fix: guard output.output in tool after-hooks for MCP tools (#1720)

MCP tool responses can have undefined output.output, causing TypeError
crashes in tool.execute.after hooks.

Changes:
- comment-checker/hook.ts: guard output.output with ?? '' before toLowerCase()
- edit-error-recovery/hook.ts: guard output.output with ?? '' before toLowerCase()
- task-resume-info/hook.ts: extract output.output ?? '' into outputText before all string operations
- Added tests for undefined output.output in edit-error-recovery and task-resume-info

src/hooks/task-resume-info/hook.ts

@@ -21,14 +21,15 @@ export function createTaskResumeInfoHook() {
     output: { title: string; output: string; metadata: unknown }
   ) => {
     if (!TARGET_TOOLS.includes(input.tool)) return
-    if (output.output.startsWith("Error:") || output.output.startsWith("Failed")) return
-    if (output.output.includes("\nto continue:")) return
+    const outputText = output.output ?? ""
+    if (outputText.startsWith("Error:") || outputText.startsWith("Failed")) return
+    if (outputText.includes("\nto continue:")) return
 
-    const sessionId = extractSessionId(output.output)
+    const sessionId = extractSessionId(outputText)
     if (!sessionId) return
 
     output.output =
-      output.output.trimEnd() +
+      outputText.trimEnd() +
       `\n\nto continue: task(session_id="${sessionId}", prompt="...")`
   }