Instead of relying on `protoc` and buildscripts, we generate the bindings using `pb-rs` and version them within our codebase. This makes for a better IDE integration, a faster build and an easier use of `rust-libp2p` because we don't force the `protoc` dependency onto them.
Resolves#3024.
Pull-Request: #3312.
dtolnay is a very reputable member of the Rust community. I'd like to propose to make an exception to the "pin all external actions to a hash" rule. The action is updated very regularly and causes spam in the form of dependabot PRs.
Additionally, by pinning the action we cannot make use of the very neat shorthand syntax of specifying the desired Rust version.
Pull-Request: #3487.
The latest release (v0.18) of `cargo semver-checks` includes a [feature](https://github.com/obi1kenobi/cargo-semver-checks/pull/339) where the rustdoc JSON files for registry baselines is cached in `target/semver-checks/cache`. The rustdoc JSON files for released crates never changes as the source code on crates.io cannot be changed once a version is published. Thus, it is unnecessary to generate that JSON on every CI run.
We extract a separate action that installs `cargo semver-checks` for us and also sets up a cache. The cache is scoped to released version of the crate, meaning it automatically invalidates once we publish a new version.
This speeds up the `cargo semver-checks` step by 50% which is ~ 1 minute per job.
Pull-Request: #3469.
We only use `strum` for the interop-tests but we add 3 dependencies to a full build of the repository for it, including a proc-macro which needs to be pipelined in front of other crates which makes them hard to parallelize. Remove it in favor of fairly trivial reimplementation of `FromStr`.
Pull-Request: #3513.
Previously, we did not flush the nonce within the handshake to the stream. This caused problems when `pnet` was composed with the websocket transport. Inserting a flush fixes these compatibility problems.
Resolves https://github.com/libp2p/rust-libp2p/issues/3475.
Pull-Request: #3476.
A large release with lots of changes I am looking forward to. Sorry for the long release cadence.
Anything folks would like to see included that is not yet in `master`? As usual I would like to only block on bug fixes.
Pull-Request: #3491.
Prefixing a variable with an underscore (`_`) in Rust indicates that it is not used. Through refactorings, it can sometimes happen that we do end up using such a variable. In this case, the underscore should be removed.
Clippy can help us with this.
Pull-Request: #3484.
Previously, a `ConnectionHandler` was immediately requested from the `NetworkBehaviour` as soon as a new dial was initiated or a new incoming connection accepted.
With this patch, we delay the creation of the handler until the connection is actually established and fully upgraded, i.e authenticated and multiplexed.
As a consequence, `NetworkBehaviour::new_handler` is now deprecated in favor of a new set of callbacks:
- `NetworkBehaviour::handle_pending_inbound_connection`
- `NetworkBehaviour::handle_pending_outbound_connection`
- `NetworkBehaviour::handle_established_inbound_connection`
- `NetworkBehaviour::handle_established_outbound_connection`
All callbacks are fallible, allowing the `NetworkBehaviour` to abort the connection either immediately or after it is fully established. All callbacks also receive a `ConnectionId` parameter which uniquely identifies the connection. For example, in case a `NetworkBehaviour` issues a dial via `NetworkBehaviourAction::Dial`, it can unambiguously detect this dial in these lifecycle callbacks via the `ConnectionId`.
Finally, `NetworkBehaviour::handle_pending_outbound_connection` also replaces `NetworkBehaviour::addresses_of_peer` by allowing the behaviour to return more addresses to be used for the dial.
Resolves#2824.
Pull-Request: #3254.
Don't close the stream `protocol::recv`.
This is a short-term fix for #3298.
The issue behind this is a general one on the QUIC transport when closing streams, as described in #3343. This PR only circumvents the issue for identify. A proper solution for our QUIC transport still needs more thought.
Pull-Request: #3344.
Despite `rebase-strategy: "disabled"`, dependabot will refresh (i.e. rebase) PRs on the specified schedule interval. With the addition of `Cargo.lock` to our repository, dependabot is opening a lot more PRs which consumes unnecessary CI resources.
We change the interval to "weekly" to reduce the noise and resource consumption.
This commit does two things:
- Check that swarm1, given that it has no ban, establishes 21 connections and swarm2, given that it has a ban, establishes 20 connections.
- Wait for swarm1 to notice disconnect, given that swarm2 closed the connection to the banned swarm1.
Fixes flake introduced in caed1fe2c7.
With https://github.com/libp2p/test-plans/pull/121 merged, we should be able to use @master
directly. Still pointing to a concrete git hash.
This includes
6d1aed2ed5, thus
allowing interop tests to run from fork pull requests.
We create the `ConnectionId` for the new connection as part of `DialOpts`. This allows `NetworkBehaviour`s to accurately track state regarding their own dial attempts.
This patch is the main enabler of https://github.com/libp2p/rust-libp2p/pull/3254. Removing the `handler` field will allow us to deprecate the `NetworkBehaviour::new_handler` function in favor of four new ones that give more control over the connection lifecycle.
Always referencing the latest version of Rust for clippy creates problems during backporting as already fixed problems in master come up again during a backport.
Building inside the container allows Windows and MacOS users to also build this binary. Thanks to a new feature from docker, `--mount=type=cache`, rebuilding layers is fast without any additional hacks.
