refactor(web): publish transient model request capacity (round 1)
This commit is contained in:
@@ -4,23 +4,20 @@
|
||||
* models, and the prompt-assembly boundary for a running selection change.
|
||||
*/
|
||||
|
||||
import { describe, expect, it, vi } from 'vitest'
|
||||
import { Context, FiberState } from 'cordis'
|
||||
import type { Fiber } from 'cordis'
|
||||
import AgentRegistry, { agentEvents, installAgentLlmTarget } from '@deepseek-ai/dsh-agent'
|
||||
import type { Agent, AgentLlmTargetRef } from '@deepseek-ai/dsh-agent'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import AgentRegistry, { agentEvents } from '@deepseek-ai/dsh-agent'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import LlmService, { LlmAdapter, ReasoningEffortId } from '@deepseek-ai/dsh-llm'
|
||||
import type {
|
||||
GenerateOptions, LlmCallConfig, LlmModelInfo, LlmModelReasoningInfo, LlmProviderInfo,
|
||||
LlmResolvedModelInfo, StreamChunk,
|
||||
} from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type { Session } from '@deepseek-ai/dsh-session'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
|
||||
import type { RpcRequest } from '@deepseek-ai/dsh-host-apiproxy/api/rpc'
|
||||
import { RpcId } from '@deepseek-ai/dsh-host-apiproxy/api/rpc'
|
||||
import type { MuxFrame } from '@deepseek-ai/dsh-host-apiproxy/api'
|
||||
import { createApiProxy } from '../src/api-proxy.ts'
|
||||
|
||||
let nextRpc = 1
|
||||
@@ -64,40 +61,6 @@ class CatalogAdapter extends LlmAdapter {
|
||||
}
|
||||
}
|
||||
|
||||
class DeferredCatalogAdapter extends CatalogAdapter {
|
||||
readonly pending: {
|
||||
result: PromiseWithResolvers<LlmResolvedModelInfo>
|
||||
signal: AbortSignal | undefined
|
||||
}[] = []
|
||||
|
||||
constructor() {
|
||||
super('Deferred', [
|
||||
{ provider: 'deferred', id: 'lifecycle-model', name: 'Lifecycle model' },
|
||||
])
|
||||
}
|
||||
|
||||
override resolveModel(
|
||||
_provider: string,
|
||||
_model: string,
|
||||
signal?: AbortSignal,
|
||||
): Promise<LlmResolvedModelInfo> {
|
||||
const result = Promise.withResolvers<LlmResolvedModelInfo>()
|
||||
this.pending.push({ result, signal })
|
||||
return result.promise
|
||||
}
|
||||
|
||||
resolve(index: number, contextWindow: number): void {
|
||||
const pending = this.pending[index]
|
||||
if (pending === undefined) throw new Error(`no pending resolution at index ${String(index)}`)
|
||||
pending.result.resolve({
|
||||
provider: 'deferred',
|
||||
id: 'lifecycle-model',
|
||||
name: 'Lifecycle model',
|
||||
context: { contextWindow },
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
const REASONING: LlmModelReasoningInfo = {
|
||||
efforts: [
|
||||
{ id: ReasoningEffortId('off'), name: 'Off' },
|
||||
@@ -107,18 +70,13 @@ const REASONING: LlmModelReasoningInfo = {
|
||||
defaultEffort: ReasoningEffortId('high'),
|
||||
}
|
||||
|
||||
async function hostContext(
|
||||
onSessions?: (fiber: Fiber) => void,
|
||||
onAgents?: (fiber: Fiber) => void,
|
||||
): Promise<Context> {
|
||||
async function hostContext(): Promise<Context> {
|
||||
const ctx = new Context()
|
||||
const sessionsFiber = await ctx.plugin(SessionStore)
|
||||
onSessions?.(sessionsFiber)
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SystemPrompt, { persona: '' })
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(UserInteractionService)
|
||||
const agentsFiber = await ctx.plugin(AgentRegistry)
|
||||
onAgents?.(agentsFiber)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
ctx.llm.registerAdapter(['deepseek'], new CatalogAdapter('DeepSeek', [
|
||||
{ provider: 'deepseek', id: 'deepseek-chat', name: 'DeepSeek Chat' },
|
||||
{ provider: 'deepseek', id: 'deepseek-reasoner', name: 'DeepSeek Reasoner', description: 'Reasoning model' },
|
||||
@@ -164,65 +122,6 @@ function expectValue<T>(response: { result: { ok: true; value: T } | { ok: false
|
||||
return response.result.value
|
||||
}
|
||||
|
||||
async function nextMetrics(
|
||||
iterator: AsyncIterator<RpcRequest<MuxFrame>>,
|
||||
): Promise<Extract<MuxFrame, { type: 'session/metrics' }>['metrics']> {
|
||||
for (;;) {
|
||||
const next = await iterator.next()
|
||||
if (next.done) throw new Error('mux ended before a metrics frame')
|
||||
if (next.value.payload.type === 'session/metrics') return next.value.payload.metrics
|
||||
}
|
||||
}
|
||||
|
||||
function attachLifecycleSession(
|
||||
ctx: Context,
|
||||
sessionId: SessionId,
|
||||
withMarker = false,
|
||||
): { session: Session; detach: () => void } {
|
||||
const session = ctx.sessions.prepare(sessionId)
|
||||
session.append('request/header', {
|
||||
header: { config: { provider: 'deferred', model: 'lifecycle-model' } },
|
||||
reason: 'initial',
|
||||
})
|
||||
if (withMarker) {
|
||||
session.append('user/message', {
|
||||
content: [{ type: 'text', text: 'replacement marker' }],
|
||||
source: { kind: 'plugin', plugin: 'test' },
|
||||
}, { surfaceOp: 'append' })
|
||||
}
|
||||
const detach = ctx.sessions.enter(session)
|
||||
ctx.sessions.announce(session)
|
||||
return { session, detach }
|
||||
}
|
||||
|
||||
function attachLifecycleAgent(
|
||||
ctx: Context,
|
||||
session: Session,
|
||||
): () => void {
|
||||
const agent = {
|
||||
id: session.id,
|
||||
session,
|
||||
status: 'running',
|
||||
ctx,
|
||||
} as Agent
|
||||
const detach = ctx.agents.enter(agent, undefined)
|
||||
ctx.agents.announce(agent)
|
||||
return detach
|
||||
}
|
||||
|
||||
function settleCapacityCompletion(): Promise<void> {
|
||||
return new Promise<void>((resolve) => { setImmediate(resolve) })
|
||||
}
|
||||
|
||||
function installDeferredAdapter(
|
||||
ctx: Context,
|
||||
adapter: DeferredCatalogAdapter,
|
||||
): Fiber & PromiseLike<Fiber> {
|
||||
return ctx.plugin(Object.assign((inner: Context) => {
|
||||
inner.llm.registerAdapter(['deferred'], adapter)
|
||||
}, { inject: ['llm'] }))
|
||||
}
|
||||
|
||||
describe('Web session model selection', () => {
|
||||
it('groups successful providers, isolates failures, and preserves an unlisted current model', async () => {
|
||||
const { ctx, sessionId } = await harness({
|
||||
@@ -230,7 +129,12 @@ describe('Web session model selection', () => {
|
||||
model: 'private-preview',
|
||||
reasoningEffort: ReasoningEffortId('max'),
|
||||
})
|
||||
const api = createApiProxy(ctx, { provider: 'deepseek', model: 'deepseek-chat', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, {
|
||||
provider: 'deepseek',
|
||||
model: 'deepseek-chat',
|
||||
cwd: '/tmp',
|
||||
workspaceRoot: '/tmp',
|
||||
})
|
||||
|
||||
const catalog = expectValue(await api.sessions.models(request({ sessionId })))
|
||||
expect(catalog.current).toEqual({
|
||||
@@ -271,7 +175,12 @@ describe('Web session model selection', () => {
|
||||
|
||||
it('accepts an advisory-unlisted model, rejects an unavailable provider, and switches only after the next assembly', async () => {
|
||||
const { ctx, agent, sessionId } = await harness()
|
||||
const api = createApiProxy(ctx, { provider: 'deepseek', model: 'deepseek-chat', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, {
|
||||
provider: 'deepseek',
|
||||
model: 'deepseek-chat',
|
||||
cwd: '/tmp',
|
||||
workspaceRoot: '/tmp',
|
||||
})
|
||||
const seed: LlmCallConfig = { provider: 'seed', model: 'seed', temperature: 0.2 }
|
||||
const signal = new AbortController().signal
|
||||
|
||||
@@ -336,534 +245,4 @@ describe('Web session model selection', () => {
|
||||
.toEqual({ provider: 'deepseek', model: 'private-preview', reasoningEffort: 'max' })
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('publishes unknown capacity immediately on selection, then the exact selected route capacity', async () => {
|
||||
const { ctx, sessionId } = await harness()
|
||||
const api = createApiProxy(ctx, { provider: 'deepseek', model: 'deepseek-chat', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
expectValue(await api.sessions.models(request({ sessionId })))
|
||||
const controller = new AbortController()
|
||||
const iterator = api.events.mux(request({}), controller.signal)[Symbol.asyncIterator]()
|
||||
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBe(64_000)
|
||||
|
||||
expectValue(await api.sessions.selectModel(request({
|
||||
sessionId,
|
||||
provider: 'deepseek',
|
||||
model: 'private-preview',
|
||||
})))
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBe(128_000)
|
||||
|
||||
controller.abort()
|
||||
await iterator.return?.()
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('uses logged capacity without installing Web routing while scheduling foreign metrics', async () => {
|
||||
const ctx = await hostContext()
|
||||
const api = createApiProxy(ctx, {
|
||||
provider: 'deepseek',
|
||||
model: 'deepseek-chat',
|
||||
cwd: '/tmp',
|
||||
workspaceRoot: '/tmp',
|
||||
})
|
||||
const controller = new AbortController()
|
||||
const iterator = api.events.mux(request({}), controller.signal)[Symbol.asyncIterator]()
|
||||
const initialMetrics = nextMetrics(iterator)
|
||||
const session = ctx.sessions.create()
|
||||
expect((await initialMetrics).contextWindow).toBeUndefined()
|
||||
session.append('request/header', {
|
||||
header: { config: { provider: 'deepseek', model: 'private-preview' } },
|
||||
reason: 'change',
|
||||
})
|
||||
const foreign = {
|
||||
id: session.id,
|
||||
session,
|
||||
status: 'running',
|
||||
ctx,
|
||||
} as Agent
|
||||
const foreignTarget: AgentLlmTargetRef = {
|
||||
current: { provider: 'foreign', model: 'foreign-model' },
|
||||
assembled: undefined,
|
||||
}
|
||||
const disposeForeignTarget = installAgentLlmTarget(foreign.ctx, foreignTarget)
|
||||
const scheduledMetrics = nextMetrics(iterator)
|
||||
ctx.agents.register(foreign)
|
||||
|
||||
expect((await scheduledMetrics).contextWindow).toBeUndefined()
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBe(128_000)
|
||||
expect((await ctx.systemPrompt.assemble()).variables)
|
||||
.toMatchObject({ provider: 'foreign', model: 'foreign-model' })
|
||||
const seed: LlmCallConfig = { provider: 'seed', model: 'seed', temperature: 0.2 }
|
||||
const signal = new AbortController().signal
|
||||
await expect(agentEvents(ctx, foreign).waterfall(
|
||||
'agent/request', 1, 0, signal, () => Promise.resolve(seed),
|
||||
)).resolves.toMatchObject({ provider: 'foreign', model: 'foreign-model' })
|
||||
|
||||
disposeForeignTarget()
|
||||
expect((await ctx.systemPrompt.assemble()).variables).not.toHaveProperty('provider')
|
||||
await expect(agentEvents(ctx, foreign).waterfall(
|
||||
'agent/request', 1, 1, signal, () => Promise.resolve(seed),
|
||||
)).resolves.toBe(seed)
|
||||
|
||||
controller.abort()
|
||||
await iterator.return?.()
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('drops capacity completion from a replaced agent that retains the exact session', async () => {
|
||||
const ctx = await hostContext()
|
||||
const deferred = new DeferredCatalogAdapter()
|
||||
ctx.llm.registerAdapter(['deferred'], deferred)
|
||||
const lifecycle = attachLifecycleSession(ctx, SessionId('capacity-agent-lifecycle'))
|
||||
const retire = attachLifecycleAgent(ctx, lifecycle.session)
|
||||
const api = createApiProxy(ctx, { provider: 'deepseek', model: 'deepseek-chat', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const controller = new AbortController()
|
||||
const iterator = api.events.mux(request({}), controller.signal)[Symbol.asyncIterator]()
|
||||
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
await vi.waitFor(() => { expect(deferred.pending).toHaveLength(1) })
|
||||
retire()
|
||||
const detachLive = attachLifecycleAgent(ctx, lifecycle.session)
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
await vi.waitFor(() => { expect(deferred.pending).toHaveLength(2) })
|
||||
|
||||
deferred.resolve(0, 64_000)
|
||||
await settleCapacityCompletion()
|
||||
deferred.resolve(1, 128_000)
|
||||
await settleCapacityCompletion()
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBe(128_000)
|
||||
|
||||
controller.abort()
|
||||
await iterator.return?.()
|
||||
detachLive()
|
||||
lifecycle.detach()
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('drops capacity completion from a replaced session while its old agent remains live', async () => {
|
||||
const ctx = await hostContext()
|
||||
const deferred = new DeferredCatalogAdapter()
|
||||
ctx.llm.registerAdapter(['deferred'], deferred)
|
||||
const sessionId = SessionId('capacity-session-lifecycle')
|
||||
const retiredSession = attachLifecycleSession(ctx, sessionId)
|
||||
const retireAgent = attachLifecycleAgent(ctx, retiredSession.session)
|
||||
const api = createApiProxy(ctx, { provider: 'deepseek', model: 'deepseek-chat', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const controller = new AbortController()
|
||||
const iterator = api.events.mux(request({}), controller.signal)[Symbol.asyncIterator]()
|
||||
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
await vi.waitFor(() => { expect(deferred.pending).toHaveLength(1) })
|
||||
retiredSession.detach()
|
||||
const liveSession = attachLifecycleSession(ctx, sessionId, true)
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
deferred.resolve(0, 64_000)
|
||||
await settleCapacityCompletion()
|
||||
retireAgent()
|
||||
const detachLiveAgent = attachLifecycleAgent(ctx, liveSession.session)
|
||||
const scheduled = await nextMetrics(iterator)
|
||||
expect(scheduled.logRevision).toBe(2)
|
||||
expect(scheduled.contextWindow).toBeUndefined()
|
||||
await vi.waitFor(() => { expect(deferred.pending).toHaveLength(2) })
|
||||
deferred.resolve(1, 128_000)
|
||||
await settleCapacityCompletion()
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBe(128_000)
|
||||
|
||||
controller.abort()
|
||||
await iterator.return?.()
|
||||
detachLiveAgent()
|
||||
liveSession.detach()
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('does not project retired agent capacity into replacement session snapshots', async () => {
|
||||
const ctx = await hostContext()
|
||||
const deferred = new DeferredCatalogAdapter()
|
||||
ctx.llm.registerAdapter(['deferred'], deferred)
|
||||
const sessionId = SessionId('capacity-snapshot-lifecycle')
|
||||
const retiredSession = attachLifecycleSession(ctx, sessionId)
|
||||
const retireAgent = attachLifecycleAgent(ctx, retiredSession.session)
|
||||
const api = createApiProxy(ctx, { provider: 'deepseek', model: 'deepseek-chat', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const primaryController = new AbortController()
|
||||
const primary = api.events.mux(request({}), primaryController.signal)[Symbol.asyncIterator]()
|
||||
|
||||
expect((await nextMetrics(primary)).contextWindow).toBeUndefined()
|
||||
await vi.waitFor(() => { expect(deferred.pending).toHaveLength(1) })
|
||||
deferred.resolve(0, 64_000)
|
||||
await settleCapacityCompletion()
|
||||
expect((await nextMetrics(primary)).contextWindow).toBe(64_000)
|
||||
|
||||
retiredSession.detach()
|
||||
const replacement = attachLifecycleSession(ctx, sessionId)
|
||||
const createdBaseline = await nextMetrics(primary)
|
||||
replacement.session.append('user/message', {
|
||||
content: [{ type: 'text', text: 'replacement marker' }],
|
||||
source: { kind: 'plugin', plugin: 'test' },
|
||||
}, { surfaceOp: 'append' })
|
||||
const scheduledFlush = await nextMetrics(primary)
|
||||
const reconnectController = new AbortController()
|
||||
const reconnect = api.events.mux(request({}), reconnectController.signal)[Symbol.asyncIterator]()
|
||||
const reconnectBaseline = await nextMetrics(reconnect)
|
||||
expect(createdBaseline.logRevision).toBe(1)
|
||||
for (const metrics of [scheduledFlush, reconnectBaseline]) {
|
||||
expect(metrics.logRevision).toBe(2)
|
||||
}
|
||||
expect({
|
||||
created: createdBaseline.contextWindow,
|
||||
scheduled: scheduledFlush.contextWindow,
|
||||
reconnect: reconnectBaseline.contextWindow,
|
||||
}).toEqual({ created: undefined, scheduled: undefined, reconnect: undefined })
|
||||
|
||||
retireAgent()
|
||||
const detachReplacementAgent = attachLifecycleAgent(ctx, replacement.session)
|
||||
expect((await nextMetrics(primary)).contextWindow).toBeUndefined()
|
||||
await vi.waitFor(() => { expect(deferred.pending).toHaveLength(2) })
|
||||
deferred.resolve(1, 128_000)
|
||||
await settleCapacityCompletion()
|
||||
expect((await nextMetrics(primary)).contextWindow).toBe(128_000)
|
||||
|
||||
primaryController.abort()
|
||||
reconnectController.abort()
|
||||
await primary.return?.()
|
||||
await reconnect.return?.()
|
||||
detachReplacementAgent()
|
||||
replacement.detach()
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('refreshes same-route capacity after adapter owner replacement', async () => {
|
||||
const ctx = await hostContext()
|
||||
const retiredAdapter = new DeferredCatalogAdapter()
|
||||
const retiredFiber = await installDeferredAdapter(ctx, retiredAdapter)
|
||||
const lifecycle = attachLifecycleSession(ctx, SessionId('capacity-adapter-lifecycle'))
|
||||
const detachAgent = attachLifecycleAgent(ctx, lifecycle.session)
|
||||
const api = createApiProxy(ctx, { provider: 'deepseek', model: 'deepseek-chat', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const controller = new AbortController()
|
||||
const iterator = api.events.mux(request({}), controller.signal)[Symbol.asyncIterator]()
|
||||
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
await vi.waitFor(() => { expect(retiredAdapter.pending).toHaveLength(1) })
|
||||
retiredAdapter.resolve(0, 64_000)
|
||||
await settleCapacityCompletion()
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBe(64_000)
|
||||
|
||||
await retiredFiber.dispose()
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
const replacementAdapter = new DeferredCatalogAdapter()
|
||||
const replacementFiber = await installDeferredAdapter(ctx, replacementAdapter)
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
await vi.waitFor(() => { expect(replacementAdapter.pending).toHaveLength(1) })
|
||||
replacementAdapter.resolve(0, 128_000)
|
||||
await settleCapacityCompletion()
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBe(128_000)
|
||||
expect(lifecycle.session.requestHeader()?.config).toMatchObject({
|
||||
provider: 'deferred',
|
||||
model: 'lifecycle-model',
|
||||
})
|
||||
|
||||
controller.abort()
|
||||
await iterator.return?.()
|
||||
detachAgent()
|
||||
lifecycle.detach()
|
||||
await replacementFiber.dispose()
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('aborts pending capacity during adapter UNLOADING and refreshes after settlement', async () => {
|
||||
const ctx = await hostContext()
|
||||
const retiredAdapter = new DeferredCatalogAdapter()
|
||||
const releaseUnload = Promise.withResolvers<undefined>()
|
||||
const releaseCancellationWait = Promise.withResolvers<undefined>()
|
||||
const abortObserved = Promise.withResolvers<undefined>()
|
||||
const retiredFiber = await ctx.plugin(Object.assign((inner: Context) => {
|
||||
inner.llm.registerAdapter(['deferred'], retiredAdapter)
|
||||
inner.effect(
|
||||
() => () => releaseUnload.promise,
|
||||
'test: hold adapter unload',
|
||||
)
|
||||
inner.effect(() => () => {
|
||||
const signal = retiredAdapter.pending[0]?.signal
|
||||
if (signal === undefined) throw new Error('pending capacity signal missing')
|
||||
const cancellation = new Promise<void>((resolve) => {
|
||||
const finish = () => {
|
||||
abortObserved.resolve(undefined)
|
||||
resolve()
|
||||
}
|
||||
if (signal.aborted) finish()
|
||||
else signal.addEventListener('abort', finish, { once: true })
|
||||
})
|
||||
return Promise.race([cancellation, releaseCancellationWait.promise])
|
||||
}, 'test: await capacity cancellation')
|
||||
}, { inject: ['llm'] }))
|
||||
const lifecycle = attachLifecycleSession(ctx, SessionId('capacity-adapter-unloading'))
|
||||
const detachAgent = attachLifecycleAgent(ctx, lifecycle.session)
|
||||
const api = createApiProxy(ctx, {
|
||||
provider: 'deepseek',
|
||||
model: 'deepseek-chat',
|
||||
cwd: '/tmp',
|
||||
workspaceRoot: '/tmp',
|
||||
})
|
||||
const controller = new AbortController()
|
||||
const iterator = api.events.mux(request({}), controller.signal)[Symbol.asyncIterator]()
|
||||
const resolveModelInfo = vi.spyOn(ctx.llm, 'resolveModelInfo')
|
||||
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
await vi.waitFor(() => { expect(retiredAdapter.pending).toHaveLength(1) })
|
||||
expect(resolveModelInfo).toHaveBeenCalledOnce()
|
||||
const listSessions = vi.spyOn(ctx.sessions, 'list')
|
||||
listSessions.mockClear()
|
||||
const pendingFrame = iterator.next()
|
||||
const disposing = retiredFiber.dispose()
|
||||
try {
|
||||
await vi.waitFor(() => {
|
||||
expect(retiredAdapter.pending[0]?.signal?.aborted).toBe(true)
|
||||
})
|
||||
await abortObserved.promise
|
||||
expect(retiredFiber.state).toBe(FiberState.UNLOADING)
|
||||
retiredAdapter.resolve(0, 64_000)
|
||||
await settleCapacityCompletion()
|
||||
expect(resolveModelInfo).toHaveBeenCalledOnce()
|
||||
expect(listSessions).not.toHaveBeenCalled()
|
||||
const outcome = await Promise.race([
|
||||
pendingFrame.then(() => 'frame' as const),
|
||||
new Promise<'idle'>((resolve) => { setImmediate(() => { resolve('idle') }) }),
|
||||
])
|
||||
expect(outcome).toBe('idle')
|
||||
} finally {
|
||||
releaseCancellationWait.resolve(undefined)
|
||||
releaseUnload.resolve(undefined)
|
||||
await disposing
|
||||
}
|
||||
|
||||
expect(retiredFiber.state).toBe(FiberState.DISPOSED)
|
||||
const settledFrame = await pendingFrame
|
||||
if (settledFrame.done || settledFrame.value.payload.type !== 'session/metrics') {
|
||||
throw new Error('expected settled metrics refresh')
|
||||
}
|
||||
expect(settledFrame.value.payload.metrics.contextWindow).toBeUndefined()
|
||||
await settleCapacityCompletion()
|
||||
expect(resolveModelInfo).toHaveBeenCalledTimes(2)
|
||||
|
||||
const replacementAdapter = new DeferredCatalogAdapter()
|
||||
const replacementFiber = await installDeferredAdapter(ctx, replacementAdapter)
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
await vi.waitFor(() => { expect(replacementAdapter.pending).toHaveLength(1) })
|
||||
expect(resolveModelInfo).toHaveBeenCalledTimes(3)
|
||||
replacementAdapter.resolve(0, 128_000)
|
||||
await settleCapacityCompletion()
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBe(128_000)
|
||||
|
||||
controller.abort()
|
||||
await iterator.return?.()
|
||||
detachAgent()
|
||||
lifecycle.detach()
|
||||
await replacementFiber.dispose()
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('aborts pending capacity when the API proxy fiber is disposed', async () => {
|
||||
const ctx = await hostContext()
|
||||
const deferred = new DeferredCatalogAdapter()
|
||||
ctx.llm.registerAdapter(['deferred'], deferred)
|
||||
const lifecycle = attachLifecycleSession(ctx, SessionId('capacity-api-proxy-teardown'))
|
||||
const detachAgent = attachLifecycleAgent(ctx, lifecycle.session)
|
||||
const proxy = Promise.withResolvers<ReturnType<typeof createApiProxy>>()
|
||||
const proxyFiber = await ctx.plugin(Object.assign((inner: Context) => {
|
||||
proxy.resolve(createApiProxy(inner, {
|
||||
provider: 'deepseek',
|
||||
model: 'deepseek-chat',
|
||||
cwd: '/tmp',
|
||||
workspaceRoot: '/tmp',
|
||||
}))
|
||||
}, { inject: ['agents', 'sessions', 'userInteraction'] }))
|
||||
const api = await proxy.promise
|
||||
const controller = new AbortController()
|
||||
const iterator = api.events.mux(request({}), controller.signal)[Symbol.asyncIterator]()
|
||||
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
await vi.waitFor(() => { expect(deferred.pending).toHaveLength(1) })
|
||||
expect(deferred.pending[0]?.signal?.aborted).toBe(false)
|
||||
|
||||
await proxyFiber.dispose()
|
||||
expect(deferred.pending[0]?.signal?.aborted).toBe(true)
|
||||
deferred.resolve(0, 64_000)
|
||||
await settleCapacityCompletion()
|
||||
const pendingFrame = iterator.next()
|
||||
const outcome = await Promise.race([
|
||||
pendingFrame.then(() => 'frame' as const),
|
||||
new Promise<'idle'>((resolve) => { setImmediate(() => { resolve('idle') }) }),
|
||||
])
|
||||
expect(outcome).toBe('idle')
|
||||
|
||||
controller.abort()
|
||||
await expect(pendingFrame).resolves.toMatchObject({ done: true })
|
||||
await iterator.return?.()
|
||||
detachAgent()
|
||||
lifecycle.detach()
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('does not read the sessions service after its disposal status', async () => {
|
||||
let sessionsFiber: Fiber | undefined
|
||||
const ctx = await hostContext((fiber) => { sessionsFiber = fiber })
|
||||
if (sessionsFiber === undefined) throw new Error('sessions fiber missing')
|
||||
createApiProxy(ctx, { provider: 'deepseek', model: 'deepseek-chat', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const sessions = ctx.get('sessions')
|
||||
if (sessions === undefined) throw new Error('sessions service missing')
|
||||
const list = vi.spyOn(sessions, 'list').mockImplementation(() => {
|
||||
throw new Error('disposed sessions service read')
|
||||
})
|
||||
|
||||
await expect(sessionsFiber.dispose()).resolves.toBeUndefined()
|
||||
expect(list).not.toHaveBeenCalled()
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('invalidates pending capacity before SessionStore teardown can reach its callback', async () => {
|
||||
let sessionsFiber: Fiber | undefined
|
||||
const ctx = await hostContext((fiber) => { sessionsFiber = fiber })
|
||||
if (sessionsFiber === undefined) throw new Error('sessions fiber missing')
|
||||
const deferred = new DeferredCatalogAdapter()
|
||||
ctx.llm.registerAdapter(['deferred'], deferred)
|
||||
const lifecycle = attachLifecycleSession(ctx, SessionId('capacity-session-store-teardown'))
|
||||
const detachAgent = attachLifecycleAgent(ctx, lifecycle.session)
|
||||
const api = createApiProxy(ctx, { provider: 'deepseek', model: 'deepseek-chat', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const controller = new AbortController()
|
||||
const iterator = api.events.mux(request({}), controller.signal)[Symbol.asyncIterator]()
|
||||
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
await vi.waitFor(() => { expect(deferred.pending).toHaveLength(1) })
|
||||
const agents = ctx.get('agents')
|
||||
if (agents === undefined) throw new Error('agent registry missing')
|
||||
expect(agents.get(lifecycle.session.id)).toBeDefined()
|
||||
const getAgent = vi.spyOn(agents, 'get')
|
||||
|
||||
await sessionsFiber.dispose()
|
||||
getAgent.mockClear()
|
||||
deferred.resolve(0, 64_000)
|
||||
await settleCapacityCompletion()
|
||||
expect(getAgent).not.toHaveBeenCalled()
|
||||
|
||||
const pendingFrame = iterator.next()
|
||||
const outcome = await Promise.race([
|
||||
pendingFrame.then(() => 'frame' as const),
|
||||
new Promise<'idle'>((resolve) => { setImmediate(() => { resolve('idle') }) }),
|
||||
])
|
||||
expect(outcome).toBe('idle')
|
||||
|
||||
controller.abort()
|
||||
await expect(pendingFrame).resolves.toMatchObject({ done: true })
|
||||
await iterator.return?.()
|
||||
detachAgent()
|
||||
lifecycle.detach()
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('publishes unknown metrics after AgentRegistry terminal disposal with mux active', async () => {
|
||||
let agentsFiber: Fiber | undefined
|
||||
const ctx = await hostContext(undefined, (fiber) => { agentsFiber = fiber })
|
||||
if (agentsFiber === undefined) throw new Error('agent registry fiber missing')
|
||||
const deferred = new DeferredCatalogAdapter()
|
||||
ctx.llm.registerAdapter(['deferred'], deferred)
|
||||
const lifecycle = attachLifecycleSession(ctx, SessionId('capacity-agent-registry-disposed'))
|
||||
const detachAgent = attachLifecycleAgent(ctx, lifecycle.session)
|
||||
const api = createApiProxy(ctx, { provider: 'deepseek', model: 'deepseek-chat', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const controller = new AbortController()
|
||||
const iterator = api.events.mux(request({}), controller.signal)[Symbol.asyncIterator]()
|
||||
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
await vi.waitFor(() => { expect(deferred.pending).toHaveLength(1) })
|
||||
deferred.resolve(0, 64_000)
|
||||
await settleCapacityCompletion()
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBe(64_000)
|
||||
|
||||
await agentsFiber.dispose()
|
||||
const refresh = nextMetrics(iterator).then(
|
||||
metrics => ({ kind: 'metrics' as const, metrics }),
|
||||
() => ({ kind: 'error' as const }),
|
||||
)
|
||||
const outcome = await Promise.race([
|
||||
refresh,
|
||||
new Promise<{ kind: 'idle' }>((resolve) => {
|
||||
setImmediate(() => { resolve({ kind: 'idle' }) })
|
||||
}),
|
||||
])
|
||||
|
||||
controller.abort()
|
||||
await refresh
|
||||
await iterator.return?.()
|
||||
detachAgent()
|
||||
lifecycle.detach()
|
||||
await ctx.fiber.dispose()
|
||||
expect(outcome.kind).toBe('metrics')
|
||||
if (outcome.kind === 'metrics') {
|
||||
expect(outcome.metrics.contextWindow).toBeUndefined()
|
||||
expect(outcome.metrics.logRevision).toBe(1)
|
||||
}
|
||||
})
|
||||
|
||||
it.each(['agents', 'sessions'] as const)(
|
||||
'drops capacity completion while %s is unavailable during unload',
|
||||
async (serviceName) => {
|
||||
let sessionsFiber: Fiber | undefined
|
||||
let agentsFiber: Fiber | undefined
|
||||
const ctx = await hostContext(
|
||||
(fiber) => { sessionsFiber = fiber },
|
||||
(fiber) => { agentsFiber = fiber },
|
||||
)
|
||||
const heldFiber = serviceName === 'sessions' ? sessionsFiber : agentsFiber
|
||||
if (heldFiber === undefined) throw new Error(`${serviceName} fiber missing`)
|
||||
const unloadStarted = Promise.withResolvers<undefined>()
|
||||
const releaseUnload = Promise.withResolvers<undefined>()
|
||||
heldFiber.ctx.effect(() => () => {
|
||||
unloadStarted.resolve(undefined)
|
||||
return releaseUnload.promise
|
||||
}, `test: hold ${serviceName} unload`)
|
||||
const deferred = new DeferredCatalogAdapter()
|
||||
ctx.llm.registerAdapter(['deferred'], deferred)
|
||||
const lifecycle = attachLifecycleSession(ctx, SessionId(`capacity-${serviceName}-unloading`))
|
||||
const detachAgent = attachLifecycleAgent(ctx, lifecycle.session)
|
||||
const api = createApiProxy(ctx, { provider: 'deepseek', model: 'deepseek-chat', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const controller = new AbortController()
|
||||
const iterator = api.events.mux(request({}), controller.signal)[Symbol.asyncIterator]()
|
||||
|
||||
expect((await nextMetrics(iterator)).contextWindow).toBeUndefined()
|
||||
await vi.waitFor(() => { expect(deferred.pending).toHaveLength(1) })
|
||||
const agents = ctx.get('agents')
|
||||
if (agents === undefined) throw new Error('agent registry missing')
|
||||
const sessions = ctx.get('sessions')
|
||||
if (sessions === undefined) throw new Error('sessions service missing')
|
||||
const getAgent = vi.spyOn(agents, 'get')
|
||||
const getSession = vi.spyOn(sessions, 'get')
|
||||
const disposing = heldFiber.dispose()
|
||||
await unloadStarted.promise
|
||||
await vi.waitFor(() => { expect(ctx.get(serviceName)).toBeUndefined() })
|
||||
expect(heldFiber.state).toBe(FiberState.UNLOADING)
|
||||
|
||||
getAgent.mockClear()
|
||||
getSession.mockClear()
|
||||
deferred.resolve(0, 64_000)
|
||||
await settleCapacityCompletion()
|
||||
const agentReads = getAgent.mock.calls.length
|
||||
const sessionReads = getSession.mock.calls.length
|
||||
const pendingFrame = iterator.next()
|
||||
const outcome = await Promise.race([
|
||||
pendingFrame.then(() => 'frame' as const),
|
||||
new Promise<'idle'>((resolve) => { setImmediate(() => { resolve('idle') }) }),
|
||||
])
|
||||
|
||||
controller.abort()
|
||||
await expect(pendingFrame).resolves.toMatchObject({ done: true })
|
||||
await iterator.return?.()
|
||||
releaseUnload.resolve(undefined)
|
||||
await disposing
|
||||
detachAgent()
|
||||
lifecycle.detach()
|
||||
await ctx.fiber.dispose()
|
||||
expect(agentReads).toBe(0)
|
||||
expect(sessionReads).toBe(0)
|
||||
expect(outcome).toBe('idle')
|
||||
},
|
||||
)
|
||||
})
|
||||
|
||||
Reference in New Issue
Block a user