pgbus 0.9.4 → 0.9.6

data/config/locales/ja.yml

@@ -84,6 +84,7 @@ ja:
       stats_cards:
         enqueued: キューに追加済み
         failed_dlq: 失敗 / DLQ
+        failed_dlq_labels: 失敗 / Dead Lettered
         processes: プロセス
         queues: キュー
         recurring: 繰り返し
@@ -126,6 +127,7 @@ ja:
           queue: 'キュー:'
           visible_at: '表示日時:'
         retry: 再試行
+        total_label: デッドレターキュー内のメッセージ
       show:
         back: DLQに戻る
         discard: 破棄
@@ -225,6 +227,10 @@ ja:
       bulk_select_all: すべて選択
       bulk_select_row: "%{id}を選択"
       bulk_selected: 選択済み
+      pagination:
+        next: 次へ
+        previous: 前へ
+        showing: "%{total} 件中 %{from}–%{to} 件を表示"
       paused_badge: 一時停止中
       queue_badge:
         dlq: DLQ
@@ -235,6 +241,7 @@ ja:
       status_badge:
         healthy: 正常
         stale: 期限切れ
+        stalled: 停滞
     insights:
       show:
         charts:
@@ -476,6 +483,7 @@ ja:
         resume: 再開
       show:
         arguments: 引数
+        back: キューに戻る
         delete_confirm: このキューを完全に削除しますか？この操作は取り消せません。
         delete_queue: キューを削除
         depth: 深さ：

data/config/locales/nb.yml

@@ -84,6 +84,7 @@ nb:
       stats_cards:
         enqueued: I kø
         failed_dlq: Mislyktes / DLQ
+        failed_dlq_labels: Mislyktes / Dead Lettered
         processes: Prosesser
         queues: Køer
         recurring: Gjentakende
@@ -126,6 +127,7 @@ nb:
           queue: 'Kø:'
           visible_at: 'Synlig ved:'
         retry: Prøv igjen
+        total_label: meldinger i dead letter-kø
       show:
         back: Tilbake til DLQ
         discard: Forkast
@@ -225,6 +227,10 @@ nb:
       bulk_select_all: Velg alle
       bulk_select_row: Velg %{id}
       bulk_selected: valgt
+      pagination:
+        next: Neste
+        previous: Forrige
+        showing: Viser %{from}–%{to} av %{total}
       paused_badge: Pause
       queue_badge:
         dlq: DLQ
@@ -235,6 +241,7 @@ nb:
       status_badge:
         healthy: Sunn
         stale: Utdatert
+        stalled: Fastlåst
     insights:
       show:
         charts:
@@ -476,6 +483,7 @@ nb:
         resume: Gjenoppta
       show:
         arguments: Argumenter
+        back: Tilbake til køer
         delete_confirm: Slette denne køen permanent? Dette kan ikke angres.
         delete_queue: Slett kø
         depth: 'Dybde:'

data/config/locales/nl.yml

@@ -84,6 +84,7 @@ nl:
       stats_cards:
         enqueued: In de wachtrij geplaatst
         failed_dlq: Mislukt / DLQ
+        failed_dlq_labels: Mislukt / Dead Lettered
         processes: Processen
         queues: Wachtrijen
         recurring: Terugkerend
@@ -126,6 +127,7 @@ nl:
           queue: 'Wachtrij:'
           visible_at: 'Zichtbaar op:'
         retry: Opnieuw proberen
+        total_label: berichten in dead letter-wachtrij
       show:
         back: Terug naar DLQ
         discard: Verwerpen
@@ -225,6 +227,10 @@ nl:
       bulk_select_all: Alles selecteren
       bulk_select_row: Selecteer %{id}
       bulk_selected: geselecteerd
+      pagination:
+        next: Volgende
+        previous: Vorige
+        showing: "%{from}–%{to} van %{total} weergegeven"
       paused_badge: Gepauzeerd
       queue_badge:
         dlq: DLQ
@@ -235,6 +241,7 @@ nl:
       status_badge:
         healthy: Gezond
         stale: Verouderd
+        stalled: Vastgelopen
     insights:
       show:
         charts:
@@ -476,6 +483,7 @@ nl:
         resume: Hervatten
       show:
         arguments: Argumenten
+        back: Terug naar wachtrijen
         delete_confirm: Deze wachtrij permanent verwijderen? Dit kan niet ongedaan worden gemaakt.
         delete_queue: Wachtrij verwijderen
         depth: 'Diepte:'

data/config/locales/pt.yml

@@ -84,6 +84,7 @@ pt:
       stats_cards:
         enqueued: Enfileirado
         failed_dlq: Falhou / DLQ
+        failed_dlq_labels: Falhados / Dead Lettered
         processes: Processos
         queues: Filas
         recurring: Recorrente
@@ -126,6 +127,7 @@ pt:
           queue: 'Fila:'
           visible_at: 'Visível em:'
         retry: Tentar novamente
+        total_label: mensagens na fila de mensagens mortas
       show:
         back: Voltar para DLQ
         discard: Descartar
@@ -225,6 +227,10 @@ pt:
       bulk_select_all: Selecionar todos
       bulk_select_row: Selecionar %{id}
       bulk_selected: selecionado
+      pagination:
+        next: Próximo
+        previous: Anterior
+        showing: Mostrando %{from}–%{to} de %{total}
       paused_badge: Pausado
       queue_badge:
         dlq: DLQ
@@ -235,6 +241,7 @@ pt:
       status_badge:
         healthy: Saudável
         stale: Obsoleto
+        stalled: Bloqueado
     insights:
       show:
         charts:
@@ -476,6 +483,7 @@ pt:
         resume: Retomar
       show:
         arguments: Argumentos
+        back: Voltar às filas
         delete_confirm: Excluir permanentemente esta fila? Esta ação não pode ser desfeita.
         delete_queue: Excluir fila
         depth: 'Profundidade:'

data/config/locales/sv.yml

@@ -84,6 +84,7 @@ sv:
       stats_cards:
         enqueued: Inlagda
         failed_dlq: Misslyckade / DLQ
+        failed_dlq_labels: Misslyckade / Dead Lettered
         processes: Processer
         queues: Köer
         recurring: Återkommande
@@ -126,6 +127,7 @@ sv:
           queue: 'Kö:'
           visible_at: 'Synlig vid:'
         retry: Försök igen
+        total_label: meddelanden i dead letter-kö
       show:
         back: Tillbaka till DLQ
         discard: Kassera
@@ -225,6 +227,10 @@ sv:
       bulk_select_all: Markera alla
       bulk_select_row: Markera %{id}
       bulk_selected: valda
+      pagination:
+        next: Nästa
+        previous: Föregående
+        showing: Visar %{from}–%{to} av %{total}
       paused_badge: Pausad
       queue_badge:
         dlq: DLQ
@@ -235,6 +241,7 @@ sv:
       status_badge:
         healthy: Hälsosam
         stale: Föråldrad
+        stalled: Fastlåst
     insights:
       show:
         charts:
@@ -476,6 +483,7 @@ sv:
         resume: Återuppta
       show:
         arguments: Argument
+        back: Tillbaka till köer
         delete_confirm: Ta bort denna kö permanent? Detta kan inte ångras.
         delete_queue: Ta bort kö
         depth: 'Djup:'

data/lib/pgbus/cli.rb

@@ -16,6 +16,8 @@ module Pgbus
         show_status
       when "queues"
         list_queues
+      when "mcp"
+        start_mcp_server
       when "version"
         puts "pgbus #{Pgbus::VERSION}"
       when "help", "--help", "-h"
@@ -132,6 +134,13 @@ module Pgbus
       end
     end
 
+    # Boots the read-only MCP diagnostic server over stdio. Loaded lazily so
+    # the optional `mcp` gem is only required when this command is invoked.
+    def start_mcp_server
+      Pgbus::MCP.load!
+      Pgbus::MCP::Runner.run
+    end
+
     def list_queues
       Pgbus.client.list_queues
       metrics = Pgbus.client.metrics
@@ -154,6 +163,7 @@ module Pgbus
           start    Start the Pgbus supervisor (workers + dispatcher)
           status   Show running Pgbus processes
           queues   List queues with metrics
+          mcp      Start the read-only MCP diagnostic server over stdio
           version  Show version
           help     Show this help
 
@@ -172,6 +182,12 @@ module Pgbus
                              pattern)
           --execution-mode   Execution mode: threads (default) or async
                              (fiber-based, lower connection usage)
+
+        Environment for `mcp`:
+          PGBUS_MCP_TOKEN          If set, PGBUS_MCP_AUTH_TOKEN must match for
+                                   the server to start (optional token gate).
+          PGBUS_MCP_ALLOW_PAYLOADS Truthy to let tools return raw message
+                                   bodies/headers (off by default; redacted).
       HELP
     end
   end

data/lib/pgbus/client.rb

@@ -1,6 +1,7 @@
 # frozen_string_literal: true
 
 require "json"
+require "timeout"
 require_relative "client/read_after"
 require_relative "client/ensure_stream_queue"
 require_relative "client/notify_stream"
@@ -110,7 +111,7 @@ module Pgbus
       full_name = config.queue_name(queue_name)
       Instrumentation.instrument("pgbus.client.read_message", queue: full_name) do
         with_stale_connection_retry do
-          synchronized { @pgmq.read(full_name, vt: vt || config.visibility_timeout) }
+          synchronized { with_read_timeout { @pgmq.read(full_name, vt: vt || config.visibility_timeout) } }
         end
       end
     end
@@ -119,7 +120,7 @@ module Pgbus
       full_name = config.queue_name(queue_name)
       Instrumentation.instrument("pgbus.client.read_batch", queue: full_name, qty: qty) do
         with_stale_connection_retry do
-          synchronized { @pgmq.read_batch(full_name, vt: vt || config.visibility_timeout, qty: qty) }
+          synchronized { with_read_timeout { @pgmq.read_batch(full_name, vt: vt || config.visibility_timeout, qty: qty) } }
         end
       end
     end
@@ -141,7 +142,7 @@ module Pgbus
 
         msgs = Instrumentation.instrument("pgbus.client.read_batch", queue: pq_name, qty: remaining) do
           with_stale_connection_retry do
-            synchronized { @pgmq.read_batch(pq_name, vt: vt || config.visibility_timeout, qty: remaining) }
+            synchronized { with_read_timeout { @pgmq.read_batch(pq_name, vt: vt || config.visibility_timeout, qty: remaining) } }
           end
         end || []
 
@@ -180,7 +181,9 @@ module Pgbus
       Instrumentation.instrument("pgbus.client.read_multi", queues: full_names, qty: qty, limit: limit) do
         with_stale_connection_retry do
           synchronized do
-            @pgmq.read_multi(full_names, vt: vt || config.visibility_timeout, qty: qty, limit: limit)
+            with_read_timeout do
+              @pgmq.read_multi(full_names, vt: vt || config.visibility_timeout, qty: qty, limit: limit)
+            end
           end
         end
       end
@@ -357,7 +360,7 @@ module Pgbus
       full_name = config.queue_name(queue_name)
       Instrumentation.instrument("pgbus.client.read_grouped", queue: full_name, qty: qty) do
         with_stale_connection_retry do
-          synchronized { @pgmq.read_grouped(full_name, vt: vt || config.visibility_timeout, qty: qty) }
+          synchronized { with_read_timeout { @pgmq.read_grouped(full_name, vt: vt || config.visibility_timeout, qty: qty) } }
         end
       end
     end
@@ -366,7 +369,7 @@ module Pgbus
       full_name = config.queue_name(queue_name)
       Instrumentation.instrument("pgbus.client.read_grouped_rr", queue: full_name, qty: qty) do
         with_stale_connection_retry do
-          synchronized { @pgmq.read_grouped_rr(full_name, vt: vt || config.visibility_timeout, qty: qty) }
+          synchronized { with_read_timeout { @pgmq.read_grouped_rr(full_name, vt: vt || config.visibility_timeout, qty: qty) } }
         end
       end
     end
@@ -374,7 +377,7 @@ module Pgbus
     def read_grouped_head(queue_name, qty:, vt: nil)
       full_name = config.queue_name(queue_name)
       with_stale_connection_retry do
-        synchronized { @pgmq.read_grouped_head(full_name, vt: vt || config.visibility_timeout, qty: qty) }
+        synchronized { with_read_timeout { @pgmq.read_grouped_head(full_name, vt: vt || config.visibility_timeout, qty: qty) } }
       end
     end
 
@@ -696,6 +699,30 @@ module Pgbus
     # connection was dead *before* pgmq-ruby tried to use it, so no SQL was
     # ever sent. Mid-flight errors like "server closed the connection" are
     # excluded from the pattern list for this reason.
+    # Bound a read at config.read_timeout so a dead socket raises
+    # Pgbus::ReadTimeoutError instead of blocking the worker loop forever.
+    #
+    # MUST wrap only the bare `@pgmq.read*` call, sitting *inside* both
+    # `synchronized` and `with_stale_connection_retry`:
+    #
+    #   with_stale_connection_retry { synchronized { with_read_timeout { @pgmq.read* } } }
+    #
+    # Two reasons for this nesting:
+    #   1. On the shared-connection path @pgmq_mutex serializes all reads.
+    #      The timeout clock must start only after the mutex is acquired,
+    #      otherwise a thread queued behind another read is charged for the
+    #      wait and raises a false ReadTimeoutError for a socket it never
+    #      touched.
+    #   2. with_stale_connection_retry can retry once; with the timeout
+    #      inside, each socket attempt gets its own full timeout budget
+    #      rather than sharing one across both attempts.
+    def with_read_timeout(&)
+      timeout = config.read_timeout
+      return yield unless timeout&.positive?
+
+      Timeout.timeout(timeout, Pgbus::ReadTimeoutError, &)
+    end
+
     def with_stale_connection_retry
       attempts = 0
       begin

data/lib/pgbus/configuration.rb

@@ -26,6 +26,12 @@ module Pgbus
     # Worker recycling
     attr_accessor :max_jobs_per_worker, :max_memory_mb, :max_worker_lifetime
 
+    # Liveness probe: supervisor kills a worker whose claim loop has not
+    # advanced for longer than stall_threshold seconds (default 90).
+    # read_timeout caps how long a single PGMQ read can block (default 30s),
+    # so a dead socket raises instead of parking the loop forever.
+    attr_accessor :stall_threshold, :read_timeout
+
     # Dispatcher settings
     attr_accessor :dispatch_interval
 
@@ -150,6 +156,9 @@ module Pgbus
       @max_memory_mb = nil
       @max_worker_lifetime = nil
 
+      @stall_threshold = 90
+      @read_timeout = 30
+
       @dispatch_interval = 1.0
 
       @circuit_breaker_enabled = true
@@ -207,7 +216,7 @@ module Pgbus
       @web_per_page = 25
       @web_live_updates = true
       @web_data_source = nil
-      @insights_default_minutes = 30 * 24 * 60 # 30 days
+      @insights_default_minutes = 60 # 1 hour
       @base_controller_class = "::ActionController::Base"
       @return_to_app_url = nil
       @metrics_enabled = true
@@ -374,6 +383,13 @@ module Pgbus
         raise ArgumentError, "retry_backoff_jitter must be between 0 and 1"
       end
 
+      unless stall_threshold.nil? || (stall_threshold.is_a?(Numeric) && stall_threshold.positive?)
+        raise ArgumentError, "stall_threshold must be a positive number or nil to disable"
+      end
+      unless read_timeout.nil? || (read_timeout.is_a?(Numeric) && read_timeout.positive?)
+        raise ArgumentError, "read_timeout must be a positive number or nil to disable"
+      end
+
       # Validate global execution_mode
       ExecutionPools.normalize_mode(execution_mode)