mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge branch 'codex/simp-ui-identity-residue' into codex/simp-hide-concrete-agent-loop
# Conflicts: # docs/event-producer-consumer.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/harness.ts # examples/coding-agent/tests/resume.e2e.ts # examples/cordis-agent/tests/harness.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts # packages/hooks/hooks-claude/tests/bridge.spec.ts # packages/hooks/hooks-claude/tests/coverage.spec.ts # packages/hooks/hooks-codex/tests/bridge.spec.ts # packages/hooks/hooks-codex/tests/coverage.spec.ts # packages/todo/tool-todo/tests/integration.spec.ts
This commit is contained in:
File diff suppressed because it is too large
Load Diff
@@ -1,18 +1,16 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import LlmService from '@deepseek-ai/dsh-llm'
|
||||
import { toolPairingBalancedAfter, toolPairingBalancedBefore } from '@deepseek-ai/dsh-compact'
|
||||
import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
|
||||
import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
|
||||
import { isToolPairingBalanced } from '@deepseek-ai/dsh-session'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
|
||||
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
|
||||
|
||||
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 type { SurfaceEvent } from '@deepseek-ai/dsh-session'
|
||||
import TokenMeterService from '@deepseek-ai/dsh-token-meter'
|
||||
import { SessionId, type SurfaceEvent } from '@deepseek-ai/dsh-session'
|
||||
|
||||
/**
|
||||
* CBR-001 regression through the real loop. A replacement checkpoint has a high
|
||||
@@ -21,15 +19,13 @@ import type { SurfaceEvent } from '@deepseek-ai/dsh-session'
|
||||
* surface-position semantics rather than raw-log scanning.
|
||||
*/
|
||||
|
||||
const TOKENS_PER_BLOCK = 10
|
||||
|
||||
class ReproCompactService extends BasicCompactService {
|
||||
override estimateContentTokens(blocks: readonly ContentBlock[]): number {
|
||||
return blocks.length * TOKENS_PER_BLOCK
|
||||
}
|
||||
|
||||
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',
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -61,13 +57,10 @@ class StepwiseToolAdapter 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))
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'work',
|
||||
@@ -77,13 +70,12 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr
|
||||
return [{ type: 'text', text: 'work result' }]
|
||||
},
|
||||
}))
|
||||
// Tiny window so a couple of tool steps cross the threshold and compaction
|
||||
// fires within the runaway turn.
|
||||
// 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,
|
||||
contextWindow: 64,
|
||||
thresholdRatio: 0.5,
|
||||
retainTokens: 20,
|
||||
retainTokens: 50,
|
||||
summarizationModel: '',
|
||||
maxTokens: 8192,
|
||||
compactionRetries: 1,
|
||||
@@ -106,7 +98,7 @@ 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(SessionId('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)
|
||||
|
||||
@@ -125,9 +117,9 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', ()
|
||||
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(isToolPairingBalanced(nodes, events, cp.seq),
|
||||
expect(toolPairingBalancedBefore(agent.session, cp.seq),
|
||||
`checkpoint seq ${cp.seq} must be a balanced region START`).toBe(true)
|
||||
expect(isToolPairingBalanced(nodes, events, nodes[index + 1] ?? null),
|
||||
expect(toolPairingBalancedAfter(agent.session, cp.seq),
|
||||
`checkpoint seq ${cp.seq} must be a balanced region END`).toBe(true)
|
||||
}
|
||||
} finally {
|
||||
|
||||
@@ -0,0 +1,94 @@
|
||||
import { mkdtemp, rm, writeFile } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { pathToFileURL } from 'node:url'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import Loader from '@cordisjs/plugin-loader'
|
||||
import Include from '@cordisjs/plugin-include'
|
||||
import LlmService from '@deepseek-ai/dsh-llm'
|
||||
import TokenMeterService from '@deepseek-ai/dsh-token-meter'
|
||||
import BasicCompactService from '@deepseek-ai/dsh-compact-basic'
|
||||
|
||||
let root: string | undefined
|
||||
let context: Context | undefined
|
||||
|
||||
afterEach(async () => {
|
||||
await context?.fiber.dispose()
|
||||
context = undefined
|
||||
if (root !== undefined) await rm(root, { recursive: true, force: true })
|
||||
root = undefined
|
||||
})
|
||||
|
||||
async function loadYaml(lines: readonly string[]): Promise<Context> {
|
||||
root = await mkdtemp(join(tmpdir(), 'dsh-token-meter-loader-'))
|
||||
const configPath = join(root, 'cordis.yml')
|
||||
await writeFile(configPath, [...lines, ''].join('\n'))
|
||||
|
||||
context = new Context()
|
||||
context.baseUrl = pathToFileURL(root).href + '/'
|
||||
await context.plugin(Loader)
|
||||
context.loader.builtins.include = Include
|
||||
const modules = new Map<string, unknown>([
|
||||
['@deepseek-ai/dsh-llm', LlmService],
|
||||
['@deepseek-ai/dsh-token-meter', TokenMeterService],
|
||||
['@deepseek-ai/dsh-compact-basic', BasicCompactService],
|
||||
])
|
||||
context.loader.internal = {
|
||||
version: 'v2',
|
||||
async import(specifier: string) {
|
||||
if (!modules.has(specifier)) throw new Error(`unexpected Loader import: ${specifier}`)
|
||||
return modules.get(specifier)
|
||||
},
|
||||
} as unknown as NonNullable<typeof context.loader.internal>
|
||||
await context.loader.create({
|
||||
name: 'cordis:include',
|
||||
config: { path: pathToFileURL(configPath).href },
|
||||
})
|
||||
await context.loader.await()
|
||||
return context
|
||||
}
|
||||
|
||||
describe('real Loader composition', () => {
|
||||
it('loads the flat token-meter and compact-basic YAML shape', async () => {
|
||||
const loaded = await loadYaml([
|
||||
"- name: '@deepseek-ai/dsh-llm'",
|
||||
"- name: '@deepseek-ai/dsh-token-meter'",
|
||||
' config:',
|
||||
' contextWindow: 4096',
|
||||
"- name: '@deepseek-ai/dsh-compact-basic'",
|
||||
' config:',
|
||||
' thresholdRatio: 0.5',
|
||||
' retainTokens: 512',
|
||||
' auto: false',
|
||||
])
|
||||
|
||||
const unloaded = [...loaded.loader.entries()]
|
||||
.filter(entry => entry.fiber === undefined && !entry.disabled)
|
||||
.map(entry => entry.options.name)
|
||||
expect(unloaded).toEqual([])
|
||||
expect(loaded.tokenMeter.contextWindow).toBe(4096)
|
||||
expect(loaded.get('compact')).toBeInstanceOf(BasicCompactService)
|
||||
expect((loaded.compact as BasicCompactService).config).toMatchObject({
|
||||
thresholdRatio: 0.5,
|
||||
retainTokens: 512,
|
||||
auto: false,
|
||||
})
|
||||
})
|
||||
|
||||
it('rejects stale token-meter config after Schemastery normalization', async () => {
|
||||
context = new Context()
|
||||
await expect(context.plugin(TokenMeterService, {
|
||||
models: { legacy: { contextWindow: 4096 } },
|
||||
} as never)).rejects.toThrow(/TokenMeterConfig: unknown key "models"/)
|
||||
})
|
||||
|
||||
it('rejects stale compact-basic config after Schemastery normalization', async () => {
|
||||
context = new Context()
|
||||
await context.plugin(LlmService)
|
||||
await context.plugin(TokenMeterService)
|
||||
await expect(context.plugin(BasicCompactService, {
|
||||
models: { legacy: { thresholdRatio: 0.5 } },
|
||||
} as never)).rejects.toThrow(/BasicCompactConfig: unknown key "models"/)
|
||||
})
|
||||
})
|
||||
Reference in New Issue
Block a user