Phase 19: the copy stops being hardcoded Mandarin

Every `中文 · English` string moves out of ~29 components into
web/src/i18n: one Pack type, a verbatim zh pack, and two ways to read
it — usePack() for components, pack() for the modules that build a line
when something happens rather than when something renders.

Anything with a value in it is a function on the pack rather than a
template at the call site, English pluralisation included: word order
isn't universal, and a pack author has to be able to move the number.
The roster constants (tones, rewrite styles, export formats, companions)
keep only value + emoji, so a label can't drift from its key.

On the server, internal/llm/lang.go replaces "Simplified Chinese" in the
three prompts that actually name her language. pt-PT is spelled
"European Portuguese (pt-PT, never Brazilian Portuguese)" in the prompt
itself, and each Lang carries her word for "why" so the tutor prompt
still recognises the question when she asks it her way.

pair_lang reaches the model through the row-scoped query each handler
already ran — the one that proves she owns the document — rather than a
second lookup that could disagree with it.

Also records Phase 18's deploy: migration 0011 rehearsed against a copy
of the live VPS database, then applied for real.

internal/llm/prompts.go

@@ -97,8 +97,8 @@ func VoiceMessages(contentText string) []Message {
 // just non-native ("do a decision" → "make a decision", "strong rain" → "heavy
 // rain"), and explicitly DEFERS real grammar/spelling errors to the grammar
 // checkpoint so the two families don't overlap. Every explanation is framed as a
-// warm "natives usually say…" note with a short Mandarin gloss — never
-// "error/wrong" — because these are stylistic, not mistakes. It is a distinct
+// warm "natives usually say…" note with a short gloss in the writer's own
+// language — never "error/wrong" — because these are stylistic, not mistakes. It is a distinct
 // pass from the grammar checkpoint (do not bundle them). `replacement` carries
 // the natural pairing the writer can accept in one tap.
 const collocationSystemPrompt = `You are a warm, encouraging writing assistant helping someone who speaks English as a second language. ` +
@@ -113,7 +113,7 @@ Identify up to 5 such non-native word pairings. For each, give the natural pairi
 	`Be gentle and specific. Do NOT flag grammar errors, spelling mistakes, or unclear sentences — those are handled ` +
 	`elsewhere. Only flag word pairings that are correct but sound non-native.%s
 
-Phrase every explanation warmly as "Natives usually say…" and include a brief Simplified Chinese gloss in parentheses. ` +
+Phrase every explanation warmly as "Natives usually say…" and include a brief %s gloss in parentheses. ` +
 	`Never use the words "error", "wrong", or "mistake" — these are friendly polish, not corrections.
 
 Respond ONLY with valid JSON. No preamble, no markdown fences. Format:
@@ -132,10 +132,11 @@ If every pairing already sounds natural, return: {"suggestions": []}`
 
 // CollocationMessages builds the message array for a collocation pass over the
 // WHOLE document (no truncation), gently steered toward the document's tone so a
-// hint can prefer a register-appropriate pairing.
-func CollocationMessages(contentText, tone string) []Message {
+// hint can prefer a register-appropriate pairing. The parenthetical gloss is
+// written in the writer's own language.
+func CollocationMessages(contentText, tone string, lang Lang) []Message {
 	return []Message{
-		{Role: "system", Content: fmt.Sprintf(collocationSystemPrompt, toneGuidance(tone))},
+		{Role: "system", Content: fmt.Sprintf(collocationSystemPrompt, toneGuidance(tone), lang.Name)},
 		{Role: "user", Content: contentText},
 	}
 }
@@ -147,26 +148,27 @@ const askPetalSystemTemplate = `You are Petal, a warm and patient English writin
 	`as a second language. You are currently discussing a specific writing suggestion.
 
 Suggestion context:
-- Original text: "%s"
-- Suggested replacement: "%s"
-- Issue type: %s
-- Initial explanation: "%s"
-- Surrounding paragraph: "%s"
+- Original text: "%[1]s"
+- Suggested replacement: "%[2]s"
+- Issue type: %[3]s
+- Initial explanation: "%[4]s"
+- Surrounding paragraph: "%[5]s"
 
 The user wants to understand this suggestion better. Detect the language of the user's message ` +
-	`and respond in that same language. If they write in Mandarin Chinese, respond entirely in ` +
-	`Mandarin. If they write in English, respond in English. Never mix languages in a single response.
+	`and respond in that same language. If they write in %[6]s, respond entirely in ` +
+	`%[6]s. If they write in English, respond in English. Never mix languages in a single response.
 
 Explain clearly and kindly. Use simple language appropriate to the user's message. Give examples ` +
-	`when helpful. If they ask "why" (or "为什么"), explain the grammar rule or idiom behind it. ` +
+	`when helpful. If they ask "why" (or "%[7]s"), explain the grammar rule or idiom behind it. ` +
 	`If they suggest an alternative phrasing, evaluate it honestly.
 
 Keep responses concise (2-4 sentences). This is a chat, not an essay. Be encouraging — ` +
 	`learning a language is hard and they're doing great.`
 
-// AskPetalSystemPrompt fills the tutor prompt with one suggestion's context.
-func AskPetalSystemPrompt(original, replacement, suggestionType, explanation, paragraph string) string {
-	return fmt.Sprintf(askPetalSystemTemplate, original, replacement, suggestionType, explanation, paragraph)
+// AskPetalSystemPrompt fills the tutor prompt with one suggestion's context and
+// the writer's pair language, which is the one she may ask her question in.
+func AskPetalSystemPrompt(original, replacement, suggestionType, explanation, paragraph string, lang Lang) string {
+	return fmt.Sprintf(askPetalSystemTemplate, original, replacement, suggestionType, explanation, paragraph, lang.Name, lang.Why)
 }
 
 // rewriteSystemTemplate drives the "say it more naturally" / tone-rewrite tool.
@@ -215,22 +217,23 @@ func RewriteMessages(text, style string) []Message {
 }
 
 // translateSystemPrompt drives the explanation translator: it renders a
-// suggestion's English explanation into Simplified Chinese so an ESL reader sees
-// the "why" in her first language. Strict about returning ONLY the translation
-// (no quotes, no pinyin, no English echo) so it can drop straight into the chat
-// bubble. Kept warm and plain — these are short, friendly one-liners.
+// suggestion's English explanation into the writer's own language so an ESL
+// reader sees the "why" in her first language. Strict about returning ONLY the
+// translation (no quotes, no romanisation, no English echo) so it can drop
+// straight into the chat bubble. Kept warm and plain — these are short, friendly
+// one-liners.
 const translateSystemPrompt = `You are Petal, a warm writing assistant. Translate the English text the user ` +
-	`sends into natural, friendly Simplified Chinese (Mandarin). It is a short explanation of a writing ` +
-	`suggestion, written for a native Chinese speaker learning English.
+	`sends into natural, friendly %[1]s. It is a short explanation of a writing ` +
+	`suggestion, written for a native %[1]s speaker learning English.
 
-Respond with ONLY the Simplified Chinese translation. No quotation marks, no pinyin, no English, no preamble — ` +
+Respond with ONLY the %[1]s translation. No quotation marks, no romanisation, no English, no preamble — ` +
 	`just the translated sentence.`
 
 // TranslateMessages builds the message array for translating one short English
-// explanation into Simplified Chinese.
-func TranslateMessages(text string) []Message {
+// explanation into the writer's own language.
+func TranslateMessages(text string, lang Lang) []Message {
 	return []Message{
-		{Role: "system", Content: translateSystemPrompt},
+		{Role: "system", Content: fmt.Sprintf(translateSystemPrompt, lang.Name)},
 		{Role: "user", Content: text},
 	}
 }