fix(#1309): retry forge token read at startup instead of giving up immediately

hive-ag3nt/src/forge_notify.rs

@@ -20,6 +20,13 @@ const POLL_INTERVAL_SECS: u64 = 30;
 const HTTP_TIMEOUT_SECS: u64 = 10;
 /// Maximum characters of a body/comment to include in the wake message.
 const BODY_TRUNCATE: usize = 500;
+/// How long to wait between token-read retries when the token file is
+/// missing or unreadable at startup (e.g. hive-priv hasn't provisioned
+/// it yet, or a chown race left it temporarily root-owned).
+const TOKEN_RETRY_SECS: u64 = 30;
+/// Give up waiting for the token after this many retries (~10 minutes).
+/// Avoids an infinite wait on agents that genuinely have no forge account.
+const TOKEN_RETRY_MAX: u32 = 20;
 
 /// Spawn point: called once from `hive-ag3nt serve` (agent) or
 /// `hive-m1nd serve` (manager). Returns immediately if the forge is not
@@ -37,18 +44,33 @@ pub async fn run(socket: PathBuf) {
 
     let state_dir = std::env::var("HYPERHIVE_STATE_DIR").unwrap_or_default();
     let token_path = format!("{state_dir}/forge-token");
-    let token = match tokio::fs::read_to_string(&token_path).await {
+    // Retry reading the token to handle races where hive-priv provisions the
-        Ok(t) => {
+    // token after the harness starts, or where a parent-container chown briefly
-            let t = t.trim().to_owned();
+    // makes the file unreadable (see #1304 / #1309). We wait up to
-            if t.is_empty() {
+    // TOKEN_RETRY_MAX * TOKEN_RETRY_SECS before giving up.
-                debug!("forge_notify: empty forge token at {token_path} — disabled");
+    let token = {
+        let mut attempts = 0u32;
+        loop {
+            match tokio::fs::read_to_string(&token_path).await {
+                Ok(t) => {
+                    let t = t.trim().to_owned();
+                    if !t.is_empty() {
+                        break t;
+                    }
+                    debug!("forge_notify: empty forge token at {token_path}");
+                }
+                Err(e) => {
+                    debug!("forge_notify: cannot read token at {token_path}: {e}");
+                }
+            }
+            attempts += 1;
+            if attempts >= TOKEN_RETRY_MAX {
+                debug!(
+                    "forge_notify: token not available after {TOKEN_RETRY_MAX} retries — disabled"
+                );
                 return;
             }
-            t
+            tokio::time::sleep(Duration::from_secs(TOKEN_RETRY_SECS)).await;
-        }
-        Err(e) => {
-            debug!("forge_notify: no forge token at {token_path} ({e}) — disabled");
-            return;
         }
     };