Merge remote-tracking branch 'origin/master' into worktree/pr743-merge-20260727

# Conflicts:
#	examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl
#	examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl
#	examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl
#	examples/acp-agent/tests/snapshots/session-query-spill/session.jsonl
#	examples/cordis-agent/tests/cordis-tools.e2e.ts
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl
This commit is contained in:
Tianyi Cui
2026-07-27 23:59:33 +08:00
528 changed files with 10636 additions and 10785 deletions

View File

@@ -149,10 +149,16 @@ export class HarnessSdkServer {
async prompt(params: SessionPromptParams): Promise<SessionPromptResult> {
const rec = await this.getOrCreateSession(params.sessionId)
if (rec.activePrompt) throw new Error(`session already has an active prompt: ${params.sessionId}`)
// An agent-loop-only reload disposes the loop's agents while this record
// survives; a retained agent accepts followup() silently, so validate the
// record against the live registry before delivery (as the ACP bridge does).
if (this.ctx.agents.get(rec.handle.agent.id) !== rec.handle.agent) {
throw new Error(`session agent was disposed outside the server: ${params.sessionId}`)
}
rec.activePrompt = true
try {
rec.lastTurnEnd = undefined
rec.handle.agent.followup(params.contentBlocks)
rec.handle.agent.followup({ content: params.contentBlocks, source: { kind: 'user' } })
await rec.handle.agent.whenIdle()
const status = this.finishedStatus(rec.lastTurnEnd)
this.transport.notify('session.finished', {

View File

@@ -5,7 +5,7 @@ import { join } from 'node:path'
import { tmpdir } from 'node:os'
import { afterEach, describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import { AgentMessageId, type Agent, type AgentHandle } from '@deepseek-ai/dsh-agent'
import AgentRegistry, { AgentMessageId, type Agent, type AgentHandle } from '@deepseek-ai/dsh-agent'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import * as agentCore from '@deepseek-ai/dsh-agent-spine-demo'
@@ -152,7 +152,7 @@ describe('HarnessSdkServer', () => {
meta: { cwd: storageDir },
agentOptions: { provider: 'deepseek', model: 'dsagent-model' },
})
orphanHandle.agent.followup([{ type: 'text', text: 'outside the sdk session map' }])
orphanHandle.agent.followup({ content: [{ type: 'text', text: 'outside the sdk session map' }], source: { kind: 'user' } })
await orphanHandle.agent.whenIdle()
await orphanHandle.dispose()
expect(llmServer.requests).toHaveLength(3)
@@ -172,21 +172,24 @@ describe('HarnessSdkServer', () => {
.mockResolvedValue(undefined)
const mainFollowup = vi.fn<Agent['followup']>().mockReturnValue(AgentMessageId('main-followup'))
const mainAgent = ({
id: SessionId('main'),
followup: mainFollowup,
whenIdle: mainWhenIdle,
} satisfies Pick<Agent, 'followup' | 'whenIdle'>) as unknown as Agent
} satisfies Pick<Agent, 'id' | 'followup' | 'whenIdle'>) as unknown as Agent
const otherFollowup = vi.fn<Agent['followup']>().mockReturnValue(AgentMessageId('other-followup'))
const otherAgent = ({
id: SessionId('other'),
followup: otherFollowup,
whenIdle: vi.fn(() => Promise.resolve()),
} satisfies Pick<Agent, 'followup' | 'whenIdle'>) as unknown as Agent
} satisfies Pick<Agent, 'id' | 'followup' | 'whenIdle'>) as unknown as Agent
const mainHandle = { agent: mainAgent, dispose: vi.fn(() => Promise.resolve()) }
const otherHandle = { agent: otherAgent, dispose: vi.fn(() => Promise.resolve()) }
const create = vi.fn(async (options: { sessionId: SessionId }) =>
String(options.sessionId) === 'main' ? mainHandle : otherHandle)
const liveAgents = new Map<string, Agent>([['main', mainAgent], ['other', otherAgent]])
const ctx = {
on: vi.fn(() => () => undefined),
agents: { create, get: () => undefined },
agents: { create, get: (id: SessionId) => liveAgents.get(String(id)) },
get: () => undefined,
} as unknown as Context
const server = new HarnessSdkServer(ctx, new FakeTransport())
@@ -215,9 +218,43 @@ describe('HarnessSdkServer', () => {
expect(otherHandle.dispose).toHaveBeenCalledOnce()
})
it('rejects a prompt for a session whose agent was disposed outside the server', async () => {
const followup = vi.fn<Agent['followup']>().mockReturnValue(AgentMessageId('stub'))
const agent = ({
id: SessionId('zombie'),
followup,
whenIdle: vi.fn(() => Promise.resolve()),
} satisfies Pick<Agent, 'id' | 'followup' | 'whenIdle'>) as unknown as Agent
const handle = { agent, dispose: vi.fn(() => Promise.resolve()) }
// The registry drops the agent after creation, modelling an agent-loop-only
// reload that leaves the server's SessionRecord pointing at a detached agent.
let live = true
const ctx = {
on: vi.fn(() => () => undefined),
agents: {
create: vi.fn(async () => handle),
get: (id: SessionId) => (live && String(id) === 'zombie' ? agent : undefined),
},
get: () => undefined,
} as unknown as Context
const server = new HarnessSdkServer(ctx, new FakeTransport())
const prompt = (text: string) => server.prompt({
sessionId: 'zombie',
contentBlocks: [{ type: 'text', text }],
})
await expect(prompt('while live')).resolves.toEqual({ accepted: true })
live = false
await expect(prompt('after detach')).rejects.toThrow('session agent was disposed outside the server: zombie')
// The detached agent was never driven by the rejected prompt.
expect(followup).toHaveBeenCalledOnce()
await server.shutdown()
})
it('reports the message-turn outcome when a later non-message turn settles before idle', async () => {
const ctx = new Context()
await ctx.plugin(SessionStore)
await ctx.plugin(AgentRegistry)
const transport = new FakeTransport()
const server = new HarnessSdkServer(ctx, transport) as unknown as {
prompt(params: { sessionId: string; contentBlocks: { type: 'text'; text: string }[] }): Promise<unknown>
@@ -226,16 +263,14 @@ describe('HarnessSdkServer', () => {
}
const session = ctx.sessions.create(SessionId('message-outcome'))
const agent = ({
id: SessionId('message-outcome'),
session,
followup(content: { type: 'text'; text: string }[]) {
followup(input: { content: { type: 'text'; text: string }[]; source: { kind: 'user' } }) {
session.append('turn/start', {
turn: 1,
trigger: { kind: 'message', source: { kind: 'user' } },
trigger: { kind: 'message', source: input.source },
})
session.append('user/message', {
content,
source: { kind: 'user' },
}, { surfaceOp: 'append' })
session.append('user/message', input, { surfaceOp: 'append' })
session.append('turn/end', { turn: 1, reason: { kind: 'max-tokens' } })
session.append('turn/start', {
turn: 2,
@@ -249,7 +284,8 @@ describe('HarnessSdkServer', () => {
return AgentMessageId('message-outcome')
},
whenIdle: () => Promise.resolve(),
} satisfies Pick<Agent, 'session' | 'followup' | 'whenIdle'>) as unknown as Agent
} satisfies Pick<Agent, 'id' | 'session' | 'followup' | 'whenIdle'>) as unknown as Agent
ctx.agents.register(agent)
server.sessions.set('message-outcome', {
handle: { agent, dispose: () => Promise.resolve() },
lastTurnEnd: undefined,

View File

@@ -42,10 +42,10 @@ import z from 'schemastery'
import {
installAgentLlmTarget,
type Agent,
type AgentMessageId,
type AgentLlmTarget,
type AgentLlmTargetRef,
type AgentStatus,
type HookContext,
} from '@deepseek-ai/dsh-agent'
import type {} from '@deepseek-ai/dsh-agent-loop'
import type {} from '@deepseek-ai/dsh-token-meter'
@@ -61,13 +61,13 @@ import type {
} from '@deepseek-ai/dsh-llm'
import type {} from '@deepseek-ai/dsh-llm-retry'
import {
displayPromptContent,
SessionId,
type JsonValue,
type Session,
type SessionEvent,
type SessionHeader,
type TodoItem,
type UserMessageData,
} from '@deepseek-ai/dsh-session'
import { foldGoal, type GoalPhase } from '@deepseek-ai/dsh-goal'
import {
@@ -1389,7 +1389,6 @@ function resumeTurnLabel(snapshot: SessionLogSnapshot): string {
case 'error': return `turn ${event.data.turn}: error`
case 'disposed': return `turn ${event.data.turn}: disposed`
case 'max-tokens': return `turn ${event.data.turn}: max tokens`
case 'rejected': return `turn ${event.data.turn}: rejected`
case 'interrupted': return `turn ${event.data.turn}: interrupted`
default: return `turn ${event.data.turn}: unknown result`
}
@@ -1904,9 +1903,9 @@ function activeSurfaceSeqs(session: Session): Set<number> {
return new Set(session.surface.nodes)
}
function sessionReferenceCard(meta: unknown): string[] | undefined {
if (typeof meta !== 'object' || meta === null) return undefined
const record = meta as Record<string, unknown>
function sessionReferenceCard(source: unknown): string[] | undefined {
if (typeof source !== 'object' || source === null) return undefined
const record = source as Record<string, unknown>
if (record['kind'] !== 'session-reference' || !Array.isArray(record['references'])) return undefined
const references = record['references'] as unknown[]
const labels: string[] = []
@@ -1921,13 +1920,6 @@ function sessionReferenceCard(meta: unknown): string[] | undefined {
return labels
}
function promptReferenceCards(event: Extract<SessionEvent, { type: 'user/message' | 'steering/message' }>): string[][] {
return event.data.envelope?.prefixContexts.flatMap((context) => {
const card = sessionReferenceCard(context.meta)
return card === undefined ? [] : [card]
}) ?? []
}
function activeToolCallIds(session: Session, active: ReadonlySet<number>): Set<string> {
const ids = new Set<string>()
for (const event of session.events) {
@@ -1972,16 +1964,10 @@ export function createTuiChat(
let toolsExpanded = false
let streaming: StreamingAssistantComponent | undefined
let runningStatus: RunningStatus | undefined
// Steering messages queued during the running turn (`agent/inbox/enqueue`
// with `info.steering`) that the loop has not yet drained, shown as a badge on
// the status line. Each entry is the queued message's serialized source: a
// drain (`steering/message`) removes one MATCHING entry, so a loop-authored
// continuation reason (which enqueues and drains under its own source) pushes
// and pops its own slot and cannot consume a pending user message's slot.
// Cleared on leaving `running`, which also absorbs a cancellation that
// discards the queue without logging drains; the status line exists only
// while running, so idle carries no badge to keep current.
const pendingSteering: string[] = []
// TUI steering submissions that the inbox has not yet claimed or discarded.
// Correlation ids avoid guessing whether a running-state submission actually
// joined steering or fell back to the queued-turn FIFO during turn close.
const pendingSteering = new Set<AgentMessageId>()
let disposed = false
let shuttingDown: Promise<void> | undefined
// Optional: skills mount conditionally, so read the global service store
@@ -2243,7 +2229,7 @@ export function createTuiChat(
const renderStatus = (running: RunningStatus): void => {
const at = now()
running.loader.setMessage(
formatTurnStatus(running.phase, at - running.phaseStartedAt, at - running.stepStartedAt, pendingSteering.length),
formatTurnStatus(running.phase, at - running.phaseStartedAt, at - running.stepStartedAt, pendingSteering.size),
)
}
@@ -2271,7 +2257,7 @@ export function createTuiChat(
const phase = prior?.phase ?? 'waiting'
const phaseStartedAt = prior?.phaseStartedAt ?? at
const stepStartedAt = prior?.stepStartedAt ?? at
const message = formatTurnStatus(phase, at - phaseStartedAt, at - stepStartedAt, pendingSteering.length)
const message = formatTurnStatus(phase, at - phaseStartedAt, at - stepStartedAt, pendingSteering.size)
const loader = new Loader(ui, text => palette.accent(text), text => palette.muted(text), message)
statusContainer.addChild(loader)
const running: RunningStatus = {
@@ -2349,7 +2335,7 @@ export function createTuiChat(
// boolean avoids narrowing `source`, so the label keeps its full union.
const source = event.data.source
if (source.kind !== 'user') {
const references = sessionReferenceCard(event.data.meta)
const references = sessionReferenceCard(event.data.source)
if (references !== undefined) {
chat.addChild(new Spacer(1))
chat.addChild(new Text(palette.dim(`Referenced sessions · ${references.map(displayText).join(', ')}`), 1, 0))
@@ -2367,33 +2353,22 @@ export function createTuiChat(
}
break
}
const text = displayText(contentText(displayPromptContent(event.data)).trim())
const text = displayText(contentText(event.data.content).trim())
if (text) {
chat.addChild(new Spacer(1))
chat.addChild(new UserMessageComponent(text, palette, mdTheme))
if (options.addHistory) editor.addToHistory(text)
}
for (const references of promptReferenceCards(event)) {
chat.addChild(new Spacer(1))
chat.addChild(new Text(palette.dim(`Referenced sessions · ${references.map(displayText).join(', ')}`), 1, 0))
}
break
}
case 'steering/message': {
const text = displayText(contentText(displayPromptContent(event.data)).trim())
const text = displayText(contentText(event.data.content).trim())
if (text) {
chat.addChild(new Spacer(1))
chat.addChild(new UserMessageComponent(text, palette, mdTheme, 'Steering'))
}
for (const references of promptReferenceCards(event)) {
chat.addChild(new Spacer(1))
chat.addChild(new Text(palette.dim(`Referenced sessions · ${references.map(displayText).join(', ')}`), 1, 0))
}
break
}
case 'prompt/blocked':
appendNotice(`Prompt blocked: ${event.data.reason}`, 'warning')
break
case 'assistant/chunk':
if (options.renderChunks) {
if (streaming === undefined) {
@@ -2411,8 +2386,9 @@ export function createTuiChat(
}
case 'llm/retry': {
clearStreaming()
const retryLimit = event.data.mode === 'always' ? '∞' : String(event.data.maxRetries)
appendNotice(
`Retrying model request (${event.data.retry}/${event.data.maxRetries}) in ${event.data.delayMs}ms: ${event.data.failure.message}`,
`Retrying model request (${event.data.retry}/${retryLimit}) in ${event.data.delayMs}ms: ${event.data.failure.message}`,
'warning',
)
break
@@ -2453,8 +2429,6 @@ export function createTuiChat(
appendNotice('Turn cancelled.', 'warning')
} else if (event.data.reason.kind === 'max-tokens') {
appendNotice('The model reached its output-token limit.', 'warning')
} else if (event.data.reason.kind === 'rejected') {
appendNotice(`Turn rejected: ${event.data.reason.reason}`, 'warning')
} else if (event.data.reason.kind === 'interrupted') {
appendNotice('The previous process ended during this turn.', 'warning')
}
@@ -2915,19 +2889,82 @@ export function createTuiChat(
).finally(() => { commandControllers.delete(controller) })
}
const dispatchMessage = (content: ContentBlock[], contexts: HookContext[]): void => {
if (agent.status === 'disposed') {
const dispatchMessage = (content: ContentBlock[], attachedContext?: UserMessageData): void => {
if (disposed) {
appendNotice(`Agent "${agent.id}" is disposed.`, 'error')
} else if (agent.status === 'running') {
agent.steer(content, { contexts })
} else {
agent.followup(content, { contexts })
return
}
if (agent.acceptsNextStep) {
// Steering is never subject to prompt admission; an attached snapshot
// drains beside it at the same step boundary through the outbox.
if (attachedContext !== undefined) {
agent.inject({ content: attachedContext.content, source: attachedContext.source })
}
pendingSteering.add(agent.steer({ content, source: { kind: 'user' } }))
refreshStatus()
return
}
if (attachedContext === undefined) {
agent.followup({ content, source: { kind: 'user' } })
return
}
// Idle: the snapshot rides the prompt's admission transaction so a
// blocking hook discards both together.
let cleanedUp = false
let acceptedId: AgentMessageId | undefined
let acceptedContent: ContentBlock[] | undefined
const enqueued = new Map<AgentMessageId, ContentBlock[]>()
const discarded = new Set<AgentMessageId>()
const cleanup = (): void => {
// Every completion path detaches all three listeners. Keep this
// idempotent so later cleanup paths cannot double-release them.
/* v8 ignore next -- unreachable idempotence guard, see above */
if (cleanedUp) return
cleanedUp = true
detachEnqueue()
detachSubmit()
detachDiscard()
}
// send() snapshots input before publishing it, and publishes enqueue
// before returning its id. Capture that snapshot by id so admission can
// use exact reference identity without depending on caller-owned input.
const detachEnqueue = ctx.on('agent/inbox/enqueue', (subject, message) => {
if (subject === agent) enqueued.set(message.id, message.content)
})
// Prepended so this wrapper is outermost: it observes the admission
// whether a downstream hook allows or blocks, and detaches either way.
const detachSubmit = ctx.on('agent/prompt-submit', async (subject, submitted, _source, _signal, next) => {
if (subject !== agent || submitted !== acceptedContent) return next()
cleanup()
const decision = await next()
if (decision.kind !== 'allow') return decision
return { ...decision, additionalContexts: [...decision.additionalContexts ?? [], attachedContext] }
}, { prepend: true })
// Installed before followup(): an enqueue listener can synchronously
// cancel and discard before followup() returns its id.
const detachDiscard = ctx.on('agent/inbox/discard', (subject, messages) => {
if (subject !== agent) return
for (const message of messages) discarded.add(message.id)
if (acceptedId !== undefined && discarded.has(acceptedId)) cleanup()
})
// followup() accepts any typed input and contains listener failures;
// this guards a future synchronous throw so the wrapper cannot leak.
/* v8 ignore start -- future-proofing guard, see above */
try {
acceptedId = agent.followup({ content, source: { kind: 'user' } })
acceptedContent = enqueued.get(acceptedId) ?? content
detachEnqueue()
if (discarded.has(acceptedId)) cleanup()
} catch (error: unknown) {
cleanup()
throw error
}
/* v8 ignore stop */
}
/** Deliver a user turn to the agent: steer while running, send while idle, or report a disposed agent. */
const deliver = (payload: string): void => {
dispatchMessage([{ type: 'text', text: payload }], [])
dispatchMessage([{ type: 'text', text: payload }])
}
/** Load a manually invoked skill and deliver its rendered body as a user turn, reporting lookup outcomes as notices. */
@@ -3187,7 +3224,7 @@ export function createTuiChat(
if (parsed.references.length === 0) {
editor.addToHistory(text)
editor.setText('')
dispatchMessage([{ type: 'text', text: parsed.text }], [])
dispatchMessage([{ type: 'text', text: parsed.text }])
return
}
const sessionReferences = ctx.get('sessionReferences')
@@ -3208,7 +3245,9 @@ export function createTuiChat(
if (disposed) return
editor.addToHistory(text)
if (editor.getText() === value) editor.setText('')
dispatchMessage(prepared.content, prepared.contexts)
// The snapshot travels with the prompt so a blocking admission hook
// discards them together — see dispatchMessage's attached-context path.
dispatchMessage(prepared.content, prepared.additionalContext)
}, (error: unknown) => {
if (!disposed && !controller.signal.aborted) {
restoreSubmittedInput()
@@ -3263,17 +3302,6 @@ export function createTuiChat(
if (event.type === 'tool/result') fileSearch.invalidate()
recordEventUsage(tokens, event)
advanceTurnPhase(event)
if (event.type === 'steering/message') {
// A queued steering message reached the model as it drained; drop its
// entry from the badge. Matching by source keeps a loop-authored
// continuation reason popping its own enqueued slot rather than a pending
// user message's slot.
const drained = pendingSteering.indexOf(JSON.stringify(event.data.source))
if (drained >= 0) {
pendingSteering.splice(drained, 1)
refreshStatus()
}
}
if ('surfaceOp' in event && typeof event.surfaceOp === 'object') {
rebuildTranscript(false)
return
@@ -3281,17 +3309,24 @@ export function createTuiChat(
renderEvent(event, { addHistory: false, renderChunks: true })
requestRender()
})
const disposeQueued = ctx.on('agent/inbox/enqueue', (subject, info) => {
if (subject !== agent || !info.steering) return
pendingSteering.push(JSON.stringify(info.source))
refreshStatus()
const settlePendingSteering = (id: AgentMessageId): void => {
if (pendingSteering.delete(id)) refreshStatus()
}
const disposeDequeued = ctx.on('agent/inbox/dequeue', (subject, message) => {
if (subject === agent) settlePendingSteering(message.id)
})
const disposeDiscarded = ctx.on('agent/inbox/discard', (subject, messages) => {
if (subject !== agent) return
let changed = false
for (const message of messages) changed = pendingSteering.delete(message.id) || changed
if (changed) refreshStatus()
})
const disposeStatus = ctx.on('agent/status', (subject, status) => {
if (subject !== agent) return
// Leaving 'running' ends the turn's status line; clear any badge so the
// next running turn starts from zero (and a cancellation, which discards
// the queue without logging drains, cannot strand a stale count).
if (status !== 'running') pendingSteering.length = 0
if (status !== 'running') pendingSteering.clear()
setStatus(status)
})
const disposeError = ctx.on('agent/error', (subject, turn, step, error) => {
@@ -3303,6 +3338,11 @@ export function createTuiChat(
})
const disposeAgent = ctx.on('agent/disposed', (subject) => {
if (subject !== agent) return
// The agent left the registry (e.g. an agent-loop-only reload) while the
// TUI stays mounted. Retained agents accept deliveries after detachment, so
// without this a later send would drive a zombie agent/session; mark
// disposed so dispatchMessage reports it instead.
disposed = true
clearStatus()
appendNotice(`Agent "${agent.id}" was disposed.`, 'warning')
})
@@ -3314,7 +3354,8 @@ export function createTuiChat(
disposeCommandChanges()
stopBannerReveal()
disposeSessionEvents()
disposeQueued()
disposeDequeued()
disposeDiscarded()
disposeStatus()
disposeError()
disposeAgent()

View File

@@ -15,7 +15,7 @@ import type {
LlmResolvedModelInfo,
} from '@deepseek-ai/dsh-llm'
import CommandService from '@deepseek-ai/dsh-commands'
import SessionStore, { SessionId, type Session, type SessionHeader } from '@deepseek-ai/dsh-session'
import SessionStore, { SessionId, type Session, type SessionHeader, type UserMessageData } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import type { ToolDefinition } from '@deepseek-ai/dsh-tools'
import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
@@ -27,12 +27,17 @@ interface FakeAgent extends Agent {
sent: ContentBlock[][]
sentOptions: (SendOptions | undefined)[]
steered: ContentBlock[][]
steeredOptions: (SendOptions | undefined)[]
steeredIds: AgentMessageId[]
steeredOptions: UserMessageData[]
injected: ContentBlock[][]
injectedOptions: UserMessageData[]
cancelled: AgentCancelCause[]
}
export interface TuiHarnessOptions {
status?: AgentStatus
/** Override the fake agent's next-step capability independently of status. */
acceptsNextStep?: boolean
config?: Config
/** Leave the session event log empty instead of seeding one turn and step. */
omitInitialLifecycle?: boolean
@@ -177,38 +182,52 @@ export async function createTuiTestHarness<TerminalType extends Terminal, Exit e
options.beforeMount?.(session)
const sent: ContentBlock[][] = []
const steered: ContentBlock[][] = []
const steeredIds: AgentMessageId[] = []
const sentOptions: (SendOptions | undefined)[] = []
const steeredOptions: (SendOptions | undefined)[] = []
const steeredOptions: UserMessageData[] = []
const injected: ContentBlock[][] = []
const injectedOptions: UserMessageData[] = []
const cancelled: AgentCancelCause[] = []
const agent: FakeAgent = {
id: sessionId,
options: options.agentOptions ?? { provider: 'deepseek', model: 'deepseek-v4-flash' },
session,
status: options.status ?? 'idle',
get acceptsNextStep() {
return options.acceptsNextStep ?? this.status === 'running'
},
ctx,
sent,
sentOptions,
steered,
steeredIds,
steeredOptions,
injected,
injectedOptions,
cancelled,
followup(content, options) {
sent.push(content)
send(input, options) {
sent.push(input.content)
sentOptions.push(options)
return AgentMessageId('stub')
},
queue(content, options) {
sent.push(content)
sentOptions.push(options)
followup(input) {
sent.push(input.content)
sentOptions.push(undefined)
return AgentMessageId('stub')
},
steer(content, options) {
steered.push(content)
steeredOptions.push(options)
steer(input) {
steered.push(input.content)
steeredOptions.push(input)
const id = AgentMessageId(`steering-${steeredIds.length + 1}`)
steeredIds.push(id)
return id
},
inject(input) {
injected.push(input.content)
injectedOptions.push(input)
return AgentMessageId('stub')
},
inject: () => AgentMessageId('stub'),
send: () => AgentMessageId('stub'),
cancel(cause = { kind: 'user' }) {
cancel(cause) {
cancelled.push(cause)
},
whenIdle() {

View File

@@ -24,10 +24,13 @@ class SnapshotAdapter extends LlmAdapter {
async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
this.requests.push(options)
const prompt = options.messages.at(-1)
if (prompt?.role !== 'user' || prompt.content.length !== 3
|| prompt.content[1]?.type !== 'text' || prompt.content[1].text !== '\n\n## My request:\n') {
throw new Error('session reference did not reach the model as one prefixed user message')
// The snapshot rides the prompt's admission: the loop appends the
// prompt first, then its additional contexts (the branch-wide ordering
// for plugin-sourced context).
const [prompt, context] = options.messages.slice(-2)
if (context?.role !== 'user' || prompt?.role !== 'user'
|| prompt.content[0]?.type !== 'text' || prompt.content[0].text !== 'Use @Source session') {
throw new Error('session reference context did not follow the direct user message')
}
yield { type: 'block-start', index: 0, blockType: 'text' }
yield { type: 'text-delta', index: 0, text: 'Combined reference request accepted.' }
@@ -113,22 +116,17 @@ describe('TUI session-reference snapshot', () => {
expect(request).toContain('Recent retained question.')
expect(request).not.toContain('SHADOWED OLD USER')
expect(request).not.toContain('SHADOWED OLD ASSISTANT')
const user = target.session.events.find(event => event.type === 'user/message')
expect(user?.type === 'user/message' && user.data.envelope).toMatchObject({
displayContent: [{ type: 'text', text: 'Use @Source session' }],
prefixContexts: [{
source: { kind: 'plugin', plugin: 'session-reference' },
meta: {
kind: 'session-reference',
references: [{ sessionId: 'source-session', compacted: true }],
},
}],
const context = target.session.events.find(event =>
event.type === 'user/message' && event.data.source.kind === 'session-reference')
expect(context?.type === 'user/message' && context.data.source).toMatchObject({
kind: 'session-reference',
references: [{ sessionId: 'source-session', compacted: true }],
})
expect(user?.type === 'user/message' && user.data.content[1]).toEqual({
type: 'text',
text: '\n\n## My request:\n',
})
expect(target.session.events.some(event => event.type === 'user/message' && event.data.source.kind !== 'user')).toBe(false)
const user = target.session.events.find(event =>
event.type === 'user/message' && event.data.source.kind === 'user')
expect(user?.type === 'user/message' && user.data.content).toEqual([
{ type: 'text', text: 'Use @Source session' },
])
const snapshot = await terminal.snapshot({ includeScrollback: true })
if (REFRESHING) {

View File

@@ -21,7 +21,7 @@ buffer
7| "▌ "
style 0-0 fg=bright-blue
8| <blank>
9| " Retrying model request (1/2) in 1000ms: temporary transport failure "
9| " Retrying model request (1/) in 1000ms: temporary transport failure "
style 1-67 fg=yellow
10| <blank>
11| " Turn cancelled. "

View File

@@ -1,7 +1,7 @@
terminal 100x34 buffer=normal length=38 base=4 viewport=4
terminal 100x34 buffer=normal length=36 base=2 viewport=2
lifecycle started=1 stopped=0 progress=inactive
title "Unsafe terminal title \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m"
cursor hidden column=100 viewportRow=33 bufferRow=37
cursor hidden column=100 viewportRow=33 bufferRow=35
buffer
0| " DEEPSEEK HARNESS"
style 1-8 fg=bright-blue bold
@@ -55,23 +55,20 @@ buffer
24| " Unsafe context \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m "
style 1-60 fg=bright-black
25| <blank>
26| " Prompt blocked: Unsafe policy \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m "
style 1-75 fg=yellow
27| <blank>
28| " Unsafe turn error \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m "
26| " Unsafe turn error \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m "
style 1-63 fg=red
29| <blank>
30| " "
31| " Question 1/1 (1 unanswered) · Unsafe header \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m "
27| <blank>
28| " "
29| " Question 1/1 (1 unanswered) · Unsafe header \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m "
style 2-90 fg=bright-black
32| " Unsafe question \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m "
33| " "
34| " 1. Unsafe option \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m Unsafe detail \\x1b]2;snapshot-c "
30| " Unsafe question \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m "
31| " "
32| " 1. Unsafe option \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m Unsafe detail \\x1b]2;snapshot-c "
style 2-65 fg=bright-blue bold
style 67-97 fg=bright-black
35| " Tab custom answer • ↑/↓ navigate • Enter submit • Esc interrupt "
33| " Tab custom answer • ↑/↓ navigate • Enter submit • Esc interrupt "
style 2-64 dim
36| " "
37| "deepseek-v4-flash /workspace/project ↑0 ↓0 0% context tools:collapsed"
34| " "
35| "deepseek-v4-flash /workspace/project ↑0 ↓0 0% context tools:collapsed"
style 0-43 dim
style 73-99 dim

View File

@@ -282,6 +282,9 @@ describe('TUI terminal-state snapshots', () => {
harness.session.append('llm/retry', {
turn: 1,
step: 1,
provider: 'mock',
mode: 'normal',
policyKey: '["normal",2,["RATE_LIMIT"],1,10000,0]',
retry: 1,
maxRetries: 2,
delayMs: 500,
@@ -310,8 +313,10 @@ describe('TUI terminal-state snapshots', () => {
harness.session.append('llm/retry', {
turn: 1,
step: 1,
provider: 'mock',
mode: 'always',
policyKey: '["always",1,10000,0]',
retry: 1,
maxRetries: 2,
delayMs: 1_000,
failure: { message: 'temporary transport failure', code: 'TRANSPORT' },
})
@@ -489,11 +494,6 @@ describe('TUI terminal-state snapshots', () => {
content: [{ type: 'text', text: `Unsafe context ${CONTROL_PROBE}` }],
source: { kind: 'plugin', plugin: `unsafe-${CONTROL_PROBE}` },
}, { surfaceOp: 'append' })
session.append('prompt/blocked', {
content: [{ type: 'text', text: 'blocked' }],
source: { kind: 'user' },
reason: `Unsafe policy ${CONTROL_PROBE}`,
})
session.append('step/end', { turn: 1, step: 1 })
session.append('turn/end', {
turn: 1,

View File

@@ -425,7 +425,6 @@ describe('resume command and /resume', () => {
[{ kind: 'error', step: 1, message: 'failed' }, 'error'],
[{ kind: 'disposed' }, 'disposed'],
[{ kind: 'max-tokens' }, 'max tokens'],
[{ kind: 'rejected', reason: 'policy' }, 'rejected'],
[{ kind: 'interrupted' }, 'interrupted'],
[{ kind: 'future-result' } as unknown as TurnEndReason, 'unknown result'],
] as const)('renders the last turn result %s', async (reason, label) => {
@@ -1085,8 +1084,13 @@ describe('pi-tui chat lifecycle and transcript', () => {
beforeMount(session) {
session.append('user/message', {
content: renderGoalChange(change),
source: { kind: 'goal', goalId: change.goal.id, revision: change.goal.revision, round: 0 },
meta: change as unknown as JsonValue,
source: {
kind: 'goal',
goalId: change.goal.id,
revision: change.goal.revision,
round: 0,
change,
},
}, { surfaceOp: 'append' })
},
})
@@ -1187,7 +1191,6 @@ describe('pi-tui chat lifecycle and transcript', () => {
// A non-plugin injected source (goal) has no `plugin` field, so its context
// card label falls back to the source kind.
result.session.append('user/message', { content: [{ type: 'text', text: 'goal context' }], source: { kind: 'goal', goalId: 'g1', revision: 1, round: 0 } as never }, { surfaceOp: 'append' })
result.session.append('prompt/blocked', { content: [{ type: 'text', text: 'blocked' }], source: { kind: 'user' }, reason: 'test policy' })
appendAssistant(result.session, [])
result.session.append('step/end', { turn: 1, step: 1 })
result.session.append('turn/end', { turn: 1, reason: { kind: 'aborted' } })
@@ -1268,7 +1271,6 @@ describe('pi-tui chat lifecycle and transcript', () => {
expect(result.terminal.output).toContain('Steering')
expect(result.terminal.output).toContain('user context')
expect(result.terminal.output).toContain('Context · goal') // goal-sourced injected context labels by kind
expect(result.terminal.output).toContain('Prompt blocked')
expect(result.terminal.output).toContain('Turn cancelled')
expect(result.terminal.progress).toContain(true)
@@ -1304,6 +1306,9 @@ describe('pi-tui chat lifecycle and transcript', () => {
result.session.append('llm/retry', {
turn: 1,
step: 1,
provider: 'mock',
mode: 'normal',
policyKey: '["normal",2,["RATE_LIMIT"],1,10000,0]',
retry: 1,
maxRetries: 2,
delayMs: 500,
@@ -1336,6 +1341,9 @@ describe('pi-tui chat lifecycle and transcript', () => {
result.session.append('llm/retry', {
turn: 1,
step: 1,
provider: 'mock',
mode: 'normal',
policyKey: '["normal",2,["RATE_LIMIT"],1,10000,0]',
retry: 1,
maxRetries: 2,
delayMs: 500,
@@ -1344,15 +1352,29 @@ describe('pi-tui chat lifecycle and transcript', () => {
result.session.append('llm/retry', {
turn: 1,
step: 2,
provider: 'mock',
mode: 'normal',
policyKey: '["normal",2,["RATE_LIMIT"],1,10000,0]',
retry: 2,
maxRetries: 2,
delayMs: 1_000,
failure: { message: 'failed before chunks', code: 'SERVER', status: 503 },
})
result.session.append('llm/retry', {
turn: 1,
step: 3,
provider: 'mock',
mode: 'always',
policyKey: '["always",1,10000,0]',
retry: 1,
delayMs: 2_000,
failure: { message: 'retry without limit', code: 'AUTH', status: 401 },
})
await tick()
expect(result.terminal.output).toContain('Retrying model request (1/2) in 500ms: rate limited')
expect(result.terminal.output).toContain('Retrying model request (2/2) in 1000ms: failed before chunks')
expect(result.terminal.output).toContain('Retrying model request (1/∞) in 2000ms: retry without limit')
await dispose(result)
})
@@ -1363,30 +1385,38 @@ describe('pi-tui chat lifecycle and transcript', () => {
expect(result.terminal.output).toContain('— Enter sends steering, Esc cancels')
expect(result.terminal.output).not.toContain('queued')
const queueSteering = (text: string): void => {
result.ctx.emit('agent/inbox/enqueue', result.agent, { id: AgentMessageId('stub'), content: [{ type: 'text', text }], source: { kind: 'user' }, contexts: [], steering: true, wakeup: true })
const submitSteering = (text: string): void => {
result.terminal.send(text)
result.terminal.send('\r')
}
const drainSteering = (text: string): void => {
const id = result.agent.steeredIds.shift()
if (id !== undefined) {
result.ctx.emit('agent/inbox/dequeue', result.agent, {
id,
content: [{ type: 'text', text }],
source: { kind: 'user' },
})
}
result.session.append('steering/message', { turn: 1, content: [{ type: 'text', text }], source: { kind: 'user' } }, { surfaceOp: 'append' })
}
// A steering queue for a different agent never touches this status line.
const other = { ...result.agent, id: SessionId('other') } as unknown as Agent
result.terminal.output = ''
result.ctx.emit('agent/inbox/enqueue', other, { id: AgentMessageId('stub'), content: [{ type: 'text', text: 'elsewhere' }], source: { kind: 'user' }, contexts: [], steering: true, wakeup: true })
result.ctx.emit('agent/inbox/enqueue', other, { id: AgentMessageId('stub'), content: [{ type: 'text', text: 'elsewhere' }], source: { kind: 'user' } }, 'queued')
await tick()
expect(result.terminal.output).not.toContain('queued')
// Two steering messages queue while the turn runs.
queueSteering('first')
submitSteering('first')
result.terminal.output = ''
queueSteering('second')
submitSteering('second')
await tick()
expect(result.terminal.output).toContain('2 queued · Enter sends steering, Esc cancels')
// A non-steering queue (an idle-style send) leaves the badge untouched.
// Draining one submitted message decrements the badge.
result.terminal.output = ''
result.ctx.emit('agent/inbox/enqueue', result.agent, { id: AgentMessageId('stub'), content: [{ type: 'text', text: 'sent' }], source: { kind: 'user' }, contexts: [], steering: false, wakeup: true })
drainSteering('first')
await tick()
expect(result.terminal.output).toContain('1 queued')
@@ -1402,13 +1432,12 @@ describe('pi-tui chat lifecycle and transcript', () => {
// A drain with no matching queued entry is ignored rather than underflowing.
result.terminal.output = ''
drainSteering('continuation')
queueSteering('after')
submitSteering('after')
await tick()
expect(result.terminal.output).toContain('1 queued')
// A steering/message whose source matches no pending badge entry (here a
// plugin source with no tracked enqueue) pops nothing, so it cannot consume
// a pending user slot even when it drains first.
// A steering/message has no inbox identity and therefore cannot consume a
// pending slot by itself.
result.terminal.output = ''
result.session.append('steering/message', {
turn: 1,
@@ -1432,15 +1461,40 @@ describe('pi-tui chat lifecycle and transcript', () => {
expect(result.terminal.output).toContain('— Enter sends steering, Esc cancels')
expect(result.terminal.output).not.toContain('queued')
// A cancellation discards queued steering: the badge clears without drains.
submitSteering('third')
submitSteering('fourth')
await tick()
expect(result.terminal.output).toContain('2 queued')
const discarded = result.agent.steeredIds.splice(0).map(id => ({
id, content: [{ type: 'text' as const, text: 'discarded' }], source: { kind: 'user' as const },
}))
// Another agent's dequeue/discard, and ones naming no pending id, leave
// the badge alone.
result.ctx.emit('agent/inbox/dequeue', other, discarded[0]!)
result.ctx.emit('agent/inbox/dequeue', result.agent, {
id: AgentMessageId('never-queued'), content: [{ type: 'text', text: 'x' }], source: { kind: 'user' },
})
result.ctx.emit('agent/inbox/discard', other, discarded)
result.ctx.emit('agent/inbox/discard', result.agent, [
{ id: AgentMessageId('never-queued'), content: [{ type: 'text', text: 'x' }], source: { kind: 'user' } },
])
await tick()
expect(result.terminal.output).toContain('2 queued')
result.terminal.output = ''
result.ctx.emit('agent/inbox/discard', result.agent, discarded)
await tick()
expect(result.terminal.output).toContain('— Enter sends steering, Esc cancels')
expect(result.terminal.output).not.toContain('queued')
await dispose(result)
})
it('derives the fine-grained turn phase from session lifecycle events', async () => {
// A live event before the turn runs has no status controller to move.
const idle = await setup()
// A steering queue arriving while idle has no status line to badge, so the
// refresh is a no-op beyond requesting a render.
idle.ctx.emit('agent/inbox/enqueue', idle.agent, { id: AgentMessageId('stub'), content: [{ type: 'text', text: 'early' }], source: { kind: 'user' }, contexts: [], steering: true, wakeup: true })
// Inbox notifications do not affect the status phase while idle.
idle.ctx.emit('agent/inbox/enqueue', idle.agent, { id: AgentMessageId('stub'), content: [{ type: 'text', text: 'early' }], source: { kind: 'user' } }, 'queued')
idle.session.append('tool/call', { turn: 1, step: 0, callId: 'pre' as never, name: 'bash', arguments: '{}' })
await tick()
expect(idle.terminal.output).not.toContain('Executing tools')
@@ -1814,6 +1868,18 @@ describe('pi-tui chat lifecycle and transcript', () => {
// /reload without a Loader in the context degrades to a warning.
expect(result.terminal.output).toContain('/reload needs the cordis Loader')
expect(result.exit).toHaveBeenCalledWith(0)
// The exit above left the TUI disposed (the mocked runtime.exit returns):
// a message submitted now is refused instead of reaching the agent. The
// refusal notice lands in the transcript, but the stopped UI no longer
// paints, so assert the refusal through the agent surface.
const sentBefore = result.agent.sent.length
const steeredBefore = result.agent.steered.length
result.terminal.send('after shutdown')
result.terminal.send('\r')
await tick()
expect(result.agent.sent).toHaveLength(sentBefore)
expect(result.agent.steered).toHaveLength(steeredBefore)
await result.controller.dispose()
await result.ctx.fiber.dispose()
@@ -1824,13 +1890,6 @@ describe('pi-tui chat lifecycle and transcript', () => {
await ctrlCExit.controller.dispose()
await ctrlCExit.ctx.fiber.dispose()
const disposedAgent = await setup()
disposedAgent.agent.status = 'disposed'
disposedAgent.terminal.send('late input')
disposedAgent.terminal.send('\r')
await tick()
expect(disposedAgent.terminal.output).toContain('is disposed')
await dispose(disposedAgent)
})
it('combines session autocomplete with files and prepares send/steer references asynchronously', async () => {
@@ -1865,20 +1924,252 @@ describe('pi-tui chat lifecycle and transcript', () => {
result.terminal.send('\r')
await vi.waitFor(() => { expect(result.agent.sent).toHaveLength(1) })
expect(result.agent.sent).toEqual([[{ type: 'text', text: '@Source chat' }]])
expect(result.agent.sentOptions[0]?.contexts).toHaveLength(1)
// Idle: the snapshot rides the prompt's admission (additionalContexts on
// the allow decision), not a separate pre-admission inject.
expect(result.agent.injected).toHaveLength(0)
const decision = await agentEvents(result.ctx, result.agent).waterfall(
'agent/prompt-submit', result.agent.sent[0]!, { kind: 'user' },
new AbortController().signal, () => Promise.resolve({ kind: 'allow' as const }),
)
expect(decision.kind).toBe('allow')
expect(decision.kind === 'allow' && decision.additionalContexts?.[0]?.source)
.toMatchObject({ kind: 'session-reference', references: [{ sessionId: 'source-session' }] })
// The one-shot wrapper detached itself at admission: replaying the
// waterfall attaches nothing a second time.
const replay = await agentEvents(result.ctx, result.agent).waterfall(
'agent/prompt-submit', result.agent.sent[0]!, { kind: 'user' },
new AbortController().signal, () => Promise.resolve({ kind: 'allow' as const }),
)
expect(replay.kind === 'allow' && replay.additionalContexts).toBeUndefined()
const mention = formatSessionReferenceMention({ sessionId: sourceId, label: 'Source chat' })
expect(result.agent.sentOptions[0]?.contexts).toMatchObject([{
source: { kind: 'plugin', plugin: 'session-reference' },
meta: { kind: 'session-reference', references: [{ sessionId: 'source-session' }] },
}])
result.agent.status = 'running'
result.terminal.send(`steer ${mention}`)
result.terminal.send('\r')
await vi.waitFor(() => { expect(result.agent.steered).toHaveLength(1) })
expect(result.agent.steered).toEqual([[{ type: 'text', text: 'steer @Source chat' }]])
expect(result.agent.steeredOptions[0]?.contexts).toHaveLength(1)
// Steering bypasses admission, so its snapshot still arrives via inject.
expect(result.agent.injected).toHaveLength(1)
await dispose(result)
})
it('keeps a referenced prompt on admission when running no longer accepts next-step input', async () => {
const result = await setup({
status: 'running',
acceptsNextStep: false,
omitInitialLifecycle: true,
async configureContext(ctx) {
ctx.provide('tools', { get: () => undefined } as never)
await ctx.plugin(TestSessionQueryService)
await ctx.plugin(SessionReferenceService)
const source = ctx.sessions.create(SessionId('admission-src'), {
meta: { cwd: process.cwd(), createdAt: 1 },
})
appendUser(source, 'source background')
source.append('session/title', {
title: 'Admission source',
messageSeqs: [0],
source: { kind: 'fallback' },
})
},
})
result.terminal.send(formatSessionReferenceMention({
sessionId: SessionId('admission-src'),
label: 'Admission source',
}))
result.terminal.send('\r')
await vi.waitFor(() => { expect(result.agent.sent).toHaveLength(1) })
expect(result.agent.steered).toHaveLength(0)
expect(result.agent.injected).toHaveLength(0)
const decision = await agentEvents(result.ctx, result.agent).waterfall(
'agent/prompt-submit', result.agent.sent[0]!, { kind: 'user' },
new AbortController().signal, () => Promise.resolve({ kind: 'allow' as const }),
)
expect(decision.kind === 'allow' && decision.additionalContexts?.[0]?.source)
.toMatchObject({ kind: 'session-reference', references: [{ sessionId: 'admission-src' }] })
await dispose(result)
})
it('releases the reference-admission wrapper on the ordinary allowed path', async () => {
const result = await setup({
async configureContext(ctx) {
ctx.provide('tools', { get: () => undefined } as never)
await ctx.plugin(TestSessionQueryService)
await ctx.plugin(SessionReferenceService)
const source = ctx.sessions.create(SessionId('leak-source'), { meta: { cwd: process.cwd(), createdAt: 1 } })
appendUser(source, 'source background')
},
})
const send = async (): Promise<void> => {
result.terminal.send('@leak-source')
await vi.waitFor(() => { expect(result.terminal.output).toContain('Session · leak-source') })
result.terminal.send('\t')
await tick()
result.terminal.send('\r')
}
await send()
await vi.waitFor(() => { expect(result.agent.sent).toHaveLength(1) })
await send()
await vi.waitFor(() => { expect(result.agent.sent).toHaveLength(2) })
// Each wrapper releases on its own allowed admission — matched by the
// message content it carries, not the returned id, which real send()
// assigns as a random UUID only after followup() returns. Running each
// prompt's admission waterfall detaches its wrapper.
for (const sent of result.agent.sent) {
await agentEvents(result.ctx, result.agent).waterfall(
'agent/prompt-submit', sent, { kind: 'user' },
new AbortController().signal, () => Promise.resolve({ kind: 'allow' as const }),
)
}
// Both wrappers now gone: a discard naming either prompt's content finds
// no armed listener, and an unrelated admission is untouched. The leak
// regression: a listener installed after its cleanup already ran would
// survive every future cleanup.
result.ctx.emit('agent/inbox/discard', result.agent, [{
id: AgentMessageId('stub'), content: result.agent.sent[0]!, source: { kind: 'user' },
}])
const unrelated = await agentEvents(result.ctx, result.agent).waterfall(
'agent/prompt-submit', [{ type: 'text', text: 'unrelated' }], { kind: 'user' },
new AbortController().signal, () => Promise.resolve({ kind: 'allow' as const }),
)
expect(unrelated.kind === 'allow' && unrelated.additionalContexts).toBeUndefined()
// Replaying either sent prompt attaches nothing: the one-shot wrappers
// are gone, not merely spent.
for (const sent of result.agent.sent) {
const replay = await agentEvents(result.ctx, result.agent).waterfall(
'agent/prompt-submit', sent, { kind: 'user' },
new AbortController().signal, () => Promise.resolve({ kind: 'allow' as const }),
)
expect(replay.kind === 'allow' && replay.additionalContexts).toBeUndefined()
}
await dispose(result)
})
it('releases the reference wrapper when enqueue synchronously discards before followup returns', async () => {
const result = await setup({
async configureContext(ctx) {
ctx.provide('tools', { get: () => undefined } as never)
await ctx.plugin(TestSessionQueryService)
await ctx.plugin(SessionReferenceService)
const source = ctx.sessions.create(SessionId('sync-source'), { meta: { cwd: process.cwd(), createdAt: 1 } })
appendUser(source, 'source background')
},
})
// Real send() publishes its snapshotted message, then an enqueue listener
// may synchronously cancel and discard it before followup() returns the
// already-assigned id. This stub reproduces that ordering.
const foreign = { ...result.agent, id: SessionId('foreign') } as unknown as Agent
result.agent.followup = (input) => {
result.agent.sent.push(input.content)
const message = {
id: AgentMessageId('stub'),
content: structuredClone(input.content),
source: structuredClone(input.source),
}
result.ctx.emit('agent/inbox/enqueue', foreign, message, 'queued')
result.ctx.emit('agent/inbox/enqueue', result.agent, message, 'queued')
result.ctx.emit('agent/inbox/discard', result.agent, [message])
return message.id
}
result.terminal.send('@sync-source')
await vi.waitFor(() => { expect(result.terminal.output).toContain('Session · sync-source') })
result.terminal.send('\t')
await tick()
result.terminal.send('\r')
await vi.waitFor(() => { expect(result.agent.sent).toHaveLength(1) })
// The synchronous discard released the listeners even though followup()
// had not returned the id yet: replaying the prompt's admission attaches
// no stranded snapshot, and nothing leaks for the TUI lifetime.
const replay = await agentEvents(result.ctx, result.agent).waterfall(
'agent/prompt-submit', result.agent.sent[0]!, { kind: 'user' },
new AbortController().signal, () => Promise.resolve({ kind: 'allow' as const }),
)
expect(replay.kind === 'allow' && replay.additionalContexts).toBeUndefined()
await dispose(result)
})
it('discards the reference snapshot with its blocked or cancelled prompt', async () => {
const result = await setup({
async configureContext(ctx) {
ctx.provide('tools', { get: () => undefined } as never)
await ctx.plugin(TestSessionQueryService)
await ctx.plugin(SessionReferenceService)
const source = ctx.sessions.create(SessionId('blocked-source'), { meta: { cwd: process.cwd(), createdAt: 1 } })
appendUser(source, 'source background')
},
})
// A downstream admission hook blocks the prompt: the attached snapshot
// must be discarded with it, not stranded for the next prompt.
let blockPrompts = true
result.ctx.on('agent/prompt-submit', async (_agent, _content, _source, _signal, next) =>
blockPrompts ? { kind: 'block' as const, reason: 'policy' } : next())
result.terminal.send('@blocked-source')
await vi.waitFor(() => { expect(result.terminal.output).toContain('Session · blocked-source') })
result.terminal.send('\t')
await tick()
result.terminal.send('\r')
await vi.waitFor(() => { expect(result.agent.sent).toHaveLength(1) })
const blocked = await agentEvents(result.ctx, result.agent).waterfall(
'agent/prompt-submit', result.agent.sent[0]!, { kind: 'user' },
new AbortController().signal, () => Promise.resolve({ kind: 'allow' as const }),
)
expect(blocked.kind).toBe('block')
// Nothing entered history and nothing waits for a later prompt: a fresh
// unrelated admission sees no leftover contexts.
expect(result.agent.injected).toHaveLength(0)
blockPrompts = false
const unrelated = await agentEvents(result.ctx, result.agent).waterfall(
'agent/prompt-submit', [{ type: 'text', text: 'unrelated' }], { kind: 'user' },
new AbortController().signal, () => Promise.resolve({ kind: 'allow' as const }),
)
expect(unrelated.kind === 'allow' && unrelated.additionalContexts).toBeUndefined()
// Second referenced prompt, this time dropped by a broad cancel before
// any admission runs: the discard listener releases the wrapper.
result.terminal.send('@blocked-source')
await vi.waitFor(() => { expect(result.terminal.output).toContain('Session · blocked-source') })
result.terminal.send('\t')
await tick()
result.terminal.send('\r')
await vi.waitFor(() => { expect(result.agent.sent).toHaveLength(2) })
// A different prompt passing the still-armed wrapper delegates untouched.
const passthrough = await agentEvents(result.ctx, result.agent).waterfall(
'agent/prompt-submit', [{ type: 'text', text: 'different prompt' }], { kind: 'user' },
new AbortController().signal, () => Promise.resolve({ kind: 'allow' as const }),
)
expect(passthrough.kind === 'allow' && passthrough.additionalContexts).toBeUndefined()
// A foreign agent's discard leaves the wrapper armed.
const foreign = { ...result.agent, id: SessionId('foreign') } as unknown as Agent
result.ctx.emit('agent/inbox/discard', foreign, [{
id: AgentMessageId('stub'),
content: result.agent.sent.at(-1)!,
source: { kind: 'user' },
}])
result.ctx.emit('agent/inbox/discard', result.agent, [{
id: AgentMessageId('stub'),
content: result.agent.sent.at(-1)!,
source: { kind: 'user' },
}])
await tick()
// Idempotent: a repeat discard after cleanup is a no-op.
result.ctx.emit('agent/inbox/discard', result.agent, [{
id: AgentMessageId('stub'),
content: result.agent.sent.at(-1)!,
source: { kind: 'user' },
}])
const afterDiscard = await agentEvents(result.ctx, result.agent).waterfall(
'agent/prompt-submit', result.agent.sent.at(-1)!, { kind: 'user' },
new AbortController().signal, () => Promise.resolve({ kind: 'allow' as const }),
)
expect(afterDiscard.kind === 'allow' && afterDiscard.additionalContexts).toBeUndefined()
await dispose(result)
})
@@ -1918,7 +2209,6 @@ describe('pi-tui chat lifecycle and transcript', () => {
result.terminal.send('\r')
await vi.waitFor(() => { expect(result.agent.sent).toHaveLength(1) })
expect(result.agent.sent[0]).toEqual([{ type: 'text', text: '@src/source-file.ts' }])
expect(result.agent.sentOptions[0]?.contexts).toEqual([])
result.terminal.send('@do')
await vi.waitFor(() => {
@@ -1934,7 +2224,6 @@ describe('pi-tui chat lifecycle and transcript', () => {
result.terminal.send('\r')
await vi.waitFor(() => { expect(result.agent.sent).toHaveLength(2) })
expect(result.agent.sent[1]).toEqual([{ type: 'text', text: '@"docs/design notes.md"' }])
expect(result.agent.sentOptions[1]?.contexts).toEqual([])
result.terminal.send('@unsafe')
await tick()
@@ -2030,9 +2319,12 @@ describe('pi-tui chat lifecycle and transcript', () => {
expect(result.agent.sent).toEqual([[
{ type: 'text', text: '@evil\\x1b\\x07\\x9b\\x0as' },
]])
expect(result.agent.sentOptions[0]?.contexts).toMatchObject([{
meta: { references: [{ sessionId: unsafeId }] },
}])
const decision = await agentEvents(result.ctx, result.agent).waterfall(
'agent/prompt-submit', result.agent.sent[0]!, { kind: 'user' },
new AbortController().signal, () => Promise.resolve({ kind: 'allow' as const }),
)
expect(decision.kind === 'allow' && decision.additionalContexts?.[0]?.source)
.toMatchObject({ references: [{ sessionId: unsafeId }] })
await dispose(result)
})
@@ -2118,84 +2410,65 @@ describe('pi-tui chat lifecycle and transcript', () => {
expect(result.terminal.output).toContain('keep @[')
result.session.append('user/message', {
content: [
{ type: 'text', text: 'hidden baked snapshot payload' },
{ type: 'text', text: '\n\n## My request:\n' },
{ type: 'text', text: 'visible referenced question' },
],
content: [{ type: 'text', text: 'hidden snapshot payload' }],
source: {
kind: 'session-reference',
references: [{ sessionId: 'prefixed', label: 'Prefixed source' }],
} as never,
}, { surfaceOp: 'append' })
result.session.append('user/message', {
content: [{ type: 'text', text: 'visible referenced question' }],
source: { kind: 'user' },
envelope: {
displayContent: [{ type: 'text', text: 'visible referenced question' }],
prefixContexts: [{
source: { kind: 'plugin', plugin: 'session-reference' },
meta: {
kind: 'session-reference',
references: [{ sessionId: 'prefixed', label: 'Prefixed source' }],
},
}],
},
}, { surfaceOp: 'append' })
await tick()
expect(result.terminal.output).toContain('visible referenced question')
expect(result.terminal.output).toContain('Referenced sessions · Prefixed source (prefixed)')
expect(result.terminal.output).not.toContain('hidden baked snapshot payload')
expect(result.terminal.output).not.toContain('hidden snapshot payload')
result.session.append('user/message', {
content: [{ type: 'text', text: 'hidden steering context' }],
source: {
kind: 'session-reference',
references: [{ sessionId: 'steering-source', label: 'Steering source' }],
} as never,
}, { surfaceOp: 'append' })
result.session.append('steering/message', {
turn: 1,
content: [
{ type: 'text', text: 'hidden non-reference prefix' },
{ type: 'text', text: '\n\n## My request:\n' },
{ type: 'text', text: 'visible steering prompt' },
],
content: [{ type: 'text', text: 'visible steering prompt' }],
source: { kind: 'user' },
envelope: {
displayContent: [{ type: 'text', text: 'visible steering prompt' }],
prefixContexts: [
{ source: { kind: 'plugin', plugin: 'other' }, meta: { kind: 'other' } },
{
source: { kind: 'plugin', plugin: 'session-reference' },
meta: {
kind: 'session-reference',
references: [{ sessionId: 'steering-source', label: 'Steering source' }],
},
},
],
},
}, { surfaceOp: 'append' })
await tick()
expect(result.terminal.output).toContain('visible steering prompt')
expect(result.terminal.output).toContain('Referenced sessions · Steering source (steering-source)')
expect(result.terminal.output).not.toContain('hidden non-reference prefix')
expect(result.terminal.output).not.toContain('hidden steering context')
result.session.append('user/message', {
content: [{ type: 'text', text: 'secret full snapshot payload' }],
source: { kind: 'plugin', plugin: 'session-reference' },
meta: {
source: {
kind: 'session-reference',
version: 1,
references: [{ sessionId: 'source', label: 'Source', capturedThroughSeq: 2 }],
},
} as never,
}, { surfaceOp: 'append' })
await tick()
expect(result.terminal.output).toContain('Referenced sessions · Source (source)')
expect(result.terminal.output).not.toContain('secret full snapshot payload')
const invalidCards: [JsonValue, string][] = [
['plain-string-source', 'invalid-shape'],
[{ kind: 'other' }, 'invalid-kind'],
[{ kind: 'session-reference', references: [null] }, 'invalid-entry'],
[{ kind: 'session-reference', references: [{}] }, 'invalid-fields'],
]
for (const [meta, text] of invalidCards) {
for (const [source, text] of invalidCards) {
result.session.append('user/message', {
content: [{ type: 'text', text }],
source: { kind: 'plugin', plugin: 'session-reference' },
meta,
source: source as never,
}, { surfaceOp: 'append' })
}
result.session.append('user/message', {
content: [{ type: 'text', text: 'same-label snapshot' }],
source: { kind: 'plugin', plugin: 'session-reference' },
meta: { kind: 'session-reference', references: [{ sessionId: 'same', label: 'same' }] },
source: { kind: 'session-reference', references: [{ sessionId: 'same', label: 'same' }] } as never,
}, { surfaceOp: 'append' })
await tick()
expect(result.terminal.output).toContain('Referenced sessions · same')
@@ -2235,7 +2508,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
let release: (() => void) | undefined
const prepare = vi.spyOn(result.ctx.sessionReferences, 'prepare').mockImplementation(
(_agent, content) => new Promise((resolve) => {
release = () => { resolve({ content, contexts: [] }) }
release = () => { resolve({ content }) }
}),
)
result.terminal.send(value)
@@ -2283,7 +2556,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
let resolveAfterDispose: (() => void) | undefined
const latePrepare = vi.spyOn(lateSuccess.ctx.sessionReferences, 'prepare').mockImplementation(
(_agent, content) => new Promise((resolve) => {
resolveAfterDispose = () => { resolve({ content, contexts: [] }) }
resolveAfterDispose = () => { resolve({ content }) }
}),
)
lateSuccess.terminal.send(value)
@@ -2414,7 +2687,6 @@ describe('pi-tui chat lifecycle and transcript', () => {
'agent/request',
0,
0,
explicitResetSeed,
new AbortController().signal,
() => Promise.resolve(explicitResetSeed),
)).resolves.toEqual({ provider: 'alpha', model: 'shared' })
@@ -2451,7 +2723,6 @@ describe('pi-tui chat lifecycle and transcript', () => {
'agent/request',
0,
0,
inheritedEffort,
new AbortController().signal,
() => Promise.resolve(inheritedEffort),
)).resolves.toEqual({ provider: 'beta', model: 'shared' })
@@ -2505,7 +2776,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
expect(assembly.variables).toMatchObject({ provider: 'beta', model: 'b1' })
const seed: LlmCallConfig = { provider: 'alpha', model: 'a1', temperature: 0.2 }
const request = await agentEvents(result.ctx, result.agent).waterfall(
'agent/request', 1, 0, seed, new AbortController().signal, () => Promise.resolve(seed),
'agent/request', 1, 0, new AbortController().signal, () => Promise.resolve(seed),
)
expect(request).toEqual({
provider: 'beta',
@@ -2590,7 +2861,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
expect(assembly.variables).toEqual({})
const seed: LlmCallConfig = { provider: 'fallback', model: 'fallback' }
await expect(agentEvents(empty.ctx, empty.agent).waterfall(
'agent/request', 1, 0, seed, new AbortController().signal, () => Promise.resolve(seed),
'agent/request', 1, 0, new AbortController().signal, () => Promise.resolve(seed),
)).resolves.toBe(seed)
await dispose(empty)
@@ -2817,12 +3088,10 @@ describe('pi-tui chat lifecycle and transcript', () => {
events.session.append('turn/start', { turn: 4, trigger: { kind: 'message', source: { kind: 'user' } } })
events.session.append('turn/end', { turn: 4, reason: { kind: 'max-tokens' } })
events.session.append('turn/start', { turn: 5, trigger: { kind: 'message', source: { kind: 'user' } } })
events.session.append('turn/end', { turn: 5, reason: { kind: 'rejected', reason: 'policy' } })
events.session.append('turn/end', { turn: 5, reason: { kind: 'interrupted' } })
events.session.append('turn/start', { turn: 6, trigger: { kind: 'message', source: { kind: 'user' } } })
events.session.append('turn/end', { turn: 6, reason: { kind: 'interrupted' } })
events.session.append('turn/start', { turn: 7, trigger: { kind: 'message', source: { kind: 'user' } } })
events.session.append('turn/end', {
turn: 7,
turn: 6,
reason: { kind: 'error', step: 1, failure: { message: 'structured provider failure', code: 'SERVER' } },
})
agentEvents(events.ctx, events.agent).emit('agent/disposed')
@@ -2832,11 +3101,29 @@ describe('pi-tui chat lifecycle and transcript', () => {
expect(events.terminal.output).toContain('Turn cancelled')
expect(events.terminal.output).toContain('structured provider failure')
expect(events.terminal.output).toContain('output-token limit')
expect(events.terminal.output).toContain('Turn rejected')
expect(events.terminal.output).toContain('previous process ended')
expect(events.terminal.output).toContain('was disposed')
await dispose(events)
})
it('rejects input after the agent is disposed out from under the TUI', async () => {
const result = await setup()
// The agent leaves the registry (e.g. an agent-loop-only reload) while the
// TUI stays mounted. A later send must report disposal, not drive the
// detached zombie agent.
agentEvents(result.ctx, result.agent).emit('agent/disposed')
await tick()
expect(result.terminal.output).toContain('was disposed')
result.terminal.send('drive the zombie')
result.terminal.send('\r')
await tick()
expect(result.agent.sent).toHaveLength(0)
expect(result.agent.steered).toHaveLength(0)
expect(result.terminal.output).toContain('is disposed')
await dispose(result)
})
})
describe('skill slash command', () => {
@@ -3484,8 +3771,8 @@ describe('terminal mounting', () => {
ctx.provide('tools', { get: () => undefined } as never)
const session = ctx.sessions.create(SessionId('main'))
ctx.agents.register({
id: session.id, options: {}, session, status: 'idle', ctx,
followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
id: session.id, options: {}, session, status: 'idle', acceptsNextStep: false, ctx,
followup: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
})
const terminal = new FakeTerminal()
mountTui(ctx, { color: false }, { terminal, exit: vi.fn() })
@@ -3508,8 +3795,8 @@ describe('terminal mounting', () => {
ctx.provide('tools', { get: () => undefined } as never)
const session = ctx.sessions.create(SessionId('main'))
ctx.agents.register({
id: session.id, options: {}, session, status: 'idle', ctx,
followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
id: session.id, options: {}, session, status: 'idle', acceptsNextStep: false, ctx,
followup: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
})
const terminal = new FakeTerminal()
// Mirror dsh-tui's own inject (minus loader, the absence under test).
@@ -3542,15 +3829,15 @@ describe('terminal mounting', () => {
const otherSession = ctx.sessions.create(SessionId('other-session'))
ctx.agents.register({
id: otherSession.id, options: {}, session: otherSession, status: 'idle', ctx,
followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
id: otherSession.id, options: {}, session: otherSession, status: 'idle', acceptsNextStep: false, ctx,
followup: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
})
expect(terminal.started).toBe(0)
const session = ctx.sessions.create(SessionId('late-session'))
const agent = {
id: session.id, options: {}, session, status: 'idle', ctx,
followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
id: session.id, options: {}, session, status: 'idle', acceptsNextStep: false, ctx,
followup: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
} as Agent
ctx.agents.register(agent)
await tick()
@@ -3579,8 +3866,8 @@ describe('terminal mounting', () => {
const session = ctx.sessions.create(SessionId('main-session'))
ctx.agents.register({
id: session.id, options: {}, session, status: 'idle', ctx,
followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
id: session.id, options: {}, session, status: 'idle', acceptsNextStep: false, ctx,
followup: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
})
await tick()
expect(terminal.started).toBe(0)
@@ -3621,8 +3908,8 @@ describe('terminal mounting', () => {
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
session.append('step/start', { turn: 1, step: 1 })
ctx.agents.register({
id: session.id, options: {}, session, status: 'running', ctx,
followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
id: session.id, options: {}, session, status: 'running', acceptsNextStep: true, ctx,
followup: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
})
const terminal = new FakeTerminal()
terminal.start = () => { throw new Error('terminal startup failed') }

View File

@@ -235,8 +235,8 @@ export class ApprovalService extends Service {
})
})
// Visibility layer 2: the boundary narrator. pre-step runs after prompt
// assembly but before the request history is derived, so the notice is
// Visibility layer 2: the boundary narrator. agent/step runs before the
// request history is derived, so the notice is
// seen by THIS step's request: idle-time flip-flops coalesce at the
// turn's first step (net-zero → nothing), and a mid-turn switch is
// narrated no later than the next step. What each session was last told
@@ -246,7 +246,7 @@ export class ApprovalService extends Service {
// switch by the user; otherwise the configured default moved under the
// session (operator/config).
const narrated = new WeakMap<Agent['session'], ApprovalPolicy>()
ctx.on('agent/pre-step', (agent) => {
ctx.on('agent/step', (agent) => {
const session = agent.session
const events = session.events
let overrideIndex = -1
@@ -269,10 +269,10 @@ export class ApprovalService extends Service {
// to go out states the truth, and there is no delta to explain.
if (told === undefined || told === current) return
const cause = overrideIndex > headerIndex ? 'changed by the user' : 'changed by the operator/config'
agent.inject(
[{ type: 'text', text: `The approval policy changed from "${told}" to "${current}" (${cause}).` }],
{ source: { kind: 'plugin', plugin: 'user-approval' } },
)
agent.inject({
content: [{ type: 'text', text: `The approval policy changed from "${told}" to "${current}" (${cause}).` }],
source: { kind: 'plugin', plugin: 'user-approval' },
})
})
}

View File

@@ -365,13 +365,15 @@ describe('approval policy (the approval/policy fold)', () => {
const agent = {
id,
session,
inject: (content: { type: string; text: string }[]) => { injected.push(content[0]?.text ?? '') },
inject: (input: { content: Array<{ type: string; text: string }> }) => {
injected.push(input.content[0]?.text ?? '')
},
} as unknown as Agent
return { agent, session, injected }
}
const preStep = (ctx: Context, agent: Agent): Promise<void> =>
agentEvents(ctx, agent).serial('agent/pre-step', 1, 1, new AbortController().signal)
agentEvents(ctx, agent).serial('agent/step', 1, 1, new AbortController().signal)
/** Append a `request/header` snapshot whose system text is exactly `system`. */
function appendHeader(session: Session, system: string): void {