[Enhancement] Standardize usage limit labels — replace ambiguous 'Usage Limit' with specific limit type identifiers

[daskuntal75]

Summary

Claude surfaces multiple independent usage limits (session-level, weekly all-models, weekly Sonnet-specific, API rate limits) but labels all of them identically as "Usage Limit" in the UI and error responses. When a limit fires, users cannot determine which limit was hit, when it resets, or what to do next.

Current behaviour (confusing)

You've reached your usage limit. Please try again later.

Same message for all limit types. No reset time. No actionable guidance.

Expected behaviour (actionable)

Daily session budget reached (resets in 4h 22m)

or

Weekly all-models budget at 100% (resets Sunday 10:00)

or

API rate limit: 60 requests/min exceeded (resets in 43 seconds)

Proposed label taxonomy

Limit type	Proposed identifier
Session daily budget	session_daily_budget
Weekly all-models budget	weekly_all_models_budget
Weekly Sonnet budget	weekly_sonnet_budget
API requests per minute	api_rpm_limit
API tokens per minute	api_tpm_limit

Apply in: console UI, in-app error messages, API error response type field, rate limit response headers.

Impact

Without clear labels, users building on the API cannot programmatically distinguish limit types and cannot surface meaningful guidance to their end users. Developers are currently reverse-engineering limit types from context clues.

Reference

https://github.com/daskuntal75/llm-cost-kit/blob/main/docs/anthropic-issues-submit-ready.md