deepseek-harness/examples/coding-agent/tests/resume.e2e.ts

68 lines
3 KiB
TypeScript
Raw Normal View History

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'
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes the two gaps in the "brand ids that cross package boundaries" policy and fixes the dependency direction so a capability package never pulls in an unrelated one. - Extract the `Branded<B>` primitive into a new standalone type-only package `@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps. dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session, dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a generic execution backend must not couple to the LLM or session vocabulary). - Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id, the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary that casts SessionId -> OwnerToken. - Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters at the config boundary and the inner create()/resume casts disappear (only the genuinely-new per-run session-id string is cast). - Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store Map keys and public params/exports (SessionStore, AgentRegistry + factory options, the ACP session-id surface + ToolPresenter CallId map, the persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps). - Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point the Branded type-equiv at dsh-brand, fix stale param types in the session/ agent/bash READMEs, regenerate the cordis catalog + module graph. Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
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'
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes the two gaps in the "brand ids that cross package boundaries" policy and fixes the dependency direction so a capability package never pulls in an unrelated one. - Extract the `Branded<B>` primitive into a new standalone type-only package `@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps. dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session, dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a generic execution backend must not couple to the LLM or session vocabulary). - Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id, the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary that casts SessionId -> OwnerToken. - Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters at the config boundary and the inner create()/resume casts disappear (only the genuinely-new per-run session-id string is cast). - Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store Map keys and public params/exports (SessionStore, AgentRegistry + factory options, the ACP session-id surface + ToolPresenter CallId map, the persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps). - Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point the Branded type-equiv at dsh-brand, fix stale param types in the session/ agent/bash READMEs, regenerate the cordis catalog + module graph. Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
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,
2026-07-14 21:57:52 +08:00
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
2026-07-14 02:32:35 +08:00
})).agent
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,
2026-07-14 21:57:52 +08:00
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
2026-07-14 02:32:35 +08:00
})).agent
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)
})