docs(i18n): address proofreading review findings
This commit is contained in:
xjt
@@ -3,4 +3,4 @@
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.md
|
||||
2026-07-10-readme-known-limitations-gate.md: 2ca1168d795692730d17b6ab23dd113e8be277e5
|
||||
2026-07-10-readme-known-limitations-gate.zh.md: dcea7cd2d2c595966687d897fc6042dfd0099115
|
||||
2026-07-10-readme-known-limitations-gate.zh.md: cabb368af5b3e35ffcb8713b2c96fdb767f6237d
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# Agent Note: 每个包README 中受门禁保护的「已知限制」章节
|
||||
# Agent Note: 每个包 README 中受门禁保护的「已知限制」章节
|
||||
|
||||
Status: implemented
|
||||
|
||||
|
||||
@@ -1,6 +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
|
||||
2026-07-23-translation-prompt-v4-contract.md: 3e1e51797aa3463c8db24d8657120434e6822789
|
||||
2026-07-23-translation-prompt-v4-contract.zh.md: 161d2b6cf3bd3499e3c505a178da40ce577ca797
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-23-translation-prompt-v4-contract.md
|
||||
2026-07-23-translation-prompt-v4-contract.md: adeb63e0f4bf03ec0b94a371f596bb84138d81ed
|
||||
2026-07-23-translation-prompt-v4-contract.zh.md: 5bd7bbf0d2d02222ca8038afb0f5a156fffea1b0
|
||||
|
||||
@@ -12,6 +12,8 @@ Automated counterpart generation needs a stable prompt that reproduces the regis
|
||||
|
||||
The committed [translation prompt](../../../../docs/i18n/translation-prompt.md) is the calibrated pipeline asset. Its renderer injects only the source language, target language, and current [terminology table](../../../../docs/i18n/terminology.md), and rejects unknown, missing, or malformed placeholder syntax before assembling a request. The request assembler retains the source basename outside the model-visible prompt and places each reviewed whole-document pair into one bare-text user/assistant example turn before the real source document. The template may carry model-specific calibration rules, but those rules remain subordinate to the repository's binding pairing, terminology, structure, and emphasis contracts.
|
||||
|
||||
The v7 calibration retains that v4 protocol and makes the instruction priority explicit: source meaning and protected structure, then the terminology table, then whole-document gold-pair voice, then general guidance and embedded examples. It directs the model to draft as a native technical author and then compare clause by clause, preserving actors, conditions, negation, modality, lifecycle conditions, direction, result channels, ownership, and quantities. Style guidance cannot invent an actor or vary a terminology-table form, defined concept, or contract verb merely for variety. Unresolved terminology stays unchanged in the translation and is reported only as pending review.
|
||||
|
||||
The response has three ordered top-level sections: `translation`, `review`, and `final`. The response consumer derives the target basename from the retained source context, preserves optional leading YAML frontmatter, and mechanically inserts or corrects the language switcher after the first H1 in `final`. The parser requires each section exactly once, rejects content outside the envelope, and tolerates one outer `xml` Markdown fence because models sometimes echo the prompt's example fence.
|
||||
|
||||
## Response framing
|
||||
@@ -28,6 +30,10 @@ The executable contract lives in [the renderer, request assembler, parser, and r
|
||||
|
||||
**Return only the final translation.** A single body is simpler to parse but discards the explicit correction pass used to catch tone, structure, terminology, and punctuation defects before publication.
|
||||
|
||||
**Replace the calibrated v4 asset wholesale with a later experimental prompt.** Later experiments clarified useful general rules but did not pass strict whole-document evaluation as complete replacements. The production asset adopts only the improvements that preserve the established examples and executable protocol.
|
||||
|
||||
**Require a strict draft-to-final change ledger.** Requiring every final edit to appear in a free-text review ledger adds output burden without proving that the review catches local semantic drift. The review records actual corrections, while the final translation remains subject to deterministic structure checks and human review.
|
||||
|
||||
## Consequences
|
||||
|
||||
Prompt wording is executable behavior and receives code review, a translation-prompt verifier, and a runnable request/response snapshot. The calibrated asset and the general translation rules can evolve for their different audiences, but review must reject contradictions with binding repository contracts. The line escape is visible only when source documentation contains a wrapper tag on its own line, and parser tests pin its lossless behavior.
|
||||
Prompt wording is executable behavior and receives code review, a translation-prompt verifier, and a runnable request/response snapshot. Focused tests pin the retained v4 examples and selected v7 safeguards. The `translation-prompt-v4` snapshot directory names the stable renderer/parser protocol lineage rather than the current calibration revision. The calibrated asset and the general translation rules can evolve for their different audiences, but review must reject contradictions with binding repository contracts. The line escape is visible only when source documentation contains a wrapper tag on its own line, and parser tests pin its lossless behavior.
|
||||
|
||||
@@ -12,6 +12,8 @@ Status: implemented
|
||||
|
||||
提交入库的[翻译提示词](../../../../docs/i18n/translation-prompt.md)是经过校准的流水线资源。其渲染器仅注入源语言、目标语言和当前[术语表](../../../../docs/i18n/terminology.md)，并在组装请求前拒绝未知、缺失或语法格式错误的占位符。请求组装器在模型可见的提示词之外保留源文件基本名，并在真正的源文档之前，将每组经评审的整篇文档对编排为一个纯文本 user/assistant 示例轮次。模板可以包含针对特定模型的校准规则，但这些规则必须服从仓库中具约束力的配对、术语、结构与强调格式契约。
|
||||
|
||||
v7 校准保留这套 v4 协议，并明确指令优先级：先保持源文含义与受保护结构，再遵循术语表，然后以整篇金标校准语体，最后应用一般指导与内嵌示例。模型先以母语技术作者的方式起草，再逐项对照源文，保留执行主体、条件、否定、情态、生命周期条件、方向、结果通道、所有权和数量。文体指导不得虚构执行主体，也不得仅为丰富措辞而改换术语表词形、已定义概念或契约动词。无法裁定的术语在译文中保持不变，只在评审段标为待人工确认。
|
||||
|
||||
响应包含三个有序的顶层分段：`translation`、`review` 和 `final`。响应消费方根据保留的源文件上下文推导目标文件基本名，保留文件开头可选的 YAML frontmatter，并以机械方式在 `final` 中第一个 H1 之后插入或校正语言切换行。解析器要求每个分段恰好出现一次，拒绝封套之外的内容，并允许响应最外层有一层 `xml` Markdown 围栏，因为模型有时会照抄提示词中的示例围栏。
|
||||
|
||||
## 响应封装格式
|
||||
@@ -28,6 +30,10 @@ Status: implemented
|
||||
|
||||
**只返回最终译文。** 单一正文更易解析，却会丢弃显式修正步骤；这个步骤用于在发布前发现语气、结构、术语和标点缺陷。
|
||||
|
||||
**用较新的实验提示词整体替换经校准的 v4 资源。** 后续实验澄清了一些有价值的通用规则，但作为完整替代方案未通过严格的整篇文档评估。生产资源只吸收能够保留既有示例与可执行协议的改进。
|
||||
|
||||
**要求严格的草稿到定稿变更账本。** 要求定稿中的每项修改都出现在自由文本评审账本中，会增加输出负担，却不能证明评审能够发现局部语义漂移。评审段记录实际修正，定稿仍需接受确定性结构检查与人工评审。
|
||||
|
||||
## 影响
|
||||
|
||||
提示词措辞属于可执行行为，因此需要经过代码评审、翻译提示词校验器校验及可运行的请求/响应快照验证。经校准的资源与通用翻译规则可以针对各自的受众分别演进，但评审必须拒绝任何与仓库约束性契约冲突的改动。只有当源文档中的封装标签独占一行时，行转义才会显现；解析器测试锁定这一无损行为。
|
||||
提示词措辞属于可执行行为，因此需要经过代码评审、翻译提示词校验器校验及可运行的请求/响应快照验证。聚焦测试固定保留的 v4 示例与选定的 v7 保护规则。`translation-prompt-v4` 快照目录命名的是稳定的渲染器／解析器协议谱系，而不是当前校准修订号。经校准的资源与通用翻译规则可以针对各自的受众分别演进，但评审必须拒绝任何与仓库约束性契约冲突的改动。只有当源文档中的封装标签独占一行时，行转义才会显现；解析器测试锁定这一无损行为。
|
||||
|
||||
@@ -3,4 +3,4 @@
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-25-semantic-pr-label-taxonomy.md
|
||||
2026-07-25-semantic-pr-label-taxonomy.md: 3217b405e968d4d2c1eba1f1a5a08008b18ba514
|
||||
2026-07-25-semantic-pr-label-taxonomy.zh.md: 89be425165315dde5ec00fc197c88dd52edcf395
|
||||
2026-07-25-semantic-pr-label-taxonomy.zh.md: 60a863c4e37fb3fb905fd4b60bf949be3abfff65
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# Agent Note: 语义化 PR标签分类体系
|
||||
# Agent Note: 语义化 PR 标签分类体系
|
||||
|
||||
Status: implemented
|
||||
|
||||
|
||||
Reference in New Issue
Block a user