refactor(session): fold the session family into packages/session/
git mv the 12 packages from session-persistence/, session-projection/, session-title/, and telemetry/ into one session/ group per the regrouping RFC; merge the four group READMEs into one bilingual triplet; rewrite the group segment in tsconfig references (intra-group references shorten to ../<pkg>), tsconfig.base.json paths/globs, knip.json keys, vitest include, gate scripts, and authored doc/note citations; regenerate module graph, doc graphs, catalogs, and the lockfile importer keys. No npm names change. Full unit suite: 8779 passed; the 18 reported failures reproduce as env flakes (ambient-proxy IPv6 tunneling, watched-dir inotify timeouts under parallel load) — each passes in isolation with NO_PROXY set, matching their known pre-existing behavior on master.
This commit is contained in:
Tianyi Cui
@@ -0,0 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# 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/session-title/session-title-all-messages-llm/README.md
|
||||
README.md: 25ec92432b5c2d18624f2f4d851552ee2b3bf5d0
|
||||
README.zh.md: 947aa614741b2b0bd50e70f1d273a625a5624cc6
|
||||
@@ -0,0 +1,28 @@
|
||||
# @deepseek-ai/dsh-session-title-all-messages-llm
|
||||
|
||||
English | [中文](README.zh.md)
|
||||
|
||||
Optional `ctx.sessionTitle` provider that summarizes every eligible human message through `ctx.llm`. It registers the `all-user-messages` cadence and starts a new revision after each new human prompt, using seeded history as well as child-session prompts. A newer revision aborts and supersedes older work; even a provider that ignores cancellation cannot commit stale output.
|
||||
|
||||
The plugin uses the complete required [shared LLM configuration](../session-title-llm/README.md#configuration). Omit both `provider` and `model` to inherit the exact route from each current logged main request, or set both to route title generation independently. If the final framed aggregate prompt exceeds `maxInputBytes`, the request fails instead of truncating history; automatic use warns and keeps the prior title.
|
||||
|
||||
## Model Experience
|
||||
|
||||
### All-messages title request
|
||||
|
||||
#### What the model sees
|
||||
|
||||
The title model receives the shared title instruction and a JSON array of all eligible human messages through the current revision, in log order with exact seqs. Seeded history is included.
|
||||
|
||||
#### Token effect
|
||||
|
||||
One auxiliary request may follow every new eligible prompt, bounded per request by `maxInputBytes` and `maxOutputTokens`; explicit refreshes may add calls. The main agent request gains zero tokens.
|
||||
|
||||
#### KV Cache effect
|
||||
|
||||
No main-request invalidation. Auxiliary input grows or changes after each prompt, so provider-specific cache reuse ends at the first changed JSON token.
|
||||
|
||||
## Known Limitations and Deferred Work
|
||||
|
||||
- Input overflow retains the prior title; this provider has no summarization-of-summaries or retention policy for very long sessions.
|
||||
- It treats all eligible human messages equally and offers no weighting, filtering, or manual-title precedence.
|
||||
@@ -0,0 +1,28 @@
|
||||
# @deepseek-ai/dsh-session-title-all-messages-llm
|
||||
|
||||
[English](README.md) | 中文
|
||||
|
||||
可选的 `ctx.sessionTitle` 提供方，通过 `ctx.llm` 总结所有符合条件的用户消息。它注册 `all-user-messages` 节奏，并在每条新用户提示词后启动新 revision，同时使用预置历史与子会话提示词。较新的 revision 会中止并取代旧工作；即使提供方忽略取消，也无法提交陈旧输出。
|
||||
|
||||
该插件使用完整且必填的[共享大语言模型（LLM）配置](../session-title-llm/README.md#configuration)。同时省略 `provider` 与 `model` 时，会继承每个当前已记录主请求的确切路由；也可以同时设置二者，使标题生成使用独立路由。如果最终封装的聚合提示词超过 `maxInputBytes`，请求会失败而不是截断历史；自动使用时会发出警告并保留先前标题。
|
||||
|
||||
## 模型体验
|
||||
|
||||
### 全消息标题请求
|
||||
|
||||
#### 模型看到的内容
|
||||
|
||||
标题模型会收到共享标题指令，以及一个 JSON 数组，其中按日志顺序包含截至当前 revision 的所有符合条件用户消息和确切 seq。预置历史也包含在内。
|
||||
|
||||
#### Token 影响
|
||||
|
||||
每条符合条件的新提示词之后都可能发送一次辅助请求，每次请求受 `maxInputBytes` 和 `maxOutputTokens` 约束；显式刷新可能增加调用。主 agent（智能体）请求不会增加 token。
|
||||
|
||||
#### KV Cache 影响
|
||||
|
||||
不会使主请求的 KV Cache 失效。每条提示词后，辅助输入都会增长或变化，因此提供方专用缓存复用会在第一个变化的 JSON token 处结束。
|
||||
|
||||
## 已知限制与暂缓事项
|
||||
|
||||
- 输入溢出时保留先前标题；对于很长的会话，此提供方没有基于摘要继续生成摘要的机制或保留策略。
|
||||
- 它平等对待所有符合条件的用户消息，不提供权重、过滤或手动标题优先级。
|
||||
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"name": "@deepseek-ai/dsh-session-title-all-messages-llm",
|
||||
"description": "All-user-messages LLM provider plugin for DeepSeek Harness session titles",
|
||||
"version": "0.0.1",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"main": "lib/index.js",
|
||||
"types": "lib/types/index.d.ts",
|
||||
"exports": {
|
||||
".": {
|
||||
"types": "./lib/types/index.d.ts",
|
||||
"default": "./lib/index.js"
|
||||
},
|
||||
"./invariant": {
|
||||
"types": "./lib/types/invariant.d.ts",
|
||||
"default": "./lib/invariant.js"
|
||||
},
|
||||
"./package.json": "./package.json"
|
||||
},
|
||||
"files": ["lib/index.js", "lib/invariant.js", "lib/types/**/*.d.ts"],
|
||||
"license": "BSD-3-Clause",
|
||||
"peerDependencies": {
|
||||
"@deepseek-ai/dsh-invariants": "^0.0.1",
|
||||
"@deepseek-ai/dsh-llm": "^0.0.1",
|
||||
"@deepseek-ai/dsh-session": "^0.0.1",
|
||||
"@deepseek-ai/dsh-session-title": "^0.0.1",
|
||||
"@deepseek-ai/dsh-session-title-llm": "^0.0.1",
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
},
|
||||
"dependencies": {
|
||||
"schemastery": "^3.18.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@deepseek-ai/dsh-invariants": "workspace:^",
|
||||
"@deepseek-ai/dsh-llm": "workspace:^",
|
||||
"@deepseek-ai/dsh-session": "workspace:^",
|
||||
"@deepseek-ai/dsh-session-title": "workspace:^",
|
||||
"@deepseek-ai/dsh-session-title-llm": "workspace:^",
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,36 @@
|
||||
/** All-human-messages model provider for `ctx.sessionTitle`. */
|
||||
|
||||
import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
import {
|
||||
registerSessionTitleLlmProvider,
|
||||
SessionTitleLlmConfigFields,
|
||||
} from '@deepseek-ai/dsh-session-title-llm'
|
||||
import type { SessionTitleLlmConfig } from '@deepseek-ai/dsh-session-title-llm'
|
||||
|
||||
export const name = 'session-title-all-messages-llm'
|
||||
export const inject = ['sessionTitle', 'llm', 'sessions']
|
||||
|
||||
/** Required LLM policy; this plugin adds no defaults. */
|
||||
export type Config = SessionTitleLlmConfig
|
||||
/** Loader schema shared with the first-message provider. */
|
||||
/* jscpd:ignore-start -- Loader requires each plugin to export its own statically walkable schema; the field validators remain shared. */
|
||||
export const Config: z<Config> = z.object({
|
||||
targetWords: SessionTitleLlmConfigFields.targetWords,
|
||||
targetCjkCharacters: SessionTitleLlmConfigFields.targetCjkCharacters,
|
||||
maxInputBytes: SessionTitleLlmConfigFields.maxInputBytes,
|
||||
maxOutputTokens: SessionTitleLlmConfigFields.maxOutputTokens,
|
||||
timeoutMs: SessionTitleLlmConfigFields.timeoutMs,
|
||||
provider: SessionTitleLlmConfigFields.provider,
|
||||
model: SessionTitleLlmConfigFields.model,
|
||||
})
|
||||
/* jscpd:ignore-end */
|
||||
|
||||
/**
|
||||
* Register the all-user-messages model provider.
|
||||
* @param ctx - context exposing session-title, LLM, and session services.
|
||||
* @param config - required route, target, byte, token, and timeout policy.
|
||||
*/
|
||||
export function apply(ctx: Context, config: Config): void {
|
||||
registerSessionTitleLlmProvider(ctx, config, name, 'all-user-messages', messages => messages)
|
||||
}
|
||||
@@ -0,0 +1,30 @@
|
||||
/**
|
||||
* Package-owned invariant companion for `@deepseek-ai/dsh-session-title-all-messages-llm`.
|
||||
* @module @deepseek-ai/dsh-session-title-all-messages-llm/invariant
|
||||
*/
|
||||
|
||||
/* jscpd:ignore-start */
|
||||
import type { Context } from 'cordis'
|
||||
import type { InvariantInstaller } from '@deepseek-ai/dsh-invariants'
|
||||
|
||||
const PACKAGE_NAME = '@deepseek-ai/dsh-session-title-all-messages-llm'
|
||||
|
||||
/** Cordis companion plugin name. */
|
||||
export const name = 'session-title-all-messages-llm-invariant'
|
||||
/** Service required before the companion can reserve package ownership. */
|
||||
export const inject = ['invariants']
|
||||
|
||||
/**
|
||||
* No runtime invariant: this thin provider delegates request and result validation to the shared
|
||||
* title service and LLM helper and retains no independent mutable state.
|
||||
*/
|
||||
const install: InvariantInstaller = () => {}
|
||||
|
||||
/**
|
||||
* Register this package's invariant companion.
|
||||
* @param ctx - Cordis context carrying the invariant service.
|
||||
* @returns the installed registration's disposer after setup succeeds.
|
||||
*/
|
||||
export const apply = (ctx: Context): Promise<() => void> =>
|
||||
Promise.resolve(ctx.invariants.register(PACKAGE_NAME, install))
|
||||
/* jscpd:ignore-end */
|
||||
@@ -0,0 +1,73 @@
|
||||
import { Context } from 'cordis'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import LlmService, { createUserMessage, LlmAdapter } from '@deepseek-ai/dsh-llm'
|
||||
import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import SessionTitleService from '@deepseek-ai/dsh-session-title'
|
||||
import * as providerPlugin from '@deepseek-ai/dsh-session-title-all-messages-llm'
|
||||
|
||||
class RecordingAdapter extends LlmAdapter {
|
||||
readonly requests: GenerateOptions[] = []
|
||||
|
||||
override async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
this.requests.push(options)
|
||||
yield { type: 'text-delta', index: 0, text: 'All messages model title' }
|
||||
yield { type: 'finish', reason: { kind: 'stop' } }
|
||||
}
|
||||
}
|
||||
|
||||
const TITLE_CONFIG = { fallbackMaxWords: 5, fallbackMaxBytes: 40, maxTitleBytes: 80 } as const
|
||||
const LLM_CONFIG = {
|
||||
targetWords: 5,
|
||||
targetCjkCharacters: 10,
|
||||
maxInputBytes: 1_000,
|
||||
maxOutputTokens: 32,
|
||||
timeoutMs: 1_000,
|
||||
} as const
|
||||
|
||||
async function settle(): Promise<void> {
|
||||
await new Promise(resolve => setTimeout(resolve, 0))
|
||||
}
|
||||
|
||||
describe('all-messages LLM title provider', () => {
|
||||
it('includes seeded history and the latest prompt while inheriting the logged request route', async () => {
|
||||
const seeded = Session.create(SessionId('seed-source'))
|
||||
seeded.append('turn/start', { turn: 1 })
|
||||
const inherited = seeded.append('user/message', createUserMessage({
|
||||
content: [{ type: 'text', text: 'inherited prompt' }], source: { kind: 'user' },
|
||||
}), { surfaceOp: 'append' })
|
||||
seeded.append('session/title', {
|
||||
title: 'Inherited fallback', messageSeqs: [inherited.seq], source: { kind: 'fallback' },
|
||||
})
|
||||
seeded.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
|
||||
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SessionTitleService, TITLE_CONFIG)
|
||||
const adapter = new RecordingAdapter()
|
||||
ctx.llm.registerAdapter(['current-route'], adapter)
|
||||
await ctx.plugin(providerPlugin, LLM_CONFIG)
|
||||
const session = ctx.sessions.create(SessionId('all-plugin'), {
|
||||
seed: seeded.events,
|
||||
meta: { parentSession: seeded.id, seedLength: seeded.seq },
|
||||
})
|
||||
session.append('turn/start', { turn: 2 })
|
||||
const latest = session.append('user/message', createUserMessage({
|
||||
content: [{ type: 'text', text: 'latest prompt' }], source: { kind: 'user' },
|
||||
}), { surfaceOp: 'append' })
|
||||
await settle()
|
||||
session.append('request/header', {
|
||||
header: { config: { provider: 'current-route', model: 'current-model' } }, reason: 'resume',
|
||||
})
|
||||
await settle()
|
||||
|
||||
expect(adapter.requests[0]).toMatchObject({ provider: 'current-route', model: 'current-model' })
|
||||
const content = adapter.requests[0]?.messages[0]?.content[0]
|
||||
expect(content?.type === 'text' && content.text).toContain('inherited prompt')
|
||||
expect(content?.type === 'text' && content.text).toContain('latest prompt')
|
||||
expect(ctx.sessionTitle.get(session)).toMatchObject({
|
||||
messageSeqs: [inherited.seq, latest.seq],
|
||||
})
|
||||
})
|
||||
})
|
||||
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"extends": "../../../tsconfig.base.json",
|
||||
"compilerOptions": { "rootDir": "src", "outDir": "lib/types" },
|
||||
"include": ["src"],
|
||||
"references": [
|
||||
{ "path": "../../../vendor/cosmokit" },
|
||||
{ "path": "../../../vendor/cordis" },
|
||||
{ "path": "../../../vendor/schemastery" },
|
||||
{ "path": "../../support/invariants" },
|
||||
{ "path": "../../llm/llm" },
|
||||
{ "path": "../session-title" },
|
||||
{ "path": "../session-title-llm" }
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user