Usage limits are communicated clearly before they are hit

Hitting a usage cap mid-prompt — after a user has typed four paragraphs and a code block — is the single most common complaint in consumer AI product reviews. It feels like being cut off mid-sentence by a bouncer, and it is entirely avoidable: the quota is known, the current usage is known, and the user wants to know when they are close. When the limit surfaces only as a 429 error at send time, the product signals that it does not value the user's time.

Expose {used, limit, period} from a /api/usage endpoint and render a persistent counter in the chat header (12 / 50 today). Trigger an amber warning banner at 80% and a blocking modal explaining upgrade options when the cap is reached. Never let the user compose a message they cannot send. Implement in src/components/chat/usage-indicator.tsx.

<span>{usage.used} / {usage.limit} messages today</span>