Add per-model provider + data-retention/prompt-training disclosure

Summary

It should be clear what's the prompt training and data retention policy on each model/provider. I don't care if Command Code doesn't train on my prompts and doesn't retain my data, that's pointless if the underlying provider could be doing that.. You're essentially saying today like "I don't use your data dude, just chill", but omitting that the underlying providers might be doing it.. Transparency is pretty important and that's why I cancelled my sub instead of upgrading it... Thought of upgrading but gave up after realizing that. It's not enough as well that you say that 98% of your models are zdr or no prompt training... It's only enough when you at least disclosure in your website the prompt training and retention policy for each model. And if possible, provide a way of disabling models whose provider might train on prompts...

Expected Behavior

Disclosure in your website the prompt training and retention policy for each model. And if possible, provide a way of disabling models whose provider might train on prompts...

Actual Behavior

Data Retention and Prompt Training policies at PROVIDER level are not disclosure. Privacy Policy is misleading as it talks about you, not the providers.

Steps to reproduce the issue

Try finding any disclosure on the prompt training or data retention policies per model... It doesn't even disclosure the providers per model..

Command Code Version

1.26.0

Operating System

macOS

Terminal/IDE

kitty

Shell

⌘ Data Retention Policy

Session file (optional)

No response

Fix prompt (optional)

No response

Additional context

OS: macOS Tahoe 26.5.2

Comece revisando as listagens de modelos/provedores do site e a Data Retention Policy existente referenciada na issue. Defina como serão representados o provedor de cada modelo, a política de treinamento de prompts e a política de retenção, e avalie a opção solicitada de desabilitar modelos com treinamento pelo provedor. Considera-se concluído quando o site divulga essas políticas para cada modelo e, se viável, oferece suporte a esse opt-out.