Merge latest origin/master into compact-post-step-overflow-recovery
# Conflicts: # docs/agent-lifecycle.md # docs/architecture.md # docs/cookbook/extension-cookbook.i18n.yaml # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # docs/rfc/INDEX.md # docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md # docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md # docs/rfc/implemented/feature/2026-07-07-session-prefix.md # packages/compact/compact-basic/README.md # packages/compact/compact-basic/src/config.ts # packages/compact/compact-basic/src/index.ts # packages/compact/compact-basic/src/summarizer.ts # packages/compact/compact-basic/tests/compact-basic.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/compact/compact/README.md # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/src/loop.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-pi-ai/README.md # packages/llm/llm-pi-ai/src/stream.ts # packages/llm/llm-pi-ai/tests/convert.spec.ts # packages/llm/llm/README.md # packages/llm/llm/src/index.ts # packages/llm/llm/tests/service.spec.ts # scripts/gen-doc-graphs.ts
This commit is contained in:
Tianyi Cui
@@ -1,18 +1,17 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import { toolPairingBalancedAfter, toolPairingBalancedBefore } from '@deepseek-ai/dsh-compact'
|
||||
import LlmService, { CONTEXT_WINDOW_EXCEEDED_CODE, LlmError } from '@deepseek-ai/dsh-llm'
|
||||
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 SessionStore from '@deepseek-ai/dsh-session'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
|
||||
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
|
||||
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
|
||||
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 type { SurfaceEvent } from '@deepseek-ai/dsh-session'
|
||||
import { SessionId, type SurfaceEvent } from '@deepseek-ai/dsh-session'
|
||||
|
||||
/**
|
||||
* CBR-001 regression through the real loop. A replacement checkpoint has a high
|
||||
@@ -22,8 +21,12 @@ import type { SurfaceEvent } from '@deepseek-ai/dsh-session'
|
||||
*/
|
||||
|
||||
class ReproCompactService extends BasicCompactService {
|
||||
override async summarize(): Promise<{ summary: ContentBlock[]; model: string }> {
|
||||
return { summary: [{ type: 'text', text: 'CHECKPOINT SUMMARY' }], model: 'stub' }
|
||||
override async summarize(): Promise<{ summary: ContentBlock[]; provider: string; model: string }> {
|
||||
return {
|
||||
summary: [{ type: 'text', text: 'CHECKPOINT SUMMARY' }],
|
||||
provider: 'mock',
|
||||
model: 'stub',
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -74,7 +77,7 @@ class OverflowRecoveryAdapter extends LlmAdapter {
|
||||
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, 400)
|
||||
throw new LlmError('request too large for model context', CONTEXT_WINDOW_EXCEEDED_CODE)
|
||||
}
|
||||
yield {
|
||||
type: 'finish',
|
||||
@@ -94,12 +97,8 @@ class OverflowRecoveryAdapter extends LlmAdapter {
|
||||
|
||||
async function harness(toolSteps: number): Promise<{ ctx: Context; compact: ReproCompactService }> {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await mountAgentLoopTestDependencies(ctx)
|
||||
await ctx.plugin(Invariants)
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
await ctx.plugin(TokenMeterService, { contextWindow: 400 })
|
||||
ctx.llm.registerAdapter(['mock'], new StepwiseToolAdapter(toolSteps))
|
||||
@@ -124,7 +123,7 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr
|
||||
return { ctx, compact }
|
||||
}
|
||||
|
||||
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
|
||||
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') {
|
||||
@@ -138,9 +137,10 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
|
||||
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, model: 'mock' }))
|
||||
ctx.on('agent/request', async (_agent, _turn, _step, config) => ({ ...config, provider: 'mock', model: 'mock' }))
|
||||
try {
|
||||
const agent = ctx.agentLoop.create(AgentId('routed-pressure'), {
|
||||
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' }])
|
||||
@@ -160,7 +160,7 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', ()
|
||||
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(AgentId('post-step-order'), { model: 'mock' })
|
||||
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)
|
||||
|
||||
@@ -186,7 +186,7 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', ()
|
||||
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(AgentId('repro'), { model: 'mock' })
|
||||
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)
|
||||
|
||||
@@ -203,12 +203,12 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', ()
|
||||
// its start and end cuts are balanced in surface order.
|
||||
const nodes = agent.session.surface.nodes
|
||||
for (const cp of checkpoints) {
|
||||
const node = nodes.find(n => n.seq === cp.seq)
|
||||
if (!node) continue // shadowed by a later checkpoint — no longer an edge.
|
||||
expect(toolPairingBalancedBefore(agent.session, node),
|
||||
`checkpoint seq ${node.seq} must be a balanced region START`).toBe(true)
|
||||
expect(toolPairingBalancedAfter(agent.session, node),
|
||||
`checkpoint seq ${node.seq} must be a balanced region END`).toBe(true)
|
||||
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 ${cp.seq} must be a balanced region END`).toBe(true)
|
||||
}
|
||||
} finally {
|
||||
await ctx.fiber.dispose()
|
||||
@@ -222,16 +222,12 @@ describe('context-overflow recovery across the real loop and compact-basic', ()
|
||||
async (delivery) => {
|
||||
const ctx = new Context()
|
||||
const adapter = new OverflowRecoveryAdapter(delivery)
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await mountAgentLoopTestDependencies(ctx)
|
||||
await ctx.plugin(Invariants)
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
await ctx.plugin(TokenMeterService, { contextWindow: 128 })
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
ctx.on('agent/request', async (_agent, _turn, _step, config) => ({ ...config, model: 'mock' }))
|
||||
ctx.on('agent/request', async (_agent, _turn, _step, config) => ({ ...config, provider: 'mock', model: 'mock' }))
|
||||
await ctx.plugin(BasicCompactService, {
|
||||
thresholdRatio: 1,
|
||||
retainTokens: 100,
|
||||
@@ -241,7 +237,8 @@ describe('context-overflow recovery across the real loop and compact-basic', ()
|
||||
})
|
||||
|
||||
try {
|
||||
const agent = ctx.agentLoop.create(AgentId(`overflow-${delivery}`), {
|
||||
const agent = ctx.agentLoop.create(SessionId(`overflow-${delivery}`), {
|
||||
provider: 'unconfigured-agent-fallback',
|
||||
model: 'unconfigured-agent-fallback',
|
||||
})
|
||||
for (let turn = 1; turn <= 2; turn += 1) {
|
||||
@@ -256,6 +253,7 @@ describe('context-overflow recovery across the real loop and compact-basic', ()
|
||||
}, { 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)}` }],
|
||||
|
||||
Reference in New Issue
Block a user