release: v3.1.1 — Ollama Cloud fix, Gemini 3.1, vision metadata, token retry

Changes:
- fix: Ollama Cloud 401 — wrong base URL (api.ollama.com → ollama.com) (#643)
- fix: Add Gemini 3.1 Pro/Flash to Antigravity provider (#645)
- feat: Vision capability metadata in /v1/models (PR #646)
- feat: Exponential backoff retry for expired OAuth tokens (PR #647)

Closes #643, closes #645
This commit is contained in:
diegosouzapw
2026-03-26 15:56:44 -03:00
parent c1835cd9cc
commit 211a7a4cfe
4 changed files with 22 additions and 4 deletions

View File

@@ -4,6 +4,24 @@
---
## [3.1.1] — 2026-03-26
### ✨ New Features
- **Vision Capability Metadata**: Added `capabilities.vision`, `input_modalities`, and `output_modalities` to `/v1/models` entries for vision-capable models (PR #646)
- **Gemini 3.1 Models**: Added `gemini-3.1-pro-preview` and `gemini-3.1-flash-lite-preview` to the Antigravity provider (#645)
### 🐛 Bug Fixes
- **Ollama Cloud 401 Error**: Fixed incorrect API base URL — changed from `api.ollama.com` to official `ollama.com/v1/chat/completions` (#643)
- **Expired Token Retry**: Added bounded retry with exponential backoff (5→10→20 min) for expired OAuth connections instead of permanently skipping them (PR #647)
### 🧪 Tests
- **936 tests, 0 failures**
---
## [3.1.0] — 2026-03-26
### ✨ New Features

View File

@@ -1,7 +1,7 @@
openapi: 3.1.0
info:
title: OmniRoute API
version: 3.1.0
version: 3.1.1
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": "3.1.0",
"version": "3.1.1",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "omniroute",
"version": "3.1.0",
"version": "3.1.1",
"hasInstallScript": true,
"license": "MIT",
"workspaces": [

View File

@@ -1,6 +1,6 @@
{
"name": "omniroute",
"version": "3.1.0",
"version": "3.1.1",
"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": {