feat: implement resumable chunked media upload with progress indicators in admin UI

CHANGELOG.md

@@ -12,6 +12,7 @@
 - Extended admin schedule and dashboard data endpoints with media duration totals, runtime strings, and media counts.
 - Added admin UI runtime display for schedule/dashboard plus media library edit/delete actions.
 - Added a dedicated plain TypeScript admin module for tab navigation, media CRUD actions, schedule/system analytics refresh, and moderation workflows without Alpine dependencies.
+- Added resumable chunked admin media upload flow with upload-session endpoints and client progress indicators.
 
 ### Changed
 
@@ -27,6 +28,7 @@
 - Implemented media upload duration probing with ffprobe and persisted media metadata to the database alongside filesystem storage.
 - Updated media listing to read from the media table and return duration metadata with HH:MM:SS runtime formatting.
 - Removed Tailwind and Alpine runtime/build dependencies from the frontend package configuration and eliminated Tailwind directives/warnings during production build.
+- Enforced 2GB upload ceiling plus server-side media file type/size validation for admin uploads.
 
 ## [1.0.3] - 2026-08-03
 

backend/chat/src/main.go

@@ -195,6 +195,36 @@ type AdminMediaResponse struct {
 	GeneratedAt string           `json:"generatedAt"`
 }
 
+type AdminMediaUploadInitRequest struct {
+	UploadID   string `json:"uploadId"`
+	FileName   string `json:"fileName"`
+	FileSize   int64  `json:"fileSize"`
+	MimeType   string `json:"mimeType"`
+	ChunkSize  int64  `json:"chunkSize"`
+	TotalChunks int   `json:"totalChunks"`
+}
+
+type AdminMediaUploadSession struct {
+	UploadID    string `json:"uploadId"`
+	FileName    string `json:"fileName"`
+	FileSize    int64  `json:"fileSize"`
+	MimeType    string `json:"mimeType"`
+	ChunkSize   int64  `json:"chunkSize"`
+	TotalChunks int    `json:"totalChunks"`
+	CreatedAt   string `json:"createdAt"`
+	UpdatedAt   string `json:"updatedAt"`
+}
+
+type AdminMediaUploadStatusResponse struct {
+	UploadID      string  `json:"uploadId"`
+	FileName      string  `json:"fileName"`
+	FileSize      int64   `json:"fileSize"`
+	ChunkSize     int64   `json:"chunkSize"`
+	TotalChunks   int     `json:"totalChunks"`
+	UploadedChunks int    `json:"uploadedChunks"`
+	Progress      float64 `json:"progress"`
+}
+
 type AdminLoginPayload struct {
 	Username string `json:"username"`
 	Password string `json:"password"`
@@ -209,6 +239,12 @@ var databaseDriverName = "sqlite"
 
 const adminSessionCookieName = "linearvoid_admin_session"
 
+const (
+	maxAdminUploadBytes      int64 = 2 * 1024 * 1024 * 1024
+	defaultAdminChunkSize    int64 = 8 * 1024 * 1024
+	maxAdminChunkSize        int64 = 32 * 1024 * 1024
+)
+
 // initRedis initializes Redis for presence, rate limiting, and pub/sub (ADR-007)
 func initRedis() {
 	redisAddress := os.Getenv("REDIS_URL")
@@ -938,6 +974,136 @@ func getMediaIDFromPath(path string) (uint, error) {
 	return uint(id), nil
 }
 
+func isAllowedMediaExtension(fileName string) bool {
+	ext := strings.ToLower(filepath.Ext(fileName))
+	switch ext {
+	case ".mp4", ".mov", ".mkv", ".webm", ".m4v", ".ts":
+		return true
+	default:
+		return false
+	}
+}
+
+func isAllowedMediaMime(mime string) bool {
+	mime = strings.TrimSpace(strings.ToLower(mime))
+	if mime == "" {
+		return true
+	}
+	if strings.HasPrefix(mime, "video/") {
+		return true
+	}
+	return mime == "application/octet-stream"
+}
+
+func getUploadWorkspaceDir() string {
+	return filepath.Join(getMediaDir(), ".uploads")
+}
+
+func getUploadSessionDir(uploadID string) string {
+	return filepath.Join(getUploadWorkspaceDir(), uploadID)
+}
+
+func getUploadSessionMetaPath(uploadID string) string {
+	return filepath.Join(getUploadSessionDir(uploadID), "session.json")
+}
+
+func getUploadChunkPath(uploadID string, chunkIndex int) string {
+	return filepath.Join(getUploadSessionDir(uploadID), fmt.Sprintf("chunk-%06d.part", chunkIndex))
+}
+
+func loadUploadSession(uploadID string) (AdminMediaUploadSession, error) {
+	var session AdminMediaUploadSession
+	data, err := os.ReadFile(getUploadSessionMetaPath(uploadID))
+	if err != nil {
+		return session, err
+	}
+	if err := json.Unmarshal(data, &session); err != nil {
+		return session, err
+	}
+	return session, nil
+}
+
+func saveUploadSession(session AdminMediaUploadSession) error {
+	if err := os.MkdirAll(getUploadSessionDir(session.UploadID), 0o755); err != nil {
+		return err
+	}
+	data, err := json.MarshalIndent(session, "", "  ")
+	if err != nil {
+		return err
+	}
+	return os.WriteFile(getUploadSessionMetaPath(session.UploadID), data, 0o644)
+}
+
+func countUploadedChunks(uploadID string, totalChunks int) int {
+	uploaded := 0
+	for i := 0; i < totalChunks; i++ {
+		if _, err := os.Stat(getUploadChunkPath(uploadID, i)); err == nil {
+			uploaded++
+		}
+	}
+	return uploaded
+}
+
+func validateUploadID(uploadID string) bool {
+	if len(uploadID) < 16 || len(uploadID) > 128 {
+		return false
+	}
+	for _, r := range uploadID {
+		if (r < 'a' || r > 'f') && (r < '0' || r > '9') {
+			return false
+		}
+	}
+	return true
+}
+
+func buildUploadStatus(session AdminMediaUploadSession) AdminMediaUploadStatusResponse {
+	uploadedChunks := countUploadedChunks(session.UploadID, session.TotalChunks)
+	progress := 0.0
+	if session.TotalChunks > 0 {
+		progress = (float64(uploadedChunks) / float64(session.TotalChunks)) * 100
+	}
+
+	return AdminMediaUploadStatusResponse{
+		UploadID:      session.UploadID,
+		FileName:      session.FileName,
+		FileSize:      session.FileSize,
+		ChunkSize:     session.ChunkSize,
+		TotalChunks:   session.TotalChunks,
+		UploadedChunks: uploadedChunks,
+		Progress:      progress,
+	}
+}
+
+func uniqueMediaTargetPath(mediaDir, fileName string) string {
+	baseName := filepath.Base(fileName)
+	ext := filepath.Ext(baseName)
+	nameOnly := strings.TrimSuffix(baseName, ext)
+	candidate := filepath.Join(mediaDir, baseName)
+
+	for i := 1; ; i++ {
+		if _, err := os.Stat(candidate); os.IsNotExist(err) {
+			return candidate
+		}
+		candidate = filepath.Join(mediaDir, fmt.Sprintf("%s-%d%s", nameOnly, i, ext))
+	}
+}
+
+func detectMediaMime(filePath string) (string, error) {
+	f, err := os.Open(filePath)
+	if err != nil {
+		return "", err
+	}
+	defer f.Close()
+
+	head := make([]byte, 512)
+	n, err := f.Read(head)
+	if err != nil && err != io.EOF {
+		return "", err
+	}
+
+	return http.DetectContentType(head[:n]), nil
+}
+
 func mediaEntryFromRecord(record Media) MediaFileEntry {
 	return MediaFileEntry{
 		ID:              record.ID,
@@ -1020,13 +1186,27 @@ func handleAdminMedia(w http.ResponseWriter, r *http.Request) {
 		}
 		defer file.Close()
 
+		fileName := filepath.Base(strings.TrimSpace(header.Filename))
+		if fileName == "" {
+			http.Error(w, "missing file name", http.StatusBadRequest)
+			return
+		}
+		if !isAllowedMediaExtension(fileName) {
+			http.Error(w, "unsupported file type", http.StatusBadRequest)
+			return
+		}
+		if header.Size > maxAdminUploadBytes {
+			http.Error(w, "file exceeds 2GB limit", http.StatusRequestEntityTooLarge)
+			return
+		}
+
 		mediaDir := getMediaDir()
 		if err := os.MkdirAll(mediaDir, 0o755); err != nil {
 			http.Error(w, fmt.Sprintf("failed to ensure media directory: %v", err), http.StatusInternalServerError)
 			return
 		}
 
-		targetPath := filepath.Join(mediaDir, filepath.Base(header.Filename))
+		targetPath := uniqueMediaTargetPath(mediaDir, fileName)
 		targetFile, err := os.Create(targetPath)
 		if err != nil {
 			http.Error(w, fmt.Sprintf("failed to create media file: %v", err), http.StatusInternalServerError)
@@ -1051,6 +1231,23 @@ func handleAdminMedia(w http.ResponseWriter, r *http.Request) {
 			http.Error(w, fmt.Sprintf("failed to read media file info: %v", err), http.StatusInternalServerError)
 			return
 		}
+		if fileInfo.Size() > maxAdminUploadBytes {
+			_ = os.Remove(targetPath)
+			http.Error(w, "file exceeds 2GB limit", http.StatusRequestEntityTooLarge)
+			return
+		}
+
+		detectedMime, err := detectMediaMime(targetPath)
+		if err != nil {
+			_ = os.Remove(targetPath)
+			http.Error(w, fmt.Sprintf("failed to inspect media file: %v", err), http.StatusBadRequest)
+			return
+		}
+		if !strings.HasPrefix(strings.ToLower(detectedMime), "video/") {
+			_ = os.Remove(targetPath)
+			http.Error(w, fmt.Sprintf("unsupported media content type: %s", detectedMime), http.StatusBadRequest)
+			return
+		}
 
 		durationSeconds, err := probeMediaDurationSeconds(targetPath)
 		if err != nil {
@@ -1059,10 +1256,10 @@ func handleAdminMedia(w http.ResponseWriter, r *http.Request) {
 			return
 		}
 
-		filename := filepath.Base(header.Filename)
+		filename := filepath.Base(targetPath)
 		mediaRecord := Media{
 			Filename:        filename,
-			OriginalName:    header.Filename,
+			OriginalName:    fileName,
 			Path:            targetPath,
 			SizeBytes:       fileInfo.Size(),
 			DurationSeconds: durationSeconds,
@@ -1089,6 +1286,336 @@ func handleAdminMedia(w http.ResponseWriter, r *http.Request) {
 	}
 }
 
+func handleAdminMediaUploads(w http.ResponseWriter, r *http.Request) {
+	const basePath = "/api/admin/media/uploads"
+
+	if r.URL.Path == basePath {
+		if r.Method != http.MethodPost {
+			http.Error(w, "method not allowed", http.StatusMethodNotAllowed)
+			return
+		}
+
+		var payload AdminMediaUploadInitRequest
+		if err := json.NewDecoder(r.Body).Decode(&payload); err != nil {
+			http.Error(w, fmt.Sprintf("invalid request body: %v", err), http.StatusBadRequest)
+			return
+		}
+
+		fileName := filepath.Base(strings.TrimSpace(payload.FileName))
+		if fileName == "" {
+			http.Error(w, "file name is required", http.StatusBadRequest)
+			return
+		}
+		if !isAllowedMediaExtension(fileName) {
+			http.Error(w, "unsupported file type", http.StatusBadRequest)
+			return
+		}
+		if payload.FileSize <= 0 {
+			http.Error(w, "file size must be positive", http.StatusBadRequest)
+			return
+		}
+		if payload.FileSize > maxAdminUploadBytes {
+			http.Error(w, "file exceeds 2GB limit", http.StatusRequestEntityTooLarge)
+			return
+		}
+		if !isAllowedMediaMime(payload.MimeType) {
+			http.Error(w, "unsupported mime type", http.StatusBadRequest)
+			return
+		}
+
+		chunkSize := payload.ChunkSize
+		if chunkSize <= 0 {
+			chunkSize = defaultAdminChunkSize
+		}
+		if chunkSize > maxAdminChunkSize {
+			http.Error(w, "chunk size exceeds server limit", http.StatusBadRequest)
+			return
+		}
+
+		expectedChunks := int((payload.FileSize + chunkSize - 1) / chunkSize)
+		if payload.TotalChunks <= 0 {
+			payload.TotalChunks = expectedChunks
+		}
+		if payload.TotalChunks != expectedChunks {
+			http.Error(w, "total chunk count mismatch", http.StatusBadRequest)
+			return
+		}
+
+		uploadID := strings.TrimSpace(payload.UploadID)
+		if uploadID != "" && !validateUploadID(uploadID) {
+			http.Error(w, "invalid upload id", http.StatusBadRequest)
+			return
+		}
+
+		now := time.Now().UTC().Format(time.RFC3339)
+		session := AdminMediaUploadSession{}
+
+		if uploadID != "" {
+			loaded, err := loadUploadSession(uploadID)
+			if err == nil {
+				if loaded.FileName != fileName || loaded.FileSize != payload.FileSize {
+					http.Error(w, "upload id does not match selected file", http.StatusConflict)
+					return
+				}
+				session = loaded
+			} else if !os.IsNotExist(err) {
+				http.Error(w, fmt.Sprintf("failed to resume upload session: %v", err), http.StatusInternalServerError)
+				return
+			}
+		}
+
+		if session.UploadID == "" {
+			randomID, err := generateSessionToken()
+			if err != nil {
+				http.Error(w, fmt.Sprintf("failed to create upload session: %v", err), http.StatusInternalServerError)
+				return
+			}
+
+			session = AdminMediaUploadSession{
+				UploadID:    randomID,
+				FileName:    fileName,
+				FileSize:    payload.FileSize,
+				MimeType:    payload.MimeType,
+				ChunkSize:   chunkSize,
+				TotalChunks: payload.TotalChunks,
+				CreatedAt:   now,
+				UpdatedAt:   now,
+			}
+		} else {
+			session.UpdatedAt = now
+		}
+
+		if err := saveUploadSession(session); err != nil {
+			http.Error(w, fmt.Sprintf("failed to persist upload session: %v", err), http.StatusInternalServerError)
+			return
+		}
+
+		w.Header().Set("Content-Type", "application/json")
+		json.NewEncoder(w).Encode(buildUploadStatus(session))
+		return
+	}
+
+	if !strings.HasPrefix(r.URL.Path, basePath+"/") {
+		http.NotFound(w, r)
+		return
+	}
+
+	remainder := strings.TrimPrefix(r.URL.Path, basePath+"/")
+	parts := strings.Split(strings.Trim(remainder, "/"), "/")
+	if len(parts) == 0 || strings.TrimSpace(parts[0]) == "" {
+		http.Error(w, "missing upload id", http.StatusBadRequest)
+		return
+	}
+
+	uploadID := strings.TrimSpace(parts[0])
+	if !validateUploadID(uploadID) {
+		http.Error(w, "invalid upload id", http.StatusBadRequest)
+		return
+	}
+
+	session, err := loadUploadSession(uploadID)
+	if err != nil {
+		if os.IsNotExist(err) {
+			http.Error(w, "upload session not found", http.StatusNotFound)
+			return
+		}
+		http.Error(w, fmt.Sprintf("failed to read upload session: %v", err), http.StatusInternalServerError)
+		return
+	}
+
+	if len(parts) == 1 {
+		if r.Method != http.MethodGet {
+			http.Error(w, "method not allowed", http.StatusMethodNotAllowed)
+			return
+		}
+
+		w.Header().Set("Content-Type", "application/json")
+		json.NewEncoder(w).Encode(buildUploadStatus(session))
+		return
+	}
+
+	if len(parts) != 2 {
+		http.NotFound(w, r)
+		return
+	}
+
+	subresource := parts[1]
+	switch subresource {
+	case "chunk":
+		if r.Method != http.MethodPut {
+			http.Error(w, "method not allowed", http.StatusMethodNotAllowed)
+			return
+		}
+
+		chunkIndexRaw := strings.TrimSpace(r.URL.Query().Get("index"))
+		chunkIndex, err := strconv.Atoi(chunkIndexRaw)
+		if err != nil || chunkIndex < 0 || chunkIndex >= session.TotalChunks {
+			http.Error(w, "invalid chunk index", http.StatusBadRequest)
+			return
+		}
+
+		chunkPath := getUploadChunkPath(uploadID, chunkIndex)
+		tmpPath := chunkPath + ".tmp"
+
+		chunkFile, err := os.Create(tmpPath)
+		if err != nil {
+			http.Error(w, fmt.Sprintf("failed to open chunk target: %v", err), http.StatusInternalServerError)
+			return
+		}
+
+		maxRead := session.ChunkSize + 1
+		written, copyErr := io.Copy(chunkFile, io.LimitReader(r.Body, maxRead))
+		closeErr := chunkFile.Close()
+		if copyErr != nil || closeErr != nil {
+			_ = os.Remove(tmpPath)
+			http.Error(w, "failed to persist upload chunk", http.StatusInternalServerError)
+			return
+		}
+
+		expectedMax := session.ChunkSize
+		if chunkIndex == session.TotalChunks-1 {
+			remaining := session.FileSize - (int64(chunkIndex) * session.ChunkSize)
+			if remaining > 0 {
+				expectedMax = remaining
+			}
+		}
+
+		if written <= 0 || written > expectedMax {
+			_ = os.Remove(tmpPath)
+			http.Error(w, "invalid chunk size", http.StatusBadRequest)
+			return
+		}
+
+		if err := os.Rename(tmpPath, chunkPath); err != nil {
+			_ = os.Remove(tmpPath)
+			http.Error(w, fmt.Sprintf("failed to finalize chunk: %v", err), http.StatusInternalServerError)
+			return
+		}
+
+		session.UpdatedAt = time.Now().UTC().Format(time.RFC3339)
+		if err := saveUploadSession(session); err != nil {
+			http.Error(w, fmt.Sprintf("failed to update upload session: %v", err), http.StatusInternalServerError)
+			return
+		}
+
+		w.Header().Set("Content-Type", "application/json")
+		json.NewEncoder(w).Encode(buildUploadStatus(session))
+	case "complete":
+		if r.Method != http.MethodPost {
+			http.Error(w, "method not allowed", http.StatusMethodNotAllowed)
+			return
+		}
+
+		if countUploadedChunks(uploadID, session.TotalChunks) != session.TotalChunks {
+			http.Error(w, "upload is incomplete", http.StatusBadRequest)
+			return
+		}
+
+		mediaDir := getMediaDir()
+		if err := os.MkdirAll(mediaDir, 0o755); err != nil {
+			http.Error(w, fmt.Sprintf("failed to ensure media directory: %v", err), http.StatusInternalServerError)
+			return
+		}
+
+		targetPath := uniqueMediaTargetPath(mediaDir, session.FileName)
+		targetFile, err := os.Create(targetPath)
+		if err != nil {
+			http.Error(w, fmt.Sprintf("failed to create media file: %v", err), http.StatusInternalServerError)
+			return
+		}
+
+		var totalWritten int64
+		for i := 0; i < session.TotalChunks; i++ {
+			chunkPath := getUploadChunkPath(uploadID, i)
+			chunkReader, err := os.Open(chunkPath)
+			if err != nil {
+				targetFile.Close()
+				_ = os.Remove(targetPath)
+				http.Error(w, fmt.Sprintf("missing chunk %d", i), http.StatusBadRequest)
+				return
+			}
+
+			written, err := io.Copy(targetFile, chunkReader)
+			_ = chunkReader.Close()
+			if err != nil {
+				targetFile.Close()
+				_ = os.Remove(targetPath)
+				http.Error(w, fmt.Sprintf("failed to assemble media file: %v", err), http.StatusInternalServerError)
+				return
+			}
+			totalWritten += written
+		}
+
+		if err := targetFile.Close(); err != nil {
+			_ = os.Remove(targetPath)
+			http.Error(w, fmt.Sprintf("failed to finalize media file: %v", err), http.StatusInternalServerError)
+			return
+		}
+
+		if totalWritten != session.FileSize {
+			_ = os.Remove(targetPath)
+			http.Error(w, "assembled file size mismatch", http.StatusBadRequest)
+			return
+		}
+
+		detectedMime, err := detectMediaMime(targetPath)
+		if err != nil {
+			_ = os.Remove(targetPath)
+			http.Error(w, fmt.Sprintf("failed to inspect media file: %v", err), http.StatusBadRequest)
+			return
+		}
+		if !strings.HasPrefix(strings.ToLower(detectedMime), "video/") {
+			_ = os.Remove(targetPath)
+			http.Error(w, fmt.Sprintf("unsupported media content type: %s", detectedMime), http.StatusBadRequest)
+			return
+		}
+
+		durationSeconds, err := probeMediaDurationSeconds(targetPath)
+		if err != nil {
+			_ = os.Remove(targetPath)
+			http.Error(w, fmt.Sprintf("failed to probe media duration: %v", err), http.StatusBadRequest)
+			return
+		}
+
+		fileInfo, err := os.Stat(targetPath)
+		if err != nil {
+			_ = os.Remove(targetPath)
+			http.Error(w, fmt.Sprintf("failed to read media file info: %v", err), http.StatusInternalServerError)
+			return
+		}
+
+		filename := filepath.Base(targetPath)
+		mediaRecord := Media{
+			Filename:        filename,
+			OriginalName:    session.FileName,
+			Path:            targetPath,
+			SizeBytes:       fileInfo.Size(),
+			DurationSeconds: durationSeconds,
+			Status:          "ready",
+			Title:           strings.TrimSuffix(filename, filepath.Ext(filename)),
+			Tags:            "",
+		}
+		if err := db.Create(&mediaRecord).Error; err != nil {
+			_ = os.Remove(targetPath)
+			http.Error(w, fmt.Sprintf("failed to persist media metadata: %v", err), http.StatusInternalServerError)
+			return
+		}
+
+		_ = os.RemoveAll(getUploadSessionDir(uploadID))
+
+		files, err := listMediaFiles()
+		if err != nil {
+			http.Error(w, fmt.Sprintf("failed to list media files: %v", err), http.StatusInternalServerError)
+			return
+		}
+
+		w.Header().Set("Content-Type", "application/json")
+		json.NewEncoder(w).Encode(AdminMediaResponse{Files: files, GeneratedAt: time.Now().UTC().Format(time.RFC3339)})
+	default:
+		http.NotFound(w, r)
+	}
+}
+
 func handleAdminMediaByID(w http.ResponseWriter, r *http.Request) {
 	mediaID, err := getMediaIDFromPath(r.URL.Path)
 	if err != nil {
@@ -1424,6 +1951,8 @@ func main() {
 	http.HandleFunc("/api/admin/users", requireAdminAuth(handleAdminUsers))
 	http.HandleFunc("/api/admin/schedule", requireAdminAuth(handleAdminSchedule))
 	http.HandleFunc("/api/admin/media", requireAdminAuth(handleAdminMedia))
+	http.HandleFunc("/api/admin/media/uploads", requireAdminAuth(handleAdminMediaUploads))
+	http.HandleFunc("/api/admin/media/uploads/", requireAdminAuth(handleAdminMediaUploads))
 	http.HandleFunc("/api/admin/media/", requireAdminAuth(handleAdminMediaByID))
 	http.HandleFunc("/metrics", handleMetrics)
 	http.HandleFunc("/health", func(w http.ResponseWriter, r *http.Request) {

docs/architecture/README.md

@@ -315,11 +315,96 @@ All source assets must be pre-normalized (H.264/AVC, AAC-LC, constant 30 fps, 2s
 
 ### Monitoring & Resilience
 
-Alert on no new segment (>30–60s), low cache hits, high R2 ops, WebSocket errors. Maintain emergency slate, auto-restart, weekly backups, incident runbook.
+Linear Void uses a two-layer monitoring model:
+
+1. **Application layer (chat + platform health)** via Prometheus metrics and a lightweight Grafana dashboard.
+2. **Infrastructure/runtime layer (Prometheus self-observability, TSDB, query engine, Go runtime)** via a detailed Grafana dashboard.
+
+#### Prometheus Baseline
+
+- Config file: `monitoring/prometheus/prometheus.yml`
+- Default scrape interval: `15s`
+- Current scrape jobs: `chat` -> `chat:3000`, `prometheus` -> `prometheus:9090`.
+
+Recommended next-step scrape targets (if/when exporters are introduced):
+
+- `nginx` (via nginx-exporter)
+- `redis` (via redis-exporter)
+- `postgres` (via postgres-exporter)
+- `node` (via node-exporter)
+
+#### Grafana Dashboards
+
+- `monitoring/grafana/dashboard.json` (Linear Void app metrics: connected clients, messages, moderation actions, Redis reachability, admin sessions, scrape health).
+- `monitoring/grafana/dashboards/dashboard.json` (Prometheus operational visibility: status, uptime, CPU/memory, TSDB ingestion/churn/errors, HTTP latencies, query load, GC/scheduler).
+
+Use the app dashboard for service-level behavior and the Prometheus overview dashboard for platform diagnostics and capacity planning.
+
+#### Alerting Rules (Prometheus Rule Groups)
+
+Define alert rules as grouped policies (for example in `monitoring/prometheus/alerts.yml`) and include them from `prometheus.yml`.
+
+Minimum recommended alert set:
+
+- **Availability**
+  `up{job="chat"} == 0` for `2m`; `up{job="prometheus"} == 0` for `2m`.
+- **Chat service health**
+  `linearvoid_chat_redis_up == 0` for `2m`; sudden disconnect spike / connected clients collapse.
+- **Playout continuity**
+  No HLS segment progression for `30-60s` (from playout-specific metric when available).
+- **Prometheus capacity and ingestion health**
+  Sustained growth in `prometheus_tsdb_wal_writes_failed_total` or `prometheus_tsdb_compactions_failed_total`, abnormal jump in `prometheus_tsdb_out_of_order_samples_total`, and high `prometheus_engine_queries` near concurrent limit.
+- **Latency and user-impact**
+  Elevated p99 handler latency from `prometheus_http_request_duration_seconds_bucket` and elevated p99 query execution latency from `prometheus_engine_query_duration_histogram_seconds_bucket`.
+
+Route warning/critical severities to the team channel and keep runbook links attached to each alert definition.
+
+Operational resilience baseline:
+
+- Emergency slate fallback for playout failure.
+- Auto-restart policies for playout/chat/nginx containers.
+- Weekly backup and restore drills for stateful data (`data/chat`, playlist metadata, Postgres).
+- Incident runbook with triage order: edge reachability -> origin health -> playout progression -> chat connectivity -> data-plane dependencies.
 
 ### Security & Moderation
 
-HTTPS/WSS only, strict CORS, Cloudflare WAF, authenticated admin paths, rate limiting, immutable moderation log. Private DMs not E2EE by default.
+Security is split between edge controls (Cloudflare), reverse proxy controls (nginx), and application controls (chat/admin backend).
+
+#### Transport and Edge Protection
+
+- Public traffic uses HTTPS/WSS at the edge.
+- Cloudflare WAF and rate limiting are part of the baseline (see `infrastructure/cloudflare/cache-rules.md`).
+- Cloudflare Worker can enforce immutable cache headers for segment paths (`infrastructure/cloudflare/worker.js`).
+
+#### Reverse Proxy Enforcement (nginx)
+
+- Admin UI and admin API paths are protected by `auth_request` before reaching backend handlers (`/admin/`, `/api/admin/`).
+- Unauthorized admin UI requests are redirected to `/admin/login/`.
+- Unauthorized admin API requests return JSON `401` from a dedicated location handler.
+- WebSocket upgrade headers are explicitly forwarded for `/ws`.
+
+#### Admin Authentication and Session Security
+
+- Admin authentication is cookie-session based (`linearvoid_admin_session`).
+- Session cookie controls in backend include `HttpOnly`, `SameSite=Strict`, and `Secure` when request is HTTPS (derived from TLS or `X-Forwarded-Proto`).
+- Session expiration is enforced server-side.
+
+#### Rate Limiting and Abuse Controls
+
+- Chat message rate limiting uses Redis `INCR + EXPIRE` windowing.
+- Current baseline in chat handler: `>10` messages within `10s` triggers a user-facing throttle response.
+- If Redis is unavailable, presence/rate-limit features degrade gracefully (warning logged; core chat remains available).
+
+#### CORS and Cross-Origin Behavior
+
+- HLS endpoints exposed by nginx include explicit `Access-Control-Allow-Origin: *` for player compatibility.
+- Admin/authenticated routes are expected to run same-origin behind nginx auth gates.
+
+#### Moderation and Privacy
+
+- Moderation commands (`/mod`, `/mute`, `/ban`) are handled in backend chat flow and persisted through chat storage paths.
+- Private DMs are application-level private channels, not end-to-end encrypted in current architecture.
+- Moderation and audit retention policies should be formalized in runbook/ops docs as part of production hardening.
 
 ### Chat
 
@@ -354,6 +439,112 @@ These ADRs together form the canonical decision log.
 
 See **Quality Goals** table in the Introduction section. Primary scenarios focus on cost (near-zero egress), availability (auto-restart + fallback), scalability (edge caching), and usability (synchronized player + responsive chat).
 
+### Performance Benchmarks and Capacity Planning
+
+#### Baseline SLO Targets (v1)
+
+- Playback startup: target < 4s after first manifest request on warm cache.
+- Steady-state playback: no segment starvation during normal operation.
+- End-to-end HLS latency: expected 15-35s (standard HLS trade-off).
+- Chat delivery latency: p95 < 500ms inside same region under normal load.
+- Admin page responsiveness: p95 API response < 1s for common read operations.
+
+#### Workload Assumptions
+
+- Primary audience in US; origin in US-East.
+- Edge cache serves most segment traffic; origin handles manifest churn and cache misses.
+- Chat traffic scales with concurrent viewers but remains low-bandwidth compared to video.
+
+#### Initial Capacity Model
+
+- Video bitrate envelopes (from ADR-001):
+  - 720p30: ~2.6-4.2 Mbps total with audio.
+  - 1080p30: ~5.1-8.2 Mbps total with audio.
+- Storage planning for 48h rolling library:
+  - 720p30: ~57-90 GB raw (allocate ~80-110 GB with headroom).
+  - 1080p30: ~110-175 GB raw (allocate ~130-180 GB with headroom).
+- Cost behavior:
+  - Viewer scale is mostly constrained by cache efficiency and request volume, not by direct origin egress.
+
+#### Benchmark Plan
+
+- Playback path:
+  - Measure time-to-first-frame and rebuffer events from multiple US regions.
+  - Track manifest freshness and segment availability at edge.
+- Chat path:
+  - Load-test concurrent websocket connections and message fan-out.
+  - Measure p50/p95 send-to-receive latency and Redis fallback behavior.
+- Admin/API path:
+  - Benchmark playlist/system endpoints for p95 latency and error rate.
+- Platform path:
+  - Observe TSDB ingestion, query p99, and GC pause behavior in Grafana.
+
+#### Capacity Triggers and Actions
+
+- Trigger: sustained viewer growth with rising cache-miss ratio.
+  - Action: tighten cache policy, enable/verify Tiered Cache, review manifest TTL.
+- Trigger: chat p95 latency drift or websocket error growth.
+  - Action: scale chat service, tune Redis, separate noisy moderation workloads.
+- Trigger: Prometheus WAL/compaction failures or query saturation.
+  - Action: tune retention/cardinality, increase resources, split dashboards/queries.
+- Trigger: origin CPU/memory pressure on playout host.
+  - Action: optimize FFmpeg profile, isolate services, add secondary origin.
+
+### Disaster Recovery and Backup Procedures
+
+#### Recovery Targets
+
+- RPO target: <= 24h for chat/moderation/admin metadata.
+- RTO target: <= 60 minutes for restoring baseline streaming + chat operations.
+
+#### Backup Scope
+
+- Persistent service volumes:
+  - Postgres data (`postgres-data` volume).
+  - Redis append-only persistence (`redis-data` volume) where enabled.
+  - Prometheus long-term TSDB (`prometheus-data` volume) if historical metrics retention is required.
+  - Grafana state (`grafana-data` volume) if dashboards/users are managed in-instance.
+- Host-mounted state directories:
+  - `data/chat`
+  - `data/playlist`
+  - `data/media` (authoritative source may be R2/object storage)
+  - `data/hls` (optional; can be regenerated by playout)
+- Configuration and infra source of truth:
+  - Compose files, nginx config, monitoring configs, and environment template.
+
+#### Backup Cadence
+
+- Daily logical Postgres backups (plus weekly full snapshot).
+- Daily sync of chat/playlist state directories.
+- Weekly integrity check by restoring backups into an isolated environment.
+- Retention policy baseline:
+  - Daily backups: 14 days
+  - Weekly backups: 8 weeks
+  - Monthly backups: 6 months
+
+#### Recovery Runbook (Minimum)
+
+1. Restore infrastructure configuration (compose, nginx, env, monitoring config).
+2. Restore Postgres and Redis persisted state.
+3. Restore `data/playlist` and chat persistence directories.
+4. Rehydrate media from authoritative object storage if local media is missing.
+5. Start stack and validate in order:
+   - `playout` health endpoint
+   - `chat` health endpoint
+   - nginx `/health`
+   - HLS playlist availability
+   - websocket chat connectivity
+6. Verify admin authentication and moderation audit visibility.
+7. Announce recovery and continue elevated monitoring for at least one playlist cycle.
+
+#### Failure Modes and Strategy
+
+- Single-host loss: redeploy stack on standby host, restore data backups, repoint DNS/edge origin.
+- Storage corruption: restore last known-good snapshot and replay latest logical backups.
+- Partial service failure: replace only impacted service and restore scoped data (for example Postgres only).
+
+Document and rehearse this runbook quarterly; recovery that is not exercised is not reliable.
+
 ## Risks and Technical Debts
 
 - Cloudflare ToS risk for heavy video on free tier (use R2 path; fallback to BunnyCDN if challenged).

frontend/admin/index.html

@@ -64,9 +64,14 @@
                     <button id="reload-media-btn" type="button" class="btn btn-secondary">Reload library</button>
                 </div>
 
-                <div class="upload-dropzone">
+                <div id="upload-dropzone" class="upload-dropzone">
                     <input type="file" id="video-upload" accept="video/*,.mp4,.mov,.mkv,.webm" hidden />
                     <button id="upload-trigger-btn" type="button" class="btn btn-primary btn-large">Drag and Drop or Click to Upload</button>
+                    <p class="small-muted">Resumable chunk upload enabled • up to 2GB per file.</p>
+                    <div id="media-upload-progress-wrap" class="upload-progress" hidden>
+                        <progress id="media-upload-progress" value="0" max="100"></progress>
+                        <p id="media-upload-progress-text" class="small-muted">Uploading (0%)</p>
+                    </div>
                     <p id="media-status" class="status-line" aria-live="polite">Loading media library...</p>
                 </div>
 

frontend/src/admin.ts

@@ -33,12 +33,84 @@ const adminConfig = {
       : 50,
 };
 
+const MAX_UPLOAD_BYTES = 2 * 1024 * 1024 * 1024;
+const UPLOAD_CHUNK_BYTES = 8 * 1024 * 1024;
+const UPLOAD_RESUME_KEY_PREFIX = "linearvoid-upload-resume:";
+
 const state = {
   mediaUploading: false,
   moderationSubmitting: false,
   playlistSaving: false,
 };
 
+const uploadProgressWrap = () =>
+  document.getElementById("media-upload-progress-wrap") as HTMLElement | null;
+
+const uploadProgressBar = () =>
+  document.getElementById("media-upload-progress") as HTMLProgressElement | null;
+
+const uploadProgressText = () =>
+  document.getElementById("media-upload-progress-text") as HTMLElement | null;
+
+const setUploadProgress = (value: number, total: number, label: string) => {
+  const wrap = uploadProgressWrap();
+  const progress = uploadProgressBar();
+  const text = uploadProgressText();
+  if (!wrap || !progress || !text) return;
+
+  wrap.hidden = false;
+  progress.max = total;
+  progress.value = value;
+
+  const pct = total > 0 ? Math.min(100, Math.round((value / total) * 100)) : 0;
+  text.textContent = `${label} (${pct}%)`;
+};
+
+const hideUploadProgress = () => {
+  const wrap = uploadProgressWrap();
+  if (wrap) wrap.hidden = true;
+};
+
+const getFileFingerprint = (file: File) =>
+  `${file.name}:${file.size}:${file.lastModified}`;
+
+const getResumeStorageKey = (fingerprint: string) =>
+  `${UPLOAD_RESUME_KEY_PREFIX}${fingerprint}`;
+
+const getStoredUploadId = (fingerprint: string) => {
+  try {
+    return window.localStorage.getItem(getResumeStorageKey(fingerprint)) || "";
+  } catch {
+    return "";
+  }
+};
+
+const setStoredUploadId = (fingerprint: string, uploadId: string) => {
+  try {
+    window.localStorage.setItem(getResumeStorageKey(fingerprint), uploadId);
+  } catch {
+    // ignore storage failures
+  }
+};
+
+const clearStoredUploadId = (fingerprint: string) => {
+  try {
+    window.localStorage.removeItem(getResumeStorageKey(fingerprint));
+  } catch {
+    // ignore storage failures
+  }
+};
+
+const readErrorMessage = async (response: Response) => {
+  const fallback = `HTTP ${response.status}`;
+  try {
+    const text = (await response.text()).trim();
+    return text || fallback;
+  } catch {
+    return fallback;
+  }
+};
+
 const setText = (id: string, text: string) => {
   const el = document.getElementById(id);
   if (el) el.textContent = text;
@@ -330,30 +402,110 @@ async function refreshMediaLibrary() {
 
 async function uploadVideo(file: File) {
   if (state.mediaUploading) return;
+
+  if (file.size <= 0) {
+    setStatus("media-status", "Cannot upload an empty file.", true);
+    return;
+  }
+  if (file.size > MAX_UPLOAD_BYTES) {
+    setStatus("media-status", "File exceeds 2GB upload limit.", true);
+    return;
+  }
+
   state.mediaUploading = true;
-  setStatus("media-status", `Uploading ${file.name}...`);
+  setStatus("media-status", `Preparing upload for ${file.name}...`);
 
   try {
-    const formData = new FormData();
+    const totalChunks = Math.ceil(file.size / UPLOAD_CHUNK_BYTES);
-    formData.append("file", file);
+    const fingerprint = getFileFingerprint(file);
 
-    const response = await fetch("/api/admin/media", {
+    const initResponse = await fetch("/api/admin/media/uploads", {
       method: "POST",
-      body: formData,
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify({
+        uploadId: getStoredUploadId(fingerprint),
+        fileName: file.name,
+        fileSize: file.size,
+        mimeType: file.type,
+        chunkSize: UPLOAD_CHUNK_BYTES,
+        totalChunks,
+      }),
     });
-    if (!response.ok) throw new Error(`HTTP ${response.status}`);
 
-    const payload = await response.json();
+    if (!initResponse.ok) {
+      throw new Error(await readErrorMessage(initResponse));
+    }
+
+    const initPayload = await initResponse.json();
+    const uploadId = String(initPayload.uploadId || "");
+    if (!uploadId) {
+      throw new Error("Upload session could not be initialized.");
+    }
+
+    setStoredUploadId(fingerprint, uploadId);
+
+    const alreadyUploaded = Number(initPayload.uploadedChunks || 0);
+    const effectiveTotalChunks = Number(initPayload.totalChunks || totalChunks);
+    const resumeFrom = Math.min(Math.max(alreadyUploaded, 0), effectiveTotalChunks);
+
+    setUploadProgress(resumeFrom, effectiveTotalChunks, "Uploading chunks");
+
+    for (let chunkIndex = resumeFrom; chunkIndex < effectiveTotalChunks; chunkIndex += 1) {
+      const start = chunkIndex * UPLOAD_CHUNK_BYTES;
+      const end = Math.min(file.size, start + UPLOAD_CHUNK_BYTES);
+      const chunk = file.slice(start, end);
+
+      const chunkResponse = await fetch(
+        `/api/admin/media/uploads/${encodeURIComponent(uploadId)}/chunk?index=${chunkIndex}`,
+        {
+          method: "PUT",
+          headers: { "Content-Type": "application/octet-stream" },
+          body: chunk,
+        },
+      );
+
+      if (!chunkResponse.ok) {
+        throw new Error(await readErrorMessage(chunkResponse));
+      }
+
+      setUploadProgress(chunkIndex + 1, effectiveTotalChunks, "Uploading chunks");
+      setStatus(
+        "media-status",
+        `Uploading ${file.name} (${chunkIndex + 1}/${effectiveTotalChunks} chunks)...`,
+      );
+    }
+
+    const completeResponse = await fetch(
+      `/api/admin/media/uploads/${encodeURIComponent(uploadId)}/complete`,
+      {
+        method: "POST",
+      },
+    );
+
+    if (!completeResponse.ok) {
+      throw new Error(await readErrorMessage(completeResponse));
+    }
+
+    setUploadProgress(effectiveTotalChunks, effectiveTotalChunks, "Finalizing");
+
+    const payload = await completeResponse.json();
     renderMediaRows(payload.files || []);
     setText("media-generated-at", payload.generatedAt || "unavailable");
     setStatus("media-status", `${file.name} uploaded.`);
+    clearStoredUploadId(fingerprint);
     await refreshOverview();
     await refreshSchedule();
   } catch (error) {
     console.error("Failed to upload media", error);
-    setStatus("media-status", "Failed to upload media file.", true);
+    const details = error instanceof Error ? error.message : "Unknown upload error.";
+    setStatus(
+      "media-status",
+      `Upload interrupted. Re-select the same file to resume. (${details})`,
+      true,
+    );
   } finally {
     state.mediaUploading = false;
+    setTimeout(() => hideUploadProgress(), 1200);
   }
 }
 
@@ -565,9 +717,26 @@ function bindEvents() {
   const uploadInput = document.getElementById(
     "video-upload",
   ) as HTMLInputElement | null;
+  const uploadDropzone = document.getElementById("upload-dropzone");
   document
     .getElementById("upload-trigger-btn")
     ?.addEventListener("click", () => uploadInput?.click());
+
+  uploadDropzone?.addEventListener("dragover", (event) => {
+    event.preventDefault();
+    uploadDropzone.classList.add("is-dragover");
+  });
+  uploadDropzone?.addEventListener("dragleave", () => {
+    uploadDropzone.classList.remove("is-dragover");
+  });
+  uploadDropzone?.addEventListener("drop", async (event) => {
+    event.preventDefault();
+    uploadDropzone.classList.remove("is-dragover");
+    const droppedFiles = event.dataTransfer?.files;
+    if (!droppedFiles || droppedFiles.length === 0) return;
+    await uploadVideo(droppedFiles[0]);
+  });
+
   uploadInput?.addEventListener("change", async (event) => {
     const target = event.target as HTMLInputElement;
     if (!target.files || target.files.length === 0) return;

frontend/src/style.css

@@ -645,6 +645,22 @@ select {
   gap: var(--space-2);
 }
 
+.upload-dropzone.is-dragover {
+  border-color: var(--brand);
+  background: #e6f6ef;
+}
+
+.upload-progress {
+  display: grid;
+  gap: var(--space-1);
+  width: min(540px, 100%);
+}
+
+.upload-progress progress {
+  width: 100%;
+  height: 0.75rem;
+}
+
 .stat-grid {
   display: grid;
   grid-template-columns: repeat(4, minmax(0, 1fr));