Merge branch 'master' of https://github.com/deepseek-harness/deepseek-harness into xtr/react-loop-simplification

# Conflicts: # .agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml # docs/architecture.i18n.yaml # docs/cookbook/extension-cookbook.i18n.yaml # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.i18n.yaml # docs/core-data-structures/core.md # docs/core-data-structures/core.zh.md # docs/core-data-structures/llm-streaming.i18n.yaml # docs/core-data-structures/llm-streaming.md # docs/core-data-structures/llm-streaming.zh.md # docs/core-data-structures/session.i18n.yaml # docs/event-producer-consumer.md # docs/persistence-catalog.md # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/README.i18n.yaml # packages/core/agent-loop/src/agent.ts # packages/core/agent/README.i18n.yaml # packages/core/session/README.i18n.yaml # packages/core/session/src/types.ts # packages/llm/llm/README.i18n.yaml # packages/llm/llm/README.md # packages/llm/llm/README.zh.md # packages/llm/llm/src/index.ts # packages/llm/llm/tests/service.spec.ts # packages/sdk/sdk-client/README.i18n.yaml # packages/sdk/sdk-protocol/README.i18n.yaml # packages/sdk/sdk-protocol/README.md # packages/sdk/sdk-protocol/README.zh.md # packages/subagent/subagent-dsh-sdk/README.i18n.yaml # packages/ui/jsonrpc/README.i18n.yaml # packages/ui/jsonrpc/README.md # packages/ui/jsonrpc/README.zh.md # packages/ui/tui/src/index.ts # python/sdk/README.i18n.yaml # scripts/gen-cordis-catalog.ts
2026-07-31 10:16:14 +08:00
parent 060c0f78f0 1351565681
commit 7a463dbe44
1106 changed files with 33236 additions and 7168 deletions
--- a/packages/core/session/README.i18n.yaml
+++ b/packages/core/session/README.i18n.yaml
@@ -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/core/session/README.md
-README.md: 8d65bf85b1b9c36568f9a972afd84695d3301649
-README.zh.md: cf16b01b7855b6cbfe66a83fb9b1183a837b7db8
+README.md: d2eb35108b7eba9963e62a1c0d2a8868c7b7a821
+README.zh.md: 85507abf55e82485268055f99f759b75f8cc5f01
--- a/packages/core/session/README.md
+++ b/packages/core/session/README.md
@@ -59,10 +59,11 @@ Providers stream token-sized deltas, so a raw log stores hundreds of `assistant/
 - `SessionSurface` — the readonly live `nodes` and `replaceGeneration` projection exposed by `session.surface`; candidate validation remains private to `Session`.
 - `foldSurface(events)` — replay the canonical surface contract into detached current event sequences and actual replacement ranges. The same pass rejects non-contiguous seqs, misplaced or malformed metadata, empty or duplicate provenance, non-earlier sources, invalid positional ranges, replacements that fail to cite every shadowed surface entry, and a `tool/result` replacement that changes anything except one current result's `content`; `SurfaceManager` shares the atomic transition while retaining only its incremental sequence cache.
 - `isSurfaceEvent(event)` / `isSurfaceEligibleType(type)` — the first narrows a `SessionEvent` to a fully formed surface event; the second detects a surface-eligible event missing its marker when validating a seed or loaded log.
+- `isAppendSurfaceEvent(event)` / `isReplacementSurfaceEvent(event)` — split a formed surface event by marker variant. Append-origin events are the durable source for a human transcript, which is not the model-visible surface: a landed replacement shadows the range it summarizes, so projecting a transcript from `session.surface` erases conversation the reader already saw. Consumers that must send exactly what the model sees keep reading `session.surface`.

 ### Request-header reconstruction (`request-header.ts`)

-`request/header` records a full canonical snapshot of the non-history request envelope with reason `initial`, `resume`, or `change`. `foldRequestHeader()` selects the latest snapshot; legacy delta events and the removed `fallback` reason are rejected. See the [reconstructable-requests Agent Note](../../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md).
+`request/header` records a full canonical snapshot of the non-history request envelope with reason `initial`, `resume`, or `change`. Its optional `adapterDefaults` map marks effective `reasoningEffort` or `maxTokens` values materialized by exact-model resolution, allowing the next request proposal to distinguish them from explicit conversation settings. `foldRequestHeader()` selects the latest snapshot; legacy delta events and the removed `fallback` reason are rejected. See the [reconstructable-requests Agent Note](../../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md).

 A `user/message` stores the complete `UserMessage` directly, including the identity created before routing or prompt admission. It renders its `content` verbatim whether it is a direct human prompt, a synthetic injection, or an admitted goal round; its typed `source` is the only channel that tells them apart and carries any domain-specific durable facts. `assistant/message`, `tool/result`, and `steering/message` likewise store complete message values. Turn execution remains enclosed by `turn/start` and `turn/end`, while an idle injection may append and flush a `user/message` between turns without running the model.

--- a/packages/core/session/README.zh.md
+++ b/packages/core/session/README.zh.md
@@ -59,10 +59,11 @@
 - `SessionSurface`：实时只读 `nodes` 和 `replaceGeneration` 投影，由 `session.surface` 暴露；候选校验仍由 `Session` 私有。
 - `foldSurface(events)`：回放规范 surface 契约，得到脱离的当前事件序列与实际替换范围。同一趟处理会拒绝不连续序号、错位或畸形元数据、空或重复溯源信息、来源并非更早事件、无效位置范围，以及没有引用所有已遮蔽 surface 条目的替换。如果一个 `tool/result` 替换修改了当前某个结果的 `content` 之外的任何内容，也会被拒绝；`SurfaceManager` 共享该原子状态转换，但只保留自己的增量序列缓存。
 - `isSurfaceEvent(event)`／`isSurfaceEligibleType(type)`：前者将 `SessionEvent` 收窄为形态完整的 surface 事件；后者在校验种子或已加载日志时，检测缺少标记的可进入 surface 事件。
+- `isAppendSurfaceEvent(event)`／`isReplacementSurfaceEvent(event)`：按标记变体拆分形态完整的 surface 事件。追加来源的事件是人类可读记录（transcript）的持久来源，而该记录并非模型可见的 surface：已落地的替换会遮蔽它所概括的范围，因此从 `session.surface` 投影记录会抹掉读者已经看到的对话。必须准确发送模型所见内容的消费方仍继续读取 `session.surface`。

 ### 请求头重建（`request-header.ts`）

-`request/header` 记录非历史请求封装的完整规范快照，其原因为 `initial`、`resume` 或 `change`。`foldRequestHeader()` 选择最新快照；旧版增量事件和已移除的 `fallback` 原因会被拒绝。详见[可重建请求 Agent Note](../../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)。
+`request/header` 记录非历史请求封装的完整规范快照，其原因为 `initial`、`resume` 或 `change`。其可选 `adapterDefaults` 映射会标记由精确模型解析填入的生效 `reasoningEffort` 或 `maxTokens` 值，使下一次请求提议能够将它们与显式对话设置区分开。`foldRequestHeader()` 选择最新快照；旧版增量事件和已移除的 `fallback` 原因会被拒绝。详见[可重建请求 Agent Note](../../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)。

 `user/message` 会直接存储完整的 `UserMessage`，其中包括路由或提示词准入前创建的标识。无论它是直接人类提示词、合成注入，还是已准入的 Goal Round，都会原样呈现其 `content`；带类型的 `source` 是区分三者的唯一通道，并携带各领域专有的持久事实。`assistant/message`、`tool/result` 和 steering（中途引导）对应的 `steering/message` 也会存储完整的消息值。轮次执行仍由 `turn/start` 与 `turn/end` 包围，而空闲注入可以在轮次之间追加并刷新一条 `user/message`，无需运行模型。

--- a/packages/core/session/src/index.ts
+++ b/packages/core/session/src/index.ts
@@ -27,7 +27,7 @@ export { interruptedTurnClosers, lastActivityTime, TOOL_NOT_STARTED, TOOL_OUTCOM
 export { decodeStorageRecord, packChunkRuns } from './chunk-rows.ts'
 export type { ChunkRow, StorageRecord } from './chunk-rows.ts'
 export type { SessionSurface, SurfaceFoldReplacement, SurfaceFoldResult } from './surface.ts'
-export { foldSurface, isSurfaceEvent, isSurfaceEligibleType } from './surface.ts'
+export { foldSurface, isAppendSurfaceEvent, isReplacementSurfaceEvent, isSurfaceEvent, isSurfaceEligibleType } from './surface.ts'
 export { canonicalHeader, foldRequestHeader, headerEquals } from './request-header.ts'

 declare module 'cordis' {
@@ -179,13 +179,18 @@ function assertCurrentLlmShape(event: Record<string, unknown>, index: number): v
    : undefined
  if (event['type'] === 'request/header') {
    const header = record?.['header']
-    const config = typeof header === 'object' && header !== null ? (header as Record<string, unknown>)['config'] : undefined
+    const headerRecord = typeof header === 'object' && header !== null && !Array.isArray(header)
+      ? header as Record<string, unknown>
+      : undefined
+    const config = headerRecord?.['config']
    if (!hasProviderModel(config)) throw new Error(`seed request/header at index ${index} lacks provider/model`)
-    const reasoningEffort = (config as Record<string, unknown>)['reasoningEffort']
+    const configRecord = config as Record<string, unknown>
+    const reasoningEffort = configRecord['reasoningEffort']
    if (reasoningEffort !== undefined
      && (typeof reasoningEffort !== 'string' || reasoningEffort.length === 0)) {
      throw new Error(`seed request/header at index ${index} has an invalid reasoningEffort`)
    }
+    assertAdapterDefaults(headerRecord?.['adapterDefaults'], configRecord, index)
  }
  const type = event['type']
  if (type !== 'user/message' && type !== 'assistant/message'
@@ -193,6 +198,26 @@ function assertCurrentLlmShape(event: Record<string, unknown>, index: number): v
  assertMessageEventShape(event, `seed ${type} at index ${index}`)
 }

+/** Validate adapter-default provenance imported from a durable request header. */
+function assertAdapterDefaults(
+  value: unknown,
+  config: Record<string, unknown>,
+  index: number,
+): void {
+  if (value === undefined) return
+  if (typeof value !== 'object' || value === null || Array.isArray(value)) {
+    throw new Error(`seed request/header at index ${index} has invalid adapterDefaults`)
+  }
+  const defaults = value as Record<string, unknown>
+  const allowed = new Set(['reasoningEffort', 'maxTokens'])
+  if (Object.keys(defaults).some(key => !allowed.has(key))
+    || Object.values(defaults).some(marker => marker !== true)
+    || defaults['reasoningEffort'] === true && config['reasoningEffort'] === undefined
+    || defaults['maxTokens'] === true && config['maxTokens'] === undefined) {
+    throw new Error(`seed request/header at index ${index} has invalid adapterDefaults`)
+  }
+}
+
 /** Validate only the event-specific invariants needed to safely replay a message. */
 function assertMessageEventShape(event: Record<string, unknown>, subject: string): void {
  const type = event['type']
@@ -442,7 +467,8 @@ export class Session {
   *   the ordered surface; `sourceEventSeqs` records provenance (the seq
   *   numbers of events this one derives from). REQUIRED for
   *   {@link SurfaceEventType} events (every message-producing event must
-   *   declare how it joins the surface, the sole source of derived history) and
+   *   declare how it joins the surface, the sole source of derived model
+   *   history) and
   *   rejected by the compiler for non-surface types like `turn/start` or
   *   `assistant/chunk`.
   * @returns the logged event — its assigned `seq`/`time` plus the SNAPSHOT of
--- a/packages/core/session/src/request-header.ts
+++ b/packages/core/session/src/request-header.ts
@@ -19,8 +19,12 @@ import type { EpochHeader, SessionEvent } from './types.ts'
 * @returns the canonical header.
 */
 export function canonicalHeader(header: EpochHeader): EpochHeader {
+  const adapterDefaults = header.adapterDefaults
  return {
    config: header.config,
+    ...adapterDefaults?.reasoningEffort === true || adapterDefaults?.maxTokens === true
+      ? { adapterDefaults }
+      : {},
    ...header.system !== undefined && header.system.length > 0 ? { system: header.system } : {},
    ...header.tools !== undefined && header.tools.length > 0 ? { tools: header.tools } : {},
  }
@@ -38,7 +42,12 @@ function sameSchema(a: ToolSchema, b: ToolSchema): boolean {
 * @returns whether config, system, and tools all match.
 */
 export function headerEquals(a: EpochHeader, b: EpochHeader): boolean {
-  if (!callConfigEquals(a.config, b.config) || a.system !== b.system) return false
+  if (
+    !callConfigEquals(a.config, b.config)
+    || a.adapterDefaults?.reasoningEffort !== b.adapterDefaults?.reasoningEffort
+    || a.adapterDefaults?.maxTokens !== b.adapterDefaults?.maxTokens
+    || a.system !== b.system
+  ) return false
  const at = a.tools ?? []
  const bt = b.tools ?? []
  return at.length === bt.length && at.every((tool, i) => sameSchema(tool, bt[i] as ToolSchema))
--- a/packages/core/session/src/surface.ts
+++ b/packages/core/session/src/surface.ts
@@ -37,6 +37,36 @@ export function isSurfaceEvent(event: SessionEvent): event is SurfaceEvent {
  return (event as SessionEvent<SurfaceEventType>).surfaceOp !== undefined
 }

+/**
+ * Narrow an event to an append-origin surface event: one that entered the
+ * surface at its own log position and was never itself a replacement copy.
+ *
+ * The model-visible surface deliberately shadows replaced ranges, so it is the
+ * wrong source for a human transcript — a landed replacement would erase
+ * conversation the user already saw. Append-origin events are that transcript's
+ * durable source material; replacement copies stay model-only.
+ * @param event - event to test.
+ * @returns true when the event appended to the surface tail.
+ */
+export function isAppendSurfaceEvent(
+  event: SessionEvent,
+): event is SurfaceEvent & { surfaceOp: 'append' } {
+  return isSurfaceEvent(event) && event.surfaceOp === 'append'
+}
+
+/**
+ * Narrow an event to a surface replacement: a node that shadowed an existing
+ * surface range instead of appending to the tail. The counterpart of
+ * {@link isAppendSurfaceEvent} over the two {@link SurfaceOp} variants.
+ * @param event - event to test.
+ * @returns true when the event replaced a surface range.
+ */
+export function isReplacementSurfaceEvent(
+  event: SessionEvent,
+): event is SurfaceEvent & { surfaceOp: Extract<SurfaceOp, { op: 'replace' }> } {
+  return isSurfaceEvent(event) && event.surfaceOp !== 'append'
+}
+
 /** One replacement operation observed while folding a session surface. */
 export interface SurfaceFoldReplacement {
  /** Seq of the event that replaced the prior surface range. */
--- a/packages/core/session/src/types.ts
+++ b/packages/core/session/src/types.ts
@@ -3,6 +3,7 @@ import type {
  AssistantMessage,
  CallId,
  LlmCallConfig,
+  LlmCallConfigAdapterDefaults,
  StreamChunk,
  TokenUsage,
  ToolResultMessage,
@@ -140,6 +141,8 @@ export interface TodoItem {
 export interface EpochHeader {
  /** The conversation's call configuration (provider, model, reasoning effort, and sampling scalars). */
  config: LlmCallConfig
+  /** Effective config fields materialized from the exact adapter rather than proposed by a caller. */
+  adapterDefaults?: LlmCallConfigAdapterDefaults
  /** Rendered system prompt text; absent for a system-less request. */
  system?: string
  /** Assembled tool schemas; absent for a tool-less request. */
--- a/packages/core/session/tests/request-header.spec.ts
+++ b/packages/core/session/tests/request-header.spec.ts
@@ -14,9 +14,24 @@ function tool(name: string, description = 'd'): ToolSchema {

 describe('canonicalHeader', () => {
  it('normalizes empty optional fields to absence and preserves populated fields', () => {
-    expect(canonicalHeader({ config: CONFIG, system: '', tools: [] })).toEqual({ config: CONFIG })
-    const full = canonicalHeader({ config: CONFIG, system: 's', tools: [tool('a')] })
-    expect(full).toEqual({ config: CONFIG, system: 's', tools: [tool('a')] })
+    expect(canonicalHeader({
+      config: CONFIG,
+      adapterDefaults: {},
+      system: '',
+      tools: [],
+    })).toEqual({ config: CONFIG })
+    const full = canonicalHeader({
+      config: { ...CONFIG, maxTokens: 256_000 },
+      adapterDefaults: { maxTokens: true },
+      system: 's',
+      tools: [tool('a')],
+    })
+    expect(full).toEqual({
+      config: { ...CONFIG, maxTokens: 256_000 },
+      adapterDefaults: { maxTokens: true },
+      system: 's',
+      tools: [tool('a')],
+    })
  })
 })

@@ -30,6 +45,14 @@ describe('headerEquals', () => {
      ...base,
      config: { ...base.config, reasoningEffort: ReasoningEffortId('high') },
    })).toBe(false)
+    expect(headerEquals(
+      { ...base, config: { ...base.config, maxTokens: 256_000 } },
+      {
+        ...base,
+        config: { ...base.config, maxTokens: 256_000 },
+        adapterDefaults: { maxTokens: true },
+      },
+    )).toBe(false)
    expect(headerEquals(base, { ...base, system: 'other' })).toBe(false)
    expect(headerEquals(base, { ...base, tools: [] })).toBe(false)
    expect(headerEquals(base, { ...base, tools: [tool('a', 'changed')] })).toBe(false)
--- a/packages/core/session/tests/session.spec.ts
+++ b/packages/core/session/tests/session.spec.ts
@@ -351,6 +351,40 @@ describe('Session', () => {
    }
  })

+  it('round-trips adapter-default provenance and rejects invalid durable values', () => {
+    const valid = {
+      type: 'request/header',
+      seq: 0,
+      time: 1,
+      data: {
+        header: {
+          config: {
+            provider: 'mock',
+            model: 'model',
+            maxTokens: 256_000,
+          },
+          adapterDefaults: { maxTokens: true },
+        },
+        reason: 'initial',
+      },
+    } as const
+    expect(new Session(SessionId('adapter-defaults'), [valid]).events[0]).toEqual(valid)
+
+    for (const adapterDefaults of [
+      null,
+      [],
+      { unknown: true },
+      { maxTokens: false },
+      { reasoningEffort: true },
+    ]) {
+      const invalid = structuredClone(valid) as unknown as SessionEvent
+      if (invalid.type !== 'request/header') throw new Error('test fixture must be a request header')
+      invalid.data.header.adapterDefaults = adapterDefaults as never
+      expect(() => new Session(SessionId('invalid-adapter-defaults'), [invalid]))
+        .toThrow('seed request/header at index 0 has invalid adapterDefaults')
+    }
+  })
+
  it('isolates the log from mutation through a derived message (append-only contract)', () => {
    const session = new Session(SessionId('s4'))
    session.append('user/message', createUserMessage({
--- a/packages/core/session/tests/surface.spec.ts
+++ b/packages/core/session/tests/surface.spec.ts
@@ -4,6 +4,8 @@ import {
  Session,
  SessionId,
  foldSurface,
+  isAppendSurfaceEvent,
+  isReplacementSurfaceEvent,
  isSurfaceEligibleType,
  isSurfaceEvent,
 } from '@deepseek-ai/dsh-session'
@@ -861,6 +863,40 @@ describe('surface type guards', () => {
    expect(isSurfaceEligibleType(markerless.type)).toBe(true)
    expect(isSurfaceEvent(markerless)).toBe(false)
  })
+
+  it('splits surface events into append-origin and replacement by their marker', () => {
+    const s = surfaceSession()
+    s.append('user/message', createUserMessage({
+      content: [{ type: 'text', text: 'checkpoint' }], source: { kind: 'plugin', plugin: 'compact' },
+    }), { surfaceOp: { op: 'replace', start: 1, end: 2 }, sourceEventSeqs: [1, 2] })
+    const appended = s.events.find(e => e.type === 'user/message')!
+    const replacement = s.events.at(-1)!
+
+    expect(isAppendSurfaceEvent(appended)).toBe(true)
+    expect(isReplacementSurfaceEvent(appended)).toBe(false)
+    expect(isAppendSurfaceEvent(replacement)).toBe(false)
+    expect(isReplacementSurfaceEvent(replacement)).toBe(true)
+  })
+
+  it('rejects log-only and markerless events from both marker guards', () => {
+    const s = surfaceSession()
+    const turnStart = s.events.find(e => e.type === 'turn/start')!
+    // A surface-eligible type whose mandatory marker is absent has no origin at
+    // all: it never entered the surface.
+    const markerless: SessionEvent = {
+      type: 'user/message',
+      seq: 0,
+      time: 0,
+      data: createUserMessage({
+        content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' },
+      }),
+    }
+
+    expect(isAppendSurfaceEvent(turnStart)).toBe(false)
+    expect(isReplacementSurfaceEvent(turnStart)).toBe(false)
+    expect(isAppendSurfaceEvent(markerless)).toBe(false)
+    expect(isReplacementSurfaceEvent(markerless)).toBe(false)
+  })
 })

 describe('SurfaceManager.replaceGeneration', () => {