Issue with MLIRGen and NVQ++ Linking

Take the phase_estimation.cpp example

struct r1PiGate {
  void operator()(cudaq::qubit &q) __qpu__ { r1(1., q); }
};

int main() {

  for (auto nQubits : std::vector<int>{2, 4, 6, 8}) {
    auto counts = cudaq::sample(
        qpe{}, nQubits, [](cudaq::qubit &q) __qpu__ { x(q); }, r1PiGate{});
    auto mostProbable = counts.most_probable();
    double theta = cudaq::to_integer(mostProbable) / (double)(1UL << nQubits);
    auto piEstimate = 1. / (2 * theta);
    printf("Pi Estimate(nQubits == %d) = %lf \n", nQubits, piEstimate);
  }
}

As is, if compiled targeting the RemoteRESTQPU, this works

nvq++ --target quantinuum --emulate phase_estimation.cpp
./a.out

However, if I just add a couple more kernel lambdas, even if unused,

struct r1PiGate {
  void operator()(cudaq::qubit &q) __qpu__ { r1(1., q); }
};

int main() {

  auto statePrep = [](cudaq::qubit &q) __qpu__ { x(q); };
  auto oracle = [](cudaq::qubit &q) __qpu__ { r1(1., q); };

  for (auto nQubits : std::vector<int>{2, 4, 6, 8}) {
    auto counts = cudaq::sample(
        qpe{}, nQubits, [](cudaq::qubit &q) __qpu__ { x(q); }, r1PiGate{});
    auto mostProbable = counts.most_probable();
    double theta = cudaq::to_integer(mostProbable) / (double)(1UL << nQubits);
    auto piEstimate = 1. / (2 * theta);
    printf("Pi Estimate(nQubits == %d) = %lf \n", nQubits, piEstimate);
  }
}

This fails because no counts come back due to the execution going through Library Mode and the ExecutionManager. The Quake gets generated, but there must be some issue with overriding the original entry point function. Perhaps the signatures are wrong somehow.