mirror of
https://github.com/priyanshujain/sanderling.git
synced 2026-10-02 19:17:10 +00:00
* 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
119 lines
4.0 KiB
Go
119 lines
4.0 KiB
Go
package verifier
|
|
|
|
import (
|
|
"encoding/json"
|
|
"strings"
|
|
"testing"
|
|
|
|
"github.com/priyanshujain/sanderling/internal/ltl"
|
|
)
|
|
|
|
// TestCombinators_VerdictTransitions loads real specs through the goja runtime
|
|
// using the chainable LTL combinators (implies/or/and/not + now + within steps)
|
|
// and drives them across snapshots. Bug class: a user spec built from these
|
|
// combinators silently mis-evaluates (wrong verdict at the wrong step).
|
|
func TestCombinators_VerdictTransitions(t *testing.T) {
|
|
const heads = `
|
|
globalThis.p = __sanderling__.extract(state => state.snapshots["p"] ?? false, "p");
|
|
globalThis.q = __sanderling__.extract(state => state.snapshots["q"] ?? false, "q");
|
|
`
|
|
type step struct {
|
|
p, q string
|
|
want ltl.Verdict
|
|
}
|
|
cases := []struct {
|
|
name string
|
|
body string
|
|
steps []step
|
|
}{
|
|
{
|
|
name: "implies",
|
|
body: `globalThis.properties = { r: __sanderling__.always(__sanderling__.now(()=>p.current).implies(__sanderling__.now(()=>q.current))) };`,
|
|
steps: []step{
|
|
{"false", "false", ltl.VerdictHolds}, // antecedent false -> vacuously holds
|
|
{"true", "true", ltl.VerdictHolds},
|
|
{"true", "false", ltl.VerdictViolated}, // p true, q false
|
|
{"false", "false", ltl.VerdictViolated}, // sticky
|
|
},
|
|
},
|
|
{
|
|
name: "or",
|
|
body: `globalThis.properties = { r: __sanderling__.always(__sanderling__.now(()=>p.current).or(__sanderling__.now(()=>q.current))) };`,
|
|
steps: []step{
|
|
{"true", "false", ltl.VerdictHolds},
|
|
{"false", "true", ltl.VerdictHolds},
|
|
{"false", "false", ltl.VerdictViolated},
|
|
},
|
|
},
|
|
{
|
|
name: "and",
|
|
body: `globalThis.properties = { r: __sanderling__.always(__sanderling__.now(()=>p.current).and(__sanderling__.now(()=>q.current))) };`,
|
|
steps: []step{
|
|
{"true", "true", ltl.VerdictHolds},
|
|
{"true", "false", ltl.VerdictViolated}, // one conjunct false
|
|
},
|
|
},
|
|
{
|
|
name: "not",
|
|
body: `globalThis.properties = { r: __sanderling__.always(__sanderling__.now(()=>p.current).not()) };`,
|
|
steps: []step{
|
|
{"false", "false", ltl.VerdictHolds},
|
|
{"true", "false", ltl.VerdictViolated},
|
|
},
|
|
},
|
|
{
|
|
name: "within_steps_deadline",
|
|
body: `globalThis.properties = { r: __sanderling__.always(__sanderling__.eventually(()=>p.current).within(2,'steps')) };`,
|
|
steps: []step{
|
|
{"false", "false", ltl.VerdictPending}, // obligation open
|
|
{"false", "false", ltl.VerdictViolated}, // deadline blown, never fired
|
|
},
|
|
},
|
|
{
|
|
name: "within_steps_satisfied",
|
|
body: `globalThis.properties = { r: __sanderling__.always(__sanderling__.eventually(()=>p.current).within(2,'steps')) };`,
|
|
steps: []step{
|
|
{"false", "false", ltl.VerdictPending},
|
|
{"true", "false", ltl.VerdictHolds}, // fired before deadline
|
|
},
|
|
},
|
|
}
|
|
|
|
for _, testCase := range cases {
|
|
t.Run(testCase.name, func(t *testing.T) {
|
|
verifier := newVerifier(t)
|
|
mustLoad(t, verifier, heads+testCase.body)
|
|
for i, s := range testCase.steps {
|
|
if err := verifier.PushSnapshot(SnapshotInput{
|
|
Snapshots: Snapshots{"p": json.RawMessage(s.p), "q": json.RawMessage(s.q)},
|
|
StepIndex: i + 1,
|
|
}); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if got := verifier.EvaluateProperties()["r"]; got != s.want {
|
|
t.Errorf("step %d (p=%s q=%s): got %v, want %v", i+1, s.p, s.q, got, s.want)
|
|
}
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
// TestWithin_InvalidUnitPanics verifies an unrecognized within() unit surfaces
|
|
// as a spec load error rather than silently constructing an unbounded
|
|
// eventually. Bug class: a typo'd unit ('ms'/'s') would otherwise build a
|
|
// formula that never enforces its deadline.
|
|
func TestWithin_InvalidUnitPanics(t *testing.T) {
|
|
for _, unit := range []string{"ms", "s", "minutes", ""} {
|
|
verifier := newVerifier(t)
|
|
src := `globalThis.properties = { r: __sanderling__.always(__sanderling__.eventually(()=>true).within(2,'` + unit + `')) };`
|
|
err := verifier.Load(src)
|
|
if err == nil {
|
|
t.Errorf("unit %q: expected load error, got nil", unit)
|
|
continue
|
|
}
|
|
if !strings.Contains(err.Error(), "within unit must be") {
|
|
t.Errorf("unit %q: error = %v, want within-unit diagnostic", unit, err)
|
|
}
|
|
}
|
|
}
|