mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-31 04:12:10 +03:00
chore: release v2.5.1
- PR #368: gpt-5.4 in Codex model registry (cx/gpt-5.4, codex/gpt-5.4) - PR #367: Codex fast tier toggle (default-off, full stack, 48 tests) - PR #366: Codex quota policy 5h/weekly with auto-rotation - fix #356: analytics charts show provider display names not raw IDs
This commit is contained in:
14
CHANGELOG.md
14
CHANGELOG.md
@@ -2,7 +2,19 @@
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
## [2.5.0] - 2026-03-14
|
||||
## [2.5.1] - 2026-03-14
|
||||
|
||||
> Codex account quota policy with auto-rotation, fast tier toggle, gpt-5.4 model, and analytics label fix.
|
||||
|
||||
### ✨ New Features (PRs #366, #367, #368)
|
||||
|
||||
- **Codex Quota Policy (PR #366)**: Per-account 5h/weekly quota window toggles in Provider dashboard. Accounts are automatically skipped when enabled windows reach 90% threshold and re-admitted after `resetAt`. Includes `quotaCache.ts` with side-effect free status getter.
|
||||
- **Codex Fast Tier Toggle (PR #367)**: Dashboard → Settings → Codex Service Tier. Default-off toggle injects `service_tier: "flex"` only for Codex requests, reducing cost ~80%. Full stack: UI tab + API endpoint + executor + translator + startup restore.
|
||||
- **gpt-5.4 Model (PR #368)**: Adds `cx/gpt-5.4` and `codex/gpt-5.4` to the Codex model registry. Regression test included.
|
||||
|
||||
### 🐛 Bug Fixes
|
||||
|
||||
- **fix #356**: Analytics charts (Top Provider, By Account, Provider Breakdown) now display human-readable provider names/labels instead of raw internal IDs for OpenAI-compatible providers.
|
||||
|
||||
> Major release: strict-random routing strategy, API key access controls, connection groups, external pricing sync, and critical bug fixes for thinking models, combo testing, and tool name validation.
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
openapi: 3.1.0
|
||||
info:
|
||||
title: OmniRoute API
|
||||
version: 2.5.0
|
||||
version: 2.5.1
|
||||
description: |
|
||||
OmniRoute is a local-first AI API proxy router. It provides an OpenAI-compatible
|
||||
endpoint that routes requests to multiple AI providers with load balancing,
|
||||
|
||||
4
package-lock.json
generated
4
package-lock.json
generated
@@ -1,12 +1,12 @@
|
||||
{
|
||||
"name": "omniroute",
|
||||
"version": "2.4.4",
|
||||
"version": "2.5.0",
|
||||
"lockfileVersion": 3,
|
||||
"requires": true,
|
||||
"packages": {
|
||||
"": {
|
||||
"name": "omniroute",
|
||||
"version": "2.4.4",
|
||||
"version": "2.5.0",
|
||||
"hasInstallScript": true,
|
||||
"license": "MIT",
|
||||
"workspaces": [
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "omniroute",
|
||||
"version": "2.5.0",
|
||||
"version": "2.5.1",
|
||||
"description": "Smart AI Router with auto fallback — route to FREE & cheap models, zero downtime. Works with Cursor, Cline, Claude Desktop, Codex, and any OpenAI-compatible tool.",
|
||||
"type": "module",
|
||||
"bin": {
|
||||
|
||||
Reference in New Issue
Block a user