feat(worker): add hg-edge and bugzilla pollers

Wires two historical sources for completeness with the 2019 timeline:

- hg-edge.mozilla.org: scans json-pushes for a configured set of
  build/* repos and matches changeset author client-side, since the
  pushlog `user=` filter targets the pusher (sheriffs/reviewers in
  this case) rather than the author. Daily poll cadence — mozilla
  retired hg, no new events expected.
- bugzilla.mozilla.org: queries /rest/bug?creator=<email>. Without
  an api key the unauthenticated endpoint only returns public bugs,
  which is what the public timeline wants anyway.

Reshape renders "<author> committed <short_node> in <repo>" for hg
and "filed bug #<id> in <product>" for bugzilla, both linking back
to the canonical upstream URL via a stamped `_host` payload field.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

crates/moments-worker/src/main.rs

@@ -4,9 +4,11 @@ use clap::Parser;
 use moments_core::{EventSource, run_poller};
 use moments_data::{
     PgStore,
+    bugzilla::{BugzillaConfig, BugzillaSource},
     gitea::{GiteaConfig, GiteaSource},
     github::{GithubConfig, GithubSource},
     github_search::{GithubSearchConfig, GithubSearchSource},
+    hg::{HgConfig, HgSource},
 };
 use reqwest::Client;
 use tracing::info;
@@ -45,6 +47,45 @@ struct Args {
     /// Seconds between Gitea activity-feed polls.
     #[arg(long, env = "GITEA_POLL_INTERVAL_SECS", default_value = "600")]
     gitea_interval_secs: u64,
+
+    #[arg(long, env = "HG_HOST", default_value = "hg-edge.mozilla.org")]
+    hg_host: String,
+
+    /// Comma-separated mozilla hg repo paths to scan, e.g. "build/puppet,build/tools".
+    #[arg(
+        long,
+        env = "HG_REPOS",
+        value_delimiter = ',',
+        default_value = "build/puppet,build/tools,build/buildbot-configs"
+    )]
+    hg_repos: Vec<String>,
+
+    /// Comma-separated case-insensitive substrings matched against changeset author fields.
+    #[arg(
+        long,
+        env = "HG_AUTHOR_TERMS",
+        value_delimiter = ',',
+        default_value = "thijssen,grenade"
+    )]
+    hg_author_terms: Vec<String>,
+
+    /// Seconds between hg pushlog scans (defaults to 24h — historical data).
+    #[arg(long, env = "HG_POLL_INTERVAL_SECS", default_value = "86400")]
+    hg_interval_secs: u64,
+
+    #[arg(long, env = "BUGZILLA_HOST", default_value = "bugzilla.mozilla.org")]
+    bugzilla_host: String,
+
+    #[arg(long, env = "BUGZILLA_EMAIL", default_value = "rthijssen@mozilla.com")]
+    bugzilla_email: String,
+
+    /// Optional bugzilla API key. Without one, only public bugs are returned.
+    #[arg(long, env = "BUGZILLA_API_KEY")]
+    bugzilla_api_key: Option<String>,
+
+    /// Seconds between bugzilla creator-query polls (defaults to 24h).
+    #[arg(long, env = "BUGZILLA_POLL_INTERVAL_SECS", default_value = "86400")]
+    bugzilla_interval_secs: u64,
 }
 
 #[tokio::main]
@@ -93,30 +134,66 @@ async fn main() -> anyhow::Result<()> {
         },
     )) as Arc<dyn EventSource>;
 
+    let hg = Arc::new(HgSource::new(
+        http.clone(),
+        store.clone(),
+        store.clone(),
+        HgConfig {
+            host: args.hg_host.clone(),
+            author_terms: args.hg_author_terms.clone(),
+            repos: args.hg_repos.clone(),
+        },
+    )) as Arc<dyn EventSource>;
+
+    let bugzilla = Arc::new(BugzillaSource::new(
+        http.clone(),
+        store.clone(),
+        store.clone(),
+        BugzillaConfig {
+            host: args.bugzilla_host.clone(),
+            creator_email: args.bugzilla_email.clone(),
+            api_key: args.bugzilla_api_key.clone(),
+            ..Default::default()
+        },
+    )) as Arc<dyn EventSource>;
+
     info!(
         github_user = args.github_user,
         gitea_host = args.gitea_host,
         gitea_user = args.gitea_user,
+        hg_host = args.hg_host,
+        hg_repos = ?args.hg_repos,
+        bugzilla_host = args.bugzilla_host,
+        bugzilla_email = args.bugzilla_email,
         events_interval_secs = args.interval_secs,
         search_interval_secs = args.search_interval_secs,
         gitea_interval_secs = args.gitea_interval_secs,
+        hg_interval_secs = args.hg_interval_secs,
+        bugzilla_interval_secs = args.bugzilla_interval_secs,
         "worker started"
     );
 
     let interval = Duration::from_secs(args.interval_secs);
     let search_interval = Duration::from_secs(args.search_interval_secs);
     let gitea_interval = Duration::from_secs(args.gitea_interval_secs);
+    let hg_interval = Duration::from_secs(args.hg_interval_secs);
+    let bugzilla_interval = Duration::from_secs(args.bugzilla_interval_secs);
 
     let github_task = tokio::spawn(async move { run_poller(github, interval).await });
     let github_search_task =
         tokio::spawn(async move { run_poller(github_search, search_interval).await });
     let gitea_task = tokio::spawn(async move { run_poller(gitea, gitea_interval).await });
+    let hg_task = tokio::spawn(async move { run_poller(hg, hg_interval).await });
+    let bugzilla_task =
+        tokio::spawn(async move { run_poller(bugzilla, bugzilla_interval).await });
 
     tokio::signal::ctrl_c().await?;
     info!("shutdown signal received");
     github_task.abort();
     github_search_task.abort();
     gitea_task.abort();
+    hg_task.abort();
+    bugzilla_task.abort();
     Ok(())
 }