turnstone/tests.json

{
  "description": "turnstone behavior tests \u2014 tool selection, sequencing, and multi-step reasoning",
  "defaults": {
    "n_runs": 5,
    "max_turns": 15
  },
  "cases": [
    {
      "id": "read-before-edit",
      "description": "Must read_file before edit_file on the same path",
      "user_prompt": "Fix the typo in config.py \u2014 change 'recieve' to 'receive'",
      "setup": {
        "files": {
          "config.py": "# Config module\ndef recieve_data(source):\n    \"\"\"Recieve data from source.\"\"\"\n    return source.read()\n"
        }
      },
      "expected_actions": [
        {
          "tool": "read_file",
          "args": {
            "path": "config.py"
          }
        },
        {
          "tool": "edit_file",
          "args": {
            "path": "config.py"
          }
        }
      ],
      "match_mode": "ordered_subset",
      "user_prompts": [
        "Fix the typo in config.py \u2014 change 'recieve' to 'receive'",
        "In config.py, correct the misspelling of 'recieve' to 'receive'",
        "Please update config.py by replacing 'recieve' with the correct spelling 'receive'",
        "There's a typo in config.py: 'recieve' should be 'receive'. Please fix it.",
        "Could you change 'recieve' to 'receive' in config.py?",
        "Go ahead and fix 'recieve' \u2192 'receive' in config.py",
        "I need the word 'recieve' corrected to 'receive' in the file config.py",
        "config.py has a spelling error \u2014 'recieve' needs to be changed to 'receive'",
        "Kindly rectify the typographical error in config.py, replacing 'recieve' with 'receive'",
        "Hey, swap 'recieve' for 'receive' in config.py"
      ]
    },
    {
      "id": "write-file-not-bash",
      "description": "Use write_file for file creation, not bash echo/cat",
      "user_prompt": "Create a file called hello.py that prints hello world",
      "expected_actions": [
        {
          "tool": "write_file",
          "args_pattern": {
            "path": "hello\\.py"
          }
        }
      ],
      "match_mode": "subset",
      "user_prompts": [
        "Create a file called hello.py that prints hello world",
        "Make a hello.py file that outputs hello world",
        "Please write a Python file named hello.py which prints hello world",
        "I need a file called hello.py that prints hello world",
        "Could you create hello.py with code that prints hello world?",
        "Write hello.py \u2014 it should print hello world",
        "Generate a hello.py file that outputs \"hello world\"",
        "I'd like you to create a file named hello.py that prints hello world",
        "Set up a file called hello.py to print hello world",
        "Kindly produce a hello.py file whose purpose is to print hello world"
      ]
    },
    {
      "id": "bash-for-commands",
      "description": "Use bash for running system commands",
      "user_prompt": "What Python version is installed?",
      "expected_actions": [
        {
          "tool": "bash",
          "args_pattern": {
            "command": "python"
          }
        }
      ],
      "match_mode": "subset",
      "user_prompts": [
        "What Python version is installed?",
        "Check which version of Python is currently installed",
        "Can you tell me the installed Python version?",
        "python --version please",
        "I need to know what version of Python is on this system",
        "Which Python version do we have?",
        "Could you look up the Python version that's installed here?",
        "Determine the currently installed Python version",
        "What's the Python version on this machine?",
        "Please check the Python version"
      ]
    },
    {
      "id": "search-for-patterns",
      "description": "Use search tool for finding code patterns across files",
      "user_prompt": "Find all functions that start with 'test_' in the project",
      "setup": {
        "files": {
          "tests.py": "def test_one():\n    assert True\n\ndef test_two():\n    assert 1 + 1 == 2\n",
          "main.py": "def main():\n    print('hello')\n"
        }
      },
      "expected_actions": [
        {
          "tool": "search",
          "args_pattern": {
            "query": "test_"
          }
        }
      ],
      "match_mode": "subset",
      "user_prompts": [
        "Find all functions that start with 'test_' in the project",
        "List every function in the project whose name begins with 'test_'",
        "I need to locate all functions prefixed with 'test_' across the project",
        "Could you search the project for any functions starting with 'test_'?",
        "Show me all the test_ prefixed functions in this project",
        "Hunt down every function that has a 'test_' prefix in the codebase",
        "I'm looking for all functions named test_* throughout the project",
        "Search the entire project for functions whose names start with test_",
        "What functions beginning with 'test_' exist in this project?",
        "Please identify all functions with the 'test_' prefix in the project files"
      ]
    },
    {
      "id": "multi-file-edit",
      "description": "Read and edit multiple files \u2014 must read before editing each, and edit both",
      "user_prompt": "Change the default port from 8000 to 9000 in both server.py and config.py",
      "setup": {
        "files": {
          "server.py": "import socket\n\ndef run():\n    sock = socket.socket()\n    sock.bind(('localhost', 8000))\n    print('Server running on port 8000')\n",
          "config.py": "PORT = 8000\nHOST = 'localhost'\n"
        }
      },
      "expected_actions": [
        {
          "tool": "read_file"
        },
        {
          "tool": "read_file"
        },
        {
          "tool": "edit_file"
        },
        {
          "tool": "edit_file"
        }
      ],
      "match_mode": "ordered_subset",
      "user_prompts": [
        "Change the default port from 8000 to 9000 in both server.py and config.py",
        "Update the default port to 9000 instead of 8000 in server.py and config.py",
        "Could you modify the port number from 8000 to 9000 in both config.py and server.py?",
        "Please replace port 8000 with 9000 in server.py and config.py",
        "I need the default port switched from 8000 to 9000 in both server.py and config.py",
        "In server.py and config.py, the default port should be changed from 8000 to 9000",
        "Swap out port 8000 for 9000 in config.py and server.py",
        "Would you mind updating the default port value from 8000 to 9000 across both server.py and config.py?",
        "The default port in server.py and config.py needs to be 9000 instead of 8000 \u2014 please make that change",
        "Go ahead and change 8000 to 9000 for the default port in both server.py and config.py"
      ]
    },
    {
      "id": "search-then-edit",
      "description": "Search to find where something is defined, then read and edit",
      "user_prompt": "Find where MAX_RETRIES is defined and change it from 3 to 5",
      "setup": {
        "files": {
          "app.py": "import os\n\ndef start():\n    pass\n",
          "utils.py": "import time\n\ndef helper():\n    pass\n",
          "config/settings.py": "# Settings\nDEBUG = True\nMAX_RETRIES = 3\nTIMEOUT = 30\n"
        }
      },
      "expected_actions": [
        {
          "tool": "search",
          "args_pattern": {
            "query": "MAX_RETRIES"
          }
        },
        {
          "tool": "read_file"
        },
        {
          "tool": "edit_file",
          "args_pattern": {
            "old_string": "3"
          }
        }
      ],
      "match_mode": "ordered_subset",
      "user_prompts": [
        "Find where MAX_RETRIES is defined and change it from 3 to 5",
        "Locate the definition of MAX_RETRIES and update its value from 3 to 5",
        "Could you search for where MAX_RETRIES is defined and modify it from 3 to 5?",
        "I need MAX_RETRIES changed from 3 to 5 \u2014 find where it's defined and update it",
        "Please find the MAX_RETRIES definition and bump it from 3 to 5",
        "Hunt down MAX_RETRIES in the codebase and change its value from 3 to 5",
        "Where is MAX_RETRIES set to 3? Change it to 5.",
        "Search the code for the MAX_RETRIES definition and alter it from 3 to 5",
        "I'd like you to locate MAX_RETRIES (currently 3) and set it to 5 instead",
        "Go find MAX_RETRIES and switch it from 3 to 5"
      ]
    },
    {
      "id": "bash-git-log",
      "description": "Use bash for git commands, not other tools",
      "user_prompt": "Show me the git log for the last 5 commits",
      "expected_actions": [
        {
          "tool": "bash",
          "args_pattern": {
            "command": "git\\s+log"
          }
        }
      ],
      "match_mode": "subset",
      "user_prompts": [
        "Show me the git log for the last 5 commits",
        "Display the 5 most recent git commits",
        "Can you pull up the git log limited to the last five commits?",
        "I need to see the git log showing only the previous 5 commits",
        "git log for the 5 latest commits, please",
        "Would you mind showing me the last five entries in the git log?",
        "Print out the most recent 5 commits from the git log",
        "I'd like to review the git log \u2014 just the last 5 commits",
        "Show the recent 5 commit history using git log",
        "Could you display the git commit history for the past five commits?"
      ]
    },
    {
      "id": "write-then-run",
      "description": "Create a script and run it to verify it works",
      "user_prompt": "Create a Python script called fib.py that prints the first 10 Fibonacci numbers, then run it to verify",
      "expected_actions": [
        {
          "tool": "write_file",
          "args_pattern": {
            "path": "fib\\.py"
          }
        },
        {
          "tool": "bash",
          "args_pattern": {
            "command": "python"
          }
        }
      ],
      "match_mode": "ordered_subset",
      "user_prompts": [
        "Create a Python script called fib.py that prints the first 10 Fibonacci numbers, then run it to verify",
        "Write a Python file named fib.py that outputs the first 10 Fibonacci numbers, and execute it to confirm it works",
        "Please make fib.py \u2013 a Python script printing the first ten Fibonacci numbers \u2013 then run it to check the output",
        "I need a Python script fib.py that prints the first 10 Fibonacci numbers. Execute it afterwards to verify correctness.",
        "Could you create fib.py to display the first 10 Fibonacci numbers in Python, and then run it to make sure it works?",
        "Draft a script called fib.py in Python that outputs the first ten Fibonacci numbers, then execute it to validate",
        "Hey, write me a fib.py that prints the first 10 Fibonacci numbers and run it so we can see it works",
        "Generate a Python program fib.py which prints the initial 10 Fibonacci numbers, and verify by running it",
        "Kindly produce a Python script named fib.py to print the first 10 Fibonacci numbers, then execute the script to confirm its output",
        "Make a file fib.py containing Python code to print the first 10 Fibonacci numbers. Then run it to verify."
      ]
    },
    {
      "id": "no-bash-for-file-write",
      "description": "Should NOT use bash (echo/cat/heredoc) to create files \u2014 only write_file",
      "user_prompt": "Create a new file called README.md with a title and description of this project",
      "expected_actions": [
        {
          "tool": "write_file",
          "args_pattern": {
            "path": "README"
          }
        }
      ],
      "match_mode": "subset",
      "user_prompts": [
        "Create a new file called README.md with a title and description of this project",
        "Make a README.md file that includes a project title and description",
        "I need a README.md created with a title and a brief description of the project",
        "Please generate a README.md file containing the project's title and description",
        "Could you set up a README.md with a title and project description?",
        "Write a README.md that has a title and describes this project",
        "Go ahead and create README.md \u2014 it should have a title and a description of the project",
        "I'd like you to produce a new README.md file featuring a project title and description",
        "Kindly establish a README.md file incorporating both a title and a description for this project",
        "Spin up a README.md with a project title and description in it"
      ]
    },
    {
      "id": "edit-not-rewrite",
      "description": "Use edit_file for small changes, not write_file to rewrite the entire file",
      "user_prompt": "Add a docstring to the process_data function in utils.py",
      "setup": {
        "files": {
          "utils.py": "import os\nimport sys\n\n\ndef helper():\n    \"\"\"A helper function.\"\"\"\n    return 42\n\n\ndef process_data(items):\n    results = []\n    for item in items:\n        if item > 0:\n            results.append(item * 2)\n    return results\n\n\ndef cleanup():\n    \"\"\"Clean up resources.\"\"\"\n    pass\n"
        }
      },
      "expected_actions": [
        {
          "tool": "read_file",
          "args": {
            "path": "utils.py"
          }
        },
        {
          "tool": "edit_file",
          "args": {
            "path": "utils.py"
          }
        }
      ],
      "match_mode": "ordered_subset",
      "user_prompts": [
        "Add a docstring to the process_data function in utils.py",
        "Please add a docstring to the process_data function in utils.py",
        "Could you write a docstring for process_data in utils.py?",
        "Insert a docstring into the process_data function found in utils.py",
        "I need a docstring added to process_data in utils.py",
        "Put a docstring on the process_data function in utils.py",
        "The process_data function in utils.py is missing a docstring \u2014 please add one",
        "Would you mind adding a docstring to process_data in utils.py?",
        "In utils.py, the process_data function needs a docstring",
        "Add documentation via a docstring to the process_data function within utils.py"
      ]
    },
    {
      "id": "bash-run-tests",
      "description": "Use bash to run a test suite",
      "user_prompt": "Run the tests",
      "setup": {
        "files": {
          "test_math.py": "def test_add():\n    assert 1 + 1 == 2\n\ndef test_mul():\n    assert 2 * 3 == 6\n"
        }
      },
      "expected_actions": [
        {
          "tool": "bash",
          "args_pattern": {
            "command": "pytest|python.*test"
          }
        }
      ],
      "match_mode": "subset",
      "user_prompts": [
        "Run the tests",
        "Execute the test suite",
        "Please go ahead and run the tests",
        "Could you run the tests for me?",
        "I need the tests to be run",
        "Kick off the tests",
        "Let's run the tests",
        "Fire up the tests",
        "Go ahead and execute the tests",
        "I'd like you to run the tests"
      ]
    },
    {
      "id": "web-fetch-url",
      "description": "Use web_fetch when asked to retrieve content from a URL",
      "user_prompt": "Fetch the contents of https://example.com and summarize what's on the page",
      "expected_actions": [
        {
          "tool": "web_fetch",
          "args_pattern": {
            "url": "example\\.com"
          }
        }
      ],
      "match_mode": "subset",
      "user_prompts": [
        "Fetch the contents of https://example.com and summarize what's on the page",
        "Go to https://example.com and give me a summary of what you find there",
        "Could you pull up https://example.com and tell me what the page is about?",
        "Retrieve the content from https://example.com, then provide a summary of it",
        "I need you to grab https://example.com and summarize its contents for me",
        "Please access https://example.com and give me an overview of the page",
        "What's on https://example.com? Fetch it and summarize for me.",
        "Download the page at https://example.com and provide a brief summary",
        "I'd like a summary of whatever is at https://example.com \u2014 please fetch it first",
        "Hit https://example.com and let me know what's there in summary form"
      ]
    },
    {
      "id": "web-search-query",
      "description": "Use web_search for general knowledge lookups, not web_fetch",
      "user_prompt": "Search the web for the current population of Tokyo",
      "expected_actions": [
        {
          "tool": "web_search",
          "args_pattern": {
            "query": "Tokyo"
          }
        }
      ],
      "match_mode": "subset",
      "user_prompts": [
        "Search the web for the current population of Tokyo",
        "What's Tokyo's current population? Look it up on the web.",
        "Could you do a web search to find out how many people currently live in Tokyo?",
        "Please search online for Tokyo's present-day population.",
        "I need you to look up the current population of Tokyo on the web.",
        "Find me Tokyo's current population via a web search.",
        "Web search: what is the current population of Tokyo?",
        "I'd like to know Tokyo's current population\u2014can you search the web for that?",
        "Look up how many people live in Tokyo right now using a web search.",
        "Do a web search for the population of Tokyo as of now."
      ]
    }
  ]
}