fix review findings: skip collided SCHEMA_VERSION 3; reject marker-less surface events

P1: both merge parents shipped SCHEMA_VERSION=3 for different layouts (surface
columns vs seed_length), so an on-disk 3 was ambiguous and wrongly accepted.
Bump to 4 (merged layout) so the version check rejects both sibling v3s.

P2: a surface-eligible event with no surfaceOp lands in the log but vanishes
from deriveMessages() (surface is the sole derivation path). The typed append
overload enforces the marker only when the type arg is a literal; it collapses
to optional when widened to the union (a caller iterating raw events). Guard at
runtime in both append() and the seed constructor — no backward-compat for
surface-less logs. Shared seed fixtures carry surfaceOp explicitly and the
appendLog helper forwards it verbatim (no synthesized default). Exports
isSurfaceEligibleType. Regression tests for all three, each verified to fail
on the unfixed code.

Gates: typecheck, test (1115), snapshot (14), doc-sync, lint, build, hygiene green.
This commit is contained in:
Hypatia May
2026-06-24 17:45:48 +08:00
parent 9cc8dc371e
commit 828c3f85c9
14 changed files with 166 additions and 36 deletions
+19 -8
View File
@@ -11,22 +11,29 @@ import { describe, expect, it } from 'vitest'
import fc from 'fast-check'
import { CallId } from '@deepseek-ai/dsh-llm'
import { Session, SessionId } from '@deepseek-ai/dsh-session'
import type { SessionEventMap, SessionEventType } from '@deepseek-ai/dsh-session'
import type { SessionEventMap, SessionEventType, SurfaceIntent } from '@deepseek-ai/dsh-session'
type Appendable = { [T in SessionEventType]: { type: T; data: SessionEventMap[T] } }[SessionEventType]
// An appendable event: its type/data plus, for surface-eligible types, the
// explicit surface intent the generator declares (mirroring how a real caller
// passes it). The intent is part of the generated fixture, NOT synthesized by
// `build`, so each arbitrary states the marker it produces.
type Appendable = {
[T in SessionEventType]: { type: T; data: SessionEventMap[T]; intent?: SurfaceIntent }
}[SessionEventType]
const textContentArb = fc.array(
fc.record({ type: fc.constant<'text'>('text'), text: fc.string() }),
{ maxLength: 3 },
)
// A message-producing event (these DO affect derived history).
// A message-producing event (these DO affect derived history). Each carries an
// explicit `surfaceOp: 'append'` intent — the marker the real loop passes.
const messageEventArb: fc.Arbitrary<Appendable> = fc.oneof(
textContentArb.map((content): Appendable => ({ type: 'user/message', data: { content, source: { kind: 'user' } } })),
textContentArb.map((content): Appendable => ({ type: 'assistant/message', data: { turn: 1, step: 1, content } })),
textContentArb.map((content): Appendable => ({ type: 'assistant/message', data: { turn: 1, step: 1, content, usage: { inputTokens: 1, outputTokens: 1 } } })),
textContentArb.map((content): Appendable => ({ type: 'user/message', data: { content, source: { kind: 'user' } }, intent: { surfaceOp: 'append' } })),
textContentArb.map((content): Appendable => ({ type: 'assistant/message', data: { turn: 1, step: 1, content }, intent: { surfaceOp: 'append' } })),
textContentArb.map((content): Appendable => ({ type: 'assistant/message', data: { turn: 1, step: 1, content, usage: { inputTokens: 1, outputTokens: 1 } }, intent: { surfaceOp: 'append' } })),
fc.record({ id: fc.string({ minLength: 1 }), content: textContentArb, isError: fc.boolean() })
.map((r): Appendable => ({ type: 'tool/result', data: { turn: 1, step: 1, callId: CallId(r.id), content: r.content, isError: r.isError } })),
.map((r): Appendable => ({ type: 'tool/result', data: { turn: 1, step: 1, callId: CallId(r.id), content: r.content, isError: r.isError }, intent: { surfaceOp: 'append' } })),
)
// A non-message event (trace/replay data — must NOT affect derived history).
@@ -44,7 +51,11 @@ const logArb = fc.array(anyEventArb, { maxLength: 25 })
let counter = 0
function build(events: Appendable[]): Session {
const session = new Session(SessionId(`prop-${counter++}`))
for (const e of events) session.append(e.type, e.data)
for (const e of events) {
// Forward the generated intent verbatim; non-surface events carry none.
if (e.intent !== undefined) session.append(e.type, e.data, e.intent)
else session.append(e.type, e.data)
}
return session
}
+31 -2
View File
@@ -2,6 +2,7 @@ import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import { CallId } from '@deepseek-ai/dsh-llm'
import SessionStore, { SESSION_FORMAT_VERSION, Session, SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
import type { SessionEventType } from '@deepseek-ai/dsh-session'
describe('Session', () => {
it('derives message history from the event log', () => {
@@ -120,6 +121,21 @@ describe('Session', () => {
expect(session.events).toHaveLength(0)
})
it('rejects a surface-eligible append with no surfaceOp marker (runtime guard for the union-widening loophole)', () => {
const session = new Session(SessionId('s5b'))
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
// The typed overload makes surfaceOp mandatory only when the type argument is
// a SPECIFIC SurfaceEventType literal. A caller iterating raw events widens it
// to the SessionEventType union, where the conditional rest collapses to
// optional — the exact shape `for (const e of log) append(e.type, e.data)`
// produces. Reproduce that here and assert the runtime guard rejects it.
const widenedType = 'user/message' as SessionEventType
expect(() => session.append(widenedType, { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }))
.toThrow(/surface-eligible and requires a surfaceOp marker/)
// The rejected append never entered the log (only turn/start is present).
expect(session.events).toHaveLength(1)
})
it('accepts dense arrays and nested plain objects', () => {
const session = new Session(SessionId('s6'))
expect(() => session.append('user/message', { content: [{ type: 'text', text: 'x' }], source: { kind: 'user' }, extra: [1, 2, [3, { a: null, b: true }]] } as never, { surfaceOp: 'append' })).not.toThrow()
@@ -143,10 +159,23 @@ describe('Session', () => {
expect(() => new Session(SessionId('seed-gap'), gapSeed)).toThrow(/contiguous|seq/)
})
it('validates seed events: rejects a surface-eligible event missing its surfaceOp marker', () => {
// A surface-eligible event (user/message) with no surfaceOp would load fine
// but vanish from deriveMessages() (the surface is the sole derivation path),
// so a resume/fork would silently lose history. append() forbids this at
// compile time; a raw seed must be rejected at runtime to match.
const markerlessSeed = [
{ type: 'turn/start' as const, seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message' as const, source: { kind: 'user' as const } } } },
{ type: 'user/message' as const, seq: 1, time: 2, data: { content: [{ type: 'text' as const, text: 'hi' }], source: { kind: 'user' as const } } },
{ type: 'turn/end' as const, seq: 2, time: 3, data: { turn: 1, reason: { kind: 'completed' as const } } },
] as SessionEvent[]
expect(() => new Session(SessionId('seed-no-marker'), markerlessSeed)).toThrow(/surface-eligible but carries no surfaceOp/)
})
it('accepts a well-formed contiguous serializable seed', () => {
const goodSeed = [
{ type: 'turn/start' as const, seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message' as const, source: { kind: 'user' as const } } } },
{ type: 'user/message' as const, seq: 1, time: 2, data: { content: [{ type: 'text' as const, text: 'hi' }], source: { kind: 'user' as const } } },
{ type: 'user/message' as const, seq: 1, time: 2, data: { content: [{ type: 'text' as const, text: 'hi' }], source: { kind: 'user' as const } }, surfaceOp: 'append' as const },
{ type: 'turn/end' as const, seq: 2, time: 3, data: { turn: 1, reason: { kind: 'completed' as const } } },
] as SessionEvent[]
const session = new Session(SessionId('seed-ok'), goodSeed)
@@ -156,7 +185,7 @@ describe('Session', () => {
it('snapshots the seed: mutating the original after construction does not affect session.events', () => {
const seed = [
{ type: 'turn/start' as const, seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message' as const, source: { kind: 'user' as const } } } },
{ type: 'user/message' as const, seq: 1, time: 2, data: { content: [{ type: 'text' as const, text: 'original' }], source: { kind: 'user' as const } } },
{ type: 'user/message' as const, seq: 1, time: 2, data: { content: [{ type: 'text' as const, text: 'original' }], source: { kind: 'user' as const } }, surfaceOp: 'append' as const },
{ type: 'turn/end' as const, seq: 2, time: 3, data: { turn: 1, reason: { kind: 'completed' as const } } },
] as SessionEvent[]
const session = new Session(SessionId('seed-snapshot'), seed)