🧹 refactor: use idiomatic sqlite result handling in PersistentDict

[clayauld]

🎯 What: The code health issue addressed

• Refactored PersistentDict to use sqlite3.Row for its connection row_factory.
• Updated __getitem__, __iter__, and __len__ to use named column access and more concise patterns.
• Removed redundant manual cursor mapping in __iter__.

💡 Why: How this improves maintainability

• Enhances code readability by using named columns (e.g., row["key"]) instead of numerical indices.
• Simplifies the implementation of dictionary methods, making the code more idiomatic and easier to maintain.
• Reduces boilerplate code associated with manual cursor management.

✅ Verification: How you confirmed the change is safe

• Ran the dedicated test suite for PersistentDict: pytest tests/test_persistent_dict.py. All 8 tests passed.
• Verified that sqlite3.Row maintains compatibility with index-based access, ensuring no regressions.

✨ Result: The improvement achieved

• A cleaner, more maintainable PersistentDict implementation that follows Python best practices for SQLite interaction.

---

PR created automatically by Jules for task 7134018262499593634 started by @clayauld

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.

[github-actions]

🤖 Automated Code Review

🔍 Linting Results Summary

✅ Black (Code Formatting) - PASSED

✅ Flake8 (Code Quality) - PASSED

✅ isort (Import Sorting) - PASSED

⚠️ MyPy (Type Checking)

src/persistent_dict.py:167: error: Returning Any from function declared to return "int"  [no-any-return]

Fix: Add missing type annotations and fix type errors.

✅ Bandit (Security) - PASSED

✅ All Linting Checks Passed!

---

This comment was automatically generated by GitHub Actions. Check the Actions tab for detailed logs.

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request refactors the PersistentDict class to enhance its interaction with SQLite, making the code more Pythonic and maintainable. By configuring the SQLite connection to use sqlite3.Row, the implementation now benefits from named column access, which significantly improves the clarity of database operations within the dictionary methods. This change simplifies the codebase, reduces potential for errors, and aligns the PersistentDict with best practices for SQLite usage in Python.

Highlights

• sqlite3.Row Integration: The PersistentDict class now utilizes sqlite3.Row as its connection's row_factory, enabling named column access for query results.
• Method Refactoring: The getitem, iter, and len methods have been updated to leverage named column access and more concise patterns, improving readability and reducing boilerplate.
• Cursor Management Simplification: Manual cursor mapping in iter has been removed, streamlining the iteration process.

Changelog

• src/persistent_dict.py
  • Configured the SQLite connection to use sqlite3.Row as its row_factory.
  • Updated getitem to directly execute the query and fetch the row, then access the value by name (row["value"]).
  • Refactored iter to use a generator expression for yielding keys, accessing them by name (row["key"]), and removing explicit cursor assignment.
  • Streamlined len by directly executing the count query and fetching the result without an intermediate cursor variable.

Activity

• The pull request was automatically created by Jules for a task initiated by @clayauld.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[github-actions]

📊 Pull Request Analysis Report

🧪 Test Results

Metric	Value
Total Tests	111
✅ Passed	111
❌ Failed	0
⏭️ Skipped	0
💥 Errors	0
📈 Success Rate	100.0%

📋 Coverage Report

Metric	Value
Overall Coverage	89.6%
Total Lines	767
Covered Lines	687
Missing Lines	80

📚 Documentation Report

Metric	Value
Documentation Coverage	100.0%
Status	✅ Up to date

📁 File Coverage Breakdown

• config/__init__.py: 100.0%
• config/config.py: 95.3%
• src/__init__.py: 100.0%
• src/caltopo_reporter.py: 95.0%
• src/gateway.py: 84.4%
• src/gateway_app.py: 83.6%
• src/mqtt_client.py: 92.0%
• src/persistent_dict.py: 90.4%
• src/utils.py: 100.0%

🎯 Recommendations

✅ Excellent Code Quality

• Great work maintaining high test pass rate and coverage!

---

📊 Analysis generated by GitHub Actions • View detailed test report

[gemini-code-assist]

Code Review

This pull request is a great refactoring that modernizes the PersistentDict class by using sqlite3.Row. This change makes the code more readable and idiomatic Python by enabling named-column access. The updates to __getitem__ and __iter__ are excellent examples of this improvement. I have one suggestion for the __len__ method to improve its consistency with the rest of your changes and simplify the implementation.