Files
deepseek-harness/packages/session-persistence/tests/contract.ts
Tianyi Cui efee449cfe feat(session-persistence): preserve interrupted turns on crash; don't truncate (review #33)
A crash can leave a durable log whose final turn never closed. The old
behavior truncated everything after the last turn/end as a "crash tail".
But a single turn can be HUGE in a long-horizon task (many steps, large
tool output), so truncating it silently destroys real, durably-written
work — truncating a turn is wrong.

New crash recovery (ADR 0018): load() PRESERVES the interrupted turn's
events and CLOSES the orphaned turn by durably appending synthetic
boundary events — a step/end if a step was open, then a turn/end carrying
the new merge-extensible TurnEndReason {kind:'interrupted'}. load()
returns the balanced log, so a resumed session is immediately usable. Only
a never-fully-written TORN tail fragment is discarded; corruption in the
committed region is still unloadable.

- dsh-session: TurnEndReason {kind:'interrupted'} + shared
  interruptedTurnClosers() repair helper.
- JSONL backend: scanLog preserves the longest contiguous prefix
  (including a partial final turn); loadCore truncates a torn fragment and
  durably writes the closers, returning the balanced log.
- runPersistenceContract gains a crash-recovery test (both backends + mock).
- Docs: ADR 0018/0017, architecture.md, package READMEs.

Also (review #33): RFC 013 records the "move event vocabulary to Zod"
question (merge-extensible maps → runtime schema registry) + blast radius;
deferred, not done here.
2026-06-16 21:27:50 +08:00

224 lines
9.4 KiB
TypeScript

/**
* Reusable contract test for any {@link SessionPersistence} backend. A backend
* package imports {@link runPersistenceContract} and calls it with a factory
* that yields a fresh, empty backend (and a teardown), so every backend is held
* to the same append-only / contiguous-seq / lazy-materialization / crash
* semantics. The JSONL backend's own spec adds file-specific tests on top.
*
* @module @deepseek-ai/dsh-session-persistence/tests/contract
*/
import { describe, expect, it } from 'vitest'
import { SessionId } from '@deepseek-ai/dsh-session'
import type { SessionEvent, SessionMeta } from '@deepseek-ai/dsh-session'
import type { SessionPersistence } from '../src/index.ts'
/** A backend under test plus its teardown. */
export interface ContractBackend {
persistence: SessionPersistence
dispose: () => Promise<void>
}
/** Build a minimal {@link SessionMeta} for a session id. */
export function meta(id: string, cwd?: string): SessionMeta {
return {
version: 1,
id: SessionId(id),
createdAt: 1000,
updatedAt: 1000,
...cwd !== undefined ? { cwd } : {},
}
}
/** A well-formed one-turn event log (contiguous seqs from 0). */
export function oneTurnLog(): SessionEvent[] {
return [
{ type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } },
{ type: 'user/message', seq: 1, time: 2, data: { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } } },
{ type: 'step/start', seq: 2, time: 3, data: { turn: 1, step: 1 } },
{ type: 'assistant/message', seq: 3, time: 4, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'hello' }] } },
{ type: 'step/end', seq: 4, time: 5, data: { turn: 1, step: 1 } },
{ type: 'turn/end', seq: 5, time: 6, data: { turn: 1, reason: { kind: 'completed' } } },
]
}
/**
* Run the backend-agnostic contract suite. `make()` MUST return a fresh, empty
* backend each call.
*/
export function runPersistenceContract(name: string, make: () => Promise<ContractBackend>): void {
describe(`SessionPersistence contract: ${name}`, () => {
it('round-trips a session: create + append → load returns identical meta and byte-identical events', async () => {
const { persistence, dispose } = await make()
try {
const m = meta('s1', '/work')
const log = oneTurnLog()
await persistence.create(m)
await persistence.append(m.id, log)
const loaded = await persistence.load(m.id)
expect(loaded.meta).toMatchObject({ version: 1, id: m.id, cwd: '/work' })
expect(loaded.events).toEqual(log)
} finally {
await dispose()
}
})
it('crash recovery: load preserves an interrupted (unclosed) turn and closes it with turn/end {interrupted}', async () => {
const { persistence, dispose } = await make()
try {
const m = meta('interrupted')
await persistence.create(m)
await persistence.append(m.id, oneTurnLog()) // turn 1, committed (seqs 0..5)
// A second turn that crashed mid-flight: turn/start + step/start were
// durably written, but no step/end / turn/end ever arrived.
await persistence.append(m.id, [
{ type: 'turn/start', seq: 6, time: 7, data: { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } } },
{ type: 'step/start', seq: 7, time: 8, data: { turn: 2, step: 1 } },
])
// load PRESERVES the interrupted turn's events (a turn can be huge — they
// must not be truncated) and closes the orphaned turn with synthetic
// boundary events: step/end (the step was open) then turn/end {interrupted}.
const loaded = await persistence.load(m.id)
expect(loaded.events.map(e => e.type)).toEqual([
'turn/start', 'user/message', 'step/start', 'assistant/message', 'step/end', 'turn/end', // turn 1
'turn/start', 'step/start', 'step/end', 'turn/end', // turn 2: real events + synthetic closers
])
expect(loaded.events.map(e => e.seq)).toEqual([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
const last = loaded.events.at(-1)!
expect(last.type === 'turn/end' && last.data.reason).toEqual({ kind: 'interrupted' })
// The closed log is durable and continuable: a fresh append continues at
// the balanced length (seq 10), and a reload round-trips identically.
await persistence.append(m.id, [
{ type: 'turn/start', seq: 10, time: 9, data: { turn: 3, trigger: { kind: 'message', source: { kind: 'user' } } } },
{ type: 'turn/end', seq: 11, time: 10, data: { turn: 3, reason: { kind: 'completed' } } },
])
const reloaded = await persistence.load(m.id)
expect(reloaded.events.map(e => e.seq)).toEqual([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11])
} finally {
await dispose()
}
})
it('has()/list() exclude a created-but-never-appended (zero-event) session', async () => {
const { persistence, dispose } = await make()
try {
await persistence.create(meta('empty'))
expect(await persistence.has(SessionId('empty'))).toBe(false)
expect((await persistence.list()).map(m => m.id)).not.toContain(SessionId('empty'))
} finally {
await dispose()
}
})
it('has()/list() include a session once it has events', async () => {
const { persistence, dispose } = await make()
try {
const m = meta('s2')
await persistence.create(m)
await persistence.append(m.id, oneTurnLog())
expect(await persistence.has(m.id)).toBe(true)
expect((await persistence.list()).map(x => x.id)).toContain(m.id)
} finally {
await dispose()
}
})
it('append rejects a batch whose first seq does not match the stored next-seq', async () => {
const { persistence, dispose } = await make()
try {
const m = meta('s3')
await persistence.create(m)
await persistence.append(m.id, oneTurnLog()) // seqs 0..5, next-seq = 6
// A re-append of an already-stored seq must be rejected, not duplicated.
const restated = oneTurnLog()
await expect(persistence.append(m.id, restated)).rejects.toThrow()
} finally {
await dispose()
}
})
it('append rejects a mid-batch seq gap', async () => {
const { persistence, dispose } = await make()
try {
const m = meta('s4')
await persistence.create(m)
const gapped: SessionEvent[] = [
{ type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } },
{ type: 'step/start', seq: 2, time: 2, data: { turn: 1, step: 1 } }, // gap: missing seq 1
]
await expect(persistence.append(m.id, gapped)).rejects.toThrow()
} finally {
await dispose()
}
})
it('append rejects non-JSON-serializable event data, naming the event type', async () => {
const { persistence, dispose } = await make()
try {
// Every value `isJsonValue` rejects must be rejected by the backend, not
// just BigInt — otherwise a backend could pass this contract while still
// accepting values that corrupt the durable round-trip. Each is a
// plugin-added `extra` field on a single user/message (seq 0).
const cyclic: Record<string, unknown> = { type: 'text', text: 'x' }
cyclic['self'] = cyclic
const badValues: unknown[] = [
1n, // BigInt
undefined, // dropped by JSON.stringify
Infinity, // → null
() => 0, // function
Symbol('s'), // symbol
new Map(), // exotic object
cyclic, // circular ref
]
for (const [i, bad] of badValues.entries()) {
// A fresh session per value isolates each rejection (a rejected append
// must leave no state behind, but isolating keeps the assertion clean).
const mi = meta(`s5-${i}`)
await persistence.create(mi)
const events = [
{ type: 'user/message', seq: 0, time: 1, data: { content: [{ type: 'text', text: 'x' }], source: { kind: 'user' }, extra: bad } },
] as unknown as SessionEvent[]
await expect(persistence.append(mi.id, events)).rejects.toThrow(/user\/message/)
}
} finally {
await dispose()
}
})
it('delete removes a session', async () => {
const { persistence, dispose } = await make()
try {
const m = meta('s6')
await persistence.create(m)
await persistence.append(m.id, oneTurnLog())
expect(await persistence.has(m.id)).toBe(true)
await persistence.delete(m.id)
expect(await persistence.has(m.id)).toBe(false)
} finally {
await dispose()
}
})
it('update mutates summary fields without touching the event log', async () => {
const { persistence, dispose } = await make()
try {
const m = meta('s7')
const log = oneTurnLog()
await persistence.create(m)
await persistence.append(m.id, log)
await persistence.update(m.id, { title: 'My session', firstPrompt: 'hi' })
const loaded = await persistence.load(m.id)
expect(loaded.meta.title).toBe('My session')
expect(loaded.meta.firstPrompt).toBe('hi')
expect(loaded.events).toEqual(log) // log untouched
} finally {
await dispose()
}
})
})
}