From 792951e4c851aa2926852aefd542d2d2567a009a Mon Sep 17 00:00:00 2001
From: Rodrigo Borba <rodrigobm10@me.com>
Date: Thu, 26 Feb 2026 16:35:15 -0300
Subject: [PATCH] fix(ci): update health check endpoint for review apps

- Return expected payload { version, timestamp, queue_services, data_services } in /health
- Fix infinite attempt loop in deploy check Github Action
- Untrack temporary wuzapi test scripts
---
 .github/workflows/deploy_check.yml        |  7 +++---
 app/controllers/health_controller.rb      | 22 +++++++++++++++++-
 progresso/deploy_check_health_endpoint.md | 27 +++++++++++++++++++++++
 3 files changed, 52 insertions(+), 4 deletions(-)
 create mode 100644 progresso/deploy_check_health_endpoint.md

diff --git a/.github/workflows/deploy_check.yml b/.github/workflows/deploy_check.yml
index 9f295a6c8..bb99a00b8 100644
--- a/.github/workflows/deploy_check.yml
+++ b/.github/workflows/deploy_check.yml
@@ -22,22 +22,23 @@ jobs:
         run: echo "https://chatwoot-pr-${{ github.event.pull_request.number }}.herokuapp.com"
       - name: Check Deployment Status
         run: |
-          max_attempts=10
+          max_attempts=15
           attempt=1
           status_code=0
           echo "Waiting for review app to be deployed/redeployed, trying in  10 minutes..."
           sleep 600
           while [ $attempt -le $max_attempts ]; do
-            response=$(curl -s -o /dev/null -w "%{http_code}" https://chatwoot-pr-${{ github.event.pull_request.number }}.herokuapp.com/api)
+            response=$(curl -s -o /dev/null -w "%{http_code}" https://chatwoot-pr-${{ github.event.pull_request.number }}.herokuapp.com/health)
             status_code=$(echo $response | head -n   1)
             if [ $status_code -eq   200 ]; then
-              body=$(curl -s https://chatwoot-pr-${{ github.event.pull_request.number }}.herokuapp.com/api)
+              body=$(curl -s https://chatwoot-pr-${{ github.event.pull_request.number }}.herokuapp.com/health)
               if echo "$body" | jq -e '.version and .timestamp and .queue_services == "ok" and .data_services == "ok"' > /dev/null; then
                 echo "Deployment successful"
                 exit 0
               else
                 echo "Deployment status unknown, retrying in   3 minutes..."
                 sleep 180
+                attempt=$((attempt +  1))
               fi
             else
               echo "Waiting for review app to be ready, retrying in  3 minutes..."
diff --git a/app/controllers/health_controller.rb b/app/controllers/health_controller.rb
index fdf969a39..f696fa4ff 100644
--- a/app/controllers/health_controller.rb
+++ b/app/controllers/health_controller.rb
@@ -2,6 +2,26 @@
 # authentication, and callbacks. Used for health checks
 class HealthController < ActionController::Base # rubocop:disable Rails/ApplicationController
   def show
-    render json: { status: 'woot' }
+    render json: {
+      version: Chatwoot.config[:version] || 'dev',
+      timestamp: Time.current.to_fs(:db),
+      queue_services: redis_status,
+      data_services: postgres_status
+    }
+  end
+
+  private
+
+  def redis_status
+    r = Redis.new(Redis::Config.app)
+    r.ping ? 'ok' : 'failing'
+  rescue StandardError
+    'failing'
+  end
+
+  def postgres_status
+    ActiveRecord::Base.connection.active? ? 'ok' : 'failing'
+  rescue StandardError
+    'failing'
   end
 end
diff --git a/progresso/deploy_check_health_endpoint.md b/progresso/deploy_check_health_endpoint.md
new file mode 100644
index 000000000..88c38e9d3
--- /dev/null
+++ b/progresso/deploy_check_health_endpoint.md
@@ -0,0 +1,27 @@
+# Correção do Deploy Check da Review App
+
+## Objetivo
+Corrigir a falha no pipeline de CI "Deploy Check" (`.github/workflows/deploy_check.yml`) que quebrava após 10 tentativas devido à Review App (Heroku) não retornar o healthcheck esperado.
+
+## Contexto
+O workflow do GitHub Actions esperava um JSON do endpoint `/api` contendo os campos `version`, `timestamp`, `queue_services` e `data_services` todos populados e com valor `"ok"` pros serviços. Porém, o endpoint `/api` (referente ao `ApiController#index`) não era exposto corretamente em alguns ambientes ou levantava erro 500 caso o Redis/Postgres demorassem a subir, além de cair em um loop infinito no script bash porque a variável `$attempt` não era incrementada se a chamada HTTP retornasse 200 mas o JSON fosse inválido.
+
+## Passos Realizados
+1. Mapeamos que já existia uma rota `get '/health', to: 'health#show'` apontando para o `HealthController` que apenas respondia `{ status: 'woot' }`.
+2. Alteramos o `HealthController#show` para retornar o JSON robusto exigido pelo workflow, fazendo o ping no Redis e no Postgres e blindando as exceções com `rescue StandardError` para nunca retornar 500 durante a fase de boot.
+3. Editamos o arquivo `.github/workflows/deploy_check.yml`:
+   - Trocamos o `curl` de `/api` para `/health`.
+   - Adicionamos a instrução `attempt=$((attempt + 1))` no bloco `else` (quando o teste do `jq` não passa), corrigindo o loop infinito.
+   - Aumentamos o `max_attempts` de 10 para 15 (dando 45 minutos de tolerância para a Review App subir o banco de dados e os dynos completamente).
+
+## Principais Arquivos Alterados
+- `app/controllers/health_controller.rb`
+- `.github/workflows/deploy_check.yml`
+
+## Como Validar
+1. Subir essas alterações (commit e push) na branch do PR.
+2. Acompanhar a aba "Actions" no GitHub e verificar o job "Check Deployment (pull_request)".
+3. O script bash deverá fazer o cURL em `/health` e, assim que o PostgreSQL e Redis reportarem `"ok"`, o step será marcado como "Deployment successful".
+
+## Como Reverter
+Basta fazer um git revert do commit que adicionou essas alterações ou retornar os arquivos aos estados anteriores (o `HealthController` retornando apenas `{ status: 'woot' }` e o `deploy_check.yml` voltando para `/api` sem o incremento).