Simple user error makes code evaluate forever - Calling DynamicPPL.Model as a function.

[JohannesNE]

I tried to make posterior predictions by adapting the example from predict() for my model.

I made a mistake where I used the conditional model, m_lin_reg instead of linear_reg.
This made the code evaluate forever and therefore did not result in any useful error message.

This is of cause a user error, but it would have saved me a lot of frustration if an error was thrown.

# based on example from ?predict
using Turing

@model function linear_reg(x, y, σ = 0.1)
    β ~ Normal(0, 1)

    μ = β .* x

    for i ∈ eachindex(y)
        y[i] ~ Normal(μ[i], σ)
    end
end

f(x) = 2 * x + 0.1 * randn()

Δ = 0.1
xs_train = 0:Δ:10; ys_train = f.(xs_train);
xs_test = [10 + Δ, 10 + 2 * Δ]; ys_test = f.(xs_test);

m_lin_reg = linear_reg(xs_train, ys_train);
chain_lin_reg = sample(m_lin_reg, NUTS(100, 0.65), 200);

# Mistake where I use conditional model `m_lin_reg` instead of the intended `linear_reg()`
# This hangs forever.
m_lin_reg_test = m_lin_reg(xs_test, Vector{Union{Missing, Float64}}(undef, length(ys_test)));

predictions = predict(m_lin_reg_test, chain_lin_reg)

ys_pred = ys_pred = vec(mean(Array(group(predictions, :y)); dims = 1));