hsa-app/internal/classify/prompt_test.go

package classify

import (
	"strings"
	"testing"

	"maisym.com/hsa/internal/config"
)

func contains(list []string, want string) bool {
	for _, s := range list {
		if s == want {
			return true
		}
	}
	return false
}

// The Tremblay family: Jean-Michel and Jude share the initial "J", so neither may
// get a bare "J. Tremblay" variant; Alex ("A") and Evan ("E") are unique and may.
func TestNameVariantsAmbiguousInitial(t *testing.T) {
	all := []config.Person{
		{First: "Jean-Michel", Last: "Tremblay"},
		{First: "Jude", Last: "Tremblay"},
		{First: "Alex", Last: "Tremblay"},
		{First: "Evan", Last: "Tremblay"},
		{First: "Lynna", Last: "Nguyen"},
	}

	jm := NameVariants(all[0], all)
	if contains(jm, "J. Tremblay") || contains(jm, "Tremblay, J.") {
		t.Errorf("Jean-Michel must not get an ambiguous single-initial variant: %v", jm)
	}
	// Compound initials are unique to Jean-Michel and should appear.
	if !contains(jm, "J-M Tremblay") {
		t.Errorf("Jean-Michel should get compound initial variant J-M Tremblay: %v", jm)
	}

	jude := NameVariants(all[1], all)
	if contains(jude, "J. Tremblay") {
		t.Errorf("Jude must not get an ambiguous single-initial variant: %v", jude)
	}

	alex := NameVariants(all[2], all)
	if !contains(alex, "A. Tremblay") {
		t.Errorf("Alex (unique initial) should get A. Tremblay: %v", alex)
	}

	// Lynna's surname is unique, so a single initial is fine.
	lynna := NameVariants(all[4], all)
	if !contains(lynna, "L. Nguyen") {
		t.Errorf("Lynna (unique surname) should get L. Nguyen: %v", lynna)
	}

	// Order/comma variants are always present and unambiguous.
	for _, want := range []string{"Jean-Michel Tremblay", "Tremblay Jean-Michel", "Tremblay, Jean-Michel"} {
		if !contains(jm, want) {
			t.Errorf("expected variant %q in %v", want, jm)
		}
	}
}

func TestBuildSystemPrompt(t *testing.T) {
	persons := []config.Person{
		{First: "Jean-Michel", Last: "Tremblay"},
		{First: "Lynna", Last: "Nguyen"},
	}
	categories := []config.Category{
		{Name: "Pharmacy", Examples: []string{"CVS", "Rx"}},
		{Name: "Other"},
	}
	p := BuildSystemPrompt(persons, categories, "2026-06-17", []string{"Treat handwritten totals as authoritative."})

	for _, want := range []string{
		"Jean-Michel Tremblay", // canonical label
		"Lynna Nguyen",
		"Pharmacy",
		"CVS",              // example injected
		"2026-06-17",       // today
		"AMBIGUOUS",        // the ambiguity rule
		"IGNORE everyone",  // ignore-other-people rule
		"null",             // unknown handling
		"raw_name",         // raw echo
		"CLOSEST to today", // date tie-breaker
	} {
		if !strings.Contains(p, want) {
			t.Errorf("system prompt missing %q", want)
		}
	}
}