Files
orca/src/shared/agent-session-thread-goal.test.ts
T
Brennan Benson 563dd5487f feat(native-chat): show a Codex chat's goal above the composer, and set it from goal mode (#22377)
* feat(native-chat): show a Codex chat's goal above the composer and set it from goal mode

Structured Codex chat now treats the thread goal as session state: a banner above the
composer shows the current goal (pursuing / paused) with clear, pause/resume and expand;
/goal enters a goal mode whose send calls thread/goal/set; the objective is journaled as a
user message marked as sent as a goal. The banner is derived from the journaled goal rows,
which Codex's resume snapshot refreshes, so a reopened or adopted chat shows its goal.

Fixes STA-8159

* fix(native-chat): replace a recorded goal by clearing first, and recover a lost goal-change response

- A set while the journal records a goal (any status) clears it before setting,
  so the new goal starts with its own time and token counters instead of
  rewriting the old goal's objective in place.
- The threadGoal plan answers an unknown outcome from the goal the journal
  records and reruns otherwise, so one request timeout no longer refuses every
  later Clear/Pause/Resume as unknown for the mounted session.
- The goal-mode chip says "Exit goal mode"; "Clear goal" stays the banner's
  action on the provider goal.
- A typed bare /goal on Enter enters goal mode, the same as picking it.
- The renderer reads the goal off the tail of its ordered snapshot; the host's
  unordered map keeps the by-sequence reader.
- Drop the composer's duplicate in-flight guard; the goal controller already
  serializes changes.
- Pin that a counter-only revision reaches a subscriber's live page under its
  original sequence.

* fix(native-chat): keep a bare /goal inside goal mode as the entrance, and pin goal delivery and serialization

- A bare `/goal` submitted while already in goal mode re-enters the mode instead
  of setting a goal whose objective is the literal text "/goal".
- The counter-only revision pin now drives the host's own event sink bound to a
  real journal, so it goes red when the publish after a lifecycle transition is
  dropped; the previous fake sink never published.
- Pin that a set which threw after journaling its objective puts that objective
  back exactly once when the ledger reruns the same operation id.
- Cover the goal controller hook: absent without host support, the loaded window
  wins over the host's answer, a second change while one is unsettled answers
  false without a request, and a refused change frees the next one.

* fix(native-chat): resume a blocked or usage-limited goal, and keep goal-mode drafts honest

- The goal bar offers Resume on a blocked or usage-limited goal, which the
  provider resumes exactly as it resumes a paused one; a goal whose token budget
  is spent still offers only Clear. The rule lives beside the other goal facts
  in shared code so every reader answers it the same way.
- A `/goal <text>` typed inside goal mode sets the objective `<text>`, as it
  does outside goal mode, instead of a goal whose objective is the literal
  command.
- Setting a goal is a host round trip; a draft edited while it was in flight is
  no longer wiped when the goal lands, matching every other host command.
- Pin that a lost status-change response is read as applied only when the
  recorded goal is in that status, that a cleared row in the loaded window
  outranks the host's earlier answer, and that the PTY lane is untouched.

* fix(native-chat): keep the load-older anchor on the loaded window when a live revision lands below it

A live revision of a row keeps that row's original sequence. When the row is
older than the client's loaded window, the shared reducer merged it in and it
became the load-older anchor, so paging `before` it skipped every row between.
A goal's counter-only revisions during a long goal turn reach any client that
attached after the goal row left its window, so a reopened chat lost rows on
scroll-back.

The reducer now admits live rows only at or above the window's oldest row
while older rows remain on the host; the journal keeps the revision and the
page reader serves it once the window reaches the row. With nothing older on
the host the window is the whole journal, so a row below the head is admitted
as before.

Also drain accepted provider events before a goal set reads the journal to
decide whether it replaces a recorded goal.
2026-09-23 10:34:06 -07:00

141 lines
5.3 KiB
TypeScript

import { describe, expect, it } from 'vitest'
import type {
AgentJournalItemBody,
AgentJournalRenderItem,
AgentJournalThreadGoal
} from './agent-session-journal-types'
import {
agentSessionThreadGoalElapsedSeconds,
agentSessionThreadGoalStatusChange,
currentAgentSessionThreadGoal,
currentAgentSessionThreadGoalBySequence,
isAgentSessionThreadGoalOpen
} from './agent-session-thread-goal'
const PAYLOAD = { head: '{"goal":', byteLength: 4096, digest: 'd'.repeat(64), truncated: true }
function goal(overrides: Partial<AgentJournalThreadGoal> = {}): AgentJournalThreadGoal {
return {
objective: 'Ship the parser',
status: 'active',
tokenBudget: null,
tokensUsed: 10,
timeUsedSeconds: 30,
createdAt: 1_000_000,
updatedAt: 1_000_000,
...overrides
}
}
function row(
sequence: number,
body: AgentJournalItemBody,
extra: Partial<AgentJournalRenderItem> = {}
): AgentJournalRenderItem {
return { itemId: `item-${sequence}`, revision: 1, sequence, observedAt: sequence, body, ...extra }
}
function goalRow(sequence: number, state: 'set' | 'cleared', value = goal()) {
return row(sequence, {
kind: 'status',
text: state === 'set' ? `Goal set: ${value.objective}` : 'Goal cleared',
providerFrame: {
provider: 'codex',
kind: `notification:thread/goal/${state === 'set' ? 'updated' : 'cleared'}`,
payload: PAYLOAD
},
threadGoal: state === 'set' ? { state: 'set', goal: value } : { state: 'cleared' }
})
}
describe('current thread goal', () => {
it('reports no answer when no row records a goal transition', () => {
expect(
currentAgentSessionThreadGoal([
row(1, { kind: 'message', role: 'user', blocks: [{ type: 'text', text: 'hi' }] }),
row(2, { kind: 'status', text: 'Context compacted' })
])
).toBeUndefined()
})
it('reads the last goal row of a rendered snapshot, past later rows of other kinds', () => {
const paused = goal({ status: 'paused' })
expect(
currentAgentSessionThreadGoal([
goalRow(1, 'set'),
goalRow(2, 'set', paused),
row(3, { kind: 'status', text: 'Context compacted' })
])
).toEqual(paused)
})
it('takes the latest transition by sequence for items held unordered', () => {
const paused = goal({ status: 'paused' })
const unordered = new Map([
['b', goalRow(5, 'set', paused)],
['a', goalRow(2, 'set')]
])
expect(currentAgentSessionThreadGoalBySequence(unordered.values())).toEqual(paused)
expect(currentAgentSessionThreadGoalBySequence([])).toBeUndefined()
})
it('answers null once the latest transition cleared the goal', () => {
expect(currentAgentSessionThreadGoal([goalRow(1, 'set'), goalRow(2, 'cleared')])).toBeNull()
})
it('answers null for a row written before the typed snapshot existed', () => {
const legacy = row(3, {
kind: 'status',
text: 'Goal set: Ship the parser',
providerFrame: {
provider: 'codex',
kind: 'notification:thread/goal/updated',
payload: PAYLOAD
}
})
// The legacy row still supersedes the older typed one; it just cannot be read.
expect(currentAgentSessionThreadGoal([goalRow(1, 'set'), legacy])).toBeNull()
})
it('ignores a subagent goal and a status this build cannot place', () => {
const subagent = { ...goalRow(4, 'cleared'), agentId: 'child-1' }
expect(currentAgentSessionThreadGoal([goalRow(1, 'set'), subagent])).toEqual(goal())
// A newer provider status must not read as a known one.
const future = goalRow(5, 'set', Object.assign(goal(), { status: 'snoozed' }))
expect(currentAgentSessionThreadGoal([goalRow(1, 'set'), future])).toBeNull()
})
})
describe('thread goal presentation facts', () => {
it('keeps every status but complete open', () => {
expect(isAgentSessionThreadGoalOpen(goal({ status: 'blocked' }))).toBe(true)
expect(isAgentSessionThreadGoalOpen(goal({ status: 'complete' }))).toBe(false)
expect(isAgentSessionThreadGoalOpen(null)).toBe(false)
})
it('pauses only an active goal, and resumes a paused, blocked or usage-limited one', () => {
expect(agentSessionThreadGoalStatusChange('active')).toBe('paused')
expect(agentSessionThreadGoalStatusChange('paused')).toBe('active')
expect(agentSessionThreadGoalStatusChange('blocked')).toBe('active')
expect(agentSessionThreadGoalStatusChange('usageLimited')).toBe('active')
// A spent budget is not a pause: the provider will not resume it.
expect(agentSessionThreadGoalStatusChange('budgetLimited')).toBeNull()
expect(agentSessionThreadGoalStatusChange('complete')).toBeNull()
})
it('adds time only while an active goal has a turn running', () => {
const now = 1_000_000 + 7_500
const running = { startedAt: null }
expect(agentSessionThreadGoalElapsedSeconds(goal(), now, null)).toBe(30)
expect(agentSessionThreadGoalElapsedSeconds(goal(), now, running)).toBe(37)
expect(agentSessionThreadGoalElapsedSeconds(goal({ status: 'paused' }), now, running)).toBe(30)
// A report older than the turn counts from the turn's start, not across the idle gap.
expect(agentSessionThreadGoalElapsedSeconds(goal(), now, { startedAt: now - 2_000 })).toBe(32)
// A provider clock ahead of this one never subtracts time.
expect(
agentSessionThreadGoalElapsedSeconds(goal({ updatedAt: now + 5_000 }), now, running)
).toBe(30)
})
})