Class: DecisionAgent::Monitoring::DashboardServer

Inherits:
Object
  • Object
show all
Defined in:
lib/decision_agent/monitoring/dashboard_server.rb

Overview

Real-time monitoring dashboard server Framework-agnostic: Pure Rack application compatible with any Rack server

Constant Summary collapse

PUBLIC_FOLDER =
File.expand_path("dashboard/public", __dir__)
VIEWS_FOLDER =
File.expand_path("dashboard/views", __dir__)

Class Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Class Attribute Details

.alert_managerObject

Returns the value of attribute alert_manager.



27
28
29
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 27

def alert_manager
  @alert_manager
end

.bindObject

Returns the value of attribute bind.



27
28
29
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 27

def bind
  @bind
end

.metrics_collectorObject

Returns the value of attribute metrics_collector.



27
28
29
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 27

def metrics_collector
  @metrics_collector
end

.portObject

Returns the value of attribute port.



27
28
29
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 27

def port
  @port
end

.prometheus_exporterObject

Returns the value of attribute prometheus_exporter.



27
28
29
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 27

def prometheus_exporter
  @prometheus_exporter
end

.public_folderObject

Returns the value of attribute public_folder.



27
28
29
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 27

def public_folder
  @public_folder
end

.views_folderObject

Returns the value of attribute views_folder.



27
28
29
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 27

def views_folder
  @views_folder
end

.websocket_clientsObject (readonly)

Returns the value of attribute websocket_clients.



28
29
30
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 28

def websocket_clients
  @websocket_clients
end

Class Method Details

.add_websocket_client(ws) ⇒ Object



377
378
379
380
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 377

def add_websocket_client(ws)
  @websocket_clients ||= []
  @websocket_clients << ws
end

.broadcast_to_clients(message) ⇒ Object



365
366
367
368
369
370
371
372
373
374
375
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 365

def broadcast_to_clients(message)
  return unless WEBSOCKET_AVAILABLE
  return if @websocket_clients.empty? # Skip if no clients connected

  json_message = message.to_json
  @websocket_clients.each do |client|
    client.send(json_message) if client.ready_state == Faye::WebSocket::API::OPEN
  rescue StandardError => e
    warn "WebSocket send failed: #{e.message}"
  end
end

.call(env) ⇒ Object

Rack call method - entry point for Rack requests



39
40
41
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 39

def call(env)
  new.call(env)
end

.configure_monitoring(metrics_collector:, prometheus_exporter:, alert_manager:) ⇒ Object



335
336
337
338
339
340
341
342
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 335

def configure_monitoring(metrics_collector:, prometheus_exporter:, alert_manager:)
  @metrics_collector = metrics_collector
  @prometheus_exporter = prometheus_exporter
  @alert_manager = alert_manager
  @websocket_clients = []

  setup_real_time_updates
end

.define_routes(router) ⇒ Object



43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 43

def define_routes(router)
  # Enable CORS
  router.before do |ctx|
    ctx.headers["Access-Control-Allow-Origin"] = "*"
    ctx.headers["Access-Control-Allow-Methods"] = "GET, POST, PUT, DELETE, OPTIONS"
    ctx.headers["Access-Control-Allow-Headers"] = "Content-Type"
  end

  # OPTIONS handler for CORS preflight
  router.options "*" do |ctx|
    ctx.status(200)
    ctx.body("")
  end

  # Class-level configuration
  class << self
    attr_accessor :metrics_collector, :prometheus_exporter, :alert_manager
    attr_reader :websocket_clients

    def configure_monitoring(metrics_collector:, prometheus_exporter:, alert_manager:)
      @metrics_collector = metrics_collector
      @prometheus_exporter = prometheus_exporter
      @alert_manager = alert_manager
      @websocket_clients = []

      setup_real_time_updates
    end

    def setup_real_time_updates
      # Register observer for real-time metric updates
      @metrics_collector.add_observer do |event_type, metric|
        broadcast_to_clients({
                               type: "metric_update",
                               event: event_type,
                               data: metric,
                               timestamp: Time.now.utc.iso8601
                             })
      end

      # Register alert handler
      @alert_manager.add_handler do |alert|
        broadcast_to_clients({
                               type: "alert",
                               data: alert,
                               timestamp: Time.now.utc.iso8601
                             })
      end
    end

    def broadcast_to_clients(message)
      return unless WEBSOCKET_AVAILABLE
      return if @websocket_clients.empty? # Skip if no clients connected

      json_message = message.to_json
      @websocket_clients.each do |client|
        client.send(json_message) if client.ready_state == Faye::WebSocket::API::OPEN
      rescue StandardError => e
        warn "WebSocket send failed: #{e.message}"
      end
    end

    def add_websocket_client(ws)
      @websocket_clients << ws
    end

    def remove_websocket_client(ws)
      @websocket_clients.delete(ws)
    end
  end

  # Main dashboard page
  router.get "/" do |ctx|
    index_file = File.join(DashboardServer.public_folder || PUBLIC_FOLDER, "index.html")
    if File.exist?(index_file)
      ctx.send_file(index_file)
    else
      ctx.status(404)
      ctx.body("Dashboard page not found")
    end
  end

  # WebSocket endpoint for real-time updates
  router.get "/ws" do |ctx|
    unless WEBSOCKET_AVAILABLE
      ctx.status(503)
      ctx.content_type "application/json"
      ctx.json({ error: "WebSocket support not available. Install faye-websocket gem." })
      next
    end

    if Faye::WebSocket.websocket?(ctx.env)
      ws = Faye::WebSocket.new(ctx.env)

      ws.on :open do |_event|
        DashboardServer.add_websocket_client(ws)

        # Send initial state
        ws.send({
          type: "connected",
          message: "Connected to DecisionAgent monitoring",
          timestamp: Time.now.utc.iso8601
        }.to_json)
      end

      ws.on :message do |event|
        # Handle client messages
        DashboardServer.handle_websocket_message(ws, event.data)
      end

      ws.on :close do |_event|
        DashboardServer.remove_websocket_client(ws)
      end

      ws.rack_response
    else
      ctx.status(426)
      ctx.content_type "application/json"
      ctx.json({ error: "WebSocket connection required" })
    end
  end

  # API: Get current statistics
  router.get "/api/stats" do |ctx|
    ctx.content_type "application/json"

    time_range = (ctx.params[:time_range] || ctx.params["time_range"])&.to_i
    stats = DashboardServer.metrics_collector.statistics(time_range: time_range)

    ctx.json(stats)
  end

  # API: Get time series data
  router.get "/api/timeseries/:metric_type" do |ctx|
    ctx.content_type "application/json"

    metric_type = (ctx.params[:metric_type] || ctx.params["metric_type"]).to_sym
    bucket_size = ((ctx.params[:bucket_size] || ctx.params["bucket_size"]) || 60).to_i
    time_range = ((ctx.params[:time_range] || ctx.params["time_range"]) || 3600).to_i

    data = DashboardServer.metrics_collector.time_series(
      metric_type: metric_type,
      bucket_size: bucket_size,
      time_range: time_range
    )

    ctx.json(data)
  end

  # API: Prometheus metrics endpoint
  router.get "/metrics" do |ctx|
    ctx.content_type DashboardServer.prometheus_exporter.class::CONTENT_TYPE
    ctx.body(DashboardServer.prometheus_exporter.export)
  end

  # API: Get Prometheus metrics in JSON format
  router.get "/api/metrics" do |ctx|
    ctx.content_type "application/json"
    ctx.json(DashboardServer.prometheus_exporter.metrics_hash)
  end

  # API: Register custom KPI
  router.post "/api/kpi" do |ctx|
    ctx.content_type "application/json"

    begin
      request_body = Web::RackRequestHelpers.read_body(ctx.env)
      data = JSON.parse(request_body, symbolize_names: true)

      DashboardServer.prometheus_exporter.register_kpi(
        name: data[:name],
        value: data[:value],
        labels: data[:labels] || {},
        help: data[:help]
      )

      ctx.json({ success: true, message: "KPI registered" })
    rescue StandardError => e
      ctx.status(400)
      ctx.json({ error: e.message })
    end
  end

  # API: Get active alerts
  router.get "/api/alerts" do |ctx|
    ctx.content_type "application/json"
    ctx.json(DashboardServer.alert_manager.active_alerts)
  end

  # API: Get all alerts
  router.get "/api/alerts/all" do |ctx|
    ctx.content_type "application/json"
    limit = ((ctx.params[:limit] || ctx.params["limit"]) || 100).to_i
    ctx.json(DashboardServer.alert_manager.all_alerts(limit: limit))
  end

  # API: Create alert rule
  router.post "/api/alerts/rules" do |ctx|
    ctx.content_type "application/json"

    begin
      request_body = Web::RackRequestHelpers.read_body(ctx.env)
      data = JSON.parse(request_body, symbolize_names: true)

      # Parse condition
      condition = DashboardServer.parse_alert_condition(data[:condition], data[:condition_type])

      rule = DashboardServer.alert_manager.add_rule(
        name: data[:name],
        condition: condition,
        severity: (data[:severity] || :warning).to_sym,
        threshold: data[:threshold],
        message: data[:message],
        cooldown: data[:cooldown] || 300
      )

      ctx.status(201)
      ctx.json(rule)
    rescue StandardError => e
      ctx.status(400)
      ctx.json({ error: e.message })
    end
  end

  # API: Toggle alert rule
  router.put "/api/alerts/rules/:rule_id/toggle" do |ctx|
    ctx.content_type "application/json"

    begin
      request_body = Web::RackRequestHelpers.read_body(ctx.env)
      data = JSON.parse(request_body, symbolize_names: true)
      enabled = data[:enabled] || false
      rule_id = ctx.params[:rule_id] || ctx.params["rule_id"]

      DashboardServer.alert_manager.toggle_rule(rule_id, enabled)

      ctx.json({ success: true, message: "Rule #{enabled ? 'enabled' : 'disabled'}" })
    rescue StandardError => e
      ctx.status(400)
      ctx.json({ error: e.message })
    end
  end

  # API: Acknowledge alert
  router.post "/api/alerts/:alert_id/acknowledge" do |ctx|
    ctx.content_type "application/json"

    begin
      request_body = Web::RackRequestHelpers.read_body(ctx.env)
      data = JSON.parse(request_body, symbolize_names: true)
      acknowledged_by = data[:acknowledged_by] || "user"
      alert_id = ctx.params[:alert_id] || ctx.params["alert_id"]

      DashboardServer.alert_manager.acknowledge_alert(alert_id, acknowledged_by: acknowledged_by)

      ctx.json({ success: true, message: "Alert acknowledged" })
    rescue StandardError => e
      ctx.status(400)
      ctx.json({ error: e.message })
    end
  end

  # API: Resolve alert
  router.post "/api/alerts/:alert_id/resolve" do |ctx|
    ctx.content_type "application/json"

    begin
      request_body = Web::RackRequestHelpers.read_body(ctx.env)
      data = JSON.parse(request_body, symbolize_names: true)
      resolved_by = data[:resolved_by] || "user"
      alert_id = ctx.params[:alert_id] || ctx.params["alert_id"]

      DashboardServer.alert_manager.resolve_alert(alert_id, resolved_by: resolved_by)

      ctx.json({ success: true, message: "Alert resolved" })
    rescue StandardError => e
      ctx.status(400)
      ctx.json({ error: e.message })
    end
  end

  # Health check
  router.get "/health" do |ctx|
    ctx.content_type "application/json"
    ctx.json({
               status: "ok",
               version: DecisionAgent::VERSION,
               websocket_clients: DashboardServer.websocket_clients.size,
               metrics_count: DashboardServer.metrics_collector.metrics_count
             })
  end
end

.handle_websocket_message(ws, data) ⇒ Object



387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 387

def handle_websocket_message(ws, data)
  message = JSON.parse(data, symbolize_names: true)

  case message[:action]
  when "subscribe"
    # Send current stats
    stats = metrics_collector.statistics
    ws.send({ type: "stats", data: stats }.to_json)
  when "get_alerts"
    alerts = alert_manager.active_alerts
    ws.send({ type: "alerts", data: alerts }.to_json)
  end
rescue StandardError => e
  ws.send({ type: "error", message: e.message }.to_json)
end

.parse_alert_condition(condition_data, condition_type) ⇒ Object



403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 403

def parse_alert_condition(condition_data, condition_type)
  case condition_type
  when "high_error_rate"
    AlertManager.high_error_rate(threshold: condition_data[:threshold] || 0.1)
  when "low_confidence"
    AlertManager.low_confidence(threshold: condition_data[:threshold] || 0.5)
  when "high_latency"
    AlertManager.high_latency(threshold_ms: condition_data[:threshold_ms] || 1000)
  when "error_spike"
    AlertManager.error_spike(threshold: condition_data[:threshold] || 10)
  when "custom"
    condition_data
  else
    raise "Unknown condition type: #{condition_type}"
  end
end

.remove_websocket_client(ws) ⇒ Object



382
383
384
385
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 382

def remove_websocket_client(ws)
  @websocket_clients ||= []
  @websocket_clients.delete(ws)
end

.routerObject



30
31
32
33
34
35
36
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 30

def router
  @router ||= begin
    router = Web::RackHelpers::Router.new
    define_routes(router)
    router
  end
end

.setup_real_time_updatesObject



344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 344

def setup_real_time_updates
  # Register observer for real-time metric updates
  @metrics_collector.add_observer do |event_type, metric|
    broadcast_to_clients({
                           type: "metric_update",
                           event: event_type,
                           data: metric,
                           timestamp: Time.now.utc.iso8601
                         })
  end

  # Register alert handler
  @alert_manager.add_handler do |alert|
    broadcast_to_clients({
                           type: "alert",
                           data: alert,
                           timestamp: Time.now.utc.iso8601
                         })
  end
end

.start!(metrics_collector:, prometheus_exporter:, alert_manager:, port: 4568, host: "0.0.0.0") ⇒ Object

Class method to start the server Framework-agnostic: uses Rack::Server which supports any Rack-compatible server



422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 422

def start!(metrics_collector:, prometheus_exporter:, alert_manager:, port: 4568, host: "0.0.0.0")
  configure_monitoring(
    metrics_collector: metrics_collector,
    prometheus_exporter: prometheus_exporter,
    alert_manager: alert_manager
  )

  @port = port
  @bind = host
  @public_folder = PUBLIC_FOLDER
  @views_folder = VIEWS_FOLDER

  puts "🎯 DecisionAgent Monitoring Dashboard starting..."
  puts "📍 Server: http://#{host == '0.0.0.0' ? 'localhost' : host}:#{port}"
  puts "⚡️  Press Ctrl+C to stop"
  puts ""

  # Use Rack::Server which automatically selects the best available handler
  # Supports: Puma, WEBrick, Thin, Unicorn, etc. (any Rack-compatible server)
  Rack::Server.start(
    app: self,
    Port: port,
    Host: host,
    server: ENV.fetch("RACK_HANDLER", nil), # Allows override via ENV
    environment: ENV.fetch("RACK_ENV", "development")
  )
end

Instance Method Details

#call(env) ⇒ Object



451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
# File 'lib/decision_agent/monitoring/dashboard_server.rb', line 451

def call(env)
  route_match = DashboardServer.router.match(env)
  return [404, { "Content-Type" => "text/plain" }, ["Not Found"]] unless route_match

  # Create request context with route params
  ctx = Web::RackRequestHelpers::RequestContext.new(env, route_match[:params] || {})

  # Run before filters
  route_match[:before_filters].each do |filter|
    filter.call(ctx)
    return ctx.to_rack_response if ctx.halted?
  end

  # Execute route handler
  begin
    route_match[:handler].call(ctx)
    ctx.to_rack_response
  rescue StandardError => e
    [500, { "Content-Type" => "application/json" }, [{ error: e.message }.to_json]]
  end
end