diff --git a/tests/data/rsp_cache.json b/tests/data/rsp_cache.json index e5f03d9cb..e81a9d073 100644 --- a/tests/data/rsp_cache.json +++ b/tests/data/rsp_cache.json @@ -434,5 +434,8 @@ }, "[{\"role\": \"system\", \"content\": \"You are Code Interpreter, a world-class programmer that can complete any goal by executing code. Strictly follow the plan and generate code step by step. Each step of the code will be executed on the user's machine, and the user will provide the code execution results to you.**Notice: The code for the next step depends on the code for the previous step. Must reuse variables in the lastest other code directly, dont creat it again, it is very import for you. Use !pip install in a standalone block to install missing packages.Usually the libraries you need are already installed.Dont check if packages already imported.**\"}, {\"role\": \"user\", \"content\": \"\\n## User Requirement\\nRun data analysis on sklearn Iris dataset, include a plot\\n## Context\\n\\n## Current Plan\\n[\\n {\\n \\\"task_id\\\": \\\"1\\\",\\n \\\"dependent_task_ids\\\": [],\\n \\\"instruction\\\": \\\"Load the sklearn Iris dataset.\\\",\\n \\\"task_type\\\": \\\"other\\\",\\n \\\"code\\\": \\\"from sklearn.datasets import load_iris\\\\niris_data = load_iris()\\\",\\n \\\"result\\\": \\\"a successful run\\\",\\n \\\"is_success\\\": true,\\n \\\"is_finished\\\": true\\n },\\n {\\n \\\"task_id\\\": \\\"2\\\",\\n \\\"dependent_task_ids\\\": [\\n \\\"1\\\"\\n ],\\n \\\"instruction\\\": \\\"Perform exploratory data analysis on the Iris dataset.\\\",\\n \\\"task_type\\\": \\\"eda\\\",\\n \\\"code\\\": \\\"import pandas as pd\\\\n\\\\n# Convert the loaded Iris dataset to a DataFrame for easier manipulation\\\\niris_df = pd.DataFrame(data=iris_data.data, columns=iris_data.feature_names)\\\\niris_df['target'] = iris_data.target\\\\n\\\\n# Display basic information about the dataset\\\\niris_df_info = iris_df.info()\\\\n\\\\n# Display statistical summary of the dataset\\\\niris_df_description = iris_df.describe()\\\\n\\\\n# Show the first few rows of the dataset\\\\ndf_head = iris_df.head()\\\\n\\\\n# Output the results\\\\ndisplay(iris_df_info, iris_df_description, df_head)\\\",\\n \\\"result\\\": \\\"a successful run\\\",\\n \\\"is_success\\\": true,\\n \\\"is_finished\\\": true\\n },\\n {\\n \\\"task_id\\\": \\\"3\\\",\\n \\\"dependent_task_ids\\\": [\\n \\\"2\\\"\\n ],\\n \\\"instruction\\\": \\\"Create a plot visualizing the Iris dataset features.\\\",\\n \\\"task_type\\\": \\\"other\\\",\\n \\\"code\\\": \\\"\\\",\\n \\\"result\\\": \\\"\\\",\\n \\\"is_success\\\": false,\\n \\\"is_finished\\\": false\\n }\\n]\\n## Current Task\\n{\\\"task_id\\\":\\\"3\\\",\\\"dependent_task_ids\\\":[\\\"2\\\"],\\\"instruction\\\":\\\"Create a plot visualizing the Iris dataset features.\\\",\\\"task_type\\\":\\\"other\\\",\\\"code_steps\\\":\\\"\\\",\\\"code\\\":\\\"\\\",\\\"result\\\":\\\"\\\",\\\"is_success\\\":false,\\\"is_finished\\\":false}\\n\"}, {\"role\": \"user\", \"content\": \"\\n# Instruction\\nWrite complete code for 'Current Task'. And avoid duplicating code from finished tasks, such as repeated import of packages, reading data, etc.\\nSpecifically, \\n\\n# Capabilities\\n- You can utilize pre-defined tools in any code lines from 'Available Tools' in the form of Python Class.\\n- You can freely combine the use of any other public packages, like sklearn, numpy, pandas, etc..\\n\\n# Available Tools (can be empty):\\nEach Class tool is described in JSON format. When you call a tool, import the tool first.\\n{}\\n\\n# Constraints:\\n- Ensure the output new code is executable in the same Jupyter notebook with previous tasks code have been executed.\\n- Always prioritize using pre-defined tools for the same functionality.\\n\"}]": { "code": "import seaborn as sns\nimport matplotlib.pyplot as plt\n\n# Pairplot to visualize the relationships between features\nsns.pairplot(iris_df, hue='target', diag_kind='kde')\n\n# Show the plot\nplt.show()" - } + }, + "\nRole: You are a senior development and qa engineer, your role is summarize the code running result.\nIf the running result does not include an error, you should explicitly approve the result.\nOn the other hand, if the running result indicates some error, you should point out which part, the development code or the test code, produces the error,\nand give specific instructions on fixing the errors. Here is the code info:\n\n## Development Code File Name\na.txt\n## Development Code\n```python\nresult = 'helloworld'\n```\n## Test File Name\n\n## Test Code\n```python\nNone\n```\n## Running Command\n\n## Running Output\nstandard output: \n```text\nhelloworld\n```\nstandard errors: \n```text\n\n```\n\nNow you should begin your analysis\n---\n## instruction:\nPlease summarize the cause of the errors and give correction instruction\n## File To Rewrite:\nDetermine the ONE file to rewrite in order to fix the error, for example, xyz.py, or test_xyz.py\n## Status:\nDetermine if all of the code works fine, if so write PASS, else FAIL,\nWRITE ONLY ONE WORD, PASS OR FAIL, IN THIS SECTION\n## Send To:\nPlease write NoOne if there are no errors, Engineer if the errors are due to problematic development codes, else QaEngineer,\nWRITE ONLY ONE WORD, NoOne OR Engineer OR QaEngineer, IN THIS SECTION.\n---\nYou should fill in necessary instruction, status, send to, and finally return all content between the --- segment line.\n": "---\n## instruction:\nNo errors detected. The development code runs successfully and outputs the expected result without any errors.\n## File To Rewrite:\nNone\n## Status:\nPASS\n## Send To:\nNoOne\n---", + "\nRole: You are a senior development and qa engineer, your role is summarize the code running result.\nIf the running result does not include an error, you should explicitly approve the result.\nOn the other hand, if the running result indicates some error, you should point out which part, the development code or the test code, produces the error,\nand give specific instructions on fixing the errors. Here is the code info:\n\n## Development Code File Name\na.sh\n## Development Code\n```python\necho 'Hello World'\n```\n## Test File Name\n\n## Test Code\n```python\nNone\n```\n## Running Command\necho Hello World\n## Running Output\nstandard output: \n```text\nHello World\n\n```\nstandard errors: \n```text\n\n```\n\nNow you should begin your analysis\n---\n## instruction:\nPlease summarize the cause of the errors and give correction instruction\n## File To Rewrite:\nDetermine the ONE file to rewrite in order to fix the error, for example, xyz.py, or test_xyz.py\n## Status:\nDetermine if all of the code works fine, if so write PASS, else FAIL,\nWRITE ONLY ONE WORD, PASS OR FAIL, IN THIS SECTION\n## Send To:\nPlease write NoOne if there are no errors, Engineer if the errors are due to problematic development codes, else QaEngineer,\nWRITE ONLY ONE WORD, NoOne OR Engineer OR QaEngineer, IN THIS SECTION.\n---\nYou should fill in necessary instruction, status, send to, and finally return all content between the --- segment line.\n": "---\n## instruction:\nNo errors detected in the running result. The development code executed successfully, and the output matches the expected result. Since there is no test code provided, no test execution was performed. Therefore, no specific instructions are needed for correction.\n## File To Rewrite:\nNone\n## Status:\nPASS\n## Send To:\nNoOne\n---", + "\nRole: You are a senior development and qa engineer, your role is summarize the code running result.\nIf the running result does not include an error, you should explicitly approve the result.\nOn the other hand, if the running result indicates some error, you should point out which part, the development code or the test code, produces the error,\nand give specific instructions on fixing the errors. Here is the code info:\n\n## Development Code File Name\na.py\n## Development Code\n```python\npython -c \"print(1/0)\"\n```\n## Test File Name\n\n## Test Code\n```python\nNone\n```\n## Running Command\npython -c print(1/0)\n## Running Output\nstandard output: \n```text\n\n```\nstandard errors: \n```text\nTraceback (most recent call last):\n File \"\", line 1, in \nZeroDivisionError: division by zero\n\n```\n\nNow you should begin your analysis\n---\n## instruction:\nPlease summarize the cause of the errors and give correction instruction\n## File To Rewrite:\nDetermine the ONE file to rewrite in order to fix the error, for example, xyz.py, or test_xyz.py\n## Status:\nDetermine if all of the code works fine, if so write PASS, else FAIL,\nWRITE ONLY ONE WORD, PASS OR FAIL, IN THIS SECTION\n## Send To:\nPlease write NoOne if there are no errors, Engineer if the errors are due to problematic development codes, else QaEngineer,\nWRITE ONLY ONE WORD, NoOne OR Engineer OR QaEngineer, IN THIS SECTION.\n---\nYou should fill in necessary instruction, status, send to, and finally return all content between the --- segment line.\n": "---\n## instruction:\nThe error is caused by attempting to divide by zero in the development code. To fix this error, you should modify the division operation to avoid division by zero. For example, you can add a condition to check if the denominator is zero before performing the division.\n\n## File To Rewrite:\na.py\n\n## Status:\nFAIL\n\n## Send To:\nEngineer\n---" } \ No newline at end of file diff --git a/tests/metagpt/actions/test_run_code.py b/tests/metagpt/actions/test_run_code.py index afd308da7..2ec8a7748 100644 --- a/tests/metagpt/actions/test_run_code.py +++ b/tests/metagpt/actions/test_run_code.py @@ -38,7 +38,7 @@ async def test_run_script(context): @pytest.mark.asyncio async def test_run(context): inputs = [ - (RunCodeContext(mode="text", code_filename="a.txt", code="print('Hello, World')"), "PASS"), + (RunCodeContext(mode="text", code_filename="a.txt", code="result = 'helloworld'"), "PASS"), ( RunCodeContext( mode="script",