This commit addresses "Max retries exceeded" errors during stress testing where all accounts would become exhausted simultaneously due to short per-second rate limits triggering cascading failures. ## Rate Limit Parser (`rate-limit-parser.js`) - Remove 2s buffer enforcement that caused cascading failures when API returned short reset times (200-600ms). Now adds 200ms buffer for sub-500ms resets - Add `parseRateLimitReason()` for smart backoff based on error type: QUOTA_EXHAUSTED, RATE_LIMIT_EXCEEDED, MODEL_CAPACITY_EXHAUSTED, SERVER_ERROR ## Message/Streaming Handlers - Add per-account+model rate limit state tracking with exponential backoff - For short rate limits (< 1 second), wait and retry on same account instead of switching - prevents thundering herd when all accounts hit per-second limits - Add throttle wait support for fallback modes (emergency/lastResort) - Add `calculateSmartBackoff()` with progressive tiers by error type ## HybridStrategy (`hybrid-strategy.js`) - Refactor `#getCandidates()` to return 4 fallback levels: - `normal`: All filters pass (health, tokens, quota) - `quota`: Bypass critical quota check - `emergency`: Bypass health check when ALL accounts unhealthy - `lastResort`: Bypass BOTH health AND token bucket checks - Add throttle wait times: 500ms for lastResort, 250ms for emergency - Fix LRU calculation to use seconds (matches opencode-antigravity-auth) ## Health Tracker - Increase `recoveryPerHour` from 2 to 10 for faster recovery (1 hour vs 5 hours) ## Account Manager - Add consecutive failure tracking: `getConsecutiveFailures()`, `incrementConsecutiveFailures()`, `resetConsecutiveFailures()` - Add cooldown mechanism separate from rate limits with `CooldownReason` - Reset consecutive failures on successful request ## Base Strategy - Add `isAccountCoolingDown()` check in `isAccountUsable()` ## Constants - Replace fixed `CAPACITY_RETRY_DELAY_MS` with progressive `CAPACITY_BACKOFF_TIERS_MS` - Add `BACKOFF_BY_ERROR_TYPE` for smart backoff - Add `QUOTA_EXHAUSTED_BACKOFF_TIERS_MS` for progressive quota backoff - Add `MIN_BACKOFF_MS` floor to prevent "Available in 0s" loops - Increase `MAX_CAPACITY_RETRIES` from 3 to 5 - Reduce `RATE_LIMIT_DEDUP_WINDOW_MS` from 5s to 2s ## Frontend - Remove `capacityRetryDelayMs` config (replaced by progressive tiers) - Update default `maxCapacityRetries` display from 3 to 5 ## Testing - Add `tests/stress-test.cjs` for concurrent request stress testing Co-Authored-By: Claude <noreply@anthropic.com>
94 lines
3.2 KiB
JavaScript
94 lines
3.2 KiB
JavaScript
/**
|
|
* 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);
|