diff --git a/src/hooks/gpt-permission-continuation/constants.ts b/src/hooks/gpt-permission-continuation/constants.ts
index 690a0f0bd..04eda9a72 100644
--- a/src/hooks/gpt-permission-continuation/constants.ts
+++ b/src/hooks/gpt-permission-continuation/constants.ts
@@ -1,5 +1,6 @@
 export const HOOK_NAME = "gpt-permission-continuation"
 export const CONTINUATION_PROMPT = "continue"
+export const MAX_CONSECUTIVE_AUTO_CONTINUES = 3
 
 export const DEFAULT_STALL_PATTERNS = [
   "if you want",
diff --git a/src/hooks/gpt-permission-continuation/gpt-permission-continuation.test.ts b/src/hooks/gpt-permission-continuation/gpt-permission-continuation.test.ts
index dfb8b4591..c4068566f 100644
--- a/src/hooks/gpt-permission-continuation/gpt-permission-continuation.test.ts
+++ b/src/hooks/gpt-permission-continuation/gpt-permission-continuation.test.ts
@@ -1,4 +1,6 @@
-import { describe, expect, test } from "bun:test"
+/// <reference path="../../../bun-test.d.ts" />
+
+import { describe, expect, it as test } from "bun:test"
 
 import { createGptPermissionContinuationHook } from "."
 
@@ -38,6 +40,20 @@ function createMockPluginInput(messages: SessionMessage[]) {
   return { ctx, promptCalls }
 }
 
+function createAssistantMessage(id: string, text: string): SessionMessage {
+  return {
+    info: { id, role: "assistant", modelID: "gpt-5.4" },
+    parts: [{ type: "text", text }],
+  }
+}
+
+function createUserMessage(id: string, text: string): SessionMessage {
+  return {
+    info: { id, role: "user" },
+    parts: [{ type: "text", text }],
+  }
+}
+
 describe("gpt-permission-continuation", () => {
   test("injects continue when the last GPT assistant reply asks for permission", async () => {
     // given
@@ -147,4 +163,87 @@ describe("gpt-permission-continuation", () => {
     // then
     expect(promptCalls).toEqual(["continue"])
   })
+
+  describe("#given repeated GPT permission tails in the same session", () => {
+    describe("#when the permission phrases keep changing", () => {
+      test("stops injecting after three consecutive auto-continues", async () => {
+        // given
+        const messages: SessionMessage[] = [
+          createUserMessage("msg-0", "Please continue the fix."),
+          createAssistantMessage("msg-1", "If you want, I can apply the patch next."),
+        ]
+        const { ctx, promptCalls } = createMockPluginInput(messages)
+        const hook = createGptPermissionContinuationHook(ctx)
+
+        // when
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: "ses-1" } } })
+        messages.push(createUserMessage("msg-2", "continue"))
+        messages.push(createAssistantMessage("msg-3", "Would you like me to continue with the tests?"))
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: "ses-1" } } })
+        messages.push(createUserMessage("msg-4", "continue"))
+        messages.push(createAssistantMessage("msg-5", "Do you want me to wire the remaining cleanup?"))
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: "ses-1" } } })
+        messages.push(createUserMessage("msg-6", "continue"))
+        messages.push(createAssistantMessage("msg-7", "Shall I finish the remaining updates?"))
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: "ses-1" } } })
+
+        // then
+        expect(promptCalls).toEqual(["continue", "continue", "continue"])
+      })
+    })
+
+    describe("#when a real user message arrives between auto-continues", () => {
+      test("resets the consecutive auto-continue counter", async () => {
+        // given
+        const messages: SessionMessage[] = [
+          createUserMessage("msg-0", "Please continue the fix."),
+          createAssistantMessage("msg-1", "If you want, I can apply the patch next."),
+        ]
+        const { ctx, promptCalls } = createMockPluginInput(messages)
+        const hook = createGptPermissionContinuationHook(ctx)
+
+        // when
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: "ses-1" } } })
+        messages.push(createUserMessage("msg-2", "continue"))
+        messages.push(createAssistantMessage("msg-3", "Would you like me to continue with the tests?"))
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: "ses-1" } } })
+        messages.push(createUserMessage("msg-4", "Please keep going and finish the cleanup."))
+        messages.push(createAssistantMessage("msg-5", "Do you want me to wire the remaining cleanup?"))
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: "ses-1" } } })
+        messages.push(createUserMessage("msg-6", "continue"))
+        messages.push(createAssistantMessage("msg-7", "Shall I finish the remaining updates?"))
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: "ses-1" } } })
+        messages.push(createUserMessage("msg-8", "continue"))
+        messages.push(createAssistantMessage("msg-9", "If you want, I can apply the final polish."))
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: "ses-1" } } })
+        messages.push(createUserMessage("msg-10", "continue"))
+        messages.push(createAssistantMessage("msg-11", "Would you like me to ship the final verification?"))
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: "ses-1" } } })
+
+        // then
+        expect(promptCalls).toEqual(["continue", "continue", "continue", "continue", "continue"])
+      })
+    })
+
+    describe("#when the same permission phrase repeats after an auto-continue", () => {
+      test("stops immediately on stagnation", async () => {
+        // given
+        const messages: SessionMessage[] = [
+          createUserMessage("msg-0", "Please continue the fix."),
+          createAssistantMessage("msg-1", "If you want, I can apply the patch next."),
+        ]
+        const { ctx, promptCalls } = createMockPluginInput(messages)
+        const hook = createGptPermissionContinuationHook(ctx)
+
+        // when
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: "ses-1" } } })
+        messages.push(createUserMessage("msg-2", "continue"))
+        messages.push(createAssistantMessage("msg-3", "If you want, I can apply the patch next."))
+        await hook.handler({ event: { type: "session.idle", properties: { sessionID: "ses-1" } } })
+
+        // then
+        expect(promptCalls).toEqual(["continue"])
+      })
+    })
+  })
 })
diff --git a/src/hooks/gpt-permission-continuation/handler.ts b/src/hooks/gpt-permission-continuation/handler.ts
index 0db3142dc..252f8e357 100644
--- a/src/hooks/gpt-permission-continuation/handler.ts
+++ b/src/hooks/gpt-permission-continuation/handler.ts
@@ -9,10 +9,16 @@ import {
   isGptAssistantMessage,
   type SessionMessage,
 } from "./assistant-message"
-import { CONTINUATION_PROMPT, HOOK_NAME } from "./constants"
+import {
+  CONTINUATION_PROMPT,
+  HOOK_NAME,
+  MAX_CONSECUTIVE_AUTO_CONTINUES,
+} from "./constants"
 import { detectStallPattern } from "./detector"
 import type { SessionStateStore } from "./session-state"
 
+type SessionState = ReturnType<SessionStateStore["getState"]>
+
 async function promptContinuation(
   ctx: PluginInput,
   sessionID: string,
@@ -33,6 +39,37 @@ async function promptContinuation(
   await ctx.client.session.prompt(payload)
 }
 
+function getLastUserMessageBefore(
+  messages: SessionMessage[],
+  lastAssistantIndex: number,
+): SessionMessage | null {
+  for (let index = lastAssistantIndex - 1; index >= 0; index--) {
+    if (messages[index].info?.role === "user") {
+      return messages[index]
+    }
+  }
+
+  return null
+}
+
+function isAutoContinuationUserMessage(message: SessionMessage): boolean {
+  return extractAssistantText(message).trim().toLowerCase() === CONTINUATION_PROMPT
+}
+
+function extractPermissionPhrase(text: string): string | null {
+  const tail = text.slice(-800)
+  const lines = tail.split("\n").map((line) => line.trim()).filter(Boolean)
+  const hotZone = lines.slice(-3).join(" ")
+  const sentenceParts = hotZone.trim().replace(/\s+/g, " ").split(/(?<=[.!?])\s+/)
+  const trailingSegment = sentenceParts[sentenceParts.length - 1]?.trim().toLowerCase() ?? ""
+  return trailingSegment || null
+}
+
+function resetAutoContinuationState(state: SessionState): void {
+  state.consecutiveAutoContinueCount = 0
+  state.lastAutoContinuePermissionPhrase = undefined
+}
+
 export function createGptPermissionContinuationHandler(args: {
   ctx: PluginInput
   sessionStateStore: SessionStateStore
@@ -78,6 +115,12 @@ export function createGptPermissionContinuationHandler(args: {
       const lastAssistantMessage = getLastAssistantMessage(messages)
       if (!lastAssistantMessage) return
 
+      const lastAssistantIndex = messages.lastIndexOf(lastAssistantMessage)
+      const previousUserMessage = getLastUserMessageBefore(messages, lastAssistantIndex)
+      if (previousUserMessage && !isAutoContinuationUserMessage(previousUserMessage)) {
+        resetAutoContinuationState(state)
+      }
+
       const messageID = lastAssistantMessage.info?.id
       if (messageID && state.lastHandledMessageID === messageID) {
         log(`[${HOOK_NAME}] Skipped: already handled assistant message`, { sessionID, messageID })
@@ -99,9 +142,39 @@ export function createGptPermissionContinuationHandler(args: {
         return
       }
 
+      const permissionPhrase = extractPermissionPhrase(assistantText)
+      if (!permissionPhrase) {
+        return
+      }
+
+      if (state.consecutiveAutoContinueCount >= MAX_CONSECUTIVE_AUTO_CONTINUES) {
+        state.lastHandledMessageID = messageID
+        log(`[${HOOK_NAME}] Skipped: reached max consecutive auto-continues`, {
+          sessionID,
+          messageID,
+          consecutiveAutoContinueCount: state.consecutiveAutoContinueCount,
+        })
+        return
+      }
+
+      if (
+        state.consecutiveAutoContinueCount >= 1
+        && state.lastAutoContinuePermissionPhrase === permissionPhrase
+      ) {
+        state.lastHandledMessageID = messageID
+        log(`[${HOOK_NAME}] Skipped: repeated permission phrase after auto-continue`, {
+          sessionID,
+          messageID,
+          permissionPhrase,
+        })
+        return
+      }
+
       state.inFlight = true
       await promptContinuation(ctx, sessionID)
       state.lastHandledMessageID = messageID
+      state.consecutiveAutoContinueCount += 1
+      state.lastAutoContinuePermissionPhrase = permissionPhrase
       state.lastInjectedAt = Date.now()
       log(`[${HOOK_NAME}] Injected continuation prompt`, { sessionID, messageID })
     } catch (error) {
diff --git a/src/hooks/gpt-permission-continuation/session-state.ts b/src/hooks/gpt-permission-continuation/session-state.ts
index 132675086..fc3497235 100644
--- a/src/hooks/gpt-permission-continuation/session-state.ts
+++ b/src/hooks/gpt-permission-continuation/session-state.ts
@@ -1,6 +1,8 @@
 type SessionState = {
   inFlight: boolean
+  consecutiveAutoContinueCount: number
   lastHandledMessageID?: string
+  lastAutoContinuePermissionPhrase?: string
   lastInjectedAt?: number
 }
 
@@ -15,6 +17,7 @@ export function createSessionStateStore() {
 
     const created: SessionState = {
       inFlight: false,
+      consecutiveAutoContinueCount: 0,
     }
     states.set(sessionID, created)
     return created