chore: add updates to force redeployment on Vercel (#348)

## Changes made
- Updated `check.sh` script to add support for automatic re-deploying in
the event that the the registry has a partial/full outage.

---------

Co-authored-by: Cian Johnston <cian@coder.com>

.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
@@ -24,7 +30,7 @@ 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 +51,7 @@ 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 +80,70 @@ 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&target=production&state=BUILDING,INITIALIZING,QUEUED,READY" \
+        --fail \
+        --silent \
+        --header "Authorization: Bearer $VERCEL_API_KEY" \
+        --header "Content-Type: application/json"
+    )
+
+    # If we have zero deployments, something is VERY wrong. Make the whole
+    # script exit with a non-zero status code
+    local latest_id
+    latest_id=$(echo "${latest_res}" | jq -r '.deployments[0].uid')
+    if [[ "${latest_id}" = "null" ]]; then
+        echo "Unable to pull any previous deployments for redeployment"
+        echo "Please redeploy the latest deployment manually in Vercel."
+        echo "https://vercel.com/codercom/registry/deployments"
+        exit 1
+    fi
+
+    local latest_date_ts_seconds
+    latest_date_ts_seconds=$(echo "${latest_res}" | jq -r '.deployments[0].createdAt/1000|floor')
+    local current_date_ts_seconds
+    current_date_ts_seconds="$(date +%s)"
+    local max_redeploy_interval_seconds=7200 # 2 hours
+    if (( current_date_ts_seconds - latest_date_ts_seconds < max_redeploy_interval_seconds )); then
+        echo "The registry was deployed less than 2 hours ago."
+        echo "Not automatically re-deploying the regitstry."
+        echo "A human reading this message should decide if a redeployment is necessary."
+        echo "Please check the Vercel dashboard for more information."
+        echo "https://vercel.com/codercom/registry/deployments"
+        exit 1
+    fi
+
+    local latest_deployment_state
+    latest_deployment_state="$(echo "${latest_res}" | jq -r '.deployments[0].state')"
+    if [[ "${latest_deployment_state}" != "READY" ]]; then
+        echo "Last deployment was not in READY state. Skipping redeployment."
+        echo "A human reading this message should decide if a redeployment is necessary."
+        echo "Please check the Vercel dashboard for more information."
+        echo "https://vercel.com/codercom/registry/deployments"
+        exit 1
+    fi
+
+    echo "============================================================="
+    echo "!!! Redeploying registry with deployment ID: ${latest_id} !!!"
+    echo "============================================================="
+
+    if ! curl -X POST "https://api.vercel.com/v13/deployments?forceNew=1&skipAutoDetectionConfirmation=1&slug=$VERCEL_TEAM_SLUG&teamId=$VERCEL_TEAM_ID" \
+        --fail \
+        --header "Authorization: Bearer $VERCEL_API_KEY" \
+        --header "Content-Type: application/json" \
+        --data-raw "{ \"deploymentId\": \"${latest_id}\", \"name\": \"${VERCEL_APP}\", \"target\": \"production\" }"; then
+        echo "DEPLOYMENT FAILED! Please check the Vercel dashboard for more information."
+        echo "https://vercel.com/codercom/registry/deployments"
+        exit 1
+    fi
+}
+
 # Check each module's accessibility
 for module in "${modules[@]}"; do
     # Trim leading/trailing whitespace from module name
@@ -81,7 +151,6 @@ for module in "${modules[@]}"; do
     url="${REGISTRY_BASE_URL}/modules/${module}"
     printf "=== Checking module %s at %s\n" "${module}" "${url}"
     status_code=$(curl --output /dev/null --head --silent --fail --location "${url}" --retry 3 --write-out "%{http_code}")
-    # shellcheck disable=SC2181
     if (( status_code != 200 )); then
         printf "==> FAIL(%s)\n" "${status_code}"
         status=1
@@ -94,11 +163,11 @@ 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"
 else
     echo "The following modules have issues: ${failures[*]}"
-    # check if all modules are down 
+    # check if all modules are down
     if (( ${#failures[@]} == ${#modules[@]} )); then
         update_component_status "MAJOROUTAGE"
     else
@@ -108,6 +177,10 @@ else
     # Create a new incident
     incident_id=$(create_incident)
     echo "Created incident with ID: $incident_id"
+
+    # If a module is down, force a reployment to try getting things back online
+    # ASAP
+    force_redeploy_registry
 fi
 
 exit "${status}"

.github/workflows/check.yaml

@@ -2,7 +2,7 @@ name: Health
 # Check modules health on registry.coder.com
 on:
   schedule:
-    - cron: "*/13 * * * *" # Runs every 13th minute
+    - cron: "0,15,30,45 * * * *" # Runs every 15 minutes
   workflow_dispatch: # Allows manual triggering of the workflow if needed
 
 jobs:
@@ -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 }}