annotate mcp connect-refused as expected hive-c0re restart

hive-ag3nt/src/client.rs

@@ -1,7 +1,7 @@
 use std::path::Path;
 use std::time::Duration;
 
-use anyhow::{Context, Result, anyhow};
+use anyhow::{Result, anyhow};
 use serde::Serialize;
 use serde::de::DeserializeOwned;
 use tokio::io::{AsyncBufReadExt, AsyncWriteExt, BufReader};
@@ -92,10 +92,29 @@ where
     Req: Serialize + ?Sized,
     Resp: DeserializeOwned,
 {
-    let stream = UnixStream::connect(socket)
+    let stream = match UnixStream::connect(socket).await {
-        .await
+        Ok(stream) => stream,
-        .with_context(|| format!("connect to {}", socket.display()))
+        Err(e) => {
-        .map_err(RequestError::Transient)?;
+            // A refused or missing socket usually means hive-c0re is
+            // mid-restart (operator redeploy / rebuild) — the socket is
+            // recreated on its boot and `request_retried` rides it out. When
+            // the error *does* surface (retries exhausted, or a non-retried
+            // caller) add that context so claude reads it as a likely
+            // transient rather than a hard failure worth escalating.
+            let restarting = matches!(
+                e.kind(),
+                std::io::ErrorKind::ConnectionRefused | std::io::ErrorKind::NotFound
+            );
+            let mut err = anyhow::Error::new(e).context(format!("connect to {}", socket.display()));
+            if restarting {
+                err = err.context(
+                    "hive-c0re may be restarting (e.g. an operator redeploy); \
+                     the harness already retried ~60s before surfacing this",
+                );
+            }
+            return Err(RequestError::Transient(err));
+        }
+    };
     let (read, mut write) = stream.into_split();
 
     let mut payload = serde_json::to_string(req).map_err(|e| RequestError::Fatal(e.into()))?;
@@ -122,3 +141,25 @@ where
     }
     serde_json::from_str(line.trim()).map_err(|e| RequestError::Fatal(e.into()))
 }
+
+#[cfg(test)]
+mod tests {
+    use super::{RequestError, try_once};
+
+    /// A connect to a non-existent socket path (ENOENT → `NotFound`) is
+    /// classified transient AND annotated with the "hive-c0re is restarting"
+    /// hint, so a surfaced tool error reads as the expected transient.
+    #[tokio::test]
+    async fn missing_socket_connect_is_transient_with_restart_hint() {
+        let bogus = std::path::Path::new("/nonexistent/hive/mcp.sock");
+        match try_once::<(), serde_json::Value>(bogus, &()).await {
+            Err(RequestError::Transient(e)) => {
+                let msg = format!("{e:#}");
+                assert!(msg.contains("restarting"), "missing restart hint: {msg}");
+                assert!(msg.contains("connect to"), "missing connect context: {msg}");
+            }
+            Err(RequestError::Fatal(e)) => panic!("expected transient, got fatal: {e:#}"),
+            Ok(_) => panic!("expected connect failure to a non-existent socket"),
+        }
+    }
+}