chore: add updates to force redeployment on Vercel

.github/scripts/check.sh

@@ -2,11 +2,17 @@
 set -o pipefail
 set -u
 
+VERBOSE="${VERBOSE:-0}"
+if [[ "${VERBOSE}" -ne "0" ]]; then
+    set -x
+fi
+
 # List of required environment variables
 required_vars=(
     "INSTATUS_API_KEY"
     "INSTATUS_PAGE_ID"
     "INSTATUS_COMPONENT_ID"
+    "VERCEL_API_KEY"
 )
 
 # Check if each required variable is set
@@ -17,14 +23,20 @@ for var in "${required_vars[@]}"; do
     fi
 done
 
+LATEST_REDEPLOY_FAILED="${LATEST_REDEPLOY_FAILED:-0}"
+if [[ "${LATEST_REDEPLOY_FAILED}" -ne "0" ]] ;then
+    echo "Trying to re-run job when previous re-deploy failed"
+    return 1
+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
+for path in $(find . -maxdepth 2 -not -path '*/.*' -type f -name main.tf | cut -d '/' -f 2 | sort -u); do
     modules+=("${path}")
 done
 
@@ -45,7 +57,7 @@ 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"
+        message+="$((i + 1)). ${failures[$i]}\n"
     done
 
     component_status="PARTIALOUTAGE"
@@ -74,6 +86,42 @@ create_incident() {
     echo "$incident_id"
 }
 
+force_redeploy_registry () {
+    # These are not secret values; safe to just expose directly in script
+    local VERCEL_TEAM_SLUG="codercom"
+    local VERCEL_TEAM_ID="team_tGkWfhEGGelkkqUUm9nXq17r"
+    local VERCEL_APP="registry"
+
+    local latest_res
+    latest_res=$(curl "https://api.vercel.com/v6/deployments?app=$VERCEL_APP&limit=1&slug=$VERCEL_TEAM_SLUG&teamId=$VERCEL_TEAM_ID" \
+        --fail \
+        --silent \
+        -H "Authorization: Bearer $VERCEL_API_KEY" \
+        -H "Content-Type: application/json"
+    )
+
+    # If we have zero deployments, something is VERY wrong. Make the whole
+    # script exit with a non-zero status code
+    local latest_id
+    latest_id=$(echo "${latest_res}" | jq '.deployments[0].uid')
+    if [[ "${latest_id}" = "null" ]]; then
+        echo "Unable to pull any previous deployments for redeployment"
+        return 1
+    fi
+
+    local redeploy_res
+    redeploy_res=$(curl -X POST "https://api.vercel.com/v13/deployments?forceNew=1&skipAutoDetectionConfirmation=1&slug=$VERCEL_TEAM_SLUG&teamId=$VERCEL_TEAM_ID" \
+        --fail \
+        --silent \
+        --output "/dev/null" \
+        -H "Authorization: Bearer $VERCEL_API_KEY" \
+        -H "Content-Type: application/json" \
+        -d "{ \"deploymentId\": \"${latest_id}\" }"
+    )
+
+    echo "${redeploy_res}"
+}
+
 # Check each module's accessibility
 for module in "${modules[@]}"; do
     # Trim leading/trailing whitespace from module name
@@ -94,11 +142,13 @@ done
 # Determine overall status and update Instatus component
 if (( status == 0 )); then
     echo "All modules are operational."
-    # set to 
+    # set to
     update_component_status "OPERATIONAL"
+
+    echo "LATEST_REDEPLOY_FAILED=0" >> "${GITHUB_ENV}"
 else
     echo "The following modules have issues: ${failures[*]}"
-    # check if all modules are down 
+    # check if all modules are down
     if (( ${#failures[@]} == ${#modules[@]} )); then
         update_component_status "MAJOROUTAGE"
     else
@@ -108,6 +158,22 @@ else
     # Create a new incident
     incident_id=$(create_incident)
     echo "Created incident with ID: $incident_id"
+
+    # If a module is down, force a reployment to try getting things back online
+    # ASAP
+    status_code=$(force_redeploy_registry)
+    # shellcheck disable=SC2181
+    if (( status_code == 200 )); then
+        echo "Reployment successful"
+    else
+        echo "Unable to redeploy automatically"
+    fi
+
+    # Update environment variable so that if automatic re-deployment fails, we
+    # don't keep running the script over and over again. Note that even if a
+    # re-deployment succeeds, that doesn't necessarily mean that everything is
+    # fully operational
+    echo "LATEST_REDEPLOY_FAILED=1" >> "${GITHUB_ENV}"
 fi
 
 exit "${status}"

.github/workflows/check.yaml

@@ -20,3 +20,4 @@ jobs:
           INSTATUS_API_KEY: ${{ secrets.INSTATUS_API_KEY }}
           INSTATUS_PAGE_ID: ${{ secrets.INSTATUS_PAGE_ID }}
           INSTATUS_COMPONENT_ID: ${{ secrets.INSTATUS_COMPONENT_ID }}
+          VERCEL_API_KEY: ${{ secrets.VERCEL_API_KEY }}