From 65bd54f8b450c2b2e7268db3ba9c790e03785778 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Thu, 30 Jul 2026 11:16:05 +0800 Subject: [PATCH] fix(tests): route the cross-adapter e2e to deepseek-official and re-record the translation-prompt snapshot --- packages/llm/llm-pi-ai/tests/adapter.e2e.ts | 2 +- .../translation-prompt-v4/request-response.expected.json | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/llm/llm-pi-ai/tests/adapter.e2e.ts b/packages/llm/llm-pi-ai/tests/adapter.e2e.ts index a3a949fea2..4637a75298 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.e2e.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.e2e.ts @@ -155,7 +155,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-pi-ai e2e (real API)', () => const prompt = ask('Reply with exactly the word: pong') const [fromDeepSeek, fromPiAi] = await Promise.all([ - assemble(deepseekCtx, { model: FLASH, messages: prompt, maxTokens: 50 }), + assemble(deepseekCtx, { provider: 'deepseek-official', model: FLASH, messages: prompt, maxTokens: 50 }), assemble(piCtx, { model: FLASH, messages: prompt, maxTokens: 50 }), ]) expect(blockKinds(fromPiAi)).toEqual(blockKinds(fromDeepSeek)) diff --git a/scripts/snapshots/translation-prompt-v4/request-response.expected.json b/scripts/snapshots/translation-prompt-v4/request-response.expected.json index 96eaad8c33..e2a409b2d6 100644 --- a/scripts/snapshots/translation-prompt-v4/request-response.expected.json +++ b/scripts/snapshots/translation-prompt-v4/request-response.expected.json @@ -4,7 +4,7 @@ "messages": [ { "role": "system", - "content": "# Translation Prompt\n\nYou are a senior technical translator specializing in LLM and agent development documentation. Your task is to translate the given source document from English to Chinese, producing natural, professional technical prose.\n\n## Quality Requirements\n\n### Structure and Format Preservation\n- Output a complete translated document that maintains exactly the same structure as the source: heading hierarchy, list shape, table columns, link targets, and code blocks.\n- Fenced code blocks must be byte-identical to the source, including ALL comments inside them. Do NOT translate comments inside code blocks. This is a hard rule with no exceptions.\n- Inline code spans (commands, flags, paths, API names, version numbers) must be kept verbatim. Never translate or reformat them.\n- Every relative link must point to the same target as in the source. Link text is translated; link targets are not.\n- Language switcher line: when translating into Chinese, write `[English](source-filename.md) | 中文`. When translating into English, write `English | [中文](source-filename.zh.md)`. Do NOT copy the switcher line from the source file unchanged — you must flip the link direction.\n- After a closing bold marker `**`, insert a space before the next character when that character is a Latin letter, digit, or CJK ideograph. Never insert a space before any punctuation (full-width or half-width).\n\n### Tone and Style\n- The translation must read as if originally written in the target language by a native speaker. If an expression sounds like a word-for-word rendering from the source language, rephrase it.\n- Write in a professional, formal tone appropriate for developer documentation. Never use colloquial or casual expressions.\n- Use polite imperative forms where the text instructs the reader to do something.\n- Keep the author's register: concise stays concise, detailed stays detailed.\n\n### Sentence Structure\n- Break long sentences with commas or semicolons. Avoid run-on sentences.\n- Prefer active voice. Convert passive constructions to active if it reads more naturally.\n- Translate meaning, not words. Restructure sentences where the target language grammar requires it.\n- Do not invent words or expressions that do not exist in natural technical writing of the target language.\n\n### Word Choice\n- Prefer precise, formal vocabulary over casual or colloquial alternatives.\n- When multiple synonyms exist, choose the one most commonly used in professional technical documentation of the target language.\n- Avoid slang, internal jargon, or overly literal translations that would not be recognized by the general developer audience.\n- Do not use the same word to translate two different source-language terms that carry distinct meanings.\n- Avoid repeating the same verb in close proximity; vary word choice for readability.\n\n#### When translating into Chinese\n- When a number modifies a noun, always include a Chinese classifier or measure word (量词). For example: \"three-package seam\" → \"由三个包构成的 seam\", not \"三包 seam\".\n\n### Punctuation\n\n#### When translating into Chinese\n- Use full-width Chinese punctuation in prose: `，。：；？！（）「」`.\n- Strongly prefer replacing all em-dashes (——) with colons, periods, commas, or parentheses. Keep an em-dash only if no other punctuation works at all.\n- Use enumeration commas (、) between parallel items, not regular commas.\n- List item endings: use semicolons or no punctuation. Do not end list items with commas.\n- Put one half-width space between Chinese text and Latin words/numbers.\n- For RFC 2119 keywords (MUST, MUST NOT, SHOULD, MAY), translate to the corresponding Chinese term (必须、禁止、应当、可以) and keep the SOURCE emphasis marker: plain source stays plain (必须), italic source stays italic (*必须*), and bold source stays bold (**必须**).\n\n#### When translating into English\n(To be added.)\n\n## Terminology\n\nA terminology table is provided below. Follow it strictly:\n- Render every listed term exactly as specified.\n- When the target language is Chinese, use the \"中文\" column. On first occurrence, write the \"首次出现\" value with its parenthetical gloss; on subsequent occurrences, write only the part before the parentheses.\n- When the target language is English, use the \"English\" column without a Chinese gloss; do not copy the \"中文\" or \"首次出现\" value into English prose.\n- If a term has already been glossed as part of a compound term, do not gloss it again when it appears alone later.\n- NEVER use translations listed in the \"不要译作\" column.\n- For technical terms not in the table, follow the target language: for a Chinese target, use an established Chinese rendering from a major Chinese-language OSS or vendor source, or keep the source term and flag it as pending when no such precedent exists; for an English target, use the established English technical term, or preserve an ambiguous source term with a short English gloss and flag it as pending. Do not invent a translation. This rule applies to terminology only; for general prose, freely restructure and paraphrase for natural expression.\n\n# Terminology\n\n本表约定本仓库的中英术语统一译法。\n\n**通用规则：**\n- \"中文\"列为中文译文的正文默认用词。若该列为英文，则中文译文的正文中保留英文不翻译。\n- 首次出现按\"首次出现\"列书写（带括号注释）；后续出现只写括号前的部分（可能为中文，也可能为英文），不出现括号内的注释。\n- \"不要译作\"列为严格禁止的译法。\n- 如果某术语已经作为另一个术语的组成部分被括注过（如 `agent loop（智能体循环）` 中已包含 `agent` 的括注），则该术语后续单独出现时无需再次括注。\n\n## 缩写类（中英文文本中均使用缩写）\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| ACP | ACP | ACP（Agent Client Protocol） | | |\n| AI | AI | AI（人工智能） | | |\n| API | API | | | |\n| CI | CI | | | |\n| CLI | CLI | CLI（命令行界面） | | |\n| e2e | e2e | | | |\n| HMR | HMR | HMR（热模块替换） | | |\n| JSON Schema | JSON Schema | | | |\n| JSONL | JSONL | | | |\n| LLM | LLM | LLM（大语言模型） | | |\n| MCP | MCP | | | |\n| PR | PR | PR（Pull Request） | | |\n| RAG | RAG | RAG（检索增强生成） | | |\n| SDK | SDK | | | |\n| SSE | SSE | SSE（Server-Sent Events） | | |\n\n## 英文类（中英文文本中均使用英文）\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| agent | agent | agent（智能体） | | |\n| Agent Note | Agent Note | Agent Note（agent 决策记录） | 智能体注记、智能体笔记 | 本仓库中由 agent 撰写的提案与决策记录 |\n| agent harness | agent harness | agent harness（智能体框架） | | agent 组合词（agent harness/workflow/loop/skill 等）整体保留英文；未括注过 agent 时首现按对应组合词或 agent 行处理 |\n| agent loop | agent loop | agent loop（智能体循环） | | |\n| blob hash | blob hash | | | `git hash-object` 的结果 |\n| Cordis | Cordis | | | |\n| dispose | dispose | dispose（资源释放） | | |\n| doc-sync | doc-sync | doc-sync（文档同步门禁） | | |\n| fiber | fiber | | | |\n| fixture | fixture | fixture（测试前置数据） | | |\n| fork | fork | | | |\n| Function Calling | Function Calling | Function Calling（函数调用） | | |\n| harness | harness | | | |\n| harness engineering | harness engineering | | | |\n| lint | lint | | | |\n| mock | mock | | | 保留英文；指测试替身 |\n| loader | loader | | | |\n| manifest | manifest | manifest（元数据清单） | | |\n| monorepo | monorepo | | | |\n| Round | Round | | 回合、目标回合、Ralph 回合 | 外层策略使用 Round 时，领域层级为 Session > Round > Turn（轮次） > Step（步骤）；Round 是可选的外层策略迭代，并非每个会话轮次都具有的通用层级。Goal Round 与 Ralph Round 均保留英文。一个 Round 承载一个轮次，步骤隶属于该轮次；明确的零步骤轮次仍保持原义。 |\n| schema | schema | | | |\n| schema DSL | schema DSL | | | |\n| seam | seam | | | 与 `extension point` 是不同概念；根据具体语境，可译为`服务边界`或`可替换点` |\n| skill | skill | skill（技能） | | |\n| spawn | spawn | | | |\n| steering | steering | steering（中途引导） | | |\n| task id | task id | | 任务 id | 保留英文 |\n| subagent | subagent | | | |\n| thinking | thinking | | | API 字段保留英文；描述模型模式时译为`思考` |\n| transcript | transcript | transcript（文本记录） | | 指会话渲染给用户或编辑器的完整文本，区别于事件日志 |\n| waterfall | waterfall | waterfall（瀑布式事件） | | |\n| wheel | wheel 包 | | | Python 打包格式 |\n| worktree | worktree | | | git 工作区概念 |\n| Zstandard | Zstandard | | | RFC 8878 compression format; `zstd` remains a code value. |\n\n## 双语类（中英文文本各自使用中英文）\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| adapter | 适配器 | | | |\n| adapter contract | 适配器契约 | 适配器契约（adapter contract） | | |\n| append-only | 仅追加 | | | |\n| artifact | 产物 | | | |\n| backend | 后端 | | | |\n| background task | 后台任务 | | | |\n| block | 块 | | | |\n| build target | 构建目标 | | | |\n| cancel | 取消 | | | |\n| feature | 功能 | | 能力 | SDK 产品与工程模型中的可管理产品单元 |\n| feature option | 功能选项 | | variant | 一项 SDK 功能内有限、可选择的实现或配置 |\n| checkpoint | 检查点 | | | |\n| chunk | 分片 | | | |\n| compaction | 压缩 | 压缩（compaction） | | |\n| companion tool | 配套工具 | | | |\n| Cordis plugin config | Cordis 插件配置 | | | Cordis 插件公开的 `Config` 对象或配置结构 |\n| config key | 配置键 | | | Cordis 插件配置中的单个字段 |\n| consumer | 消费方 | | | |\n| content block | 内容块 | | | |\n| Cookbook | 实操手册 | | | 文档标题用语 |\n| context | 上下文 | | | |\n| counterpart | 对侧文件 | | 对应物、配对物 | 双语配对语境；泛指\"另一侧\"时可写「另一侧」 |\n| context compaction | 上下文压缩 | 上下文压缩（context compaction） | | |\n| contract | 契约 | | | 如：`pairing contract` →`配对契约` |\n| Cordis config entry | Cordis 配置项 | | | 指 `cordis.yml` 插件列表中的一项；插件实现本身写`Cordis 插件` |\n| Cordis plugin | Cordis 插件 | | | Cordis 加载的插件实现，不指 `cordis.yml` 中的一项配置 |\n| coverage | 覆盖率 | | | |\n| crash recovery | 崩溃恢复 | | | |\n| deploy root | 部署根目录 | | | |\n| durability | 持久性 | | | |\n| feature requirement | 功能依赖 | | | 功能或功能选项通过 `requires` 声明的关系 |\n| ergonomics | 易用性 / 开发体验 | | 人体工学 | API 或面向模型的接口用「易用性」；工具链或开发者工作流用「开发体验」 |\n| event | 事件 | | | |\n| event log | 事件日志 | | | |\n| event stream | 事件流 | | | |\n| event-sourced | 事件溯源 | | | 沿用 DDD 社区通行译法 |\n| Executive summary | 摘要 | | | 事故复盘标题用语 |\n| executor | 执行器 | | | |\n| expected output | 预期输出 | | 金标 | 指 snapshot 比较产物；翻译语料的人工校准样例不在此列 |\n| extension | 扩展 | | | |\n| extension point | 扩展点 | | | 注意与 `seam` 区分 |\n| fail-fast | 快速失败 | | | |\n| fenced code block | 围栏代码块 | | | 沿用 MDN 中文翻译 |\n| fingerprint | 指纹 | | | 通用内容指纹；双语配对机制使用 sidecar record 记录两侧 blob hash |\n| finish reason | 结束原因 | | | |\n| foreground run | 前台运行 | | | |\n| freshness | 新鲜度 | | | 沿用 MDN 中文翻译；在本项目中指译文相对源文的同步状态 |\n| hook | 钩子 | | | |\n| implementation | 实现 | | | |\n| inference | 推理 | 推理（inference） | | 需要和 `reasoning` 区分时保留英文括注 |\n| info string | 信息字符串 | | | 沿用 CommonMark 中文翻译；指代码围栏 ``` 之后的语言标注 |\n| injection | 注入 | | | |\n| integration | 集成 | | | |\n| interface | 接口 | | | |\n| language switcher | 语言切换行 | | | i18n 配对机制用语：双语配对文件顶部的互链行 |\n| memory | 记忆 / 内存 | | | 与 `agent` 搭配时译为`记忆`（如 `agent memory` →`智能体记忆`）；指系统资源时译为`内存` |\n| merge | 合并 | | | |\n| message | 消息 | | | |\n| mod | 模组 | | | |\n| model provider | 模型提供方 | | | |\n| module | 模块 | | | |\n| non-escalation | 非升权 | | 非升级、不可升级 | 仅用于安全与权限语境，指主体不得获得超出既有授权的权限；普通升级不适用此行 |\n| npm dependency | NPM 依赖 | | | `package.json` 中的包关系；`dependencies`、`devDependencies` 等字段保持原样 |\n| opt-out ratio | opt-out 比例 | | 退出检查比例 | |\n| orphan | 遗留 | | 孤儿、孤立 | 指英文源已不存在的 `.zh.md`（如「遗留译文」）；进程语境按 OS 惯用语译「孤儿进程」 |\n| orphan branch | 孤立分支 | | 孤儿分支 | 沿用 git 官方中文翻译 |\n| package | 包 | 包（package） | | 指 npm 包（`@deepseek-ai/dsh-*`）；`package.json` 等代码标识保持原样 |\n| pairing | 配对 | | | |\n| parent-subset grants | 父级子集授权 | | 父集合授权 | 指授权范围仅限于父级所持授权的子集 |\n| peer dependency | 对等依赖 | 对等依赖（peer dependency） | | |\n| permission | 权限 | | | |\n| persistence | 持久化 | | | |\n| pipeline | 流水线 | | | |\n| plugin | 插件 | | | |\n| prompt | 提示词 | | | |\n| provider | 提供方 | | | |\n| provider-neutral | 提供方无关 | | | |\n| quality gate | 质量门禁 | | | |\n| quiescence | 完全停稳 | | 静默、静止状态 | 指生命周期工作全部结算后的状态 |\n| reasoning | 推理 | 推理（reasoning） | | 需要和 `inference` 区分时保留英文括注 |\n| reasoning_content | 思考内容 | | | |\n| registry | 注册表 | | | |\n| replay | 回放 | | | |\n| resume | 恢复 | | | |\n| runtime | 运行时 | | | |\n| same-world subprocess | 与宿主共享文件系统和内核的子进程 | | 同世界子进程 | |\n| sandbox | 沙箱 | | | |\n| service | 服务 | | | |\n| serving surface | 对外服务接口 | | | |\n| session | 会话 | | | |\n| session event | 会话事件 | | | |\n| sidecar record | 伴随记录 | | 旁挂记录 | 指与文档同目录的伴随记录文件 |\n| smoke test | 冒烟测试 | | | |\n| snapshot | 快照 | | | |\n| source of truth | 真源 | | | |\n| spine | 主干 | | | |\n| staged | 暂存 | | | 沿用 git 官方中文翻译 |\n| stale | 陈旧 | | 过期 | 与 `fresh`（`新鲜`）成对；门禁输出中保留英文 `stale` 不翻译；`expired` 才译为`过期` |\n| step | 步骤 | | | |\n| stream | 流 | | | |\n| streaming | 流式输出 | | | |\n| structural signature | 结构签名 | | | i18n 配对机制用语：门禁比对两侧文件时提取的有序结构序列（标题层级、代码块、列表等） |\n| Summary | 概述 | | | 事故复盘标题用语 |\n| system prompt | 系统提示词 | | | |\n| taxonomy | 分类体系 | | | |\n| token usage | token 用量 | | | |\n| tool | 工具 | | | |\n| tool call | 工具调用 | | | |\n| tool result | 工具结果 | | | |\n| tool schema | 工具 schema | | | |\n| toolkit | 工具包 | | | |\n| turn | 轮次 | | | |\n| VFS | VFS | 虚拟文件系统（VFS） | | |\n| typecheck | 类型检查 | | | |\n| vocabulary | 词汇 | | | |\n| wire format | 协议格式 | 协议格式（wire format） | | |\n| workflow | 工作流 | | | |\n| wrapper | 包装层 | | | 软件层或 SDK 包装层 |\n| wrapper script | 包装脚本 | | | 可执行脚本包装层 |\n\n\n## Output Format\n\nProduce your output in three XML sections:\n\nThe outer section tags are framing. If Markdown inside any section body contains a line consisting only of ``, ``, ``, ``, ``, or ``, prefix that line with `\\`. If the original line already has one or more backslashes immediately before the tag, add one more. The parser removes exactly one framing escape; tags mentioned inline need no escaping.\n\n```xml\n\n(Complete translation of the source document)\n\n\n\n(Self-review notes, one correction per line with category tag, e.g.)\n- [Tone] \"旁挂记录\" → \"伴随记录\"（生造词）\n- [Sentence] 第 3 段补充逗号断句\n- [Punctuation] 两处破折号替换为冒号\n- 无修正\n\n\n\n(Final translation after corrections)\n\n```\n\n## Self-Review Instructions\n\nAfter writing ``, re-read it in the target language only, without looking at the source. Check by category:\n\n**Structure**\n- Is the heading hierarchy, list shape, and code block content identical to the source?\n- Are ALL comments inside code blocks left untranslated (byte-identical to source)?\n- Is the language switcher line correctly flipped (not copied from source)?\n- Are link targets preserved, and are spaces after bold markers present only before Latin letters, digits, or CJK ideographs?\n- Are wrapper-tag lines inside section bodies escaped with one additional backslash?\n\n**Tone & Style**\n- Does every sentence read as if originally written by a native speaker?\n- Is there any colloquial, casual, or overly informal phrasing?\n\n**Sentence Structure**\n- Are there run-on sentences that need breaking?\n- Are there stiff passive constructions that should be converted to active voice?\n\n**Word Choice**\n- Are there overly literal translations that sound unnatural?\n- Is the same target-language word used to translate two distinct source concepts?\n- Is any slang or internal jargon present?\n\n**Terminology**\n- For a Chinese target, are first-occurrence glosses correctly applied (not missing, not repeated)? For an English target, are Chinese glosses absent?\n- Are any \"不要译作\" forbidden translations present?\n- For unlisted terms, does a Chinese target use established Chinese precedent or retain the source term as pending, and does an English target use established English terminology or preserve only an ambiguous source term with a short English gloss?\n\n**Punctuation** (when target is Chinese)\n- Are there em-dashes that should be replaced with colons, periods, or commas?\n- Are list items ending with commas instead of semicolons?\n- Do RFC 2119 keywords preserve the source emphasis exactly?\n\nRecord corrections in `` with category tags. Then output the corrected version in ``. If no corrections are needed, write \"无修正\" in `` and copy the translation unchanged into ``.\n\n## Examples\n\nBelow are representative examples of common problems and their corrections. Follow the \"Good\" versions.\n\n### Colloquial verb → Professional verb\n- Source: `The repo pins pnpm@11.7.0 in package.json`\n- Bad: `仓库在 package.json 中钉住 pnpm@11.7.0`\n- Good: `该仓库在 package.json 中固定使用 pnpm@11.7.0`\n\n### Run-on sentence → Natural phrasing with pause\n- Source: `Read docs/architecture.md before changing anything under packages/.`\n- Bad: `改动 packages/ 下的任何东西之前先读 docs/architecture.md。`\n- Good: `在修改 packages/ 目录下的任何内容之前，请先阅读 docs/architecture.md。`\n\n### Stiff passive voice → Active and natural\n- Source: `a green gate means the pair was confirmed consistent at these exact contents, not that the confirmation was sound.`\n- Bad: `门禁绿意味着这对文档曾在当前内容上被确认一致，不意味着这次确认本身是对的。`\n- Good: `门禁通过意味着这组文档在当前内容上的一致性得到了确认，不代表确认本身正确可靠。`\n\n### Invented word → Natural expression\n- Source: `A sidecar record of both blob hashes makes consistency checkable`\n- Bad: `旁挂记录两侧 blob hash，使一致性可检查`\n- Good: `伴随记录保存两侧 blob hash，使一致性可检查`\n\n### Em-dash → Colon/period\n- Source: `FIXME — an issue that should block a new release. A release should not ship with an open FIXME unless reviewers explicitly agree the change can be merged anyway.`\n- Bad: `FIXME——应当阻塞新版本发布的问题。除非评审者明确同意可以照常合入，发布不应带着未解决的 FIXME 出门。`\n- Good: `FIXME：应当阻塞新版本发布的问题。除非评审者明确同意该更改可以合并，否则发布版本不应包含未解决的 FIXME。`\n\n### Overly literal → Meaningful rendering\n- Source: `awkward phrasing is easier to hear without the source anchoring you`\n- Bad: `没有源文锚着，别扭的表述更容易被听出来`\n- Good: `不对照原文时，更容易察觉别扭的表达`\n\n### Terminology — do not translate what should be kept in English\n- Source: `typed service seams, and explicit extension points`\n- Bad: `类型化的服务 seam（扩展点）与显式扩展点`\n- Good: `类型化的服务 seam 与显式扩展点`\n\n### Slang/jargon → Professional phrasing\n- Source: `The committed agent workflow lives in .agents/skills/dsh-translate-docs`\n- Bad: `进仓的 agent 工作流见 .agents/skills/dsh-translate-docs`\n- Good: `仓库内置的 agent 工作流见 .agents/skills/dsh-translate-docs`\n\n### \"For humans\" — translate the intent, not the word\n- Source: `For humans, start with the development guide`\n- Bad: `对于人工读者，请先从开发指南开始`（\"人工读者\"生硬）\n- Good: `面向开发者：请先阅读开发指南`（\"开发者\"自然，且中文里冒号在此处更自然）\n\n### Code block comments — NEVER translate\n- Source code block contains: `# full-screen TUI coding agent (needs DEEPSEEK_API_KEY)`\n- Bad: `# 全屏 TUI coding agent（需要 DEEPSEEK_API_KEY）`\n- Good: `# full-screen TUI coding agent (needs DEEPSEEK_API_KEY)` (keep exactly as-is, byte-for-byte)\n\n### Language switcher — flip direction\n- Source file (English) has: `English | [中文](README.zh.md)`\n- Bad (copying source unchanged): `English | [中文](README.zh.md)`\n- Good (flipped for Chinese file): `[English](README.md) | 中文`\n\n---\n\nNow translate the following document:" + "content": "# Translation Prompt\n\nYou are a senior technical translator specializing in LLM and agent development documentation. Your task is to translate the given source document from English to Chinese, producing natural, professional technical prose.\n\n## Quality Requirements\n\n### Structure and Format Preservation\n- Output a complete translated document that maintains exactly the same structure as the source: heading hierarchy, list shape, table columns, link targets, and code blocks.\n- Fenced code blocks must be byte-identical to the source, including ALL comments inside them. Do NOT translate comments inside code blocks. This is a hard rule with no exceptions.\n- Inline code spans (commands, flags, paths, API names, version numbers) must be kept verbatim. Never translate or reformat them.\n- Every relative link must point to the same target as in the source. Link text is translated; link targets are not.\n- Language switcher line: when translating into Chinese, write `[English](source-filename.md) | 中文`. When translating into English, write `English | [中文](source-filename.zh.md)`. Do NOT copy the switcher line from the source file unchanged — you must flip the link direction.\n- After a closing bold marker `**`, insert a space before the next character when that character is a Latin letter, digit, or CJK ideograph. Never insert a space before any punctuation (full-width or half-width).\n\n### Tone and Style\n- The translation must read as if originally written in the target language by a native speaker. If an expression sounds like a word-for-word rendering from the source language, rephrase it.\n- Write in a professional, formal tone appropriate for developer documentation. Never use colloquial or casual expressions.\n- Use polite imperative forms where the text instructs the reader to do something.\n- Keep the author's register: concise stays concise, detailed stays detailed.\n\n### Sentence Structure\n- Break long sentences with commas or semicolons. Avoid run-on sentences.\n- Prefer active voice. Convert passive constructions to active if it reads more naturally.\n- Translate meaning, not words. Restructure sentences where the target language grammar requires it.\n- Do not invent words or expressions that do not exist in natural technical writing of the target language.\n\n### Word Choice\n- Prefer precise, formal vocabulary over casual or colloquial alternatives.\n- When multiple synonyms exist, choose the one most commonly used in professional technical documentation of the target language.\n- Avoid slang, internal jargon, or overly literal translations that would not be recognized by the general developer audience.\n- Do not use the same word to translate two different source-language terms that carry distinct meanings.\n- Avoid repeating the same verb in close proximity; vary word choice for readability.\n\n#### When translating into Chinese\n- When a number modifies a noun, always include a Chinese classifier or measure word (量词). For example: \"three-package seam\" → \"由三个包构成的 seam\", not \"三包 seam\".\n\n### Punctuation\n\n#### When translating into Chinese\n- Use full-width Chinese punctuation in prose: `，。：；？！（）「」`.\n- Strongly prefer replacing all em-dashes (——) with colons, periods, commas, or parentheses. Keep an em-dash only if no other punctuation works at all.\n- Use enumeration commas (、) between parallel items, not regular commas.\n- List item endings: use semicolons or no punctuation. Do not end list items with commas.\n- Put one half-width space between Chinese text and Latin words/numbers.\n- For RFC 2119 keywords (MUST, MUST NOT, SHOULD, MAY), translate to the corresponding Chinese term (必须、禁止、应当、可以) and keep the SOURCE emphasis marker: plain source stays plain (必须), italic source stays italic (*必须*), and bold source stays bold (**必须**).\n\n#### When translating into English\n(To be added.)\n\n## Terminology\n\nA terminology table is provided below. Follow it strictly:\n- Render every listed term exactly as specified.\n- When the target language is Chinese, use the \"中文\" column. On first occurrence, write the \"首次出现\" value with its parenthetical gloss; on subsequent occurrences, write only the part before the parentheses.\n- When the target language is English, use the \"English\" column without a Chinese gloss; do not copy the \"中文\" or \"首次出现\" value into English prose.\n- If a term has already been glossed as part of a compound term, do not gloss it again when it appears alone later.\n- NEVER use translations listed in the \"不要译作\" column.\n- For technical terms not in the table, follow the target language: for a Chinese target, use an established Chinese rendering from a major Chinese-language OSS or vendor source, or keep the source term and flag it as pending when no such precedent exists; for an English target, use the established English technical term, or preserve an ambiguous source term with a short English gloss and flag it as pending. Do not invent a translation. This rule applies to terminology only; for general prose, freely restructure and paraphrase for natural expression.\n\n# Terminology\n\n本表约定本仓库的中英术语统一译法。\n\n**通用规则：**\n- \"中文\"列为中文译文的正文默认用词。若该列为英文，则中文译文的正文中保留英文不翻译。\n- 首次出现按\"首次出现\"列书写（带括号注释）；后续出现只写括号前的部分（可能为中文，也可能为英文），不出现括号内的注释。\n- \"不要译作\"列为严格禁止的译法。\n- 如果某术语已经作为另一个术语的组成部分被括注过（如 `agent loop（智能体循环）` 中已包含 `agent` 的括注），则该术语后续单独出现时无需再次括注。\n\n## 缩写类（中英文文本中均使用缩写）\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| ACP | ACP | ACP（Agent Client Protocol） | | |\n| AI | AI | AI（人工智能） | | |\n| API | API | | | |\n| CI | CI | | | |\n| CLI | CLI | CLI（命令行界面） | | |\n| e2e | e2e | | | |\n| HMR | HMR | HMR（热模块替换） | | |\n| JSON Schema | JSON Schema | | | |\n| JSONL | JSONL | | | |\n| LLM | LLM | LLM（大语言模型） | | |\n| MCP | MCP | | | |\n| PR | PR | PR（Pull Request） | | |\n| RAG | RAG | RAG（检索增强生成） | | |\n| SDK | SDK | | | |\n| SSE | SSE | SSE（Server-Sent Events） | | |\n\n## 英文类（中英文文本中均使用英文）\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| agent | agent | agent（智能体） | | |\n| Agent Note | Agent Note | Agent Note（agent 决策记录） | 智能体注记、智能体笔记 | 本仓库中由 agent 撰写的提案与决策记录 |\n| agent harness | agent harness | agent harness（智能体框架） | | agent 组合词（agent harness/workflow/loop/skill 等）整体保留英文；未括注过 agent 时首现按对应组合词或 agent 行处理 |\n| agent loop | agent loop | agent loop（智能体循环） | | |\n| blob hash | blob hash | | | `git hash-object` 的结果 |\n| Cordis | Cordis | | | |\n| dispose | dispose | dispose（资源释放） | | |\n| doc-sync | doc-sync | doc-sync（文档同步门禁） | | |\n| fiber | fiber | | | |\n| fixture | fixture | fixture（测试前置数据） | | |\n| fork | fork | | | |\n| Function Calling | Function Calling | Function Calling（函数调用） | | |\n| harness | harness | | | |\n| harness engineering | harness engineering | | | |\n| lint | lint | | | |\n| mock | mock | | | 保留英文；指测试替身 |\n| loader | loader | | | |\n| manifest | manifest | manifest（元数据清单） | | |\n| monorepo | monorepo | | | |\n| Round | Round | | 回合、目标回合、Ralph 回合 | 外层策略使用 Round 时，领域层级为 Session > Round > Turn（轮次） > Step（步骤）；Round 是可选的外层策略迭代，并非每个会话轮次都具有的通用层级。Goal Round 与 Ralph Round 均保留英文。一个 Round 承载一个轮次，步骤隶属于该轮次；明确的零步骤轮次仍保持原义。 |\n| schema | schema | | | |\n| schema DSL | schema DSL | | | |\n| seam | seam | | | 与 `extension point` 是不同概念；根据具体语境，可译为`服务边界`或`可替换点` |\n| skill | skill | skill（技能） | | |\n| spawn | spawn | | | |\n| steering | steering | steering（中途引导） | | |\n| task id | task id | | 任务 id | 保留英文 |\n| subagent | subagent | | | |\n| thinking | thinking | | | API 字段保留英文；描述模型模式时译为`思考` |\n| transcript | transcript | transcript（文本记录） | | 指会话渲染给用户或编辑器的完整文本，区别于事件日志 |\n| waterfall | waterfall | waterfall（瀑布式事件） | | |\n| wheel | wheel 包 | | | Python 打包格式 |\n| worktree | worktree | | | git 工作区概念 |\n| Zstandard | Zstandard | | | RFC 8878 compression format; `zstd` remains a code value. |\n\n## 双语类（中英文文本各自使用中英文）\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| adapter | 适配器 | | | |\n| adapter contract | 适配器契约 | 适配器契约（adapter contract） | | |\n| append-only | 仅追加 | | | |\n| artifact | 产物 | | | |\n| backend | 后端 | | | |\n| background task | 后台任务 | | | |\n| block | 块 | | | |\n| build target | 构建目标 | | | |\n| cancel | 取消 | | | |\n| feature | 功能 | | 能力 | SDK 产品与工程模型中的可管理产品单元 |\n| feature option | 功能选项 | | variant | 一项 SDK 功能内有限、可选择的实现或配置 |\n| checkpoint | 检查点 | | | |\n| chunk | 分片 | | | |\n| compaction | 压缩 | 压缩（compaction） | | |\n| companion tool | 配套工具 | | | |\n| Cordis plugin config | Cordis 插件配置 | | | Cordis 插件公开的 `Config` 对象或配置结构 |\n| config key | 配置键 | | | Cordis 插件配置中的单个字段 |\n| consumer | 消费方 | | | |\n| content block | 内容块 | | | |\n| Cookbook | 实操手册 | | | 文档标题用语 |\n| context | 上下文 | | | |\n| counterpart | 对侧文件 | | 对应物、配对物 | 双语配对语境；泛指\"另一侧\"时可写「另一侧」 |\n| configurable-provider directory | 可配置提供方目录 | | | llm seam 中 `registerConfigurableProviders()` 维护的目录；沿用 Service Catalog →「服务目录」先例 |\n| context compaction | 上下文压缩 | 上下文压缩（context compaction） | | |\n| contract | 契约 | | | 如：`pairing contract` →`配对契约` |\n| Cordis config entry | Cordis 配置项 | | | 指 `cordis.yml` 插件列表中的一项；插件实现本身写`Cordis 插件` |\n| Cordis plugin | Cordis 插件 | | | Cordis 加载的插件实现，不指 `cordis.yml` 中的一项配置 |\n| coverage | 覆盖率 | | | |\n| crash recovery | 崩溃恢复 | | | |\n| deploy root | 部署根目录 | | | |\n| dormant | 休眠 | | 睡眠、蛰伏 | 指已声明可配置但当前未注册路由的提供方 |\n| durability | 持久性 | | | |\n| feature requirement | 功能依赖 | | | 功能或功能选项通过 `requires` 声明的关系 |\n| ergonomics | 易用性 / 开发体验 | | 人体工学 | API 或面向模型的接口用「易用性」；工具链或开发者工作流用「开发体验」 |\n| event | 事件 | | | |\n| event log | 事件日志 | | | |\n| event stream | 事件流 | | | |\n| event-sourced | 事件溯源 | | | 沿用 DDD 社区通行译法 |\n| Executive summary | 摘要 | | | 事故复盘标题用语 |\n| executor | 执行器 | | | |\n| expected output | 预期输出 | | 金标 | 指 snapshot 比较产物；翻译语料的人工校准样例不在此列 |\n| extension | 扩展 | | | |\n| extension point | 扩展点 | | | 注意与 `seam` 区分 |\n| fail-fast | 快速失败 | | | |\n| fenced code block | 围栏代码块 | | | 沿用 MDN 中文翻译 |\n| fingerprint | 指纹 | | | 通用内容指纹；双语配对机制使用 sidecar record 记录两侧 blob hash |\n| finish reason | 结束原因 | | | |\n| foreground run | 前台运行 | | | |\n| freshness | 新鲜度 | | | 沿用 MDN 中文翻译；在本项目中指译文相对源文的同步状态 |\n| hook | 钩子 | | | |\n| implementation | 实现 | | | |\n| inference | 推理 | 推理（inference） | | 需要和 `reasoning` 区分时保留英文括注 |\n| info string | 信息字符串 | | | 沿用 CommonMark 中文翻译；指代码围栏 ``` 之后的语言标注 |\n| injection | 注入 | | | |\n| integration | 集成 | | | |\n| interface | 接口 | | | |\n| language switcher | 语言切换行 | | | i18n 配对机制用语：双语配对文件顶部的互链行 |\n| memory | 记忆 / 内存 | | | 与 `agent` 搭配时译为`记忆`（如 `agent memory` →`智能体记忆`）；指系统资源时译为`内存` |\n| merge | 合并 | | | |\n| message | 消息 | | | |\n| mod | 模组 | | | |\n| model provider | 模型提供方 | | | |\n| module | 模块 | | | |\n| non-escalation | 非升权 | | 非升级、不可升级 | 仅用于安全与权限语境，指主体不得获得超出既有授权的权限；普通升级不适用此行 |\n| npm dependency | NPM 依赖 | | | `package.json` 中的包关系；`dependencies`、`devDependencies` 等字段保持原样 |\n| opt-out ratio | opt-out 比例 | | 退出检查比例 | |\n| orphan | 遗留 | | 孤儿、孤立 | 指英文源已不存在的 `.zh.md`（如「遗留译文」）；进程语境按 OS 惯用语译「孤儿进程」 |\n| orphan branch | 孤立分支 | | 孤儿分支 | 沿用 git 官方中文翻译 |\n| package | 包 | 包（package） | | 指 npm 包（`@deepseek-ai/dsh-*`）；`package.json` 等代码标识保持原样 |\n| pairing | 配对 | | | |\n| parent-subset grants | 父级子集授权 | | 父集合授权 | 指授权范围仅限于父级所持授权的子集 |\n| peer dependency | 对等依赖 | 对等依赖（peer dependency） | | |\n| permission | 权限 | | | |\n| persistence | 持久化 | | | |\n| pipeline | 流水线 | | | |\n| plugin | 插件 | | | |\n| prompt | 提示词 | | | |\n| provider | 提供方 | | | |\n| provider-neutral | 提供方无关 | | | |\n| quality gate | 质量门禁 | | | |\n| quiescence | 完全停稳 | | 静默、静止状态 | 指生命周期工作全部结算后的状态 |\n| reasoning | 推理 | 推理（reasoning） | | 需要和 `inference` 区分时保留英文括注 |\n| reasoning_content | 思考内容 | | | |\n| registry | 注册表 | | | |\n| replay | 回放 | | | |\n| resume | 恢复 | | | |\n| runtime | 运行时 | | | |\n| same-world subprocess | 与宿主共享文件系统和内核的子进程 | | 同世界子进程 | |\n| sandbox | 沙箱 | | | |\n| service | 服务 | | | |\n| serving surface | 对外服务接口 | | | |\n| session | 会话 | | | |\n| session event | 会话事件 | | | |\n| sidecar record | 伴随记录 | | 旁挂记录 | 指与文档同目录的伴随记录文件 |\n| smoke test | 冒烟测试 | | | |\n| snapshot | 快照 | | | |\n| source of truth | 真源 | | | |\n| spine | 主干 | | | |\n| staged | 暂存 | | | 沿用 git 官方中文翻译 |\n| stale | 陈旧 | | 过期 | 与 `fresh`（`新鲜`）成对；门禁输出中保留英文 `stale` 不翻译；`expired` 才译为`过期` |\n| step | 步骤 | | | |\n| stream | 流 | | | |\n| streaming | 流式输出 | | | |\n| structural signature | 结构签名 | | | i18n 配对机制用语：门禁比对两侧文件时提取的有序结构序列（标题层级、代码块、列表等） |\n| Summary | 概述 | | | 事故复盘标题用语 |\n| system prompt | 系统提示词 | | | |\n| taxonomy | 分类体系 | | | |\n| token usage | token 用量 | | | |\n| tool | 工具 | | | |\n| tool call | 工具调用 | | | |\n| tool result | 工具结果 | | | |\n| tool schema | 工具 schema | | | |\n| toolkit | 工具包 | | | |\n| turn | 轮次 | | | |\n| VFS | VFS | 虚拟文件系统（VFS） | | |\n| typecheck | 类型检查 | | | |\n| vocabulary | 词汇 | | | |\n| wire format | 协议格式 | 协议格式（wire format） | | |\n| workflow | 工作流 | | | |\n| wrapper | 包装层 | | | 软件层或 SDK 包装层 |\n| wrapper script | 包装脚本 | | | 可执行脚本包装层 |\n\n\n## Output Format\n\nProduce your output in three XML sections:\n\nThe outer section tags are framing. If Markdown inside any section body contains a line consisting only of ``, ``, ``, ``, ``, or ``, prefix that line with `\\`. If the original line already has one or more backslashes immediately before the tag, add one more. The parser removes exactly one framing escape; tags mentioned inline need no escaping.\n\n```xml\n\n(Complete translation of the source document)\n\n\n\n(Self-review notes, one correction per line with category tag, e.g.)\n- [Tone] \"旁挂记录\" → \"伴随记录\"（生造词）\n- [Sentence] 第 3 段补充逗号断句\n- [Punctuation] 两处破折号替换为冒号\n- 无修正\n\n\n\n(Final translation after corrections)\n\n```\n\n## Self-Review Instructions\n\nAfter writing ``, re-read it in the target language only, without looking at the source. Check by category:\n\n**Structure**\n- Is the heading hierarchy, list shape, and code block content identical to the source?\n- Are ALL comments inside code blocks left untranslated (byte-identical to source)?\n- Is the language switcher line correctly flipped (not copied from source)?\n- Are link targets preserved, and are spaces after bold markers present only before Latin letters, digits, or CJK ideographs?\n- Are wrapper-tag lines inside section bodies escaped with one additional backslash?\n\n**Tone & Style**\n- Does every sentence read as if originally written by a native speaker?\n- Is there any colloquial, casual, or overly informal phrasing?\n\n**Sentence Structure**\n- Are there run-on sentences that need breaking?\n- Are there stiff passive constructions that should be converted to active voice?\n\n**Word Choice**\n- Are there overly literal translations that sound unnatural?\n- Is the same target-language word used to translate two distinct source concepts?\n- Is any slang or internal jargon present?\n\n**Terminology**\n- For a Chinese target, are first-occurrence glosses correctly applied (not missing, not repeated)? For an English target, are Chinese glosses absent?\n- Are any \"不要译作\" forbidden translations present?\n- For unlisted terms, does a Chinese target use established Chinese precedent or retain the source term as pending, and does an English target use established English terminology or preserve only an ambiguous source term with a short English gloss?\n\n**Punctuation** (when target is Chinese)\n- Are there em-dashes that should be replaced with colons, periods, or commas?\n- Are list items ending with commas instead of semicolons?\n- Do RFC 2119 keywords preserve the source emphasis exactly?\n\nRecord corrections in `` with category tags. Then output the corrected version in ``. If no corrections are needed, write \"无修正\" in `` and copy the translation unchanged into ``.\n\n## Examples\n\nBelow are representative examples of common problems and their corrections. Follow the \"Good\" versions.\n\n### Colloquial verb → Professional verb\n- Source: `The repo pins pnpm@11.7.0 in package.json`\n- Bad: `仓库在 package.json 中钉住 pnpm@11.7.0`\n- Good: `该仓库在 package.json 中固定使用 pnpm@11.7.0`\n\n### Run-on sentence → Natural phrasing with pause\n- Source: `Read docs/architecture.md before changing anything under packages/.`\n- Bad: `改动 packages/ 下的任何东西之前先读 docs/architecture.md。`\n- Good: `在修改 packages/ 目录下的任何内容之前，请先阅读 docs/architecture.md。`\n\n### Stiff passive voice → Active and natural\n- Source: `a green gate means the pair was confirmed consistent at these exact contents, not that the confirmation was sound.`\n- Bad: `门禁绿意味着这对文档曾在当前内容上被确认一致，不意味着这次确认本身是对的。`\n- Good: `门禁通过意味着这组文档在当前内容上的一致性得到了确认，不代表确认本身正确可靠。`\n\n### Invented word → Natural expression\n- Source: `A sidecar record of both blob hashes makes consistency checkable`\n- Bad: `旁挂记录两侧 blob hash，使一致性可检查`\n- Good: `伴随记录保存两侧 blob hash，使一致性可检查`\n\n### Em-dash → Colon/period\n- Source: `FIXME — an issue that should block a new release. A release should not ship with an open FIXME unless reviewers explicitly agree the change can be merged anyway.`\n- Bad: `FIXME——应当阻塞新版本发布的问题。除非评审者明确同意可以照常合入，发布不应带着未解决的 FIXME 出门。`\n- Good: `FIXME：应当阻塞新版本发布的问题。除非评审者明确同意该更改可以合并，否则发布版本不应包含未解决的 FIXME。`\n\n### Overly literal → Meaningful rendering\n- Source: `awkward phrasing is easier to hear without the source anchoring you`\n- Bad: `没有源文锚着，别扭的表述更容易被听出来`\n- Good: `不对照原文时，更容易察觉别扭的表达`\n\n### Terminology — do not translate what should be kept in English\n- Source: `typed service seams, and explicit extension points`\n- Bad: `类型化的服务 seam（扩展点）与显式扩展点`\n- Good: `类型化的服务 seam 与显式扩展点`\n\n### Slang/jargon → Professional phrasing\n- Source: `The committed agent workflow lives in .agents/skills/dsh-translate-docs`\n- Bad: `进仓的 agent 工作流见 .agents/skills/dsh-translate-docs`\n- Good: `仓库内置的 agent 工作流见 .agents/skills/dsh-translate-docs`\n\n### \"For humans\" — translate the intent, not the word\n- Source: `For humans, start with the development guide`\n- Bad: `对于人工读者，请先从开发指南开始`（\"人工读者\"生硬）\n- Good: `面向开发者：请先阅读开发指南`（\"开发者\"自然，且中文里冒号在此处更自然）\n\n### Code block comments — NEVER translate\n- Source code block contains: `# full-screen TUI coding agent (needs DEEPSEEK_API_KEY)`\n- Bad: `# 全屏 TUI coding agent（需要 DEEPSEEK_API_KEY）`\n- Good: `# full-screen TUI coding agent (needs DEEPSEEK_API_KEY)` (keep exactly as-is, byte-for-byte)\n\n### Language switcher — flip direction\n- Source file (English) has: `English | [中文](README.zh.md)`\n- Bad (copying source unchanged): `English | [中文](README.zh.md)`\n- Good (flipped for Chinese file): `[English](README.md) | 中文`\n\n---\n\nNow translate the following document:" }, { "role": "user",