Files
OmniRoute/@omniroute/opencode-plugin/tests/combos.test.ts
Diego Rodrigues de Sa e Souza 19d91d82e2 Release v3.8.34 (#4614)
* chore(release): open v3.8.34 development cycle

* chore(quality): release-green pre-flight validator + nightly signal (C+D) (#4622)

C — scripts/quality/validate-release-green.mjs (npm run check:release-green):
reproduces the release-equivalent validation (typecheck, eslint, db-rules,
public-creds, full unit, vitest, ratchets, optional --with-build package-artifact)
against the current working tree and classifies each red as HARD (real defect,
exit 1) vs DRIFT (ratchet — reported, never affects exit / never blocks). Pure
helpers exported + orchestration behind a direct-run guard; unit-tested.

D — .github/workflows/nightly-release-green.yml: runs C on the active release
branch nightly (and on workflow_dispatch) and opens/updates a single tracking
issue on HARD failures. Never a required check, never touches a contributor PR.

Closes the gap where the full gate (ci.yml) only ran on the release PR, so reds
accrued silently on release/** and surfaced in 40-min layers at release time.
Non-blocking by construction; drift is the maintainer's to rebaseline at release.

Co-authored-by: Diego Rodrigues de Sa e Souza <diego.souza@cdwasolutions.com.br>

* fix(providers): show revealed connection API keys (#4583)

Integrated into release/v3.8.34

* fix(resilience): respect upstream retry hint toggle (#4585)

Integrated into release/v3.8.34

* feat(settings): expose stream recovery feature flags (#4586)

Integrated into release/v3.8.34

* fix(logs): make active request stale sweep configurable (#4599)

Integrated into release/v3.8.34

* fix(plugin): auto-prefix providerId with 'opencode-' for OC 1.17.8+ native gate (#4527)

Integrated into release/v3.8.34 (supersedes #4445)

* fix(models): treat unknown output caps as unset (#4584)

Integrated into release/v3.8.34

* fix(executors): strip temperature for GitHub Copilot gpt-5.4 family (#4564)

Integrated into release/v3.8.34 (rebuilt onto tip)

* fix(oauth): update Qwen OAuth URLs from chat.qwen.ai to qwen.ai (#4561)

Integrated into release/v3.8.34 (rebuilt onto tip)

* fix(api/settings): prevent cached /api/settings responses (port from 9router#951) (#4566)

Integrated into release/v3.8.34 (rebuilt onto tip)

* feat(audio): MiniMax T2A v2 TTS dispatch in audioSpeech (port #1043) (#4553)

Integrated into release/v3.8.34 (rebuilt onto tip)

* fix(dashboard): surface manual config CTA when Open Claw CLI auto-detect fails (#4562)

Integrated into release/v3.8.34 (rebuilt onto tip)

* feat(providers): optional model ID for custom API-key validation (#4555)

Integrated into release/v3.8.34 (rebuilt onto tip)

* fix(cli): align data dir and env loading with runtime (#4607)

Integrated into release/v3.8.34 (rebuilt onto tip)

* fix(quota): expose Bailian quota windows (#4610)

Integrated into release/v3.8.34 (rebuilt onto tip)

* fix: retain provider cooldowns for configured max window (#4588)

Integrated into release/v3.8.34 (rebuilt — bundled commits stripped)

* fix: reject invalid provider cooldown bounds (#4589)

Integrated into release/v3.8.34 (rebuilt — bundled commits stripped)

* fix: preserve production combo metrics on shadow eviction (#4590)

Integrated into release/v3.8.34 (rebuilt — bundled commits stripped)

* fix(stream): estimate input tokens when upstream reports prompt_tokens=0 (#4615)

Integrated into release/v3.8.34 (rebuilt onto tip)

* fix(catalog): shorten no-thinking gateway prefix to no-think/ (#4525)

Integrated into release/v3.8.34 (rebuilt — kept only the prefix rename, dropped stale-base reverts)

* fix(relay): apply IP rate limit to bifrost sidecar (#4593)

Integrated into release/v3.8.34 (rebuilt onto tip; merge before #4612)

* fix(bifrost): finalize SSE relay usage after stream (#4612)

Integrated into release/v3.8.34 (rebuilt + reconciled with #4593)

* feat(compression): per-request `x-omniroute-compression` header (Phase 3) (#4645)

* docs(compression): Phase 3 per-request header design spec

Approved brainstorming output for the x-omniroute-compression header:
header-first precedence, name-first combo matching (Decision A), explicit
value bypasses auto-trigger (Decision B), DerivedPlan.source, and the
X-OmniRoute-Compression response header.

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

* docs(compression): Phase 3 per-request header implementation plan

4-task TDD plan (resolver header-first + source, parser, chatCore wiring +
response header, docs/file-size) with full code and exact commands.

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

* feat(compression): header-first resolver + plan source (Phase 3 core)

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

* feat(compression): resolveCompressionHeader parser (Phase 3)

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

* feat(compression): wire x-omniroute-compression header + response header (Phase 3)

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

* refactor(compression): extract plan-resolution leaf (planResolution.ts) under size cap (Phase 3)

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

* docs(compression): document x-omniroute-compression header (Phase 3)

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

* fix(compression): harden named-combo map + trim engine: header id (Phase 3 review)

Addresses gemini-code-assist review on #4645:
- Extract buildNamedComboLookup (pure) so a blank/whitespace/null combo name
  contributes only its id key (no '' key, no throw that disables all combos).
- Trim the engine:<id> header value so 'engine: rtk' resolves.

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

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <diego.souza@cdwasolutions.com.br>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix: exclude exhausted connections from auto scoring (#4592)

Integrated into release/v3.8.34 (rebuilt + opt-in gate fix)

* fix(dashboard): memoize compatible provider groups (#4613)

Integrated into release/v3.8.34 (rebuilt + test added)

* fix(dashboard): isolate quota widget refresh clock (#4611)

Integrated into release/v3.8.34 (rebuilt + jsdom test)

* fix(dashboard): gate topology side effects behind widget visibility (#4606)

Integrated into release/v3.8.34 (rebuilt + jsdom test)

* fix(dashboard): keep play_arrow spinning on provider Test All buttons (#4563)

Integrated into release/v3.8.34 (rebuilt onto tip; UI-cosmetic per owner)

* fix(db): schedule retention cleanup + fix cleanup table/column names (extracted from #4428) (#4691)

Integrated into release/v3.8.34 (cleanup core extracted from #4428, credit @oyi77)

* fix(telemetry): back off live-WS event forwarding when the sidecar is unreachable (#4604) (#4687)

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(api): serve GET /v1/models/{model} as JSON, not the HTML dashboard (#4674) (#4677)

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* feat(opencode): add go deepseek reasoning variants (#4647)

Integrated into release/v3.8.34

* fix(executors): robust deepseek-web tool-call parsing and agentic context retention (#4644)

Integrated into release/v3.8.34

* fix(cli): authenticate `omniroute logs` and honor active context (#4638)

Integrated into release/v3.8.34 (authored by Rahul Sharma, AI co-author trailer stripped per project policy)

* fix(proxy): apply pipelining:0 + connections cap to the direct dispatcher (#4580) (#4684)

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(executors): Firecrawl web_fetch 500 with include_metadata=true (#4692)

Integrated into release/v3.8.34

* fix(routing): include all noAuth models in auto-combos + add reka-flash + best-free template (#4621)

Integrated into release/v3.8.34 (dead getFirstRegistryModelId dropped, rebuilt onto tip)

* fix(dashboard): gate home topology live-WS networking (#4596) (#4618)

Integrated into release/v3.8.34 (adapted onto #4606's extracted topology section: default-hidden flip + enabled gate on useLiveDashboard)

* fix(cli): align `omniroute` env loading with the runtime data dir (#4597) (#4619)

Integrated into release/v3.8.34 (data-dir.mjs refactor reconciled with #4607; loadEnvFile aligned to getDefaultDataDir)

* chore(quality): reconcile file-size baseline for #4644 (deepseek-web.ts 1117->1125) (#4695)

file-size reconcile for #4644

* Support quota scraping for OpenCode Go and Ollama Cloud (#4642)

Integrated into release/v3.8.34 (Ollama Cloud + OpenCode Go dashboard quota scraping; rebuilt onto tip, gates green: typecheck/public-creds/file-size/lint/docs-sync + 31 tests)

* feat(executors): land M365 Copilot pure framing + connection helpers (#4042) (#4696)

Land M365 pure modules ahead of draft #4400

* deps: bump production + development groups; migrate js-yaml to v5 ESM (#4697)

Incorporates Dependabot #4667 + #4668 + js-yaml v5 ESM migration into release/v3.8.34

* fix: noAuth provider validation + kimi executor routing (#4699)

Integrated into release/v3.8.34 (noAuth in NOAUTH_PROVIDERS dynamic check + remove misrouted kimi web alias; 9 tests)

* refactor(imageGeneration): extract 8 provider families to co-located files (#4609)

Integrated into release/v3.8.34 (extraction completed: added missing imports/exports per module, main imports handlers locally; 145 image-gen tests pass, typecheck/cycles/file-size green)

* chore(release): v3.8.34 — finalize changelog, rebaseline drift, fix release-green reds

- Finalize CHANGELOG [3.8.34] (43 bullets, full contributor attribution) + seed i18n mirrors
- Rebaseline inherited cycle drift surfaced by release-green pre-flight: eslint warnings
  3900->3907, cognitive-complexity 797->801 (release-finalize touches no prod code; all
  drift is from this cycle's contributor merges)
- fix(providers): keep reka-flash-3 as the Reka provider default. #4621 inserted reka-flash
  at the head of the model list, silently changing the default from reka-flash-3 (the
  free-tier model) to reka-flash; reorder so reka-flash-3 stays default, reka-flash retained.
- test: align provider-models-config / provider-models-route / web-cookie-providers-new with
  #4621 (reka-flash now in the Reka catalog) and #4699 (the `kimi` API-key provider correctly
  falls through to DefaultExecutor instead of KimiWebExecutor)
- chore(quality): allowlist the COMPRESSION_GUIDE doc name in check-fabricated-docs
  (false-positive env-var match; docs/compression/COMPRESSION_GUIDE.md exists)

* fix(release-green): resolve release-PR full-CI reds for v3.8.34

Surfaced only on the release PR (these gates don't run on PR->release fast-gates):

- fix(quota): complete HTML-comment sanitization in opencodeOllamaUsage SSR reset-time
  parsing — strip any <!--...--> generically instead of the two literal React hydration
  markers, so no partial "<!--" can survive (CodeQL js/incomplete-multi-character-
  sanitization, HIGH, introduced by #4642). Regression test added.
- test(codex): correct the Codex-fingerprint body key order assertion to match the
  canonical bodyFieldOrder (prompt_cache_key precedes include); #4584 flipped the two
  and integration tests don't run on fast-gates so it never executed until the release PR.
- chore(quality): rebaseline inherited cycle drift surfaced by full CI —
  zizmorFindings 152->155 (+3 unpinned-uses in nightly-release-green.yml from #4622,
  same @vN convention as ci.yml) and openapiCoverage.pct 38.4->37.8 (-0.6, contributor
  routes added faster than openapi docs). Release-finalize touches no prod routes.

* fix(release-green): complete CodeQL sanitization + rebaseline complexity drift

- fix(quota): handle unterminated HTML comments in opencodeOllamaUsage SSR reset-time
  parsing — the `(?:-->|$)` arm consumes a trailing "<!--" with no closing "-->", so no
  partial "<!--" can survive (CodeQL js/incomplete-multi-character-sanitization persisted
  with the plain <!--...--> form because an unclosed comment could still leave "<!--").
- chore(quality): rebaseline cyclomatic complexity 1915->1916 (+1) — inherited v3.8.34
  cycle drift (contributor feature branches); check:complexity does not run on PR->release
  fast-gates so it surfaced only on the release PR. Release-finalize adds 0 complexity
  (measured 1916 with/without the regex tweak). dead-code/cognitive/type-coverage/
  compression-budget/codeql ratchets all pass.

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <diego.souza@cdwasolutions.com.br>
Co-authored-by: Randi <55005611+rdself@users.noreply.github.com>
Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com>
Co-authored-by: KooshaPari <42529354+KooshaPari@users.noreply.github.com>
Co-authored-by: Abhishek Divekar <adivekar@utexas.edu>
Co-authored-by: Rahul sharma <sharmaR0810@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>
Co-authored-by: Ronald Estacion <DevEstacion@users.noreply.github.com>
Co-authored-by: Igor <60442260+BugsBag@users.noreply.github.com>
Co-authored-by: Oonishi <275808243+ponkcore@users.noreply.github.com>
Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com>
Co-authored-by: Jan Leon <Jan.gaschler@gmail.com>
2026-06-23 03:08:29 -03:00

712 lines
26 KiB
TypeScript

/**
* T-05 combo-discovery contract tests.
*
* Covers:
* - `defaultOmniRouteCombosFetcher(baseURL, apiKey, timeoutMs?)`
* — envelope tolerance (`{combos: [...]}` and bare array), non-2xx errors.
* - `mapComboToModelV2(combo, members, providerId, baseURL)`
* — LCD policy across capabilities, limits, modalities; defensive
* posture on empty members; nice-name preference.
* - `createOmniRouteProviderHook(opts, deps)` extension
* — combos merged into the models map; collision resolution (combo
* wins, warn-once); soft-fail when the combos fetcher throws;
* combos cached + reused under the same TTL key as models.
*
* Mocking strategy mirrors `provider.test.ts`: both fetchers are
* dependency-injected at hook construction, no `fetch` monkey-patch.
*/
import test from "node:test";
import assert from "node:assert/strict";
import {
createOmniRouteProviderHook,
defaultOmniRouteCombosFetcher,
mapComboToModelV2,
type OmniRouteCombosFetcher,
type OmniRouteModelsFetcher,
type OmniRouteRawCombo,
type OmniRouteRawModelEntry,
} from "../src/index.js";
// ────────────────────────────────────────────────────────────────────────────
// Fixtures
// ────────────────────────────────────────────────────────────────────────────
const MODEL_PRIMARY: OmniRouteRawModelEntry = {
id: "claude-primary",
capabilities: {
tool_calling: true,
reasoning: true,
vision: true,
thinking: true,
temperature: true,
},
context_length: 200_000,
max_output_tokens: 64_000,
max_input_tokens: 180_000,
input_modalities: ["text", "image"],
output_modalities: ["text"],
};
const MODEL_SECONDARY: OmniRouteRawModelEntry = {
id: "claude-secondary",
capabilities: {
tool_calling: true,
reasoning: false,
vision: true,
thinking: false,
temperature: true,
},
context_length: 100_000,
max_output_tokens: 32_000,
max_input_tokens: 96_000,
input_modalities: ["text", "image"],
output_modalities: ["text"],
};
const MODEL_NO_TOOLS: OmniRouteRawModelEntry = {
id: "gemini-3-flash",
capabilities: { tool_calling: false, reasoning: false, vision: false, thinking: false },
context_length: 1_000_000,
max_output_tokens: 8_192,
input_modalities: ["text"],
output_modalities: ["text"],
};
const COMBO_CLAUDE_TIER: OmniRouteRawCombo = {
id: "combo-claude-tier",
name: "Claude Tier",
strategy: "priority",
models: [
{ id: "s1", kind: "model", model: "claude-primary", weight: 100 },
{ id: "s2", kind: "model", model: "claude-secondary", weight: 80 },
],
};
// ────────────────────────────────────────────────────────────────────────────
// Helpers
// ────────────────────────────────────────────────────────────────────────────
function stubModelsFetcher(
payload: OmniRouteRawModelEntry[]
): OmniRouteModelsFetcher & { callCount: () => number } {
let n = 0;
const f: OmniRouteModelsFetcher = async () => {
n++;
return payload;
};
return Object.assign(f, { callCount: () => n });
}
function stubCombosFetcher(
payload: OmniRouteRawCombo[]
): OmniRouteCombosFetcher & { callCount: () => number; callsBy: () => Array<[string, string]> } {
let n = 0;
const calls: Array<[string, string]> = [];
const f: OmniRouteCombosFetcher = async (baseURL, apiKey) => {
n++;
calls.push([baseURL, apiKey]);
return payload;
};
return Object.assign(f, {
callCount: () => n,
callsBy: () => calls,
});
}
function failingCombosFetcher(
err = new Error("boom")
): OmniRouteCombosFetcher & { callCount: () => number } {
let n = 0;
const f: OmniRouteCombosFetcher = async () => {
n++;
throw err;
};
return Object.assign(f, { callCount: () => n });
}
const apiAuth = (key: string): unknown => ({ type: "api", key });
// Capture console.warn invocations for the duration of a callback, then
// restore the original. Needed because the collision + soft-fail paths
// emit warnings we want to assert on.
async function withWarnCapture<T>(
fn: (warnings: Array<{ args: unknown[] }>) => Promise<T>
): Promise<{ result: T; warnings: Array<{ args: unknown[] }> }> {
const original = console.warn;
const warnings: Array<{ args: unknown[] }> = [];
console.warn = (...args: unknown[]) => {
warnings.push({ args });
};
try {
const result = await fn(warnings);
return { result, warnings };
} finally {
console.warn = original;
}
}
// ────────────────────────────────────────────────────────────────────────────
// defaultOmniRouteCombosFetcher — envelope tolerance + error surfacing
// ────────────────────────────────────────────────────────────────────────────
test("defaultOmniRouteCombosFetcher: parses {combos:[…]} envelope", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = (async (input: unknown) => {
const url = typeof input === "string" ? input : (input as { url: string }).url;
assert.equal(url, "https://or.example.com/api/combos");
return new Response(
JSON.stringify({
combos: [
{ id: "c1", name: "Combo One", strategy: "priority", models: [] },
{ id: "c2", name: "Combo Two", strategy: "weighted", models: [] },
],
}),
{ status: 200, headers: { "Content-Type": "application/json" } }
);
}) as typeof fetch;
try {
const combos = await defaultOmniRouteCombosFetcher("https://or.example.com", "sk-test");
assert.equal(combos.length, 2);
assert.equal(combos[0].id, "c1");
assert.equal(combos[1].id, "c2");
} finally {
globalThis.fetch = originalFetch;
}
});
test("defaultOmniRouteCombosFetcher: parses bare array envelope", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = (async () => {
return new Response(JSON.stringify([{ id: "c1" }, { id: "c2" }, { not_an_id: 42 }]), {
status: 200,
});
}) as typeof fetch;
try {
const combos = await defaultOmniRouteCombosFetcher("https://or.example.com/v1", "sk-test");
// Strip /v1 before /api/combos, AND filter out entries with no string id.
assert.equal(combos.length, 2);
assert.equal(combos[0].id, "c1");
assert.equal(combos[1].id, "c2");
} finally {
globalThis.fetch = originalFetch;
}
});
test("defaultOmniRouteCombosFetcher: strips trailing /v1 before /api/combos", async () => {
const originalFetch = globalThis.fetch;
let observedUrl = "";
globalThis.fetch = (async (input: unknown) => {
observedUrl = typeof input === "string" ? input : (input as { url: string }).url;
return new Response(JSON.stringify({ combos: [] }), { status: 200 });
}) as typeof fetch;
try {
await defaultOmniRouteCombosFetcher("https://or.example.com/v1/", "sk-test");
assert.equal(observedUrl, "https://or.example.com/api/combos");
} finally {
globalThis.fetch = originalFetch;
}
});
test("defaultOmniRouteCombosFetcher: throws on non-2xx with status code in message", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = (async () => {
return new Response(JSON.stringify({ error: "Invalid token" }), {
status: 403,
statusText: "Forbidden",
});
}) as typeof fetch;
try {
await assert.rejects(
async () => {
await defaultOmniRouteCombosFetcher("https://or.example.com", "sk-bad");
},
(err: unknown) => {
const msg = err instanceof Error ? err.message : String(err);
assert.match(msg, /403/, "status code must appear in message");
assert.match(msg, /\/api\/combos/, "url must appear in message");
return true;
}
);
} finally {
globalThis.fetch = originalFetch;
}
});
test("defaultOmniRouteCombosFetcher: throws when apiKey missing", async () => {
await assert.rejects(
async () => defaultOmniRouteCombosFetcher("https://or.example.com", ""),
/apiKey required/
);
});
test("defaultOmniRouteCombosFetcher: throws when baseURL missing", async () => {
await assert.rejects(
async () => defaultOmniRouteCombosFetcher("", "sk-test"),
/baseURL required/
);
});
// ────────────────────────────────────────────────────────────────────────────
// mapComboToModelV2 — LCD semantics
// ────────────────────────────────────────────────────────────────────────────
test("mapComboToModelV2: empty members → capabilities all false (defensive)", () => {
const m = mapComboToModelV2(
{ id: "combo-empty", name: "Empty Combo" },
[],
"omniroute",
"https://or.example.com/v1"
);
assert.equal(m.id, "combo-empty");
assert.equal(m.name, "Empty Combo");
assert.equal(m.capabilities.temperature, false);
assert.equal(m.capabilities.reasoning, false);
assert.equal(m.capabilities.attachment, false);
assert.equal(m.capabilities.toolcall, false);
assert.equal(m.capabilities.input.text, false);
assert.equal(m.capabilities.output.text, false);
assert.equal(m.limit.context, 0);
assert.equal(m.limit.output, 0);
assert.equal(m.limit.input, undefined);
assert.deepEqual(m.cost, { input: 0, output: 0, cache: { read: 0, write: 0 } });
});
test("mapComboToModelV2: all members reasoning=true → combo reasoning=true", () => {
const m = mapComboToModelV2(
{ id: "c", models: [] },
[
MODEL_PRIMARY,
{
...MODEL_PRIMARY,
id: "p2",
capabilities: { ...MODEL_PRIMARY.capabilities, thinking: false, reasoning: true },
},
],
"omniroute",
"https://or.example.com/v1"
);
assert.equal(m.capabilities.reasoning, true);
});
test("mapComboToModelV2: any member reasoning=false → combo reasoning=false", () => {
const m = mapComboToModelV2(
{ id: "c", models: [] },
[MODEL_PRIMARY, MODEL_NO_TOOLS], // gemini-3-flash has reasoning:false, thinking:false
"omniroute",
"https://or.example.com/v1"
);
assert.equal(m.capabilities.reasoning, false);
});
test("mapComboToModelV2: limit.context is min of members'", () => {
const m = mapComboToModelV2(
{ id: "c", models: [] },
[MODEL_PRIMARY, MODEL_SECONDARY, MODEL_NO_TOOLS],
"omniroute",
"https://or.example.com/v1"
);
// min(200_000, 100_000, 1_000_000) = 100_000
assert.equal(m.limit.context, 100_000);
// min(64_000, 32_000, 8_192) = 8_192
assert.equal(m.limit.output, 8_192);
});
test("mapComboToModelV2: limit.input only emitted when EVERY member declares one", () => {
const m1 = mapComboToModelV2(
{ id: "c", models: [] },
[MODEL_PRIMARY, MODEL_SECONDARY],
"omniroute",
"https://or.example.com/v1"
);
// Both declare max_input_tokens → limit.input = min(180000, 96000)
assert.equal(m1.limit.input, 96_000);
const m2 = mapComboToModelV2(
{ id: "c", models: [] },
[MODEL_PRIMARY, MODEL_NO_TOOLS], // gemini-3-flash doesn't declare max_input_tokens
"omniroute",
"https://or.example.com/v1"
);
assert.equal(m2.limit.input, undefined);
});
test("mapComboToModelV2: nice name preferred from combo.name", () => {
const m1 = mapComboToModelV2(
{ id: "combo-x", name: "Pretty Name" },
[MODEL_PRIMARY],
"omniroute",
"https://or.example.com/v1"
);
assert.equal(m1.name, "Pretty Name");
// Falls back to id when name is absent or empty.
const m2 = mapComboToModelV2(
{ id: "combo-y" },
[MODEL_PRIMARY],
"omniroute",
"https://or.example.com/v1"
);
assert.equal(m2.name, "combo-y");
const m3 = mapComboToModelV2(
{ id: "combo-z", name: " " },
[MODEL_PRIMARY],
"omniroute",
"https://or.example.com/v1"
);
assert.equal(m3.name, "combo-z");
});
test("mapComboToModelV2: attachment AND vision flag both honored across members", () => {
// MODEL_PRIMARY: vision=true; MODEL_SECONDARY: vision=true → combo attachment=true
const yes = mapComboToModelV2(
{ id: "c1", models: [] },
[MODEL_PRIMARY, MODEL_SECONDARY],
"omniroute",
"https://or.example.com/v1"
);
assert.equal(yes.capabilities.attachment, true);
// Add a member with no vision/attachment → AND collapses to false
const no = mapComboToModelV2(
{ id: "c2", models: [] },
[MODEL_PRIMARY, MODEL_NO_TOOLS],
"omniroute",
"https://or.example.com/v1"
);
assert.equal(no.capabilities.attachment, false);
});
test("mapComboToModelV2: modalities AND'd across members", () => {
const m = mapComboToModelV2(
{ id: "c", models: [] },
[MODEL_PRIMARY, MODEL_SECONDARY], // both have text+image
"omniroute",
"https://or.example.com/v1"
);
assert.equal(m.capabilities.input.text, true);
assert.equal(m.capabilities.input.image, true);
assert.equal(m.capabilities.input.audio, false);
// Add a text-only member → image collapses to false.
const m2 = mapComboToModelV2(
{ id: "c", models: [] },
[MODEL_PRIMARY, MODEL_NO_TOOLS],
"omniroute",
"https://or.example.com/v1"
);
assert.equal(m2.capabilities.input.text, true);
assert.equal(m2.capabilities.input.image, false);
});
test("mapComboToModelV2: api block matches providerId + baseURL", () => {
const m = mapComboToModelV2(
{ id: "c" },
[MODEL_PRIMARY],
"omniroute-preprod",
"https://or-preprod.example.com/v1"
);
assert.equal(m.providerID, "omniroute-preprod");
assert.equal(m.api.id, "openai-compatible");
assert.equal(m.api.url, "https://or-preprod.example.com/v1");
assert.equal(m.api.npm, "@ai-sdk/openai-compatible");
assert.equal(m.status, "active");
});
test("mapComboToModelV2: explicit member temperature=false drops combo temperature=false", () => {
const tempFalse: OmniRouteRawModelEntry = {
id: "no-temp",
capabilities: { tool_calling: true, temperature: false },
context_length: 100_000,
max_output_tokens: 8_000,
input_modalities: ["text"],
output_modalities: ["text"],
};
const m = mapComboToModelV2(
{ id: "c" },
[MODEL_PRIMARY, tempFalse],
"omniroute",
"https://or.example.com/v1"
);
assert.equal(m.capabilities.temperature, false);
});
// ────────────────────────────────────────────────────────────────────────────
// createOmniRouteProviderHook — combos merge + collision + soft-fail + cache
// ────────────────────────────────────────────────────────────────────────────
test("models() returns combo entries merged into the map", async () => {
const modelsFetcher = stubModelsFetcher([MODEL_PRIMARY, MODEL_SECONDARY, MODEL_NO_TOOLS]);
const combosFetcher = stubCombosFetcher([COMBO_CLAUDE_TIER]);
const hook = createOmniRouteProviderHook(
{ baseURL: "https://or.example.com/v1" },
{ fetcher: modelsFetcher, combosFetcher }
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
// 3 raw models + 1 combo = 4 entries
assert.equal(Object.keys(out).length, 4);
assert.ok(out["opencode-omniroute/claude-primary"]);
assert.ok(out["opencode-omniroute/claude-secondary"]);
assert.ok(out["opencode-omniroute/gemini-3-flash"]);
assert.ok(out["opencode-omniroute/claude-tier"]);
const combo = out["opencode-omniroute/claude-tier"];
assert.equal(combo.name, "Claude Tier");
assert.equal(combo.providerID, "opencode-omniroute");
// LCD over claude-primary (200k, reasoning) + claude-secondary (100k, no reasoning)
assert.equal(combo.limit.context, 100_000);
assert.equal(combo.capabilities.reasoning, false);
assert.equal(combo.capabilities.toolcall, true);
});
test("models(): combo with unknown member ids degrades to all-false LCD posture", async () => {
const modelsFetcher = stubModelsFetcher([MODEL_PRIMARY]); // catalog only has claude-primary
const combosFetcher = stubCombosFetcher([
{
id: "phantom",
name: "Phantom Combo",
models: [
{ id: "s1", kind: "model", model: "does-not-exist-1", weight: 50 },
{ id: "s2", kind: "model", model: "does-not-exist-2", weight: 50 },
],
},
]);
const hook = createOmniRouteProviderHook(
{ baseURL: "https://or.example.com/v1" },
{ fetcher: modelsFetcher, combosFetcher }
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
assert.ok(out["opencode-omniroute/phantom-combo"]);
// With zero resolvable members, LCD = all-false (defensive posture).
assert.equal(out["opencode-omniroute/phantom-combo"].capabilities.toolcall, false);
assert.equal(out["opencode-omniroute/phantom-combo"].capabilities.reasoning, false);
assert.equal(out["opencode-omniroute/phantom-combo"].limit.context, 0);
});
test("models(): hidden combos are excluded from the map", async () => {
const modelsFetcher = stubModelsFetcher([MODEL_PRIMARY]);
const combosFetcher = stubCombosFetcher([
{
id: "visible",
name: "Visible",
models: [{ id: "s1", kind: "model", model: "claude-primary", weight: 100 }],
},
{
id: "hidden",
name: "Hidden",
isHidden: true,
models: [{ id: "s1", kind: "model", model: "claude-primary", weight: 100 }],
},
]);
const hook = createOmniRouteProviderHook(
{ baseURL: "https://or.example.com/v1" },
{ fetcher: modelsFetcher, combosFetcher }
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
assert.ok(out["opencode-omniroute/visible"]);
assert.ok(!out["opencode-omniroute/hidden"], "hidden combo must be omitted");
});
test("models(): combo name exactly matches raw model id → raw deleted, raw deleted, no warn", async () => {
// Combo.name === raw model id triggers the dedup deletion. This mirrors
// the real OmniRoute payload where /v1/models pre-mirrors combos as
// no-slash raw entries whose ids match /api/combos friendly names.
const colliderCombo: OmniRouteRawCombo = {
id: "uuid-collider",
name: "claude-primary", // EXACT match to MODEL_PRIMARY.id
models: [{ id: "s1", kind: "model", model: "claude-secondary", weight: 100 }],
};
const modelsFetcher = stubModelsFetcher([MODEL_PRIMARY, MODEL_SECONDARY]);
const combosFetcher = stubCombosFetcher([colliderCombo]);
const hook = createOmniRouteProviderHook(
{ baseURL: "https://or.example.com/v1" },
{ fetcher: modelsFetcher, combosFetcher }
);
const { result: out, warnings } = await withWarnCapture(async (_w) => {
return hook.models!({} as never, { auth: apiAuth("sk-z") as never });
});
// Raw model replaced by combo of the same key; combo now lives at the bare slug.
assert.ok(out["opencode-omniroute/claude-primary"], "combo surfaces under prefixed key");
assert.equal(out["opencode-omniroute/claude-primary"].name, "claude-primary");
// No collision warning fires — dedup makes keys disjoint.
const collisionWarns = warnings.filter((w) => {
const msg = w.args[0];
return typeof msg === "string" && msg.includes("collides");
});
assert.equal(collisionWarns.length, 0, "no collision warn after dedup");
});
test("models(): two combos with same slug → second gets disambiguator suffix", async () => {
// Both combos slug to `claude` — second must get `claude-<id-prefix>`.
const combos: OmniRouteRawCombo[] = [
{
id: "uuid-a",
name: "Claude",
models: [{ id: "s", kind: "model", model: "claude-primary", weight: 1 }],
},
{
id: "uuid-b",
name: "Claude",
models: [{ id: "s", kind: "model", model: "claude-secondary", weight: 1 }],
},
];
const hook = createOmniRouteProviderHook(
{ baseURL: "https://or.example.com/v1" },
{
fetcher: stubModelsFetcher([MODEL_PRIMARY, MODEL_SECONDARY]),
combosFetcher: stubCombosFetcher(combos),
}
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
// First combo gets the bare slug; second gets disambiguated.
assert.ok(out["opencode-omniroute/claude"], "first combo at prefixed slug");
assert.ok(out["opencode-omniroute/claude-uuid"], "second combo disambiguated by id prefix");
});
test("models(): combos fetch fails → falls back to models-only, warn emitted, no throw", async () => {
const modelsFetcher = stubModelsFetcher([MODEL_PRIMARY, MODEL_SECONDARY]);
const combosFetcher = failingCombosFetcher(new Error("ECONNRESET"));
const hook = createOmniRouteProviderHook(
{ baseURL: "https://or.example.com/v1" },
{ fetcher: modelsFetcher, combosFetcher }
);
const { result: out, warnings } = await withWarnCapture(async () => {
return hook.models!({} as never, { auth: apiAuth("sk-z") as never });
});
// Catalog includes the models but NOT any combo entries.
assert.equal(Object.keys(out).length, 2);
assert.ok(out["opencode-omniroute/claude-primary"]);
assert.ok(out["opencode-omniroute/claude-secondary"]);
// Soft-fail warning surfaced.
const softFail = warnings.find((w) => {
const msg = w.args[0];
return typeof msg === "string" && msg.includes("combos fetch failed");
});
assert.ok(softFail, "soft-fail warning must be emitted on combos fetch error");
assert.equal(combosFetcher.callCount(), 1);
});
test("models(): combos cached + reused within TTL (one combo fetch per TTL window)", async () => {
const modelsFetcher = stubModelsFetcher([MODEL_PRIMARY, MODEL_SECONDARY]);
const combosFetcher = stubCombosFetcher([COMBO_CLAUDE_TIER]);
let nowMs = 1_000_000;
const hook = createOmniRouteProviderHook(
{ baseURL: "https://or.example.com/v1", modelCacheTtl: 60_000 },
{ fetcher: modelsFetcher, combosFetcher, now: () => nowMs }
);
await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
nowMs += 30_000; // half the TTL
const second = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
assert.equal(combosFetcher.callCount(), 1, "combos fetched only once within TTL");
assert.equal(modelsFetcher.callCount(), 1, "models fetched only once within TTL");
assert.ok(second["opencode-omniroute/claude-tier"]);
});
test("models(): combos refetched after TTL expiry (same key as models)", async () => {
const modelsFetcher = stubModelsFetcher([MODEL_PRIMARY]);
const combosFetcher = stubCombosFetcher([COMBO_CLAUDE_TIER]);
let nowMs = 1_000_000;
const hook = createOmniRouteProviderHook(
{ baseURL: "https://or.example.com/v1", modelCacheTtl: 60_000 },
{ fetcher: modelsFetcher, combosFetcher, now: () => nowMs }
);
await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
nowMs += 60_001;
await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
assert.equal(combosFetcher.callCount(), 2, "combos must refetch past TTL");
assert.equal(modelsFetcher.callCount(), 2, "models must refetch past TTL");
});
test("models(): combos fetcher receives the resolved baseURL + apiKey", async () => {
const modelsFetcher = stubModelsFetcher([MODEL_PRIMARY]);
const combosFetcher = stubCombosFetcher([COMBO_CLAUDE_TIER]);
const hook = createOmniRouteProviderHook(
{ baseURL: "https://or.example.com/v1" },
{ fetcher: modelsFetcher, combosFetcher }
);
await hook.models!({} as never, { auth: apiAuth("sk-spy") as never });
assert.deepEqual(combosFetcher.callsBy()[0], ["https://or.example.com/v1", "sk-spy"]);
});
test("models(): nested combo-ref context is the min of nested + raw members", async () => {
// Top-level combo MASTER-LIGHT has 1 raw model (claude-primary, 200k)
// and 2 combo-refs: OldLLM (8k member) and KIRO (32k member). The OLD
// plugin would advertise 200k (only the raw model); the fix should
// make it advertise 8k (the bottleneck across the member graph).
const modelsFetcher = stubModelsFetcher([
MODEL_PRIMARY,
{
id: "oldllm-member-1",
context_length: 8_000,
max_output_tokens: 4_000,
capabilities: {
tool_calling: false,
reasoning: false,
vision: false,
thinking: false,
temperature: true,
},
input_modalities: ["text"],
output_modalities: ["text"],
},
{
id: "kiro-member-1",
context_length: 32_000,
max_output_tokens: 8_000,
capabilities: {
tool_calling: true,
reasoning: false,
vision: false,
thinking: false,
temperature: true,
},
input_modalities: ["text"],
output_modalities: ["text"],
},
]);
const combosFetcher = stubCombosFetcher([
{
id: "oldllm",
name: "OldLLM",
models: [{ id: "s1", kind: "model", model: "oldllm-member-1", weight: 100 }],
},
{
id: "kiro",
name: "KIRO",
models: [{ id: "s1", kind: "model", model: "kiro-member-1", weight: 100 }],
},
{
id: "master-light",
name: "MASTER-LIGHT",
models: [
{ id: "r1", kind: "model", model: "claude-primary", weight: 50 },
{ id: "r2", kind: "combo-ref", comboName: "OldLLM", weight: 25 },
{ id: "r3", kind: "combo-ref", comboName: "KIRO", weight: 25 },
],
},
]);
const hook = createOmniRouteProviderHook(
{ baseURL: "https://or.example.com/v1" },
{ fetcher: modelsFetcher, combosFetcher }
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
const masterLight = out["opencode-omniroute/master-light"];
assert.ok(masterLight, "MASTER-LIGHT entry must exist");
assert.equal(
masterLight.limit.context,
8_000,
`expected 8_000 (OldLLM bottleneck), got ${masterLight.limit.context}`
);
});