Files
sanderling/internal/ltl/evaluator.go
T
pj 7493945251 feat: LTL operators, sampling, and default generators (#17)
* feat(ltl): add Now/Next/Eventually/Implies/Or/And/Not formulas

Replace the fold-with-latch evaluator with a residual-formula reducer.
Each Observe() instantiates a fresh obligation from the root (stripping
an outer Always), reduces each pending obligation against current state,
latches Violated on first failure, and surfaces Pending verdicts for
deferred obligations. Existing Always/Pure/Thunk tests continue to pass.

* feat(ltl): support relative duration for eventually().within()

* feat(proto): add Swipe, PressKey, RecentLogs RPCs

* feat(verifier,runner): formula handles, new action kinds, rich state

- verifier: add formula-spec registry; bindNow/bindNext/bindEventually with
  chainable .implies/.or/.and/.not and .within(n,unit) on eventually; bindFrom
  for uniform sampling. bindAlways keeps accepting plain predicates.
- verifier: store lastTree, lastAction, step time, logs, exceptions on the
  Verifier; SnapshotInput replaces the (snapshots, tree) pair. stateObject now
  produces state.lastAction/time/logs/exceptions matching the TS State type.
- verifier: make taps/swipes/waitOnce/pressKey built-in generators actually
  fire; taps picks a clickable, enabled element from the last hierarchy.
- agent: add exceptions field to Message wire format.
- driver: add Swipe/PressKey/RecentLogs to Driver interface; wire maestro
  client and mock driver. LogEntry exposed for runner consumption.
- runner: apply Swipe/PressKey/Wait actions; collect logcat and exceptions;
  pass lastAction and step time into PushSnapshot.

* feat(spec-api): LTL operators, new actions, richer State

- ltl.ts exports now/next/eventually; always overload accepts a Formula
- types.ts: Formula gains implies/or/and/not; EventuallyFormula adds .within;
  State gains lastAction/time/logs/exceptions; Swipe/PressKey/Wait action types
- actions.ts: Swipe/PressKey/Wait/from constructors; waitOnce + pressKey
  default generators
- tests exercise the chaining, sampling, and new actions through a recorded
  fake runtime

* feat(sidecar): add swipe, pressKey, recentLogs RPC handlers

* feat(sdk-android): capture uncaught exceptions

Install a default uncaught handler on Uatu.start, chained with any
existing handler so Android's crash reporter still runs. Expose
Uatu.reportError for callers to forward caught throwables. A bounded
circular buffer (default 50) drains into each STATE message's new
exceptions field. Protocol.kt serializes/deserializes the field,
matching the Go wire format added to internal/agent/protocol.go.

* feat(spec-api): add @uatu/spec/defaults/properties bundle

* feat(sample-app): exercise new LTL operators + defaults

spec.ts now imports eventually/next/now/from from @uatu/spec and
noUncaughtExceptions from @uatu/spec/defaults/properties. It declares
three properties that exercise the new surface:

- accountCountNonNegative: plain always() safety
- addAccountAdvances: always(now(x).implies(next(y)))
- eventuallyLoggedIn: eventually(p).within(30, "seconds")
- noUncaughtExceptions: imported default

The weighted actions root uses from() for random phone/name sampling
and entries for taps/swipes/waitOnce/pressKey built-ins.

SampleApplication gains a debug hook gated on the system property
uatu.inject_error so the e2e run can synthesize an Uatu.reportError and
verify noUncaughtExceptions violates.

cmd/uatu/test_run.go adds a subpath alias so specs importing
"@uatu/spec/defaults/properties" resolve against the in-tree source
when running from the uatu checkout. The spec-integration tests swap
the old click-counter fixtures for the new login hierarchy.

* feat(trace): record swipe/key/wait details + exceptions

trace.Step gains an Exceptions array so the trace captures the
class/message/stackTrace for each SDK-reported throwable in a step.
trace.Action gains FromX/FromY/ToX/ToY/Key/DurationMillis so the full
payload of Swipe/PressKey/Wait actions is visible in trace.jsonl.

sample-app's debug error hook now gates on ApplicationInfo.DEBUGGABLE
instead of a system property (adb setprop fails on non-rooted
emulators).
2026-04-20 02:19:39 +07:00

229 lines
5.6 KiB
Go

package ltl
import (
"fmt"
"time"
)
type Verdict int
const (
VerdictHolds Verdict = iota
VerdictViolated
VerdictPending
)
func (v Verdict) String() string {
switch v {
case VerdictHolds:
return "holds"
case VerdictViolated:
return "violated"
case VerdictPending:
return "pending"
default:
return fmt.Sprintf("verdict(%d)", int(v))
}
}
// Evaluator reduces a formula across observed steps using residual-formula
// semantics. Each step either resolves pending obligations (to holds or
// violated) or carries them forward as residuals. Once a single obligation
// violates, the overall verdict latches to Violated.
type Evaluator struct {
root Formula
pending []Formula
violated bool
}
func NewEvaluator(formula Formula) *Evaluator {
return &Evaluator{root: formula}
}
// Observe evaluates the formula against the current state and returns the
// running verdict. Uses the real wall clock for deadline-bound operators;
// callers that need reproducible time should use ObserveAt.
func (e *Evaluator) Observe() Verdict {
return e.ObserveAt(time.Now())
}
// ObserveAt is like Observe but takes the current step time explicitly.
func (e *Evaluator) ObserveAt(now time.Time) Verdict {
if e.violated {
return VerdictViolated
}
fresh := rootObligation(e.root)
obligations := append(e.pending, fresh)
e.pending = e.pending[:0]
for _, obligation := range obligations {
result := reduce(obligation, now)
switch result.status {
case statusHolds:
// drop
case statusViolated:
e.violated = true
e.pending = nil
return VerdictViolated
case statusPending:
e.pending = append(e.pending, result.formula)
}
}
if len(e.pending) > 0 {
return VerdictPending
}
return VerdictHolds
}
// rootObligation returns the formula to instantiate at each step. An outer
// Always is stripped so its inner is re-evaluated every step; any other root
// formula is itself re-instantiated each step (matching the v0.1 semantics
// where a bare Thunk is re-observed on every call).
func rootObligation(root Formula) Formula {
if always, ok := root.(AlwaysFormula); ok {
return always.Inner
}
return root
}
type residualStatus int
const (
statusHolds residualStatus = iota
statusViolated
statusPending
)
type reduceResult struct {
status residualStatus
formula Formula
}
func holds() reduceResult { return reduceResult{status: statusHolds} }
func violated() reduceResult { return reduceResult{status: statusViolated} }
func pending(f Formula) reduceResult {
return reduceResult{status: statusPending, formula: f}
}
func reduce(formula Formula, now time.Time) reduceResult {
switch concrete := formula.(type) {
case PureFormula:
if concrete.Value {
return holds()
}
return violated()
case ThunkFormula:
if concrete.Func() {
return holds()
}
return violated()
case NowFormula:
return reduce(concrete.Inner, now)
case NextFormula:
// Next defers the inner obligation to the following step without
// evaluating it now.
return pending(concrete.Inner)
case EventuallyFormula:
// First-reduction deadline resolution: if the formula was built with
// a relative duration, fix the absolute deadline to (now + duration)
// so subsequent reductions compare against a stable value.
if !concrete.HasDeadline && concrete.Duration > 0 {
concrete.Deadline = now.Add(concrete.Duration)
concrete.HasDeadline = true
}
innerResult := reduce(concrete.Inner, now)
if innerResult.status == statusHolds {
return holds()
}
if concrete.HasStepBound && concrete.StepBound <= 1 {
return violated()
}
if concrete.HasDeadline && !now.Before(concrete.Deadline) {
return violated()
}
next := concrete
if concrete.HasStepBound {
next.StepBound = concrete.StepBound - 1
}
return pending(next)
case ImpliesFormula:
antecedent := reduce(concrete.Antecedent, now)
switch antecedent.status {
case statusHolds:
return reduce(concrete.Consequent, now)
case statusViolated:
return holds()
case statusPending:
return pending(ImpliesFormula{
Antecedent: antecedent.formula,
Consequent: concrete.Consequent,
})
}
case OrFormula:
left := reduce(concrete.Left, now)
right := reduce(concrete.Right, now)
if left.status == statusHolds || right.status == statusHolds {
return holds()
}
if left.status == statusViolated && right.status == statusViolated {
return violated()
}
if left.status == statusViolated {
return pending(right.formula)
}
if right.status == statusViolated {
return pending(left.formula)
}
return pending(OrFormula{Left: left.formula, Right: right.formula})
case AndFormula:
left := reduce(concrete.Left, now)
right := reduce(concrete.Right, now)
if left.status == statusViolated || right.status == statusViolated {
return violated()
}
if left.status == statusHolds && right.status == statusHolds {
return holds()
}
if left.status == statusHolds {
return pending(right.formula)
}
if right.status == statusHolds {
return pending(left.formula)
}
return pending(AndFormula{Left: left.formula, Right: right.formula})
case NotFormula:
inner := reduce(concrete.Inner, now)
switch inner.status {
case statusHolds:
return violated()
case statusViolated:
return holds()
case statusPending:
return pending(NotFormula{Inner: inner.formula})
}
case AlwaysFormula:
innerResult := reduce(concrete.Inner, now)
if innerResult.status == statusViolated {
return violated()
}
next := AlwaysFormula{Inner: concrete.Inner}
if innerResult.status == statusHolds {
return pending(next)
}
return pending(AndFormula{Left: innerResult.formula, Right: next})
}
panic(fmt.Sprintf("ltl: unsupported formula type %T", formula))
}