mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
fix(tui,host): project the human transcript from append-origin events
The terminal and history pagination both treated the model-visible surface as the human transcript. A landed compaction replacement therefore erased the conversation it summarized — messages the reader had already seen — and a model-only replacement copy consumed a page's `maxMessages` quota, which could also split a compaction's provenance from the replacement citing it. `dsh-session` now exports the marker split `isAppendSurfaceEvent` / `isReplacementSurfaceEvent`. The terminal replays append-origin surface events, keeps a shadowed step's tool cards paired through its append-origin assistant message, and renders one dim marker where a compaction landed; the checkpoint is recognized through the compaction seam's `isCompactCheckpointSource` contract, not the shape of the replacement. `session.history` counts only append-origin human messages. Everything model-facing keeps reading `session.surface`.
This commit is contained in:
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/host/apiproxy/README.md
|
||||
README.md: ca4471454f5be5d3fcba38ce665d4fb3fbd85e74
|
||||
README.zh.md: 953539e1198a52b2bf7cdd9ca1b0d263cc2ae6f9
|
||||
README.md: 190e7f8d36f74bfd7232cc5b4dbb937f265ef1d5
|
||||
README.zh.md: 9fb9d24412e950b0648cd07c4b5c73aa0174405c
|
||||
|
||||
@@ -10,6 +10,8 @@ Wire messages form a four-quadrant discriminated union — who initiates × requ
|
||||
|
||||
The layering/protocol decisions are recorded in the [GUI layering and RPC protocol RFC](../../../.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md); the browser-side consumption architecture in the [web client architecture RFC](../../../.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md).
|
||||
|
||||
`session.history` pages on append-origin human-message boundaries: `maxMessages` counts `user/message`, `assistant/message`, and `steering/message` events that entered the surface by appending, so a model-only replacement copy consumes no quota. Each page stays one contiguous raw event range, which keeps a compaction's log-only provenance on the same page as the replacement that cites it.
|
||||
|
||||
`session.history`'s tail page (`beforeSeq` absent) additionally carries an optional `projections` block — the watermark snapshot of every unit registered on `ctx.sessionProjections` (`@deepseek-ai/dsh-session-projection`), with `asOfSeq` = the last event seq the values reflect (`-1` on an empty log). The gateway also subscribes to the registry's change feed and mints a `session/projection` mux frame per changed unit (`{sessionId, key, value, seq}` — live push state, never logged; clients hold one generic per-session value store under higher-seq-wins). The carrier holds zero domain knowledge (each value passed its unit's own schema inside the registry; the wire schemas keep `values`/`value` wide); loadOlder pages never carry the block, and a composition without the registry serves histories without either surface.
|
||||
|
||||
Session titles ride the generic projection pair like every other domain — the history-tail `projections` block plus `session/projection` frames under the `title` key (the bespoke `session/title` frame is retired). Titles do not join `session.list`; cold sessions remain metadata-only there until opening or resuming attaches their logs.
|
||||
|
||||
@@ -10,6 +10,8 @@
|
||||
|
||||
分层与协议决策记录在 [GUI 分层与 RPC 协议 RFC](../../../.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md)中;浏览器侧消费架构记录在 [Web 客户端架构 RFC](../../../.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md)中。
|
||||
|
||||
`session.history` 按追加来源的人类消息边界分页:`maxMessages` 统计以追加方式进入 surface 的 `user/message`、`assistant/message` 和 `steering/message` 事件,因此仅供模型使用的替换副本不占用配额。每一页仍是一段连续的原始事件区间,从而让压缩(compaction)的仅日志溯源信息与引用它的替换留在同一页。
|
||||
|
||||
`session.history` 的尾页(不带 `beforeSeq`)额外携带一个可选的 `projections` 块——`ctx.sessionProjections`(`@deepseek-ai/dsh-session-projection`)上每个已注册单元的水位线快照,`asOfSeq` = 这些值共同反映到的最后一个事件 seq(空日志为 `-1`)。网关还订阅注册表的变更流,为每个状态发生变化的单元铸造一个 `session/projection` mux 帧(`{sessionId, key, value, seq}`——实时推送状态,绝不入日志;客户端按 seq 高者胜维护一个按会话的通用值仓)。载体不持有任何领域知识(每个值在注册表内部已过其单元自己的 schema;协议 schema 对 `values`/`value` 保持宽松);loadOlder 页永不携带该块,未装注册表的组合则两个面都不提供。
|
||||
|
||||
会话标题与其他所有领域一样搭乘这对通用投影机制——历史尾页的 `projections` 块外加 `title` 键下的 `session/projection` 帧(专设的 `session/title` 帧已下线)。标题不会加入 `session.list`;冷会话在其中仍只有元数据,直到打开或恢复操作附加其日志。
|
||||
|
||||
@@ -14,6 +14,7 @@ import type {
|
||||
import { createUserMessage, ReasoningEffortId } from '@deepseek-ai/dsh-llm'
|
||||
import { errorChain } from '@deepseek-ai/dsh-llm'
|
||||
import type { MessageId, MessageSource } from '@deepseek-ai/dsh-llm'
|
||||
import { isAppendSurfaceEvent } from '@deepseek-ai/dsh-session'
|
||||
import type { Session, SessionEvent, SessionHeader, SessionId, UserMessage } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionPersistence } from '@deepseek-ai/dsh-session-persistence'
|
||||
import type { Workspace, WorkspaceRecord } from '@deepseek-ai/dsh-workspace'
|
||||
@@ -57,14 +58,17 @@ import { openNativePath } from './native-path-opener.ts'
|
||||
/** Page size when history is called without maxMessages. */
|
||||
const DEFAULT_MAX_MESSAGES = 50
|
||||
|
||||
/** Surface message event types (the pagination counting unit). */
|
||||
/** Human message event types (the pagination counting unit). */
|
||||
const MESSAGE_TYPES = new Set(['user/message', 'assistant/message', 'steering/message'])
|
||||
|
||||
/**
|
||||
* Message-boundary pagination: count maxMessages surface messages backwards from
|
||||
* the window tail; the cut is the starting seq of the oldest message group
|
||||
* (chunks group via sourceEventSeqs — never cut mid-message). The tail page
|
||||
* naturally includes the in-progress partial.
|
||||
* Message-boundary pagination: count maxMessages append-origin human messages
|
||||
* backwards from the window tail. Replacement copies are model-only, so they
|
||||
* consume no quota; the page stays one contiguous raw range, which keeps a
|
||||
* compaction's log-only provenance on the same page as its replacement. The cut
|
||||
* is the starting seq of the oldest message group (chunks group via
|
||||
* sourceEventSeqs — never cut mid-message). The tail page naturally includes the
|
||||
* in-progress partial.
|
||||
*/
|
||||
function paginate(
|
||||
events: readonly SessionEvent[],
|
||||
@@ -76,7 +80,7 @@ function paginate(
|
||||
let cut = 0
|
||||
for (let i = window.length - 1; i >= 0; i--) {
|
||||
const event = window[i] as SessionEvent
|
||||
if (!MESSAGE_TYPES.has(event.type)) continue
|
||||
if (!MESSAGE_TYPES.has(event.type) || !isAppendSurfaceEvent(event)) continue
|
||||
count++
|
||||
const sources = (event as { sourceEventSeqs?: number[] }).sourceEventSeqs
|
||||
const groupStart = sources !== undefined && sources.length > 0 ? Math.min(event.seq, ...sources) : event.seq
|
||||
|
||||
@@ -176,9 +176,11 @@ export interface SessionsApi {
|
||||
Promise<RpcResponse<{ sessionId: SessionId }>>
|
||||
|
||||
/**
|
||||
* Reads a window of history events; page boundaries align to message boundaries: one page =
|
||||
* all raw events owned by a whole number of messages (including their chunk / tool events),
|
||||
* never cut mid-message. The tail page (beforeSeq absent) additionally carries the in-flight
|
||||
* Reads a window of history events; page boundaries align to append-origin human-message
|
||||
* boundaries: one page = all raw events owned by a whole number of such messages (including
|
||||
* their chunk / tool events), never cut mid-message. Model-only replacement copies consume no
|
||||
* `maxMessages`, so a compaction's provenance stays on the page of its replacement. The tail
|
||||
* page (beforeSeq absent) additionally carries the in-flight
|
||||
* partial — chunk events already emitted for the last unfinalized message.
|
||||
* Each entry pairs the raw SessionEvent with the host-computed view (tool events whose
|
||||
* presenter produced one, evaluated against the registry at pagination time); the client
|
||||
|
||||
@@ -14,7 +14,7 @@ import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import SessionStore from '@deepseek-ai/dsh-session'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
|
||||
import { CallId, createToolResultMessage } from '@deepseek-ai/dsh-llm'
|
||||
import { CallId, createMessage, createToolResultMessage, createUserMessage } from '@deepseek-ai/dsh-llm'
|
||||
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
|
||||
import type { Session, SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type { ToolDefinition } from '@deepseek-ai/dsh-tools'
|
||||
@@ -35,6 +35,35 @@ function tool(name: string, presenters: Pick<ToolDefinition, 'presentCall' | 'pr
|
||||
})
|
||||
}
|
||||
|
||||
/** Append a production-shaped human prompt to the session surface. */
|
||||
function appendUserText(session: Session, text: string): SessionEvent {
|
||||
return session.append('user/message', createUserMessage({
|
||||
content: [{ type: 'text', text }], source: { kind: 'user' },
|
||||
}), { surfaceOp: 'append' })
|
||||
}
|
||||
|
||||
/** Append a production-shaped assistant message to the session surface. */
|
||||
function appendAssistantText(session: Session, text: string, step: number): SessionEvent {
|
||||
return session.append('assistant/message', {
|
||||
turn: 1,
|
||||
step,
|
||||
message: createMessage({
|
||||
role: 'assistant',
|
||||
content: [{ type: 'text', text }],
|
||||
source: { kind: 'model', provider: 'p', model: 'm' },
|
||||
}),
|
||||
}, { surfaceOp: 'append' })
|
||||
}
|
||||
|
||||
/**
|
||||
* Append a plugin-owned log-only event. The host proxy is projection-only, so it
|
||||
* declares no compaction vocabulary; the cast writes the real event shape without
|
||||
* depending on the owning package.
|
||||
*/
|
||||
function appendExtension(session: Session, type: string, data: unknown): SessionEvent {
|
||||
return (session.append as unknown as (type: string, data: unknown) => SessionEvent)(type, data)
|
||||
}
|
||||
|
||||
async function harness(): Promise<{ ctx: Context }> {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
@@ -207,6 +236,55 @@ describe('mux live view computation', () => {
|
||||
expect('view' in (byKey.get('tool/result:h-plain') ?? {})).toBe(false)
|
||||
})
|
||||
|
||||
it('counts only append-origin messages toward maxMessages and keeps compaction provenance whole', async () => {
|
||||
const { ctx } = await harness()
|
||||
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const session = ctx.sessions.create()
|
||||
ctx.agents.register({ id: session.id, session, status: 'idle', ctx } as Agent)
|
||||
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
const first = appendUserText(session, 'first prompt')
|
||||
appendAssistantText(session, 'first reply', 1)
|
||||
const third = appendUserText(session, 'second prompt')
|
||||
appendAssistantText(session, 'second reply', 2)
|
||||
const shadowed = [...session.surface.nodes]
|
||||
// A compaction transaction: log-only provenance immediately followed by the
|
||||
// replacement that shadows the range.
|
||||
const summary = appendExtension(session, 'compact/summary', {
|
||||
summary: [{ type: 'text', text: 'summary' }],
|
||||
shadowedRange: { start: shadowed[0], end: shadowed.at(-1) },
|
||||
shadowedSeqs: shadowed,
|
||||
shadowedTokenCount: 0,
|
||||
provider: 'p',
|
||||
model: 'm',
|
||||
})
|
||||
session.append('user/message', createUserMessage({
|
||||
content: [{ type: 'text', text: '<context_checkpoint>summary</context_checkpoint>' }],
|
||||
source: { kind: 'plugin', plugin: 'compact' },
|
||||
}), {
|
||||
surfaceOp: { op: 'replace', start: shadowed[0] as number, end: shadowed.at(-1) as number },
|
||||
sourceEventSeqs: [...shadowed, summary.seq],
|
||||
})
|
||||
|
||||
const response = await api.sessions.history({
|
||||
rpcId: RpcId('t-hist-compact'),
|
||||
payload: { sessionId: session.id, maxMessages: 2 },
|
||||
})
|
||||
if (!response.result.ok) throw new Error('unreachable')
|
||||
const page = response.result.value.events.map(entry => entry.event)
|
||||
// Two append-origin messages fill the page even though a replacement copy of
|
||||
// the same event type sits in the window: the copy is model-only.
|
||||
const messages = page.filter(event => event.type === 'user/message' || event.type === 'assistant/message')
|
||||
expect(messages.map(event => event.seq)).toEqual([third.seq, third.seq + 1, third.seq + 3])
|
||||
expect(page.some(event => event.seq === first.seq)).toBe(false)
|
||||
expect(response.result.value.hasMore).toBe(true)
|
||||
// The range stays contiguous, so the checkpoint's provenance is readable on
|
||||
// the same page as the checkpoint itself.
|
||||
const summaryIndex = page.findIndex(event => event.seq === summary.seq)
|
||||
expect(summaryIndex).toBeGreaterThan(-1)
|
||||
expect(page[summaryIndex + 1]?.seq).toBe(summary.seq + 1)
|
||||
expect(page.map(event => event.seq)).toEqual(page.map((_event, index) => third.seq + index))
|
||||
})
|
||||
|
||||
it('drops a disposed session from the live open-call table (result after dispose gets no view)', async () => {
|
||||
const { ctx } = await harness()
|
||||
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
Reference in New Issue
Block a user