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/gpt-permission-continuation/session-state.ts

@@ -0,0 +1,34 @@
+type SessionState = {
+  inFlight: boolean
+  lastHandledMessageID?: string
+  lastInjectedAt?: number
+}
+
+export type SessionStateStore = ReturnType<typeof createSessionStateStore>
+
+export function createSessionStateStore() {
+  const states = new Map<string, SessionState>()
+
+  const getState = (sessionID: string): SessionState => {
+    const existing = states.get(sessionID)
+    if (existing) return existing
+
+    const created: SessionState = {
+      inFlight: false,
+    }
+    states.set(sessionID, created)
+    return created
+  }
+
+  return {
+    getState,
+    wasRecentlyInjected(sessionID: string, windowMs: number): boolean {
+      const state = states.get(sessionID)
+      if (!state?.lastInjectedAt) return false
+      return Date.now() - state.lastInjectedAt <= windowMs
+    },
+    cleanup(sessionID: string): void {
+      states.delete(sessionID)
+    },
+  }
+}