|
||||
const tools = createResearchTools([account], vi.fn(), fetchPage)
|
||||
await tools.execute('open_temporary_deck', open)
|
||||
for (let index = 0; index < 12; index++) {
|
||||
const result = await tools.execute('fetch_column_posts', {
|
||||
columnId: 'column',
|
||||
})
|
||||
expect(result).toMatchObject({
|
||||
ok: false,
|
||||
error: { code: 'source-unavailable' },
|
||||
})
|
||||
expect(JSON.stringify(result)).not.toContain('secret-token')
|
||||
}
|
||||
await tools.execute('open_temporary_deck', open)
|
||||
expect(
|
||||
await tools.execute('fetch_column_posts', { columnId: 'column' }),
|
||||
).toMatchObject({ ok: false, error: { code: 'budget-exhausted' } })
|
||||
expect(fetchPage).toHaveBeenCalledTimes(12)
|
||||
})
|
||||
|
||||
it('discards a late result from a replaced view and prevents concurrent pagination', async () => {
|
||||
let finish: (page: { posts: ResearchPost[] }) => void = () => {}
|
||||
const fetchPage = vi.fn(
|
||||
() =>
|
||||
new Promise<{ posts: ResearchPost[] }>((resolve) => {
|
||||
finish = resolve
|
||||
}),
|
||||
)
|
||||
const tools = createResearchTools([account], vi.fn(), fetchPage)
|
||||
await tools.execute('open_temporary_deck', open)
|
||||
const pending = tools.execute('fetch_column_posts', { columnId: 'column' })
|
||||
expect(
|
||||
await tools.execute('fetch_column_posts', { columnId: 'column' }),
|
||||
).toMatchObject({ ok: false, error: { code: 'busy' } })
|
||||
await tools.execute('open_temporary_deck', { ...open, title: 'New view' })
|
||||
finish({ posts: [post] })
|
||||
expect(await pending).toMatchObject({
|
||||
ok: false,
|
||||
error: { code: 'view-changed' },
|
||||
})
|
||||
expect(tools.evidenceCount).toBe(0)
|
||||
})
|
||||
|
||||
it('does not allow the host callback to mutate the bound fetch definition', async () => {
|
||||
const onDeck = (deck: Deck) => {
|
||||
const current = deck.columns[0]
|
||||
if (current) current.connectionId = 'altered'
|
||||
}
|
||||
const fetchPage = vi.fn().mockResolvedValue({ posts: [] })
|
||||
const tools = createResearchTools([account], onDeck, fetchPage)
|
||||
await tools.execute('open_temporary_deck', open)
|
||||
await tools.execute('fetch_column_posts', { columnId: 'column' })
|
||||
expect(fetchPage).toHaveBeenCalledWith(
|
||||
expect.objectContaining({ connectionId: account.id }),
|
||||
undefined,
|
||||
)
|
||||
})
|
||||
Reference in New Issue
Block a user