Speed up paired tmux startup

[axeldelafosse]

Summary

• pass the initial Codex prompt directly in the fresh paired tmux launch command
• remove the serialized Codex ready polling and fixed post-launch waits from paired tmux startup
• update tmux coverage to assert fresh launches use startup prompts while resumed sessions still avoid replaying work

Verification

• bun test
• bun run check
• measured fresh paired tmux startup with --prompt TASK.md and a unique LOOP_RUN_ID
  • before: ~9.3s
  • after: ~1.4s

Notes

• plain-text prompts still pay the PLAN.md planning/review cost before tmux starts; that is a separate pre-tmux path

[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 dramatically improves the startup performance of paired tmux sessions. By integrating the initial Codex prompt directly into the launch command and removing several polling and fixed delay mechanisms, the time taken for a fresh session to become ready has been reduced from approximately 9.3 seconds to 1.4 seconds. This optimization enhances the responsiveness and efficiency of the development environment.

Highlights

• Direct Prompt Injection: The initial Codex prompt is now passed directly into the fresh paired tmux launch command, streamlining the startup process.
• Reduced Startup Delays: Serialized Codex ready polling and fixed post-launch waits have been eliminated, significantly reducing paired tmux startup time.
• Enhanced Test Coverage: Tmux test coverage was updated to verify that fresh launches correctly utilize startup prompts, while resumed sessions avoid replaying work.

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.

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. ↩

[gemini-code-assist]

Code Review

This pull request refactors the prompt handling and session startup logic for Claude and Codex agents within the tmux module. Key changes include reducing CLAUDE_PROMPT_INITIAL_POLLS from 8 to 4, removing several constants and functions related to Codex readiness polling and prompt seeding, and modifying buildCodexCommand to directly accept the codexPrompt. The startPairedSession function has been simplified by removing explicit prompt dispatching logic. Corresponding tests have been updated to reflect these changes, including removing assertions about typed prompts and adding new tests for Claude startup wait times and delayed trust prompt handling. No feedback to provide.