Files
OmniRoute/tests/unit/model-intelligence-db.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

444 lines
14 KiB
TypeScript

/**
* Unit tests for src/lib/db/modelIntelligence.ts
*
* Uses the project's own DB infrastructure (core.ts getDbInstance)
* with a temp DATA_DIR. Follows the Node.js native test runner pattern.
*/
import { describe, it, beforeEach } 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-mi-test-"),
);
process.env.DATA_DIR = TEST_DATA_DIR;
const core = await import("../../src/lib/db/core.ts");
const mi = await import("../../src/lib/db/modelIntelligence.ts");
function resetStorage(): void {
core.resetDbInstance();
try {
if (fs.existsSync(TEST_DATA_DIR)) {
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
}
} catch { /* EBUSY — ignore */ }
fs.mkdirSync(TEST_DATA_DIR, { recursive: true });
}
function insertEntry(
model: string,
source: string,
category: string,
score: number,
opts: {
eloRaw?: number | null;
confidence?: string | null;
expiresAt?: string | null;
} = {},
): void {
const db = core.getDbInstance();
db.prepare(
`INSERT OR REPLACE INTO model_intelligence
(model, source, category, score, elo_raw, confidence, synced_at, expires_at)
VALUES (?, ?, ?, ?, ?, ?, datetime('now'), ?)`,
).run(
model,
source,
category,
score,
opts.eloRaw ?? null,
opts.confidence ?? null,
opts.expiresAt ?? null,
);
}
// ─── Tests ───────────────────────────────────────────────
describe("upsertModelIntelligence", () => {
beforeEach(() => { resetStorage(); });
it("inserts a new entry", () => {
mi.upsertModelIntelligence({
model: "claude-sonnet",
source: "arena_elo",
category: "coding",
score: 0.92,
eloRaw: 1350,
confidence: "high",
expiresAt: null,
});
const entry = mi.getModelIntelligenceBySource("claude-sonnet", "arena_elo", "coding");
assert.ok(entry, "Row should exist after upsert");
assert.strictEqual(entry.model, "claude-sonnet");
assert.strictEqual(entry.source, "arena_elo");
assert.strictEqual(entry.category, "coding");
assert.strictEqual(entry.score, 0.92);
assert.strictEqual(entry.eloRaw, 1350);
assert.strictEqual(entry.confidence, "high");
assert.ok(entry.syncedAt, "synced_at should be auto-populated");
});
it("updates an existing entry (INSERT OR REPLACE)", () => {
insertEntry("gpt-4o", "arena_elo", "coding", 0.85);
mi.upsertModelIntelligence({
model: "gpt-4o",
source: "arena_elo",
category: "coding",
score: 0.90,
eloRaw: 1400,
confidence: "high",
expiresAt: null,
});
const entry = mi.getModelIntelligenceBySource("gpt-4o", "arena_elo", "coding");
assert.ok(entry);
assert.strictEqual(entry.score, 0.90);
assert.strictEqual(entry.eloRaw, 1400);
});
});
describe("getModelIntelligence", () => {
beforeEach(() => { resetStorage(); });
it("returns user_override when all three sources exist (highest priority)", () => {
insertEntry("claude-sonnet", "models_dev_tier", "coding", 0.75);
insertEntry("claude-sonnet", "arena_elo", "coding", 0.88);
insertEntry("claude-sonnet", "user_override", "coding", 0.99);
const entry = mi.getModelIntelligence("claude-sonnet", "coding");
assert.ok(entry);
assert.strictEqual(entry.source, "user_override");
assert.strictEqual(entry.score, 0.99);
});
it("returns arena_elo when no user_override exists", () => {
insertEntry("gpt-4o", "arena_elo", "coding", 0.87);
insertEntry("gpt-4o", "models_dev_tier", "coding", 0.70);
const entry = mi.getModelIntelligence("gpt-4o", "coding");
assert.ok(entry);
assert.strictEqual(entry.source, "arena_elo");
assert.strictEqual(entry.score, 0.87);
});
it("returns models_dev_tier when only that source exists", () => {
insertEntry("llama-4", "models_dev_tier", "coding", 0.65);
const entry = mi.getModelIntelligence("llama-4", "coding");
assert.ok(entry);
assert.strictEqual(entry.source, "models_dev_tier");
assert.strictEqual(entry.score, 0.65);
});
it("returns null when no entry exists", () => {
const entry = mi.getModelIntelligence("nonexistent-model", "coding");
assert.strictEqual(entry, null);
});
it("skips expired entries and falls through to next source", () => {
insertEntry("gemini-pro", "arena_elo", "coding", 0.82, {
expiresAt: "2000-01-01T00:00:00Z",
});
insertEntry("gemini-pro", "models_dev_tier", "coding", 0.70);
const entry = mi.getModelIntelligence("gemini-pro", "coding");
assert.ok(entry);
assert.strictEqual(entry.source, "models_dev_tier");
});
it("returns null when all entries for a model+category are expired", () => {
insertEntry("expired-model", "arena_elo", "coding", 0.80, {
expiresAt: "2000-01-01T00:00:00Z",
});
const entry = mi.getModelIntelligence("expired-model", "coding");
assert.strictEqual(entry, null);
});
it("model names require exact match (case-sensitive in DB)", () => {
insertEntry("Claude-Sonnet", "arena_elo", "coding", 0.90);
const exact = mi.getModelIntelligence("Claude-Sonnet", "coding");
assert.ok(exact);
const different = mi.getModelIntelligence("claude-sonnet", "coding");
assert.strictEqual(different, null);
});
});
describe("getModelIntelligenceBySource", () => {
beforeEach(() => { resetStorage(); });
it("returns a specific source entry", () => {
insertEntry("claude-sonnet", "arena_elo", "coding", 0.88);
insertEntry("claude-sonnet", "user_override", "coding", 0.99);
const entry = mi.getModelIntelligenceBySource("claude-sonnet", "arena_elo", "coding");
assert.ok(entry);
assert.strictEqual(entry.source, "arena_elo");
assert.strictEqual(entry.score, 0.88);
});
it("returns null when the specific source does not exist", () => {
insertEntry("claude-sonnet", "arena_elo", "coding", 0.88);
const entry = mi.getModelIntelligenceBySource("claude-sonnet", "user_override", "coding");
assert.strictEqual(entry, null);
});
it("returns null when no entries exist at all", () => {
const entry = mi.getModelIntelligenceBySource("nonexistent", "arena_elo", "coding");
assert.strictEqual(entry, null);
});
});
describe("deleteModelIntelligence", () => {
beforeEach(() => { resetStorage(); });
it("deletes an entry and returns true", () => {
insertEntry("gpt-4o", "arena_elo", "coding", 0.87);
const deleted = mi.deleteModelIntelligence("gpt-4o", "arena_elo", "coding");
assert.strictEqual(deleted, true);
const entry = mi.getModelIntelligenceBySource("gpt-4o", "arena_elo", "coding");
assert.strictEqual(entry, null);
});
it("returns false when entry does not exist", () => {
const deleted = mi.deleteModelIntelligence("nonexistent", "arena_elo", "coding");
assert.strictEqual(deleted, false);
});
});
describe("deleteExpiredIntelligence", () => {
beforeEach(() => { resetStorage(); });
it("deletes only expired entries leaving valid ones", () => {
insertEntry("old-model", "arena_elo", "coding", 0.7, {
expiresAt: "2000-01-01T00:00:00Z",
});
insertEntry("fresh-model", "arena_elo", "coding", 0.9, {
expiresAt: "2099-12-31T23:59:59Z",
});
insertEntry("permanent-model", "user_override", "coding", 0.95);
const deleted = mi.deleteExpiredIntelligence();
assert.strictEqual(deleted, 1);
const remaining = mi.listModelIntelligence();
assert.strictEqual(remaining.length, 2);
});
it("deletes expired entries for a specific source only", () => {
insertEntry("old-arena", "arena_elo", "coding", 0.7, {
expiresAt: "2000-01-01T00:00:00Z",
});
insertEntry("old-tier", "models_dev_tier", "coding", 0.5, {
expiresAt: "2000-01-01T00:00:00Z",
});
const deleted = mi.deleteExpiredIntelligence("arena_elo");
assert.strictEqual(deleted, 1);
const remaining = mi.listModelIntelligence();
assert.strictEqual(remaining.length, 1);
assert.strictEqual(remaining[0].source, "models_dev_tier");
});
it("returns 0 when no expired entries exist", () => {
insertEntry("fresh-model", "arena_elo", "coding", 0.9, {
expiresAt: "2099-12-31T23:59:59Z",
});
const deleted = mi.deleteExpiredIntelligence();
assert.strictEqual(deleted, 0);
});
});
describe("listModelIntelligence", () => {
beforeEach(() => { resetStorage(); });
it("lists all entries when no filters provided", () => {
insertEntry("model-a", "arena_elo", "coding", 0.8);
insertEntry("model-b", "arena_elo", "review", 0.75);
insertEntry("model-c", "user_override", "coding", 0.95);
const entries = mi.listModelIntelligence();
assert.strictEqual(entries.length, 3);
});
it("filters by source", () => {
insertEntry("model-a", "arena_elo", "coding", 0.8);
insertEntry("model-b", "user_override", "coding", 0.95);
insertEntry("model-c", "models_dev_tier", "coding", 0.6);
const entries = mi.listModelIntelligence({ source: "arena_elo" });
assert.strictEqual(entries.length, 1);
assert.strictEqual(entries[0].source, "arena_elo");
});
it("filters by category", () => {
insertEntry("model-a", "arena_elo", "coding", 0.8);
insertEntry("model-b", "arena_elo", "review", 0.75);
insertEntry("model-c", "arena_elo", "documentation", 0.7);
const entries = mi.listModelIntelligence({ category: "review" });
assert.strictEqual(entries.length, 1);
assert.strictEqual(entries[0].category, "review");
});
it("filters by both source and category", () => {
insertEntry("model-a", "arena_elo", "coding", 0.8);
insertEntry("model-b", "arena_elo", "review", 0.75);
insertEntry("model-c", "user_override", "coding", 0.95);
const entries = mi.listModelIntelligence({ source: "arena_elo", category: "coding" });
assert.strictEqual(entries.length, 1);
assert.strictEqual(entries[0].model, "model-a");
});
it("returns empty array for empty table", () => {
const entries = mi.listModelIntelligence();
assert.ok(Array.isArray(entries));
assert.strictEqual(entries.length, 0);
});
});
describe("bulkUpsertModelIntelligence", () => {
beforeEach(() => { resetStorage(); });
it("bulk inserts multiple entries", () => {
const count = mi.bulkUpsertModelIntelligence([
{ model: "model-a", source: "arena_elo", category: "coding", score: 0.80, eloRaw: 1300, confidence: "high", expiresAt: "2099-12-31T23:59:59Z" },
{ model: "model-b", source: "arena_elo", category: "coding", score: 0.70, eloRaw: 1200, confidence: "medium", expiresAt: "2099-12-31T23:59:59Z" },
{ model: "model-c", source: "arena_elo", category: "review", score: 0.85, eloRaw: 1350, confidence: "high", expiresAt: "2099-12-31T23:59:59Z" },
]);
assert.strictEqual(count, 3);
const entries = mi.listModelIntelligence();
assert.strictEqual(entries.length, 3);
});
it("returns 0 for empty input array", () => {
const count = mi.bulkUpsertModelIntelligence([]);
assert.strictEqual(count, 0);
});
it("replaces existing entries on conflict (INSERT OR REPLACE)", () => {
insertEntry("model-a", "arena_elo", "coding", 0.70);
mi.bulkUpsertModelIntelligence([
{ model: "model-a", source: "arena_elo", category: "coding", score: 0.90, eloRaw: 1450, confidence: "high", expiresAt: null },
]);
const entry = mi.getModelIntelligenceBySource("model-a", "arena_elo", "coding");
assert.ok(entry);
assert.strictEqual(entry.score, 0.90);
assert.strictEqual(entry.eloRaw, 1450);
});
});
describe("getResolvedTaskFitness", () => {
beforeEach(() => { resetStorage(); });
it("returns user_override score when all sources exist", () => {
insertEntry("claude-sonnet", "models_dev_tier", "coding", 0.75);
insertEntry("claude-sonnet", "arena_elo", "coding", 0.88);
insertEntry("claude-sonnet", "user_override", "coding", 0.99);
const score = mi.getResolvedTaskFitness("claude-sonnet", "coding");
assert.strictEqual(score, 0.99);
});
it("returns arena_elo score when no user_override exists", () => {
insertEntry("gpt-4o", "arena_elo", "coding", 0.87);
insertEntry("gpt-4o", "models_dev_tier", "coding", 0.70);
const score = mi.getResolvedTaskFitness("gpt-4o", "coding");
assert.strictEqual(score, 0.87);
});
it("returns models_dev_tier score when only that source exists", () => {
insertEntry("llama-4", "models_dev_tier", "coding", 0.65);
const score = mi.getResolvedTaskFitness("llama-4", "coding");
assert.strictEqual(score, 0.65);
});
it("returns null when nothing exists", () => {
const score = mi.getResolvedTaskFitness("nonexistent", "coding");
assert.strictEqual(score, null);
});
it("skips expired entries in the resolution chain", () => {
insertEntry("gemini-pro", "arena_elo", "coding", 0.82, {
expiresAt: "2000-01-01T00:00:00Z",
});
insertEntry("gemini-pro", "models_dev_tier", "coding", 0.70);
const score = mi.getResolvedTaskFitness("gemini-pro", "coding");
assert.strictEqual(score, 0.70);
});
});
describe("edge cases", () => {
beforeEach(() => { resetStorage(); });
it("score values are stored and retrieved with float precision", () => {
mi.upsertModelIntelligence({
model: "precise-model",
source: "arena_elo",
category: "coding",
score: 0.1234,
eloRaw: null,
confidence: null,
expiresAt: null,
});
const entry = mi.getModelIntelligence("precise-model", "coding");
assert.ok(entry);
assert.ok(Math.abs(entry.score - 0.1234) < 0.0001);
});
it("null eloRaw and confidence are handled correctly", () => {
mi.upsertModelIntelligence({
model: "minimal-model",
source: "models_dev_tier",
category: "default",
score: 0.6,
eloRaw: null,
confidence: null,
expiresAt: null,
});
const entry = mi.getModelIntelligence("minimal-model", "default");
assert.ok(entry);
assert.strictEqual(entry.eloRaw, null);
assert.strictEqual(entry.confidence, null);
});
it("NULL expires_at means never expires", () => {
mi.upsertModelIntelligence({
model: "permanent-model",
source: "user_override",
category: "coding",
score: 0.95,
eloRaw: null,
confidence: null,
expiresAt: null,
});
const entry = mi.getModelIntelligence("permanent-model", "coding");
assert.ok(entry);
assert.strictEqual(entry.expiresAt, null);
assert.strictEqual(entry.score, 0.95);
});
});