chore: integrate Instatus API for module checks

- Improve monitoring by implementing Instatus API to update component
  status based on module check results.
- Automate incident reports for module failures to enable efficient
  troubleshooting.

.github/scripts/check.sh

@@ -1,24 +1,70 @@
 #!/usr/bin/env bash
 set -o pipefail
-REGISTRY_BASE_URL="${REGISTRY_BASE_URL:-https://registry.coder.com}"
 set -u
 
-if [[ -n "${VERBOSE:-}" ]]; then
-    set -x
-fi
+REGISTRY_BASE_URL="${REGISTRY_BASE_URL:-https://registry.coder.com}"
 
 status=0
 declare -a modules=()
 declare -a failures=()
+
+# Collect all module directories containing a main.tf file
 for path in $(find . -not -path '*/.*' -type f -name main.tf -maxdepth 2 | cut -d '/' -f 2 | sort -u); do
     modules+=("${path}")
 done
+
 echo "Checking modules: ${modules[*]}"
+
+# Function to update the component status on Instatus
+update_component_status() {
+    local component_status=$1
+    # see https://instatus.com/help/api/components
+    (curl -X PUT "https://api.instatus.com/v1/$INSTATUS_PAGE_ID/components/$INSTATUS_COMPONENT_ID" \
+        -H "Authorization: Bearer $INSTATUS_API_KEY" \
+        -H "Content-Type: application/json" \
+        -d "{\"status\": \"$component_status\"}")
+}
+
+# Function to create an incident
+create_incident() {
+    local incident_name="Testing Instatus"
+    local message="The following modules are experiencing issues:\n"
+    for i in "${!failures[@]}"; do
+        message+="$(($i + 1)). ${failures[$i]}\n"
+    done
+
+    component_status="PARTIALOUTAGE"
+    if (( ${#failures[@]} == ${#modules[@]} )); then
+        component_status="MAJOROUTAGE"
+    fi
+    # see https://instatus.com/help/api/incidents
+    response=$(curl -s -X POST "https://api.instatus.com/v1/$INSTATUS_PAGE_ID/incidents" \
+        -H "Authorization: Bearer $INSTATUS_API_KEY" \
+        -H "Content-Type: application/json" \
+        -d "{
+            \"name\": \"$incident_name\",
+            \"message\": \"$message\",
+            \"components\": [\"$INSTATUS_COMPONENT_ID\"],
+            \"status\": \"INVESTIGATING\",
+            \"notify\": true,
+            \"statuses\": [
+                {
+                    \"id\": \"$INSTATUS_COMPONENT_ID\",
+                    \"status\": \"PARTIALOUTAGE\"
+                }
+            ]
+        }")
+
+    incident_id=$(echo "$response" | jq -r '.id')
+    echo "$incident_id"
+}
+
+# Check each module's accessibility
 for module in "${modules[@]}"; do
     # Trim leading/trailing whitespace from module name
     module=$(echo "${module}" | xargs)
     url="${REGISTRY_BASE_URL}/modules/${module}"
-    printf "=== Check module %s at %s\n" "${module}" "${url}"
+    printf "=== Checking module %s at %s\n" "${module}" "${url}"
     status_code=$(curl --output /dev/null --head --silent --fail --location "${url}" --retry 3 --write-out "%{http_code}")
     # shellcheck disable=SC2181
     if (( status_code != 200 )); then
@@ -30,7 +76,23 @@ for module in "${modules[@]}"; do
     fi
 done
 
-if (( status != 0 )); then
-    echo "The following modules appear to have issues: ${failures[*]}"
+# Determine overall status and update Instatus component
+if (( status == 0 )); then
+    echo "All modules are operational."
+    # set to 
+    update_component_status "OPERATIONAL"
+else
+    echo "The following modules have issues: ${failures[*]}"
+    # check if all modules are down 
+    if (( ${#failures[@]} == ${#modules[@]} )); then
+        update_component_status "MAJOROUTAGE"
+    else
+        update_component_status "PARTIALOUTAGE"
+    fi
+
+    # Create a new incident
+    incident_id=$(create_incident)
+    echo "Created incident with ID: $incident_id"
 fi
+
 exit "${status}"

.github/workflows/check.yaml

@@ -16,3 +16,7 @@ jobs:
       - name: Run check.sh
         run: |
           ./.github/scripts/check.sh
+        env:
+          INSTATUS_API_KEY: ${{ secrets.INSTATUS_API_KEY }}
+          INSTATUS_PAGE_ID: ${{ secrets.INSTATUS_PAGE_ID }}
+          INSTATUS_COMPONENT_ID: ${{ secrets.INSTATUS_COMPONENT_ID }}