Files
OmniRoute/tests/unit/services/geminiRateLimitTracker.test.ts
Diego Rodrigues de Sa e Souza de60b4b171 Release v3.8.23
* chore(release): open v3.8.23 development cycle

* fix(anthropic): strip top_p when temperature is set to avoid 400 (#3691)

Integrated into release/v3.8.23

* fix(vertex): support Vertex AI Express-mode API keys (#3690)

Integrated into release/v3.8.23

* fix(stream): error on empty Claude SSE instead of synthetic success (#3689)

Integrated into release/v3.8.23

* fix(oauth): stop token-refresh invalidation loop + harden proxy resolution (#3692)

Integrated into release/v3.8.23

* docs: add FUNDING.yml and Support section to README (#3698)

Integrated into release/v3.8.23

* feat: gemini - handle known ratelimits (#3686)

Integrated into release/v3.8.23

* fix: stream combo fails over on empty content-filtered response (#3685) (#3702)

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(antigravity): preserve gemini-3.1-pro high/low budget tiers (#3696) (#3703)

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(auto-combo): add auto-updating model intelligence scoring (#3660)

Integrated into release/v3.8.23

* fix(gemini): context-mode fallback for signatureless tool calls (#3688) (#3704)

* chore(quality-gate): reconcile file-size baseline (27 files + providerLimits.ts) (#3705)

* feat(vertex): dynamic model discovery via Generative Language models API (#3712)

Integrated into release/v3.8.23. Vertex dynamic model discovery — surfaces image models (imagen-*, gemini-*-image), embeddings and audio from the live Generative Language catalog, with cached→static fallback and the shared parseGeminiModelsList helper. Validated: parser test 5/5, typecheck:core clean.

* fix(combo): gate reasoning token buffer (#3700)

Integrated into release/v3.8.23. Makes the #3588 reasoning token buffer safe and configurable: only inflates max_tokens when the model has a known, non-default output cap and the buffered value fits inside it; otherwise preserves/clamps the client limit. Adds the reasoningTokenBufferEnabled kill switch (default ON). Validated: combo-routing-engine 81/81, combo-config 25/25, combo-quality-validator-reasoning 12/12, phase1f 10/10, typecheck:core clean.

* refactor(#3501): god-component Phase 1g-1j — client 4062→3408 LOC (-654) (#3717)

Phase 1g-1j of #3501: client 4062→3408 LOC. Pure extraction (ProviderPlaygroundPanel, useCommandCodeAuth, useExternalLinkFlow+ExternalLinkModal, useAuthFileHandlers) + loadConnProxies ReferenceError fix + phase1f test path fix.

Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>

* refactor(#3501): god-component Phase 1k-1m — client 3408→2553 LOC (-855) (#3721)

Phase 1k-1m of #3501: client 3408→2553 LOC. Pure extraction (useModelImportHandlers+ImportProgressModal, useModelVisibilityHandlers, ProviderModelsSection).

Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>

* docs(changelog): restore #3590 bullet lost on the v3.8.20 release branch

The fix itself reached main pre-tag via cherry-pick #3591, but its changelog
bullet (commit e33fdd4ab) only ever existed on release/v3.8.20 after the
squash-merge. Restored under [3.8.20] per the 2026-06-12 release-branch
leftover audit (_tasks/release-audit/release-leftovers-audit-2026-06-12.md).

* fix(kiro): resolve quota for IAM Identity Center accounts missing a profileArn (#3722)

Integrated into release/v3.8.23

* refactor(#3501): god-component Phase 1n-1s — client 2553→1376 LOC (-1177) (#3725)

Phase 1n-1s of #3501: client 2553→1376 LOC. Pure extraction (ConnectionsListPanel, ConnectionsHeaderToolbar, ZedImportCard, BatchTestResultsModal, AdaptaTutorialModal, useApiKeySave + helpers).

Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>

* feat(model-lockout): settings UI, backend integration, error classification, and success-decay recovery (#3629)

Integrated into release/v3.8.23

* refactor(#3501): god-component Phase 1t — client 1376→781 LOC (≤800 TARGET REACHED ) (#3727)

Phase 1t of #3501: client 1376→781 LOC (≤800 reached). Original god-component 12,882→781 (−94%).

Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>

* fix: bundle @omniroute/opencode-plugin inside omniroute + add 'setup opencode' CLI command (#3726)

Integrated into release/v3.8.23

* feat(vertex): self-tracked USD spend since account added (#3724)

Integrated into release/v3.8.23

* fix(qwen-web): migrate to v2 chat API with full cookie-jar replay (#3288) (#3723)

Integrated into release/v3.8.23

* fix(sse): make safeLogEvents async — 'await' in a sync function broke every chatHelpers import

#3692 added a lazy 'await import(proxyEgress)' for egress-IP visibility inside
safeLogEvents, which is a sync function — an ES syntax error. It went unnoticed
because typecheck:core does not cover src/sse and no test in the merge gates
loaded chatHelpers via tsx; any consumer that did (chat-context-relay and
chat-route-coverage suites, integration harnesses) failed at module load with
'await can only be used inside an async function'.

safeLogEvents is fire-and-forget logging with an outer try/catch, so making it
async (and 'void'-ing the single chat.ts call site) preserves behavior exactly.

Validation: tests/unit/chat-context-relay.test.ts + chat-route-coverage.test.ts
went from failing-at-load to green (+14 tests destravados).

* fix(sse): remove cross-provider credential leak in emergency fallback + combo/proxy audit fixes (#3699)

Integrated into release/v3.8.23

* fix(executors): inject MiMoCode anti-abuse marker so free endpoint stops 403ing (#3728)

Integrated into release/v3.8.23

* fix(dashboard): repair "Test all models" — toast crash, status icons, auto-hide (#3729)

Integrated into release/v3.8.23

* chore(deps): bump actions/upload-artifact from 4 to 7 (#3735)

Integrated into release/v3.8.23 — aligns upload-artifact to v7 (already used across ci.yml).

* chore(deps): bump actions/cache from 4 to 5 (#3734)

Integrated into release/v3.8.23 — actions/cache v4→v5.

* chore(deps): bump actions/download-artifact from 4 to 8 (#3733)

Integrated into release/v3.8.23 — download-artifact v4→v8.

* feat(fallback): add OMNIROUTE_EMERGENCY_FALLBACK env switch (#3741)

Adds an OMNIROUTE_EMERGENCY_FALLBACK env switch to disable the emergency budget-exhaustion fallback (reroute to free nvidia/gpt-oss-120b). Default unchanged (enabled). Closes #3739, related #2879.

Integrated into release/v3.8.23.

* i18n: comprehensive zh-CN translation improvements (#3736)

Aligns zh-CN to en (hundreds of entries), translates batch-action labels + settings sidebar menu, adds categoryConfig/endpointTokenSaver keys, resolves __MISSING__ stubs. Sidebar/SidebarTab hardcoded strings replaced with t(). en.json purely additive (8 new sidebar.* keys, 0 removed); cli-i18n gate green.

Integrated into release/v3.8.23.

* chore(release): v3.8.23 — 2026-06-12

- CHANGELOG: complete v3.8.23 section (28 bullets, 27 commits)
- fix(webdav): resolve promise on writeStream finish, not req end — eliminates
  intermittent 500 on PUT update (writeStream may not have flushed at rename time)
- test(autoCombo): stub DB calls from PR #3660 in tieredRotation.test.ts to prevent
  5s timeout in vitest (getModelIntelligenceBySource DB init path)
- chore(env-sync): add XDG_DATA_HOME + OMNIROUTE_OPENCODE_PLUGIN_DIR to IGNORE_FROM_CODE
  allowlist (introduced by PR #3726 setup-open-code.mjs, not OmniRoute config vars)
- chore(cli): regenerated bin/cli/api-commands/*.mjs (7 new, 27 updated)

* fix(model-family): fallback lookup also tries bare model name with dots

getNextFamilyFallback normalized dots-to-hyphens ("gemini-3.1-pro-high" →
"gemini-3-1-pro-high") but MODEL_FAMILIES keys use the literal dot form. The
lookup always missed, returning null for any model whose dots are part of the
name rather than a version separator.

Fallback: try MODEL_FAMILIES[lookupKey] ?? MODEL_FAMILIES[bareModel] so both
naming conventions are covered. Fixes T30 test (pre-existing since v3.8.22).

* feat: expose API key cost drilldown + quota % used (#3742)

Adds all-time USD cost per API key in the API Key Manager, a per-key deep-link into the Cost Explorer (filtered + grouped by model), URL-param hydration of range/groupBy/apiKeyIds, and a '% used' quota display. Review adjustments: extracted URL-param parsers to a tested module (Rule #18), i18n'd the new strings (en + zh-CN), dropped the redundant webdav-handler entry already on release.

Integrated into release/v3.8.23.

* feat: add provider display modes — All / Configured / Compact (#3743)

Replaces the Providers page configured-only toggle with All/Configured/Compact display modes (Compact = flat deduped grid, no-auth last). Persists the preference and migrates the legacy localStorage key. Rebased onto release/v3.8.23.

Integrated into release/v3.8.23.

* fix(cache): scope semantic-cache signature to API key (#3740)

Adds the api_key_id dimension to generateSignature's SHA-256 hash so two callers with different API keys never receive each other's cached responses. Threads apiKeyId through checkSemanticCache + both write sites; migration 098 clears pre-existing key-less entries; unauthenticated requests stay isolated from keyed ones. 3 TDD tests.

Integrated into release/v3.8.23.

* fix(responses): apply OpenAI Responses API stream=false spec default (#3708)

resolveStreamFlag now applies the stream=false-when-omitted default for sourceFormat=openai-responses (same as the existing claude path), so spec-compliant /v1/responses upstreams that return JSON no longer fall through to the wildcard-Accept heuristic and trigger STREAM_EARLY_EOF / 502. Codex CLI (stream:true) and explicit text/event-stream clients unaffected.

Integrated into release/v3.8.23.

* chore(release): reconcile CI gates for v3.8.23

- file-size baseline: re-freeze 8 files grown by PRs #3742/#3743/#3740
  (cost drilldown, provider display modes, cache key isolation)
- ARCHITECTURE.md: update executor count 55→60 (check:docs-counts drift)
- .env.example: add OMNIROUTE_EMERGENCY_FALLBACK (#3741, env-doc-sync)
- CHANGELOG: add formatted bullets for #3742, #3743, #3708, #3740,
  model-family-fallback fix; remove duplicate raw ### Fixed section

* test: restore assert count to satisfy check:test-masking gate

Three test files had net assertion removals after behavior-changing PRs:
- chatcore-translation-paths: emergency fallback moved to routing layer
  (#3699) — add body error assertion + model-name guard
- executor-vertex-extended: non-JSON is now Express API key (#3690) —
  add projects/-path guard to the express-key URL test
- stream-utils: empty streams now emit error (#3685) — add code/message/
  status/completePayload guards to both passthrough and translate variants

All new assertions are meaningful (code enum value, 5xx range, non-empty
message, onComplete must-not-fire contract).

* fix(ci): move rtl-logical-classes test to ui/ so vitest:ui runner collects it

---------

Co-authored-by: Felipe Almeman <4226997+zhiru@users.noreply.github.com>
Co-authored-by: NOXX - Commiter <artur1992123@mail.ru>
Co-authored-by: Nick Sullivan <142708+TechNickAI@users.noreply.github.com>
Co-authored-by: Markus Hartung <mail@hartmark.se>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: PizzaV <103120356+pizzav-xyz@users.noreply.github.com>
Co-authored-by: Randi <55005611+rdself@users.noreply.github.com>
Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>
Co-authored-by: Chewji <126886556+Chewji9875@users.noreply.github.com>
Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com>
Co-authored-by: Felipe Sartori <felipesartori.ti@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Zois Pagoulatos <zpagoulatos@hotmail.com>
Co-authored-by: sdfsdfw2 <167810361+sdfsdfw2@users.noreply.github.com>
Co-authored-by: Witroch4 <witalo_rocha@hotmail.com>
2026-06-12 23:49:22 -03:00

324 lines
13 KiB
TypeScript

import test from "node:test";
import assert from "node:assert/strict";
import {
getModelRpd,
getModelRpm,
incrementRequestCount,
getDailyRequestCount,
getMinuteRequestCount,
isRpdExhausted,
isRpmExhausted,
resetCounters,
} from "../../../open-sse/services/geminiRateLimitTracker.ts";
test.beforeEach(() => {
resetCounters();
});
// ── getModelRpd ──────────────────────────────────────────────────────────────
test("getModelRpd returns known RPD for exact model match", () => {
assert.equal(getModelRpd("gemini-2.5-flash"), 20);
});
test("getModelRpd returns known RPD for model with gemini/ prefix", () => {
assert.equal(getModelRpd("gemini/gemini-2.5-flash"), 20);
});
test("getModelRpd returns 0 for model with zero RPD (Gemini 2.5 Pro)", () => {
assert.equal(getModelRpd("gemini-2.5-pro"), 0);
});
test("getModelRpd returns 0 for unknown model", () => {
assert.equal(getModelRpd("gemini/fake-model-not-in-list"), 0);
});
test("getModelRpd returns 0 for empty string", () => {
assert.equal(getModelRpd(""), 0);
});
test("getModelRpd matches gemma-4-31b-it via suffix fallback", () => {
// The JSON has "gemma-4-31b-it", and callers may pass "gemma-4-31b-it"
assert.equal(getModelRpd("gemma-4-31b-it"), 1500);
});
test("getModelRpd strips gemma- prefix correctly for gemma models", () => {
// stripModelPrefix("gemini/gemma-4-31b-it") → "gemma-4-31b-it"
assert.equal(getModelRpd("gemini/gemma-4-31b-it"), 1500);
});
test("getModelRpd handles image-generation models (no RPM value, -1)", () => {
// RPD is 25 for imagen models; RPM is -1 in the JSON
assert.equal(getModelRpd("imagen-4-generate"), 25);
});
test("getModelRpd handles models with unlimited RPD (-1)", () => {
// gemini-3.5-live-translate has rpd: -1
assert.equal(getModelRpd("gemini-3.5-live-translate"), 0);
});
test("getModelRpd returns 0 for null input", () => {
assert.equal(getModelRpd(null as unknown as string), 0);
});
test("getModelRpd returns 0 for undefined input", () => {
assert.equal(getModelRpd(undefined as unknown as string), 0);
});
// ── incrementRequestCount / getDailyRequestCount ─────────────────────────────
test("incrementRequestCount starts at 1 for first request", () => {
incrementRequestCount("gemini-2.5-flash");
assert.equal(getDailyRequestCount("gemini-2.5-flash"), 1);
});
test("incrementRequestCount increments sequentially", () => {
incrementRequestCount("gemini-2.5-flash");
incrementRequestCount("gemini-2.5-flash");
incrementRequestCount("gemini-2.5-flash");
assert.equal(getDailyRequestCount("gemini-2.5-flash"), 3);
});
test("incrementRequestCount treats gemini/ prefix and bare name as same model", () => {
incrementRequestCount("gemini-2.5-flash");
incrementRequestCount("gemini/gemini-2.5-flash");
assert.equal(getDailyRequestCount("gemini-2.5-flash"), 2);
assert.equal(getDailyRequestCount("gemini/gemini-2.5-flash"), 2);
});
test("models have independent counters", () => {
incrementRequestCount("gemini-2.5-flash");
incrementRequestCount("gemini-2.5-flash");
incrementRequestCount("gemma-4-31b-it");
assert.equal(getDailyRequestCount("gemini-2.5-flash"), 2);
assert.equal(getDailyRequestCount("gemma-4-31b-it"), 1);
});
test("getDailyRequestCount returns 0 for model with no requests", () => {
assert.equal(getDailyRequestCount("gemini-2.5-flash"), 0);
});
test("incrementRequestCount does nothing for empty model ID", () => {
incrementRequestCount("");
assert.equal(getDailyRequestCount("gemini-2.5-flash"), 0);
});
test("resetCounters clears all state between tests", () => {
incrementRequestCount("gemini-2.5-flash");
incrementRequestCount("gemma-4-31b-it");
resetCounters();
assert.equal(getDailyRequestCount("gemini-2.5-flash"), 0);
assert.equal(getDailyRequestCount("gemma-4-31b-it"), 0);
});
// ── isRpdExhausted ───────────────────────────────────────────────────────────
test("isRpdExhausted returns false when count is below RPD limit", () => {
// gemini-2.5-flash has RPD=20
for (let i = 0; i < 19; i++) incrementRequestCount("gemini-2.5-flash");
assert.equal(isRpdExhausted("gemini-2.5-flash"), false);
});
test("isRpdExhausted returns true when count equals RPD limit", () => {
// gemini-2.5-flash has RPD=20
for (let i = 0; i < 20; i++) incrementRequestCount("gemini-2.5-flash");
assert.equal(isRpdExhausted("gemini-2.5-flash"), true);
});
test("isRpdExhausted returns true when count exceeds RPD limit", () => {
for (let i = 0; i < 25; i++) incrementRequestCount("gemini-2.5-flash");
assert.equal(isRpdExhausted("gemini-2.5-flash"), true);
});
test("isRpdExhausted returns false for model with RPD=0", () => {
// gemini-2.5-pro has rpd=0
incrementRequestCount("gemini-2.5-pro");
assert.equal(isRpdExhausted("gemini-2.5-pro"), false);
});
test("isRpdExhausted returns false for unknown model", () => {
incrementRequestCount("gemini/unknown-model");
assert.equal(isRpdExhausted("gemini/unknown-model"), false);
});
test("isRpdExhausted returns false for model with unlimited RPD (-1, no data)", () => {
// gemini-3.5-live-translate has rpd: -1
incrementRequestCount("gemini-3.5-live-translate");
assert.equal(isRpdExhausted("gemini-3.5-live-translate"), false);
});
test("isRpdExhausted works with gemini/ prefix for the model", () => {
for (let i = 0; i < 20; i++) incrementRequestCount("gemini/gemini-2.5-flash");
assert.equal(isRpdExhausted("gemini/gemini-2.5-flash"), true);
});
// ── Integration: Gemma 4 RPM scenario ────────────────────────────────────────
test("Gemma 4: 15 RPM hits never trigger quota_exhausted (RPD=1500)", () => {
// Gemma 4 has RPD=1500, so 15 RPM hits should not trigger RPD exhaustion
for (let i = 0; i < 15; i++) incrementRequestCount("gemini/gemma-4-31b-it");
assert.equal(isRpdExhausted("gemini/gemma-4-31b-it"), false);
assert.equal(getDailyRequestCount("gemini/gemma-4-31b-it"), 15);
});
test("Gemma 4: RPD exhaustion requires 1500 requests", () => {
for (let i = 0; i < 1499; i++) incrementRequestCount("gemini/gemma-4-31b-it");
assert.equal(isRpdExhausted("gemini/gemma-4-31b-it"), false);
incrementRequestCount("gemini/gemma-4-31b-it");
assert.equal(isRpdExhausted("gemini/gemma-4-31b-it"), true);
});
// ── Integration: Gemini 2.5 Flash RPD scenario ───────────────────────────────
test("Gemini 2.5 Flash: first 19 requests do NOT exhaust RPD, 20th does", () => {
for (let i = 0; i < 19; i++) incrementRequestCount("gemini-2.5-flash");
assert.equal(isRpdExhausted("gemini-2.5-flash"), false, "19 requests < 20 RPD");
incrementRequestCount("gemini-2.5-flash");
assert.equal(isRpdExhausted("gemini-2.5-flash"), true, "20 requests = 20 RPD");
});
test("Gemini 2.5 Flash: excess requests stay exhausted", () => {
for (let i = 0; i < 22; i++) incrementRequestCount("gemini-2.5-flash");
assert.equal(isRpdExhausted("gemini-2.5-flash"), true);
assert.equal(getDailyRequestCount("gemini-2.5-flash"), 22);
});
// ── getModelRpm ───────────────────────────────────────────────────────────────
test("getModelRpm returns known RPM for exact model match", () => {
assert.equal(getModelRpm("gemini-2.5-flash"), 5);
});
test("getModelRpm returns known RPM for model with gemini/ prefix", () => {
assert.equal(getModelRpm("gemini/gemini-2.5-flash"), 5);
});
test("getModelRpm returns 0 for model with zero RPM", () => {
assert.equal(getModelRpm("gemini-2.5-pro"), 0);
});
test("getModelRpm returns 0 for unknown model", () => {
assert.equal(getModelRpm("gemini/fake-model-not-in-list"), 0);
});
test("getModelRpm returns 0 for empty string", () => {
assert.equal(getModelRpm(""), 0);
});
test("getModelRpm returns 0 for models with RPM=-1 (imagen)", () => {
assert.equal(getModelRpm("imagen-4-generate"), 0);
});
test("getModelRpm returns 0 for null input", () => {
assert.equal(getModelRpm(null as unknown as string), 0);
});
// ── incrementMinuteRequestCount / getMinuteRequestCount ───────────────────────
test("getMinuteRequestCount returns 0 before first request", () => {
assert.equal(getMinuteRequestCount("gemini-2.5-flash"), 0);
});
test("incrementMinuteRequestCount starts at 1", () => {
incrementRequestCount("gemini-2.5-flash");
assert.equal(getMinuteRequestCount("gemini-2.5-flash"), 1);
});
test("incrementMinuteRequestCount increments with each call", () => {
incrementRequestCount("gemini-2.5-flash");
incrementRequestCount("gemini-2.5-flash");
incrementRequestCount("gemini-2.5-flash");
assert.equal(getMinuteRequestCount("gemini-2.5-flash"), 3);
});
test("incrementMinuteRequestCount normalizes gemini/ prefix", () => {
incrementRequestCount("gemini-2.5-flash");
incrementRequestCount("gemini/gemini-2.5-flash");
assert.equal(getMinuteRequestCount("gemini-2.5-flash"), 2);
});
test("minute counters are independent per model", () => {
incrementRequestCount("gemini-2.5-flash");
incrementRequestCount("gemini-2.5-flash");
incrementRequestCount("gemma-4-31b-it");
assert.equal(getMinuteRequestCount("gemini-2.5-flash"), 2);
assert.equal(getMinuteRequestCount("gemma-4-31b-it"), 1);
});
test("incrementRequestCount does nothing for empty model ID", () => {
incrementRequestCount("");
assert.equal(getMinuteRequestCount("gemini-2.5-flash"), 0);
});
test("resetCounters clears minute windows", () => {
incrementRequestCount("gemini-2.5-flash");
incrementRequestCount("gemma-4-31b-it");
resetCounters();
assert.equal(getMinuteRequestCount("gemini-2.5-flash"), 0);
assert.equal(getMinuteRequestCount("gemma-4-31b-it"), 0);
});
// ── isRpmExhausted ────────────────────────────────────────────────────────────
test("isRpmExhausted returns false below RPM limit", () => {
// gemini-2.5-flash has RPM=5
for (let i = 0; i < 4; i++) incrementRequestCount("gemini-2.5-flash");
assert.equal(isRpmExhausted("gemini-2.5-flash"), false);
});
test("isRpmExhausted returns true at RPM limit", () => {
for (let i = 0; i < 5; i++) incrementRequestCount("gemini-2.5-flash");
assert.equal(isRpmExhausted("gemini-2.5-flash"), true);
});
test("isRpmExhausted returns true above RPM limit", () => {
for (let i = 0; i < 8; i++) incrementRequestCount("gemini-2.5-flash");
assert.equal(isRpmExhausted("gemini-2.5-flash"), true);
});
test("isRpmExhausted returns false for model with RPM=0", () => {
incrementRequestCount("gemini-2.5-pro");
assert.equal(isRpmExhausted("gemini-2.5-pro"), false);
});
test("isRpmExhausted returns false for unknown model", () => {
incrementRequestCount("gemini/unknown-model");
assert.equal(isRpmExhausted("gemini/unknown-model"), false);
});
test("isRpmExhausted returns false for model with RPM=-1 (imagen)", () => {
incrementRequestCount("imagen-4-generate");
assert.equal(isRpmExhausted("imagen-4-generate"), false);
});
test("isRpmExhausted works with gemini/ prefix", () => {
for (let i = 0; i < 5; i++) incrementRequestCount("gemini/gemini-2.5-flash");
assert.equal(isRpmExhausted("gemini/gemini-2.5-flash"), true);
});
// ── Integration: RPM + RPD work independently ─────────────────────────────────
test("RPM and RPD limits are tracked independently", () => {
// Gemma 4: RPM=15, RPD=1500
// After 15 requests, RPM is exhausted but RPD is not
for (let i = 0; i < 15; i++) incrementRequestCount("gemini/gemma-4-31b-it");
assert.equal(isRpmExhausted("gemini/gemma-4-31b-it"), true);
assert.equal(isRpdExhausted("gemini/gemma-4-31b-it"), false);
});
test("Gemini 2.5 Flash: RPM=5 always hits before RPD=20", () => {
// After 5 requests, RPM is exhausted; after 20, RPD is exhausted
for (let i = 0; i < 5; i++) incrementRequestCount("gemini-2.5-flash");
assert.equal(isRpmExhausted("gemini-2.5-flash"), true);
assert.equal(isRpdExhausted("gemini-2.5-flash"), false);
incrementRequestCount("gemini-2.5-flash"); // 6
incrementRequestCount("gemini-2.5-flash"); // 7
incrementRequestCount("gemini-2.5-flash"); // 8
// Still at RPD=8 which is < 20
assert.equal(isRpdExhausted("gemini-2.5-flash"), false);
});