feat(worker): add commits to github search backfill

Walk back the earlier decision to skip /search/commits. The fork
inflation that worried me isn't misattribution — those commits
really were authored by the user; they just persist in forks after
the original repo went away. Skipping them dropped legitimate
historical work from the timeline.

The duplicate-SHA-across-forks issue is a pure dedup concern:
  * keyed `github-commit:<sha>` (SHA only — globally unique by Git's
    content addressing; same commit in two forks lands in one row);
  * within a single page, dedup by id before INSERT (postgres ON
    CONFLICT errors when the conflict target appears twice in one
    statement);
  * across pages and runs, last-write-wins via upsert. The repo
    association may flip between forks but the commit content is
    identical.

Visibility is read inline from `repository.private` on the search
item, no extra lookup needed. Also opportunistically populates the
shared visibility cache so the issue loop in the same poll skips
/repos/{full_name} GETs for any repo it already saw via commits.

Reshape: presentation/github.rs gains a Commit path — short SHA
linked, repo linked, first line of the commit message as subtitle.
GitCommit icon.

Tests: +3 in github_search (parse uses sha as id, marks private,
rejects non-github URL), +1 in presentation (commit reshape uses
short sha + first message line) — 18 total green.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-03 18:54:32 +03:00
parent e4052c4c9a
commit 7772393598
2 changed files with 255 additions and 14 deletions

View File

@@ -6,8 +6,10 @@ use serde_json::Value;
pub(crate) fn reshape(event: &Event) -> TimelineItem {
// Search-API items have a different payload shape (the search item itself
// rather than a wrapped event), so dispatch them through a separate path.
if matches!(event.action.as_str(), "Issue" | "PullRequest") {
return search_reshape(event);
match event.action.as_str() {
"Issue" | "PullRequest" => return search_reshape(event),
"Commit" => return commit_reshape(event),
_ => {}
}
let p = &event.payload;
@@ -426,6 +428,58 @@ fn search_reshape(event: &Event) -> TimelineItem {
}
}
fn commit_reshape(event: &Event) -> TimelineItem {
let p = &event.payload;
let sha = p.get("sha").and_then(Value::as_str).unwrap_or("");
let short_sha: String = sha.chars().take(7).collect();
let html_url = p.get("html_url").and_then(Value::as_str).unwrap_or("");
let message_first_line = p
.get("commit")
.and_then(|c| c.get("message"))
.and_then(Value::as_str)
.unwrap_or("")
.lines()
.next()
.unwrap_or("")
.to_string();
let repo = p
.get("repository")
.and_then(|r| r.get("full_name"))
.and_then(Value::as_str)
.unwrap_or("(unknown repo)");
let author_login = p
.get("author")
.and_then(|a| a.get("login"))
.and_then(Value::as_str);
let mut title = Vec::new();
if let Some(actor) = author_login {
title.push(TitleSegment::link(
actor.to_string(),
format!("https://github.com/{actor}"),
));
title.push(TitleSegment::text(" "));
}
title.push(TitleSegment::text("committed "));
title.push(TitleSegment::link(short_sha, html_url.to_string()));
title.push(TitleSegment::text(" in "));
title.push(repo_link(repo));
let subtitle = (!message_first_line.is_empty())
.then(|| vec![TitleSegment::text(message_first_line)]);
TimelineItem {
id: event.id.clone(),
source: Source::Github,
action: event.action.clone(),
occurred_at: event.occurred_at,
icon: TimelineIcon::GitCommit,
title,
subtitle,
body: None,
}
}
fn repo_from_url(url: &str) -> Option<String> {
let stripped = url.strip_prefix("https://github.com/")?;
let mut parts = stripped.splitn(3, '/');
@@ -600,6 +654,35 @@ mod tests {
);
}
#[test]
fn commit_reshape_uses_short_sha_and_first_message_line() {
let raw = json!({
"sha": "a6fcefbe909a97ad5a049b9fa48bc74309af10d9",
"html_url": "https://github.com/faith1337z/Trade/commit/a6fcefbe909a97ad5a049b9fa48bc74309af10d9",
"commit": {
"message": "split multiline message into multiple irc messages\n\nbody body body"
},
"repository": { "full_name": "faith1337z/Trade" },
"author": { "login": "grenade" }
});
let item = reshape(&ev("Commit", raw));
assert_eq!(item.icon, TimelineIcon::GitCommit);
let rendered: String = item
.title
.iter()
.map(|s| match s {
TitleSegment::Text { text } => text.clone(),
TitleSegment::Link { text, .. } => text.clone(),
})
.collect();
assert!(rendered.contains("committed a6fcefb in faith1337z/Trade"), "got: {rendered}");
// body of the commit message is dropped; only first line in subtitle
assert_eq!(
item.subtitle.unwrap(),
vec![TitleSegment::text("split multiline message into multiple irc messages")]
);
}
#[test]
fn unknown_event_falls_back() {
let raw = json!({