mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge remote-tracking branch 'origin/master' into worktree/web-multimodal-image-input
# Conflicts: # docs/architecture.i18n.yaml # docs/architecture.md # docs/architecture.zh.md # docs/config-catalog.md # docs/core-data-structures/core.i18n.yaml # docs/core-data-structures/llm-streaming.i18n.yaml # docs/module-graph.md # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl # packages/README.i18n.yaml # packages/client/connection/src/client/fixture.ts # packages/client/connection/src/index.ts # packages/client/runtime/README.i18n.yaml # packages/client/runtime/README.md # packages/client/runtime/README.zh.md # packages/client/runtime/src/client/sessions/conversation.ts # packages/client/ui-conversation/README.i18n.yaml # packages/client/ui-conversation/src/client/apply.ts # packages/client/ui-conversation/src/client/chat/ChatView.tsx # packages/client/ui-conversation/src/client/chat/MessageItem.tsx # packages/client/ui-conversation/src/client/contract/slots.ts # packages/client/ui-trajectory/tests/views.spec.tsx # packages/compact/compact-basic/README.i18n.yaml # packages/cordis/tool-cordis/src/api-catalog.ts # packages/host/apiproxy/src/api-proxy.ts # packages/host/apiproxy/src/api/index.ts # packages/host/apiproxy/src/api/sessions.ts # packages/host/apiproxy/src/index.ts # packages/host/apiproxy/tests/fetch-carrier.spec.ts # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-deepseek/tests/adapter.spec.ts # packages/llm/llm-deepseek/tests/serialize.spec.ts # packages/llm/llm-pi-ai/README.i18n.yaml # packages/llm/llm-pi-ai/src/adapter.ts # packages/llm/llm-pi-ai/src/index.ts # packages/llm/llm-pi-ai/tests/adapter.spec.ts # packages/llm/llm/src/types.ts # packages/ui/tui/README.i18n.yaml # packages/ui/tui/src/index.ts # packages/ui/tui/tests/tui.spec.ts
This commit is contained in:
Yichen Jiang
@@ -17,13 +17,13 @@ import type {
|
||||
ContentBlock,
|
||||
GenerateOptions,
|
||||
LlmFailure,
|
||||
LlmModelContext,
|
||||
LlmResolvedModelInfo,
|
||||
Message,
|
||||
StreamChunk,
|
||||
} from '@deepseek-ai/dsh-llm'
|
||||
import { Session, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import TokenMeterService from '@deepseek-ai/dsh-token-meter'
|
||||
import { agentEvents, type Agent } from '@deepseek-ai/dsh-agent'
|
||||
import { agentEvents, type Agent, type RequestErrorAction } from '@deepseek-ai/dsh-agent'
|
||||
import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune'
|
||||
|
||||
const SIGNAL = new AbortController().signal
|
||||
@@ -34,8 +34,13 @@ class ContextAdapter extends LlmAdapter {
|
||||
super()
|
||||
}
|
||||
|
||||
override resolveModelContext(): Promise<LlmModelContext> {
|
||||
return Promise.resolve({ contextWindow: this.contextWindow })
|
||||
override resolveModel(provider: string, model: string): Promise<LlmResolvedModelInfo> {
|
||||
return Promise.resolve({
|
||||
provider,
|
||||
id: model,
|
||||
name: model,
|
||||
context: { contextWindow: this.contextWindow },
|
||||
})
|
||||
}
|
||||
|
||||
override async * stream(): AsyncIterable<StreamChunk> {
|
||||
@@ -48,9 +53,14 @@ class RoutedContextAdapter extends LlmAdapter {
|
||||
super()
|
||||
}
|
||||
|
||||
override resolveModelContext(provider: string): Promise<LlmModelContext | undefined> {
|
||||
override resolveModel(provider: string, model: string): Promise<LlmResolvedModelInfo> {
|
||||
const contextWindow = this.windows[provider]
|
||||
return Promise.resolve(contextWindow === undefined ? undefined : { contextWindow })
|
||||
return Promise.resolve({
|
||||
provider,
|
||||
id: model,
|
||||
name: model,
|
||||
...contextWindow === undefined ? {} : { context: { contextWindow } },
|
||||
})
|
||||
}
|
||||
|
||||
override async * stream(): AsyncIterable<StreamChunk> {
|
||||
@@ -67,7 +77,10 @@ function createContext(contextWindow = 1_000): Context {
|
||||
}
|
||||
|
||||
function agent(session: Session, model?: string): Agent {
|
||||
return { session, options: model === undefined ? {} : { provider: model, model } } as Agent
|
||||
return {
|
||||
session,
|
||||
options: model === undefined ? {} : { provider: model, model },
|
||||
} as Agent
|
||||
}
|
||||
|
||||
/** Flatten every text fragment the summarizer received, recursing tool-result blocks. */
|
||||
@@ -454,6 +467,18 @@ describe('pressure measurement and retention', () => {
|
||||
.resolves.not.toBeNull()
|
||||
})
|
||||
|
||||
it('forwards turn cancellation to proactive model metadata resolution', async () => {
|
||||
const ctx = createContext()
|
||||
const resolveModelInfo = vi.spyOn(ctx.llm, 'resolveModelInfo')
|
||||
const compact = service(compactConfig, ctx)
|
||||
const session = conversation()
|
||||
const signal = new AbortController().signal
|
||||
|
||||
await expect(compact.compactIfNeeded(agent(session, MODEL), 'pressure', signal))
|
||||
.resolves.not.toBeNull()
|
||||
expect(resolveModelInfo).toHaveBeenCalledWith(MODEL, MODEL, signal)
|
||||
})
|
||||
|
||||
it('re-resolves capacity after a same-model-id provider switch in one session', async () => {
|
||||
const ctx = new Context()
|
||||
void new LlmService(ctx)
|
||||
@@ -486,7 +511,11 @@ describe('pressure measurement and retention', () => {
|
||||
void new LlmService(ctx)
|
||||
void new TokenMeterService(ctx)
|
||||
ctx.llm.registerAdapter(['unknown-context'], new ContextAdapter(1_000))
|
||||
vi.spyOn(ctx.llm, 'resolveModelContext').mockResolvedValue(undefined)
|
||||
vi.spyOn(ctx.llm, 'resolveModelInfo').mockImplementation((provider, model) => Promise.resolve({
|
||||
provider,
|
||||
id: model,
|
||||
name: model,
|
||||
}))
|
||||
const compact = service(compactConfig, ctx)
|
||||
const session = conversation(4)
|
||||
session.append('request/header', {
|
||||
@@ -543,7 +572,7 @@ describe('pressure measurement and retention', () => {
|
||||
expect(session.surface.nodes.length).toBeLessThan(8)
|
||||
})
|
||||
|
||||
it('counts the durable routed request envelope without putting its prefix on the surface', async () => {
|
||||
it('counts the durable routed request envelope without putting it on the surface', async () => {
|
||||
const compact = service({
|
||||
auto: false,
|
||||
thresholdRatio: 0.9,
|
||||
@@ -552,22 +581,15 @@ describe('pressure measurement and retention', () => {
|
||||
const session = conversation(2, 'x'.repeat(600))
|
||||
expect(await compactIfNeeded(compact, session)).toBeNull()
|
||||
|
||||
const prefix = [{ role: 'user' as const, content: [{ type: 'text' as const, text: 'p'.repeat(600) }] }]
|
||||
session.append('request/header', {
|
||||
header: {
|
||||
config: { provider: MODEL, model: MODEL },
|
||||
system: 's'.repeat(600),
|
||||
messagePrefix: prefix,
|
||||
system: 's'.repeat(2_000),
|
||||
},
|
||||
reason: 'resume',
|
||||
})
|
||||
const result = await compactIfNeeded(compact, session)
|
||||
expect(result).not.toBeNull()
|
||||
expect(prefix).toHaveLength(1)
|
||||
// The routed request prefix must not reach the surface as its own message
|
||||
// (the compaction summary itself is an expected plugin-sourced checkpoint).
|
||||
expect(session.events.some(event => event.type === 'user/message'
|
||||
&& event.data.content.some(block => block.type === 'text' && block.text.includes('p'.repeat(600))))).toBe(false)
|
||||
})
|
||||
|
||||
it('uses the latest logged request envelope without an AgentOptions override', async () => {
|
||||
@@ -797,13 +819,12 @@ describe('compaction region transaction', () => {
|
||||
expect(replay.deriveMessages()).toEqual(session.deriveMessages())
|
||||
})
|
||||
|
||||
it('replays the latest routed header prefix so the summarizer reuses the cache', async () => {
|
||||
it('replays the latest routed header so the summarizer reuses the cache', async () => {
|
||||
const compact = service()
|
||||
const session = conversation(3)
|
||||
const tools = [{ name: 'do_thing', description: 'd', parameters: { type: 'object' } }]
|
||||
const messagePrefix: Message[] = [{ role: 'user', content: [{ type: 'text', text: 'SESSION PREFIX' }] }]
|
||||
session.append('request/header', {
|
||||
header: { config: { provider: MODEL, model: MODEL }, system: 'CONVERSATION SYSTEM', tools, messagePrefix },
|
||||
header: { config: { provider: MODEL, model: MODEL }, system: 'CONVERSATION SYSTEM', tools },
|
||||
reason: 'resume',
|
||||
})
|
||||
const nodes = session.surface.nodes
|
||||
@@ -812,7 +833,6 @@ describe('compaction region transaction', () => {
|
||||
const { input } = compact.calls[0]!
|
||||
expect(input.system).toBe('CONVERSATION SYSTEM')
|
||||
expect(input.tools).toEqual(tools)
|
||||
expect(input.messages[0]).toEqual(messagePrefix[0])
|
||||
expect(summarizedText(input)).toContain('fixture user 1')
|
||||
})
|
||||
|
||||
@@ -1316,22 +1336,21 @@ describe('default one-shot summarizer', () => {
|
||||
|
||||
describe('automatic listener and loader composition', () => {
|
||||
function postStep(ctx: Context, owner: Agent, signal = SIGNAL): Promise<unknown> {
|
||||
return agentEvents(ctx, owner).serial('agent/post-step', 1, 1, signal)
|
||||
return agentEvents(ctx, owner).serial('agent/step', 1, 1, signal)
|
||||
}
|
||||
|
||||
function recover(
|
||||
ctx: Context,
|
||||
owner: Agent,
|
||||
error: Error & { code?: string },
|
||||
retryAttempt = 0,
|
||||
signal = SIGNAL,
|
||||
next: () => Promise<{ action: 'fail' | 'retry' }> = () => Promise.resolve({ action: 'fail' }),
|
||||
): Promise<{ action: 'fail' | 'retry' }> {
|
||||
next: () => Promise<RequestErrorAction> = () => Promise.resolve(undefined),
|
||||
): Promise<boolean> {
|
||||
const failure: LlmFailure = { message: error.message, code: error.code ?? 'UNKNOWN' }
|
||||
const priorFailures = Object.freeze(Array.from({ length: retryAttempt }, () => failure))
|
||||
const turn = owner.session.events.findLast(event => event.type === 'turn/start')?.data.turn ?? 1
|
||||
return agentEvents(ctx, owner).waterfall(
|
||||
'agent/request-error', 1, 1, error, failure, priorFailures, signal, next,
|
||||
)
|
||||
'agent/request-error', turn, 1, error, failure, [], undefined, signal, next,
|
||||
).then(action => action?.kind === 'retry')
|
||||
}
|
||||
|
||||
function overflow(message = 'provider overflow'): Error & { code: string } {
|
||||
@@ -1390,7 +1409,11 @@ describe('automatic listener and loader composition', () => {
|
||||
const ctx = createContext()
|
||||
const warnings: string[] = []
|
||||
ctx.logger.warn = ((message: string) => void warnings.push(message)) as typeof ctx.logger.warn
|
||||
vi.spyOn(ctx.llm, 'resolveModelContext').mockResolvedValue(undefined)
|
||||
vi.spyOn(ctx.llm, 'resolveModelInfo').mockImplementation((provider, model) => Promise.resolve({
|
||||
provider,
|
||||
id: model,
|
||||
name: model,
|
||||
}))
|
||||
void new TestCompactService(ctx, {
|
||||
thresholdRatio: 0.5,
|
||||
retainTokens: 180,
|
||||
@@ -1436,7 +1459,7 @@ describe('automatic listener and loader composition', () => {
|
||||
expect(ctx.tokenMeter.measure(session).totalTokens).toBeLessThan(threshold)
|
||||
const decision = await recover(ctx, agent(session, 'unconfigured-agent-fallback'), overflow())
|
||||
|
||||
expect(decision).toEqual({ action: 'retry' })
|
||||
expect(decision).toBe(true)
|
||||
expect(session.surface.replaceGeneration).toBe(beforeGeneration + 1)
|
||||
expect(session.events.some(event => event.type === 'compact/summary')).toBe(true)
|
||||
expect(session.surface.nodes).toContain(retainedSeq)
|
||||
@@ -1455,7 +1478,7 @@ describe('automatic listener and loader composition', () => {
|
||||
})
|
||||
const session = oversizedToolResult()
|
||||
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' })
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toBe(true)
|
||||
expect(session.surface.replaceGeneration).toBe(1)
|
||||
expect(session.events.some(event => event.type === 'compact/summary')).toBe(false)
|
||||
expect(compact.calls).toHaveLength(0)
|
||||
@@ -1474,7 +1497,7 @@ describe('automatic listener and loader composition', () => {
|
||||
})
|
||||
const session = toolConversation()
|
||||
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' })
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toBe(true)
|
||||
expect(session.events.some(event => event.type === 'compact/summary')).toBe(true)
|
||||
expect(compact.calls).toHaveLength(1)
|
||||
expect(summarizedText(compact.calls[0]!.input)).toContain('tool result middle pruned')
|
||||
@@ -1496,7 +1519,7 @@ describe('automatic listener and loader composition', () => {
|
||||
compact.error = new Error('summary unavailable after prune')
|
||||
const session = oversizedToolResult(3_000, true)
|
||||
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' })
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toBe(true)
|
||||
expect(session.surface.replaceGeneration).toBe(1)
|
||||
expect(session.events.filter(event => event.type === 'tool/result')).toHaveLength(2)
|
||||
expect(session.events.findLast(event => event.type === 'compact/end')?.data)
|
||||
@@ -1520,8 +1543,7 @@ describe('automatic listener and loader composition', () => {
|
||||
compact.error = new Error('summary cancelled after prune')
|
||||
const session = oversizedToolResult(3_000, true)
|
||||
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow(), 0, controller.signal))
|
||||
.toEqual({ action: 'fail' })
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow(), controller.signal)).toBe(false)
|
||||
expect(session.surface.replaceGeneration).toBe(1)
|
||||
})
|
||||
|
||||
@@ -1535,7 +1557,7 @@ describe('automatic listener and loader composition', () => {
|
||||
const newestAssistant = session.surface.nodes.at(-2)!
|
||||
const newestResult = session.surface.nodes.at(-1)!
|
||||
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' })
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toBe(true)
|
||||
const currentAssistant = session.surface.nodes.find(node => node === newestAssistant)
|
||||
const currentResult = session.surface.nodes.find(node => node === newestResult)
|
||||
expect(currentAssistant).toBeDefined()
|
||||
@@ -1559,7 +1581,7 @@ describe('automatic listener and loader composition', () => {
|
||||
}
|
||||
vi.spyOn(compact, 'compactIfNeeded').mockResolvedValue(fakeResult)
|
||||
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'fail' })
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toBe(false)
|
||||
expect(session.surface.replaceGeneration).toBe(0)
|
||||
})
|
||||
|
||||
@@ -1574,7 +1596,6 @@ describe('automatic listener and loader composition', () => {
|
||||
ctx,
|
||||
agent(conversation(2), MODEL),
|
||||
overflow(),
|
||||
0,
|
||||
SIGNAL,
|
||||
() => {
|
||||
calls += 1
|
||||
@@ -1592,7 +1613,7 @@ describe('automatic listener and loader composition', () => {
|
||||
compact.error = new Error('summary unavailable')
|
||||
const original = overflow('original provider overflow')
|
||||
|
||||
expect(await recover(ctx, agent(conversation(3), MODEL), original)).toEqual({ action: 'fail' })
|
||||
expect(await recover(ctx, agent(conversation(3), MODEL), original)).toBe(false)
|
||||
expect(original).toMatchObject({
|
||||
message: 'original provider overflow',
|
||||
code: CONTEXT_WINDOW_EXCEEDED_CODE,
|
||||
@@ -1611,12 +1632,12 @@ describe('automatic listener and loader composition', () => {
|
||||
const original = overflow('original provider failure')
|
||||
let delegations = 0
|
||||
|
||||
const decision = await recover(ctx, agent(session, MODEL), original, 0, SIGNAL, () => {
|
||||
const decision = await recover(ctx, agent(session, MODEL), original, SIGNAL, () => {
|
||||
delegations += 1
|
||||
return Promise.resolve({ action: 'fail' })
|
||||
return Promise.resolve(undefined)
|
||||
})
|
||||
|
||||
expect(decision).toEqual({ action: 'fail' })
|
||||
expect(decision).toBe(false)
|
||||
expect(delegations).toBe(1)
|
||||
expect(session.surface.replaceGeneration).toBe(generation)
|
||||
expect(original).toMatchObject({
|
||||
@@ -1635,7 +1656,7 @@ describe('automatic listener and loader composition', () => {
|
||||
reason: 'resume',
|
||||
})
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow('unlisted-model overflow')))
|
||||
.toEqual({ action: 'retry' })
|
||||
.toBe(true)
|
||||
})
|
||||
|
||||
it('delegates canonical overflow when no durable routed target exists', async () => {
|
||||
@@ -1647,21 +1668,19 @@ describe('automatic listener and loader composition', () => {
|
||||
trigger: { kind: 'message', source: { kind: 'user' } },
|
||||
})
|
||||
|
||||
await expect(recover(ctx, agent(session, MODEL), overflow())).resolves.toEqual({ action: 'fail' })
|
||||
await expect(recover(ctx, agent(session, MODEL), overflow())).resolves.toBe(false)
|
||||
})
|
||||
|
||||
it('honors retry caps, non-context failures, and cancellation', async () => {
|
||||
it('honors retry caps and ignores non-context failures', async () => {
|
||||
const ctx = createContext()
|
||||
const compact = new TestCompactService(ctx, { maxOverflowRetries: 1 })
|
||||
const compactSpy = vi.spyOn(compact, 'compactIfNeeded')
|
||||
const owner = agent(conversation(3), MODEL)
|
||||
expect(await recover(ctx, owner, Object.assign(new Error('rate limit'), { code: 'RATE_LIMIT' })))
|
||||
.toEqual({ action: 'fail' })
|
||||
expect(await recover(ctx, owner, overflow(), 1)).toEqual({ action: 'fail' })
|
||||
|
||||
const controller = new AbortController()
|
||||
controller.abort('cancelled')
|
||||
expect(await recover(ctx, owner, overflow(), 0, controller.signal)).toEqual({ action: 'fail' })
|
||||
.toBe(false)
|
||||
expect(await recover(ctx, owner, overflow())).toBe(true)
|
||||
compactSpy.mockClear()
|
||||
expect(await recover(ctx, owner, overflow())).toBe(false)
|
||||
expect(compactSpy).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
@@ -1676,9 +1695,11 @@ describe('automatic listener and loader composition', () => {
|
||||
}],
|
||||
})
|
||||
const compactSpy = vi.spyOn(compact, 'compactIfNeeded')
|
||||
const owner = agent(conversation(3), MODEL)
|
||||
|
||||
expect(await recover(ctx, agent(conversation(3), MODEL), overflow(), 1))
|
||||
.toEqual({ action: 'fail' })
|
||||
expect(await recover(ctx, owner, overflow())).toBe(true)
|
||||
compactSpy.mockClear()
|
||||
expect(await recover(ctx, owner, overflow())).toBe(false)
|
||||
expect(compactSpy).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
@@ -1690,8 +1711,7 @@ describe('automatic listener and loader composition', () => {
|
||||
const session = conversation(3)
|
||||
const generation = session.surface.replaceGeneration
|
||||
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow(), 0, controller.signal))
|
||||
.toEqual({ action: 'fail' })
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow(), controller.signal)).toBe(false)
|
||||
expect(session.surface.replaceGeneration).toBe(generation + 1)
|
||||
})
|
||||
|
||||
@@ -1706,7 +1726,7 @@ describe('automatic listener and loader composition', () => {
|
||||
await postStep(ctx, agent(session, MODEL))
|
||||
const summaries = session.events.filter(event => event.type === 'compact/summary').length
|
||||
expect(summaries).toBe(1)
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'fail' })
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toBe(false)
|
||||
expect(session.events.filter(event => event.type === 'compact/summary')).toHaveLength(summaries)
|
||||
})
|
||||
|
||||
@@ -1720,7 +1740,7 @@ describe('automatic listener and loader composition', () => {
|
||||
const session = conversation(4)
|
||||
await postStep(ctx, agent(session, MODEL))
|
||||
expect(session.events.some(event => event.type === 'compact/start')).toBe(false)
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'fail' })
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toBe(false)
|
||||
})
|
||||
|
||||
it('loads and disposes the real zero-config service stack', async () => {
|
||||
@@ -1749,6 +1769,6 @@ describe('automatic listener and loader composition', () => {
|
||||
const session = conversation(4)
|
||||
await postStep(ctx, agent(session, MODEL))
|
||||
expect(session.events.some(event => event.type === 'compact/start')).toBe(false)
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'fail' })
|
||||
expect(await recover(ctx, agent(session, MODEL), overflow())).toBe(false)
|
||||
})
|
||||
})
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
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 { CONTEXT_WINDOW_EXCEEDED_CODE, LlmError, resolveRetryPolicy } from '@deepseek-ai/dsh-llm'
|
||||
import type { ContentBlock, GenerateOptions, LlmResolvedModelInfo, ResolvedRetryPolicy, StreamChunk } from '@deepseek-ai/dsh-llm'
|
||||
import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
|
||||
import { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
@@ -15,7 +15,7 @@ import * as AgentLoopInvariant from '@deepseek-ai/dsh-agent-loop/invariant'
|
||||
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'
|
||||
import { Session, SessionId, type SessionEvent, type SurfaceEvent } from '@deepseek-ai/dsh-session'
|
||||
|
||||
/**
|
||||
* CBR-001 regression through the real loop. A replacement checkpoint has a high
|
||||
@@ -41,8 +41,13 @@ class StepwiseToolAdapter extends LlmAdapter {
|
||||
super()
|
||||
}
|
||||
|
||||
override resolveModelContext(): Promise<{ contextWindow: number }> {
|
||||
return Promise.resolve({ contextWindow: 400 })
|
||||
override resolveModel(provider: string, model: string): Promise<LlmResolvedModelInfo> {
|
||||
return Promise.resolve({
|
||||
provider,
|
||||
id: model,
|
||||
name: model,
|
||||
context: { contextWindow: 400 },
|
||||
})
|
||||
}
|
||||
|
||||
async * stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
@@ -68,6 +73,11 @@ class StepwiseToolAdapter extends LlmAdapter {
|
||||
class OverflowRecoveryAdapter extends LlmAdapter {
|
||||
readonly conversationRequests: GenerateOptions[] = []
|
||||
readonly summaryRequests: GenerateOptions[] = []
|
||||
private readonly retryPolicy = resolveRetryPolicy({
|
||||
mode: 'normal',
|
||||
maxRetries: 1,
|
||||
backoff: { initialDelayMs: 1, maxDelayMs: 1, jitterRatio: 0 },
|
||||
}, 'compaction test provider retryPolicy')
|
||||
|
||||
constructor(
|
||||
private readonly delivery: 'thrown' | 'in-band',
|
||||
@@ -76,8 +86,17 @@ class OverflowRecoveryAdapter extends LlmAdapter {
|
||||
super()
|
||||
}
|
||||
|
||||
override resolveModelContext(): Promise<{ contextWindow: number }> {
|
||||
return Promise.resolve({ contextWindow: 128 })
|
||||
override resolveModel(provider: string, model: string): Promise<LlmResolvedModelInfo> {
|
||||
return Promise.resolve({
|
||||
provider,
|
||||
id: model,
|
||||
name: model,
|
||||
context: { contextWindow: 128 },
|
||||
})
|
||||
}
|
||||
|
||||
override providerRetryPolicy(_provider: string): ResolvedRetryPolicy {
|
||||
return this.retryPolicy
|
||||
}
|
||||
|
||||
override async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
@@ -165,39 +184,43 @@ function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
|
||||
})
|
||||
}
|
||||
|
||||
function seedOverflowHistory(agent: Agent): void {
|
||||
function overflowHistorySeed(): SessionEvent[] {
|
||||
const session = new Session(SessionId('overflow-history-seed'))
|
||||
for (let turn = 1; turn <= 2; turn += 1) {
|
||||
const sentinel = turn === 1 ? 'OLD HISTORY SENTINEL' : 'RECENT HISTORY'
|
||||
agent.session.append('turn/start', {
|
||||
session.append('turn/start', {
|
||||
turn,
|
||||
trigger: { kind: 'message', source: { kind: 'user' } },
|
||||
})
|
||||
agent.session.append('user/message', {
|
||||
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', {
|
||||
session.append('step/start', { turn, step: 1 })
|
||||
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' } })
|
||||
session.append('step/end', { turn, step: 1 })
|
||||
session.append('turn/end', { turn, reason: { kind: 'completed' } })
|
||||
}
|
||||
return [...session.events]
|
||||
}
|
||||
|
||||
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' }))
|
||||
ctx.on('agent/request', async (_agent, _turn, _step, _signal, next) => ({
|
||||
...await next(), provider: 'mock', model: 'mock',
|
||||
}))
|
||||
try {
|
||||
const agent = ctx.agentLoop.create(SessionId('routed-pressure'), {
|
||||
provider: 'unconfigured-agent-fallback',
|
||||
model: 'unconfigured-agent-fallback',
|
||||
})
|
||||
agent.followup([{ type: 'text', text: 'do a routed multi-step task' }])
|
||||
agent.followup({ content: [{ type: 'text', text: 'do a routed multi-step task' }], source: { kind: 'user' } })
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
expect(agent.session.requestHeader()?.config.model).toBe('mock')
|
||||
@@ -211,11 +234,11 @@ 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 () => {
|
||||
it('runs automatic pressure between the completed tool step and the next step', async () => {
|
||||
const { ctx } = await harness(8)
|
||||
try {
|
||||
const agent = ctx.agentLoop.create(SessionId('post-step-order'), { provider: 'mock', model: 'mock' })
|
||||
agent.followup([{ type: 'text', text: 'do tool work' }])
|
||||
agent.followup({ content: [{ type: 'text', text: 'do tool work' }], source: { kind: 'user' } })
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const events = [...agent.session.events]
|
||||
@@ -225,13 +248,19 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', ()
|
||||
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 =>
|
||||
const precedingStepEnd = events.find(event =>
|
||||
event.type === 'step/end'
|
||||
&& event.data.step === precedingResult.data.step
|
||||
&& event.seq > precedingResult.seq,
|
||||
)
|
||||
const nextStepStart = events.find(event =>
|
||||
event.type === 'step/start'
|
||||
&& event.data.step === precedingResult.data.step + 1
|
||||
&& event.seq > compactStart!.seq,
|
||||
)
|
||||
expect(precedingResult.seq).toBeLessThan(compactStart!.seq)
|
||||
expect(compactStart!.seq).toBeLessThan(stepEnd!.seq)
|
||||
expect(precedingStepEnd!.seq).toBeLessThan(compactStart!.seq)
|
||||
expect(compactStart!.seq).toBeLessThan(nextStepStart!.seq)
|
||||
} finally {
|
||||
await ctx.fiber.dispose()
|
||||
}
|
||||
@@ -241,7 +270,7 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', ()
|
||||
const { ctx } = await harness(8)
|
||||
try {
|
||||
const agent = ctx.agentLoop.create(SessionId('repro'), { provider: 'mock', model: 'mock' })
|
||||
agent.followup([{ type: 'text', text: 'do a long multi-step task' }])
|
||||
agent.followup({ content: [{ type: 'text', text: 'do a long multi-step task' }], source: { kind: 'user' } })
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const events = [...agent.session.events]
|
||||
@@ -281,7 +310,9 @@ describe('context-overflow recovery across the real loop and compact-basic', ()
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
await ctx.plugin(TokenMeterService)
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
ctx.on('agent/request', async (_agent, _turn, _step, config) => ({ ...config, provider: 'mock', model: 'mock' }))
|
||||
ctx.on('agent/request', async (_agent, _turn, _step, _signal, next) => ({
|
||||
...await next(), provider: 'mock', model: 'mock',
|
||||
}))
|
||||
await ctx.plugin(BasicCompactService, {
|
||||
thresholdRatio: 1,
|
||||
retainTokens: 100,
|
||||
@@ -291,13 +322,16 @@ describe('context-overflow recovery across the real loop and compact-basic', ()
|
||||
})
|
||||
|
||||
try {
|
||||
const agent = ctx.agentLoop.create(SessionId(`overflow-${delivery}`), {
|
||||
provider: 'unconfigured-agent-fallback',
|
||||
model: 'unconfigured-agent-fallback',
|
||||
const { agent } = await ctx.agentLoop.createAgent(ctx, {
|
||||
sessionId: SessionId(`overflow-${delivery}`),
|
||||
seed: overflowHistorySeed(),
|
||||
agentOptions: {
|
||||
provider: 'unconfigured-agent-fallback',
|
||||
model: 'unconfigured-agent-fallback',
|
||||
},
|
||||
})
|
||||
seedOverflowHistory(agent)
|
||||
|
||||
agent.followup([{ type: 'text', text: 'continue from history' }])
|
||||
agent.followup({ content: [{ type: 'text', text: 'continue from history' }], source: { kind: 'user' } })
|
||||
await agent.whenIdle()
|
||||
|
||||
expect(adapter.conversationRequests).toHaveLength(2)
|
||||
@@ -308,11 +342,17 @@ describe('context-overflow recovery across the real loop and compact-basic', ()
|
||||
expect(retry).not.toContain('OLD HISTORY SENTINEL')
|
||||
|
||||
const events = [...agent.session.events]
|
||||
const failedEnd = events.find(event =>
|
||||
const failedStepEnd = events.find(event =>
|
||||
event.type === 'step/end' && event.data.turn === 3 && event.data.step === 1,
|
||||
)!
|
||||
const failedEnd = events.find(event =>
|
||||
event.type === 'turn/end' && event.data.turn === 3,
|
||||
)!
|
||||
const retryStart = events.find(event =>
|
||||
event.type === 'step/start' && event.data.turn === 3 && event.data.step === 2,
|
||||
event.type === 'turn/start' && event.data.turn === 4,
|
||||
)!
|
||||
const retryStep = events.find(event =>
|
||||
event.type === 'step/start' && event.data.turn === 4 && event.data.step === 1,
|
||||
)!
|
||||
const compaction = events.filter(event =>
|
||||
event.type === 'compact/start'
|
||||
@@ -324,7 +364,11 @@ describe('context-overflow recovery across the real loop and compact-basic', ()
|
||||
'compact/summary',
|
||||
'compact/end',
|
||||
])
|
||||
expect(compaction.every(event => event.seq > failedEnd.seq && event.seq < retryStart.seq)).toBe(true)
|
||||
expect(retryStart.seq).toBeGreaterThan(failedEnd.seq)
|
||||
expect(compaction.every(event =>
|
||||
event.seq > failedStepEnd.seq && event.seq < failedEnd.seq,
|
||||
)).toBe(true)
|
||||
expect(retryStep.seq).toBeGreaterThan(retryStart.seq)
|
||||
expect(events.at(-1)).toMatchObject({
|
||||
type: 'turn/end',
|
||||
data: { reason: { kind: 'completed' } },
|
||||
@@ -340,12 +384,7 @@ describe('context-overflow recovery across the real loop and compact-basic', ()
|
||||
const adapter = new OverflowRecoveryAdapter('thrown', true)
|
||||
await mountAgentLoopTestDependencies(ctx)
|
||||
await mountInvariants(ctx)
|
||||
await ctx.plugin(LlmRetry, {
|
||||
maxTransientRetries: 1,
|
||||
initialDelayMs: 1,
|
||||
maxDelayMs: 1,
|
||||
jitterRatio: 0,
|
||||
})
|
||||
await ctx.plugin(LlmRetry)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
await ctx.plugin(TokenMeterService)
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
@@ -358,17 +397,20 @@ describe('context-overflow recovery across the real loop and compact-basic', ()
|
||||
})
|
||||
|
||||
try {
|
||||
const agent = ctx.agentLoop.create(SessionId('alternating-recovery'), { provider: 'mock', model: 'mock' })
|
||||
seedOverflowHistory(agent)
|
||||
agent.followup([{ type: 'text', text: 'continue from history' }])
|
||||
const { agent } = await ctx.agentLoop.createAgent(ctx, {
|
||||
sessionId: SessionId('alternating-recovery'),
|
||||
seed: overflowHistorySeed(),
|
||||
agentOptions: { provider: 'mock', model: 'mock' },
|
||||
})
|
||||
agent.followup({ content: [{ type: 'text', text: 'continue from history' }], source: { kind: 'user' } })
|
||||
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])
|
||||
.toEqual([expect.objectContaining({ turn: 4, step: 1, retry: 1, failure: { message: 'temporary provider outage', code: 'SERVER' } })])
|
||||
expect(agent.session.events.filter(event => event.type === 'turn/start').slice(-3).map(event => event.data.turn))
|
||||
.toEqual([3, 4, 5])
|
||||
expect(agent.session.events.at(-1)).toMatchObject({
|
||||
type: 'turn/end',
|
||||
data: { reason: { kind: 'completed' } },
|
||||
|
||||
Reference in New Issue
Block a user