Files
OmniRoute/tests/unit/chat-helpers.test.ts
Diego Rodrigues de Sa e Souza bf8b56b29f Release v3.8.20 (#3547)
* chore(release): open v3.8.20 development cycle

* fix(images): prefer bare combos over image aliases (#3527)

Integrated into release/v3.8.20

* fix(translator): map Codex local_shell tool (#3534)

Integrated into release/v3.8.20

* fix(usage): make opencode-go quota fetcher fail-open instead of throwing 500 (#3522)

Integrated into release/v3.8.20

* Fix Runtime page breaker state rendering (#3533)

Integrated into release/v3.8.20

* Expose provider breaker degradation threshold setting (#3535)

Integrated into release/v3.8.20

* fix(executor): strip provider prefix from versioned built-in tool model field (#3532)

Integrated into release/v3.8.20

* feat(providers): add Claude Fable 5 support (#3524)

Integrated into release/v3.8.20

* feat(resilience): add global provider cooldown tracking to prevent combo re-walking (#3556)

Integrated into release/v3.8.20 (default OFF, opt-in)

* fix(translator): scope thoughtSignature bypass to Antigravity/CLI only (#3560)

Integrated into release/v3.8.20. Co-authored-by: Six7Day <six7day@gmail.com>

* fix(routing): normalize thinking:disabled for combo-substituted models that reject it (#3554) (#3563)

Integrated into release/v3.8.20

* fix(usage): accept 0/empty budget limits so the dashboard can save and clear (#3537) (#3564)

Integrated into release/v3.8.20

* docs(changelog): credit @Six7Day for #3560 thoughtSignature fix (#3414)

The #3560 squash co-author trailer landed inline (unparsed by GitHub), so add
an explicit CHANGELOG credit ensuring @Six7Day (original #3414) and @oyi77 are
on the public record for the Gemini thoughtSignature fix.

* fix(gamification): dedup badge unlock via user_badges so events don't re-fire every request (#3472) (#3565)

Integrated into release/v3.8.20

* fix(routing): pass through 'auto' keyword on codex /v1/responses instead of rewriting to codex/auto (#3509) (#3566)

Integrated into release/v3.8.20

* fix(cli-tools): normalize apiKey null in guide-settings schema so cloud-mode config saves (#3552) (#3567)

Integrated into release/v3.8.20

* fix(catalog): reclassify PublicAI from keyless to one-time-initial (requires API key) (#3558) (#3568)

Integrated into release/v3.8.20

* fix(gemini-web): surface missing Playwright browser as actionable 503 + cooldown hint, not a retryable 500 loop (#3516) (#3570)

Integrated into release/v3.8.20

* fix(security): sanitize raw err.message in web executors + embeddings/search response bodies (Rule #12) (#3494, #3495) (#3573)

Integrated into release/v3.8.20

* fix(dashboard): point CustomHostsManager + FeatureFlagsGrid at real routes (#3486, #3487) (#3574)

Integrated into release/v3.8.20

* chore(providers): remove dead krutrim entry (#3483) + docs(api): fix agent-bridge per-agent state route (#3489) (#3575)

Integrated into release/v3.8.20

* docs(api): correct API_REFERENCE.md paths for skills/plugins/admin/cache/acp/system-info (#3497) (#3577)

Integrated into release/v3.8.20

* fix(proxy): drive SOCKS5 UI option from runtime ENABLE_SOCKS5_PROXY, not build-time NEXT_PUBLIC (#3508) (#3579)

Integrated into release/v3.8.20

* fix(playground): filter playground models by node prefix so custom-endpoint models appear (#3505) (#3581)

Integrated into release/v3.8.20

* fix(usage): show an informative message instead of a blank Kiro quota card when no usage breakdown (#3506) (#3582)

Integrated into release/v3.8.20

* docs(changelog): add the #3506 Kiro quota entry (missed in #3582 due to a stale-base CHANGELOG anchor) (#3583)

Integrated into release/v3.8.20

* fix(auto-update): use stable PROJECT_ROOT walker, not frozen process.cwd() (#3561)

Integrated into release/v3.8.20. Auto-update PROJECT_ROOT now uses a stable __dirname-anchored upward walker instead of the no-op process.cwd() resolver.

* fix: address PR #3518 review comments (lifecycle hooks, regex, indentation, route params) (#3562)

Integrated into release/v3.8.20. Addresses #3518 review: regex literals, logs/[id] route params (Next 16), indentation, and wires plugin lifecycle hooks (onInstall/onActivate/onDeactivate/onUninstall) in the loader so manager.ts can register them. Adds Rule #18 regression test.

* docs(changelog): credit @ViFigueiredo (#3423) for PROJECT_ROOT + log #3561/#3562 (v3.8.20)

* fix: openai to gemini incorrectly translates historical tool calls into text (#3569)

Integrated into release/v3.8.20. Standard Gemini direct path now maps historical tool calls to native functionCall/functionResponse parts (signaturelessToolCallMode: native) instead of inert text — validated against the real Gemini API (gemini-2.5-flash returns 200 for signatureless native functionCall, even with tools+thinking; Hard Rule #18). Eliminates the text-serialization leak. Antigravity/CLI sentinel path (#3560) untouched.

* docs(changelog)+test: reconcile standard-Gemini native mode (#3569) — update round-2 rationale comment + log VPS validation

* docs(changelog): reconcile v3.8.20 — add 9 missing bullets + move [Unreleased] to versioned section

* docs(changelog): complete v3.8.20 reconciliation — 27 bullets, 11 contributors

---------

Co-authored-by: Alexander Averyanov <alex@averyan.ru>
Co-authored-by: Hakan Kurşun <bykamaka@gmail.com>
Co-authored-by: Wilson <pedbookmed@gmail.com>
Co-authored-by: Randi <55005611+rdself@users.noreply.github.com>
Co-authored-by: Giorgos Giakoumettis <giorgos@yiakoumettis.gr>
Co-authored-by: PizzaV <103120356+pizzav-xyz@users.noreply.github.com>
Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com>
Co-authored-by: Markus Hartung <mail@hartmark.se>
2026-06-10 13:49:08 -03:00

406 lines
13 KiB
TypeScript

import test from "node:test";
import assert from "node:assert/strict";
import fs from "node:fs";
import os from "node:os";
import path from "node:path";
const TEST_DATA_DIR = fs.mkdtempSync(path.join(os.tmpdir(), "omniroute-chat-helpers-"));
process.env.DATA_DIR = TEST_DATA_DIR;
const core = await import("../../src/lib/db/core.ts");
const providersDb = await import("../../src/lib/db/providers.ts");
const {
resolveModelOrError,
checkPipelineGates,
executeChatWithBreaker,
handleNoCredentials,
safeResolveProxy,
safeLogEvents,
withSessionHeader,
} = await import("../../src/sse/handlers/chatHelpers.ts");
const { getCircuitBreaker, resetAllCircuitBreakers, STATE } =
await import("../../src/shared/utils/circuitBreaker.ts");
async function resetStorage() {
resetAllCircuitBreakers();
core.resetDbInstance();
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
fs.mkdirSync(TEST_DATA_DIR, { recursive: true });
}
async function seedConnection(provider, overrides = {}) {
return providersDb.createProviderConnection({
provider,
authType: "apikey",
name: overrides.name || `${provider}-helper-${Math.random().toString(16).slice(2, 8)}`,
apiKey: overrides.apiKey || `sk-${provider}-helper`,
isActive: overrides.isActive ?? true,
testStatus: overrides.testStatus || "active",
providerSpecificData: overrides.providerSpecificData || {},
});
}
test.beforeEach(async () => {
await resetStorage();
});
test.after(async () => {
await resetStorage();
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
});
test("resolveModelOrError rejects ambiguous aliases without a provider prefix", async () => {
const result = await resolveModelOrError(
"claude-sonnet-4-6",
{ messages: [{ role: "user", content: "hello" }] },
"/v1/chat/completions"
);
assert.ok(result.error);
assert.equal(result.error.status, 400);
const json = (await result.error.json()) as any;
assert.match(json.error.message, /Ambiguous model/i);
});
test("resolveModelOrError rejects ambiguous slashful canonical ids instead of misrouting them", async () => {
const result = await resolveModelOrError(
"openai/gpt-oss-120b",
{ messages: [{ role: "user", content: "hello" }] },
"/v1/chat/completions"
);
assert.ok(result.error);
assert.equal(result.error.status, 400);
const json = (await result.error.json()) as any;
assert.match(json.error.message, /Ambiguous model/i);
assert.match(json.error.message, /openai\/gpt-oss-120b/i);
});
test("resolveModelOrError rejects malformed model strings", async () => {
const result = await resolveModelOrError(
"../etc/passwd",
{ messages: [{ role: "user", content: "hello" }] },
"/v1/chat/completions"
);
assert.ok(result.error);
assert.equal(result.error.status, 400);
const json = (await result.error.json()) as any;
assert.match(json.error.message, /Invalid model format/i);
});
test("resolveModelOrError routes Codex native compact gpt-5.5 requests to Codex", async () => {
const result = await resolveModelOrError(
"gpt-5.5",
{ model: "gpt-5.5", input: "compact this session", reasoning: { effort: "xhigh" } },
"/v1/responses/compact",
{ "user-agent": "codex-cli/0.128.0" }
);
assert.equal(result.provider, "codex");
assert.equal(result.model, "gpt-5.5");
});
test("resolveModelOrError keeps non-Codex gpt-5.5 Responses requests on OpenAI", async () => {
const result = await resolveModelOrError(
"gpt-5.5",
{ model: "gpt-5.5", input: "hello" },
"/v1/responses",
{ "user-agent": "OpenAI/Node" }
);
assert.equal(result.provider, "openai");
assert.equal(result.model, "gpt-5.5");
});
test("resolveModelOrError routes bare gpt-5.5 to Codex medium when Codex is the only active account", async () => {
await seedConnection("codex");
const result = await resolveModelOrError(
"gpt-5.5",
{ model: "gpt-5.5", input: "hello" },
"/v1/responses",
{ "user-agent": "OpenAI/Node" }
);
assert.equal(result.provider, "codex");
assert.equal(result.model, "gpt-5.5");
assert.equal(result.targetFormat, "openai-responses");
});
test("resolveModelOrError keeps bare gpt-5.5 on OpenAI when OpenAI is the only active account", async () => {
await seedConnection("openai");
const result = await resolveModelOrError(
"gpt-5.5",
{ model: "gpt-5.5", input: "hello" },
"/v1/responses",
{ "user-agent": "OpenAI/Node" }
);
assert.equal(result.provider, "openai");
assert.equal(result.model, "gpt-5.5");
});
test("checkPipelineGates blocks providers with an open circuit breaker", async () => {
const breaker = getCircuitBreaker("openai");
breaker.state = STATE.OPEN;
breaker.lastFailureTime = Date.now();
breaker.resetTimeout = 5_000;
const response = await checkPipelineGates("openai", "gpt-4o-mini", {
providerProfile: {
failureThreshold: 5,
resetTimeoutMs: 5_000,
},
});
const json = (await response.json()) as any;
const retryAfter = Number(response.headers.get("Retry-After"));
assert.equal(response.status, 503);
assert.ok(retryAfter >= 4);
assert.ok(retryAfter <= 5);
assert.match(json.error.message, /circuit breaker is open/i);
assert.equal(json.error.code, "provider_circuit_open");
assert.equal(response.headers.get("X-OmniRoute-Provider-Breaker"), "open");
});
test("checkPipelineGates reapplies runtime breaker settings to existing breakers", async () => {
const breaker = getCircuitBreaker("openai", {
failureThreshold: 5,
resetTimeout: 30_000,
});
breaker.state = STATE.OPEN;
breaker.lastFailureTime = Date.now() - 6_000;
const response = await checkPipelineGates("openai", "gpt-4o-mini", {
providerProfile: {
failureThreshold: 60,
degradationThreshold: 30,
resetTimeoutMs: 5_000,
},
});
assert.equal(response, null);
assert.equal(breaker.resetTimeout, 5_000);
assert.equal(breaker.failureThreshold, 60);
assert.equal(breaker.degradationThreshold, 30);
});
test("handleNoCredentials reports missing provider credentials and exhausted accounts", async () => {
const missing = handleNoCredentials(null, null, "openai", "gpt-4o-mini", null, null);
const exhausted = handleNoCredentials(
null,
"conn_123",
"openai",
"gpt-4o-mini",
"Primary account failed",
500
);
const missingJson = (await missing.json()) as any;
const exhaustedJson = (await exhausted.json()) as any;
assert.equal(missing.status, 400);
assert.match(missingJson.error.message, /No credentials for provider: openai/);
assert.equal(exhausted.status, 500);
assert.match(exhaustedJson.error.message, /Primary account failed/);
});
test("handleNoCredentials returns Retry-After when every account is rate limited", async () => {
const retryAfter = new Date(Date.now() + 45_000).toISOString();
const response = handleNoCredentials(
{
allRateLimited: true,
retryAfter,
retryAfterHuman: "reset after 45s",
lastErrorCode: 429,
lastError: "Quota exceeded",
},
"conn_123",
"openai",
"gpt-4o-mini",
null,
null
);
const json = (await response.json()) as any;
assert.equal(response.status, 429);
assert.ok(Number(response.headers.get("Retry-After")) >= 1);
assert.match(json.error.message, /\[openai\/gpt-4o-mini\] Quota exceeded/);
});
test("handleNoCredentials returns structured model_cooldown when every credential for the model is cooling down", async () => {
const retryAfter = new Date(Date.now() + 12_000).toISOString();
const response = handleNoCredentials(
{
allRateLimited: true,
retryAfter,
retryAfterHuman: "reset after 12s",
cooldownScope: "model",
cooldownModel: "gemini-2.5-pro",
lastErrorCode: 429,
lastError: "too many requests",
},
"conn_123",
"gemini",
"gemini-2.5-pro",
null,
null
);
const json = (await response.json()) as any;
assert.equal(response.status, 429);
assert.equal(Number(response.headers.get("Retry-After")) >= 1, true);
assert.equal(json.error.code, "model_cooldown");
assert.equal(json.error.type, "rate_limit_error");
assert.equal(json.error.model, "gemini-2.5-pro");
assert.ok(json.error.reset_seconds >= 1);
assert.match(json.error.message, /cooling down/i);
});
test("handleNoCredentials returns 401 with re-auth hint when every connection is in a terminal state", async () => {
// Classic scenario: AWS SSO refresh tokens hit their 90-day TTL, every Kiro
// connection flips to is_active=0 + testStatus=banned/expired. Surface as
// 401 with a reconnect hint instead of the misleading 400 "No credentials".
const response = handleNoCredentials(
{ allExpired: true, expiredCount: 1, expiredStatus: "banned" },
null,
"kiro",
"claude-sonnet-4.6",
null,
null
);
const json = (await response.json()) as any;
assert.equal(response.status, 401);
assert.match(json.error.message, /\[kiro\]/);
assert.match(json.error.message, /banned by upstream/);
assert.match(json.error.message, /please reconnect/i);
});
test("handleNoCredentials maps allExpired status='expired' to the 'authentication expired' reason", async () => {
const response = handleNoCredentials(
{ allExpired: true, expiredCount: 3, expiredStatus: "expired" },
null,
"cline",
"claude-sonnet-4.6",
null,
null
);
const json = (await response.json()) as any;
assert.equal(response.status, 401);
assert.match(json.error.message, /3 connection\(s\) authentication expired/);
});
test("safeResolveProxy returns the direct route when no proxy config is present", async () => {
const connection = await seedConnection("openai", { apiKey: "sk-openai-direct" });
const resolved = await safeResolveProxy((connection as any).id);
assert.deepEqual(resolved, {
proxy: null,
level: "direct",
levelId: null,
});
});
test("executeChatWithBreaker converts proxy fast-fail errors", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = async () => {
const error = new Error("Proxy unreachable");
(error as Error & { code?: string }).code = "PROXY_UNREACHABLE";
throw error;
};
try {
const credentials = {
connectionId: "conn_helper",
apiKey: "sk-openai-helper",
providerSpecificData: {},
};
const breaker = getCircuitBreaker("openai");
const proxyResult = await executeChatWithBreaker({
bypassCircuitBreaker: false,
breaker,
body: { model: "openai/gpt-4o-mini" },
provider: "openai",
model: "gpt-4o-mini",
refreshedCredentials: credentials,
proxyInfo: null,
log: console,
clientRawRequest: null,
credentials,
apiKeyInfo: null,
userAgent: "",
comboName: null,
comboStrategy: null,
isCombo: false,
extendedContext: false,
comboStepId: null,
comboExecutionKey: null,
});
assert.equal(proxyResult.result.status, 502);
assert.match(String(proxyResult.result.error || ""), /Proxy unreachable/);
} finally {
globalThis.fetch = originalFetch;
}
});
test("safeLogEvents tolerates success and timeout payloads", () => {
const credentials = { connectionId: "conn_log_12345678" };
safeLogEvents({
result: { success: true, status: 200 },
proxyInfo: null,
proxyLatency: 12,
provider: "openai",
model: "gpt-4o-mini",
sourceFormat: "openai-chat",
targetFormat: "openai-chat",
credentials,
comboName: null,
clientRawRequest: { endpoint: "/v1/chat/completions" },
});
safeLogEvents({
result: { success: false, status: 504, error: "timeout" },
proxyInfo: { proxy: null, level: "direct", levelId: null },
proxyLatency: 25,
provider: "openai",
model: "gpt-4o-mini",
sourceFormat: "openai-chat",
targetFormat: "openai-chat",
credentials,
comboName: "combo-a",
clientRawRequest: { endpoint: "/v1/chat/completions" },
tlsFingerprintUsed: true,
});
});
test("withSessionHeader adds headers to mutable and immutable responses", async () => {
const mutable = withSessionHeader(new Response("ok"), "sess_mutable");
const immutable = withSessionHeader(Response.redirect("https://example.com"), "sess_redirect");
assert.equal(mutable.headers.get("X-OmniRoute-Session-Id"), "sess_mutable");
assert.equal(immutable.headers.get("X-OmniRoute-Session-Id"), "sess_redirect");
assert.equal(immutable.status, 302);
assert.equal(await immutable.text(), "");
});
test("resolveModelOrError returns model_not_found error for unrecognised bare model names", async () => {
const result = await resolveModelOrError(
"completely-unknown-model-xyz",
{ messages: [{ role: "user", content: "hello" }] },
"/v1/chat/completions"
);
assert.ok(result.error);
assert.equal(result.error.status, 400);
const json = (await result.error.json()) as any;
assert.match(json.error.message, /Unable to determine provider/i);
assert.match(json.error.message, /completely-unknown-model-xyz/i);
});