Skip to content

⚡ Bolt: Optimize push_rules filtering logic#189

Merged
abhimehro merged 1 commit intomainfrom
bolt-optimize-push-rules-8637011872004009951
Feb 13, 2026
Merged

⚡ Bolt: Optimize push_rules filtering logic#189
abhimehro merged 1 commit intomainfrom
bolt-optimize-push-rules-8637011872004009951

Conversation

@abhimehro
Copy link
Owner

  • 💡 What: Replaced the manual loop and seen set in push_rules with dict.fromkeys(hostnames).
  • 🎯 Why: The original implementation iterated over potentially large lists of hostnames in Python, checking against a seen set for every item. This is computationally expensive for large lists. dict.fromkeys() performs ordered deduplication in C, which is significantly faster.
  • 📊 Impact: Reduces execution time of the filtering logic by ~21% (measured 0.1247s -> 0.0976s on a 100k item list with mocked API).
  • Also reduces log spam by deduplicating invalid rules before logging them.
  • 🔬 Measurement: Verified with a benchmark script that mocked the API client.

PR created automatically by Jules for task 8637011872004009951 started by @abhimehro

Co-authored-by: abhimehro <84992105+abhimehro@users.noreply.github.com>
Copilot AI review requested due to automatic review settings February 11, 2026 15:09
@google-labs-jules
Copy link

👋 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.

@trunk-io
Copy link

trunk-io bot commented Feb 11, 2026

Merging to main in this repository is managed by Trunk.

  • To merge this pull request, check the box to the left or comment /trunk merge below.

@github-actions
Copy link

👋 Development Partner is reviewing this PR. Will provide feedback shortly.

@gemini-code-assist
Copy link

Summary of Changes

Hello @abhimehro, 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 introduces a significant performance optimization to the push_rules function by replacing a Python-level deduplication loop with dict.fromkeys(). This change drastically improves the efficiency of processing large lists of hostnames, leading to faster execution and a reduction in unnecessary log entries by deduplicating invalid rules earlier in the process.

Highlights

  • Performance Optimization: Replaced a manual loop with a seen set for deduplication in push_rules with dict.fromkeys(hostnames), resulting in approximately a 21% reduction in execution time for filtering logic on large lists.
  • Reduced Log Spam: The new deduplication method naturally handles invalid rules before logging, which helps in reducing log spam by preventing redundant warnings for the same invalid entries.
Changelog
  • .jules/bolt.md
    • Added a new entry documenting the learning and action related to using dict.fromkeys() for ordered deduplication.
  • main.py
    • Refactored the push_rules function to leverage dict.fromkeys() for efficient, ordered deduplication of hostnames.
    • Removed the manual seen set and associated logic, simplifying the code.
    • Updated comments to reflect the new optimization strategy.
Activity
  • PR created automatically by Jules for task [8637011872004009951] started by @abhimehro.
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.

skipped_unsafe = 0

for h in hostnames:
for h in unique_hostnames:

Check warning

Code scanning / Pylintpython3 (reported by Codacy)

Variable name "h" doesn't conform to snake_case naming style Warning

Variable name "h" doesn't conform to snake_case naming style
skipped_unsafe = 0

for h in hostnames:
for h in unique_hostnames:

Check warning

Code scanning / Pylint (reported by Codacy)

Variable name "h" doesn't conform to snake_case naming style Warning

Variable name "h" doesn't conform to snake_case naming style
Copy link

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR optimizes push_rules() in main.py by replacing a Python loop + seen set used for ordered deduplication with dict.fromkeys(hostnames), aiming to speed up filtering on large hostname lists and reduce repeated warning logs for duplicated invalid rules.

Changes:

  • Deduplicate hostnames in-order using dict.fromkeys() before validation/filtering in push_rules().
  • Reduce warning-log repetition by validating only the first occurrence of each hostname.
  • Document the optimization learning in Bolt’s journal.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File Description
main.py Uses dict.fromkeys() for ordered deduplication before validating/filtering rules in push_rules().
.jules/bolt.md Adds a journal entry describing the ordered deduplication optimization and guidance.

Copy link

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request optimizes the push_rules function by using dict.fromkeys() for faster, order-preserving deduplication of hostnames. This is a solid improvement that also has the benefit of reducing log spam for duplicate invalid rules. The implementation is correct and the performance gain is well-documented. I have one minor suggestion to improve the readability of the filtering loop.

Comment on lines +1085 to 1094
for h in unique_hostnames:
if not is_valid_rule(h):
log.warning(
f"Skipping unsafe rule in {sanitize_for_log(folder_name)}: {sanitize_for_log(h)}"
)
skipped_unsafe += 1
continue

if h not in existing_rules and h not in seen:
if h not in existing_rules:
filtered_hostnames.append(h)

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

For improved readability, you can combine the two if statements in this loop into a single if/elif structure. This removes the need for continue and slightly flattens the logic, making the conditions for filtering hostnames clearer.

Suggested change
for h in unique_hostnames:
if not is_valid_rule(h):
log.warning(
f"Skipping unsafe rule in {sanitize_for_log(folder_name)}: {sanitize_for_log(h)}"
)
skipped_unsafe += 1
continue
if h not in existing_rules and h not in seen:
if h not in existing_rules:
filtered_hostnames.append(h)
for h in unique_hostnames:
if not is_valid_rule(h):
log.warning(
f"Skipping unsafe rule in {sanitize_for_log(folder_name)}: {sanitize_for_log(h)}"
)
skipped_unsafe += 1
elif h not in existing_rules:
filtered_hostnames.append(h)

@abhimehro abhimehro merged commit c180eba into main Feb 13, 2026
25 checks passed
@abhimehro abhimehro deleted the bolt-optimize-push-rules-8637011872004009951 branch February 13, 2026 02:26
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants