From ba70bd97bc16c658964fd7293cff1f103114c465 Mon Sep 17 00:00:00 2001
From: Rodrigo Rodriguez <me@rodrigorodriguez.com>
Date: Sun, 15 Feb 2026 11:26:27 +0000
Subject: [PATCH] fix: Bootstrap should check Valkey is running and use correct
 component name

- Fix component name mismatch: "redis" -> "cache" in bootstrap_manager
- Add cache_health_check() function to verify Valkey is responding
- Add health check loop after starting cache (12s wait with PING test)
- Ensures cache is ready before proceeding with bootstrap

This fixes the issue where botserver would hang waiting for cache
connection because the cache component was never started.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
---
 src/core/bootstrap/bootstrap_manager.rs | 34 ++++++++++++++++++-------
 src/core/bootstrap/bootstrap_utils.rs   | 29 +++++++++++++++++++++
 2 files changed, 54 insertions(+), 9 deletions(-)

diff --git a/src/core/bootstrap/bootstrap_manager.rs b/src/core/bootstrap/bootstrap_manager.rs
index 4c3ed9a21..8f215c936 100644
--- a/src/core/bootstrap/bootstrap_manager.rs
+++ b/src/core/bootstrap/bootstrap_manager.rs
@@ -1,6 +1,6 @@
 // Bootstrap manager implementation
 use crate::core::bootstrap::bootstrap_types::{BootstrapManager, BootstrapProgress};
-use crate::core::bootstrap::bootstrap_utils::{safe_pkill, vault_health_check};
+use crate::core::bootstrap::bootstrap_utils::{cache_health_check, safe_pkill, vault_health_check};
 use crate::core::config::AppConfig;
 use crate::core::package_manager::{InstallMode, PackageManager};
 use log::{info, warn};
@@ -102,14 +102,30 @@ impl BootstrapManager {
             }
         }
 
-        if pm.is_installed("redis") {
-            info!("Starting Redis...");
-            match pm.start("redis") {
-                Ok(_child) => {
-                    info!("Redis started");
-                }
-                Err(e) => {
-                    warn!("Failed to start Redis: {}", e);
+        if pm.is_installed("cache") {
+            let cache_already_running = cache_health_check();
+            if cache_already_running {
+                info!("Valkey cache is already running");
+            } else {
+                info!("Starting Valkey cache...");
+                match pm.start("cache") {
+                    Ok(_child) => {
+                        info!("Valkey cache process started, waiting for readiness...");
+                        // Wait for cache to be ready
+                        for i in 0..12 {
+                            sleep(Duration::from_secs(1)).await;
+                            if cache_health_check() {
+                                info!("Valkey cache is responding");
+                                break;
+                            }
+                            if i == 11 {
+                                warn!("Valkey cache did not respond after 12 seconds");
+                            }
+                        }
+                    }
+                    Err(e) => {
+                        warn!("Failed to start Valkey cache: {}", e);
+                    }
                 }
             }
         }
diff --git a/src/core/bootstrap/bootstrap_utils.rs b/src/core/bootstrap/bootstrap_utils.rs
index 70b91bddd..8d89af4e4 100644
--- a/src/core/bootstrap/bootstrap_utils.rs
+++ b/src/core/bootstrap/bootstrap_utils.rs
@@ -91,6 +91,35 @@ pub fn vault_health_check() -> bool {
     false
 }
 
+/// Check if Valkey/Redis cache is healthy
+pub fn cache_health_check() -> bool {
+    // Try to PING the cache server
+    match Command::new("redis-cli")
+        .args(["-h", "127.0.0.1", "-p", "6379", "ping"])
+        .output()
+    {
+        Ok(output) => {
+            if output.status.success() {
+                let response = String::from_utf8_lossy(&output.stdout);
+                response.trim().to_uppercase() == "PONG"
+            } else {
+                false
+            }
+        }
+        Err(_) => {
+            // If redis-cli is not available, try TCP connection
+            match Command::new("sh")
+                .arg("-c")
+                .arg("timeout 1 bash -c '</dev/tcp/127.0.0.1/6379' 2>/dev/null")
+                .output()
+            {
+                Ok(output) => output.status.success(),
+                Err(_) => false,
+            }
+        }
+    }
+}
+
 /// Get current user safely
 pub fn safe_fuser() -> String {
     // Return shell command that uses $USER environment variable