diff --git a/metagpt/prompts/di/role_zero.py b/metagpt/prompts/di/role_zero.py
index 478f5c0d4..de1673e62 100644
--- a/metagpt/prompts/di/role_zero.py
+++ b/metagpt/prompts/di/role_zero.py
@@ -80,6 +80,18 @@ Review and reflect on the history carefully, provide a different response.
 Describe if you should terminate using **end** command, or use **RoleZero.ask_human** to ask human for help, or try a different approach and output different commands. You are NOT allowed to provide the same commands again.
 Your reflection, then the commands in a json array:
 """
+ASK_HUMAN_COMMAND = """
+```json
+[
+    {
+        "command_name": "RoleZero.ask_human",
+        "args": {
+            "question": "I'm a little uncertain about the next step, could you provide me with some guidance?"
+        }
+    }
+]
+```
+"""
 JSON_REPAIR_PROMPT = """
 ## json data
 {json_data}
diff --git a/metagpt/roles/di/role_zero.py b/metagpt/roles/di/role_zero.py
index 6d6eb26ce..ad5c2d26a 100644
--- a/metagpt/roles/di/role_zero.py
+++ b/metagpt/roles/di/role_zero.py
@@ -15,6 +15,7 @@ from metagpt.exp_pool.context_builders import RoleZeroContextBuilder
 from metagpt.exp_pool.serializers import RoleZeroSerializer
 from metagpt.logs import logger
 from metagpt.prompts.di.role_zero import (
+    ASK_HUMAN_COMMAND,
     CMD_PROMPT,
     JSON_REPAIR_PROMPT,
     QUICK_THINK_PROMPT,
@@ -272,6 +273,11 @@ class RoleZero(Role):
             # If an identical response is detected, it is a bad response, mostly due to LLM repeating generated content
             # In this case, ask human for help and regenerate
             # TODO: switch to llm_cached_aask
+
+            #  Hard rule to ask human for help
+            if past_rsp.count(command_rsp) >= 3:
+                return ASK_HUMAN_COMMAND
+            # Try correction by self
             logger.warning(f"Duplicate response detected: {command_rsp}")
             regenerate_req = req + [UserMessage(content=REGENERATE_PROMPT)]
             regenerate_req = self.llm.format_msg(regenerate_req)
diff --git a/metagpt/roles/di/swe_agent.py b/metagpt/roles/di/swe_agent.py
index 7be794265..2384ac147 100644
--- a/metagpt/roles/di/swe_agent.py
+++ b/metagpt/roles/di/swe_agent.py
@@ -16,7 +16,7 @@ from metagpt.tools.libs.terminal import Bash
 class SWEAgent(RoleZero):
     name: str = "Swen"
     profile: str = "Issue Solver"
-    goal: str = "Resolve GitHub issue"
+    goal: str = "Resolve GitHub issue or bug in any existing codebase"
     system_msg: str = [SWE_AGENT_SYSTEM_TEMPLATE]
     _instruction: str = NEXT_STEP_TEMPLATE
     tools: list[str] = [