Files
OmniRoute/tests/unit/usage-analytics.test.mjs
T
Diego Rodrigues de Sa e Souza 70a4d38d04
Build Electron Desktop App / Validate version (push) Failing after 34s
Build Electron Desktop App / Build Electron (macos-arm64) (push) Has been skipped
Build Electron Desktop App / Build Electron (linux) (push) Has been skipped
Build Electron Desktop App / Build Electron (macos-intel) (push) Has been skipped
Build Electron Desktop App / Build Electron (windows) (push) Has been skipped
Build Electron Desktop App / Create Release (push) Has been skipped
Build Electron Desktop App / Publish to npm (push) Has been skipped
Release v3.4.0 (Integration) (#861)
* test(settings): add unit tests for debugMode and hiddenSidebarItems

Tests cover:
- PATCH debugMode=true/false
- PATCH hiddenSidebarItems with array values
- Combined updates with both fields

* test(e2e): add Playwright tests for settings toggles

Tests cover:
- Debug mode toggle on/off
- Sidebar visibility toggle
- Settings persistence after page reload

* fix(tests): address code review issues

- Unit tests: fix async/await for getSettings, use direct db functions
- E2E tests: remove conditional logic, use Playwright auto-waiting assertions

* feat(logging): unify request log retention and artifacts

* docs: add dashboard settings toggles to CONTRIBUTING

Add section documenting:
- Debug Mode toggle (Settings → Advanced)
- Sidebar Visibility toggle (Settings → General)

* fix(cache): only inject prompt_cache_key for supported providers

Only inject prompt_cache_key for providers that support prompt caching
(Claude, Anthropic, ZAI, Qwen, DeepSeek). This fixes issue #848 where
NVIDIA API rejected the parameter.

* fix(model-sync): log only channel-level model changes

* feat(providers): add 4 free models to opencode-zen

* feat(providers): add explicit contextLength for opencode-zen free models

* feat(providers): add contextLength for all opencode-zen models

* feat: Improve the Chinese translation

* fix: preserve client cache_control for all Claude-protocol providers

Previously, the cache control preservation logic only recognized a
hardcoded list of providers (claude, anthropic, zai, qwen, deepseek).
This caused OmniRoute to inject its own cache_control markers for
Claude-protocol providers not in that list (bailian-coding-plan, glm,
minimax, minimax-cn, etc.), overwriting the client's cache markers.

The fix checks both:
1. Known caching providers list (existing behavior)
2. Whether targetFormat === 'claude' (all Claude-protocol providers)

This ensures all Claude-compatible providers properly preserve client
cache_control headers when appropriate (Claude Code client, deterministic
routing, etc.).

Also removes unused CacheStatsCard from settings/components (duplicate
of the one in cache/ page).

Fixes cache token calculation for GLM, Minimax, and other Claude-compatible providers.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: pure passthrough for Claude→Claude when cache_control preserved

The Claude passthrough path round-trips through OpenAI format
(claude→openai→claude) for structural normalization. This strips
cache_control markers from every content block since OpenAI format
has no equivalent, causing ~42k cache creation tokens per request
with zero cache reads.

When preserveCacheControl is true (Claude Code client, "always"
setting, or deterministic combo), skip the round-trip entirely and
forward the body as-is. Claude Code sends well-formed Messages API
payloads — the normalization was only needed for non-Code clients.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: restore CacheStatsCard — was not a duplicate

The first commit incorrectly deleted CacheStatsCard from
settings/components/ as a "duplicate". It's the only copy — both
settings/page.tsx and cache/page.tsx import from this location.

Restored the i18n-ized version from main.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(429): parse long quota reset times from error body

- Parse XhYmZs format from antigravity error messages (e.g., 27h41m36s)
- Dynamic retry-after threshold (60s default) instead of hardcoded 10s
- Add parseRetryFromErrorText() in accountFallback.ts for body parsing
- Fix 403 'verify your account' to trigger permanent deactivation
- Add keyword matching for 'quota will reset', 'exhausted capacity'
- Add unit tests for retry parsing and keyword matching

Fixes #858 (Antigravity 429 handling)
Fixes #832 (Qwen quota 429 - same underlying bug)

* chore: bump version to v3.4.0-dev

* fix(migrations): rename 013 to 014 to avoid collision with v3.3.11

* chore(docs): update CHANGELOG for v3.4.0 integrations

* fix: Claude token refresh, Antigravity quota, and 429 rate-limit handling

- Fix Claude OAuth token refresh to use form-urlencoded format (standard OAuth2)
- Add anthropic-beta header required by Claude OAuth API
- Switch Antigravity quota to use retrieveUserQuota API (same as Gemini CLI)
- Parse quota reset time for all providers (not just Antigravity)
- Add quota reset keywords to error classifier
- Cap maximum retry time at 24 hours to prevent infinite wait

Closes #836, #857, #858, #832

* fix(dashboard): resolve /dashboard/limits hanging UI with 70+ accounts via chunk parallelization (#784)

---------

Co-authored-by: oyi77 <oyi77@users.noreply.github.com>
Co-authored-by: R.D. <rogerproself@gmail.com>
Co-authored-by: kang-heewon <heewon.dev@gmail.com>
Co-authored-by: gmw <rorschach1167@qq.com>
Co-authored-by: tombii <github@tombii.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
2026-03-31 10:22:52 -03:00

298 lines
9.1 KiB
JavaScript

import test from "node:test";
import assert from "node:assert/strict";
import fs from "node:fs";
import os from "node:os";
import path from "node:path";
const TEST_DATA_DIR = fs.mkdtempSync(path.join(os.tmpdir(), "omniroute-usage-analytics-"));
process.env.DATA_DIR = TEST_DATA_DIR;
const core = await import("../../src/lib/db/core.ts");
const localDb = await import("../../src/lib/localDb.ts");
const providersDb = await import("../../src/lib/db/providers.ts");
const usageHistory = await import("../../src/lib/usage/usageHistory.ts");
const usageStats = await import("../../src/lib/usage/usageStats.ts");
const callLogs = await import("../../src/lib/usage/callLogs.ts");
const { calculateCost } = await import("../../src/lib/usage/costCalculator.ts");
function clearPendingRequests() {
const pending = usageHistory.getPendingRequests();
for (const key of Object.keys(pending.byModel)) delete pending.byModel[key];
for (const key of Object.keys(pending.byAccount)) delete pending.byAccount[key];
}
async function resetStorage() {
core.resetDbInstance();
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
fs.mkdirSync(TEST_DATA_DIR, { recursive: true });
clearPendingRequests();
}
test.beforeEach(async () => {
await resetStorage();
});
test.after(() => {
core.resetDbInstance();
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
});
test("usage history persists entries and supports filtering and usageDb compatibility", async () => {
const recentTimestamp = new Date().toISOString();
const olderTimestamp = new Date(Date.now() - 2 * 60 * 60 * 1000).toISOString();
await usageHistory.saveRequestUsage({
provider: "provider-a",
model: "model-a",
connectionId: "conn-a",
apiKeyId: "key-a",
apiKeyName: "Key A",
tokens: {
input: 10,
output: 5,
cacheRead: 2,
cacheCreation: 1,
reasoning: 3,
},
status: "success",
success: true,
latencyMs: 120,
timeToFirstTokenMs: 30,
timestamp: recentTimestamp,
});
await usageHistory.saveRequestUsage({
provider: "provider-b",
model: "model-b",
connectionId: "conn-b",
tokens: {
prompt_tokens: 20,
completion_tokens: 7,
cached_tokens: 4,
cache_creation_input_tokens: 2,
reasoning_tokens: 1,
},
status: "error",
success: false,
latencyMs: 400,
errorCode: "rate_limited",
timestamp: olderTimestamp,
});
const filtered = await usageHistory.getUsageHistory({
provider: "provider-a",
startDate: new Date(Date.now() - 5 * 60 * 1000).toISOString(),
});
const all = await usageHistory.getUsageDb();
assert.equal(filtered.length, 1);
assert.equal(filtered[0].provider, "provider-a");
assert.equal(filtered[0].tokens.input, 10);
assert.equal(filtered[0].tokens.output, 5);
assert.equal(filtered[0].tokens.cacheRead, 2);
assert.equal(filtered[0].tokens.cacheCreation, 1);
assert.equal(filtered[0].tokens.reasoning, 3);
assert.equal(filtered[0].timeToFirstTokenMs, 30);
assert.equal(all.data.history.length, 2);
assert.equal(all.data.history[0].provider, "provider-b");
assert.equal(all.data.history[1].provider, "provider-a");
assert.equal(all.data.history[0].success, false);
assert.equal(all.data.history[1].success, true);
});
test("getModelLatencyStats aggregates success rate and latency percentiles", async () => {
const now = Date.now();
const entries = [
{ latencyMs: 100, success: true },
{ latencyMs: 200, success: true },
{ latencyMs: 400, success: true },
{ latencyMs: 900, success: false },
];
for (const [index, entry] of entries.entries()) {
await usageHistory.saveRequestUsage({
provider: "latency-provider",
model: "latency-model",
success: entry.success,
latencyMs: entry.latencyMs,
timestamp: new Date(now - index * 60 * 1000).toISOString(),
});
}
const stats = await usageHistory.getModelLatencyStats({
windowHours: 1,
minSamples: 2,
maxRows: 50,
});
const entry = stats["latency-provider/latency-model"];
assert.ok(entry);
assert.equal(entry.totalRequests, 4);
assert.equal(entry.successfulRequests, 3);
assert.equal(entry.successRate, 0.75);
assert.equal(entry.avgLatencyMs, 233);
assert.equal(entry.p50LatencyMs, 200);
assert.equal(entry.p95LatencyMs, 400);
assert.equal(entry.p99LatencyMs, 400);
assert.ok(entry.latencyStdDev > 0);
});
test("getModelLatencyStats falls back to all latencies when successful sample count is too small", async () => {
await usageHistory.saveRequestUsage({
provider: "fallback-provider",
model: "fallback-model",
success: true,
latencyMs: 100,
timestamp: new Date().toISOString(),
});
await usageHistory.saveRequestUsage({
provider: "fallback-provider",
model: "fallback-model",
success: false,
latencyMs: 500,
timestamp: new Date().toISOString(),
});
const stats = await usageHistory.getModelLatencyStats({
windowHours: 1,
minSamples: 2,
});
const entry = stats["fallback-provider/fallback-model"];
assert.ok(entry);
assert.equal(entry.successRate, 0.5);
assert.equal(entry.avgLatencyMs, 300);
assert.equal(entry.p50LatencyMs, 500);
});
test("getUsageStats aggregates totals, buckets, pending requests, and cost breakdowns", async () => {
await localDb.updatePricing({
"pricing-provider": {
"pricing-model": {
input: 1000,
cached: 100,
output: 2000,
reasoning: 3000,
cache_creation: 1500,
},
},
});
const connection = await providersDb.createProviderConnection({
provider: "pricing-provider",
authType: "apikey",
name: "Primary Account",
apiKey: "sk-test",
});
const recentTokens = {
input: 100,
output: 50,
cacheRead: 20,
cacheCreation: 10,
reasoning: 5,
};
const oldTokens = {
input: 40,
output: 10,
cacheRead: 0,
cacheCreation: 0,
reasoning: 0,
};
await usageHistory.saveRequestUsage({
provider: "pricing-provider",
model: "pricing-model",
connectionId: connection.id,
apiKeyId: "api-key-1",
apiKeyName: "Service Key",
tokens: recentTokens,
success: true,
latencyMs: 150,
timestamp: new Date().toISOString(),
});
await usageHistory.saveRequestUsage({
provider: "pricing-provider",
model: "pricing-model",
connectionId: connection.id,
apiKeyId: "api-key-1",
apiKeyName: "Service Key",
tokens: oldTokens,
success: true,
latencyMs: 80,
timestamp: new Date(Date.now() - 20 * 60 * 1000).toISOString(),
});
usageHistory.trackPendingRequest("pricing-model", "pricing-provider", connection.id, true);
usageHistory.trackPendingRequest("pricing-model", "pricing-provider", connection.id, true);
usageHistory.trackPendingRequest("pricing-model", "pricing-provider", connection.id, false);
const stats = await usageStats.getUsageStats();
const expectedCost =
(await calculateCost("pricing-provider", "pricing-model", recentTokens)) +
(await calculateCost("pricing-provider", "pricing-model", oldTokens));
assert.equal(stats.totalRequests, 2);
assert.equal(stats.totalPromptTokens, 140);
assert.equal(stats.totalCompletionTokens, 60);
assert.ok(Math.abs(stats.totalCost - expectedCost) < 1e-9);
assert.equal(stats.byProvider["pricing-provider"].requests, 2);
assert.equal(stats.byProvider["pricing-provider"].promptTokens, 140);
assert.equal(stats.byModel["pricing-model (pricing-provider)"].requests, 2);
const accountKey = "pricing-model (pricing-provider - Primary Account)";
assert.equal(stats.byAccount[accountKey].requests, 2);
assert.equal(stats.byAccount[accountKey].accountName, "Primary Account");
assert.equal(stats.byApiKey["Service Key (api-key-1)"].requests, 2);
assert.equal(stats.pending.byModel["pricing-model (pricing-provider)"], 1);
assert.equal(stats.pending.byAccount[connection.id]["pricing-model (pricing-provider)"], 1);
assert.deepEqual(stats.activeRequests, [
{
model: "pricing-model",
provider: "pricing-provider",
account: "Primary Account",
count: 1,
},
]);
assert.equal(stats.last10Minutes.length, 10);
const recentBucketTotal = stats.last10Minutes.reduce((sum, bucket) => sum + bucket.requests, 0);
assert.equal(recentBucketTotal, 1);
});
test("recent request summaries are generated from SQLite call logs", async () => {
const connection = await providersDb.createProviderConnection({
provider: "log-provider",
authType: "apikey",
name: "Named Account",
apiKey: "sk-test",
});
for (let i = 0; i < 205; i++) {
await callLogs.saveCallLog({
id: `log-${i}`,
timestamp: new Date(Date.now() + i).toISOString(),
method: "POST",
path: "/v1/chat/completions",
status: 200,
model: `model-${i}`,
provider: "log-provider",
connectionId: connection.id,
tokens: { input: i + 1, output: i + 2 },
requestBody: { index: i },
responseBody: { ok: true, index: i },
});
}
const recent = await usageHistory.getRecentLogs(3);
assert.equal(recent.length, 3);
assert.match(recent[0], /model-204/);
assert.match(recent[0], /LOG-PROVIDER/);
assert.match(recent[0], /Named Account/);
assert.match(recent[0], /205 \| 206 \| 200$/);
});