Merge remote-tracking branch 'origin/master' into feat/telemetry-otel-plugin

Resolutions: regenerate the conflicted generated docs (cordis services
catalog, event-producer-consumer, module-graph); take master's
packages/README pair and re-insert the telemetry row on both sides;
re-record the README and session-doc translation pairs.
This commit is contained in:
kingwl
2026-07-27 20:26:21 +08:00
1287 changed files with 40863 additions and 13931 deletions

View File

@@ -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
README.md: 18d6d385ff0c35ddbe7dc9a172ce9cd563bc4c1c
README.zh.md: 93ea574eb01fd27fcd68f8b58a9e4187dfbd4fcb
README.md: e46ff43c95df0ae1a6ec536d30417b342c11b151
README.zh.md: abe4dbef6c7d26861cab987704c772a45e57a808

View File

@@ -52,7 +52,7 @@ Durable values need one accepted representation, not a check followed by a secon
### Chunk-row storage codec (`chunk-rows.ts`)
Providers stream token-sized deltas, so a raw log stores hundreds of `assistant/chunk` lines whose JSON envelopes dwarf their payloads. `packChunkRuns(events)` packs each run of ≥3 consecutive same-block delta chunks into one storage row — `text-chunks`, `reasoning-chunks`, or `tool-call-chunks` (bare slash-less tags: storage vocabulary, not `SessionEventMap` members) — and `decodeStorageRecord(value)` expands a parsed line back into its exact events (`seq0`/`time0` + per-member `dt` gaps reconstruct every `seq`/`time`). The encoder whitelists exact shapes and stores anything unrecognized verbatim; the decoder validates row-tagged values and throws on malformation. Owned here so the JSONL backend and the fixture readers (`dsh-llm-replay`, `dsh-acp-snapshot`) share one codec; the write-side switch is the backend's `packChunks` config.
Providers stream token-sized deltas, so a raw log stores hundreds of `assistant/chunk` lines whose JSON envelopes dwarf their payloads. `packChunkRuns(events)` packs each run of ≥3 consecutive same-block delta chunks into one storage row — `text-chunks`, `reasoning-chunks`, or `tool-call-chunks` (bare slash-less tags: storage vocabulary, not `SessionEventMap` members) — and `decodeStorageRecord(value)` expands a parsed line back into its exact events (`seq0`/`time0` + per-member `dt` gaps reconstruct every `seq`/`time`). The encoder whitelists exact shapes and stores anything unrecognized verbatim; the decoder validates row-tagged values and throws on malformation. Owned here so the JSONL backend and the fixture readers (`dsh-llm-replay`, `dsh-acp-snapshot`) share one codec; the backend's default-enabled `packChunks` config controls writes only.
### Surface types

View File

@@ -52,7 +52,7 @@
### 分片行存储编解码器(`chunk-rows.ts`
提供方以 token 大小的增量流式输出,因此原始日志会存储数百行 `assistant/chunk`,其 JSON 封装远大于载荷。`packChunkRuns(events)` 将每段至少 3 个连续、同块的增量分片打包为一个存储行:`text-chunks``reasoning-chunks``tool-call-chunks`(不含斜杠的裸标签,属于存储词汇而不是 `SessionEventMap` 成员)。`decodeStorageRecord(value)` 则将已解析行展开回完全一致的事件(`seq0``time0` 加上每个成员的 `dt` 间隔,可重建每个 `seq``time`)。编码器只允许精确形态,并逐字存储任何无法识别的内容;解码器校验带行标签的值,形态错误时抛出异常。编解码器由此包所有,使 JSONL 后端和 fixture测试前置数据读取器`dsh-llm-replay``dsh-acp-snapshot`)共享同一编解码器;写入侧开关是后端的 `packChunks` 配置。
提供方以 token 大小的增量流式输出,因此原始日志会存储数百行 `assistant/chunk`,其 JSON 封装远大于载荷。`packChunkRuns(events)` 将每段至少 3 个连续、同块的增量分片打包为一个存储行:`text-chunks``reasoning-chunks``tool-call-chunks`(不含斜杠的裸标签,属于存储词汇而不是 `SessionEventMap` 成员)。`decodeStorageRecord(value)` 则将已解析行展开回完全一致的事件(`seq0``time0` 加上每个成员的 `dt` 间隔,可重建每个 `seq``time`)。编码器只允许精确形态,并逐字存储任何无法识别的内容;解码器校验带行标签的值,形态错误时抛出异常。编解码器由此包所有,使 JSONL 后端和 fixture测试前置数据读取器`dsh-llm-replay``dsh-acp-snapshot`)共享同一编解码器;后端默认启用`packChunks` 配置只控制写入
### Surface 类型

View File

@@ -183,6 +183,11 @@ function assertCurrentLlmShape(event: Record<string, unknown>, index: number): v
const header = record['header']
const config = typeof header === 'object' && header !== null ? (header as Record<string, unknown>)['config'] : undefined
if (!hasProviderModel(config)) throw new Error(`seed request/header at index ${index} lacks provider/model`)
const reasoningEffort = (config as Record<string, unknown>)['reasoningEffort']
if (reasoningEffort !== undefined
&& (typeof reasoningEffort !== 'string' || reasoningEffort.length === 0)) {
throw new Error(`seed request/header at index ${index} has an invalid reasoningEffort`)
}
}
if (event['type'] === 'assistant/message' && !hasProviderModel(record['provenance'])) {
throw new Error(`seed assistant/message at index ${index} lacks provider/model provenance`)

View File

@@ -156,7 +156,7 @@ export interface TodoItem {
* canonical empty optional fields are absent.
*/
export interface EpochHeader {
/** The conversation's call configuration (provider, model, and sampling scalars). */
/** The conversation's call configuration (provider, model, reasoning effort, and sampling scalars). */
config: LlmCallConfig
/** Rendered system prompt text; absent for a system-less request. */
system?: string

View File

@@ -4,6 +4,7 @@ import { describe, expect, it } from 'vitest'
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'
import { ReasoningEffortId } from '@deepseek-ai/dsh-llm'
const CONFIG = { provider: 'mock', model: 'm' }
@@ -29,6 +30,10 @@ describe('headerEquals', () => {
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,
config: { ...base.config, reasoningEffort: ReasoningEffortId('high') },
})).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)

View File

@@ -1,6 +1,6 @@
import { describe, expect, expectTypeOf, it, vi } from 'vitest'
import { Context } from 'cordis'
import { CallId } from '@deepseek-ai/dsh-llm'
import { CallId, ReasoningEffortId } from '@deepseek-ai/dsh-llm'
import SessionStore, {
displayPromptContent,
findLastMessageTurnEnd,
@@ -118,6 +118,11 @@ describe('Session', () => {
})
it('renders injected-context and steering messages as plain user content', () => {
expect(displayPromptContent({
content: [{ type: 'text', text: 'plain prompt' }],
source: { kind: 'user' },
})).toEqual([{ type: 'text', text: 'plain prompt' }])
const session = new Session(SessionId('s2'))
session.append('user/message', {
content: [{ type: 'text', text: 'file changed: a.ts' }],
@@ -228,6 +233,35 @@ describe('Session', () => {
.toEqual([unrelatedPrimitiveData])
})
it('round-trips a non-empty reasoning effort and rejects invalid durable values', () => {
const valid = {
type: 'request/header',
seq: 0,
time: 1,
data: {
header: {
config: {
provider: 'mock',
model: 'model',
reasoningEffort: ReasoningEffortId('adapter-owned'),
},
},
reason: 'initial',
},
} as const
expect(new Session(SessionId('reasoning-effort'), [valid]).events[0])
.toEqual(valid)
for (const reasoningEffort of ['', 1]) {
const invalid = structuredClone(valid) as unknown as SessionEvent
if (invalid.type !== 'request/header') throw new Error('test fixture must be a request header')
const config = invalid.data.header.config as unknown as Record<string, unknown>
config.reasoningEffort = reasoningEffort
expect(() => new Session(SessionId('invalid-reasoning-effort'), [invalid]))
.toThrow('seed request/header at index 0 has an invalid reasoningEffort')
}
})
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' })