LobeHub
LobeHub
Back to Home
Changelog

Introducing CAO: Your Chief Agent Operator

CAO is an agent that reviews its own work, brings in sub-agents when it needs help, and only stops to ask you when a decision matters.

Introducing CAO: Your Chief Agent Operator

Features

  • CAO (Chief Agent Operator). Your agent can now keep going on its own. It reviews its own work, decides the next step, and continues without waiting for you to say "next." When a decision genuinely needs you, it pauses, tells you what it tried, and asks a clear question. For larger tasks, it can put together a small team of sub-agents and hand off parts of the work while the main agent stays in charge of the plan. You can open any sub-agent's conversation to see its progress. Learn more about CAO →
  • Project skills in the working sidebar, with a built-in Markdown preview.
  • Per-suggestion models. Pick a different model for each kind of follow-up suggestion.
  • New model: Baidu Ernie 5.1.

Improvements

  • Chat input actions show as icon and label, and only the latest reply animates while streaming.
  • Cleaner tab bar styling, and task schedule labels no longer wrap awkwardly.
  • Recurring tasks are more reliable, with a run-count cap and protection against schedules that fire too often.
  • A cleaner Agent Documents view: easier to find what you saved, without old web-crawl clutter.
  • DeepSeek is priced at official rates again.

Fixes

  • Desktop no longer signs you out during background token refreshes, and it remembers which page you were on after an update.
  • Local-file search handles hidden files that start with ., and grep parameters pass through correctly.
  • Unsupported documents now fail with a clear message instead of a confusing error.
  • Gemini tool calls handle thinking signatures and enums correctly, and per-tool timeouts now hold.
  • Task pages keep the right agent context, and memory updates stay out of your main thread.

Version details

Features

  • v2.1.58support slack mpim and fix discord dm problem.
  • v2.1.58add service model assignments settings.
  • v2.1.58inline skill auth in recommended task templates.
  • v2.1.58add user activity business hook.
  • v2.1.58add Gemini 3.1 Flash-Lite provider cards.
  • v2.1.58home daily brief with linkable welcome + paired input hint.
  • v2.1.58add signOperationJwt with 4h expiry for hetero-agent operations.
  • v2.1.58migrate Notion to LobeHub Market.
  • v2.1.58Cloud Claude Code V3 — repo picker, GitHub token, sandbox context.

What's improved

  • v2.1.58use @lobehub/ui built-in HtmlPreview instead of custom component.
  • v2.1.58polish desktop header icons, sidebar density, and task menus.
  • v2.1.58standardize header action icon sizes.
  • v2.1.58add reasoning_effort support for Grok 4.3.
  • v2.1.58increase chat topic title length.
  • v2.1.58format tool execution time as Xmin Ys instead of X.Y min.
  • v2.1.58Add new DeepSeek-V4 models.
  • v2.1.58use visible divider between queued messages.
  • v2.1.58update auth captcha retry copy.

What's fixed

  • v2.1.58Docs image.
  • v2.1.58update Task page placeholder copy.
  • v2.1.58sidebar add agent.
  • v2.1.58replace ScrollShadow with ScrollArea to fix React #185 infinite render loop.
  • v2.1.58reject inactive OIDC access.
  • v2.1.58drop unreachable aihubmix empty-apiKey test.
  • v2.1.58consume visual content parts in server runtime.
  • v2.1.58store onboarding interests as keys.
  • v2.1.58remove the old cron job from lobehub.
  • v2.1.58refresh content baseline from DB on every ingest call.
  • v2.1.58gateway client-tool pluginState + drop redundant Exit code: 0 tail.
  • v2.1.58first inject the cloudecc runtime session should use the existingStatus.
  • v2.1.58slack connect error & slash commands.
  • v2.1.58polish task agent manager.
  • v2.1.58remove signin captcha flow.
  • v2.1.58add temporary email auth error locale.
  • v2.1.58add bot callback service.
  • v2.1.58sanitize sensitive comments and examples from production JS bundle.
  • v2.1.58multiple account link.
LobeHub

Super-Agents on Your Team

Bring Super-Agents onto your team, starting today.