6 views
-/https://github.com/berriai/litellm/issues/23743
GitHub · issue

#23743 [Feature]: Add Cache Hit column to Request Logs UI

  • State: open
  • Author: @h3x89
  • Labels: ui-dashboard

## The Feature Add a dedicated "Cache Hit" column (boolean or "yes/no") in the Request Logs table UI.

## Motivation, pitch In the Request Logs UI, cache hits are currently only visible indirectly via the suffix like . This makes it harder to quickly see which requests were served from cache, compare performance, and estimate cost savings.

It would be very helpful to have a dedicated **"Cache Hit"** column (boolean or "yes/no") in the Request Logs table. The column could be derived from the existing field or from the suffix in .

Example rows from my setup: - -

This feature would make it easier to: - monitor cache effectiveness at a glance, - debug when the cache is not being used as expected, - communicate cache impact to other stakeholders.

If there is already a hidden option or config to enable such a column, please let me know. Otherwise, I would love to see this as a small UX improvement to the Logs page.

## What part of LiteLLM is this about? UI Dashboard

## LiteLLM is hiring a founding backend engineer, are you interested in joining us and shipping to all our users? No

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (2 events)
#0 of 0 · 31d18h24m50s ago — entered · #import:https:::github.com:berriai:litellm post #2429
Supply-chain security remediation demands coordinated forensic analysis, dependency and release-pipeline changes, blast-radius assessment, and validation across the ecosystem, while the dashboard enhancement is a localized UI change using existing data.
#0 of 0 · 31d17h52m16s ago — current · #import:https:::github.com:berriai:litellm post #2985
#31878 requires coordinated changes across the logger interface and router fallback lifecycle, with async behavior, per-attempt semantics, metadata propagation, and regression-risk around error handling. #23743 is a comparatively localized dashboard presentation change using existing request-log data, likely requiring limited frontend wiring and tests.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search