Add GitHub prompt to CodeAct (#1792)

* Added github to CodeAct

* More codeact

* Simplify prompt

* Modify codeact prompt

* fix integration test for CodeAct

* yet another integration test fix for codeact

* fix plugin use in jupyter

* update edit tests

* fix jupyter plugin potential port conflict

* fix test ipython with latest ipython fix

* update integration test

* wait a bit for jupyter execution

* add one unit tests for sandbox

* fix integration test

---------

Co-authored-by: OpenDevinBot <bot@opendevin.com>
Co-authored-by: Xingyao Wang <xingyao6@illinois.edu>

agenthub/codeact_agent/codeact_agent.py

@@ -1,6 +1,12 @@
 import re
 
-from agenthub.codeact_agent.prompt import EXAMPLES, SYSTEM_MESSAGE
+from agenthub.codeact_agent.prompt import (
+    COMMAND_DOCS,
+    EXAMPLES,
+    GITHUB_MESSAGE,
+    SYSTEM_PREFIX,
+    SYSTEM_SUFFIX,
+)
 from opendevin.controller.agent import Agent
 from opendevin.controller.state.state import State
 from opendevin.core.logger import opendevin_logger as logger
@@ -22,6 +28,8 @@ from opendevin.runtime.plugins import (
     SWEAgentCommandsRequirement,
 )
 
+ENABLE_GITHUB = True
+
 
 def parse_response(response) -> str:
     action = response.choices[0].message.content
@@ -77,7 +85,7 @@ def swe_agent_edit_hack(bash_command: str) -> str:
 
 
 class CodeActAgent(Agent):
-    VERSION = '1.1'
+    VERSION = '1.2'
     """
     The Code Act Agent is a minimalist agent.
     The agent works by passing the model a list of action-observation pairs and prompting the model to take the next step.
@@ -119,6 +127,12 @@ class CodeActAgent(Agent):
         SWEAgentCommandsRequirement(),
     ]
 
+    system_message: str = (
+        f'{SYSTEM_PREFIX}\n{GITHUB_MESSAGE}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
+        if ENABLE_GITHUB
+        else f'{SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
+    )
+
     def __init__(
         self,
         llm: LLM,
@@ -138,7 +152,7 @@ class CodeActAgent(Agent):
         """
         super().reset()
         self.messages: list[dict[str, str]] = [
-            {'role': 'system', 'content': SYSTEM_MESSAGE},
+            {'role': 'system', 'content': self.system_message},
             {
                 'role': 'user',
                 'content': f"Here is an example of how you can interact with the environment for task solving:\n{EXAMPLES}\n\nNOW, LET'S START!",

agenthub/codeact_agent/prompt.py

@@ -21,13 +21,13 @@ edit <start_line>:<end_line>
 end_of_edit - replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing the same command a second time will just lead to the same error message again. Remember, the file must be open before editing.
 """
 
-_COMMAND_DOCS = (
+COMMAND_DOCS = (
     '\nApart from the standard bash commands, you can also use the following special commands in <execute_bash> environment:\n'
     f'{_SWEAGENT_BASH_DOCS}'
     "Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. If you'd like to add the line '        print(x)' you must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run."
 )
 
-SYSTEM_MESSAGE = f"""A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
+SYSTEM_PREFIX = """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
 The assistant can interact with an interactive Python (Jupyter Notebook) environment and receive the corresponding output when needed. The code should be enclosed using "<execute_ipython>" tag, for example:
 <execute_ipython>
 print("Hello World!")
@@ -41,12 +41,15 @@ If the assistant encounters an import error in IPython for a newly installed pac
 <execute_ipython>
 import IPython
 IPython.Application.instance().kernel.do_shutdown(True)  # Restart the kernel
-</execute_ipython>
+</execute_ipython>"""
 
-{_COMMAND_DOCS}
+GITHUB_MESSAGE = """To do any activities on GitHub, you should use the token in the $GITHUB_TOKEN environment variable.
+For instance, to push a local branch `my_branch` to the github repo `owner/repo`, you can use the following four commands:
+<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
+If you require access to GitHub but $GITHUB_TOKEN is not set, ask the user to set it for you."""
 
-The assistant's response should be concise, but do express their thoughts.
-Try to include one of <execute_ipython> or <execute_bash> in each of your responses, unless it is a direct answer to a question OR a message to the user.
+SYSTEM_SUFFIX = """The assistant's response should be concise.
+You should include <execute_ipython> or <execute_bash> in every one of your responses, unless you are finished with the task or need more input or action from the user in order to proceed.
 IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
 """
 

tests/integration/mock/CodeActAgent/test_edits/prompt_001.log

@@ -17,6 +17,10 @@ If the assistant encounters an import error in IPython for a newly installed pac
 import IPython
 IPython.Application.instance().kernel.do_shutdown(True)  # Restart the kernel
 </execute_ipython>
+To do any activities on GitHub, you should use the token in the $GITHUB_TOKEN environment variable.
+For instance, to push a local branch `my_branch` to the github repo `owner/repo`, you can use the following four commands:
+<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
+If you require access to GitHub but $GITHUB_TOKEN is not set, ask the user to set it for you.
 
 
 Apart from the standard bash commands, you can also use the following special commands in <execute_bash> environment:
@@ -33,8 +37,8 @@ edit <start_line>:<end_line>
 end_of_edit - replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing the same command a second time will just lead to the same error message again. Remember, the file must be open before editing.
 Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. If you'd like to add the line '        print(x)' you must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
 
-The assistant's response should be concise, but do express their thoughts.
-Try to include one of <execute_ipython> or <execute_bash> in each of your responses, unless it is a direct answer to a question OR a message to the user.
+The assistant's response should be concise.
+You should include <execute_ipython> or <execute_bash> in every one of your responses, unless you are finished with the task or need more input or action from the user in order to proceed.
 IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
 
 

tests/integration/mock/CodeActAgent/test_edits/prompt_002.log

@@ -17,6 +17,10 @@ If the assistant encounters an import error in IPython for a newly installed pac
 import IPython
 IPython.Application.instance().kernel.do_shutdown(True)  # Restart the kernel
 </execute_ipython>
+To do any activities on GitHub, you should use the token in the $GITHUB_TOKEN environment variable.
+For instance, to push a local branch `my_branch` to the github repo `owner/repo`, you can use the following four commands:
+<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
+If you require access to GitHub but $GITHUB_TOKEN is not set, ask the user to set it for you.
 
 
 Apart from the standard bash commands, you can also use the following special commands in <execute_bash> environment:
@@ -33,8 +37,8 @@ edit <start_line>:<end_line>
 end_of_edit - replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing the same command a second time will just lead to the same error message again. Remember, the file must be open before editing.
 Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. If you'd like to add the line '        print(x)' you must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
 
-The assistant's response should be concise, but do express their thoughts.
-Try to include one of <execute_ipython> or <execute_bash> in each of your responses, unless it is a direct answer to a question OR a message to the user.
+The assistant's response should be concise.
+You should include <execute_ipython> or <execute_bash> in every one of your responses, unless you are finished with the task or need more input or action from the user in order to proceed.
 IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
 
 
@@ -224,7 +228,7 @@ ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
 
 ----------
 
-Certainly! I will start by opening the file `bad.txt` to see what content it has and then proceed to fix any typos I find.
+Certainly! I will start by opening the file `bad.txt` to see the content and then proceed to fix the typos.
 
 <execute_bash>
 open bad.txt
@@ -233,10 +237,10 @@ open bad.txt
 ----------
 
 OBSERVATION:
-[File: /workspace/bad.txt (4 lines total)]
-1:This is a stupid typoo.
-2:Really?
-3:No mor typos!
+[File: /workspace/bad.txt (4 lines total)]
+1:This is a stupid typoo.
+2:Really?
+3:No mor typos!
 4:Enjoy!
 [Command -1 finished with exit code 0]]
 

tests/integration/mock/CodeActAgent/test_edits/prompt_003.log

@@ -17,6 +17,10 @@ If the assistant encounters an import error in IPython for a newly installed pac
 import IPython
 IPython.Application.instance().kernel.do_shutdown(True)  # Restart the kernel
 </execute_ipython>
+To do any activities on GitHub, you should use the token in the $GITHUB_TOKEN environment variable.
+For instance, to push a local branch `my_branch` to the github repo `owner/repo`, you can use the following four commands:
+<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
+If you require access to GitHub but $GITHUB_TOKEN is not set, ask the user to set it for you.
 
 
 Apart from the standard bash commands, you can also use the following special commands in <execute_bash> environment:
@@ -33,8 +37,8 @@ edit <start_line>:<end_line>
 end_of_edit - replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing the same command a second time will just lead to the same error message again. Remember, the file must be open before editing.
 Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. If you'd like to add the line '        print(x)' you must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
 
-The assistant's response should be concise, but do express their thoughts.
-Try to include one of <execute_ipython> or <execute_bash> in each of your responses, unless it is a direct answer to a question OR a message to the user.
+The assistant's response should be concise.
+You should include <execute_ipython> or <execute_bash> in every one of your responses, unless you are finished with the task or need more input or action from the user in order to proceed.
 IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
 
 
@@ -224,7 +228,7 @@ ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
 
 ----------
 
-Certainly! I will start by opening the file `bad.txt` to see what content it has and then proceed to fix any typos I find.
+Certainly! I will start by opening the file `bad.txt` to see the content and then proceed to fix the typos.
 
 <execute_bash>
 open bad.txt
@@ -233,10 +237,10 @@ open bad.txt
 ----------
 
 OBSERVATION:
-[File: /workspace/bad.txt (4 lines total)]
-1:This is a stupid typoo.
-2:Really?
-3:No mor typos!
+[File: /workspace/bad.txt (4 lines total)]
+1:This is a stupid typoo.
+2:Really?
+3:No mor typos!
 4:Enjoy!
 [Command -1 finished with exit code 0]]
 
@@ -244,7 +248,7 @@ ENVIRONMENT REMINDER: You have 97 turns left to complete the task.
 
 ----------
 
-I see a few typos in the file `bad.txt`. I will correct them now.
+I will now edit the file to correct the typos.
 
 <execute_bash>
 edit 1:1
@@ -258,17 +262,17 @@ end_of_edit
 ----------
 
 OBSERVATION:
-> > [File: /workspace/bad.txt (4 lines total)]
-1:This is a stupid typo.
-2:Really?
-3:No mor typos!
-4:Enjoy!
-File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.
-> > [File: /workspace/bad.txt (4 lines total)]
-1:This is a stupid typo.
-2:Really?
-3:No more typos!
-4:Enjoy!
+> > [File: /workspace/bad.txt (4 lines total)]
+1:This is a stupid typo.
+2:Really?
+3:No mor typos!
+4:Enjoy!
+File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.
+> > [File: /workspace/bad.txt (4 lines total)]
+1:This is a stupid typo.
+2:Really?
+3:No more typos!
+4:Enjoy!
 File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.
 [Command -1 finished with exit code 0]]
 

tests/integration/mock/CodeActAgent/test_edits/response_001.log

@@ -1,4 +1,4 @@
-Certainly! I will start by opening the file `bad.txt` to see what content it has and then proceed to fix any typos I find.
+Certainly! I will start by opening the file `bad.txt` to see the content and then proceed to fix the typos.
 
 <execute_bash>
 open bad.txt

tests/integration/mock/CodeActAgent/test_edits/response_002.log

@@ -1,4 +1,4 @@
-I see a few typos in the file `bad.txt`. I will correct them now.
+I will now edit the file to correct the typos.
 
 <execute_bash>
 edit 1:1

tests/integration/mock/CodeActAgent/test_edits/response_003.log

@@ -1 +1 @@
-The typos in the file `bad.txt` have been fixed. The content should now be correct without any spelling mistakes. If there's anything else you need, let me know!
+The typos in `bad.txt` have been fixed. The task is complete. If you need further assistance, feel free to ask!

tests/integration/mock/CodeActAgent/test_ipython/prompt_001.log

@@ -17,6 +17,10 @@ If the assistant encounters an import error in IPython for a newly installed pac
 import IPython
 IPython.Application.instance().kernel.do_shutdown(True)  # Restart the kernel
 </execute_ipython>
+To do any activities on GitHub, you should use the token in the $GITHUB_TOKEN environment variable.
+For instance, to push a local branch `my_branch` to the github repo `owner/repo`, you can use the following four commands:
+<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
+If you require access to GitHub but $GITHUB_TOKEN is not set, ask the user to set it for you.
 
 
 Apart from the standard bash commands, you can also use the following special commands in <execute_bash> environment:
@@ -33,8 +37,8 @@ edit <start_line>:<end_line>
 end_of_edit - replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing the same command a second time will just lead to the same error message again. Remember, the file must be open before editing.
 Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. If you'd like to add the line '        print(x)' you must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
 
-The assistant's response should be concise, but do express their thoughts.
-Try to include one of <execute_ipython> or <execute_bash> in each of your responses, unless it is a direct answer to a question OR a message to the user.
+The assistant's response should be concise.
+You should include <execute_ipython> or <execute_bash> in every one of your responses, unless you are finished with the task or need more input or action from the user in order to proceed.
 IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
 
 

tests/integration/mock/CodeActAgent/test_ipython/prompt_002.log

@@ -17,6 +17,10 @@ If the assistant encounters an import error in IPython for a newly installed pac
 import IPython
 IPython.Application.instance().kernel.do_shutdown(True)  # Restart the kernel
 </execute_ipython>
+To do any activities on GitHub, you should use the token in the $GITHUB_TOKEN environment variable.
+For instance, to push a local branch `my_branch` to the github repo `owner/repo`, you can use the following four commands:
+<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
+If you require access to GitHub but $GITHUB_TOKEN is not set, ask the user to set it for you.
 
 
 Apart from the standard bash commands, you can also use the following special commands in <execute_bash> environment:
@@ -33,8 +37,8 @@ edit <start_line>:<end_line>
 end_of_edit - replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing the same command a second time will just lead to the same error message again. Remember, the file must be open before editing.
 Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. If you'd like to add the line '        print(x)' you must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
 
-The assistant's response should be concise, but do express their thoughts.
-Try to include one of <execute_ipython> or <execute_bash> in each of your responses, unless it is a direct answer to a question OR a message to the user.
+The assistant's response should be concise.
+You should include <execute_ipython> or <execute_bash> in every one of your responses, unless you are finished with the task or need more input or action from the user in order to proceed.
 IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
 
 
@@ -224,10 +228,10 @@ ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
 
 ----------
 
-Certainly! I will write the text 'hello world' to the file `/workspace/test.txt` using IPython.
+Certainly! I will write the text 'hello world' to the file `/workspace/test.txt` using Jupyter IPython.
 
 <execute_ipython>
-# Writing 'hello world' to the specified text file
+# Write 'hello world' to the specified text file
 with open('/workspace/test.txt', 'w') as file:
     file.write('hello world')
 </execute_ipython>

tests/integration/mock/CodeActAgent/test_ipython/response_001.log

@@ -1,6 +1,6 @@
-Certainly! I will write the text 'hello world' to the file `/workspace/test.txt` using IPython.
+Certainly! I will write the text 'hello world' to the file `/workspace/test.txt` using Jupyter IPython.
 
 <execute_ipython>
-# Writing 'hello world' to the specified text file
+# Write 'hello world' to the specified text file
 with open('/workspace/test.txt', 'w') as file:
     file.write('hello world')

tests/integration/mock/CodeActAgent/test_ipython/response_002.log

@@ -1 +1 @@
-The text 'hello world' has been successfully written to `/workspace/test.txt`. If you need any further assistance or another task to be done, feel free to let me know!
+The text 'hello world' has been successfully written to `/workspace/test.txt`. If you need any further assistance, feel free to ask!

tests/integration/mock/CodeActAgent/test_write_simple_script/prompt_001.log

@@ -17,6 +17,10 @@ If the assistant encounters an import error in IPython for a newly installed pac
 import IPython
 IPython.Application.instance().kernel.do_shutdown(True)  # Restart the kernel
 </execute_ipython>
+To do any activities on GitHub, you should use the token in the $GITHUB_TOKEN environment variable.
+For instance, to push a local branch `my_branch` to the github repo `owner/repo`, you can use the following four commands:
+<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
+If you require access to GitHub but $GITHUB_TOKEN is not set, ask the user to set it for you.
 
 
 Apart from the standard bash commands, you can also use the following special commands in <execute_bash> environment:
@@ -33,8 +37,8 @@ edit <start_line>:<end_line>
 end_of_edit - replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing the same command a second time will just lead to the same error message again. Remember, the file must be open before editing.
 Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. If you'd like to add the line '        print(x)' you must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
 
-The assistant's response should be concise, but do express their thoughts.
-Try to include one of <execute_ipython> or <execute_bash> in each of your responses, unless it is a direct answer to a question OR a message to the user.
+The assistant's response should be concise.
+You should include <execute_ipython> or <execute_bash> in every one of your responses, unless you are finished with the task or need more input or action from the user in order to proceed.
 IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
 
 

tests/integration/mock/CodeActAgent/test_write_simple_script/prompt_002.log

@@ -17,6 +17,10 @@ If the assistant encounters an import error in IPython for a newly installed pac
 import IPython
 IPython.Application.instance().kernel.do_shutdown(True)  # Restart the kernel
 </execute_ipython>
+To do any activities on GitHub, you should use the token in the $GITHUB_TOKEN environment variable.
+For instance, to push a local branch `my_branch` to the github repo `owner/repo`, you can use the following four commands:
+<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
+If you require access to GitHub but $GITHUB_TOKEN is not set, ask the user to set it for you.
 
 
 Apart from the standard bash commands, you can also use the following special commands in <execute_bash> environment:
@@ -33,8 +37,8 @@ edit <start_line>:<end_line>
 end_of_edit - replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing the same command a second time will just lead to the same error message again. Remember, the file must be open before editing.
 Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. If you'd like to add the line '        print(x)' you must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
 
-The assistant's response should be concise, but do express their thoughts.
-Try to include one of <execute_ipython> or <execute_bash> in each of your responses, unless it is a direct answer to a question OR a message to the user.
+The assistant's response should be concise.
+You should include <execute_ipython> or <execute_bash> in every one of your responses, unless you are finished with the task or need more input or action from the user in order to proceed.
 IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
 
 
@@ -224,10 +228,10 @@ ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
 
 ----------
 
-Certainly! I will create a shell script named `hello.sh` that prints "hello" when executed.
+Certainly! I will create a shell script named `hello.sh` that prints 'hello'.
 
 <execute_bash>
-echo 'echo hello' > hello.sh && chmod +x hello.sh
+echo "echo 'hello'" > hello.sh && chmod +x hello.sh
 </execute_bash>
 
 ----------

tests/integration/mock/CodeActAgent/test_write_simple_script/response_001.log

@@ -1,4 +1,4 @@
-Certainly! I will create a shell script named `hello.sh` that prints "hello" when executed.
+Certainly! I will create a shell script named `hello.sh` that prints 'hello'.
 
 <execute_bash>
-echo 'echo hello' > hello.sh && chmod +x hello.sh
+echo "echo 'hello'" > hello.sh && chmod +x hello.sh

tests/integration/mock/CodeActAgent/test_write_simple_script/response_002.log

@@ -1 +1 @@
-The shell script `hello.sh` has been created and made executable. You can now run this script to print "hello". If you need anything else, feel free to ask!
+The shell script `hello.sh` has been created and made executable. You can now run it to print 'hello'.