mirror of
https://github.com/multica-ai/multica.git
synced 2026-07-06 22:09:44 +02:00
* feat(server): funnel/community/commercial business metrics + PostHog pairing (MUL-2949) PR3 of the Grafana board metrics split (parent MUL-2328). Adds 23 new Prometheus counter/histogram families to the PR2 BusinessMetrics collector covering the activation/community/commercial funnels, and binds every PostHog event emission to a matching metric increment so the two sides cannot drift. Funnel: signup, workspace_created, team_invite_sent/accepted, onboarding_*, cloud_waitlist_joined. Content: issue_created, chat_message_sent, agent_created, squad_created, autopilot_created, issue_executed. Runtime: runtime_registered/ready/failed/offline + ready_seconds histogram, daemon_ws_message_received_total. Autopilot: autopilot_run_started/terminal/skipped. Webhook/GitHub: webhook_delivery_total, github_event_received_total, github_pr_review_total, github_pr_merge_seconds histogram. CloudRuntime: cloudruntime_request_total + duration histogram, wired through a small RequestRecorder interface so the cloudruntime package stays decoupled from metrics. Commercial: feedback_submitted, contact_sales_submitted. The pairing helper metrics.RecordEvent(client, m, ev) emits the PostHog event AND increments the matching counter via IncForEvent dispatch, reading labels from the analytics event Properties. Every existing h.Analytics.Capture(analytics.X(...)) call site has been migrated to the helper across handler/, service/, and cmd/server/runtime_sweeper.go. Lint enforcement (server/internal/metrics/business_pairing_test.go): - TestEveryAnalyticsEventHasPrometheusCounter: every Event* constant in analytics/events.go either dispatches via IncForEvent or is in the taskMetricEvents allow-list (PR2 typed RecordTask* methods). - TestNoNakedAnalyticsCaptureInHandlersOrServices: AST-walks handler/ service/cmd-server for direct Analytics.Capture(...) calls — only service/task.go's captureTaskEvent helper is allow-listed. - TestEveryAnalyticsRecordEventTakesAnalyticsHelper: validates the third arg of every metrics.RecordEvent call is built from analytics.*. Cardinality protection: all new label values pass through fixed allow-lists in labels_pr3.go; unknown values collapse to 'other'/'unknown'/'error'. Refs: - Spec MUL-2328 / MUL-2949. - Builds on PR2 (MUL-2948) — collectors registered through the same BusinessMetrics struct, no separate Registry. - Uses PR1's taskfailure.Reason (MUL-2946) for runtime_failed's failure_reason label via NormalizeFailureReason. Out of scope: Sampler-class metrics (PR4 / MUL-2947), pr_review_total emission point (no review event handler exists yet — counter is defined, TODO to wire up when /api/webhooks/github grows pull_request_review handling). Co-authored-by: multica-agent <github@multica.ai> * fix(server): tighten PR3 review items — signup_source bucket, fill platform/kind/form_source enums, onboarding_started server emission, lint scope (MUL-2949) Addresses 张大彪's review on #3698: 1. signup_source: NormalizeSignupSource added to labels_pr3.go with a fixed allow-list bucket (direct/google/twitter/linkedin/.../other). Parses JSON cookie payload for utm_source/source/referrer fields, strips URL schemes, maps well-known hostnames to channel buckets. PostHog event still ships the raw cookie value for analytics; only the Prometheus label is bucketed. 2. Filled the unknown/other label gaps: - analytics.IssueCreated and analytics.ChatMessageSent now take a platform parameter sourced from middleware.ClientMetadataFromContext (X-Client-Platform header) at the handler. Autopilot-originated issues stamp PlatformServer. - analytics.FeedbackSubmitted now takes a kind parameter; CreateFeedback reads req.Kind (default "general") so the picker selection lights up the metric's kind label instead of long-term "other". - analytics.ContactSalesSubmitted now takes a formSource (page / onboarding / agents_page); CreateContactSales reads req.Source. The metric reads ev.Properties["form_source"] so the analytics CoreProperties.Source ("marketing_contact_sales") stays backward-compat for PostHog dashboards. 3. analytics.OnboardingStarted helper added; server-side emission lives in PatchOnboarding, fired exactly once per user on the first PATCH that carries a non-empty questionnaire payload (firstTouch logic compares prior bytes against {} / null). Frontend onboarding_started keeps firing on page open; the server emission is what guarantees the Prometheus counter exists so Grafana can be cross-checked against the PostHog funnel without depending on the SDK roundtrip. 4. business_pairing_test.go tightened: - TestNoNakedAnalyticsCaptureInHandlersOrServices now allow-lists at function granularity (just captureTaskEvent in service/task.go), not whole-file. Any future naked Capture in the same file fails CI. - TestEveryAnalyticsRecordEventTakesAnalyticsHelper now does def-use tracking inside the enclosing FuncDecl: when RecordEvent's third arg is an *ast.Ident, the test walks the function body for the assignment that defined it and confirms the RHS is an analytics.<Helper>(...) call. Bare local idents that didn't originate from analytics are now caught. 5. gofmt -w applied across the touched files; gofmt -l clean. Tests: go test ./internal/metrics/... ./internal/analytics/... pass. Pre-existing TestClaimTask_/TestWebhook_MergedPR/TestDeleteIssueByIdentifier failures on origin/main are DB-environment-dependent and not regressions from this change. Co-authored-by: multica-agent <github@multica.ai> * fix(server): normalise onboarding_started platform label + regression test (MUL-2949) Addresses 张大彪's last review nit: - IncForEvent's EventOnboardingStarted case now wraps the platform property with NormalizePlatform, matching every other platform-bearing metric. A misbehaving frontend can no longer leak a raw X-Client-Platform header value into the multica_onboarding_started_total{platform=...} series. - New labels_pr3_test.go covers every PR3 normalizer with both a happy-path value and an unknown value, asserting the unknown collapses to the documented fallback bucket. Includes a focused regression for onboarding_started: emits one event with an attacker-shaped platform string and asserts the metric only exposes web + unknown label values (no raw header bleed). - testutil.go gains a small GatherForTest helper so the regression test can pull the typed MetricFamily map without re-implementing the registry-walk dance. Co-authored-by: multica-agent <github@multica.ai> * fix(server): NormalizeTaskSource on workspace_created + document lint limitations (MUL-2949) Final review touch-ups before merge: - IncForEvent's EventWorkspaceCreated case wraps source through NormalizeTaskSource, matching the other source-bearing dispatches (issue_created, agent_created, issue_executed). Closes the last raw property leak in the dispatcher table. - business_pairing_test.go inline docstrings now spell out the two known limitations of the lint gate that 张大彪 / Eve flagged: analyticsBackedIdents matches by ident NAME (not SSA def-use, so a nested-scope shadow could pass) and isMetricsRecordEvent hard-codes the import alias set. PR description carries a Follow-ups section with the same two items so the work is visible after merge. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: 魏和尚 <agent+wei@multica.ai> Co-authored-by: multica-agent <github@multica.ai>
492 lines
13 KiB
Go
492 lines
13 KiB
Go
package daemonws
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"log/slog"
|
|
"net/http"
|
|
"strings"
|
|
"sync"
|
|
"time"
|
|
|
|
"github.com/gorilla/websocket"
|
|
"github.com/multica-ai/multica/server/pkg/protocol"
|
|
)
|
|
|
|
const (
|
|
writeWait = 10 * time.Second
|
|
pongWait = 60 * time.Second
|
|
pingPeriod = (pongWait * 9) / 10
|
|
)
|
|
|
|
// ClientIdentity captures the already-authenticated daemon connection scope.
|
|
type ClientIdentity struct {
|
|
DaemonID string
|
|
UserID string
|
|
WorkspaceID string
|
|
RuntimeIDs []string
|
|
ClientVersion string
|
|
}
|
|
|
|
type client struct {
|
|
hub *Hub
|
|
conn *websocket.Conn
|
|
send chan []byte
|
|
identity ClientIdentity
|
|
runtimes map[string]struct{}
|
|
|
|
dedupMu sync.Mutex
|
|
seenIDs map[string]struct{}
|
|
seenList []string
|
|
}
|
|
|
|
const eventDedupCapacity = 128
|
|
|
|
// markSeen records eventID as already delivered to this client. Empty event IDs
|
|
// disable dedup and are always delivered.
|
|
func (c *client) markSeen(eventID string) bool {
|
|
if eventID == "" {
|
|
return true
|
|
}
|
|
c.dedupMu.Lock()
|
|
defer c.dedupMu.Unlock()
|
|
if c.seenIDs == nil {
|
|
c.seenIDs = make(map[string]struct{}, eventDedupCapacity)
|
|
}
|
|
if _, ok := c.seenIDs[eventID]; ok {
|
|
return false
|
|
}
|
|
c.seenIDs[eventID] = struct{}{}
|
|
c.seenList = append(c.seenList, eventID)
|
|
if len(c.seenList) > eventDedupCapacity {
|
|
drop := c.seenList[0]
|
|
c.seenList = c.seenList[1:]
|
|
delete(c.seenIDs, drop)
|
|
}
|
|
return true
|
|
}
|
|
|
|
// HeartbeatHandler processes a daemon:heartbeat frame. It must verify that
|
|
// runtimeID is one of identity.RuntimeIDs (the connection's authenticated
|
|
// scope) and return the ack payload to send back. Returning an error skips
|
|
// the ack and is logged at debug level.
|
|
type HeartbeatHandler func(ctx context.Context, identity ClientIdentity, runtimeID string, supportsBatchImport bool) (*protocol.DaemonHeartbeatAckPayload, error)
|
|
|
|
// MessageKindRecorder is the optional metric hook called once per inbound
|
|
// daemon WebSocket frame. kind is the protocol message type with the
|
|
// "daemon:" prefix stripped (e.g. "heartbeat") or the literal "unknown" for
|
|
// types we don't model. A nil recorder is safely no-op'd.
|
|
type MessageKindRecorder interface {
|
|
RecordDaemonWSMessageReceived(kind string)
|
|
}
|
|
|
|
// Hub keeps daemon WebSocket connections indexed by runtime ID. Messages are
|
|
// best-effort wakeup hints; the daemon still uses HTTP claim for correctness.
|
|
type Hub struct {
|
|
upgrader websocket.Upgrader
|
|
|
|
mu sync.RWMutex
|
|
clients map[*client]bool
|
|
byRuntime map[string]map[*client]bool
|
|
|
|
hbMu sync.RWMutex
|
|
onHeartbeat HeartbeatHandler
|
|
|
|
kindMu sync.RWMutex
|
|
kindRecorder MessageKindRecorder
|
|
}
|
|
|
|
func NewHub() *Hub {
|
|
return &Hub{
|
|
upgrader: websocket.Upgrader{
|
|
// Daemon clients authenticate with Authorization headers before the
|
|
// upgrade. Browsers cannot set those headers through the native WS API,
|
|
// and DaemonAuth does not accept cookies, so cookie-based CSWSH does
|
|
// not apply to this endpoint. Re-evaluate this if DaemonAuth ever
|
|
// grows cookie fallback.
|
|
CheckOrigin: func(r *http.Request) bool { return true },
|
|
},
|
|
clients: make(map[*client]bool),
|
|
byRuntime: make(map[string]map[*client]bool),
|
|
}
|
|
}
|
|
|
|
// SetHeartbeatHandler installs the callback used for daemon:heartbeat frames.
|
|
// Wiring is done after handler construction because the handler depends on
|
|
// DB queries that aren't available when the hub is built. A nil handler
|
|
// disables WS heartbeat processing — daemons fall back to HTTP heartbeat
|
|
// transparently because their fallback timer fires whenever no ack arrives.
|
|
func (h *Hub) SetHeartbeatHandler(fn HeartbeatHandler) {
|
|
if h == nil {
|
|
return
|
|
}
|
|
h.hbMu.Lock()
|
|
h.onHeartbeat = fn
|
|
h.hbMu.Unlock()
|
|
}
|
|
|
|
func (h *Hub) heartbeatHandler() HeartbeatHandler {
|
|
h.hbMu.RLock()
|
|
defer h.hbMu.RUnlock()
|
|
return h.onHeartbeat
|
|
}
|
|
|
|
// SetMessageKindRecorder installs an optional callback fired exactly once per
|
|
// inbound daemon WebSocket frame. Used by the metrics layer to count traffic
|
|
// by handler kind without hard-coupling the hub to any specific collector.
|
|
func (h *Hub) SetMessageKindRecorder(rec MessageKindRecorder) {
|
|
if h == nil {
|
|
return
|
|
}
|
|
h.kindMu.Lock()
|
|
h.kindRecorder = rec
|
|
h.kindMu.Unlock()
|
|
}
|
|
|
|
func (h *Hub) messageKindRecorder() MessageKindRecorder {
|
|
if h == nil {
|
|
return nil
|
|
}
|
|
h.kindMu.RLock()
|
|
defer h.kindMu.RUnlock()
|
|
return h.kindRecorder
|
|
}
|
|
|
|
func (h *Hub) HandleWebSocket(w http.ResponseWriter, r *http.Request, identity ClientIdentity) {
|
|
if len(identity.RuntimeIDs) == 0 {
|
|
http.Error(w, `{"error":"runtime_ids required"}`, http.StatusBadRequest)
|
|
return
|
|
}
|
|
|
|
conn, err := h.upgrader.Upgrade(w, r, nil)
|
|
if err != nil {
|
|
slog.Error("daemon websocket upgrade failed", "error", err)
|
|
return
|
|
}
|
|
|
|
runtimes := make(map[string]struct{}, len(identity.RuntimeIDs))
|
|
for _, runtimeID := range identity.RuntimeIDs {
|
|
if runtimeID != "" {
|
|
runtimes[runtimeID] = struct{}{}
|
|
}
|
|
}
|
|
if len(runtimes) == 0 {
|
|
conn.WriteMessage(websocket.TextMessage, []byte(`{"error":"runtime_ids required"}`))
|
|
conn.Close()
|
|
return
|
|
}
|
|
|
|
c := &client{
|
|
hub: h,
|
|
conn: conn,
|
|
send: make(chan []byte, 16),
|
|
identity: identity,
|
|
runtimes: runtimes,
|
|
}
|
|
h.register(c)
|
|
|
|
go c.writePump()
|
|
go c.readPump()
|
|
}
|
|
|
|
// NotifyTaskAvailable sends a best-effort wakeup to daemons watching runtimeID.
|
|
func (h *Hub) NotifyTaskAvailable(runtimeID, taskID string) {
|
|
h.notifyTaskAvailable(runtimeID, taskID, "")
|
|
}
|
|
|
|
func (h *Hub) notifyTaskAvailable(runtimeID, taskID, eventID string) {
|
|
if h == nil || runtimeID == "" {
|
|
return
|
|
}
|
|
data, err := taskAvailableFrame(runtimeID, taskID)
|
|
if err != nil {
|
|
return
|
|
}
|
|
delivered, deduped := h.notifyFrame(runtimeID, data, eventID)
|
|
if delivered {
|
|
M.WakeupDeliveredHit.Add(1)
|
|
} else if !deduped {
|
|
M.WakeupDeliveredMiss.Add(1)
|
|
}
|
|
}
|
|
|
|
func (h *Hub) DeliverDaemonRuntime(scopeID string, frame []byte, eventID string) {
|
|
if h == nil {
|
|
return
|
|
}
|
|
M.WakeupReceivedTotal.Add(1)
|
|
var msg protocol.Message
|
|
if err := json.Unmarshal(frame, &msg); err != nil {
|
|
slog.Debug("daemon websocket relay: invalid frame", "error", err, "scope_id", scopeID, "event_id", eventID)
|
|
M.WakeupDeliveredMiss.Add(1)
|
|
return
|
|
}
|
|
if msg.Type != protocol.EventDaemonTaskAvailable {
|
|
M.WakeupDeliveredMiss.Add(1)
|
|
return
|
|
}
|
|
var payload protocol.TaskAvailablePayload
|
|
if err := json.Unmarshal(msg.Payload, &payload); err != nil || payload.RuntimeID == "" {
|
|
slog.Debug("daemon websocket relay: invalid task_available payload", "error", err, "scope_id", scopeID, "event_id", eventID)
|
|
M.WakeupDeliveredMiss.Add(1)
|
|
return
|
|
}
|
|
delivered, deduped := h.notifyFrame(payload.RuntimeID, frame, eventID)
|
|
if delivered {
|
|
M.WakeupDeliveredHit.Add(1)
|
|
} else if !deduped {
|
|
M.WakeupDeliveredMiss.Add(1)
|
|
}
|
|
}
|
|
|
|
func (h *Hub) notifyFrame(runtimeID string, data []byte, eventID string) (delivered bool, deduped bool) {
|
|
h.mu.RLock()
|
|
clients := h.byRuntime[runtimeID]
|
|
slow := make([]*client, 0)
|
|
for c := range clients {
|
|
if !c.markSeen(eventID) {
|
|
deduped = true
|
|
continue
|
|
}
|
|
select {
|
|
case c.send <- data:
|
|
delivered = true
|
|
default:
|
|
slow = append(slow, c)
|
|
}
|
|
}
|
|
h.mu.RUnlock()
|
|
|
|
for _, c := range slow {
|
|
h.unregister(c)
|
|
c.conn.Close()
|
|
}
|
|
if len(slow) > 0 {
|
|
M.SlowEvictionsTotal.Add(int64(len(slow)))
|
|
}
|
|
return delivered, deduped
|
|
}
|
|
|
|
func taskAvailableFrame(runtimeID, taskID string) ([]byte, error) {
|
|
return json.Marshal(protocol.Message{
|
|
Type: protocol.EventDaemonTaskAvailable,
|
|
Payload: mustMarshalRaw(protocol.TaskAvailablePayload{
|
|
RuntimeID: runtimeID,
|
|
TaskID: taskID,
|
|
}),
|
|
})
|
|
}
|
|
|
|
func mustMarshalRaw(v any) json.RawMessage {
|
|
data, err := json.Marshal(v)
|
|
if err != nil {
|
|
return nil
|
|
}
|
|
return data
|
|
}
|
|
|
|
func (h *Hub) RuntimeConnectionCount(runtimeID string) int {
|
|
h.mu.RLock()
|
|
defer h.mu.RUnlock()
|
|
return len(h.byRuntime[runtimeID])
|
|
}
|
|
|
|
func (h *Hub) register(c *client) {
|
|
h.mu.Lock()
|
|
h.clients[c] = true
|
|
for runtimeID := range c.runtimes {
|
|
conns := h.byRuntime[runtimeID]
|
|
if conns == nil {
|
|
conns = make(map[*client]bool)
|
|
h.byRuntime[runtimeID] = conns
|
|
}
|
|
conns[c] = true
|
|
}
|
|
total := len(h.clients)
|
|
h.mu.Unlock()
|
|
|
|
M.ConnectsTotal.Add(1)
|
|
M.ActiveConnections.Add(1)
|
|
slog.Info("daemon websocket connected",
|
|
"daemon_id", c.identity.DaemonID,
|
|
"user_id", c.identity.UserID,
|
|
"workspace_id", c.identity.WorkspaceID,
|
|
"runtimes", len(c.runtimes),
|
|
"client_version", c.identity.ClientVersion,
|
|
"total_clients", total,
|
|
)
|
|
}
|
|
|
|
func (h *Hub) unregister(c *client) {
|
|
h.mu.Lock()
|
|
if !h.clients[c] {
|
|
h.mu.Unlock()
|
|
return
|
|
}
|
|
delete(h.clients, c)
|
|
for runtimeID := range c.runtimes {
|
|
if conns := h.byRuntime[runtimeID]; conns != nil {
|
|
delete(conns, c)
|
|
if len(conns) == 0 {
|
|
delete(h.byRuntime, runtimeID)
|
|
}
|
|
}
|
|
}
|
|
close(c.send)
|
|
total := len(h.clients)
|
|
h.mu.Unlock()
|
|
|
|
M.DisconnectsTotal.Add(1)
|
|
M.ActiveConnections.Add(-1)
|
|
slog.Info("daemon websocket disconnected",
|
|
"daemon_id", c.identity.DaemonID,
|
|
"user_id", c.identity.UserID,
|
|
"workspace_id", c.identity.WorkspaceID,
|
|
"runtimes", len(c.runtimes),
|
|
"total_clients", total,
|
|
)
|
|
}
|
|
|
|
func (c *client) readPump() {
|
|
defer func() {
|
|
c.hub.unregister(c)
|
|
c.conn.Close()
|
|
}()
|
|
|
|
c.conn.SetReadLimit(4096)
|
|
c.conn.SetReadDeadline(time.Now().Add(pongWait))
|
|
c.conn.SetPongHandler(func(string) error {
|
|
c.conn.SetReadDeadline(time.Now().Add(pongWait))
|
|
return nil
|
|
})
|
|
|
|
for {
|
|
_, raw, err := c.conn.ReadMessage()
|
|
if err != nil {
|
|
if websocket.IsUnexpectedCloseError(err, websocket.CloseGoingAway, websocket.CloseNormalClosure) {
|
|
slog.Debug("daemon websocket read error", "error", err, "daemon_id", c.identity.DaemonID)
|
|
}
|
|
return
|
|
}
|
|
c.handleFrame(raw)
|
|
}
|
|
}
|
|
|
|
func (c *client) handleFrame(raw []byte) {
|
|
var msg protocol.Message
|
|
if err := json.Unmarshal(raw, &msg); err != nil {
|
|
slog.Debug("daemon websocket invalid frame", "error", err, "daemon_id", c.identity.DaemonID)
|
|
if rec := c.hub.messageKindRecorder(); rec != nil {
|
|
rec.RecordDaemonWSMessageReceived("invalid")
|
|
}
|
|
return
|
|
}
|
|
kind := strings.TrimPrefix(msg.Type, "daemon:")
|
|
if kind == "" {
|
|
kind = "unknown"
|
|
}
|
|
if rec := c.hub.messageKindRecorder(); rec != nil {
|
|
rec.RecordDaemonWSMessageReceived(kind)
|
|
}
|
|
switch msg.Type {
|
|
case protocol.EventDaemonHeartbeat:
|
|
c.handleHeartbeatFrame(msg.Payload)
|
|
default:
|
|
// Unknown app messages are intentionally ignored for forward
|
|
// compatibility with future daemon → server message types.
|
|
}
|
|
}
|
|
|
|
// handleHeartbeatFrame processes an inbound daemon:heartbeat from the daemon,
|
|
// invokes the hub's handler, and writes back a daemon:heartbeat_ack.
|
|
func (c *client) handleHeartbeatFrame(raw json.RawMessage) {
|
|
handler := c.hub.heartbeatHandler()
|
|
if handler == nil {
|
|
// Server doesn't have a heartbeat handler wired — daemon will time
|
|
// out waiting for an ack and fall back to HTTP heartbeat.
|
|
return
|
|
}
|
|
|
|
var payload protocol.DaemonHeartbeatRequestPayload
|
|
if err := json.Unmarshal(raw, &payload); err != nil {
|
|
slog.Debug("daemon websocket heartbeat invalid payload", "error", err, "daemon_id", c.identity.DaemonID)
|
|
return
|
|
}
|
|
if payload.RuntimeID == "" {
|
|
slog.Debug("daemon websocket heartbeat missing runtime_id", "daemon_id", c.identity.DaemonID)
|
|
return
|
|
}
|
|
if _, ok := c.runtimes[payload.RuntimeID]; !ok {
|
|
// The connection authenticated for a fixed runtime set; reject any
|
|
// heartbeat for a runtime the client did not register for.
|
|
slog.Warn("daemon websocket heartbeat for unauthorized runtime",
|
|
"daemon_id", c.identity.DaemonID,
|
|
"runtime_id", payload.RuntimeID)
|
|
return
|
|
}
|
|
|
|
// Intentionally do NOT wrap this ctx with WithTimeout. The handler
|
|
// reaches LocalSkill{List,Import}Store.PopPending, whose Redis Lua
|
|
// claim script has side effects (ZREM + SET-running) that cannot be
|
|
// safely un-run if the client cancels mid-script — the same invariant
|
|
// that keeps the HTTP heartbeat from putting a per-call timeout on
|
|
// PopPending. The natural bound is the read pump's lifetime (the conn
|
|
// closes if the daemon goes away) plus Redis's own server-side limits.
|
|
ack, err := handler(context.Background(), c.identity, payload.RuntimeID, payload.SupportsBatchImport)
|
|
if err != nil {
|
|
slog.Warn("daemon websocket heartbeat handler failed",
|
|
"error", err,
|
|
"daemon_id", c.identity.DaemonID,
|
|
"runtime_id", payload.RuntimeID)
|
|
return
|
|
}
|
|
if ack == nil {
|
|
return
|
|
}
|
|
frame, err := json.Marshal(protocol.Message{
|
|
Type: protocol.EventDaemonHeartbeatAck,
|
|
Payload: mustMarshalRaw(ack),
|
|
})
|
|
if err != nil {
|
|
slog.Debug("daemon websocket heartbeat ack marshal failed", "error", err)
|
|
return
|
|
}
|
|
select {
|
|
case c.send <- frame:
|
|
default:
|
|
// Send buffer is full — slow client. Don't block the read pump; the
|
|
// next writePump tick or notifyFrame eviction will clean up.
|
|
slog.Debug("daemon websocket heartbeat ack dropped: send buffer full",
|
|
"daemon_id", c.identity.DaemonID,
|
|
"runtime_id", payload.RuntimeID)
|
|
}
|
|
}
|
|
|
|
func (c *client) writePump() {
|
|
ticker := time.NewTicker(pingPeriod)
|
|
defer func() {
|
|
ticker.Stop()
|
|
c.conn.Close()
|
|
}()
|
|
|
|
for {
|
|
select {
|
|
case message, ok := <-c.send:
|
|
c.conn.SetWriteDeadline(time.Now().Add(writeWait))
|
|
if !ok {
|
|
c.conn.WriteMessage(websocket.CloseMessage, []byte{})
|
|
return
|
|
}
|
|
if err := c.conn.WriteMessage(websocket.TextMessage, message); err != nil {
|
|
slog.Debug("daemon websocket write error", "error", err, "daemon_id", c.identity.DaemonID)
|
|
return
|
|
}
|
|
case <-ticker.C:
|
|
c.conn.SetWriteDeadline(time.Now().Add(writeWait))
|
|
if err := c.conn.WriteMessage(websocket.PingMessage, nil); err != nil {
|
|
return
|
|
}
|
|
}
|
|
}
|
|
}
|