Files
sanderling/internal/ltl/evaluator_test.go
T
pj 94d9511312 test: full test-suite refactor sweep (#61)
* chore(test): start test-suite refactor sweep

* test(ltl): pin exact multi-obligation residual AST

* test(ltl): table-test finalize Kleene connective combinations

* test(ltl): pin reduce over pending inner for bound, Or, Not

* test(ltl): marshal bounded Always steps/duration/deadline

* test(verifier): cover LTL combinator verdict transitions and within unit panic

* test(verifier): table-test DecodeAction kinds and lastAction field exposure

* test(verifier): assert WithPlatform(ios) reaches the picker host and key pool

* test(verifier): widen weighted-selection assertion to a 5x skew margin

* test(verifier): un-skip ax-find round trip with a committed tree fixture

* test(runner): pin isWDADrop to sidecar reconnect-failed message origin

* test(runner): assert PressKey/Wait trace encoding records kind-specific fields

* test(runner): cover RenderSummary unsupported-verbs surfacing branch

* test(trace): set Hierarchy in round-trip and lock lossy Tree contract

Also add a -race concurrent WriteStep test that asserts N well-formed JSONL lines, catching torn lines if the writer mutex is dropped.

* test(trace): round-trip witnesses/changes/metrics/exceptions, pin step-0 witness

* test(trace): document ViolationsAreGreppable grep contract and lock-free WriteScreenshot

* test(hierarchy): cover invalid-JSON and malformed-bounds parser paths

* test(trace): guard writer mutex via WriteStep/Close race on w.file

* test(replay): drop unfailable assets and devproxy assertions

* test(replay): cache reuses on equal mtime, reparses after append

* test(replay): violation marker falls back to detection step when attributed missing

* test(replay): corrupt meta/trace dirs return 500 with error body

* test(replay): SSE client receives runs.changed after a broadcast

* test(replay): Run coalesces creates, ignores write/chmod, closes subs on cancel

* fix(sidecar): synchronize health fixture writes and exercise healthError

* test(sidecar): cover swipe/longpress/doubletap/erase/presskey/metrics/logs translations

* test(sidecar): cover DoubleTapSelector composition and mid-gesture cancel

* test(sidecar): assert gRPC error status surfaces from action RPC

* fix(chrome): route action methods through runCtx so caller cancellation aborts CDP

* fix(chrome): route hierarchy/screenshot/waitidle/metrics through runCtx

* refactor(ios): extract pure simctl JSON parsers

* refactor(ios): add command-runner seams for EnsureSimulator

* test(ios): table-test simctl parsers and EnsureSimulator seams

* test(sidecarassets): cover placeholder build path

* test(sidecarassets): assert reuse via sentinel bytes not mtime

* test(bundler): cover properties-only spec registration

* refactor(testrun): extract prepareBundleInputs from Execute

* test(testrun): cover prepareBundleInputs aliases and missing-runtime error

* test(testrun): table-test resolveRuntimeSibling search edges

* test(testrun): exact-output tests for progressHandler line format

* fix(cmd): point bundle-check aliases at pkg/spec/src

* test(cmd): smoke-test bundle-check resolves spec aliases

* test(cmd): table-test hier-check parse and FindAll on fixture

* test(cmd): unit-test buildBrowseURL deep-link vs root

* test(cmd): drop flaky TestRun_Doctor that launched real Chromium

* test(cmd): pin pipeline error to bundle resolution on web platform

* test(replay-ui): add bun test script

* ci(replay-ui): run bun test via make web-test target

* ci(replay-ui): point bun cache key at replay-ui/bun.lock

* test(replay-ui): exercise real URL encoding and non-ok throw in getJson

* refactor(replay-ui): extract snapshot flatten/getAtPath into lib module

* test(replay-ui): pin snapshot flatten/getAtPath path round-trip

* refactor(replay-ui): extract action selector/format into lib module

* test(replay-ui): pin action selector parse and row formatting

* refactor(replay-ui): share one statusFor between panels

* refactor(replay-ui): extract run-history derivation into lib module

* test(replay-ui): pin shared statusFor precedence and ordering

* test(replay-ui): pin run-history derivation alignment

* refactor(replay-ui): export clampIndex for testing

* refactor(replay-ui): extract keyboard-nav dispatch into pure module

* refactor(replay-ui): extract metrics formatters into lib module

* test(replay-ui): pin clampIndex step boundaries

* test(replay-ui): pin keyboard-nav ownership and key routing

* test(replay-ui): pin metrics formatters and path gap handling

* refactor(sidecar): expose device-output parsers as internal for testing

* test(sidecar): table-test device-output parsers against malformed input

* test(sidecar): cover logcat parsing year inference and line skipping

* test(sidecar): pin pressKey keycode mapping and unknown-key rejection

* test(sidecar): metrics bundleId falls back to launched app and honors override

* test(sidecar): loosen deadline upper bound to tolerate slow CI scheduling

* test(web-runtime): export selector builders for unit tests

* test(web-runtime): guard sanitize cycle, function, and depth limits

* test(web-runtime): table-test selector builder quoting and escaping

* test(sidecar): collapse scalar-forwarding RPC tests into a table

* test(replay-ui): dedup step/summary fixtures into shared module

* test(ios): collapse pickSimulator point-tests into a table
2026-06-06 13:59:08 +05:30

158 lines
5.4 KiB
Go

package ltl
import (
"strings"
"testing"
"time"
)
func observe(formula Formula, count int) []Verdict {
evaluator := NewEvaluator(formula)
verdicts := make([]Verdict, 0, count)
for range count {
verdicts = append(verdicts, evaluator.Observe())
}
return verdicts
}
func TestPure_HoldsThenStays(t *testing.T) {
got := observe(Always(Pure(true)), 3)
for index, verdict := range got {
if verdict != VerdictHolds {
t.Errorf("step %d: got %v, want holds", index, verdict)
}
}
}
func TestPure_FalseImmediatelyViolates(t *testing.T) {
got := observe(Always(Pure(false)), 3)
for index, verdict := range got {
if verdict != VerdictViolated {
t.Errorf("step %d: got %v, want violated", index, verdict)
}
}
}
func TestThunk_TransitionFromHoldToViolate(t *testing.T) {
values := []bool{true, true, false, true, true}
step := 0
evaluator := NewEvaluator(Always(Thunk(func() (bool, error) {
current := values[step]
step++
return current, nil
})))
wantSequence := []Verdict{
VerdictHolds, // true
VerdictHolds, // true
VerdictViolated, // false — latches
VerdictViolated, // true after violation — still violated
VerdictViolated, // true after violation — still violated
}
for index, want := range wantSequence {
got := evaluator.Observe()
if got != want {
t.Errorf("step %d: got %v, want %v", index, got, want)
}
}
}
func TestEvaluator_StickinessAfterViolation(t *testing.T) {
state := true
evaluator := NewEvaluator(Always(Thunk(func() (bool, error) { return state, nil })))
if got := evaluator.Observe(); got != VerdictHolds {
t.Fatalf("step 1: got %v, want holds", got)
}
state = false
if got := evaluator.Observe(); got != VerdictViolated {
t.Fatalf("step 2: got %v, want violated", got)
}
state = true
if got := evaluator.Observe(); got != VerdictViolated {
t.Fatalf("step 3 (recovered state): violation should latch, got %v", got)
}
}
func TestEvaluator_TopLevelPureCountedAtEachStep(t *testing.T) {
got := observe(Pure(true), 2)
if got[0] != VerdictHolds || got[1] != VerdictHolds {
t.Errorf("bare Pure(true): %v", got)
}
}
func TestEvaluator_TopLevelThunkRespectsObservation(t *testing.T) {
state := true
evaluator := NewEvaluator(Thunk(func() (bool, error) { return state, nil }))
if got := evaluator.Observe(); got != VerdictHolds {
t.Errorf("expected holds, got %v", got)
}
state = false
if got := evaluator.Observe(); got != VerdictViolated {
t.Errorf("expected violated, got %v", got)
}
}
func TestDescribe(t *testing.T) {
formula := Always(Pure(true))
if got := Describe(formula); !strings.Contains(got, "Always") || !strings.Contains(got, "Pure(true)") {
t.Errorf("Describe wrong: %q", got)
}
thunk := Always(Thunk(func() (bool, error) { return true, nil }))
if got := Describe(thunk); !strings.Contains(got, "Thunk") {
t.Errorf("Describe(thunk) wrong: %q", got)
}
}
// TestEventuallyWithinSteps_NextInnerHitsBoundFirstStep pins the boundary: a
// 1-step Eventually whose inner is a Next defers the inner to step 2, but the
// window closes at step 1, so the obligation is unmet and violates. Bug class:
// off-by-one at the step bound treating the deferred inner as still in-window.
func TestEventuallyWithinSteps_NextInnerHitsBoundFirstStep(t *testing.T) {
evaluator := NewEvaluator(EventuallyWithinSteps(Next(ThunkNamed("p", func() (bool, error) { return true, nil })), 1))
if got := evaluator.ObserveAt(time.Unix(0, 0)); got != VerdictViolated {
t.Errorf("EventuallyWithinSteps(Next(p), 1) step 1: got %v, want violated", got)
}
}
// TestOr_ViolatedDisjunctDoesNotViolateWhileOtherPending guards the Or-reduce
// path where one disjunct fails (Pure(false)) while the other is still pending
// (Next(p)). The disjunction must stay pending on the failing step, never
// violate. Bug class: Or-reduction dropping the still-pending branch and
// latching violated on a single failed disjunct.
func TestOr_ViolatedDisjunctDoesNotViolateWhileOtherPending(t *testing.T) {
evaluator := NewEvaluator(Always(Or(Pure(false), Next(ThunkNamed("p", func() (bool, error) { return true, nil })))))
if got := evaluator.ObserveAt(time.Unix(0, 0)); got != VerdictPending {
t.Errorf("step 1: got %v, want pending (Pure(false) disjunct must not violate)", got)
}
if got := evaluator.ObserveAt(time.Unix(1, 0)); got != VerdictPending {
t.Errorf("step 2: got %v, want pending", got)
}
}
// TestNot_OverPendingStaysPendingThenResolves pins Not over a pending inner: it
// must carry a Not-wrapped residual rather than collapse to a definite verdict
// at the step the inner is still deferred. Bug class: negation of a pending
// verdict resolving early to holds/violated.
func TestNot_OverPendingStaysPendingThenResolves(t *testing.T) {
// Next(p) is deferred at step 1, so Not(Next(p)) is pending, not definite.
// At step 2 the inner Next holds, so Not violates.
evaluator := NewEvaluator(Always(Not(Next(ThunkNamed("p", func() (bool, error) { return true, nil })))))
if got := evaluator.ObserveAt(time.Unix(0, 0)); got != VerdictPending {
t.Errorf("step 1: got %v, want pending", got)
}
if got := evaluator.ObserveAt(time.Unix(1, 0)); got != VerdictViolated {
t.Errorf("step 2: got %v, want violated (Not over a held inner)", got)
}
}
func TestObserve_PanicsOnUnknownFormulaType(t *testing.T) {
type unsupportedFormula struct{ Formula }
defer func() {
if recovered := recover(); recovered == nil {
t.Errorf("expected panic on unsupported formula type")
}
}()
reduce(unsupportedFormula{}, time.Now())
}