refactor: extract provision_space from matrix::ensure_all instead of allow

Per mara's standing calibration (#2463): extraction > silencing for
too_many_lines. Splits the space + chat-room provisioning tail into its
own fn, bringing ensure_all back under the 100-line threshold without
an #[allow].

hive-c0re/src/main.rs

@@ -197,6 +197,22 @@ async fn main() -> Result<()> {
     }
 }
 
+/// Banner message for a failing matrix `ensure_all` sweep, shared by both
+/// the initial and periodic `record_err` call sites in `cmd_serve` so the
+/// wording can't drift between them.
+fn matrix_sweep_banner(ctx: sweep_health::SweepFailure) -> String {
+    let age = ctx.since_last_ok.map_or_else(
+        || "no success this session".to_owned(),
+        |d| format!("last ok {} ago", sweep_health::fmt_age(d)),
+    );
+    format!(
+        "matrix user/space sweep failing ({} consecutive, {age}) \
+         — some agents may be missing matrix accounts, space membership, \
+         or chat-room invites",
+        ctx.consecutive
+    )
+}
+
 /// Start the coordinator daemon: open the broker, run migrations, spawn
 /// background tasks (auto-update, vacuums, crash-watcher, reminder-scheduler,
 /// dashboard), then serve the admin socket until a signal arrives.
@@ -414,11 +430,24 @@ async fn cmd_serve(
     let mut matrix_shutdown = coord.shutdown_rx();
     tokio::spawn(async move {
         let interval = std::time::Duration::from_mins(30);
-        matrix::ensure_all().await;
+        // Debounced banner: a lone bad sweep (homeserver mid-restart, a
+        // transient HTTP blip) shouldn't flap the dashboard, but a sweep
+        // that's been failing for hours (missing agent invites, a broken
+        // admin token) should surface. Cleared the moment a sweep is clean.
+        let mut health = sweep_health::SweepHealth::new("matrix_ensure_all", "warn", 2);
+        if matrix::ensure_all().await {
+            health.record_ok();
+        } else {
+            health.record_err(matrix_sweep_banner);
+        }
         loop {
             tokio::select! {
                 () = tokio::time::sleep(interval) => {
-                    matrix::ensure_all().await;
+                    if matrix::ensure_all().await {
+                        health.record_ok();
+                    } else {
+                        health.record_err(matrix_sweep_banner);
+                    }
                 }
                 _ = matrix_shutdown.changed() => {
                     tracing::info!("matrix ensure_all: shutdown signal received");

hive-c0re/src/matrix.rs

@@ -1503,20 +1503,28 @@ async fn resolve_room_alias(
 }
 
 /// Sweep every existing container (manager + sub-agents) and ensure
-/// each has a matrix user + token on the local homeserver. Called once
-/// at hive-c0re startup, alongside `forge::ensure_all`. No-op when the
+/// each has a matrix user + token on the local homeserver. Called at
+/// hive-c0re startup, alongside `forge::ensure_all`, and then
+/// periodically (see the caller in `main.rs`). No-op when the
 /// hive-matrix container isn't running. Per-step failures are logged
 /// but don't abort the sweep.
-pub async fn ensure_all() {
+///
+/// Returns `true` when every step of the sweep succeeded, `false` when at
+/// least one step failed — the caller feeds this into a
+/// [`crate::stats::sweep_health::SweepHealth`] to raise a debounced
+/// dashboard banner on persistent failure (this sweep re-runs every 30
+/// minutes, so a one-off blip self-heals without ever bannering).
+pub async fn ensure_all() -> bool {
     if !is_present().await {
         tracing::debug!("matrix: hive-matrix container absent, skipping user sweep");
-        return;
+        return true;
     }
+    let mut ok = true;
     let register_token = match ensure_register_token() {
         Ok(t) => t,
         Err(e) => {
             tracing::warn!(error = ?e, "matrix: ensure_register_token failed");
-            return;
+            return false;
         }
     };
     // One HTTP client for the whole sweep — connection pool is
@@ -1528,7 +1536,7 @@ pub async fn ensure_all() {
         Ok(c) => c,
         Err(e) => {
             tracing::warn!(error = ?e, "matrix: build HTTP client failed; skipping sweep");
-            return;
+            return false;
         }
     };
     // Provision hive admin user FIRST so it's the first registered
@@ -1536,10 +1544,11 @@ pub async fn ensure_all() {
     // registered user admin automatically).
     if let Err(e) = ensure_admin_user(&client, &register_token).await {
         tracing::warn!(error = ?e, "matrix: ensure_admin_user failed");
+        ok = false;
     }
     let Ok(containers) = crate::lifecycle::list().await else {
         tracing::warn!("matrix: nixos-container list failed; skipping user sweep");
-        return;
+        return false;
     };
     let mut agent_names: Vec<String> = Vec::new();
     for c in &containers {
@@ -1550,33 +1559,45 @@ pub async fn ensure_all() {
         agent_names.push(name.to_owned());
     }
 
-    // Provision the hive Space and invite all agents (+ the admin account).
+    if !provision_space(&client, &agent_names).await {
+        ok = false;
+    }
+    ok
+}
+
+/// Provision the hive Space + default chat room and invite every agent
+/// (+ the admin account) to both. Split out of [`ensure_all`] purely to
+/// keep that function under the `too_many_lines` threshold — this is the
+/// tail half of the same sequential sweep and shares its aggregate-bool,
+/// log-and-continue failure handling.
+async fn provision_space(client: &reqwest::Client, agent_names: &[String]) -> bool {
+    let mut ok = true;
     // server_name is needed to form full Matrix user IDs for invites.
     let admin_token = match read_admin_token() {
         Ok(t) => t,
         Err(e) => {
             tracing::warn!(error = ?e, "matrix: skipping hive space provisioning (no admin token)");
-            return;
+            return false;
         }
     };
     // server_name first — the agent invites need it (fully-qualified user ids).
-    let server_name = match discover_server_name(&client).await {
+    let server_name = match discover_server_name(client).await {
         Ok(s) => s,
         Err(e) => {
             tracing::warn!(error = ?e, "matrix: discover_server_name failed; skipping space provisioning");
-            return;
+            return false;
         }
     };
-    let room_id = match ensure_hive_space(&client, &admin_token).await {
+    let room_id = match ensure_hive_space(client, &admin_token).await {
         Ok(id) => id,
         Err(e) => {
             tracing::warn!(error = ?e, "matrix: ensure_hive_space failed");
-            return;
+            return false;
         }
     };
     // Invite @hive admin first, then all agents.
     if let Err(e) = invite_to_room(
-        &client,
+        client,
         &admin_token,
         &room_id,
         HIVE_ADMIN_LOCALPART,
@@ -1585,10 +1606,12 @@ pub async fn ensure_all() {
     .await
     {
         tracing::warn!(error = ?e, "matrix: invite @hive to space failed");
+        ok = false;
     }
-    for name in &agent_names {
-        if let Err(e) = invite_to_room(&client, &admin_token, &room_id, name, &server_name).await {
+    for name in agent_names {
+        if let Err(e) = invite_to_room(client, &admin_token, &room_id, name, &server_name).await {
             tracing::warn!(%name, error = ?e, "matrix: invite agent to space failed");
+            ok = false;
         }
     }
 
@@ -1597,10 +1620,10 @@ pub async fn ensure_all() {
     // rooms to chat in (Matrix semantics — children aren't auto-joined), so
     // without this the Space is empty. The restricted join rule additionally
     // lets the operator (a Space member) join from the Space hierarchy.
-    match ensure_hive_chat_room(&client, &admin_token, &room_id, &server_name).await {
+    match ensure_hive_chat_room(client, &admin_token, &room_id, &server_name).await {
         Ok(chat_room_id) => {
             if let Err(e) = invite_to_room(
-                &client,
+                client,
                 &admin_token,
                 &chat_room_id,
                 HIVE_ADMIN_LOCALPART,
@@ -1609,19 +1632,23 @@ pub async fn ensure_all() {
             .await
             {
                 tracing::warn!(error = ?e, "matrix: invite @hive to chat room failed");
+                ok = false;
             }
-            for name in &agent_names {
+            for name in agent_names {
                 if let Err(e) =
-                    invite_to_room(&client, &admin_token, &chat_room_id, name, &server_name).await
+                    invite_to_room(client, &admin_token, &chat_room_id, name, &server_name).await
                 {
                     tracing::warn!(%name, error = ?e, "matrix: invite agent to chat room failed");
+                    ok = false;
                 }
             }
         }
         Err(e) => {
             tracing::warn!(error = ?e, "matrix: ensure_hive_chat_room failed");
+            ok = false;
         }
     }
+    ok
 }
 
 #[cfg(test)]