CUB-200: fix WS initial sync ordering — start readLoop before initialSync
Some checks failed
Dev Build & Deploy / test-and-build (pull_request) Failing after 0s
Dev Build & Deploy / docker-build-push (pull_request) Has been skipped

The root cause of the initial sync timeout was that connectAndRun called
initialSync (which uses Send/RPC) before starting readLoop, but Send's
response delivery depends on readLoop→routeFrame→handleResponse. Without
the readLoop running, agents.list and sessions.list would always time out.

Fix: start readLoop in a goroutine before calling initialSync so that
RPC responses are properly routed back to pending Send() calls. After
initialSync completes, event handlers are registered and MarkWSReady
is called. The connectAndRun function then blocks on the readLoop
goroutine's completion.

Also added TestConnectAndRun_InitialSyncOrdering which verifies that
agents are persisted from initial sync (would hang/timeout under the
old ordering).
This commit is contained in:
2026-05-20 21:42:31 +00:00
parent 1b82e1d3a6
commit d370d5ec23
2 changed files with 125 additions and 11 deletions

View File

@@ -11,6 +11,7 @@ import (
"testing"
"time"
"code.cubecraftcreations.com/CubeCraft-Creations/Control-Center/go-backend/internal/handler"
"code.cubecraftcreations.com/CubeCraft-Creations/Control-Center/go-backend/internal/models"
"github.com/gorilla/websocket"
@@ -466,6 +467,104 @@ func TestAgentItemToCard(t *testing.T) {
})
}
// ── 6. Test: Initial sync ordering (readLoop active before Send) ──────────
// TestConnectAndRun_InitialSyncOrdering verifies that the WS client
// completes initial sync successfully. This test would hang/timeout if
// readLoop were NOT started before initialSync, because Send() relies on
// readLoop→routeFrame→handleResponse to deliver RPC responses.
func TestConnectAndRun_InitialSyncOrdering(t *testing.T) {
repo := &mockAgentRepo{agents: make(map[string]models.AgentCardData)}
broker := handler.NewBroker()
capture := newBroadcastCapture(broker)
defer capture.close()
srv := newTestWSServer(t, func(conn *websocket.Conn) {
// Handshake
handleHandshake(t, conn)
// After handshake, respond to RPCs
for {
var req map[string]any
if err := conn.ReadJSON(&req); err != nil {
break
}
reqID, _ := req["id"].(string)
method, _ := req["method"].(string)
var result any
switch method {
case "agents.list":
result = []map[string]any{
{"id": "otto", "name": "Otto", "role": "Orchestrator", "channel": "discord"},
{"id": "dex", "name": "Dex", "role": "Backend Dev", "channel": "telegram"},
}
case "sessions.list":
result = []map[string]any{
{"sessionKey": "s1", "agentId": "otto", "status": "running", "totalTokens": 500, "lastActivityAt": "2025-05-20T12:00:00Z"},
}
default:
result = map[string]any{}
}
res := map[string]any{
"type": "res",
"id": reqID,
"ok": true,
"result": result,
}
if err := conn.WriteJSON(res); err != nil {
break
}
}
})
defer srv.Close()
client := NewWSClient(WSConfig{URL: wsURL(srv), AuthToken: "test-token"}, repo, broker, slog.Default())
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
defer cancel()
done := make(chan struct{})
go func() {
client.Start(ctx)
close(done)
}()
// Wait for initial sync to complete by checking repo state.
// The agents should be persisted from the RPC responses.
deadline := time.Now().Add(5 * time.Second)
for time.Now().Before(deadline) {
repo.mu.Lock()
_, ottoOK := repo.agents["otto"]
_, dexOK := repo.agents["dex"]
repo.mu.Unlock()
if ottoOK && dexOK {
break
}
time.Sleep(50 * time.Millisecond)
}
repo.mu.Lock()
_, ottoOK := repo.agents["otto"]
_, dexOK := repo.agents["dex"]
repo.mu.Unlock()
if !ottoOK {
t.Error("otto not found in repo after initial sync — readLoop may not have been active before Send()")
}
if !dexOK {
t.Error("dex not found in repo after initial sync — readLoop may not have been active before Send()")
}
cancel()
select {
case <-done:
case <-time.After(3 * time.Second):
t.Fatal("WSClient did not shut down cleanly")
}
}
func TestStrPtr(t *testing.T) {
s := "hello"
p := strPtr(s)