sanderling/internal/verifier/policy_parity_test.go

package verifier

import (
	"errors"
	"fmt"
	"maps"
	"slices"
	"testing"
)

// policyTreeJSON gives every builtin verb something to act on, with every label
// distinct so no two candidates render the same way.
const policyTreeJSON = `{
  "attributes": {"bounds": "[0,0,400,800]"},
  "children": [
    {"attributes": {"resource-id": "Save", "text": "Save", "bounds": "[0,0,200,60]"}, "clickable": true, "enabled": true, "children": []},
    {"attributes": {"resource-id": "Cancel", "text": "Cancel", "bounds": "[200,0,400,60]"}, "clickable": true, "enabled": true, "children": []},
    {"attributes": {"resource-id": "Amount", "class": "EditText", "hintText": "Amount", "bounds": "[0,100,400,160]"}, "enabled": true, "children": []},
    {"attributes": {"resource-id": "Note", "class": "EditText", "hintText": "Note", "bounds": "[0,200,400,260]"}, "enabled": true, "children": []},
    {"attributes": {"resource-id": "List", "scrollable": "true", "bounds": "[0,300,400,700]"}, "children": []}
  ]
}`

// policyVerbs is every builtin verb a spec can put in its action tree.
var policyVerbs = []string{
	"taps", "doubleTaps", "longPresses", "typing", "scrolls", "swipes", "pressKeys", "waitOnce",
}

// seededDrawBudget is how many times the seeded picker is driven per verb. The
// candidate sets here are a handful of entries wide, so this exhausts them many
// times over; a miss would mean the picker cannot reach one of its own
// candidates, which is itself the bug worth failing on.
const seededDrawBudget = 300

// TestPoliciesEnumerateTheSameActions is the guard on the claim the paper makes
// about the two action policies: they differ in the pick and in nothing else.
// For every builtin verb, the actions the seeded picker can draw and the
// candidates the model policy is offered must be the same set. Enumeration lives
// in one place (pick.ts builtinCandidates) precisely so this cannot drift, and
// this test is what notices if a second one ever grows back.
func TestPoliciesEnumerateTheSameActions(t *testing.T) {
	for _, verb := range policyVerbs {
		t.Run(verb, func(t *testing.T) {
			seeded := seededReachableActions(t, verb)
			model := modelOfferedActions(t, verb)
			if len(model) == 0 {
				t.Fatalf("%s offered the model no candidates at all", verb)
			}
			if !slices.Equal(slices.Sorted(maps.Keys(seeded)), slices.Sorted(maps.Keys(model))) {
				t.Errorf("action spaces differ for %s\n seeded=%v\n  model=%v",
					verb, slices.Sorted(maps.Keys(seeded)), slices.Sorted(maps.Keys(model)))
			}
		})
	}
}

// TestModelCandidateDescriptionsAreUniqueAndNamed checks the rendering half of
// the contract: every enumerated action reaches the model as its own distinctly
// named line, so the number it picks and the action that executes agree.
func TestModelCandidateDescriptionsAreUniqueAndNamed(t *testing.T) {
	for _, verb := range policyVerbs {
		t.Run(verb, func(t *testing.T) {
			verifier := loadVerbSpec(t, verb)
			seen := map[string]bool{}
			for _, candidate := range verifier.Candidates() {
				if candidate.Description == "" {
					t.Fatalf("%s produced a candidate with no description: %+v", verb, candidate.Action)
				}
				if seen[candidate.Description] {
					t.Errorf("%s rendered %q twice, so the model cannot address both",
						verb, candidate.Description)
				}
				seen[candidate.Description] = true
			}
		})
	}
}

// TestModelIsOfferedTheUntargetedVerbs pins the two verbs the model arm used to
// be blind to: with no element to enumerate over, a key press and a wait were
// dropped, so the model could never navigate back or let the app settle.
func TestModelIsOfferedTheUntargetedVerbs(t *testing.T) {
	verifier := loadVerbSpec(t, "pressKeys")
	if !hasCandidate(verifier.Candidates(), "Press back") {
		t.Errorf("pressKeys missing from the model's candidates: %v",
			descriptions(verifier.Candidates()))
	}
	verifier = loadVerbSpec(t, "waitOnce")
	if !hasCandidate(verifier.Candidates(), "Wait") {
		t.Errorf("waitOnce missing from the model's candidates: %v",
			descriptions(verifier.Candidates()))
	}
}

// loadVerbSpec builds a verifier whose whole action tree is one builtin verb,
// with policyTreeJSON pushed as the current state.
func loadVerbSpec(t *testing.T, verb string) *Verifier {
	t.Helper()
	verifier := newVerifier(t, WithSeed(0x5eed))
	loadActionSpec(t, verifier, fmt.Sprintf(
		"import { %s } from \"@sanderling/spec\";\nglobalThis.actions = %s;", verb, verb))
	pushTree(t, verifier, policyTreeJSON)
	return verifier
}

// seededReachableActions drives the seeded picker over its draw budget and
// returns every distinct action it produced.
func seededReachableActions(t *testing.T, verb string) map[string]Action {
	t.Helper()
	verifier := loadVerbSpec(t, verb)
	reachable := map[string]Action{}
	for range seededDrawBudget {
		action, err := verifier.NextAction()
		if errors.Is(err, ErrNoAction) {
			continue
		}
		if err != nil {
			t.Fatalf("%s next action: %v", verb, err)
		}
		reachable[actionIdentity(action)] = action
	}
	return reachable
}

// modelOfferedActions returns the actions behind the numbered list the model
// policy picks from.
func modelOfferedActions(t *testing.T, verb string) map[string]Action {
	t.Helper()
	verifier := loadVerbSpec(t, verb)
	offered := map[string]Action{}
	for _, candidate := range verifier.Candidates() {
		offered[actionIdentity(candidate.Action)] = candidate.Action
	}
	return offered
}

// actionIdentity keys an action by everything except the values the policy owns
// rather than the candidate set: the typed text, which the seeded arm draws from
// the edge-case corpus and the model writes itself, and a swipe's drag distance,
// which the seeded arm draws and the enumeration lists at a nominal length.
// Comparing those would compare policies instead of action spaces. A swipe's
// direction is NOT policy-owned, so it survives as the sign of the drag.
func actionIdentity(action Action) string {
	action.Text = ""
	if action.Kind == ActionKindSwipe {
		action.ToX = sign(action.ToX - action.FromX)
		action.ToY = sign(action.ToY - action.FromY)
	}
	return fmt.Sprintf("%+v", action)
}

func sign(value int) int {
	switch {
	case value > 0:
		return 1
	case value < 0:
		return -1
	default:
		return 0
	}
}