Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -78,6 +78,8 @@ const validConfig = {
classifierRepetitions: 1,
deciderRepetitions: 1,
classifierMaxP95LatencyMs: 1000,
autoDeciderMinCostUsd: 15,
autoDeciderMaxCostUsd: 25,
updatedAt: null,
updatedBy: null,
};
Expand Down
54 changes: 52 additions & 2 deletions apps/web/src/app/admin/auto-routing/BenchmarksSection.test.ts
Original file line number Diff line number Diff line change
@@ -1,9 +1,11 @@
import { describe, expect, it } from '@jest/globals';
import type { BenchmarkConfig } from '@kilocode/auto-routing-contracts';
import React from 'react';
import { renderToStaticMarkup } from 'react-dom/server';
import {
configToFormState,
costPerAccuracy,
effectiveDeciderModels,
formatCostPerAccuracy,
formatAccuracy,
formatUsd,
Expand Down Expand Up @@ -119,18 +121,28 @@ describe('configToFormState', () => {
expect(state.classifierRepetitions).toBe(1);
expect(state.deciderRepetitions).toBe(1);
expect(state.classifierMaxP95LatencyMs).toBe('1000');
expect(state.autoDeciderMinCostUsd).toBe(15);
expect(state.autoDeciderMaxCostUsd).toBe(25);
expect(state.classifierModels).toBe('');
expect(state.deciderModels).toEqual([]);
expect(state.autoDeciderModels).toEqual([]);
expect(state.excludedAutoDeciderModels).toBe('');
expect(state.maxConcurrency).toBe(100);
expect(state.benchmarkUserId).toBe('ce12ef3d-ae95-4d77-b4f0-23735f0a0591');
expect(state.benchmarkOrgId).toBe('9d278969-5453-4ae3-a51f-a8d2274a7b56');
});
});

describe('formStateToConfig round-trip', () => {
const baseConfig = {
const baseConfig: BenchmarkConfig = {
classifierModels: ['model-a', 'model-b'],
deciderModels: [{ id: 'model-c', reasoningEffort: null }],
manualDeciderModels: [{ id: 'manual-model', reasoningEffort: 'low' }],
autoDeciderModels: [
{ id: 'auto-model', reasoningEffort: null, avgAttemptCostUsd: 21.25 },
{ id: 'excluded-auto-model', reasoningEffort: 'high', avgAttemptCostUsd: 18 },
],
excludedAutoDeciderModels: ['excluded-auto-model'],
minAccuracy: 0.8,
switchCostFactor: 3,
maxConcurrency: 4,
Expand All @@ -139,22 +151,37 @@ describe('formStateToConfig round-trip', () => {
classifierRepetitions: 3,
deciderRepetitions: 2,
classifierMaxP95LatencyMs: 500,
autoDeciderMinCostUsd: 12,
autoDeciderMaxCostUsd: 24,
updatedAt: null,
updatedBy: null,
};

it('preserves classifierRepetitions, deciderRepetitions, and classifierMaxP95LatencyMs', () => {
it('preserves repetitions, classifierMaxP95LatencyMs, and auto decider cost bounds', () => {
const state = configToFormState(baseConfig);
expect(state.classifierRepetitions).toBe(3);
expect(state.deciderRepetitions).toBe(2);
expect(state.classifierMaxP95LatencyMs).toBe('500');
expect(state.autoDeciderMinCostUsd).toBe(12);
expect(state.autoDeciderMaxCostUsd).toBe(24);
expect(state.benchmarkOrgId).toBe('org-123');
expect(state.deciderModels).toEqual([{ id: 'manual-model', reasoningEffort: 'low' }]);
expect(state.autoDeciderModels).toEqual(baseConfig.autoDeciderModels);
expect(state.excludedAutoDeciderModels).toBe('excluded-auto-model');

const result = formStateToConfig(state, baseConfig);
expect(result.classifierRepetitions).toBe(3);
expect(result.deciderRepetitions).toBe(2);
expect(result.classifierMaxP95LatencyMs).toBe(500);
expect(result.autoDeciderMinCostUsd).toBe(12);
expect(result.autoDeciderMaxCostUsd).toBe(24);
expect(result.benchmarkOrgId).toBe('org-123');
expect(result.manualDeciderModels).toEqual([{ id: 'manual-model', reasoningEffort: 'low' }]);
expect(result.excludedAutoDeciderModels).toEqual(['excluded-auto-model']);
expect(result.deciderModels).toEqual([
{ id: 'manual-model', reasoningEffort: 'low' },
{ id: 'auto-model', reasoningEffort: null },
]);
});

it('converts empty-string classifierMaxP95LatencyMs form value to null in config', () => {
Expand All @@ -164,3 +191,26 @@ describe('formStateToConfig round-trip', () => {
expect(result.classifierMaxP95LatencyMs).toBeNull();
});
});

describe('effectiveDeciderModels', () => {
it('combines manual models with non-excluded auto models and lets manual override an auto duplicate', () => {
expect(
effectiveDeciderModels({
manualDeciderModels: [
{ id: 'manual/model', reasoningEffort: null },
{ id: 'auto/duplicate', reasoningEffort: 'high' },
],
autoDeciderModels: [
{ id: 'auto/duplicate', reasoningEffort: null, avgAttemptCostUsd: 20 },
{ id: 'auto/included', reasoningEffort: 'low', avgAttemptCostUsd: 22 },
{ id: 'auto/excluded', reasoningEffort: null, avgAttemptCostUsd: 23 },
],
excludedAutoDeciderModels: ['auto/excluded'],
})
).toEqual([
{ id: 'manual/model', reasoningEffort: null },
{ id: 'auto/duplicate', reasoningEffort: 'high' },
{ id: 'auto/included', reasoningEffort: 'low' },
]);
});
});
Loading