mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
dca7ba18d4
* feat(ui): show models under each tier in routing benchmark chart - Add TierTurnsChart: donut chart showing turns per complexity tier with tier-assigned models listed below each tier name in the legend - Only complexity routers show models; quality routers show tier name + % (quality tiers don't pin specific models) - Change 'Estimated spend at highest-cost model' wording to 'highest-tier' to clarify it's the most capable tier's estimated cost, not just the single-highest model Closes LIT-5302 * fix(ui): use categorical colors for tier donut, trim redundant turn count - Tier donut chart now uses a dedicated categorical palette instead of SEQUENTIAL_COLOR_RAMP, which is a blue monochrome gradient meant for magnitude series, not distinct categories. - Space out the tier legend rows (gap-3 -> gap-6) for readability. - Drop the turn count from "avg saved per session" since Routing by tier already shows the total turns. Co-Authored-By: Claude <noreply@anthropic.com> * test(ui): drop prohibited explanatory comments in TierTurnsChart test Per repo convention against source comments; the test name and assertions already communicate the scenario. Addresses Greptile review. Co-Authored-By: Claude <noreply@anthropic.com> * Remove dead modulo from color index in TierTurnsChart The colors array is built with length equal to slices.length, so idx % colors.length is always a no-op in the render loop. Simplify to idx for clarity. * fix(ui): wrap CostOptimizationView tests in QueryClientProvider The tests render CostOptimizationView which uses useCan() → useIsOrgAdmin() → useOrganizations() and useDailyActivityRange(), both of which call React Query's useQuery(). Without QueryClientProvider wrapping the render, React Query throws 'No QueryClient set' error. Also mock the required networking calls (organizationListCall, userDailyActivityCall) to prevent spurious network errors in test runs. All 7 tests now pass (CostOptimizationView + CostOptimizationView.activity). * style(ui): format test files and extract object literal to fix linting - Format CostOptimizationView.test.tsx with prettier - Extract getToolSpend mock response to named variable to satisfy eslint - Pass frontend-lint checks * fix(ui): hoist mockToolSpendResponse into vi.hoisted to fix test initialization Extracting the response object to a named variable violated hoisting rules: vi.mock() factories are evaluated at hoisting time before regular const declarations. Move mockToolSpendResponse into vi.hoisted() block. --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| litellm-dashboard | ||
| Dockerfile | ||
| nginx.conf | ||