Merge remote-tracking branch 'origin/master' into worktree/routed-model-compaction-policy
# Conflicts: # .agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml # .agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md # .agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # examples/headless-agent/tests/harness.ts # examples/repl-agent/cordis.yml # packages/compact/compact-basic/README.md # packages/compact/compact-basic/src/index.ts # packages/compact/compact-basic/tests/compact-basic.spec.ts # packages/compact/compact-basic/tests/loader-composition.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/llm/README.md # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-pi-ai/src/adapter.ts # packages/llm/llm/README.md # packages/llm/llm/src/index.ts # scripts/gen-cordis-catalog.ts # website/zh-CN/api/harness/events.md # website/zh-CN/api/harness/llm.md # website/zh-CN/api/harness/token-meter.md # website/zh-CN/guide/config.md
This commit is contained in:
86
examples/headless-agent/tests/compaction.e2e.ts
Normal file
86
examples/headless-agent/tests/compaction.e2e.ts
Normal file
@@ -0,0 +1,86 @@
|
||||
import { mkdtemp, rm, writeFile } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import type { Context } from 'cordis'
|
||||
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
|
||||
import { SessionId } from '@deepseek-ai/dsh-session'
|
||||
|
||||
/**
|
||||
* Key-gated smoke for mid-session compaction. It verifies the compact event
|
||||
* pair, replacement of older surface nodes, and a final answer after compaction.
|
||||
*/
|
||||
// FIXME(compaction-snapshot): this is the only full compaction coverage because
|
||||
// replay cannot serve the summarizer's unlogged model call.
|
||||
|
||||
let workdir: string | undefined
|
||||
let ctx: Context | undefined
|
||||
|
||||
afterEach(async () => {
|
||||
await ctx?.fiber.dispose()
|
||||
ctx = undefined
|
||||
if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
|
||||
workdir = undefined
|
||||
})
|
||||
|
||||
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compacts mid-flight and keeps running', () => {
|
||||
it('summarizes older history into a checkpoint without breaking the task', async () => {
|
||||
workdir = await mkdtemp(join(tmpdir(), 'dsh-compaction-'))
|
||||
for (let i = 1; i <= 4; i++) {
|
||||
await writeFile(join(workdir, `file${i}.txt`), `This is file number ${i}. `.repeat(50))
|
||||
}
|
||||
|
||||
// Reasoning tokens require a larger generation cap than the retained checkpoint.
|
||||
ctx = await codingHarness(workdir, {
|
||||
persona: SYSTEM_PROMPT,
|
||||
modelContextWindow: 2000,
|
||||
compact: {
|
||||
thresholdRatio: 0.5,
|
||||
retainTokens: 400,
|
||||
summarizationProvider: '',
|
||||
summarizationModel: '',
|
||||
maxTokens: 1024,
|
||||
compactionRetries: 1,
|
||||
},
|
||||
persistenceRoot: join(workdir, '.sessions'),
|
||||
})
|
||||
const agent = ctx.agentLoop.create(SessionId('e2e-compaction'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
|
||||
|
||||
agent.send([{
|
||||
type: 'text',
|
||||
text: 'Read file1.txt, file2.txt, file3.txt, and file4.txt one at a '
|
||||
+ 'time using cat (a separate bash command for each). After reading all four, tell me how '
|
||||
+ 'many files you read and the number mentioned in file1.txt.',
|
||||
}])
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const events = [...agent.session.events]
|
||||
|
||||
// A compaction ran: the start…end bracket landed in the real log.
|
||||
const starts = events.filter(e => e.type === 'compact/start')
|
||||
const ends = events.filter(e => e.type === 'compact/end')
|
||||
expect(starts.length).toBeGreaterThan(0)
|
||||
expect(ends.length).toBe(starts.length) // every start was released
|
||||
|
||||
// It succeeded at least once: a compact/summary provenance event and a
|
||||
// replace-op user/message (the surface mutation) both landed.
|
||||
const summaries = events.filter(e => e.type === 'compact/summary')
|
||||
expect(summaries.length).toBeGreaterThan(0)
|
||||
const replaceNode = events.find((e) => {
|
||||
const se = e as unknown as { type: string; surfaceOp?: unknown }
|
||||
return se.type === 'user/message' && typeof se.surfaceOp === 'object' && se.surfaceOp !== null
|
||||
})
|
||||
expect(replaceNode).toBeDefined()
|
||||
|
||||
// The summary shadowed real older nodes (the surface shrank vs. the raw
|
||||
// message-producing event count).
|
||||
const summaryData = summaries[0]!.data as { shadowedSeqs: number[] }
|
||||
expect(summaryData.shadowedSeqs.length).toBeGreaterThan(0)
|
||||
|
||||
// The conversation survived compaction: the agent produced a final answer
|
||||
// that reflects the work (it read four files).
|
||||
const answer = finalText(events).toLowerCase()
|
||||
expect(answer.length).toBeGreaterThan(0)
|
||||
expect(answer).toMatch(/\b(4|four)\b/)
|
||||
}, 240_000)
|
||||
})
|
||||
Reference in New Issue
Block a user