This PR isolates the bugfix for the `NetworkBehaviour` derive implementation for structures with generic fields. When `out_event` was not provided, the generated enum was missing the `NetworkBehaviour` impl constraint for the generic variants whilst using the generics for `<Generic>::OutEvent`.
Meanwhile I also found that the generated `poll` function `loop`s the sub behaviours and either `return`'s when `Poll::Ready` or `break`'s when `Poll::Pending`. This is a relict from when we still had `NetworkBehaviourEventProcess` which had added a branch within this loop that did not `return` but consume the event and `continue`. This trait was removed a while ago meaning this `loop` is no longer needed.
Previously, we used the full reference to the `OutEvent` of the `ConnectionHandler` in all implementations of `NetworkBehaviour`. Not only is this very verbose, it is also more brittle to changes. With the current implementation plan for #2824, we will be removing the `IntoConnectionHandler` abstraction. Using a type-alias to refer to the `OutEvent` makes the migration much easier.
Currently, our `NetworkBehaviour` derive macro depends on the `libp2p` crate to be in scope. This prevents standalone usage which forces us to depend on `libp2p` in all our tests where we want to derive a `NetworkBehaviour`.
This PR introduces a `prelude` option that - by default - points to `libp2p::swarm::derive_prelude`, a new module added to `libp2p_swarm`. With this config option, users of `libp2p_swarm` can now refer to the macro without depending on `libp2p`, breaking the circular dependency in our workspace. For consistency with the ecosystem, the macro is now also re-exported by `libp2p_swarm` instead of `libp2p` at the same position as the trait that it implements.
Lastly, we introduce an off-by-default `macros` feature flag that shrinks the dependency tree for users that don't need the derive macro.
