Merge pull request #726 from diegosouzapw/release/v3.2.1

chore(release): v3.2.1 — context pinning fix + global fallback
This commit is contained in:
Diego Rodrigues de Sa e Souza
2026-03-28 21:19:24 -03:00
committed by GitHub
4 changed files with 20 additions and 4 deletions

View File

@@ -4,6 +4,22 @@
---
## [3.2.1] — 2026-03-29
### ✨ New Features
- **Global Fallback Provider (#689)** — When all combo models are exhausted (502/503), OmniRoute now attempts a configurable global fallback model before returning the error. Set `globalFallbackModel` in settings to enable.
### 🐛 Bug Fixes
- **Fix #721** — Fixed context pinning bypass during tool-call responses. Non-streaming tagging used wrong JSON path (`json.messages``json.choices[0].message`). Streaming injection now triggers on `finish_reason` chunks for tool-call-only streams. `injectModelTag()` now appends synthetic pin messages for non-string content.
- **Fix #709** — Confirmed already fixed (v3.1.9) — `system-info.mjs` creates directories recursively. Closed.
- **Fix #707** — Confirmed already fixed (v3.1.9) — empty tool name sanitization in `chatCore.ts`. Closed.
### 🧪 Tests
- Added 6 unit tests for context pinning with tool-call responses (null content, array content, roundtrip, re-injection)
## [3.2.0] — 2026-03-28
### ✨ New Features

View File

@@ -1,7 +1,7 @@
openapi: 3.1.0
info:
title: OmniRoute API
version: 3.2.0
version: 3.2.1
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
View File

@@ -1,12 +1,12 @@
{
"name": "omniroute",
"version": "3.2.0",
"version": "3.2.1",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "omniroute",
"version": "3.2.0",
"version": "3.2.1",
"hasInstallScript": true,
"license": "MIT",
"workspaces": [

View File

@@ -1,6 +1,6 @@
{
"name": "omniroute",
"version": "3.2.0",
"version": "3.2.1",
"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": {