fix: EventBus panic on SSE disconnect + JWT secret persistence + recover() guards

- eventbus.go: Fix send-on-closed-channel panic in SubscribeGlobal by
  using a done channel; add recover() in fan-out goroutine; track active
  global subs for proper cleanup on unsubscribe
- config.go: Persist JWT secret to $DATA_DIR/.jwt_secret instead of
  regenerating a random one on every restart (which invalidated all sessions)
- handlers_ws.go: Replace time.After with time.Ticker to fix timer leak in
  SSE keepalive loop
- handlers_jobs.go: Add recover() in fire-and-forget job goroutine; fix nil
  pointer deref when GetByID fails after job creation
- handlers_machines.go: Add recover() in ProbeAllMachines goroutine
- scheduler.go: Add recover() in scheduled job run goroutine
- engine.go: Add recover() in per-machine probe goroutines
This commit is contained in:
2026-07-08 22:38:56 -04:00
parent 1798fc6804
commit 58e7f51ba7
7 changed files with 89 additions and 20 deletions
+11 -1
View File
@@ -4,6 +4,7 @@ import (
"database/sql"
"encoding/json"
"fmt"
"log/slog"
"net/http"
"os"
"strconv"
@@ -150,11 +151,20 @@ func (h *JobHandler) TriggerRun(w http.ResponseWriter, r *http.Request) {
}
go func() {
defer func() {
if r := recover(); r != nil {
slog.Error("job run goroutine panicked", "job_id", jobID, "panic", r)
}
}()
h.engine.Run(r.Context(), jobID, pairID)
}()
jobRepo := models.NewJobRepository(h.db)
j, _ := jobRepo.GetByID(jobID)
j, err := jobRepo.GetByID(jobID)
if err != nil {
writeError(w, http.StatusInternalServerError, "failed to fetch created job")
return
}
writeJSON(w, jobToResp(*j), http.StatusCreated)
}