fix(tui): guide long shell work to background

[cyq1017]

Fixes #2939.

Summary

• spell out the >5 second threshold for shell work in the model prompt
• align the exec_shell background schema with task_shell_start / wait guidance
• add prompt and schema coverage for the guidance

Verification

• CARGO_TARGET_DIR=/tmp/codewhale-2939-supervisor-target cargo test -p codewhale-tui test_exec_shell_schema_guides_gt_five_second_work_to_background
• CARGO_TARGET_DIR=/tmp/codewhale-2939-supervisor-target cargo test -p codewhale-tui composed_prompt_keeps_shell_guidance_when_shell_tools_are_available
• cargo fmt --all -- --check
• git diff --check HEAD^..HEAD

[greptile-apps]

Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.

[gemini-code-assist]

Code Review

This pull request updates the system prompts, tool descriptions, and associated tests to explicitly define "long-running" shell commands as those expected to take more than 5 seconds. This establishes a concrete threshold for when background execution (via task_shell_start or background: true) should be preferred over foreground execution. There are no review comments, so I have no feedback to provide.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[greptile-apps]

Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.

[Hmbown]

Merged — thanks @cyq1017. This is the prompt-side half of #2939 (agent stalling on long-running shell commands); the >5s rule in both prompt and tool schema should shift behavior immediately.