fix: rename python tool to ipython for better tooluse format adherence

[ErikBjare]

Attempt at improving #327

No idea if it actually performs better.

---

Important

Renames the 'python' tool to 'ipython' for better tool use format adherence, updating initialization and tests accordingly.

• Behavior:
  • Renames tool from python to ipython in gptme/tools/__init__.py and gptme/tools/python.py.
  • Updates tool initialization logic in init_tools() to sort by ipython.
• Tests:
  • Updates test_tools_info() in test_util_cli.py to check for ipython instead of python.

^{This description was created by for 113fa58. It will automatically update as commits are pushed.}

[ellipsis-dev]

👍 Looks good to me! Reviewed everything up to 955afab in 13 seconds

More details

• Looked at 44 lines of code in 3 files
• Skipped 0 files when reviewing.
• Skipped posting 1 drafted comments based on config settings.

1. gptme/tools/__init__.py:79

• Draft comment:
  The import statement should be updated to reflect the tool name change from 'python' to 'ipython'.
• Reason this comment was not posted:
  Comment was not on a valid diff hunk.

Workflow ID: wflow_s6YCea8pKD6G18RS

---

You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.

[codecov-commenter]

❌ 1 Tests Failed:

Tests completed	Failed	Passed	Skipped
148	1	147	3

View the top 1 failed tests by shortest run time

tests.test_cli::test_subagent

Stack Traces | 0.021s run time

args = ['--name', 'test-3593-test_subagent', '--tools', 'python,subagent', 'We are in a test. Use the subagent tool to compute `fib(15)`, where `fib(1) = 1` and `fib(2) = 1`.', '-', ...]
runner = <click.testing.CliRunner object at 0x7fc23b179ed0>

    @pytest.mark.slow
    @pytest.mark.flaky(retries=2, delay=5)
    @pytest.mark.skipif(
        os.environ.get("MODEL") == "openai/gpt-4o-mini", reason="unreliable for gpt-4o-mini"
    )
    def test_subagent(args: list[str], runner: CliRunner):
        # f14: 377
        # f15: 610
        # f16: 987
        args.extend(["--tools", "python,subagent"])
        args.extend(
            [
                "We are in a test. Use the subagent tool to compute `fib(15)`, where `fib(1) = 1` and `fib(2) = 1`.",
                "-",
                "Answer with the value.",
            ]
        )
        print(f"running: gptme {' '.join(args)}")
        result = runner.invoke(gptme.cli.main, args)
        print(result.output)
    
        # apparently this is not obviously 610
        accepteds = ["377", "610"]
>       assert any(
            [accepted in result.output for accepted in accepteds]
        ), f"Accepteds '{accepteds}' not in output: {result.output}"
E       AssertionError: Accepteds '['377', '610']' not in output: 
E       assert False
E        +  where False = any([False, False])

.../gptme/tests/test_cli.py:343: AssertionError

To view more test analytics, go to the Test Analytics Dashboard
📢 Thoughts on this report? Let us know!

[ellipsis-dev]

👍 Looks good to me! Incremental review on 113fa58 in 19 seconds

More details

• Looked at 52 lines of code in 3 files
• Skipped 0 files when reviewing.
• Skipped posting 0 drafted comments based on config settings.

Workflow ID: wflow_v7TPTFwBBZoHjjRW

---

You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.