Fix Poetry environments misidentified as Venv

[Copilot]

Poetry environments in cache directories were reported as kind = 'Venv' instead of 'Poetry' when workspace directories weren't configured or pyproject.toml wasn't in the workspace.

Example:

Path: /Users/user/Library/Caches/pypoetry/virtualenvs/nestedpoetry-yJwtIF_Q-py3.11/
Before: kind = 'Venv'
After:  kind = 'Poetry'

Changes

Root cause: Poetry::try_from() only checked cached environments from find(). Uncached environments returned None, falling through to Venv locator.

Solution: Added fallback path-based detection when cache lookup fails:

fn is_poetry_environment(path: &Path) -> bool {
    // Check path contains "pypoetry/virtualenvs"
    // Validate directory name matches: {name}-{8-char-hash}-py{version}
    // Regex: ^.+-[A-Za-z0-9_-]{8}-py.*$
}

Updated try_from() to check path pattern after cache miss, creating Poetry environment if pattern matches. Works across platforms (macOS, Linux, Windows) without filesystem I/O.

Testing

Added 8 unit tests covering:

• Platform-specific paths (macOS/Linux/Windows cache directories)
• Pattern variations (with/without version suffix)
• Negative cases (non-Poetry paths, wrong hash length)
• Real-world examples from bug report

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Bug: Poetry path returned as type "venv"</issue_title>
<issue_description>you can see from the path it is in the poetry folder but the type comes back as venv instead

</issue_description>

<agent_instructions>The issue is that poetry envs sometimes get reported as venvs.
Analyse and perform root causes analysis before attempting to fix this issue.
Once you have determine the root cause use that information to create tests and then try to fix the issue and verify whether the tests pass.
</agent_instructions>

Comments on the Issue (you are @copilot in this section)

• Fixes Bug: Poetry path returned as type "venv" #267

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.