Switch init pyproject to dulwich

[Secrus]

Pull Request Check List

• [ ] Added tests for changed code.
• [ ] Updated documentation for changed code.

Switched init command creating pyproject.toml config to using dulwich instead of subprocess-based solution from poetry-core.

[sourcery-ai]

Hey - I've found 2 issues, and left some high level feedback:

• Casting dulwich config values with str(...) will produce representations like "b'foo'" rather than decoding the underlying bytes; consider decoding with an explicit encoding (e.g. value.decode('utf-8')) before using them in the author string.
• author_email = str(get_vcs_config_value("user", "email")) will turn None into the string 'None', which then passes the if author_email: check and produces " <None>"; guard against None before converting to string or building the author string.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- Casting dulwich config values with `str(...)` will produce representations like `"b'foo'"` rather than decoding the underlying bytes; consider decoding with an explicit encoding (e.g. `value.decode('utf-8')`) before using them in the author string.
- `author_email = str(get_vcs_config_value("user", "email"))` will turn `None` into the string `'None'`, which then passes the `if author_email:` check and produces `" <None>"`; guard against `None` before converting to string or building the author string.

## Individual Comments

### Comment 1
<location path="src/poetry/console/commands/init.py" line_range="149-151" />
<code_context>
         if not description and is_interactive:
             description = self.ask(self.create_question("Description []: ", default=""))

+        vcs_config = StackedConfig.default()
+
+        def get_vcs_config_value(*keys: str) -> bytes | None:
+            try:
+                value = vcs_config.get(*keys)
</code_context>
<issue_to_address>
**suggestion (bug_risk):** Decode dulwich config values to text instead of returning raw bytes

`StackedConfig.get` returns `bytes`, and the helper currently passes those through, leaving callers to do `str(...)` and ending up with values like `"b'John Doe'"`. Consider decoding here (e.g., UTF-8) and returning `str | None` so downstream code consistently works with text rather than raw bytes.
</issue_to_address>

### Comment 2
<location path="src/poetry/console/commands/init.py" line_range="159-161" />
<code_context>
-        if not author and vcs_config.get("user.name"):
-            author = vcs_config["user.name"]
-            author_email = vcs_config.get("user.email")
+        if not author and (vcs_username := get_vcs_config_value("user", "name")):
+            author = str(vcs_username)
+            author_email = str(get_vcs_config_value("user", "email"))
             if author_email:
                 author += f" <{author_email}>"
</code_context>
<issue_to_address>
**issue (bug_risk):** Avoid `str(None)` and potential `b'...'` representations when building the author string

If `get_vcs_config_value(
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}