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

refactor: simplify session log representation

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-13 23:56:10 +08:00
parent d060c0dd4f
commit 1123e946c0
64 changed files with 522 additions and 1032 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
packages/core/agent-loop/src/loop.ts
View File

@@ -170,8 +170,8 @@ export interface LoopHandle {
* boundary = session.deriveMessages() ⟵ the reconstruction boundary: snapshot in the
* session('step/start') same sync frame, strictly before step/start
* config = waterfall agent/request(config) ⟵ frozen seed; a returned replacement switches
* session('request/header'|'request/header-delta') ⟵ the header event this request owes the
* log (initial/resume anchor, delta, fallback)
* session('request/header') ⟵ the header event this request owes the
* log (initial/resume anchor or changed snapshot)
* req = freeze({header..., messages: prefix+boundary, sessionId, signal})
* stream ctx.llm.stream(req) ⟵ waterfall llm/stream (raw chunks, frozen req)
* session('assistant/chunk')
@@ -774,7 +774,7 @@ async function runStep(
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- runTurn composes the prefix before every runStep call
const sessionPrefix = transmission.sessionPrefix!
// The request header (the log's request/header* vocabulary): canonical form,
// The request header (the log's request/header snapshots): canonical form,
// recorded before dispatch so the log always explains the request —
// including the session prefix, which no other event carries.
const header = canonicalHeader({

21
packages/core/agent-loop/src/request-log.ts
View File

@@ -5,12 +5,12 @@
* otherwise transmission-stateless — the comparison baseline is the log's own
* folded header (`Session.requestHeader()`), so resume and fork need no
* special path: a fresh loop instance simply logs a `'resume'` snapshot on
* its first request and deltas from there.
* its first request and full changed-header snapshots from there.
*
* @module dsh-agent-loop/request-log
*/
import { diffHeader, headerEquals, applyHeaderDelta } from '@deepseek-ai/dsh-session'
import { headerEquals } from '@deepseek-ai/dsh-session'
import type { EpochHeader, Session } from '@deepseek-ai/dsh-session'
import type { Message } from '@deepseek-ai/dsh-llm'
@@ -38,7 +38,7 @@ export function createTransmissionLog(): TransmissionLog {
/**
* Append whatever header event this request owes the log, so folding the log
* reproduces the header the request was built under. Exactly one of four
* reproduces the header the request was built under. Exactly one of three
* things happens:
*
* 1. This loop instance has not logged a header yet → a full `request/header`
@@ -48,11 +48,7 @@ export function createTransmissionLog(): TransmissionLog {
* snapshot is appended even when nothing changed).
* 2. The header equals the folded baseline → nothing; the log already
* explains this request.
* 3. It differs and the delta round-trips (`applyHeaderDelta` on the baseline
* reproduces the header exactly) → a `request/header-delta`.
* 4. It differs and the delta encoding cannot express the change (a pure tool
* reordering) → a full snapshot with reason `'fallback'`; deltas are an
* encoding optimization, never a correctness dependency.
* 3. It differs → a full snapshot with reason `'change'`.
*
* @param session - the session whose log explains the request.
* @param state - this loop instance's bookkeeping (mutated on first log).
@@ -69,12 +65,5 @@ export function recordRequestHeader(session: Session, state: TransmissionLog, he
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion
const baseline = session.requestHeader()!
if (headerEquals(baseline, header)) return
const delta = diffHeader(baseline, header)
/* v8 ignore next -- headerEquals false ⟹ diffHeader defined: both compare the same four parts */
if (delta === undefined) return
if (headerEquals(applyHeaderDelta(baseline, delta), header)) {
session.append('request/header-delta', delta)
} else {
session.append('request/header', { header, reason: 'fallback' })
}
session.append('request/header', { header, reason: 'change' })
}

6
packages/core/agent-loop/tests/interception.spec.ts
View File

@@ -374,8 +374,8 @@ describe('agent/session-prefix', () => {
expect(request.messages[0]).toEqual(reminder)
}
// The anchoring snapshot is the prefix's durable record — and the ONLY
// header event: reuse means no request/header-delta ever.
const headerEvents = events(agent).filter(e => e.type === 'request/header' || e.type === 'request/header-delta')
// header event: reuse means no changed snapshot ever.
const headerEvents = events(agent).filter(e => e.type === 'request/header')
expect(headerEvents).toHaveLength(1)
expect(headerEvents[0]?.type === 'request/header' && headerEvents[0].data.header.messagePrefix).toEqual([reminder])
// Never session history: the derivation starts at the real user prompt.
@@ -491,7 +491,7 @@ describe('agent/session-prefix', () => {
// cached prefix is a deep-frozen clone, so step 2's request is unchanged.
held.content = [{ type: 'text', text: 'v2' }]
expect(adapter.requests[1]!.messages[0]).toEqual({ role: 'user', content: [{ type: 'text', text: 'v1' }] })
expect(events(agent).filter(e => e.type === 'request/header-delta')).toHaveLength(0)
expect(events(agent).filter(e => e.type === 'request/header')).toHaveLength(1)
})
})

23
packages/core/agent-loop/tests/request-log.spec.ts
View File

@@ -1,9 +1,8 @@
/**
* recordRequestHeader unit tests: exactly one of four things per request —
* recordRequestHeader unit tests: exactly one of three things per request —
* an 'initial' snapshot (log has no header yet), a 'resume' snapshot (fresh
* loop instance over a log that has one), nothing (header unchanged), a
* round-tripping delta, or a 'fallback' snapshot when the delta encoding
* cannot express the change (pure tool reordering).
* loop instance over a log that has one), nothing (header unchanged), or a
* full 'change' snapshot.
*/
import { describe, expect, it } from 'vitest'
@@ -23,7 +22,7 @@ function openSession(id: string): Session {
}
function headerEvents(session: Session): SessionEvent[] {
return session.events.filter(e => e.type === 'request/header' || e.type === 'request/header-delta')
return session.events.filter(e => e.type === 'request/header')
}
describe('recordRequestHeader', () => {
@@ -53,8 +52,8 @@ describe('recordRequestHeader', () => {
expect(events[1]?.type === 'request/header' && events[1].data.reason).toBe('resume')
})
it('logs a round-tripping delta for a mid-run change, and the fold reproduces the header', () => {
const session = openSession('rl-delta')
it("logs a full 'change' snapshot for a mid-run change, and the fold reproduces the header", () => {
const session = openSession('rl-change')
const state = createTransmissionLog()
const first = canonicalHeader({ config: { model: 'm' }, system: 'a\nb', tools: [tool('t')] })
recordRequestHeader(session, state, first)
@@ -63,12 +62,12 @@ describe('recordRequestHeader', () => {
recordRequestHeader(session, state, second)
const events = headerEvents(session)
expect(events).toHaveLength(2)
expect(events[1]?.type).toBe('request/header-delta')
expect(events[1]?.type === 'request/header' && events[1].data.reason).toBe('change')
expect(session.requestHeader()).toEqual(second)
})
it("records a change the delta cannot express (pure reordering) as a 'fallback' snapshot", () => {
const session = openSession('rl-fallback')
it("records a pure tool reordering as a 'change' snapshot", () => {
const session = openSession('rl-reorder')
const state = createTransmissionLog()
const first = canonicalHeader({ config: { model: 'm' }, tools: [tool('a'), tool('b')] })
recordRequestHeader(session, state, first)
@@ -77,9 +76,7 @@ describe('recordRequestHeader', () => {
recordRequestHeader(session, state, reordered)
const events = headerEvents(session)
expect(events).toHaveLength(2)
expect(events[1]?.type === 'request/header' && events[1].data.reason).toBe('fallback')
// The fold still lands on the exact header — deltas are an encoding
// optimization, never a correctness dependency.
expect(events[1]?.type === 'request/header' && events[1].data.reason).toBe('change')
expect(session.requestHeader()).toEqual(reordered)
})
})

23
packages/core/agent-loop/tests/request-reconstruction.spec.ts
View File

@@ -1,7 +1,7 @@
/**
* Loop-level reconstructability: every request the loop sends is a pure
* function of the session log — messages are the derivation at the step/start
* boundary, the header is the fold of request/header* events — and every
* boundary, the header is the latest request/header snapshot — and every
* request is an append-extension of its predecessor unless a logged event
* (compaction replace, header change) explains the difference. The requests
* recorded by the mock adapter are the observable; the offline-rebuild test
@@ -87,7 +87,7 @@ describe('request stability across the loop', () => {
expect(Object.isFrozen(request.messages)).toBe(true)
}
// One anchoring header snapshot; no further header events (nothing changed).
const headerEvents = agent.session.events.filter(e => e.type === 'request/header' || e.type === 'request/header-delta')
const headerEvents = agent.session.events.filter(e => e.type === 'request/header')
expect(headerEvents).toHaveLength(1)
expect(headerEvents[0]?.type === 'request/header' && headerEvents[0].data.reason).toBe('initial')
})
@@ -124,8 +124,8 @@ describe('request stability across the loop', () => {
content: [{ type: 'text', text: '[summary of turn 1]' }],
source: { kind: 'plugin', plugin: 'test-compact' },
}, {
surfaceOp: { op: 'replace', start: nodes[0]!.seq, end: nodes[1]!.seq },
sourceEventSeqs: [nodes[0]!.seq, nodes[1]!.seq],
surfaceOp: { op: 'replace', start: nodes[0]!, end: nodes[1]! },
sourceEventSeqs: [nodes[0]!, nodes[1]!],
})
})
@@ -139,7 +139,7 @@ describe('request stability across the loop', () => {
expect(agent.session.events.filter(e => e.type === 'request/header')).toHaveLength(1)
})
it('a real system-prompt change is a logged header delta; a stable prompt logs nothing', async () => {
it('a real system-prompt change is a full changed-header snapshot; a stable prompt logs nothing', async () => {
const adapter = new MockAdapter([textResponse('one'), textResponse('two'), textResponse('three')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
@@ -149,14 +149,15 @@ describe('request stability across the loop', () => {
send(agent, 'second')
await waitForIdle(ctx, agent)
// Identical assembly re-rendered per step is NOT a change.
expect(agent.session.events.filter(e => e.type === 'request/header-delta')).toHaveLength(0)
expect(agent.session.events.filter(e => e.type === 'request/header')).toHaveLength(1)
ctx.systemPrompt.section({ name: 'extra', order: 2, text: 'new guidance' })
send(agent, 'third')
await waitForIdle(ctx, agent)
const deltas = agent.session.events.filter(e => e.type === 'request/header-delta')
expect(deltas).toHaveLength(1)
const snapshots = agent.session.events.filter(e => e.type === 'request/header')
expect(snapshots).toHaveLength(2)
expect(snapshots[1]?.data.reason).toBe('change')
expect(adapter.requests[2]!.system).toContain('new guidance')
// History is preserved across the change — only the header moved.
expect(adapter.requests[2]!.messages.length).toBeGreaterThan(adapter.requests[1]!.messages.length)
@@ -262,9 +263,9 @@ describe('request stability across the loop', () => {
send(agent, 'second')
await waitForIdle(ctx, agent)
// No delta was logged (nothing really changed), and the session's own
// No changed snapshot was logged (nothing really changed), and the session's own
// fold is immutable state.
expect(agent.session.events.filter(e => e.type === 'request/header-delta')).toHaveLength(0)
expect(agent.session.events.filter(e => e.type === 'request/header')).toHaveLength(1)
expect(Object.isFrozen(agent.session.requestHeader())).toBe(true)
expect(adapter.requests[1]!.temperature).toBeUndefined()
})
@@ -298,7 +299,7 @@ describe('request stability across the loop', () => {
const rebuilt = new Session(SessionId(`rebuild-${index}`), structuredClone(events.slice(0, stepStart.seq)))
expect(structuredClone(request.messages)).toEqual(rebuilt.deriveMessages())
// Header: the fold of request/header* events up to this step's dispatch
// Header: the latest request/header snapshot up to this step's dispatch
// (its header event sits between step/start and the first chunk).
const firstChunk = events.find(e => e.type === 'assistant/chunk' && e.seq > stepStart.seq)!
const header = foldRequestHeader(events.slice(0, firstChunk.seq))!