Watch
0
0
Fork
You've already forked hyperhive
0
hyperhive/swarm-controller/src/pr_conflicts.rs

762 lines
27 KiB
Rust

//! Telling the notification router when an open pull request stops or starts
//! merging into its target branch.
//!
//! Forgejo sends no delivery when a push to a branch changes whether the pull
//! requests targeting it merge, and the router holds no forge client. So the
//! controller watches the pushes it already receives on the `vcs-activity`
//! hook: after a push to the default branch, or to a branch it has seen an
//! open pull request target ([`OpenPulls`]), it waits for the forge to recompute, lists
//! the open pull requests that target the branch, and publishes one
//! [`MERGEABILITY_EVENT`] per pull request. The router keeps whether each pull
//! request was already conflicting and acts only on a change.
//!
//! The forge's `mergeable` flag is false for a conflict, for an error, for a
//! draft, and while the check still runs. A draft is left out, and a pull
//! request counts as conflicting only when two reads one [`RECHECK`] apart both
//! say false, which a check still running does not survive.
use std::collections::{BTreeSet, HashMap, HashSet};
use std::future::Future;
use std::sync::{LazyLock, Mutex, PoisonError};
use std::time::Duration;
use forgejo_api::structs::PullRequest;
use serde_json::{Value as Json, json};
use swarm_wire::forge_events::MERGEABILITY_EVENT;
use crate::routes::AppState;
/// How long after a push the forge gets to recompute before the first read.
const SETTLE: Duration = Duration::from_secs(30);
/// The wait between reads of a pull request that did not read as mergeable.
const RECHECK: Duration = Duration::from_secs(30);
/// The most reads one check makes.
const MAX_READS: usize = 4;
/// One push to a branch, as far as this module needs it.
#[derive(Clone, Debug, PartialEq, Eq)]
pub(crate) struct BranchPush {
/// `owner/name`.
pub(crate) repo: String,
pub(crate) repo_id: i64,
pub(crate) branch: String,
/// The repo's default branch, empty when the body names none.
pub(crate) default_branch: String,
}
impl BranchPush {
/// The push a `push` webhook body describes, or `None` for anything else:
/// a tag, a push that deleted its branch, or a body that is no push.
pub(crate) fn parse(body: &[u8]) -> Option<Self> {
let json: Json = serde_json::from_slice(body).ok()?;
let branch = json.get("ref")?.as_str()?.strip_prefix("refs/heads/")?;
let deleted = json
.get("after")
.and_then(Json::as_str)
.is_some_and(|after| !after.is_empty() && after.bytes().all(|b| b == b'0'));
let repository = json.get("repository")?;
if branch.is_empty() || deleted {
return None;
}
Some(Self {
repo: repository.get("full_name")?.as_str()?.to_owned(),
repo_id: repository.get("id")?.as_i64()?,
branch: branch.to_owned(),
default_branch: repository
.get("default_branch")
.and_then(Json::as_str)
.unwrap_or_default()
.to_owned(),
})
}
fn key(&self) -> (String, String) {
(self.repo.clone(), self.branch.clone())
}
}
/// The branches with a check under way, so a burst of pushes to one branch is
/// one check and not one each.
#[derive(Default)]
pub(crate) struct Debounce {
/// Whether a push arrived since the check last started.
running: Mutex<HashMap<(String, String), bool>>,
}
impl Debounce {
/// A push to `key`. True when no check was running, which the caller
/// starts; false when one was, which will run again once it finishes.
pub(crate) fn begin(&self, key: (String, String)) -> bool {
let mut running = self.running.lock().unwrap_or_else(PoisonError::into_inner);
if let Some(pushed_again) = running.get_mut(&key) {
*pushed_again = true;
return false;
}
running.insert(key, false);
true
}
/// Free `key` whatever pushes arrived, for a check that ended without
/// finishing.
pub(crate) fn release(&self, key: &(String, String)) {
self.running
.lock()
.unwrap_or_else(PoisonError::into_inner)
.remove(key);
}
/// A check of `key` is done. True when a push arrived meanwhile, so the
/// check runs again; false when it was the last, and the branch is free.
pub(crate) fn finish(&self, key: &(String, String)) -> bool {
let mut running = self.running.lock().unwrap_or_else(PoisonError::into_inner);
match running.get_mut(key) {
Some(pushed_again) if *pushed_again => {
*pushed_again = false;
true
}
_ => {
running.remove(key);
false
}
}
}
}
static RUNNING: LazyLock<Debounce> = LazyLock::new(Debounce::default);
/// What a check needs of one listed pull request.
#[derive(Clone, Debug, PartialEq, Eq)]
pub(crate) struct Pull {
pub(crate) number: i64,
title: String,
url: String,
author: String,
assignees: BTreeSet<String>,
head: String,
draft: bool,
/// The forge's flag: `None` when it did not say.
mergeable: Option<bool>,
}
impl Pull {
/// `pull` as listed, or `None` when it names no number or no author, so
/// there is nobody to tell.
pub(crate) fn from_listed(pull: &PullRequest) -> Option<Self> {
let login = |u: &forgejo_api::structs::User| u.login.clone();
Some(Self {
number: pull.number?,
title: pull.title.clone().unwrap_or_default(),
url: pull
.html_url
.as_ref()
.map(ToString::to_string)
.unwrap_or_default(),
author: pull.user.as_ref().and_then(login)?,
assignees: pull.assignees.iter().flatten().filter_map(login).collect(),
head: pull
.head
.as_ref()
.and_then(|h| h.sha.clone())
.unwrap_or_default(),
draft: pull.draft.unwrap_or(false),
mergeable: pull.mergeable,
})
}
/// The body of the event that says `action` (`conflicting` or
/// `mergeable`) of this pull request: a `pull_request` delivery the
/// router's parser reads.
fn event_body(&self, push: &BranchPush, action: &str) -> Vec<u8> {
let user = |login: &str| json!({ "login": login });
let body = json!({
"action": action,
"number": self.number,
"pull_request": {
"number": self.number,
"title": self.title,
"html_url": self.url,
"user": user(&self.author),
"assignees": self.assignees.iter().map(|a| user(a)).collect::<Vec<_>>(),
"head": { "sha": self.head },
"base": { "ref": push.branch },
"draft": self.draft,
"mergeable": action == "mergeable",
},
"repository": { "id": push.repo_id, "full_name": push.repo },
});
serde_json::to_vec(&body).unwrap_or_default()
}
}
/// Read the open pull requests on `push`'s branch with `list`, up to
/// [`MAX_READS`] times [`RECHECK`] apart, and `publish` what each says: the
/// action `mergeable` the first read that finds it so, and `conflicting` the
/// second read in a row that finds the forge's flag false. A pull request that
/// is a draft, or never settles, gets nothing.
pub(crate) async fn check<L, LF, P, PF>(push: &BranchPush, recheck: Duration, list: L, publish: P)
where
L: Fn() -> LF,
LF: Future<Output = anyhow::Result<Vec<Pull>>>,
P: Fn(&'static str, Vec<u8>) -> PF,
PF: Future<Output = ()>,
{
let mut after_false = HashSet::new();
let mut settled = HashSet::new();
for read in 0..MAX_READS {
if read > 0 {
tokio::time::sleep(recheck).await;
}
let pulls = match list().await {
Ok(pulls) => pulls,
Err(e) => {
tracing::warn!(repo = %push.repo, branch = %push.branch, error = ?e, "pr conflicts: listing pull requests failed");
return;
}
};
for pull in &pulls {
if pull.draft || settled.contains(&pull.number) {
continue;
}
let action = match pull.mergeable {
Some(true) => "mergeable",
Some(false) if after_false.contains(&pull.number) => "conflicting",
Some(false) => {
after_false.insert(pull.number);
continue;
}
None => {
after_false.remove(&pull.number);
continue;
}
};
settled.insert(pull.number);
publish(action, pull.event_body(push, action)).await;
}
if pulls.iter().all(|p| p.draft || settled.contains(&p.number)) {
return;
}
}
}
/// The open PRs the controller has seen on a `pull_request` delivery, by
/// (repo, number), with the branch each targets.
///
/// Only a push to the repo's default branch, or to a branch in here, starts a
/// check; a push to any other branch has no PR to find. The set lives in
/// memory and is empty after a restart, so a PR that targets a branch other
/// than the default (a stacked PR) is checked again only from its next
/// `pull_request` delivery.
#[derive(Default)]
pub(crate) struct OpenPulls {
bases: Mutex<HashMap<(String, i64), String>>,
}
impl OpenPulls {
/// Take in a `pull_request` family delivery: an open PR is recorded under
/// its target branch (replacing an earlier one if it was retargeted), a
/// closed one is forgotten. A body that is no PR delivery changes nothing.
pub(crate) fn note(&self, body: &[u8]) {
let Ok(json) = serde_json::from_slice::<Json>(body) else {
return;
};
let (Some(pull), Some(repo)) = (
json.get("pull_request"),
json.pointer("/repository/full_name").and_then(Json::as_str),
) else {
return;
};
let Some(number) = pull.get("number").and_then(Json::as_i64) else {
return;
};
let key = (repo.to_owned(), number);
let closed = json.get("action").and_then(Json::as_str) == Some("closed")
|| pull.get("state").and_then(Json::as_str) == Some("closed");
let mut bases = self.bases.lock().unwrap_or_else(PoisonError::into_inner);
match pull.pointer("/base/ref").and_then(Json::as_str) {
Some(base) if !closed => {
bases.insert(key, base.to_owned());
}
_ => {
bases.remove(&key);
}
}
}
fn targets(&self, repo: &str, branch: &str) -> bool {
self.bases
.lock()
.unwrap_or_else(PoisonError::into_inner)
.iter()
.any(|((r, _), base)| r == repo && base == branch)
}
}
static OPEN_PULLS: LazyLock<OpenPulls> = LazyLock::new(OpenPulls::default);
/// A `pull_request` family delivery arrived.
pub(crate) fn on_pull_request(body: &[u8]) {
OPEN_PULLS.note(body);
}
/// Whether `push` starts a check: the branch is one a PR can target as far as
/// the controller knows, and no check of it is running (if one is, it runs
/// again when done). True means the caller runs the check and frees the
/// branch afterwards.
fn begin_check(open: &OpenPulls, running: &Debounce, push: &BranchPush) -> bool {
let default = !push.default_branch.is_empty() && push.default_branch == push.branch;
(default || open.targets(&push.repo, &push.branch)) && running.begin(push.key())
}
/// Keeps a branch's key in [`Debounce`] set while a check runs, and frees it
/// however the check ends, a panic or an abandoned task included.
struct Held<'a> {
debounce: &'a Debounce,
key: (String, String),
freed: bool,
}
impl Held<'_> {
/// The check is done: true when pushes arrived meanwhile and it runs
/// again, false when the branch is free.
fn again(&mut self) -> bool {
let again = self.debounce.finish(&self.key);
self.freed = !again;
again
}
}
impl Drop for Held<'_> {
fn drop(&mut self) {
if !self.freed {
self.debounce.release(&self.key);
}
}
}
/// `fut`, the forge call named `work`, or an error when the forge does not
/// answer within the forge deadline. The forge client has no timeout of its
/// own.
async fn bounded<T>(work: &str, fut: impl Future<Output = anyhow::Result<T>>) -> anyhow::Result<T> {
crate::forge::within_forge_deadline(work, fut)
.await
.unwrap_or_else(|| {
anyhow::bail!(
"the forge did not answer within {}s",
crate::forge::FORGE_DEADLINE.as_secs()
)
})
}
/// A push arrived on the `vcs-activity` hook. Starts the check for its branch
/// unless the branch has no PR to find or a check is already under way, in
/// which case that one runs again when it is done.
pub(crate) fn on_push(state: &AppState, body: &[u8]) {
let Some(push) = BranchPush::parse(body) else {
return;
};
if begin_check(&OPEN_PULLS, &RUNNING, &push) {
tokio::spawn(watch(state.clone(), push));
}
}
async fn watch(state: AppState, push: BranchPush) {
let mut running = Held {
debounce: &RUNNING,
key: push.key(),
freed: false,
};
let Some((owner, name)) = push.repo.split_once('/') else {
return;
};
loop {
tokio::time::sleep(SETTLE).await;
if let Some(forge) = state.forge.get() {
check(
&push,
RECHECK,
|| async {
let listed = bounded(
"list open pulls",
forge.open_pulls_on(owner, name, &push.branch),
)
.await?;
Ok(listed.iter().filter_map(Pull::from_listed).collect())
},
|action, body| {
let (state, push) = (&state, &push);
async move {
if let Err(not_kept) =
crate::forge_events::publish_event(state, MERGEABILITY_EVENT, body)
.await
{
tracing::warn!(repo = %push.repo, action, reason = ?not_kept, "pr conflicts: event not kept");
}
}
},
)
.await;
}
if !running.again() {
return;
}
}
}
#[cfg(test)]
mod tests {
use super::*;
use std::sync::{Arc, Mutex};
fn push() -> BranchPush {
BranchPush {
repo: "o/r".to_owned(),
repo_id: 7,
branch: "main".to_owned(),
default_branch: "main".to_owned(),
}
}
fn pull(number: i64, mergeable: Option<bool>) -> Pull {
Pull {
number,
title: "t".to_owned(),
url: "https://forge/o/r/pulls/1".to_owned(),
author: "atlas".to_owned(),
assignees: BTreeSet::from(["iris".to_owned()]),
head: "abc".to_owned(),
draft: false,
mergeable,
}
}
/// What `check` published for the reads `reads` give in turn, as
/// `(action, number)`, and how many reads it made.
async fn run(reads: Vec<Vec<Pull>>) -> (Vec<(String, i64)>, usize) {
let seen = Arc::new(Mutex::new(Vec::new()));
let calls = Arc::new(Mutex::new(0_usize));
let reads = Arc::new(reads);
check(
&push(),
Duration::ZERO,
|| {
let (reads, calls) = (Arc::clone(&reads), Arc::clone(&calls));
async move {
let mut n = calls.lock().expect("lock");
let read = reads.get(*n).or(reads.last()).cloned().unwrap_or_default();
*n += 1;
Ok(read)
}
},
|action, body| {
let seen = Arc::clone(&seen);
async move {
let json: Json = serde_json::from_slice(&body).expect("json");
assert_eq!(json["action"], action);
seen.lock()
.expect("lock")
.push((action.to_owned(), json["number"].as_i64().expect("number")));
}
},
)
.await;
let published = seen.lock().expect("lock").clone();
let made = *calls.lock().expect("lock");
(published, made)
}
fn act(a: &str, n: i64) -> (String, i64) {
(a.to_owned(), n)
}
#[tokio::test]
async fn each_pull_request_is_published_by_what_the_forge_says() {
let (published, reads) = run(vec![vec![pull(1, Some(true)), pull(2, Some(false))]]).await;
assert_eq!(published[0], act("mergeable", 1));
assert_eq!(reads, 2, "the conflicting one is read again to confirm it");
assert_eq!(published.len(), 2);
assert_eq!(published[1], act("conflicting", 2));
}
#[tokio::test]
async fn all_mergeable_pull_requests_cost_one_read() {
let (published, reads) = run(vec![vec![pull(1, Some(true)), pull(2, Some(true))]]).await;
assert_eq!(published, [act("mergeable", 1), act("mergeable", 2)]);
assert_eq!(reads, 1);
let (none, reads) = run(vec![vec![]]).await;
assert!(none.is_empty());
assert_eq!(reads, 1);
}
/// A check still running reads as false; it must not become a conflict.
#[tokio::test]
async fn a_check_still_running_is_not_a_conflict() {
let (published, reads) =
run(vec![vec![pull(1, Some(false))], vec![pull(1, Some(true))]]).await;
assert_eq!(published, [act("mergeable", 1)]);
assert_eq!(reads, 2);
}
#[tokio::test]
async fn a_pull_request_the_forge_has_not_decided_is_read_again() {
let (published, reads) = run(vec![
vec![pull(1, None)],
vec![pull(1, None)],
vec![pull(1, Some(true))],
])
.await;
assert_eq!(published, [act("mergeable", 1)]);
assert_eq!(reads, 3);
let (published, reads) = run(vec![vec![pull(1, None)]]).await;
assert!(published.is_empty(), "never decided, never published");
assert_eq!(reads, MAX_READS);
// False, then undecided, then false is not two false reads in a row.
let (published, _) = run(vec![
vec![pull(1, Some(false))],
vec![pull(1, None)],
vec![pull(1, Some(false))],
vec![pull(1, None)],
])
.await;
assert!(published.is_empty());
}
#[tokio::test]
async fn a_draft_is_left_alone() {
let draft = Pull {
draft: true,
..pull(1, Some(false))
};
let (published, reads) = run(vec![vec![draft.clone()]]).await;
assert!(published.is_empty());
assert_eq!(reads, 1);
// Beside a pull request that needs a second read, the draft would
// read false twice, as it always does.
let (published, reads) = run(vec![vec![draft, pull(2, Some(false))]]).await;
assert_eq!(published, [act("conflicting", 2)]);
assert_eq!(reads, 2);
}
#[tokio::test]
async fn a_failed_listing_publishes_nothing() {
let published = Arc::new(Mutex::new(0_usize));
let counted = Arc::clone(&published);
check(
&push(),
Duration::ZERO,
|| async { anyhow::bail!("forge down") },
|_, _| {
let counted = Arc::clone(&counted);
async move {
*counted.lock().expect("lock") += 1;
}
},
)
.await;
assert_eq!(*published.lock().expect("lock"), 0);
}
/// The body is a `pull_request` delivery in the shape the router parses.
#[test]
fn the_event_body_names_the_author_the_assignees_and_the_base() {
let body = pull(3, Some(false)).event_body(&push(), "conflicting");
let json: Json = serde_json::from_slice(&body).expect("json");
assert_eq!(json["action"], "conflicting");
assert_eq!(json["repository"]["id"], 7);
assert_eq!(json["repository"]["full_name"], "o/r");
assert_eq!(json["pull_request"]["number"], 3);
assert_eq!(json["pull_request"]["user"]["login"], "atlas");
assert_eq!(json["pull_request"]["assignees"][0]["login"], "iris");
assert_eq!(json["pull_request"]["base"]["ref"], "main");
assert_eq!(json["pull_request"]["head"]["sha"], "abc");
}
#[test]
fn a_listed_pull_request_is_read_and_one_without_an_author_is_not() {
let listed = |user: Json| -> PullRequest {
serde_json::from_value(json!({
"number": 4,
"title": "t",
"html_url": "https://forge/o/r/pulls/4",
"user": user,
"assignees": [{ "login": "iris" }],
"head": { "sha": "abc" },
"draft": false,
"mergeable": false,
"labels": [],
"requested_reviewers": [],
"base": { "ref": "main" },
"created_at": "2026-11-07T08:00:00Z",
"updated_at": "2026-11-07T09:00:00Z",
"additions": 1,
"deletions": 1,
}))
.expect("a pull request")
};
let got = Pull::from_listed(&listed(json!({ "login": "atlas" }))).expect("read");
assert_eq!(got.number, 4);
assert_eq!(got.author, "atlas");
assert_eq!(got.mergeable, Some(false));
assert_eq!(got.assignees, BTreeSet::from(["iris".to_owned()]));
assert_eq!(Pull::from_listed(&listed(Json::Null)), None);
}
fn push_body(git_ref: &str, after: &str) -> Vec<u8> {
serde_json::to_vec(&json!({
"ref": git_ref,
"after": after,
"repository": { "id": 7, "full_name": "o/r", "default_branch": "main" },
}))
.expect("json")
}
#[test]
fn a_push_to_a_branch_is_read_and_a_tag_or_a_delete_is_not() {
assert_eq!(
BranchPush::parse(&push_body("refs/heads/feat/x", "abc123")),
Some(BranchPush {
repo: "o/r".to_owned(),
repo_id: 7,
branch: "feat/x".to_owned(),
default_branch: "main".to_owned(),
})
);
assert_eq!(
BranchPush::parse(&push_body("refs/tags/v1", "abc123")),
None
);
assert_eq!(
BranchPush::parse(&push_body("refs/heads/main", "0000000")),
None
);
assert_eq!(BranchPush::parse(b"not json"), None);
}
/// Pushes during a check make it run once more, however many they are.
#[test]
fn pushes_during_a_check_are_one_more_check() {
let d = Debounce::default();
let key = |b: &str| ("o/r".to_owned(), b.to_owned());
assert!(d.begin(key("main")), "the first push starts a check");
assert!(!d.begin(key("main")));
assert!(!d.begin(key("main")));
assert!(d.begin(key("other")), "another branch has its own");
assert!(d.finish(&key("main")), "the pushes since ask for one more");
assert!(!d.finish(&key("main")), "and then the branch is free");
assert!(d.begin(key("main")), "so the next push starts a new check");
assert!(!d.finish(&key("other")));
}
fn pull_delivery(action: &str, repo: &str, number: i64, base: &str) -> Vec<u8> {
serde_json::to_vec(&json!({
"action": action,
"pull_request": { "number": number, "base": { "ref": base } },
"repository": { "full_name": repo },
}))
.expect("json")
}
fn on_branch(branch: &str) -> BranchPush {
BranchPush {
branch: branch.to_owned(),
..push()
}
}
/// A push to a branch no PR is known to target starts no check, and
/// leaves nothing marked running.
#[test]
fn a_push_to_a_branch_no_pull_request_targets_starts_nothing() {
let (open, running) = (OpenPulls::default(), Debounce::default());
let topic = on_branch("agent/topic");
assert!(!begin_check(&open, &running, &topic));
assert!(running.begin(topic.key()), "nothing was marked running");
running.release(&topic.key());
// Controls: the default branch, and a branch a PR is known to target.
assert!(begin_check(&open, &running, &push()));
open.note(&pull_delivery("opened", "o/r", 3, "agent/topic"));
assert!(begin_check(&open, &running, &topic));
assert!(!begin_check(&open, &running, &topic), "one check at a time");
// A body naming no default branch checks only a branch a PR targets.
let unnamed = BranchPush {
default_branch: String::new(),
..on_branch("main")
};
assert!(!begin_check(&open, &running, &unnamed));
// Another repo's PR on the same branch name is not this repo's.
let other = BranchPush {
repo: "o/other".to_owned(),
..topic
};
assert!(!begin_check(&open, &running, &other));
}
#[test]
fn the_known_targets_follow_the_pull_request_deliveries() {
let open = OpenPulls::default();
open.note(&pull_delivery("opened", "o/r", 5, "base-a"));
open.note(&pull_delivery("opened", "o/r", 6, "base-a"));
assert!(open.targets("o/r", "base-a"));
open.note(&pull_delivery("edited", "o/r", 5, "base-b"));
assert!(open.targets("o/r", "base-b"), "5 was retargeted");
assert!(open.targets("o/r", "base-a"), "6 still targets it");
open.note(&pull_delivery("closed", "o/r", 6, "base-a"));
assert!(!open.targets("o/r", "base-a"));
open.note(&pull_delivery("closed", "o/r", 5, "base-b"));
assert!(!open.targets("o/r", "base-b"));
open.note(b"not json");
open.note(br#"{"issue":{"number":1}}"#);
assert!(!open.targets("o/r", "base-a"), "no PR delivery, no change");
}
/// A forge that never answers ends the check at the deadline and frees the
/// branch for the next push.
#[tokio::test(start_paused = true)]
async fn a_list_that_never_answers_ends_the_check_and_frees_the_branch() {
let running = Debounce::default();
let p = push();
assert!(running.begin(p.key()));
let mut guard = Held {
debounce: &running,
key: p.key(),
freed: false,
};
let start = tokio::time::Instant::now();
check(
&p,
Duration::ZERO,
|| bounded("list open pulls", std::future::pending()),
|_, _| async {},
)
.await;
assert_eq!(start.elapsed(), crate::forge::FORGE_DEADLINE);
assert!(!guard.again());
assert!(running.begin(p.key()), "the branch is free");
}
#[test]
fn a_check_that_panics_frees_the_branch() {
let running = Debounce::default();
let key = push().key();
assert!(running.begin(key.clone()));
let ended = std::panic::catch_unwind(std::panic::AssertUnwindSafe(|| {
let _guard = Held {
debounce: &running,
key: key.clone(),
freed: false,
};
panic!("the check died");
}));
assert!(ended.is_err());
assert!(running.begin(key), "the branch is free");
}
}