Document quotas for remote generation

[devin-ai-integration]

Summary

Adds a new Quotas section to the SDK "How it works" page documenting the rate limits for remote (cloud) generation:

• Leaky bucket algorithm: burst of 10 generations, refill of 5 per minute
• Callout that local generation (--local) isn't subject to quotas
• Link to contact us for higher limits

Updates since last revision

• Fixed vale lint: is not → isn't per Microsoft.Contractions rule

Local testing

Verified the page renders correctly via fern docs dev:

View original video (rec-e22d483bc7de49359a3204ef6a980e03-edited.mp4)

Review & Testing Checklist for Human

• Verify the quota values (burst=10, refill=5/min) match what was shipped in the backend
• Check section placement — the Quotas section sits between the cloud workflow steps and the sequence diagram accordions; confirm this reads naturally
• Confirm the link to the self-hosted page (/learn/sdks/deep-dives/self-hosted) resolves correctly on the preview deploy

Notes

Requested by: Fern Support
Link to Devin run

[devin-ai-integration]

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

• Address comments on this PR. Add '(aside)' to your comment to have me ignore it.
• Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

• Disable automatic comment and CI monitoring

[github-actions]

🚫 [vale] _{reported by reviewdog 🐶}
[Microsoft.Contractions] Use 'isn't' instead of 'is not'.

[github-actions]

🌿 Preview your docs: https://fern-preview-3bb52396-f27a-41cd-852b-23f8aadc1de3.docs.buildwithfern.com/learn

Here are the markdown pages you've updated:

• learn/sdks/overview/how-it-works