fix(continuation): auto-continue GPT permission-seeking replies

Resume GPT sessions when the last assistant reply ends in a permission-seeking tail, while honoring stop-continuation and avoiding duplicate continuation across todo and atlas flows.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

src/hooks/todo-continuation-enforcer/idle-event.ts

@@ -29,6 +29,7 @@ export async function handleSessionIdle(args: {
   backgroundManager?: BackgroundManager
   skipAgents?: string[]
   isContinuationStopped?: (sessionID: string) => boolean
+  shouldSkipContinuation?: (sessionID: string) => boolean
 }): Promise<void> {
   const {
     ctx,
@@ -37,6 +38,7 @@ export async function handleSessionIdle(args: {
     backgroundManager,
     skipAgents = DEFAULT_SKIP_AGENTS,
     isContinuationStopped,
+    shouldSkipContinuation,
   } = args
 
   log(`[${HOOK_NAME}] session.idle`, { sessionID })
@@ -186,6 +188,11 @@ export async function handleSessionIdle(args: {
     return
   }
 
+  if (shouldSkipContinuation?.(sessionID)) {
+    log(`[${HOOK_NAME}] Skipped: another continuation hook already injected`, { sessionID })
+    return
+  }
+
   const progressUpdate = sessionStateStore.trackContinuationProgress(sessionID, incompleteCount, todos)
   if (shouldStopForStagnation({ sessionID, incompleteCount, progressUpdate })) {
     return