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/atlas/idle-event.ts

@@ -110,6 +110,7 @@ function scheduleRetry(input: {
     const currentProgress = getPlanProgress(currentBoulder.active_plan)
     if (currentProgress.isComplete) return
     if (options?.isContinuationStopped?.(sessionID)) return
+    if (options?.shouldSkipContinuation?.(sessionID)) return
     if (hasRunningBackgroundTasks(sessionID, options)) return
 
     await injectContinuation({
@@ -192,6 +193,11 @@ export async function handleAtlasSessionIdle(input: {
     return
   }
 
+  if (options?.shouldSkipContinuation?.(sessionID)) {
+    log(`[${HOOK_NAME}] Skipped: another continuation hook already injected`, { sessionID })
+    return
+  }
+
   if (sessionState.lastContinuationInjectedAt && now - sessionState.lastContinuationInjectedAt < CONTINUATION_COOLDOWN_MS) {
     scheduleRetry({ ctx, sessionID, sessionState, options })
     log(`[${HOOK_NAME}] Skipped: continuation cooldown active`, {