Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(invariants): address Codex review of dev invariants (PR 2)

Browse Source 
- HMR state soundness: inject sessions, rebuild per-session trace by replaying
  each existing session's log at (re-)apply, so a reload mid-turn no longer
  falsely rejects the next event
- tighten nesting: turn/end rejects an open step; step/start rejects an open
  step; chunk/message/tool events must name the open turn+step; pendingCalls
  clears at step/end so a cross-step tool/result can't satisfy a stale call
- drop the default export (it stripped the inject metadata when loaded by
  name; functional plugins expose named exports only — matches tool-bash)
- document deepFreeze's top-down precondition; sync RFC 005/008 bodies to the
  as-implemented decision
This commit is contained in:
Tianyi Cui
2026-06-13 23:50:43 +08:00
parent 11a29fdefe
commit 89e63f1436
5 changed files with 167 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

85
packages/invariants/tests/invariants.spec.ts
View File

@@ -3,7 +3,8 @@ import { Context } from 'cordis'
import { CallId } from '@deepseek-ai/dsh-llm'
import type { Agent } from '@deepseek-ai/dsh-agent'
import SessionStore from '@deepseek-ai/dsh-session'
import Invariants, { InvariantError } from '@deepseek-ai/dsh-invariants'
import * as Invariants from '@deepseek-ai/dsh-invariants'
import { InvariantError } from '@deepseek-ai/dsh-invariants'
/** A Context with the session store and the invariants plugin registered. */
async function setup(config?: { freeze?: boolean }) {
@@ -63,7 +64,7 @@ describe('session-log invariants', () => {
const session = ctx.sessions.create()
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
session.append('step/start', { turn: 1, step: 1 })
expect(() => session.append('step/end', { turn: 1, step: 2 })).toThrow(/does not match open step 1/)
expect(() => session.append('step/end', { turn: 1, step: 2 })).toThrow(/open is turn 1\/step 1/)
})
it('rejects an assistant/chunk outside an open step', async () => {
@@ -71,7 +72,7 @@ describe('session-log invariants', () => {
const session = ctx.sessions.create()
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
expect(() => session.append('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'x' } }))
.toThrow(/outside an open step/)
.toThrow(/open is turn 1\/step null/)
})
it('rejects a tool/result with no prior tool/call', async () => {
@@ -114,6 +115,84 @@ describe('session-log invariants', () => {
// b is a fresh session — its own turn/start must not see a's open turn.
expect(() => b.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })).not.toThrow()
})
it('accepts multiple steps in a turn and consecutive turns', async () => {
const { ctx } = await setup({ freeze: false })
const session = ctx.sessions.create()
expect(() => {
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
session.append('step/start', { turn: 1, step: 1 })
session.append('assistant/message', { turn: 1, step: 1, content: [] })
session.append('step/end', { turn: 1, step: 1 })
session.append('step/start', { turn: 1, step: 2 })
session.append('assistant/message', { turn: 1, step: 2, content: [] })
session.append('step/end', { turn: 1, step: 2 })
session.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } })
session.append('turn/end', { turn: 2, reason: { kind: 'completed' } })
}).not.toThrow()
})
it('rejects a turn/end while a step is still open', async () => {
const { ctx } = await setup({ freeze: false })
const session = ctx.sessions.create()
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
session.append('step/start', { turn: 1, step: 1 })
expect(() => session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }))
.toThrow(/while step 1 is still open/)
})
it('rejects a step/start while a step is still open', async () => {
const { ctx } = await setup({ freeze: false })
const session = ctx.sessions.create()
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
session.append('step/start', { turn: 1, step: 1 })
expect(() => session.append('step/start', { turn: 1, step: 2 })).toThrow(/while step 1 is still open/)
})
it('rejects a tool/result satisfying a call from a previous step', async () => {
const { ctx } = await setup({ freeze: false })
const session = ctx.sessions.create()
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
session.append('step/start', { turn: 1, step: 1 })
session.append('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'echo', arguments: '{}' })
// step ends with the call unresolved — pendingCalls is cleared.
session.append('step/end', { turn: 1, step: 1 })
session.append('step/start', { turn: 1, step: 2 })
expect(() => session.append('tool/result', { turn: 1, step: 2, callId: CallId('c1'), content: [], isError: false }))
.toThrow(/no prior tool\/call in this step/)
})
it('rejects an assistant/message naming the wrong step', async () => {
const { ctx } = await setup({ freeze: false })
const session = ctx.sessions.create()
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
session.append('step/start', { turn: 1, step: 1 })
expect(() => session.append('assistant/message', { turn: 1, step: 2, content: [] }))
.toThrow(/open is turn 1\/step 1/)
})
})
describe('HMR state rebuild', () => {
it('rebuilds trace state for a session that exists at (re-)apply time', async () => {
const ctx = new Context()
await ctx.plugin(SessionStore)
// First registration, mid-turn: a turn is open when the plugin reloads.
const first = await ctx.plugin(Invariants, { freeze: false })
const session = ctx.sessions.create()
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
session.append('step/start', { turn: 1, step: 1 })
await first.dispose()
// Re-apply (HMR): the fresh fiber must replay the existing log so the open
// step is known — the next chunk must NOT be a false positive.
await ctx.plugin(Invariants, { freeze: false })
expect(() => session.append('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'h' } }))
.not.toThrow()
// And a genuine violation is still caught after the rebuild.
expect(() => session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }))
.toThrow(/turn 1 is still open/)
})
})
describe('dev-freeze', () => {