Maven/cmd/semantic-router-experiment/slice21/guard_test.go

package main

import (
	"encoding/json"
	"os"
	"strings"
	"testing"

	"github.com/kami/maven/internal/morph"
)

func TestEvaluateFixtures(t *testing.T) {
	for _, fx := range Fixtures {
		got := Evaluate(fx.Utterance)
		if got.Eligibility != fx.Want {
			t.Errorf("%s: want %s got %s (reasons %v)", fx.Utterance, fx.Want, got.Eligibility, got.Reasons)
		}
	}
}

// TestMeasuredDiscriminators pins the corpus-verified numbers on the frozen
// pool. These are the exact measurements the rules were built on, so a change
// that moves them is a rule regression visible in the slice.
func loadPool(t *testing.T) []Row {
	t.Helper()
	b, err := os.ReadFile("/tmp/mvn-s21/pool.json")
	if os.IsNotExist(err) {
		t.Skip("pool.json missing; run slice21_emit.py first")
	}
	if err != nil {
		t.Fatal(err)
	}
	var rows []Row
	if err := json.Unmarshal(b, &rows); err != nil {
		t.Fatal(err)
	}
	return rows
}

func TestDevCapabilityProhibition(t *testing.T) {
	if !morph.Available() {
		t.Skip("morph dict unavailable")
	}
	rows := loadPool(t)
	var n, pass, blockedN, ambig int
	for _, r := range rows {
		if !hasTok(r.Tags, "capability_question") {
			continue
		}
		n++
		switch Evaluate(variants(r.NText)[vOrig]).Eligibility {
		case Permissive:
			pass++
		case Blocked:
			blockedN++
		case Ambiguous:
			ambig++
		}
	}
	if n != 126 {
		t.Fatalf("capability-question rows = %d, want 126", n)
	}
	if pass != 0 {
		t.Fatalf("capability-question dangerous pass = %d, want 0", pass)
	}
	if blockedN != 126 && ambig != 0 {
		t.Errorf("blocked=%d ambig=%d, expect all 126 blocked", blockedN, ambig)
	}
}

func TestDevBareCanPoliteIsAction(t *testing.T) {
	if !morph.Available() {
		t.Skip("morph dict unavailable")
	}
	rows := loadPool(t)
	total, action, perm := 0, 0, 0
	for _, r := range rows {
		toks := tokens(r.NText)
		if !hasTok(toks, "можешь") || hasAny(toks, ruAddress) ||
			hasAny(toks, append([]string{}, ruAbilityForms.single...)) {
			continue
		}
		total++
		if r.Route == "action" {
			action++
		}
		if Evaluate(r.NText).Eligibility == Permissive {
			perm++
		}
	}
	if total != 127 || action != 127 {
		t.Fatalf("bare-можешь+polite: n=%d action=%d, want 127/127", total, action)
	}
	if perm != 127 {
		t.Fatalf("bare-можешь+polite permissive=%d, want 127", perm)
	}
}

func TestDevEnglishCanPoliteIsAction(t *testing.T) {
	if !morph.Available() {
		t.Skip("morph dict unavailable")
	}
	rows := loadPool(t)
	total, action, perm := 0, 0, 0
	for _, r := range rows {
		toks := tokens(r.NText)
		if !hasAny(toks, enCanForms) {
			continue
		}
		total++
		if r.Route == "action" {
			action++
		}
		if Evaluate(r.NText).Eligibility == Permissive {
			perm++
		}
	}
	if total != 96 || action != 96 {
		t.Fatalf("can-rows: n=%d action=%d, want 96/96", total, action)
	}
	if perm != 96 {
		t.Fatalf("can-rows permissive=%d, want 96", perm)
	}
}

func TestNoPermissiveRowEndsInQuestion(t *testing.T) {
	// asymmetric posture: the guard must never approve a trailing-? frame --
	// the corpus has 0 action rows ending in "?", and approving any would
	// bet on punctuation the slice has ruled uncertain.
	rows := loadPool(t)
	for _, r := range rows {
		if !strings.HasSuffix(r.NText, "?") {
			continue
		}
		if got := Evaluate(r.NText).Eligibility; got == Permissive {
			t.Errorf("canonical '?': %q approved (%s)", r.Text, got)
		}
	}
}