Merge branch 'codex/simp-session-dead-surface' into codex/simp-session-log-representation
# Conflicts: # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.md # docs/persistence-catalog.md # docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md # docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md # docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md # docs/rfc/implemented/feature/2026-07-06-sandbox.md # docs/rfc/implemented/feature/2026-07-07-session-prefix.md # packages/compact/compact-basic/src/index.ts # packages/compact/compact-basic/tests/compact-basic.spec.ts # packages/core/agent-loop/src/loop.ts # packages/core/agent-loop/src/request-log.ts # packages/core/agent-loop/tests/request-reconstruction.spec.ts # packages/core/agent/src/types.ts # packages/core/session/README.md # packages/core/session/src/request-header.ts # packages/core/session/src/surface.ts # packages/core/session/src/tool-pairing.ts # packages/core/session/src/types.ts # packages/core/session/tests/surface.spec.ts # packages/core/session/tests/tool-pairing.spec.ts # packages/llm/llm/src/call-config.ts # packages/support/acp-snapshot/src/suite.ts # packages/support/invariants/README.md # packages/ui/user-approval/README.md
This commit is contained in:
Tianyi Cui
@@ -1,10 +1,7 @@
|
||||
/**
|
||||
* Derived-message cache tests: the session projects each surface node exactly
|
||||
* once (O(new nodes) per call), rebuilds on a surface replace (the
|
||||
* replaceGeneration signal), returns a fresh array snapshot
|
||||
* per call over shared frozen messages, and stays deep-equal to a from-scratch
|
||||
* replay derivation at every step — the incremental==scratch property the
|
||||
* reconstructability RFC's invariant enforces in dev at request time.
|
||||
* Derived-message cache contract against a scratch oracle: project new nodes
|
||||
* once, rebuild on surface replacements, return fresh arrays over shared
|
||||
* frozen messages, and remain value-equal to replay at every step.
|
||||
*/
|
||||
|
||||
import { describe, expect, it } from 'vitest'
|
||||
@@ -28,7 +25,6 @@ describe('derived-message cache', () => {
|
||||
userText(session, 'two')
|
||||
session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'reply' }] }, { surfaceOp: 'append' })
|
||||
expect(session.deriveMessages()).toEqual(scratch(session))
|
||||
// An empty-content assistant/message (usage host) projects to nothing.
|
||||
session.append('assistant/message', { turn: 1, step: 2, content: [], usage: { inputTokens: 1, outputTokens: 0 } }, { surfaceOp: 'append' })
|
||||
expect(session.deriveMessages()).toEqual(scratch(session))
|
||||
})
|
||||
@@ -48,7 +44,6 @@ describe('derived-message cache', () => {
|
||||
|
||||
expect(session.deriveMessages()).toHaveLength(1)
|
||||
expect(session.deriveMessages()).toEqual(scratch(session))
|
||||
// The array a caller took before the replace is untouched.
|
||||
expect(beforeReplace).toHaveLength(2)
|
||||
})
|
||||
|
||||
@@ -61,7 +56,7 @@ describe('derived-message cache', () => {
|
||||
const second = session.deriveMessages()
|
||||
expect(first).toHaveLength(1)
|
||||
expect(second).toHaveLength(2)
|
||||
// Shared projection objects: the same frozen message instance, once ever.
|
||||
// Array snapshots share their frozen message projections.
|
||||
expect(second[0]).toBe(first[0])
|
||||
expect(Object.isFrozen(first[0])).toBe(true)
|
||||
})
|
||||
@@ -73,8 +68,7 @@ describe('Session.deriveEventMessage — the per-event projection', () => {
|
||||
const session = new Session(SessionId('per-event'))
|
||||
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
const event = session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
|
||||
// The fold path (deriveMessages) and the per-event path share the
|
||||
// projection, so an external reconstructor cannot disagree with the cache.
|
||||
// Full and per-event derivation share one projection.
|
||||
expect(session.deriveEventMessage(event)).toEqual(session.deriveMessages().at(-1))
|
||||
})
|
||||
|
||||
|
||||
@@ -1,16 +1,6 @@
|
||||
/**
|
||||
* Negative-path tests for the persistence log catalog generator
|
||||
* (`scripts/gen-persistence-catalog.ts`).
|
||||
*
|
||||
* The generated catalog is frozen by a regenerate-and-diff freshness gate, so
|
||||
* the freshness half is exercised by `pnpm run verify-persistence-catalog` in
|
||||
* CI. What a freshness diff CANNOT prove is that the generator REJECTS
|
||||
* malformed source the way it promises to — a member without description
|
||||
* prose, a forbidden `@mode` tag, a non-literal member name, a duplicate event
|
||||
* declaration, a missing or ambiguous `SurfaceEventType` union, a stale union
|
||||
* member. These tests drive the exported collectors against synthetic fixture
|
||||
* packages to prove each guard fires (and that well-formed declarations pass),
|
||||
* mirroring the gen-cordis-catalog negative tests.
|
||||
*/
|
||||
|
||||
import { mkdtempSync, mkdirSync, rmSync, writeFileSync } from 'node:fs'
|
||||
|
||||
@@ -13,10 +13,8 @@ import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import { Session, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionEventMap, SessionEventType, SurfaceIntent } from '@deepseek-ai/dsh-session'
|
||||
|
||||
// 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.
|
||||
// Each arbitrary supplies its own surface intent; `build` must not synthesize
|
||||
// one or the property would fail to exercise malformed fixture choices.
|
||||
type Appendable = {
|
||||
[T in SessionEventType]: { type: T; data: SessionEventMap[T]; intent?: SurfaceIntent }
|
||||
}[SessionEventType]
|
||||
|
||||
@@ -155,11 +155,8 @@ describe('interruptedTurnClosers', () => {
|
||||
})
|
||||
|
||||
it('handles tool/call without a matching assistant/message entry gracefully', () => {
|
||||
// A tool/call event exists in the log but no assistant/message registered
|
||||
// the callId in pendingCalls (e.g., a plugin appended it directly, or the
|
||||
// assistant/message from a prior step didn't have this call). The repair
|
||||
// should still close the turn — it just won't synthesize a result for this
|
||||
// call (there's nothing to answer).
|
||||
// A raw tool/call with no assistant-registered pending call has nothing to
|
||||
// answer; repair still closes the step and turn without synthesizing a result.
|
||||
const events: SessionEvent[] = [
|
||||
userTurnStart(1, 0),
|
||||
{ type: 'step/start', seq: 1, time: 1, data: { turn: 1, step: 1 } },
|
||||
|
||||
@@ -81,9 +81,6 @@ describe('Session', () => {
|
||||
const before = structuredClone(session.events)
|
||||
|
||||
// A misbehaving consumer tries to mutate the messages it was handed.
|
||||
// Derived messages are frozen shared projections (cloned once off the
|
||||
// log, then deep-frozen): every mutation attempt THROWS in strict mode —
|
||||
// isolation by unrepresentability, not by per-call cloning.
|
||||
const messages = session.deriveMessages()
|
||||
const userBlock = messages[0]!.content[0]!
|
||||
expect(() => { if (userBlock.type === 'text') userBlock.text = 'HACKED' }).toThrow(TypeError)
|
||||
@@ -132,11 +129,8 @@ describe('Session', () => {
|
||||
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.
|
||||
// A widened SessionEventType bypasses the overload's conditional requirement,
|
||||
// so the runtime guard must still reject the missing surface marker.
|
||||
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/)
|
||||
@@ -663,10 +657,8 @@ describe('SessionStore', () => {
|
||||
})
|
||||
|
||||
it('enter() rejects a stale prepared session whose id is already live (no overwrite)', async () => {
|
||||
// prepare()/enter() are public cross-package primitives that a caller may
|
||||
// separate with arbitrary work. A stale prepared session must NOT overwrite
|
||||
// a live store entry of the same id — its detach disposer would later delete
|
||||
// the REAL session, breaking the store-uniqueness invariant.
|
||||
// A stale prepared object must not replace the live same-id entry; its later
|
||||
// detach would otherwise remove the wrong session.
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
const stale = ctx.sessions.prepare(SessionId('racy'))
|
||||
|
||||
Reference in New Issue
Block a user