Merge branch 'working' into job_peek_lchen

job_peek_lchen: Add fetchfile feature (job output/error peek proxy)
working: HA/Raft infrastructure (consensus, replication, config mgmt)

Conflict resolution summary:
- controller.capnp: fetchfile @41, fetchfilereply @18, fetchfilemsg @30
- cluster.c: bifurcated OPCode_reply for fetchfile + config-push ACK
- job.c: kept full fetchfile pending-request subsystem (~183 lines)
- request.c: kept both xce_fetchfile_req() and XCE_RETRY_DEFAULTS
- helper.c: added missing preVoteRequest/preVoteReply mappings
- All 15 new test registrations (test_cbuf.c + 14 HA tests)

src/frontend/apiserver/backend/clib.go

@@ -76,6 +76,30 @@ var idCtxOnce sync.Once
 // Must be set via StartNotificationListener before RegisterToBackend.
 var gHandler NotificationHandler
 
+func tryConnect(host string, port int, from, key string) error {
+	cAddr := C.CString(host)
+	cFrom := C.CString(from)
+	cKey := C.CString(key)
+	defer func() {
+		C.free(unsafe.Pointer(cAddr))
+		C.free(unsafe.Pointer(cFrom))
+		C.free(unsafe.Pointer(cKey))
+	}()
+
+	var cConfig C.xce_client_config_t
+	cConfig.nmasters = 1
+	cConfig.masters[0] = cAddr
+	cConfig.master_ports[0] = C.int(port)
+	cConfig.from = cFrom
+	cConfig.key = cKey
+
+	rc := C.xce_backend_init(&cConfig, &gCtx)
+	if rc < 0 {
+		return fmt.Errorf("xce_backend_init failed on %s:%d: %d", host, port, int(rc))
+	}
+	return nil
+}
+
 // RegisterToBackend initialises the XCE client library and joins as an API
 // server.  StartNotificationListener should be called first so that push
 // events have a handler ready before the first push can arrive.
@@ -89,27 +113,31 @@ func RegisterToBackend(config *BackendConfig) error {
 		key = "keepsecret$"
 	}
 
-	cAddr := C.CString(config.Address)
-	cFrom := C.CString(from)
-	cKey := C.CString(key)
-	defer func() {
-		C.free(unsafe.Pointer(cAddr))
-		C.free(unsafe.Pointer(cFrom))
-		C.free(unsafe.Pointer(cKey))
-	}()
-
-	var cConfig C.xce_client_config_t
-	cConfig.nmasters = 1
-	cConfig.masters[0] = cAddr
-	cConfig.master_ports[0] = C.int(config.Port)
-	cConfig.from = cFrom
-	cConfig.key = cKey
-
-	rc := C.xce_backend_init(&cConfig, &gCtx)
-	if rc < 0 {
-		return fmt.Errorf("xce_backend_init failed: %d", int(rc))
+	if len(config.Peers) > 0 {
+		var lastErr error
+		for _, peer := range config.Peers {
+			host, port, err := parsePeer(peer)
+			if err != nil {
+				logger.Warn("Skipping invalid peer", zap.String("peer", peer), zap.Error(err))
+				lastErr = err
+				continue
+			}
+			if err := tryConnect(host, port, from, key); err != nil {
+				logger.Warn("Candidate unreachable, trying next",
+					zap.String("host", host), zap.Int("port", port), zap.Error(err))
+				lastErr = err
+				continue
+			}
+			logger.Info("Backend connection established (HA)",
+				zap.String("host", host), zap.Int("port", port))
+			return nil
+		}
+		return fmt.Errorf("all HA candidates failed: %w", lastErr)
 	}
 
+	if err := tryConnect(config.Address, config.Port, from, key); err != nil {
+		return err
+	}
 	logger.Info("Backend connection established",
 		zap.String("address", config.Address),
 		zap.Int("port", config.Port))