Files
deepseek-harness/examples/coding-agent/tests/resume.e2e.ts
Tianyi Cui 59dc310bb5 Merge branch 'codex/simp-agent-entry-state' into codex/simp-unify-agent-session-id
# Conflicts:
#	docs/architecture.md
#	docs/config-catalog.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/core.md
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	examples/coding-agent/tests/code-mode.e2e.ts
#	examples/coding-agent/tests/coding-task.e2e.ts
#	examples/coding-agent/tests/compaction.e2e.ts
#	examples/coding-agent/tests/full-loop.e2e.ts
#	examples/coding-agent/tests/todo-write.e2e.ts
#	examples/cordis-agent/tests/cordis-tools.e2e.ts
#	packages/bash/tool-bash/tests/integration.spec.ts
#	packages/bash/tool-bash/tests/tools.spec.ts
#	packages/compact/compact-basic/tests/compact-loop-repro.spec.ts
#	packages/context/time-context/tests/time-context.spec.ts
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/cordis/tool-cordis/tests/integration.spec.ts
#	packages/core/agent-loop/README.md
#	packages/core/agent-loop/src/agent.ts
#	packages/core/agent-loop/src/index.ts
#	packages/core/agent-loop/tests/agent.spec.ts
#	packages/core/agent-loop/tests/cancel.spec.ts
#	packages/core/agent-loop/tests/config-session-id.spec.ts
#	packages/core/agent-loop/tests/contract-regressions.spec.ts
#	packages/core/agent-loop/tests/coverage-edges.spec.ts
#	packages/core/agent-loop/tests/interception.spec.ts
#	packages/core/agent-loop/tests/loop.spec.ts
#	packages/core/agent-loop/tests/properties.spec.ts
#	packages/core/agent-loop/tests/request-cache.e2e.ts
#	packages/core/agent-loop/tests/request-reconstruction.spec.ts
#	packages/core/agent-loop/tests/resume.spec.ts
#	packages/core/agent-loop/tests/scope-lifecycle.spec.ts
#	packages/core/agent-loop/tests/tool-order.spec.ts
#	packages/core/agent-loop/tests/turn-stop.spec.ts
#	packages/core/agent/src/types.ts
#	packages/examples/agent-spine-demo/README.md
#	packages/examples/agent-spine-demo/tests/agent-core.spec.ts
#	packages/examples/stdio-demo/README.md
#	packages/examples/stdio-demo/src/index.ts
#	packages/examples/stdio-demo/tests/stdio-agent.spec.ts
#	packages/fs/tool-fs/tests/fs-tools.e2e.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/subagent/subagent-fork/tests/multi-subagent.spec.ts
#	packages/subagent/subagent-fork/tests/subagent-fork.spec.ts
#	packages/subagent/subagent-inprocess/tests/structured.spec.ts
#	packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts
#	packages/subagent/subagent-spawn/tests/spawn.e2e.ts
#	packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts
#	packages/todo/tool-todo/tests/integration.spec.ts
#	packages/ui/acp/tests/dispose.spec.ts
#	packages/ui/acp/tests/edges.spec.ts
#	packages/workflow/workflow-workerthread/tests/integration.spec.ts
2026-07-18 12:21:15 +08:00

69 lines
3.1 KiB
TypeScript

import { mkdtemp, rm } 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 type { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import { SessionId } from '@deepseek-ai/dsh-session'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
/**
* Proves durable conversation continuity end-to-end: run 1 tells the REAL model
* a fact and persists the turn to JSONL; run 2 is a fresh harness (new Context,
* same `.sessions` root) that RESUMES the persisted session id and asks the
* model to recall the fact. The recall can only come from the rehydrated event
* log — a fresh session would have no idea. Key-gated like the other e2es.
*/
const SECRET = 'plum-galaxy-1791'
const SESSION_ID = SessionId('resume-e2e-session')
let ctx: Context | undefined
let root: string | undefined
afterEach(async () => {
// Dispose even on failure/retry: agent-loop teardown stops the loop and the
// JSONL backend flushes; then drop the on-disk session log.
await ctx?.fiber.dispose()
ctx = undefined
if (root !== undefined) await rm(root, { recursive: true, force: true })
root = undefined
})
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted session across processes', () => {
it('recalls a fact stored in a prior, separately-disposed session', async () => {
root = await mkdtemp(join(tmpdir(), 'dsh-resume-e2e-'))
// Run 1: a fresh agent on a KNOWN session id learns a secret, then we
// dispose the whole context (simulating process exit) so only the JSONL
// log on disk survives.
ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root })
const first = (await ctx.agents.create({
sessionId: SESSION_ID,
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
})).agent as ReactLoopAgent
first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
await waitForIdle(ctx, first)
await ctx.fiber.dispose()
ctx = undefined
// Run 2: a brand-new context over the SAME root resumes the persisted
// session. The loaded event log seeds the live session, so the model sees
// run 1's exchange as conversation history.
ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root })
const resumed = (await ctx.agents.resume({
resumeSessionId: SESSION_ID,
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
})).agent as ReactLoopAgent
expect(resumed.session.id).toBe(SESSION_ID)
// The prior user turn is in the rehydrated log before the model is asked.
expect(JSON.stringify(resumed.session.deriveMessages())).toContain(SECRET)
resumed.send([{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }])
await waitForIdle(ctx, resumed)
// The model recalls it — only possible from the resumed history.
expect(finalText([...resumed.session.events])).toContain(SECRET)
}, 180_000)
})