Example for SWE agent

examples/swe_agent/main.ipynb

@@ -0,0 +1,333 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "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",
+    "\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",
+    "\n",
+    "## Prerequisites\n",
+    "\n",
+    "- Follow [READMD.md](https://github.com/modelscope/agentscope) to install AgentScope. \n",
+    "- Prepare a model configuration. AgentScope supports both local deployed model services (CPU or GPU) and third-party services. More details and example model configurations please refer to our [tutorial]\n",
+    "- Understand the ServiceFactory module and how to use it to pre-process the tool functions for LLMs. You can refer to the [ReAct agent example](../conversation_with_react_agent/main.ipynb).\n",
+    "\n",
+    "## Note\n",
+    "\n",
+    "- The example is tested with the following models. For other models, you may need to adjust the prompt.\n",
+    "    - gpt-4\n",
+    "- How to enable agents with stronger programming capabilities remains an open challenge, and the current implementations are not perfect. Please feel free to explore it yourself."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Step 1: Initialize the AgentScope environment and SWE-agent\n",
+    "\n",
+    "Here we init the agentscope environment and load the SWE-agent.\n",
+    "\n",
+    "The code of SWE-agent is in `swe_agent.py`, and the related prompts are in `swe_agent_prompts.py`.\n",
+    "\n",
+    "If you are interested in the details, please refer to the code and the origianl SWE-agent repo [here](https://github.com/princeton-nlp/SWE-agent)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from swe_agent import SWEAgent\n",
+    "\n",
+    "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",
+    ")\n",
+    "loaded_model = load_model_by_config_name('gpt-4')\n",
+    "\n",
+    "agent = SWEAgent(\n",
+    "    name=\"assistant\",\n",
+    "    model_config_name='gpt-4',\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Step 2: Create the code to be processed by the SWE-agent\n",
+    "\n",
+    "Here we use the `write_file` function to write the following code into `gcd.py`.\n",
+    "The code here is a wrong implementation of the Greatest Common Divisor (GCD) algorithm.\n",
+    "We will ask the SWE-agent to correct it in our next step."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'status': <ServiceExecStatus.SUCCESS: 1>,\n",
+       " 'content': 'WRITE OPERATION:\\nYou have written to \"gcd.py\"                 on these lines: 0:-1.\\ndef gcd(a, b):\\n    if a == 0:\\n        return b\\n    while a != 0:\\n        a, b = b, a\\n    return b\\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\\n'}"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from agentscope.service import write_file\n",
+    "\n",
+    "# here the gcd code is written in a wrong way\n",
+    "wrong_gcd_text = \"\"\"\n",
+    "def gcd(a, b):\n",
+    "    if a == 0:\n",
+    "        return b\n",
+    "    while a != 0:\n",
+    "        a, b = b, a\n",
+    "    return b\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",
+    "\"\"\"\n",
+    "\n",
+    "write_file(\"gcd.py\", wrong_gcd_text)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Step 3: Ask the SWE-agent to correct the code\n",
+    "\n",
+    "Here we simple ask the SWE-agent to correct the code in `gcd.py`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "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",
+      "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",
+      "    \"action\": {\n",
+      "        \"name\": \"read_file\",\n",
+      "        \"arguments\": {\n",
+      "            \"file_path\": \"gcd.py\"\n",
+      "        }\n",
+      "    }\n",
+      "}\n",
+      "assistant: \n",
+      "====Observation====\n",
+      "\n",
+      "def gcd(a, b):\n",
+      "    if a == 0:\n",
+      "        return b\n",
+      "    while a != 0:\n",
+      "        a, b = b, a\n",
+      "    return b\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",
+      "\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",
+      "\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",
+      "\n",
+      "\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",
+      "    \"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",
+      "            \"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",
+      "        a, b = b, a % b\n",
+      "    return a\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",
+      "\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",
+      "    \"action\": {\n",
+      "        \"name\": \"execute_shell_command\",\n",
+      "        \"arguments\": {\n",
+      "            \"command\": \"python3 gcd.py\"\n",
+      "        }\n",
+      "    }\n",
+      "}\n",
+      "assistant: \n",
+      "====Observation====\n",
+      "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",
+      "    \"action\": {\n",
+      "        \"name\": \"exit\",\n",
+      "        \"arguments\": {}\n",
+      "    }\n",
+      "}\n",
+      "assistant: \n",
+      "====Observation====\n",
+      "Current task finished, exitting.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from loguru import logger\n",
+    "from agentscope.message import Msg\n",
+    "\n",
+    "mss = Msg(\n",
+    "    name=\"user\", \n",
+    "    content=\"The file in gcd.py is not returning the correct answer, can you fix the file for me?\", \n",
+    "    role=\"user\"\n",
+    ")\n",
+    "logger.chat(mss)\n",
+    "answer_mss = agent(mss)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Conlusion\n",
+    "\n",
+    "After a few iterations, the assistant response:\n",
+    "```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",
+    "    \"action\": {\n",
+    "        \"name\": \"execute_shell_command\",\n",
+    "        \"arguments\": {\n",
+    "            \"command\": \"python3 gcd.py\"\n",
+    "        }\n",
+    "    }\n",
+    "}\n",
+    "assistant: \n",
+    "====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",
+    "    \"action\": {\n",
+    "        \"name\": \"exit\",\n",
+    "        \"arguments\": {}\n",
+    "    }\n",
+    "}\n",
+    "assistant: \n",
+    "====Observation====\n",
+    "Current task finished, exitting.\n",
+    "\n",
+    "```\n",
+    "\n",
+    "The SWE-agent finish the job successfully, and the code is now working fine."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "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",
+    "\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!"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "datajuicer",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}