feat(network): SSE optimization for local LLM streaming (#31 #32 #33) (#26)
CI / CI (push) Successful in 3m35s
CI / CI (push) Successful in 3m35s
Addresses three critical network issues for LLM streaming performance: **#33 Disable proxy buffering for SSE** - Add X-Accel-Buffering: no header to response - Tells nginx/Ingress to stream events immediately instead of buffering **#32 HTTP/2 multiplexing for concurrent streams** - Enable HTTP/2 in server config via http2.ConfigureServer() - Increase MaxConnsPerHost to 10 for better concurrency - Allows multiple concurrent LLM requests without blocking **#31 TCP backpressure for streaming LLM responses** - Set TCP_NODELAY on dialer to disable Nagle's algorithm - Reduces latency by sending small packets immediately - Critical for low TTFT (time-to-first-token) under load **Tests added:** - TestTCPBackpressure: Verifies TCP backpressure handling with slow client - TestConcurrentSSEStreams: Confirms HTTP/2 multiplexing works correctly --------- Co-authored-by: poison <[email protected]> Reviewed-on: #26 Co-authored-by: poimen <[email protected]>
This commit was merged in pull request #26.
This commit is contained in:
@@ -0,0 +1,160 @@
|
||||
package notification
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"log"
|
||||
"net/http"
|
||||
"net/smtp"
|
||||
"os"
|
||||
)
|
||||
|
||||
// SendMsgRequest represents a sendMsg API request.
|
||||
type SendMsgRequest struct {
|
||||
Format string `json:"format"` // "smtp" or "sms"
|
||||
Title string `json:"title"`
|
||||
Message string `json:"message"`
|
||||
Priority int `json:"priority,omitempty"`
|
||||
Extras map[string]string `json:"extras,omitempty"` // e.g., {"to_email": "[email protected]", "phone": "+1234567890"}
|
||||
}
|
||||
|
||||
// SendMsgResponse represents a sendMsg API response.
|
||||
type SendMsgResponse struct {
|
||||
Status string `json:"status"`
|
||||
MessageID string `json:"messageId,omitempty"`
|
||||
Error string `json:"error,omitempty"`
|
||||
}
|
||||
|
||||
// Handler handles sendMsg requests and forwards to appropriate channel (email, SMS, or Gotify push).
|
||||
type Handler struct {
|
||||
smtpHost string
|
||||
smtpPort string
|
||||
smtpFrom string
|
||||
smtpUser string
|
||||
smtpPass string
|
||||
smsAPIURL string
|
||||
smsAPIKey string
|
||||
gotifyURL string
|
||||
gotifyToken string
|
||||
}
|
||||
|
||||
// NewHandler creates a new notification handler from environment variables.
|
||||
func NewHandler() *Handler {
|
||||
return &Handler{
|
||||
smtpHost: os.Getenv("SMTP_HOST"),
|
||||
smtpPort: os.Getenv("SMTP_PORT"),
|
||||
smtpFrom: os.Getenv("SMTP_FROM"),
|
||||
smtpUser: os.Getenv("SMTP_USER"),
|
||||
smtpPass: os.Getenv("SMTP_PASS"),
|
||||
smsAPIURL: os.Getenv("SMS_API_URL"),
|
||||
smsAPIKey: os.Getenv("SMS_API_KEY"),
|
||||
gotifyURL: os.Getenv("GOTIFY_URL"),
|
||||
gotifyToken: os.Getenv("GOTIFY_TOKEN"),
|
||||
}
|
||||
}
|
||||
|
||||
// ServeHTTP handles sendMsg requests.
|
||||
func (h *Handler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
|
||||
if r.Method != http.MethodPost {
|
||||
http.Error(w, "method not allowed", http.StatusMethodNotAllowed)
|
||||
return
|
||||
}
|
||||
|
||||
var req SendMsgRequest
|
||||
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
w.WriteHeader(http.StatusBadRequest)
|
||||
json.NewEncoder(w).Encode(SendMsgResponse{
|
||||
Status: "error",
|
||||
Error: "invalid request: " + err.Error(),
|
||||
})
|
||||
return
|
||||
}
|
||||
|
||||
// Route based on format
|
||||
var resp SendMsgResponse
|
||||
switch req.Format {
|
||||
case "smtp":
|
||||
resp = h.sendEmail(req)
|
||||
case "sms":
|
||||
resp = h.sendSMS(req)
|
||||
default:
|
||||
resp = SendMsgResponse{
|
||||
Status: "error",
|
||||
Error: "unsupported format: " + req.Format,
|
||||
}
|
||||
}
|
||||
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
if resp.Error != "" {
|
||||
w.WriteHeader(http.StatusInternalServerError)
|
||||
} else {
|
||||
w.WriteHeader(http.StatusOK)
|
||||
}
|
||||
json.NewEncoder(w).Encode(resp)
|
||||
}
|
||||
|
||||
// sendEmail sends an email via SMTP.
|
||||
func (h *Handler) sendEmail(req SendMsgRequest) SendMsgResponse {
|
||||
toEmail := req.Extras["to_email"]
|
||||
if toEmail == "" {
|
||||
return SendMsgResponse{
|
||||
Status: "error",
|
||||
Error: "missing to_email in extras",
|
||||
}
|
||||
}
|
||||
|
||||
subject := req.Title
|
||||
if subject == "" {
|
||||
subject = "Notification"
|
||||
}
|
||||
|
||||
// Construct email body
|
||||
body := req.Message
|
||||
if req.Extras != nil {
|
||||
if cc := req.Extras["cc"]; cc != "" {
|
||||
body = fmt.Sprintf("CC: %s\n\n%s", cc, body)
|
||||
}
|
||||
}
|
||||
|
||||
msg := fmt.Sprintf(
|
||||
"From: %s\r\nTo: %s\r\nSubject: %s\r\nContent-Type: text/plain; charset=UTF-8\r\n\r\n%s",
|
||||
h.smtpFrom, toEmail, subject, body,
|
||||
)
|
||||
|
||||
// Send via SMTP
|
||||
smtpAddr := fmt.Sprintf("%s:%s", h.smtpHost, h.smtpPort)
|
||||
auth := smtp.PlainAuth("", h.smtpUser, h.smtpPass, h.smtpHost)
|
||||
|
||||
if err := smtp.SendMail(smtpAddr, auth, h.smtpFrom, []string{toEmail}, []byte(msg)); err != nil {
|
||||
log.Printf("error sending email to %s: %v", toEmail, err)
|
||||
return SendMsgResponse{
|
||||
Status: "error",
|
||||
Error: "failed to send email: " + err.Error(),
|
||||
}
|
||||
}
|
||||
|
||||
return SendMsgResponse{
|
||||
Status: "success",
|
||||
MessageID: fmt.Sprintf("email-%s", toEmail),
|
||||
}
|
||||
}
|
||||
|
||||
// sendSMS sends an SMS via configured provider.
|
||||
// Placeholder: integrate with Twilio, AWS SNS, or similar.
|
||||
func (h *Handler) sendSMS(req SendMsgRequest) SendMsgResponse {
|
||||
phone := req.Extras["phone"]
|
||||
if phone == "" {
|
||||
return SendMsgResponse{
|
||||
Status: "error",
|
||||
Error: "missing phone in extras",
|
||||
}
|
||||
}
|
||||
|
||||
// TODO: Implement SMS provider integration (Twilio, AWS SNS, etc.)
|
||||
// For now, return error
|
||||
return SendMsgResponse{
|
||||
Status: "error",
|
||||
Error: "SMS not implemented yet",
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user