tests/stress-test-normal.cjs

/**
 * Stress Test - Send multiple concurrent requests to test rate limit handling
 *
 * Usage: node tests/stress-test.cjs [count] [model]
 * Example: node tests/stress-test.cjs 10 gemini-3-flash
 */

const BASE_URL = process.env.ANTHROPIC_BASE_URL || 'http://localhost:8080';

const count = parseInt(process.argv[2]) || 8;
const model = process.argv[3] || 'gemini-3-flash';

async function sendRequest(id) {
    const startTime = Date.now();
    try {
        const response = await fetch(`${BASE_URL}/v1/messages`, {
            method: 'POST',
            headers: {
                'Content-Type': 'application/json',
                'x-api-key': 'test',
                'anthropic-version': '2023-06-01'
            },
            body: JSON.stringify({
                model: model,
                max_tokens: 100,
                messages: [
                    { role: 'user', content: `Request ${id}: Say "Hello ${id}" and nothing else.` }
                ]
            })
        });

        const elapsed = Date.now() - startTime;

        if (!response.ok) {
            const errorText = await response.text();
            console.log(`[${id}] ❌ ${response.status} after ${elapsed}ms: ${errorText.substring(0, 100)}`);
            return { id, success: false, status: response.status, elapsed };
        }

        const data = await response.json();
        const text = data.content?.[0]?.text?.substring(0, 50) || 'No text';
        console.log(`[${id}] ✅ 200 after ${elapsed}ms: "${text}..."`);
        return { id, success: true, status: 200, elapsed };
    } catch (error) {
        const elapsed = Date.now() - startTime;
        console.log(`[${id}] ❌ Error after ${elapsed}ms: ${error.message}`);
        return { id, success: false, error: error.message, elapsed };
    }
}

async function runStressTest() {
    console.log(`\n🚀 Stress Test: Sending ${count} concurrent requests to ${model}\n`);
    console.log(`Target: ${BASE_URL}/v1/messages\n`);
    console.log('─'.repeat(70));

    const startTime = Date.now();

    // Send all requests concurrently
    const promises = [];
    for (let i = 1; i <= count; i++) {
        promises.push(sendRequest(i));
    }

    const results = await Promise.all(promises);

    const totalElapsed = Date.now() - startTime;
    console.log('─'.repeat(70));

    // Summary
    const successful = results.filter(r => r.success).length;
    const failed = results.filter(r => !r.success).length;
    const avgElapsed = Math.round(results.reduce((sum, r) => sum + r.elapsed, 0) / results.length);

    console.log(`\n📊 Summary:`);
    console.log(`   Total time: ${totalElapsed}ms`);
    console.log(`   Successful: ${successful}/${count}`);
    console.log(`   Failed: ${failed}/${count}`);
    console.log(`   Avg response time: ${avgElapsed}ms`);

    if (failed > 0) {
        const errors = results.filter(r => !r.success);
        const statusCounts = {};
        errors.forEach(e => {
            const key = e.status || 'network';
            statusCounts[key] = (statusCounts[key] || 0) + 1;
        });
        console.log(`   Error breakdown: ${JSON.stringify(statusCounts)}`);
    }

    console.log('');
}

runStressTest().catch(console.error);