mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-02 13:22:11 +03:00
* 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>
455 lines
14 KiB
TypeScript
455 lines
14 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";
|
|
|
|
// Fallback coverage for the strategies that previously only had happy-path tests
|
|
// (fill-first, p2c, random, cost-optimized, strict-random), plus circuit-breaker
|
|
// HALF_OPEN recovery in the combo loop and strategy-name normalization.
|
|
|
|
const TEST_DATA_DIR = fs.mkdtempSync(path.join(os.tmpdir(), "omniroute-combo-fallbacks-"));
|
|
const ORIGINAL_DATA_DIR = process.env.DATA_DIR;
|
|
process.env.DATA_DIR = TEST_DATA_DIR;
|
|
|
|
const { handleComboChat, preScreenTargets } = await import("../../open-sse/services/combo.ts");
|
|
const core = await import("../../src/lib/db/core.ts");
|
|
const settingsDb = await import("../../src/lib/db/settings.ts");
|
|
const { resetAllComboMetrics } = await import("../../open-sse/services/comboMetrics.ts");
|
|
const { resetAllCircuitBreakers, getCircuitBreaker } =
|
|
await import("../../src/shared/utils/circuitBreaker.ts");
|
|
const { resetAll: resetAllSemaphores } = await import("../../open-sse/services/rateLimitSemaphore.ts");
|
|
const { _resetAllDecks } = await import("../../src/shared/utils/shuffleDeck.ts");
|
|
const { clearSessions } = await import("../../open-sse/services/sessionManager.ts");
|
|
|
|
function createLog() {
|
|
const entries: any[] = [];
|
|
return {
|
|
info: (tag: any, msg: any) => entries.push({ level: "info", tag, msg }),
|
|
warn: (tag: any, msg: any) => entries.push({ level: "warn", tag, msg }),
|
|
error: (tag: any, msg: any) => entries.push({ level: "error", tag, msg }),
|
|
debug: (tag: any, msg: any) => entries.push({ level: "debug", tag, msg }),
|
|
entries,
|
|
};
|
|
}
|
|
|
|
function okResponse(body: any = { choices: [{ message: { content: "ok" } }] }) {
|
|
return new Response(JSON.stringify(body), {
|
|
status: 200,
|
|
headers: { "content-type": "application/json" },
|
|
});
|
|
}
|
|
|
|
function errorResponse(status: number, message: string = `Error ${status}`) {
|
|
return new Response(JSON.stringify({ error: { message } }), {
|
|
status,
|
|
headers: { "content-type": "application/json" },
|
|
});
|
|
}
|
|
|
|
async function cleanupTestDataDir() {
|
|
let lastError;
|
|
for (let attempt = 0; attempt < 5; attempt += 1) {
|
|
try {
|
|
core.resetDbInstance();
|
|
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
|
|
return;
|
|
} catch (error: any) {
|
|
lastError = error;
|
|
await new Promise((resolve) => setTimeout(resolve, 25));
|
|
}
|
|
}
|
|
if (lastError) throw lastError;
|
|
}
|
|
|
|
test.beforeEach(async () => {
|
|
resetAllComboMetrics();
|
|
resetAllCircuitBreakers();
|
|
resetAllSemaphores();
|
|
_resetAllDecks();
|
|
clearSessions();
|
|
await cleanupTestDataDir();
|
|
fs.mkdirSync(TEST_DATA_DIR, { recursive: true });
|
|
await settingsDb.resetAllPricing();
|
|
settingsDb.clearAllLKGP();
|
|
});
|
|
|
|
test.after(async () => {
|
|
resetAllComboMetrics();
|
|
resetAllCircuitBreakers();
|
|
resetAllSemaphores();
|
|
_resetAllDecks();
|
|
settingsDb.clearAllLKGP();
|
|
if (ORIGINAL_DATA_DIR === undefined) {
|
|
delete process.env.DATA_DIR;
|
|
} else {
|
|
process.env.DATA_DIR = ORIGINAL_DATA_DIR;
|
|
}
|
|
await cleanupTestDataDir();
|
|
});
|
|
|
|
test("fill-first falls back to the second target when the first fails", async () => {
|
|
const calls: string[] = [];
|
|
const result = await handleComboChat({
|
|
body: {},
|
|
combo: {
|
|
name: "fill-first-fallback",
|
|
strategy: "fill-first",
|
|
models: ["openai/gpt-4o-mini", "claude/sonnet"],
|
|
config: { maxRetries: 0, retryDelayMs: 0, fallbackDelayMs: 0 },
|
|
},
|
|
handleSingleModel: async (_body: any, modelStr: string) => {
|
|
calls.push(modelStr);
|
|
if (modelStr === "openai/gpt-4o-mini") return errorResponse(503);
|
|
return okResponse();
|
|
},
|
|
isModelAvailable: async () => true,
|
|
log: createLog(),
|
|
settings: null,
|
|
allCombos: null,
|
|
});
|
|
|
|
assert.equal(result.ok, true);
|
|
assert.deepEqual(calls, ["openai/gpt-4o-mini", "claude/sonnet"]);
|
|
});
|
|
|
|
test("p2c falls back to the remaining target when the selected one fails", async () => {
|
|
const calls: string[] = [];
|
|
const result = await handleComboChat({
|
|
body: {},
|
|
combo: {
|
|
name: "p2c-fallback",
|
|
strategy: "p2c",
|
|
models: ["openai/gpt-4o-mini", "claude/sonnet"],
|
|
config: { maxRetries: 0, retryDelayMs: 0, fallbackDelayMs: 0 },
|
|
},
|
|
handleSingleModel: async (_body: any, modelStr: string) => {
|
|
calls.push(modelStr);
|
|
// Whichever target p2c selects first fails; the other one serves.
|
|
if (calls.length === 1) return errorResponse(500);
|
|
return okResponse();
|
|
},
|
|
isModelAvailable: async () => true,
|
|
log: createLog(),
|
|
settings: null,
|
|
allCombos: null,
|
|
});
|
|
|
|
assert.equal(result.ok, true);
|
|
assert.equal(calls.length, 2, "both targets should be attempted");
|
|
assert.notEqual(calls[0], calls[1], "fallback must go to the other target");
|
|
});
|
|
|
|
test("p2c works with a single-target pool", async () => {
|
|
const calls: string[] = [];
|
|
const result = await handleComboChat({
|
|
body: {},
|
|
combo: {
|
|
name: "p2c-single",
|
|
strategy: "p2c",
|
|
models: ["openai/gpt-4o-mini"],
|
|
config: { maxRetries: 0 },
|
|
},
|
|
handleSingleModel: async (_body: any, modelStr: string) => {
|
|
calls.push(modelStr);
|
|
return okResponse();
|
|
},
|
|
isModelAvailable: async () => true,
|
|
log: createLog(),
|
|
settings: null,
|
|
allCombos: null,
|
|
});
|
|
|
|
assert.equal(result.ok, true);
|
|
assert.deepEqual(calls, ["openai/gpt-4o-mini"]);
|
|
});
|
|
|
|
test("random strategy falls through the shuffle order until the healthy target serves", async () => {
|
|
const calls: string[] = [];
|
|
const result = await handleComboChat({
|
|
body: {},
|
|
combo: {
|
|
name: "random-fallback",
|
|
strategy: "random",
|
|
models: ["openai/gpt-4o-mini", "claude/sonnet", "gemini/gemini-2.5-flash"],
|
|
config: { maxRetries: 0, retryDelayMs: 0, fallbackDelayMs: 0 },
|
|
},
|
|
handleSingleModel: async (_body: any, modelStr: string) => {
|
|
calls.push(modelStr);
|
|
// Only one target is healthy — wherever the shuffle puts it, the combo
|
|
// must keep falling through until it is reached.
|
|
if (modelStr === "gemini/gemini-2.5-flash") return okResponse();
|
|
return errorResponse(500);
|
|
},
|
|
isModelAvailable: async () => true,
|
|
log: createLog(),
|
|
settings: null,
|
|
allCombos: null,
|
|
});
|
|
|
|
assert.equal(result.ok, true);
|
|
assert.equal(calls[calls.length - 1], "gemini/gemini-2.5-flash");
|
|
assert.ok(calls.length >= 1 && calls.length <= 3);
|
|
});
|
|
|
|
test("cost-optimized falls back to the next-cheapest target when the cheapest fails", async () => {
|
|
// Cross-provider on purpose: a 5xx on a target without a pinned connectionId
|
|
// conservatively marks the whole provider for the rest of the request
|
|
// (#1731v2), so a same-provider second target would be skipped, not retried.
|
|
await settingsDb.updatePricing({
|
|
openai: {
|
|
"gpt-4o-nano": { input: 0.1, output: 0.2 },
|
|
},
|
|
claude: {
|
|
sonnet: { input: 5, output: 10 },
|
|
},
|
|
});
|
|
|
|
const calls: string[] = [];
|
|
const result = await handleComboChat({
|
|
body: {},
|
|
combo: {
|
|
name: "cost-fallback",
|
|
strategy: "cost-optimized",
|
|
models: ["claude/sonnet", "openai/gpt-4o-nano"],
|
|
config: { maxRetries: 0, retryDelayMs: 0, fallbackDelayMs: 0 },
|
|
},
|
|
handleSingleModel: async (_body: any, modelStr: string) => {
|
|
calls.push(modelStr);
|
|
if (modelStr === "openai/gpt-4o-nano") return errorResponse(500);
|
|
return okResponse();
|
|
},
|
|
isModelAvailable: async () => true,
|
|
log: createLog(),
|
|
settings: null,
|
|
allCombos: null,
|
|
});
|
|
|
|
assert.equal(result.ok, true);
|
|
assert.deepEqual(
|
|
calls,
|
|
["openai/gpt-4o-nano", "claude/sonnet"],
|
|
"cheapest first, then next-cheapest on failure"
|
|
);
|
|
});
|
|
|
|
test("cost-optimized preserves the original order on price ties", async () => {
|
|
await settingsDb.updatePricing({
|
|
openai: {
|
|
"gpt-4o-mini": { input: 1, output: 2 },
|
|
"gpt-4o": { input: 1, output: 2 },
|
|
},
|
|
});
|
|
|
|
const calls: string[] = [];
|
|
const result = await handleComboChat({
|
|
body: {},
|
|
combo: {
|
|
name: "cost-tie",
|
|
strategy: "cost-optimized",
|
|
models: ["openai/gpt-4o", "openai/gpt-4o-mini"],
|
|
config: { maxRetries: 0 },
|
|
},
|
|
handleSingleModel: async (_body: any, modelStr: string) => {
|
|
calls.push(modelStr);
|
|
return okResponse();
|
|
},
|
|
isModelAvailable: async () => true,
|
|
log: createLog(),
|
|
settings: null,
|
|
allCombos: null,
|
|
});
|
|
|
|
assert.equal(result.ok, true);
|
|
assert.deepEqual(calls, ["openai/gpt-4o"], "tie keeps the configured order (stable sort)");
|
|
});
|
|
|
|
test("strict-random falls back to the remaining target when the deck pick fails", async () => {
|
|
const calls: string[] = [];
|
|
const result = await handleComboChat({
|
|
body: {},
|
|
combo: {
|
|
name: "strict-random-fallback",
|
|
strategy: "strict-random",
|
|
models: ["openai/gpt-4o-mini", "claude/sonnet"],
|
|
config: { maxRetries: 0, retryDelayMs: 0, fallbackDelayMs: 0 },
|
|
},
|
|
handleSingleModel: async (_body: any, modelStr: string) => {
|
|
calls.push(modelStr);
|
|
if (calls.length === 1) return errorResponse(500);
|
|
return okResponse();
|
|
},
|
|
isModelAvailable: async () => true,
|
|
log: createLog(),
|
|
settings: null,
|
|
allCombos: null,
|
|
});
|
|
|
|
assert.equal(result.ok, true);
|
|
assert.equal(calls.length, 2);
|
|
assert.notEqual(calls[0], calls[1]);
|
|
});
|
|
|
|
test("strict-random survives a stale deck entry after a target is removed", async () => {
|
|
const comboTwoTargets = {
|
|
name: "strict-random-stale",
|
|
strategy: "strict-random",
|
|
models: ["openai/gpt-4o-mini", "claude/sonnet"],
|
|
config: { maxRetries: 0 },
|
|
};
|
|
|
|
// First request builds the deck with both targets.
|
|
const first = await handleComboChat({
|
|
body: {},
|
|
combo: comboTwoTargets,
|
|
handleSingleModel: async () => okResponse(),
|
|
isModelAvailable: async () => true,
|
|
log: createLog(),
|
|
settings: null,
|
|
allCombos: null,
|
|
});
|
|
assert.equal(first.ok, true);
|
|
|
|
// Same combo name, but one target was removed by the operator. The deck may
|
|
// still hold the removed target's key; the combo must degrade gracefully.
|
|
const calls: string[] = [];
|
|
const second = await handleComboChat({
|
|
body: {},
|
|
combo: {
|
|
...comboTwoTargets,
|
|
models: ["claude/sonnet"],
|
|
},
|
|
handleSingleModel: async (_body: any, modelStr: string) => {
|
|
calls.push(modelStr);
|
|
return okResponse();
|
|
},
|
|
isModelAvailable: async () => true,
|
|
log: createLog(),
|
|
settings: null,
|
|
allCombos: null,
|
|
});
|
|
|
|
assert.equal(second.ok, true, "stale deck entry must not break routing");
|
|
assert.deepEqual(calls, ["claude/sonnet"]);
|
|
});
|
|
|
|
test("unknown strategy value normalizes to priority order", async () => {
|
|
const calls: string[] = [];
|
|
const result = await handleComboChat({
|
|
body: {},
|
|
combo: {
|
|
name: "typo-strategy",
|
|
strategy: "weigthed", // typo on purpose
|
|
models: ["openai/gpt-4o-mini", "claude/sonnet"],
|
|
config: { maxRetries: 0 },
|
|
},
|
|
handleSingleModel: async (_body: any, modelStr: string) => {
|
|
calls.push(modelStr);
|
|
return okResponse();
|
|
},
|
|
isModelAvailable: async () => true,
|
|
log: createLog(),
|
|
settings: null,
|
|
allCombos: null,
|
|
});
|
|
|
|
assert.equal(result.ok, true);
|
|
assert.deepEqual(calls, ["openai/gpt-4o-mini"], "typo falls back to priority (first model)");
|
|
});
|
|
|
|
test("combo skips a provider while its breaker is OPEN and attempts it again after the reset timeout (HALF_OPEN)", async () => {
|
|
const breaker = getCircuitBreaker("openai", { failureThreshold: 1, resetTimeout: 40 });
|
|
try {
|
|
await breaker.execute(async () => {
|
|
throw new Error("simulated provider failure");
|
|
});
|
|
} catch {
|
|
// expected — trips the breaker OPEN
|
|
}
|
|
assert.equal(breaker.getStatus().state, "OPEN");
|
|
|
|
const comboDef = {
|
|
name: "half-open-recovery",
|
|
strategy: "priority",
|
|
models: ["openai/gpt-4o-mini", "claude/sonnet"],
|
|
config: { maxRetries: 0, retryDelayMs: 0, fallbackDelayMs: 0 },
|
|
};
|
|
|
|
// While OPEN: the openai target must be skipped, claude serves.
|
|
const callsWhileOpen: string[] = [];
|
|
const blocked = await handleComboChat({
|
|
body: {},
|
|
combo: comboDef,
|
|
handleSingleModel: async (_body: any, modelStr: string) => {
|
|
callsWhileOpen.push(modelStr);
|
|
return okResponse();
|
|
},
|
|
isModelAvailable: async () => true,
|
|
log: createLog(),
|
|
settings: null,
|
|
allCombos: null,
|
|
});
|
|
assert.equal(blocked.ok, true);
|
|
assert.deepEqual(callsWhileOpen, ["claude/sonnet"], "OPEN breaker target must be skipped");
|
|
|
|
// After the reset timeout the breaker reads HALF_OPEN — the combo must probe
|
|
// the provider again instead of excluding it forever (lazy recovery contract).
|
|
await new Promise((resolve) => setTimeout(resolve, 80));
|
|
assert.equal(breaker.getStatus().state, "HALF_OPEN");
|
|
|
|
const callsAfterExpiry: string[] = [];
|
|
const probed = await handleComboChat({
|
|
body: {},
|
|
combo: comboDef,
|
|
handleSingleModel: async (_body: any, modelStr: string) => {
|
|
callsAfterExpiry.push(modelStr);
|
|
return okResponse();
|
|
},
|
|
isModelAvailable: async () => true,
|
|
log: createLog(),
|
|
settings: null,
|
|
allCombos: null,
|
|
});
|
|
assert.equal(probed.ok, true);
|
|
assert.deepEqual(
|
|
callsAfterExpiry,
|
|
["openai/gpt-4o-mini"],
|
|
"HALF_OPEN provider must be probed again"
|
|
);
|
|
});
|
|
|
|
test("preScreenTargets marks an expired-OPEN (HALF_OPEN) target as available", async () => {
|
|
const breaker = getCircuitBreaker("openai", { failureThreshold: 1, resetTimeout: 30 });
|
|
try {
|
|
await breaker.execute(async () => {
|
|
throw new Error("simulated failure");
|
|
});
|
|
} catch {
|
|
// expected
|
|
}
|
|
await new Promise((resolve) => setTimeout(resolve, 60));
|
|
|
|
const targets = [
|
|
{
|
|
kind: "model" as const,
|
|
stepId: "step-1",
|
|
executionKey: "openai/gpt-4o",
|
|
modelStr: "openai/gpt-4o",
|
|
provider: "openai",
|
|
providerId: "conn-1",
|
|
connectionId: "conn-1",
|
|
weight: 1,
|
|
label: null,
|
|
},
|
|
];
|
|
|
|
const results = await preScreenTargets(targets as any);
|
|
const openaiResult = results.get("openai/gpt-4o");
|
|
assert.ok(openaiResult, "openai target should have a pre-screen result");
|
|
assert.equal(
|
|
openaiResult.available,
|
|
true,
|
|
"HALF_OPEN (expired OPEN) target must be available for a probe request"
|
|
);
|
|
});
|