monolabsdev/openbench-ai

v0.10.0 Breaking

This release includes 1 breaking change for platform teams planning a safe upgrade.

Published 3d LLM Frameworks

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

local-llm multi-model offline-ai ollama privacy-first tauri

ReleasePort's take

Light signal

editorial:auto 3d

Version v0.10.0 introduces a multi‑provider architecture that replaces the previous Ollama‑only support with a configurable provider abstraction.

Why it matters: The new multi‑provider design (fact ID 39483) expands integration options beyond Ollama, enabling deployments to select alternate backends; relevant for all users planning extensibility before upgrading to v0.10.0.

Summary

AI summary

Multi-provider architecture replaces Ollama‑only support with a configurable provider abstraction.

Changes in this release

Type	Severity	Summary	CVE
Feature	Medium	Adds multi-provider architecture supporting non-Ollama backends Adds multi-provider architecture supporting non-Ollama backends Source: llm_adapter@2026-05-31 Confidence: high	—
Feature	Low	Adds auto-updater status chip to UI Adds auto-updater status chip to UI Source: llm_adapter@2026-05-31 Confidence: high	—
Refactor
Refactor	Low	Refactors nested conditionals across provider selector, tool loop, and migrations Refactors nested conditionals across provider selector, tool loop, and migrations Source: llm_adapter@2026-05-31 Confidence: high	—
Refactor	Low	Renames TS boolean props to `isX` convention Renames TS boolean props to `isX` convention Source: llm_adapter@2026-05-31 Confidence: high	—
Refactor	Low	Migrates render guards from `&&` short-circuits to ternaries for consistency Migrates render guards from `&&` short-circuits to ternaries for consistency Source: llm_adapter@2026-05-31 Confidence: high	—
Refactor	Low	Bumps version to 0.10.0 Bumps version to 0.10.0 Source: llm_adapter@2026-05-31 Confidence: low	—

Full changelog

OpenBench v0.10.0

Released: 31 May 2026

Multi-provider support arrives — Ollama is no longer the only game in town.

What's new

Multi-provider architecture

Replaces the single get_active_provider() call with a full provider abstraction layer. A new ProviderType enum and factory enable routing to non-Ollama backends, with config persistence and health-check caching. Provider type is now threaded through chat and title-generation commands.

Auto-updater status chip

A UI chip surfaces the auto-updater state inline, so available updates are visible without digging into settings.

Housekeeping

Nested conditionals flattened across the provider selector, tool loop, and migrations.
TS boolean props renamed to the isX convention.
Render guards migrated from && short-circuits to ternaries for consistency.
Version bumped to 0.10.0.

Full Changelog: https://github.com/monolabsdev/poly-ui/compare/v0.9.0...v0.10.0

Breaking Changes

Removed `get_active_provider()` call; replaced with a full provider abstraction layer including `ProviderType` enum and factory.

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track monolabsdev/openbench-ai

Get notified when new releases ship.

About monolabsdev/openbench-ai

All releases →