docs(i18n): restore prompt-v4 as the pipeline baseline
按 jingtingxiang 拍板将 prompt 回到 v4 基线:模板正文恢复内嵌的 格式/语气/句式/词汇/标点全量约束与 11 组正误例(量词规则按术语表 现行裁定 package→包 写作「由三个包构成的 seam」),不再注入 translation-rules.md——该文件约束人和 agent,不进模板;占位符收敛 为 source_lang/target_lang/terminology 三个,切换行由模型按文档 自身拼写。渲染器、解析器、conformance 门禁与单测同步回 v4 契约: 三段裸 XML(translation/review/final 顺序唯一),容忍整体 ```xml 围栏回显;saxes 依赖随 CDATA 协议一并移除。
This commit is contained in:
@@ -1,20 +1,16 @@
|
||||
/**
|
||||
* Executable renderer and strict response parser for the committed
|
||||
* documentation-translation prompt contract.
|
||||
* Executable renderer and response parser for the committed
|
||||
* documentation-translation prompt contract (prompt-v4).
|
||||
*
|
||||
* The v4 contract: three placeholders (`source_lang`, `target_lang`,
|
||||
* `terminology`), whole-document translation, and a three-section response
|
||||
* (`<translation>`, `<review>`, `<final>` in order, bare XML tags with raw
|
||||
* Markdown bodies). The switcher filename is spelled out by the model from
|
||||
* the document itself; the pipeline injects no other repository file.
|
||||
*/
|
||||
|
||||
import { basename } from 'node:path'
|
||||
import { SaxesParser } from 'saxes'
|
||||
|
||||
/** Placeholder names supported by the committed translation prompt. */
|
||||
export const TRANSLATION_PROMPT_PLACEHOLDERS = [
|
||||
'source_lang',
|
||||
'target_lang',
|
||||
'translation_rules',
|
||||
'terminology',
|
||||
'source_filename',
|
||||
'source_filename_zh',
|
||||
] as const
|
||||
export const TRANSLATION_PROMPT_PLACEHOLDERS = ['source_lang', 'target_lang', 'terminology'] as const
|
||||
|
||||
type TranslationPromptPlaceholder = (typeof TRANSLATION_PROMPT_PLACEHOLDERS)[number]
|
||||
|
||||
@@ -24,15 +20,11 @@ type TranslationLanguage = 'English' | 'Chinese'
|
||||
/** Inputs that vary for one rendered translation request. */
|
||||
export interface TranslationPromptInput {
|
||||
sourceLanguage: TranslationLanguage
|
||||
/** Source basename, including `.md` or `.zh.md`. */
|
||||
sourceFilename: string
|
||||
/** Complete current `translation-rules.md` contents. */
|
||||
translationRules: string
|
||||
/** Complete current `terminology.md` contents. */
|
||||
terminology: string
|
||||
}
|
||||
|
||||
/** Parsed contents of the three-element XML response. */
|
||||
/** Parsed contents of the three-section response. */
|
||||
export interface TranslationResponse {
|
||||
translation: string
|
||||
review: string
|
||||
@@ -42,7 +34,7 @@ export interface TranslationResponse {
|
||||
const PLACEHOLDER = /{{([a-z_]+)}}/g
|
||||
const TEMPLATE_OPEN = '## 模板正文\n\n````text\n'
|
||||
const TEMPLATE_CLOSE = '\n````'
|
||||
const RESPONSE_CHILDREN = ['translation', 'review', 'final'] as const
|
||||
const RESPONSE_SECTIONS = ['translation', 'review', 'final'] as const
|
||||
|
||||
/** Extract the machine-consumed text fence from `translation-prompt.md`. */
|
||||
function extractTranslationPrompt(document: string): string {
|
||||
@@ -61,31 +53,15 @@ export function documentedTranslationPromptPlaceholders(document: string): strin
|
||||
return [...document.slice(0, preambleEnd).matchAll(/^\| `{{([a-z_]+)}}` \|/gm)].map(match => match[1] ?? '')
|
||||
}
|
||||
|
||||
/** Render one system prompt from the checked-in template and canonical rules. */
|
||||
/** Render one system prompt from the checked-in template. */
|
||||
export function renderTranslationPrompt(document: string, input: TranslationPromptInput): string {
|
||||
if (basename(input.sourceFilename) !== input.sourceFilename) {
|
||||
throw new Error(`translation prompt: sourceFilename must be a basename; got ${JSON.stringify(input.sourceFilename)}`)
|
||||
}
|
||||
const sourceIsChinese = input.sourceFilename.endsWith('.zh.md')
|
||||
if (input.sourceLanguage === 'Chinese' ? !sourceIsChinese : sourceIsChinese || !input.sourceFilename.endsWith('.md')) {
|
||||
throw new Error(`translation prompt: ${input.sourceFilename} does not match source language ${input.sourceLanguage}`)
|
||||
}
|
||||
|
||||
const targetLanguage: TranslationLanguage = input.sourceLanguage === 'English' ? 'Chinese' : 'English'
|
||||
const sourceFilenameZh = sourceIsChinese ? input.sourceFilename : input.sourceFilename.replace(/\.md$/, '.zh.md')
|
||||
const values: Record<TranslationPromptPlaceholder, string> = {
|
||||
source_lang: input.sourceLanguage,
|
||||
target_lang: targetLanguage,
|
||||
translation_rules: input.translationRules,
|
||||
terminology: input.terminology,
|
||||
source_filename: input.sourceFilename,
|
||||
source_filename_zh: sourceFilenameZh,
|
||||
}
|
||||
const template = extractTranslationPrompt(document)
|
||||
const placeholderFreeTemplate = template.replace(PLACEHOLDER, '')
|
||||
if (placeholderFreeTemplate.includes('{{') || placeholderFreeTemplate.includes('}}')) {
|
||||
throw new Error('translation prompt: template contains malformed placeholder syntax')
|
||||
}
|
||||
const names = [...template.matchAll(PLACEHOLDER)].map(match => match[1] ?? '')
|
||||
const unknown = names.filter(name => !TRANSLATION_PROMPT_PLACEHOLDERS.includes(name as TranslationPromptPlaceholder))
|
||||
if (unknown.length > 0) throw new Error(`translation prompt: unsupported placeholder(s): ${[...new Set(unknown)].join(', ')}`)
|
||||
@@ -95,77 +71,37 @@ export function renderTranslationPrompt(document: string, input: TranslationProm
|
||||
return template.replace(PLACEHOLDER, (_token, name: string) => values[name as TranslationPromptPlaceholder])
|
||||
}
|
||||
|
||||
/** Escape one value so it remains byte-identical inside an XML CDATA field. */
|
||||
function escapeTranslationCdata(value: string): string {
|
||||
return value.replaceAll(']]>', ']]]]><![CDATA[>')
|
||||
}
|
||||
|
||||
/** Serialize a response using the exact XML wire contract in the prompt. */
|
||||
/** Serialize a response in the exact three-section shape the prompt requests. */
|
||||
export function renderTranslationResponse(response: TranslationResponse): string {
|
||||
return [
|
||||
'<dsh-translation-response version="1">',
|
||||
`<translation><![CDATA[${escapeTranslationCdata(response.translation)}]]></translation>`,
|
||||
`<review><![CDATA[${escapeTranslationCdata(response.review)}]]></review>`,
|
||||
`<final><![CDATA[${escapeTranslationCdata(response.final)}]]></final>`,
|
||||
'</dsh-translation-response>',
|
||||
].join('\n')
|
||||
return RESPONSE_SECTIONS.map(section => `<${section}>\n${response[section]}\n</${section}>`).join('\n\n')
|
||||
}
|
||||
|
||||
/** Parse and validate the exact XML response shape emitted by the model. */
|
||||
export function parseTranslationResponse(xml: string): TranslationResponse {
|
||||
const values: TranslationResponse = { translation: '', review: '', final: '' }
|
||||
const stack: string[] = []
|
||||
const cdataFields = new Set<string>()
|
||||
let rootSeen = false
|
||||
let childIndex = 0
|
||||
const fail = (message: string): never => {
|
||||
throw new Error(`translation response: ${message}`)
|
||||
}
|
||||
const parser = new SaxesParser({ xmlns: false })
|
||||
/**
|
||||
* Parse the three-section response. Sections must each appear exactly once
|
||||
* and in order; bodies are raw Markdown taken verbatim between the tags.
|
||||
* A fenced ```xml wrapper around the whole response is tolerated, matching
|
||||
* the shape some models echo back from the prompt's own example.
|
||||
*/
|
||||
export function parseTranslationResponse(text: string): TranslationResponse {
|
||||
let body = text.trim()
|
||||
const fenced = /^```(?:xml)?\n([\s\S]*?)\n```$/.exec(body)
|
||||
if (fenced?.[1] !== undefined) body = fenced[1].trim()
|
||||
|
||||
parser.on('opentag', (tag) => {
|
||||
if (stack.length === 0) {
|
||||
if (rootSeen) fail('contains more than one root element')
|
||||
if (tag.name !== 'dsh-translation-response') fail(`expected dsh-translation-response root, got ${tag.name}`)
|
||||
const attributes = Object.keys(tag.attributes)
|
||||
if (attributes.length !== 1 || tag.attributes.version !== '1') fail('root must have only version="1"')
|
||||
rootSeen = true
|
||||
} else if (stack.length === 1) {
|
||||
const expected = RESPONSE_CHILDREN[childIndex]
|
||||
if (tag.name !== expected) fail(`expected ${expected ?? 'no more children'}, got ${tag.name}`)
|
||||
if (Object.keys(tag.attributes).length !== 0) fail(`${tag.name} must not have attributes`)
|
||||
childIndex++
|
||||
} else {
|
||||
fail(`nested element ${tag.name} is not allowed`)
|
||||
}
|
||||
stack.push(tag.name)
|
||||
})
|
||||
parser.on('text', (value) => {
|
||||
if (stack.length <= 1 && value.trim() === '') return
|
||||
fail('all response field content must be inside CDATA')
|
||||
})
|
||||
parser.on('cdata', (value) => {
|
||||
const field = stack.at(-1)
|
||||
if (field === undefined || !RESPONSE_CHILDREN.includes(field as (typeof RESPONSE_CHILDREN)[number])) {
|
||||
fail('CDATA is allowed only inside translation, review, or final')
|
||||
}
|
||||
const key = field as (typeof RESPONSE_CHILDREN)[number]
|
||||
values[key] += value
|
||||
cdataFields.add(key)
|
||||
})
|
||||
parser.on('closetag', (tag) => {
|
||||
const expected = stack.pop()
|
||||
if (expected !== tag.name) fail(`closing ${tag.name} does not match ${expected ?? 'nothing'}`)
|
||||
})
|
||||
parser.on('comment', () => fail('comments are not allowed'))
|
||||
parser.on('doctype', () => fail('doctypes are not allowed'))
|
||||
parser.on('processinginstruction', () => fail('processing instructions are not allowed'))
|
||||
parser.on('error', error => fail(`invalid XML: ${error.message}`))
|
||||
parser.write(xml).close()
|
||||
|
||||
if (childIndex !== RESPONSE_CHILDREN.length) fail('translation, review, and final must each appear exactly once and in order')
|
||||
for (const field of RESPONSE_CHILDREN) {
|
||||
if (!cdataFields.has(field)) fail(`${field} must contain a CDATA section`)
|
||||
const values: Partial<Record<(typeof RESPONSE_SECTIONS)[number], string>> = {}
|
||||
let cursor = 0
|
||||
for (const section of RESPONSE_SECTIONS) {
|
||||
const open = `<${section}>`
|
||||
const close = `</${section}>`
|
||||
const start = body.indexOf(open, cursor)
|
||||
if (start === -1) throw new Error(`translation response: missing <${section}> section`)
|
||||
const end = body.indexOf(close, start + open.length)
|
||||
if (end === -1) throw new Error(`translation response: unterminated <${section}> section`)
|
||||
values[section] = body.slice(start + open.length, end).replace(/^\n/, '').replace(/\n$/, '')
|
||||
cursor = end + close.length
|
||||
}
|
||||
return values
|
||||
for (const section of RESPONSE_SECTIONS) {
|
||||
const again = body.indexOf(`<${section}>`, cursor)
|
||||
if (again !== -1) throw new Error(`translation response: duplicate <${section}> section`)
|
||||
}
|
||||
return values as TranslationResponse
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user