Skip to content

Commit

Permalink
fix issues and update parser
Browse files Browse the repository at this point in the history
  • Loading branch information
@garyzhang99
garyzhang99 committed May 15, 2024
1 parent 2f05622 commit 903d49d
Show file tree
Hide file tree
Showing 7 changed files with 187 additions and 214 deletions.
73 changes: 22 additions & 51 deletions examples/swe_agent/main.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -6,10 +6,11 @@
"source": [
"# Example with SWE-agent\n",
"\n",
"SWE-agent is an agent designed for solving github issues.\n",
"More details can be found in https://swe-agent.com/.\n",
"SWE-agent(SoftWare Engineering Agent) is an agent designed for solving real world software engineering problems, such as fixing github issues.\n",
"More details can be found in their [homepage](https://swe-agent.com/) and related [github repo](https://swe-agent.com/).\n",
"\n",
"In the example here, we partially implement the SWE-agent, and provide a simple example of how to use the implemented SWE-agent to fix a bug in a python file.\n",
"You should note that currently how to enable agents with stronger programming capabilities remains an open challenge, and the performance of the paritially implemented SWE-agent is not guaranteed.\n",
"\n",
"## Prerequisites\n",
"\n",
Expand Down Expand Up @@ -48,7 +49,7 @@
"import agentscope\n",
"from agentscope.models import load_model_by_config_name\n",
"agentscope.init(\n",
" model_configs=\"xxx\", # fill you model config file path here\n",
" model_configs=\"xxx.json\", # fill you model config file path here\n",
")\n",
"loaded_model = load_model_by_config_name('gpt-4')\n",
"\n",
Expand Down Expand Up @@ -87,7 +88,7 @@
}
],
"source": [
"from agentscope.service import write_file\n",
"from swe_agent_service_func import write_file\n",
"\n",
"# here the gcd code is written in a wrong way\n",
"wrong_gcd_text = \"\"\"\n",
Expand Down Expand Up @@ -127,9 +128,9 @@
"name": "stdout",
"output_type": "stream",
"text": [
"user: The file in gcd.py is not returning the correct answer, can you fix the file for me?.\n",
"user: The file in gcd.py is not returning the correct answer, can you fix the file for me?\n",
"assistant: {\n",
" \"thought\": \"First, I need to view the file gcd.py to understand the bug the user is referring to. I'll read the file gcd.py using the `read_file` command.\",\n",
" \"thought\": \"To debug the gcd.py file, first we need to read the contents of the file to understand the existing program logic.\",\n",
" \"action\": {\n",
" \"name\": \"read_file\",\n",
" \"arguments\": {\n",
Expand All @@ -155,57 +156,30 @@
"print(\"LCM of 12 and 18 is:\", lcm(12, 18))\n",
"\n",
"\n",
"assistant: {\n",
" \"thought\": \"I can see that the gcd algorithm implemented in the gcd function within gcd.py file is incorrect. In the while loop of the gcd function, a and b should repeatedly subtract one from the other until a is zero but it's subtracting a from itself which would result in always zero. I'll correct this by modifying the line 5: 'a, b = b, a' to 'a, b = b % a, a'. \",\n",
" \"action\": {\n",
" \"name\": \"write_file\",\n",
" \"arguments\": {\n",
" \"start_line\": 3,\n",
" \"end_line\": 6,\n",
" \"content\": \" if a == 0:\\n return b\\n while b != 0:\\n a, b = b % a, a\",\n",
" \"file_path\": \"gcd.py\"\n",
" }\n",
" }\n",
"}\n",
"assistant: \n",
"====Observation====\n",
"WRITE OPERATION:\n",
"You have written to \"gcd.py\" on these lines: 3:6.\n",
"def gcd(a, b):\n",
" if a == 0:\n",
" if a == 0:\n",
" return b\n",
" while b != 0:\n",
" a, b = b % a, a\n",
"assistant: ```json\n",
"Upon reviewing the contents of gcd.py, I can see the gcd function is incorrectly implemented. While the function starts correctly by evaluating `if a == 0: return b`, the loop structure `while a != 0: a, b = b, a` does not accurately compute the greatest common divisor (gcd). \n",
"\n",
"def lcm(a, b):\n",
" return (a * b) // gcd(a, b)\n",
"\n",
"# testing on GCD and LCM functions\n",
"print(\"GCD of 12 and 18 is:\", gcd(12, 18))\n",
"print(\"LCM of 12 and 18 is:\", lcm(12, 18))\n",
"Instead, this loop intends to swap a and b while 'a' is not zero, but does not perform any operation that would actually calculate the gcd. In fact, without proper adjustments, this results in an infinite loop when 'a' is not zero.\n",
"\n",
"The correct implementation should be using Euclid's algorithm for calculating gcd which goes: while b is not zero, swap a, b = b, remainder of (a divided by b), when b becomes zero, 'a' is the gcd.\n",
"\n",
"I will replace the current gcd function in the file with this correct implementation.```\n",
"system: {'action': {'name': 'error'}, 'error_msg': 'Your response is not a JSON object, and cannot be parsed by `json.loads` in parse function:\\n## Your Response:\\n[YOUR RESPONSE BEGIN]\\n```json\\nUpon reviewing the contents of gcd.py, I can see the gcd function is incorrectly implemented. While the function starts correctly by evaluating `if a == 0: return b`, the loop structure `while a != 0: a, b = b, a` does not accurately compute the greatest common divisor (gcd). \\n\\nInstead, this loop intends to swap a and b while \\'a\\' is not zero, but does not perform any operation that would actually calculate the gcd. In fact, without proper adjustments, this results in an infinite loop when \\'a\\' is not zero.\\n\\nThe correct implementation should be using Euclid\\'s algorithm for calculating gcd which goes: while b is not zero, swap a, b = b, remainder of (a divided by b), when b becomes zero, \\'a\\' is the gcd.\\n\\nI will replace the current gcd function in the file with this correct implementation.```\\n[YOUR RESPONSE END]\\n\\n## Error Information:\\nThe content between ```json and ``` MUST be a JSON object.When parsing \"```json\\nUpon reviewing the contents of gcd.py, I can see the gcd function is incorrectly implemented. While the function starts correctly by evaluating `if a == 0: return b`, the loop structure `while a != 0: a, b = b, a` does not accurately compute the greatest common divisor (gcd). \\n\\nInstead, this loop intends to swap a and b while \\'a\\' is not zero, but does not perform any operation that would actually calculate the gcd. In fact, without proper adjustments, this results in an infinite loop when \\'a\\' is not zero.\\n\\nThe correct implementation should be using Euclid\\'s algorithm for calculating gcd which goes: while b is not zero, swap a, b = b, remainder of (a divided by b), when b becomes zero, \\'a\\' is the gcd.\\n\\nI will replace the current gcd function in the file with this correct implementation.```\", an error occurred: Expecting value: line 2 column 1 (char 1)\\n\\nAnalyze the reason, and re-correct your response in the correct format.'}\n",
"assistant: {\n",
" \"thought\": \"The gcd function implemented is incorrect and it's causing the lcm function to fail as well. In the gcd function, while loop is incorrect. We should calculate gcd based on the fact that GCD of two numbers a and b is same as the GCD of b and a mod b. 'a mod b' can be calculated using the '%' operator. When b becomes 0, a will hold the largest common divisor (GCD). Let's fix this.\",\n",
" \"thought\": \"To fix the gcd function, I need to use Euclid's algorithm. The algorithm is: while b is not zero, swap a, b = b, remainder of (a divided by b), when b becomes zero, 'a' is the gcd. I will replace the current faulty gcd function in the file with this correct implementation.\",\n",
" \"action\": {\n",
" \"name\": \"write_file\",\n",
" \"arguments\": {\n",
" \"start_line\": 2,\n",
" \"end_line\": 6,\n",
" \"content\": \" if b == 0:\\n return a\\n while b:\\n a, b = b, a % b\\n return a\",\n",
" \"content\": \"def gcd(a, b):\\n while b != 0:\\n a, b = b, a % b\\n return a\\n\\ndef lcm(a, b):\\n return (a * b) // gcd(a, b)\\n\\n# testing on GCD and LCM functions\\nprint(\\\"GCD of 12 and 18 is:\\\", gcd(12, 18))\\nprint(\\\"LCM of 12 and 18 is:\\\", lcm(12, 18))\",\n",
" \"file_path\": \"gcd.py\"\n",
" }\n",
" }\n",
"}\n",
"assistant: \n",
"====Observation====\n",
"WRITE OPERATION:\n",
"You have written to \"gcd.py\" on these lines: 2:6.\n",
"def gcd(a, b):\n",
" if b == 0:\n",
" return a\n",
" while b:\n",
"You have written to \"gcd.py\" on these lines: 0:-1.def gcd(a, b):\n",
" while b != 0:\n",
" a, b = b, a % b\n",
" return a\n",
"\n",
Expand All @@ -216,9 +190,8 @@
"print(\"GCD of 12 and 18 is:\", gcd(12, 18))\n",
"print(\"LCM of 12 and 18 is:\", lcm(12, 18))\n",
"\n",
"\n",
"assistant: {\n",
" \"thought\": \"It seems the gcd function in gcd.py has been fixed and any changes required have already been made in my previous actions. I should run the python file to determine if it produces expected results. To do that, I can use the 'execute_shell_command' by running the 'python3' command with 'gcd.py'.\",\n",
" \"thought\": \"Now I have fixed the gcd function, I now need to test if it's working as expected. I can do this by executing the Python file.\",\n",
" \"action\": {\n",
" \"name\": \"execute_shell_command\",\n",
" \"arguments\": {\n",
Expand All @@ -231,7 +204,7 @@
"GCD of 12 and 18 is: 6\n",
"LCM of 12 and 18 is: 36\n",
"assistant: {\n",
" \"thought\": \"The gcd.py file is fixed correctly and no further actions are needed.\",\n",
" \"thought\": \"The code has been corrected and tested. It is now returning the correct gcd and lcm. No further actions are required.\",\n",
" \"action\": {\n",
" \"name\": \"exit\",\n",
" \"arguments\": {}\n",
Expand Down Expand Up @@ -266,7 +239,7 @@
"```text\n",
"\n",
"assistant: {\n",
" \"thought\": \"It seems the gcd function in gcd.py has been fixed and any changes required have already been made in my previous actions. I should run the python file to determine if it produces expected results. To do that, I can use the 'execute_shell_command' by running the 'python3' command with 'gcd.py'.\",\n",
" \"thought\": \"Now I have fixed the gcd function, I now need to test if it's working as expected. I can do this by executing the Python file.\",\n",
" \"action\": {\n",
" \"name\": \"execute_shell_command\",\n",
" \"arguments\": {\n",
Expand All @@ -278,10 +251,8 @@
"====Observation====\n",
"GCD of 12 and 18 is: 6\n",
"LCM of 12 and 18 is: 36\n",
"\n",
"\n",
"assistant: {\n",
" \"thought\": \"The gcd.py file is fixed correctly and no further actions are needed.\",\n",
" \"thought\": \"The code has been corrected and tested. It is now returning the correct gcd and lcm. No further actions are required.\",\n",
" \"action\": {\n",
" \"name\": \"exit\",\n",
" \"arguments\": {}\n",
Expand All @@ -303,7 +274,7 @@
"Above we shown a example of how to use the SWE-agent to fix code errors.\n",
"Although the design of the SWE-agent is primarily aimed at addressing GitHub issues, with modifications, it can also be utilized for more general programming tasks.\n",
"\n",
"Currently, how to program using an agent remains a challenging open question, with the efficacy of agent programming potentially influenced by factors such as prompt construction, model capabilities, and the complexity of the task at hand. Here we just provide an interesting toy example. \n",
"Currently, how to enable agent with general programming ablities remains a challenging open question, with the efficacy of agent programming potentially influenced by factors such as prompt construction, model capabilities, and the complexity of the task at hand. Here we just provide an interesting toy example. \n",
"\n",
"We encourage users to experiment by altering the prompts within this example or by assigning different tasks to the agent, among other methods of exploration. Please feel free to experiment and explore on your own. The AgentScope team will continue to provide updates, enhancing the capabilities of the Programming Agents in the future!"
]
Expand Down
29 changes: 17 additions & 12 deletions examples/swe_agent/swe_agent.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -9,15 +9,19 @@

from agentscope.agents import AgentBase
from agentscope.message import Msg
from agentscope.models import ResponseParser, ResponseParsingError
from agentscope.exception import ResponseParsingError
from agentscope.parsers import MarkdownJsonDictParser
from typing import List, Callable
import json
from agentscope.service import (
ServiceFactory,
execute_shell_command,
)

from swe_agent_service_func import (
exec_py_linting,
write_file,
read_file,
exec_py_linting,
)

from swe_agent_prompts import (
Expand Down Expand Up @@ -108,6 +112,7 @@ def __init__(

self.main_goal = ""
self.commands_prompt = ""
self.parser = MarkdownJsonDictParser()
self.get_commands_prompt()

def get_current_file_content(self) -> None:
Expand Down Expand Up @@ -157,12 +162,12 @@ def step(self) -> Msg:
in_prompt = self.model.format(message_list)
res = self.model(
in_prompt,
parse_func=ResponseParser.to_dict,
parse_func=self.parser.parse,
max_retries=1,
).json
)

except ResponseParsingError as e:
response_msg = Msg(self.name, e.response.text, "assistant")
response_msg = Msg(self.name, e.raw_response, "assistant")
self.speak(response_msg)

# Re-correct by model itself
Expand All @@ -171,9 +176,9 @@ def step(self) -> Msg:
content={
"action": {"name": "error"},
"error_msg": ERROR_INFO_PROMPT.format(
parse_func=ResponseParser.to_dict,
error_info=e.error_info,
response=e.response.text,
parse_func=self.parser.parse,
error_info=e.message,
response=e.raw_response,
),
},
role="system",
Expand All @@ -183,16 +188,16 @@ def step(self) -> Msg:
self.running_memory.append(error_msg)
return error_msg

msg_res = Msg(self.name, res, role="assistant")
msg_res = Msg(self.name, res.parsed, role="assistant")

self.speak(
Msg(self.name, json.dumps(res, indent=4), role="assistant"),
Msg(self.name, json.dumps(res.parsed, indent=4), role="assistant"),
)

# parse and execute action
action = res.get("action")
action = res.parsed.get("action")

obs = self.prase_command(res["action"])
obs = self.prase_command(res.parsed["action"])
self.speak(
Msg(self.name, "\n====Observation====\n" + obs, role="assistant"),
)
Expand Down
2 changes: 1 addition & 1 deletion examples/swe_agent/swe_agent_prompts.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,7 @@ def get_step_prompt(
5. After modifying python files, you can run `exec_py_linting` to check for errors. If there are errors, fix them and repeat the previous step.
NOTE THAT THIS ENVIRONMENT DOES NOT SUPPORT INTERACTIVE SESSION COMMANDS, such as "vim" or "python", or "python3". So DONOT execute them by running `execute_shell_command` with `python` command or `python3` command.
NOTE THAT THIS ENVIRONMENT DOES NOT SUPPORT INTERACTIVE SESSION COMMANDS, such as "vim" or "python", or "python3". So DONOT execute them by running `execute_shell_command` with `python` command or `python3` command if the code need additional inputs.
If you want to check whether a python file is valid, you can use `exec_py_linting` to check for errors.
{RESPONSE_FORMAT_PROMPT}
Expand Down
Loading

0 comments on commit 903d49d

Please sign in to comment.