This release includes breaking changes for platform teams planning a safe upgrade.
✓ No known CVEs patched in this version
Topics
+13 more
ReleasePort's take
Light signalPackaged installs without bundled AionCore now display a recovery screen with download link and diagnostic report instead of failing silently. Cross‑architecture builds correctly bundle the matching AionCore binary, eliminating previous mismatches.
Why it matters: Fixes silent failures for installations lacking AionCore (severity 40) and ensures correct architecture‑specific binaries are bundled, preventing runtime mismatches.
Summary
AI summaryUpdates Bug Fixes, Faster Conversations, and Model Selector Reliability across a mixed release.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Model selector now persists user‑chosen model across navigation and remembers the last choice in Settings dropdowns for all views. Model selector now persists user‑chosen model across navigation and remembers the last choice in Settings dropdowns for all views. Source: llm_adapter@2026-05-28 Confidence: high |
— |
| Performance | Medium |
Re‑opening a conversation lazily loads full tool output, making large histories open noticeably faster. Re‑opening a conversation lazily loads full tool output, making large histories open noticeably faster. Source: llm_adapter@2026-05-28 Confidence: high |
— |
| Performance | Medium |
Removed redundant warmup and MCP sync during message startup, reducing first‑reply latency especially on aionrs and ACP backends. Removed redundant warmup and MCP sync during message startup, reducing first‑reply latency especially on aionrs and ACP backends. Source: llm_adapter@2026-05-28 Confidence: high |
— |
| Bugfix | Medium |
Packaged installs without bundled AionCore now show a recovery screen with download link and diagnostic report instead of failing silently. Packaged installs without bundled AionCore now show a recovery screen with download link and diagnostic report instead of failing silently. Source: llm_adapter@2026-05-28 Confidence: high |
— |
| Bugfix | Medium |
Provider health checks in Settings now use a dedicated probe and surface the backend's real error message, eliminating stale "error" text. Provider health checks in Settings now use a dedicated probe and surface the backend's real error message, eliminating stale "error" text. Source: llm_adapter@2026-05-28 Confidence: high |
— |
| Bugfix | Medium |
Cross-architecture builds now bundle the matching AionCore binary instead of the runner's architecture. Cross-architecture builds now bundle the matching AionCore binary instead of the runner's architecture. Source: llm_adapter@2026-05-28 Confidence: high |
— |
Full changelog
Highlights
Faster Conversations
- Re-opening a conversation no longer pays for refetching every long tool output up front — full tool content is loaded on demand when you expand a truncated tool call, so big histories open noticeably faster.
- Removed redundant warmup and MCP sync work on the message-send path so the first reply in a conversation arrives sooner, especially on aionrs and ACP backends.
Model Selector Reliability
- Switching the model inside a conversation now sticks: leaving and returning to the conversation keeps your chosen model, and the home page dropdown remembers the last choice across ACP, aionrs, and team views.
Bug Fixes
- Packaged installs that ship without bundled AionCore now show a clear recovery screen with a download link and diagnostic report action instead of failing silently; release builds also verify the bundled runtime during packaging so this can't ship broken again.
- Provider health checks in Settings now use a dedicated probe and surface the backend's real error message — no more stale "error" text or temporary conversation rows polluting your sidebar.
- Cross-architecture builds (e.g. Mac x64 from an arm runner) now bundle the matching AionCore binary instead of the runner's architecture.
What's Changed
- fix(backend): handle incomplete bundled aioncore installs by @piorpua in https://github.com/iOfficeAI/AionUi/pull/3078
- fix(settings): use health check error message by @piorpua in https://github.com/iOfficeAI/AionUi/pull/3080
- Avoid redundant warmup and MCP sync during message startup by @piorpua in https://github.com/iOfficeAI/AionUi/pull/3082
- fix(model-selector): trust backend current model and persist user preferences by @TCP404 in https://github.com/iOfficeAI/AionUi/pull/3084
- Lazy-load full tool message content by @piorpua in https://github.com/iOfficeAI/AionUi/pull/3086
- fix(settings): use provider health check probe by @piorpua in https://github.com/iOfficeAI/AionUi/pull/3090
- fix(build): align bundled aioncore target arch by @piorpua in https://github.com/iOfficeAI/AionUi/pull/3092
- chore: bump version to 2.1.6 by @piorpua in https://github.com/iOfficeAI/AionUi/pull/3094
Full Changelog: https://github.com/iOfficeAI/AionUi/compare/v2.1.5...v2.1.6
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
About AionUi
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | Star if you like it!
Related context
Related tools
Beta — feedback welcome: [email protected]