Files
OmniRoute/tests/unit/combo-routing-engine.test.ts
Diego Rodrigues de Sa e Souza 9e45baae58 chore(release): v3.6.6 — Stabilization (#1241)
* fix(streaming): #1211 greedy strip omniModel tags to prevent literal \n\n artifacts

- Changed regex quantifier from ? to * in combo.ts, comboAgentMiddleware.ts,
  and contextHandoff.ts to greedily strip all JSON-escaped newline sequences
  surrounding <omniModel> tags in SSE streaming chunks
- Added \r to the character class for cross-platform robustness
- Fixed Playwright strict-mode violation in combo-unification.spec.ts
- Bumped OpenAPI version and CHANGELOG to 3.6.6

* fix: 3 bugs found during issue triage (#1175, #1187/#1218, #1202)

- fix(gemini): strip VS Code JSON Schema extensions from tool schemas (#1175)
  Add enumDescriptions, markdownDescription, markdownEnumDescriptions,
  enumItemLabels and tags to UNSUPPORTED_SCHEMA_CONSTRAINTS so the Gemini
  sanitizer removes them before forwarding. GitHub Copilot injects these
  non-standard fields into tool definitions, causing Gemini to reject with
  'Unknown name enumDescriptions at functionDeclarations[n].parameters'.

- fix(health-check): unwrap proxy config object before passing to getAccessToken (#1187 #1218)
  resolveProxyForConnection() returns { proxy, level, levelId } but the health
  check loop was passing the full wrapper to getAccessToken(), which expects the
  inner config object (.host, .port etc). The proxy dispatcher validated .host
  on the wrapper (undefined) and threw 'Context proxy host is required', silently
  marking every connection as unhealthy every sweep. Fix mirrors the pattern
  already used in chatHelpers.ts: proxyResult?.proxy || null.

- fix(ui): debounce models.dev sync interval slider to save only on release (#1202)
  The slider's onChange fired updateInterval() on every drag tick, sending a
  PATCH per pixel of movement. Rapid API responses overwrote UI state mid-drag.
  Introduce draftIntervalHours for smooth visual feedback; the PATCH fires
  on onMouseUp / onBlur once the user releases the control.

* fix(providers): update Xiaomi MiMo token-plan endpoints (#1238)

Integrated into release/v3.6.6

* fix(cc-compatible): trim beta flags and preserve cache passthrough (#1230)

Integrated into release/v3.6.6

* feat(memory+skills): full-featured memory & skills systems with tests (#1228)

Integrated into release/v3.6.6

* fix: forward client x-initiator header to GitHub Copilot upstream (#1227)

Integrated into release/v3.6.6

* feat(bailian-quota): add Alibaba Coding Plan quota monitoring (#1235)

* fix: resolve v3.6.6 backlog bugs (#1206, #1211, #1220, #1231)

- fix(core): #1206 inject startup guard against app/ and src/app/ conflict
- fix(health): #1220 add HEALTHCHECK_STAGGER_MS to prevent token refresh bursting
- fix(proxy): #1231 prioritize HTTP 429 over quota body heuristics
- fix(sse): #1211 strip leading double-newlines in responses API stream

* fix(tests): resolve memory migration and skills route pagination bugs from PR overlaps

* docs: Update CHANGELOG.md with v3.6.6 features (#1182, #1165, #1177)

* chore(release): bump version to 3.6.6

Update package versions for the electron app and open-sse package.
Sync llm.txt metadata and feature headings with the 3.6.6 release.

* feat(core): harden outbound provider calls and add cooldown retries

Add guarded outbound fetch helpers with private/local URL blocking,
controlled retries, timeout normalization, and route-level status
propagation for provider validation and model discovery.

Introduce cooldown-aware chat retries with configurable
requestRetry and maxRetryIntervalSec settings, model-scoped cooldown
responses, and improved rate-limit learning from headers and error
bodies so short upstream lockouts can recover automatically.

Also align Antigravity and Codex header handling, require API keys
for Pollinations, validate web runtime env at startup, restore
sanitized Gemini tool names in translated responses, and inject a
synthetic Claude text block when upstream SSE completes empty.

* feat(models): add glmt preset and hybrid token counting

Introduce GLM Thinking as a first-class provider preset with shared GLM
model metadata, pricing, usage sync, dashboard support, and provider
request defaults for higher token budgets and longer timeouts.

Use provider-side /messages/count_tokens when a Claude-compatible
upstream supports it, while preserving estimated fallback behavior for
missing models, missing credentials, and upstream failures.

Also add startup seeding for default model aliases and normalize common
cross-proxy model dialects so canonical slashful model ids do not get
misrouted during resolution.

* feat(api): add sync tokens and v1 websocket bridge

Add dedicated sync token storage, issuance, revocation, and bundle
download routes backed by stable config bundle versioning and ETag
support.

Expose the v1 websocket handshake route and custom Next server bridge so
OpenAI-compatible websocket traffic can be upgraded and proxied through
the dashboard and API bridge.

Expand compliance auditing with structured metadata, pagination, request
context, auth and provider credential events, and SSRF-blocked
validation logging.

* docs: Update all documentation for v3.6.6

- CHANGELOG: Add WebSocket bridge, GLM Thinking preset, safe outbound
  fetch/SSRF guard, cooldown-aware retries, compliance audit v2, model
  alias seeding, and all Internal Improvements for the 3 new commits
- README: Expand v3.6.x highlights table with 10 new features; add
  SafeOutboundFetch, CooldownAwareRetry, SSRF guard, TPS metric, sync
  tokens, WebSocket bridge to Resilience/Observability/Deployment tables
- ARCHITECTURE: Bump date; add new modules to executive summary, API
  routes, SSE core services, Auth/Security section; add SSRF/Outbound
  guard failure mode (section 6); expand module mapping
- ENVIRONMENT: Add OMNIROUTE_CRYPT_KEY/OMNIROUTE_API_KEY_BASE64 legacy
  aliases, OUTBOUND_SSRF_GUARD_ENABLED, CODEX_CLIENT_VERSION, and
  REQUEST_RETRY/MAX_RETRY_INTERVAL_SEC cooldown retry settings
- FEATURES: Add 6 new feature sections — V1 WebSocket Bridge, Sync
  Tokens & Config Bundle, GLM Thinking Preset, Safe Outbound Fetch &
  SSRF Guard, Cooldown-Aware Retries, Compliance Audit v2

* fix: use api64 for proxy test (#1255)

Integrated into release/v3.6.6 — IPv6 proxy test fix

* fix(page): update custom models section to include all providers #1200 (#1256)

Integrated into release/v3.6.6 — Gemini custom model picker fix

* fix: provide default client_id fallbacks to prevent broken OAuth requests (#1246)

Integrated into release/v3.6.6 — OAuth client_id default fallbacks

* fix: translate max_tokens/max_completion_tokens → max_output_tokens in Chat→Responses translator (#1245)

Integrated into release/v3.6.6 — max_tokens → max_output_tokens Responses API translation + unit tests

* feat(oauth): support cursor-agent CLI as Cursor credential source (#1258)

Integrated into release/v3.6.6 — cursor-agent CLI credential source support

* fix(cc-compatible): restore upstream SSE and correct stream/combo timeout behavior (#1257)

Integrated into release/v3.6.6 — CC-compatible upstream SSE restore + stream timeout fix + README table repair

* fix(cli-tools): resolve API key resolution and model mapping bugs in CLI tools (#1263)

Integrated into release/v3.6.6

* feat(cli-tools): add Qwen Code CLI integration (#1266)

Integrated into release/v3.6.6

* fix(i18n): add missing zh-CN translations and fix logger imports (#1269)

Integrated into release/v3.6.6

* fix(i18n): add Chinese i18n support to dashboard components (#1274)

Integrated into release/v3.6.6

* feat: update Pollinations to require API key, remove free tier flag (#1177)

* feat: friendly error messages for crypto/encryption failures (#1165)

* feat: add TPS (tokens per second) metric column to request logs (#1182)

* feat: merge custom/imported models into filter list for all providers (#1191)

* feat(fallback): Fix provider-profile-driven lockouts (#1267)

This integrates rdself's unify-provider-profile-locks PR manually to handle structural conflicts.

* fix(claude): proper Anthropic SDK integration (#1271)

* fix(healthcheck): use correct proxy wrapper format for getAccessToken (#1272)

* chore(release): v3.6.6 — skills registry stability fix + final integration

* fix(auth): harden bootstrap auth and memory dashboard behavior

Restrict unauthenticated writes to /api/settings/require-login to
the initial bootstrap window while keeping read-only checks public.
This prevents post-setup config changes without blocking first-run
login setup, and the onboarding flow now logs in immediately after
setting the password.

Restore memory API filtering and pagination behavior by supporting q
searches, honoring offset-based requests, and avoiding unrelated
fallback results when FTS misses. Update dashboard stats fallback to
use the response totals consistently.

Package the MCP server with explicit file entries and add regression
tests for bootstrap auth and memory route behavior

* fix(codex): remove max_output_tokens from body for compatibility

* chore(release): v3.6.6 — include PR 1274 fixes in changelog

* chore: exclude additional build artifacts and internal directories from npm package distribution

* fix: update Gemini OAuth test to match registry defaults + codex UI improvements

* fix: restore .mjs refs for scripts/ in test imports after ts migration

* fix: restore next.config.mjs ref in dev-origins test

* fix: implement db migration safety checks and codex config format

* fix: disable mass-migration abort during unit tests based on auto-backup flag

* fix: update script regex in auto-update tests to use .mjs

* feat: Add Perplexity Web (Session) provider (#1289)

Integrated into release/v3.6.6

* fix(cli): resolve codex routing config parsing, standardize select model button positioning, and clarify oauth documentation

* docs(changelog): record recent cli, provider, and test updates

Document the latest fixes for Codex routing configuration parsing and
Lobehub provider icon fallback behavior.

Add the note that the remaining JavaScript test files were migrated to
TypeScript ES modules to reflect the completed test stack transition.

* chore(release): merge #1286 minor improvements manually to avoid testing conflict

* chore(test): rename perplexity-web.test.mjs to .ts to maintain 100% TS codebase

* chore(docs): update CHANGELOG.md for perplexity-web provider

* fix(security): resolve CodeQL incomplete URL substring sanitization via URL parsing in test mocks

* fix: integrate compressContext() into chatCore.ts request pipeline

Proactively compress oversized contexts before sending to upstream providers,
preventing context_length_exceeded errors. Compression triggers at 85% of
model's context limit using the existing 3-layer compressContext() function.

- Import compressContext, estimateTokens, getTokenLimit from contextManager
- Add compression check after translation, before executor dispatch
- Estimate tokens and compare against 85% threshold of model's context limit
- Apply 3-layer compression (trim tools, compress thinking, purify history)
- Log compression events with before/after token counts and layers applied
- Audit compression events for observability
- Add unit tests verifying integration behavior

Closes #1290

* fix(tests): align reasoning expectations with GLM thinking structure

* fix: prevent orphaned tool_result messages in purifyHistory()

When purifyHistory() drops oldest messages to fit context window, it can
split tool_use/tool_result pairs — keeping the tool_result but dropping
the tool_use that initiated it. This causes upstream providers to reject
the request with format errors.

Add fixToolPairs() that runs after each purification pass to remove:
- OpenAI format: orphaned role='tool' messages without matching tool_calls ID
- Claude format: orphaned tool_result content blocks without matching tool_use ID

Closes #1291

* fix(tests): supply tool_use in mock so it is not dropped

* chore: convert remaining test to TypeScript

* fix(tests): restore compatibility with compressContext threshold test after tsx migration

* docs: finalize v3.6.6 release documentation

* fix(core): finalize provider removal, type issues, and codex API key config

* fix(dashboard): render Web/Cookie, Search, Audio provider sections and fix TypeScript errors

* fix: increase MCP web_search timeout to 60s (#1278)

* fix: route combo testing properly for embedding models (#1260)

* fix: accumulate excluded accounts in combo fallback loop (#1233)

* fix: strip leading whitespace and newlines from first streaming chunk (#1211)

* docs: clarify VPS and Docker settings for OAuth credentials (#1204)

* fix: return real retry-after for pipeline gates (#1301)

Integrated into release/v3.6.6 — returns real Retry-After values from pipeline gates

* feat: streaming semantic cache, Cursor auto-version detection, and call-log enhancements (#1296)

Integrated into release/v3.6.6 — streaming semantic cache, Cursor auto-version detection, call-log cache_source tracking

* feat(api): support more OpenAI types (image, embeddings, audio-transcriptions, audio-speech) (#1297)

Integrated into release/v3.6.6 — adds embeddings, audio-transcriptions, audio-speech, and images-generations support for custom OpenAI-compatible providers, plus Pollinations image registry

* deps: bump hono from 4.12.12 to 4.12.14 (#1302)

Integrated into release/v3.6.6

* deps: bump hono from 4.12.12 to 4.12.14 (#1306)

Integrated into release/v3.6.6

* chore: stabilization fixes for v3.6.6 (#1298, #1254, #59, CI)

* fix(providers): match correct endpoint for Xiaomi MiMo, strip routing prefix for custom openai endpoints (#1303, #1261)

* feat(storage): add database backup cleanup controls

* chore(release): v3.6.6 — Final Stabilization Push

* Backport call log storage refactor to release/v3.6.6 (#1307)

Integrated into release/v3.6.6

* deps: update dompurify to 3.4.0 to resolve CVE-XYZ (#60)

* test: disable sqlite auto backup in CI to resolve E2E timeout (#24481475058)

* chore(docs): sync CHANGELOG for v3.6.6 with missing features and fixes

* chore(release): prep v3.6.6 infrastructure and type safety fixes

- Migrated legacy .mjs scripts to .ts (bin, prepublish, policies)
- Resolved pre-commit strict lint (t11 budget) errors in combo.ts
- Explicitly typed all TS bindings in pack-artifact policies
- Updated package.json commands to run Node via tsx/esm internally
- Hardened CI/CD with explicit node version 22.22.2 checks
- Completed stage validations for v3.6.6 final release

* chore: fix TS build errors and e2e timeouts in CI

- Migrate nodeRuntimeSupport to TS interfaces avoiding implicit any
- Increase visibility timeouts in skills-marketplace E2E test to 15s to bypass CI flakiness
- Complete migration of .mjs scripts to .ts ensuring type safety

* chore(release): sync package version 3.6.6 across workspaces

* test(e2e): universally increase UI component visibility timeouts from 5s to 15s to bypass CI starvation

* chore(build): inject baseUrl, paths, and types:node into MITM tsconfig within prepublish hook to fix missing types in CI check

---------

Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
Co-authored-by: Jack <5443152+hijak@users.noreply.github.com>
Co-authored-by: Randi <55005611+rdself@users.noreply.github.com>
Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com>
Co-authored-by: Samuel Cedric <ceds.sam@gmail.com>
Co-authored-by: Max Garmash <max@37bytes.com>
Co-authored-by: Markus Hartung <mail@hartmark.se>
Co-authored-by: Gi99lin <74502520+Gi99lin@users.noreply.github.com>
Co-authored-by: Payne <baboialex95@gmail.com>
Co-authored-by: Benson K B <bensonkbmca@gmail.com>
Co-authored-by: clousky2020 <33016567+clousky2020@users.noreply.github.com>
Co-authored-by: Ravi Tharuma <25951435+RaviTharuma@users.noreply.github.com>
Co-authored-by: oyi77 <oyi77@users.noreply.github.com>
Co-authored-by: Hdsje <vovan877@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: xiaoge1688 <moyekongling@gmail.com>
2026-04-16 05:26:17 -03:00

1744 lines
49 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-combo-routing-"));
process.env.DATA_DIR = TEST_DATA_DIR;
const {
getComboFromData,
getComboModelsFromData,
validateComboDAG,
resolveNestedComboModels,
handleComboChat,
shouldFallbackComboBadRequest,
} = await import("../../open-sse/services/combo.ts");
const { normalizeComboStep } = await import("../../src/lib/combos/steps.ts");
const { registerStrategy } = await import("../../open-sse/services/autoCombo/routerStrategy.ts");
const core = await import("../../src/lib/db/core.ts");
const settingsDb = await import("../../src/lib/db/settings.ts");
const { saveModelsDevCapabilities, clearModelsDevCapabilities } =
await import("../../src/lib/modelsDevSync.ts");
const { getComboMetrics, recordComboRequest, resetAllComboMetrics } =
await import("../../open-sse/services/comboMetrics.ts");
const { getCircuitBreaker, resetAllCircuitBreakers } =
await import("../../src/shared/utils/circuitBreaker.ts");
const { acquire: acquireSemaphore, resetAll: resetAllSemaphores } =
await import("../../open-sse/services/rateLimitSemaphore.ts");
const { _resetAllDecks } = await import("../../src/shared/utils/shuffleDeck.ts");
function createLog() {
const entries = [];
return {
info: (tag, msg) => entries.push({ level: "info", tag, msg }),
warn: (tag, msg) => entries.push({ level: "warn", tag, msg }),
error: (tag, msg) => entries.push({ level: "error", tag, msg }),
entries,
};
}
function okResponse(body = { choices: [{ message: { content: "ok" } }] }) {
return new Response(JSON.stringify(body), {
status: 200,
headers: { "content-type": "application/json" },
});
}
function errorResponse(status, message = `Error ${status}`) {
return new Response(JSON.stringify({ error: { message } }), {
status,
headers: { "content-type": "application/json" },
});
}
function streamResponse(chunks) {
return new Response(chunks.join(""), {
status: 200,
headers: { "content-type": "text/event-stream" },
});
}
function capabilityEntry(limitContext) {
return {
tool_call: true,
reasoning: false,
attachment: false,
structured_output: true,
temperature: true,
modalities_input: JSON.stringify(["text"]),
modalities_output: JSON.stringify(["text"]),
knowledge_cutoff: null,
release_date: null,
last_updated: null,
status: null,
family: null,
open_weights: false,
limit_context: limitContext,
limit_input: limitContext,
limit_output: 4096,
interleaved_field: null,
};
}
function getComboTargetBreakerKey(comboName, index, stepInput) {
const step = normalizeComboStep(stepInput, { comboName, index });
if (!step) throw new Error(`Failed to normalize combo step for ${comboName}#${index}`);
return `combo:${comboName}:${step.id}`;
}
async function resetStorage() {
core.resetDbInstance();
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
fs.mkdirSync(TEST_DATA_DIR, { recursive: true });
await settingsDb.resetAllPricing();
settingsDb.clearAllLKGP();
clearModelsDevCapabilities();
}
test.beforeEach(async () => {
resetAllComboMetrics();
resetAllCircuitBreakers();
resetAllSemaphores();
_resetAllDecks();
await resetStorage();
});
test.after(async () => {
resetAllComboMetrics();
resetAllCircuitBreakers();
resetAllSemaphores();
_resetAllDecks();
await resetStorage();
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
});
test("getComboFromData and getComboModelsFromData resolve combos from array and object containers", () => {
const combos = [
{ name: "alpha", models: ["openai/gpt-4o-mini", { model: "claude/sonnet", weight: 2 }] },
];
const fromArray = getComboFromData("alpha", combos);
const fromObject = getComboFromData("alpha", { combos });
const models = getComboModelsFromData("alpha", { combos });
assert.equal(fromArray.name, "alpha");
assert.equal(fromObject.name, "alpha");
assert.deepEqual(models, ["openai/gpt-4o-mini", "claude/sonnet"]);
});
test("validateComboDAG rejects circular references and resolveNestedComboModels expands nested combos", () => {
const combos = [
{ name: "root", models: ["child-a", "openai/gpt-4o-mini"] },
{ name: "child-a", models: ["child-b", "claude/sonnet"] },
{ name: "child-b", models: ["groq/llama-3.3-70b"] },
];
validateComboDAG("root", combos);
assert.deepEqual(resolveNestedComboModels(combos[0], combos), [
"groq/llama-3.3-70b",
"claude/sonnet",
"openai/gpt-4o-mini",
]);
assert.throws(
() =>
validateComboDAG("loop-a", [
{ name: "loop-a", models: ["loop-b"] },
{ name: "loop-b", models: ["loop-a"] },
]),
/Circular combo reference detected/
);
});
test("resolveNestedComboModels expands explicit combo-ref steps", () => {
const combos = [
{
name: "root",
models: [
{ id: "root-ref-child", kind: "combo-ref", comboName: "child", weight: 0 },
{ id: "root-model", kind: "model", providerId: "openai", model: "openai/gpt-4o-mini" },
],
},
{
name: "child",
models: [
{ id: "child-model", kind: "model", providerId: "anthropic", model: "claude/sonnet" },
],
},
];
validateComboDAG("root", combos);
assert.deepEqual(resolveNestedComboModels(combos[0], combos), [
"claude/sonnet",
"openai/gpt-4o-mini",
]);
});
test("validateComboDAG enforces maximum nesting depth", () => {
const combos = [
{ name: "c1", models: ["c2"] },
{ name: "c2", models: ["c3"] },
{ name: "c3", models: ["c4"] },
{ name: "c4", models: ["c5"] },
{ name: "c5", models: ["openai/gpt-4o-mini"] },
];
assert.throws(() => validateComboDAG("c1", combos), /Max combo nesting depth/);
});
test("handleComboChat priority strategy defaults to first model and records success metrics", async () => {
const calls = [];
const combo = {
name: "priority-default",
models: ["openai/gpt-4o-mini", "claude/sonnet"],
};
const result = await handleComboChat({
body: {},
combo,
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
const metrics = getComboMetrics("priority-default");
const firstStep = normalizeComboStep(combo.models[0], {
comboName: combo.name,
index: 0,
});
assert.equal(result.ok, true);
assert.deepEqual(calls, ["openai/gpt-4o-mini"]);
assert.equal(metrics.totalRequests, 1);
assert.equal(metrics.totalSuccesses, 1);
assert.equal(metrics.byModel["openai/gpt-4o-mini"].requests, 1);
assert.equal(metrics.byTarget[firstStep.id].requests, 1);
assert.equal(metrics.byTarget[firstStep.id].model, "openai/gpt-4o-mini");
assert.equal(metrics.strategy, "priority");
});
test("handleComboChat priority strategy honors composite tier order before fallback", async () => {
const calls = [];
const combo = {
name: "priority-composite-tiers",
strategy: "priority",
models: [
{
kind: "model",
id: "step-primary",
providerId: "openai",
model: "openai/gpt-4o-mini",
},
{
kind: "model",
id: "step-backup",
providerId: "anthropic",
model: "claude/sonnet",
},
{
kind: "model",
id: "step-last",
providerId: "google",
model: "gemini/gemini-2.5-flash",
},
],
config: {
maxRetries: 0,
compositeTiers: {
defaultTier: "backup",
tiers: {
backup: {
stepId: "step-backup",
fallbackTier: "primary",
},
primary: {
stepId: "step-primary",
},
},
},
},
};
const result = await handleComboChat({
body: {},
combo,
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
if (modelStr === "claude/sonnet") {
return errorResponse(503, "backup failed");
}
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.deepEqual(calls, ["claude/sonnet", "openai/gpt-4o-mini"]);
});
test("handleComboChat weighted strategy selects by weight and falls back in descending weight order", async () => {
const originalRandom = Math.random;
const calls = [];
Math.random = () => 0.95;
try {
const result = await handleComboChat({
body: {},
combo: {
name: "weighted-selection",
strategy: "weighted",
models: [
{ model: "openai/gpt-4o-mini", weight: 1 },
{ model: "claude/sonnet", weight: 9 },
],
config: { maxRetries: 0 },
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
if (modelStr === "claude/sonnet") return errorResponse(500, "temporary");
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.deepEqual(calls, ["claude/sonnet", "openai/gpt-4o-mini"]);
} finally {
Math.random = originalRandom;
}
});
test("handleComboChat weighted strategy falls back to uniform random when all weights are zero", async () => {
const originalRandom = Math.random;
const calls = [];
Math.random = () => 0.75;
try {
const result = await handleComboChat({
body: {},
combo: {
name: "weighted-zero-fallback",
strategy: "weighted",
models: [
{ model: "model-a", weight: 0 },
{ model: "model-b", weight: 0 },
],
config: { maxRetries: 0 },
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.deepEqual(calls, ["model-b"]);
} finally {
Math.random = originalRandom;
}
});
test("handleComboChat random strategy uses shuffled model order", async () => {
const originalRandom = Math.random;
const calls = [];
const sequence = [0.99, 0.0];
let idx = 0;
Math.random = () => sequence[idx++] ?? 0;
try {
await handleComboChat({
body: {},
combo: {
name: "random-order",
strategy: "random",
models: ["model-a", "model-b", "model-c"],
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(calls.length, 1);
assert.notEqual(calls[0], "model-a");
} finally {
Math.random = originalRandom;
}
});
test("handleComboChat least-used strategy prefers the model with fewer recorded requests", async () => {
recordComboRequest("least-used-combo", "model-a", {
success: true,
latencyMs: 100,
strategy: "least-used",
});
recordComboRequest("least-used-combo", "model-a", {
success: true,
latencyMs: 100,
strategy: "least-used",
});
recordComboRequest("least-used-combo", "model-b", {
success: true,
latencyMs: 100,
strategy: "least-used",
});
const calls = [];
await handleComboChat({
body: {},
combo: {
name: "least-used-combo",
strategy: "least-used",
models: ["model-a", "model-b", "model-c"],
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(calls[0], "model-c");
});
test("handleComboChat skips unavailable models and falls through to the next active target", async () => {
const calls = [];
const result = await handleComboChat({
body: {},
combo: {
name: "availability-skip",
strategy: "priority",
models: ["model-a", "model-b"],
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async (modelStr) => modelStr !== "model-a",
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.deepEqual(calls, ["model-b"]);
});
test("handleComboChat falls through empty successful responses and records failure metrics before succeeding", async () => {
const calls = [];
const result = await handleComboChat({
body: {},
combo: {
name: "quality-fallback",
strategy: "priority",
models: ["model-a", "model-b"],
config: { maxRetries: 0 },
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
if (modelStr === "model-a") {
return okResponse({ choices: [{ message: { content: "" } }] });
}
return okResponse({ choices: [{ message: { content: "fallback ok" } }] });
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
const metrics = getComboMetrics("quality-fallback");
assert.equal(result.ok, true);
assert.deepEqual(calls, ["model-a", "model-b"]);
assert.equal(metrics.totalRequests, 2);
assert.equal(metrics.totalFailures, 1);
assert.equal(metrics.totalSuccesses, 1);
assert.equal(metrics.byModel["model-a"].lastStatus, "error");
assert.equal(metrics.byModel["model-b"].lastStatus, "ok");
});
test("handleComboChat records per-target metrics separately when the same model repeats with different accounts", async () => {
const calls = [];
const combo = {
name: "per-target-repeat",
strategy: "priority",
models: [
{
kind: "model",
providerId: "openai",
model: "openai/gpt-4o-mini",
connectionId: "conn-openai-a",
label: "Account A",
},
{
kind: "model",
providerId: "openai",
model: "openai/gpt-4o-mini",
connectionId: "conn-openai-b",
label: "Account B",
},
],
config: { maxRetries: 0 },
};
const result = await handleComboChat({
body: {},
combo,
handleSingleModel: async (_body, modelStr, target) => {
calls.push(`${modelStr}:${target?.connectionId || "none"}`);
if (target?.connectionId === "conn-openai-a") {
return errorResponse(503, "account-a down");
}
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
const firstStep = normalizeComboStep(combo.models[0], {
comboName: combo.name,
index: 0,
});
const secondStep = normalizeComboStep(combo.models[1], {
comboName: combo.name,
index: 1,
});
const metrics = getComboMetrics(combo.name);
assert.equal(result.ok, true);
assert.deepEqual(calls, ["openai/gpt-4o-mini:conn-openai-a", "openai/gpt-4o-mini:conn-openai-b"]);
assert.equal(metrics.byModel["openai/gpt-4o-mini"].requests, 2);
assert.equal(metrics.byTarget[firstStep.id].failures, 1);
assert.equal(metrics.byTarget[firstStep.id].connectionId, "conn-openai-a");
assert.equal(metrics.byTarget[secondStep.id].successes, 1);
assert.equal(metrics.byTarget[secondStep.id].connectionId, "conn-openai-b");
});
test("handleComboChat preserves the first failure status but surfaces the last error message", async () => {
const result = await handleComboChat({
body: {},
combo: {
name: "all-fail",
strategy: "priority",
models: ["model-a", "model-b"],
config: { maxRetries: 0 },
},
handleSingleModel: async (_body, modelStr) => {
return errorResponse(modelStr === "model-a" ? 500 : 429, `fail:${modelStr}`);
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
const payload = await result.json();
assert.equal(result.status, 500);
assert.equal(payload.error.message, "fail:model-b");
});
test("handleComboChat round-robin rotates sequentially across requests", async () => {
const calls = [];
const combo = {
name: "rr-sequence",
strategy: "round-robin",
models: ["model-a", "model-b"],
config: { maxRetries: 0, concurrencyPerModel: 1, queueTimeoutMs: 1000 },
};
for (let i = 0; i < 3; i++) {
const result = await handleComboChat({
body: {},
combo,
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
}
assert.deepEqual(calls, ["model-a", "model-b", "model-a"]);
});
test("handleComboChat round-robin starts from composite tier default ordering", async () => {
const calls = [];
const combo = {
name: "rr-composite-order",
strategy: "round-robin",
models: [
{
kind: "model",
id: "step-primary",
providerId: "openai",
model: "openai/gpt-4o-mini",
},
{
kind: "model",
id: "step-backup",
providerId: "anthropic",
model: "claude/sonnet",
},
],
config: {
maxRetries: 0,
concurrencyPerModel: 1,
queueTimeoutMs: 1000,
compositeTiers: {
defaultTier: "backup",
tiers: {
backup: {
stepId: "step-backup",
fallbackTier: "primary",
},
primary: {
stepId: "step-primary",
},
},
},
},
};
for (let i = 0; i < 2; i++) {
const result = await handleComboChat({
body: {},
combo,
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
}
assert.deepEqual(calls, ["claude/sonnet", "openai/gpt-4o-mini"]);
});
test("combo helpers short-circuit safely for missing combos, cycles, and excessive depth", () => {
assert.equal(getComboFromData("missing", null), null);
assert.equal(getComboModelsFromData("missing", { combos: [] }), null);
assert.doesNotThrow(() =>
validateComboDAG("ghost", {
combos: [{ name: "alpha", models: ["openai/gpt-4o-mini"] }],
})
);
assert.doesNotThrow(() => validateComboDAG("empty", [{ name: "empty" }]));
assert.deepEqual(
resolveNestedComboModels(
{ name: "loop", models: ["model-a", "model-b"] },
[],
new Set(["loop"])
),
[]
);
assert.deepEqual(
resolveNestedComboModels(
{ name: "deep", models: ["model-a", { model: "model-b", weight: 2 }] },
[],
new Set(),
99
),
["model-a", "model-b"]
);
});
test("shouldFallbackComboBadRequest only flags known provider-scoped 400 patterns", () => {
assert.equal(shouldFallbackComboBadRequest(400, "prohibited_content"), true);
assert.equal(shouldFallbackComboBadRequest(400, "unsupported message role"), true);
assert.equal(shouldFallbackComboBadRequest(400, "tool_call weather_lookup not found"), true);
assert.equal(shouldFallbackComboBadRequest(429, "prohibited_content"), false);
assert.equal(shouldFallbackComboBadRequest(400, null), false);
assert.equal(shouldFallbackComboBadRequest(400, "generic bad request"), false);
});
test("handleComboChat accepts binary and Responses-style 200 bodies but falls through malformed success payloads", async () => {
const binaryResult = await handleComboChat({
body: {},
combo: {
name: "quality-binary",
strategy: "priority",
models: ["model-a"],
config: { maxRetries: 0 },
},
handleSingleModel: async () =>
new Response("binary-payload", {
status: 200,
headers: { "content-type": "application/octet-stream" },
}),
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(binaryResult.ok, true);
assert.equal(await binaryResult.text(), "binary-payload");
const responsesResult = await handleComboChat({
body: {},
combo: {
name: "quality-responses",
strategy: "priority",
models: ["model-a"],
config: { maxRetries: 0 },
},
handleSingleModel: async () =>
okResponse({
output: [{ type: "output_text", text: "done" }],
}),
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(responsesResult.ok, true);
const calls = [];
const malformedResult = await handleComboChat({
body: {},
combo: {
name: "quality-malformed",
strategy: "priority",
models: ["model-a", "model-b", "model-c"],
config: { maxRetries: 0 },
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
if (modelStr === "model-a") {
return new Response("", {
status: 200,
headers: { "content-type": "application/json" },
});
}
if (modelStr === "model-b") {
return okResponse({ choices: [{}] });
}
return okResponse({ choices: [{ message: { content: "recovered" } }] });
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(malformedResult.ok, true);
assert.deepEqual(calls, ["model-a", "model-b", "model-c"]);
});
test("handleComboChat accepts text-mode SSE payloads as valid non-streaming passthrough responses", async () => {
const result = await handleComboChat({
body: {},
combo: {
name: "quality-sse-data",
strategy: "priority",
models: ["model-a"],
config: { maxRetries: 0 },
},
handleSingleModel: async () =>
new Response('data: {"choices":[{"delta":{"content":"hello"}}]}\n\n', {
status: 200,
headers: { "content-type": "text/plain" },
}),
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.match(await result.text(), /^data:/);
});
test("handleComboChat falls through invalid JSON and embedded 200 error bodies before succeeding", async () => {
const calls = [];
const result = await handleComboChat({
body: {},
combo: {
name: "quality-invalid-json-and-error",
strategy: "priority",
models: ["model-a", "model-b", "model-c"],
config: { maxRetries: 0 },
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
if (modelStr === "model-a") {
return new Response("{bad-json", {
status: 200,
headers: { "content-type": "text/plain" },
});
}
if (modelStr === "model-b") {
return new Response(JSON.stringify({ error: { message: "embedded upstream failure" } }), {
status: 200,
headers: { "content-type": "application/json" },
});
}
return okResponse({ choices: [{ delta: { content: "recovered" } }] });
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.deepEqual(calls, ["model-a", "model-b", "model-c"]);
});
test("handleComboChat returns the earliest retry-after when all priority targets are rate-limited", async () => {
const soon = new Date(Date.now() + 1_000).toISOString();
const later = new Date(Date.now() + 5_000).toISOString();
const result = await handleComboChat({
body: {},
combo: {
name: "priority-retry-after",
strategy: "priority",
models: ["model-a", "model-b"],
},
handleSingleModel: async (_body, modelStr) =>
new Response(
JSON.stringify({
error: { message: `limited:${modelStr}` },
retryAfter: modelStr === "model-a" ? later : soon,
}),
{
status: 429,
headers: { "content-type": "application/json" },
}
),
isModelAvailable: async () => true,
log: createLog(),
settings: {
comboDefaults: { maxRetries: 0, retryDelayMs: 1 },
},
allCombos: null,
});
const payload = await result.json();
assert.equal(result.status, 429);
assert.match(payload.error.message, /limited:model-b/);
assert.ok(Number(result.headers.get("Retry-After")) >= 1);
});
test("handleComboChat returns 404 model_not_found when a combo has no executable targets", async () => {
const result = await handleComboChat({
body: {},
combo: {
name: "empty-priority",
strategy: "priority",
models: [],
},
handleSingleModel: async () => {
throw new Error("handleSingleModel should not run for empty combos");
},
isModelAvailable: async () => true,
log: createLog(),
settings: {
comboDefaults: {
maxRetries: 0,
retryDelayMs: 1,
},
},
allCombos: null,
});
const payload = await result.json();
assert.equal(result.status, 404);
assert.equal(payload.error.code, "model_not_found");
assert.match(payload.error.message, /Combo has no executable targets/);
});
test("handleComboChat round-robin returns 404 when no models are configured", async () => {
const result = await handleComboChat({
body: {},
combo: {
name: "rr-empty",
strategy: "round-robin",
models: [],
},
handleSingleModel: async () => {
throw new Error("handleSingleModel should not run for empty round-robin combos");
},
isModelAvailable: async () => true,
log: createLog(),
settings: {
comboDefaults: {
concurrencyPerModel: 1,
queueTimeoutMs: 5,
maxRetries: 0,
retryDelayMs: 1,
},
},
allCombos: null,
});
const payload = await result.json();
assert.equal(result.status, 404);
assert.equal(payload.error.code, "model_not_found");
assert.match(payload.error.message, /Round-robin combo has no executable targets/);
});
test("handleComboChat round-robin falls through semaphore timeouts and malformed success payloads", async () => {
const release = await acquireSemaphore(
getComboTargetBreakerKey("rr-timeout-fallback", 0, "model-a"),
{
maxConcurrency: 1,
timeoutMs: 100,
}
);
const calls = [];
try {
const result = await handleComboChat({
body: {},
combo: {
name: "rr-timeout-fallback",
strategy: "round-robin",
models: ["model-a", "model-b", "model-c"],
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
if (modelStr === "model-b") {
return okResponse({ choices: [{}] });
}
return okResponse({ choices: [{ message: { content: "rr ok" } }] });
},
isModelAvailable: async () => true,
log: createLog(),
settings: {
comboDefaults: {
concurrencyPerModel: 1,
queueTimeoutMs: 5,
maxRetries: 0,
retryDelayMs: 1,
},
},
allCombos: null,
});
assert.equal(result.ok, true);
assert.deepEqual(calls, ["model-b", "model-c"]);
} finally {
release();
}
});
test("handleComboChat round-robin surfaces retry-after metadata after exhausting all models", async () => {
const sooner = new Date(Date.now() + 1_500).toISOString();
const later = new Date(Date.now() + 7_000).toISOString();
const result = await handleComboChat({
body: {},
combo: {
name: "rr-retry-after",
strategy: "round-robin",
models: ["model-a", "model-b"],
},
handleSingleModel: async (_body, modelStr) =>
new Response(
JSON.stringify({
error: { message: `rr-limited:${modelStr}` },
retryAfter: modelStr === "model-a" ? later : sooner,
}),
{
status: 429,
headers: { "content-type": "application/json" },
}
),
isModelAvailable: async () => true,
log: createLog(),
settings: {
comboDefaults: {
concurrencyPerModel: 1,
queueTimeoutMs: 5,
maxRetries: 0,
retryDelayMs: 1,
},
},
allCombos: null,
});
const payload = await result.json();
assert.equal(result.status, 429);
assert.match(payload.error.message, /rr-limited:model-b/);
assert.ok(Number(result.headers.get("Retry-After")) >= 1);
});
test("handleComboChat round-robin keeps generic 400 errors terminal", async () => {
const calls = [];
const result = await handleComboChat({
body: {},
combo: {
name: "rr-terminal-400",
strategy: "round-robin",
models: ["model-a", "model-b"],
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
if (modelStr === "model-a") {
return new Response(JSON.stringify({ error: { message: "generic bad request" } }), {
status: 400,
headers: { "content-type": "application/json" },
});
}
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: {
comboDefaults: {
concurrencyPerModel: 1,
queueTimeoutMs: 5,
maxRetries: 0,
retryDelayMs: 1,
},
},
allCombos: null,
});
assert.equal(result.status, 400);
assert.deepEqual(calls, ["model-a"]);
assert.match((await result.json()).error.message, /generic bad request/);
});
test("handleComboChat round-robin falls through provider-scoped 400s and returns the final error payload when no target recovers", async () => {
const calls = [];
const result = await handleComboChat({
body: {},
combo: {
name: "rr-provider-scoped-400-fallback",
strategy: "round-robin",
models: ["model-a", "model-b"],
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
if (modelStr === "model-a") {
return new Response(
JSON.stringify({ error: { message: "unsupported message role for this provider" } }),
{
status: 400,
headers: { "content-type": "application/json" },
}
);
}
return errorResponse(500, "rr-final-fail");
},
isModelAvailable: async () => true,
log: createLog(),
settings: {
comboDefaults: {
concurrencyPerModel: 1,
queueTimeoutMs: 5,
maxRetries: 0,
retryDelayMs: 1,
},
},
allCombos: null,
});
const payload = await result.json();
assert.equal(result.status, 400);
assert.equal(payload.error.message, "rr-final-fail");
assert.deepEqual(calls, ["model-a", "model-b"]);
});
test("handleComboChat strict-random uses the shared deck without repeating within a cycle", async () => {
const calls = [];
const combo = {
name: "strict-random-deck",
strategy: "strict-random",
models: ["model-a", "model-b", "model-c"],
};
for (let i = 0; i < 3; i++) {
const result = await handleComboChat({
body: {},
combo,
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
}
assert.equal(new Set(calls).size, 3);
});
test("handleComboChat cost-optimized orders models by the cheapest configured input price", async () => {
await settingsDb.updatePricing({
openai: {
"gpt-4o-mini": { input: 5, output: 10 },
"gpt-4o": { input: 1, output: 2 },
"gpt-4o-nano": { input: 0.1, output: 0.2 },
},
});
const calls = [];
const result = await handleComboChat({
body: {},
combo: {
name: "cost-optimized-combo",
strategy: "cost-optimized",
models: ["openai/gpt-4o-mini", "openai/gpt-4o", "openai/gpt-4o-nano"],
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.equal(calls[0], "openai/gpt-4o-nano");
});
test("handleComboChat weighted strategy resolves nested combos before falling back to the next weighted target", async () => {
const originalRandom = Math.random;
const calls = [];
Math.random = () => 0.01;
try {
const result = await handleComboChat({
body: {},
combo: {
name: "weighted-nested-selection",
strategy: "weighted",
models: [
{ model: "nested-priority", weight: 9 },
{ model: "model-c", weight: 1 },
],
config: { maxRetries: 0 },
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
if (modelStr === "model-a") return errorResponse(500, "nested-first-fail");
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: [
{
name: "weighted-nested-selection",
models: [
{ model: "nested-priority", weight: 9 },
{ model: "model-c", weight: 1 },
],
},
{ name: "nested-priority", models: ["model-a", "model-b"] },
],
});
assert.equal(result.ok, true);
assert.deepEqual(calls, ["model-a", "model-b"]);
} finally {
Math.random = originalRandom;
}
});
test("handleComboChat context-optimized orders models by the largest synced context window", async () => {
saveModelsDevCapabilities({
openai: {
"gpt-4o-mini": capabilityEntry(128000),
"gpt-4o": capabilityEntry(64000),
"gpt-4o-max": capabilityEntry(256000),
},
});
const calls = [];
const result = await handleComboChat({
body: {},
combo: {
name: "context-optimized-combo",
strategy: "context-optimized",
models: ["openai/gpt-4o-mini", "openai/gpt-4o", "openai/gpt-4o-max"],
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.equal(calls[0], "openai/gpt-4o-max");
});
test("handleComboChat returns a 503 when every model is unavailable before execution", async () => {
const result = await handleComboChat({
body: {},
combo: {
name: "inactive-accounts",
strategy: "priority",
models: ["openai/model-a", "openai/model-b"],
},
handleSingleModel: async () => {
throw new Error("handleSingleModel should not run when all models are inactive");
},
isModelAvailable: async () => false,
log: createLog(),
settings: null,
allCombos: null,
});
const payload = await result.json();
assert.equal(result.status, 503);
assert.equal(payload.error.code, "ALL_ACCOUNTS_INACTIVE");
});
test("handleComboChat returns the circuit-breaker unavailable response when all breakers are open", async () => {
for (const [index, modelStr] of ["openai/model-a", "openai/model-b"].entries()) {
const breaker = getCircuitBreaker(
getComboTargetBreakerKey("all-breakers-open", index, modelStr),
{
failureThreshold: 1,
resetTimeout: 60000,
}
);
breaker._onFailure();
}
const result = await handleComboChat({
body: {},
combo: {
name: "all-breakers-open",
strategy: "priority",
models: ["openai/model-a", "openai/model-b"],
},
handleSingleModel: async () => {
throw new Error("handleSingleModel should not run when all breakers are open");
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.status, 503);
assert.match((await result.json()).error.message, /circuit breakers open/);
});
test("handleComboChat auto strategy honors LKGP after filtering to tool-capable models", async () => {
await settingsDb.setLKGP("auto-lkgp", "auto-lkgp", "claude");
const calls = [];
const result = await handleComboChat({
body: {
messages: [{ role: "user", content: "Write code using a tool" }],
tools: [{ type: "function", function: { name: "lookup_weather" } }],
},
combo: {
id: "auto-lkgp",
name: "auto-lkgp",
strategy: "auto",
models: ["openai/gpt-oss-120b", "openai/gpt-4o-mini", "claude/claude-sonnet-4-6"],
autoConfig: { routingStrategy: "lkgp" },
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.equal(calls[0], "claude/claude-sonnet-4-6");
});
test("handleComboChat standalone lkgp strategy prioritizes the last known good provider", async () => {
await settingsDb.setLKGP("standalone-lkgp", "standalone-lkgp", "anthropic");
const calls = [];
const result = await handleComboChat({
body: {},
combo: {
id: "standalone-lkgp",
name: "standalone-lkgp",
strategy: "lkgp",
models: ["openai/gpt-4o-mini", "anthropic/claude-sonnet-4-6"],
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.equal(calls[0], "anthropic/claude-sonnet-4-6");
});
test("handleComboChat standalone lkgp strategy falls back to original order when no state exists", async () => {
const calls = [];
const result = await handleComboChat({
body: {},
combo: {
id: "standalone-lkgp-no-state",
name: "standalone-lkgp-no-state",
strategy: "lkgp",
models: ["openai/gpt-4o-mini", "anthropic/claude-sonnet-4-6"],
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.equal(calls[0], "openai/gpt-4o-mini");
});
test("handleComboChat standalone lkgp strategy updates LKGP after a successful call", async () => {
const result = await handleComboChat({
body: {},
combo: {
id: "standalone-lkgp-save",
name: "standalone-lkgp-save",
strategy: "lkgp",
models: ["openai/gpt-4o-mini"],
},
handleSingleModel: async () => okResponse(),
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
const persistedProvider = await settingsDb.getLKGP(
"standalone-lkgp-save",
"standalone-lkgp-save"
);
assert.equal(result.ok, true);
assert.equal(persistedProvider, "openai");
});
test("handleComboChat auto strategy falls back to the full pool when tool filtering empties candidates", async () => {
await settingsDb.updatePricing({
openai: {
"gpt-oss-120b": { input: 5, output: 10 },
},
deepseek: {
reasoner: { input: 0.1, output: 0.2 },
},
});
const calls = [];
const result = await handleComboChat({
body: {
input: [{ role: "user", text: "Summarize this request" }],
tools: [{ type: "function", function: { name: "unsupported_tool" } }],
},
combo: {
name: "auto-cost-fallback",
strategy: "auto",
models: ["openai/gpt-oss-120b", "deepseek/reasoner"],
autoConfig: { routingStrategy: "cost" },
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: {
intentSimpleMaxWords: 5,
intentExtraSimpleKeywords: "summarize, brief",
},
allCombos: null,
});
assert.equal(result.ok, true);
assert.equal(calls[0], "deepseek/reasoner");
});
test("handleComboChat auto strategy falls back to rules when a custom router strategy throws", async () => {
registerStrategy("throwing-test", {
name: "throwing-test",
description: "test strategy that always throws",
select() {
throw new Error("synthetic router failure");
},
});
const log = createLog();
const calls = [];
const result = await handleComboChat({
body: { prompt: "Hello there" },
combo: {
name: "auto-throwing-strategy",
strategy: "auto",
models: ["openai/gpt-4o-mini"],
autoConfig: { routingStrategy: "throwing-test" },
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log,
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.deepEqual(calls, ["openai/gpt-4o-mini"]);
assert.ok(
log.entries.some(
(entry) => entry.level === "warn" && /falling back to rules/i.test(String(entry.msg))
)
);
});
test("handleComboChat auto strategy reads strategyName from combo.config.auto and can prefer latency", async () => {
const calls = [];
const result = await handleComboChat({
body: { prompt: "Just answer briefly" },
combo: {
name: "auto-latency-strategy-name",
strategy: "auto",
models: ["openai/gpt-4o-mini", "gemini/gemini-2.5-flash"],
config: {
auto: {
strategyName: "latency",
},
},
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.equal(calls[0], "gemini/gemini-2.5-flash");
});
test("handleComboChat context cache protection pins the model and tags tool-call responses", async () => {
const calls = [];
const result = await handleComboChat({
body: {
model: "openai/gpt-4o-mini",
messages: [
{
role: "assistant",
content: "cached\n<omniModel>claude/claude-sonnet-4-6</omniModel>",
},
],
},
combo: {
name: "context-cache-pinned",
strategy: "priority",
models: ["openai/gpt-4o-mini", "claude/claude-sonnet-4-6"],
context_cache_protection: true,
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
return okResponse({
choices: [
{
message: {
role: "assistant",
tool_calls: [
{
id: "call_1",
type: "function",
function: { name: "lookup_weather", arguments: "{}" },
},
],
},
},
],
});
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
const payload = await result.json();
assert.equal(result.ok, true);
assert.deepEqual(calls, ["claude/claude-sonnet-4-6"]);
assert.match(
payload.choices[0].message.content,
/<omniModel>claude\/claude-sonnet-4-6<\/omniModel>/
);
});
test("handleComboChat context cache protection sanitizes streamed text tags from client output", async () => {
const result = await handleComboChat({
body: { stream: true, messages: [{ role: "user", content: "stream it" }] },
combo: {
name: "context-cache-stream",
strategy: "priority",
models: ["openai/gpt-4o-mini"],
context_cache_protection: true,
},
handleSingleModel: async () =>
streamResponse([
'data: {"choices":[{"index":0,"delta":{"content":"hello world"},"finish_reason":null}]}\n\n',
'data: {"choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}\n\n',
"data: [DONE]\n\n",
]),
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
const text = await result.text();
assert.equal(result.ok, true);
assert.equal(result.headers.get("X-OmniRoute-Model"), "openai/gpt-4o-mini");
assert.match(text, /hello world/);
assert.doesNotMatch(text, /<omniModel>/);
});
test("handleComboChat context cache protection injects a hidden tag for tool-call-only streams", async () => {
const result = await handleComboChat({
body: { stream: true, messages: [{ role: "user", content: "tool only" }] },
combo: {
name: "context-cache-tool-stream",
strategy: "priority",
models: ["openai/gpt-4o-mini"],
context_cache_protection: true,
},
handleSingleModel: async () =>
streamResponse([
'data: {"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"id":"call_1","type":"function","function":{"name":"lookup","arguments":"{}"}}]},"finish_reason":null}]}\n\n',
'data: {"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}\n\n',
"data: [DONE]\n\n",
]),
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
const text = await result.text();
assert.equal(result.ok, true);
assert.match(text, /"finish_reason":"tool_calls"/);
assert.doesNotMatch(text, /<omniModel>/);
});
test("handleComboChat context cache protection flushes cleanly when a stream ends without content", async () => {
const result = await handleComboChat({
body: { stream: true, messages: [{ role: "user", content: "empty stream" }] },
combo: {
name: "context-cache-empty-stream",
strategy: "priority",
models: ["openai/gpt-4o-mini"],
context_cache_protection: true,
},
handleSingleModel: async () => streamResponse(["data: [DONE]\n\n"]),
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
const text = await result.text();
assert.equal(result.ok, true);
assert.equal(result.headers.get("X-OmniRoute-Model"), "openai/gpt-4o-mini");
assert.match(text, /data: \[DONE\]/);
assert.match(text, /"content":""/);
assert.doesNotMatch(text, /<omniModel>/);
});
test("handleComboChat round-robin resolves nested combos and returns inactive when every target is skipped", async () => {
const result = await handleComboChat({
body: {},
combo: {
name: "rr-nested-inactive",
strategy: "round-robin",
models: ["nested-combo"],
},
handleSingleModel: async () => {
throw new Error("round-robin should not execute when all nested targets are inactive");
},
isModelAvailable: async () => false,
log: createLog(),
settings: null,
allCombos: [
{ name: "rr-nested-inactive", models: ["nested-combo"] },
{ name: "nested-combo", models: ["openai/model-a"] },
],
});
const payload = await result.json();
assert.equal(result.status, 503);
assert.equal(payload.error.code, "ALL_ACCOUNTS_INACTIVE");
});
test("handleComboChat round-robin returns circuit-breaker unavailable when every model is open", async () => {
for (const [index, modelStr] of ["openai/model-a", "openai/model-b"].entries()) {
const breaker = getCircuitBreaker(
getComboTargetBreakerKey("rr-breakers-open", index, modelStr),
{
failureThreshold: 1,
resetTimeout: 60000,
}
);
breaker._onFailure();
}
const result = await handleComboChat({
body: {},
combo: {
name: "rr-breakers-open",
strategy: "round-robin",
models: ["openai/model-a", "openai/model-b"],
config: { maxRetries: 0 },
},
handleSingleModel: async () => {
throw new Error("round-robin should not execute when all breakers are open");
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.status, 503);
assert.match((await result.json()).error.message, /circuit breakers open/);
});
test("handleComboChat round-robin retries a transient failure on the same model before succeeding", async () => {
const calls = [];
let attempts = 0;
const result = await handleComboChat({
body: {},
combo: {
name: "rr-same-model-retry",
strategy: "round-robin",
models: ["model-a"],
config: { maxRetries: 1, retryDelayMs: 1, concurrencyPerModel: 1, queueTimeoutMs: 5 },
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
attempts += 1;
if (attempts === 1) return errorResponse(503, "try again");
return okResponse();
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.deepEqual(calls, ["model-a", "model-a"]);
});
test("handleComboChat round-robin recovers from provider-scoped 400s when a later model succeeds", async () => {
const calls = [];
const result = await handleComboChat({
body: {},
combo: {
name: "rr-provider-400-recover",
strategy: "round-robin",
models: ["model-a", "model-b"],
config: { maxRetries: 0, retryDelayMs: 1, concurrencyPerModel: 1, queueTimeoutMs: 5 },
},
handleSingleModel: async (_body, modelStr) => {
calls.push(modelStr);
if (modelStr === "model-a") {
return new Response(
JSON.stringify({ error: { message: "unsupported message role for this provider" } }),
{
status: 400,
headers: { "content-type": "application/json" },
}
);
}
return okResponse({ choices: [{ message: { content: "recovered" } }] });
},
isModelAvailable: async () => true,
log: createLog(),
settings: null,
allCombos: null,
});
assert.equal(result.ok, true);
assert.deepEqual(calls, ["model-a", "model-b"]);
});