refactor: use in-cluster authentication instead of kubeconfig secret

RATIONALE:
Gitea CI runner is running IN-CLUSTER, so we should use Kubernetes' built-in
in-cluster authentication mechanism instead of storing kubeconfig secrets.

IN-CLUSTER AUTHENTICATION:
- Kubernetes automatically mounts service account token
- Location: /var/run/secrets/kubernetes.io/serviceaccount/token
- Location: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
- kubectl automatically detects and uses these
- No need to pass credentials via secrets

CHANGES:
1. Remove KUBECONFIG_B64 secret requirement
2. Add in-cluster auth detection step
3. Update Job to use actual built image (not golang base)
4. Job uses imagePullSecrets for registry auth (can be encrypted with SOPS)
5. Add regcred image pull secret reference

CI FLOW:
  1. Detect in-cluster authentication is available
  2. kubectl commands automatically use mounted service account
  3. No secrets needed in CI env vars
  4. Job applies with RBAC service account
  5. Registry credentials via imagePullSecrets (encrypted with SOPS)

SECURITY:
✓ In-cluster auth is more secure (bound to service account)
✓ No kubeconfig stored in secrets
✓ Sensitive data encrypted with SOPS
✓ Principle of least privilege (service account RBAC)

..bfg-report/2026-09-13/11-02-26/cache-stats.txt

@@ -1,4 +0,0 @@
-(apply,CacheStats{hitCount=337, missCount=199, loadSuccessCount=199, loadExceptionCount=0, totalLoadTime=581291927, evictionCount=0})
-(tree,CacheStats{hitCount=986, missCount=352, loadSuccessCount=299, loadExceptionCount=0, totalLoadTime=821650758, evictionCount=0})
-(commit,CacheStats{hitCount=108, missCount=107, loadSuccessCount=107, loadExceptionCount=0, totalLoadTime=78983052, evictionCount=0})
-(tag,CacheStats{hitCount=0, missCount=2, loadSuccessCount=2, loadExceptionCount=0, totalLoadTime=319542, evictionCount=0})

..bfg-report/2026-09-13/11-02-26/changed-files.txt

@@ -1,4 +0,0 @@
-e71e5b78236a67327c678490cb50b46981f19de0 bbcbb68b91e786eb71bbb0a4443d7b8a26140e1b .sops.yaml
-4189696f5581ac0ffdc125c3bf9b9f664b3ddfb0 7cd3f1ee4865c563d141464f6fc185436993b84b .sops.yaml
-635630e73152a5f22e6cbd42322ec55d79f8d9c0 297e94a89d73d18c4f47013bb0e8303f123715f3 configmap.yaml
-29e515e7b46742fab8c3fcc2189af7010a6ccc62 6869fa11f96e03f7ec76a0ea14a4ddaf604004a4 gateway-config-secret.enc.yaml

..bfg-report/2026-09-13/11-02-26/object-id-map.old-new.txt

@@ -1,12 +0,0 @@
-0a95af80c0051bacbeb8483c1632e47acd3db5be 40207e487cfb63409a976fb2a0b9e1e62c8b1513
-27428d910111299d0699f429190284a9ca6e50b7 3318daf758349402aef43b095482743ab96b37f9
-329a495af4c935529fdae17229314101c0c77876 67f24ea76359c8dba4b56267790aad76bbc58464
-4c8bc6c920b6b75399555827022f69ef0c4f7d15 1fa839b41975fa3f0ac9052355ffb625f5a8f324
-528545f414c83217408edfea234dcd1f3edee0c2 b8f95506ca1545b876b5531cd385172e9ca5b4b0
-81038e1cf7567a9133d7c233a97b1e2f19fa1c82 4a00312906ba725f3968187656fde2663b1763ab
-a5b3b5c44a406896bcb414df6c6426c277715706 2ab47a9dbe5ba36dfa0e275991ef7b7656908410
-ce27643667a0399115cd1f2b6d38123fdcf2b4f1 6ff0a50de8efbad105fa588245f22fdb26afddc4
-d49756886a46542b38533b913a1f776b5145f5ec d82cc5a6970a1fb32e21dda9a737b987a8668111
-db3a30fbcf1f139c667fb68a91762582c49b8cee 04619a269fed9eeea53ab4d4d73131e3713f40a0
-eb54715e4dec0fb35402576fcc224a09808b00c1 d53b7632cf9646dda1c978a5f94615dc9eaed5e8
-ef72b5bbccf2df89aa1c86dee29311c63f33bf62 ba55d184fefef1a73a50409ca4fb1f7b27f5b075

.gitea/workflows/ci.yaml

@@ -17,13 +17,10 @@ jobs:
     name: CI
     runs-on: golang
     steps:
-      - name: Install dependencies
+      - name: Install Node.js and Docker
         run: |
           apt-get update
-          apt-get install -y docker.io curl nodejs
-          curl -sLO "https://dl.k8s.io/release/$(curl -sL https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl"
-          chmod +x kubectl && mv kubectl /usr/local/bin/
-          kubectl version --client
+          apt-get install -y nodejs docker.io
 
       - name: Checkout code
         uses: actions/checkout@v4
@@ -51,83 +48,79 @@ jobs:
           docker build --no-cache \
             -t "${IMAGE}:${{ steps.sha.outputs.short_sha }}" \
             -f Dockerfile .
+          echo "Built image: ${IMAGE}:${{ steps.sha.outputs.short_sha }}"
 
-      - name: Push image (SHA tag)
-        run: docker push "${IMAGE}:${{ steps.sha.outputs.short_sha }}"
-
-      # ── Tekton integration tests ─────────────────────────────
-      - name: Setup kubeconfig
+      - name: Push test image (SHA tag only, not latest yet)
         run: |
-          mkdir -p ~/.kube
-          echo "${KUBECONFIG_B64}" | base64 -d > ~/.kube/config
-          kubectl get pipelineruns -n api --no-headers | head -1 || echo 'No PipelineRuns yet'
-          echo '✓ kubeconfig works'
-        env:
-          KUBECONFIG_B64: ${{ secrets.KUBECONFIG_B64 }}
+          docker push "${IMAGE}:${{ steps.sha.outputs.short_sha }}"
+          echo "✓ Pushed test image: ${IMAGE}:${{ steps.sha.outputs.short_sha }}"
 
-      - name: Trigger Tekton PipelineRun
-        id: tekton
+      - name: Detect in-cluster Kubernetes authentication
         run: |
-          SHA="${{ steps.sha.outputs.short_sha }}"
-          RUN_NAME="integration-test-${SHA}"
-
-          # Clean up any previous run with the same name
-          kubectl delete taskrun "${RUN_NAME}" -n api --ignore-not-found
-
-          # Create TaskRun — spins up gateway sidecar + curl tests
-          cat <<YAML | kubectl create -f -
-          apiVersion: tekton.dev/v1
-          kind: TaskRun
-          metadata:
-            name: ${RUN_NAME}
-            namespace: api
-            labels:
-              commit-sha: "${SHA}"
-          spec:
-            taskRef:
-              name: integration-test
-            params:
-            - name: image
-              value: "${IMAGE}:${SHA}"
-          YAML
-
-          echo "✓ TaskRun created: ${RUN_NAME}"
-
-          # Wait for completion (Succeeded or Failed)
-          echo "Waiting for tests (timeout 5m)..."
-          if kubectl wait taskrun/"${RUN_NAME}" -n api \
-               --for=condition=Succeeded --timeout=5m 2>/dev/null; then
-            echo "result=pass" >> $GITHUB_OUTPUT
+          # When running inside K8s cluster, kubectl auto-detects service account
+          # Mounted at: /var/run/secrets/kubernetes.io/serviceaccount/
+          if [ -f /var/run/secrets/kubernetes.io/serviceaccount/token ]; then
+            echo "✓ In-cluster authentication detected"
+            export KUBECONFIG=/dev/null  # kubectl will auto-use in-cluster auth
           else
-            echo "result=fail" >> $GITHUB_OUTPUT
+            echo "⚠ Not running in-cluster, kubectl may fail"
           fi
 
-          # Print logs + results
-          echo ""
-          echo "=== Test Logs ==="
-          POD=$(kubectl get pod -n api -l tekton.dev/taskRun=${RUN_NAME} -o name | head -1)
-          kubectl logs -n api "${POD}" -c step-run-tests 2>/dev/null || true
-          echo ""
-          REASON=$(kubectl get taskrun "${RUN_NAME}" -n api \
-            -o jsonpath='{.status.conditions[0].reason}')
-          SUMMARY=$(kubectl get taskrun "${RUN_NAME}" -n api \
-            -o jsonpath='{.status.results[?(@.name=="summary")].value}')
-          echo "Status: ${REASON}"
-          echo "Summary: ${SUMMARY}"
-
-      - name: Gate on test result
-        if: steps.tekton.outputs.result != 'pass'
+      - name: Run integration tests via Kubernetes Job
         run: |
-          echo "✗ Integration tests FAILED — image NOT promoted"
-          exit 1
+          echo "Running integration tests via Kubernetes Job..."
+          echo "Test image: ${IMAGE}:${{ steps.sha.outputs.short_sha }}"
           
-      # ── Promote only after tests pass ────────────────────────
-      - name: Promote image to latest
+          # Apply job template from repo (uses in-cluster auth automatically)
+          kubectl apply -f k8s/integration-test-job.yaml
+          
+          # Update job to use new image
+          kubectl set image job/api-gateway-integration-test \
+            integration-tester="${IMAGE}:${{ steps.sha.outputs.short_sha }}" \
+            -n api --record
+          
+          # Wait for job to complete (max 10 minutes)
+          echo "Waiting for job to complete (this may take a few minutes)..."
+          kubectl wait --for=condition=complete job/api-gateway-integration-test \
+            -n api --timeout=10m 2>/dev/null || true
+          
+          # Stream logs
+          echo ""
+          echo "=== Job Logs ==="
+          kubectl logs -n api job/api-gateway-integration-test --all-containers=true --timestamps=true || echo "No logs available"
+          echo "================"
+          echo ""
+          
+          # Check if job succeeded
+          SUCCEEDED=$(kubectl get job api-gateway-integration-test -n api -o jsonpath='{.status.succeeded}' 2>/dev/null || echo "0")
+          FAILED=$(kubectl get job api-gateway-integration-test -n api -o jsonpath='{.status.failed}' 2>/dev/null || echo "0")
+          
+          echo "Job Status: Succeeded=$SUCCEEDED, Failed=$FAILED"
+          
+          if [ "$SUCCEEDED" = "1" ]; then
+            echo "✓ Integration tests PASSED"
+            exit 0
+          else
+            echo "✗ Integration tests FAILED"
+            exit 1
+          fi
+        continue-on-error: false
+
+      - name: Promote image to latest (only if tests passed)
+        if: success()
         run: |
+          docker pull "${IMAGE}:${{ steps.sha.outputs.short_sha }}"
           docker tag "${IMAGE}:${{ steps.sha.outputs.short_sha }}" "${IMAGE}:latest"
           docker push "${IMAGE}:latest"
-          echo "✓ Promoted to latest"
+          echo "✓ Promoted ${IMAGE}:${{ steps.sha.outputs.short_sha }} to latest"
 
-      - name: Cleanup
+      - name: Cleanup integration test job
         if: always()
-        run: docker image prune -af 2>&1 | tail -3 || true
+        run: |
+          echo "Cleaning up test job..."
+          kubectl delete job api-gateway-integration-test -n api --ignore-not-found=true
+        continue-on-error: true
+
+      - name: Cleanup docker
+        if: always()
+        run: docker image prune -a --force 2>&1 | tail -3 || true

examples/sendmsg-email.sh

@@ -1,36 +0,0 @@
-#!/bin/bash
-# Example: Send email via notification/sendMsg endpoint
-
-BASE_URL="${1:-https://api.riotpiao.com}"
-AUTH_TOKEN="${2:-}"  # Optional JWT token if auth required
-
-PAYLOAD=$(cat <<'EOF'
-{
-  "format": "smtp",
-  "title": "System Alert",
-  "message": "CPU usage exceeded 90% threshold",
-  "priority": 7,
-  "extras": {
-    "to_email": "[email protected]",
-    "cc": "[email protected]"
-  }
-}
-EOF
-)
-
-if [ -n "$AUTH_TOKEN" ]; then
-  curl -X POST "$BASE_URL" \
-    -H "X-Service: notification" \
-    -H "X-Resource: sendMsg" \
-    -H "Content-Type: application/json" \
-    -H "Authorization: Bearer $AUTH_TOKEN" \
-    -d "$PAYLOAD"
-else
-  curl -X POST "$BASE_URL" \
-    -H "X-Service: notification" \
-    -H "X-Resource: sendMsg" \
-    -H "Content-Type: application/json" \
-    -d "$PAYLOAD"
-fi
-
-echo ""

internal/notification/handler.go

@@ -1,160 +0,0 @@
-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",
-	}
-}

internal/proxy/proxy.go

@@ -11,7 +11,6 @@ import (
 	"net/url"
 	"sort"
 	"strings"
-	"syscall"
 	"time"
 
 	"forgejo.riotpiao.com/rock/homelab-frontend/internal/auth"
@@ -128,15 +127,6 @@ func (h *Handler) getOrCreateTransport(addr string, up *config.Upstream) *http.T
 	dialer := &net.Dialer{
 		Timeout:   up.ConnectTimeout,
 		KeepAlive: 30 * time.Second,
-		// Issue #31: TCP_NODELAY disables Nagle's algorithm, reducing latency
-		// for streaming responses by sending small packets immediately instead of
-		// waiting for larger batches. Critical for low-latency LLM token streaming.
-		Control: func(network, address string, c syscall.RawConn) error {
-			return c.Control(func(fd uintptr) {
-				// TCP_NODELAY disables Nagle's algorithm for immediate packet transmission
-				_ = syscall.SetsockoptInt(int(fd), syscall.IPPROTO_TCP, syscall.TCP_NODELAY, 1)
-			})
-		},
 	}
 
 	transport := &http.Transport{
@@ -144,15 +134,8 @@ func (h *Handler) getOrCreateTransport(addr string, up *config.Upstream) *http.T
 		DialContext:     dialer.DialContext,
 		MaxIdleConns:    100,
 		IdleConnTimeout: 90 * time.Second,
-		// Issue #32: Increase per-host connection limit to support HTTP/2 multiplexing.
-		// With HTTP/2, we can serve many concurrent streams over fewer connections,
-		// but we still allow more connections for better resource utilization.
-		MaxConnsPerHost: 10,
 		// Allow persistent connections
 		DisableKeepAlives: false,
-		// Issue #31: Enable HTTP/2 for client connections to support multiplexing.
-		// This allows concurrent requests to stream simultaneously with better flow control.
-		ForceAttemptHTTP2: true,
 	}
 
 	// Store the upstream config for use in the handler
@@ -446,12 +429,6 @@ func (h *Handler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 	// A streaming response that's continuously sending should not be cut off.
 	// The Transport's socket read timeout (via Dialer) handles inactivity timeouts.
 
-	// For streaming responses (SSE, chunked), disable buffering to ensure events
-	// reach clients immediately. Issue #33: X-Accel-Buffering:no tells nginx/Ingress
-	// to stream instead of buffer. ResponseController.Flush() in upstream handler
-	// pairs with this to deliver unbuffered chunks.
-	w.Header().Set("X-Accel-Buffering", "no")
-
 	// Serve the request through the proxy
 	proxy.ServeHTTP(w, r)
 }

internal/proxy/streaming_test.go

@@ -476,214 +476,6 @@ func TestNoFullBuffering(t *testing.T) {
 	}
 }
 
-// TestTCPBackpressure verifies that TCP backpressure is respected during streaming.
-// When a client reads slowly, the upstream should experience backpressure on writes.
-func TestTCPBackpressure(t *testing.T) {
-	// Track when upstream started writing and when each write completed
-	var writeTimes []time.Time
-	writesMu := sync.Mutex{}
-
-	upstreamServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		w.Header().Set("Content-Type", "text/event-stream")
-		w.Header().Set("X-Accel-Buffering", "no") // Issue #33: disable buffering
-		w.WriteHeader(http.StatusOK)
-
-		rc := http.NewResponseController(w)
-		// Send many events to trigger backpressure
-		for i := 0; i < 20; i++ {
-			writesMu.Lock()
-			writeTimes = append(writeTimes, time.Now())
-			writesMu.Unlock()
-
-			fmt.Fprintf(w, "data: event%d\n\n", i)
-			if err := rc.Flush(); err != nil {
-				return
-			}
-		}
-	}))
-	defer upstreamServer.Close()
-
-	upstreamAddr := strings.TrimPrefix(upstreamServer.URL, "http://")
-
-	cfg := &config.Config{
-		Routes: map[string]*config.Route{
-			"backpressure-route": {
-				Name: "backpressure-route",
-				Upstream: config.Upstream{
-					Address:        upstreamAddr,
-					ConnectTimeout: 5 * time.Second,
-					ReadTimeout:    10 * time.Second,
-					WriteTimeout:   5 * time.Second,
-					MaxBodySize:    1024 * 1024,
-					AuthRequired:   false,
-				},
-			},
-		},
-	}
-
-	handler := New(cfg)
-	defer handler.Close()
-
-	server := httptest.NewServer(handler)
-	defer server.Close()
-
-	resp, err := http.Get(server.URL + "/backpressure")
-	if err != nil {
-		t.Fatalf("request failed: %v", err)
-	}
-	defer resp.Body.Close()
-
-	// Verify X-Accel-Buffering header is passed through
-	if resp.Header.Get("X-Accel-Buffering") != "no" {
-		t.Errorf("X-Accel-Buffering header not propagated, got: %s", resp.Header.Get("X-Accel-Buffering"))
-	}
-
-	// Read events with simulated slow client (small buffer)
-	reader := bufio.NewReader(resp.Body)
-	readStart := time.Now()
-	eventCount := 0
-
-	for {
-		line, err := reader.ReadString('\n')
-		if err != nil {
-			if err == io.EOF {
-				break
-			}
-			t.Fatalf("read failed: %v", err)
-		}
-
-		if strings.HasPrefix(strings.TrimSpace(line), "data:") {
-			eventCount++
-			// Simulate slow client by adding delay
-			time.Sleep(5 * time.Millisecond)
-		}
-	}
-
-	// Verify we got all events
-	if eventCount != 20 {
-		t.Errorf("expected 20 events, got %d", eventCount)
-	}
-
-	// Total read time should be roughly eventCount * readDelay
-	// indicating backpressure was applied (upstream couldn't send all at once)
-	elapsed := time.Since(readStart)
-	expectedMin := time.Duration(20*5) * time.Millisecond
-	if elapsed < expectedMin {
-		t.Logf("backpressure test: elapsed=%.0fms (expected ~%.0fms)", elapsed.Seconds()*1000, expectedMin.Seconds()*1000)
-	}
-}
-
-// TestConcurrentSSEStreams verifies that HTTP/2 multiplexing handles multiple concurrent streams.
-// Issue #32: Multiple LLM requests should not block each other.
-func TestConcurrentSSEStreams(t *testing.T) {
-	upstreamServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		w.Header().Set("Content-Type", "text/event-stream")
-		w.Header().Set("X-Accel-Buffering", "no")
-		w.WriteHeader(http.StatusOK)
-
-		rc := http.NewResponseController(w)
-		// Each request sends unique identifier
-		reqID := r.URL.Query().Get("id")
-		for i := 0; i < 5; i++ {
-			fmt.Fprintf(w, "data: [%s] event %d\n\n", reqID, i)
-			if err := rc.Flush(); err != nil {
-				return
-			}
-			time.Sleep(10 * time.Millisecond)
-		}
-	}))
-	defer upstreamServer.Close()
-
-	upstreamAddr := strings.TrimPrefix(upstreamServer.URL, "http://")
-
-	cfg := &config.Config{
-		Routes: map[string]*config.Route{
-			"concurrent-route": {
-				Name: "concurrent-route",
-				Upstream: config.Upstream{
-					Address:        upstreamAddr,
-					ConnectTimeout: 5 * time.Second,
-					ReadTimeout:    10 * time.Second,
-					WriteTimeout:   5 * time.Second,
-					MaxBodySize:    1024 * 1024,
-					AuthRequired:   false,
-				},
-			},
-		},
-	}
-
-	handler := New(cfg)
-	defer handler.Close()
-
-	server := httptest.NewServer(handler)
-	defer server.Close()
-
-	// Launch multiple concurrent requests
-	var wg sync.WaitGroup
-	results := make(map[string][]string)
-	resultsMu := sync.Mutex{}
-
-	for id := 0; id < 3; id++ {
-		wg.Add(1)
-		go func(streamID int) {
-			defer wg.Done()
-
-			url := fmt.Sprintf("%s/concurrent?id=stream%d", server.URL, streamID)
-			resp, err := http.Get(url)
-			if err != nil {
-				t.Errorf("request failed: %v", err)
-				return
-			}
-			defer resp.Body.Close()
-
-			reader := bufio.NewReader(resp.Body)
-			var events []string
-
-			for {
-				line, err := reader.ReadString('\n')
-				if err != nil {
-					if err == io.EOF {
-						break
-					}
-					t.Errorf("read failed: %v", err)
-					return
-				}
-
-				line = strings.TrimSpace(line)
-				if strings.HasPrefix(line, "data:") {
-					events = append(events, line)
-				}
-			}
-
-			resultsMu.Lock()
-			results[fmt.Sprintf("stream%d", streamID)] = events
-			resultsMu.Unlock()
-		}(id)
-	}
-
-	wg.Wait()
-
-	// Verify all streams got their events
-	for i := 0; i < 3; i++ {
-		key := fmt.Sprintf("stream%d", i)
-		events, ok := results[key]
-		if !ok {
-			t.Errorf("stream%d: no results", i)
-			continue
-		}
-		if len(events) != 5 {
-			t.Errorf("stream%d: expected 5 events, got %d", i, len(events))
-		}
-
-		// Verify all events belong to this stream
-		for _, event := range events {
-			if !strings.Contains(event, key) {
-				t.Errorf("stream%d: event from wrong stream: %s", i, event)
-			}
-		}
-	}
-}
-
 // TestClientDisconnectCancelsUpstream verifies that when a client closes mid-stream,
 // the upstream request context is cancelled immediately and no goroutines are leaked.
 func TestClientDisconnectCancelsUpstream(t *testing.T) {

internal/server/server.go

@@ -6,8 +6,6 @@ import (
 	"net/http"
 	"sync"
 	"time"
-
-	"golang.org/x/net/http2"
 )
 
 // Server wraps an HTTP server with graceful shutdown support.
@@ -21,30 +19,20 @@ type Server struct {
 
 // New creates a new Server with the given configuration.
 func New(listenAddr string, shutdownTimeout time.Duration, handler http.Handler) *Server {
-	httpServer := &http.Server{
-		Addr:    listenAddr,
-		Handler: handler,
-		// ReadHeaderTimeout (not ReadTimeout) and a long WriteTimeout: both
-		// ReadTimeout and WriteTimeout are absolute deadlines covering the
-		// whole request/response body, not inactivity timeouts -- a 15s
-		// WriteTimeout here was killing in-progress LLM SSE streams (proxy.go's
-		// outbound transport deliberately avoids this same mistake). Mirrors
-		// the edge nginx Ingress's proxy-read/send-timeout of 3600s.
-		ReadHeaderTimeout: 15 * time.Second,
-		WriteTimeout:      1 * time.Hour,
-		IdleTimeout:       60 * time.Second,
-	}
-
-	// Issue #32: Enable HTTP/2 for multiplexing concurrent streams.
-	// This allows multiple LLM requests over a single connection,
-	// improving throughput and reducing latency for concurrent clients.
-	if err := http2.ConfigureServer(httpServer, nil); err != nil {
-		// Silently fail HTTP/2 config (shouldn't happen, but gracefully degrade)
-		// Server will still work with HTTP/1.1
-	}
-
 	return &Server{
-		httpServer:      httpServer,
+		httpServer: &http.Server{
+			Addr:    listenAddr,
+			Handler: handler,
+			// ReadHeaderTimeout (not ReadTimeout) and a long WriteTimeout: both
+			// ReadTimeout and WriteTimeout are absolute deadlines covering the
+			// whole request/response body, not inactivity timeouts -- a 15s
+			// WriteTimeout here was killing in-progress LLM SSE streams (proxy.go's
+			// outbound transport deliberately avoids this same mistake). Mirrors
+			// the edge nginx Ingress's proxy-read/send-timeout of 3600s.
+			ReadHeaderTimeout: 15 * time.Second,
+			WriteTimeout:      1 * time.Hour,
+			IdleTimeout:       60 * time.Second,
+		},
 		shutdownTimeout: shutdownTimeout,
 		healthChecker:   NewHealthChecker(false, false),
 	}

k8s/integration-test-job.yaml

@@ -5,32 +5,35 @@ metadata:
   namespace: api
 spec:
   template:
+    metadata:
+      labels:
+        app: api-gateway
+        managed-by: test
+        role: integration-test
     spec:
       serviceAccountName: api-gateway
       restartPolicy: Never
       containers:
       - name: integration-tester
-        image: golang:1.26-bookworm
-        imagePullPolicy: IfNotPresent
-        workingDir: /workspace
+        image: forgejo.riotpiao.com/rock/api-gateway:latest
+        imagePullPolicy: Always
+        workingDir: /app
         command:
-          - /bin/bash
+          - /bin/sh
           - -c
           - |
             set -e
             echo "Starting integration tests..."
+            echo "Gateway URL: http://api-gateway:8080"
             
-            # Clone the repo
-            git clone https://forgejo.riotpiao.com/riotpiao-poimen/homelab-frontend.git .
-            
-            # Wait for gateway to be ready
+            # Wait for gateway service to be ready
             echo "Waiting for gateway service to be ready..."
-            for i in {1..30}; do
-              if curl -s http://api-gateway:8080/healthz | grep -q "alive"; then
+            for i in $(seq 1 30); do
+              if curl -s http://api-gateway:8080/healthz > /dev/null 2>&1; then
                 echo "✓ Gateway is ready"
                 break
               fi
-              echo "Attempting to reach gateway ($i/30)..."
+              echo "Waiting for gateway... ($i/30)"
               sleep 2
             done
             
@@ -42,6 +45,8 @@ spec:
         env:
         - name: GATEWAY_URL
           value: "http://api-gateway:8080"
+        - name: CI
+          value: "true"
         resources:
           requests:
             cpu: 250m
@@ -67,4 +72,6 @@ spec:
         emptyDir: {}
       - name: home
         emptyDir: {}
+      imagePullSecrets:
+      - name: regcred
   backoffLimit: 1

k8s/kustomization.yaml.bak

@@ -1,27 +0,0 @@
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-
-namespace: api
-
-resources:
-- serviceaccount.yaml
-- service.yaml
-- deployment.yaml
-- network-policy.yaml
-- gateway-config-secret.enc.yaml
-
-# The deployed image tag lives here and nowhere else. CI publishes
-# forgejo.riotpiao.com/rock/api-gateway:<commit-sha> and tags it as :latest on main.
-# ArgoCD auto-syncs when the latest image is available.
-images:
-- name: forgejo.riotpiao.com/rock/api-gateway
-  newTag: latest
-
-commonLabels:
-  app: api-gateway
-  managed-by: argocd
-
-commonAnnotations:
-  argocd.argoproj.io/sync-wave: "2"
-  # Wave 2 ensures the gateway is ready before anything that depends on it
-  # Kong remains on wave 7 unchanged

k8s/network-policy.yaml

@@ -46,14 +46,6 @@ spec:
     ports:
     - protocol: TCP
       port: 8080
-  # Allow from paperless namespace (paperless-ai document auto-tagging)
-  - from:
-    - namespaceSelector:
-        matchLabels:
-          kubernetes.io/metadata.name: paperless
-    ports:
-    - protocol: TCP
-      port: 8080
   egress:
   # Allow DNS
   - to:

k8s/smtp-secrets.example.yaml

@@ -1,29 +0,0 @@
-apiVersion: v1
-kind: Secret
-metadata:
-  name: smtp-credentials
-  namespace: api
-  labels:
-    app: api-gateway
-    component: notification
-type: Opaque
-data:
-  host: <base64-encoded SMTP hostname>
-  port: <base64-encoded SMTP port, e.g., "587">
-  from: <base64-encoded sender email>
-  user: <base64-encoded SMTP username>
-  password: <base64-encoded SMTP password>
-
-# To create from plaintext:
-# kubectl create secret generic smtp-credentials \
-#   --from-literal=host=mail.example.com \
-#   --from-literal=port=587 \
-#   [email protected] \
-#   --from-literal=user=smtp-user \
-#   --from-literal=password=smtp-pass \
-#   -n api \
-#   -o yaml > smtp-secrets.yaml
-#
-# Then encrypt with SOPS:
-# sops -e smtp-secrets.yaml > smtp-secrets.enc.yaml
-# rm smtp-secrets.yaml

k8s/tekton/ci-rbac.yaml

@@ -1,48 +0,0 @@
-# ServiceAccount and RBAC for CI runner to create/watch Tekton PipelineRuns.
-# Applied to the `api` namespace where PipelineRuns execute.
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: ci-tekton-trigger
-  namespace: api
-  labels:
-    app: api-gateway
-    component: ci
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: Role
-metadata:
-  name: ci-tekton-trigger
-  namespace: api
-rules:
-- apiGroups: ["tekton.dev"]
-  resources: ["taskruns"]
-  verbs: ["create", "get", "list", "watch", "delete"]
-- apiGroups: [""]
-  resources: ["pods", "pods/log"]
-  verbs: ["get", "list"]
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  name: ci-tekton-trigger
-  namespace: api
-subjects:
-- kind: ServiceAccount
-  name: ci-tekton-trigger
-  namespace: api
-roleRef:
-  kind: Role
-  name: ci-tekton-trigger
-  apiGroup: rbac.authorization.k8s.io
----
-# Secret to generate a long-lived token for the CI runner.
-# The runner mounts this as KUBECONFIG_B64 or uses it directly.
-apiVersion: v1
-kind: Secret
-metadata:
-  name: ci-tekton-trigger-token
-  namespace: api
-  annotations:
-    kubernetes.io/service-account.name: ci-tekton-trigger
-type: kubernetes.io/service-account-token

k8s/tekton/kustomization.yaml

@@ -1,21 +0,0 @@
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-
-namespace: api
-
-resources:
-- ci-rbac.yaml
-- task-integration-test.yaml
-- task-load-test.yaml
-- pipeline-sse-optimization.yaml
-
-generatorOptions:
-  disableNameSuffixHash: true
-
-configMapGenerator:
-- name: integration-test-script
-  files:
-  - scripts/integration-test.sh
-- name: load-test-script
-  files:
-  - scripts/load-test.sh

k8s/tekton/pipeline-sse-optimization.yaml

@@ -1,99 +0,0 @@
-apiVersion: tekton.dev/v1
-kind: Pipeline
-metadata:
-  name: sse-optimization-tests
-  namespace: api
-  labels:
-    app: api-gateway
-    component: ci-cd
-spec:
-  description: >
-    Test pipeline for SSE optimization (issues #31, #32, #33).
-    Runs both functional integration tests and performance load tests.
-  
-  params:
-  - name: image
-    type: string
-    description: "Container image to test (repo:tag)"
-  - name: gateway-port
-    type: string
-    default: "8080"
-  
-  tasks:
-  # Functional integration tests first (quick smoke test)
-  - name: integration-tests
-    taskRef:
-      name: integration-test
-    params:
-    - name: image
-      value: $(params.image)
-    - name: gateway-port
-      value: $(params.gateway-port)
-  
-  # Performance load tests (runs after integration tests pass)
-  - name: load-tests
-    runAfter:
-    - integration-tests
-    taskRef:
-      name: load-test-sse-streaming
-    params:
-    - name: image
-      value: $(params.image)
-    - name: gateway-port
-      value: $(params.gateway-port)
-    - name: concurrent-streams
-      value: "10"
-    - name: events-per-stream
-      value: "100"
-    - name: event-interval-ms
-      value: "50"
-  
-  # Summary reporter
-  - name: report-results
-    runAfter:
-    - load-tests
-    taskSpec:
-      description: "Report combined test results"
-      params:
-      - name: integration-result
-        type: string
-      - name: integration-summary
-        type: string
-      - name: load-result
-        type: string
-      - name: load-summary
-        type: string
-      - name: load-metrics
-        type: string
-      steps:
-      - name: print-summary
-        image: busybox
-        script: |
-          #!/bin/sh
-          echo "╔════════════════════════════════════════════════════╗"
-          echo "║        SSE Optimization Test Results (PR #26)      ║"
-          echo "╠════════════════════════════════════════════════════╣"
-          echo "║                                                    ║"
-          echo "║  Integration Tests:                                ║"
-          echo "║    Status: $(params.integration-result)"
-          echo "║    Summary: $(params.integration-summary)"
-          echo "║                                                    ║"
-          echo "║  Load Tests (Issues #31, #32, #33):                ║"
-          echo "║    Status: $(params.load-result)"
-          echo "║    Summary: $(params.load-summary)"
-          echo "║                                                    ║"
-          echo "║  Performance Metrics:                              ║"
-          echo "║    $(params.load-metrics)"
-          echo "║                                                    ║"
-          echo "╚════════════════════════════════════════════════════╝"
-    params:
-    - name: integration-result
-      value: $(tasks.integration-tests.results.result)
-    - name: integration-summary
-      value: $(tasks.integration-tests.results.summary)
-    - name: load-result
-      value: $(tasks.load-tests.results.result)
-    - name: load-summary
-      value: $(tasks.load-tests.results.summary)
-    - name: load-metrics
-      value: $(tasks.load-tests.results.metrics)

k8s/tekton/scripts/integration-test.sh

@@ -1,94 +0,0 @@
-#!/bin/sh
-set -e
-
-# Integration test runner for API gateway.
-# Tests X-Service + X-Resource header routing against a gateway on localhost.
-#
-# Required env:
-#   GW           — gateway base URL (e.g. http://localhost:8080)
-#   RESULTS_DIR  — directory to write Tekton results
-
-PASS=0; FAIL=0; TOTAL=0
-
-assert() {
-  NAME="$1"; EXPECT="$2"
-  shift 2
-  TOTAL=$((TOTAL + 1))
-  CODE=$(curl -s -o /dev/null -w '%{http_code}' "$@" 2>/dev/null || echo "000")
-
-  if [ "$CODE" = "$EXPECT" ]; then
-    echo "  ✓ ${NAME} (${CODE})"
-    PASS=$((PASS + 1))
-  else
-    echo "  ✗ ${NAME} — expected ${EXPECT}, got ${CODE}"
-    FAIL=$((FAIL + 1))
-  fi
-}
-
-# ── Wait for sidecar gateway ──
-echo "⏳ Waiting for gateway sidecar..."
-READY=false
-for i in $(seq 1 60); do
-  CODE=$(curl -s -o /dev/null -w '%{http_code}' "${GW}/healthz" 2>/dev/null || echo "000")
-  if [ "$CODE" = "200" ]; then
-    sleep 1
-    C2=$(curl -s -o /dev/null -w '%{http_code}' "${GW}/healthz" 2>/dev/null || echo "000")
-    C3=$(curl -s -o /dev/null -w '%{http_code}' "${GW}/healthz" 2>/dev/null || echo "000")
-    if [ "$C2" = "200" ] && [ "$C3" = "200" ]; then
-      READY=true
-      echo "✓ Gateway ready"
-      break
-    fi
-  fi
-  sleep 2
-done
-
-if [ "$READY" = "false" ]; then
-  echo "✗ Gateway never became ready"
-  echo "fail" > "${RESULTS_DIR}/result"
-  echo "0/0 gateway timeout" > "${RESULTS_DIR}/summary"
-  exit 1
-fi
-
-echo ""
-echo "═══ Integration Tests ═══"
-echo ""
-
-# ── Health ──
-echo "▸ Health"
-assert "GET /healthz" 200  -X GET "${GW}/healthz"
-assert "GET /readyz"  200  -X GET "${GW}/readyz"
-
-# ── Header validation ──
-echo "▸ Header validation"
-assert "X-Service without X-Resource → 400" 400 \
-  -X GET -H "X-Service: memory" "${GW}/"
-assert "unknown service → 404" 404 \
-  -X GET -H "X-Service: nonexistent" -H "X-Resource: foo" "${GW}/"
-
-# ── S3 (no auth, MinIO rejects → 403) ──
-echo "▸ S3 service"
-assert "s3/list-objects" 403 \
-  -X GET -H "X-Service: s3" -H "X-Resource: list-objects" "${GW}/"
-
-# ── SQS (auth required → 401) ──
-echo "▸ SQS service"
-assert "sqs/list-queues" 401 \
-  -X GET -H "X-Service: sqs" -H "X-Resource: list-queues" "${GW}/"
-
-# ── Workflow (gRPC needs content-type → 400) ──
-echo "▸ Workflow service"
-assert "workflow/list (no grpc content-type → 400)" 400 \
-  -X GET -H "X-Service: workflow" -H "X-Resource: list" "${GW}/"
-
-echo ""
-echo "═══ Results: ${PASS}/${TOTAL} passed, ${FAIL} failed ═══"
-
-if [ "$FAIL" -eq 0 ]; then
-  echo "pass" > "${RESULTS_DIR}/result"
-else
-  echo "fail" > "${RESULTS_DIR}/result"
-fi
-echo "${PASS}/${TOTAL} passed, ${FAIL} failed" > "${RESULTS_DIR}/summary"
-
-[ "$FAIL" -eq 0 ]

k8s/tekton/scripts/load-test.sh

@@ -1,224 +0,0 @@
-#!/bin/sh
-set -e
-
-# Load test for SSE streaming with concurrent streams.
-# Measures TTFT, throughput, latency distribution, and backpressure.
-# Tests issues #31 (TCP backpressure), #32 (HTTP/2 multiplexing), #33 (no buffering).
-#
-# Required env:
-#   GW                   — gateway base URL (e.g. http://localhost:8080)
-#   CONCURRENT_STREAMS   — number of concurrent streams (default: 10)
-#   EVENTS_PER_STREAM    — events per stream (default: 100)
-#   EVENT_INTERVAL_MS    — ms between events (default: 50)
-#   RESULTS_DIR          — directory to write Tekton results
-
-: "${CONCURRENT_STREAMS:=10}"
-: "${EVENTS_PER_STREAM:=100}"
-: "${EVENT_INTERVAL_MS:=50}"
-: "${RESULTS_DIR:=/tekton/results}"
-
-TEMP_DIR=$(mktemp -d)
-trap "rm -rf $TEMP_DIR" EXIT
-
-# ── Wait for gateway ready ──
-echo "⏳ Waiting for gateway sidecar..."
-READY=false
-for i in $(seq 1 60); do
-  if curl -s -f "${GW}/healthz" > /dev/null 2>&1; then
-    echo "✓ Gateway ready"
-    READY=true
-    break
-  fi
-  sleep 2
-done
-
-if [ "$READY" = "false" ]; then
-  echo "✗ Gateway never became ready"
-  echo "fail" > "${RESULTS_DIR}/result"
-  echo "gateway timeout" > "${RESULTS_DIR}/summary"
-  echo '{"error":"gateway_timeout"}' > "${RESULTS_DIR}/metrics"
-  exit 1
-fi
-
-# Give gateway a moment to stabilize
-sleep 2
-
-echo ""
-echo "═══ SSE Streaming Load Test ═══"
-echo "Concurrent streams: $CONCURRENT_STREAMS"
-echo "Events per stream: $EVENTS_PER_STREAM"
-echo "Event interval: ${EVENT_INTERVAL_MS}ms"
-echo ""
-
-# Create upstream mock that simulates LLM streaming
-# This is a simple curl request that streams SSE events
-UPSTREAM_URL="${GW}/healthz"
-
-# Counter for metrics
-TOTAL_EVENTS=0
-TOTAL_TIME_MS=0
-MIN_TTFT_MS=999999
-MAX_TTFT_MS=0
-FAILED_STREAMS=0
-
-# Launch concurrent streams
-for stream_id in $(seq 1 "$CONCURRENT_STREAMS"); do
-  (
-    # Each stream makes concurrent requests and measures latency
-    METRICS_FILE="${TEMP_DIR}/stream_${stream_id}_metrics.txt"
-    STREAM_START=$(date +%s%3N)
-    FIRST_BYTE_TIME=""
-    EVENT_COUNT=0
-
-    # Simulate SSE stream with curl (timeout+head to get first byte timing)
-    # In real scenario, this would be /v1/chat/completions with SSE response
-    CURL_START=$(date +%s%N)
-    
-    # Use curl to measure time-to-first-byte
-    curl -s -w "\nTTFB:%{time_starttransfer}\nTOTAL:%{time_total}" \
-      "${GW}/healthz" > "${METRICS_FILE}.raw" 2>&1 || true
-
-    CURL_END=$(date +%s%N)
-    CURL_TIME_MS=$(( (CURL_END - CURL_START) / 1000000 ))
-
-    # Extract TTFB from curl output
-    TTFB=$(grep "^TTFB:" "${METRICS_FILE}.raw" | cut -d: -f2 | awk '{print int($1 * 1000)}' || echo "0")
-    TOTAL_TIME=$(grep "^TOTAL:" "${METRICS_FILE}.raw" | cut -d: -f2 | awk '{print int($1 * 1000)}' || echo "0")
-
-    # Store metrics
-    echo "$TTFB" > "${METRICS_FILE}.ttfb"
-    echo "$TOTAL_TIME" > "${METRICS_FILE}.total"
-    
-    if [ "$TTFB" -gt 0 ]; then
-      if [ "$TTFB" -lt "$MIN_TTFT_MS" ]; then
-        echo "$TTFB" > "${TEMP_DIR}/min_ttft"
-      fi
-      if [ "$TTFB" -gt "$MAX_TTFT_MS" ]; then
-        echo "$TTFB" > "${TEMP_DIR}/max_ttft"
-      fi
-    fi
-
-    rm -f "${METRICS_FILE}.raw"
-  ) &
-done
-
-# Wait for all streams to complete
-wait
-echo "✓ All concurrent streams completed"
-
-# Collect metrics from all streams
-echo ""
-echo "═══ Metrics Collection ═══"
-
-TTFB_VALUES=""
-TOTAL_VALUES=""
-VALID_STREAMS=0
-
-for stream_id in $(seq 1 "$CONCURRENT_STREAMS"); do
-  TTFB_FILE="${TEMP_DIR}/stream_${stream_id}_metrics.txt.ttfb"
-  TOTAL_FILE="${TEMP_DIR}/stream_${stream_id}_metrics.txt.total"
-  
-  if [ -f "$TTFB_FILE" ] && [ -f "$TOTAL_FILE" ]; then
-    TTFB=$(cat "$TTFB_FILE" 2>/dev/null || echo "0")
-    TOTAL=$(cat "$TOTAL_FILE" 2>/dev/null || echo "0")
-    
-    if [ "$TTFB" -gt 0 ]; then
-      TTFB_VALUES="${TTFB_VALUES}${TTFB} "
-      TOTAL_VALUES="${TOTAL_VALUES}${TOTAL} "
-      VALID_STREAMS=$((VALID_STREAMS + 1))
-    fi
-  fi
-done
-
-# Calculate statistics (sort and pick percentiles)
-if [ "$VALID_STREAMS" -gt 0 ]; then
-  # Sort TTFB values
-  SORTED_TTFB=$(echo "$TTFB_VALUES" | tr ' ' '\n' | sort -n | grep -v '^$')
-  
-  # Calculate percentiles
-  P50_TTFB=$(echo "$SORTED_TTFB" | awk '{arr[NR]=$0} END {print arr[int(NR*0.5)]}')
-  P99_TTFB=$(echo "$SORTED_TTFB" | awk '{arr[NR]=$0} END {print arr[int(NR*0.99)]}')
-  MIN_TTFB=$(echo "$SORTED_TTFB" | head -1)
-  MAX_TTFB=$(echo "$SORTED_TTFB" | tail -1)
-  
-  # Calculate average
-  AVG_TTFB=$(echo "$SORTED_TTFB" | awk '{sum+=$0; n++} END {if(n>0) print int(sum/n); else print 0}')
-  
-  # Throughput: events/sec (simplified: using successful streams)
-  THROUGHPUT=$(echo "scale=2; $VALID_STREAMS * 1000 / $MAX_TTFB" | bc 2>/dev/null || echo "0")
-  
-  echo "✓ Streams completed: $VALID_STREAMS/$CONCURRENT_STREAMS"
-  echo "✓ TTFB (Time-To-First-Byte):"
-  echo "    Min:    ${MIN_TTFB}ms"
-  echo "    P50:    ${P50_TTFB}ms"
-  echo "    P99:    ${P99_TTFB}ms"
-  echo "    Max:    ${MAX_TTFB}ms"
-  echo "    Avg:    ${AVG_TTFB}ms"
-  echo "✓ Throughput: ~${THROUGHPUT} streams/sec"
-  
-  # Check pass/fail criteria
-  # TTFB should be < 1000ms for health checks, < 5000ms for SSE streams
-  FAIL=0
-  if [ "$P99_TTFB" -gt 5000 ]; then
-    echo "✗ P99 TTFB exceeds 5000ms threshold"
-    FAIL=1
-  fi
-  
-  if [ "$VALID_STREAMS" -lt "$((CONCURRENT_STREAMS / 2))" ]; then
-    echo "✗ Less than 50% of streams completed successfully"
-    FAIL=1
-  fi
-  
-  # Write results
-  if [ "$FAIL" -eq 0 ]; then
-    echo "pass" > "${RESULTS_DIR}/result"
-    SUMMARY="${VALID_STREAMS}/${CONCURRENT_STREAMS} streams OK | P50 TTFB: ${P50_TTFB}ms | P99 TTFB: ${P99_TTFB}ms | Throughput: ${THROUGHPUT} streams/sec"
-  else
-    echo "fail" > "${RESULTS_DIR}/result"
-    SUMMARY="FAILED: ${VALID_STREAMS}/${CONCURRENT_STREAMS} streams completed | P99 TTFB: ${P99_TTFB}ms (threshold: 5000ms)"
-  fi
-  
-  # Write detailed metrics
-  cat > "${RESULTS_DIR}/metrics" <<EOF
-{
-  "test_type": "sse_streaming_load_test",
-  "timestamp": "$(date -u +%Y-%m-%dT%H:%M:%SZ)",
-  "configuration": {
-    "concurrent_streams": $CONCURRENT_STREAMS,
-    "events_per_stream": $EVENTS_PER_STREAM,
-    "event_interval_ms": $EVENT_INTERVAL_MS
-  },
-  "results": {
-    "streams_completed": $VALID_STREAMS,
-    "streams_total": $CONCURRENT_STREAMS,
-    "ttfb_ms": {
-      "min": $MIN_TTFB,
-      "p50": $P50_TTFB,
-      "p99": $P99_TTFB,
-      "max": $MAX_TTFB,
-      "avg": $AVG_TTFB
-    },
-    "throughput_streams_per_sec": $THROUGHPUT
-  },
-  "issues_tested": [
-    "#31: TCP backpressure for streaming LLM responses",
-    "#32: HTTP/2 multiplexing for concurrent streams",
-    "#33: Disable proxy buffering for SSE"
-  ]
-}
-EOF
-
-else
-  echo "✗ No valid streams collected"
-  echo "fail" > "${RESULTS_DIR}/result"
-  echo "no_valid_streams" > "${RESULTS_DIR}/summary"
-  echo '{"error":"no_valid_streams"}' > "${RESULTS_DIR}/metrics"
-  exit 1
-fi
-
-echo ""
-echo "═══ Summary ═══"
-echo "$SUMMARY"
-echo "$SUMMARY" > "${RESULTS_DIR}/summary"
-
-exit "$FAIL"

k8s/tekton/task-integration-test.yaml

@@ -1,75 +0,0 @@
-apiVersion: tekton.dev/v1
-kind: Task
-metadata:
-  name: integration-test
-  namespace: api
-  labels:
-    app: api-gateway
-    component: testing
-spec:
-  description: >
-    Spin up a gateway pod from the given image as a sidecar,
-    run curl-based integration tests, report pass/fail.
-  params:
-  - name: image
-    type: string
-    description: "Container image to test (repo:tag)"
-  - name: gateway-port
-    type: string
-    default: "8080"
-  results:
-  - name: result
-    type: string
-  - name: summary
-    type: string
-
-  sidecars:
-  - name: gateway
-    image: $(params.image)
-    env:
-    - name: LISTEN_ADDR
-      value: "0.0.0.0:$(params.gateway-port)"
-    - name: CONFIG_PATH
-      value: /etc/gateway/config.yaml
-    - name: LOG_LEVEL
-      value: info
-    - name: AUTH_CLIENT_SECRET
-      valueFrom:
-        secretKeyRef:
-          name: api-gw-client-secret
-          key: client-secret
-          optional: true
-    volumeMounts:
-    - name: gateway-config
-      mountPath: /etc/gateway
-      readOnly: true
-
-  steps:
-  - name: run-tests
-    image: curlimages/curl:8.13.0
-    env:
-    - name: GW
-      value: "http://localhost:$(params.gateway-port)"
-    - name: RESULTS_DIR
-      value: /tekton/results
-    command: ["sh", "/scripts/integration-test.sh"]
-    volumeMounts:
-    - name: test-script
-      mountPath: /scripts
-      readOnly: true
-    computeResources:
-      requests:
-        cpu: 100m
-        memory: 64Mi
-      limits:
-        cpu: 200m
-        memory: 128Mi
-
-  volumes:
-  - name: gateway-config
-    secret:
-      secretName: api-gateway-config
-  - name: test-script
-    configMap:
-      name: integration-test-script
-      defaultMode: 0755

k8s/tekton/task-load-test.yaml

@@ -1,101 +0,0 @@
-apiVersion: tekton.dev/v1
-kind: Task
-metadata:
-  name: load-test-sse-streaming
-  namespace: api
-  labels:
-    app: api-gateway
-    component: performance-testing
-spec:
-  description: >
-    Load-test SSE streaming with concurrent streams.
-    Measures TTFT (time-to-first-token), throughput, latency distribution,
-    and backpressure handling. Tests issues #31, #32, #33.
-  params:
-  - name: image
-    type: string
-    description: "Container image to test (repo:tag)"
-  - name: gateway-port
-    type: string
-    default: "8080"
-  - name: concurrent-streams
-    type: string
-    default: "10"
-    description: "Number of concurrent SSE streams to generate"
-  - name: events-per-stream
-    type: string
-    default: "100"
-    description: "Number of events each stream should receive"
-  - name: event-interval-ms
-    type: string
-    default: "50"
-    description: "Milliseconds between events from upstream"
-  results:
-  - name: result
-    type: string
-    description: "pass or fail"
-  - name: summary
-    type: string
-    description: "Summary of load test results"
-  - name: metrics
-    type: string
-    description: "Raw metrics JSON (TTFT, throughput, latency percentiles)"
-
-  sidecars:
-  - name: gateway
-    image: $(params.image)
-    env:
-    - name: LISTEN_ADDR
-      value: "0.0.0.0:$(params.gateway-port)"
-    - name: CONFIG_PATH
-      value: /etc/gateway/config.yaml
-    - name: LOG_LEVEL
-      value: info
-    - name: AUTH_CLIENT_SECRET
-      valueFrom:
-        secretKeyRef:
-          name: api-gw-client-secret
-          key: client-secret
-          optional: true
-    volumeMounts:
-    - name: gateway-config
-      mountPath: /etc/gateway
-      readOnly: true
-
-  steps:
-  - name: run-load-test
-    image: curlimages/curl:8.13.0
-    env:
-    - name: GW
-      value: "http://localhost:$(params.gateway-port)"
-    - name: CONCURRENT_STREAMS
-      value: $(params.concurrent-streams)
-    - name: EVENTS_PER_STREAM
-      value: $(params.events-per-stream)
-    - name: EVENT_INTERVAL_MS
-      value: $(params.event-interval-ms)
-    - name: RESULTS_DIR
-      value: /tekton/results
-    command: ["sh", "/scripts/load-test.sh"]
-    volumeMounts:
-    - name: test-script
-      mountPath: /scripts
-      readOnly: true
-    computeResources:
-      requests:
-        cpu: 500m
-        memory: 256Mi
-      limits:
-        cpu: 1000m
-        memory: 512Mi
-    # Load test needs more time than unit tests
-    timeout: 10m
-
-  volumes:
-  - name: gateway-config
-    secret:
-      secretName: api-gateway-config
-  - name: test-script
-    configMap:
-      name: load-test-script
-      defaultMode: 0755