Files
OmniRoute/tests/unit/autoCombo/tieredRotation.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

240 lines
8.8 KiB
TypeScript

/**
* Tests for ScoreTierRotator and connectionDensity factor.
* Verifies that multi-connection providers surface in ranked candidates
* and that tiered rotation distributes traffic fairly.
*/
import { describe, it, expect, beforeEach, afterEach, vi } from "vitest";
import { selectProvider, type AutoComboConfig } from "../../../open-sse/services/autoCombo/engine";
import {
calculateFactors,
calculateScore,
DEFAULT_WEIGHTS,
scorePool,
type ProviderCandidate,
type ScoredProvider,
} from "../../../open-sse/services/autoCombo/scoring";
import { getTaskFitness } from "../../../open-sse/services/autoCombo/taskFitness";
import { resetDiversity } from "../../../open-sse/services/autoCombo/providerDiversity";
// Stub DB calls introduced by PR #3660 (Arena ELO / models.dev intelligence scoring).
// This file tests rotation logic, not intelligence scoring — the DB shouldn't be
// initialized during these unit tests, and the stub makes them fast and isolated.
vi.mock("../../../src/lib/db/modelIntelligence.ts", () => ({
getModelIntelligenceBySource: vi.fn(() => null),
setUserFitnessOverrideEntry: vi.fn(),
deleteUserFitnessOverrideEntry: vi.fn(),
}));
function makeCandidate(overrides: Partial<ProviderCandidate>): ProviderCandidate {
return {
provider: "unknown",
model: "unknown-model",
quotaRemaining: 100,
quotaTotal: 100,
circuitBreakerState: "CLOSED",
costPer1MTokens: 1,
p95LatencyMs: 1000,
latencyStdDev: 100,
errorRate: 0.01,
...overrides,
};
}
function makeConfig(name: string): AutoComboConfig {
return {
id: `test-${name}`,
name,
type: "auto",
candidatePool: [],
weights: { ...DEFAULT_WEIGHTS },
explorationRate: 0,
routerStrategy: "rules",
};
}
describe("Connection Density Factor", () => {
const baseCandidate = makeCandidate({ provider: "cerebras", model: "llama-70b" });
it("multi-connection provider scores higher than single-connection at same quality", () => {
const multiConn = makeCandidate({ provider: "cerebras", model: "llama-70b", connectionPoolSize: 43 });
const singleConn = makeCandidate({ provider: "anthropic", model: "claude-sonnet", connectionPoolSize: 1 });
const pool = [multiConn, singleConn];
const multiFactors = calculateFactors(multiConn, pool, "coding", getTaskFitness);
const singleFactors = calculateFactors(singleConn, pool, "coding", getTaskFitness);
const multiScore = calculateScore(multiFactors, DEFAULT_WEIGHTS);
const singleScore = calculateScore(singleFactors, DEFAULT_WEIGHTS);
expect(multiFactors.connectionDensity).toBe(1.0);
expect(singleFactors.connectionDensity).toBe(0.0);
expect(multiScore).toBeGreaterThan(singleScore);
});
it("density scales linearly from 0 to 10 connections, caps at 10+", () => {
const make = (size: number) => makeCandidate({ connectionPoolSize: size });
const sizes = [1, 2, 5, 10, 20, 43];
const densities = sizes.map((s) => {
const c = make(s);
const pool = [c];
return calculateFactors(c, pool, "coding", getTaskFitness).connectionDensity;
});
expect(densities[0]).toBeCloseTo(0.0, 5);
expect(densities[1]).toBeCloseTo(0.1, 5);
expect(densities[2]).toBeCloseTo(0.4, 5);
expect(densities[3]).toBeCloseTo(0.9, 5);
expect(densities[4]).toBe(1.0);
expect(densities[5]).toBe(1.0);
});
it("missing connectionPoolSize defaults to 1 (backward compat)", () => {
const candidate = makeCandidate({ provider: "x" });
const pool = [candidate];
const factors = calculateFactors(candidate, pool, "coding", getTaskFitness);
expect(factors.connectionDensity).toBe(0.0);
});
it("DEFAULT_WEIGHTS still sum to 1.0 after adding density", () => {
const sum = Object.values(DEFAULT_WEIGHTS).reduce((a, b) => a + b, 0);
expect(Math.abs(sum - 1.0)).toBeLessThan(0.01);
});
});
describe("Tiered Rotation in selectProvider", () => {
beforeEach(() => {
resetDiversity();
});
it("smart combo rotates within top tier across many requests", () => {
const topA = makeCandidate({ provider: "openai", model: "gpt-4o", quotaRemaining: 95 });
const topB = makeCandidate({ provider: "anthropic", model: "claude-opus", quotaRemaining: 90 });
const topC = makeCandidate({ provider: "google", model: "gemini-ultra", quotaRemaining: 88 });
const mid = makeCandidate({ provider: "mistral", model: "mistral-large", quotaRemaining: 70 });
const pool = [topA, topB, topC, mid];
const config = makeConfig("smart");
const seen = new Set<string>();
for (let i = 0; i < 50; i++) {
const result = selectProvider(config, pool, "coding");
seen.add(`${result.provider}/${result.model}`);
}
expect(seen.size).toBeGreaterThanOrEqual(2);
expect(seen.has("openai/gpt-4o") || seen.has("anthropic/claude-opus")).toBe(true);
});
it("cheap combo pulls from rest tier (lower scores) more often than smart", () => {
const top = makeCandidate({ provider: "openai", model: "gpt-4o", quotaRemaining: 100 });
const rest = makeCandidate({
provider: "cheap-provider",
model: "cheap-model",
quotaRemaining: 100,
costPer1MTokens: 0,
p95LatencyMs: 5000,
});
const pool = [top, rest];
const config = makeConfig("cheap");
const counts: Record<string, number> = {};
for (let i = 0; i < 200; i++) {
const result = selectProvider(config, pool, "coding");
counts[result.provider] = (counts[result.provider] ?? 0) + 1;
}
expect(counts["cheap-provider"]).toBeGreaterThan(0);
});
it("single-candidate pool always returns the same candidate", () => {
const only = makeCandidate({ provider: "only", model: "only-model" });
const config = makeConfig("smart");
for (let i = 0; i < 10; i++) {
const result = selectProvider(config, [only], "coding");
expect(result.provider).toBe("only");
expect(result.model).toBe("only-model");
}
});
});
describe("scorePool with connectionDensity", () => {
it("Cerebras with 43 keys ranks above single-connection providers of similar quality", () => {
const cerebras = makeCandidate({
provider: "cerebras",
model: "llama-3.1-70b",
connectionPoolSize: 43,
quotaRemaining: 100,
});
const anthropic = makeCandidate({
provider: "anthropic",
model: "claude-sonnet",
connectionPoolSize: 1,
quotaRemaining: 100,
});
const pool = [cerebras, anthropic];
const scored = scorePool(pool, "coding", DEFAULT_WEIGHTS, getTaskFitness);
expect(scored[0].provider).toBe("cerebras");
});
});
describe("Per-Connection Rotation", () => {
it("rotates across all 43 Cerebras connection IDs, not just one", () => {
const cerebrasCandidates: ProviderCandidate[] = Array.from({ length: 43 }, (_, i) =>
makeCandidate({
provider: "cerebras",
model: "llama-3.1-70b",
connectionId: `cerebras-conn-${i + 1}`,
})
);
const config = makeConfig("smart");
const seenConnections = new Set<string>();
for (let i = 0; i < 200; i++) {
const result = selectProvider(config, cerebrasCandidates, "coding");
if (result.connectionId) seenConnections.add(result.connectionId);
}
expect(seenConnections.size).toBeGreaterThanOrEqual(10);
});
it("different combos maintain independent round-robin state", () => {
const candidates: ProviderCandidate[] = Array.from({ length: 5 }, (_, i) =>
makeCandidate({ provider: "p", model: "m", connectionId: `c-${i}` })
);
const smartConfig = makeConfig("smart-A");
const fastConfig = makeConfig("fast-B");
for (let i = 0; i < 5; i++) {
selectProvider(smartConfig, candidates, "coding");
}
const smartResults: string[] = [];
for (let i = 0; i < 5; i++) {
const r = selectProvider(smartConfig, candidates, "coding");
if (r.connectionId) smartResults.push(r.connectionId);
}
for (let i = 0; i < 5; i++) {
selectProvider(fastConfig, candidates, "coding");
}
const fastResults: string[] = [];
for (let i = 0; i < 5; i++) {
const r = selectProvider(fastConfig, candidates, "coding");
if (r.connectionId) fastResults.push(r.connectionId);
}
expect(smartResults.length).toBe(5);
expect(fastResults.length).toBe(5);
expect(new Set(smartResults).size).toBeGreaterThan(1);
expect(new Set(fastResults).size).toBeGreaterThan(1);
});
it("tied-score candidates from same provider+model are all reachable", () => {
const candidates: ProviderCandidate[] = Array.from({ length: 5 }, (_, i) =>
makeCandidate({ provider: "free", model: "free-model", connectionId: `key-${i}` })
);
const config = makeConfig("smart");
const visited = new Set<string>();
for (let i = 0; i < 20; i++) {
const result = selectProvider(config, candidates, "coding");
if (result.connectionId) visited.add(result.connectionId);
}
expect(visited.size).toBeGreaterThan(1);
});
});