johno/beads
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add RPC diagnostics with BD_RPC_DEBUG env var

Browse Source 
- Add BD_RPC_DEBUG=1 for lightweight timing logs to stderr
- Log socket path, socket exists check, dial timing, health check timing
- Improve daemon status message when lock not held
- Helps field triage of connection issues without verbose daemon logs
- Fixes bd-j7e2
This commit is contained in:
Steve Yegge
2025-11-07 21:29:22 -08:00
parent 1c86fc1434
commit fe705befbe
4 changed files with 48 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.beads/bd.sock.startlock Normal file
View File

@@ -0,0 +1 @@
36165

2
.beads/beads.jsonl
View File

@@ -275,7 +275,7 @@
{"id":"bd-iye7","content_hash":"5b39d4322d23d2a38968d81f5100cb438de4cc935f1d6d6be73e8db4be57f1bd","title":"Add path normalization to getMultiRepoJSONLPaths()","description":"From bd-xo6b code review: getMultiRepoJSONLPaths() does not handle non-standard paths correctly.\n\nProblems:\n- No tilde expansion: ~/repos/foo treated as literal path\n- No absolute path conversion: ../other-repo breaks if working directory changes\n- No duplicate detection: If Primary=. and Additional=[.], same JSONL processed twice\n- No empty string handling: Empty paths create invalid /.beads/issues.jsonl\n\nImpact:\nConfig with tilde or relative paths will fail\n\nFix needed:\n1. Use filepath.Abs() for all paths\n2. Add tilde expansion via os.UserHomeDir()\n3. Deduplicate paths (use map to track seen paths)\n4. Filter out empty strings\n5. Validate paths exist and are readable\n\nFiles:\n- cmd/bd/deletion_tracking.go:333-358 (getMultiRepoJSONLPaths function)","status":"closed","priority":1,"issue_type":"bug","created_at":"2025-11-06T19:31:51.882743-08:00","updated_at":"2025-11-06T19:35:41.246311-08:00","closed_at":"2025-11-06T19:35:41.246311-08:00","source_repo":".","dependencies":[{"issue_id":"bd-iye7","depends_on_id":"bd-xo6b","type":"discovered-from","created_at":"2025-11-06T19:32:12.267906-08:00","created_by":"daemon"}]}
{"id":"bd-j0rm","content_hash":"a9d63140e09a3aba769436c54c204e9369912a7d8d51d2aae9e68c8148357d3b","title":"Ready issue","description":"","status":"open","priority":1,"issue_type":"task","created_at":"2025-11-07T19:05:35.35216-08:00","updated_at":"2025-11-07T19:05:35.35216-08:00","source_repo":"."}
{"id":"bd-j5aj","content_hash":"2236f911e6f321a74aa61bdf702d24949e44a68ed511d12dd011aa4103c89230","title":"Issue 2","description":"","status":"open","priority":1,"issue_type":"task","created_at":"2025-11-07T19:07:16.364549-08:00","updated_at":"2025-11-07T19:07:16.364549-08:00","source_repo":"."}
{"id":"bd-j7e2","content_hash":"e5cee574c055f80bb884f99f6a5a918f5e7dafa84392f4d4ea6b4b67c406e415","title":"RPC diagnostics: BD_RPC_DEBUG timing logs","description":"Add lightweight diagnostic logging for RPC connection attempts:\n- BD_RPC_DEBUG=1 prints to stderr:\n - Socket path being dialed\n - Socket exists check result \n - Dial start/stop time\n - Connection outcome\n- Improve bd daemon --status messaging when lock not held\n\nThis helps field triage of connection issues without verbose daemon logs.","status":"open","priority":3,"issue_type":"task","created_at":"2025-11-07T16:42:12.772364-08:00","updated_at":"2025-11-07T16:42:12.772364-08:00","source_repo":".","dependencies":[{"issue_id":"bd-j7e2","depends_on_id":"bd-ndyz","type":"discovered-from","created_at":"2025-11-07T16:42:12.773714-08:00","created_by":"daemon"}]}
{"id":"bd-j7e2","content_hash":"aa810a603c630b2435f7a75d4c38a57b72e557e64913c1b701ccda87109f2ffe","title":"RPC diagnostics: BD_RPC_DEBUG timing logs","description":"Add lightweight diagnostic logging for RPC connection attempts:\n- BD_RPC_DEBUG=1 prints to stderr:\n - Socket path being dialed\n - Socket exists check result \n - Dial start/stop time\n - Connection outcome\n- Improve bd daemon --status messaging when lock not held\n\nThis helps field triage of connection issues without verbose daemon logs.","status":"in_progress","priority":3,"issue_type":"task","created_at":"2025-11-07T16:42:12.772364-08:00","updated_at":"2025-11-07T21:26:53.618078-08:00","source_repo":".","dependencies":[{"issue_id":"bd-j7e2","depends_on_id":"bd-ndyz","type":"discovered-from","created_at":"2025-11-07T16:42:12.773714-08:00","created_by":"daemon"}]}
{"id":"bd-jpm9","content_hash":"cdd43e0460cfe2e1c0f49728248d4bb441f5c6b17943dd9d13efe32de3e42147","title":"Issue to close","description":"","status":"closed","priority":1,"issue_type":"bug","created_at":"2025-11-07T19:07:13.57982-08:00","updated_at":"2025-11-07T19:07:13.602394-08:00","closed_at":"2025-11-07T19:07:13.602394-08:00","source_repo":"."}
{"id":"bd-jx90","content_hash":"5e08ff79669eaf606022b1ab13a167c0689e9d9a1b2f3bb4fb880ca792546411","title":"Add simple cleanup command to delete closed issues","description":"Users want a simple command to delete all closed issues without requiring Anthropic API key (unlike compact). Requested in GH #243.","status":"open","priority":2,"issue_type":"feature","created_at":"2025-11-07T00:26:30.372137-08:00","updated_at":"2025-11-07T00:26:30.372137-08:00","source_repo":"."}
{"id":"bd-k0j9","content_hash":"52d1e6f87bd7655018bd89dbbbaf8da66bdcba45de6138fd237810365a04606a","title":"Test dependency parent","description":"","status":"closed","priority":2,"issue_type":"task","created_at":"2025-11-05T11:23:02.505901-08:00","updated_at":"2025-11-05T11:23:20.91305-08:00","closed_at":"2025-11-05T11:23:20.91305-08:00","source_repo":"."}

11
cmd/bd/daemon_lifecycle.go
View File

@@ -117,7 +117,16 @@ func showDaemonHealth(global bool) {
}
if client == nil {
fmt.Println("Daemon is not running")
// Check if lock is held to provide better diagnostic message
beadsDir := filepath.Dir(socketPath)
running, _ := tryDaemonLock(beadsDir)
if running {
fmt.Println("Daemon lock is held but connection failed")
fmt.Println("This may indicate a crashed daemon. Try: bd daemons killall")
} else {
fmt.Println("Daemon is not running")
fmt.Println("Start with: bd daemon start")
}
os.Exit(1)
}
defer func() { _ = client.Close() }()

37
internal/rpc/client.go
View File

@@ -13,6 +13,19 @@ import (
"github.com/steveyegge/beads/internal/lockfile"
)
// rpcDebugEnabled returns true if BD_RPC_DEBUG environment variable is set
func rpcDebugEnabled() bool {
val := os.Getenv("BD_RPC_DEBUG")
return val == "1" || val == "true"
}
// rpcDebugLog logs to stderr if BD_RPC_DEBUG is enabled
func rpcDebugLog(format string, args ...interface{}) {
if rpcDebugEnabled() {
fmt.Fprintf(os.Stderr, "[RPC DEBUG] "+format+"\n", args...)
}
}
// ClientVersion is the version of this RPC client
// This should match the bd CLI version for proper compatibility checks
// It's set dynamically by main.go from cmd/bd/version.go before making RPC calls
@@ -35,35 +48,49 @@ func TryConnect(socketPath string) (*Client, error) {
// TryConnectWithTimeout attempts to connect to the daemon socket using the provided dial timeout.
// Returns nil if no daemon is running or unhealthy.
func TryConnectWithTimeout(socketPath string, dialTimeout time.Duration) (*Client, error) {
rpcDebugLog("attempting connection to socket: %s", socketPath)
// Fast probe: check daemon lock before attempting RPC connection if socket doesn't exist
// This eliminates unnecessary connection attempts when no daemon is running
// If socket exists, we skip lock check for backwards compatibility and test scenarios
socketExists := endpointExists(socketPath)
rpcDebugLog("socket exists check: %v", socketExists)
if !socketExists {
beadsDir := filepath.Dir(socketPath)
running, _ := lockfile.TryDaemonLock(beadsDir)
if !running {
debug.Logf("daemon lock not held and socket missing (no daemon running)")
rpcDebugLog("daemon lock not held (no daemon running)")
// Self-heal: clean up stale artifacts when lock is free and socket is missing
cleanupStaleDaemonArtifacts(beadsDir)
return nil, nil
}
rpcDebugLog("daemon lock held but socket missing (race or cleanup issue)")
}
if !socketExists {
debug.Logf("RPC endpoint does not exist: %s", socketPath)
rpcDebugLog("connection aborted: socket does not exist")
return nil, nil
}
if dialTimeout <= 0 {
dialTimeout = 200 * time.Millisecond
}
rpcDebugLog("dialing socket (timeout: %v)", dialTimeout)
dialStart := time.Now()
conn, err := dialRPC(socketPath, dialTimeout)
dialDuration := time.Since(dialStart)
if err != nil {
debug.Logf("failed to connect to RPC endpoint: %v", err)
rpcDebugLog("dial failed after %v: %v", dialDuration, err)
return nil, nil
}
rpcDebugLog("dial succeeded in %v", dialDuration)
client := &Client{
conn: conn,
@@ -71,21 +98,29 @@ func TryConnectWithTimeout(socketPath string, dialTimeout time.Duration) (*Clien
timeout: 30 * time.Second,
}
rpcDebugLog("performing health check")
healthStart := time.Now()
health, err := client.Health()
healthDuration := time.Since(healthStart)
if err != nil {
debug.Logf("health check failed: %v", err)
rpcDebugLog("health check failed after %v: %v", healthDuration, err)
_ = conn.Close()
return nil, nil
}
if health.Status == "unhealthy" {
debug.Logf("daemon unhealthy: %s", health.Error)
rpcDebugLog("daemon unhealthy (checked in %v): %s", healthDuration, health.Error)
_ = conn.Close()
return nil, nil
}
debug.Logf("connected to daemon (status: %s, uptime: %.1fs)",
health.Status, health.Uptime)
rpcDebugLog("connection successful (health check: %v, status: %s, uptime: %.1fs)",
healthDuration, health.Status, health.Uptime)
return client, nil
}