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

Merge branch 'worktree/agent-execution-context-rfc' into worktree/explicit-turn-signal

Browse Source
This commit is contained in:
Yichen Jiang
2026-07-18 21:33:17 +08:00
parent 55916f931d a42c28cdc9
commit cddb79e844
683 changed files with 37770 additions and 8712 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
packages/core/session/tests/derived-cache.spec.ts
View File

@@ -23,9 +23,9 @@ describe('derived-message cache', () => {
userText(session, 'one')
expect(session.deriveMessages()).toEqual(scratch(session))
userText(session, 'two')
session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'reply' }] }, { surfaceOp: 'append' })
session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'reply' }] }, { surfaceOp: 'append' })
expect(session.deriveMessages()).toEqual(scratch(session))
session.append('assistant/message', { turn: 1, step: 2, content: [], usage: { inputTokens: 1, outputTokens: 0 } }, { surfaceOp: 'append' })
session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 2, content: [], usage: { inputTokens: 1, outputTokens: 0 } }, { surfaceOp: 'append' })
expect(session.deriveMessages()).toEqual(scratch(session))
})
@@ -40,7 +40,7 @@ describe('derived-message cache', () => {
const nodes = session.surface.nodes
session.append('context/message', {
content: [{ type: 'text', text: 'summary' }], source: { kind: 'plugin', plugin: '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]!] })
expect(session.deriveMessages()).toHaveLength(1)
expect(session.deriveMessages()).toEqual(scratch(session))
@@ -89,7 +89,7 @@ describe('Session.deriveEventMessage — the per-event projection', () => {
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
const boundary = session.append('step/start', { turn: 1, step: 1 })
expect(session.deriveEventMessage(boundary)).toBeNull()
const empty = session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append' })
const empty = session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append' })
expect(session.deriveEventMessage(empty)).toBeNull()
})
})

4
packages/core/session/tests/fork.spec.ts
View File

@@ -195,14 +195,14 @@ describe('SessionStore.fork', () => {
['assistant/message', (session) => {
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: [{ type: 'text', text: 'partial' }] }, { surfaceOp: 'append' })
session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'partial' }] }, { surfaceOp: 'append' })
return lastSeq(session)
}],
['tool/call', (session) => {
const callId = CallId('call-open')
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
session.append('step/start', { turn: 1, step: 1 })
session.append('assistant/message', {
session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' },
turn: 1,
step: 1,
content: [{ type: 'tool-call', id: callId, name: 'bash', arguments: '{}' }],

4
packages/core/session/tests/properties.spec.ts
View File

@@ -28,8 +28,8 @@ const textContentArb = fc.array(
// 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' } }, 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' } })),
textContentArb.map((content): Appendable => ({ type: 'assistant/message', data: { turn: 1, step: 1, content, provenance: { provider: 'mock', model: 'mock' } }, intent: { surfaceOp: 'append' } })),
textContentArb.map((content): Appendable => ({ type: 'assistant/message', data: { turn: 1, step: 1, content, provenance: { provider: 'mock', model: 'mock' }, 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 }, intent: { surfaceOp: 'append' } })),
)

14
packages/core/session/tests/repair.spec.ts
View File

@@ -56,7 +56,7 @@ describe('interruptedTurnClosers', () => {
{ type: 'assistant/message', seq: 2, time: 2, data: { turn: 2, step: 1, content: [
{ type: 'text', text: 'calling a tool' },
{ type: 'tool-call', id: CallId('call-1'), name: 'bash', arguments: '{}' },
] } },
], provenance: { provider: 'mock', model: 'mock' } } },
]
const closers = interruptedTurnClosers(events)
// tool/result (for the orphaned call) → step/end → turn/end, contiguous seqs.
@@ -74,7 +74,7 @@ describe('interruptedTurnClosers', () => {
{ type: 'step/start', seq: 1, time: 1, data: { turn: 2, step: 1 } },
{ type: 'assistant/message', seq: 2, time: 2, data: { turn: 2, step: 1, content: [
{ type: 'tool-call', id: CallId('call-1'), name: 'bash', arguments: '{}' },
] } },
], provenance: { provider: 'mock', model: 'mock' } } },
{ type: 'tool/result', seq: 3, time: 3, data: { turn: 2, step: 1, callId: CallId('call-1'), content: [{ type: 'text', text: 'ok' }], isError: false } },
]
// The call is answered, so only the open step + turn need closing.
@@ -88,7 +88,7 @@ describe('interruptedTurnClosers', () => {
{ type: 'step/start', seq: 1, time: 1, data: { turn: 2, step: 1 } },
{ type: 'assistant/message', seq: 2, time: 2, data: { turn: 2, step: 1, content: [
{ type: 'tool-call', id: CallId('call-1'), name: 'bash', arguments: '{}' },
] } },
], provenance: { provider: 'mock', model: 'mock' } } },
{ type: 'step/end', seq: 3, time: 3, data: { turn: 2, step: 1 } },
]
@@ -105,7 +105,7 @@ describe('interruptedTurnClosers', () => {
{ type: 'step/start', seq: 1, time: 1, data: { turn: 1, step: 1 } },
{ type: 'assistant/message', seq: 2, time: 2, data: { turn: 1, step: 1, content: [
{ type: 'tool-call', id: CallId('old-call'), name: 'bash', arguments: '{}' },
] } },
], provenance: { provider: 'mock', model: 'mock' } } },
{ type: 'tool/result', seq: 3, time: 3, data: { turn: 1, step: 1, callId: CallId('old-call'), content: [], isError: false } },
{ type: 'step/end', seq: 4, time: 4, data: { turn: 1, step: 1 } },
{ type: 'turn/end', seq: 5, time: 5, data: { turn: 1, reason: { kind: 'completed' } } },
@@ -113,7 +113,7 @@ describe('interruptedTurnClosers', () => {
{ type: 'step/start', seq: 7, time: 7, data: { turn: 2, step: 1 } },
{ type: 'assistant/message', seq: 8, time: 8, data: { turn: 2, step: 1, content: [
{ type: 'tool-call', id: CallId('new-call'), name: 'bash', arguments: '{}' },
] } },
], provenance: { provider: 'mock', model: 'mock' } } },
]
const closers = interruptedTurnClosers(events)
expect(closers.map(e => e.type)).toEqual(['tool/result', 'step/end', 'turn/end'])
@@ -128,7 +128,7 @@ describe('interruptedTurnClosers', () => {
{ type: 'assistant/message', seq: 2, time: 2, data: { turn: 1, step: 1, content: [
{ type: 'tool-call', id: CallId('call-a'), name: 'bash', arguments: '{}' },
{ type: 'tool-call', id: CallId('call-b'), name: 'bash', arguments: '{}' },
] } },
], provenance: { provider: 'mock', model: 'mock' } } },
// call-a got answered before the crash; call-b did not.
{ type: 'tool/result', seq: 3, time: 3, data: { turn: 1, step: 1, callId: CallId('call-a'), content: [], isError: false } },
]
@@ -144,7 +144,7 @@ describe('interruptedTurnClosers', () => {
{ type: 'step/start', seq: 1, time: 1, data: { turn: 1, step: 1 } },
{ type: 'assistant/message', seq: 2, time: 2, data: { turn: 1, step: 1, content: [
{ type: 'tool-call', id: CallId('call-1'), name: 'bash', arguments: '{}' },
] } },
], provenance: { provider: 'mock', model: 'mock' } } },
{ type: 'tool/call', seq: 3, time: 3, data: { turn: 1, step: 1, callId: CallId('call-1'), name: 'bash', arguments: '{}' } },
]
const closers = interruptedTurnClosers(events)

215
packages/core/session/tests/request-header.spec.ts
View File

@@ -1,18 +1,11 @@
/**
* Request-header utility tests: canonical form, the system line-diff
* (prefix/suffix trim), the name-keyed tools delta, config replacement, the
* round-trip contract (including the reorder case the encoding cannot
* express), and the log fold. These pin the reconstruction algebra: for every
* logged delta, apply(prev, delta) === next, and folding a log prefix yields
* the header its next request was built under.
*/
/** Request-header canonicalization, equality, snapshot folding, and format rejection. */
import { describe, expect, it } from 'vitest'
import { Session, SessionId, applyHeaderDelta, canonicalHeader, diffHeader, foldRequestHeader, headerEquals } from '@deepseek-ai/dsh-session'
import { Session, SessionId, canonicalHeader, foldRequestHeader, headerEquals } from '@deepseek-ai/dsh-session'
import type { EpochHeader, SessionEvent } from '@deepseek-ai/dsh-session'
import type { Message, ToolSchema } from '@deepseek-ai/dsh-llm'
const CONFIG = { model: 'm' }
const CONFIG = { provider: 'mock', model: 'm' }
function tool(name: string, description = 'd'): ToolSchema {
return { name, description, parameters: { type: 'object' } }
@@ -22,165 +15,77 @@ function msg(text: string): Message {
return { role: 'user', content: [{ type: 'text', text }] }
}
/** Round-trip helper: diff must reproduce `next` from `prev` exactly. */
function roundTrip(prev: EpochHeader, next: EpochHeader): ReturnType<typeof diffHeader> {
const delta = diffHeader(prev, next)
if (delta !== undefined) {
expect(applyHeaderDelta(prev, delta)).toEqual(canonicalHeader(next))
}
return delta
}
describe('canonicalHeader', () => {
it('normalizes empty system and empty tools to absent fields', () => {
expect(canonicalHeader({ config: CONFIG, system: '', tools: [] })).toEqual({ config: CONFIG })
const full = canonicalHeader({ config: CONFIG, system: 's', tools: [tool('a')] })
expect(full.system).toBe('s')
expect(full.tools).toHaveLength(1)
it('normalizes empty optional fields to absence and preserves populated fields', () => {
expect(canonicalHeader({ config: CONFIG, system: '', tools: [], messagePrefix: [] })).toEqual({ config: CONFIG })
const full = canonicalHeader({ config: CONFIG, system: 's', tools: [tool('a')], messagePrefix: [msg('p')] })
expect(full).toEqual({ config: CONFIG, system: 's', tools: [tool('a')], messagePrefix: [msg('p')] })
})
})
describe('diffHeader / applyHeaderDelta', () => {
it('returns undefined for equal headers', () => {
const header = canonicalHeader({ config: CONFIG, system: 'a\nb', tools: [tool('t')] })
expect(diffHeader(header, header)).toBeUndefined()
describe('headerEquals', () => {
const base = canonicalHeader({ config: CONFIG, system: 's', tools: [tool('a')], messagePrefix: [msg('p')] })
it('compares every canonical field and preserves tool order', () => {
expect(headerEquals(base, structuredClone(base))).toBe(true)
expect(headerEquals(base, { ...base, config: { provider: 'mock', model: 'other' } })).toBe(false)
expect(headerEquals(base, { ...base, system: 'other' })).toBe(false)
expect(headerEquals(base, { ...base, messagePrefix: [msg('other')] })).toBe(false)
expect(headerEquals(base, { ...base, tools: [] })).toBe(false)
expect(headerEquals(base, { ...base, tools: [tool('a', 'changed')] })).toBe(false)
expect(headerEquals({ config: CONFIG, tools: [tool('a'), tool('b')] }, { config: CONFIG, tools: [tool('b'), tool('a')] })).toBe(false)
})
it('encodes a mid-prompt line change as a prefix/suffix trim', () => {
const prev = canonicalHeader({ config: CONFIG, system: 'keep1\nold\nkeep2\nkeep3' })
const next = canonicalHeader({ config: CONFIG, system: 'keep1\nnew A\nnew B\nkeep2\nkeep3' })
const delta = roundTrip(prev, next)
expect(delta?.system).toEqual({ keepStart: 1, keepEnd: 2, insert: ['new A', 'new B'] })
expect(delta?.tools).toBeUndefined()
expect(delta?.config).toBeUndefined()
})
it('degenerates to a full replacement when nothing is shared, and round-trips absence transitions', () => {
const none = canonicalHeader({ config: CONFIG })
const some = canonicalHeader({ config: CONFIG, system: 'x\ny' })
const gained = roundTrip(none, some)
expect(gained?.system).toEqual({ keepStart: 0, keepEnd: 0, insert: ['x', 'y'] })
const lost = roundTrip(some, none)
expect(lost?.system).toEqual({ keepStart: 0, keepEnd: 0, insert: [] })
})
it('does not double-count overlapping prefix and suffix (repeated lines)', () => {
const prev = canonicalHeader({ config: CONFIG, system: 'a\na' })
const next = canonicalHeader({ config: CONFIG, system: 'a\na\na' })
roundTrip(prev, next)
})
it('encodes tool addition, removal, and in-place schema change by name', () => {
const prev = canonicalHeader({ config: CONFIG, tools: [tool('keep'), tool('drop'), tool('edit', 'before')] })
const next = canonicalHeader({ config: CONFIG, tools: [tool('keep'), tool('edit', 'after'), tool('new')] })
const delta = roundTrip(prev, next)
expect(delta?.tools?.added.map(t => t.name)).toEqual(['new'])
expect(delta?.tools?.removed).toEqual(['drop'])
expect(delta?.tools?.changed.map(t => t.name)).toEqual(['edit'])
})
it('round-trips a tool set gained from a tool-less header and lost back to one', () => {
const none = canonicalHeader({ config: CONFIG })
const some = canonicalHeader({ config: CONFIG, tools: [tool('t')] })
const gained = roundTrip(none, some)
expect(gained?.tools?.added.map(t => t.name)).toEqual(['t'])
const lost = roundTrip(some, none)
expect(lost?.tools?.removed).toEqual(['t'])
})
it('cannot express a pure reordering — the writer detects it via the round-trip check', () => {
const prev = canonicalHeader({ config: CONFIG, tools: [tool('a'), tool('b')] })
const next = canonicalHeader({ config: CONFIG, tools: [tool('b'), tool('a')] })
const delta = diffHeader(prev, next)
// A delta IS produced (the lists differ)…
expect(delta).toBeDefined()
// …but applying it cannot reproduce the new order — exactly the case the
// writer's guard turns into a 'fallback' snapshot.
expect(applyHeaderDelta(prev, delta!)).not.toEqual(next)
})
it('replaces the config whole and leaves untouched parts alone', () => {
const prev = canonicalHeader({ config: { model: 'm' }, system: 's', tools: [tool('t')] })
const next = canonicalHeader({ config: { model: 'm2', temperature: 0.1 }, system: 's', tools: [tool('t')] })
const delta = roundTrip(prev, next)
expect(delta).toEqual({ config: { model: 'm2', temperature: 0.1 } })
})
})
describe('the session prefix (messagePrefix)', () => {
it('canonicalHeader normalizes an empty prefix to an absent field', () => {
expect(canonicalHeader({ config: CONFIG, messagePrefix: [] })).toEqual({ config: CONFIG })
const full = canonicalHeader({ config: CONFIG, messagePrefix: [msg('p')] })
expect(full.messagePrefix).toEqual([msg('p')])
})
it('headerEquals treats absence and empty as one representation, content differences as unequal', () => {
expect(headerEquals(canonicalHeader({ config: CONFIG }), { config: CONFIG, messagePrefix: [] })).toBe(true)
expect(headerEquals({ config: CONFIG, messagePrefix: [msg('a')] }, { config: CONFIG, messagePrefix: [msg('b')] })).toBe(false)
expect(headerEquals({ config: CONFIG, messagePrefix: [msg('a')] }, { config: CONFIG })).toBe(false)
})
it('replaces a changed prefix whole and leaves untouched parts alone', () => {
const prev = canonicalHeader({ config: CONFIG, system: 'keep', messagePrefix: [msg('old')] })
const next = canonicalHeader({ config: CONFIG, system: 'keep', messagePrefix: [msg('new'), msg('more')] })
const delta = roundTrip(prev, next)
expect(delta).toEqual({ messagePrefix: [msg('new'), msg('more')] })
})
it('round-trips a prefix gained from a bare header and lost back to one (empty array encodes absence)', () => {
const none = canonicalHeader({ config: CONFIG })
const some = canonicalHeader({ config: CONFIG, messagePrefix: [msg('p')] })
const gained = roundTrip(none, some)
expect(gained).toEqual({ messagePrefix: [msg('p')] })
const lost = roundTrip(some, none)
expect(lost).toEqual({ messagePrefix: [] })
})
it('folds prefix deltas over the log like any other header amendment', () => {
const session = new Session(SessionId('fold-prefix'))
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
const first = canonicalHeader({ config: CONFIG, messagePrefix: [msg('catalog v1')] })
session.append('request/header', { header: first, reason: 'initial' })
const second = canonicalHeader({ config: CONFIG, messagePrefix: [msg('catalog v2')] })
session.append('request/header-delta', diffHeader(first, second)!)
expect(foldRequestHeader(session.events)).toEqual(second)
session.append('request/header-delta', diffHeader(second, canonicalHeader({ config: CONFIG }))!)
expect(foldRequestHeader(session.events)).toEqual({ config: CONFIG })
it('treats absent and empty prefix/tool arrays as equivalent canonical absence', () => {
expect(headerEquals({ config: CONFIG }, { config: CONFIG, tools: [], messagePrefix: [] })).toBe(true)
})
})
describe('foldRequestHeader', () => {
function headerEvents(session: Session): readonly SessionEvent[] {
return session.events
}
it('returns undefined on a log with no header events', () => {
const session = new Session(SessionId('fold-none'))
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
expect(foldRequestHeader(headerEvents(session))).toBeUndefined()
it('returns the supplied baseline when no snapshot follows', () => {
const from: EpochHeader = { config: CONFIG, system: 'baseline' }
const unrelated: SessionEvent[] = [
{ type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } },
]
expect(foldRequestHeader(unrelated)).toBeUndefined()
expect(foldRequestHeader(unrelated, from)).toBe(from)
})
it('folds snapshot then deltas into the header in force, skipping unrelated events', () => {
it('takes the latest full snapshot and skips unrelated events', () => {
const session = new Session(SessionId('fold'))
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
const first = canonicalHeader({ config: { model: 'm' }, system: 'a\nb', tools: [tool('t')] })
session.append('request/header', { header: first, reason: 'initial' })
session.append('request/header', { header: { config: CONFIG, system: 'first' }, reason: 'initial' })
session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
const second = canonicalHeader({ config: { model: 'm' }, system: 'a\nc', tools: [tool('t')] })
session.append('request/header-delta', diffHeader(first, second)!)
expect(foldRequestHeader(headerEvents(session))).toEqual(second)
// A later snapshot replaces the state wholesale (the 'resume'/'fallback' anchor).
const third = canonicalHeader({ config: { model: 'other' } })
session.append('request/header', { header: third, reason: 'resume' })
expect(foldRequestHeader(headerEvents(session))).toEqual(third)
})
it('throws on a delta before any snapshot (corrupt log)', () => {
const session = new Session(SessionId('fold-corrupt'))
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
session.append('request/header-delta', { config: { model: 'x' } })
expect(() => foldRequestHeader(headerEvents(session))).toThrow(/before any request\/header snapshot/)
session.append('request/header', { header: { config: { provider: 'mock', model: 'other' }, tools: [] }, reason: 'change' })
expect(foldRequestHeader(session.events)).toEqual({ config: { provider: 'mock', model: 'other' } })
})
})
describe('legacy request-header format', () => {
it('rejects request/header-delta in seeds and untyped appends', () => {
const legacy = [{
type: 'request/header-delta', seq: 0, time: 1, data: { config: CONFIG },
}] as unknown as SessionEvent[]
expect(() => new Session(SessionId('legacy'), legacy)).toThrow(/unsupported legacy request\/header-delta/)
const session = new Session(SessionId('legacy-append-delta'))
const appendLegacy = session.append.bind(session) as (type: string, data: unknown) => SessionEvent
expect(() => appendLegacy('request/header-delta', { config: CONFIG }))
.toThrow(/unsupported legacy request\/header-delta/)
expect(session.events).toHaveLength(0)
})
it('rejects the removed fallback reason in seeds and untyped appends', () => {
const legacy = [{
type: 'request/header', seq: 0, time: 1, data: { header: { config: CONFIG }, reason: 'fallback' },
}] as unknown as SessionEvent[]
expect(() => new Session(SessionId('legacy-seed-reason'), legacy))
.toThrow('unsupported legacy request/header reason "fallback"')
const session = new Session(SessionId('legacy-append-reason'))
const appendLegacy = session.append.bind(session) as (type: string, data: unknown) => SessionEvent
expect(() => appendLegacy('request/header', { header: { config: CONFIG }, reason: 'fallback' }))
.toThrow('unsupported legacy request/header reason "fallback"')
expect(session.events).toHaveLength(0)
})
})

96
packages/core/session/tests/session.spec.ts
View File

@@ -10,7 +10,7 @@ describe('Session', () => {
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
session.append('user/message', { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
session.append('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'hi' } })
session.append('assistant/message', {
session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' },
turn: 1, step: 1,
content: [
{ type: 'text', text: 'let me check' },
@@ -69,11 +69,33 @@ describe('Session', () => {
expect(steeringMessage!.content[0]).toMatchObject({ type: 'text', text: '<steering source="user">' })
})
it('renders raw context without a generic envelope while preserving structured metadata', () => {
const session = new Session(SessionId('s2-raw'))
const meta = {
kind: 'workspace-instructions',
version: 1,
changes: [{ action: 'set', scope: 'pkg', path: 'pkg/AGENTS.md', digest: 'abc123' }],
}
session.append('context/message', {
content: [{ type: 'text', text: '<system-reminder>Additional instructions from: pkg/AGENTS.md</system-reminder>' }],
source: { kind: 'plugin', plugin: 'workspace-context' },
envelope: 'raw',
meta,
}, { surfaceOp: 'append' })
expect(session.deriveMessages()).toEqual([{
role: 'user',
content: [{ type: 'text', text: '<system-reminder>Additional instructions from: pkg/AGENTS.md</system-reminder>' }],
}])
const event = session.events[0]
expect(event?.type === 'context/message' && event.data.meta).toEqual(meta)
})
it('replays identically from a seeded event log', () => {
const original = new Session(SessionId('s3'))
original.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
original.append('user/message', { content: [{ type: 'text', text: 'q' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
original.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, { surfaceOp: 'append' })
original.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, { surfaceOp: 'append' })
original.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
const replayed = new Session(SessionId('s3-replay'), [...original.events])
@@ -81,6 +103,36 @@ describe('Session', () => {
expect(replayed.seq).toBe(original.seq)
})
it('rejects pre-provider request headers and assistant messages on seed/load', () => {
const requestHeader = {
type: 'request/header', seq: 0, time: 1,
data: { header: { config: { model: 'old-model' } }, reason: 'initial' },
} as unknown as SessionEvent
expect(() => new Session(SessionId('old-header'), [requestHeader]))
.toThrow('seed request/header at index 0 lacks provider/model')
const assistantMessage = {
type: 'assistant/message', seq: 0, time: 1,
data: { turn: 1, step: 1, content: [{ type: 'text', text: 'old' }] },
surfaceOp: 'append',
} as unknown as SessionEvent
expect(() => new Session(SessionId('old-assistant'), [assistantMessage]))
.toThrow('seed assistant/message at index 0 lacks provider/model provenance')
const malformedHeader = {
type: 'request/header', seq: 0, time: 1,
data: { header: 'old-header' },
} as unknown as SessionEvent
expect(() => new Session(SessionId('malformed-header'), [malformedHeader]))
.toThrow('seed request/header at index 0 lacks provider/model')
const unrelatedPrimitiveData = {
type: 'plugin/event', seq: 0, time: 1, data: null,
} as unknown as SessionEvent
expect(new Session(SessionId('primitive-plugin-data'), [unrelatedPrimitiveData]).events)
.toEqual([unrelatedPrimitiveData])
})
it('isolates the log from mutation through a derived message (append-only contract)', () => {
const session = new Session(SessionId('s4'))
session.append('user/message', { content: [{ type: 'text', text: 'original' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
@@ -305,35 +357,52 @@ describe('Session', () => {
type: 'user/message',
seq: 0,
time: 1,
data: { content: [{ type: 'text', text: 'source' }], source: { kind: 'user' } },
surfaceOp: 'append',
}, {
type: 'user/message',
seq: 1,
time: 2,
data: { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } },
surfaceOp,
sourceEventSeqs: [0],
}] as unknown as SessionEvent[]
const session = new Session(SessionId('seed-unstable-metadata'), seed)
const event = session.events[0]!
const event = session.events[1]!
if (event.type !== 'user/message') throw new Error('test fixture must remain a user/message')
expect(reads).toBe(1)
expect(event.surfaceOp).toEqual({ op: 'replace', start: 0, end: 0 })
})
it('adds seed context when surface validation throws a non-Error value', () => {
it.each([
['an Error', new Error('validator failed'), 'validator failed'],
['a non-Error value', 'validator failed', 'invalid surface metadata'],
] as const)('adds seed context when surface validation throws %s', (_name, failure, expected) => {
const originalHasOwn = Object.hasOwn
const hasOwn = vi.spyOn(Object, 'hasOwn').mockImplementation((object: object, property: PropertyKey): boolean => {
if ((object as Record<string, unknown>)['op'] === 'replace') throw 'validator failed'
if ((object as Record<string, unknown>)['op'] === 'replace') throw failure
return originalHasOwn(object, property)
})
const seed = [{
type: 'user/message',
seq: 0,
time: 1,
data: { content: [{ type: 'text', text: 'source' }], source: { kind: 'user' } },
surfaceOp: 'append',
}, {
type: 'user/message',
seq: 1,
time: 2,
data: { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } },
surfaceOp: { op: 'replace', start: 0, end: 0 },
sourceEventSeqs: [0],
}] as unknown as SessionEvent[]
try {
expect(() => new Session(SessionId('seed-non-error-metadata-failure'), seed))
.toThrow('invalid seed event at index 0: invalid surface metadata')
.toThrow(`invalid seed event at index 1: ${expected}`)
} finally {
hasOwn.mockRestore()
}
@@ -419,6 +488,11 @@ describe('Session', () => {
it('reads a nested append-metadata getter once and stores its first JSON value', () => {
const session = new Session(SessionId('append-unstable-metadata'))
const source = session.append(
'user/message',
{ content: [{ type: 'text', text: 'source' }], source: { kind: 'user' } },
{ surfaceOp: 'append' },
)
let reads = 0
const surfaceOp = Object.defineProperty({ op: 'replace', end: 0 }, 'start', {
enumerable: true,
@@ -431,12 +505,12 @@ describe('Session', () => {
const event = session.append(
'user/message',
{ content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } },
{ surfaceOp } as never,
{ surfaceOp, sourceEventSeqs: [0] } as never,
)
expect(reads).toBe(1)
expect(event.surfaceOp).toEqual({ op: 'replace', start: 0, end: 0 })
expect(session.events).toEqual([event])
expect(session.events).toEqual([source, event])
})
it('rejects invalid plain surface metadata shapes at append', () => {
@@ -472,7 +546,7 @@ describe('Session', () => {
'turn/start',
{ turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } },
{ surfaceOp: 'append' },
)).toThrow(/not surface-eligible and cannot carry surface metadata/)
)).toThrow(/not surface-eligible and cannot carry surfaceOp/)
expect(() => new Session(SessionId('non-surface-metadata-seed'), [{
type: 'turn/start',
seq: 0,
@@ -1173,8 +1247,8 @@ describe('todo/write event', () => {
session.append('todo/write', { todos: [{ content: 'a task', status: 'pending' }] })
// The todo event must not add a message to the derived history…
expect(session.deriveMessages()).toHaveLength(before)
// …and must not appear on the surface linked list.
expect(session.surface.nodes.some(node => node.seq === session.seq - 1)).toBe(false)
// …and must not appear on the ordered surface.
expect(session.surface.nodes).not.toContain(session.seq - 1)
})
it('round-trips through a seeded replay identically (durable, no surfaceOp needed)', () => {

252
packages/core/session/tests/surface.spec.ts
View File

@@ -1,6 +1,12 @@
import { describe, expect, it } from 'vitest'
import type { SessionEvent, SurfaceEvent, SurfaceEventType } from '@deepseek-ai/dsh-session'
import { Session, SessionId, foldSurface, isSurfaceEligibleType, isSurfaceEvent } from '@deepseek-ai/dsh-session'
import {
Session,
SessionId,
foldSurface,
isSurfaceEligibleType,
isSurfaceEvent,
} from '@deepseek-ai/dsh-session'
import { CallId } from '@deepseek-ai/dsh-llm'
/** Build a minimal session with turn boundaries and a single user message. */
@@ -8,18 +14,93 @@ function surfaceSession(): Session {
const s = new Session(SessionId('ss'))
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
s.append('user/message', { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'hi' }] }, { surfaceOp: 'append' })
s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'hi' }] }, { surfaceOp: 'append' })
s.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
return s
}
function provenanceEvent(seq: number, sourceEventSeqs: unknown): SessionEvent {
return {
type: 'user/message',
seq,
time: seq,
data: { content: [], source: { kind: 'user' } },
surfaceOp: 'append',
...sourceEventSeqs === undefined ? {} : { sourceEventSeqs },
} as unknown as SessionEvent
}
describe('foldSurface provenance', () => {
it('accepts absent or valid provenance and complete replacement coverage', () => {
const events = [
provenanceEvent(0, undefined),
provenanceEvent(1, undefined),
{
...provenanceEvent(2, [0, 1]),
surfaceOp: { op: 'replace', start: 0, end: 1 },
},
] as SessionEvent[]
expect(() => foldSurface(events)).not.toThrow()
})
it('rejects provenance on a non-surface event', () => {
const event = {
type: 'turn/start',
seq: 0,
time: 1,
data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } },
sourceEventSeqs: [0],
} as unknown as SessionEvent
expect(() => foldSurface([event])).toThrow(/cannot carry sourceEventSeqs/)
})
it('accepts explicit empty provenance on an assistant message', () => {
const event = {
type: 'assistant/message',
seq: 0,
time: 0,
data: {
provenance: { provider: 'mock', model: 'mock' },
turn: 1,
step: 1,
content: [],
},
surfaceOp: 'append',
sourceEventSeqs: [],
} as SessionEvent
expect(() => foldSurface([event])).not.toThrow()
})
it.each([
['a non-array', [{ ...provenanceEvent(0, undefined), sourceEventSeqs: 'invalid' }], /must be an array/],
['an empty array', [provenanceEvent(0, [])], /must not be empty/],
['duplicates', [provenanceEvent(0, undefined), provenanceEvent(1, [0, 0])], /must not contain duplicates/],
['a sparse array', [provenanceEvent(0, Array<number>(1))], /densely contain/],
['a non-number', [{ ...provenanceEvent(0, undefined), sourceEventSeqs: ['0'] }], /non-negative safe integers/],
['a fractional number', [provenanceEvent(0, [0.5])], /non-negative safe integers/],
['a negative number', [provenanceEvent(0, [-1])], /non-negative safe integers/],
['a self reference', [provenanceEvent(0, [0])], /must reference earlier events/],
['a non-contiguous event seq', [provenanceEvent(0, undefined), provenanceEvent(2, [1])], /seq 2 is not contiguous; expected 1/],
['incomplete replacement coverage', [
provenanceEvent(0, undefined),
provenanceEvent(1, undefined),
{ ...provenanceEvent(2, [0]), surfaceOp: { op: 'replace', start: 0, end: 1 } },
], /missing 1/],
] as const)(
'rejects %s',
(_name, events, expected) => {
expect(() => foldSurface(events as unknown as SessionEvent[])).toThrow(expected)
},
)
})
describe('SurfaceManager', () => {
it('shares exact nodes and nested replacement ranges with foldSurface', () => {
it('shares ordered entries and nested replacement ranges with foldSurface', () => {
const s = new Session(SessionId('shared-fold'))
s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'summary' }] }, { surfaceOp: { op: 'replace', start: 0, end: 0 }, sourceEventSeqs: [0] })
s.append('assistant/message', { turn: 1, step: 2, content: [{ type: 'text', text: 'summary 2' }] }, { surfaceOp: { op: 'replace', start: 2, end: 1 }, sourceEventSeqs: [2, 1] })
s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'summary' }] }, { surfaceOp: { op: 'replace', start: 0, end: 0 }, sourceEventSeqs: [0] })
s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 2, content: [{ type: 'text', text: 'summary 2' }] }, { surfaceOp: { op: 'replace', start: 2, end: 1 }, sourceEventSeqs: [2, 1] })
const folded = foldSurface(s.events)
expect(folded.nodes).toEqual(s.surface.nodes)
@@ -27,18 +108,19 @@ describe('SurfaceManager', () => {
{ seq: 2, start: 0, end: 0, shadowedSeqs: [0] },
{ seq: 3, start: 2, end: 1, shadowedSeqs: [2, 1] },
])
folded.nodes[0]!.next = 99
folded.nodes[0] = 99
folded.replacements[0]!.shadowedSeqs.push(99)
expect(s.surface.nodes).toEqual([{ seq: 3, prev: null, next: null }])
expect(s.surface.nodes).toEqual([3])
expect(foldSurface(s.events).nodes).toEqual([3])
expect(foldSurface(s.events).replacements[0]!.shadowedSeqs).toEqual([0])
})
it('does not retain fold-only replacement history in incremental state', () => {
const s = new Session(SessionId('incremental-state'))
s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'b' }] }, { surfaceOp: { op: 'replace', start: 0, end: 0 } })
s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'b' }] }, { surfaceOp: { op: 'replace', start: 0, end: 0 }, sourceEventSeqs: [0] })
expect(s.surface.nodes).toEqual([{ seq: 1, prev: null, next: null }])
expect(s.surface.nodes).toEqual([1])
const manager = s.surface as unknown as { _state: object }
expect(Object.hasOwn(manager._state, 'replacements')).toBe(false)
expect(foldSurface(s.events).replacements).toEqual([
@@ -47,12 +129,29 @@ describe('SurfaceManager', () => {
})
it('foldSurface reports the same invalid replacement failures as the incremental manager', () => {
const s = new Session(SessionId('shared-fold-invalid'))
s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
s.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 42, end: 0 }, sourceEventSeqs: [0] })
const events = [
provenanceEvent(0, undefined),
{ ...provenanceEvent(1, [0]), surfaceOp: { op: 'replace', start: 42, end: 0 } },
] as SessionEvent[]
expect(() => foldSurface(s.events)).toThrow(/start seq 42 not found/)
expect(() => s.surface.nodes).toThrow(/start seq 42 not found/)
expect(() => foldSurface(events)).toThrow(/start seq 42 not found/)
expect(() => new Session(SessionId('shared-fold-invalid'), events))
.toThrow(/start seq 42 not found/)
})
it('leaves incremental state unchanged when candidate validation fails', () => {
const s = new Session(SessionId('atomic-validation'))
s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
expect(() => s.append(
'assistant/message',
{ provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'invalid' }] },
{ surfaceOp: { op: 'replace', start: 0, end: 0 } },
)).toThrow(/missing 0/)
expect(s.events).toHaveLength(1)
s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
expect(s.surface.nodes).toEqual([0, 1])
})
it('foldSurface rejects a surface-eligible event without its mandatory marker', () => {
@@ -64,21 +163,28 @@ describe('SurfaceManager', () => {
}
expect(() => foldSurface([malformed]))
.toThrow(/surface event "user\/message" \(seq 0\) carries no surfaceOp marker/)
.toThrow(/surface-eligible and requires a surfaceOp marker/)
})
it('rebuilds a linked list from surfaceOp: append markers', () => {
it('foldSurface rejects surfaceOp on a non-surface event', () => {
const malformed = {
type: 'turn/start',
seq: 0,
time: 1,
data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } },
surfaceOp: 'append',
} as unknown as SessionEvent
expect(() => foldSurface([malformed]))
.toThrow(/not surface-eligible and cannot carry surfaceOp/)
})
it('folds an ordered sequence list from surfaceOp: append markers', () => {
const s = surfaceSession()
const nodes = s.surface.nodes
// Only the user/message and assistant/message carry surfaceOp: 'append'.
// The turn boundaries do not have surface markers.
expect(nodes.length).toBe(2)
expect(nodes[0]!.seq).toBe(1) // user/message (turn/start is seq 0)
expect(nodes[0]!.prev).toBeNull()
expect(nodes[0]!.next).toBe(2) // assistant/message (seq 2)
expect(nodes[1]!.seq).toBe(2)
expect(nodes[1]!.prev).toBe(1)
expect(nodes[1]!.next).toBeNull()
expect(nodes).toEqual([1, 2])
})
it('empty surface yields empty nodes', () => {
@@ -99,9 +205,7 @@ describe('SurfaceManager', () => {
// Append another surface node
s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'ok' }], isError: false }, { surfaceOp: 'append' })
expect(s.surface.nodes.length).toBe(3)
expect(s.surface.nodes[2]!.seq).toBe(4) // seq 4: after turn/end at seq 3
expect(s.surface.nodes[2]!.prev).toBe(2)
expect(s.surface.nodes[1]!.next).toBe(4)
expect(s.surface.nodes[2]!).toBe(4) // seq 4: after turn/end at seq 3
})
it('replays identically from a seeded log with surface markers', () => {
@@ -109,21 +213,17 @@ describe('SurfaceManager', () => {
original.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'ok' }], isError: false }, { surfaceOp: 'append' })
const replayed = new Session(SessionId('replay'), [...original.events])
// Surface rebuilds from the seeded log's markers.
expect(replayed.surface.nodes.map(n => n.seq)).toEqual([1, 2, 4])
expect(replayed.surface.nodes).toEqual([1, 2, 4])
expect(replayed.deriveMessages()).toEqual(original.deriveMessages())
})
it('rebuild with replace operation splices out shadowed nodes', () => {
const s = surfaceSession()
// Replace surface seqs 1 (user) and 2 (assistant) with the summary.
s.append('assistant/message',
{ turn: 2, step: 1, content: [{ type: 'text', text: 'summary' }] },
{ provenance: { provider: 'mock', model: 'mock' }, turn: 2, step: 1, content: [{ type: 'text', text: 'summary' }] },
{ surfaceOp: { op: 'replace', start: 1, end: 2 }, sourceEventSeqs: [1, 2] },
)
expect(s.surface.nodes.length).toBe(1)
expect(s.surface.nodes[0]!.seq).toBe(4) // seq of the compaction marker
expect(s.surface.nodes[0]!.prev).toBeNull()
expect(s.surface.nodes[0]!.next).toBeNull()
expect(s.surface.nodes).toEqual([4])
})
it('replace with both ends at real nodes splices only the range', () => {
@@ -133,15 +233,10 @@ describe('SurfaceManager', () => {
s.append('user/message', { content: [{ type: 'text', text: 'c' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2
// Replace seq 0 through 1 inclusive: shadow a and b, keep c.
s.append('assistant/message',
{ turn: 1, step: 1, content: [{ type: 'text', text: 'summary' }] },
{ provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'summary' }] },
{ surfaceOp: { op: 'replace', start: 0, end: 1 }, sourceEventSeqs: [0, 1] },
) // seq 3
expect(s.surface.nodes.map(n => n.seq)).toEqual([3, 2])
// Links: 3 ↔ 2
expect(s.surface.nodes[0]!.prev).toBeNull()
expect(s.surface.nodes[0]!.next).toBe(2)
expect(s.surface.nodes[1]!.prev).toBe(3)
expect(s.surface.nodes[1]!.next).toBeNull()
expect(s.surface.nodes).toEqual([3, 2])
})
it('single-node replacement (start === end)', () => {
@@ -150,32 +245,28 @@ describe('SurfaceManager', () => {
s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 1
// Replace only seq 1 (single node).
s.append('assistant/message',
{ turn: 1, step: 1, content: [{ type: 'text', text: 'x' }] },
{ provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'x' }] },
{ surfaceOp: { op: 'replace', start: 1, end: 1 }, sourceEventSeqs: [1] },
) // seq 2
expect(s.surface.nodes.map(n => n.seq)).toEqual([0, 2])
expect(s.surface.nodes[0]!.next).toBe(2)
expect(s.surface.nodes[1]!.prev).toBe(0)
expect(s.surface.nodes).toEqual([0, 2])
})
it('throws when replace start is not found', () => {
const s = new Session(SessionId('bad-start'))
s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 0
s.append('assistant/message',
{ turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] },
{ surfaceOp: { op: 'replace', start: 5, end: 0 }, sourceEventSeqs: [5, 0] },
)
expect(() => s.surface.nodes).toThrow(/surface replace: start seq 5 not found/)
expect(() => s.append('assistant/message',
{ provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] },
{ surfaceOp: { op: 'replace', start: 5, end: 0 }, sourceEventSeqs: [0] },
)).toThrow(/surface replace: start seq 5 not found/)
})
it('throws when replace end is not found', () => {
const s = new Session(SessionId('bad-end'))
s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 0
s.append('assistant/message',
{ turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] },
expect(() => s.append('assistant/message',
{ provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] },
{ surfaceOp: { op: 'replace', start: 0, end: 99 }, sourceEventSeqs: [0] },
)
expect(() => s.surface.nodes).toThrow(/surface replace: end seq 99 not found/)
)).toThrow(/surface replace: end seq 99 not found/)
})
it('throws when start is after end', () => {
@@ -183,49 +274,42 @@ describe('SurfaceManager', () => {
s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 0
s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 1
// start=1, end=0 would be reversed order.
s.append('assistant/message',
{ turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] },
expect(() => s.append('assistant/message',
{ provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] },
{ surfaceOp: { op: 'replace', start: 1, end: 0 }, sourceEventSeqs: [1, 0] },
)
expect(() => s.surface.nodes).toThrow(/start seq 1.*after end seq 0/)
)).toThrow(/start seq 1.*after end seq 0/)
})
it('sourceEventSeqs is snapshot so caller mutation does not affect logged event', () => {
const s = new Session(SessionId('immutable'))
const sources = [10, 20]
s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'h' }] }, { surfaceOp: 'append', sourceEventSeqs: sources })
s.append('user/message', { content: [{ type: 'text', text: 'source' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
const sources = [0]
s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'h' }] }, { surfaceOp: 'append', sourceEventSeqs: sources })
// Mutate caller's array after append.
sources.push(30)
sources.push(1)
sources[0] = 99
const logged = s.events[0]! as SurfaceEvent
expect(logged.sourceEventSeqs).toEqual([10, 20])
const logged = s.events[1]! as SurfaceEvent
expect(logged.sourceEventSeqs).toEqual([0])
})
it('replace starting at non-head position links to previous node correctly', () => {
it('replace starting at non-head position preserves surrounding order', () => {
const s = new Session(SessionId('mid-replace'))
s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 0
s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 1
s.append('user/message', { content: [{ type: 'text', text: 'c' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2
// Replace the middle node (seq 1) only, keeping seq 0 and seq 2.
s.append('assistant/message',
{ turn: 1, step: 1, content: [{ type: 'text', text: 'x' }] },
{ provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'x' }] },
{ surfaceOp: { op: 'replace', start: 1, end: 1 }, sourceEventSeqs: [1] },
) // seq 3
expect(s.surface.nodes.map(n => n.seq)).toEqual([0, 3, 2])
// Links: 0 → 3 → 2
expect(s.surface.nodes[0]!.prev).toBeNull()
expect(s.surface.nodes[0]!.next).toBe(3)
expect(s.surface.nodes[1]!.prev).toBe(0)
expect(s.surface.nodes[1]!.next).toBe(2)
expect(s.surface.nodes[2]!.prev).toBe(3)
expect(s.surface.nodes[2]!.next).toBeNull()
expect(s.surface.nodes).toEqual([0, 3, 2])
})
it('surfaceOp replace object is snapshot so caller mutation is isolated', () => {
const s = new Session(SessionId('immutable-op'))
s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
const op = { op: 'replace' as const, start: 0, end: 0 }
s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: op, sourceEventSeqs: [0] })
s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: op, sourceEventSeqs: [0] })
// Mutate caller's object after append.
op.start = 99
const logged = s.events[1]! as SurfaceEvent
@@ -250,7 +334,7 @@ describe('deriveMessages with surface', () => {
s.append('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'h' } })
s.append('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'text-delta', index: 1, text: 'i' } })
s.append('user/message', { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'hi' }] }, { surfaceOp: 'append' })
s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'hi' }] }, { surfaceOp: 'append' })
s.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
// Chunks and boundaries are NOT in the surface, so only 2 messages.
expect(s.deriveMessages()).toHaveLength(2)
@@ -259,7 +343,7 @@ describe('deriveMessages with surface', () => {
it('deriveMessages via surface respects replace (shadowed nodes are excluded)', () => {
const s = new Session(SessionId('compacted'))
s.append('user/message', { content: [{ type: 'text', text: 'original' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'compacted' }] }, { surfaceOp: { op: 'replace', start: 0, end: 0 }, sourceEventSeqs: [0] })
s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'compacted' }] }, { surfaceOp: { op: 'replace', start: 0, end: 0 }, sourceEventSeqs: [0] })
// Only the compaction node is visible.
const messages = s.deriveMessages()
expect(messages).toHaveLength(1)
@@ -280,15 +364,17 @@ describe('deriveMessages with surface', () => {
describe('Session.append surface opts', () => {
it('records sourceEventSeqs and surfaceOp on the event', () => {
const s = new Session(SessionId('opts'))
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
s.append('step/start', { turn: 1, step: 1 })
const event = s.append('assistant/message',
{ turn: 1, step: 1, content: [{ type: 'text', text: 'h' }] },
{ surfaceOp: 'append', sourceEventSeqs: [3, 5, 7] },
{ provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'h' }] },
{ surfaceOp: 'append', sourceEventSeqs: [0, 1] },
)
expect(event.sourceEventSeqs).toEqual([3, 5, 7])
expect(event.sourceEventSeqs).toEqual([0, 1])
expect(event.surfaceOp).toBe('append')
// The logged event matches the returned event.
expect((s.events[0]! as SurfaceEvent).sourceEventSeqs).toEqual([3, 5, 7])
expect((s.events[0]! as SurfaceEvent).surfaceOp).toBe('append')
expect((s.events[2]! as SurfaceEvent).sourceEventSeqs).toEqual([0, 1])
expect((s.events[2]! as SurfaceEvent).surfaceOp).toBe('append')
})
it('deriveMessages skips a surface node that derives to null (empty assistant/message)', () => {
@@ -298,7 +384,7 @@ describe('Session.append surface opts', () => {
const seed: SessionEvent[] = [
{ type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } },
{ type: 'step/start', seq: 1, time: 2, data: { turn: 1, step: 1 } },
{ type: 'assistant/message', seq: 2, time: 3, data: { turn: 1, step: 1, content: [] }, surfaceOp: 'append' },
{ type: 'assistant/message', seq: 2, time: 3, data: { turn: 1, step: 1, content: [], provenance: { provider: 'mock', model: 'mock' } }, surfaceOp: 'append' },
{ type: 'step/end', seq: 3, time: 4, data: { turn: 1, step: 1 } },
{ type: 'turn/end', seq: 4, time: 5, data: { turn: 1, reason: { kind: 'completed' } } },
]
@@ -316,7 +402,7 @@ describe('Session.append surface opts', () => {
it('surfaceOp primitives are not cloned (they are immutable)', () => {
const s = new Session(SessionId('prim'))
const event = s.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append' })
const event = s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append' })
// The string 'append' is a primitive — identity-preserving is fine.
expect(event.surfaceOp).toBe('append')
})
@@ -390,7 +476,7 @@ describe('SurfaceManager.replaceGeneration', () => {
const nodes = s.surface.nodes
s.append('context/message', {
content: [{ type: 'text', text: 'summary' }], source: { kind: 'plugin', plugin: '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]!] })
expect(s.surface.replaceGeneration).toBe(1)
})
})

292
packages/core/session/tests/tool-pairing.spec.ts
View File

@@ -1,292 +0,0 @@
import { describe, expect, it } from 'vitest'
import { CallId } from '@deepseek-ai/dsh-llm'
import { Session, SessionId, isToolPairingBalanced } from '../src/index.ts'
import type { SessionEvent, SurfaceNode } from '../src/index.ts'
/**
* Unit coverage for compaction-cut safety: a cut is balanced only when it
* separates no assistant tool call from its result. Non-step nodes are neutral,
* and replace operations prove surface order—not raw log order—is authoritative.
*/
const SURFACE = { surfaceOp: 'append' as const }
/** Surface nodes + log for a session, the two args the balance check takes. */
function surfaceOf(session: Session): { nodes: readonly SurfaceNode[]; events: readonly SessionEvent[] } {
return { nodes: session.surface.nodes, events: session.events }
}
/** The cut BEFORE the surface node at `seq` is balanced (safe region start). */
function startBalanced(session: Session, seq: number): boolean {
const { nodes, events } = surfaceOf(session)
return isToolPairingBalanced(nodes, events, seq)
}
/** The cut AFTER the surface node at `seq` is balanced (safe region end). */
function endBalanced(session: Session, seq: number): boolean {
const { nodes, events } = surfaceOf(session)
const node = nodes.find(n => n.seq === seq)
if (!node) throw new Error(`seq ${seq} is not a surface node`)
return isToolPairingBalanced(nodes, events, node.next)
}
/** Surface seq of the nth (0-based) event of a given type. */
function seqOf(s: Session, type: SessionEvent['type'], nth = 0): number {
return s.events.filter(e => e.type === type)[nth]!.seq
}
/** A closed turn with one closed step holding an assistant + its tool result. */
function toolStepSession(): Session {
const s = new Session(SessionId('tool-step'))
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
s.append('user/message', { content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }, SURFACE)
s.append('step/start', { turn: 1, step: 1 })
s.append('assistant/message', {
turn: 1, step: 1,
content: [
{ type: 'text', text: 'calling' },
{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' },
],
}, SURFACE)
s.append('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'bash', arguments: '{}' })
s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'out' }], isError: false }, SURFACE)
s.append('step/end', { turn: 1, step: 1 })
s.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
return s
}
describe('isToolPairingBalanced — region START (cut before a node)', () => {
it('is true for a pre-step user/message (belongs to no step)', () => {
const s = toolStepSession()
expect(startBalanced(s, seqOf(s, 'user/message'))).toBe(true)
})
it('is true for the first surface node of a step (the assistant/message)', () => {
// The cut before the assistant is balanced — nothing unanswered precedes it.
const s = toolStepSession()
expect(startBalanced(s, seqOf(s, 'assistant/message'))).toBe(true)
})
it('is false for a tool/result whose assistant/message precedes it in the same step', () => {
// The cut before the tool/result has one unanswered tool-call (the
// assistant's) → starting the region here would orphan that call.
const s = toolStepSession()
expect(startBalanced(s, seqOf(s, 'tool/result'))).toBe(false)
})
it('is true at the surface head (nothing precedes)', () => {
const s = new Session(SessionId('lone'))
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
s.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, SURFACE)
expect(startBalanced(s, seqOf(s, 'user/message'))).toBe(true)
})
})
describe('isToolPairingBalanced — region END (cut after a node)', () => {
it('is true for the last surface node of a closed step (the tool/result)', () => {
// After the tool/result the assistant's single call is answered → balanced.
const s = toolStepSession()
expect(endBalanced(s, seqOf(s, 'tool/result'))).toBe(true)
})
it('is false for an assistant/message with a later tool/result in the same step', () => {
// After the assistant its tool-call is still unanswered → ending here strands
// the result.
const s = toolStepSession()
expect(endBalanced(s, seqOf(s, 'assistant/message'))).toBe(false)
})
it('is true for a pre-step user/message', () => {
const s = toolStepSession()
expect(endBalanced(s, seqOf(s, 'user/message'))).toBe(true)
})
it('is false at the tail when the node is inside an open (unclosed) step', () => {
// step/start then an assistant tool-call, but no tool/result yet (mid-flight).
// The after-tail cut still has one unanswered call → not balanced.
const s = new Session(SessionId('open-step'))
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
s.append('step/start', { turn: 1, step: 1 })
s.append('assistant/message', {
turn: 1, step: 1,
content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }],
}, SURFACE)
expect(endBalanced(s, seqOf(s, 'assistant/message'))).toBe(false)
})
it('is true at the tail when the node is a trailing inter-step node (step already closed)', () => {
// A steering message appended after step/end, at the tail. The prior step's
// pair is balanced and steering is neutral → the after-tail cut is balanced.
const s = new Session(SessionId('trailing-steer'))
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
s.append('step/start', { turn: 1, step: 1 })
s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, SURFACE)
s.append('step/end', { turn: 1, step: 1 })
s.append('steering/message', { turn: 1, content: [{ type: 'text', text: 's' }], source: { kind: 'user' } }, SURFACE)
expect(endBalanced(s, seqOf(s, 'steering/message'))).toBe(true)
})
it('is true at the tail when no step ever opened', () => {
const s = new Session(SessionId('no-step'))
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
s.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, SURFACE)
expect(endBalanced(s, seqOf(s, 'user/message'))).toBe(true)
})
})
describe('isToolPairingBalanced — multiple tool calls in one assistant message', () => {
// An assistant message with two tool-calls needs BOTH results before the cut
// after it is balanced — depth +2, then -1, -1.
function twoCallStep(): Session {
const s = new Session(SessionId('two-call'))
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
s.append('step/start', { turn: 1, step: 1 })
s.append('assistant/message', {
turn: 1, step: 1,
content: [
{ type: 'tool-call', id: CallId('c1'), name: 'a', arguments: '{}' },
{ type: 'tool-call', id: CallId('c2'), name: 'b', arguments: '{}' },
],
}, SURFACE)
s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: '1' }], isError: false }, SURFACE)
s.append('tool/result', { turn: 1, step: 1, callId: CallId('c2'), content: [{ type: 'text', text: '2' }], isError: false }, SURFACE)
s.append('step/end', { turn: 1, step: 1 })
s.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
return s
}
it('is unbalanced after the first of two results (one call still open)', () => {
const s = twoCallStep()
expect(endBalanced(s, seqOf(s, 'tool/result', 0))).toBe(false)
})
it('is balanced after the second result (both calls answered)', () => {
const s = twoCallStep()
expect(endBalanced(s, seqOf(s, 'tool/result', 1))).toBe(true)
})
})
describe('isToolPairingBalanced — a mid-step injection context/message', () => {
// The injected context is pairing-neutral, but both adjacent cuts remain
// unbalanced because the tool call is still open across them.
function midStepInjection(): Session {
const s = new Session(SessionId('mid-inject'))
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
s.append('step/start', { turn: 1, step: 1 })
s.append('assistant/message', {
turn: 1, step: 1,
content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }],
}, SURFACE)
s.append('context/message', { content: [{ type: 'text', text: 'bg task done' }], source: { kind: 'plugin', plugin: 'tool-bash' } }, SURFACE)
s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'out' }], isError: false }, SURFACE)
s.append('step/end', { turn: 1, step: 1 })
s.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
return s
}
it('start cut before the mid-step context/message is unbalanced (call still open)', () => {
const s = midStepInjection()
expect(startBalanced(s, seqOf(s, 'context/message'))).toBe(false)
})
it('end cut after the mid-step context/message is unbalanced (call still open)', () => {
const s = midStepInjection()
expect(endBalanced(s, seqOf(s, 'context/message'))).toBe(false)
})
})
describe('isToolPairingBalanced on an injection turn (no step)', () => {
// An idle inject() wraps a context/message in a bare turn/start →
// context/message → turn/end with NO step. The context node is a free boundary
// both ways (pairing-neutral, nothing open around it).
function injectionSession(): Session {
const s = new Session(SessionId('injection'))
s.append('turn/start', { turn: 1, trigger: { kind: 'injection', source: { kind: 'user' } } })
s.append('context/message', { content: [{ type: 'text', text: 'ctx' }], source: { kind: 'user' } }, SURFACE)
s.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
return s
}
it('start: balanced', () => {
const s = injectionSession()
expect(startBalanced(s, seqOf(s, 'context/message'))).toBe(true)
})
it('end: balanced', () => {
const s = injectionSession()
expect(endBalanced(s, seqOf(s, 'context/message'))).toBe(true)
})
})
describe('isToolPairingBalanced — CBR-001: a head checkpoint left by a replace op', () => {
// A replacement checkpoint has a high log seq but sits at the surface head;
// its cuts are balanced regardless of later raw-log neighbors.
function checkpointHeadedSession(): Session {
const s = new Session(SessionId('checkpoint'))
// A closed turn with a tool step → surface [u1, asst(call), result].
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
s.append('step/start', { turn: 1, step: 1 })
s.append('user/message', { content: [{ type: 'text', text: 'u1' }], source: { kind: 'user' } }, SURFACE)
s.append('assistant/message', {
turn: 1, step: 1,
content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }],
}, SURFACE)
s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'out' }], isError: false }, SURFACE)
s.append('step/end', { turn: 1, step: 1 })
s.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
// An OPEN turn whose step is in progress (loop fires compaction here).
s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } })
s.append('step/start', { turn: 2, step: 1 })
// Compaction replaces the whole turn-1 surface ([u1, asst, result]) with one
// summary user/message — appended now, so it carries a high log seq.
const u1 = seqOf(s, 'user/message')
const result = s.events.find(e => e.type === 'tool/result')!.seq
s.append('user/message', {
content: [{ type: 'text', text: 'CHECKPOINT' }],
source: { kind: 'plugin', plugin: 'compact' },
}, { surfaceOp: { op: 'replace', start: u1, end: result } })
// The step's own assistant/message lands AFTER the checkpoint in the log,
// still inside the open step.
s.append('assistant/message', { turn: 2, step: 1, content: [{ type: 'text', text: 'a2' }] }, SURFACE)
return s
}
it('the head checkpoint sits at the surface head while a later surface node follows it in the log', () => {
const s = checkpointHeadedSession()
const nodes = s.surface.nodes
const checkpointSeq = nodes[0]!.seq
// The checkpoint heads the surface, yet a surface node (the open step's
// assistant) follows it in LOG order — the exact split between surface
// position and log position that the log-position scan tripped on.
const laterSurfaceInLog = s.events.find(
e => e.seq > checkpointSeq && nodes.some(n => n.seq === e.seq),
)
expect(laterSurfaceInLog).toBeDefined()
expect(nodes[0]!.seq).toBe(checkpointSeq)
})
it('start cut before the head checkpoint is balanced (it is the head)', () => {
const s = checkpointHeadedSession()
expect(startBalanced(s, s.surface.nodes[0]!.seq)).toBe(true)
})
it('end cut after the head checkpoint is balanced (it carries no tool pair)', () => {
// This is the exact assertion the log-position scan failed: the forward log scan from the
// checkpoint reached the open step's assistant/message and wrongly reported mid-step.
const s = checkpointHeadedSession()
expect(endBalanced(s, s.surface.nodes[0]!.seq)).toBe(true)
})
})
describe('isToolPairingBalanced — corrupt surface guard', () => {
it('throws when a tool/result has no preceding tool-call (depth goes negative)', () => {
// A surface that opens with a tool/result (no assistant call before it) is
// structurally corrupt — surfaced loudly rather than mis-classified.
const s = new Session(SessionId('corrupt'))
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
s.append('step/start', { turn: 1, step: 1 })
s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'x' }], isError: false }, SURFACE)
const { nodes, events } = surfaceOf(s)
expect(() => isToolPairingBalanced(nodes, events, null)).toThrow(/no matching tool-call/)
})
})