| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358 |
- import { describe, expect, it } from 'vitest'
- import { Context } from 'cordis'
- import { toolPairingBalancedAfter, toolPairingBalancedBefore } from '@deepseek-ai/dsh-compact'
- import { CONTEXT_WINDOW_EXCEEDED_CODE, LlmError } from '@deepseek-ai/dsh-llm'
- import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
- import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
- import { defineTool } from '@deepseek-ai/dsh-tools'
- import type { Agent } from '@deepseek-ai/dsh-agent'
- import AgentLoop from '@deepseek-ai/dsh-agent-loop'
- import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
- import * as Invariants from '@deepseek-ai/dsh-invariants'
- import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
- import TokenMeterService from '@deepseek-ai/dsh-token-meter'
- import * as LlmRetry from '@deepseek-ai/dsh-llm-retry'
- import { SessionId, type SurfaceEvent } from '@deepseek-ai/dsh-session'
- /**
- * CBR-001 regression through the real loop. A replacement checkpoint has a high
- * log seq at the surface head and carries no tool pair, so both adjacent cuts
- * must be safe and re-compacting that checkpoint alone must succeed. This pins
- * surface-position semantics rather than raw-log scanning.
- */
- class ReproCompactService extends BasicCompactService {
- override async summarize(): Promise<{ summary: ContentBlock[]; provider: string; model: string }> {
- return {
- summary: [{ type: 'text', text: 'CHECKPOINT SUMMARY' }],
- provider: 'mock',
- model: 'stub',
- }
- }
- }
- /** Each call emits one tool-call until exhausted, then a final text answer. */
- class StepwiseToolAdapter extends LlmAdapter {
- calls = 0
- constructor(private toolSteps: number) {
- super()
- }
- async * stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
- const n = this.calls
- this.calls += 1
- if (n < this.toolSteps) {
- const id = CallId(`c${n}`)
- const args = `{"i":${n}}`
- yield { type: 'block-start', index: 0, blockType: 'text' }
- yield { type: 'block-end', index: 0, block: { type: 'text', text: `step ${n}` } }
- yield { type: 'block-start', index: 1, blockType: 'tool-call' }
- yield { type: 'block-end', index: 1, block: { type: 'tool-call', id, name: 'work', arguments: args } }
- yield { type: 'finish', reason: { kind: 'tool-calls' } }
- return
- }
- yield { type: 'block-start', index: 0, blockType: 'text' }
- yield { type: 'block-end', index: 0, block: { type: 'text', text: 'all done' } }
- yield { type: 'finish', reason: { kind: 'stop' } }
- }
- }
- /** First conversation request overflows, then the rebuilt retry succeeds. */
- class OverflowRecoveryAdapter extends LlmAdapter {
- readonly conversationRequests: GenerateOptions[] = []
- readonly summaryRequests: GenerateOptions[] = []
- constructor(
- private readonly delivery: 'thrown' | 'in-band',
- private readonly transientAfterOverflow = false,
- ) {
- super()
- }
- override async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
- if (options.system?.includes('You are a compaction engine')) {
- this.summaryRequests.push(options)
- yield { type: 'block-start', index: 0, blockType: 'text' }
- yield { type: 'block-end', index: 0, block: { type: 'text', text: 'RECOVERY CHECKPOINT' } }
- yield { type: 'finish', reason: { kind: 'stop' } }
- return
- }
- this.conversationRequests.push(options)
- if (this.conversationRequests.length === 1) {
- if (this.delivery === 'thrown') {
- throw new LlmError('request too large for model context', CONTEXT_WINDOW_EXCEEDED_CODE)
- }
- yield {
- type: 'finish',
- reason: {
- kind: 'error',
- failure: {
- message: 'request too large for model context',
- code: CONTEXT_WINDOW_EXCEEDED_CODE,
- },
- },
- }
- return
- }
- if (this.transientAfterOverflow && this.conversationRequests.length === 2) {
- throw new LlmError('temporary provider outage', 'SERVER')
- }
- yield { type: 'block-start', index: 0, blockType: 'text' }
- yield { type: 'block-end', index: 0, block: { type: 'text', text: 'recovered' } }
- yield { type: 'finish', reason: { kind: 'stop' } }
- }
- }
- async function harness(toolSteps: number): Promise<{ ctx: Context; compact: ReproCompactService }> {
- const ctx = new Context()
- await mountAgentLoopTestDependencies(ctx)
- await ctx.plugin(Invariants)
- await ctx.plugin(AgentLoop, { agents: [] })
- await ctx.plugin(TokenMeterService, { contextWindow: 400 })
- ctx.llm.registerAdapter(['mock'], new StepwiseToolAdapter(toolSteps))
- ctx.tools.register(defineTool({
- name: 'work',
- description: 'does work',
- parameters: { i: { type: 'number' } },
- async execute() {
- return [{ type: 'text', text: 'work result' }]
- },
- }))
- // Small window so several tool steps cross the threshold and compaction
- // fires within the runaway turn after enough history can shrink.
- const compact = new ReproCompactService(ctx, {
- auto: true,
- thresholdRatio: 0.5,
- retainTokens: 50,
- summarizationModel: '',
- maxTokens: 8192,
- compactionRetries: 1,
- })
- return { ctx, compact }
- }
- function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
- return new Promise((resolve) => {
- const dispose = ctx.on('agent/status', (subject, status) => {
- if (subject === agent && status === 'idle') {
- dispose()
- resolve()
- }
- })
- })
- }
- function seedOverflowHistory(agent: Agent): void {
- for (let turn = 1; turn <= 2; turn += 1) {
- const sentinel = turn === 1 ? 'OLD HISTORY SENTINEL' : 'RECENT HISTORY'
- agent.session.append('turn/start', {
- turn,
- trigger: { kind: 'message', source: { kind: 'user' } },
- })
- agent.session.append('user/message', {
- content: [{ type: 'text', text: `${sentinel} ${'old context '.repeat(200)}` }],
- source: { kind: 'user' },
- }, { surfaceOp: 'append' })
- agent.session.append('step/start', { turn, step: 1 })
- agent.session.append('assistant/message', {
- provenance: { provider: 'mock', model: 'mock' },
- turn,
- step: 1,
- content: [{ type: 'text', text: `historical response ${turn} ${'detail '.repeat(200)}` }],
- }, { surfaceOp: 'append' })
- agent.session.append('step/end', { turn, step: 1 })
- agent.session.append('turn/end', { turn, reason: { kind: 'completed' } })
- }
- }
- describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () => {
- it('uses the model actually routed by agent/request for post-step pressure', async () => {
- const { ctx } = await harness(8)
- ctx.on('agent/request', async (_agent, _turn, _step, config) => ({ ...config, provider: 'mock', model: 'mock' }))
- try {
- const agent = ctx.agentLoop.create(SessionId('routed-pressure'), {
- provider: 'unconfigured-agent-fallback',
- model: 'unconfigured-agent-fallback',
- })
- agent.send([{ type: 'text', text: 'do a routed multi-step task' }])
- await waitForIdle(ctx, agent)
- expect(agent.session.requestHeader()?.config.model).toBe('mock')
- expect(agent.session.events.some(event => event.type === 'compact/summary')).toBe(true)
- expect(agent.session.events.at(-1)).toMatchObject({
- type: 'turn/end',
- data: { reason: { kind: 'completed' } },
- })
- } finally {
- await ctx.fiber.dispose()
- }
- })
- it('runs automatic pressure after the current tool result and before step/end', async () => {
- const { ctx } = await harness(8)
- try {
- const agent = ctx.agentLoop.create(SessionId('post-step-order'), { provider: 'mock', model: 'mock' })
- agent.send([{ type: 'text', text: 'do tool work' }])
- await waitForIdle(ctx, agent)
- const events = [...agent.session.events]
- const compactStart = events.find(event => event.type === 'compact/start')
- expect(compactStart).toBeDefined()
- const precedingResult = events.findLast(event =>
- event.type === 'tool/result' && event.seq < compactStart!.seq,
- )
- if (precedingResult?.type !== 'tool/result') throw new Error('expected a durable tool result before compaction')
- const stepEnd = events.find(event =>
- event.type === 'step/end'
- && event.data.step === precedingResult.data.step
- && event.seq > compactStart!.seq,
- )
- expect(precedingResult.seq).toBeLessThan(compactStart!.seq)
- expect(compactStart!.seq).toBeLessThan(stepEnd!.seq)
- } finally {
- await ctx.fiber.dispose()
- }
- })
- it('the head checkpoint the loop lands is a balanced cut on both sides', async () => {
- const { ctx } = await harness(8)
- try {
- const agent = ctx.agentLoop.create(SessionId('repro'), { provider: 'mock', model: 'mock' })
- agent.send([{ type: 'text', text: 'do a long multi-step task' }])
- await waitForIdle(ctx, agent)
- const events = [...agent.session.events]
- // A compaction ran: at least one checkpoint landed on the surface.
- const checkpoints = events.filter(
- (e): e is SurfaceEvent =>
- e.type === 'user/message'
- && typeof (e as SurfaceEvent).surfaceOp === 'object',
- )
- expect(checkpoints.length).toBeGreaterThan(0)
- // High log position does not make a text-only checkpoint mid-step; both
- // its start and end cuts are balanced in surface order.
- const nodes = agent.session.surface.nodes
- for (const cp of checkpoints) {
- const index = nodes.indexOf(cp.seq)
- if (index === -1) continue // shadowed by a later checkpoint — no longer an edge.
- expect(toolPairingBalancedBefore(agent.session, cp.seq),
- `checkpoint seq ${cp.seq} must be a balanced region START`).toBe(true)
- expect(toolPairingBalancedAfter(agent.session, cp.seq),
- `checkpoint seq ${cp.seq} must be a balanced region END`).toBe(true)
- }
- } finally {
- await ctx.fiber.dispose()
- }
- })
- })
- describe('context-overflow recovery across the real loop and compact-basic', () => {
- it.each(['thrown', 'in-band'] as const)(
- 'force-compacts a %s overflow between failed and retry steps',
- async (delivery) => {
- const ctx = new Context()
- const adapter = new OverflowRecoveryAdapter(delivery)
- await mountAgentLoopTestDependencies(ctx)
- await ctx.plugin(Invariants)
- await ctx.plugin(AgentLoop, { agents: [] })
- await ctx.plugin(TokenMeterService, { contextWindow: 128 })
- ctx.llm.registerAdapter(['mock'], adapter)
- ctx.on('agent/request', async (_agent, _turn, _step, config) => ({ ...config, provider: 'mock', model: 'mock' }))
- await ctx.plugin(BasicCompactService, {
- thresholdRatio: 1,
- retainTokens: 100,
- maxTokens: 64,
- compactionRetries: 0,
- maxOverflowRetries: 1,
- })
- try {
- const agent = ctx.agentLoop.create(SessionId(`overflow-${delivery}`), {
- provider: 'unconfigured-agent-fallback',
- model: 'unconfigured-agent-fallback',
- })
- seedOverflowHistory(agent)
- agent.send([{ type: 'text', text: 'continue from history' }])
- await agent.whenIdle()
- expect(adapter.conversationRequests).toHaveLength(2)
- expect(adapter.summaryRequests).toHaveLength(1)
- expect(JSON.stringify(adapter.conversationRequests[0]!.messages)).toContain('OLD HISTORY SENTINEL')
- const retry = JSON.stringify(adapter.conversationRequests[1]!.messages)
- expect(retry).toContain('RECOVERY CHECKPOINT')
- expect(retry).not.toContain('OLD HISTORY SENTINEL')
- const events = [...agent.session.events]
- const failedEnd = events.find(event =>
- event.type === 'step/end' && event.data.turn === 3 && event.data.step === 1,
- )!
- const retryStart = events.find(event =>
- event.type === 'step/start' && event.data.turn === 3 && event.data.step === 2,
- )!
- const compaction = events.filter(event =>
- event.type === 'compact/start'
- || event.type === 'compact/summary'
- || event.type === 'compact/end',
- )
- expect(compaction.map(event => event.type)).toEqual([
- 'compact/start',
- 'compact/summary',
- 'compact/end',
- ])
- expect(compaction.every(event => event.seq > failedEnd.seq && event.seq < retryStart.seq)).toBe(true)
- expect(events.at(-1)).toMatchObject({
- type: 'turn/end',
- data: { reason: { kind: 'completed' } },
- })
- } finally {
- await ctx.fiber.dispose()
- }
- },
- )
- it('keeps context-overflow and transient retry budgets independent in one sequence', async () => {
- const ctx = new Context()
- const adapter = new OverflowRecoveryAdapter('thrown', true)
- await mountAgentLoopTestDependencies(ctx)
- await ctx.plugin(Invariants)
- await ctx.plugin(LlmRetry, {
- maxTransientRetries: 1,
- initialDelayMs: 1,
- maxDelayMs: 1,
- jitterRatio: 0,
- })
- await ctx.plugin(AgentLoop, { agents: [] })
- await ctx.plugin(TokenMeterService, { contextWindow: 128 })
- ctx.llm.registerAdapter(['mock'], adapter)
- await ctx.plugin(BasicCompactService, {
- thresholdRatio: 1,
- retainTokens: 100,
- maxTokens: 64,
- compactionRetries: 0,
- maxOverflowRetries: 1,
- })
- try {
- const agent = ctx.agentLoop.create(SessionId('alternating-recovery'), { provider: 'mock', model: 'mock' })
- seedOverflowHistory(agent)
- agent.send([{ type: 'text', text: 'continue from history' }])
- await agent.whenIdle()
- expect(adapter.conversationRequests).toHaveLength(3)
- expect(adapter.summaryRequests).toHaveLength(1)
- expect(agent.session.events.filter(event => event.type === 'llm/retry').map(event => event.data))
- .toEqual([expect.objectContaining({ step: 2, retry: 1, failure: { message: 'temporary provider outage', code: 'SERVER' } })])
- expect(agent.session.events.filter(event => event.type === 'step/start').slice(-3).map(event => event.data.step))
- .toEqual([1, 2, 3])
- expect(agent.session.events.at(-1)).toMatchObject({
- type: 'turn/end',
- data: { reason: { kind: 'completed' } },
- })
- } finally {
- await ctx.fiber.dispose()
- }
- })
- })
|