From e1fb428f6dfe48302e583f18f0a70671bd0a5a51 Mon Sep 17 00:00:00 2001
From: Pulse Agent <agent@pulse.ai>
Date: Wed, 20 May 2026 10:59:24 -0300
Subject: [PATCH] =?UTF-8?q?docs(runbook):=20Docker=20Swarm=20runbook=20com?=
 =?UTF-8?q?pleto=20+=20recovery=20commands=20+=20checklists=20de=20sess?=
 =?UTF-8?q?=C3=A3o?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 runbook/DOCKER-SWARM-RUNBOOK.md | 49 +++++++++++++++++++++++++++++++++
 runbook/RECOVERY-COMMANDS.md    | 43 +++++++++++++++++++++++++++++
 2 files changed, 92 insertions(+)
 create mode 100644 runbook/DOCKER-SWARM-RUNBOOK.md
 create mode 100644 runbook/RECOVERY-COMMANDS.md

diff --git a/runbook/DOCKER-SWARM-RUNBOOK.md b/runbook/DOCKER-SWARM-RUNBOOK.md
new file mode 100644
index 0000000..3a6fe98
--- /dev/null
+++ b/runbook/DOCKER-SWARM-RUNBOOK.md
@@ -0,0 +1,49 @@
+# Docker Swarm Runbook — Pulse Agent
+
+_Atualizado: 2026-05-20 | Responsável: Pulse Agent_
+
+## 📋 Inventário de Stacks (8 ativos)
+
+| Stack | Serviços | Status |
+|-------|----------|--------|
+| bot | beebot | 🟢 |
+| code | file (8dcode) | 🟢 |
+| database | mongos-master, dbadmin | 🟡 degraded |
+| design | penpot (7 containers) | 🟢 |
+| dock | portainer, agent | 🟡 |
+| git | gitea | 🟢 |
+| pro | leantime, leantime-db | 🟡 |
+| proxy | caddy (80/443) | 🟢 |
+
+## 🚨 Serviços críticos e seus riscos
+
+| Serviço | Risco | Recuperação |
+|---------|-------|-------------|
+| `bot_office` | HIGH — OOM kill (exit 137), agora UP porém frágil | `docker service scale bot_office=2` |
+| `database_mongos-master` | HIGH — 4 containers falharam exit(139) SIGSEGV | `docker service update --force database_mongos-master` |
+| `pro_leantime` | HIGH — 4 containers unhealthy, exit(137) | `docker service update --force pro_leantime` |
+| `dock_portainer` | MEDIUM — múltiplos Failed | `docker service update --force dock_portainer` |
+| `proxy_caddy` | MEDIUM — mount path inválido em réplicas antigas | fix compose mount |
+
+## 🔧 Comandos de recuperação rápida
+
+```bash
+# Status detalhado
+docker stack ps --no-trunc --no-resolve <stack>
+
+# Forçar recriação
+docker service update --force <stack>_<service>
+
+# Escalar (forçar nova réplica)
+docker service scale <stack>_<service>=2
+docker service scale <stack>_<service>=1
+
+# Limpar órfãos
+docker ps -a -f 'status=exited' --format '{{.Names}}' | xargs docker rm -f
+docker ps -a -f 'status=dead' --format '{{.Names}}' | xargs docker rm -f
+```
+
+## 📊 Health check coverage
+
+- **3/19** containers com health check definido
+- **TODO**: adicionar health check para bot_office, gitea, pro_leantime-db, todos do design stack
diff --git a/runbook/RECOVERY-COMMANDS.md b/runbook/RECOVERY-COMMANDS.md
new file mode 100644
index 0000000..dce9d32
--- /dev/null
+++ b/runbook/RECOVERY-COMMANDS.md
@@ -0,0 +1,43 @@
+# Comandos de Recuperação — Docker Swarm
+
+_Alfabeto de comandos para o Pulse usar quando algo quebrar._
+
+## Emergency — todos os serviços down
+
+```bash
+docker node ls                              # verificar saúde do nó
+docker stack rm <stack> && sleep 3           # remover stack problemática
+docker swarm init                           # só se necessário
+docker stack deploy -c <stack>.yml <stack>  # re-deploy
+```
+
+## Serviço específico — forçar restart
+
+```bash
+docker service ps <stack>_<service>                # ver tasks atuais
+docker service update --force <stack>_<service>    # forçar nova task
+```
+
+## Limpar containers órfãos
+
+```bash
+docker ps -a -f "status=exited" --format '{{.Names}}' | xargs -r docker rm -f
+docker ps -a -f "status=dead"   --format '{{.Names}}' | xargs -r docker rm -f
+```
+
+## Swarm reset (extreme)
+
+```bash
+docker swarm leave --force && docker swarm init --advertise-addr <ip>
+```
+
+## Health check manual de um container
+
+```bash
+# Status geral
+docker inspect --format '{{json .State.Health}}' <container_id> | python3 -m json.tool
+
+# Com health check definido
+docker inspect --format '{{.State.Health.Status}}' <container_id>
+# → "healthy" | "unhealthy" | "starting"
+```