petal/internal/llm/lang_test.go

package llm

import (
	"strings"
	"testing"
)

func TestLangForFallsBackToDefault(t *testing.T) {
	if got := LangFor("zh"); got.Code != "zh" {
		t.Fatalf("LangFor(zh) = %+v", got)
	}
	if got := LangFor("pt-PT"); got.Code != "pt-PT" {
		t.Fatalf("LangFor(pt-PT) = %+v", got)
	}
	// A blank column, a stray value, and stray whitespace all resolve rather
	// than erroring — a prompt is the wrong place to discover a config problem.
	for _, in := range []string{"", "  ", "klingon", "ZH"} {
		if got := LangFor(in); got.Code != DefaultLang.Code {
			t.Fatalf("LangFor(%q) = %q, want the default %q", in, got.Code, DefaultLang.Code)
		}
	}
	if got := LangFor(" zh "); got.Code != "zh" {
		t.Fatalf("LangFor with padding = %+v", got)
	}
}

// The three prompts that name the writer's language must actually name *hers*.
// Before Phase 19 all three said "Simplified Chinese" outright, which is the
// bug this guards: a pt-PT writer asking "porquê" would have been answered in
// Mandarin.
func TestPromptsNameTheWritersLanguage(t *testing.T) {
	pt := LangFor("pt-PT")

	collocation := CollocationMessages("The rain was strong.", "casual", pt)[0].Content
	if !strings.Contains(collocation, "European Portuguese") {
		t.Fatalf("collocation prompt doesn't ask for a pt-PT gloss:\n%s", collocation)
	}
	if strings.Contains(collocation, "Simplified Chinese") {
		t.Fatalf("collocation prompt still hardcodes Chinese:\n%s", collocation)
	}
	// The tone steering must survive alongside the language — they share one
	// format string, and getting the verbs in the wrong order silently drops one.
	if !strings.Contains(collocation, "relaxed, friendly, and conversational") {
		t.Fatalf("collocation prompt lost its tone guidance:\n%s", collocation)
	}

	translate := TranslateMessages("Try a shorter sentence here.", pt)[0].Content
	if !strings.Contains(translate, "European Portuguese") || strings.Contains(translate, "Chinese") {
		t.Fatalf("translate prompt targets the wrong language:\n%s", translate)
	}

	ask := AskPetalSystemPrompt("origin", "replacement", "grammar", "explanation", "paragraph", pt)
	if !strings.Contains(ask, "European Portuguese") || strings.Contains(ask, "Mandarin") {
		t.Fatalf("ask-petal prompt targets the wrong language:\n%s", ask)
	}
	if !strings.Contains(ask, "porquê") {
		t.Fatalf("ask-petal prompt doesn't recognise her word for \"why\":\n%s", ask)
	}
	// The suggestion context is positional in that template; a mis-numbered
	// verb would quietly blank one of these fields.
	for _, want := range []string{"origin", "replacement", "grammar", "explanation", "paragraph"} {
		if !strings.Contains(ask, want) {
			t.Fatalf("ask-petal prompt dropped %q:\n%s", want, ask)
		}
	}
	if strings.Contains(ask, "%!") {
		t.Fatalf("ask-petal prompt has a formatting error:\n%s", ask)
	}
}

// The zh pair is in daily use and must be untouched by the extraction: its
// prompts should read exactly as they did when they were hardcoded.
func TestDefaultPairStillReadsAsBefore(t *testing.T) {
	zh := LangFor("zh")

	if got := CollocationMessages("x", "", zh)[0].Content; !strings.Contains(got, "Simplified Chinese (Mandarin) gloss in parentheses") {
		t.Fatalf("zh collocation gloss changed:\n%s", got)
	}
	if got := TranslateMessages("x", zh)[0].Content; !strings.Contains(got, "natural, friendly Simplified Chinese (Mandarin)") {
		t.Fatalf("zh translate target changed:\n%s", got)
	}
	if got := AskPetalSystemPrompt("a", "b", "c", "d", "e", zh); !strings.Contains(got, "为什么") {
		t.Fatalf("zh ask-petal lost its Mandarin \"why\":\n%s", got)
	}
}

// UX item 6: the Ask Petal answer is bilingual, pair language first, halves
// separated by one blank line. That separator is not a stylistic preference —
// AskPetal.tsx splits on it to render the two halves the way the companion
// renders its two lines — so the instruction has to survive prompt edits.
//
// The direction the writer is learning in is deliberately not encoded: the pair
// is (English + X), and an English speaker learning French needs the same two
// halves a Mandarin speaker learning English does. The prompt asks for both and
// lets the reader choose, so there is nothing here that names one half the
// answer and the other a courtesy.
func TestAskPetalAnswersInBothLanguages(t *testing.T) {
	for _, code := range []string{"zh", "pt-PT", "fr", "es"} {
		lang := LangFor(code)
		ask := AskPetalSystemPrompt("a", "b", "grammar", "d", "e", lang)

		if !strings.Contains(ask, "BOTH languages") {
			t.Fatalf("%s: ask-petal no longer asks for both languages:\n%s", code, ask)
		}
		if !strings.Contains(ask, "single blank line") {
			t.Fatalf("%s: ask-petal lost the blank-line separator the client splits on:\n%s", code, ask)
		}
		// Order matters to the rendering: the pair language is the prominent
		// half, English the muted one beneath it.
		if !strings.Contains(ask, "first the whole answer in "+lang.Name) {
			t.Fatalf("%s: ask-petal doesn't put %s first:\n%s", code, lang.Name, ask)
		}
		// The instruction it replaced. Left in place it directly contradicts the
		// new one, and a model given both will pick one at random.
		if strings.Contains(ask, "Never mix languages") {
			t.Fatalf("%s: ask-petal still forbids the bilingual reply it now asks for:\n%s", code, ask)
		}
		if strings.Contains(ask, "%!") {
			t.Fatalf("%s: ask-petal prompt has a formatting error:\n%s", code, ask)
		}
	}
}