[Feature Request] Configurable max token threshold for auto-compact trigger point

Bug Description
could you please create a max tokens config so I can use like 450k context? My usecase runs on /loop and I need an auto compact to run ath this point otherwise I keep running opus 1m with 70% context and the model struggles to logic, ends up becoming lazy

Environment Info

• Platform: darwin
• Terminal: ghostty
• Version: 2.1.87
• Feedback ID: 1adbc899-d782-4349-a6a5-433256c7a798

Errors

[{"error":"Error: Failed to delete keychain entry\n    at x_q (/$bunfs/root/src/entrypoints/cli.js:235:279183)\n    at async ALq (/$bunfs/root/src/entrypoints/cli.js:386:698)\n    at async oW6 (/$bunfs/root/src/entrypoints/cli.js:386:596)\n    at async $tH (/$bunfs/root/src/entrypoints/cli.js:2828:2077)\n    at async TfH (/$bunfs/root/src/entrypoints/cli.js:2852:4908)\n    at async <anonymous> (/$bunfs/root/src/entrypoints/cli.js:2920:17164)\n    at processTicksAndRejections (native:7:39)","timestamp":"2026-03-29T11:04:18.414Z"}]